You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@stanbol.apache.org by rw...@apache.org on 2011/06/29 15:37:57 UTC

svn commit: r1141099 - in /incubator/stanbol/trunk/defaultdata: ./ src/main/resources/org/apache/stanbol/defaultdata/site/ src/main/resources/org/apache/stanbol/defaultdata/site/dbpedia/ src/main/resources/org/apache/stanbol/defaultdata/site/dbpedia/co...

Author: rwesten
Date: Wed Jun 29 13:37:57 2011
New Revision: 1141099

URL: http://svn.apache.org/viewvc?rev=1141099&view=rev
Log:
### updated default 

* added small (43k entities) solr index
* added configurations for the dbpedia (referenced site, cache, solr index, SolrYard, EntityTaggingEngine)
* added the path of the dbpedia solr index to the Data-Files header
* added the Install-Path header with the path for the dbpedia configuration to trigger the installation of this files by the sling installer framework
* updated the version to "0.0.3"

NOTE:

* the addition of the configuration files will allow to remove the same files form the different launchers. This makes it easier to maintain such configurations
* the solr index (15MByte) is not contained in the SVN repository and need to be manually downloaded before building this bundle. Currently it is available form http://www.salzburgresearch.at/~rwesten/stanbol/dbpedia_150k_en_de_fr_it/dbpedia.solrindex.zip)

As soon as this bundle is available I will commit the according changes in the full launcher and the stable launcher (STANBOL-241)

Added:
    incubator/stanbol/trunk/defaultdata/src/main/resources/org/apache/stanbol/defaultdata/site/
    incubator/stanbol/trunk/defaultdata/src/main/resources/org/apache/stanbol/defaultdata/site/dbpedia/
    incubator/stanbol/trunk/defaultdata/src/main/resources/org/apache/stanbol/defaultdata/site/dbpedia/config/
    incubator/stanbol/trunk/defaultdata/src/main/resources/org/apache/stanbol/defaultdata/site/dbpedia/config/dbpedia_43k.solrindex.ref
    incubator/stanbol/trunk/defaultdata/src/main/resources/org/apache/stanbol/defaultdata/site/dbpedia/config/org.apache.stanbol.enhancer.engines.entitytagging.impl.NamedEntityTaggingEngine-dbpedia.config
    incubator/stanbol/trunk/defaultdata/src/main/resources/org/apache/stanbol/defaultdata/site/dbpedia/config/org.apache.stanbol.entityhub.core.site.CacheImpl-dbpedia.config
    incubator/stanbol/trunk/defaultdata/src/main/resources/org/apache/stanbol/defaultdata/site/dbpedia/config/org.apache.stanbol.entityhub.site.referencedSite-dbpedia.config
    incubator/stanbol/trunk/defaultdata/src/main/resources/org/apache/stanbol/defaultdata/site/dbpedia/config/org.apache.stanbol.entityhub.yard.solr.impl.SolrYard-dbpedia.config
    incubator/stanbol/trunk/defaultdata/src/main/resources/org/apache/stanbol/defaultdata/site/dbpedia/index/
Modified:
    incubator/stanbol/trunk/defaultdata/pom.xml

Modified: incubator/stanbol/trunk/defaultdata/pom.xml
URL: http://svn.apache.org/viewvc/incubator/stanbol/trunk/defaultdata/pom.xml?rev=1141099&r1=1141098&r2=1141099&view=diff
==============================================================================
--- incubator/stanbol/trunk/defaultdata/pom.xml (original)
+++ incubator/stanbol/trunk/defaultdata/pom.xml Wed Jun 29 13:37:57 2011
@@ -14,7 +14,7 @@
     See also:
     https://issues.apache.org/jira/browse/OPENNLP-68
   -->
-  <version>0.0.2</version>
+  <version>0.0.3</version>
   <packaging>bundle</packaging>
 
