Lucene入门教程（一）

最新推荐文章于 2021-09-05 10:06:57 发布

转载最新推荐文章于 2021-09-05 10:06:57 发布 · 861 阅读

收录于

Lucene

本文介绍 Lucene 4.5 的基本概念，包括如何为文档建立索引和搜索索引文件。通过实际代码示例展示了如何使用 Java API 创建索引，并演示了如何查询已建立的索引。

Lucene 4.5，document详解，例子实现，方法重写。

在这里分享一下Lucene的学习，主要参考官网上的一下教程和PDF版的《Lucene In Action》。当然，博客中很多内容都是摘自上面两个地方。

1. 什么是Lucene

Lucene是一个高性能的、可扩展的信息检索工具。你可以把它融入到应用程序中以增加索引和搜索功能。Lucene是一个纯Java实现的成熟、自由、开源的软件项目。

它不是一个完整的全文检索引擎，而是一个全文检索引擎的架构，提供了完整的查询引擎和索引引擎，部分文本分析引擎。

官方网站：http://lucene.apache.org/

CSDN下载地址：http://download.csdn.net/detail/jolingogo/6472385

2. 索引和搜索

使用Lucene，需要理解索引和搜索这两个概念。

索引：为了快速搜索大量文本文件，首先必须为文件建立索引，就像为一本书建立目录，然后把文本转换成你能够快速搜索到的格式，

而不是使用那种慢速顺序扫描的处理法。这个转换过程就叫做索引操作（indexing），他的输出就称为索引文件（index）。

可以把索引想象成一种数据结构，这种数据结构允许对存储在其中的单词进行快速随机存取。

搜索：是在一个索引中查找关键字的过程，这个过程的目的是为了找到这些关键字在哪些地方出现过。

搜索的质量通常有查确率（precise）和查全率（recall）来衡量。查全率可以衡量这个搜索系统查找到相关文档的能力，

而查确率则是用来衡量搜索系统过滤非相关文档的能力。

3. 第一个示例

准备工作：

1.新建2个文件夹

Lucene_data 里面，我新建了几个txt文本文件

Lucene_index用来存放索引

2. pom.xml

[html] view plain copy

    <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">  
        <modelVersion>4.0.0</modelVersion>  
      
        <groupId>org.ygy</groupId>  
        <artifactId>lucene</artifactId>  
        <version>0.0.1-SNAPSHOT</version>  
        <packaging>jar</packaging>  
      
        <name>lucene</name>  
        <url>http://maven.apache.org</url>  
      
        <properties>  
            <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>  
        </properties>  
      
        <dependencies>  
            <dependency>  
                <groupId>junit</groupId>  
                <artifactId>junit</artifactId>  
                <version>4.10</version>  
                <scope>test</scope>  
            </dependency>  
      
            <!-- Lucene依赖包 -->  
            <dependency>  
                <groupId>org.apache.lucene</groupId>  
                <artifactId>lucene-core</artifactId>  
                <version>4.5.1</version>  
            </dependency>  
      
            <dependency>  
                <groupId>org.apache.lucene</groupId>  
                <artifactId>lucene-analyzers-icu</artifactId>  
                <version>4.5.1</version>  
            </dependency>  
      
            <dependency>  
                <groupId>org.apache.lucene</groupId>  
                <artifactId>lucene-queryparser</artifactId>  
                <version>4.5.1</version>  
            </dependency>  
      
