UTF-8 to UTF-32 simple implementation

converter.cpp

#include <iostream>
#include <iomanip>  // For std::hex
#include <cstdint>  // For uint32_t


void Read(const char8_t* ptr, char32_t &cp) {
    char32_t u1, u2, u3, u4;
    u1 = *ptr++;

    if (u1 <= 0x7F) {  // One byte code point
        cp = u1;
    } else if (u1 <= 0xDF) {  // Two bytes code point
        u2 = *ptr++;
        cp = ((u1 & 0x1F) << 6) | (u2 & 0x3F);
    } else if (u1 <= 0xEF) {  // Three bytes code point
        u2 = *ptr++;
        u3 = *ptr++;
        cp = ((u1 & 0x0F) << 12) | ((u2 & 0x3F) << 6) | (u3 & 0x3F);
    } else if (u1 <= 0xF7) {  // Four bytes code point
        u2 = *ptr++;
        u3 = *ptr++;
        u4 = *ptr++;
        cp = ((u1 & 0x07) << 18) | ((u2 & 0x3F) << 12) | ((u3 & 0x3F) << 6) | (u4 & 0x3F);
    }
}

// Function to print code points in hex format
void printCodePoint(char32_t cp) {
    std::cout << "Code point: U+" << std::hex << std::uppercase << std::setfill('0') 
              << std::setw(4) << static_cast<uint32_t>(cp) << std::dec << std::endl;
}


using namespace std;

int main() {
    const char8_t* testStr = u8"Hello, 世界, الحمد لله"; // Mixed ASCII and multi-byte UTF-8

    const char8_t* ptr = testStr;
    char32_t cp;
    
    std::cout << "Testing UTF-8 to UTF-32 conversion:" << std::endl;
    while (*ptr) {
        Read(ptr, cp);
        printCodePoint(cp);
        
        // Increment pointer according to the number of bytes processed
        if (cp <= 0x7F) {  // 1-byte character
            ptr += 1;
        } else if (cp <= 0x7FF) {  // 2-byte character
            ptr += 2;
        } else if (cp <= 0xFFFF) {  // 3-byte character
            ptr += 3;
        } else if (cp <= 0x10FFFF) {  // 4-byte character
            ptr += 4;
        }
    }

    return 0;
}

/*
OUTPUT:

Testing UTF-8 to UTF-32 conversion:
Code point: U+0048
Code point: U+0065
Code point: U+006C
Code point: U+006C
Code point: U+006F
Code point: U+002C
Code point: U+0020
Code point: U+4E16
Code point: U+754C
Code point: U+002C
Code point: U+0020
Code point: U+0627
Code point: U+0644
Code point: U+062D
Code point: U+0645
Code point: U+062F
Code point: U+0020
Code point: U+0644
Code point: U+0644
Code point: U+0647
*/

WIKI: UTF-8 encodes code points in one to four bytes, depending on the value of the code point. In the following table, the characters u to z are replaced by the bits of the code point, from the positions U+uvwxyz: