Details
-
Bug
-
Status: Resolved
-
Major
-
Resolution: Fixed
-
None
-
None
-
None
Description
With solr4.0 and tika1.2 we get an exeption when trying to index a powerpoint file that contains a specific .wmf-image.
As it seems, the powerpoint file must be created in Office97 (or older?) to generate the error, since re-saving the file in Office2000 or Office2010 makes the problem go away.
Full stacktrace from the solr-server below:
2012-dec-19 14:39:46 org.apache.solr.common.SolrException log
ALLVARLIG: org.apache.solr.common.SolrException: org.apache.tika.exception.TikaException: Unexpected RuntimeException from org.apache.tika.parser.microsoft.OfficeParser@12f195
at org.apache.solr.handler.extraction.ExtractingDocumentLoader.load(ExtractingDocumentLoader.java:225)
at org.apache.solr.handler.ContentStreamHandlerBase.handleRequestBody(ContentStreamHandlerBase.java:74)
at org.apache.solr.handler.RequestHandlerBase.handleRequest(RequestHandlerBase.java:129)
at org.apache.solr.core.RequestHandlers$LazyRequestHandlerWrapper.handleRequest(RequestHandlers.java:240)
at org.apache.solr.core.SolrCore.execute(SolrCore.java:1699)
at org.apache.solr.servlet.SolrDispatchFilter.execute(SolrDispatchFilter.java:455)
at org.apache.solr.servlet.SolrDispatchFilter.doFilter(SolrDispatchFilter.java:276)
at org.apache.catalina.core.ApplicationFilterChain.internalDoFilter(ApplicationFilterChain.java:235)
at org.apache.catalina.core.ApplicationFilterChain.doFilter(ApplicationFilterChain.java:206)
at org.apache.catalina.core.StandardWrapperValve.invoke(StandardWrapperValve.java:233)
at org.apache.catalina.core.StandardContextValve.invoke(StandardContextValve.java:191)
at org.apache.catalina.authenticator.AuthenticatorBase.invoke(AuthenticatorBase.java:563)
at org.apache.catalina.core.StandardHostValve.invoke(StandardHostValve.java:127)
at org.apache.catalina.valves.ErrorReportValve.invoke(ErrorReportValve.java:102)
at org.apache.catalina.core.StandardEngineValve.invoke(StandardEngineValve.java:109)
at org.apache.catalina.connector.CoyoteAdapter.service(CoyoteAdapter.java:293)
at org.apache.coyote.http11.Http11Processor.process(Http11Processor.java:859)
at org.apache.coyote.http11.Http11Protocol$Http11ConnectionHandler.process(Http11Protocol.java:602)
at org.apache.tomcat.util.net.JIoEndpoint$Worker.run(JIoEndpoint.java:489)
at java.lang.Thread.run(Thread.java:662)
Caused by: org.apache.tika.exception.TikaException: Unexpected RuntimeException from org.apache.tika.parser.microsoft.OfficeParser@12f195
at org.apache.tika.parser.CompositeParser.parse(CompositeParser.java:244)
at org.apache.tika.parser.CompositeParser.parse(CompositeParser.java:242)
at org.apache.tika.parser.CompositeParser.parse(CompositeParser.java:242)
at org.apache.tika.parser.AutoDetectParser.parse(AutoDetectParser.java:120)
at org.apache.solr.handler.extraction.ExtractingDocumentLoader.load(ExtractingDocumentLoader.java:219)
... 19 more
Caused by: org.apache.poi.hslf.exceptions.HSLFException: java.util.zip.ZipException: unknown compression method
at org.apache.poi.hslf.blip.WMF.getData(WMF.java:65)
at org.apache.tika.parser.microsoft.HSLFExtractor.handleSlideEmbeddedPictures(HSLFExtractor.java:204)
at org.apache.tika.parser.microsoft.HSLFExtractor.parse(HSLFExtractor.java:162)
at org.apache.tika.parser.microsoft.OfficeParser.parse(OfficeParser.java:189)
at org.apache.tika.parser.microsoft.OfficeParser.parse(OfficeParser.java:161)
at org.apache.tika.parser.CompositeParser.parse(CompositeParser.java:242)
... 23 more
Caused by: java.util.zip.ZipException: unknown compression method
