Noticed a SQL in gitea.com has a bigger load. It seems both `is_pull`
and `pin_order` are not indexed columns in the database.
```SQL
SELECT `id`, `repo_id`, `index`, `poster_id`, `original_author`, `original_author_id`, `name`, `content`, `content_version`, `milestone_id`, `priority`, `is_closed`, `is_pull`, `num_comments`, `ref`, `pin_order`, `deadline_unix`, `created_unix`, `updated_unix`, `closed_unix`, `is_locked`, `time_estimate` FROM `issue` WHERE (repo_id =?) AND (is_pull = 0) AND (pin_order > 0) ORDER BY pin_order
```
I came across a comment
https://github.com/go-gitea/gitea/pull/24406#issuecomment-1527747296
from @delvh , which presents a more reasonable approach. Based on this,
this PR will migrate all issue and pull request pin data from the
`issue` table to the `issue_pin` table. This change benefits larger
Gitea instances by improving scalability and performance.
---------
Co-authored-by: wxiaoguang <wxiaoguang@gmail.com>
* download endpoint has to use 302 redirect
* fake blob download used if direct download not possible
* downloading v3 artifacts not possible
New repo apis based on GitHub Rest V3
- GET /runs/{run}/artifacts (Cannot use run index of url due to not
being unique)
- GET /artifacts
- GET + DELETE /artifacts/{artifact_id}
- GET /artifacts/{artifact_id}/zip
- (GET /artifacts/{artifact_id}/zip/raw this is a workaround for a http
302 assertion in actions/toolkit)
- api docs removed this is protected by a signed url like the internal
artifacts api and no longer usable with any token or swagger
- returns http 401 if the signature is invalid
- or change the artifact id
- or expired after 1 hour
Closes#33353Closes#32124
---------
Co-authored-by: wxiaoguang <wxiaoguang@gmail.com>
When listing commits, Gitea attempts to retrieve the actual user based
on the commit email. Querying users one by one from the database is
inefficient. This PR optimizes the process by batch querying users by
email, reducing the number of database queries.
- Find the runner before deleting
- Move the main logic from `routers/web/repo/setting/runners.go` to
`routers/web/shared/actions/runners.go`.
---------
Co-authored-by: wxiaoguang <wxiaoguang@gmail.com>
- Find the variable before updating or deleting
- Move the main logic from `routers/web/repo/setting/variables.go` to
`routers/web/shared/actions/variables.go`.
---------
Co-authored-by: wxiaoguang <wxiaoguang@gmail.com>
Co-authored-by: Giteabot <teabot@gitea.io>
1. Fix incorrect `MentionCount` (actually it seems to be deadcode,
affects nothing)
2. Remove fallback sha1 support for time limit token
3. Use route middleware `reqRepoActionsWriter` for `ArtifactsDeleteView`
4. Use clearer message "Failed to authenticate user" instead of "Verify"
when auth fails
5. `tests/integration/benchmarks_test.go` is not quite right, actually
it is never used, so delete it.
6. Remove or update TODO comments
- Both have `RejectTransfer` and `CancelTransfer` because the permission
checks are not the same. `CancelTransfer` can be done by the doer or
those who have admin permission to access this repository.
`RejectTransfer` can be done by the receiver user if it's an individual
or those who can create repositories if it's an organization.
- Some tests are wrong, this PR corrects them.
---------
Co-authored-by: wxiaoguang <wxiaoguang@gmail.com>
This is a follow-up to https://github.com/go-gitea/gitea/pull/33097.
When linking a submodule at a commit in either the repo view, or a diff
when adding a new submodule, link to the tree view of that submodules
intead of the individual commit. This shows the user the full tree,
instead of the diff of the commit.
This makes the assumption that the tree for a given SHA is at
`<repo_url>/tree/<sha>`. This URL format is supported by both Github &
Gitlab, but not Gitea. To fix this, add a redirect from
`<username>/<repo>/tree/<ref>` to `<username>/<repo>/src/<ref>`, so that
Gitea can support this URL structure.
