Im trying to index .doc,.docx,pdf files,
im using this url:
curl
"http://localhost:8080/solr/document/update/extract?literal.id=12&commit=true";
-F"myfile=@complex.doc"
This is the error I get:
Oct 07, 2013 5:02:18 PM org.apache.solr.common.SolrException log
SEVERE: null:java.lang.RuntimeException: java.lang.NoSuchFieldError:
SMALLER_BIG_BLOCK_SIZE_DETAILS
at
org.apache.solr.servlet.SolrDispatchFilter.sendError(SolrDispatchFilter.java:651)
at
org.apache.solr.servlet.SolrDispatchFilter.doFilter(SolrDispatchFilter.java:364)
at
org.apache.solr.servlet.SolrDispatchFilter.doFilter(SolrDispatchFilter.java:141)
at
org.apache.catalina.core.ApplicationFilterChain.internalDoFilter(ApplicationFilterChain.java:243)
at
org.apache.catalina.core.ApplicationFilterChain.doFilter(ApplicationFilterChain.java:210)
at
org.apache.catalina.core.StandardWrapperValve.invoke(StandardWrapperValve.java:224)
at
org.apache.catalina.core.StandardContextValve.invoke(StandardContextValve.java:169)
at
org.apache.catalina.core.StandardHostValve.invoke(StandardHostValve.java:168)
at
org.apache.catalina.valves.ErrorReportValve.invoke(ErrorReportValve.java:98)
at
org.apache.catalina.valves.AccessLogValve.invoke(AccessLogValve.java:928)
at
org.apache.catalina.core.StandardEngineValve.invoke(StandardEngineValve.java:118)
at
org.apache.catalina.connector.CoyoteAdapter.service(CoyoteAdapter.java:407)
at
org.apache.coyote.http11.AbstractHttp11Processor.process(AbstractHttp11Processor.java:987)
at
org.apache.coyote.AbstractProtocol$AbstractConnectionHandler.process(AbstractProtocol.java:539)
at
org.apache.tomcat.util.net.JIoEndpoint$SocketProcessor.run(JIoEndpoint.java:298)
at java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.lang.Thread.run(Unknown Source)
Caused by: java.lang.NoSuchFieldError: SMALLER_BIG_BLOCK_SIZE_DETAILS
at
org.apache.poi.poifs.filesystem.NPOIFSFileSystem.<init>(NPOIFSFileSystem.java:93)
at
org.apache.poi.poifs.filesystem.NPOIFSFileSystem.<init>(NPOIFSFileSystem.java:190)
at
org.apache.poi.poifs.filesystem.NPOIFSFileSystem.<init>(NPOIFSFileSystem.java:184)
at
org.apache.tika.parser.microsoft.POIFSContainerDetector.getTopLevelNames(POIFSContainerDetector.java:376)
at
org.apache.tika.parser.microsoft.POIFSContainerDetector.detect(POIFSContainerDetector.java:165)
at
org.apache.tika.detect.CompositeDetector.detect(CompositeDetector.java:61)
at
org.apache.tika.parser.AutoDetectParser.parse(AutoDetectParser.java:113)
at
org.apache.solr.handler.extraction.ExtractingDocumentLoader.load(ExtractingDocumentLoader.java:219)
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:1797)
at
org.apache.solr.servlet.SolrDispatchFilter.execute(SolrDispatchFilter.java:637)
at
org.apache.solr.servlet.SolrDispatchFilter.doFilter(SolrDispatchFilter.java:343)
... 16 more
Also using same type of url,txt,mp3 and pdf files are indexed successfully.
(curl
"http://localhost:8080/solr/document/update/extract?literal.id=12&commit=true";
-F"myfile=@abc.txt")
Schema.xml is:
<schema name="documents">
<fields>
<field name="id" type="string" indexed="true" stored="true" required="true"
multiValued="false"/>
<field name="author" type="string" indexed="true" stored="true"
multiValued="true"/>
<field name="comments" type="text" indexed="true" stored="true"
multiValued="false"/>
<field name="keywords" type="text" indexed="true" stored="true"
multiValued="false"/>
<field name="contents" type="text" indexed="true" stored="true"
multiValued="false"/>
<field name="title" type="text" indexed="true" stored="true"
multiValued="false"/>
<field name="revision_number" type="string" indexed="true" stored="true"
multiValued="false"/>
<field name="_version_" type="long" indexed="true" stored="true"
multiValued="false"/>
<dynamicField name="ignored_*" type="string" indexed="false" stored="true"
multiValued="true"/>
<copyfield source="id" dest="text" />
<copyfield source="author" dest="text" />
</fields>
<types>
<fieldType name="integer" class="solr.IntField" />
<fieldType name="long" class="solr.LongField" />
<fieldType name="string" class="solr.StrField" />
<fieldType name="text" class="solr.TextField" />
<fieldtype name="ignored" stored="false" indexed="false" multiValued="true"
class="solr.StrField" />
</types>
<uniqueKey>id</uniqueKey>
</schema>
Im not able to understand what kind of error this is,please help me.
--
View this message in context:
http://lucene.472066.n3.nabble.com/no-such-field-error-smaller-big-block-size-details-while-indexing-doc-files-tp4093883.html
Sent from the Solr - User mailing list archive at Nabble.com.
