MediaWiki

SBachenberg

Joined 5 January 2010

My Projects:

  1. SMW Extension:SolrStore

My Public SSH Key

How to use SolrStore as Remote Autocomplete for Semantic Forms

edit
  1. Edit your Schema.xml
    1. Add new FieldTypes needed for a good Autocompletetion 
      <fieldType name="text_suggest" class="solr.TextField" positionIncrementGap="100">
        <analyzer type="index">
            <charFilter class="solr.MappingCharFilterFactory" mapping="mapping-ISOLatin1Accent.txt"/>
            <tokenizer class="solr.StandardTokenizerFactory"/>
            <filter class="solr.WordDelimiterFilterFactory"
                generateWordParts="1"
                generateNumberParts="1"
                catenateWords="1"
                catenateNumbers="1"
                catenateAll="1"
                splitOnCaseChange="1"
                splitOnNumerics="1"
                preserveOriginal="1"
            />
            <filter class="solr.LowerCaseFilterFactory"/>
            <filter class="solr.PatternReplaceFilterFactory" pattern="([^\w\d\*æøåÆØÅ ])" replacement=" " replace="all"/>
        </analyzer>
        <analyzer type="query">
            <charFilter class="solr.MappingCharFilterFactory" mapping="mapping-ISOLatin1Accent.txt"/>
            <tokenizer class="solr.StandardTokenizerFactory"/>
            <filter class="solr.WordDelimiterFilterFactory"
                generateWordParts="0"
                generateNumberParts="0"
                catenateWords="0"
                catenateNumbers="0"
                catenateAll="0"
                splitOnCaseChange="0"
                splitOnNumerics="0"
            />
            <filter class="solr.LowerCaseFilterFactory"/>
            <filter class="solr.PatternReplaceFilterFactory" pattern="([^\w\d\*æøåÆØÅ ])" replacement=" " replace="all"/>
        </analyzer>
    </fieldType>    

    <fieldType name="text_suggest_edge" class="solr.TextField">
        <analyzer type="index">
            <charFilter class="solr.MappingCharFilterFactory" mapping="mapping-ISOLatin1Accent.txt"/>
            <tokenizer class="solr.KeywordTokenizerFactory"/>
            <filter class="solr.LowerCaseFilterFactory"/>
            <filter class="solr.PatternReplaceFilterFactory" pattern="([\.,;:-_])" replacement=" " replace="all"/>
            <filter class="solr.EdgeNGramFilterFactory" maxGramSize="30" minGramSize="1"/>
            <filter class="solr.PatternReplaceFilterFactory" pattern="([^\w\d\*æøåÆØÅ ])" replacement="" replace="all"/>
        </analyzer>
        <analyzer type="query">
            <charFilter class="solr.MappingCharFilterFactory" mapping="mapping-ISOLatin1Accent.txt"/>
            <tokenizer class="solr.KeywordTokenizerFactory"/>
            <filter class="solr.LowerCaseFilterFactory"/>
            <filter class="solr.PatternReplaceFilterFactory" pattern="([\.,;:-_])" replacement=" " replace="all"/>
            <filter class="solr.PatternReplaceFilterFactory" pattern="([^\w\d\*æøåÆØÅ ])" replacement="" replace="all"/>
            <filter class="solr.PatternReplaceFilterFactory" pattern="^(.{30})(.*)?" replacement="$1" replace="all"/>
        </analyzer>
    </fieldType>    

