## Summary
This PR adds support for closing keywords (`closes`, `fixes`, `reopens`,
etc.) with full URL references in markdown links.
**Before:**
- `closes #123` ✅ works
- `closes org/repo#123` ✅ works
- `Closes [this issue](https://gitea.io/user/repo/issues/123)` ❌ didn't
work
- `Fixes [#456](https://gitea.io/org/project/issues/456)` ❌ didn't work
**After:**
All of the above now work correctly.
## Problem
When users reference issues using full URLs in markdown links (e.g.,
`Closes [this issue](https://gitea.io/user/repo/issues/123)`), the
closing keywords were not detected. This was because the URL processing
code explicitly stated:
```go
// Note: closing/reopening keywords not supported with URLs
```
Both methods of writing the reference render the same in the UI, so
users expected the closing keywords to behave the same.
## Solution
The fix works by:
1. Passing the original (unstripped) content to
`findAllIssueReferencesBytes`
2. When processing URL links from markdown, finding the URL position in
the original content
3. For markdown links `[text](url)`, finding the opening bracket `[`
position
4. Using that position to detect closing keywords before the link
## Testing
Added test cases for:
- `Closes [this issue](url)` - single URL with closing keyword
- `This fixes [#456](url)` - keyword in middle of text
- `Reopens [PR](url)` - reopen keyword with pull request URL
- Multiple URLs where only one has a closing keyword
All existing tests continue to pass.
Fixes#27549
This pull request adds an option to automatically verify SSH keys from
LDAP authentication sources.
This allows a correct authentication and verification workflow for
LDAP-enabled organizations; under normal circumstances SSH keys in LDAP
are not managed by users manually.
Use the dynamically parsed host in the request for LFS links, but not
use the hard-coded AppURL.
Make LFS server support multi-domain or run Gitea behind a reverse-proxy
with different ROOT_URL.
---------
Co-authored-by: wxiaoguang <wxiaoguang@gmail.com>
Crowdin does not remove empty lines in nested JSON translation files.
Therefore, we use flattened translation keys instead. We have also
updated the key-loading logic to ensure that empty values are not
applied during translation.
---------
Signed-off-by: Lunny Xiao <xiaolunwen@gmail.com>
Co-authored-by: TheFox0x7 <thefox0x7@gmail.com>
Co-authored-by: silverwind <me@silverwind.io>
- Replace fomantic form CSS with custom module
- Moved code in `form.css` to `modules/form.css`, removed around 70% of
the previous module.
- Moved captcha styles previously in `form.css` to its own file.
There is probably more unused CSS, like form error state colors which to
my knowledge is not used anywhere, but I'm not sure about that one so I
kept it.
One notable change is the removal of `type` combinator here, which
lowers the selector specificity and I noticed one issue where selector
`.ui.search > .prompt` was winning, so I added a workaround for that
until the `search` module can be removed as well.
```css
.ui.form .fields.error .field input:not([type])
.ui.form .fields.error .field input[type="date"]
```
Co-authored-by: Lunny Xiao <xiaolunwen@gmail.com>
Co-authored-by: Giteabot <teabot@gitea.io>
Fixes: https://github.com/go-gitea/gitea/issues/36216
Now `detectWebAuthnSupport` returns the error type and lets the caller
decide whether they call `webAuthnError` and show the error. It no
longer shows the error during page load when the user has not even
interacted with the feature.
The bug affects all users on HTTP, so I think a quick fix release for
this might be good.
## Summary
This PR refactors the `SearchIssues` function in
`routers/api/v1/repo/issue.go` by extracting common logic into reusable
helper functions:
- `parseIssueIsClosed()`: Parses the "state" query parameter and returns
the corresponding `isClosed` option
- `parseIssueIsPull()`: Parses the "type" query parameter and returns
the corresponding `isPull` option
- `buildSearchIssuesRepoIDs()`: Builds the list of repository IDs for
issue search based on query parameters
### Benefits:
- Improved code readability
- Smaller, more focused functions
- Easier to test individual components
- Potential for reuse in other handlers
### Changes:
- Extracted 3 helper functions from the ~292 line `SearchIssues`
function
- No functional changes - behavior remains the same
- Proper error handling preserved
## Test plan
- [ ] Verify existing API tests pass
- [ ] Manual testing of `/repos/issues/search` endpoint
Ref: #35015
---------
Co-authored-by: wxiaoguang <wxiaoguang@gmail.com>
Currently, when editing or deleting a file and the edit/commit form has
changes, navigating the file tree will discard all changes without any
warning. This PR prevents partial reloading when the edit form has
unsaved changes, which will trigger a browser native warning dialog.
