通過cpdetector這個開源的jar包可以自動判斷當前文件的內(nèi)容編碼，從而在讀取的時候選擇正確的編碼讀取，避免亂碼問題。
測試結(jié)果，提供截圖:
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 + " ";
}
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"));
}
}