Symlinks are followed when you click on a link next to an entry, either
until a file has been found or until we know that the link is dead.
When the link cannot be accessed, we fall back to the current behavior
of showing the document containing the target.
---------
Co-authored-by: wxiaoguang <wxiaoguang@gmail.com>
enable nolintlint scope requirement
add comments to new directives so it's more obvious why they are in
place
---
I can also toggle the mandatory comments on if that's something of
interest.
---------
Co-authored-by: wxiaoguang <wxiaoguang@gmail.com>
Co-authored-by: Giteabot <teabot@gitea.io>
Follow up the "editor" refactor, use the same approach to simplify code,
and fix some docs & comments
---------
Signed-off-by: wxiaoguang <wxiaoguang@gmail.com>
Co-authored-by: delvh <dev.lh@web.de>
This PR fixes a state de-synchronization bug with the issue stopwatch,
it resolves the issue by replacing the ambiguous `/toggle` endpoint
with two explicit endpoints: `/start` and `/stop`.
- The "Start timer" button now exclusively calls the `/start` endpoint.
- The "Stop timer" button now exclusively calls the `/stop` endpoint.
This ensures the user's intent is clearly communicated to the server,
eliminating the state inconsistency and fixing the bug.
---------
Signed-off-by: wxiaoguang <wxiaoguang@gmail.com>
Co-authored-by: wxiaoguang <wxiaoguang@gmail.com>
Fix#34504
Since one required context can match more than one commit statuses, we
should not directly compare the lengths of `requiredCommitStatuses` and
`requiredContexts`
---------
Signed-off-by: Zettat123 <zettat123@gmail.com>
Co-authored-by: wxiaoguang <wxiaoguang@gmail.com>
When viewing a file that the user can't edit because they can't write to
the branch, the new, upload, patch, edit and delete functionality is no
longer disabled.
If no user fork of the repository exists, there is now a page to create one.
It will automatically create a fork with a single branch matching the one
being viewed, and a unique repository name will be automatically picked.
When a fork exists, but it's archived, a mirror or the user can't write
code to it, there will instead be a message explaining the situation.
If the usable fork exists, a message will appear at the top of the edit page
explaining that the changes will be applied to a branch in the fork. The
base repository branch will be pushed to a new branch to the fork, and
then the edits will be applied on top.
The suggestion to fork happens when accessing /_edit/, so that for
example online documentation can have an "edit this page" link to
the base repository that does the right thing.
Also includes changes to properly report errors when trying to commit
to a new branch that is protected, and when trying to commit to an
existing branch when choosing the new branch option.
Resolves#9017, #20882
---------
Co-authored-by: Brecht Van Lommel <brecht@blender.org>
Co-authored-by: wxiaoguang <wxiaoguang@gmail.com>
# Fix Feishu Webhook Signature Verification
This PR implements proper signature verification for Feishu (Lark)
webhooks according to the [official
documentation](https://open.feishu.cn/document/client-docs/bot-v3/add-custom-bot).
## Changes
- Implemented the `GenSign` function based on Feishu's official Go
sample code
- Modified the webhook request creation to include timestamp and
signature in the payload when a secret is configured
- Fixed the signature generation algorithm to properly use HMAC-SHA256
with the correct string format
## Implementation Details
The signature verification works as follows:
1. When a webhook secret is provided, a timestamp is generated
2. The signature string is created using `timestamp + "\n" + secret`
3. The HMAC-SHA256 algorithm is applied to an empty string using the
signature string as the key
4. The result is Base64 encoded to produce the final signature
5. Both timestamp and signature are added to the payload
According to Feishu's documentation, the timestamp must be within 1 hour
(3600 seconds) of the current time to be considered valid.
## Security Note
Feishu emphasizes the importance of keeping webhook URLs secure. Do not
disclose them on GitHub, blogs, or any public sites to prevent
unauthorized use.
## References
- [Feishu Custom Bot
Documentation](https://open.feishu.cn/document/client-docs/bot-v3/add-custom-bot)
---------
Co-authored-by: hiifong <i@hiif.ong>
Co-authored-by: wxiaoguang <wxiaoguang@gmail.com>
The merge-upstream route was so far performing any kind of merge, even
those that would create merge commits and thus make your branch diverge
from upstream, requiring manual intervention via the git cli to undo the
damage.
With the new optional parameter ff_only, we can instruct gitea to error
out, if a non-fast-forward merge would be performed.
Upgrade to
[v0.19.0](https://github.com/golang/tools/releases/tag/gopls%2Fv0.19.0)
and fix issues. Runs with new `warning` serverity setting. This likely
does less checks than before. Additionally, add `make fix` which runs
modernize. This is also verified on CI.
For the record, here are the issues discoverd when running with `info`
severity, in case we want to fix these:
```
tests/integration/repo_test.go:95:5-14: could use tagged switch on i
tests/integration/api_packages_generic_test.go:149:4-64: could use tagged switch on setting.Packages.Storage.Type
services/webhook/msteams_test.go:33:4-33: could use tagged switch on fact.Name
services/webhook/msteams_test.go:59:4-33: could use tagged switch on fact.Name
services/webhook/msteams_test.go:85:4-33: could use tagged switch on fact.Name
services/webhook/msteams_test.go:111:4-33: could use tagged switch on fact.Name
services/webhook/msteams_test.go:138:4-33: could use tagged switch on fact.Name
services/webhook/msteams_test.go:161:4-33: could use tagged switch on fact.Name
services/webhook/msteams_test.go:187:4-33: could use tagged switch on fact.Name
services/webhook/msteams_test.go:213:4-33: could use tagged switch on fact.Name
services/webhook/msteams_test.go:239:4-33: could use tagged switch on fact.Name
services/webhook/msteams_test.go:266:4-33: could use tagged switch on fact.Name
services/webhook/msteams_test.go:407:4-33: could use tagged switch on fact.Name
tests/integration/api_packages_conan_test.go:350:6-33: could use tagged switch on pf.Name
models/issues/tracked_time_test.go:98:3-18: could use tagged switch on user.ID
tests/integration/api_token_test.go:505:5-43: could use tagged switch on minRequiredLevel
services/gitdiff/gitdiff.go:220:33-46: method "getLineLegacy" is unused
```
---------
Co-authored-by: Lunny Xiao <xiaolunwen@gmail.com>
1. Use `OpenXxx` instead of `GetXxx` because the returned readers should
be correctly closed, and clarify the behaviors of the functions: they
increase the download counter
2. Use `packages-content` styles instead of `issue-content`
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>