---------
Co-authored-by: wxiaoguang <wxiaoguang@gmail.com>
Add additional logic with tests to restore the
previous behaviour when writing the principals file.
Fixes: #36212
---------
Signed-off-by: Peter Verraedt <peter.verraedt@kuleuven.be>
Co-authored-by: wxiaoguang <wxiaoguang@gmail.com>
Bumps
[appleboy/git-push-action](https://github.com/appleboy/git-push-action)
from 0.0.3 to 1.0.0.
<details>
<summary>Release notes</summary>
<p><em>Sourced from <a
href="https://github.com/appleboy/git-push-action/releases">appleboy/git-push-action's
releases</a>.</em></p>
<blockquote>
<h2>v1.0.0</h2>
<h2>Changelog</h2>
<h3>Enhancements</h3>
<ul>
<li>50ae8aaf06c6fc08b3d13da3aa03deb50d970125: chore(docker): improve
overall system performance and API integration (<a
href="https://github.com/appleboy"><code>@appleboy</code></a>)</li>
</ul>
<h3>Build process updates</h3>
<ul>
<li>feea2e25baaa5ea24a9689a8af03f229ec1dd1a2: ci: improve testing
workflow and API usage (<a
href="https://github.com/appleboy"><code>@appleboy</code></a>)</li>
<li>5d65d1094eb0415898554ba83c4f3196778f9a85: ci: improve testing
workflow and API usage (<a
href="https://github.com/appleboy"><code>@appleboy</code></a>)</li>
<li>b31dd8d6e7ba1e80a96a4772d8c4290fe7bac0ce: build: update base image
in Dockerfile (<a
href="https://github.com/appleboy"><code>@appleboy</code></a>)</li>
<li>fc585cfea49d10c08f8009f674c05961a0934647: ci(goreleaser): implement
automated release process with GoReleaser (<a
href="https://github.com/appleboy"><code>@appleboy</code></a>)</li>
<li>b1e5e3d76ccb4afd43bc0859672a6f9113fa0458: ci(test): optimize CI
workflow and test configurations (<a
href="https://github.com/appleboy"><code>@appleboy</code></a>)</li>
</ul>
<h3>Documentation updates</h3>
<ul>
<li>8f1f45876617e5d74085a38164c421be39f099b3: docs(readme): refactor
codebase and improve test coverage (<a
href="https://github.com/appleboy"><code>@appleboy</code></a>)</li>
</ul>
</blockquote>
</details>
<details>
<summary>Commits</summary>
<ul>
<li><a
href="b1e5e3d76c"><code>b1e5e3d</code></a>
ci(test): optimize CI workflow and test configurations</li>
<li><a
href="8f1f458766"><code>8f1f458</code></a>
docs(readme): refactor codebase and improve test coverage</li>
<li><a
href="fc585cfea4"><code>fc585cf</code></a>
ci(goreleaser): implement automated release process with GoReleaser</li>
<li><a
href="50ae8aaf06"><code>50ae8aa</code></a>
chore(docker): improve overall system performance and API
integration</li>
<li><a
href="b31dd8d6e7"><code>b31dd8d</code></a>
build: update base image in Dockerfile</li>
<li><a
href="5d65d1094e"><code>5d65d10</code></a>
ci: improve testing workflow and API usage</li>
<li><a
href="feea2e25ba"><code>feea2e2</code></a>
ci: improve testing workflow and API usage</li>
<li>See full diff in <a
href="https://github.com/appleboy/git-push-action/compare/v0.0.3...v1.0.0">compare
view</a></li>
</ul>
</details>
<br />
[](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores)
Dependabot will resolve any conflicts with this PR as long as you don't
alter it yourself. You can also trigger a rebase manually by commenting
`@dependabot rebase`.
