package cn.tz.lucene;
import java.io.File;
import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.index.IndexReader;
import org.apache.lucene.index.IndexWriterConfig;
import org.apache.lucene.index.Term;
import org.apache.lucene.queryparser.classic.MultiFieldQueryParser;
import org.apache.lucene.queryparser.classic.QueryParser;
import org.apache.lucene.search.BooleanQuery;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.NumericRangeQuery;
import org.apache.lucene.search.Query;
import org.apache.lucene.search.ScoreDoc;
import org.apache.lucene.search.TermQuery;
import org.apache.lucene.search.TopDocs;
import org.apache.lucene.search.BooleanClause.Occur;
import org.apache.lucene.store.FSDirectory;
import org.apache.lucene.util.Version;
import org.junit.Test;
import org.wltea.analyzer.lucene.IKAnalyzer;
public class IndexSearchTest {
@Test
public void testIndexSearch() throws Exception{
//创建分词器
//Analyzer analyzer=new StandardAnalyzer();
Analyzer analyzer=new IKAnalyzer();
FSDirectory directory=FSDirectory.open(new File("d:\\lucene"));
//创建索引和文档的读对象
IndexReader reader=IndexReader.open(directory);
//创建索引的搜索对象
IndexSearcher indexSearcher=new IndexSearcher(reader);
//创建查询对象
//第一个参数:默认搜索域,没有指定搜索域时才使用的
QueryParser queryParser= new QueryParser("fileName",analyzer);
//格式： 域名:搜索关键词
//Query query = queryParser.parse("fileName:apache");
Query query = queryParser.parse("fileName:not exit");
//第一个参数:查询语句对象 第二个参数:显示的数据条数
TopDocs topDocs = indexSearcher.search(query,5);
System.out.println("***** 一共有"+topDocs.totalHits+" 条记录 *****");
//从搜索的结果中获取结果集
ScoreDoc[] scoreDocs = topDocs.scoreDocs;
for(ScoreDoc scoreDoc:scoreDocs){
//获取文档id
int docId = scoreDoc.doc;
//通过文档id从硬盘中读取对应得文件
Document doc = reader.document(docId);
System.out.println("fileName:"+doc.get("fileName"));
System.out.println("fileSize:"+doc.get("fileSize"));
System.out.println("==================================");
}
reader.close();
}
/**
* 使用TermQuery不需要分词器:它是分词后进行查询
* @throws Exception
*/
@Test
public void testTermQuery() throws Exception{
Analyzer analyzer=new IKAnalyzer();
FSDirectory dir=FSDirectory.open(new File("d:\\lucene"));
//读对象
IndexReader reader=IndexReader.open(dir);
//查询对象
Term term=new Term("fileName","apache");
Query query=new TermQuery(term);
//搜索对象
IndexSearcher searcher=new IndexSearcher(reader);
TopDocs topDocs = searcher.search(query, 10);
System.out.println("总条数: "+topDocs.totalHits);
//从查询结果中获取结果集
ScoreDoc[] scoreDocs = topDocs.scoreDocs;
for(ScoreDoc scoreDoc:scoreDocs){
//获取文档ID
int docID = scoreDoc.doc;
//根据文档ID获取文档
Document document = reader.document(docID);
System.out.println("文件名: "+document.get("fileName"));
System.out.println("文件大小 : "+document.get("fileSize"));
System.out.println("======================================");
}
reader.close();
}
/**
* NumericRangeQuery:
* 用于数字范围的查询
* 注意:只针对数字类型的Field域才可以进行检索
* 例如:LongFeild,FloatFeild...
* @throws Exception
*/
@Test
public void testNumericRangeQuery() throws Exception{
Analyzer analyzer=new IKAnalyzer();
//数据源
FSDirectory dir=FSDirectory.open(new File("d:\\lucene"));
IndexReader reader=IndexReader.open(dir);
IndexSearcher search=new IndexSearcher(reader);
//创建query对象
//参数:域名 最小值 最大值 是否包含最小值 是否包含最大值
NumericRangeQuery query=NumericRangeQuery.newLongRange("fileSize",100L,1000L,true,true);
TopDocs topDocs = search.search(query, 10);
System.out.println("文件数量: "+topDocs.totalHits);
//将查询结果转为结果集
ScoreDoc[] scoreDocs = topDocs.scoreDocs;
for(ScoreDoc scoreDoc:scoreDocs){
//获取文档ID
int docID = scoreDoc.doc;
//根据文档ID获取文档
Document doc = reader.document(docID);
System.out.println("文件名称: "+doc.get("fileName"));
System.out.println("文件大小: "+doc.get("fileSize"));
System.out.println("=========================");
}
reader.close();
}
/**
* BooleanQuery:用于多个条件(组合)查询
*
*/
@Test
public void testBooleanQuery() throws Exception{
FSDirectory dir=FSDirectory.open(new File("d:\\lucene"));
IndexReader reader=IndexReader.open(dir);
IndexSearcher searcher=new IndexSearcher(reader);
TermQuery termQuery=new TermQuery(new Term("fileName","apache"));
NumericRangeQuery numericRangeQuery=NumericRangeQuery.newLongRange("fileSize",100L,1000L,true,true);
BooleanQuery booleanQuery=new BooleanQuery();
//Occur:
//MUST:and
//MUST_NOT:not
//Should:or
//查询文件名字包含有apache,文件大小在100-1000bit之内的
booleanQuery.add(termQuery, Occur.MUST);
booleanQuery.add(numericRangeQuery,Occur.MUST);
TopDocs topDocs=searcher.search(booleanQuery, 10);
System.out.println("文件数量 ： "+topDocs.totalHits);
ScoreDoc[] scoreDocs = topDocs.scoreDocs;
for(ScoreDoc scoreDoc:scoreDocs){
int docId = scoreDoc.doc;
Document document = reader.document(docId);
System.out.println("文件名称: "+document.get("fileName"));
System.out.println("文件大小: "+document.get("fileSize"));
System.out.println("==============================");
}
}
/**
* MultiFieldQueryParser:从多个域进行查询
*
*/
@Test
public void testMultiFieldQueryParser() throws Exception{
Analyzer analyzer=new IKAnalyzer();
FSDirectory directory=FSDirectory.open(new File("d:\\lucene"));
IndexReader reader=IndexReader.open(directory);
IndexSearcher searcher=new IndexSearcher(reader);
//需求:查询文件名称和文件内容中包含有"apache"的内容
//从fileName、fileContent域中进行查询
String[] fields={"fileName","fileContent"};
MultiFieldQueryParser multiQueryParser=new MultiFieldQueryParser(fields, analyzer);
Query query = multiQueryParser.parse("apache");
TopDocs topDocs=searcher.search(query, 5);
System.out.println("总记录数： "+topDocs.totalHits);
//根据查询结果返回结果集,并遍历
for(ScoreDoc scoreDoc:topDocs.scoreDocs){
int docId = scoreDoc.doc;
Document doc = reader.document(docId);
System.out.println("文档名称："+doc.get("fileName"));
System.out.println("文档大小："+doc.get("fileSize"));
System.out.println("===============================");
}
}
}
