Looks like I identified that one i <https://bz.apache.org/bugzilla/show_bug.cgi?id=60833>n our regression corpus here: https://bz.apache.org/bugzilla/show_bug.cgi?id=60833#c10
Please open an issue on POI's bug tracker. If you need an example file, we can dig one up. On Wed, Jul 29, 2020 at 10:10 AM Slava G <[email protected]> wrote: > Hi, > I have some Excel files that opens fine in Excel or Numbers in Mac but > TIKA (inprocess and app) throws exception: > > > org.apache.tika.exception.TikaException: Unexpected RuntimeException from > org.apache.tika.parser.microsoft.OfficeParser@408ae0bf > at org.apache.tika.parser.CompositeParser.parse(CompositeParser.java:293) > 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$Handler.actionPerformed(AbstractButton.java:2348) > at > javax.swing.DefaultButtonModel.fireActionPerformed(DefaultButtonModel.java:402) > at javax.swing.DefaultButtonModel.setPressed(DefaultButtonModel.java:259) > at javax.swing.AbstractButton.doClick(AbstractButton.java:376) > at javax.swing.plaf.basic.BasicMenuItemUI.doClick(BasicMenuItemUI.java:842) > at com.apple.laf.AquaMenuItemUI.doClick(AquaMenuItemUI.java:157) > at > javax.swing.plaf.basic.BasicMenuItemUI$Handler.mouseReleased(BasicMenuItemUI.java:886) > at java.awt.Component.processMouseEvent(Component.java:6539) > at javax.swing.JComponent.processMouseEvent(JComponent.java:3324) > at java.awt.Component.processEvent(Component.java:6304) > at java.awt.Container.processEvent(Container.java:2239) > at java.awt.Component.dispatchEventImpl(Component.java:4889) > at java.awt.Container.dispatchEventImpl(Container.java:2297) > at java.awt.Component.dispatchEvent(Component.java:4711) > at java.awt.LightweightDispatcher.retargetMouseEvent(Container.java:4904) > at java.awt.LightweightDispatcher.processMouseEvent(Container.java:4535) > at java.awt.LightweightDispatcher.dispatchEvent(Container.java:4476) > at java.awt.Container.dispatchEventImpl(Container.java:2283) > at java.awt.Window.dispatchEventImpl(Window.java:2746) > at java.awt.Component.dispatchEvent(Component.java:4711) > at java.awt.EventQueue.dispatchEventImpl(EventQueue.java:760) > 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:74) > at > java.security.ProtectionDomain$JavaSecurityAccessImpl.doIntersectionPrivilege(ProtectionDomain.java:84) > at java.awt.EventQueue$4.run(EventQueue.java:733) > at java.awt.EventQueue$4.run(EventQueue.java:731) > at java.security.AccessController.doPrivileged(Native Method) > at > java.security.ProtectionDomain$JavaSecurityAccessImpl.doIntersectionPrivilege(ProtectionDomain.java:74) > at java.awt.EventQueue.dispatchEvent(EventQueue.java:730) > at > java.awt.EventDispatchThread.pumpOneEventForFilters(EventDispatchThread.java:205) > 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: > org.apache.poi.hssf.record.RecordInputStream$LeftoverDataException: > Initialisation of record 0x203(NumberRecord) left 4 bytes remaining still > to be read. > at > org.apache.poi.hssf.record.RecordInputStream.hasNextRecord(RecordInputStream.java:188) > at > org.apache.poi.hssf.record.RecordFactoryInputStream.nextRecord(RecordFactoryInputStream.java:235) > at > org.apache.poi.hssf.eventusermodel.HSSFEventFactory.genericProcessEvents(HSSFEventFactory.java:168) > at > org.apache.poi.hssf.eventusermodel.HSSFEventFactory.processEvents(HSSFEventFactory.java:129) > at > org.apache.tika.parser.microsoft.ExcelExtractor$TikaHSSFListener.processFile(ExcelExtractor.java:343) > at > org.apache.tika.parser.microsoft.ExcelExtractor.parse(ExcelExtractor.java:172) > at > org.apache.tika.parser.microsoft.OfficeParser.parse(OfficeParser.java:183) > at > org.apache.tika.parser.microsoft.OfficeParser.parse(OfficeParser.java:131) > at org.apache.tika.parser.CompositeParser.parse(CompositeParser.java:280) > ... 46 more > > I'm using TIKA 1.24.1 but it also happens in the previous version. > Thanks > >