[//]: # (dependabot-automerge-start)
[//]: # (dependabot-automerge-end)
---
<details>
<summary>Dependabot commands and options</summary>
<br />
You can trigger Dependabot actions by commenting on this PR:
- `@dependabot rebase` will rebase this PR
- `@dependabot recreate` will recreate this PR, overwriting any edits
that have been made to it
- `@dependabot merge` will merge this PR after your CI passes on it
- `@dependabot squash and merge` will squash and merge this PR after
your CI passes on it
- `@dependabot cancel merge` will cancel a previously requested merge
and block automerging
- `@dependabot reopen` will reopen this PR if it is closed
- `@dependabot close` will close this PR and stop Dependabot recreating
it. You can achieve the same result by closing it manually
- `@dependabot show <dependency name> ignore conditions` will show all
of the ignore conditions of the specified dependency
- `@dependabot ignore this major version` will close this PR and stop
Dependabot creating any more for this major version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this minor version` will close this PR and stop
Dependabot creating any more for this minor version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this dependency` will close this PR and stop
Dependabot creating any more for this dependency (unless you reopen the
PR or upgrade to it yourself)
</details>
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Unbreak the release pipelines. The issue is caused by
https://gitlab.alpinelinux.org/alpine/aports/-/issues/17775 which
supposedly fixed in 3.23.2 and our build did use that version from what
I see, but maybe it's not fixed yet for `riscv`. We should try this
upgrade again later.
Bumps
[dev-hanz-ops/install-gh-cli-action](https://github.com/dev-hanz-ops/install-gh-cli-action)
from 0.1.0 to 0.2.1.
<details>
<summary>Release notes</summary>
<p><em>Sourced from <a
href="https://github.com/dev-hanz-ops/install-gh-cli-action/releases">dev-hanz-ops/install-gh-cli-action's
releases</a>.</em></p>
<blockquote>
<h2>v0.2.1 - arm64 support</h2>
<ul>
<li>support arm64 architecture - <a
href="https://redirect.github.com/dev-hanz-ops/install-gh-cli-action/pull/10">dev-hanz-ops/install-gh-cli-action#10</a>
(by <a
href="https://github.com/whatthefinemanual"><code>@whatthefinemanual</code></a>)</li>
</ul>
<h2>v0.2.0 - update to node20</h2>
<ul>
<li><a
href="8fff9050da</a>
(update to node20)</li>
</ul>
</blockquote>
</details>
<details>
<summary>Commits</summary>
<ul>
<li><a
href="af38ce09b1"><code>af38ce0</code></a>
run build</li>
<li><a
href="eef2976ced"><code>eef2976</code></a>
feature: Add multi architecture support (<a
href="https://redirect.github.com/dev-hanz-ops/install-gh-cli-action/issues/10">#10</a>)</li>
<li><a
href="2d19dc38f3"><code>2d19dc3</code></a>
docs: update recomended action version (<a
href="https://redirect.github.com/dev-hanz-ops/install-gh-cli-action/issues/8">#8</a>)</li>
<li><a
href="8fff9050da"><code>8fff905</code></a>
update to node 20</li>
<li><a
href="67bfd05393"><code>67bfd05</code></a>
README: only linux amd64</li>
<li><a
href="4474568036"><code>4474568</code></a>
Update readme with working example (<a
href="https://redirect.github.com/dev-hanz-ops/install-gh-cli-action/issues/3">#3</a>)</li>
<li>See full diff in <a
href="https://github.com/dev-hanz-ops/install-gh-cli-action/compare/v0.1.0...v0.2.1">compare
view</a></li>
</ul>
</details>
<br />
[](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores)
Dependabot will resolve any conflicts with this PR as long as you don't
alter it yourself. You can also trigger a rebase manually by commenting
`@dependabot rebase`.
[//]: # (dependabot-automerge-start)
[//]: # (dependabot-automerge-end)
---
<details>
<summary>Dependabot commands and options</summary>
<br />
You can trigger Dependabot actions by commenting on this PR:
- `@dependabot rebase` will rebase this PR
- `@dependabot recreate` will recreate this PR, overwriting any edits
that have been made to it
- `@dependabot merge` will merge this PR after your CI passes on it
- `@dependabot squash and merge` will squash and merge this PR after
your CI passes on it
- `@dependabot cancel merge` will cancel a previously requested merge
and block automerging
- `@dependabot reopen` will reopen this PR if it is closed
- `@dependabot close` will close this PR and stop Dependabot recreating
it. You can achieve the same result by closing it manually
- `@dependabot show <dependency name> ignore conditions` will show all
of the ignore conditions of the specified dependency
- `@dependabot ignore this major version` will close this PR and stop
Dependabot creating any more for this major version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this minor version` will close this PR and stop
Dependabot creating any more for this minor version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this dependency` will close this PR and stop
Dependabot creating any more for this dependency (unless you reopen the
PR or upgrade to it yourself)
</details>
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
The test `TestGiteaUploadUpdateGitForPullRequest` modified the shared
meta test repositories directly, so this PR removes that test and
replaces it with an integration test that migrates a real repository
from gitea.com into a local test instance.
