Message416648
> My main hesitation with this name is that I suspect users may think that `use_utc_designator` means that they *unconditionally* want to use `Z` — without reading the documentation (which we can assume 99% of users won't do)
I was thinking along similar lines when I used `use_utc_designator` in the PR, but I drew a different conclusion. I was thinking that the name `use_utc_designator` is sufficiently abstruse that no one would even be able to guess that it's referring to "Z" without actually reading the documentation for the parameter. In particular, I worry that `zulu=True` or `allow_Z=True` might lead people to make the mistake of thinking that they'll always get "Z" instead of "+00:00".
> A name like `utc_as_z` is definitely less... elegant, but conveys the concept a bit more clearly.
This would definitely be more memorable and more approachable. If we stick with making it conditional on `tzname() == "UTC"`, I definitely think we want to have "utc" in the name of the parameter, and `utc_as_z` satisfies that.
`utc_as_z` seems reasonable to me. Let me know if you'd like me to update the PR. |
|
Date |
User |
Action |
Args |
2022-04-04 01:30:42 | godlygeek | set | recipients:
+ godlygeek, brett.cannon, belopolsky, eric.araujo, p-ganssle |
2022-04-04 01:30:42 | godlygeek | set | messageid: <1649035842.8.0.582542762741.issue46614@roundup.psfhosted.org> |
2022-04-04 01:30:42 | godlygeek | link | issue46614 messages |
2022-04-04 01:30:42 | godlygeek | create | |
|