发布于 2015-06-10 00:10:27 | 250 次阅读 | 评论: 0 | 来源: 网友投递
Apache Lucene全文检索引擎工具包
Lucene是apache软件基金会4 jakarta项目组的一个子项目，是一个开放源代码的全文检索引擎工具包，即它不是一个完整的全文检索引擎，而是一个全文检索引擎的架构，提供了完整的查询引擎和索引引擎，部分文本分析引擎（英文与德文两种西方语言）。Lucene的目的是为软件开发人员提供一个简单易用的工具包，以方便的在目标系统中实现全文检索的功能，或者是以此为基础建立起完整的全文检索引擎。
示例代码：
/*
* Filter这个类的功能是实现对于查询的过滤器，
* 对于用户搜索的，可以把保密的网站或者文档对用户不进行显示
* 例如：
* 这里就是一个图书馆的查询系统，图书馆的有些珍贵资料是不予显示的。
* 只有高级权限的(Advanced)的用户才可以显示
*
* */
package filter;
import java.io.IOException;
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;
public class FilterOneTest {
private final int SECURITY_ADVANCED = 1;
private final int SECURITY_MIDDLE = 2;
private final int SECURITY_NORMAL = 3;
public FilterOneTest(String INDEX_STORE_PATH) {
try{
IndexWriter writer = new IndexWriter(INDEX_STORE_PATH, new StandardAnalyzer(), true);
writer.setUseCompoundFile(false);
Document doc1 = new Document();
Field f1 = new Field("bookNumber", "0000003", Field.Store.YES, Field.Index.UN_TOKENIZED);
Field f2 = new Field("bookname", "论宇称非对称模型", Field.Store.YES, Field.Index.TOKENIZED);
Field f3 = new Field("publishdate", "1999-01-01", Field.Store.YES, Field.Index.UN_TOKENIZED);
Field f4 = new Field("securitylevel", SECURITY_ADVANCED + "", 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", "1995-07-15", 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", "1963-02-14", Field.Store.YES, Field.Index.UN_TOKENIZED);
f4 = new Field("securitylevel", SECURITY_ADVANCED + "", 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", "1988-05-01", Field.Store.YES, Field.Index.UN_TOKENIZED);
f4 = new Field("securitylevel", SECURITY_ADVANCED + "", 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", "原子弹的爆破过程", Field.Store.YES, Field.Index.TOKENIZED);
f3 = new Field("publishdate", "1959-10-21", Field.Store.YES, Field.Index.UN_TOKENIZED);
f4 = new Field("securitylevel", SECURITY_ADVANCED + "", 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", "钢铁是怎样炼成的", Field.Store.YES, Field.Index.TOKENIZED);
f3 = new Field("publishdate", "1970-01-11", 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", "0000002", Field.Store.YES, Field.Index.UN_TOKENIZED);
f2 = new Field("bookname", "白毛女", Field.Store.YES, Field.Index.TOKENIZED);
f3 = new Field("publishdate", "1977-09-07", 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);
writer.addDocument(doc1);
writer.addDocument(doc2);
writer.addDocument(doc3);
writer.addDocument(doc4);
writer.addDocument(doc5);
writer.addDocument(doc6);
writer.addDocument(doc7);
writer.close();
IndexReader reader = IndexReader.open(INDEX_STORE_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：");
System.out.print(doc.get("securitylevel"));
int level = Integer.parseInt(doc.get("securitylevel"));
switch(level){
case SECURITY_ADVANCED:
System.out.println("高级");
break;
case SECURITY_MIDDLE:
System.out.println("中级");
break;
case SECURITY_NORMAL:
System.out.println("一般");
break;
}
System.out.println(">>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>");
}
}catch(IOException e){
e.printStackTrace();
}
}
public static void main(String[] args) {
// TODO Auto-generated method stub
FilterOneTest fot = new FilterOneTest("E:\Lucene项目\索引文件");
}
}