      
        </dependencies>  
    </project>

3.1 建立索引

[java] view plain copy

package org.ygy.lucene;
import java.io.BufferedReader;
import java.io.File;
import java.io.FileInputStream;
import java.io.FileNotFoundException;
import java.io.IOException;
import java.io.InputStreamReader;
import java.util.Date;
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;
import org.apache.lucene.document.LongField;
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.index.Term;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.FSDirectory;
import org.apache.lucene.util.Version;
/**
* 建立索引
*
* @author yuguiyang
*
*/
public class IndexFiles {
// -index F:\Lucene_index -docs F:\Lucene_data
public static void main(String[] args) {
String usage = "java org.apache.lucene.demo.IndexFiles [-index INDEX_PATH] [-docs DOCS_PATH] [-update]\n\nThis indexes the documents in DOCS_PATH, creating a Lucene indexin INDEX_PATH that can be searched with SearchFiles";
String indexPath = "index"; // 索引存放的路径
String docsPath = null; // 需要给哪些文件建立索引（即资源库的地址）
boolean create = true; // 是否新建索引
for (int i = 0; i < args.length; i++) {
if ("-index".equals(args[i])) {
indexPath = args[(i + 1)];
i++;
} else if ("-docs".equals(args[i])) {
docsPath = args[(i + 1)];
i++;
} else if ("-update".equals(args[i])) {
create = false;
}
}
if (docsPath == null) {
System.err.println("Usage: " + usage);
System.exit(1);
}
// 验证资源文件地址
File docDir = new File(docsPath);
if ((!docDir.exists()) || (!docDir.canRead())) {
System.out.println("Document directory '" + docDir.getAbsolutePath()
+ "' does not exist or is not readable, please check the path");
System.exit(1);
}
// 开始建立索引
Date start = new Date();
try {
System.out.println("Indexing to directory '" + indexPath + "'...");
// 根据索引存放地址，创建目录
Directory dir = FSDirectory.open(new File(indexPath));
// 初始化分析器
Analyzer analyzer = new StandardAnalyzer(Version.LUCENE_45);
//索引配置
IndexWriterConfig iwc = new IndexWriterConfig(Version.LUCENE_45, analyzer);
if (create) {
iwc.setOpenMode(IndexWriterConfig.OpenMode.CREATE);
} else {
iwc.setOpenMode(IndexWriterConfig.OpenMode.CREATE_OR_APPEND);
}
//初始化索引
IndexWriter writer = new IndexWriter(dir, iwc);
indexDocs(writer, docDir);
//关闭索引
writer.close();
Date end = new Date();
System.out.println(end.getTime() - start.getTime() + " total milliseconds");
} catch (IOException e) {
System.out.println(" caught a " + e.getClass() + "\n with message: " + e.getMessage());
}
}
//递归的方式，遍历每一个文件
static void indexDocs(IndexWriter writer, File file) throws IOException {
if (file.canRead())
if (file.isDirectory()) {
String[] files = file.list();
if (files != null)
for (int i = 0; i < files.length; i++)
indexDocs(writer, new File(file, files[i]));
} else {
FileInputStream fis;
try {
fis = new FileInputStream(file);
} catch (FileNotFoundException fnfe) {
return;
}
try {
Document doc = new Document();
Field pathField = new StringField("path", file.getPath(), Field.Store.YES);
doc.add(pathField);
doc.add(new LongField("modified", file.lastModified(), Field.Store.NO));
doc.add(new TextField("contents", new BufferedReader(new InputStreamReader(fis, "UTF-8"))));
if (writer.getConfig().getOpenMode() == IndexWriterConfig.OpenMode.CREATE) {
System.out.println("adding " + file);
writer.addDocument(doc);
} else {
System.out.println("updating " + file);
writer.updateDocument(new Term("path", file.getPath()), doc);
}
} finally {
fis.close();
}
}
}
}

