[ https://issues.apache.org/jira/browse/SOLR-3775?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Uwe Schindler closed SOLR-3775. ------------------------------- Resolution: Unresolved Assignee: Uwe Schindler This is a POI (or TIKA) issue. > Unexpected RuntimeException > --------------------------- > > Key: SOLR-3775 > URL: https://issues.apache.org/jira/browse/SOLR-3775 > Project: Solr > Issue Type: Bug > Affects Versions: 4.0-BETA > Reporter: Alex C > Assignee: Uwe Schindler > > Hi. I'm using Solr 4.0 Beta (no modifications to default installation) to > index, and it's blowing up on Word *.DOC files: > {code}curl > "http://localhost:8983/solr/update/extract?literal.id=doc15&commit=true" -F > "myfile=@15.doc"{code} > Here's the exception. And the same files go through Solr 3.6.1 just fine. > {noformat} <?xml version="1.0" encoding="UTF-8"?> > <response> > <lst name="responseHeader"><int name="status">500</int><int > name="QTime">18</int > ></lst><lst name="error"><str > name="msg">org.apache.tika.exception.TikaException > : Unexpected RuntimeException from > org.apache.tika.parser.microsoft.OfficeParser > @328c62ce</str><str name="trace">org.apache.solr.common.SolrException: > org.apache.tika.exception.TikaException: Unexpected RuntimeException from > org.apache.tika.parser.microsoft.OfficeParser@328c62ce > at > org.apache.solr.handler.extraction.ExtractingDocumentLoader.load(Extr > actingDocumentLoader.java:230) > at > org.apache.solr.handler.ContentStreamHandlerBase.handleRequestBody(Co > ntentStreamHandlerBase.java:74) > at > org.apache.solr.handler.RequestHandlerBase.handleRequest(RequestHandl > erBase.java:129) > at > org.apache.solr.core.RequestHandlers$LazyRequestHandlerWrapper.handle > Request(RequestHandlers.java:240) > at org.apache.solr.core.SolrCore.execute(SolrCore.java:1656) > at > org.apache.solr.servlet.SolrDispatchFilter.execute(SolrDispatchFilter > .java:454) > at > org.apache.solr.servlet.SolrDispatchFilter.doFilter(SolrDispatchFilte > r.java:275) > at > org.eclipse.jetty.servlet.ServletHandler$CachedChain.doFilter(Servlet > Handler.java:1337) > at > org.eclipse.jetty.servlet.ServletHandler.doHandle(ServletHandler.java > :484) > at > org.eclipse.jetty.server.handler.ScopedHandler.handle(ScopedHandler.j > ava:119) > at > org.eclipse.jetty.security.SecurityHandler.handle(SecurityHandler.java:524) > at > org.eclipse.jetty.server.session.SessionHandler.doHandle(SessionHandl > er.java:233) > at > org.eclipse.jetty.server.handler.ContextHandler.doHandle(ContextHandl > er.java:1065) > at > org.eclipse.jetty.servlet.ServletHandler.doScope(ServletHandler.java: > 413) > at > org.eclipse.jetty.server.session.SessionHandler.doScope(SessionHandle > r.java:192) > at > org.eclipse.jetty.server.handler.ContextHandler.doScope(ContextHandle > r.java:999) > at > org.eclipse.jetty.server.handler.ScopedHandler.handle(ScopedHandler.j > ava:117) > at > org.eclipse.jetty.server.handler.ContextHandlerCollection.handle(Cont > extHandlerCollection.java:250) > at > org.eclipse.jetty.server.handler.HandlerCollection.handle(HandlerColl > ection.java:149) > at > org.eclipse.jetty.server.handler.HandlerWrapper.handle(HandlerWrapper > .java:111) > at org.eclipse.jetty.server.Server.handle(Server.java:351) > at > org.eclipse.jetty.server.AbstractHttpConnection.handleRequest(Abstrac > tHttpConnection.java:454) > at > org.eclipse.jetty.server.BlockingHttpConnection.handleRequest(Blockin > gHttpConnection.java:47) > at > org.eclipse.jetty.server.AbstractHttpConnection.headerComplete(Abstra > ctHttpConnection.java:890) > at > org.eclipse.jetty.server.AbstractHttpConnection$RequestHandler.header > Complete(AbstractHttpConnection.java:944) > at > org.eclipse.jetty.http.HttpParser.parseNext(HttpParser.java:642) > at > org.eclipse.jetty.http.HttpParser.parseAvailable(HttpParser.java:230) > at > org.eclipse.jetty.server.BlockingHttpConnection.handle(BlockingHttpCo > nnection.java:66) > at > org.eclipse.jetty.server.bio.SocketConnector$ConnectorEndPoint.run(So > cketConnector.java:254) > at > org.eclipse.jetty.util.thread.QueuedThreadPool.runJob(QueuedThreadPoo > l.java:599) > at > org.eclipse.jetty.util.thread.QueuedThreadPool$3.run(QueuedThreadPool > .java:534) > at java.lang.Thread.run(Unknown Source) > Caused by: org.apache.tika.exception.TikaException: Unexpected > RuntimeException > from org.apache.tika.parser.microsoft.OfficeParser@328c62ce > 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.AutoDetectParser.parse(AutoDetectParser.java:1 > 20) > at > org.apache.solr.handler.extraction.ExtractingDocumentLoader.load(Extr > actingDocumentLoader.java:224) > ... 31 more > Caused by: java.lang.ArrayIndexOutOfBoundsException: 7 > at > org.apache.poi.util.LittleEndian.getInt(LittleEndian.java:163) > at > org.apache.poi.hwpf.model.Colorref.<init>(Colorref.java:81) > at > org.apache.poi.hwpf.model.types.SHDAbstractType.fillFields(SHDAbstrac > tType.java:56) > at > org.apache.poi.hwpf.usermodel.ShadingDescriptor.<init>(ShadingD > escriptor.java:38) > at > org.apache.poi.hwpf.sprm.CharacterSprmUncompressor.unCompressCHPOpera > tion(CharacterSprmUncompressor.java:582) > at > org.apache.poi.hwpf.sprm.CharacterSprmUncompressor.uncompressCHP(Char > acterSprmUncompressor.java:65) > at > org.apache.poi.hwpf.model.StyleSheet.createChp(StyleSheet.java:288) > at > org.apache.poi.hwpf.model.StyleSheet.<init>(StyleSheet.java:121 > ) > at > org.apache.poi.hwpf.HWPFDocument.<init>(HWPFDocument.java:346) > at > org.apache.tika.parser.microsoft.WordExtractor.parse(WordExtractor.ja > va:77) > at > org.apache.tika.parser.microsoft.OfficeParser.parse(OfficeParser.java > :185) > at > org.apache.tika.parser.microsoft.OfficeParser.parse(OfficeParser.java > :160) > at > org.apache.tika.parser.CompositeParser.parse(CompositeParser.java:242 > ) > ... 34 more > </str><int name="code">500</int></lst> > </response>{noformat} -- This message is automatically generated by JIRA. If you think it was sent incorrectly, please contact your JIRA administrators For more information on JIRA, see: http://www.atlassian.com/software/jira --------------------------------------------------------------------- To unsubscribe, e-mail: dev-unsubscr...@lucene.apache.org For additional commands, e-mail: dev-h...@lucene.apache.org