Message154830
| Author |
eric.araujo |
| Recipients |
crustymonkey, eric.araujo, orsenthil |
| Date |
2012年03月03日.11:44:52 |
| SpamBayes Score |
5.394229e-08 |
| Marked as misclassified |
No |
| Message-id |
<1330775094.23.0.374847776774.issue14144@psf.upfronthosting.co.za> |
| In-reply-to |
| Content |
> However, an added option which leaves the current behavior as the default shouldn't hurt.
My opinion too. urllib is sometimes a client, sometimes a library used to build clients, which need a knob to implement their own decisions or possibly ask the user for confirmation.
A new argument being a new feature, this patch must target 3.3.
Some comments on the patch:
+ # NOTE: Setting redirect_post_data to True *can* introduce security
+ # issues and is not recommended unless you are sure of where the
+ # POST data is being redirected!
I would tone down this note, for example:
# setting redirect_post_data to True can introduce security
# issues, use with caution
+ redirect_post_data = False
Is an attribute okay or should methods (__init__, maybe methods that do the requests too) grow a new parameter? |
|
History
|
|---|
| Date |
User |
Action |
Args |
| 2012年03月03日 11:44:54 | eric.araujo | set | recipients:
+ eric.araujo, orsenthil, crustymonkey |
| 2012年03月03日 11:44:54 | eric.araujo | set | messageid: <1330775094.23.0.374847776774.issue14144@psf.upfronthosting.co.za> |
| 2012年03月03日 11:44:53 | eric.araujo | link | issue14144 messages |
| 2012年03月03日 11:44:52 | eric.araujo | create |
|