how2j.cn

-->
下载区
文件名 文件大小
lucene.rar 14m

解压rar如果失败,请用5.21版本或者更高版本的winrar

点击下载 winrar5.21
步骤 1 : 索引删除和更新   
步骤 2 : 先说没有删除前的情形   
步骤 3 : 删除索引   
步骤 4 : 更多删除   
步骤 5 : 更新索引   

步骤 1 :

索引删除和更新

edit
索引建立好了之后,还是需要维护的,比如新增,删除和维护。 新增就是建立索引的过程,这里就不表了,本教材主要讲索引的删除和更新。
索引里的数据,其实就是一个一个的Document 对象,那么本文就是介绍如何删除和更新这些Documen对象。
步骤 2 :

先说没有删除前的情形

edit
直接使用14万条数据 里的代码,不过使用不一样的查询语句。
如图所示,通过关键字 “鞭" 可以查询到一条id是51173的数据。
先说没有删除前的情形
package com.how2java; import java.io.IOException; import java.io.StringReader; import java.util.List; import java.util.Scanner; import org.apache.lucene.analysis.TokenStream; 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.index.Term; 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.highlight.Highlighter; import org.apache.lucene.search.highlight.QueryScorer; import org.apache.lucene.search.highlight.SimpleHTMLFormatter; import org.apache.lucene.store.Directory; import org.apache.lucene.store.RAMDirectory; import org.wltea.analyzer.lucene.IKAnalyzer; public class TestLucene { public static void main(String[] args) throws Exception { // 1. 准备中文分词器 IKAnalyzer analyzer = new IKAnalyzer(); // 2. 索引 Directory index = createIndex(analyzer); // 3. 查询器 Scanner s = new Scanner(System.in); while(true){ System.out.print("请输入查询关键字:"); String keyword = s.nextLine(); System.out.println("当前关键字是:"+keyword); Query query = new QueryParser( "name", analyzer).parse(keyword); // 4. 搜索 IndexReader reader = DirectoryReader.open(index); IndexSearcher searcher=new IndexSearcher(reader); int numberPerPage = 10; ScoreDoc[] hits = searcher.search(query, numberPerPage).scoreDocs; // 5. 显示查询结果 showSearchResults(searcher, hits,query,analyzer); // 6. 关闭查询 reader.close(); } } private static void showSearchResults(IndexSearcher searcher, ScoreDoc[] hits, Query query, IKAnalyzer analyzer) throws Exception { System.out.println("找到 " + hits.length + " 个命中."); SimpleHTMLFormatter simpleHTMLFormatter = new SimpleHTMLFormatter("<span style='color:red'>", "</span>"); Highlighter highlighter = new Highlighter(simpleHTMLFormatter, new QueryScorer(query)); System.out.println("找到 " + hits.length + " 个命中."); System.out.println("序号\t匹配度得分\t结果"); for (int i = 0; i < hits.length; ++i) { ScoreDoc scoreDoc= hits[i]; int docId = scoreDoc.doc; Document d = searcher.doc(docId); List<IndexableField> fields= d.getFields(); System.out.print((i + 1) ); System.out.print("\t" + scoreDoc.score); for (IndexableField f : fields) { if("name".equals(f.name())){ TokenStream tokenStream = analyzer.tokenStream(f.name(), new StringReader(d.get(f.name()))); String fieldContent = highlighter.getBestFragment(tokenStream, d.get(f.name())); System.out.print("\t"+fieldContent); } else{ System.out.print("\t"+d.get(f.name())); } } System.out.println("<br>"); } } private static Directory createIndex(IKAnalyzer analyzer) throws IOException { Directory index = new RAMDirectory(); IndexWriterConfig config = new IndexWriterConfig(analyzer); IndexWriter writer = new IndexWriter(index, config); String fileName = "140k_products.txt"; List<Product> products = ProductUtil.file2list(fileName); int total = products.size(); int count = 0; int per = 0; int oldPer =0; for (Product p : products) { addDoc(writer, p); count++; per = count*100/total; if(per!=oldPer){ oldPer = per; System.out.printf("索引中,总共要添加 %d 条记录,当前添加进度是: %d%% %n",total,per); } } writer.close(); return index; } private static void addDoc(IndexWriter w, Product p) throws IOException { Document doc = new Document(); doc.add(new TextField("id", String.valueOf(p.getId()), Field.Store.YES)); doc.add(new TextField("name", p.getName(), Field.Store.YES)); doc.add(new TextField("category", p.getCategory(), Field.Store.YES)); doc.add(new TextField("price", String.valueOf(p.getPrice()), Field.Store.YES)); doc.add(new TextField("place", p.getPlace(), Field.Store.YES)); doc.add(new TextField("code", p.getCode(), Field.Store.YES)); w.addDocument(doc); } }
删除id=51173的Document之后,如图所示,再搜索字,就查询不到结果了。
删除关键代码如下,通过 Term对象删除

