Backport #35410 by ahanoff
Fixes#35159
Swift Package Manager expects an 'author.name' field in package
metadata, but Gitea was only providing schema.org format fields
(givenName, middleName, familyName). This caused SPM to fail with
keyNotFound error when fetching package metadata.
Changes:
- Add 'name' field to Person struct (inherited from
https://schema.org/Thing)
- Populate 'name' field in API response using existing String() method
- Maintains backward compatibility with existing schema.org fields
- Provides both formats for maximum compatibility
The fix ensures Swift Package Manager can successfully resolve packages
while preserving full schema.org compliance.
Co-authored-by: Akhan Zhakiyanov <ahanoff@gmail.com>
Backport #35402 by @silverwind
As per https://github.com/bitnami/containers/issues/83267, my
understanding is that the `docker.io/bitnami` images will be deleted on
September 29.
To prevent this failure mode, use the images on the `bitnamilegacy` org
instead which are snapshots from when they stopped updating them.
Long-term, we should replace these images with official ones.
Co-authored-by: silverwind <me@silverwind.io>
Backport #35287 by @alexblackie
GitHub changed where the attachments on releases are stored, which means
repo migrations with releases now fail because the redirect URLs don't
match the base URL validation. We need to update the base URL check to
check for the `release-assets` subdomain as well.
Co-authored-by: Alex Blackie <alex@blackie.ca>
Backport #35198 by @lunny
Fix#31113
After #22385 introduced LFS GC, it never worked due to a bug in the INI
library: fields in structs embedded more than one level deep are not
populated from the INI file.
This PR fixes the issue by replacing the multi-level embedded struct
with a single-level struct for parsing the cron.gc_lfs configuration.
Added a new test for retrieving cron settings to demonstrate the bug in
the INI package.
Co-authored-by: Lunny Xiao <xiaolunwen@gmail.com>
The commit range in the UI follows a half-open, half-closed convention:
(,]. When reviewing a range of commits, the beforeCommitID should be set
to the commit immediately preceding the first selected commit. For
single-commit reviews, we must identify and use the previous commit of
that specific commit.
The endpoint ViewPullFilesStartingFromCommit is currently unused and can
be safely removed.
Fix#35157
Replace #35184
Partially extract from #35077
Backport #35192
Backport #35149
with `nix develop -c $SHELL` you can enter the dev environment. now with
`make clean-all generate build -j1` you will get a static linked binary
that has sqlite support
outside of an nix dev shell if you set `STATIC=true` you also will get a
static binary
Backport #35156 by @bartvdbraak
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: Bart van der Braak <bartvdbraak@gmail.com>
Co-authored-by: wxiaoguang <wxiaoguang@gmail.com>
Backport #35009
This PR fixes the response format for the OpenAPI Spec of
`ActionsListRepositoryWorkflows`.
It was specified in the OpenAPI spec as returning a `[]*ActionWorkflow`,
but it actually should return a `api.ActionWorkflowResponse`.
The test already expects an `api.ActionWorkflowResponse` like expected.
Co-authored-by: Scion <Filiecs2@gmail.com>
Backport #34863 by @wxiaoguang
Remove the misleading error log, fix#34738
Make the "search" input auto-focused, fix#34807
Co-authored-by: wxiaoguang <wxiaoguang@gmail.com>
Backport #34815Fix#34504
Since one required context can match more than one commit statuses, we
should not directly compare the lengths of `requiredCommitStatuses` and
`requiredContexts`
Backport #34632 by @anthony-zh
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: anthony-zh <118415914+anthony-zh@users.noreply.github.com>
Co-authored-by: wxiaoguang <wxiaoguang@gmail.com>
Backport #34703 by @lunny
Fix#34688
This PR will store the `publisher_id` of `release`(tag) table as
pusher's id. It could be a real userID or a system user id. If the user
is deleted, ghost will be replaced.
This PR will also correct the wrong user `Ghost` in the feeds and wrong
committer on tag list page if pushing a tag from an actions. Now the
behavior is the same as Github. Some codes are deleted because it tries
to get commit author as pusher which is not right.
Co-authored-by: Lunny Xiao <xiaolunwen@gmail.com>
Backport #34745 by MaxWebZ
When adding a link using the "Add a link" button in comment editor,
pasting a URL resulted in incorrect Markdown formatting (double
brackets) instead of replacing the placeholder text.
This fix adds a context check to prevent creating a new markdown link
when we're already inside an existing one.
Fixes#34740
Co-authored-by: MaxWebZ <5054326@gmail.com>
Co-authored-by: wxiaoguang <wxiaoguang@gmail.com>
Backport #34621 by @charles7668
Close#34511Close#34590
Add comment ID to the footnote item's id attribute to ensure uniqueness.
