[ 
https://issues.apache.org/jira/browse/NUTCH-2186?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
 ]

Sebastian Nagel updated NUTCH-2186:
-----------------------------------
    Fix Version/s:     (was: 1.14)
                   1.15

> -addBinaryContent flag can cause "String length must be a multiple of four" 
> error in IndexingJob
> ------------------------------------------------------------------------------------------------
>
>                 Key: NUTCH-2186
>                 URL: https://issues.apache.org/jira/browse/NUTCH-2186
>             Project: Nutch
>          Issue Type: Bug
>          Components: indexer
>    Affects Versions: 1.11
>         Environment: Apache Nutch 1.12-SNAPSHOT (trunk as of date this issue 
> was opened)
> Apache Solr 4.10.2
>            Reporter: Lewis John McGibbney
>             Fix For: 1.15
>
>
> When using the following indexing command
> {code}
> ./runtime/local/bin/nutch index -crawldb 
> /usr/local/trunk_new1/esdswg_crawl/crawldb/ -linkdb 
> /usr/local/trunk_new1/esdswg_crawl/linkdb/ -segmentDir 
> /usr/local/trunk_new1/esdswg_crawl/segments -addBinaryContent -deleteGone
> {code}
> I am able to generate the following error in my Solr logs
> {code}
> msg=String length must be a multiple of four.
>       at 
> org.apache.solr.update.DocumentBuilder.toDocument(DocumentBuilder.java:178)
>       at 
> org.apache.solr.update.AddUpdateCommand.getLuceneDocument(AddUpdateCommand.java:78)
>       at 
> org.apache.solr.update.DirectUpdateHandler2.addDoc0(DirectUpdateHandler2.java:238)
>       at 
> org.apache.solr.update.DirectUpdateHandler2.addDoc(DirectUpdateHandler2.java:164)
>       at 
> org.apache.solr.update.processor.RunUpdateProcessor.processAdd(RunUpdateProcessorFactory.java:69)
>       at 
> org.apache.solr.update.processor.UpdateRequestProcessor.processAdd(UpdateRequestProcessor.java:51)
>       at 
> org.apache.solr.update.processor.DistributedUpdateProcessor.doLocalAdd(DistributedUpdateProcessor.java:926)
>       at 
> org.apache.solr.update.processor.DistributedUpdateProcessor.versionAdd(DistributedUpdateProcessor.java:1080)
>       at 
> org.apache.solr.update.processor.DistributedUpdateProcessor.processAdd(DistributedUpdateProcessor.java:692)
>       at 
> org.apache.solr.update.processor.LogUpdateProcessor.processAdd(LogUpdateProcessorFactory.java:100)
>       at 
> org.apache.solr.handler.loader.XMLLoader.processUpdate(XMLLoader.java:247)
>       at org.apache.solr.handler.loader.XMLLoader.load(XMLLoader.java:174)
>       at 
> org.apache.solr.handler.UpdateRequestHandler$1.load(UpdateRequestHandler.java:99)
>       at 
> org.apache.solr.handler.ContentStreamHandlerBase.handleRequestBody(ContentStreamHandlerBase.java:74)
>       at 
> org.apache.solr.handler.RequestHandlerBase.handleRequest(RequestHandlerBase.java:135)
>       at org.apache.solr.core.SolrCore.execute(SolrCore.java:1967)
>       at 
> org.apache.solr.servlet.SolrDispatchFilter.execute(SolrDispatchFilter.java:777)
>       at 
> org.apache.solr.servlet.SolrDispatchFilter.doFilter(SolrDispatchFilter.java:418)
>       at 
> org.apache.solr.servlet.SolrDispatchFilter.doFilter(SolrDispatchFilter.java:207)
>       at 
> org.eclipse.jetty.servlet.ServletHandler$CachedChain.doFilter(ServletHandler.java:1419)
>       at 
> org.eclipse.jetty.servlet.ServletHandler.doHandle(ServletHandler.java:455)
>       at 
> org.eclipse.jetty.server.handler.ScopedHandler.handle(ScopedHandler.java:137)
>       at 
> org.eclipse.jetty.security.SecurityHandler.handle(SecurityHandler.java:557)
>       at 
> org.eclipse.jetty.server.session.SessionHandler.doHandle(SessionHandler.java:231)
>       at 
> org.eclipse.jetty.server.handler.ContextHandler.doHandle(ContextHandler.java:1075)
>       at 
> org.eclipse.jetty.servlet.ServletHandler.doScope(ServletHandler.java:384)
>       at 
> org.eclipse.jetty.server.session.SessionHandler.doScope(SessionHandler.java:193)
>       at 
> org.eclipse.jetty.server.handler.ContextHandler.doScope(ContextHandler.java:1009)
>       at 
> org.eclipse.jetty.server.handler.ScopedHandler.handle(ScopedHandler.java:135)
>       at 
> org.eclipse.jetty.server.handler.ContextHandlerCollection.handle(ContextHandlerCollection.java:255)
>       at 
> org.eclipse.jetty.server.handler.HandlerCollection.handle(HandlerCollection.java:154)
>       at 
> org.eclipse.jetty.server.handler.HandlerWrapper.handle(HandlerWrapper.java:116)
>       at org.eclipse.jetty.server.Server.handle(Server.java:368)
>       at 
> org.eclipse.jetty.server.AbstractHttpConnection.handleRequest(AbstractHttpConnection.java:489)
>       at 
> org.eclipse.jetty.server.BlockingHttpConnection.handleRequest(BlockingHttpConnection.java:53)
>       at 
> org.eclipse.jetty.server.AbstractHttpConnection.content(AbstractHttpConnection.java:953)
>       at 
> org.eclipse.jetty.server.AbstractHttpConnection$RequestHandler.content(AbstractHttpConnection.java:1014)
>       at org.eclipse.jetty.http.HttpParser.parseNext(HttpParser.java:953)
>       at org.eclipse.jetty.http.HttpParser.parseAvailable(HttpParser.java:240)
>       at 
> org.eclipse.jetty.server.BlockingHttpConnection.handle(BlockingHttpConnection.java:72)
>       at 
> org.eclipse.jetty.server.bio.SocketConnector$ConnectorEndPoint.run(SocketConnector.java:264)
>       at 
> org.eclipse.jetty.util.thread.QueuedThreadPool.runJob(QueuedThreadPool.java:608)
>       at 
> org.eclipse.jetty.util.thread.QueuedThreadPool$3.run(QueuedThreadPool.java:543)
>       at java.lang.Thread.run(Thread.java:745)
> Caused by: java.lang.IllegalArgumentException: String length must be a 
> multiple of four.
>       at org.apache.solr.common.util.Base64.base64ToByteArray(Base64.java:98)
>       at org.apache.solr.schema.BinaryField.createField(BinaryField.java:79)
>       at org.apache.solr.schema.FieldType.createFields(FieldType.java:304)
>       at 
> org.apache.solr.update.DocumentBuilder.addField(DocumentBuilder.java:50)
>       at 
> org.apache.solr.update.DocumentBuilder.toDocument(DocumentBuilder.java:125)
>       ... 43 more
> {code}



--
This message was sent by Atlassian JIRA
(v6.4.14#64029)

Reply via email to