Mario Bisonti created TIKA-2703:
-----------------------------------

             Summary: Error indexing a xlsx file
                 Key: TIKA-2703
                 URL: https://issues.apache.org/jira/browse/TIKA-2703
             Project: Tika
          Issue Type: Bug
         Environment: Tika 1.17 on solr 7.3 
            Reporter: Mario Bisonti


Hallo.

Indexing a xlsx file of 38 MB

 

I obtain the error:
Error from server at http://localhost:8983/solr/core_share: Expected mime type 
application/xml but got text/html. <html> <head> <meta 
http-equiv="Content-Type" content="text/html;charset=utf-8"/> <title>Error 500 
Server Error</title> </head> <body><h2>HTTP ERROR 500</h2> <p>Problem accessing 
/solr/core_share/update/extract. Reason: <pre> Server Error</pre></p><h3>Caused 
by:</h3><pre>java.lang.OutOfMemoryError at 
java.base/java.lang.AbstractStringBuilder.hugeCapacity(AbstractStringBuilder.java:188)
 at 
java.base/java.lang.AbstractStringBuilder.newCapacity(AbstractStringBuilder.java:180)
 at 
java.base/java.lang.AbstractStringBuilder.ensureCapacityInternal(AbstractStringBuilder.java:147)
 at 
java.base/java.lang.AbstractStringBuilder.append(AbstractStringBuilder.java:660)
 at java.base/java.lang.StringBuilder.append(StringBuilder.java:195) at 
org.apache.solr.handler.extraction.SolrContentHandler.characters(SolrContentHandler.java:302)
 at 
org.apache.tika.sax.ContentHandlerDecorator.characters(ContentHandlerDecorator.java:146)
 at 
org.apache.tika.sax.SecureContentHandler.characters(SecureContentHandler.java:270)
 at 
org.apache.tika.sax.ContentHandlerDecorator.characters(ContentHandlerDecorator.java:146)
 at 
org.apache.tika.sax.ContentHandlerDecorator.characters(ContentHandlerDecorator.java:146)
 at 
org.apache.tika.sax.ContentHandlerDecorator.characters(ContentHandlerDecorator.java:146)
 at 
org.apache.tika.sax.SafeContentHandler.access$001(SafeContentHandler.java:46) 
at org.apache.tika.sax.SafeContentHandler$1.write(SafeContentHandler.java:82) 
at org.apache.tika.sax.SafeContentHandler.filter(SafeContentHandler.java:140) 
at 
org.apache.tika.sax.SafeContentHandler.characters(SafeContentHandler.java:287) 
at 
org.apache.tika.sax.XHTMLContentHandler.characters(XHTMLContentHandler.java:279)
 at 
org.apache.tika.sax.XHTMLContentHandler.characters(XHTMLContentHandler.java:306)
 at 
org.apache.tika.parser.microsoft.ooxml.OOXMLTikaBodyPartHandler.run(OOXMLTikaBodyPartHandler.java:147)
 at 
org.apache.tika.parser.microsoft.ooxml.OOXMLWordAndPowerPointTextHandler.handleEndOfRun(OOXMLWordAndPowerPointTextHandler.java:468)
 at 
org.apache.tika.parser.microsoft.ooxml.OOXMLWordAndPowerPointTextHandler.endElement(OOXMLWordAndPowerPointTextHandler.java:450)
 at 
org.apache.tika.sax.ContentHandlerDecorator.endElement(ContentHandlerDecorator.java:136)
 at 
org.apache.tika.sax.ContentHandlerDecorator.endElement(ContentHandlerDecorator.java:136)
 at 
java.xml/com.sun.org.apache.xerces.internal.parsers.AbstractSAXParser.endElement(AbstractSAXParser.java:609)
