Lucene 实例 -- 基本用法

Lucene 实例 -- 基本用法

摘自:
http://www.lucenetutorial.com/lucene-in-5-minutes.html

该例子基于Lucene 4.8.0

简而言之,Lucene的基础使用分为两个步骤
1, 创建索引
2, 查询

创建索引又分为以下几步:

1.1, 创建索引的存储位置(Directory类)
1.2, 创建索引写者(IndexWriter)
1.3, 创建索引文档(Document)并添加相关域(Field)
1.4, 索引写者添加索引文档
1.5, 关闭相关资源

查询分为以下几步:

2.1, 打开索引存储位置的文件,创建索引查询(IndexSearcher)
2.2, 创建查询(Query)
2.3, 查询(search方法)
2.4, 获取搜索结果的指针(TopDocs),此时的指针并没有载入读取搜索结果的实质内容,仅仅是指针

2.5, 获取搜索结果内容(Document,get方法)

一些重要的类:

IndexWriter

Directory

Analyzer

Document

Field

IndexSearcher

Query

TopDocs

具体代码如下:

import java.io.IOException;

import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.document.StringField;
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.queryparser.classic.ParseException;
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.TopScoreDocCollector;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.RAMDirectory;
import org.apache.lucene.util.Version;

//创建索引又分为以下几步:
//1.1, 创建索引的存储位置(Directory类)
//1.2, 创建索引写者(IndexWriter)
//1.3, 创建索引文档(Document)并添加相关域(Field)
//1.4, 索引写者添加索引文档
//1.5, 关闭相关资源
//
//查询分为以下几步:
//2.1, 打开索引存储位置的文件,创建索引查询(IndexSearcher)
//2.2, 创建查询(Query)
//2.3, 查询(search方法)
//2.4, 获取搜索结果的指针(TopDocs),此时的指针并没有载入读取搜索结果的实质内容,仅仅是指针
//2.5, 获取搜索结果内容(Document,get方法)
public class HelloLucene {
	public static void main(String[] args) throws IOException, ParseException {
		// 0. Specify the analyzer for tokenizing text.
		// The same analyzer should be used for indexing and searching
		// 这个类是用来把文本文件里的内容分割成一个个字符串
		// 如果用SimpleAnalyzer类,那么会把整个文件内容当成是一个字符串
		StandardAnalyzer analyzer = new StandardAnalyzer(Version.LUCENE_48);

		// 1. create the index
		Directory index = new RAMDirectory(); // 1.1

		IndexWriterConfig config = new IndexWriterConfig(Version.LUCENE_48, analyzer);

		IndexWriter w = new IndexWriter(index, config); // 1.2
		addDoc(w, "Lucene in Action", "193398817");
		addDoc(w, "Lucene for Dummies", "55320055Z");
		addDoc(w, "Managing Gigabytes", "55063554A");
		addDoc(w, "The Art of Computer Science", "9900333X");
		w.close(); // 1.5

		// 2. query
		String querystr = args.length > 0 ? args[0] : "lucene";

		// the "title" arg specifies the default field to use
		// when no field is explicitly specified in the query.
		Query q = new QueryParser(Version.LUCENE_48, "title", analyzer).parse(querystr); // 2.2

		// 3. search
		int hitsPerPage = 10;
		IndexReader reader = DirectoryReader.open(index); // 2.1
		IndexSearcher searcher = new IndexSearcher(reader); // 2.1
		TopScoreDocCollector collector = TopScoreDocCollector.create(hitsPerPage, true);
		searcher.search(q, collector); // 2.3
		ScoreDoc[] hits = collector.topDocs().scoreDocs; // 2.4

		// 4. display results
		System.out.println("Found " + hits.length + " hits.");
		for (int i = 0; i < hits.length; ++i) {
			int docId = hits[i].doc;
			Document d = searcher.doc(docId); // 2.5
			System.out.println((i + 1) + ". " + d.get("isbn") + "\t" + d.get("title"));
		}

		// reader can only be closed when there
		// is no need to access the documents any more.
		reader.close();
	}

	private static void addDoc(IndexWriter w, String title, String isbn) throws IOException {
		Document doc = new Document(); // 1.3
		doc.add(new TextField("title", title, Field.Store.YES)); // 1.3

		// use a string field for isbn because we don't want it tokenized
		doc.add(new StringField("isbn", isbn, Field.Store.YES)); // 1.3
		w.addDocument(doc); // 1.4
	}
}