Re: [squid-users] open webpage category database proposal

On Saturday 26 July 2003 6:25 pm, Henrik Nordstrom wrote:

> All you need to make that technically work is to define a DNS
> namespace for URLs. DNS as such is very neutral as long as it is
> defined that the name space for this purpose and is not to look up
> host names. To not confuse others who look into the database A
> records should be avoided. There is many other suitable record types
> to use.

Agreed. DNS is very versatile. However, the fact that you may need to
query on quite a long URL (going well beyond the first /) makes the database
much more complex than the one used for email RBLs.

> One of many difficulties, but probably relatively minor if the system
> works by content classification rather than abstract terms about how
> suitable the content is. If you classify the site as a certain type
> of web site (port, email, portal, business, banking, trading etc)
> then unless you did an error others is likely to agree.

I agree, but I don't really see how this sort of classification is useful?

I assumed the whole point of the idea was to be able to identify sites
carrying pornography, jokes, religious views, anarchist material, pirated
music, copied software etc?

> I would not agree, but I would not thing it is feasible on a "free"
> basis alone.

However, "free", "open" and "volunteer" were important parts of the initial
proposal; that's the main reason why I didn't think it could be achieved.

Antony.

-- 
Most people are aware that the Universe is big.
 - Paul Davies, Professor of Theoretical Physics