<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>com.xingyun</groupId><artifactId>lucene-sample</artifactId><version>0.0.1-SNAPSHOT</version><packaging>jar</packaging><name>lucene-sample</name><properties><project.build.sourceEncoding>UTF-8</project.build.sourceEncoding></properties><build><plugins><plugin><groupId>org.codehaus.mojo</groupId><artifactId>exec-maven-plugin</artifactId><version>1.3.2</version><executions><execution><id>ex</id><phase>package</phase><goals><goal>exec</goal></goals><configuration><executable>java</executable><arguments><argument>-classpath</argument><classpath /><argument>HelloLucene.HelloLucene</argument></arguments></configuration></execution></executions></plugin></plugins></build><dependencies><dependency><groupId>org.apache.lucene</groupId><artifactId>lucene-core</artifactId><version>4.0.0</version></dependency><dependency><groupId>org.apache.lucene</groupId><artifactId>lucene-queries</artifactId><version>4.0.0</version></dependency><dependency><groupId>org.apache.lucene</groupId><artifactId>lucene-test-framework</artifactId><version>4.0.0</version></dependency><dependency><groupId>org.apache.lucene</groupId><artifactId>lucene-analyzers-common</artifactId><version>4.0.0</version></dependency><dependency><groupId>org.apache.lucene</groupId><artifactId>lucene-queryparser</artifactId><version>4.0.0</version></dependency></dependencies>
</project>

package com.xingyun;import java.io.IOException;
import java.text.ParseException;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.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;public class HelloLucene {public static void main(String[] args) throws IOException, ParseException {// 对于这个简单的例子，我们将从一些字符串中创建一个内存索引。// 0. Specify the analyzer for tokenizing text.// The same analyzer should be used for indexing and searchingStandardAnalyzer analyzer = new StandardAnalyzer(Version.LUCENE_40);// 1. create the indexDirectory index = new RAMDirectory();IndexWriterConfig config = new IndexWriterConfig(Version.LUCENE_40, analyzer);IndexWriter w = new IndexWriter(index, config);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();// 2. queryString 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 = null;try {q = new QueryParser(Version.LUCENE_40, "title", analyzer).parse(querystr);} catch (org.apache.lucene.queryparser.classic.ParseException e) {e.printStackTrace();}// 3. searchint hitsPerPage = 10;IndexReader reader = DirectoryReader.open(index);IndexSearcher searcher = new IndexSearcher(reader);TopScoreDocCollector collector = TopScoreDocCollector.create(hitsPerPage, true);searcher.search(q, collector);ScoreDoc[] hits = collector.topDocs().scoreDocs;// 4. display resultsSystem.out.println("Found " + hits.length + " hits.");for (int i = 0; i < hits.length; ++i) {int docId = hits[i].doc;Document d = searcher.doc(docId);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();doc.add(new TextField("title", title, Field.Store.YES));// use a string field for isbn because we don't want it tokenizeddoc.add(new StringField("isbn", isbn, Field.Store.YES));w.addDocument(doc);}}

StandardAnalyzer analyzer = new StandardAnalyzer();
Directory index = new RAMDirectory();IndexWriterConfig config = new IndexWriterConfig(analyzer);IndexWriter w = new IndexWriter(index, config);
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();

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

String querystr = args.length > 0 ? args[0] : "lucene";
Query q = new QueryParser("title", analyzer).parse(querystr);

int hitsPerPage = 10;
IndexReader reader = DirectoryReader.open(index);
IndexSearcher searcher = new IndexSearcher(reader);
TopDocs docs = searcher.search(q, hitsPerPage);
ScoreDoc[] hits = docs.scoreDocs;

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);System.out.println((i + 1) + ". " + d.get("isbn") + "\t" + d.get("title"));
}

Lucene 概述： https://www.ibm.com/developerworks/cn/java/j-lo-lucene1/

视频实战教程：

基于Lucene4.6+Solr4.6+Heritrix1.14+S2SH实战开发从无到有垂直搜索引擎

网盘地址：https://pan.baidu.com/s/1nwkAamt 密码: 9ang

备用地址（腾讯微云）：http://url.cn/5CmEW7s 密码：p8TmhQ