This PR also fixes a bug where pull-request migrations were not
correctly syncing head branches to the database.
- Update all JS deps
- Tested affected `dependencies`
- Replace eslint `unstable_native_nodejs_ts_config` with optional `jiti`
dependency. This will be more compatible with editor integrations that
may not pass this flag.
- Enable additional eslint rules, no new issues
- Move `typescript` to `devDependencies` because `make frontend` works
without it
Similar to GitHub, release notes can now be generated automatically.
The generator is server-side and gathers the merged PRs and contributors
and returns the corresponding Markdown text.
---------
Co-authored-by: wxiaoguang <wxiaoguang@gmail.com>
as you seen, in cureent status `initUserAuthWebAuthn` will prcheck
`window.isSecureContext`, if not ok, will hide the `passkey` btton and
return directly. I think it's not right, first, not show any error
message looks not a good ui, and it's looks will make an empty container
was show if the registion button was disabled also (maybe f-i-x #36115),
then initUserAuthWebAuthn has `window.isSecureContext` check also which
looks duplcate ref:
26602fd207/web_src/js/features/user-auth-webauthn.ts (L202-L206)
so I'd like move hideElem(elSignInPasskeyBtn); to
`detectWebAuthnSupport` failed routs to make it simple and show insecure
error corectly.
Signed-off-by: a1012112796 <1012112796@qq.com>
Co-authored-by: Lunny Xiao <xiaolunwen@gmail.com>
Per-repository signing keys have never been officially supported, as
they would require users to modify the repository’s config file.
At this point, it is clear that only global signing keys (GPG or SSH)
should be allowed. If we want to introduce per-repository signing keys
in the future, it will require a complete design proposal.
The endpoint will not be removed for repository special signing key, but
it will reference the global signing key.
---------
Signed-off-by: Lunny Xiao <xiaolunwen@gmail.com>
Co-authored-by: delvh <dev.lh@web.de>
1. Full file highlighting (fix the legacy todo "we should instead
highlight the whole file at once")
* Fix#24383
2. Correctly covert file content encoding
3. Remove dead code, split large for-loop into small functions/blocks to
make code maintainable
Fixes: https://github.com/go-gitea/gitea/issues/35863
The old code had a conflict between using HTML attributes vs. style
properties where the style was overriding the previously set HTML
attributes:
```html
<img width="300" height="277.02439470988946" style="width: 275px; height: 0px;">
```
I made it so in all cases only `style` properties are used and the
previous width/height values are now set via `style`. Also I did a
number of much-needed typescript improvements to the file.
---------
Co-authored-by: wxiaoguang <wxiaoguang@gmail.com>
1 Move `IsRepositoryModelOrDirExist` and `CheckCreateRepository` to
service layer
2 Use `gitrepo.Pushxxx` instead of `git.Push` when possible
3 use `gitrepo.Clonexxx` instead of `gitrepo.Clone` when possible
1. Our textarea already has some editor-like feature like tab
indentation, so I thought why not also add insertion of matching closing
quotes/brackets over selected text. This does that.
2. `textareaInsertText` is replaced with `replaceTextareaSelection`
which does the same but create a new edit history entry in the textarea
so CTRL-Z works. The button that inserts tables into the textarea can
now also be reverted via CTRL-Z, which was not possible before.
When migrating issues or pull requests from a big repository, some
issue/pull request maybe deleted when migrating. So that there will be
duplicated issues/pull requests because we are get information with
pagination. This PR introduced a map to record all migrated issue pull
request index when migrating to avoid the failure because of duplicated
records.
Resolves#35994
Do not render code expansion arrows when `DiffBlobExcerptData` is not
available (code file preview, pull conversation diff comment).