//删除id=51173的数据
IndexWriterConfig config = new IndexWriterConfig(analyzer);
IndexWriter indexWriter = new IndexWriter(index, config);
indexWriter.deleteDocuments(new Term("id", "51173"));
indexWriter.commit();
indexWriter.close();
删除索引
//删除id=51173的数据 IndexWriterConfig config = new IndexWriterConfig(analyzer); IndexWriter indexWriter = new IndexWriter(index, config); indexWriter.deleteDocuments(new Term("id", "51173")); indexWriter.commit(); indexWriter.close();
package com.how2java; import java.io.IOException; import java.io.StringReader; import java.util.List; import java.util.Scanner; import org.apache.lucene.analysis.TokenStream; 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.index.Term; 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.highlight.Highlighter; import org.apache.lucene.search.highlight.QueryScorer; import org.apache.lucene.search.highlight.SimpleHTMLFormatter; import org.apache.lucene.store.Directory; import org.apache.lucene.store.RAMDirectory; import org.wltea.analyzer.lucene.IKAnalyzer; public class TestLucene { public static void main(String[] args) throws Exception { // 1. 准备中文分词器 IKAnalyzer analyzer = new IKAnalyzer(); // 2. 索引 Directory index = createIndex(analyzer); // 3. 查询器 Scanner s = new Scanner(System.in); //删除id=51173的数据 IndexWriterConfig config = new IndexWriterConfig(analyzer); IndexWriter indexWriter = new IndexWriter(index, config); indexWriter.deleteDocuments(new Term("id", "51173")); indexWriter.commit(); indexWriter.close(); while(true){ System.out.print("请输入查询关键字:"); String keyword = s.nextLine(); System.out.println("当前关键字是:"+keyword); Query query = new QueryParser( "name", analyzer).parse(keyword); // 4. 搜索 IndexReader reader = DirectoryReader.open(index); IndexSearcher searcher=new IndexSearcher(reader); int numberPerPage = 10; ScoreDoc[] hits = searcher.search(query, numberPerPage).scoreDocs; // 5. 显示查询结果 showSearchResults(searcher, hits,query,analyzer); // 6. 关闭查询 reader.close(); } } private static void showSearchResults(IndexSearcher searcher, ScoreDoc[] hits, Query query, IKAnalyzer analyzer) throws Exception { System.out.println("找到 " + hits.length + " 个命中."); SimpleHTMLFormatter simpleHTMLFormatter = new SimpleHTMLFormatter("<span style='color:red'>", "</span>"); Highlighter highlighter = new Highlighter(simpleHTMLFormatter, new QueryScorer(query)); System.out.println("找到 " + hits.length + " 个命中."); System.out.println("序号\t匹配度得分\t结果"); for (int i = 0; i < hits.length; ++i) { ScoreDoc scoreDoc= hits[i]; int docId = scoreDoc.doc; Document d = searcher.doc(docId); List<IndexableField> fields= d.getFields(); System.out.print((i + 1) ); System.out.print("\t" + scoreDoc.score); for (IndexableField f : fields) { if("name".equals(f.name())){ TokenStream tokenStream = analyzer.tokenStream(f.name(), new StringReader(d.get(f.name()))); String fieldContent = highlighter.getBestFragment(tokenStream, d.get(f.name())); System.out.print("\t"+fieldContent); } else{ System.out.print("\t"+d.get(f.name())); } } System.out.println("<br>"); } } private static Directory createIndex(IKAnalyzer analyzer) throws IOException { Directory index = new RAMDirectory(); IndexWriterConfig config = new IndexWriterConfig(analyzer); IndexWriter writer = new IndexWriter(index, config); String fileName = "140k_products.txt"; List<Product> products = ProductUtil.file2list(fileName); int total = products.size(); int count = 0; int per = 0; int oldPer =0; for (Product p : products) { addDoc(writer, p); count++; per = count*100/total; if(per!=oldPer){ oldPer = per; System.out.printf("索引中,总共要添加 %d 条记录,当前添加进度是: %d%% %n",total,per); } } writer.close(); return index; } private static void addDoc(IndexWriter w, Product p) throws IOException { Document doc = new Document(); doc.add(new TextField("id", String.valueOf(p.getId()), Field.Store.YES)); doc.add(new TextField("name", p.getName(), Field.Store.YES)); doc.add(new TextField("category", p.getCategory(), Field.Store.YES)); doc.add(new TextField("price", String.valueOf(p.getPrice()), Field.Store.YES)); doc.add(new TextField("place", p.getPlace(), Field.Store.YES)); doc.add(new TextField("code", p.getCode(), Field.Store.YES)); w.addDocument(doc); } }
还可以按照如下方法来删除索引,API 很明显,就不做代码示例了

