lucene学习笔记三(查询)
...省略索引创建的步骤,如果不懂请看http://my.oschina.net/kkrgwbj/blog/513329
lucene提供的查询方式有很多,api中列出的几种查询方式如下图:
在这里,我只简简单单的举例以下几种查询
创建Directory,IndexSearcher
package com.kkrgwbj.index;
import java.io.File;
import java.io.IOException;
import java.util.Calendar;
import org.apache.lucene.document.Document;
import org.apache.lucene.index.DirectoryReader;
import org.apache.lucene.index.IndexReader;
import org.apache.lucene.index.Term;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.Query;
import org.apache.lucene.search.ScoreDoc;
import org.apache.lucene.search.TermQuery;
import org.apache.lucene.search.TermRangeQuery;
import org.apache.lucene.search.TopDocs;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.FSDirectory;
import org.apache.lucene.util.BytesRef;
public class SearchUtil {
private Directory directory;
private IndexReader indexReader;
public SearchUtil() {
try {
directory = FSDirectory.open(new File("D:/workspace/lucene/index02").toPath());
} catch (IOException e) {
e.printStackTrace();
}
}
/**
* 创建IndexSearcher
*
* @return
*/
public IndexSearcher getSearcher() {
if (indexReader == null) {
try {
indexReader = DirectoryReader.open(directory);
} catch (IOException e) {
e.printStackTrace();
}
} else {
try {
IndexReader tr = DirectoryReader.openIfChanged((DirectoryReader) indexReader);
if (tr != null) {
indexReader.close();
indexReader = tr;
}
} catch (IOException e) {
e.printStackTrace();
}
}
return new IndexSearcher(indexReader);
}
固定的term查询
/**
* 根据固定的term查询
*
* @param field
* @param name
*/
public void searchByTerm(String field, String name) {
// 创建IndexSearch
IndexSearcher indexSearcher = getSearcher();
Query query = new TermQuery(new Term(field, name));
try {
TopDocs tds = indexSearcher.search(query, 10);
System.out.println("一共查询了:" + tds.totalHits);
for (ScoreDoc item : tds.scoreDocs) {
Document doc = indexSearcher.doc(item.doc);
Calendar cal = Calendar.getInstance();
cal.setTimeInMillis(Long.valueOf(doc.get("date")));
System.out.println("名字:" + doc.get("name") + "邮箱:" + doc.get("email") + "id:" + doc.get("id") + "附件个数:"
+ doc.get("attach") + "日期:" + cal.getTime().toString());
}
} catch (IOException e) {
e.printStackTrace();
} finally {
if (indexReader != null)
try {
indexReader.close();
} catch (IOException e) {
e.printStackTrace();
}
}
}
term范围查询
/**
* 范围查询
*
* @param field
* 查询的域
* @param start
* 查询的开始
* @param end
* 查询的结束
* @param num
* 返回的行数
*/
public void searchByTermRange(String field, String start, String end, int num) {
IndexSearcher indexSearcher = getSearcher();
Query query = new TermRangeQuery(field, new BytesRef(start), new BytesRef(end), true, true);
try {
TopDocs tds = indexSearcher.search(query, 10);
System.out.println("一共查询了:" + tds.totalHits);
for (ScoreDoc item : tds.scoreDocs) {
Document doc = indexSearcher.doc(item.doc);
Calendar cal = Calendar.getInstance();
cal.setTimeInMillis(Long.valueOf(doc.get("date")));
System.out.println("名字:" + doc.get("name") + "邮箱:" + doc.get("email") + "id:" + doc.get("id") + "附件个数:"
+ doc.get("attach") + "日期:" + cal.getTime().toString());
}
} catch (Exception e) {
e.printStackTrace();
} finally {
if (indexReader != null)
try {
indexReader.close();
} catch (IOException e) {
e.printStackTrace();
}
}
}
数字范围的查询
/**
* 数字范围的查询
* @param field
* @param start
* @param end
* @param num
*/
public void searchByNumericRange(String field,int start,int end,int num){
IndexSearcher indexSearcher = getSearcher();
Query query = NumericRangeQuery.newIntRange(field, start, end,true,true);
try {
TopDocs tds = indexSearcher.search(query, 10);
System.out.println("一共查询了:" + tds.totalHits);
for (ScoreDoc item : tds.scoreDocs) {
Document doc = indexSearcher.doc(item.doc);
Calendar cal = Calendar.getInstance();
cal.setTimeInMillis(Long.valueOf(doc.get("date")));
System.out.println("名字:" + doc.get("name") + "邮箱:" + doc.get("email") + "id:" + doc.get("id") + "附件个数:"
+ doc.get("attach") + "日期:" + cal.getTime().toString());
}
} catch (Exception e) {
e.printStackTrace();
} finally {
if (indexReader != null)
try {
indexReader.close();
} catch (IOException e) {
e.printStackTrace();
}
}
}
前缀查询
/**
* 前缀搜索
* @param field
* @param value
* @param num
*/
public void searchByPrefix(String field,String value,int num){
IndexSearcher indexSearcher = getSearcher();
Query query = new PrefixQuery(new Term(field, value));
try {
TopDocs tds = indexSearcher.search(query, 10);
System.out.println("一共查询了:" + tds.totalHits);
for (ScoreDoc item : tds.scoreDocs) {
Document doc = indexSearcher.doc(item.doc);
Calendar cal = Calendar.getInstance();
cal.setTimeInMillis(Long.valueOf(doc.get("date")));
System.out.println("名字:" + doc.get("name") + "邮箱:" + doc.get("email") + "id:" + doc.get("id") + "附件个数:"
+ doc.get("attach") + "日期:" + cal.getTime().toString());
}
} catch (Exception e) {
e.printStackTrace();
} finally {
if (indexReader != null)
try {
indexReader.close();
} catch (IOException e) {
e.printStackTrace();
}
}
}
连接多个子查询:
public void searchByBoolean(int num) {
IndexSearcher indexSearcher = getSearcher();
BooleanQuery.Builder booleanBuild = new BooleanQuery.Builder();
// 名字中含有mick,并且内容含有game的
/**
* BooleanQuery可以连接多个子查询
* Occur.MUST:必须出现(相当于数据库的and)
* Occur.SHOULD:表示可以出现(相当于数据库的or)
* Occur.MUSTNOT:不能出现(相当于数据库的not)
*/
booleanBuild.add(new TermQuery(new Term("name", "mick")), Occur.MUST);
booleanBuild.add(new TermQuery(new Term("content", "game")), Occur.MUST);
BooleanQuery booleanQuery = booleanBuild.build();
try {
TopDocs tds = indexSearcher.search(booleanQuery, 10);
System.out.println("一共查询了:" + tds.totalHits);
for (ScoreDoc item : tds.scoreDocs) {
Document doc = indexSearcher.doc(item.doc);
Calendar cal = Calendar.getInstance();
cal.setTimeInMillis(Long.valueOf(doc.get("date")));
System.out.println("名字:" + doc.get("name") + "邮箱:" + doc.get("email") + "id:" + doc.get("id") + "附件个数:"
+ doc.get("attach") + "日期:" + cal.getTime().toString());
}
} catch (Exception e) {
e.printStackTrace();
} finally {
if (indexReader != null)
try {
indexReader.close();
} catch (IOException e) {
e.printStackTrace();
}
}
}
junit测试
