java自动根据文件内容的编码来读取避免乱码

阅读更多

 

通过cpdetector这个开源的jar包可以自动判断当前文件的内容编码，从而在读取的时候选择正确的编码读取，避免乱码问题。

 

 原创不易，转载请注明出处:java自动根据文件内容的编码来读取避免乱码

 

测试结果,提供截图:

GBK文件内容

UTF8文件内容

 

运行结果:

 

package com.zuidaima.test;

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;

import java.io.BufferedReader;
import java.io.File;
import java.io.FileInputStream;
import java.io.InputStreamReader;

public class Main {

	public static String getContent(String path) throws Exception {
		File file = new File(path);
		CodepageDetectorProxy detector = CodepageDetectorProxy.getInstance();
		detector.add(new ParsingDetector(false));
		detector.add(JChardetFacade.getInstance());
		detector.add(ASCIIDetector.getInstance());
		detector.add(UnicodeDetector.getInstance());
		java.nio.charset.Charset charset = null;
		try {
			charset = detector.detectCodepage(file.toURI().toURL());
		} catch (Exception ex) {
			ex.printStackTrace();
		}
		String charsetName = null;
		if (charset != null) {
			charsetName = charset.name();
		} else {
			charsetName = "UTF-8";
		}
		BufferedReader reader = new BufferedReader(new InputStreamReader(
				new FileInputStream(file), charsetName));
		String line = null;
		String lines = "";
		while ((line = reader.readLine()) != null) {
			lines += line + "\n";
		}
		reader.close();
		return lines;
	}

	public static void main(String[] args) throws Exception {
		System.out.println(getContent("bin/gbk.txt"));
		System.out.println(getContent("bin/utf8.txt"));
	}
}

 代码下载地址:http://www.zuidaima.com/share/1550463235574784.htm