好了，虽然，上面的代码还不是很明白，但是，运行一下先。

运行时，需要指定一些参数：

运行结果：

好了，索引建立成功了，看一下，F:\Lucene_index文件夹

这些文件具体是什么，不太清楚，暂且当做是索引文件吧。

3.2 搜索

[java] view plain copy

package org.ygy.lucene;
import java.io.BufferedReader;
import java.io.File;
import java.io.FileInputStream;
import java.io.IOException;
import java.io.InputStreamReader;
import java.util.Date;
import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.index.DirectoryReader;
import org.apache.lucene.index.IndexReader;
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.TopDocs;
import org.apache.lucene.store.FSDirectory;
import org.apache.lucene.util.Version;
public class SearchFiles {
public static void main(String[] args) throws Exception {
//对参数的一些处理
String usage = "Usage:\tjava org.apache.lucene.demo.SearchFiles [-index dir] [-field f] [-repeat n] [-queries file] [-query string] [-raw] [-paging hitsPerPage]\n\nSee http://lucene.apache.org/core/4_1_0/demo/ for details.";
if ((args.length > 0) && (("-h".equals(args[0])) || ("-help".equals(args[0])))) {
System.out.println(usage);
System.exit(0);
}
String index = "index";
String field = "contents";
String queries = null;
int repeat = 0;
boolean raw = false;
String queryString = null;
int hitsPerPage = 10;
for (int i = 0; i < args.length; i++) {
if ("-index".equals(args[i])) {
index = args[(i + 1)];
i++;
} else if ("-field".equals(args[i])) {
field = args[(i + 1)];
i++;
} else if ("-queries".equals(args[i])) {
queries = args[(i + 1)];
i++;
} else if ("-query".equals(args[i])) {
queryString = args[(i + 1)];
i++;
} else if ("-repeat".equals(args[i])) {
repeat = Integer.parseInt(args[(i + 1)]);
i++;
} else if ("-raw".equals(args[i])) {
raw = true;
} else if ("-paging".equals(args[i])) {
hitsPerPage = Integer.parseInt(args[(i + 1)]);
if (hitsPerPage <= 0) {
System.err.println("There must be at least 1 hit per page.");
System.exit(1);
}
i++;
}
}
//读取索引
IndexReader reader = DirectoryReader.open(FSDirectory.open(new File(index)));
//查询索引
IndexSearcher searcher = new IndexSearcher(reader);
//分析器
Analyzer analyzer = new StandardAnalyzer(Version.LUCENE_45);
BufferedReader in = null;
if (queries != null)
in = new BufferedReader(new InputStreamReader(new FileInputStream(queries), "UTF-8"));
else {
in = new BufferedReader(new InputStreamReader(System.in, "UTF-8"));
}
//解析器
QueryParser parser = new QueryParser(Version.LUCENE_45, field, analyzer);
while (true) {
if ((queries == null) && (queryString == null)) {
System.out.println("Enter query: ");
}
String line = queryString != null ? queryString : in.readLine();
if ((line == null) || (line.length() == -1)) {
break;
}
line = line.trim();
if (line.length() == 0) {
break;
}
Query query = parser.parse(line);
System.out.println("Searching for: " + query.toString(field));
if (repeat > 0) {
Date start = new Date();
for (int i = 0; i < repeat; i++) {
searcher.search(query, null, 100);
}
Date end = new Date();
System.out.println("Time: " + (end.getTime() - start.getTime()) + "ms");
}
doPagingSearch(in, searcher, query, hitsPerPage, raw, (queries == null) && (queryString == null));
if (queryString != null) {
break;
}
}
reader.close();
}
public static void doPagingSearch(BufferedReader in, IndexSearcher searcher, Query query, int hitsPerPage,
boolean raw, boolean interactive) throws IOException {
TopDocs results = searcher.search(query, 5 * hitsPerPage);
ScoreDoc[] hits = results.scoreDocs;
int numTotalHits = results.totalHits;
System.out.println(numTotalHits + " total matching documents");
int start = 0;
int end = Math.min(numTotalHits, hitsPerPage);
while (true) {
if (end > hits.length) {
System.out.println("Only results 1 - " + hits.length + " of " + numTotalHits
+ " total matching documents collected.");
System.out.println("Collect more (y/n) ?");
String line = in.readLine();
if ((line.length() == 0) || (line.charAt(0) == 'n')) {
break;
}
hits = searcher.search(query, numTotalHits).scoreDocs;
}
end = Math.min(hits.length, start + hitsPerPage);
for (int i = start; i < end; i++) {
if (raw) {
System.out.println("doc=" + hits[i].doc + " score=" + hits[i].score);
} else {
Document doc = searcher.doc(hits[i].doc);
String path = doc.get("path");
if (path != null) {
System.out.println(i + 1 + ". " + path);
String title = doc.get("title");
if (title != null)
System.out.println(" Title: " + doc.get("title"));
} else {
System.out.println(i + 1 + ". " + "No path for this document");
}
}
}
if ((!interactive) || (end == 0)) {
break;
}
if (numTotalHits >= end) {
boolean quit = false;
while (true) {
System.out.print("Press ");
if (start - hitsPerPage >= 0) {
System.out.print("(p)revious page, ");
}
if (start + hitsPerPage < numTotalHits) {
System.out.print("(n)ext page, ");
}
System.out.println("(q)uit or enter number to jump to a page.");
String line = in.readLine();
if ((line.length() == 0) || (line.charAt(0) == 'q')) {
quit = true;
break;
}
if (line.charAt(0) == 'p') {
start = Math.max(0, start - hitsPerPage);
break;
}
if (line.charAt(0) == 'n') {
if (start + hitsPerPage >= numTotalHits)
break;
start += hitsPerPage;
break;
}
int page = Integer.parseInt(line);
if ((page - 1) * hitsPerPage < numTotalHits) {
start = (page - 1) * hitsPerPage;
break;
}
System.out.println("No such page");
}
if (quit)
break;
end = Math.min(numTotalHits, start + hitsPerPage);
}
}
}
}