SpringBoot集成Lucene
需要编写的类大概如下
首先是pom.xml
<!-- Lucene --> <!--核心包--> <dependency> <groupId>org.apache.lucene</groupId> <artifactId>lucene-core</artifactId> <version>7.6.0</version> </dependency> <!--对分词索引查询解析--> <dependency> <groupId>org.apache.lucene</groupId> <artifactId>lucene-queryparser</artifactId> <version>7.6.0</version> </dependency> <!--一般分词器，适用于英文分词--> <dependency> <groupId>org.apache.lucene</groupId> <artifactId>lucene-analyzers-common</artifactId> <version>7.6.0</version> </dependency> <!--检索关键字高亮显示 --> <dependency> <groupId>org.apache.lucene</groupId> <artifactId>lucene-highlighter</artifactId> <version>7.6.0</version> </dependency> <!-- smartcn中文分词器 --> <dependency> <groupId>org.apache.lucene</groupId> <artifactId>lucene-analyzers-smartcn</artifactId> <version>7.6.0</version> </dependency>
application.properties，配置索引文件的存放位置
#Lucene索引位置 Lucene.Index.Path=D:/java_test/Lucene
LuceneConfig.java，Lucene的Bean
import java.io.File;
import java.io.IOException;
import java.nio.file.Path;
import java.nio.file.Paths;
import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.cn.smart.SmartChineseAnalyzer;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.index.IndexWriterConfig;
import org.apache.lucene.search.ControlledRealTimeReopenThread;
import org.apache.lucene.search.SearcherFactory;
import org.apache.lucene.search.SearcherManager;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.FSDirectory;
import org.springframework.beans.factory.annotation.Value;
import org.springframework.context.annotation.Bean;
import org.springframework.context.annotation.Configuration;
@Configuration
public class LuceneConfig {
/**
* lucene索引,存放位置
*/
@Value("${Lucene.Index.Path}")
private String LUCENE_INDEX_PATH/* = "D:\\java_test\\Lucene" */;
/**
* 创建一个 Analyzer 实例
*
* @return
*/
@Bean
public Analyzer analyzer() {
return new SmartChineseAnalyzer();
}
/**
* 索引位置
*
* @return
* @throws IOException
*/
@Bean
public Directory directory() throws IOException {
Path path = Paths.get(LUCENE_INDEX_PATH);
File file = path.toFile();
if(!file.exists()) {
//如果文件夹不存在,则创建
file.mkdirs();
}
return FSDirectory.open(path);
}
/**
* 创建indexWriter
*
* @param directory
* @param analyzer
* @return
* @throws IOException
*/
@Bean
public IndexWriter indexWriter(Directory directory, Analyzer analyzer) throws IOException {
IndexWriterConfig indexWriterConfig = new IndexWriterConfig(analyzer);
IndexWriter indexWriter = new IndexWriter(directory, indexWriterConfig);
// 清空索引
indexWriter.deleteAll();
indexWriter.commit();
return indexWriter;
}
/**
* SearcherManager管理
*
* @param directory
* @return
* @throws IOException
*/
@Bean
public SearcherManager searcherManager(Directory directory, IndexWriter indexWriter) throws IOException {
SearcherManager searcherManager = new SearcherManager(indexWriter, false, false, new SearcherFactory());
ControlledRealTimeReopenThread cRTReopenThead = new ControlledRealTimeReopenThread(indexWriter, searcherManager,
5.0, 0.025);
cRTReopenThead.setDaemon(true);
//线程名称
cRTReopenThead.setName("更新IndexReader线程");
// 开启线程
cRTReopenThead.start();
return searcherManager;
}
}LuceneDaoImpl.java，自己的逻辑，初始化索引、更新索引、删除索引
import java.io.IOException;
import java.util.ArrayList;
import java.util.List;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.document.StringField;
import org.apache.lucene.document.TextField;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.index.Term;
import org.springframework.beans.factory.annotation.Autowired;
import org.springframework.stereotype.Component;
import com.daimeng.framework.lucene.LuceneDao;
import com.daimeng.web.article.entity.ArticleInfo;
@Component
public class LuceneDaoImpl implements LuceneDao{
@Autowired
private IndexWriter indexWriter;
/**
*
* @功能描述: 创建索引
