lucene搜索引擎的基本使用

客官°小女子只卖身不卖艺 2022-04-12 13:13 249阅读 0赞

给大家简单介绍使用lucene这个搜索引擎,这里我只讲使用,如果想知道它的原理或者更深层次的东西可以看看别的博客

# \* 1.构建Lucene索引 #

首先贴上maven的pom.xml文件

<?xml version="1.0" encoding="UTF-8"?>
    
    <project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
        xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
        <parent>
            <artifactId>Maven</artifactId>
            <groupId>com.hw</groupId>
            <version>1.0-SNAPSHOT</version>
        </parent>
        <modelVersion>4.0.0</modelVersion>
    
        <artifactId>lucene</artifactId>
        <packaging>war</packaging>
    
        <name>lucene Maven Webapp</name>
        
        <url>http://www.example.com</url>
    
        <properties>
            <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
            <maven.compiler.source>1.7</maven.compiler.source>
            <maven.compiler.target>1.7</maven.compiler.target>
        </properties>
    
        <dependencies>
            <dependency>
                <groupId>junit</groupId>
                <artifactId>junit</artifactId>
                <version>4.11</version>
                <scope>test</scope>
            </dependency>
    
            
            <dependency>
                <groupId>mysql</groupId>
                <artifactId>mysql-connector-java</artifactId>
                <version>5.1.44</version>
            </dependency>
    
            
            <dependency>
                <groupId>org.apache.httpcomponents</groupId>
                <artifactId>httpclient</artifactId>
                <version>4.5.2</version>
            </dependency>
    
            
            <dependency>
                <groupId>org.jsoup</groupId>
                <artifactId>jsoup</artifactId>
                <version>1.10.1</version>
            </dependency>
    
    
            
            <dependency>
                <groupId>log4j</groupId>
                <artifactId>log4j</artifactId>
                <version>1.2.16</version>
            </dependency>
    
            
            <dependency>
                <groupId>net.sf.ehcache</groupId>
                <artifactId>ehcache</artifactId>
                <version>2.10.3</version>
            </dependency>
    
            
            <dependency>
                <groupId>commons-io</groupId>
                <artifactId>commons-io</artifactId>
                <version>2.5</version>
            </dependency>
    
            <dependency>
                <groupId>com.alibaba</groupId>
                <artifactId>fastjson</artifactId>
                <version>1.2.47</version>
            </dependency>
    
            <dependency>
                <groupId>org.apache.struts</groupId>
                <artifactId>struts2-core</artifactId>
                <version>2.5.16</version>
            </dependency>
    
            <dependency>
                <groupId>javax.servlet</groupId>
                <artifactId>javax.servlet-api</artifactId>
                <version>4.0.1</version>
                <scope>provided</scope>
            </dependency>
    
    
            <dependency>
                <groupId>org.apache.lucene</groupId>
                <artifactId>lucene-core</artifactId>
                <version>5.3.1</version>
            </dependency>
            <dependency>
                <groupId>org.apache.lucene</groupId>
                <artifactId>lucene-queryparser</artifactId>
                <version>5.3.1</version>
            </dependency>
            <dependency>
                <groupId>org.apache.lucene</groupId>
                <artifactId>lucene-analyzers-common</artifactId>
                <version>5.3.1</version>
            </dependency>
    
            <dependency>
                <groupId>org.apache.lucene</groupId>
                <artifactId>lucene-analyzers-smartcn</artifactId>
                <version>5.3.1</version>
            </dependency>
    
            <dependency>
                <groupId>org.apache.lucene</groupId>
                <artifactId>lucene-highlighter</artifactId>
                <version>5.3.1</version>
            </dependency>
    
            <dependency>
                <groupId>jstl</groupId>
                <artifactId>jstl</artifactId>
                <version>1.2</version>
            </dependency>
    
            <dependency>
                <groupId>taglibs</groupId>
                <artifactId>standard</artifactId>
                <version>1.1.2</version>
            </dependency>
    
            
            <dependency>
                <groupId>org.apache.tomcat</groupId>
                <artifactId>tomcat-jsp-api</artifactId>
                <version>8.5.31</version>
            </dependency>
    
        </dependencies>
    
        <build>
            <finalName>lucene</finalName>
            <pluginManagement>
                <plugins>
                    <plugin>
                        <artifactId>maven-clean-plugin</artifactId>
                        <version>3.0.0</version>
                    </plugin>
                    
                    <plugin>
                        <artifactId>maven-resources-plugin</artifactId>
                        <version>3.0.2</version>
                    </plugin>
                    <plugin>
                        <artifactId>maven-compiler-plugin</artifactId>
                        <version>3.7.0</version>
                    </plugin>
                    <plugin>
                        <artifactId>maven-surefire-plugin</artifactId>
                        <version>2.20.1</version>
                    </plugin>
                    <plugin>
                        <artifactId>maven-war-plugin</artifactId>
                        <version>3.2.0</version>
                    </plugin>
                    <plugin>
                        <artifactId>maven-install-plugin</artifactId>
                        <version>2.5.2</version>
                    </plugin>
                    <plugin>
                        <artifactId>maven-deploy-plugin</artifactId>
                        <version>2.8.2</version>
                    </plugin>
    
