USING Solr 5.1.0

This is the schema file

<?xml version="1.0" encoding="UTF-8" ?>


<schema name="example" version="1.5">
  
   <field name="_version_" type="long" indexed="true" stored="true"/>
 
   <field name="_root_" type="string" indexed="true" stored="false"/>

   <field name="id" type="string" indexed="true" stored="true"
required="false" multiValued="false" />
   <field name="filepath" type="string" indexed="true" stored ="true"
required="false" multiValued="false" />  
   <field name="title" type="string" indexed="true" stored ="true"
required="false" multiValued="false" />  
   <field name="author" type="string" indexed="true" stored ="true"
required="false" multiValued="false" />  
   <field name="text" type="string" indexed="true" stored ="false"
required="false" multiValued="true" />  
   <field name="key" type="string" indexed="true" stored ="false"
required="false" multiValued="false" /> 

 
   
   <dynamicField name="*_name"  type="text_general"   multiValued="false"
indexed="true"  stored="true" />

   <dynamicField name="*_i"  type="int"    indexed="true"  stored="true"/>
   <dynamicField name="*_is" type="int"    indexed="true"  stored="true" 
multiValued="true"/>
   <dynamicField name="*_s"  type="string"  indexed="true"  stored="true" />
   <dynamicField name="*_ss" type="string"  indexed="true"  stored="true"
multiValued="true"/>
   <dynamicField name="*_l"  type="long"   indexed="true"  stored="true"/>
   <dynamicField name="*_ls" type="long"   indexed="true"  stored="true" 
multiValued="true"/>
   <dynamicField name="*_t"  type="text_general"    indexed="true" 
stored="true"/>
   <dynamicField name="*_txt" type="text_general"   indexed="true" 
stored="true" multiValued="true"/>
   <dynamicField name="*_en"  type="text_en"    indexed="true" 
stored="true" multiValued="true"/>
   <dynamicField name="*_b"  type="boolean" indexed="true" stored="true"/>
   <dynamicField name="*_bs" type="boolean" indexed="true" stored="true" 
multiValued="true"/>
   <dynamicField name="*_f"  type="float"  indexed="true"  stored="true"/>
   <dynamicField name="*_fs" type="float"  indexed="true"  stored="true" 
multiValued="true"/>
   <dynamicField name="*_d"  type="double" indexed="true"  stored="true"/>
   <dynamicField name="*_ds" type="double" indexed="true"  stored="true" 
multiValued="true"/>


   <dynamicField name="*_coordinate"  type="tdouble" indexed="true" 
stored="false" />

   <dynamicField name="*_dt"  type="date"    indexed="true"  stored="true"/>
   <dynamicField name="*_dts" type="date"    indexed="true"  stored="true"
multiValued="true"/>
   <dynamicField name="*_p"  type="location" indexed="true" stored="true"/>

 
   <dynamicField name="*_ti" type="tint"    indexed="true"  stored="true"/>
   <dynamicField name="*_tl" type="tlong"   indexed="true"  stored="true"/>
   <dynamicField name="*_tf" type="tfloat"  indexed="true"  stored="true"/>
   <dynamicField name="*_td" type="tdouble" indexed="true"  stored="true"/>
   <dynamicField name="*_tdt" type="tdate"  indexed="true"  stored="true"/>

   <dynamicField name="*_c"   type="currency" indexed="true" 
stored="true"/>

   <dynamicField name="ignored_*" type="ignored" multiValued="true"/>
   <dynamicField name="attr_*" type="text_general" indexed="true"
stored="true" multiValued="true"/>

   <dynamicField name="random_*" type="random" />



 <uniqueKey>filepath</uniqueKey>


    <fieldType name="string" class="solr.StrField" sortMissingLast="true" />


    <fieldType name="boolean" class="solr.BoolField"
sortMissingLast="true"/>

    <fieldType name="int" class="solr.TrieIntField" precisionStep="0"
positionIncrementGap="0"/>
    <fieldType name="float" class="solr.TrieFloatField" precisionStep="0"
positionIncrementGap="0"/>
    <fieldType name="long" class="solr.TrieLongField" precisionStep="0"
positionIncrementGap="0"/>
    <fieldType name="double" class="solr.TrieDoubleField" precisionStep="0"
positionIncrementGap="0"/>

    <fieldType name="tint" class="solr.TrieIntField" precisionStep="8"
positionIncrementGap="0"/>
    <fieldType name="tfloat" class="solr.TrieFloatField" precisionStep="8"
positionIncrementGap="0"/>
    <fieldType name="tlong" class="solr.TrieLongField" precisionStep="8"
positionIncrementGap="0"/>
    <fieldType name="tdouble" class="solr.TrieDoubleField" precisionStep="8"
positionIncrementGap="0"/>

