lucene入門

時間 2019-11-08

標籤 lucene 入門简体版

原文原文鏈接

1、lucene簡介java

　　Lucene是apache下的一個靠性能的、功能全面的用純java開發的一個全文搜索引擎庫。它幾乎適合任何須要全文搜索應用程序，尤爲是跨平臺。lucene是開源的免費的工程。lucene使用簡單可是提供的功能很是強大。相關特色以下：數據庫

在硬件上的速度超過150GB/小時
更小的內存需求，只須要1MB堆空間
快速地增長索引、與批量索引
索引的大小大於爲被索引文本的20%-30%

　　lucene下載地址爲：http://lucene.apache.org/ apache

　　文本示例工程使用maven構建，lucene版本爲5.2.1。相關依賴文件以下：app

<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>com.shh</groupId>
    <artifactId>lucene</artifactId>
    <packaging>war</packaging>
    <version>0.0.1-SNAPSHOT</version>
    <name>lucene Maven Webapp</name>
    <url>http://maven.apache.org</url>
    <properties>
        <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
        <lucene.version>5.2.1</lucene.version>
    </properties>

    <dependencies>
        <dependency>
            <groupId>org.apache.lucene</groupId>
            <artifactId>lucene-core</artifactId>
            <version>${lucene.version}</version>
        </dependency>

        <dependency>
            <groupId>org.apache.lucene</groupId>
            <artifactId>lucene-queryparser</artifactId>
            <version>${lucene.version}</version>
        </dependency>
        <dependency>
            <groupId>org.apache.lucene</groupId>
            <artifactId>lucene-analyzers-common</artifactId>
            <version>${lucene.version}</version>
        </dependency>

        <!-- 分詞器 -->
        <dependency>
            <groupId>org.apache.lucene</groupId>
            <artifactId>lucene-analyzers-smartcn</artifactId>
            <version>${lucene.version}</version>
        </dependency>

        <dependency>
            <groupId>org.apache.lucene</groupId>
            <artifactId>lucene-highlighter</artifactId>
            <version>${lucene.version}</version>
        </dependency>
    </dependencies>

    <build>
        <finalName>lucene</finalName> 
    </build>
</project>

2、示例maven

　　一、索引的建立性能

　　相關代碼以下：ui

 1 package com.test.lucene;
 2 
 3 import java.io.IOException; 
 4 import java.nio.file.Paths; 
 5 
 6 import org.apache.lucene.analysis.Analyzer;
 7 import org.apache.lucene.analysis.standard.StandardAnalyzer;
 8 import org.apache.lucene.document.Document;
 9 import org.apache.lucene.document.Field.Store;
10 import org.apache.lucene.document.IntField;
11 import org.apache.lucene.document.StringField;
12 import org.apache.lucene.document.TextField;
13 import org.apache.lucene.index.IndexWriter;
14 import org.apache.lucene.index.IndexWriterConfig;
15 import org.apache.lucene.index.IndexWriterConfig.OpenMode;
16 import org.apache.lucene.store.Directory;
17 import org.apache.lucene.store.FSDirectory;
18 
19 /**
20  * 建立索引
21  */
22 public class IndexCreate {
23     
24     public static void main(String[] args) {
25         // 指定分詞技術，這裏使用的是標準分詞
26         Analyzer analyzer = new StandardAnalyzer();
27 
28         // indexWriter的配置信息
29         IndexWriterConfig indexWriterConfig = new IndexWriterConfig(analyzer);
30 
31         // 索引的打開方式：沒有則建立，有則打開
32         indexWriterConfig.setOpenMode(OpenMode.CREATE_OR_APPEND);
33 
34         Directory directory = null;
35         IndexWriter indexWriter = null;
36         try {
37             // 索引在硬盤上的存儲路徑
38             directory = FSDirectory.open(Paths.get("D://index/test"));
39             //indexWriter用來建立索引文件
40             indexWriter = new IndexWriter(directory, indexWriterConfig);
41         } catch (IOException e) {
42             e.printStackTrace();
43         }
44         
45         //建立文檔一
46         Document doc1 = new Document();
47         doc1.add(new StringField("id", "abcde", Store.YES));
48         doc1.add(new TextField("content", "中國廣州", Store.YES));
49         doc1.add(new IntField("num", 1, Store.YES));
50 
51         //建立文檔二
52         Document doc2 = new Document();
53         doc2.add(new StringField("id", "asdff", Store.YES));
54         doc2.add(new TextField("content", "中國上海", Store.YES));
55         doc2.add(new IntField("num", 2, Store.YES));
56 
57         try {
58             //添加須要索引的文檔
59             indexWriter.addDocument(doc1);
60             indexWriter.addDocument(doc2);
61  
62             // 將indexWrite操做提交，若是不提交，以前的操做將不會保存到硬盤
63             // 可是這一步很消耗系統資源，索引執行該操做須要有必定的策略
64             indexWriter.commit();
65         } catch (IOException e) {
66             e.printStackTrace();
67         } finally {
68             // 關閉資源
69             try { 
70                 indexWriter.close();
71                 directory.close(); 
72             } catch (IOException e) {
73                 e.printStackTrace();
74             }
75         }
76     }
77 }

　　二、搜索搜索引擎

　　相關代碼以下：url

 1 package com.test.lucene;
 2 
 3 import java.io.IOException;
 4 import java.nio.file.Paths;
 5 
 6 import org.apache.lucene.analysis.Analyzer;
 7 import org.apache.lucene.analysis.standard.StandardAnalyzer;
 8 import org.apache.lucene.document.Document;
 9 import org.apache.lucene.index.DirectoryReader;
10 import org.apache.lucene.queryparser.classic.ParseException;
11 import org.apache.lucene.queryparser.classic.QueryParser;
12 import org.apache.lucene.search.IndexSearcher;
13 import org.apache.lucene.search.Query;
14 import org.apache.lucene.search.TopDocs;
15 import org.apache.lucene.store.Directory;
16 import org.apache.lucene.store.FSDirectory;
17 
18 /**
19  * 搜索
20  */
21 public class IndexSearch {
22     
23     public static void main(String[] args) {
24         //索引存放的位置
25         Directory directory = null;
26         try {
27             // 索引硬盤存儲路徑
28             directory = FSDirectory.open(Paths.get("D://index/test"));
29             // 讀取索引
30             DirectoryReader directoryReader = DirectoryReader.open(directory);
31             // 建立索引檢索對象
32             IndexSearcher searcher = new IndexSearcher(directoryReader);
33             // 分詞技術
34             Analyzer analyzer = new StandardAnalyzer();
35             // 建立Query
36             QueryParser parser = new QueryParser("content", analyzer);
37             Query query = parser.parse("廣州");// 查詢content爲廣州的
38             // 檢索索引，獲取符合條件的前10條記錄
39             TopDocs topDocs = searcher.search(query, 10);
40             if (topDocs != null) {
41                 System.out.println("符合條件的記錄爲： " + topDocs.totalHits);
42                 for (int i = 0; i < topDocs.scoreDocs.length; i++) {
43                     Document doc = searcher.doc(topDocs.scoreDocs[i].doc);
44                     System.out.println("id = " + doc.get("id"));
45                     System.out.println("content = " + doc.get("content"));
46                     System.out.println("num = " + doc.get("num"));
47                 }
48             }
49             directory.close();
50             directoryReader.close();
51         } catch (IOException e) {
52             e.printStackTrace();
53         } catch (ParseException e) {
54             e.printStackTrace();
55         }
56     }
57 }