Message216734
| Author |
monsanto |
| Recipients |
Jeremy Banks, Mark.Bucciarelli, Ronny.Pfannschmidt, adamtj, asvetlov, aymeric.augustin, dholth, ghaering, monsanto, r.david.murray, scott.urban, torsten, tshepang, zzzeek |
| Date |
2014年04月17日.20:01:11 |
| SpamBayes Score |
-1.0 |
| Marked as misclassified |
Yes |
| Message-id |
<1397764872.15.0.00715565210278.issue10740@psf.upfronthosting.co.za> |
| In-reply-to |
| Content |
> Unfortunately, I don't have backwards-compatible proposal to fix this. Trying to account for a bit more syntax will help in the short term but not fix the underlying issue.
aaugustin -- the patch by torsen made 3 years ago is backwards compatible. It adds a hook that you can use to disable autocommits, but you have to opt-in. I think that is good enough for now. We can worry about how to transition people away from the broken transaction model in the future.
Let's treat this as any other backwards compatibility problem in Python. We have a flag, that when enabled, removes the shitty behavior. In a future release, you get a warning for relying on the shitty behavior. In a release after that, we kill the old behavior. Then we deprecate the flag. In other words, it literally doesn't matter what the flag is. torsen's is fine. We just need some way to enable transactional DDL. |
|
History
|
|---|
| Date |
User |
Action |
Args |
| 2014年04月17日 20:01:12 | monsanto | set | recipients:
+ monsanto, ghaering, Jeremy Banks, r.david.murray, zzzeek, asvetlov, adamtj, dholth, torsten, scott.urban, aymeric.augustin, tshepang, Ronny.Pfannschmidt, Mark.Bucciarelli |
| 2014年04月17日 20:01:12 | monsanto | set | messageid: <1397764872.15.0.00715565210278.issue10740@psf.upfronthosting.co.za> |
| 2014年04月17日 20:01:12 | monsanto | link | issue10740 messages |
| 2014年04月17日 20:01:11 | monsanto | create |
|