On Fri, Mar 17, 2006 at 11:46:21PM +0000, Julian Foad wrote:
> Well, it depends on how we advertise (document) it. The way Malcolm has
> described it, its purpose is clearly to allow only the ASCII sub-set, and
> callers will have a right to rely on that.
>
> The other way of doing this, "document the current limitation", is fine as
> long as it is very clear, such as:
>
> +/** Determine whether the UTF-8 string @a name is a valid XML "Name".
> + * Return TRUE if it definitely is, and FALSE if not or if this function
> + * is unsure. (Early implementations of this function recognise only
> + * the ASCII subset of XML "Names".)
>
Yes, that sounds like a better idea. Let me know if you'd like me to
update the docstring again. (I'm not really following the discussion
about exports, so I'm not sure if you're also suggesting we might want
to drop the function altogether).
Regards,
Malcolm
---------------------------------------------------------------------
To unsubscribe, e-mail: dev-unsubscribe@subversion.tigris.org
For additional commands, e-mail: dev-help@subversion.tigris.org
Received on Sat Mar 18 13:50:39 2006