三搜索引擎篇-lucene入门代码示例

Posted 2021-04-24 java潇邦

一、lucene是什么？

最受欢迎的java开源全文搜索引擎开发工具包。提供了完整的查询引擎和索引引擎， 部分文本分词引擎。Lucene的目的是为软件开发人员提供一个简单易用的工具包， 以方便在目标系统中实现全文检索功能， 或者是以此为基础建立起完整的全文检索引擎。

二、lucene代码示例：

package com.javaxiaobang.es.lucene;
import com.alibaba.fastjson.JSON;import com.alibaba.fastjson.JSONObject;import com.alibaba.fastjson.util.IOUtils;import com.javaxiaobang.es.constant.EsConstants;import org.apache.lucene.analysis.Analyzer;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.DirectoryReader;import org.apache.lucene.index.IndexReader;import org.apache.lucene.index.IndexWriter;import org.apache.lucene.index.IndexWriterConfig;import org.apache.lucene.index.IndexableField;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.nio.file.Paths;import java.util.List;import java.util.Map;import java.util.Set;
/** * 功 能：lucene * 作 者：java潇邦 * 时 间：2020/5/4 */public class LuceneMain {
 /** * 源码地址：https://gitee.com/sunrisexq/es */ public static void main(String[] args) { //1、创建索引 createIndex(EsConstants.INDEX_DATA_DIR); //2、添加索引文档 addIndexDoc(EsConstants.INDEX_DATA_DIR, EsConstants.JSON_CONTENT); //3、查询内容 query(EsConstants.INDEX_DATA_DIR, "歌手","杰伦"); }
 /** * 创建索引 * * @param indexDir 索引存放位置 */ public static void createIndex(String indexDir) { IndexWriter writer = null; try { //获取目录 Directory directory = FSDirectory.open(Paths.get(indexDir)); //设置分词器 Analyzer analyzer = new StandardAnalyzer(); //准备config IndexWriterConfig indexWriterConfig = new IndexWriterConfig(analyzer); //创建lucene实例 writer = new IndexWriter(directory, indexWriterConfig); System.out.println("索引创建成功"); } catch (Exception e) { e.printStackTrace(); } finally { IOUtils.close(writer); } }
 /** * 添加索引文档 * * @param indexDir 索引存放位置 * @param jsonContent json内容 */ public static void addIndexDoc(String indexDir, String jsonContent) { IndexWriter writer = null; try { //获取目录 Directory directory = FSDirectory.open(Paths.get(indexDir)); //设置分词器 Analyzer analyzer = new StandardAnalyzer(); //准备config IndexWriterConfig indexWriterConfig = new IndexWriterConfig(analyzer); //创建lucene实例 writer = new IndexWriter(directory, indexWriterConfig); Document document = jsonToDoc(jsonContent); writer.addDocument(document); System.out.println("索引文档添加成功"); } catch (Exception e) { e.printStackTrace(); } finally { IOUtils.close(writer); } }
 /** * json内容转document文档 * * @param jsonContent json内容 * @return */ public static Document jsonToDoc(String jsonContent) { Document document = new Document(); JSONObject jsonObj = JSONObject.parseObject(jsonContent); Set<Map.Entry<String, Object>> entrySet = jsonObj.entrySet(); for (Map.Entry<String, Object> entry : entrySet) { document.add(new TextField(entry.getKey(), entry.getValue() == null ? "" : entry.getValue().toString(), Field.Store.YES)); } return document; }
 /** * 查询文档 * @param indexDir 索引存放位置 * @param queryParam 查询条件 * @param queryContent 查询单词内容 * @return */ public static String query(String indexDir, String queryParam, String queryContent) { StringBuilder result = new StringBuilder(); IndexReader reader = null; try { //获取目录 Directory directory = FSDirectory.open(Paths.get((indexDir))); //获取reader reader = DirectoryReader.open(directory); //获取索引实例 IndexSearcher searcher = new IndexSearcher(reader); //设置分词器 Analyzer analyzer = new StandardAnalyzer(); //创建解析器 QueryParser queryParser = new QueryParser(queryParam, analyzer); Query query = queryParser.parse(queryContent); TopDocs topDocs = searcher.search(query, 10); System.out.println("topDocs内容:" + JSON.toJSONString(topDocs)); for (ScoreDoc scoreDoc : topDocs.scoreDocs) { //拿到文档实例 Document document = searcher.doc(scoreDoc.doc); //获取所有文档字段 List<IndexableField> fieldList = document.getFields(); //处理文档字段 for (IndexableField field:fieldList){ result.append(field.name()); result.append(":"); result.append(field.stringValue()); result.append(",\r\n"); } } System.out.println("查询结果："+result); } catch (Exception e) { e.printStackTrace(); }finally { IOUtils.close(reader); } return result.toString(); }
}

https://gitee.com/sunrisexq/es