using System;

using System.Text;

using System.Collections.Generic;

using System.Linq;

using System.Globalization;

​

using NUnit.Framework;

​

//https://stackoverflow.com/questions/78409290/converting-a-c-sharp-string-to-a-hex-representation-of-its-utf8-encoded-characte

​

public static partial class TextHelper

{

    public static string ToUtf8HexValues(this string s)

    {

        Span<byte> runeByteSpan = stackalloc byte[4]; // rune.EncodeToUtf8() can be up to 4 bytes as shown in https://github.com/dotnet/runtime/blob/main/src/libraries/System.Private.CoreLib/src/System/Text/Rune.cs#L1060

        Span<char> charSpan = stackalloc char[2]; // Greater than or equal to the max number of hex chars in a byte value, which is 2.

        var sb = new StringBuilder();

        foreach (var rune in s.EnumerateRunes())

        {

            if (sb.Length > 0)

                sb.Append(' ');

            for (int i = 0, length = rune.EncodeToUtf8(runeByteSpan); i < length; i++)

                if (runeByteSpan[i].TryFormat(charSpan, out var n, "X"))

                    sb.Append(charSpan.Slice(0, n));

        }

        return sb.ToString();

    }

}

​

public static partial class TextHelper

{

    public static IEnumerable<ReadOnlyMemory<char>> TextElements(this string s) => (s ?? "").AsMemory().TextElements();

​

    public static IEnumerable<ReadOnlyMemory<char>> TextElements(this ReadOnlyMemory<char> s)

    {

        for (int index = 0, length = StringInfo.GetNextTextElementLength(s.Span); 

             length > 0; 

             index += length, length = StringInfo.GetNextTextElementLength(s.Span.Slice(index)))

            yield return s.Slice(index, length);

    }   

    public static string ToUtf8GraphemeHexValues(this string s)

    {

        Span<byte> runeByteSpan = stackalloc byte[4]; // rune.EncodeToUtf8() can be up to 4 bytes as shown in https://github.com/dotnet/runtime/blob/main/src/libraries/System.Private.CoreLib/src/System/Text/Rune.cs#L1060

        Span<char> charSpan = stackalloc char[2]; // Greater than or equal to the max number of hex chars in a byte value, which is 2.

        var sb = new StringBuilder();

        foreach (var chunk in s.TextElements())

        {

            if (sb.Length > 0)

                sb.Append(' ');

            foreach (var rune in chunk.Span.EnumerateRunes())

                for (int i = 0, length = rune.EncodeToUtf8(runeByteSpan); i < length; i++)

                    if (runeByteSpan[i].TryFormat(charSpan, out var n, "X"))

                        sb.Append(charSpan.Slice(0, n));

        }

        return sb.ToString();

    }

}

​

public class Program

{

    public static void Main()

    {

        var input1 = "$£€𐍈";

        var input2 = "$£€𐍈𝐀\u0302";

        var s2 = input2.ToUtf8GraphemeHexValues();

        Console.WriteLine($"{input2}.ToUtf8GraphemeHexValues() = {s2}");

        Assert.That(s2 == "24 C2A3 E282AC F0908D88 F09D9080CC82");

        Assert.That(s2 != input2.ToUtf8HexValues());    

​

        var s1 = input1.ToUtf8HexValues();

        Console.WriteLine($"\n{input1}.ToUtf8HexValues() = {s1}");

        Assert.That(s1 == "24 C2A3 E282AC F0908D88");

        Assert.That(s1 == input1.ToUtf8GraphemeHexValues());

​

        // "Woman Firefighter: Medium Skin Tone".

        // From this answer https://stackoverflow.com/a/66064611/3744182

        // By https://stackoverflow.com/users/1086121/canton7

        // To https://stackoverflow.com/questions/66062139/combining-some-unicode-nonspacing-marks-with-associated-letters-for-uniform-pr

        var input3 = "👩🏽•🚒";

        var s3 = input3.ToUtf8GraphemeHexValues();

        Console.WriteLine($"\n{input3}.ToUtf8GraphemeHexValues() = {s3}");

        // Here we assert that "Woman Firefighter: Medium Skin Tone" consists of only 1 text element, by asserting it contains no spaces.

        Assert.That(!s3.Contains(" "));

        var input4 = "𐍈";

        var s4 = input4.ToUtf8GraphemeHexValues();

​

        Console.WriteLine($"\n{input4}.ToUtf8GraphemeHexValues() = {s4}");

        //https://codepoints.net/U+10348?lang=en

        Assert.That(s4 == "F0908D88");

        //https://stackoverflow.com/questions/42778709/the-longest-character-in-utf-8

        var input5 = "𐍈 ﷽";

​

        var s5 = input5.ToUtf8GraphemeHexValues();

​

        Console.WriteLine($"\n{input5}.ToUtf8GraphemeHexValues() = {s5}");

​

        //https://www.compart.com/en/unicode/U+FDFD

        Assert.That(s5 == "F0908D88 20 EFB7BD");

    }

}

​