at java.util.zip.InflaterInputStream.read(InflaterInputStream.java:147)
at java.io.FilterInputStream.read(FilterInputStream.java:90)
at org.apache.poi.hslf.blip.WMF.getData(WMF.java:59)
... 28 more
2012-dec-19 14:39:46 org.apache.solr.common.SolrException log
ALLVARLIG: null:org.apache.solr.common.SolrException: org.apache.tika.exception.TikaException: Unexpected RuntimeException from org.apache.tika.parser.microsoft.OfficeParser@12f195
at org.apache.solr.handler.extraction.ExtractingDocumentLoader.load(ExtractingDocumentLoader.java:225)
at org.apache.solr.handler.ContentStreamHandlerBase.handleRequestBody(ContentStreamHandlerBase.java:74)
at org.apache.solr.handler.RequestHandlerBase.handleRequest(RequestHandlerBase.java:129)
at org.apache.solr.core.RequestHandlers$LazyRequestHandlerWrapper.handleRequest(RequestHandlers.java:240)
at org.apache.solr.core.SolrCore.execute(SolrCore.java:1699)
at org.apache.solr.servlet.SolrDispatchFilter.execute(SolrDispatchFilter.java:455)
at org.apache.solr.servlet.SolrDispatchFilter.doFilter(SolrDispatchFilter.java:276)
at org.apache.catalina.core.ApplicationFilterChain.internalDoFilter(ApplicationFilterChain.java:235)
at org.apache.catalina.core.ApplicationFilterChain.doFilter(ApplicationFilterChain.java:206)
at org.apache.catalina.core.StandardWrapperValve.invoke(StandardWrapperValve.java:233)
at org.apache.catalina.core.StandardContextValve.invoke(StandardContextValve.java:191)
at org.apache.catalina.authenticator.AuthenticatorBase.invoke(AuthenticatorBase.java:563)
at org.apache.catalina.core.StandardHostValve.invoke(StandardHostValve.java:127)
at org.apache.catalina.valves.ErrorReportValve.invoke(ErrorReportValve.java:102)
at org.apache.catalina.core.StandardEngineValve.invoke(StandardEngineValve.java:109)
at org.apache.catalina.connector.CoyoteAdapter.service(CoyoteAdapter.java:293)
at org.apache.coyote.http11.Http11Processor.process(Http11Processor.java:859)
at org.apache.coyote.http11.Http11Protocol$Http11ConnectionHandler.process(Http11Protocol.java:602)
at org.apache.tomcat.util.net.JIoEndpoint$Worker.run(JIoEndpoint.java:489)
at java.lang.Thread.run(Thread.java:662)
Caused by: org.apache.tika.exception.TikaException: Unexpected RuntimeException from org.apache.tika.parser.microsoft.OfficeParser@12f195
at org.apache.tika.parser.CompositeParser.parse(CompositeParser.java:244)
at org.apache.tika.parser.CompositeParser.parse(CompositeParser.java:242)
at org.apache.tika.parser.CompositeParser.parse(CompositeParser.java:242)
at org.apache.tika.parser.AutoDetectParser.parse(AutoDetectParser.java:120)
at org.apache.solr.handler.extraction.ExtractingDocumentLoader.load(ExtractingDocumentLoader.java:219)
... 19 more
Caused by: org.apache.poi.hslf.exceptions.HSLFException: java.util.zip.ZipException: unknown compression method
at org.apache.poi.hslf.blip.WMF.getData(WMF.java:65)
at org.apache.tika.parser.microsoft.HSLFExtractor.handleSlideEmbeddedPictures(HSLFExtractor.java:204)
at org.apache.tika.parser.microsoft.HSLFExtractor.parse(HSLFExtractor.java:162)
at org.apache.tika.parser.microsoft.OfficeParser.parse(OfficeParser.java:189)
at org.apache.tika.parser.microsoft.OfficeParser.parse(OfficeParser.java:161)
at org.apache.tika.parser.CompositeParser.parse(CompositeParser.java:242)
... 23 more
Caused by: java.util.zip.ZipException: unknown compression method
at java.util.zip.InflaterInputStream.read(InflaterInputStream.java:147)
at java.io.FilterInputStream.read(FilterInputStream.java:90)
at org.apache.poi.hslf.blip.WMF.getData(WMF.java:59)
... 28 more