Replace #36032Fix#36030
This PR use `net/smtp` instead of gomail's smtp. Now
github.com/wneessen/go-mail will be used only for generating email
message body.
---------
Co-authored-by: Giteabot <teabot@gitea.io>
Follow #36058 for API edit user bug when editing email.
- The Admin Edit User API includes a breaking change. Previously, when
updating a user with an email from an unallowed domain, the request
would succeed but return a warning in the response headers. Now, the
request will fail and return an error in the response body instead.
- Removed `AdminAddOrSetPrimaryEmailAddress` because it will not be used
any where.
Fix https://github.com/go-gitea/gitea/pull/36058#issuecomment-3600005186
---------
Co-authored-by: Giteabot <teabot@gitea.io>
Fix#20390
We should use `ReplacePrimaryEmailAddress` instead of
`AdminAddOrSetPrimaryEmailAddress` when modify user's email from admin
panel. And also we need a database transaction to keep deletion and
insertion succeed at the same time.
Permission & protection check:
- Fix Delete Release permission check
- Fix Update Pull Request with rebase branch protection check
- Fix Issue Dependency permission check
- Fix Delete Comment History ID check
Information leaking:
- Show unified message for non-existing user and invalid password
- Fix#35984
- Don't expose release draft to non-writer users.
- Make API returns signature's email address instead of the user
profile's.
Auth & Login:
- Avoid GCM OAuth2 attempt when OAuth2 is disabled
- Fix#35510
---------
Co-authored-by: wxiaoguang <wxiaoguang@gmail.com>
Fix#35781, #27472
The PR will not correct the wrong numbers automatically.
There is a cron task `check_repo_stats` which will be run when Gitea
start or midnight. It will correct the numbers.
This PR fixes a panic issue in the WaitGroup that occurs when Gitea is
shut down using Ctrl+C.
It ensures that all active connection pointers in the server are
properly tracked and forcibly closed when the hammer shutdown is
invoked.
The process remains graceful — the normal shutdown sequence runs before
the hammer is triggered, and existing connections are given a timeout
period to complete gracefully.
This PR also fixes `no logger writer` problem. Now the log close will
only be invoked when the command exit.
- Fixes#35468
- Fixes#35551
- Fixes#35559
- Replace #35578
---------
Co-authored-by: wxiaoguang <wxiaoguang@gmail.com>
This PR moved the creation of pushing comments before pull request
mergeable checking. So that when the pull request status changed, the
comments should have been created.
---------
Co-authored-by: wxiaoguang <wxiaoguang@gmail.com>
To prevent potential bugs, the logic in #35543 makes `gitcmd.Command`
panic when attempting to override stdout or stderr. Instead of using
`PrepareCmd`, this PR now uses the WithXXX methods directly to avoid the
panic.
Fix#35603
Refactor Git command functions to use WithXXX methods instead of
exposing RunOpts.
This change simplifies reuse across gitrepo and improves consistency,
encapsulation, and maintainability of command options.
---------
Co-authored-by: wxiaoguang <wxiaoguang@gmail.com>
Extend the maximum length of comment.treepath from 255 to 4000
characters.
All databases supported by Gitea allow VARCHAR fields of 4000, so
compatibility is ensured. Git itself does not impose a strict limit on
path length. On Windows, the `core.longpaths` setting has already been
enabled to handle long file paths.
Fix#33716
---------
Signed-off-by: wxiaoguang <wxiaoguang@gmail.com>
Co-authored-by: wxiaoguang <wxiaoguang@gmail.com>
Co-authored-by: Giteabot <teabot@gitea.io>
- ~Upgrade golang to 1.25~ blocked by the issue
https://github.com/go-swagger/go-swagger/issues/3220
- Upgrade minor versions of most dependencies
- Upgrade github.com/google/go-github version to v74
- Fix meilisearch because of sdk interface change
- Use github.com/Necoro/html2text which is a fork instead of html2text
because of https://github.com/jaytaylor/html2text/issues/67 which
resulted in complie failure.
- Fix some deprecated methods of gitlab go client.
Partially fix#32018
`git config` and `git remote` write operations create a temporary file
named `config.lock`. Since these operations are not atomic, they must
not be run in parallel. If two requests attempt to modify the same
repository concurrently—such as during a compare operation—one may fail
due to the presence of an existing `config.lock` file.
In cases where `config.lock` is left behind due to an unexpected program
exit, a global lock mechanism could allow us to safely remove the stale
lock file when a related error is detected. While this behavior is not
yet implemented in this PR, it is planned for a future enhancement.
---------
Signed-off-by: wxiaoguang <wxiaoguang@gmail.com>
Co-authored-by: wxiaoguang <wxiaoguang@gmail.com>
This PR removes the GetTags function from the git module and keeps only
GetTagInfos. All previous usages of GetTags have been replaced with
database-based tag functions.
---------
Co-authored-by: wxiaoguang <wxiaoguang@gmail.com>
For some reasons, branches between database and git are not synced. If a
branch exists in database but not in the git, it should be able to be
deleted.
---------
Co-authored-by: wxiaoguang <wxiaoguang@gmail.com>
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.
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
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
A quick fix for #34991
`ValidateCommitsWithEmails` will create a fake user for a git commit
user with a related Gitea user. The UI should not display a link for
such users.
`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.
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.
Lunny XiaoandGitHub
