andreacavalli
/
CavalliumDBEngine
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

Implement term fields

This commit is contained in:
Andrea Cavalli 2022-05-30 01:08:46 +02:00
parent e1bd57c837
commit 6dfc10859f
3 changed files with 34 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
src/main/data-generator/lucene-query.yaml
View File

@ -69,6 +69,7 @@ versions:
# Should be at least one field!
defaultFields: String[]
pointsConfig: PointConfig[]
termFields: String[]
PointConfig:
data:
field: String

12
src/main/java/it/cavallium/dbengine/client/query/NoOpAnalyzer.java Normal file
View File

@ -0,0 +1,12 @@
package it.cavallium.dbengine.client.query;
import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.core.KeywordTokenizer;
public class NoOpAnalyzer extends Analyzer {
@Override
protected TokenStreamComponents createComponents(String fieldName) {
return new TokenStreamComponents(new KeywordTokenizer());
}
}

21
src/main/java/it/cavallium/dbengine/client/query/QueryParser.java
View File

@ -46,8 +46,20 @@ import it.cavallium.dbengine.client.query.current.data.WildcardQuery;
import it.cavallium.dbengine.lucene.RandomSortField;
import java.text.DecimalFormat;
import java.text.NumberFormat;
import java.util.Map;
import java.util.function.Function;
import java.util.stream.Collectors;
import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.LowerCaseFilter;
import org.apache.lucene.analysis.StopFilter;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.Tokenizer;
import org.apache.lucene.analysis.core.KeywordTokenizer;
import org.apache.lucene.analysis.en.EnglishPossessiveFilter;
import org.apache.lucene.analysis.en.PorterStemFilter;
import org.apache.lucene.analysis.miscellaneous.PerFieldAnalyzerWrapper;
import org.apache.lucene.analysis.miscellaneous.SetKeywordMarkerFilter;
import org.apache.lucene.analysis.standard.StandardTokenizer;
import org.apache.lucene.document.DoublePoint;
import org.apache.lucene.document.FloatPoint;
import org.apache.lucene.document.IntPoint;
@ -78,7 +90,16 @@ public class QueryParser {
switch (query.getBasicType$()) {
case StandardQuery:
var standardQuery = (it.cavallium.dbengine.client.query.current.data.StandardQuery) query;
// Fix the analyzer
Map<String, Analyzer> customAnalyzers = standardQuery
.termFields()
.stream()
.collect(Collectors.toMap(Function.identity(), term -> new NoOpAnalyzer()));
analyzer = new PerFieldAnalyzerWrapper(analyzer, customAnalyzers);
var standardQueryParser = new StandardQueryParser(analyzer);
standardQueryParser.setPointsConfigMap(standardQuery
.pointsConfig()
.stream()