学步园

import java.io.IOException;
import java.util.BitSet;

import org.apache.lucene.analysis.standard.StandardAnalyzer;
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.Term;
import org.apache.lucene.index.TermDocs;
import org.apache.lucene.search.Filter;
import org.apache.lucene.search.Hits;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.RangeQuery;

/**
 * 测试过滤Filter
 * @author Administrator
 *
 */


public class FilterTest {

 private static final String INDEX_STORE_PATH="d:\\test";
 private static final int SECURITY_ADVANCE=0;
 private static final int SECURITY_MIDDLE=1;
 private static final int SECURITY_NORMAL=2;
 
 public static void main(String[] args)throws IOException
 {
  //indexwriter(INDEX_STORE_PATH);
  //read(INDEX_STORE_PATH);
  System.out.println("****************************");
  search(INDEX_STORE_PATH);
 }
 
 /*
  * 建立索引
  */
 public static void indexwriter(String path) throws IOException
 {
  //建立文档
  Document doc1=new Document();
  Field f1=new Field("booknumber","0000003",Field.Store.YES,Field.Index.UN_TOKENIZED);
        Field f2=new Field("bookname","论宇宙非对称模型",Field.Store.YES,Field.Index.TOKENIZED);
        Field f3=new Field("publishdate","1970-01-01",Field.Store.YES,
    Field.Index.UN_TOKENIZED);
        Field f4=new Field("securitylevel",SECURITY_ADVANCE+"",Field.Store.YES,
    Field.Index.UN_TOKENIZED);
        doc1.add(f1);
        doc1.add(f2);
        doc1.add(f3);
        doc1.add(f4);
        //-----
        Document doc2=new Document();
   f1=new Field("booknumber","0000005",Field.Store.YES,Field.Index.UN_TOKENIZED);
         f2=new Field("bookname","钢铁战士",Field.Store.YES,Field.Index.TOKENIZED);
         f3=new Field("publishdate","1995-01-01",Field.Store.YES,
    Field.Index.UN_TOKENIZED);
         f4=new Field("securitylevel",SECURITY_MIDDLE+"",Field.Store.YES,
    Field.Index.UN_TOKENIZED);
        doc2.add(f1);
        doc2.add(f2);
        doc2.add(f3);
        doc2.add(f4);
        //----
        Document doc3=new Document();
  f1=new Field("booknumber","0000001",Field.Store.YES,Field.Index.UN_TOKENIZED);
        f2=new Field("bookname","相对论",Field.Store.YES,Field.Index.TOKENIZED);
        f3=new Field("publishdate","1970-01-01",Field.Store.YES,
    Field.Index.UN_TOKENIZED);
        f4=new Field("securitylevel",SECURITY_ADVANCE+"",Field.Store.YES,
    Field.Index.UN_TOKENIZED);
       doc3.add(f1);
       doc3.add(f2);
       doc3.add(f3);
       doc3.add(f4);
       //----
       Document doc4=new Document();
    f1=new Field("booknumber","0000006",Field.Store.YES,Field.Index.UN_TOKENIZED);
       f2=new Field("bookname","黑猫警长",Field.Store.YES,Field.Index.TOKENIZED);
       f3=new Field("publishdate","1999-01-01",Field.Store.YES,
    Field.Index.UN_TOKENIZED);
       f4=new Field("securitylevel",SECURITY_NORMAL+"",Field.Store.YES,
    Field.Index.UN_TOKENIZED);
      doc4.add(f1);
      doc4.add(f2);
      doc4.add(f3);
      doc4.add(f4);
      //----
      Document doc5=new Document();
   f1=new Field("booknumber","0000004",Field.Store.YES,Field.Index.UN_TOKENIZED);
      f2=new Field("bookname","原子弹的爆炸模拟",Field.Store.YES,Field.Index.TOKENIZED);
      f3=new Field("publishdate","1995-01-01",Field.Store.YES,
    Field.Index.UN_TOKENIZED);
      f4=new Field("securitylevel",SECURITY_ADVANCE+"",Field.Store.YES,
    Field.Index.UN_TOKENIZED);
     doc5.add(f1);
     doc5.add(f2);
     doc5.add(f3);
     doc5.add(f4);
     //----
     Document doc6=new Document();
   f1=new Field("booknumber","0000007",Field.Store.YES,Field.Index.UN_TOKENIZED);
     f2=new Field("bookname","钢铁是怎么炼成的",Field.Store.YES,Field.Index.TOKENIZED);
     f3=new Field("publishdate","1995-08-01",Field.Store.YES,
    Field.Index.UN_TOKENIZED);
     f4=new Field("securitylevel",SECURITY_MIDDLE+"",Field.Store.YES,
    Field.Index.UN_TOKENIZED);
    doc6.add(f1);
    doc6.add(f2);
    doc6.add(f3);
    doc6.add(f4);
     //----
    Document doc7=new Document();
   f1=new Field("booknumber","0000004",Field.Store.YES,Field.Index.UN_TOKENIZED);
    f2=new Field("bookname","白毛女",Field.Store.YES,Field.Index.TOKENIZED);
    f3=new Field("publishdate","1995-01-01",Field.Store.YES,
    Field.Index.UN_TOKENIZED);
    f4=new Field("securitylevel",SECURITY_NORMAL+"",Field.Store.YES,
    Field.Index.UN_TOKENIZED);
   doc7.add(f1);
   doc7.add(f2);
   doc7.add(f3);
   doc7.add(f4);
   
