2.5、Lucene查询详解

---

---

目录

2.5.1、搜索入门

2.5.2、多域搜索（MultiFieldQueryParse）

2.5.3、词项搜索（TermQuery）

2.5.4、布尔搜索（BooleanQuery）

2.5.5、范围搜索（RangeQuery）

2.5.6、前缀搜索（PrefixQuery）

2.5.7、多关键字搜索（PhraseQuery）

2.5.8、模糊搜索（FuzzyQuery）

2.5.9、通配符搜索（WildcardQuery）

-—————————————————

文档索引完成以后就能对其进行搜索；

当用户输入一个关键字，

​ –> 首先 对这个关键字 进行 分析和处理， 转化成后台可以理解的形式

​ –> 进行检索

2.5.1、搜索入门

处理关键词 <==> 构建Query对象的过程；

搜索文档 <==> 实例化 IndexSearcher 对象，使用search()方法完成；

​ 参数：Query对象

​ 结果：保存在 TopDocs 类型的文档集合中；

删除indexdir下的索引文件后，重新使用CreateIndex.java 生成索引

package com.learn.lucene.chapter2.queries;

import com.learn.lucene.chapter2.ik.IKAnalyzer8x;
import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.index.DirectoryReader;
import org.apache.lucene.index.IndexReader;
import org.apache.lucene.queryparser.classic.ParseException;
import org.apache.lucene.queryparser.classic.QueryParser;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.Query;
import org.apache.lucene.search.ScoreDoc;
import org.apache.lucene.search.TopDocs;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.FSDirectory;

import java.io.IOException;
import java.nio.file.Path;
import java.nio.file.Paths;

/**
 * 2.5.1、查询
 */
public class QueryParseTest {
	public static void main(String[] args) throws IOException, ParseException {
		String field = "title";
		Path indexPath = Paths.get("indexdir");
		Directory directory = FSDirectory.open(indexPath);
		IndexReader reader = DirectoryReader.open(directory);
		IndexSearcher searcher = new IndexSearcher(reader);
		Analyzer analyzer = new IKAnalyzer8x();
		QueryParser parser = new QueryParser(field, analyzer);
		parser.setDefaultOperator(QueryParser.Operator.AND);
		Query query = parser.parse("农村学生");
		System.out.println("Query: " + query.toString());  // 查询关键词
		// 返回前10条
		TopDocs topDocs = searcher.search(query, 10);
		for (ScoreDoc scoreDoc : topDocs.scoreDocs) {
			Document doc = searcher.doc(scoreDoc.doc);
			System.out.println("DocID: " + scoreDoc.doc);
			System.out.println("id: " + doc.get("id"));
			System.out.println("title: " + doc.get("title"));
			System.out.println("文档评分: " + scoreDoc.score);
		}
		directory.close();
		reader.close();
	}

}

运行结果：

修改后再运行：

​

2.5.2、多域搜索（MultiFieldQueryParse）

根据多个字段搜索

package com.learn.lucene.chapter2.queries;

import com.learn.lucene.chapter2.ik.IKAnalyzer8x;
import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.index.DirectoryReader;
import org.apache.lucene.index.IndexReader;
import org.apache.lucene.queryparser.classic.MultiFieldQueryParser;
import org.apache.lucene.queryparser.classic.ParseException;
import org.apache.lucene.queryparser.classic.QueryParser;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.Query;
import org.apache.lucene.search.ScoreDoc;
import org.apache.lucene.search.TopDocs;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.FSDirectory;

import java.io.IOException;
import java.nio.file.Path;
import java.nio.file.Paths;

/**
 * 2.5.2、多域搜索
 */
public class MultiFieldQueryParseTest {
	public static void main(String[] args) throws IOException, ParseException {
		String[] field = {"title", "content"};
		Path indexPath = Paths.get("indexdir");
		Directory directory = FSDirectory.open(indexPath);
		IndexReader reader = DirectoryReader.open(directory);
		IndexSearcher searcher = new IndexSearcher(reader);
		Analyzer analyzer = new IKAnalyzer8x(true);
		MultiFieldQueryParser parser = new MultiFieldQueryParser(field, analyzer);
		parser.setDefaultOperator(QueryParser.Operator.AND);
		Query query = parser.parse("美国");
		System.out.println("Query: " + query.toString());  // 查询关键词
		// 返回前10条
		TopDocs topDocs = searcher.search(query, 10);
		for (ScoreDoc scoreDoc : topDocs.scoreDocs) {
			Document doc = searcher.doc(scoreDoc.doc);
			System.out.println("DocID: " + scoreDoc.doc);
			System.out.println("id: " + doc.get("id"));
			System.out.println("title: " + doc.get("title"));
			System.out.println("content: " + doc.get("content"));
			System.out.println("文档评分: " + scoreDoc.score);
		}
		directory.close();
		reader.close();
	}
}

