search

voyanttools / trombone

GNU General Public License v3.0
3 stars 2 forks source link

Larger corpus uploads are failing #34

Open ajmacdonald opened 12 months ago

ajmacdonald commented 12 months ago 
An error occurred during multi-threaded document expansion.
java.lang.IllegalStateException: An error occurred during multi-threaded document expansion.
    at org.voyanttools.trombone.input.extract.StoredDocumentSourceExtractor.getExtractedStoredDocumentSources(StoredDocumentSourceExtractor.java:151)
    at org.voyanttools.trombone.tool.build.DocumentExtractor.run(DocumentExtractor.java:90)
    at org.voyanttools.trombone.tool.build.RealCorpusCreator.run(RealCorpusCreator.java:93)
    at org.voyanttools.trombone.tool.corpus.CorpusCreator.run(CorpusCreator.java:49)
    at org.voyanttools.trombone.tool.util.ToolRunner.run(ToolRunner.java:134)
    at org.voyanttools.trombone.Controller.run(Controller.java:110)
    at org.voyanttools.voyant.Trombone.runTromboneController(Trombone.java:337)
    at org.voyanttools.voyant.Trombone.doRequest(Trombone.java:311)
    at org.voyanttools.voyant.Trombone.doRequest(Trombone.java:146)
    at org.voyanttools.voyant.Trombone.doPost(Trombone.java:87)
    at javax.servlet.http.HttpServlet.service(HttpServlet.java:681)
    at javax.servlet.http.HttpServlet.service(HttpServlet.java:764)
    at org.apache.catalina.core.ApplicationFilterChain.internalDoFilter(ApplicationFilterChain.java:227)
    at org.apache.catalina.core.ApplicationFilterChain.doFilter(ApplicationFilterChain.java:162)
    at org.apache.tomcat.websocket.server.WsFilter.doFilter(WsFilter.java:53)
    at org.apache.catalina.core.ApplicationFilterChain.internalDoFilter(ApplicationFilterChain.java:189)
    at org.apache.catalina.core.ApplicationFilterChain.doFilter(ApplicationFilterChain.java:162)
    at org.apache.catalina.core.StandardWrapperValve.invoke(StandardWrapperValve.java:197)
    at org.apache.catalina.core.StandardContextValve.invoke(StandardContextValve.java:97)
    at org.apache.catalina.authenticator.AuthenticatorBase.invoke(AuthenticatorBase.java:540)
    at org.apache.catalina.core.StandardHostValve.invoke(StandardHostValve.java:135)
    at org.apache.catalina.valves.ErrorReportValve.invoke(ErrorReportValve.java:92)
    at org.apache.catalina.valves.AbstractAccessLogValve.invoke(AbstractAccessLogValve.java:687)
    at org.apache.catalina.core.StandardEngineValve.invoke(StandardEngineValve.java:78)
    at org.apache.catalina.connector.CoyoteAdapter.service(CoyoteAdapter.java:359)
    at org.apache.coyote.http11.Http11Processor.service(Http11Processor.java:399)
    at org.apache.coyote.AbstractProcessorLight.process(AbstractProcessorLight.java:65)
    at org.apache.coyote.AbstractProtocol$ConnectionHandler.process(AbstractProtocol.java:889)
    at org.apache.tomcat.util.net.NioEndpoint$SocketProcessor.doRun(NioEndpoint.java:1735)
    at org.apache.tomcat.util.net.SocketProcessorBase.run(SocketProcessorBase.java:49)
    at org.apache.tomcat.util.threads.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1191)
    at org.apache.tomcat.util.threads.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:659)
    at org.apache.tomcat.util.threads.TaskThread$WrappingRunnable.run(TaskThread.java:61)
    at java.base/java.lang.Thread.run(Thread.java:829)
Caused by: java.util.concurrent.ExecutionException: java.io.IOException: Unable to transform node during XML extraction: 26358564fa46d5950096cec70e2ea369 STREAM: foo.xml
    at java.base/java.util.concurrent.FutureTask.report(FutureTask.java:122)
    at java.base/java.util.concurrent.FutureTask.get(FutureTask.java:191)
    at org.voyanttools.trombone.input.extract.StoredDocumentSourceExtractor.getExtractedStoredDocumentSources(StoredDocumentSourceExtractor.java:137)
    ... 33 more
Caused by: java.io.IOException: Unable to transform node during XML extraction: 26358564fa46d5950096cec70e2ea369 STREAM: foo.xml
    at org.voyanttools.trombone.input.extract.XmlExtractor$ExtractableXmlInputSource.getInputStream(XmlExtractor.java:412)
    at org.voyanttools.trombone.storage.file.FileStoredDocumentSourceStorage.getStoredDocumentSource(FileStoredDocumentSourceStorage.java:115)
    at org.voyanttools.trombone.input.extract.StoredDocumentSourceExtractor.getExtractedStoredDocumentSource(StoredDocumentSourceExtractor.java:217)
    at org.voyanttools.trombone.input.extract.StoredDocumentSourceExtractor$CallableExtractor.call(StoredDocumentSourceExtractor.java:245)
    at org.voyanttools.trombone.input.extract.StoredDocumentSourceExtractor$CallableExtractor.call(StoredDocumentSourceExtractor.java:227)
    at java.base/java.util.concurrent.FutureTask.run(FutureTask.java:264)
    at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1128)
    at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:628)
    ... 1 more
Caused by: java.lang.NullPointerException
    at org.apache.xml.serializer.ToStream.writeAttrString(ToStream.java:1922)
    at org.apache.xml.serializer.ToStream.processAttributes(ToStream.java:1902)
    at org.apache.xml.serializer.ToStream.closeStartTag(ToStream.java:2378)
    at org.apache.xml.serializer.ToStream.startElement(ToStream.java:1739)
    at org.apache.xalan.transformer.TransformerIdentityImpl.startElement(TransformerIdentityImpl.java:1072)
    at org.apache.xml.serializer.TreeWalker.startNode(TreeWalker.java:357)
    at org.apache.xml.serializer.TreeWalker.traverse(TreeWalker.java:143)
    at org.apache.xalan.transformer.TransformerIdentityImpl.transform(TransformerIdentityImpl.java:389)
    at org.voyanttools.trombone.input.extract.XmlExtractor$ExtractableXmlInputSource.getInputStream(XmlExtractor.java:407)
    ... 8 more