                    <plugin>
                        <groupId>org.apache.maven.plugins</groupId>
                        <artifactId>maven-compiler-plugin</artifactId>
                        <version>3.7.0</version>
                        <configuration>
                            <source>1.8</source>
                            <target>1.8</target>
                            <encoding>UTF-8</encoding>
                        </configuration>
                    </plugin>
                </plugins>
    
            </pluginManagement>
    
        </build>
    </project>

数据库信息和存储位置

![20181203161439411.png][]

然后是生成文件的代码

public class IndexStarter {
    //    dao方法
        private static BlogDao blogDao = new BlogDao();
    //执行生成索引文件
        public static void main(String[] args) {
            //SmartChineseAnalyzer  中文分词器
            IndexWriterConfig config = new IndexWriterConfig(new SmartChineseAnalyzer());
            //索引文件生成位置
            Directory d = null;
            IndexWriter writer = null;
            try {
                //位置
                d = FSDirectory.open(Paths.get(PropertiesUtil.getValue("indexPath")));
                writer = new IndexWriter(d, config);
                //为数据库中的所有所有文件构建索引
                List<Map<String, Object>> list = blogDao.list(null, null);
                Document doc = null;
                for (Map<String, Object> map : list) {
                    doc = new Document();
                    doc.add(new StringField("id", (String) map.get("id"), Field.Store.YES));
                    //textfield为将该数据作为分词查询
                    doc.add(new TextField("title", (String) map.get("title"), Field.Store.YES));
                    doc.add(new StringField("url", (String) map.get("url"), Field.Store.YES));
                    writer.addDocument(doc);
                }
            } catch (IOException e) {
                e.printStackTrace();
            } catch (IllegalAccessException e) {
                e.printStackTrace();
            } catch (InstantiationException e) {
                e.printStackTrace();
            } catch (SQLException e) {
                e.printStackTrace();
            } finally {
                //关闭流
                if (writer != null) {
                    try {
                        writer.close();
                    } catch (IOException e) {
                        e.printStackTrace();
                    }
                }
            }
    
        }
    }

#    \* 2.读取索引文件,获取命中片段,使得命中片段高亮显示 #

action

public String execute() {
            try {
                HttpServletRequest request = ServletActionContext.getRequest();
                if (StringUtils.isBlank(title)) {
                    List<Map<String, Object>> blogList = this.blogDao.list(title, null);
                    request.setAttribute("blogList", blogList);
                } else {
                    SmartChineseAnalyzer analyzer = new SmartChineseAnalyzer();
                    IndexReader indexReader = DirectoryReader.open(FSDirectory.open(Paths.get(PropertiesUtil.getValue("indexPath"))));
                    IndexSearcher searcher = new IndexSearcher(indexReader);
    //拿一句话到目录中的索引文件词库进行关键字碰撞
                    Query query = new QueryParser("title", analyzer).parse(title);
                    TopDocs docs = searcher.search(query, 100);
    
    //关键字高亮
                    //将碰撞出来的关键字点亮
                    QueryScorer queryScorer = new QueryScorer(query);
                    //以什么实行点亮关键字
                    Formatter formatter = new SimpleHTMLFormatter("<span style='color:red'><b>", "</span><b>");
                    Highlighter highlighter = new Highlighter(formatter, queryScorer);
    
                    List<Map<String, Object>> blogList = new ArrayList<>();
                    Map<String, Object> map = null;
                    ScoreDoc[] scoreDocs = docs.scoreDocs;
                    for (ScoreDoc scoreDoc : scoreDocs) {
                        map = new HashMap<>();
                        //拿到文档
                        Document doc = searcher.doc(scoreDoc.doc);
                        map.put("id", doc.get("id"));
                        String title = doc.get("title");
                        if (StringUtils.isNotBlank(title)) {
                            title = highlighter.getBestFragment(analyzer, "title", title);
                        }
                        map.put("title", title);
                        map.put("url", doc.get("url"));
                        blogList.add(map);
                    }
                    request.setAttribute("blogList", blogList);
                }
            } catch (Exception e) {
                e.printStackTrace();
            }
            return "blogList";
        }

前台代码:

<body>
    <form action="${pageContext.request.contextPath}/sy/blogAction.action"
    		method="post">
    		博客标题：<input type="text" name="title"> <input type="submit"
    			value="确定">
    	</form>
    	<table border="1" width="100%">
    		<tr>
    			<td>编号</td>
    			<td>名称</td>
    			<td>价格</td>
    		</tr>
    		<c:forEach items="${blogList }" var="blog">
    			<tr>
    				<td>${blog.id }</td>
    				<td>${blog.title }</td>
    				<td><a href="${blog.url }">${blog.title }</a></td>
    			</tr>
    		</c:forEach>
    	</table>
    </body>

效果图:

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzQxNTk0MTQ2_size_16_color_FFFFFF_t_70][]

## 能将一句话分词搜索 ##

[20181203161439411.png]: /images/20220412/72cf9273442d4d9e9ff219e8a2dc4252.png
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzQxNTk0MTQ2_size_16_color_FFFFFF_t_70]: /images/20220412/ba95e444857f4261b943dfd066f70827.png