Java实现按字节长度截取字符串

public static String substringByBytes(String str, int byteLength) {
    if (str == null || str.isEmpty() || byteLength <= 0) {
        return "";
    }
    
    byte[] bytes = str.getBytes();
    if (byteLength >= bytes.length) {
        return str;
    }
    
    // 处理截取位置可能是多字节字符的情况
    int len = 0;
    for (int i = 0; i < str.length(); i++) {
        char c = str.charAt(i);
        len += (c <= 255) ? 1 : 2; // 假设非ASCII字符占2字节
        
        if (len > byteLength) {
            return str.substring(0, i);
        } else if (len == byteLength) {
            return str.substring(0, i + 1);
        }
    }
    return str;
}

public static String substringByBytes(String str, int byteLength, String charsetName) 
        throws UnsupportedEncodingException {
    if (str == null || str.isEmpty() || byteLength <= 0) {
        return "";
    }
    
    byte[] bytes = str.getBytes(charsetName);
    if (byteLength >= bytes.length) {
        return str;
    }
    
    // 根据编码创建新的字符串
    return new String(bytes, 0, byteLength, charsetName);
}

public static String substringByBytes(String str, int maxBytes, String charsetName) 
        throws UnsupportedEncodingException {
    if (str == null || charsetName == null || charsetName.isEmpty()) {
        return str;
    }
    
    byte[] bytes = str.getBytes(charsetName);
    if (bytes.length <= maxBytes) {
        return str;
    }
    
    // 处理截断可能导致的半个字符问题
    int nBytes = 0;
    int i = 0;
    for (; i < str.length(); i++) {
        char c = str.charAt(i);
        int charBytes = String.valueOf(c).getBytes(charsetName).length;
        if (nBytes + charBytes > maxBytes) {
            break;
        }
        nBytes += charBytes;
    }
    
    return str.substring(0, i);
}

public static void main(String[] args) {
    String testStr = "你好，Java世界！Hello World!";
    
    try {
        System.out.println(substringByBytes(testStr, 10)); // 输出：你好，J
        System.out.println(substringByBytes(testStr, 15, "UTF-8")); // 输出：你好，Java
        System.out.println(substringByBytes(testStr, 20, "GBK")); // 输出：你好，Java世界！
    } catch (UnsupportedEncodingException e) {
        e.printStackTrace();
    }
}

public class ByteLengthStringCutter {
    public static String cutByByteLength(String input, int byteLength) {
        if (input == null || byteLength <= 0) {
            return "";
        }
 
        byte[] bytes = input.getBytes(StandardCharsets.UTF_8);
        if (bytes.length <= byteLength) {
            return input;
        }
 
        StringBuilder sb = new StringBuilder();
        try {
            for (int i = 0; i < byteLength; i++) {
                sb.append((char) bytes[i]);
            }
            return sb.toString();
        } catch (IllegalArgumentException e) {
            // 处理无效的UTF-8序列
            return cutByByteLength(input, byteLength - 1);
        }
    }
}

public class SubstringDemo {

    public static void main(String[] args) {
        // 输入待截取的字符串和截取长度
        String str = "这是一个测试字符串";
        int length = 5; // 需要截取的字节长度

        try {
            // 将字符串转换为字节数组
            byte[] bytes = str.getBytes("UTF-8");
            
            // 进行字节截取
            String result = new String(bytes, 0, length, "UTF-8");

            // 输出截取后的结果
            System.out.println("截取后的结果为：" + result);
        } catch (Exception e) {
            e.printStackTrace();
        }
    }
}