Lucene过滤器 - baobeituping - ITeye技术网站
有的应用有些要求，对于某类型的内容即使满足条件了，但是也不能被搜索出来，lucene中提供了过滤器的功能，通过自定义的过滤器继承Filter，从而实现特定的过滤功能。
Filter是一种过滤行为BitSet是一种位集合队列，这个队列中只有两种取值，TRUE或FALSE，LUCENE以这两种取值代表文档是否被过滤，也就是说，LUCENE返回结果时，会首先遍历BITSET，仅将那些对应值为TRUE的文档返回。
过滤器：
package com.filter;
import java.io.IOException;
import java.util.BitSet;
import org.apache.lucene.index.IndexReader;
import org.apache.lucene.index.Term;
import org.apache.lucene.index.TermDocs;
import org.apache.lucene.search.Filter;
public class AdvancedSecurityFilter extends Filter {
//安全级别的常量
public static final int ADVANCED=0;
@Override
public BitSet bits(IndexReader reader) throws IOException {
//首先初始化一个BITSET对象
final BitSet bits = new BitSet(reader.maxDoc());
//先将整个集合设置为TRUE,表示当前集合内的所有文档都是可以被检索到的。
bits.set(0,bits.size()-1);
//构造一个TERM对象，代表最高安全级别
Term term = new Term("securitylevel",ADVANCED+"");
//从索引中搜索出所有最高安全级别的文档
TermDocs termDocs = reader.termDocs(term);
//遍历每个文档，并将其
while(termDocs.next())
{
bits.set(termDocs.doc(),false);
}
return bits;
}
}
过滤器使用实例：
public class FilterDemo {
/**
* @param args
*/
public static final int ADVANCED=0;
public static final int MIDDLE =1;
public static final int NORMAL=2;
public static void main(String[] args) {
try {
/*File file = new File("d://demo");
Analyzer luceneAnalyzer = new StandardAnalyzer();
IndexWriter writer = new IndexWriter(file, luceneAnalyzer, false);
Document doc1 = new Document();
Field f1 = new Field("bookNumber","0003",Field.Store.YES,Field.Index.UN_TOKENIZED);
Field f2 = new Field("bookName","非对称模型",Field.Store.YES,Field.Index.UN_TOKENIZED);
Field f3 = new Field("securitylevel",ADVANCED+"",Field.Store.YES,Field.Index.UN_TOKENIZED);
doc1.add(f1);
doc1.add(f2);
doc1.add(f3);
Document doc2 = new Document();
Field f4 = new Field("bookNumber","0001",Field.Store.YES,Field.Index.UN_TOKENIZED);
Field f5 = new Field("bookName","钢铁战士",Field.Store.YES,Field.Index.TOKENIZED);
Field f6 = new Field("securitylevel",MIDDLE+"",Field.Store.YES,Field.Index.UN_TOKENIZED);
doc2.add(f4);
doc2.add(f5);
doc2.add(f6);
Document doc3 = new Document();
Field f7 = new Field("bookNumber","0004",Field.Store.YES,Field.Index.UN_TOKENIZED);
Field f8 = new Field("bookName","黑猫警长",Field.Store.YES,Field.Index.TOKENIZED);
Field f9 = new Field("securitylevel",NORMAL+"",Field.Store.YES,Field.Index.UN_TOKENIZED);
doc3.add(f7);
doc3.add(f8);
doc3.add(f9);
writer.addDocument(doc1);
writer.addDocument(doc2);
writer.addDocument(doc3);
writer.setUseCompoundFile(true);
writer.optimize();
writer.close();*/
Term begin = new Term("bookNumber","0001");
Term end = new Term("bookNumber","0004");
RangeQuery q = new RangeQuery(begin,end,true);
IndexSearcher searcher = new IndexSearcher("d://demo");
System.out.println(q.toString());
//通过将自定义的过滤器配置在search方法中，从而达到过滤的目的。
Hits hits = searcher.search(q,new AdvancedSecurityFilter());
for(int i=0;i<hits.length();i++)
{
System.out.println(hits.doc(i));
}
} catch (Exception e) {
e.printStackTrace();
}
}
}