[ https://issues.apache.org/jira/browse/TIKA-2752?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16648422#comment-16648422 ]
Tim Allison commented on TIKA-2752: ----------------------------------- These are the tags I get before the NPE is thrown: {noformat} <html xmlns="http://www.w3.org/1999/xhtml"> <head> <meta name="X-Parsed-By" content="org.apache.tika.parser.DefaultParser" /> <meta name="X-Parsed-By" content="org.apache.tika.parser.rtf.RTFParser" /> <meta name="Content-Type" content="application/rtf" /> <title></title> </head> <body><p> Test 1</li> </ul> <p /> <p /> <p /> <p /> <p /> <p> </p> <p> </p> <p> {noformat} When I try to open the document in MSWord, it complains that something about the tables is corrupt and it offers to fix the document. I think this file is corrupt. I'm not sure what we can/should do about it. Recommendations? > Tika-App RTFParser crashes with NullPointerException > ---------------------------------------------------- > > Key: TIKA-2752 > URL: https://issues.apache.org/jira/browse/TIKA-2752 > Project: Tika > Issue Type: Bug > Components: parser > Affects Versions: 1.19.1 > Environment: tika-app 1.19.1 macOS > tika-core lib java > Reporter: Vicky Chawda > Priority: Critical > Labels: RTFParser, tika-app > Attachments: sample.rtf > > > The RTFParser seems to crash on RTF files. The attached file produces the > following stacktrace: > Apache Tika was unable to parse the document > at sample.rtf. > Apache Tika was unable to parse the document > at /Users/vchawda/Desktop/sample.rtf. > The full exception stack trace is included below: > org.apache.tika.exception.TikaException: Unexpected RuntimeException from > org.apache.tika.parser.rtf.RTFParser@3d8af52b > at org.apache.tika.parser.CompositeParser.parse(CompositeParser.java:282) > at org.apache.tika.parser.CompositeParser.parse(CompositeParser.java:280) > at org.apache.tika.parser.AutoDetectParser.parse(AutoDetectParser.java:143) > at org.apache.tika.parser.ParserDecorator.parse(ParserDecorator.java:188) > at org.apache.tika.parser.DigestingParser.parse(DigestingParser.java:84) > at org.apache.tika.gui.TikaGUI.handleStream(TikaGUI.java:358) > at org.apache.tika.gui.TikaGUI.openFile(TikaGUI.java:309) > at org.apache.tika.gui.TikaGUI.actionPerformed(TikaGUI.java:267) > at javax.swing.AbstractButton.fireActionPerformed(AbstractButton.java:2022) > at > javax.swing.AbstractButton$Handler.actionPerformed(AbstractButton.java:2348) > at > javax.swing.DefaultButtonModel.fireActionPerformed(DefaultButtonModel.java:402) > at javax.swing.DefaultButtonModel.setPressed(DefaultButtonModel.java:259) > at javax.swing.AbstractButton.doClick(AbstractButton.java:376) > at javax.swing.plaf.basic.BasicMenuItemUI.doClick(BasicMenuItemUI.java:833) > at com.apple.laf.AquaMenuItemUI.doClick(AquaMenuItemUI.java:157) > at > javax.swing.plaf.basic.BasicMenuItemUI$Handler.mouseReleased(BasicMenuItemUI.java:877) > at java.awt.Component.processMouseEvent(Component.java:6533) > at javax.swing.JComponent.processMouseEvent(JComponent.java:3324) > at java.awt.Component.processEvent(Component.java:6298) > at java.awt.Container.processEvent(Container.java:2236) > at java.awt.Component.dispatchEventImpl(Component.java:4889) > at java.awt.Container.dispatchEventImpl(Container.java:2294) > at java.awt.Component.dispatchEvent(Component.java:4711) > at java.awt.LightweightDispatcher.retargetMouseEvent(Container.java:4888) > at java.awt.LightweightDispatcher.processMouseEvent(Container.java:4525) > at java.awt.LightweightDispatcher.dispatchEvent(Container.java:4466) > at java.awt.Container.dispatchEventImpl(Container.java:2280) > at java.awt.Window.dispatchEventImpl(Window.java:2746) > at java.awt.Component.dispatchEvent(Component.java:4711) > at java.awt.EventQueue.dispatchEventImpl(EventQueue.java:758) > at java.awt.EventQueue.access$500(EventQueue.java:97) > at java.awt.EventQueue$3.run(EventQueue.java:709) > at java.awt.EventQueue$3.run(EventQueue.java:703) > at java.security.AccessController.doPrivileged(Native Method) > at > java.security.ProtectionDomain$JavaSecurityAccessImpl.doIntersectionPrivilege(ProtectionDomain.java:80) > at > java.security.ProtectionDomain$JavaSecurityAccessImpl.doIntersectionPrivilege(ProtectionDomain.java:90) > at java.awt.EventQueue$4.run(EventQueue.java:731) > at java.awt.EventQueue$4.run(EventQueue.java:729) > at java.security.AccessController.doPrivileged(Native Method) > at > java.security.ProtectionDomain$JavaSecurityAccessImpl.doIntersectionPrivilege(ProtectionDomain.java:80) > at java.awt.EventQueue.dispatchEvent(EventQueue.java:728) > at > java.awt.EventDispatchThread.pumpOneEventForFilters(EventDispatchThread.java:201) > at > java.awt.EventDispatchThread.pumpEventsForFilter(EventDispatchThread.java:116) > at > java.awt.EventDispatchThread.pumpEventsForHierarchy(EventDispatchThread.java:105) > at java.awt.EventDispatchThread.pumpEvents(EventDispatchThread.java:101) > at java.awt.EventDispatchThread.pumpEvents(EventDispatchThread.java:93) > at java.awt.EventDispatchThread.run(EventDispatchThread.java:82) > Caused by: java.lang.NullPointerException > at > com.sun.org.apache.xml.internal.serializer.ToHTMLStream.endElement(ToHTMLStream.java:911) > at > com.sun.org.apache.xalan.internal.xsltc.trax.TransformerHandlerImpl.endElement(TransformerHandlerImpl.java:284) > at > org.apache.tika.sax.ContentHandlerDecorator.endElement(ContentHandlerDecorator.java:136) > at org.apache.tika.gui.TikaGUI$2.endElement(TikaGUI.java:581) > at > org.apache.tika.sax.TeeContentHandler.endElement(TeeContentHandler.java:94) > at > org.apache.tika.sax.ContentHandlerDecorator.endElement(ContentHandlerDecorator.java:136) > at > org.apache.tika.sax.SecureContentHandler.endElement(SecureContentHandler.java:256) > at > org.apache.tika.sax.ContentHandlerDecorator.endElement(ContentHandlerDecorator.java:136) > at > org.apache.tika.sax.ContentHandlerDecorator.endElement(ContentHandlerDecorator.java:136) > at > org.apache.tika.sax.ContentHandlerDecorator.endElement(ContentHandlerDecorator.java:136) > at > org.apache.tika.sax.SafeContentHandler.endElement(SafeContentHandler.java:274) > at > org.apache.tika.sax.XHTMLContentHandler.endDocument(XHTMLContentHandler.java:232) > at org.apache.tika.parser.rtf.TextExtractor.extract(TextExtractor.java:481) > at org.apache.tika.parser.rtf.TextExtractor.extract(TextExtractor.java:442) > at org.apache.tika.parser.rtf.RTFParser.parse(RTFParser.java:98) > at org.apache.tika.parser.CompositeParser.parse(CompositeParser.java:280) > ... 46 more -- This message was sent by Atlassian JIRA (v7.6.3#76005)