---------
Signed-off-by: wxiaoguang <wxiaoguang@gmail.com>
Co-authored-by: wxiaoguang <wxiaoguang@gmail.com>
fix#36071
looks that's because if an svg in hiden env, it's color added by
`fill="url(#a)"` will become not usefull. by ai helping, I think moving
it out of page by position is a good solution. fell free creat a new
pull request if you have a better soluton. Thanks.
<img width="2198" height="1120" alt="image"
src="https://github.com/user-attachments/assets/bbf7c171-0b7f-412a-a1bc-aea3f1629636"
/>
---------
Signed-off-by: a1012112796 <1012112796@qq.com>
Co-authored-by: wxiaoguang <wxiaoguang@gmail.com>
- Update and autofix most issues
- Corrected variable names to `cutOk`
- Impossible condition in `services/migrations/onedev_test.go` removed
- `modules/setting/config_env.go:128:3` looks like a false-positive,
added nolint
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>
A big step towards enabling strict mode in Typescript.
There was definitely a good share of potential bugs while refactoring
this. When in doubt, I opted to keep the potentially broken behaviour.
Notably, the `DOMEvent` type is gone, it was broken and we're better of
with type assertions on `e.target`.
---------
Signed-off-by: silverwind <me@silverwind.io>
Signed-off-by: wxiaoguang <wxiaoguang@gmail.com>
Co-authored-by: delvh <dev.lh@web.de>
Co-authored-by: wxiaoguang <wxiaoguang@gmail.com>
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.
/claim #35898Resolves#35898
### Summary of key changes:
1. Add file name search/Go to file functionality to repo button row.
2. Add backend functionality to delete directory
3. Add context menu for directories with functionality to copy path & delete a directory
4. Move Add/Upload file dropdown to right for parity with Github UI
5. Add tree view to the edit/upload UI
---------
Co-authored-by: wxiaoguang <wxiaoguang@gmail.com>
Many (but not all) analyzers ran by `gopls check` are available in
`golangci-lint` as part of default-disabled `govet` linters, so I think
it's best we remove this manual linting step and let `golangci-lint`
handle it. I hand-picked two available linters that were previously
linted using gopls and this list is not exhaustive.
This will reduce CI time by about 3 minutes.
Partially fix#34710
The bug described in #34710 can be divided into two parts: `push.paths`
and `pull_request.paths`. This PR fixes the issue related to
`pull_request.paths`. The root cause is that the check for whether the
workflow can be triggered happens **before** updating the PR’s merge
base. This causes the file-change detection to use the old merge base.
Therefore, we need to update the merge base first and then check whether
the workflow can be triggered.
- Updated error message in `incoming.go` to remove unnecessary wrapping
of the error.
- Corrected typo in error message in `wiki.go` for clarity.
---------
Co-authored-by: Giteabot <teabot@gitea.io>
- Update JS deps
- Regenerate SVGs
- Fix air `bin` deprecation
- Fix `monaco.languages.typescript` deprecation
- Remove `eslint-plugin-no-use-extend-native`, it's unnecessary with
typescript
- Enable new `@typescript-eslint` rules
- Disable `@typescript-eslint/no-redundant-type-constituents`, this rule
has bugs when not running under `strictNullChecks` (pending in
https://github.com/go-gitea/gitea/pull/35843).
Presently, attempting to rename a non-local (e.g. Oauth2 or LDAP) user
results in an error, even if the requester is an administrator. As far
as I can tell, this is a security feature, not architectural in nature,
as automatic account linking could be used to take control of another
user's account. This is not a concern for an administrator, who we
should trust to know what they are doing.
This patch allows admins, and only admins, to rename non-local users.
Fixes https://github.com/go-gitea/gitea/issues/18308 (sort of)
---------
Co-authored-by: wxiaoguang <wxiaoguang@gmail.com>
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>
This patch amends https://github.com/go-gitea/gitea/pull/27507.
Since https://github.com/go-gitea/gitea/pull/35072, `selectable` css
class can be used for providing hover effect for tables. This patch let
the wiki page be able to make use of that css class, and we can safely
remove the custom css for this purpose.
Behavior is not changed.
----
Side note: I made this patch locally months ago but completely forget to
submit it as a PR 😂
Consistently use a `star` icon to highlight the default column of a
project.
