[
https://issues.apache.org/jira/browse/NUTCH-2650?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Sebastian Nagel reassigned NUTCH-2650:
--------------------------------------
Assignee: Sebastian Nagel
> -addBinaryContent -base64 flags are causing "String length must be a multiple
> of four" error in IndexingJob
> -----------------------------------------------------------------------------------------------------------
>
> Key: NUTCH-2650
> URL: https://issues.apache.org/jira/browse/NUTCH-2650
> Project: Nutch
> Issue Type: Bug
> Components: indexer
> Affects Versions: 1.14
> Reporter: asmita
> Assignee: Sebastian Nagel
> Priority: Major
> Fix For: 1.16
>
>
> I am running Nutch crawl command as follows, in distributed mode:
> {code:java}
> runtime/deploy/bin/crawl -i -D
> solr.server.url=http://my-solr:8983/solr/my-collection -D
> solr.server.type=cloud -D solr.zookeeper.url=http://my-solr:9983 -s
> /user/my-user/seed /user/my-user/crawl 1
> {code}
> The IndexingJob fails with the following error:
>
> {code:java}
> org.apache.solr.common.SolrException: ERROR:
> [doc=3b9a9fb7fd92d32287da1b2f3df5f8a1] Error adding field
> 'binaryContent'='.......==
> ' msg=String length must be a multiple of four.
> at
> org.apache.solr.update.DocumentBuilder.toDocument(DocumentBuilder.java:208)
> at
> org.apache.solr.update.AddUpdateCommand.getLuceneDocument(AddUpdateCommand.java:101)
> at
> org.apache.solr.update.DirectUpdateHandler2.updateDocument(DirectUpdateHandler2.java:963)
> at
> org.apache.solr.update.DirectUpdateHandler2.updateDocOrDocValues(DirectUpdateHandler2.java:954)
> at
> org.apache.solr.update.DirectUpdateHandler2.doNormalUpdate(DirectUpdateHandler2.java:334)
> at
> org.apache.solr.update.DirectUpdateHandler2.addDoc0(DirectUpdateHandler2.java:271)
> at
> org.apache.solr.update.DirectUpdateHandler2.addDoc(DirectUpdateHandler2.java:221)
> at
> org.apache.solr.update.processor.RunUpdateProcessor.processAdd(RunUpdateProcessorFactory.java:67)
> at
> org.apache.solr.update.processor.UpdateRequestProcessor.processAdd(UpdateRequestProcessor.java:55)
> at
> org.apache.solr.update.processor.DistributedUpdateProcessor.doLocalAdd(DistributedUpdateProcessor.java:950)
> at
> org.apache.solr.update.processor.DistributedUpdateProcessor.versionAdd(DistributedUpdateProcessor.java:1163)
> at
> org.apache.solr.update.processor.DistributedUpdateProcessor.processAdd(DistributedUpdateProcessor.java:633)
> at
> org.apache.solr.update.processor.LogUpdateProcessorFactory$LogUpdateProcessor.processAdd(LogUpdateProcessorFactory.java:103)
> at
> org.apache.solr.update.processor.UpdateRequestProcessor.processAdd(UpdateRequestProcessor.java:55)
> at
> org.apache.solr.update.processor.AddSchemaFieldsUpdateProcessorFactory$AddSchemaFieldsUpdateProcessor.processAdd(AddSchemaFieldsUpdateProcessorFactory.java:475)
> at
> org.apache.solr.update.processor.UpdateRequestProcessor.processAdd(UpdateRequestProcessor.java:55)
> at
> org.apache.solr.update.processor.FieldMutatingUpdateProcessor.processAdd(FieldMutatingUpdateProcessor.java:118)
> at
> org.apache.solr.update.processor.UpdateRequestProcessor.processAdd(UpdateRequestProcessor.java:55)
> at
> org.apache.solr.update.processor.FieldMutatingUpdateProcessor.processAdd(FieldMutatingUpdateProcessor.java:118)
> at
> org.apache.solr.update.processor.UpdateRequestProcessor.processAdd(UpdateRequestProcessor.java:55)
> at
> org.apache.solr.update.processor.FieldMutatingUpdateProcessor.processAdd(FieldMutatingUpdateProcessor.java:118)