 at 
java.xml/com.sun.org.apache.xerces.internal.impl.XMLDocumentFragmentScannerImpl.scanEndElement(XMLDocumentFragmentScannerImpl.java:1714)
 at 
java.xml/com.sun.org.apache.xerces.internal.impl.XMLDocumentFragmentScannerImpl$FragmentContentDriver.next(XMLDocumentFragmentScannerImpl.java:2879)
 at 
java.xml/com.sun.org.apache.xerces.internal.impl.XMLDocumentScannerImpl.next(XMLDocumentScannerImpl.java:602)
 at 
java.xml/com.sun.org.apache.xerces.internal.impl.XMLNSDocumentScannerImpl.next(XMLNSDocumentScannerImpl.java:112)
 at 
java.xml/com.sun.org.apache.xerces.internal.impl.XMLDocumentFragmentScannerImpl.scanDocument(XMLDocumentFragmentScannerImpl.java:532)
 at 
java.xml/com.sun.org.apache.xerces.internal.parsers.XML11Configuration.parse(XML11Configuration.java:888)
 at 
java.xml/com.sun.org.apache.xerces.internal.parsers.XML11Configuration.parse(XML11Configuration.java:824)
 at 
java.xml/com.sun.org.apache.xerces.internal.parsers.XMLParser.parse(XMLParser.java:141)
 at 
java.xml/com.sun.org.apache.xerces.internal.parsers.AbstractSAXParser.parse(AbstractSAXParser.java:1213)
 at 
java.xml/com.sun.org.apache.xerces.internal.jaxp.SAXParserImpl$JAXPSAXParser.parse(SAXParserImpl.java:635)
 at 
java.xml/com.sun.org.apache.xerces.internal.jaxp.SAXParserImpl.parse(SAXParserImpl.java:324)
 at java.xml/javax.xml.parsers.SAXParser.parse(SAXParser.java:197) at 
org.apache.tika.parser.microsoft.ooxml.AbstractOOXMLExtractor.handleGeneralTextContainingPart(AbstractOOXMLExtractor.java:506)
 at 
org.apache.tika.parser.microsoft.ooxml.XSSFExcelExtractorDecorator.processShapes(XSSFExcelExtractorDecorator.java:279)
 at 
org.apache.tika.parser.microsoft.ooxml.XSSFExcelExtractorDecorator.buildXHTML(XSSFExcelExtractorDecorator.java:185)
 at 
org.apache.tika.parser.microsoft.ooxml.AbstractOOXMLExtractor.getXHTML(AbstractOOXMLExtractor.java:135)
 at 
org.apache.tika.parser.microsoft.ooxml.XSSFExcelExtractorDecorator.getXHTML(XSSFExcelExtractorDecorator.java:120)
 at 
org.apache.tika.parser.microsoft.ooxml.OOXMLExtractorFactory.parse(OOXMLExtractorFactory.java:143)
 at 
org.apache.tika.parser.microsoft.ooxml.OOXMLParser.parse(OOXMLParser.java:106) 
at org.apache.tika.parser.CompositeParser.parse(CompositeParser.java:280) at 
org.apache.tika.parser.CompositeParser.parse(CompositeParser.java:280) at 
org.apache.tika.parser.AutoDetectParser.parse(AutoDetectParser.java:143) at 
org.apache.solr.handler.extraction.ExtractingDocumentLoader.load(ExtractingDocumentLoader.java:228)
 at 
org.apache.solr.handler.ContentStreamHandlerBase.handleRequestBody(ContentStreamHandlerBase.java:68)
 at 
org.apache.solr.handler.RequestHandlerBase.handleRequest(RequestHandlerBase.java:195)
 at org.apache.solr.core.SolrCore.execute(SolrCore.java:2503) at 
org.apache.solr.servlet.HttpSolrCall.execute(HttpSolrCall.java:711) at 
org.apache.solr.servlet.HttpSolrCall.call(HttpSolrCall.java:517) at 
org.apache.solr.servlet.SolrDispatchFilter.doFilter(SolrDispatchFilter.java:384)
 at 