The icon is both shown while viewing the project, as well as while
changing the default status of this column.
<img width="1065" height="370" alt="image"
src="https://github.com/user-attachments/assets/1ca5773d-8eec-4b90-ad0b-22b1f4bd4cfd"
/>
`GITEA_PR_ID` is already part of the env variables available in the
githooks, but it contains a database ID instead of commonly used index
that is part of `owner/repo!index`
This would allow developers to keep a local file that'd add personal
makefile targets for niche convenience customization without having to
have the git workspace polluted with uncommitted changes.
---------
Signed-off-by: techknowlogick <techknowlogick@gitea.com>
From [docs](https://go.dev/doc/toolchain#config):
> The go line declares the minimum required Go version for using the
module or workspace. For compatibility reasons, if the go line is
omitted from a go.mod file, the module is considered to have an implicit
go 1.16 line, and if the go line is omitted from a go.work file, the
workspace is considered to have an implicit go 1.18 line.
> The toolchain line declares a suggested toolchain to use with the
module or workspace. As described in “[Go toolchain
selection](https://go.dev/doc/toolchain#select)” below, the go command
may run this specific toolchain when operating in that module or
workspace if the default toolchain’s version is less than the suggested
toolchain’s version. If the toolchain line is omitted, the module or
workspace is considered to have an implicit toolchain goV line, where V
is the Go version from the go line.
This is better than setting `go` to the latest version which may break
builds when that go version is unavailable, for example with
`GOTOOLCHAIN=local` in the official go docker images.
Fix#35852, the root problem is that the "name" field is heavily abused
(since #6816, and no way to get a clear fix)
There are still a lot of legacy problems in old code.
Co-authored-by: Giteabot <teabot@gitea.io>
Current template uses the owner followed by the instance URL as the repo
name. Technically this can work if the repo happens to be named the
exact same way. But if, for example, you follow [the
docs](https://docs.gitea.com/usage/packages/arch/#publish-a-package),
you'll end up with a package in `core` while the pacman conf refers to a
non-existent repo `testuser.gitea.example.com`. Whatever is in the
square brackets get substituted in for `$repo`, so we do not want
anything except the exact repo name there.
And since it's now referring to the repo and not the owner, I've updated
the pacman conf to show all repositories.
---------
Co-authored-by: Giteabot <teabot@gitea.io>
`flake-utils` is currently only used for outputting system-specific dev
shells. This can actually be achieved only using functionality already
present within `nixpkgs`, thus there is no need for an extra dependency.
Additionally, we move to use the `packages` and `env` args for `mkShell`
to more clearly outline what they are used for.
---
Further reading:
https://determinate.systems/blog/best-practices-for-nix-at-work/#avoid-flake-helper-libraries-if-possible
As a side note, using `with` to import large scopes is [discouraged by
official Nix
resources](https://nix.dev/guides/best-practices#with-scopes), so an
alternative approach to list installed packages could be something like
this:
```nix
packages =
(builtins.attrValues {
inherit (pkgs)
# generic
git
git-lfs
gnumake
gnused
gnutar
gzip
zip
# frontend
cairo
pixman
pkg-config
# linting
uv
# backend
gofumpt
sqlite
;
inherit
# frontend
nodejs
pnpm
# linting
python3
# backend
go
;
})
++ linuxOnlyInputs;
```
But I saw this as too pedantic to include in the initial PR.
Co-authored-by: 6543 <6543@obermui.de>
https://github.com/golangci/golangci-lint/releases/tag/v2.6.0
- `modernize` linter is enabled, this is the same as `gopls modernize`
- ~~`perfsprint` linter is disabled because it conflicts with
`modernize` (maybe there is a middle ground)~~
- gocritic `deprecatedComment` is disabled as it conflicts with
`go-swagger`
#35783 fixes an actions rerun bug. Due to this bug, some runs may be
incorrectly marked as `StatusWaiting` even though all the jobs are in
done status. These runs cannot be run or cancelled. This PR adds a new
doctor command to fix the inconsistent run status.
```
gitea doctor check --run fix-actions-unfinished-run-status --fix
```
Thanks to @ChristopherHX for the test.
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.
