org.apache.solr.handler.extraction
Class ExtractingRequestHandler

java.lang.Object
  org.apache.solr.handler.RequestHandlerBase
      org.apache.solr.handler.ContentStreamHandlerBase
          org.apache.solr.handler.extraction.ExtractingRequestHandler

All Implemented Interfaces:

org.apache.solr.core.SolrInfoMBean, org.apache.solr.request.SolrRequestHandler, org.apache.solr.util.plugin.SolrCoreAware

public class ExtractingRequestHandler
extends org.apache.solr.handler.ContentStreamHandlerBase
implements org.apache.solr.util.plugin.SolrCoreAware

Handler for rich documents like PDF or Word or any other file format that Tika handles that need the text to be extracted first from the document.

Nested Class Summary

Nested classes/interfaces inherited from interface org.apache.solr.core.SolrInfoMBean

org.apache.solr.core.SolrInfoMBean.Category

Field Summary

protected org.apache.tika.config.TikaConfig	config
static String	CONFIG_LOCATION
static String	DATE_FORMATS
protected Collection<String>	dateFormats
protected SolrContentHandlerFactory	factory

Fields inherited from class org.apache.solr.handler.RequestHandlerBase

appends, defaults, httpCaching, initArgs, invariants

Constructor Summary

ExtractingRequestHandler()

Method Summary

protected SolrContentHandlerFactory	createFactory()
String	getDescription()
String	getSource()
String	getSourceId()
String	getVersion()
void	inform(org.apache.solr.core.SolrCore core)
void	init(org.apache.solr.common.util.NamedList args)
protected org.apache.solr.handler.ContentStreamLoader	newLoader(org.apache.solr.request.SolrQueryRequest req, org.apache.solr.update.processor.UpdateRequestProcessor processor)

Methods inherited from class org.apache.solr.handler.ContentStreamHandlerBase

handleRequestBody

Methods inherited from class org.apache.solr.handler.RequestHandlerBase

getCategory, getDocs, getInitArgs, getName, getStatistics, handleRequest

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Field Detail

CONFIG_LOCATION

public static final String CONFIG_LOCATION

See Also:

Constant Field Values

DATE_FORMATS

public static final String DATE_FORMATS

See Also:

Constant Field Values

config

protected org.apache.tika.config.TikaConfig config

dateFormats

protected Collection<String> dateFormats

factory

protected SolrContentHandlerFactory factory

Constructor Detail

ExtractingRequestHandler

public ExtractingRequestHandler()

Method Detail

init

public void init(org.apache.solr.common.util.NamedList args)

Specified by:

init in interface org.apache.solr.request.SolrRequestHandler

Overrides:

init in class org.apache.solr.handler.RequestHandlerBase

inform

public void inform(org.apache.solr.core.SolrCore core)

Specified by:

inform in interface org.apache.solr.util.plugin.SolrCoreAware

createFactory

protected SolrContentHandlerFactory createFactory()

newLoader

protected org.apache.solr.handler.ContentStreamLoader newLoader(org.apache.solr.request.SolrQueryRequest req,
                                                                org.apache.solr.update.processor.UpdateRequestProcessor processor)

Specified by:

newLoader in class org.apache.solr.handler.ContentStreamHandlerBase

getDescription

public String getDescription()

Specified by:

getDescription in interface org.apache.solr.core.SolrInfoMBean

Specified by:

getDescription in class org.apache.solr.handler.RequestHandlerBase

getVersion

public String getVersion()

Specified by:

getVersion in interface org.apache.solr.core.SolrInfoMBean

Specified by:

getVersion in class org.apache.solr.handler.RequestHandlerBase

getSourceId

public String getSourceId()

Specified by:

getSourceId in interface org.apache.solr.core.SolrInfoMBean

Specified by:

getSourceId in class org.apache.solr.handler.RequestHandlerBase

getSource

public String getSource()

Specified by:

getSource in interface org.apache.solr.core.SolrInfoMBean

Specified by:

getSource in class org.apache.solr.handler.RequestHandlerBase