By default, the code extracts 200 package versions. If too many packages
are generated every day or if rule cleaning is enabled later, which
means there are more than 200 versions corresponding to the library
package, it may not be cleaned up completely, resulting in residue
Fix#31961
---------
Co-authored-by: yeyuanjie <yecao100@126.com>
Co-authored-by: wxiaoguang <wxiaoguang@gmail.com>
1. Add some missing (optional) fields for nuget v2, and sort the fields
to make it easier to maintain
2. Add missing "platform" for rubygems: `VERSION-PLATFORM` and
`VERSION_PLATFORM`
Co-authored-by: Giteabot <teabot@gitea.io>
`UpdateAllCols` is dangerous, the columns should be updated when
necessary.
This PR replaces some `updateRepository` invokes to reduce possible
problems and wrongly updated time. Some parts have been fixed in #34388,
but some are hidden in the function `updateRepository`. Alternatively,
using `UpdateRepositoryColsNoAutoTime` to update the changed columns.
Some `UpdateRepoSize` invokes are duplicated, so they will be removed
when extracting from `updateRepository`.
Noticed the SQL will be executed 4 times when visit the file render view
page. For a repository which have many pull requests, it maybe slow.
```SQL
2025/06/08 15:24:44 models/issues/pull_list.go:69:GetUnmergedPullRequestsByHeadInfo() [I] [SQL] SELECT * FROM `pull_request` INNER JOIN `issue` ON issue.id = pull_request.issue_id WHERE (head_repo_id = ? AND head_branch = ? AND has_merged = ? AND issue.is_closed = ? AND flow = ?) [393 main false false 0] - 2.004167ms
2025/06/08 15:24:44 models/issues/pull_list.go:69:GetUnmergedPullRequestsByHeadInfo() [I] [SQL] SELECT * FROM `pull_request` INNER JOIN `issue` ON issue.id = pull_request.issue_id WHERE (head_repo_id = ? AND head_branch = ? AND has_merged = ? AND issue.is_closed = ? AND flow = ?) [393 main false false 0] - 1.03975ms
2025/06/08 15:24:44 models/issues/pull_list.go:69:GetUnmergedPullRequestsByHeadInfo() [I] [SQL] SELECT * FROM `pull_request` INNER JOIN `issue` ON issue.id = pull_request.issue_id WHERE (head_repo_id = ? AND head_branch = ? AND has_merged = ? AND issue.is_closed = ? AND flow = ?) [393 main false false 0] - 881.583µs
2025/06/08 15:24:44 models/issues/pull_list.go:69:GetUnmergedPullRequestsByHeadInfo() [I] [SQL] SELECT * FROM `pull_request` INNER JOIN `issue` ON issue.id = pull_request.issue_id WHERE (head_repo_id = ? AND head_branch = ? AND has_merged = ? AND issue.is_closed = ? AND flow = ?) [393 main false false 0] - 935.084µs
```
This PR did a refactor to query it once only.
* Signed SSH commits can look in the UI like on GitHub, just like gpg keys today in Gitea
* SSH format can be added in gitea config
* SSH Signing worked before with DEFAULT_TRUST_MODEL=committer
`TRUSTED_SSH_KEYS` can be a list of additional ssh public key contents
to trust for every user of this instance
Closes#34329
Related #31392
---------
Co-authored-by: Lunny Xiao <xiaolunwen@gmail.com>
Co-authored-by: techknowlogick <techknowlogick@gitea.com>
Co-authored-by: wxiaoguang <wxiaoguang@gmail.com>
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.
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
`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>
This PR adds "View workflow file" to Actions list page, and replaces the
redundant link.
Related #34530
---------
Co-authored-by: wxiaoguang <wxiaoguang@gmail.com>
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.
* repository deletion, delete ephemeral runners with active tasks as
well skips regular cleanup
* user deletion, delete ephemeral runners with active tasks as well
skips regular cleanup
* delete ephemeral runners once status changes to done
* You no longer see used ephemeral runners after the task is done
* if you see one the cron job takes care of it
This PR changes 3rd party notifications wording on a PR review that
requests changes and can be considered a follow up for #5858 to also fix
#5857 in 3rd party notifications.