In preparation to work on enabling
https://www.typescriptlang.org/tsconfig/#strictNullChecks, I fixed all
the issues outside of `web_src` that came up when the option was
enabled. There was also one lint issue in web_src that apparently only
came up with the option enabled, so I fixed that as well.
`isTruthy` is introduced because Typescript has a bug regarding
`filter(Boolean)` which they are seemingly unwilling to fix.
---------
Signed-off-by: silverwind <me@silverwind.io>
following the approach from nixpkgs that ignore the .worktrees folder,
we could also do the same, this would allow worktrees to be worked on in
the same folder as the primary branch.
ref:
b6420c7bca
add mount cache directives to container builds, which speeds up local
builds bypassing node and go package download entirely on second build
and caching go compilation.
drop job level split on regular/rootless, which allows to reuse the
previously made stage for rootless, skipping duplicate builds in CI.
---------
Co-authored-by: Lunny Xiao <xiaolunwen@gmail.com>
During https://github.com/go-gitea/gitea/issues/35790, it was noticed
that this PNG image had the wrong file extension. I also verified
`dingtalk.ico` and that one is actually an `.ico`.
1. Add the color on the link to the referenced file, which is the more
likely thing the user wants to click
2. Use monospace font on the SHA
3. Tweak text colors
4. Change SHA link to go to the commit instead of the repo root with
commit filter set
5. Added the repo name to the file link text
6. Fix broken line numbering rendering
- Update all JS dependencies
- Added new unicorn rules
- `updates` now also supports updating `packageManager` and `engines`,
and I see no reason not to do that, so I think we can try keeping these
updated as well. If something in the build breaks because of this, I
will revert and exclude `pnpm` from updating further, but as far as I
understand, only corepack respects this field and pnpm itself does not
care about it.
- Regenerate SVGs.
Followup to https://github.com/go-gitea/gitea/pull/35734.
- Move `codeformat` folder to `tools`
- Add `tools` to `GO_DIRS`
- Move `misspellings.csv` to `assets` so we can lint the whole `tools`
directory without filter shenanigans.
---------
Co-authored-by: wxiaoguang <wxiaoguang@gmail.com>
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 moves "no online runner" warning to the runs list.
A job's `runs-on` may contain expressions like `runs-on: [self-hosted,
"${{ inputs.chosen-os }}"]` so the value of `runs-on` may be different
in each run. We cannot check it through the workflow file.
<details>
<summary>Screenshots</summary>
Before:
<img width="960" alt="3d2a91746271d8b1f12c8f7d20eba550"
src="https://github.com/user-attachments/assets/7a972c50-db97-49d2-b12b-c1a439732a11"
/>
After:
<img width="960" alt="image"
src="https://github.com/user-attachments/assets/fc076e0e-bd08-4afe-99b9-c0eb0fd2c7e7"
/>
</details>
This PR also splits `prepareWorkflowDispatchTemplate` function into 2
functions:
- `prepareWorkflowTemplate` get and check all of the workflows
- `prepareWorkflowDispatchTemplate` only prepare workflow dispatch
config for `workflow_dispatch` workflows.
---------
Co-authored-by: wxiaoguang <wxiaoguang@gmail.com>
Some minor tooling tweaks:
- Ignore .venv in golangci-lint
- Move go tools to tools directory (e.g. everything that is not "build")
- Enable reportUnusedInlineConfigs in eslint, no current violations
- Apply modernize fix in code-batch-process, modernize cli did
apparently not catch it because of the `go:build ignore` tag.
* use a single function to do Action Tokens Permission checks
* allows easier customization
* add basic tests
* lfs file locks should work now
---------
Signed-off-by: ChristopherHX <christopher.homberger@web.de>
Co-authored-by: wxiaoguang <wxiaoguang@gmail.com>
Fix#35690
Change the "restricted user" behavior introduced by #6274. Now
restricted user can also access public repositories when sign-in is not
required.
For required sign-in, the behavior isn't changed.
This PR adds a quick approve button on PR page to allow reviewers to
approve all pending checks. Only users with write permission to the
Actions unit can approve.
---------
Signed-off-by: Zettat123 <zettat123@gmail.com>
Co-authored-by: wxiaoguang <wxiaoguang@gmail.com>
Fixes#32257
/claim #32257
Implemented commenting on unchanged lines in Pull Request diffs, lines
are accessed by expanding the diff preview. Comments also appear in the
"Files Changed" tab on the unchanged lines where they were placed.