1. add `GetSiteCookieFlashMessage` to help to parse flash message
2. clarify `handleRepoHomeFeed` logic
3. remove unnecessary global variables, use `sync.OnceValue` instead
4. add some tests for `IsUsableUsername` and `IsUsableRepoName`
Extract from #33320
This PR uses a map instead of a struct to store webhook event
information. It removes many duplicated functions and makes the logic
clearer.
After the RefName refactoring, the `ctx.Repo.CommitID` is only set when
there is a `RepoRefByType` middleware.
Many handlers do not use that middleware and they only use "default
branch"
Estimated time represented in hours it might be convenient to
have tracked time represented in the same way to be compared and
managed.
---------
Co-authored-by: Sysoev, Vladimir <i@vsysoev.ru>
Co-authored-by: wxiaoguang <wxiaoguang@gmail.com>
1. the error check was added for go-git, it was caused by the empty `.keep` file in the test fixtures.
2. use `PostFormValue` instead of `PostForm.Get` (`Get` needs to parse the form ahead)
3. fix incorrect container text (it should show "Images" in the header but not "OS/Arch")
4. align maven xml
5. fix closed PR color&icon
Currently, anyone with write permissions to a repo are able to rename
default or protected branches.
This change follows
[GitHub's](https://docs.github.com/en/repositories/configuring-branches-and-merges-in-your-repository/managing-branches-in-your-repository/renaming-a-branch)
design by only allowing repo/site admins to change these branches.
However, it also follows are current design for protected branches and
only allows admins to modify branch names == branch protection rule
names. Glob-based rules cannot be renamed by anyone (as was already the
case, but we now catch `ErrBranchIsProtected` which we previously did
not catch, throwing a 500).
Major changes:
1. do not sync ".keep" file during tests
2. fix incorrect route handler and empty repo handling (backported as #33253 with tests)
3. do not use `RepoRef`: most of the calls are abuses.
4. Use `git.RefType` instead of a new type definition `RepoRefType` on `context`.
---------
Co-authored-by: wxiaoguang <wxiaoguang@gmail.com>
Found while investigating #33210.
This line no longer makes sense because the form field "TagName" is
required, so this would mean that this code path would never be covered.
Because it isn't covered, we end up going down the "update release"
logic where we eventually set `Release.IsTag` to false (meaning it will
now be treated as a release instead of a tag).
This snapshot rewrites the condition to ensure that we aren't trying to
create a tag that already exists.
---------
Co-authored-by: wxiaoguang <wxiaoguang@gmail.com>
1. "blob" is not a "ref", it shouldn't (and not unable to) be handled by
`RepoRefByType`
2. the `/blob/{sha}` handle should use the path param "sha" directly
The `ctx.Repo.RefName` was used to be a "short name", it causes a lot of
ambiguity.
This PR does some refactoring and use `RefFullName` to replace the
legacy `RefName`, and simplify RepoAssignment
Resolve#32341
~Depends on #27151~
- [x] It will display a checkbox of deleting the head branch on the pull
request view page when starting an auto-merge task.
- [x] Add permission check before deleting the branch
- [x] Add delete branch comment for those closing pull requests because
of head branch or base branch was deleted.
- [x] Merge `RetargetChildrenOnMerge` and `AddDeletePRBranchComment`
into `service.DeleteBranch`.
This adds links to submodules in diffs, similar to the existing link
when viewing a repo at a specific commit. It does this by expanding diff
parsing to recognize changes to submodules, and find the specific refs
that are added, deleted or changed.
Related #25888
---------
Co-authored-by: wxiaoguang <wxiaoguang@gmail.com>
This PR fixes a performance problem when reviewing a pull request in a
big instance which have many records in the `review` table.
Traditionally, we should add more indexes in that table. But since
dismissed reviews of 1 pull request will not be too many as expected in
a common repository. Filtering reviews in the memory should be more
quick .
---------
Co-authored-by: wxiaoguang <wxiaoguang@gmail.com>