 
    <fieldType name="date" class="solr.TrieDateField" precisionStep="0"
positionIncrementGap="0"/>

  
    <fieldType name="tdate" class="solr.TrieDateField" precisionStep="6"
positionIncrementGap="0"/>


    <fieldType name="binary" class="solr.BinaryField"/>

 
    <fieldType name="random" class="solr.RandomSortField" indexed="true" />


    <fieldType name="text_ws" class="solr.TextField"
positionIncrementGap="100">
      <analyzer>
        <tokenizer class="solr.WhitespaceTokenizerFactory"/>
      </analyzer>
    </fieldType>

    <fieldType name="text_general" class="solr.TextField"
positionIncrementGap="100">
      <analyzer type="index">
        <tokenizer class="solr.StandardTokenizerFactory"/>
        <filter class="solr.StopFilterFactory" ignoreCase="true"
words="stopwords.txt" />
        
        <filter class="solr.LowerCaseFilterFactory"/>
      </analyzer>
      <analyzer type="query">
        <tokenizer class="solr.StandardTokenizerFactory"/>
        <filter class="solr.StopFilterFactory" ignoreCase="true"
words="stopwords.txt" />
        <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt"
ignoreCase="true" expand="true"/>
        <filter class="solr.LowerCaseFilterFactory"/>
      </analyzer>
    </fieldType>

    <fieldType name="text_en" class="solr.TextField"
positionIncrementGap="100">
      <analyzer type="index">
        <tokenizer class="solr.StandardTokenizerFactory"/>
    
 
        <filter class="solr.StopFilterFactory"
                ignoreCase="true"
                words="lang/stopwords_en.txt"
                />
        <filter class="solr.LowerCaseFilterFactory"/>
    <filter class="solr.EnglishPossessiveFilterFactory"/>
        <filter class="solr.KeywordMarkerFilterFactory"
protected="protwords.txt"/>
    
        <filter class="solr.PorterStemFilterFactory"/>
      </analyzer>
      <analyzer type="query">
        <tokenizer class="solr.StandardTokenizerFactory"/>
        <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt"
ignoreCase="true" expand="true"/>
        <filter class="solr.StopFilterFactory"
                ignoreCase="true"
                words="lang/stopwords_en.txt"
                />
        <filter class="solr.LowerCaseFilterFactory"/>
    <filter class="solr.EnglishPossessiveFilterFactory"/>
        <filter class="solr.KeywordMarkerFilterFactory"
protected="protwords.txt"/>
    
        <filter class="solr.PorterStemFilterFactory"/>
      </analyzer>
    </fieldType>

  
    <fieldType name="text_en_splitting" class="solr.TextField"
positionIncrementGap="100" autoGeneratePhraseQueries="true">
      <analyzer type="index">
        <tokenizer class="solr.WhitespaceTokenizerFactory"/>
  
        <filter class="solr.StopFilterFactory"
                ignoreCase="true"
                words="lang/stopwords_en.txt"
                />
        <filter class="solr.WordDelimiterFilterFactory"
generateWordParts="1" generateNumberParts="1" catenateWords="1"
catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
        <filter class="solr.LowerCaseFilterFactory"/>
        <filter class="solr.KeywordMarkerFilterFactory"
protected="protwords.txt"/>
        <filter class="solr.PorterStemFilterFactory"/>
      </analyzer>
      <analyzer type="query">
        <tokenizer class="solr.WhitespaceTokenizerFactory"/>
        <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt"
ignoreCase="true" expand="true"/>
        <filter class="solr.StopFilterFactory"
                ignoreCase="true"
                words="lang/stopwords_en.txt"
                />
        <filter class="solr.WordDelimiterFilterFactory"
generateWordParts="1" generateNumberParts="1" catenateWords="0"
catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
        <filter class="solr.LowerCaseFilterFactory"/>
        <filter class="solr.KeywordMarkerFilterFactory"
protected="protwords.txt"/>
        <filter class="solr.PorterStemFilterFactory"/>
      </analyzer>
    </fieldType>

   
    <fieldType name="text_en_splitting_tight" class="solr.TextField"
positionIncrementGap="100" autoGeneratePhraseQueries="true">
      <analyzer>
        <tokenizer class="solr.WhitespaceTokenizerFactory"/>
        <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt"
ignoreCase="true" expand="false"/>
        <filter class="solr.StopFilterFactory" ignoreCase="true"
words="lang/stopwords_en.txt"/>
        <filter class="solr.WordDelimiterFilterFactory"
generateWordParts="0" generateNumberParts="0" catenateWords="1"
catenateNumbers="1" catenateAll="0"/>
        <filter class="solr.LowerCaseFilterFactory"/>
        <filter class="solr.KeywordMarkerFilterFactory"
protected="protwords.txt"/>
        <filter class="solr.EnglishMinimalStemFilterFactory"/>
        