* StringField-字符串：构建一个字符串的Field,但不会进行分词,将整串字符串存入索引中,适合存储固定(id,身份证号,订单号等)
* FloatPoint、LongPoint、DoublePoint-数值型：这个Field用来构建一个float数字型Field，进行分词和索引，比如(价格)
* StoredField-重载方法、支持多种类型：这个Field用来构建不同类型Field,不分析，不索引，但要Field存储在文档中
* TextField-字符串或者流：一般此对字段需要进行检索查询
* @方法名称: createArticleIndex
* @路径 com.daimeng.framework.lucene
* @作者 daimeng.fun
* @E-Mail sephy9527@qq.com
* @创建时间 2020年10月4日 下午8:04:43
* @version V1.0
* @param list
* @throws IOException
* @return void
*/
@Override
public void createArticleIndex(ArrayList<ArticleInfo> list) throws IOException {
List<Document> docs = new ArrayList<Document>();
for (ArticleInfo obj : list) {
Document doc = new Document();
doc.add(new StringField("id", obj.getId()+"", Field.Store.YES));
// doc.add(new TextField("title", obj.getTitle(), Field.Store.YES));
// doc.add(new TextField("shortContext", obj.getShortContext(), Field.Store.YES));
// doc.add(new TextField("context", obj.getContext(), Field.Store.YES));
doc.add(new TextField("text", obj.getTitle() + obj.getShortContext() + obj.getContext(), Field.Store.YES));
// doc.add(new TextField("articleType", obj.getArticleType(), Field.Store.YES));
// doc.add(new TextField("realname", obj.getCreateUser().getRealname(), Field.Store.YES));
// doc.add(new TextField("createTm", DateUtils.getDateStrFormat(obj.getCreateTm(), DateUtils.YYYY_MM_DDHH_MM_SS), Field.Store.YES));
// // 保存price,
// float price = p.getPrice();
// // 建立倒排索引
// doc.add(new FloatPoint("price", price));
// // 正排索引用于排序、聚合
// doc.add(new FloatDocValuesField("price", price));
// // 存储到索引库
// doc.add(new StoredField("price", price));
// doc.add(new TextField("place", p.getPlace(), Field.Store.YES));
// doc.add(new StringField("code", p.getCode(), Field.Store.YES));
docs.add(doc);
}
//将文档放在内存中,并没有放入索引库
indexWriter.addDocuments(docs);
//提交索引到索引库
indexWriter.commit();
}
@Override
public void reflushArticleInfoIndex(ArticleInfo obj) throws IOException{
indexWriter.deleteDocuments(new Term("id",obj.getId()+""));
Document doc = new Document();
doc.add(new StringField("id", obj.getId()+"", Field.Store.YES));
doc.add(new TextField("text", obj.getTitle() + obj.getShortContext() + obj.getContext(), Field.Store.YES));
indexWriter.addDocument(doc);
indexWriter.commit();
}
@Override
public void deleteArticleInfoIndex(ArticleInfo obj) throws IOException {
indexWriter.deleteDocuments(new Term("id",obj.getId()+""));
}
}LuceneServiceImpl.java，自己的逻辑，主要是搜索逻辑
import java.util.ArrayList;
import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.index.Term;
import org.apache.lucene.queryparser.classic.QueryParser;
import org.apache.lucene.search.BooleanClause.Occur;
import org.apache.lucene.search.BooleanQuery;
import org.apache.lucene.search.BooleanQuery.Builder;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.ScoreDoc;
import org.apache.lucene.search.SearcherManager;
import org.apache.lucene.search.Sort;
import org.apache.lucene.search.TermQuery;
import org.apache.lucene.search.TopDocs;
import org.springframework.beans.factory.annotation.Autowired;
import org.springframework.stereotype.Service;
import com.daimeng.framework.lucene.LuceneService;
import com.daimeng.util.Constants;
import com.daimeng.web.article.entity.ArticleInfo;
import com.daimeng.web.article.service.ArticleService;
import com.github.pagehelper.PageInfo;
@Service
public class LuceneServiceImpl implements LuceneService{
@Autowired
private Analyzer analyzer;
@Autowired
private SearcherManager searcherManager;
@Autowired
private ArticleService articleService;
@Override
public PageInfo<ArticleInfo> searchArticle(String keywords, int page) throws Exception {
//新searcherManager中的searcher,获取到最新的IndexSearcher
searcherManager.maybeRefresh();
IndexSearcher indexSearcher = searcherManager.acquire();
// Map<String, String> queryParam = new HashMap<String, String>();
