这几天闲着没什么事,就鼓捣了一下Lucene的全文检索方面的内容,首先在Apache的Lucene站点 上大致浏览了一下Lucene的相关文档及知识,由于英文不怎么好,干脆直接找中文相关的内容看了,弄了两天,自己整了个Lucene的大致的实现程序,并且添加进自己的站点项目中,做了个简单的测试,出了一点效果,在这里将大致过程做个简单的记录:
1、在原有的maven项目上,增加了一个test-lucene的子模块,原有的与其相关的模块为test-persisit(主要做持久化操作),test-model(主要定义模型的模块), 大致的POM文件如下:
<?xml version="1.0" encoding="UTF-8"?> <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> <parent> <artifactId>test</artifactId> <groupId>org.clzps</groupId> <version>0.0.1-SNAPSHOT</version> </parent> <groupId>org.clzps</groupId> <artifactId>test-lucene</artifactId> <version>0.0.1-SNAPSHOT</version> <packaging>jar</packaging> <name>test-lucene</name> <url>http://maven.apache.org</url> <properties> <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding> <lucene.version>3.1.0</lucene.version> </properties> <dependencies> <!-- 项目模块相关依赖 --> <dependency> <groupId>org.clzps</groupId> <artifactId>test-model</artifactId> <version>${project.version}</version> <type>jar</type> </dependency> <dependency> <groupId>org.clzps</groupId> <artifactId>test-persist</artifactId> <version>${project.version}</version> <type>jar</type> </dependency> <dependency> <groupId>org.apache.lucene</groupId> <artifactId>lucene-analyzers</artifactId> <version>${lucene.version}</version> <type>jar</type> <scope>compile</scope> </dependency> <dependency> <groupId>org.apache.lucene</groupId> <artifactId>lucene-core</artifactId> <version>${lucene.version}</version> <type>jar</type> <scope>compile</scope> </dependency> <dependency> <groupId>org.apache.lucene</groupId> <artifactId>lucene-highlighter</artifactId> <version>${lucene.version}</version> <type>jar</type> <scope>compile</scope> </dependency> <dependency> <groupId>org.apache.lucene</groupId> <artifactId>lucene-smartcn</artifactId> <version>${lucene.version}</version> <type>jar</type> <scope>compile</scope> </dependency> </dependencies> </project>
2、主要的Java文件内容,实现外部应用的直接调用,包括创建index过程,加载index过程(索引已经创建好),搜索过程,具体就不详细描述了,主要自己做记录,看代码:
public class LuceneService {
/**
* Logger
*/
// private final Logger logger = Logger.getLogger(getClass());
/**
* 分词器
*/
private static Analyzer analyzer = Constants.analyzer;
public static void setAnalyzer(Analyzer analyzer) {
LuceneServiceImpl.analyzer = analyzer;
}
/**
* 索引目录路径
*/
private static String indexDirPath = Constants.indexDirectoryPath;
public static void setIndexDirPath(String indexDirPath) {
LuceneServiceImpl.indexDirPath = indexDirPath;
}
/**
* Directory变量
*/
private static FSDirectory fsdirectory = null;
private static RAMDirectory ramDirectory = null;
private static IndexReader fsIndexReader = null;
private static IndexReader ramIndexReader = null;
private void IndexRamToDisk() {
IndexWriterConfig iwConfig = new IndexWriterConfig(Version.LUCENE_31, analyzer);
iwConfig.setOpenMode(OpenMode.CREATE_OR_APPEND);
IndexWriter fsIndexWriter = null;
try {
fsdirectory = FSDirectory.open(new File(indexDirPath));
fsIndexWriter = new IndexWriter(fsdirectory, iwConfig);
fsIndexWriter.addIndexes(new Directory[]{ramDirectory});
fsIndexWriter.optimize();
fsIndexWriter.close();
//关闭ramDirectory
ramDirectory.close();
ramDirectory = null;
} catch (CorruptIndexException e) {
e.printStackTrace();
} catch (LockObtainFailedException e) {
e.printStackTrace();
} catch (IOException e) {
e.printStackTrace();
}
loadIndex();
}
public void createIndex(List<ArticleData> objList) {
IndexWriterConfig iwConfig = new IndexWriterConfig(Version.LUCENE_31, analyzer);
iwConfig.setOpenMode(OpenMode.CREATE);
IndexWriter ramIndexWriter = null;
ramDirectory = new RAMDirectory();
try {
ramIndexWriter = new IndexWriter(ramDirectory, iwConfig);
ramIndexWriter.deleteAll();
ramIndexWriter.commit();
for(int i = 0; i < objList.size(); i++) {
Document doc = AnyObjects2DocumentUtils.Persist2Document(objList.get(i));
ramIndexWriter.addDocument(doc);
System.out.println(i);
}
ramIndexWriter.close();
IndexRamToDisk();
} catch (IOException e) {
e.printStackTrace();
}
}
public void loadIndex() {
try {
if(fsdirectory == null) {
fsdirectory = FSDirectory.open(new File(indexDirPath));
}
fsIndexReader = IndexReader.open(fsdirectory);
} catch (IOException e) {
e.printStackTrace();
}
}
public void search(String queryStr) {
Long start = new Date().getTime();
String[] fields = new String[]{"title","content"};
try {
Query query = new MultiFieldQueryParser(Version.LUCENE_31, fields, analyzer).parse(queryStr);
MultiReader multiReader = null;
if(fsIndexReader == null) return;
if(ramIndexReader == null) {
multiReader = new MultiReader(new IndexReader[]{fsIndexReader});
} else {
multiReader = new MultiReader(new IndexReader[]{fsIndexReader, ramIndexReader});
}
IndexSearcher indexSearcher = new IndexSearcher(multiReader);
TopDocs topDocs = indexSearcher.search(query, null, 100);
System.out.println("检索到【" + topDocs.totalHits + "】条匹配的结果!");
System.out.println("--------------------------------------------------------");
ScoreDoc[] scoreDoc = topDocs.scoreDocs;
for(int i = 0; i < scoreDoc.length; i++) {
Document document = indexSearcher.doc(scoreDoc[i].doc);
Object2DocumentUtils.PrintDocument(document);
}
Long end = new Date().getTime();
System.out.println("搜索时间:" + (end-start));
} catch (ParseException e) {
e.printStackTrace();
} catch (IOException e) {
e.printStackTrace();
}
}
}
3、通过下面的测试代码,即可进行创建Index,加载Index和搜索过程了:
@Test
public void testCreateOrLoadIndex() {
File file = new File(indexDirectoryPath);
if(file.exists()) {
luceneService.loadIndex();
} else {
createIndex();
}
luceneService.search("事件");
}