analyzer

2021-12-04 10:57:16 +01:00
parent 7555063580
commit 0a3b949968
111 changed files with 57 additions and 7 deletions
@@ -0,0 +1,45 @@
+/**
+ * 
+ */
+package de.bstly.board;
+
+import org.apache.lucene.analysis.core.LowerCaseFilterFactory;
+import org.apache.lucene.analysis.core.WhitespaceTokenizerFactory;
+import org.apache.lucene.analysis.miscellaneous.ASCIIFoldingFilterFactory;
+import org.apache.lucene.analysis.ngram.EdgeNGramFilterFactory;
+import org.apache.lucene.analysis.snowball.SnowballPorterFilterFactory;
+import org.hibernate.search.backend.lucene.analysis.LuceneAnalysisConfigurationContext;
+import org.hibernate.search.backend.lucene.analysis.LuceneAnalysisConfigurer;
+import org.springframework.context.annotation.Configuration;
+
+/**
+ * @author _bastler@bstly.de
+ *
+ */
+@Configuration
+public class LuceneConfig implements LuceneAnalysisConfigurer {
+
+	/*
+	 * @see org.hibernate.search.backend.lucene.analysis.LuceneAnalysisConfigurer#
+	 * configure(org.hibernate.search.backend.lucene.analysis.
+	 * LuceneAnalysisConfigurationContext)
+	 */
+	@Override
+	public void configure(LuceneAnalysisConfigurationContext context) {
+		context.analyzer("english").custom().tokenizer(WhitespaceTokenizerFactory.class)
+				.tokenFilter(LowerCaseFilterFactory.class)
+				.tokenFilter(SnowballPorterFilterFactory.class).param("language", "English")
+				.tokenFilter(ASCIIFoldingFilterFactory.class)
+				.tokenFilter(EdgeNGramFilterFactory.class).param("minGramSize", "1")
+				.param("maxGramSize", "10");
+
+		context.analyzer("german").custom().tokenizer(WhitespaceTokenizerFactory.class)
+				.tokenFilter(LowerCaseFilterFactory.class)
+				.tokenFilter(SnowballPorterFilterFactory.class).param("language", "German")
+				.tokenFilter(ASCIIFoldingFilterFactory.class)
+				.tokenFilter(EdgeNGramFilterFactory.class).param("minGramSize", "1")
+				.param("maxGramSize", "10");
+
+	}
+
+}