第二章：lucene构建索引（新增、查询、更新、删除）

ゞ浴缸里的玫瑰 2022-08-06 11:23 148阅读 0赞

package lucene2;
    
    
    import java.io.IOException;
    
    
    import junit.framework.TestCase;
    
    
    import org.apache.lucene.analysis.WhitespaceAnalyzer;
    import org.apache.lucene.document.Document;
    import org.apache.lucene.document.Field;
    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.IndexSearcher;
    import org.apache.lucene.search.Query;
    import org.apache.lucene.search.TermQuery;
    import org.apache.lucene.search.TopDocs;
    import org.apache.lucene.store.Directory;
    import org.apache.lucene.store.RAMDirectory;
    import org.apache.lucene.util.Version;
    import org.junit.Test;
    
    
    /**
     * 构建索引（基本的新增、查询、更新、删除）
     * @author zhangwx
     *
     */
    public class IndexTest extends TestCase{
    	protected String[] ids = {"1","2"};
    	protected String[] unidexed = {"Netherlands","Italy"};
    	protected String[] unstored ={"Amsterdam has lots of bridges","Venice has lots of canals"};
    	protected String[] text = {"Amsterdam","Venice"};
    	
    	private Directory directory;//索引目录
    	
    	@Override
    	protected void setUp() throws Exception {
    		directory = new RAMDirectory();//内存索引
    		IndexWriter writer = getWriter();
    		for(int i=0;i<ids.length;i++){
    			Document doc = new Document();
    			doc.add(new Field("id",ids[i],Field.Store.YES,Field.Index.NOT_ANALYZED));
    			doc.add(new Field("country",unidexed[i],Field.Store.YES,Field.Index.NO));
    			doc.add(new Field("contents",unstored[i],Field.Store.NO,Field.Index.ANALYZED));
    			doc.add(new Field("city",text[i],Field.Store.YES,Field.Index.ANALYZED));
    			writer.addDocument(doc);
    		}
    		writer.commit();
    		writer.close();//记住：writer用完随时关闭（可能造成writer.lock异常）
    	}
    	
    	/**
    	 * 创建IndexWriter
    	 * @return IndexWriter
    	 * @throws Exception
    	 */
    	private IndexWriter getWriter() throws Exception{
    		IndexWriterConfig config = new IndexWriterConfig(Version.LUCENE_35, new WhitespaceAnalyzer(Version.LUCENE_35));
    		return new IndexWriter(directory,config);
    	}
    	
    	protected int getHitCount(String filedName,String searchString) throws Exception{
    		IndexReader reader = IndexReader.open(directory);
    		IndexSearcher searcher = new IndexSearcher(reader);
    		Term term = new Term(filedName,searchString);
    		Query query = new TermQuery(term);
    		int hitCount = hitCount(searcher, query);
    		searcher.close();
    		reader.close();
    		return hitCount;
    	}
    	
    	public static int hitCount(IndexSearcher searcher,Query query) throws IOException{
    		TopDocs search = searcher.search(query,1);
    		return search.totalHits;
    	}
    	
    	
    	@Test
    	public void testIndexWriter() throws Exception{
    		IndexWriter writer = getWriter();
    		assertEquals(ids.length, writer.numDocs());//确认写入的文档数
    		writer.close();
    	}
    	
    	@Test
    	public void testIndexReader() throws Exception{
    		IndexReader reader = IndexReader.open(directory);
    		assertEquals(ids.length, reader.maxDoc());//确认读取的最大文档数
    		assertEquals(ids.length, reader.numDocs());//确认有效的文档数
    		reader.close();
    	}
    	
    	@Test
    	public void testIndexReader2() throws Exception{
    		int hitCount = getHitCount("contents","lots");
    		assertEquals(ids.length, hitCount);
    		System.out.println(hitCount);
    	}
    	
    	/**
    	 * 从索引中删除文档 优化操作前（未执行writer.optimize()之前被删除的文档仍然存在索引中只是状态被标记为已删除）
    	 * @throws Exception
    	 */
    	@Test
    	public void testDeleteBeforeOptimize() throws Exception{
    		IndexWriter writer = getWriter();
    		assertEquals(2, writer.numDocs());//确认索引中的2个文档
    		writer.deleteDocuments(new Term("id","1"));//删除id=1的文档
    		writer.commit();
    		assertTrue(writer.hasDeletions());//确认被标记为删除 （是否存在被标记为删除的文档）
    		assertEquals(2, writer.maxDoc());//确认删除后仍然有2个文档（一个文档被标记为删除，一个未删除）
    		assertEquals(1, writer.numDocs());//确认剩余一个文档
    		writer.close();
    	}
    	
    	/**
    	 * 从索引中删除文档 优化操作后 （执行writer.optimize()后被删除的文档将会消失）
    	 * @throws Exception
    	 */
    	@Test
    	public void testDeleteAfterOptimize() throws Exception{
    		IndexWriter writer = getWriter();
    		assertEquals(2, writer.numDocs());//删除前确认索引中两个文档
    		writer.deleteDocuments(new Term("id","1"));//删除id=1的文档
    		writer.optimize();//执行优化操作
    		writer.commit();
    		assertFalse(writer.hasDeletions());//确认是否存在被标记为删除的文档
    		assertEquals(1, writer.maxDoc());//确认文档总数
    		assertEquals(1, writer.numDocs());//确认可使用文档数
    		writer.close();
    	}
    	
    	
    	/**
    	 * 更新索引（原理：先调用deleteDocuments(term) 再调用addDocument() 即先删除原有文档再添加）
    	 * 本例中用新文档来替换id为1的旧文档。
    	 * @throws Exception
    	 */
    	@Test
    	public void testUpdate() throws Exception{
    		assertEquals(1, getHitCount("city", "Amsterdam"));//更新前查询city=Amsterdam，确认存在
    		IndexWriter writer = getWriter();
    		Document doc = new Document();
    		doc.add(new Field("id","1",Field.Store.YES,Field.Index.NOT_ANALYZED));
    		doc.add(new Field("country","Netherlands",Field.Store.YES,Field.Index.NO));
    		doc.add(new Field("contents","Den Haag has a lot of musenums",Field.Store.NO,Field.Index.ANALYZED));
    		doc.add(new Field("city","Haag",Field.Store.YES,Field.Index.ANALYZED));
    		writer.updateDocument(new Term("id","1"), doc);//更新文档（先删除id=1的旧文档，再添加新doc）
    		writer.close();
    		assertEquals(0, getHitCount("city", "Amsterdam"));//确认更新后city=Amsterdam记录不存在
    		assertEquals(1, getHitCount("city", "Haag"));//确认city=Den Haag的新闻档已添加
    	}
    }