   <name>Apache Stanbol Default Data</name>
@@ -61,7 +61,7 @@
               DataFileProvider
               -->
             <Data-Files> 
-              org/apache/stanbol/defaultdata/opennlp
+              org/apache/stanbol/defaultdata/opennlp,org/apache/stanbol/defaultdata/site/dbpedia/index
             </Data-Files>
             <!-- 
               Use a priority lower than 0 to allow providers without a
@@ -70,6 +70,9 @@
             <Data-Files-Priority>
               -100
             </Data-Files-Priority>
+            <Install-Path>
+              org/apache/stanbol/defaultdata/site/dbpedia
+            </Install-Path>
           </instructions>
         </configuration>
       </plugin>

Added: incubator/stanbol/trunk/defaultdata/src/main/resources/org/apache/stanbol/defaultdata/site/dbpedia/config/dbpedia_43k.solrindex.ref
URL: http://svn.apache.org/viewvc/incubator/stanbol/trunk/defaultdata/src/main/resources/org/apache/stanbol/defaultdata/site/dbpedia/config/dbpedia_43k.solrindex.ref?rev=1141099&view=auto
==============================================================================
--- incubator/stanbol/trunk/defaultdata/src/main/resources/org/apache/stanbol/defaultdata/site/dbpedia/config/dbpedia_43k.solrindex.ref (added)
+++ incubator/stanbol/trunk/defaultdata/src/main/resources/org/apache/stanbol/defaultdata/site/dbpedia/config/dbpedia_43k.solrindex.ref Wed Jun 29 13:37:57 2011
@@ -0,0 +1,3 @@
+Name=SolrIndex for dbpedia
+Description=DBpedia.org 
+Index-Archive=dbpedia_43k.solrindex.zip

Added: incubator/stanbol/trunk/defaultdata/src/main/resources/org/apache/stanbol/defaultdata/site/dbpedia/config/org.apache.stanbol.enhancer.engines.entitytagging.impl.NamedEntityTaggingEngine-dbpedia.config
URL: http://svn.apache.org/viewvc/incubator/stanbol/trunk/defaultdata/src/main/resources/org/apache/stanbol/defaultdata/site/dbpedia/config/org.apache.stanbol.enhancer.engines.entitytagging.impl.NamedEntityTaggingEngine-dbpedia.config?rev=1141099&view=auto
==============================================================================
--- incubator/stanbol/trunk/defaultdata/src/main/resources/org/apache/stanbol/defaultdata/site/dbpedia/config/org.apache.stanbol.enhancer.engines.entitytagging.impl.NamedEntityTaggingEngine-dbpedia.config (added)
+++ incubator/stanbol/trunk/defaultdata/src/main/resources/org/apache/stanbol/defaultdata/site/dbpedia/config/org.apache.stanbol.enhancer.engines.entitytagging.impl.NamedEntityTaggingEngine-dbpedia.config Wed Jun 29 13:37:57 2011
@@ -0,0 +1,8 @@
+org.apache.stanbol.enhancer.engines.entitytagging.nameField="rdfs:label"
+org.apache.stanbol.enhancer.engines.entitytagging.personType="dbp-ont:Person"
+org.apache.stanbol.enhancer.engines.entitytagging.personState=B"true"
+org.apache.stanbol.enhancer.engines.entitytagging.referencedSiteId="dbpedia"
+org.apache.stanbol.enhancer.engines.entitytagging.placeState=B"true"
+org.apache.stanbol.enhancer.engines.entitytagging.organisationState=B"true"
+org.apache.stanbol.enhancer.engines.entitytagging.organisationType="dbp-ont:Organisation"
+org.apache.stanbol.enhancer.engines.entitytagging.placeType="dbp-ont:Place"

