Re: [PATCH v1] unit-tests for request first-line parser.

On 08/29/2010 09:08 PM, Amos Jeffries wrote:

> By "offset memory" I mean the values from previous runs that HttpParser
> stores for offset to various pieces of the request line.
>
> init() reset the overall start/end offsets known for the line, but left
> the finer details like start/end offsets in held for method/URL/version at
> some random value from a previous run or in the case of a unused
> HttpParser, pointing at some random offset in RAM heap space relative to
> the about to be processed read buffer.

The random offset would not be possible once init() becomes a
constructor, as it should. Stale finer details is a bug if we reuse
parsers outside of test cases. It feels like we should probably destruct
the parser structure instead of trying to invalidate and then
re-initialize it, but it is your call.

Thank you,

Alex.
Received on Mon Aug 30 2010 - 05:00:59 MDT