一、Unicode

示例代码：

package demo;/*** @Date: 2023-3-17 周五 15:48* @Author: Special Care* @Description: TODO Unicode编码* @Version: 1.0.0*/
public class UnicodeDemo01 {public static void main(String[] args) {/*** Unicode编码* Java中的字符存储的是一个符号的Unicode编码* 可以显示为10进制或16进制形式* Java的字符范围0~65535(FFFF)*/char c1 = 'A'; // 65   41char c2 = '中'; // 20013   4e2dchar c3 = '✈'; // 9992   2708char c4 = 'a'; // 97   61System.out.println((int)c1);// 65System.out.println(Integer.toHexString(c1));// 41System.out.println((int)c2);// 20013System.out.println(Integer.toHexString(c2));// 4e2dSystem.out.println((int)c3);// 9992System.out.println(Integer.toHexString(c3));// 2708System.out.println((int)c4);// 97System.out.println(Integer.toHexString(c4));// 61}
}

二、网络传输与Unicode

三、UTF-8如何编码

四、使用UTF-8转换传输Unicode

五、利用Java-API进行UTF8编码和解码

package demo;import java.nio.charset.StandardCharsets;/*** @Date: 2023-3-17 周五 16:44* @Author: Special Care* @Description: TODO 测试UTF-8编解码API* @Version: 1.0.0*/
public class UTF8Demo {public static void main(String[] args) throws Exception{/*** 测试UTF-8编解码API*/String str = "Javaλ表达式";// 将字符串中的文字进行UTF-8编码// str.getBytes(StandardCharsets.UTF_8)也可以写成str.getBytes("UTF_8")// 经过getBytes方法的转换得到了UTF-8编码的字节数组byte[] bytes = str.getBytes(StandardCharsets.UTF_8);// bytes就可以利用网络进行传输// 将字节数组中的UTF-8编码的字符进行解码// new String(bytes, "UTF-8")String s = new String(bytes, StandardCharsets.UTF_8);System.out.println(s); // Javaλ表达式}
}

六、利用代码输出Unicode编码和UTF8编码

package demo;import java.nio.charset.StandardCharsets;/*** @Date: 2023-3-17 周五 16:44* @Author: 李林泼* @Description: TODO 测试UTF-8编解码API* @Version: 1.0.0*/
public class UTF8Demo {public static void main(String[] args) throws Exception{/*** 测试UTF-8编解码API*/String str = "Javaλ表达式";// 将字符串中的文字进行UTF-8编码// str.getBytes(StandardCharsets.UTF_8)也可以写成str.getBytes("UTF_8")// 经过getBytes方法的转换得到了UTF-8编码的字节数组byte[] bytes = str.getBytes(StandardCharsets.UTF_8);// bytes就可以利用网络进行传输// 将字节数组中的UTF-8编码的字符进行解码// new String(bytes, "UTF-8")String s = new String(bytes, StandardCharsets.UTF_8);System.out.println(s);/*** 输出字符串中每个字符的Unicode* String str = "Javaλ表达式";*/System.out.println("Unicode:");for (int i = 0; i < str.length(); i++) {// i = 0, 1, 2, 3, 4, ...char c = str.charAt(i);System.out.print(c);System.out.print(":");System.out.println(Integer.toBinaryString(c));}System.out.println();System.out.println("UTF-8:");for (byte b : bytes) {System.out.println(Integer.toBinaryString(b & 0xff));}/*** Javaλ表达式* Unicode:* J:1001010* a:1100001* v:1110110* a:1100001* λ:1110111011* 表:1000100001101000* 达:1000111110111110* 式:101111100001111** UTF-8:* 1001010* 1100001* 1110110* 1100001* 11001110* 10111011* 11101000* 10100001* 10101000* 11101000* 10111110* 10111110* 11100101* 10111100* 10001111*/}
}

