Message94223
| Author |
loewis |
| Recipients |
Trundle, barry-scott, loewis, r.david.murray, sebastinas |
| Date |
2009年10月18日.20:03:10 |
| SpamBayes Score |
0.0007673367 |
| Marked as misclassified |
No |
| Message-id |
<4ADB747B.2090503@v.loewis.de> |
| In-reply-to |
<1255879125.44.0.193745924143.issue6952@psf.upfronthosting.co.za> |
| Content |
> 1) I can comment the casts to maintain this goal.
> 2) Or change the output paramter const ness.
>
> Given your feedback I'm guessing you want me to go further with
> the use of const and do (2).
Ah, ok - as I said, I didn't look into detail further. IIUC, changing
output parameters to const could break existing code (right?); this
should be avoided absolutely.
Rather than having the casts, I think I would prefer to take no action
at these places; I recommend to discuss that on python-dev (some may
argue in favor of changing output pointers to const if that is
semantically correct). |
|