Added: incubator/stanbol/trunk/defaultdata/src/main/resources/org/apache/stanbol/defaultdata/site/dbpedia/config/org.apache.stanbol.entityhub.core.site.CacheImpl-dbpedia.config
URL: http://svn.apache.org/viewvc/incubator/stanbol/trunk/defaultdata/src/main/resources/org/apache/stanbol/defaultdata/site/dbpedia/config/org.apache.stanbol.entityhub.core.site.CacheImpl-dbpedia.config?rev=1141099&view=auto
==============================================================================
--- incubator/stanbol/trunk/defaultdata/src/main/resources/org/apache/stanbol/defaultdata/site/dbpedia/config/org.apache.stanbol.entityhub.core.site.CacheImpl-dbpedia.config (added)
+++ incubator/stanbol/trunk/defaultdata/src/main/resources/org/apache/stanbol/defaultdata/site/dbpedia/config/org.apache.stanbol.entityhub.core.site.CacheImpl-dbpedia.config Wed Jun 29 13:37:57 2011
@@ -0,0 +1,4 @@
+org.apache.stanbol.entityhub.yard.name="dbpedia\ Cache"
+org.apache.stanbol.entityhub.yard.cacheYardId="dbpediaDefaultdataIndex"
+org.apache.stanbol.entityhub.yard.id="dbpediaDefaultdataIndex"
+org.apache.stanbol.entityhub.yard.description="Cache\ for\ the\ dbpedia\ Referenced\ Site\ using\ the\ dbpediaIndex."