> at
> org.apache.solr.update.processor.UpdateRequestProcessor.processAdd(UpdateRequestProcessor.java:55)
> at
> org.apache.solr.update.processor.FieldMutatingUpdateProcessor.processAdd(FieldMutatingUpdateProcessor.java:118)
> at
> org.apache.solr.update.processor.UpdateRequestProcessor.processAdd(UpdateRequestProcessor.java:55)
> at
> org.apache.solr.update.processor.FieldNameMutatingUpdateProcessorFactory$1.processAdd(FieldNameMutatingUpdateProcessorFactory.java:75)
> at
> org.apache.solr.update.processor.UpdateRequestProcessor.processAdd(UpdateRequestProcessor.java:55)
> at
> org.apache.solr.update.processor.FieldMutatingUpdateProcessor.processAdd(FieldMutatingUpdateProcessor.java:118)
> at
> org.apache.solr.update.processor.UpdateRequestProcessor.processAdd(UpdateRequestProcessor.java:55)
> at
> org.apache.solr.update.processor.AbstractDefaultValueUpdateProcessorFactory$DefaultValueUpdateProcessor.processAdd(AbstractDefaultValueUpdateProcessorFactory.java:92)
> at
> org.apache.solr.handler.loader.JavabinLoader$1.update(JavabinLoader.java:98)
> at
> org.apache.solr.client.solrj.request.JavaBinUpdateRequestCodec$1.readOuterMostDocIterator(JavaBinUpdateRequestCodec.java:188)
> at
> org.apache.solr.client.solrj.request.JavaBinUpdateRequestCodec$1.readIterator(JavaBinUpdateRequestCodec.java:144)
> at
> org.apache.solr.common.util.JavaBinCodec.readObject(JavaBinCodec.java:311)
> at
> org.apache.solr.common.util.JavaBinCodec.readVal(JavaBinCodec.java:256)
> at
> org.apache.solr.client.solrj.request.JavaBinUpdateRequestCodec$1.readNamedList(JavaBinUpdateRequestCodec.java:130)
> at
> org.apache.solr.common.util.JavaBinCodec.readObject(JavaBinCodec.java:276)
> at
> org.apache.solr.common.util.JavaBinCodec.readVal(JavaBinCodec.java:256)
> at
> org.apache.solr.common.util.JavaBinCodec.unmarshal(JavaBinCodec.java:178)
> at
> org.apache.solr.client.solrj.request.JavaBinUpdateRequestCodec.unmarshal(JavaBinUpdateRequestCodec.java:195)
> at
> org.apache.solr.handler.loader.JavabinLoader.parseAndLoadDocs(JavabinLoader.java:109)
> at
> org.apache.solr.handler.loader.JavabinLoader.load(JavabinLoader.java:55)
> at
> org.apache.solr.handler.UpdateRequestHandler$1.load(UpdateRequestHandler.java:97)
> at
> org.apache.solr.handler.ContentStreamHandlerBase.handleRequestBody(ContentStreamHandlerBase.java:68)
> at
> org.apache.solr.handler.RequestHandlerBase.handleRequest(RequestHandlerBase.java:195)
> at org.apache.solr.core.SolrCore.execute(SolrCore.java:2503)
> at org.apache.solr.servlet.HttpSolrCall.execute(HttpSolrCall.java:711)
> at org.apache.solr.servlet.HttpSolrCall.call(HttpSolrCall.java:517)
> at
> org.apache.solr.servlet.SolrDispatchFilter.doFilter(SolrDispatchFilter.java:384)
> at
> org.apache.solr.servlet.SolrDispatchFilter.doFilter(SolrDispatchFilter.java:330)
> at
> org.eclipse.jetty.servlet.ServletHandler$CachedChain.doFilter(ServletHandler.java:1637)
> at
> org.eclipse.jetty.servlets.CrossOriginFilter.handle(CrossOriginFilter.java:311)
> at
> org.eclipse.jetty.servlets.CrossOriginFilter.doFilter(CrossOriginFilter.java:265)
> at
> org.eclipse.jetty.servlet.ServletHandler$CachedChain.doFilter(ServletHandler.java:1629)
> at
> org.eclipse.jetty.servlet.ServletHandler.doHandle(ServletHandler.java:533)
> at
> org.eclipse.jetty.server.handler.ScopedHandler.handle(ScopedHandler.java:143)
> at
> org.eclipse.jetty.security.SecurityHandler.handle(SecurityHandler.java:548)
> at