org.apache.solr.servlet.SolrDispatchFilter.doFilter(SolrDispatchFilter.java:330)
 at 
org.eclipse.jetty.servlet.ServletHandler$CachedChain.doFilter(ServletHandler.java:1629)
 at org.eclipse.jetty.servlet.ServletHandler.doHandle(ServletHandler.java:533) 
at 
org.eclipse.jetty.server.handler.ScopedHandler.handle(ScopedHandler.java:143) 
at org.eclipse.jetty.security.SecurityHandler.handle(SecurityHandler.java:548) 
at 
org.eclipse.jetty.server.handler.HandlerWrapper.handle(HandlerWrapper.java:132) 
at 
org.eclipse.jetty.server.handler.ScopedHandler.nextHandle(ScopedHandler.java:190)
 at 
org.eclipse.jetty.server.session.SessionHandler.doHandle(SessionHandler.java:1595)
 at 
org.eclipse.jetty.server.handler.ScopedHandler.nextHandle(ScopedHandler.java:188)
 at 
org.eclipse.jetty.server.handler.ContextHandler.doHandle(ContextHandler.java:1253)
 at 
org.eclipse.jetty.server.handler.ScopedHandler.nextScope(ScopedHandler.java:168)
 at org.eclipse.jetty.servlet.ServletHandler.doScope(ServletHandler.java:473) 
at 
org.eclipse.jetty.server.session.SessionHandler.doScope(SessionHandler.java:1564)
 at 
org.eclipse.jetty.server.handler.ScopedHandler.nextScope(ScopedHandler.java:166)
 at 
org.eclipse.jetty.server.handler.ContextHandler.doScope(ContextHandler.java:1155)
 at 
org.eclipse.jetty.server.handler.ScopedHandler.handle(ScopedHandler.java:141) 
at 
org.eclipse.jetty.server.handler.ContextHandlerCollection.handle(ContextHandlerCollection.java:219)
 at 
org.eclipse.jetty.server.handler.HandlerCollection.handle(HandlerCollection.java:126)
 at 
org.eclipse.jetty.server.handler.HandlerWrapper.handle(HandlerWrapper.java:132) 
at 
org.eclipse.jetty.rewrite.handler.RewriteHandler.handle(RewriteHandler.java:335)
 at 
org.eclipse.jetty.server.handler.HandlerWrapper.handle(HandlerWrapper.java:132) 
at org.eclipse.jetty.server.Server.handle(Server.java:530) at 
org.eclipse.jetty.server.HttpChannel.handle(HttpChannel.java:347) at 
org.eclipse.jetty.server.HttpConnection.onFillable(HttpConnection.java:256) at 
org.eclipse.jetty.io.AbstractConnection$ReadCallback.succeeded(AbstractConnection.java:279)
 at org.eclipse.jetty.io.FillInterest.fillable(FillInterest.java:102) at 
org.eclipse.jetty.io.ChannelEndPoint$2.run(ChannelEndPoint.java:124) at 
org.eclipse.jetty.util.thread.strategy.EatWhatYouKill.doProduce(EatWhatYouKill.java:247)
 at 
org.eclipse.jetty.util.thread.strategy.EatWhatYouKill.produce(EatWhatYouKill.java:140)
 at 
org.eclipse.jetty.util.thread.strategy.EatWhatYouKill.run(EatWhatYouKill.java:131)
 at 
org.eclipse.jetty.util.thread.ReservedThreadExecutor$ReservedThread.run(ReservedThreadExecutor.java:382)
 at 
org.eclipse.jetty.util.thread.QueuedThreadPool.runJob(QueuedThreadPool.java:708)
 at 
org.eclipse.jetty.util.thread.QueuedThreadPool$2.run(QueuedThreadPool.java:626) 
at java.base/java.lang.Thread.run(Thread.java:844) </pre> </body> </html>

 

 

How could I solve it?

 

Thanks a lot

Mario



--
This message was sent by Atlassian JIRA
(v7.6.3#76005)

Reply via email to