Added: incubator/stanbol/trunk/defaultdata/src/main/resources/org/apache/stanbol/defaultdata/site/dbpedia/config/org.apache.stanbol.entityhub.site.referencedSite-dbpedia.config
URL: http://svn.apache.org/viewvc/incubator/stanbol/trunk/defaultdata/src/main/resources/org/apache/stanbol/defaultdata/site/dbpedia/config/org.apache.stanbol.entityhub.site.referencedSite-dbpedia.config?rev=1141099&view=auto
==============================================================================
--- incubator/stanbol/trunk/defaultdata/src/main/resources/org/apache/stanbol/defaultdata/site/dbpedia/config/org.apache.stanbol.entityhub.site.referencedSite-dbpedia.config (added)
+++ incubator/stanbol/trunk/defaultdata/src/main/resources/org/apache/stanbol/defaultdata/site/dbpedia/config/org.apache.stanbol.entityhub.site.referencedSite-dbpedia.config Wed Jun 29 13:37:57 2011
@@ -0,0 +1,18 @@
+org.apache.stanbol.entityhub.site.attributionUrl="http://wiki.dbpedia.org/About"
+org.apache.stanbol.entityhub.site.cacheId="dbpediaDefaultdataIndex"
+org.apache.stanbol.entityhub.site.name="dbpedia"
+org.apache.stanbol.entityhub.site.dereferencerType="org.apache.stanbol.entityhub.dereferencer.SparqlDereferencer"
+org.apache.stanbol.entityhub.site.defaultMappedEntityState="proposed"
+org.apache.stanbol.entityhub.site.fieldMappings=("#\ ---\ Define\ the\ Languages\ for\ all\ fields\ ---","\ |\ @\=null;en;de;fr;it","#\ ---\ RDF,\ RDFS\ and\ OWL\ Mappings\ ---","rdfs:label\ |\ d\=entityhub:text","rdfs:comment\ |\ d\=entityhub:text","rdf:type\ |\ d\=entityhub:ref","rdfs:seeAlso\ |\ d\=entityhub:ref","#\ map\ also\ wikiPageRedirects\ to\ rdfs:seeAlso","dbp-ont:wikiPageRedirects\ |\ d\=entityhub:ref\ >\ rdfs:seeAlso","","#\ used\ by\ LOD\ to\ link\ to\ URIs\ used\ to\ identify\ the\ same\ Entity","owl:sameAs\ |\ d\=entityhub:ref","","#\ ---\ Dublin\ Core\ (dc\ terms\ and\ dc\ elements)\ ---","#\ dc:*","#\ DC\ terms\ subject\ is\ used\ by\ some\ DBpedia\ entities\ to\ store\ the\ Categories","#\ Others\ use\ skos:subject.\ Therefore\ ensure\ that\ dc:subjects\ are\ references","dc:subject\ |\ d\=entityhub:ref","#\ and\ copy\ the\ values\ to\ skos:subject","#\ dc:modified\ |\ d\=xsd:dateTime","#\ dc:created\ |\ d\=xsd:dateTime","","#\ all\ DC\ Elements\ (one\ co
 uld\ also\ define\ the\ mappings\ to\ the\ DC\ Terms\ counterparts\ here","#\ do\ not\ store\ dc-elements\ properties,\ but\ map\ them\ to\ the\ dc\ terms\ counterpart","#dc-elements:*","#\ dc-elements:contributor\ >\ dc:contributor","#\ dc-elements:coverage\ >\ dc:coverage","#\ dc-elements:creator\ >\ dc:creator","#\ dc-elements:date\ |\ d\=xsd:dateTime\ >\ dc:date","#\ dc-elements:description\ >\ dc:description","#\ dc-elements:format\ >\ dc:format","#\ dc-elements:identifier\ >\ dc:identifier","#\ dc-elements:language\ >\ dc:language","#\ dc-elements:publisher\ >\ dc:publisher","#\ dc-elements:relation\ >\ dc:relation","#\ dc-elements:rights\ >\ dc:rights","#\ dc-elements:source\ >\ dc:source","dc-elements:subject\ |\ d\=entityhub:ref\ >\ dc:subject","#\ copy\ subjects\ also\ to\ skos:subject","#\ dc-elements:subject\ |\ d\=entityhub:ref\ >\ skos:subject","#\ dc-elements:title\ >\ dc:title","#\ dc-elements:type\ >\ dc:type","","#\ ---\ Spatial\ Things\ ---","geo:lat\ |\ d
 \=xsd:double","geo:long\ |\ d\=xsd:double","geo:alt\ |\ d\=xsd:int","#\ one\ can\ also\ copy\ the\ valued\ from\ the\ DBpedia\ properties","#\ use\ the\ elevation\ if\ present","dbp-ont:elevation\ |\ d\=xsd:int\ >\ geo:alt","","#\ ---\ Thesaurus\ (via\ SKOS)\ ---","#SKOS\ can\ be\ used\ to\ define\ hierarchical\ terminologies","skos:*","skos:broader\ |\ d\=entityhub:ref","skos:narrower\ |\ d\=entityhub:ref","skos:related\ |\ d\=entityhub:ref","skos:member\ |\ d\=entityhub:ref","skos:subject\ |\ d\=entityhub:ref\ >\ dc:subject","skos:inScheme\ |\ d\=entityhub:ref","skos:hasTopConcept\ |\ d\=entityhub:ref","skos:topConceptOf\ |\ d\=entityhub:ref","","#\ ---\ Social\ Networks\ (via\ foaf)\ ---","#The\ Friend\ of\ a\ Friend\ schema\ often\ used\ to\ describe\ social\ relations\ between\ people","#\ foaf:*\ ","#\ foaf:knows\ |\ d\=entityhub:ref","#\ foaf:made\ |\ d\=entityhub:ref","#\ foaf:maker\ |\ d\=entityhub:ref","#\ foaf:member\ |\ d\=entityhub:ref","foaf:homepage\ |\ d\=xsd
 :anyURI","foaf:depiction\ |\ d\=xsd:anyURI","#\ also\ use\ the\ DBpedia\ thumbnail\ as\ oaf:depiction","dbp-ont:thumbnail\ |\ d\=xsd:anyURI\ >\ foaf:depiction","foaf:img\ |\ d\=xsd:anyURI","foaf:logo\ |\ d\=xsd:anyURI","#\ Documents\ about\ the\ entity","foaf:page\ |\ d\=xsd:anyURI","","#\ ---\ dbpedia\ specific","#\ the\ \"dbp-ont\"\ defines\ knowledge\ mapped\ to\ the\ DBPedia\ ontology","#\ dbp-ont:*","dbp-ont:birthDate\ |\ d\=xsd:dateTime","dbp-ont:deathDate\ |\ d\=xsd:dateTime","dbp-ont:populationTotal\ |\ d\=xsd:long","dbp-ont:wikiPageExternalLink\ |\ d\=xsd:anyURI","dbpedia-owl:areaTotal\ |\ d\=xsd:double","","#\ the\ \"DBpedia\ properties\ are\ all\ key\ values\ pairs\ extracted\ from\ the\ info\ boxes","#\ on\ the\ right\ hand\ side\ of\ Wikipedia\ pages.","#\ Data\ Quality\ is\ to\ low\ to\ use\ them\ efficiently","#\ dbp-prop:*","","#\ Copy\ only\ population\ for\ now\ (one\ could\ add\ additional\ if\ necessary)!","#\ use\ dbp-ont:populationTotal\ instead","#\ db
 p-prop:population\ |\ d\=xsd:long","","#Deactivated\ mappings\ based\ on\ dbprops","#dbp-prop:latitude\ |\ d\=xsd:double\ >\ geo:lat","#dbp-prop:longitude\ |\ d\=xsd:double\ >\ geo:long","#dbp-prop:elevation\ |\ d\=xsd:int;xsd:float\ >\ geo:alt","#dbp-prop:website\ |\ d\=xsd:anyURI\ >\ foaf:homepage")
+org.apache.stanbol.entityhub.site.licenseName=["Creative\ Commons\ Attribution-ShareAlike\ 3.0","GNU\ Free\ Documentation\ License"]
+org.apache.stanbol.entityhub.site.defaultSymbolState="proposed"
+org.apache.stanbol.entityhub.site.searcherType="org.apache.stanbol.entityhub.searcher.VirtuosoSearcher"
+org.apache.stanbol.entityhub.site.defaultExpireDuration=I"0"
+org.apache.stanbol.entityhub.site.cacheStrategy="all"
+org.apache.stanbol.entityhub.site.attribution="DBpedia.org"
+org.apache.stanbol.entityhub.site.accessUri="http://dbpedia.org/sparql/"
+org.apache.stanbol.entityhub.site.id="dbpedia"
+org.apache.stanbol.entityhub.site.entityPrefix=["http://dbpedia.org/resource/","http://dbpedia.org/ontology/"]
+org.apache.stanbol.entityhub.site.licenseUrl=["http://en.wikipedia.org/wiki/Wikipedia:Text_of_Creative_Commons_Attribution-ShareAlike_3.0_Unported_License","http://en.wikipedia.org/wiki/Wikipedia:Text_of_the_GNU_Free_Documentation_License"]
+org.apache.stanbol.entityhub.site.queryUri="http://dbpedia.org/sparql"
+org.apache.stanbol.entityhub.site.description="DBpedia.org\ "

