Re: Feedback about the content processing framework

On Wed, 31 Jan 2001, Robert Collins wrote:

> At the moment, the API rule is that the first buffer will always
> be the headers, with no body. There is a flag FILTER_EOF which
> matches your CP_LAST_CHUNK.
>
> FILTER is more appropriate, because content processing is a sub
> case of filters which are more generic.

Would using different functions instead of flags be a "cleaner", less
confusing/error-prone approach?

        myfilterNoteHeaders(buf, ...) // guaranteed to be called once
        myFilterNoteData(buf, ...) // called zero or more times
        myFilterNoteEnd(...) // guaranteed to be called once

If nothing else, it will make coredump analysis easier. :)

Just a thought.

Alex.
Received on Wed Jan 31 2001 - 08:29:18 MST