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

Bugfix

Browse Source
This commit is contained in:
Andrea Cavalli 2022-01-11 22:28:42 +01:00
parent 4e5e4423ff
commit ce506f22dd
1 changed files with 3 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
src/main/java/it/cavallium/dbengine/lucene/analyzer/WordAnalyzer.java
View File

@ -7,20 +7,20 @@ import org.apache.lucene.analysis.LowerCaseFilter;
import org.apache.lucene.analysis.TokenStream; import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.Tokenizer; import org.apache.lucene.analysis.Tokenizer;
import org.apache.lucene.analysis.core.KeywordTokenizer; import org.apache.lucene.analysis.core.KeywordTokenizer;
import org.apache.lucene.analysis.en.EnglishMinimalStemFilter;
import org.apache.lucene.analysis.en.EnglishMinimalStemFilterFactory; import org.apache.lucene.analysis.en.EnglishMinimalStemFilterFactory;
import org.apache.lucene.analysis.icu.ICUCollationAttributeFactory; import org.apache.lucene.analysis.icu.ICUCollationAttributeFactory;
import org.apache.lucene.analysis.icu.ICUCollationKeyAnalyzer; import org.apache.lucene.analysis.icu.ICUCollationKeyAnalyzer;
import org.apache.lucene.analysis.icu.ICUFoldingFilter; import org.apache.lucene.analysis.icu.ICUFoldingFilter;
import org.apache.lucene.analysis.icu.ICUFoldingFilterFactory; import org.apache.lucene.analysis.icu.ICUFoldingFilterFactory;
import org.apache.lucene.analysis.icu.segmentation.ICUTokenizer; import org.apache.lucene.analysis.icu.segmentation.ICUTokenizer;
import org.apache.lucene.analysis.it.ItalianLightStemFilter;
import org.apache.lucene.analysis.it.ItalianLightStemFilterFactory; import org.apache.lucene.analysis.it.ItalianLightStemFilterFactory;
import org.apache.lucene.analysis.standard.StandardAnalyzer; import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.analysis.standard.StandardTokenizer; import org.apache.lucene.analysis.standard.StandardTokenizer;
public class WordAnalyzer extends Analyzer { public class WordAnalyzer extends Analyzer {
private static final EnglishMinimalStemFilterFactory ENGLISH_MINIMAL_STEM_FILTER_FACTORY = new EnglishMinimalStemFilterFactory();
private static final ItalianLightStemFilterFactory ITALIAN_LIGHT_STEM_FILTER_FACTORY = new ItalianLightStemFilterFactory();
private static final Collator ROOT_COLLATOR = Collator.getInstance(ULocale.ROOT); private static final Collator ROOT_COLLATOR = Collator.getInstance(ULocale.ROOT);
private static final ICUCollationAttributeFactory ROOT_ICU_ATTRIBUTE_FACTORY = new ICUCollationAttributeFactory(ROOT_COLLATOR); private static final ICUCollationAttributeFactory ROOT_ICU_ATTRIBUTE_FACTORY = new ICUCollationAttributeFactory(ROOT_COLLATOR);
@ -51,7 +51,7 @@ public class WordAnalyzer extends Analyzer {
TokenStream tokenStream = standardTokenizer; TokenStream tokenStream = standardTokenizer;
tokenStream = new LowerCaseFilter(tokenStream); tokenStream = new LowerCaseFilter(tokenStream);
if (stem) { if (stem) {
tokenStream = ITALIAN_LIGHT_STEM_FILTER_FACTORY.create(ENGLISH_MINIMAL_STEM_FILTER_FACTORY.create(tokenStream)); tokenStream = new ItalianLightStemFilter(new EnglishMinimalStemFilter(tokenStream));
} }
return new TokenStreamComponents(r -> { return new TokenStreamComponents(r -> {
standardTokenizer.setMaxTokenLength(maxTokenLength); standardTokenizer.setMaxTokenLength(maxTokenLength);