Hi Alex,
Thank you for your response.
It worked. I am very happy for the results. I reports the steps below. The
purpose is to create a dynamic field to simplify field definition in
managed-schema file and to simplify field rank in solrconfig.xml file.
STEPS:
1. file creation of db-data-config.xml
<dataConfig>
<dataSource name ="data_source_?????"
type="JdbcDataSource"
driver="com.mysql.jdbc.Driver"
url="jdbc:mysql://machineName:3306/databaseName?zeroDateTimeBehavior=convertToNull"
user="?????"
password="?????" />
<document name="db-fulltext-index">
<entity name="pdb_entry" pk="pdb_id_stem"
transformer="my.solr.transformer.FieldTransformer"
query=" * from pdb_entry where status_code = 'REL' " >
<entity name="citation" onError="continue"
transformer="my.solr.transformer.FieldTransformer"
query="select title from citation where
Structure_ID='${pdb_entry.pdb_id_stem}' and id = 'primary' " >
</entity>
<entity name="citation_author" onError="continue"
transformer="my.solr.transformer.FieldTransformer"
query="select name from citation_author where
Structure_ID='${pdb_entry.pdb_id_stem}' and citation_id = 'primary' " >
</entity>
</entity>
</document>
</dataConfig>
2. Modification of solrconfig.xml file: notice of the ranking
<lib dir="${solr.install.dir:../../../..}/dist/"
regex="solr-dataimporthandler-\d.*\.jar" />
<lib dir="${solr.install.dir:../../../..}/dist/"
regex="mysql-connector-java-5.0.7-bin.jar" />
<lib dir="${solr.install.dir:../../../..}/dist/"
regex="solr-rcsb-plugin.jar" />
<requestHandler name="/dataimport"
class="org.apache.solr.handler.dataimport.DataImportHandler">
<lst name="defaults">
<str name="config">db-data-config.xml</str>
</lst>
</requestHandler>
<requestHandler name="/search" class="solr.SearchHandler">
<lst name="defaults">
<str name="indent">true</str>
<str name="echoParams">explicit</str>
<str name="defType">edismax</str>
<str name="qf">pdb_id_stem^20.0</str>
<str name="qf">title_stem^20.0</str>
<str name="qf">keywords_stem^10.0</str>
<str name="qf">*_stem^0.3</str>
<str name="qf">rest_fields_stem ^0.3</str>
<str name="mm">7</str>
<int name="rows">1000</int>
<str name="df">text</str>
</lst>
</requestHandler>
3. Modification of managed-schema file: Notice of change <uniqueKey>,
creation of a dynamic field "*_stem",,,
<field name="pdb_id_stem" type="string" indexed="true" stored="true"
required="true" multiValued="false" />
<field name="rest_fields_stem" type="pdb_text_stem" indexed="true"
stored="true" multiValued="true"/>
<copyField source="*_stem" dest="rest_fields_stem"/>
<dynamicField name="*_stem" type="pdb_text_stem" indexed="true"
stored="true"/>
<fieldtype name="pdb_text_stem" class="solr.TextField"
positionIncrementGap="100">
<analyzer type="index">
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt"
ignoreCase="true" expand="true" />
<filter class="solr.StopFilterFactory" ignoreCase="true"/>
<filter class="solr.WordDelimiterFilterFactory" generateWordParts="1"
generateNumberParts="1" catenateWords="0" catenateNumbers="0"
catenateAll="0"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
<filter class="solr.PorterStemFilterFactory"/>
</analyzer>
<analyzer type="query">
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true"/>
<filter class="solr.WordDelimiterFilterFactory" generateWordParts="1"
generateNumberParts="1" catenateWords="0" catenateNumbers="0"
catenateAll="0"/>
<filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt"
ignoreCase="true" expand="true" />
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
<filter class="solr.PorterStemFilterFactory"/>
</analyzer>
</fieldtype>
<uniqueKey>pdb_id_stem</uniqueKey>
4. creation of a customer transformer:
package my.solr.transformer;
import java.util.ArrayList;
import java.util.List;
import java.util.Map;
import java.util.Set;
import org.apache.solr.handler.dataimport.Context;
import org.apache.solr.handler.dataimport.DataImporter;
import org.apache.solr.handler.dataimport.Transformer;
public class FieldTransformer extends Transformer {
public Map<String, Object> transformRow(Map<String, Object> row, Context
context) {
List<Map<String, String>> fields = ((Context)
context).getAllEntityFields();
int rowSize = row.size();
//System.out.println("row size to start = " + rowSize);
//Converting HashMap keys into ArrayList
Set<String> keySet = row.keySet();
List<String> keyList = new ArrayList<String>(keySet);
for (int i = 0; i < rowSize; i++) {
String columnName = keyList.get(i);
Object value = row.get(columnName);
if (value != null &&
!value.toString().trim().equals("")) {
row.put(columnName + "_stem", value.toString().trim());
//System.out.println("value = " +
value.toString().trim());
//System.out.println("row.size = " + row.size());
};
row.remove(columnName);
}
System.out.println("row size ended = " + row.size());
return row;
}
}
5. NOTE: when using customer transformer, need to add the following two jar
fiels to this destination:
cp solr-dataimporthandler-6.1.0.jar
/opt/solr-6.1.0/server/solr-webapp/webapp/WEB-INF/lib
cp solr-dataimporthandler-extras-6.1.0.jar
/opt/solr-6.1.0/server/solr-webapp/webapp/WEB-INF/lib
6. screen shot:
<http://lucene.472066.n3.nabble.com/file/n4293261/Screenshot-20.png>
--
View this message in context:
http://lucene.472066.n3.nabble.com/help-with-DIH-transformer-to-add-a-suffix-to-column-names-tp4292448p4293261.html
Sent from the Solr - User mailing list archive at Nabble.com.
