Message123895
| Author |
belopolsky |
| Recipients |
belopolsky, doko, georg.brandl, loewis, mark.dickinson, pitrou, r.david.murray, rhettinger, rnk, ruseel, tim.golden, tim.peters, tlesher, vstinner |
| Date |
2010年12月13日.19:29:39 |
| SpamBayes Score |
4.336531e-13 |
| Marked as misclassified |
No |
| Message-id |
<1292268581.13.0.183673441254.issue9012@psf.upfronthosting.co.za> |
| In-reply-to |
| Content |
> it sounds like the patch is ready for commit.
there are two pending patches here:
time.diff - a hack that makes _time.c look like a module while it is not.
add_time_to_vc8_build.diff - a patch for VC 8.0 project file.
I don't like time.diff because it fixes the symptom rather than the core problem. I believe the code that is shared between C modules should be segregated into a true module which would expose its C API via capsule mechanism. Others suggested that this is an overkill and that capsule mechanism is not suitable for the stdlib. On the latter argument, I would like to point that unicodedata already uses capsule mechanism to make itself available to Python's builtin str type.
As I mentioned in msg109219, this situation is not unique to time/datetime. The math and cmath modules similarly use linker tricks to share code in _math.c.
Unassigning because I don't have an informed opinion on add_time_to_vc8_build.diff and cannot move the _time.c issue forward until similar problem is solved for _math.c which I used as the basis for _time.c design. |
|
History
|
|---|
| Date |
User |
Action |
Args |
| 2010年12月13日 19:29:41 | belopolsky | set | recipients:
+ belopolsky, tim.peters, loewis, georg.brandl, rhettinger, doko, mark.dickinson, pitrou, vstinner, ruseel, tim.golden, tlesher, r.david.murray, rnk |
| 2010年12月13日 19:29:41 | belopolsky | set | messageid: <1292268581.13.0.183673441254.issue9012@psf.upfronthosting.co.za> |
| 2010年12月13日 19:29:39 | belopolsky | link | issue9012 messages |
| 2010年12月13日 19:29:39 | belopolsky | create |
|