This kind of information extraction comes from Apache Tika that is shipped with Solr. However Solr does not ship every possible parser with its installation. So, I think you are hitting Tika where it manages to figure out what type of content you have, but does not have (Apache POI - another O/S project) library installed.
What you need to do is to get the additional jar from Tika/POI's project/download and make it visible to Solr (probably as an extension jar in a lib folder somewhere - I am a bit hazy on that for latest Solr). The version of Tika that Solr uses is part of the changes notes. For 6.4, it is https://github.com/apache/lucene-solr/blob/releases/lucene-solr/6.4.0/solr/CHANGES.txt and it is Tika 1.13 Hope it helps, Alex. ---- http://www.solr-start.com/ - Resources for Solr users, new and experienced On 3 February 2017 at 05:57, Gytis Mikuciunas <gyt...@gmail.com> wrote: > Hi, > > > I'm using single core Solr 6.4 instance on windows server (windows server > 2012 R2 standard), > Java v8, (build 1.8.0_121-b13). > > All works more or less ok, except MS Visio vsdx files indexing. > > > Every time it throws an error (no matters if it tries to index vsdx file or > for example docx with visio diagram inside). > > Thx in advance for your help. If you need some additional info, please ask. > > > Error/Exception from log: > > > Null:java.lang.RuntimeException: java.lang.NoClassDefFoundError: Could not > initialize class > org.apache.poi.xdgf.usermodel.section.geometry.GeometryRowFactory > at > org.apache.poi.xdgf.usermodel.section.GeometrySection.<init>(GeometrySection.java:55) > at > org.apache.poi.xdgf.usermodel.XDGFSheet.<init>(XDGFSheet.java:77) > at > org.apache.poi.xdgf.usermodel.XDGFShape.<init>(XDGFShape.java:113) > at > org.apache.poi.xdgf.usermodel.XDGFShape.<init>(XDGFShape.java:107) > at > org.apache.poi.xdgf.usermodel.XDGFBaseContents.onDocumentRead(XDGFBaseContents.java:82) > at > org.apache.poi.xdgf.usermodel.XDGFMasterContents.onDocumentRead(XDGFMasterContents.java:66) > at > org.apache.poi.xdgf.usermodel.XDGFMasters.onDocumentRead(XDGFMasters.java:101) > at > org.apache.poi.xdgf.usermodel.XmlVisioDocument.onDocumentRead(XmlVisioDocument.java:106) > at org.apache.poi.POIXMLDocument.load(POIXMLDocument.java:160) > at > org.apache.poi.xdgf.usermodel.XmlVisioDocument.<init>(XmlVisioDocument.java:79) > at > org.apache.poi.xdgf.extractor.XDGFVisioExtractor.<init>(XDGFVisioExtractor.java:41) > at > org.apache.poi.extractor.ExtractorFactory.createExtractor(ExtractorFactory.java:212) > at > org.apache.tika.parser.microsoft.ooxml.OOXMLExtractorFactory.parse(OOXMLExtractorFactory.java:86) > at > org.apache.tika.parser.microsoft.ooxml.OOXMLParser.parse(OOXMLParser.java:87) > at > org.apache.tika.parser.CompositeParser.parse(CompositeParser.java:280) > at > org.apache.tika.parser.CompositeParser.parse(CompositeParser.java:280) > at > org.apache.tika.parser.AutoDetectParser.parse(AutoDetectParser.java:120) > at > org.apache.tika.parser.DelegatingParser.parse(DelegatingParser.java:72) > at > org.apache.tika.extractor.ParsingEmbeddedDocumentExtractor.parseEmbedded(ParsingEmbeddedDocumentExtractor.java:102) > at > org.apache.tika.parser.microsoft.ooxml.AbstractOOXMLExtractor.handleEmbeddedFile(AbstractOOXMLExtractor.java:298) > at > org.apache.tika.parser.microsoft.ooxml.AbstractOOXMLExtractor.handleEmbeddedParts(AbstractOOXMLExtractor.java:199) > at > org.apache.tika.parser.microsoft.ooxml.AbstractOOXMLExtractor.getXHTML(AbstractOOXMLExtractor.java:112) > at > org.apache.tika.parser.microsoft.ooxml.OOXMLExtractorFactory.parse(OOXMLExtractorFactory.java:112) > at > org.apache.tika.parser.microsoft.ooxml.OOXMLParser.parse(OOXMLParser.java:87) > at > org.apache.tika.parser.CompositeParser.parse(CompositeParser.java:280) > at > org.apache.tika.parser.CompositeParser.parse(CompositeParser.java:280) > at > org.apache.tika.parser.AutoDetectParser.parse(AutoDetectParser.java:120) > at > org.apache.solr.handler.extraction.ExtractingDocumentLoader.load(ExtractingDocumentLoader.java:228) > at > org.apache.solr.handler.ContentStreamHandlerBase.handleRequestBody(ContentStreamHandlerBase.java:68) > at > org.apache.solr.handler.RequestHandlerBase.handleRequest(RequestHandlerBase.java:166) > at org.apache.solr.core.SolrCore.execute(SolrCore.java:2306) > at > org.apache.solr.servlet.HttpSolrCall.execute(HttpSolrCall.java:658) > at org.apache.solr.servlet.HttpSolrCall.call(HttpSolrCall.java:464) > at > org.apache.solr.servlet.SolrDispatchFilter.doFilter(SolrDispatchFilter.java:345) > at > org.apache.solr.servlet.SolrDispatchFilter.doFilter(SolrDispatchFilter.java:296) > at > org.eclipse.jetty.servlet.ServletHandler$CachedChain.doFilter(ServletHandler.java:1691) > at > org.eclipse.jetty.servlet.ServletHandler.doHandle(ServletHandler.java:582) > at > org.eclipse.jetty.server.handler.ScopedHandler.handle(ScopedHandler.java:143) > at > org.eclipse.jetty.security.SecurityHandler.handle(SecurityHandler.java:513) > at > org.eclipse.jetty.server.session.SessionHandler.doHandle(SessionHandler.java:226) > at > org.eclipse.jetty.server.handler.ContextHandler.doHandle(ContextHandler.java:1180) > at > org.eclipse.jetty.servlet.ServletHandler.doScope(ServletHandler.java:512) > at > org.eclipse.jetty.server.session.SessionHandler.doScope(SessionHandler.java:185) > at > org.eclipse.jetty.server.handler.ContextHandler.doScope(ContextHandler.java:1112) > at > org.eclipse.jetty.server.handler.ScopedHandler.handle(ScopedHandler.java:141) > at > org.eclipse.jetty.server.handler.ContextHandlerCollection.handle(ContextHandlerCollection.java:213) > at > org.eclipse.jetty.server.handler.HandlerCollection.handle(HandlerCollection.java:119) > at > org.eclipse.jetty.server.handler.HandlerWrapper.handle(HandlerWrapper.java:134) > at org.eclipse.jetty.server.Server.handle(Server.java:534) > at org.eclipse.jetty.server.HttpChannel.handle(HttpChannel.java:320) > at > org.eclipse.jetty.server.HttpConnection.onFillable(HttpConnection.java:251) > at > org.eclipse.jetty.io.AbstractConnection$ReadCallback.succeeded(AbstractConnection.java:273) > at org.eclipse.jetty.io.FillInterest.fillable(FillInterest.java:95) > at > org.eclipse.jetty.io.SelectChannelEndPoint$2.run(SelectChannelEndPoint.java:93) > at > org.eclipse.jetty.util.thread.strategy.ExecuteProduceConsume.executeProduceConsume(ExecuteProduceConsume.java:303) > at > org.eclipse.jetty.util.thread.strategy.ExecuteProduceConsume.produceConsume(ExecuteProduceConsume.java:148) > at > org.eclipse.jetty.util.thread.strategy.ExecuteProduceConsume.run(ExecuteProduceConsume.java:136) > at > org.eclipse.jetty.util.thread.QueuedThreadPool.runJob(QueuedThreadPool.java:671) > at > org.eclipse.jetty.util.thread.QueuedThreadPool$2.run(QueuedThreadPool.java:589) > at java.lang.Thread.run(Unknown Source) > > > > Regards, > Gytis