Function get_num_bytes

example/cacheHierarchy/fkYAML/node.hpp:1842–1862

@brief Query the number of UTF-8 character bytes with the first byte. @param first_byte The first byte of a UTF-8 character. @return The number of UTF-8 character bytes.

/// @param first_byte The first byte of a UTF-8 character.
/// @return The number of UTF-8 character bytes.
inline uint32_t get_num_bytes(uint8_t first_byte) {
    // The first byte starts with 0b0XXX'XXXX -> 1-byte character
    if FK_YAML_LIKELY (first_byte < 0x80) {
        return 1;
    }
    // The first byte starts with 0b110X'XXXX -> 2-byte character
    if ((first_byte & 0xE0) == 0xC0) {
        return 2;
    }
    // The first byte starts with 0b1110'XXXX -> 3-byte character
    if ((first_byte & 0xF0) == 0xE0) {
        return 3;
    }
    // The first byte starts with 0b1111'0XXX -> 4-byte character
    if ((first_byte & 0xF8) == 0xF0) {
        return 4;
    }

    // The first byte starts with 0b10XX'XXXX or 0b1111'1XXX -> invalid
    throw fkyaml::invalid_encoding("Invalid UTF-8 encoding.", {first_byte});
}

/// @brief Checks if `byte` is a valid 1-byte UTF-8 character.
/// @param[in] byte The byte value.