0

I've been trying to translate an example whitespace remover from here on SO to run in a C++-cli project. The following looks fine as far as intellisense is concerned:

static String^ TrimAllWithInplaceCharArray(String^ str)
{
    unsigned int len = str->Length;
    array<wchar_t, 1>^ src = str->ToCharArray();
    int dstIdx = 0;
    for (unsigned int i = 0; i < len; i++) {
        wchar_t ch = src[i];
        switch (ch) {
            case L'\u0020': case L'\u00A0': case L'\u1680': case L'\u2000': case L'\u2001':
            case L'\u2002': case L'\u2003': case L'\u2004': case L'\u2005': case L'\u2006':
            case L'\u2007': case L'\u2008': case L'\u2009': case L'\u200A': case L'\u202F':
            case L'\u205F': case L'\u3000': case L'\u2028': case L'\u2029': case L'\u0009':
            case L'\u000A': case L'\u000B': case L'\u000C': case L'\u000D': case L'\u0085':
                continue;
            default:
                src[dstIdx++] = ch;
                break;
        }
    }
    return gcnew String(src, 0, dstIdx);
}

...but doesn't compile:

error C3851 : '\u0020' : a universal - character - name cannot designate a character in the basic character set
error C3850 : '\u0009' : a universal - character - name specifies an invalid character
error C3850 : '\u000A' : a universal - character - name specifies an invalid character
error C2196 : case value '63' already used
error C3850 : '\u000B' : a universal - character - name specifies an invalid character
error C2196 : case value '63' already used
error C3850 : '\u000C' : a universal - character - name specifies an invalid character
error C2196 : case value '63' already used
error C3850 : '\u000D' : a universal - character - name specifies an invalid character
error C2196 : case value '63' already used
error C3850 : '\u0085' : a universal - character - name specifies an invalid character
error C2196 : case value '63' already used

Am I miss-representing a data type or the literal values in some way?

Community
  • 1
  • 1
Jon Cage
  • 36,366
  • 38
  • 137
  • 215
  • 1
    Hard to guess, it compiles clean. It is the kind of error you'd get when the compiler sees `L\u0020` instead of `L'\u0020'`. Or some other kind of Unicode glyph that looks like an apostrophe. So it no longer recognizes it as a literal. Typical copy/pasta accident btw. Use a hex viewer to look at the source file. – Hans Passant Feb 09 '17 at 12:27
  • How about trying to remove the "00". Use '\u20' instead of '\u0020' for example. Just a quick guess. – SunsetQuest Feb 09 '17 at 16:47

1 Answers1

0

See if the following works...

static String^ TrimAllWithInplaceCharArray(String^ str)
{
    unsigned int len = str->Length;
    array<wchar_t, 1>^ src = str->ToCharArray();
    int dstIdx = 0;
    for (unsigned int i = 0; i < len; i++) {
        wchar_t ch = src[i];
        switch (ch) {
        case L'\x20': case L'\xA0': case L'\u1680': case L'\u2000': case L'\u2001':
        case L'\u2002': case L'\u2003': case L'\u2004': case L'\u2005': case L'\u2006':
        case L'\u2007': case L'\u2008': case L'\u2009': case L'\u200A': case L'\u202F':
        case L'\u205F': case L'\u3000': case L'\u2028': case L'\u2029': case L'\x09':
        case L'\x0A': case L'\x0B': case L'\x0C': case L'\x0D': case L'\x85':
            continue;
        default:
            src[dstIdx++] = ch;
            break;
        }
    }
    return gcnew String(src, 0, dstIdx);
}

Found this here...

"You cannot use - u0022 because you cannot use a universal character name that designates a character in the basic character set."

SunsetQuest
  • 8,041
  • 2
  • 47
  • 42
  • 1
    Some more useful background on string literals here: http://stackoverflow.com/questions/10220401/c-string-literals-escape-character – Jon Cage Feb 10 '17 at 08:29