DeleteDocuments(Query query):根据Query条件来删除单个或多个Document
DeleteDocuments(Query[] queries):根据Query条件来删除单个或多个Document
DeleteDocuments(Term term):根据Term来删除单个或多个Document
DeleteDocuments(Term[] terms):根据Term来删除单个或多个Document
DeleteAll():删除所有的Document
如图所示,更新索引后,再用查询,得到的结果是查出了更新之后的数据。 更新的关键代码:

// 更新索引
IndexWriterConfig config = new IndexWriterConfig(analyzer);
IndexWriter indexWriter = new IndexWriter(index, config);
Document doc = new Document();
doc.add(new TextField("id", "51173", Field.Store.YES));
doc.add(new TextField("name", "神鞭,鞭没了,神还在", Field.Store.YES));
doc.add(new TextField("category", "道具", Field.Store.YES));
doc.add(new TextField("price", "998", Field.Store.YES));
doc.add(new TextField("place", "南海群岛", Field.Store.YES));
doc.add(new TextField("code", "888888", Field.Store.YES));

indexWriter.updateDocument(new Term("id", "51173"), doc );
indexWriter.commit();
indexWriter.close();
更新索引
package com.how2java; import java.io.IOException; import java.io.StringReader; import java.util.List; import java.util.Scanner; import org.apache.lucene.analysis.TokenStream; 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.index.Term; 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.highlight.Highlighter; import org.apache.lucene.search.highlight.QueryScorer; import org.apache.lucene.search.highlight.SimpleHTMLFormatter; import org.apache.lucene.store.Directory; import org.apache.lucene.store.RAMDirectory; import org.wltea.analyzer.lucene.IKAnalyzer; public class TestLucene { public static void main(String[] args) throws Exception { // 1. 准备中文分词器 IKAnalyzer analyzer = new IKAnalyzer(); // 2. 索引 Directory index = createIndex(analyzer); // 3. 查询器 // 更新索引 IndexWriterConfig config = new IndexWriterConfig(analyzer); IndexWriter indexWriter = new IndexWriter(index, config); Document doc = new Document(); doc.add(new TextField("id", "51173", Field.Store.YES)); doc.add(new TextField("name", "神鞭,鞭没了,神还在", Field.Store.YES)); doc.add(new TextField("category", "道具", Field.Store.YES)); doc.add(new TextField("price", "998", Field.Store.YES)); doc.add(new TextField("place", "南海群岛", Field.Store.YES)); doc.add(new TextField("code", "888888", Field.Store.YES)); indexWriter.updateDocument(new Term("id", "51173"), doc ); indexWriter.commit(); indexWriter.close(); Scanner s = new Scanner(System.in); while(true){ System.out.print("请输入查询关键字:"); String keyword = s.nextLine(); System.out.println("当前关键字是:"+keyword); Query query = new QueryParser( "name", analyzer).parse(keyword); // 4. 搜索 IndexReader reader = DirectoryReader.open(index); IndexSearcher searcher=new IndexSearcher(reader); int numberPerPage = 10; ScoreDoc[] hits = searcher.search(query, numberPerPage).scoreDocs; // 5. 显示查询结果 showSearchResults(searcher, hits,query,analyzer); // 6. 