 //建立索引
 IndexWriter writer=new IndexWriter( path ,new StandardAnalyzer(),true);
 writer.setUseCompoundFile(false);
 writer.addDocument(doc1);
 writer.addDocument(doc2);
 writer.addDocument(doc3);
 writer.addDocument(doc4);
 writer.addDocument(doc5);
 writer.addDocument(doc6);
 writer.addDocument(doc7);
 writer.close();
 System.out.printf("建立索引完毕！\n");
 }
 /*
  * IndexReader阅读索引
  */
 public static void read(String path) throws IOException
 {
  IndexReader reader=IndexReader.open(path);
  for(int i=0;i<reader.numDocs();i++)
  {
   Document doc=reader.document(i);
   System.out.print("书号：");
   System.out.println(doc.get("booknumber"));
   System.out.print("书名：");
   System.out.println(doc.get("bookname"));
   System.out.print("发布日期：");
   System.out.println(doc.get("publishdate"));
   System.out.print("安全级别：");
   int leve=Integer.parseInt(doc.get("securitylevel"));
   switch(leve)
   {
   case SECURITY_ADVANCE:
    System.out.println("高级");
    break;
   case SECURITY_MIDDLE:
    System.out.println("中级");
    break;
   case SECURITY_NORMAL:
    System.out.println("低级");
    break;
   default:
    break;
   }
   System.out.println("-------------------------");
  }
 }
 
   /*
    * 过滤检索
    */
 public static void search(String path) throws IOException
 {
  //构建一个RangeQuery
  Term begin=new Term("publishdate","1900-01-01");
  Term end=new Term("publishdate","2010-01-01");
  RangeQuery query=new RangeQuery(begin,end,true);
  //
  IndexSearcher searcher=new IndexSearcher(path);
  //使用AdvancedSecurity来做过滤器
  AdvancedSecurity filter=new AdvancedSecurity();
  //使用字符过滤
  /*String text="钢铁";
  TestFilter filter=new TestFilter(text);  */
  Hits hits=searcher.search(query, filter);
  //
  for(int i=0;i<hits.length();i++)
  {
   Document doc=hits.doc(i);
   System.out.print("书号：");
   System.out.println(doc.get("booknumber"));
   System.out.print("书名：");
   System.out.println(doc.get("bookname"));
   System.out.print("发布日期：");
   System.out.println(doc.get("publishdate"));
   System.out.print("安全级别：");
   int leve=Integer.parseInt(doc.get("securitylevel"));
   switch(leve)
   {
   case SECURITY_ADVANCE:
    System.out.println("高级");
    break;
   case SECURITY_MIDDLE:
    System.out.println("中级");
    break;
   case SECURITY_NORMAL:
    System.out.println("低级");
    break;
   default:
    break;
   }
   System.out.println("-------------------------");
     }
 }
 }


class AdvancedSecurity extends Filter  //过滤安全级别为高级级别的
{
 public static final int SECURITY_ADVACED=0;
 //继承自Filter的抽象类
 public BitSet bits(IndexReader reader) throws IOException
 {
  //初始化一个Bitset对象
  final BitSet bits=new BitSet(reader.maxDoc());
  //将整个集合至于全部true
  //以至于全部文档都可以被检索
  bits.set(0,bits.size()-1);
  
  //构造一个Trem对象，代表安全级别
  Term term=new Term("securitylevel",SECURITY_ADVACED+"");
  //从检索中取出高级级别的文档
  TermDocs termdocs=reader.termDocs(term);
  
  //遍历每个文档
  while(termdocs.next())
   bits.set(termdocs.doc(), false);
  return bits;
  
 }
}

class TestFilter extends Filter   //过滤包含某个关键字的文档
{
 public String FilterText;
 //重构
 public  TestFilter(String text)
 {
  //
  this.FilterText=text;
 }
 

 
 public  BitSet bits(IndexReader reader) throws IOException
 {
  final BitSet bits=new BitSet(reader.maxDoc());
  bits.set(0,bits.size()-1);
  //
  Term term=new Term("bookname",FilterText);
  TermDocs tdocs=reader.termDocs(term);
  
  //遍历每个文档
  while(tdocs.next())
   bits.set(tdocs.doc(), false);
  
  return bits;
 }
}