lucene自定义过滤器

喜欢ヅ旅行 2022-02-28 05:33 285阅读 0赞

package util;
    
    import java.io.IOException;
    import org.apache.lucene.index.IndexReader;
    import org.apache.lucene.index.Term;
    import org.apache.lucene.index.TermDocs;
    import org.apache.lucene.search.DocIdSet;
    import org.apache.lucene.search.Filter;
    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.util.OpenBitSet;
    /**
     * 过滤指定的文件名
     * @author user
     *
     */
    public class MyIDFilter extends Filter{
    	
    	public static void main(String[] args) throws Exception {
    		IndexSearcher searcher = DocUtil.getSearcher();
    		Query query = new TermQuery(new Term("content","java"));
    		Filter filterFilename = new MyIDFilter();
    //		TopDocs topdoc = searcher.search(query, 100);
    		TopDocs topdoc = searcher.search(query, filterFilename, 100);
    		DocUtil.printDocument(topdoc, searcher);
    		searcher.close();
    	}
    	
    	private String[] filenames = {"1.txt","2.txt","3.txt"};
    	@Override
    	public DocIdSet getDocIdSet(IndexReader reader) throws IOException {
    		//创建一个元素bitset,默认所有的元素都是0
    		OpenBitSet obs = new OpenBitSet(reader.maxDoc());
    		//先把元素填满,只要有传入的文档号被设置,该文档的对应元素就会被设置为1
    		obs.set(0, reader.maxDoc() - 1);
    		int[] docs = new int[1];//存储查询出来的对象的位置
    		int[] freqs = new int[1];//存储查询出来的对象出现的频率
    		//根据id所在的doc位置,并且将其设置为0
    		for(String filename : filenames){
    			//获取TermDocs
    			TermDocs tds = reader.termDocs(new Term("filename",filename));
    			//会将查询出来的对象的位置存储到docs中,出现的频率存储到freqs中,返回获取的条数
    			int count = tds.read(docs, freqs);
    			if(count == 1){
    				//将这个元素删除
    				obs.clear(docs[0]);
    			}
    		}
    		return obs;
    	}
    }