关闭查询 reader.close(); } } private static void showSearchResults(IndexSearcher searcher, ScoreDoc[] hits, Query query, IKAnalyzer analyzer) throws Exception { System.out.println("找到 " + hits.length + " 个命中."); SimpleHTMLFormatter simpleHTMLFormatter = new SimpleHTMLFormatter("<span style='color:red'>", "</span>"); Highlighter highlighter = new Highlighter(simpleHTMLFormatter, new QueryScorer(query)); System.out.println("找到 " + hits.length + " 个命中."); System.out.println("序号\t匹配度得分\t结果"); for (int i = 0; i < hits.length; ++i) { ScoreDoc scoreDoc= hits[i]; int docId = scoreDoc.doc; Document d = searcher.doc(docId); List<IndexableField> fields= d.getFields(); System.out.print((i + 1) ); System.out.print("\t" + scoreDoc.score); for (IndexableField f : fields) { if("name".equals(f.name())){ TokenStream tokenStream = analyzer.tokenStream(f.name(), new StringReader(d.get(f.name()))); String fieldContent = highlighter.getBestFragment(tokenStream, d.get(f.name())); System.out.print("\t"+fieldContent); } else{ System.out.print("\t"+d.get(f.name())); } } System.out.println("<br>"); } } private static Directory createIndex(IKAnalyzer analyzer) throws IOException { Directory index = new RAMDirectory(); IndexWriterConfig config = new IndexWriterConfig(analyzer); IndexWriter writer = new IndexWriter(index, config); String fileName = "140k_products.txt"; List<Product> products = ProductUtil.file2list(fileName); int total = products.size(); int count = 0; int per = 0; int oldPer =0; for (Product p : products) { addDoc(writer, p); count++; per = count*100/total; if(per!=oldPer){ oldPer = per; System.out.printf("索引中,总共要添加 %d 条记录,当前添加进度是: %d%% %n",total,per); } } writer.close(); return index; } private static void addDoc(IndexWriter w, Product p) throws IOException { Document doc = new Document(); doc.add(new TextField("id", String.valueOf(p.getId()), Field.Store.YES)); doc.add(new TextField("name", p.getName(), Field.Store.YES)); doc.add(new TextField("category", p.getCategory(), Field.Store.YES)); doc.add(new TextField("price", String.valueOf(p.getPrice()), Field.Store.YES)); doc.add(new TextField("place", p.getPlace(), Field.Store.YES)); doc.add(new TextField("code", p.getCode(), Field.Store.YES)); w.addDocument(doc); } }


HOW2J公众号,关注后实时获知最新的教程和优惠活动,谢谢。


问答区域    
2021-05-12 更新问题
JAVA界的盖伦

更新时,如果不知道id,怎么处理呢




2 个答案

萌森
答案时间:2021-11-25
new Term("id", "51173") 把知道的换上去,虽然这样更新不准确

AbCdEFf
答案时间:2021-09-11
盖伦!



回答已经提交成功,正在审核。 请于 我的回答 处查看回答记录,谢谢
答案 或者 代码至少填写一项, 如果是自己有问题,请重新提问,否则站长有可能看不到








提问之前请登陆
提问已经提交成功,正在审核。 请于 我的提问 处查看提问记录,谢谢
关于 工具和中间件-搜索引擎技术-索引删除和更新 的提问

尽量提供截图代码异常信息,有助于分析和解决问题。 也可进本站QQ群交流: 578362961
提问尽量提供完整的代码,环境描述,越是有利于问题的重现,您的问题越能更快得到解答。
对教程中代码有疑问,请提供是哪个步骤,哪一行有疑问,这样便于快速定位问题,提高问题得到解答的速度
在已经存在的几千个提问里,有相当大的比例,是因为使用了和站长不同版本的开发环境导致的,比如 jdk, eclpise, idea, mysql,tomcat 等等软件的版本不一致。
请使用和站长一样的版本,可以节约自己大量的学习时间。 站长把教学中用的软件版本整理了,都统一放在了这里, 方便大家下载: https://how2j.cn/k/helloworld/helloworld-version/1718.html

上传截图