> org.eclipse.jetty.server.handler.HandlerWrapper.handle(HandlerWrapper.java:132)
> at
> org.eclipse.jetty.server.handler.ScopedHandler.nextHandle(ScopedHandler.java:190)
> at
> org.eclipse.jetty.server.session.SessionHandler.doHandle(SessionHandler.java:1595)
> at
> org.eclipse.jetty.server.handler.ScopedHandler.nextHandle(ScopedHandler.java:188)
> at
> org.eclipse.jetty.server.handler.ContextHandler.doHandle(ContextHandler.java:1253)
> at
> org.eclipse.jetty.server.handler.ScopedHandler.nextScope(ScopedHandler.java:168)
> at
> org.eclipse.jetty.servlet.ServletHandler.doScope(ServletHandler.java:473)
> at
> org.eclipse.jetty.server.session.SessionHandler.doScope(SessionHandler.java:1564)
> at
> org.eclipse.jetty.server.handler.ScopedHandler.nextScope(ScopedHandler.java:166)
> at
> org.eclipse.jetty.server.handler.ContextHandler.doScope(ContextHandler.java:1155)
> at
> org.eclipse.jetty.server.handler.ScopedHandler.handle(ScopedHandler.java:141)
> at
> org.eclipse.jetty.server.handler.ContextHandlerCollection.handle(ContextHandlerCollection.java:219)
> at
> org.eclipse.jetty.server.handler.HandlerCollection.handle(HandlerCollection.java:126)
> at
> org.eclipse.jetty.server.handler.HandlerWrapper.handle(HandlerWrapper.java:132)
> at
> org.eclipse.jetty.rewrite.handler.RewriteHandler.handle(RewriteHandler.java:335)
> at
> org.eclipse.jetty.server.handler.HandlerWrapper.handle(HandlerWrapper.java:132)
> at org.eclipse.jetty.server.Server.handle(Server.java:530)
> at org.eclipse.jetty.server.HttpChannel.handle(HttpChannel.java:347)
> at
> org.eclipse.jetty.server.HttpConnection.onFillable(HttpConnection.java:256)
> at
> org.eclipse.jetty.io.AbstractConnection$ReadCallback.succeeded(AbstractConnection.java:279)
> at org.eclipse.jetty.io.FillInterest.fillable(FillInterest.java:102)
> at org.eclipse.jetty.io.ChannelEndPoint$2.run(ChannelEndPoint.java:124)
> at
> org.eclipse.jetty.util.thread.strategy.EatWhatYouKill.doProduce(EatWhatYouKill.java:247)
> at
> org.eclipse.jetty.util.thread.strategy.EatWhatYouKill.produce(EatWhatYouKill.java:140)
> at
> org.eclipse.jetty.util.thread.strategy.EatWhatYouKill.run(EatWhatYouKill.java:131)
> at
> org.eclipse.jetty.util.thread.ReservedThreadExecutor$ReservedThread.run(ReservedThreadExecutor.java:382)
> at
> org.eclipse.jetty.util.thread.QueuedThreadPool.runJob(QueuedThreadPool.java:708)
> at
> org.eclipse.jetty.util.thread.QueuedThreadPool$2.run(QueuedThreadPool.java:626)
> at java.lang.Thread.run(Thread.java:748)
> Caused by: java.lang.IllegalArgumentException: String length must be a
> multiple of four.
> at org.apache.solr.common.util.Base64.base64ToByteArray(Base64.java:102)
> at org.apache.solr.schema.BinaryField.createField(BinaryField.java:101)
> at org.apache.solr.schema.FieldType.createFields(FieldType.java:317)
> at
> org.apache.solr.update.DocumentBuilder.addField(DocumentBuilder.java:66)
> at
> org.apache.solr.update.DocumentBuilder.toDocument(DocumentBuilder.java:159)
> ... 84 more
> {code}
> Solr version: 7.3.1
> Indexing command from logs:
> {code:java}
> runtime/deploy/bin/nutch index -Dsolr.zookeeper.url=http://my-solr:9983
> -Dsolr.server.type=cloud
> -Dsolr.server.url=http://my-solr:8983/solr/my-collection
> /user/my-user/crawl/crawldb -linkdb /user/my-user/crawl/linkdb
> /user/my-user/crawl/segments/20181011040457 -addBinaryContent -base64
> {code}
>
> (removed huge binary content from the log)
--
This message was sent by Atlassian JIRA
(v7.6.3#76005)
