package com.search.crawler;
import java.io.File;
import java.io.FileInputStream;
import java.io.FileNotFoundException;
import java.io.FileReader;
import java.io.IOException;
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.index.IndexWriter;
import org.apache.lucene.queryParser.ParseException;
import org.apache.lucene.queryParser.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.Directory;
import org.apache.lucene.store.FSDirectory;
import org.apache.lucene.util.Version;
public class IndexProcess {
private static String indexPath = "src/indexFiles"; //生成索引存放目录
public static void createIndex(String docsPath) {
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);
}
System.out.println("Indexing to directory '" + indexPath + "'...");
Directory dir = null;
try {
dir = FSDirectory.open(new File(indexPath));
Analyzer analyzer = new StandardAnalyzer(Version.LUCENE_31);
IndexWriter writer = new IndexWriter(dir, analyzer, true, new IndexWriter.MaxFieldLength(25000));
indexDocs(writer, docDir);
writer.close();
dir.close();
} catch (IOException e) {
// TODO Auto-generated catch block
e.printStackTrace();
}
}
static void indexDocs(IndexWriter writer, File file) throws IOException {
// do not try to index files that cannot be read
if (file.canRead()) {
if (file.isDirectory()) {
File[] files = file.listFiles();
if (files != null) {
for (int i = 0; i < files.length; i++) {
indexDocs(writer, files[i]);
}
}
} else {
FileInputStream fis = null;
try {
fis = new FileInputStream(file);
} catch (FileNotFoundException fnfe) {
fnfe.printStackTrace();
}
try {
// make a new, empty document
Document doc = new Document();
//create index of path
doc.add( new Field("path", file.getPath(), Field.Store.YES, Field.Index.ANALYZED));
//create index of content
doc.add(new Field("content", new FileReader(file)));
writer.addDocument(doc);
} finally {
fis.close();
}
}
}
}
static void search(String key ,String value) {
Date startTime = new Date(); //
Directory dir = null;
try {
dir = FSDirectory.open(new File(indexPath));
IndexSearcher searcher = new IndexSearcher(dir,true);
QueryParser par = new QueryParser(Version.LUCENE_31,key,new StandardAnalyzer(Version.LUCENE_31));
Query query = null;
try {
query = par.parse(value);
} catch (ParseException e) {
// TODO Auto-generated catch block
e.printStackTrace();
}
// System.out.println(query.toString());
TopDocs topDocs = searcher.search(query, null, 1000);
ScoreDoc[] scores = topDocs.scoreDocs;
for (ScoreDoc soc : scores) {
System.out.println(soc+"\t"+searcher.doc(soc.doc).get("path") );
}
} catch (IOException e) {
// TODO Auto-generated catch block
e.printStackTrace();
}
Date endTime = new Date();
System.out.println("总共花了" + (endTime.getTime() - startTime.getTime())+ "毫秒时间");
}
/**
* @param args
*/
public static void main(String[] args) {
// TODO Auto-generated method stub
IndexProcess.createIndex("src/index");
System.out.println("search starting :");
IndexProcess.search("content","revision");
}
}
分享到:
相关推荐
lucene-demo-3.3.0.jar lucene-grouping-3.3.0.jar lucene-highlighter-3.3.0.jar lucene-icu-3.3.0.jar lucene-instantiated-3.3.0.jar lucene-memory-3.3.0.jar lucene-misc-3.3.0.jar lucene-queries-3.3.0.jar ...
Lucene 3.0.0源码包含了多个模块,如core、analysis、queryparser、demo等,分别对应不同的功能模块。开发者可以通过阅读源码了解其内部实现原理,以便更好地进行二次开发和优化。 3.2 关键类解析 - Document:表示...
尽管 Lucene.NET 曾经面临开发停滞的问题,但随着时间的推移,该项目已经稳定下来,并继续为.NET 开发者提供了一个强大的全文搜索解决方案。 **1.2 Lucene 工作原理** Lucene 的核心机制基于索引检索技术,通过...
Lucene的索引机制基于倒排索引,这种技术通过牺牲存储空间来换取快速的检索速度。在索引过程中,Lucene会对输入的文本进行分词,创建一个词项到文档位置的映射。当进行查询时,系统会快速定位到包含查询词的文档,而...
- **添加路径**: 将demo.jar的路径添加到系统环境变量CLASSPATH中,例如:“D:\java\lucene-1.4-final\lucene-demos-1.4-final.jar”。 #### 4. Lucene的核心概念 - **索引(Index)**: 索引是Lucene中最核心的概念...
3.1.3.1. 在PHP Session 中的缺省持久(Persistence) 3.1.3.2. 实现订制存储 3.1.4. 使用Zend_Auth 3.2. 数据库表认证 3.2.1. 简介 3.2.2. 高级使用:持久一个 DbTable 结果对象 3.2.3. 高级用法示例 3.3. ...