import java.io.IOException;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.index.CorruptIndexException;
import org.apache.lucene.index.IndexWriter;
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.store.Directory;
import org.apache.lucene.store.LockObtainFailedException;
import org.junit.Test;
import org.wltea.analyzer.lucene.IKAnalyzer;
import org.wltea.analyzer.lucene.IKQueryParser;
import org.wltea.analyzer.lucene.IKSimilarity;
import com.itheima11.lucene.utils.LuceneUtils;
public class IKIndex {
@Test
public void createIndex() {
// Lucene Document的域名
String fieldName = "text";
// 检索内容
String text = "IK Analyzer是一个结合词典分词和文法分词的中文分词开源工具包。它使用了全新的正向迭代最细粒度切分算法。 ";
// 实例化IKAnalyzer分词器
IKAnalyzer analyzer = new IKAnalyzer();
// 增加停用词
// List<String> words = new ArrayList<String>();
// words.add("中文分词工具包");
// Dictionary.loadExtendStopWords(words);
Directory directory = null;
IndexWriter iwriter = null;
try {
// 建立内存索引对象
// directory = new RAMDirectory();
iwriter = new IndexWriter(LuceneUtils.directory, analyzer, true,
IndexWriter.MaxFieldLength.LIMITED);
Document doc = new Document();
doc.add(new Field(fieldName, text, Field.Store.YES,
Field.Index.ANALYZED));
iwriter.addDocument(doc);
iwriter.close();
} catch (CorruptIndexException e) {
e.printStackTrace();
} catch (LockObtainFailedException e) {
e.printStackTrace();
} catch (IOException e) {
e.printStackTrace();
} finally {
if (directory != null) {
try {
directory.close();
} catch (IOException e) {
e.printStackTrace();
}
}
}
}
@Test
public void query() {
// Lucene Document的域名
String fieldName = "text";
// 实例化搜索器
IndexSearcher isearcher = null;
Directory directory = null;
try {
// 建立内存索引对象
// directory = new RAMDirectory();
isearcher = new IndexSearcher(LuceneUtils.directory);
// 在索引器中使用IKSimilarity相似度评估器
isearcher.setSimilarity(new IKSimilarity());
String keyword = "中文分词工具包";
// 使用IKQueryParser查询分析器构造Query对象
Query query = IKQueryParser.parse(fieldName, keyword);
// 搜索相似度最高的5条记录
TopDocs topDocs = isearcher.search(query, 5);
System.out.println("命中: " + topDocs.totalHits);
// 输出结果
ScoreDoc[] scoreDocs = topDocs.scoreDocs;
for (int i = 0; i < topDocs.totalHits; i++) {
Document targetDoc = isearcher.doc(scoreDocs[i].doc);
System.out.println("内容: " + targetDoc.toString());
}
} catch (CorruptIndexException e) {
e.printStackTrace();
} catch (LockObtainFailedException e) {
e.printStackTrace();
} catch (IOException e) {
e.printStackTrace();
} finally {
if (isearcher != null) {
try {
isearcher.close();
} catch (IOException e) {
e.printStackTrace();
}
}
if (directory != null) {
try {
directory.close();
} catch (IOException e) {
e.printStackTrace();
}
}
}
}
}
Lucene-IKAnalyzer使用
最新推荐文章于 2024-07-04 16:23:35 发布