lucene 与IKAnalyzer实现中文分词查询（最新jar及实现代码）

野性酷女 2022-06-15 02:14 187阅读 0赞

资源地址：http://download.csdn.net/detail/qq540061627/4063916

lucene3.5 IKAnalyzer3.2.5 实例中文分词通过，目前在网上找的lucene 和IKAnalyzer 的最新版本测试通过。内含：示例代码，以及最新jar包。

lucene lucene3.5 IKAnalyzer IKAnalyzer3.2.5 jar 中文 分词

测试项目截图（测试项目所用jar可见）：

![0_1329229410sYGM.gif][]

创建索引：

import java.io.File;
    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.document.Field.Index;
    import org.apache.lucene.document.Field.Store;
    import org.apache.lucene.index.CorruptIndexException;
    import org.apache.lucene.index.IndexWriter;
    import org.apache.lucene.index.IndexWriterConfig;
    import org.apache.lucene.index.IndexWriterConfig.OpenMode;
    import org.apache.lucene.store.Directory;
    import org.apache.lucene.store.LockObtainFailedException;
    import org.apache.lucene.store.SimpleFSDirectory;
    import org.apache.lucene.util.Version;
    import org.wltea.analyzer.lucene.IKAnalyzer;
    
    public class FileIndexer {
    	private File baseDir = new File("F:\\dateDir");
    	private File indexDir2 = new File("F:\\indexDir");
    	Analyzer luceneAnalyzer = new IKAnalyzer();
    	Directory indexDir = null ;
    	public FileIndexer() {
    		if (!this.baseDir.exists() || !this.indexDir2.exists()) {
    			return;
    		}
    	}
    
    	@SuppressWarnings("deprecation")
    	public void createIndex() {
    		try {
    
    			IndexWriterConfig config = new IndexWriterConfig(Version.LUCENE_35,luceneAnalyzer);
    			
    			indexDir=new SimpleFSDirectory(indexDir2);
    			config.setOpenMode(OpenMode.CREATE);
    			IndexWriter indexWriter = null;
    			
    			indexWriter = new IndexWriter(indexDir,config);
    			
    			
    			Document doc1 = new Document();
    			doc1.add(new Field("id","1",Store.YES,Index.ANALYZED));
    			doc1.add(new Field("name","liangge",Store.YES,Index.ANALYZED));
    			doc1.add(new Field("content","我是中国人",Store.YES,Index.ANALYZED));
    			Document doc2 = new Document();
    			doc2.add(new Field("id","2",Store.YES,Index.ANALYZED));
    			doc2.add(new Field("name","liangge is a girl",Store.YES,Index.ANALYZED));
    			doc2.add(new Field("content","liangge am a good girl",Store.YES,Index.ANALYZED));
    	        indexWriter.addDocument(doc1);
    	        indexWriter.addDocument(doc2);
    	        indexWriter.close();
    			
    			
    			
    			
    			System.out.println("完毕");
    		} catch (CorruptIndexException e) {
    			e.printStackTrace();
    		} catch (LockObtainFailedException e) {
    			e.printStackTrace();
    		} catch (IOException e) {
    			e.printStackTrace();
    		}
    	}
    
    
    	public static void main(String[] args) {
    		FileIndexer lucene = new FileIndexer();
    		lucene.createIndex();
    	}
    }

单Field搜索：

import java.io.File;
    import java.io.IOException;
    import java.util.ArrayList;
    import java.util.List;
    
    import org.apache.lucene.document.Document;
    import org.apache.lucene.index.CorruptIndexException;
    import org.apache.lucene.index.IndexReader;
    import org.apache.lucene.queryParser.QueryParser;
    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.FSDirectory;
    import org.apache.lucene.store.LockObtainFailedException;
    import org.apache.lucene.store.SimpleFSDirectory;
    import org.wltea.analyzer.lucene.IKQueryParser;
    import org.wltea.analyzer.lucene.IKSimilarity;
    
    
    public class FileSearcher {
    
    private File indexDir = new File("F:\\indexDir");;
    	
    	public List search(String fieldName, String keyword) {
    		Directory directory = null;
    		IndexSearcher is = null;
    		TopDocs topDocs=null;
    
    		try {
    
    
    			Query query = IKQueryParser.parse(fieldName, keyword);  // 
    			System.out.println(query.toString()+"----------"+QueryParser.escape(keyword));
    			
    			directory = SimpleFSDirectory.open(indexDir);
    			 IndexReader reader = IndexReader.open(new SimpleFSDirectory(indexDir));
    			is = new IndexSearcher(reader);
    			is.setSimilarity(new IKSimilarity()); //
    			
    			topDocs = is.search(query,100);  // 
    
    		ScoreDoc[] scoreDocs = topDocs.scoreDocs;
    		for (int j = 0; j < topDocs.totalHits; j++) {
    			Document dd=is.doc(scoreDocs[j].doc);
    			System.out.println(dd.toString());
    			System.out.println(dd.get("id"));
    			System.out.println(dd.get("name"));
    			System.out.println(dd.get("content"));
    		}
    
    		} catch (CorruptIndexException e) {
    			e.printStackTrace();
    		} catch (LockObtainFailedException e) {
    			e.printStackTrace();
    		} catch (IOException e) {
    			e.printStackTrace();
    		} finally {
    			if (is != null) {
    				try {is.close();} 
    					catch (IOException e) {e.printStackTrace();}
    			}
    			if (directory != null) {
    				try {directory.close();} 
    					catch (IOException e) {e.printStackTrace();}
    			}
    		}
    		return null;
    	}
    
    	public static void main(String[] args) {
    		FileSearcher search = new FileSearcher();
    		search.search("content", "我是中国人");
    	}
    }

完整实例 资源地址：资源地址：http://download.csdn.net/detail/qq540061627/4063916

希望对你有帮助(正在进一步研究中，准备整合进一个现有的SSH框架，实现商品搜索，欢迎交流)。

[0_1329229410sYGM.gif]: /images/20220615/405fedfda02b47a8bdc1655af09b75e8.png