On 21.11.2012 07:29, Alex Rousskov wrote:
> Hello,
>
> Should the following calls use setDenyMessage() instead?
>
>> ./auth/negotiate/UserRequest.cc:
>> auth_user_request->denyMessage("Authentication in progress");
>> ./auth/negotiate/UserRequest.cc:
>> auth_user_request->denyMessage("NTLM authentication requires a
>> persistent connection");
>> ./auth/negotiate/UserRequest.cc:
>> auth_user_request->denyMessage("Login successful");
>> ./auth/negotiate/UserRequest.cc:
>> auth_user_request->denyMessage(arg);
>> ./auth/negotiate/UserRequest.cc:
>> auth_user_request->denyMessage(blob);
>> ./auth/ntlm/UserRequest.cc:
>> auth_user_request->denyMessage("Authentication in progress");
>> ./auth/ntlm/UserRequest.cc:
>> auth_user_request->denyMessage("NTLM authentication requires a
>> persistent connection");
>> ./auth/ntlm/UserRequest.cc:
>> auth_user_request->denyMessage("Login successful");
>> ./auth/ntlm/UserRequest.cc:
>> auth_user_request->denyMessage(blob);
>> ./auth/ntlm/UserRequest.cc:
>> auth_user_request->denyMessage(blob);
>
>
Yes they should.
I think more importantly that the three forms of this accessor should
be combined into the more normal overloaded forms ASAP:
void denyMessage(const char *msg);
const char *denyMessage(void);
There are only three points in the code needing that default-string
accessor and a fast inline get()?get():default pattern would seem to be
very appropriate for all those usage points.
Amos
Received on Wed Nov 21 2012 - 01:09:26 MST
This archive was generated by hypermail 2.2.0 : Wed Nov 21 2012 - 12:00:08 MST