[ https://issues.apache.org/jira/browse/TIKA-801?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Michael McCandless updated TIKA-801: ------------------------------------ Attachment: TIKA-801.patch bq. See the org.apache.tika.sax.EmbeddedContentHandler class. Excellent! I did that (patch attached) and these RTF/HTML Outlook docs are now fine through TikaGUI. > ContentHandlerDecorator outputs invalid element > ----------------------------------------------- > > Key: TIKA-801 > URL: https://issues.apache.org/jira/browse/TIKA-801 > Project: Tika > Issue Type: Bug > Affects Versions: 1.0, 1.1 > Reporter: Andrzej Bialecki > Assignee: Michael McCandless > Attachments: FW Testing.msg, TIKA-801.patch > > > * Start Tika GUI > * try opening test-outlook.msg (from tika-parsers test resources) > * the following exception is thrown: > {code} > org.apache.tika.exception.TikaException: Unexpected RuntimeException from > org.apache.tika.parser.microsoft.OfficeParser@12e14ebc > at > org.apache.tika.parser.CompositeParser.parse(CompositeParser.java:245) > at > org.apache.tika.parser.CompositeParser.parse(CompositeParser.java:243) > at > org.apache.tika.parser.AutoDetectParser.parse(AutoDetectParser.java:120) > at org.apache.tika.gui.TikaGUI.handleStream(TikaGUI.java:320) > at org.apache.tika.gui.TikaGUI.openFile(TikaGUI.java:279) > at org.apache.tika.gui.TikaGUI.actionPerformed(TikaGUI.java:238) > at > javax.swing.AbstractButton.fireActionPerformed(AbstractButton.java:2028) > at > javax.swing.AbstractButton$Handler.actionPerformed(AbstractButton.java:2351) > at > javax.swing.DefaultButtonModel.fireActionPerformed(DefaultButtonModel.java:387) > at > javax.swing.DefaultButtonModel.setPressed(DefaultButtonModel.java:242) > at javax.swing.AbstractButton.doClick(AbstractButton.java:389) > at > javax.swing.plaf.basic.BasicMenuItemUI.doClick(BasicMenuItemUI.java:809) > at com.apple.laf.AquaMenuItemUI.doClick(AquaMenuItemUI.java:137) > at > javax.swing.plaf.basic.BasicMenuItemUI$Handler.mouseReleased(BasicMenuItemUI.java:850) > at java.awt.Component.processMouseEvent(Component.java:6373) > at javax.swing.JComponent.processMouseEvent(JComponent.java:3267) > at java.awt.Component.processEvent(Component.java:6138) > at java.awt.Container.processEvent(Container.java:2085) > at java.awt.Component.dispatchEventImpl(Component.java:4735) > at java.awt.Container.dispatchEventImpl(Container.java:2143) > at java.awt.Component.dispatchEvent(Component.java:4565) > at > java.awt.LightweightDispatcher.retargetMouseEvent(Container.java:4621) > at java.awt.LightweightDispatcher.processMouseEvent(Container.java:4282) > at java.awt.LightweightDispatcher.dispatchEvent(Container.java:4212) > at java.awt.Container.dispatchEventImpl(Container.java:2129) > at java.awt.Window.dispatchEventImpl(Window.java:2478) > at java.awt.Component.dispatchEvent(Component.java:4565) > at java.awt.EventQueue.dispatchEventImpl(EventQueue.java:679) > at java.awt.EventQueue.access$000(EventQueue.java:85) > at java.awt.EventQueue$1.run(EventQueue.java:638) > at java.awt.EventQueue$1.run(EventQueue.java:636) > at java.security.AccessController.doPrivileged(Native Method) > at > java.security.AccessControlContext$1.doIntersectionPrivilege(AccessControlContext.java:87) > at > java.security.AccessControlContext$1.doIntersectionPrivilege(AccessControlContext.java:98) > at java.awt.EventQueue$2.run(EventQueue.java:652) > at java.awt.EventQueue$2.run(EventQueue.java:650) > at java.security.AccessController.doPrivileged(Native Method) > at > java.security.AccessControlContext$1.doIntersectionPrivilege(AccessControlContext.java:87) > at java.awt.EventQueue.dispatchEvent(EventQueue.java:649) > at > java.awt.EventDispatchThread.pumpOneEventForFilters(EventDispatchThread.java:296) > at > java.awt.EventDispatchThread.pumpEventsForFilter(EventDispatchThread.java:211) > at > java.awt.EventDispatchThread.pumpEventsForHierarchy(EventDispatchThread.java:201) > at java.awt.EventDispatchThread.pumpEvents(EventDispatchThread.java:196) > at java.awt.EventDispatchThread.pumpEvents(EventDispatchThread.java:188) > at java.awt.EventDispatchThread.run(EventDispatchThread.java:122) > Caused by: java.lang.NullPointerException > at > com.sun.org.apache.xml.internal.serializer.ToHTMLStream.endElement(ToHTMLStream.java:907) > at > com.sun.org.apache.xalan.internal.xsltc.trax.TransformerHandlerImpl.endElement(TransformerHandlerImpl.java:273) > at > org.apache.tika.sax.ContentHandlerDecorator.endElement(ContentHandlerDecorator.java:136) > at org.apache.tika.gui.TikaGUI$2.endElement(TikaGUI.java:519) > 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:273) > at > org.apache.tika.sax.XHTMLContentHandler.endDocument(XHTMLContentHandler.java:213) > at > org.apache.tika.parser.microsoft.OfficeParser.parse(OfficeParser.java:159) > at > org.apache.tika.parser.CompositeParser.parse(CompositeParser.java:243) > ... 44 more > {code} > The same file is parsed without any errors when not in GUI mode. -- This message is automatically generated by JIRA. If you think it was sent incorrectly, please contact your JIRA administrators: https://issues.apache.org/jira/secure/ContactAdministrators!default.jspa For more information on JIRA, see: http://www.atlassian.com/software/jira