Extract from #34531
## Move Commit status state to a standalone package
Move the state from `structs` to `commitstatus` package. It also
introduce `CommitStatusStates` so that the combine function could be
used from UI and API logic.
## Combined commit status Changed
This PR will follow Github's combined commit status. Before this PR,
every commit status could be a combined one.
According to
https://docs.github.com/en/rest/commits/statuses?apiVersion=2022-11-28#get-the-combined-status-for-a-specific-reference
> Additionally, a combined state is returned. The state is one of:
> failure if any of the contexts report as error or failure
> pending if there are no statuses or a context is pending
> success if the latest status for all contexts is success
This PR will follow that rule and remove the `NoBetterThan` logic. This
also fixes the inconsistent between UI and API. In the API convert
package, it has implemented this which is different from the UI. It also
fixed the missing `URL` and `CommitURL` in the API.
## `CalcCommitStatus` return nil if there is no commit statuses
The behavior of `CalcCommitStatus` is changed. If the parameter commit
statuses is empty, it will return nil. The reference places should check
the returned value themselves.
The notification count is currently positioned using top/left
coordinates from its container's top/left corner. This works fine for
fixed-size containers like the bell icon.
This PR changes the positioning to use bottom/left coordinates from the
container's top/right corner instead. This improvement is needed when
placing notification counts on text that can vary in size due to
different languages or fonts.
The bell and stopwatch should look the same after this change.
---
*Sponsored by Kithara Software GmbH*
Co-authored-by: Marcel Haß <m.hass@kithara.com>
If user leaves the page, the context will become cancelled, so that the
update process maybe terminal in an unexpected status. This PR haven't
resolve the problem totally. It uses a background context to not cancel
the update process even if the user leaved the pull request view page.
Fix#31779
Fixes https://github.com/go-gitea/gitea/issues/34560
explanation of the bug in the issue
setting `issue.isLabelsLoaded = false` before calling `deleteIssueLabel`
guarantee we will load the new state of the labels into the issue object
before sending it in the webhook.
Previously, pressing the down arrow key on the last item of a list would
incorrectly load the latest page when not release key. This commit
corrects the logic to ensure that the next page is loaded as intended.
`GetIssuesLastCommitStatus` will revoke `GetIssuesAllCommitStatus` but
it has been invoked. The `CommitStatus` template variable has never been
used in notification subscription page so that it could be removed.
Similar to #34544, this PR changes the `opts` argument in
`SearchRepositoryByName()` to be passed by value instead of by pointer,
as its mutations do not escape the function scope and are not used
elsewhere. This simplifies reasoning about the function and avoids
unnecessary pointer usage.
This insight emerged during an initial attempt to refactor
`RenderUserSearch()`, which currently intermixes multiple concerns.
---------
Co-authored-by: Philip Peterson <philip-peterson@users.noreply.github.com>
This fixes 3 issues I encountered when debugging problems with our LDAP sync:
1. The comparison of the hashed image data in `IsUploadAvatarChanged` is
wrong. It seems to be from before avatar hashing was changed and unified
in #22289. This results in the function always returning `true` for any
avatars, even if they weren't changed.
2. Even if there's no avatar to upload (i.e. no avatar available for the
LDAP entry), the upload function would still be called for every single
user, only to then fail, because the data isn't valid. This is
unnecessary.
3. Another small issue is that the comparison function (and thus hashing
of data) is called for every user, even if there is no avatar attribute
configured at all for the LDAP source. Thus, I switched the condition
nesting, so that no cycles are wasted when avatar sync isn't configured
in the first place.
I also added a trace log for when there is actually a new avatar being
uploaded for an existing user, which is now only shown when that is
actually the case.
---------
Co-authored-by: wxiaoguang <wxiaoguang@gmail.com>
If the message from form.MergeMessageField is empty, we will miss a "\n"
between the title and the "Co-authored-by:" line. The title and message
should have a blank line between of them.
---------
Co-authored-by: wxiaoguang <wxiaoguang@gmail.com>
Fix the issue where the line-button fails to work after selecting a file
from the file tree.
---------
Co-authored-by: wxiaoguang <wxiaoguang@gmail.com>
This PR adds "View workflow file" to Actions list page, and replaces the
redundant link.
Related #34530
---------
Co-authored-by: wxiaoguang <wxiaoguang@gmail.com>
This PR changes the `opts` argument in `SearchUsers()` to be passed by
value instead of by pointer, as its mutations do not escape the function
scope and are not used elsewhere. This simplifies reasoning about the
function and avoids unnecessary pointer usage.
This insight emerged during an initial attempt to refactor
`RenderUserSearch()`, which currently intermixes multiple concerns.
Co-authored-by: Philip Peterson <philip-peterson@users.noreply.github.com>
- Change CreateVariable API response status from 204 No Content to 201
Created
- Update related integration tests to expect 201 Created instead of 204
No Content
## ⚠️ BREAKING ⚠️
Change the response status code of the Create Variable API under both
Org and Repo levels to `201` instead of 204.
API SDK: https://gitea.com/gitea/go-sdk/pulls/713
---------
Signed-off-by: Bo-Yi Wu <appleboy.tw@gmail.com>
Signed-off-by: appleboy <appleboy.tw@gmail.com>
Co-authored-by: delvh <dev.lh@web.de>
postgres 12 is end of life since 6 months. 13 and above are still
supported but I think it's overall better if we test a more recent
version of postgres because that's what new users will be running on.
Ref: https://endoflife.date/postgresql
The tags synchronization is very slow for a non-mirror repository with
many tags especially forking. This PR make all repositories' tags
synchronization use the same function and remove the low performance
synchronization function. The commit count of tag now will not be stored
into database when syncing. Since the commits count will always be read
from cache or git data, the `NumCommits` in the release table will be
updated for the first read from git data.