运行结果：

​

2.5.3、词项搜索（TermQuery）

TermQuery 是 最常用的 Query

TermQuery 是 Lucene中搜索的最基本单位

本质上：一个词条就是一个 key/value 对

使用TermQuery：

• 首先构造一个 Term对象；Term term = new Term(“title”, “美国”);
• 然后使用Term对象为参数，构造一个TermQuery对象；TermQuery query = new TermQuery(term);

package com.learn.lucene.chapter2.queries;

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.queryparser.classic.ParseException;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.ScoreDoc;
import org.apache.lucene.search.TermQuery;
import org.apache.lucene.search.TopDocs;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.FSDirectory;

import java.io.IOException;
import java.nio.file.Path;
import java.nio.file.Paths;

/**
 * 2.5.3 词项搜索
 */
public class TermQueryTest {
	public static void main(String[] args) throws IOException, ParseException {

		Path indexPath = Paths.get("indexdir");
		Directory directory = FSDirectory.open(indexPath);
		IndexReader reader = DirectoryReader.open(directory);
		IndexSearcher searcher = new IndexSearcher(reader);
		Term term = new Term("title", "美国");
		TermQuery query = new TermQuery(term);
		System.out.println("Query: " + query.toString());  // 查询关键词
		// 返回前10条
		TopDocs topDocs = searcher.search(query, 10);
		for (ScoreDoc scoreDoc : topDocs.scoreDocs) {
			Document doc = searcher.doc(scoreDoc.doc);
			System.out.println("DocID: " + scoreDoc.doc);
			System.out.println("id: " + doc.get("id"));
			System.out.println("title: " + doc.get("title"));
			System.out.println("文档评分: " + scoreDoc.score);
		}
		directory.close();
		reader.close();
	}
}

运行结果：

​

2.5.4、布尔搜索（BooleanQuery）

BooleanQuery 可以 组合 其他 Query，并标明他们的逻辑关系；

例如：查询 content 中包含美国，并且 title 不包含美国的文档；

package com.learn.lucene.chapter2.queries;

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.queryparser.classic.ParseException;
import org.apache.lucene.search.*;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.FSDirectory;

import java.io.IOException;
import java.nio.file.Path;
import java.nio.file.Paths;

/**
 * 2.5.4、布尔搜索（BooleanQuery）
 * 查询 content 中包含美国，并且 title 不包含美国的文档；
 */
public class BooleanQueryTest {
	public static void main(String[] args) throws IOException, ParseException {
		Path indexPath = Paths.get("indexdir");
		Directory directory = FSDirectory.open(indexPath);
		IndexReader reader = DirectoryReader.open(directory);
		IndexSearcher searcher = new IndexSearcher(reader);
		TermQuery query1 = new TermQuery(new Term("title", "美国"));
		TermQuery query2 = new TermQuery(new Term("content", "美国"));
		BooleanClause booleanClause1 = new BooleanClause(query1, BooleanClause.Occur.MUST_NOT);
		BooleanClause booleanClause2 = new BooleanClause(query2, BooleanClause.Occur.MUST);
		BooleanQuery query = new BooleanQuery.Builder().add(booleanClause1).add(booleanClause2).build();

		System.out.println("Query: " + query.toString());  // 查询关键词
		// 返回前10条
		TopDocs topDocs = searcher.search(query, 10);
		for (ScoreDoc scoreDoc : topDocs.scoreDocs) {
			Document doc = searcher.doc(scoreDoc.doc);
			System.out.println("DocID: " + scoreDoc.doc);
			System.out.println("id: " + doc.get("id"));
			System.out.println("title: " + doc.get("title"));
			System.out.println("content: " + doc.get("content"));
			System.out.println("文档评分: " + scoreDoc.score);
		}
		directory.close();
		reader.close();
	}