    <fieldType name="text_suggest_ngram" class="solr.TextField">
        <analyzer type="index">
            <charFilter class="solr.MappingCharFilterFactory" mapping="mapping-ISOLatin1Accent.txt"/>
            <tokenizer class="solr.StandardTokenizerFactory"/>
            <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
            <filter class="solr.LowerCaseFilterFactory"/>
            <filter class="solr.EdgeNGramFilterFactory" maxGramSize="20" minGramSize="1"/>
            <filter class="solr.PatternReplaceFilterFactory" pattern="([^\w\d\*æøåÆØÅ ])" replacement="" replace="all"/>
        </analyzer>
        <analyzer type="query">
            <charFilter class="solr.MappingCharFilterFactory" mapping="mapping-ISOLatin1Accent.txt"/>
            <tokenizer class="solr.StandardTokenizerFactory"/>
            <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="0"/>
            <filter class="solr.LowerCaseFilterFactory"/>
            <filter class="solr.PatternReplaceFilterFactory" pattern="([^\w\d\*æøåÆØÅ ])" replacement="" replace="all"/>
        <filter class="solr.PatternReplaceFilterFactory" pattern="^(.{20})(.*)?" replacement="$1" replace="all"/>
        </analyzer>
    </fieldType>     

    <fieldType name="alphaNumericSort" 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 |the |les |la |le |l'|de la |du |des )" replacement="" replace="all" />
            <filter class="solr.PatternReplaceFilterFactory" pattern="([^a-z0-9])" replacement="" replace="all"    />
        </analyzer>
    </fieldType>    

    <fieldType class="solr.TextField" name="text_auto">
     <analyzer>
      <tokenizer class="solr.KeywordTokenizerFactory"/>
      <filter class="solr.LowerCaseFilterFactory"/>
     </analyzer>
    </fieldType>
    2. Add the Fields needed 
      <field name="person_suggest" type="text_suggest" indexed="true" stored="true"/>
<field name="person_suggest_edge" type="text_suggest_edge" indexed="true" stored="true"/>
<field name="person_suggest_ngram" type="text_suggest_ngram" indexed="true" stored="true"/>
<field name="Person_s" type="text_auto" indexed="true" stored="true" />

      The Field we use in our Wiki is called "Person", so the automatically generated field is called "Person_s", because it's a string. We need do define it on our selfs because the auto generated field is multivalued and this doesn't work with multivalued fields!

    3. Create CopyFields for your new defined Fields 
      <copyField source="Person_s" dest="person_suggest" />
<copyField source="Person_s" dest="person_suggest_edge" />
<copyField source="Person_s" dest="person_suggest_ngram" />
  2. Edit your solrconfig.xml 
    <requestHandler name="/suggestPerson" class="solr.SearchHandler">
        <lst name="defaults">
            <str name="echoParams">explicit</str>
            <str name="defType">edismax</str>
            <str name="rows">10</str>
            <str name="fl">Person_s,dbkey,score</str>
            <str name="qf">person_suggest^15 person_suggest_ngram^25.0</str>
            <str name="pf">person_suggest_edge^25.0</str>
            <str name="sort">score desc,dbkey asc</str>
        </lst>
    </requestHandler>
  3. Restart your Solr and start a re-index
  4. Edit your Semantic Forms Extension
    1. go to <your-wiki>/extensions/SemanticForms/includes/
    2. Edit SF_Utils.php line 615 before: 
      $return_values = array();
foreach ( $data->sfautocomplete as $val ) {
       $return_values[] = (array)$val;
}
return $return_values;

      after: 

      $return_values = array();
if ( strpos($external_url_alias, 'solr') === false) {
       foreach ( $data->sfautocomplete as $val ) {
            $return_values[] = (array)$val;
       }
} else {        
       foreach ( $data->response->docs as $val ) {
            $return_values[] = array( "title" => $val->{'Person_s'} );
       }
}
return $return_values;
  5. Edit your LocalSettings.php 
    $sfgAutocompletionURLs['solrPerson'] = "$wgSolrUrl/suggestPerson?q=<substr>&wt=json&indent=true&omitHeader=true";
  6. Edit your Form 
    {{{field|Person|input type=textarea with autocomplete|autogrow|values from url=solrPerson}}}
Retrieved from "https://www.mediawiki.org/w/index.php?title=User:SBachenberg&oldid=914779"