/**
* IK Analyzer Demo
* @param args
*/
import java.io.IOException;
import org.apache.lucene.analysis.Analyzer;
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.apache.lucene.store.RAMDirectory;
import org.wltea.analyzer.lucene.IKAnalyzer;
import org.wltea.analyzer.lucene.IKQueryParser;
import org.wltea.analyzer.lucene.IKSimilarity;
/**
* @author linly
*/
public class IKAnalyzerDemo {
public static void main(String[] args) {
// Lucene Document的域名
String contextfeild= "context";
String textfeild="text";
// 检索内容
String text = "IK Analyzer是一--个新易联众$吖孖结合ni﹌妹词典分词和文法分词的中文分词开源工具包吧。它使用了全新的正向迭代最细粒度切分算法。";
String text2 = "易联众国家认识吗你";
// 实例化IKAnalyzer分词器
Analyzer analyzer = new IKAnalyzer();
Directory directory = null;
IndexWriter iwriter = null;
IndexSearcher isearcher = null;
try {
// 建立内存索引对象
directory = new RAMDirectory();
iwriter = new IndexWriter(directory, analyzer, true,
IndexWriter.MaxFieldLength.LIMITED);
Document doc = new Document();
doc.add(new Field(contextfeild, text, Field.Store.YES,
Field.Index.ANALYZED));
doc.add(new Field(textfeild, text2, Field.Store.YES,
Field.Index.ANALYZED));
iwriter.addDocument(doc);
iwriter.close();
// 实例化搜索器
isearcher = new IndexSearcher(directory);
// 在索引器中使用IKSimilarity相似度评估器
isearcher.setSimilarity(new IKSimilarity());
String keyword ="源";
// 使用IKQueryParser查询分析器构造Query对象
Query query = IKQueryParser.parseMultiField(new String[]{contextfeild,textfeild}, keyword);
// 搜索相似度最高的5条记录
TopDocs topDocs = isearcher.search(query, 1000);
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();
}
}
}
}
}
ikTest.rar （22个子文件） 
ikTest 
.project 382B src FileSearcher.java 2KB extstopword.dic 170B IKAnalyzerDemo.java 3KB IKAnalyzer.cfg.xml 295B exist.dic 34B FileIndexer.java 2KB IKAnalyzerTest.java 1KB lib 
IKAnalyzer3.2.0Stable.jar 1.11MB IKAnalyzer3.2.5Stable.jar 1.11MB lucene-core-3.6.2.jar 1.47MB commons-logging.jar 37KB lucene-core-3.5.0.jar 1.4MB .settings org.eclipse.core.resources.prefs 180B .classpath 426B bin IKAnalyzerDemo.class 5KB extstopword.dic 170B IKAnalyzer.cfg.xml 295B exist.dic 34B IKAnalyzerTest.class 2KB FileSearcher.class 4KB FileIndexer.class 3KB
评论1
最新资源