Hi - You should stick to Nutch' schema.xml and not manually add a text or body
field that aren't going to be populated anyway. Nutch sends data, by default,
to the content field.
-----Original message-----
> From:Rafał Kuć <r....@solr.pl>
> Sent: Tue 09-Oct-2012 14:32
> To: solr-user@lucene.apache.org
> Subject: Re: Search in body
>
> Hello!
>
> I assume you've added the body field, but you don't populate it. As
> far as I remember Nutch don't fill the body field by default. What
> you are expecting to have in the body field ?
>
> --
> Regards,
> Rafał Kuć
> Sematext :: http://sematext.com/ :: Solr - Lucene - Nutch - ElasticSearch
>
> > I've just indexed again, and no luck.
>
> > Below is my schema
>
> > <schema name="nutch" version="1.4">
> > <types>
> > <fieldType name="string" class="solr.StrField"
> > sortMissingLast="true"
> > omitNorms="true"/>
> > <fieldType name="long" class="solr.TrieLongField" precisionStep="0"
> > omitNorms="true" positionIncrementGap="0"/>
> > <fieldType name="float" class="solr.TrieFloatField"
> > precisionStep="0"
> > omitNorms="true" positionIncrementGap="0"/>
> > <fieldType name="date" class="solr.TrieDateField" precisionStep="0"
> > omitNorms="true" positionIncrementGap="0"/>
>
> > <fieldType name="text" class="solr.TextField"
> > positionIncrementGap="100">
> > <analyzer>
> > <tokenizer class="solr.WhitespaceTokenizerFactory"/>
> > <filter class="solr.StopFilterFactory"
> > ignoreCase="true" words="stopwords.txt"/>
> > <filter class="solr.WordDelimiterFilterFactory"
> > generateWordParts="1" generateNumberParts="1"
> > catenateWords="1" catenateNumbers="1" catenateAll="0"
> > splitOnCaseChange="1"/>
> > <filter class="solr.LowerCaseFilterFactory"/>
> > <filter class="solr.EnglishPorterFilterFactory"
> > protected="protwords.txt"/>
> > <filter
> > class="solr.RemoveDuplicatesTokenFilterFactory"/>
> > </analyzer>
> > </fieldType>
> > <fieldType name="url" class="solr.TextField"
> > positionIncrementGap="100">
> > <analyzer>
> > <tokenizer class="solr.StandardTokenizerFactory"/>
> > <filter class="solr.LowerCaseFilterFactory"/>
> > <filter class="solr.WordDelimiterFilterFactory"
> > generateWordParts="1" generateNumberParts="1"/>
> > </analyzer>
> > </fieldType>
> > </types>
> > <fields>
> > <field name="id" type="string" stored="true" indexed="true"/>
>
> > <!-- core fields -->
> > <field name="segment" type="string" stored="true" indexed="false"/>
> > <field name="digest" type="string" stored="true" indexed="false"/>
> > <field name="boost" type="float" stored="true" indexed="false"/>
>
> > <!-- fields for index-basic plugin -->
> > <field name="host" type="string" stored="false" indexed="true"/>
> > <field name="url" type="url" stored="true" indexed="true"
> > required="true"/>
> > <field name="content" type="text" stored="false" indexed="true"/>
> > <field name="title" type="text" stored="true" indexed="true"/>
> > <field name="text" type="text" stored="true" indexed="true"/>
> > <field name="body" type="text" stored="true" indexed="true"/>
> > <field name="cache" type="string" stored="true" indexed="false"/>
> > <field name="tstamp" type="date" stored="true" indexed="false"/>
>
> > <!-- fields for index-anchor plugin -->
> > <field name="anchor" type="string" stored="true" indexed="true"
> > multiValued="true"/>
>
> > <!-- fields for index-more plugin -->
> > <field name="type" type="string" stored="true" indexed="true"
> > multiValued="true"/>
> > <field name="contentLength" type="long" stored="true"
> > indexed="false"/>
> > <field name="lastModified" type="date" stored="true"
> > indexed="false"/>
> > <field name="date" type="date" stored="true" indexed="true"/>
>
> > <!-- fields for languageidentifier plugin -->
> > <field name="lang" type="string" stored="true" indexed="true"/>
>
> > <!-- fields for subcollection plugin -->
> > <field name="subcollection" type="string" stored="true"
> > indexed="true" multiValued="true"/>
>
> > <!-- fields for feed plugin (tag is also used by
> > microformats-reltag)-->
> > <field name="author" type="string" stored="true" indexed="true"/>
> > <field name="tag" type="string" stored="true" indexed="true"
> multiValued="true"/>>
> > <field name="feed" type="string" stored="true" indexed="true"/>
> > <field name="publishedDate" type="date" stored="true"
> > indexed="true"/>
> > <field name="updatedDate" type="date" stored="true"
> > indexed="true"/>
>
> > <!-- fields for creativecommons plugin -->
> > <field name="cc" type="string" stored="true" indexed="true"
> > multiValued="true"/>
> > </fields>
> > <uniqueKey>id</uniqueKey>
> > <defaultSearchField>content</defaultSearchField>
> > <solrQueryParser defaultOperator="OR"/>
> > </schema>
>
> > I don't know how to show you example data, my URL is
> > http://www.sabanciuniv.edu
>
> > Regards,
>
> > On 10/09/2012 02:58 PM, Rafał Kuć wrote:
> >> Hello!
> >>
> >> After altering your schema.xml have you indexed your documents again ?
> >>
> >> It would be nice to see how you schema.xml looks like and example of
> >> the data, because otherwise we can only guess.
> >>
>
>
