System.Globalization.StringInfo.GetCurrentTextElementLen C# (CSharp) Method

        internal static int GetCurrentTextElementLen(String str, int index, int len, ref UnicodeCategory ucCurrent, ref int currentCharCount)
        {
            BCLDebug.Assert(index >= 0 && len >= 0, "StringInfo.GetCurrentTextElementLen() : index = " + index + ", len = " + len);
            BCLDebug.Assert(index < len, "StringInfo.GetCurrentTextElementLen() : index = " + index + ", len = " + len);
            if (index + currentCharCount == len)
            {
                // This is the last character/surrogate in the string.
                return (currentCharCount);
            }

            // Call an internal GetUnicodeCategory, which will tell us both the unicode category, and also tell us if it is a surrogate pair or not.
            int nextCharCount;
            UnicodeCategory ucNext = CharUnicodeInfo.InternalGetUnicodeCategory(str, index + currentCharCount, out nextCharCount);
            if (CharUnicodeInfo.IsCombiningCategory(ucNext)) {
                // The next element is a combining class.
                // Check if the current text element to see if it is a valid base category (i.e. it should not be a combining category,
                // not a format character, and not a control character).

                if (CharUnicodeInfo.IsCombiningCategory(ucCurrent) 
                    || (ucCurrent == UnicodeCategory.Format) 
                    || (ucCurrent == UnicodeCategory.Control) 
                    || (ucCurrent == UnicodeCategory.OtherNotAssigned)
                    || (ucCurrent == UnicodeCategory.Surrogate))    // An unpair high surrogate or low surrogate
                { 
                   // Will fall thru and return the currentCharCount
                } else {
                    int startIndex = index; // Remember the current index.

                    // We have a valid base characters, and we have a character (or surrogate) that is combining.
                    // Check if there are more combining characters to follow.
                    // Check if the next character is a nonspacing character.
                    index += currentCharCount + nextCharCount;
                    
                    while (index < len)
                    {
                        ucNext = CharUnicodeInfo.InternalGetUnicodeCategory(str, index, out nextCharCount);
                        if (!CharUnicodeInfo.IsCombiningCategory(ucNext)) {
                            ucCurrent = ucNext;
                            currentCharCount = nextCharCount;
                            break;
                        }
                        index += nextCharCount;
                    }
                    return (index - startIndex);
                }
            }
            // The return value will be the currentCharCount.
            int ret = currentCharCount;
            ucCurrent = ucNext;
            // Update currentCharCount.
            currentCharCount = nextCharCount;
            return (ret);
        }
        

        public static int[] ParseCombiningCharacters(string str)
        {
            if (str == null)
            {
                throw new ArgumentNullException("str");
            }
            int length = str.Length;

            int[] array = new int[length];
            if (length == 0)
            {
                return(array);
            }
            int             num = 0;
            int             i   = 0;
            int             num2;
            UnicodeCategory unicodeCategory = CharUnicodeInfo.InternalGetUnicodeCategory(str, 0, out num2);

            while (i < length)
            {
                array[num++] = i;
                i           += StringInfo.GetCurrentTextElementLen(str, i, length, ref unicodeCategory, ref num2);
            }
            if (num < length)
            {
                int[] array2 = new int[num];
                Array.Copy(array, array2, num);
                return(array2);
            }
            return(array);
        }