RE: [squid-users] LDAP Authentication with Umlauts

Hi,

I also had problems with umlauts. We use our Lotus Domino Server as LDAP
server and since an update from version 6.5 to 8, our users are unable to
authenticate via IE or Firefox if their password contains umlauts.
We are running squid on BSD and Linux and on both system you are able to
authenticate using squid_ldap_auth on command line.
I figured out that if you use the command line (set to utf-8) the utf-8
code will be send and if you try to use IE or Firefox the ASCII code will
be send.
So I wrote a small work around by adding a new function
rfc1738_unescape_with_utf to squid_ldap_auth.c. The base content is the
original function rfc1738_unescape, but I added a switch statement to
change the character representation from ascii to utf-8 (see code for
german special chars below).

void
rfc1738_unescape_with_utf(char *s)
{
    char hexnum[3];
    int i, j; /* i is write, j is read */
    unsigned int x;
    for (i = j = 0; s[j]; i++, j++) {
        s[i] = s[j];
        if (s[i] != '%')
            continue;
        if (s[j + 1] == '%') { /* %% case */
            j++;
            continue;
        }
        if (s[j + 1] && s[j + 2]) {
            if (s[j + 1] == '0' && s[j + 2] == '0') { /* %00 case */
                j += 2;
                continue;
            }
            hexnum[0] = s[j + 1];
            hexnum[1] = s[j + 2];
            hexnum[2] = '\0';
            if (1 == sscanf(hexnum, "%x", &x)) {
                switch(x) {
                    case 196 :
                        s[i] = (char) 195;
                        s[i + 1] = (char) 132;
                        i++;
                        break;
                    case 214 :
                        s[i] = (char) 195;
                        s[i + 1] = (char) 150;
                        i++;
                        break;
                    case 220 :
                        s[i] = (char) 195;
                        s[i + 1] = (char) 156;
                        i++;
                        break;
                    case 223 :
                        s[i] = (char) 195;
                        s[i + 1] = (char) 159;
                        i++;
                        break;
                    case 228 :
                        s[i] = (char) 195;
                        s[i + 1] = (char) 164;
                        i++;
                        break;
                    case 246 :
                        s[i] = (char) 195;
                        s[i + 1] = (char) 182;
                        i++;
                        break;
                    case 252 :
                        s[i] = (char) 195;
                        s[i + 1] = (char) 188;
                        i++;
                        break;
                    default :
                        s[i] = (char) (0x0ff & x);
                }
                j += 2;
            }
        }
    }
    s[i] = '\0';
}

Regards

Enrico Hoyme
Received on Thu Jul 03 2008 - 10:39:20 MDT