The difference in the actual notification would be the following:
```diff
- Pull request review rejected
+ Pull request review changes requested
```
While this is a simple string change at first look, it has a deeper UX
meaning.
# Motivation
We could observe that some developers are hesitant to press the "Request
changes" button since their peers first see that their changes were
rejected, thus a more appropriate wording that also falls in line with
the meaning and UI would be beneficial.
## Meaning
Pressing the `Request changes` button in a PR review means that as a
reviewer you are willing to merge the general change in a PR if changes
requested review comments are implemented.
Rejecting a PR on the other hand would be equivalent with closing it
since that change isn't welcome at all (e.g. out of scope feature).
## Sync with UI
The UI button says `request changes` and the other options
## Considered Problems
This might break some automation for users who rely on string matching.
* mssql does not support fetching 0 repositories
* remove paging by NumRepos that might be 0
* extend admin api test to purge user 2
Fixes#34448
---------
Co-authored-by: wxiaoguang <wxiaoguang@gmail.com>
Issue: After switching the default branch, other branches are still
compared against the old default branch due to outdated divergence
cache.
Change: Clear the divergence cache in SetRepoDefaultBranch to ensure
correct comparisons against the new default branch.
Fixes#34369
Files that should be stored in LFS and are uploaded/edited from the API
or web UI aren't stored in LFS. This may be a regression from #34154.
---------
Co-authored-by: wxiaoguang <wxiaoguang@gmail.com>
In the Gitea GUI, the user can see the time that _AccessTokens_ and
_PublicKeys_ were last used. This information is not returned by the
_/users/{username}/tokens_ and _/user/keys_ endpoints in the API. This
PR adds the missing data.
The time of last usage for for _tokens_ & _keys_ seem to be stored in
the _Updated_ field of the structs internally. For consistency, I have
used the name _updated_at_ for the new field returned by the _API_.
However, for the _API_ user, I don't think that name reflects the data
returned, as I believe it is the time of last usage. I propose that we
use the name _last_used_at_ instead. Let's hear reviewers opinion on
that.
* PublicKey
1. _last_used_at_: string($date-time)
* AccessToken
1. _created_at_: string($date-time) (for parity with public keys)
2. _last_used_at_: string($date-time)
Fix#34313
If archive downloads are are disabled using
_DISABLE_DOWNLOAD_SOURCE_ARCHIVES_, archive links are still returned by
the API.
This PR changes the data returned, so the fields _zipball_url_ and
_tarball_url_ are omitted if archive downloads have been disabled.
Resolve#32159
Fix#34224
The previous implementation in #33744 will get the pushed commits
changed files. But it's not always right when push a merged commit. This
PR reverted the logic in #33744 and will always get the PR's changed
files and get code owners.
Fix#880
Design:
1. A global setting `security.TWO_FACTOR_AUTH`.
* To support org-level config, we need to introduce a better "owner
setting" system first (in the future)
2. A user without 2FA can login and may explore, but can NOT read or
write to any repositories via API/web.
3. Keep things as simple as possible.
* This option only aggressively suggest users to enable their 2FA at the
moment, it does NOT guarantee that users must have 2FA before all other
operations, it should be good enough for real world use cases.
* Some details and tests could be improved in the future since this
change only adds a check and seems won't affect too much.
---------
Co-authored-by: Lunny Xiao <xiaolunwen@gmail.com>
`[repository.pull-request] DELAY_CHECK_FOR_INACTIVE_DAYS` is a new
setting to delay the mergeable check for pull requests that have been
inactive for the specified number of days.
This avoids potentially long delays for big repositories with many pull
requests. and reduces system load overall when there are many
repositories or pull requests.
When viewing the PR, checking will start immediately and the PR merge
box will automatically reload when complete. Accessing the PR through
the API will also start checking immediately.
The default value of `7` provides a balance between system load, and
keeping behavior similar to what it was before both for users and API
access. With `0` all conflict checking will be delayed, while `-1`
always checks immediately to restore the previous behavior.
---------
Co-authored-by: wxiaoguang <wxiaoguang@gmail.com>
