You are viewing a plain text version of this content. The canonical link for it is here.
Posted to user@nutch.apache.org by gsamsa <ma...@gmail.com> on 2014/09/24 22:29:20 UTC
Nutch 1.9 with Solr 3.6.2 - Solr does not show any data
Hello guys,
I have installed apache nutch 1.9 and solr 3.6.2. Nutch is running
correctly, however, I have some problems with solr. When opening:
/http://127.0.0.1:8983/solr//
I see the following:
<http://lucene.472066.n3.nabble.com/file/n4160993/solr.jpg>
When clicking solr admin nothing redirects me...
My schema.xml looks like that:
/<?xml version="1.0" encoding="UTF-8" ?>
<schema name="nutch" version="1.5">
<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"
required="true"/>
<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"/>
<field name="host" type="string" stored="false" indexed="true"/>
<field name="url" type="url" stored="true" indexed="true"/>
<field name="content" type="text" stored="false" indexed="true"/>
<field name="title" type="text" stored="true" indexed="true"/>
<field name="cache" type="string" stored="true" indexed="false"/>
<field name="tstamp" type="date" stored="true" indexed="false"/>
<field name="anchor" type="string" stored="true" indexed="true"
multiValued="true"/>
<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"/>
<field name="lang" type="string" stored="true" indexed="true"/>
<field name="subcollection" type="string" stored="true"
indexed="true" multiValued="true"/>
<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"/>
<field name="cc" type="string" stored="true" indexed="true"
multiValued="true"/>
<field name="tld" type="string" stored="false" indexed="false"/>
<field name="_version_" type="long" stored="true" indexed="true"/>
</fields>
<uniqueKey>id</uniqueKey>
<defaultSearchField>content</defaultSearchField>
<solrQueryParser defaultOperator="OR"/>
</schema>
/
Furthermore, I have set solr up like from the apache wiki
<http://wiki.apache.org/nutch/NutchTutorial#A6._Integrate_Solr_with_Nutch>
:
/mv ${APACHE_SOLR_HOME}/example/solr/conf/schema.xml
${APACHE_SOLR_HOME}/example/solr/conf/schema.xml.org
cp ${NUTCH_RUNTIME_HOME}/conf/schema.xml
${APACHE_SOLR_HOME}/example/solr/conf/
vi ${APACHE_SOLR_HOME}/example/solr/conf/schema.xml
Copy exactly in 351 line: <field name="_version_" type="long" indexed="true"
stored="true"/>
restart Solr with the command “java -jar start.jar” under
${APACHE_SOLR_HOME}/example/
Any recommendations what I am doing wrong?
Would it be better to use the latest *solr 4.10*? Any good tutorials how to
configure this version?
I really appreciate your answers!
--
View this message in context: http://lucene.472066.n3.nabble.com/Nutch-1-9-with-Solr-3-6-2-Solr-does-not-show-any-data-tp4160993.html
Sent from the Nutch - User mailing list archive at Nabble.com.
Re: Nutch 1.9 with Solr 3.6.2 - Solr does not show any data
Posted by Talat Uyarer <ta...@uyarer.com>.
Hi,
I think you fix this problem. Am I wrong ?
Talat
On Sep 28, 2014 1:28 AM, "gsamsa" <ma...@gmail.com> wrote:
> Hello guys,
>
> I have installed apache nutch 1.9 and solr 3.6.2. Nutch is running
> correctly, however, I have some problems with solr. When opening:
>
> /http://127.0.0.1:8983/solr//
>
> I see the following:
> <http://lucene.472066.n3.nabble.com/file/n4160993/solr.jpg>
>
> When clicking solr admin nothing redirects me...
>
> My schema.xml looks like that:
>
> /<?xml version="1.0" encoding="UTF-8" ?>
> <schema name="nutch" version="1.5">
> <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"
> required="true"/>
>
>
> <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"/>
>
>
> <field name="host" type="string" stored="false" indexed="true"/>
> <field name="url" type="url" stored="true" indexed="true"/>
> <field name="content" type="text" stored="false" indexed="true"/>
> <field name="title" type="text" stored="true" indexed="true"/>
> <field name="cache" type="string" stored="true" indexed="false"/>
> <field name="tstamp" type="date" stored="true" indexed="false"/>
>
>
> <field name="anchor" type="string" stored="true" indexed="true"
> multiValued="true"/>
>
>
> <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"/>
>
>
> <field name="lang" type="string" stored="true" indexed="true"/>
>
>
> <field name="subcollection" type="string" stored="true"
> indexed="true" multiValued="true"/>
>
>
> <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"/>
>
>
> <field name="cc" type="string" stored="true" indexed="true"
> multiValued="true"/>
>
>
> <field name="tld" type="string" stored="false" indexed="false"/>
>
> <field name="_version_" type="long" stored="true" indexed="true"/>
> </fields>
> <uniqueKey>id</uniqueKey>
> <defaultSearchField>content</defaultSearchField>
> <solrQueryParser defaultOperator="OR"/>
> </schema>
> /
>
> Furthermore, I have set solr up like from the apache wiki
> <http://wiki.apache.org/nutch/NutchTutorial#A6._Integrate_Solr_with_Nutch>
> :
>
> /mv ${APACHE_SOLR_HOME}/example/solr/conf/schema.xml
> ${APACHE_SOLR_HOME}/example/solr/conf/schema.xml.org
>
> cp ${NUTCH_RUNTIME_HOME}/conf/schema.xml
> ${APACHE_SOLR_HOME}/example/solr/conf/
> vi ${APACHE_SOLR_HOME}/example/solr/conf/schema.xml
>
> Copy exactly in 351 line: <field name="_version_" type="long"
> indexed="true"
> stored="true"/>
>
> restart Solr with the command “java -jar start.jar” under
> ${APACHE_SOLR_HOME}/example/
>
>
> Any recommendations what I am doing wrong?
>
> Would it be better to use the latest *solr 4.10*? Any good tutorials how to
> configure this version?
>
> I really appreciate your answers!
>
>
>
>
>
> --
> View this message in context:
> http://lucene.472066.n3.nabble.com/Nutch-1-9-with-Solr-3-6-2-Solr-does-not-show-any-data-tp4160993.html
> Sent from the Nutch - User mailing list archive at Nabble.com.
>