Backport #35647
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>
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.
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.
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.
This PR moved git attributes related code to `modules/git/attribute` sub
package and moved language stats related code to
`modules/git/languagestats` sub package to make it easier to maintain.
And it also introduced a performance improvement which use the `git
check-attr --source` which can be run in a bare git repository so that
we don't need to create a git index file. The new parameter need a git
version >= 2.40 . If git version less than 2.40, it will fall back to
previous implementation.
---------
Co-authored-by: wxiaoguang <wxiaoguang@gmail.com>
Co-authored-by: yp05327 <576951401@qq.com>
When list commits, some of the commits authors are the same at many
situations. But current logic will always fetch the same GPG keys from
database. This PR will cache the GPG keys, emails and users for the
context so that reducing the database queries.
---------
Co-authored-by: wxiaoguang <wxiaoguang@gmail.com>
This PR uniform all temporary directory usage so that it will be easier
to manage.
Relate to #31792
- [x] Added a new setting to allow users to configure the global
temporary directory.
- [x] Move all temporary files and directories to be placed under
os.Temp()/gitea.
- [x] `setting.Repository.Local.LocalCopyPath` now will be
`setting.TempPath/local-repo` and the customized path is removed.
```diff
-;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
-;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
-;[repository.local]
-;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
-;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
-;;
-;; Path for local repository copy. Defaults to TEMP_PATH + `local-repo`, this is deprecated and cannot be changed
-;LOCAL_COPY_PATH = local-repo
```
- [x] `setting.Repository.Upload.TempPath` now will be
`settting.TempPath/uploads` and the customized path is removed.
```diff
;[repository.upload]
-;;
-;; Path for uploads. Defaults to TEMP_PATH + `uploads`
-;TEMP_PATH = uploads
```
- [x] `setting.Packages.ChunkedUploadPath` now will be
`settting.TempPath/package-upload` and the customized path is removed.
```diff
;[packages]
-;;
-;; Path for chunked uploads. Defaults it's `package-upload` under `TEMP_PATH` unless it's an absolute path.
-;CHUNKED_UPLOAD_PATH = package-upload
```
- [x] `setting.SSH.KeyTestPath` now will be
`settting.TempPath/ssh_key_test` and the customized path is removed.
```diff
[server]
-;;
-;; Directory to create temporary files in when testing public keys using ssh-keygen,
-;; default is the system temporary directory.
-;SSH_KEY_TEST_PATH =
```
TODO:
- [ ] setting.PprofDataPath haven't been changed because it may need to
be kept until somebody read it but temp path may be clean up any time.
---------
Co-authored-by: wxiaoguang <wxiaoguang@gmail.com>
Fix#28144
To make the resources will be cleanup once failed. All repository
operations now follow a consistent pattern:
- 1. Create a database record for the repository with the status
being_migrated.
- 2. Register a deferred cleanup function to delete the repository and
its related data if the operation fails.
- 3. Perform the actual Git and database operations step by step.
- 4. Upon successful completion, update the repository’s status to
ready.
The adopt operation is a special case — if it fails, the repository on
disk should not be deleted.
