win1252(cp1252), iso8859, utf8转换乱码问题 http://bbs.csdn.net/topics/390010852

乱码溯因.java

import java.io.UnsupportedEncodingException;
import java.nio.charset.Charset;

/**
 * 原问题在 http://bbs.csdn.net/topics/390010852:
 * 代码如下：
    try
    {
        PreparedStatement preStmt = con.prepareStatement("insert into t_bb(f_no,f_name) values(?,?)");
        preStmt.setString(1,"ABCDEFG");
        preStmt.setString(2,"中国从前有个传说");
        preStmt.executeUpdate();
    }
    catch(SQLException e)
    {
        System.out.println(new String(e.toString().getBytes("iso-8859-1"),"utf-8"));
    }
    
    <p>执行插入数据失败后，提示如下：
    Duplicate entry 'ABCDEFG-中�?��?�??�??个传说' for key 'PRIMARY'
    部分中文能正常显示，而部分为乱码，这是怎么回事？
 *
 */
public class 乱码溯因 {

  public static void main(String[] 参数) throws UnsupportedEncodingException {
    String 初始字符串 = "中国从前有个传说";
    
    // 受 http://blog.csdn.net/zyf814/article/details/17021949 启发
    String 编码1 = "utf-8";
    String 编码2 = "windows-1252";
    String 编码3 = "iso-8859-1";
    String 编码4 = "utf-8";
    
    byte[] 字节 = 初始字符串.getBytes(编码1);
    System.out.println("UTF8表示:\n" + encodeHex(字节));
    String 转编码后 = new String(字节, 编码2);
    System.out.println(编码2 + "表示:\n" + encodeHex(转编码后.getBytes(编码2)));
    byte[] 转码字节 = 转编码后.getBytes(编码3);
    System.out.println(编码3 + "表示:\n" + encodeHex(转码字节));
    String 二转编码后 = new String(转码字节, 编码4);
    System.out.println(编码4 + "表示:\n" + encodeHex(二转编码后.getBytes(编码4)));
    System.out.println(二转编码后);
  }

  public static final String encodeHex(byte[] bytes) {
    StringBuffer buff = new StringBuffer(bytes.length * 2);
    String b;
    for (int i = 0; i < bytes.length; i++) {
      b = Integer.toHexString(bytes[i]);
      // byte是两个字节的,而上面的Integer.toHexString会把字节扩展为4个字节
      buff.append(b.length() > 2 ? b.substring(6, 8) : b);
      buff.append(" ");
    }
    return buff.toString();
  }

}