// for(String str : keywords) {
// queryParam.put("title", str);
// queryParam.put("shortContext", str);
// queryParam.put("context", str);
// }
Builder builder = new BooleanQuery.Builder();
Sort sort = new Sort();
// 排序规则
//com.infinova.yimall.entity.Sort sort1 = pageQuery.getSort();
// if (sort1 != null && sort1.getOrder() != null) {
// if ("ASC".equals((sort1.getOrder()).toUpperCase())) {
// sort.setSort(new SortField(sort1.getField(), SortField.Type.FLOAT, false));
// } else if ("DESC".equals((sort1.getOrder()).toUpperCase())) {
// sort.setSort(new SortField(sort1.getField(), SortField.Type.FLOAT, true));
// }
// }
if (keywords != null) {
// 输入空格,不进行模糊查询
if (!"".equals(keywords.replaceAll(" ", ""))) {
// 模糊匹配,匹配词
builder.add(new QueryParser("text", analyzer).parse(keywords), Occur.MUST);
// builder.add(new QueryParser("title", analyzer).parse(keywords), Occur.MUST);
// builder.add(new QueryParser("shortContext", analyzer).parse(keywords), Occur.MUST);
// builder.add(new QueryParser("context", analyzer).parse(keywords), Occur.MUST);
// builder.add(new QueryParser("realname", analyzer).parse(keywords), Occur.MUST);
// 精确查询
//builder.add(new TermQuery(new Term("id", keywords)), Occur.MUST);
}
}
// if (queryParam.get("lowerPrice") != null && queryParam.get("upperPrice") != null) {
// // 价格范围查询
// builder.add(FloatPoint.newRangeQuery("price", Float.parseFloat(queryParam.get("lowerPrice")),
// Float.parseFloat(queryParam.get("upperPrice"))), Occur.MUST);
// }
TopDocs topDocs = indexSearcher.search(builder.build(), page * Constants.PAGE_SIZE_10, sort);
ArrayList<ArticleInfo> list = new ArrayList<ArticleInfo>();
ScoreDoc[] hits = topDocs.scoreDocs;
for (int i = (page - 1) * Constants.PAGE_SIZE_10; i < hits.length; i++) {
Document doc = indexSearcher.doc(hits[i].doc);
System.out.println(doc.toString());
ArticleInfo info = articleService.findArticleInfoById(Integer.parseInt(doc.get("id")));
// info.setId(Integer.parseInt(doc.get("id")));
// info.setTitle(doc.get("title"));
// info.setShortContext(doc.get("shortContext"));
// info.setContext(doc.get("context"));
list.add(info);
}
PageInfo<ArticleInfo> pi = new PageInfo<ArticleInfo>(list);
pi.setPageNum(page);
pi.setSize(list.size());
pi.setPageSize(Constants.PAGE_SIZE_10);
pi.setTotal(topDocs.totalHits);
Long pages = 0L;
if(topDocs.totalHits % Constants.PAGE_SIZE_10 > 0) {
pages = (Long) (topDocs.totalHits / Constants.PAGE_SIZE_10) + 1;
}else {
pages = (Long) (topDocs.totalHits / Constants.PAGE_SIZE_10);
}
pi.setPages(Integer.valueOf(pages.toString()));
return pi;
}
}InitArticleIndexOrderRunner.java，启动后运行的OrderRunner，为了启动后初始化索引
import org.springframework.beans.factory.annotation.Autowired;
import org.springframework.boot.CommandLineRunner;
import org.springframework.core.annotation.Order;
import org.springframework.stereotype.Component;
import com.daimeng.util.Constants;
import com.daimeng.web.article.service.ArticleService;
/**
*
* @功能描述: 项目启动后立即执行
* @名称: InitArticleIndexOrderRunner.java
* @路径 com.daimeng.framework.lucene
* @作者 daimeng.fun
* @E-Mail sephy9527@qq.com
* @创建时间 2020年10月4日 下午7:51:04
* @version V1.0
*/
@Component
@Order(1)
public class InitArticleIndexOrderRunner implements CommandLineRunner {
@Autowired
private ArticleService articleService;
@Override
public void run(String... args) throws Exception {
Constants.println("The OrderRunner1 start to initialize ...");
articleService.synAllArticleInfo();
}
}同步方法如下，查询出需要存入索引的内容列表，然后调用LuceneDao的初始化方法
@Override
public void synAllArticleInfo() {
try {
ArrayList<ArticleInfo> all = articleRepository.findByArticleTypeAndStatusCdOrderByIdDesc("01",1);
luceneDao.createArticleIndex(all);
} catch (Exception e) {
e.printStackTrace();
}
}启动项目后，会初始化索引文件
至此，旧成功了，然后开发页面去调用LuceneService的searchArticle方法即可