}

运行结果：

​

2.5.5、范围搜索（RangeQuery）

举例：查询新闻回复条数在 500~1000 之间的文档

package com.learn.lucene.chapter2.queries;

import org.apache.lucene.document.Document;
import org.apache.lucene.document.IntPoint;
import org.apache.lucene.index.DirectoryReader;
import org.apache.lucene.index.IndexReader;
import org.apache.lucene.queryparser.classic.ParseException;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.Query;
import org.apache.lucene.search.ScoreDoc;
import org.apache.lucene.search.TopDocs;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.FSDirectory;

import java.io.IOException;
import java.nio.file.Path;
import java.nio.file.Paths;

/**
 * 2.5.5、范围搜索（RangeQuery）
 * 举例：查询新闻回复条数在 500~1000 之间的文档
 */
public class RangeQueryTest {
	public static void main(String[] args) throws IOException, ParseException {

		Path indexPath = Paths.get("indexdir");
		Directory directory = FSDirectory.open(indexPath);
		IndexReader reader = DirectoryReader.open(directory);
		IndexSearcher searcher = new IndexSearcher(reader);
		Query query = IntPoint.newRangeQuery("reply", 500, 1000);
		System.out.println("Query: " + query.toString());  // 查询关键词
		// 返回前10条
		TopDocs topDocs = searcher.search(query, 10);
		for (ScoreDoc scoreDoc : topDocs.scoreDocs) {
			Document doc = searcher.doc(scoreDoc.doc);
			System.out.println("DocID: " + scoreDoc.doc);
			System.out.println("id: " + doc.get("id"));
			System.out.println("title: " + doc.get("title"));
			System.out.println("content: " + doc.get("content"));
			System.out.println("reply: " + doc.get("reply_display"));
			System.out.println("文档评分: " + scoreDoc.score);
		}
		directory.close();
		reader.close();
	}
}

​

2.5.6、前缀搜索（PrefixQuery）

举例：搜索 包含以“学”开头的词项 的文档

package com.learn.lucene.chapter2.queries;

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.queryparser.classic.ParseException;
import org.apache.lucene.search.*;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.FSDirectory;

import java.io.IOException;
import java.nio.file.Path;
import java.nio.file.Paths;

/**
 * 2.5.6、前缀搜索（PrefixQuery）
 * 举例：搜索 包含以“学”开头的词项 的文档
 */
public class PrefixQueryTest {
	public static void main(String[] args) throws IOException, ParseException {

		Path indexPath = Paths.get("indexdir");
		Directory directory = FSDirectory.open(indexPath);
		IndexReader reader = DirectoryReader.open(directory);
		IndexSearcher searcher = new IndexSearcher(reader);
		Term term = new Term("title", "学");
		Query query = new PrefixQuery(term);
		System.out.println("Query: " + query.toString());  // 查询关键词
		// 返回前10条
		TopDocs topDocs = searcher.search(query, 10);
		for (ScoreDoc scoreDoc : topDocs.scoreDocs) {
			Document doc = searcher.doc(scoreDoc.doc);
			System.out.println("DocID: " + scoreDoc.doc);
			System.out.println("id: " + doc.get("id"));
			System.out.println("title: " + doc.get("title"));
			System.out.println("文档评分: " + scoreDoc.score);
		}
		directory.close();
		reader.close();
	}
}

运行结果：

​

2.5.7、多关键字搜索（PhraseQuery）

• PhraseQuery 可以 通过add方法添加多个关键字
• 还可以通过 setSlop() 设定“坡度”，允许关键字之间 无关词汇存在量

package com.learn.lucene.chapter2.queries;

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.queryparser.classic.ParseException;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.PhraseQuery;
import org.apache.lucene.search.ScoreDoc;
import org.apache.lucene.search.TopDocs;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.FSDirectory;

import java.io.IOException;
import java.nio.file.Path;
import java.nio.file.Paths;

/**
 * 2.5.7、多关键字搜索（PhraseQuery）
 * PhraseQuery 可以 通过add方法添加多个关键字
 * 还可以通过 setSlop() 设定“坡度”，允许关键字之间 无关词汇存在量
 */
public class PhraseQueryTest {
	public static void main(String[] args) throws IOException, ParseException {
		String str = "习近平会见奥巴马，学习国外经验";

