Lighting@刘迎光

下面是全文检索引擎的初步应用，但是很遗憾，原生的lucene不支持中文分词，所以需要插件支持，在后面会继续讲到。

代码摘自：http://iluoxuan.iteye.com/blog/1708695

POM.xml文件：

<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/maven-v4_0_0.xsd">
    <modelVersion>4.0.0</modelVersion>
    <groupId>cn.firewarm</groupId>
    <artifactId>testLucene</artifactId>
    <packaging>war</packaging>
    <version>0.0.1-SNAPSHOT</version>
    <name>testLucene Maven Webapp</name>
    <url>http://maven.apache.org</url>
    <repositories>
        <repository>
            <id>mine</id>
            <name>public Releases</name>
            <layout>default</layout>
            <url>http://nexus.liuyingguang.cn:8081/nexus/content/groups/public/</url>
        </repository>
    </repositories>
    <dependencies>
        <dependency>
            <groupId>org.apache.lucene</groupId>
            <artifactId>lucene-core</artifactId>
            <version>4.10.1</version>
        </dependency>
        <dependency>
            <groupId>org.apache.lucene</groupId>
            <artifactId>lucene-analyzers-common</artifactId>
            <version>4.10.1</version>
        </dependency>
 
        <dependency>
            <groupId>org.apache.lucene</groupId>
            <artifactId>lucene-queryparser</artifactId>
            <version>4.10.1</version>
        </dependency>
        <dependency>
            <groupId>org.apache.commons</groupId>
            <artifactId>commons-vfs2</artifactId>
            <version>2.1</version>
        </dependency>
        <dependency>
            <groupId>commons-io</groupId>
            <artifactId>commons-io</artifactId>
            <version>2.4</version>
        </dependency>
    </dependencies>
    <build>
        <finalName>testLucene</finalName>
    </build>
</project>

创建索引的代码如下：

package com.search.lucene;
 
import java.io.File;
 
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.Store;
import org.apache.lucene.document.StringField;
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 org.apache.lucene.util.Version;
import org.junit.Before;
import org.junit.Test;
 
public class IndexFile {
 
    protected String[] ids={"1", "2"};
 
    protected String[] content={"Amsterdam has lost of add  cancals", "i love  add this girl"};
 
    protected String[] city={"Amsterdam", "Venice"};
 
    private Directory dir;
 
    /**
     * 初始添加文档
     * @throws Exception
     */
    @Test
    public void init() throws Exception {
        String pathFile="D://lucene/index";
        dir=FSDirectory.open(new File(pathFile));
        IndexWriter writer=getWriter();
        for(int i=0; i < ids.length; i++) {
            Document doc=new Document();
            doc.add(new StringField("id", ids[i], Store.YES));
            doc.add(new TextField("content", content[i], Store.YES));
            doc.add(new StringField("city", city[i], Store.YES));
            writer.addDocument(doc);
        }
        System.out.println("init ok?");
        writer.close();
    }
 
    /**
     * 获得IndexWriter对象
     * @return
     * @throws Exception
     */
    public IndexWriter getWriter() throws Exception {
        Analyzer analyzer=new StandardAnalyzer(Version.LUCENE_40);
        IndexWriterConfig iwc=new IndexWriterConfig(Version.LUCENE_40, analyzer);
        return new IndexWriter(dir, iwc);
    }
 
}

查询代码如下：

package com.search.lucene;
 
import java.io.File;
 
import org.apache.lucene.document.Document;
import org.apache.lucene.index.DirectoryReader;
import org.apache.lucene.index.IndexReader;
import org.apache.lucene.index.Term;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.ScoreDoc;
import org.apache.lucene.search.TermQuery;
import org.apache.lucene.search.TopDocs;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.FSDirectory;
import org.junit.Test;
 
public class IndexSearch {
 
    /**
     * 查询
     * @throws Exception
     */
    @Test
    public void search() throws Exception {
        String filePath="D://lucene/index";
        Directory dir=FSDirectory.open(new File(filePath));
        IndexReader reader=DirectoryReader.open(dir);
        IndexSearcher searcher=new IndexSearcher(reader);
        Term term=new Term("content", "add");
        TermQuery query=new TermQuery(term);
        TopDocs topdocs=searcher.search(query, 5);
        ScoreDoc[] scoreDocs=topdocs.scoreDocs;
        System.out.println("查询结果总数---" + topdocs.totalHits+"最大的评分--"+topdocs.getMaxScore());
        for(int i=0; i < scoreDocs.length; i++) {
            int doc = scoreDocs[i].doc;
            Document document = searcher.doc(doc);
            System.out.println("content===="+document.get("content"));
            System.out.println("id--" + scoreDocs[i].doc + "---scors--" + scoreDocs[i].score+"---index--"+scoreDocs[i].shardIndex);
        }
        reader.close();
    }
}

by 刘迎光@萤火虫工作室 
OpenBI交流群：495266201 
MicroService 微服务交流群：217722918 
mail: liuyg#liuyingguang.cn 
博主首页（==防止爬虫==）：http://blog.liuyingguang.cn