# download and extraction target dir #base-dir= moved to $extraction-framework/core/src/main/resources/universal.properties # Source file. If source file name ends with .gz or .bz2, it is unzipped on the fly. # Must exist in the directory xxwiki/yyyymmdd and have the prefix xxwiki-yyyymmdd- # where xx is the wiki code and yyyymmdd is the dump date. # default: #source=# moved to $extraction-framework/core/src/main/resources/universal.properties # use only directories that contain a 'download-complete' file? Default is false. require-download-complete=false # List of languages or article count ranges, e.g. 'en,de,fr' or '10000-20000' or '10000-', or '@mappings' languages=@mappings # extractor class names starting with "." are prefixed by "org.dbpedia.extraction.mappings" extractors=.MappingExtractor,.RedirectExtractor #extractors.ar=.MappingExtractor,.TopicalConceptsExtractor # #extractors.be=.MappingExtractor # #extractors.bg=.MappingExtractor # #extractors.bn=.MappingExtractor # #extractors.ca=.MappingExtractor,.DisambiguationExtractor,.HomepageExtractor,.TopicalConceptsExtractor # #extractors.ced=.MappingExtractor # #extractors.commons=.MappingExtractor,.ContributorExtractor,.TemplateParameterExtractor,.FileTypeExtractor,.GalleryExtractor,.ImageAnnotationExtractor,.CommonsKMLExtractor,.DBpediaResourceExtractor # #extractors.cs=.MappingExtractor # #extractors.cy=.MappingExtractor # #extractors.da=.MappingExtractor # #extractors.de=.MappingExtractor,.DisambiguationExtractor,.HomepageExtractor,.ImageExtractorNew,.PersondataExtractor,.PndExtractor,.CommonsResourceExtractor # #extractors.el=.MappingExtractor,.DisambiguationExtractor,.HomepageExtractor,.ImageExtractorNew,.TopicalConceptsExtractor # #extractors.en=.MappingExtractor,.CitationExtractor,.DisambiguationExtractor,.GenderExtractor,.HomepageExtractor,.ImageExtractorNew,.PersondataExtractor,.PndExtractor,.TopicalConceptsExtractor,.AnchorTextExtractor,.CommonsResourceExtractor # #extractors.eo=.MappingExtractor # #extractors.es=.MappingExtractor,.DisambiguationExtractor,.HomepageExtractor,.ImageExtractorNew,.TopicalConceptsExtractor,.CommonsResourceExtractor # #extractors.et=.MappingExtractor # #extractors.eu=.MappingExtractor,.DisambiguationExtractor,.HomepageExtractor,.ImageExtractorNew,.TopicalConceptsExtractor # #extractors.fa=.MappingExtractor # #extractors.fi=.MappingExtractor # #extractors.fr=.MappingExtractor,.DisambiguationExtractor,.HomepageExtractor,.ImageExtractorNew,.PndExtractor,.TopicalConceptsExtractor,.fr.PopulationExtractor,.CommonsResourceExtractor # #extractors.ga=.MappingExtractor,.HomepageExtractor # #extractors.gl=.MappingExtractor # #extractors.hi=.MappingExtractor # #extractors.hr=.MappingExtractor # #extractors.hu=.MappingExtractor # #extractors.id=.MappingExtractor # #extractors.it=.MappingExtractor,.DisambiguationExtractor,.HomepageExtractor,.ImageExtractorNew,.TopicalConceptsExtractor # #extractors.ja=.MappingExtractor,.DisambiguationExtractor,.HomepageExtractor,.ImageExtractorNew,.TopicalConceptsExtractor,.CommonsResourceExtractor # #extractors.ko=.MappingExtractor,.DisambiguationExtractor # #extractors.lt=.MappingExtractor # #extractors.lv=.MappingExtractor # #extractors.nl=.MappingExtractor,.DisambiguationExtractor,.ImageExtractorNew,.CommonsResourceExtractor # #extractors.mk=.MappingExtractor # #extractors.mt=.MappingExtractor # #extractors.pl=.MappingExtractor,.DisambiguationExtractor,.HomepageExtractor,.ImageExtractorNew # #extractors.pt=.MappingExtractor,.DisambiguationExtractor,.HomepageExtractor,.ImageExtractorNew,.TopicalConceptsExtractor,.CommonsResourceExtractor # #extractors.ru=.MappingExtractor,.DisambiguationExtractor,.HomepageExtractor,.ImageExtractorNew,.TopicalConceptsExtractor # #extractors.sk=.MappingExtractor # #extractors.sl=.MappingExtractor # #extractors.sr=.MappingExtractor # #extractors.tr=.MappingExtractor # #extractors.ur=.MappingExtractor # #extractors.vi=.MappingExtractor # #extractors.war=.MappingExtractor #only the raw extractor here: all other wikidata extractors are executed in an separate extraction for wikidata (see: extraction.wikidata.properties) #extractors.wikidata=.WikidataSameAsExtractor,.WikidataRawExtractor #extractors.zh=.MappingExtractor # If we need to Exclude Non-Free Images in this Extraction, set this to true copyrightCheck=false