UTF-8 exception code filtering

From , 2 Years ago, written in Java, viewed 129 times.

public static String filterOffUtf8Mb4(String text)throws UnsupportedEncodingException {
        byte[] bytes = text.getBytes("utf-8");
        ByteBuffer buffer = ByteBuffer.allocate(bytes.length);
        int i = 0;
        while (i < bytes.length) {
                short b = bytes[i];
                        if (b > 0) {
                                buffer.put(bytes[i++]);
                                continue;
                        }
                        b += 256;
                        if ((b ^ 0xC0) >> 4 == 0) {
                                buffer.put(bytes, i, 2);
                                i += 2;
                        }
                        else if ((b ^ 0xE0) >> 4 == 0) {
                                buffer.put(bytes, i, 3);
                                i += 3;
                        }
                        else if ((b ^ 0xF0) >> 4 == 0) {
                                i += 4;
                        }
                        // 添加处理如b的指为-48等情况出现的死循环
                        else {
                                buffer.put(bytes[i++]);
                                continue;
                        }
 
                }
 
                buffer.flip();
 
                return new String(buffer.array(), "utf-8");
        }

Reply to "UTF-8 exception code filtering"

Here you can reply to the paste above

Author What's your name?

Title Give your paste a title.

Language What language is your paste written in?

Your paste Paste your paste here

Create Shorturl Create a shorter url that redirects to your paste?

Private Private paste aren't shown in recent listings.

Delete After When should we delete your paste?

Spam protection Type in the letters

https://burned.cc - Burn After Reading Website

Pastebin.vip

UTF-8 exception code filtering

Reply to "UTF-8 exception code filtering"