regex matches on url escape chars

[Colin Nicholson]

Hi,

Found the answer - the % sign was being treated as the start of a hex
sequence, so putting the hex code for the % sign (%25) did the trick.


The working snippet is now:

if (req.url ~ "facebook%252Ecom") {
       set req.url = "/checkurl/facebook.com";
}




Colin


On 26/02/2010 17:24, Colin Nicholson wrote:
> Hi,
> 
> I have a web service which checks URLs sent to it by our software and
> looks up a categorisation for that url (product is a web filter).
> 
> The request is of the form
> 
> /checkurl/http%3A%2F%2Fwww%2Efacebook%2Ecom%3A80%2Fx%2F2613988206%2Ffalse%2Fp%5F1327924941%3D2
> 
> which is checking
> http://www.facebook.com:80/x/2613988206/false/p_1327924941=2.
> 
> 
> I would like to rewrite the request, in this case, to be just
> /checkurl/facebook%2Ecom, but I can't get the % escape codes to match
> anything.
> 
> If the escape codes weren't in use, the following code works fine:
> 
> if (req.url ~ "facebook\.com") {
>         set req.url = "/checkurl/facebook.com";
> }
> 
> but
> 
> if (req.url ~ "facebook\%2Ecom") {
>         set req.url = "/checkurl/facebook%2Ecom";
> }
> 
> does not work. I've tried escaping the %2E with a backslash, but still
> nothing. It isn't practical to change our software to not use the escape
> codes unfortunately.
> 
> 
> Does anyone have any ideas?
> 
> 
> Thanks,
> Colin