Added: incubator/stanbol/trunk/defaultdata/src/main/resources/org/apache/stanbol/defaultdata/site/dbpedia/config/org.apache.stanbol.entityhub.yard.solr.impl.SolrYard-dbpedia.config
URL: http://svn.apache.org/viewvc/incubator/stanbol/trunk/defaultdata/src/main/resources/org/apache/stanbol/defaultdata/site/dbpedia/config/org.apache.stanbol.entityhub.yard.solr.impl.SolrYard-dbpedia.config?rev=1141099&view=auto
==============================================================================
--- incubator/stanbol/trunk/defaultdata/src/main/resources/org/apache/stanbol/defaultdata/site/dbpedia/config/org.apache.stanbol.entityhub.yard.solr.impl.SolrYard-dbpedia.config (added)
+++ incubator/stanbol/trunk/defaultdata/src/main/resources/org/apache/stanbol/defaultdata/site/dbpedia/config/org.apache.stanbol.entityhub.yard.solr.impl.SolrYard-dbpedia.config Wed Jun 29 13:37:57 2011
@@ -0,0 +1,7 @@
+org.apache.stanbol.entityhub.yard.solr.solrUri="dbpedia_43k"
+org.apache.stanbol.entityhub.yard.name="dbpedia\ default\ data\ index"
+org.apache.stanbol.entityhub.yard.solr.multiYardIndexLayout=B"false"
+org.apache.stanbol.entityhub.yard.solr.useDefaultConfig=B"false"
+org.apache.stanbol.entityhub.yard.solr.documentBoost="http://www.iks-project.eu/ontology/rick/model/entityRank"
+org.apache.stanbol.entityhub.yard.id="dbpediaDefaultdataIndex"
+org.apache.stanbol.entityhub.yard.description="Small\ local\ index\ with\ 43000\ entities\ for\ the\ Referenced\ Site\ \"dbpedia\"."