Created
October 8, 2025 18:29
-
-
Save japajoe/5915b098b6871048ed7baed68b25c44f to your computer and use it in GitHub Desktop.
Check if string is valid UTF8
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| bool isValidUTF8(const char *pText, size_t size, size_t &charCount) { | |
| if(size == 0) | |
| size = strlen(pText); | |
| int numBytes = 0; // Number of bytes expected in the current UTF-8 character | |
| unsigned char byte; | |
| const uint8_t *pPayload = reinterpret_cast<const uint8_t*>(pText); | |
| for (size_t i = 0; i < size; ++i) { | |
| byte = pPayload[i]; | |
| if (numBytes == 0) | |
| { | |
| // Determine the number of bytes in the UTF-8 character | |
| if ((byte & 0x80) == 0) | |
| { | |
| // 1-byte character (ASCII) | |
| charCount++; | |
| continue; | |
| } | |
| else if ((byte & 0xE0) == 0xC0) | |
| { | |
| // 2-byte character | |
| numBytes = 1; | |
| } | |
| else if ((byte & 0xF0) == 0xE0) | |
| { | |
| // 3-byte character | |
| numBytes = 2; | |
| } | |
| else if ((byte & 0xF8) == 0xF0) | |
| { | |
| // 4-byte character | |
| numBytes = 3; | |
| } | |
| else | |
| { | |
| // Invalid first byte | |
| return false; | |
| } | |
| charCount++; | |
| } | |
| else | |
| { | |
| // Check continuation bytes | |
| if ((byte & 0xC0) != 0x80) | |
| { | |
| return false; // Invalid continuation byte | |
| } | |
| numBytes--; | |
| } | |
| } | |
| return numBytes == 0; // Ensure all characters were complete | |
| } |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment