GBK-UTF-8-Unicode编码字节问题

 

import java.io.UnsupportedEncodingException;
/**
 * Java中 中英文编码 所占字节位
 * @author NEU-2015
 *
 */
public class DE {
    public static void main(String[] args) {
        String[] charsetNames = {     "UTF-8",
                                    "UTF-16",
                                    "UTF-16BE",
                                    "UTF-16LE",
                                    "UTF-32",
                                    "UTF-32BE",
                                    "UTF-32LE",
                                    "UNICODE",
                                    "GBK",
                                    "GB2312",
                                    "GB18030",
                                    "ISO8859-1",
                                    "BIG5",
                                    "ASCII" };
        for (int i = 0; i < charsetNames.length; i++) {
            printByteLength(charsetNames[i]);
        }
    }

    public static void printByteLength(String charsetName) {
        String en = "a";
        // 一个英文字符
        String zh = "啊";
        // 一个中文字符
        try {
            System.out.println(charsetName + "编码英文字符所占字节数:" + en.getBytes(charsetName).length);
            System.out.println(charsetName + "编码中文字符所占字节数:" + zh.getBytes(charsetName).length);
            System.out.println();
        } catch (UnsupportedEncodingException e) {
            System.out.println("非法编码格式!");
        }
    }
}

 

 

对于GBK编码标准，英文占用1个字节，中文占用2个字节

对于UTF-8编码标准，英文占用1个字节，中文占用3个字节