【编码与乱码】(06)---字符的各种值转换

package example.encoding;

/**
* The Class ChineseValidator.
*/
public class CharacterValueConveter {

/**
* The main method.
*
* @param args the arguments
*/
public static void main(String args[]) {
CharacterValueConveter conveter = new CharacterValueConveter();
conveter.testConvertion("中文");
}

/**
* Test convertion.
*
* @param content the content
*/
public void testConvertion(String content) {
byte[] bytes = content.getBytes();

System.out.println("Original String : " + content);
System.out.println();

// Get bytes array
System.out.println("Convert string to bytes array : ");
for (int i = 0; i < bytes.length; i++) {
System.out.println(" byte[" + i + "]=" + bytes[i]);
}
System.out.println();

// Get each character and unicode
System.out.println("Start to convert by character: " + "\n");
for (int j = 0; j < content.length(); j++) {
char c = content.charAt(j);
printAllValue(c);
}
}

/**
* Prints the all value.
*
* @param c the c
*/
public void printAllValue(char c) {

byte b = (byte) c;
int i = (int) c;
short s = (short) c;
String binaryString = Integer.toBinaryString(i);
String hexString = Integer.toHexString(i);

StringBuffer output = new StringBuffer();
// Base value
output.append("Character : ").append(c).append("\n");
output.append(" byte value : ").append(b).append("\n");
output.append(" int value : ").append(i).append("\n");
output.append(" short value : ").append(s).append("\n");

// Hex value and binary value
output.append(" hex value :").append(hexString).append("\n");
output.append(" binary value : ").append(binaryString).append("\n");

// Unicode value in java file & web page with decimal encoding
output.append(" unicode value (Base 10): ");
output.append("\\u").append(i).append(";").append("\n");

output.append(" unicode value (Base 10 in web page): ");
output.append("&#").append(i).append(";").append("\n");

// Unicode value in java file & web page with hexadecimal encoding
output.append(" unicode value (Base 16): ");
output.append("\\u").append(hexString).append(";").append("\n");

output.append(" unicode value (Base 16 in web page): ");
output.append("&#").append(hexString).append(";").append("\n");

System.out.println(output.toString());
}

}

最终的测试结果如下：

Original String : 中文

Convert string to bytes array :

byte[0]=-42

byte[1]=-48

byte[2]=-50

byte[3]=-60

Start to convert by character:

Character : 中

byte value : 45

int value : 20013

short value : 20013

hex value :4e2d

binary value : 100111000101101

unicode value (Base 10): \u20013;

unicode value (Base 10 in web page): 中

unicode value (Base 16): \u4e2d;

unicode value (Base 16 in web page): e2d;

Character : 文

byte value : -121

int value : 25991

short value : 25991

hex value :6587

binary value : 110010110000111

unicode value (Base 10): \u25991;

unicode value (Base 10 in web page): 文

unicode value (Base 16): \u6587;

unicode value (Base 16 in web page): ᦻ

可以看到在Java中，字符的unicode有两种表示显示：一种是10进制形式，一种是16进制形式。它们可以分别通过：int i = (int)(string.charAt(i))和Integer.toHexString(i);获得。而且在java文件和Web页面，同一个unicode的表示形式是不同。web页面需要用&#进行转义，在java文件中则使用\u进行转义。