Co-authored-by: charles <30816317+charles7668@users.noreply.github.com>
Co-authored-by: wxiaoguang <wxiaoguang@gmail.com>
Backport #34666 by wxiaoguang
Fix#25846
1. the ImageConfig can be empty, fall back to default
2. the blob size can be empty, it still needs "Content-Length" header
Co-authored-by: wxiaoguang <wxiaoguang@gmail.com>
Backport #34509 by @lunny
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
Co-authored-by: Lunny Xiao <xiaolunwen@gmail.com>
Backport #34575 by @badhezi
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.
Co-authored-by: badhezi <zlilaharon@gmail.com>
Backport #34142 by @lunny
Fix the bug when deleting orphaned issues attachments. The attachments
maybe stored on other storages service rather than disk.
Co-authored-by: Lunny Xiao <xiaolunwen@gmail.com>
Backport #34573 by @raucao
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: Râu Cao <842+raucao@users.noreply.github.com>
Co-authored-by: wxiaoguang <wxiaoguang@gmail.com>
Backport #34512 by tclin914
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: Jim Lin <jim@andestech.com>
Co-authored-by: wxiaoguang <wxiaoguang@gmail.com>
Backport #34525 by @MarkusAmshove
closes#34171
Adds a new sort option `recentclose` for issues and pull requests which
will return items in a descending order of when they were closed
Co-authored-by: Markus Amshove <scm@amshove.org>
Backport #34514 by @silverwind
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
Co-authored-by: silverwind <me@silverwind.io>
Backport #34355 by @lunny
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.
Co-authored-by: Lunny Xiao <xiaolunwen@gmail.com>
Backport #34480 by @ChristopherHX
* previously deleting an already deleted runner returned http 500
* previously any database error for the get endpoint was http 404 and
never 500
Co-authored-by: ChristopherHX <christopher.homberger@web.de>
Backport #34449 by @ChristopherHX
* 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: ChristopherHX <christopher.homberger@web.de>
Co-authored-by: wxiaoguang <wxiaoguang@gmail.com>
Backport #34438 by @silverwind
In the comment editor, there is a bug in Firefox where the scroll
position unexpectedly moves up, which is annoying. This is not
reproducible in Chrome and Safari. To reproduce here are some steps:
- Go into an editable issue
- Scroll page to bottom
- Focus the textarea and press Return many times, causing the textarea
to get a scrollbar
- Scroll page to bottom again
- Press Return once more
- Page should not scroll up.
This fixes the bug by adding a temporary margin, and I verified it works
in all browsers.
Co-authored-by: silverwind <me@silverwind.io>
Co-authored-by: wxiaoguang <wxiaoguang@gmail.com>
Backport #34412 by wxiaoguang
Fix#34398, fix#33308
Remove all `repo.ComposeCommentMetas` from templates,
only use `repo` to render commit message.
Co-authored-by: wxiaoguang <wxiaoguang@gmail.com>
Backport #34370 by @GWDx
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
Co-authored-by: GWDx <gwdx@mail.ustc.edu.cn>
Backport #34367 by bytedream
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: bytedream <bytedream@protonmail.com>
Co-authored-by: wxiaoguang <wxiaoguang@gmail.com>
Backport #34385 by @lunny
There will be a possible bug when migrating from Github
https://github.com/google/go-github/issues/3229
This PR upgrades go-github from v61 to v71 to resolve that problem.
Co-authored-by: Lunny Xiao <xiaolunwen@gmail.com>
Backport #34334 by @lunny
The `ci.HeadGitRepo` was opened and closed in the function
`ParseCompareInfo` but reused in the function `PrepareCompareDiff`.
Co-authored-by: Lunny Xiao <xiaolunwen@gmail.com>
Backport #34323 by @tobiasbp
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
Co-authored-by: Tobias Balle-Petersen <tobiasbp@gmail.com>
Backport #34324 by @tobiasbp
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
Co-authored-by: Tobias Balle-Petersen <tobiasbp@gmail.com>
// Should "running" win? Maybe no: old code does make "running" win, but GitHub does fail fast.
// failure with other status, usually fail fast, but "running" wins to match GitHub's behavior
// another reason that we can't make "failure" wins over "running": it would cause a weird behavior that user cannot cancel a workflow or get current running workflows correctly by filter after a job fail.
// GetTeamsWithAccessToAnyRepoUnit returns all teams in an organization that have given access level to the repository special unit.
// This function is only used for finding some teams that can be used as branch protection allowlist or reviewers, it isn't really used for access control.
// FIXME: TEAM-UNIT-PERMISSION this logic is not complete, search the fixme keyword to see more details
varignoreRevsFileCleanupfunc()// TODO: maybe it should check the returned err in a defer func to make sure the cleanup could always be executed correctly
assert.NoError(t,err,"Unable to get commit information for entries of subtree: %s in commit: %s from testcase due to error: %v",testCase.Path,testCase.CommitID,err)
Lunny Xiao
Giteabot
6543
wxiaoguang
ChristopherHX
Zettat123
NorthRealm