trying english now

extractionConfiguration/download.text.properties

@@ -8,7 +8,6 @@ base-url=http://dumps.wikimedia.your.org/
 # source=pages-articles.xml.bz2
 
 # languages to download
-TODO testing for english
 languages=en
 #,af,als,am,an,ar,arz,ast,azb,az,ba,bar,bat-smg,be,bg,bn,bpy,br,bs,bug,ca,cdo,ceb,ce,ckb,cs,cv,cy,da,de,el,eml,eo,es,et,eu,fa,fi,fo,fr,fy,ga,gd,gl,gu,he,hi,hr,hsb,ht,hu,hy,ia,id,ilo,io,is,it,ja,jv,ka,kk,kn,ko,ku,ky,la,lb,li,lmo,lt,lv,mai,mg,mhr,min,mk,ml,mn,mrj,mr,ms,my,mzn,nap,nds,ne,new,nl,nn,no,oc,or,os,pa,pl,pms,pnb,pt,qu,ro,ru,sah,sa,scn,sco,sd,sh,si,simple,sk,sl,sq,sr,su,sv,sw,ta,te,tg,th,tl,tr,tt,uk,ur,uz,vec,vi,vo,wa,war,wuu,xmf,yi,yo,zh,zh-min-nan,zh-yue
 

extractionConfiguration/extraction.test.properties

@@ -16,8 +16,8 @@ languages=ro
 
 # extractor class names starting with "." are prefixed by "org.dbpedia.extraction.mappings"
 
-extractors=.NifExtractor
-#extractors=.MappingExtractor
+#extractors=.NifExtractor
+extractors=.MappingExtractor
 
 uri-policy.iri=generic:en; xml-safe-predicates:*
 format.ttl.bz2=turtle-triples;uri-policy.iri

extractionConfiguration/extraction.text.en.properties

@@ -78,7 +78,7 @@ short-abstract-min-length=200
 #parameters specific to the nif extraction
 
 #only extract abstract (not the whole page)
-nif-extract-abstract-only=false
+nif-extract-abstract-only=true
 #the request query string
 nif-query=&format=xml&action=parse&prop=text&page=%s&pageid=%d
 #the xml path of the response

marvin_extraction_run.sh

 #!/bin/bash
 
+echo "LC_ALL=en_US.UTF-8"
+export LC_ALL=en_US.UTF-8
 
 
 #######################