        <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
      </analyzer>
    </fieldType>

   
    <fieldType name="text_general_rev" class="solr.TextField"
positionIncrementGap="100">
      <analyzer type="index">
        <tokenizer class="solr.StandardTokenizerFactory"/>
        <filter class="solr.StopFilterFactory" ignoreCase="true"
words="stopwords.txt" />
        <filter class="solr.LowerCaseFilterFactory"/>
        <filter class="solr.ReversedWildcardFilterFactory"
withOriginal="true"
           maxPosAsterisk="3" maxPosQuestion="2"
maxFractionAsterisk="0.33"/>
      </analyzer>
      <analyzer type="query">
        <tokenizer class="solr.StandardTokenizerFactory"/>
        <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt"
ignoreCase="true" expand="true"/>
        <filter class="solr.StopFilterFactory" ignoreCase="true"
words="stopwords.txt" />
        <filter class="solr.LowerCaseFilterFactory"/>
      </analyzer>
    </fieldType>

   
    <fieldType name="alphaOnlySort" class="solr.TextField"
sortMissingLast="true" omitNorms="true">
      <analyzer>
      
        <tokenizer class="solr.KeywordTokenizerFactory"/>
      
        <filter class="solr.LowerCaseFilterFactory" />
      
        <filter class="solr.TrimFilterFactory" />
       
        <filter class="solr.PatternReplaceFilterFactory"
                pattern="([^a-z])" replacement="" replace="all"
        />
      </analyzer>
    </fieldType>


    <fieldType name="lowercase" class="solr.TextField"
positionIncrementGap="100">
      <analyzer>
        <tokenizer class="solr.KeywordTokenizerFactory"/>
        <filter class="solr.LowerCaseFilterFactory" />
      </analyzer>
    </fieldType>

  
    <fieldType name="ignored" stored="false" indexed="false"
multiValued="true" class="solr.StrField" />

   
    <fieldType name="point" class="solr.PointType" dimension="2"
subFieldSuffix="_d"/>

  
    <fieldType name="location" class="solr.LatLonType"
subFieldSuffix="_coordinate"/>

   
    <fieldType name="location_rpt"
class="solr.SpatialRecursivePrefixTreeFieldType"
        geo="true" distErrPct="0.025" maxDistErr="0.001"
distanceUnits="kilometers" />

   
    <fieldType name="bbox" class="solr.BBoxField"
               geo="true" distanceUnits="kilometers"
numberType="_bbox_coord" />
    <fieldType name="_bbox_coord" class="solr.TrieDoubleField"
precisionStep="8" docValues="true" stored="false"/>

  
    <fieldType name="currency" class="solr.CurrencyField" precisionStep="8"
defaultCurrency="USD" currencyConfig="currency.xml" />

</schema>

ENTIRE STACK TRACE

/home/paden/Documents/LWP_Files/BIGDATA/5974412.pdf
org.apache.solr.client.solrj.impl.HttpSolrClient$RemoteSolrException: Error
from server at http://localhost:8983/solr/Testcore3: Exception writing
document id /home/paden/Documents/LWP_Files/BIGDATA/5974412.pdf to the
index; possible analysis error.
    at
org.apache.solr.client.solrj.impl.HttpSolrClient.executeMethod(HttpSolrClient.java:556)
    at
org.apache.solr.client.solrj.impl.HttpSolrClient.request(HttpSolrClient.java:233)
    at
org.apache.solr.client.solrj.impl.HttpSolrClient.request(HttpSolrClient.java:225)
    at
org.apache.solr.client.solrj.SolrRequest.process(SolrRequest.java:135)
    at org.apache.solr.client.solrj.SolrClient.add(SolrClient.java:174)
    at org.apache.solr.client.solrj.SolrClient.add(SolrClient.java:139)
    at org.apache.solr.client.solrj.SolrClient.add(SolrClient.java:153)
    at TikaSqlIndexer.Index(TikaSqlIndexer.java:238)
    at TikaSqlIndexer.main(TikaSqlIndexer.java:85)



--
View this message in context: 
http://lucene.472066.n3.nabble.com/Error-when-submitting-PDF-to-Solr-w-text-fields-using-SolrJ-tp4212704p4212736.html
Sent from the Solr - User mailing list archive at Nabble.com.

Reply via email to