Instead of always hiding the dropzone when it's not active:
- hide it when when there are no uploaded files and it becomes inactive
- don't hide it when there are uploaded files
Fixes#35125
---------
Co-authored-by: wxiaoguang <wxiaoguang@gmail.com>
This PR upgrade xorm to v1.3.10 which fixed a bug when both `longtext
json` tags in the struct field. The `longtext` will be ignored and
`json` will be considered as `text`.
A migration has been introduced to modify the column directly to
longtext. And another two columns should also be migrated from text to
longtext.
All these changes only affect mysql database because for other databases
Gitea supported, text is the same as longtext.
Fix#27244Fix#34764Fix#35042
Issue: https://github.com/go-gitea/gitea/issues/9637
Changes introduced: I have clarified the problematic terms (owner and
parent) in all affected endpoints.
The changes were made to relevant:
- HTTP endpoint parameters' descriptions
- response/request models' fields
This MR is big, but most changes are the same. If you'd like me to break
this MR into several smaller ones, let me know :)
---------
Co-authored-by: wxiaoguang <wxiaoguang@gmail.com>
#35015
For easier review, the changes are split into separate commits by broad
category. The extended commit messages include brief summaries. I am
happy to make a separate pull request for each category if preferred.
While many of the changes are corrections, some are influenced by style.
In those cases I have aimed mainly for consistency throughout the file,
picking a style variant that I think is widely accepted and aids
clarity.
There are additional things that could be improved that I have not
touched. For example, contractions (phrasing variants such as "doesn't"
vs. "does not") could be made more consistent. Not sure how colloquial
or formal the maintainers would like the UI to be.
---------
Signed-off-by: Dominik Rubo <dr-1@posteo.net>
Co-authored-by: Dominik Rubo <dominik.rubo@posteo.net>
Co-authored-by: delvh <dev.lh@web.de>
Follow up #35096, fix#35095, fix#35115 and add more tests
The old code used some fragile behaviors which depend on the "nil"
receiver. This PR should be a complete fix for more edge cases.