		Path indexPath = Paths.get("indexdir");
		Directory directory = FSDirectory.open(indexPath);
		IndexReader reader = DirectoryReader.open(directory);
		IndexSearcher searcher = new IndexSearcher(reader);
		PhraseQuery.Builder builder = new PhraseQuery.Builder();
		builder.add(new Term("title", "奥巴马"), str.indexOf("奥巴马"));
		builder.add(new Term("title", "学习国外经验"), str.indexOf("学习国外经验"));
		PhraseQuery query = builder.build();
		System.out.println("Query: " + query.toString());  // 查询关键词
		// 返回前10条
		TopDocs topDocs = searcher.search(query, 10);
		for (ScoreDoc scoreDoc : topDocs.scoreDocs) {
			Document doc = searcher.doc(scoreDoc.doc);
			System.out.println("DocID: " + scoreDoc.doc);
			System.out.println("id: " + doc.get("id"));
			System.out.println("title: " + doc.get("title"));
			System.out.println("content: " + doc.get("content"));
			System.out.println("reply: " + doc.get("reply_display"));
			System.out.println("文档评分: " + scoreDoc.score);
		}
		directory.close();
		reader.close();
	}
}

运行结果(感觉没有成功)：

​

2.5.8、模糊搜索（FuzzyQuery）

它可以简单的识别两个相近的词语。

举例：“Trump”，写成“Trmp”，拼写错误，仍然可以搜索得到正确的结果

package com.learn.lucene.chapter2.queries;

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.queryparser.classic.ParseException;
import org.apache.lucene.search.*;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.FSDirectory;

import java.io.IOException;
import java.nio.file.Path;
import java.nio.file.Paths;

/**
 * 2.5.8、模糊搜索（FuzzyQuery）
 * 它可以简单的识别两个相近的词语。
 * 举例：“Trump”，写成“Trmp”，拼写错误，仍然可以搜索得到正确的结果
 */
public class FuzzyQueryTest {
	public static void main(String[] args) throws IOException, ParseException {
		Path indexPath = Paths.get("indexdir");
		Directory directory = FSDirectory.open(indexPath);
		IndexReader reader = DirectoryReader.open(directory);
		IndexSearcher searcher = new IndexSearcher(reader);
		Query query = new FuzzyQuery(new Term("title", "Trmp"));
		System.out.println("Query: " + query.toString());  // 查询关键词
		// 返回前10条
		TopDocs topDocs = searcher.search(query, 10);
		for (ScoreDoc scoreDoc : topDocs.scoreDocs) {
			Document doc = searcher.doc(scoreDoc.doc);
			System.out.println("DocID: " + scoreDoc.doc);
			System.out.println("id: " + doc.get("id"));
			System.out.println("title: " + doc.get("title"));
			System.out.println("content: " + doc.get("content"));
			System.out.println("reply: " + doc.get("reply_display"));
			System.out.println("文档评分: " + scoreDoc.score);
		}
		directory.close();
		reader.close();
	}
}

​

2.5.9、通配符搜索（WildcardQuery）

package com.learn.lucene.chapter2.queries;

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.queryparser.classic.ParseException;
import org.apache.lucene.search.*;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.FSDirectory;

import java.io.IOException;
import java.nio.file.Path;
import java.nio.file.Paths;

/**
 * 2.5.9、通配符搜索（WildcardQuery）
 */
public class WildcardQueryTest {
	public static void main(String[] args) throws IOException, ParseException {
		Path indexPath = Paths.get("indexdir");
		Directory directory = FSDirectory.open(indexPath);
		IndexReader reader = DirectoryReader.open(directory);
		IndexSearcher searcher = new IndexSearcher(reader);
		Query query = new WildcardQuery(new Term("title", "习?平"));
		System.out.println("Query: " + query.toString());  // 查询关键词
		// 返回前10条
		TopDocs topDocs = searcher.search(query, 10);
		for (ScoreDoc scoreDoc : topDocs.scoreDocs) {
			Document doc = searcher.doc(scoreDoc.doc);
			System.out.println("DocID: " + scoreDoc.doc);
			System.out.println("id: " + doc.get("id"));
			System.out.println("title: " + doc.get("title"));
			System.out.println("content: " + doc.get("content"));
			System.out.println("reply: " + doc.get("reply_display"));
			System.out.println("文档评分: " + scoreDoc.score);
		}
		directory.close();
		reader.close();
	}
}