Lucene全文检索学习笔记（一）：lucene的应用

1. Lucene的使用

---

1.1 引入Jar包

        <dependency>
<groupId>org.apache.lucene</groupId>
<artifactId>lucene-core</artifactId>
<version>6.5.0</version>
</dependency>
<dependency>
<groupId>org.apache.lucene</groupId>
<artifactId>lucene-queryparser</artifactId>
<version>6.6.0</version>
</dependency>

• Lucene-core-6.5.0.jar 常用的文档，索引，搜索，存储等相关核心代码。
• Lucene-queryparser-6.6.0.jar 提供了搜索相关的代码，用于各种搜索，比如模糊搜索，范围搜索

1.2 生成索引

package com.infinova.system.service.test;

import java.io.IOException;
import java.nio.file.FileSystems;
import java.util.List;

import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.document.TextField;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.index.IndexWriterConfig;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.FSDirectory;

import com.alibaba.fastjson.JSON;
import com.infinova.system.pojo.ResourceZonning;

public class LuceneTest {
public void Index(List<ResourceZonning> rz) {
        IndexWriterConfig cfg = new IndexWriterConfig(new StandardAnalyzer());

try {
            Directory directory = FSDirectory.open(FileSystems.getDefault().getPath("D:/index/"));
            IndexWriter writer = new IndexWriter(directory, cfg);
            writer.deleteAll(); // 清除以前的index
for (ResourceZonning resourceZonning : rz) {
                Document doc = new Document();
                doc.add(new TextField("id", resourceZonning.getResId(), Field.Store.YES));
                doc.add(new TextField("json", JSON.toJSONString(resourceZonning), Field.Store.YES));
                writer.addDocument(doc);
            }
            writer.close();
        } catch (IOException e) {
            System.out.println(e);
        }
    }
}

1.3 搜索

package com.infinova.system.service.test;

import java.io.IOException;
import java.nio.file.FileSystems;

import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
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;

public class IndexSearch {
private static void doSearch(Query query) {
// 创建IndexSearcher
// 指定索引库的地址
try {
                Directory directory = FSDirectory.open(FileSystems.getDefault().getPath("D:/index/"));
                IndexReader reader = DirectoryReader.open(directory);
                IndexSearcher searcher = new IndexSearcher(reader);
                TopDocs topDocs = searcher.search(query, 20);
// 根据查询条件匹配出的记录总数
int count = topDocs.totalHits;
                System.out.println("匹配总数:" + count);
// 根据查询条件匹配出的记录
                ScoreDoc[] scoreDocs = topDocs.scoreDocs;
for (ScoreDoc scoreDoc : scoreDocs) {
int docId = scoreDoc.doc;
                    Document doc = searcher.doc(docId);
                    System.out.println("资源ID：" + doc.get("id"));
                    System.out.println("资源json：" + doc.get("json"));
                    System.out.println("==========================");
                }
                reader.close();
            } catch (IOException e) {
                e.printStackTrace();
            }
        }
public static void main(String[] args) throws ParseException {
        Analyzer analyzer = new StandardAnalyzer();
// 使用QueryParser搜索时，需要指定分词器，搜索时的分词器要和索引时的分词器一致
        QueryParser parser = new QueryParser("json", analyzer);
// 通过queryparser来创建query对象 详细语法会在后面一章解释
        Query query = parser.parse("1.1.1*");
        doSearch(query);
    }
}