There seems to be a problem in this function, I'd expect it to either escape
or convert to utf-8 some of the unicode characters. For example, in the
following sample
// test app to call the widechar version of url functions, showing bug in
Japanese locale
#include <windows.h>
#include <wininet.h>
#include <stdio.h>
void main()
{
wchar_t buf[1024];
DWORD dsize = _countof(buf);
wchar_t wszName[] = {L'C', L':', L'\', 0xff11, 0};
BOOL b = ::InternetCanonicalizeUrlW(wszName, buf, &dsize, 0);
if (b) {
URL_COMPONENTSW uc;
memset(&uc, 0, sizeof(uc)); // default all fields to null
wchar_t wszUrlPath[200];
uc.lpszUrlPath = wszUrlPath;
uc.dwUrlPathLength = _countof(wszUrlPath);
BOOL b2 = ::InternetCrackUrlW(buf, 0, 0, &uc);
if (b2) {
printf("UrlPath len = %d: ", uc.dwUrlPathLength);
for (int i = 0; i < uc.dwUrlPathLength; i++) {
printf(" %x", wszUrlPath[i]);
}
printf("
");
}
}
}
If you run it on US locale, you get this output:
UrlPath len = 4: 43 3a 5c ff11
And on Japanese locale, this output:
UrlPath len = 4: 43 3a 5c 45
Thanks for any information.
--
Ravi K.
