ycyin

2023年8月8日

大约 3 分钟

root@Ubuntu:~/dockerfiles/javabase# docker run --rm -it container-registry.oracle.com/java/jdk:8u381-oraclelinux8 /bin/bash
[root@884b90c73fb1 /]#
[root@884b90c73fb1 /]# vi CharsetSupportValidation.java
[root@884b90c73fb1 /]# javac CharsetSupportValidation.java
[root@884b90c73fb1 /]# java CharsetSupportValidation GB18030-2022 \u9fec
Charset GB18030-2022 is supported.
Original: 鿬
Encoded bytes: 82359633
Decoded: 鿬

import java.nio.charset.Charset;
import java.nio.charset.UnsupportedCharsetException;

public class CharsetSupportValidation {
    public static void main(String[] args) {
        if (args.length != 2) {
            System.out.println("Usage: java CharsetSupportValidation <charset> <unicode>");
            return;
        }

        String charsetName = args[0];
        String testString = unescapeUnicode(args[1]);

        try {
            Charset charset = Charset.forName(charsetName);

            // 尝试编码和解码操作
            byte[] encodedBytes = testString.getBytes(charset);
            String decodedString = new String(encodedBytes, charset);

            System.out.println("Charset " + charsetName + " is supported.");
            System.out.println("Original: " + testString); // 原始字符串
            // 将字符串转为指定的charset字符集的编码
            System.out.println("Encoded bytes: " + bytesToHexString(decodedString.getBytes(charset))); 
            System.out.println("Decoded: " + decodedString); // 将字符串通过charset字符集编码后的字符串
        } catch (UnsupportedCharsetException e) {
            System.out.println("Charset " + charsetName + " is not supported.");
        }
    }

    // 将字节数组转换为十六进制字符串
    public static String bytesToHexString(byte[] bytes) {
        StringBuilder hexString = new StringBuilder();
        for (byte b : bytes) {
            String hex = Integer.toHexString(b & 0xFF);
            if (hex.length() == 1) {
                hexString.append('0'); // 确保两位十六进制表示
            }
            hexString.append(hex);
        }
        return hexString.toString();
    }

    // Convert Unicode escape sequence to character
    public static String unescapeUnicode(String input) {
        StringBuilder result = new StringBuilder();
        int length = input.length();
        for (int i = 0; i < length; i++) {
            char currentChar = input.charAt(i);
            if (currentChar == '\\' && i + 1 < length && input.charAt(i + 1) == 'u') {
                // Found a Unicode escape sequence
                String hexDigits = input.substring(i + 2, i + 6);
                char unicodeChar = (char) Integer.parseInt(hexDigits, 16);
                result.append(unicodeChar);
                i += 5; // Skip the rest of the escape sequence
            } else {
                result.append(currentChar);
            }
        }
        return result.toString();
    }
}