Blog » Apache Lucene

.. ist eine Search-Engine Das folgende Code-Beispiel arbeitet mit Apache Lucene 8.4.1.

import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.core.LowerCaseFilterFactory;
import org.apache.lucene.analysis.custom.CustomAnalyzer;
import org.apache.lucene.analysis.miscellaneous.ASCIIFoldingFilterFactory;
import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.document.StoredField;
import org.apache.lucene.document.TextField;
import org.apache.lucene.index.DirectoryReader;
import org.apache.lucene.index.IndexReader;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.index.IndexWriterConfig;
import org.apache.lucene.index.Term;
import org.apache.lucene.search.BoostQuery;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.Query;
import org.apache.lucene.search.ScoreDoc;
import org.apache.lucene.search.TopDocs;
import org.apache.lucene.search.WildcardQuery;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.MMapDirectory;
// define index storage location
Directory directory = new MMapDirectory(java.nio.Path);
// create text analyzer
Analyzer analyzer = CustomAnalyzer.builder()
.withTokenizer(LetterOrDigitTokenizerFactory.class)
.addTokenFilter(LowerCaseFilterFactory.class)
.addTokenFilter(ASCIIFoldingFilterFactory.class)
.build();
// fill search index
IndexWriterConfig configuration = new IndexWriterConfig(analyzer);
try (IndexWriter writer = new IndexWriter(index, configuration)) {
writer.deleteAll();
writer.commit();
for (String s : strings) {
Document document = new Document();
document.add(new TextField(IDENTIFIER, s, Field.Store.YES));
// add more fields if necessary, lucene allows to add several field types
writer.addDocument(document);
}
}
// query search index (limited to 50 matches)
// it is easily possible to combine multiple queries
Query query = new WildcardQuery(new Term(IDENTIFIER, needle));
IndexReader reader = DirectoryReader.open(index);
IndexSearcher searcher = new IndexSearcher(reader);
TopDocs scoredDocuments = searcher.search(query, 50);
for (ScoreDoc scoreDocument : scoredDocuments.scoreDocs) {
Document document = searcher.doc(scoreDocument.doc);
// TODO do something with this individual matching result document
}