基于lucene的案例开发：ClassUtil & CharsetUtil

标签：lucene   java   编码检测   工程路径   

/**
 * @Description:  类工具
 */
package com.lulei.util;

public class ClassUtil {
	
	/**
	 * @param c
	 * @return
	 * @Description: 返回类class文件所在的目录
	 */
	public static String getClassPath(Class<?> c) {
		return c.getResource("").getPath().replaceAll("%20", " ");
	}
	
	/**
	 * @Description: 
	 * @param c
	 * @param hasName 是否显示文件名
	 * @return 返回类class文件的地址
	 */
	public static String getClassPath(Class<?> c, boolean hasName) {
		String name = c.getSimpleName() + ".class";
		String path = c.getResource(name).getPath().replaceAll("%20", " ");
		if (hasName) {
			return path;
		} else {
			return path.substring(0, path.length() - name.length());
		}
	}
	
	/**
	 * @Description: 返回类class文件所在的顶级目录
	 * @param c
	 * @return
	 */
	public static String getClassRootPath(Class<?> c) {
		return c.getResource("/").getPath().replaceAll("%20", " ");
	}
	
	public static void main(String[] args) {
		System.out.println(ClassUtil.getClassPath(ClassUtil.class, true));
		System.out.println(ClassUtil.getClassPath(Math.class, true));
		System.out.println(ClassUtil.getClassRootPath(Math.class));
	}
}

 /**  
 *@Description:  编码方式检测类  
 */ 
package com.lulei.util;  

import java.io.IOException;
import java.io.InputStream;
import java.net.URL;
import java.nio.charset.Charset;

import info.monitorenter.cpdetector.io.ASCIIDetector;
import info.monitorenter.cpdetector.io.CodepageDetectorProxy;
import info.monitorenter.cpdetector.io.JChardetFacade;
import info.monitorenter.cpdetector.io.ParsingDetector;
import info.monitorenter.cpdetector.io.UnicodeDetector;
  
public class CharsetUtil {
	private static final CodepageDetectorProxy detector;
	
	static {//初始化探测器
		detector = CodepageDetectorProxy.getInstance();
		detector.add(new ParsingDetector(false));
		detector.add(ASCIIDetector.getInstance());
		detector.add(UnicodeDetector.getInstance());
		detector.add(JChardetFacade.getInstance());
	}

	/**
	 * @param url
	 * @param defaultCharset
	 * @Author:lulei  
	 * @return 获取文件的编码方式
	 */
	public static String getStreamCharset (URL url, String defaultCharset) {
		if (url == null) {
			return defaultCharset;
		}
		try {
			//使用第三方jar包检测文件的编码
			Charset charset = detector.detectCodepage(url);
			if (charset != null) {
				return charset.name();
			}
		} catch (Exception e1) {
			// TODO Auto-generated catch block
			e1.printStackTrace();
		}
		return defaultCharset;
	}
	
	/**
	 * @param inputStream
	 * @param defaultCharset
	 * @return
	 * @Author:lulei  
	 * @Description: 获取文件流的编码方式
	 */
	public static String getStreamCharset (InputStream inputStream, String defaultCharset) {
		if (inputStream == null) {
			return defaultCharset;
		}
		int count = 200;
		try {
			count = inputStream.available();
		} catch (IOException e) {
			// TODO Auto-generated catch block
			e.printStackTrace();
		}
		try {
			//使用第三方jar包检测文件的编码
			Charset charset = detector.detectCodepage(inputStream, count);
			if (charset != null) {
				return charset.name();
			}
		} catch (Exception e1) {
			// TODO Auto-generated catch block
			e1.printStackTrace();
		}
		return defaultCharset;
	}
	
	public static void main(String[] args) throws Exception {
		URL url = new URL("http://www.csdn.net");
		System.out.println(CharsetUtil.getStreamCharset(url, "default"));
	}
}

基于lucene的案例开发：ClassUtil & CharsetUtil

标签：lucene   java   编码检测   工程路径   

原文地址：http://blog.csdn.net/xiaojimanman/article/details/43194793