七、手写UTF8编码、解码

package demo;import java.util.Arrays;/*** @Date: 2023-3-17 周五 17:15* @Author: 李林泼* @Description: TODO 手工编写UTF-8编码、解码* @Version: 1.0.0*/
public class UTF8Coding {/*** 手工编写UTF-8编码* Char. number range  |    UTF-8 octet sequence*    (hexadecimal)    |           (binary)* --------------------+------------------------------* 0000 0000-0000 007F | 0xxxxxxx* 0000 0000-0000 07FF | 110xxxxx 10xxxxxx* 0000 0000-0000 FFFF | 1110xxxx 10xxxxxx 10xxxxxx* 0000 0000-0010 FFFF | 11110xxx 10xxxxxx 10xxxxxx 10xxxxxx*//*** 将一个字符串编码为UTF-8字节数组* @param str 被编码的字符串* @return 经过UTF-8编码以后字节数组*/public static byte[] getBytes(String str){// 预估一下返回值的最大情况byte[] bytes = new byte[str.length() * 4];// index代表bytes数组中数据的存储位置int index = 0;// 遍历字符串中每个字符，根据字符的Unicode编码范围，进行编码// 将编码存储到bytes，bytes中就是返回值UTF-8数据for (int i = 0; i < str.length(); i++) {char c = str.charAt(i);// 判断c范围，根据范围进行编码if (c <= 0x7F){// c在0~0x7F范围内，是1字节编码，1字节编码添加到bytesbytes[index++] = (byte) c;}else if (c <= 0x7FF){// c在0x80~0x7FF范围内，处理两个字节的UTF-8编码//    b1       b2// 110xxxxx 10xxxxxx// 截取字符的后6位//            0b111111int b2 = (c & 0x3F) | 0b10000000;//                    0b11111int b1 = ((c >>> 6) & 0x1F) | 0b11000000;bytes[index++] = (byte) b1;bytes[index++] = (byte) b2;}else if (c < 0xFFFF){// 处理3字节编码// 1110xxxx 10xxxxxx 10xxxxxxint b3 = (c & 0b111111) | 0b10000000;int b2 = ((c >>> 6) & 0b111111) | 0b10000000;int b1 = ((c >>> 12) & 0b1111) | 0b11100000;bytes[index++] = (byte) b1;bytes[index++] = (byte) b2;bytes[index++] = (byte) b3;}}return Arrays.copyOf(bytes,index);}/*** 将UTF-8编码的字节数组解码为字符串(Unicode字符)* @param bytes UTF-8编码的字节* @return 解码以后的字符串*/public static String decode(byte[] bytes){char[] chs = new char[bytes.length];int index = 0;// 遍历字节数组，检查每个字节// 如果字节以0开头，则是单字节编码// 如果是以110开头，则是双字节编码// 如果是以1110开头，则是三字节编码for (int i = 0; i < bytes.length; ) {int b1 = bytes[i++] & 0xff;if ((b1 >>> 7) == 0){// 检查01001010是否为单字节编码0xxxxxxx// b1      00000000 00000000 00000000 01001010// b1>>>7  000000000000000 00000000 00000000 0chs[index++] = (char)b1;}else if ((b1 >>> 5) == 0b110){// 检查是否为双字节编码 b1 11001110 b2 10111011// b1 -> int// b1      00000000 00000000 00000000 11001110// b1>>>5  0000000000000 00000000 00000000 110int b2 = bytes[i++] & 0xff;// b1      00000000 00000000 00000000 11001110// b2      00000000 00000000 00000000 10111011// c       00000000 00000000 0000001110 111011int c = ((b1 & 0b11111)<<6) | (b2 & 0b111111);chs[index++] = (char) c;}else if ((b1 >>> 4) == 0b1110){// 检查是否为三字节编码：11101000 10100001 10101000int b2 = bytes[i++] & 0xff;int b3 = bytes[i++] & 0xff;int c = ((b1 & 0b1111)<<12) | ((b2 & 0b111111)<<6) | (b3 & 0b111111);System.out.println("b1:" + Integer.toBinaryString(b1));System.out.println("b2:" + Integer.toBinaryString(b2));System.out.println("b3:" + Integer.toBinaryString(b3));System.out.println("c:" + Integer.toBinaryString(c));chs[index++] = (char) c;}}return new String(chs,0,index);}public static void main(String[] args) {String str = "Javaλ表达式";System.out.println("Unicode:");for (int i = 0; i < str.length(); i++) {char c = str.charAt(i);System.out.print(c);System.out.print(":");System.out.println(Integer.toBinaryString(c));}// 调用手写UTF-8编码方法byte[] bytes = getBytes(str);for (byte b : bytes) {System.out.println(Integer.toBinaryString(b & 0xff));}// 检查手写的UTF-8解码运算String s = decode(bytes);System.out.println(s);}/*** Unicode:* J:1001010* a:1100001* v:1110110* a:1100001* λ:1110111011* 表:1000100001101000* 达:1000111110111110* 式:101111100001111* 1001010* 1100001* 1110110* 1100001* 11001110* 10111011* 11101000* 10100001* 10101000* 11101000* 10111110* 10111110* 11100101* 10111100* 10001111* b1:11101000* b2:10100001* b3:10101000* c:1000100001101000* b1:11101000* b2:10111110* b3:10111110* c:1000111110111110* b1:11100101* b2:10111100* b3:10001111* c:101111100001111* Javaλ表达式*/
}

八、总结UTF8