问如何从字符串中间执行区分区域性的“starts with”操作？

EN

x heiße y
  ^--- cursor

x heisse y
  ^--- cursor

//Poor man's case folding.
//There are some edge cases where this doesn't work
public static String toCaseFold( String input, Locale cultureInfo ) {
    return input.toUpperCase(cultureInfo).toLowerCase(cultureInfo);
}

public static bool MaybeRequiresNormalizationToFormC(string input)
{
    if( input == null ) throw new ArgumentNullException("input");

    int len = input.Length;
    for (int i = 0; i < len; ++i)
    {
        if (input[i] > 0x2FF)
        {
            return true;
        }
    }

    return false;
}

public static partial class GlobalizationExtensions {
    public static int IsPrefix(
        this CompareInfo compareInfo,
        String source, String prefix, int startIndex, CompareOptions options
        ) {
        if(compareInfo.IndexOf(source, prefix, startIndex, options)!=startIndex)
            return ~0;
        else
            // source is started with prefix
            // therefore the loop must exit
            for(int length2=0, length1=prefix.Length; ; )
                if(0==compareInfo.Compare(
                        prefix, 0, length1, 
                        source, startIndex, ++length2, options))
                    return length2;
    }
}

var candidate="ßssß\u00E9\u0302";
var text="abcd ssßss\u0065\u0301\u0302sss";

var count=
    culture.CompareInfo.IsPrefix(text, candidate, 5, CompareOptions.IgnoreCase);

public static partial class GlobalizationExtensions {
    public static int Compare(
        this CompareInfo compareInfo,
        String source, String prefix, int startIndex, ref int length2, 
        CompareOptions options) {
        int length1=prefix.Length, v2, v1;

        if(0==(v1=compareInfo.Compare(
            prefix, 0, length1, source, startIndex, length2, options))
            ) {
            return 0;
        }
        else {
            if(0==(v2=compareInfo.Compare(
                prefix, 0, length1, source, startIndex, 1+length2, options))
                ) {
                ++length2;
                return 0;
            }
            else {
                if(v1<0||v2<0) {
                    length2-=2;
                    return -1;
                }
                else {
                    length2+=2;
                    return 1;
                }
            }
        }
    }

    public static int IsPrefix(
        this CompareInfo compareInfo,
        String source, String prefix, int startIndex, CompareOptions options
        ) {
        if(compareInfo.IndexOf(source, prefix, startIndex, options)
                !=startIndex)
            return ~0;
        else
            for(int length2=
                    Math.Min(prefix.Length, source.Length-(1+startIndex)); ; )
                if(0==compareInfo.Compare(
                        source, prefix, startIndex, ref length2, options))
                    return length2;
    }
}

// Noda time code from MatchCaseInsensitive in ValueCursor.cs
static int IsMatch_Original(string source, int index, string match, CompareInfo compareInfo)
{
    unchecked
    {
        if (match.Length > source.Length - index)
        {
            return 0;
        }

        // TODO(V1.2): This will fail if the length in the input string is different to the length in the
        // match string for culture-specific reasons. It's not clear how to handle that...
        if (compareInfo.Compare(source, index, match.Length, match, 0, match.Length, CompareOptions.IgnoreCase) == 0)
        {
            return match.Length;
        }

        return 0;
    }
}

// Using StringInfo.GetNextTextElement to match by text elements instead of characters
static int IsMatch_New(string source, int index, string match, CompareInfo compareInfo)
{
    int sourceIndex = index;
    int matchIndex = 0;

    // Loop until we reach the end of source or match
    while (sourceIndex < source.Length && matchIndex < match.Length)
    {
        // Get text elements at the current positions of source and match
        // Normally that will be just one character but may be more in case of Unicode combining characters
        string sourceElem = StringInfo.GetNextTextElement(source, sourceIndex);
        string matchElem = StringInfo.GetNextTextElement(match, matchIndex);

        // Compare the current elements.
        if (compareInfo.Compare(sourceElem, matchElem, CompareOptions.IgnoreCase) != 0)
        {
            return 0; // No match
        }

        // Advance in source and match (by number of characters)
        sourceIndex += sourceElem.Length;
        matchIndex += matchElem.Length;
    }

    // Check if we reached end of source and not end of match
    if (matchIndex != match.Length)
    {
        return 0; // No match
    }

    // Found match. Return number of matching characters from source.
    return sourceIndex - index;
}

// This should be faster
static int IsMatch_Faster(string source, int index, string match, CompareInfo compareInfo)
{
    int sourceLength = source.Length;
    int matchLength = match.Length;
    int sourceIndex = index;
    int matchIndex = 0;

    // Loop until we reach the end of source or match
    while (sourceIndex < sourceLength && matchIndex < matchLength)
    {
        sourceIndex += GetTextElemLen(source, sourceIndex, sourceLength);
        matchIndex += GetTextElemLen(match, matchIndex, matchLength);
    }

    // Check if we reached end of source and not end of match
    if (matchIndex != matchLength)
    {
        return 0; // No match
    }

    // Check if we've found a match
    if (compareInfo.Compare(source, index, sourceIndex - index, match, 0, matchIndex, CompareOptions.IgnoreCase) != 0)
    {
        return 0; // No match
    }

    // Found match. Return number of matching characters from source.
    return sourceIndex - index;
}

static int GetTextElemLen(string str, int index, int strLen)
{
    bool stop = false;
    int elemLen;

    for (elemLen = 0; index < strLen && !stop; ++elemLen, ++index)
    {
        stop = !IsCombiningCharacter(str, index);
    }

    return elemLen;
}

static bool IsCombiningCharacter(string str, int index)
{
    switch (CharUnicodeInfo.GetUnicodeCategory(str, index))
    {
        case UnicodeCategory.NonSpacingMark:
        case UnicodeCategory.SpacingCombiningMark:
        case UnicodeCategory.EnclosingMark:
            return true;

        default:
            return false;
    }
}

static Tuple<string, int, string, int>[] tests = new []
{
    Tuple.Create("x b\u00e9d y", 2, "be\u0301d", 3),
    Tuple.Create("x be\u0301d y", 2, "b\u00e9d", 4),

    Tuple.Create("x b\u00e9d", 2, "be\u0301d", 3),
    Tuple.Create("x be\u0301d", 2, "b\u00e9d", 4),

    Tuple.Create("b\u00e9d y", 0, "be\u0301d", 3),
    Tuple.Create("be\u0301d y", 0, "b\u00e9d", 4),

    Tuple.Create("b\u00e9d", 0, "be\u0301d", 3),
    Tuple.Create("be\u0301d", 0, "b\u00e9d", 4),

    Tuple.Create("b\u00e9", 0, "be\u0301d", 0),
    Tuple.Create("be\u0301", 0, "b\u00e9d", 0),
};

Test #0: Orignal=BAD; New=OK; Faster=OK
Test #1: Orignal=BAD; New=OK; Faster=OK
Test #2: Orignal=BAD; New=OK; Faster=OK
Test #3: Orignal=BAD; New=OK; Faster=OK
Test #4: Orignal=BAD; New=OK; Faster=OK
Test #5: Orignal=BAD; New=OK; Faster=OK
Test #6: Orignal=BAD; New=OK; Faster=OK
Test #7: Orignal=BAD; New=OK; Faster=OK
Test #8: Orignal=OK; New=OK; Faster=OK
Test #9: Orignal=OK; New=OK; Faster=OK