在结果中查询二次过滤QuueryFilter
2015-04-03 16:40
274 查看
/*
*在结果中查询二次过滤QuueryFilter
*可以按照上下文所规定的范围进行对文本的过滤
*/
结果图：
package filter;
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.QueryFilter;
import org.apache.lucene.search.RangeQuery;
import org.apache.lucene.search.TermQuery;
public class QueryFiltertest {
private final int SECURITY_ADVANCED = 0;
private final int SECURITY_MIDDLE = 1;
private final int SECURITY_NORMAL = 2;
public QueryFiltertest(String INDEX_STORE_PATH) {
// TODO Auto-generated constructor stub
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();
//首先构造一个RangQuery，查询某一个时间段内出版所有文档
Term begin = new Term("publishdate", "1970-01-01");
Term end = new Term("publishdate", "1990-01-01");
RangeQuery q = new RangeQuery(begin, end, true);
QueryFilter filter = new QueryFilter(q);
Term normal = new Term("securitylevel", SECURITY_NORMAL + "");
TermQuery query = new TermQuery(normal);
IndexSearcher searcher = new IndexSearcher(INDEX_STORE_PATH);
//检索
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：");
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();
}
}
//级别过滤器
public class AdvancedSecurityFilter extends Filter{
//安全级别常量
public static final int SECURITY_ADVANCED = 0;
@Override
public BitSet bits(IndexReader reader) throws IOException {
// TODO Auto-generated method stub
//首先初始化一个BigSet对象
final BitSet bits = new BitSet(reader.maxDoc());
//先将整个集合置为true
//表示当前集合内的所有文档都可以被检索到
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", SECURITY_ADVANCED + "");
//从索引中取出具有最高安全级别的文档
TermDocs termDocs = reader.termDocs(term);
//方法一
//遍历每个文档
while(termDocs.next()){
bits.set(termDocs.doc(), false);
}
return bits;
}
}
public static void main(String[] args) {
// TODO Auto-generated method stub
QueryFiltertest rf = new QueryFiltertest("E:\\Lucene项目\\索引文件");
}
}
*在结果中查询二次过滤QuueryFilter
*可以按照上下文所规定的范围进行对文本的过滤
*/
结果图：
package filter;
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.QueryFilter;
import org.apache.lucene.search.RangeQuery;
import org.apache.lucene.search.TermQuery;
public class QueryFiltertest {
private final int SECURITY_ADVANCED = 0;
private final int SECURITY_MIDDLE = 1;
private final int SECURITY_NORMAL = 2;
public QueryFiltertest(String INDEX_STORE_PATH) {
// TODO Auto-generated constructor stub
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();
//首先构造一个RangQuery，查询某一个时间段内出版所有文档
Term begin = new Term("publishdate", "1970-01-01");
Term end = new Term("publishdate", "1990-01-01");
RangeQuery q = new RangeQuery(begin, end, true);
QueryFilter filter = new QueryFilter(q);
Term normal = new Term("securitylevel", SECURITY_NORMAL + "");
TermQuery query = new TermQuery(normal);
IndexSearcher searcher = new IndexSearcher(INDEX_STORE_PATH);
//检索
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：");
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();
}
}
//级别过滤器
public class AdvancedSecurityFilter extends Filter{
//安全级别常量
public static final int SECURITY_ADVANCED = 0;
@Override
public BitSet bits(IndexReader reader) throws IOException {
// TODO Auto-generated method stub
//首先初始化一个BigSet对象
final BitSet bits = new BitSet(reader.maxDoc());
//先将整个集合置为true
//表示当前集合内的所有文档都可以被检索到
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", SECURITY_ADVANCED + "");
//从索引中取出具有最高安全级别的文档
TermDocs termDocs = reader.termDocs(term);
//方法一
//遍历每个文档
while(termDocs.next()){
bits.set(termDocs.doc(), false);
}
return bits;
}
}
public static void main(String[] args) {
// TODO Auto-generated method stub
QueryFiltertest rf = new QueryFiltertest("E:\\Lucene项目\\索引文件");
}
}
内容来自用户分享和网络整理，不保证内容的准确性，如有侵权内容，可联系管理员处理 
相关文章推荐
- Lucene查询结果Hits的二次封装
- django ORM model filter 条件过滤，及多表连接查询、反向查询 和 多条件查询
- 关于同时设置 VAR_FILTERS 和 DEFAULT_FILTER 造成数据二次过滤的BUG
- django ORM model filter 条件过滤，及多表连接查询、反向查询，某字段的distinct
- django ORM model filter 条件过滤，及多表连接查询、反向查询，某字段的distinct
- MySql中一次查询结果用作二次查询条件
- Oracle中使用正则表达式过滤查询结果
- Search and Filter Sessions--查询和过滤sessions
- Hbase查询结果分页（PageFilter）
- 使用navicat for mysql 将查询语句过滤的结果导出成insert语句时没有带表名的解决办法
- mysql如何根据select结果进行二次连接查询
- XsqlFilterResult----动态生成sql语句的类，过滤一些为空的查询条件 .
- ExtJs 4 Grid filter in asp.net mvc action表格 查询与过滤的最佳解析解决方案
- LDAP查询过滤语法 LDAP Filter Syntax
- django ORM model filter 条件过滤，及多表连接查询、反向查询，某字段的distinct
- django ORM model filter 条件过滤，及多表连接查询、反向查询字段
- 结构化查询（Query DSL）和结构化过滤（Filter DSL）
- PHP 数据库查询结果转换数组后进行再查询过滤
- Revit 二次开发---空间过滤(空间查询)
- SqlServer 在查询结果中如何过滤掉重复数据