---------
Co-authored-by: wxiaoguang <wxiaoguang@gmail.com>
1. Fix incorrect column in `applySubscribedCondition`, add a test
2. Fix debian version parsing, add more tests fix#35695
3. Fix log level for HTTP errors, fix#35651
4. Fix abused "panic" handler in API `Migrate`
5. Fix the redirection from PR to issue, add a test
6. Fix Actions variable & secret name validation, add more tests
* envNameCIRegexMatch is unnecessary, removed
* validating in "delete" function doesn't make sense, removed
7. Fix incorrect link in release email
---------
Signed-off-by: wxiaoguang <wxiaoguang@gmail.com>
Co-authored-by: delvh <dev.lh@web.de>
Fix#35649
* Use upstream `git-lfs-transfer`
* The Close should be called when error occurs (bug fix)
* The connection pool should be shared (bug fix)
* Add more tests to cover "LFS over SSH download"
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>
- Update all JS dependencies
- Enable eslint `no-useless-assignment` and fix 2 discovered issues
- Replace `gitea-vscode` svg with new `octicon-vscode`
- Remove now-unused `@ts-expect-error` comments
- Change Monaco wrapping behaviour to match the wrapping in code view:
no wrapping indent and break on any character.
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
Use a helper method around the jobparser for parsing a single job
structure from an ActionRunJob
---------
Co-authored-by: wxiaoguang <wxiaoguang@gmail.com>
The test calls out to a web service which may be down or unreachable as
seen in the linked issue. It's better for tests to not have such
external dependencies to make them absolutely stable.
Fixes: https://github.com/go-gitea/gitea/issues/35571
Fix the swagger documentation for the `diffpatch` API endpoint,
and fix the wrong API path caused by a refactoring change.
Closes#35602
---------
Co-authored-by: wxiaoguang <wxiaoguang@gmail.com>
The Gitea codebase was logging `Elasticsearch` and `Meilisearch`
connection strings directly to log files without sanitizing them. Since
connection strings often contain credentials in the format
`protocol://username:password@host:port`, this resulted in passwords
being exposed in plain text in log output.
Fix:
- wrapped all instances of setting.Indexer.RepoConnStr and
setting.Indexer.IssueConnStr with the `util.SanitizeCredentialURLs()`
function before logging them.
Fixes: #35530
Co-authored-by: Lunny Xiao <xiaolunwen@gmail.com>
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>
Allows users to specify a "force" option in API /contents routes when
modifying files in a new branch. When "force" is true, and the branch
already exists, a force push will occur provided the branch does not
have a branch protection rule that disables force pushing.
This is useful as a way to manage a branch remotely through only the
API. For example in an automated release tool you can pull commits,
analyze, and update a release PR branch all remotely without needing to
clone or perform any local git operations.
Resolve#35538
---------
Co-authored-by: Rob Gonnella <rob.gonnella@papayapay.com>
Co-authored-by: wxiaoguang <wxiaoguang@gmail.com>
Implements reliable auto-expand and auto-scroll behavior for the Actions
logs view.
* Expands running or unfinished steps automatically.
* Smoothly scrolls to the latest log line during execution.
* Controlled via existing “Always auto-scroll” and “Expand running
steps” options.
Fixes#35570.
---------
Co-authored-by: wxiaoguang <wxiaoguang@gmail.com>
To reduce the risk of npm supply chain attacks and to speed up
dependency installation, I've
[bundled](https://github.com/silverwind/spectral-cli-bundle) the
spectral package into a zero-dependency module. The upstream package is
pretty dead currently, so I expect to keep up with their updates.
The package
[exports](de05948c53/package.json (L9))
a `spectral` bin script, so `pnpm exec spectral` continues to work
as-is.
In total, this removes 86 dependencies from the npm dependency tree.
Tag creation/deletion was triggering push webhooks even when branch
filters were configured, causing unintended pipeline executions.
This change modifies the branch filter logic to check the full ref
name directly instead of first determining if it's a "branch" event.
Fixes: Tag events now properly respect branch filters
- Add getPayloadRef() function to extract full ref names
- Update PrepareWebhook() to use direct ref matching
- Prevents refs/tags/* from matching refs/heads/* filters
Closes#35449
---------
Co-authored-by: wxiaoguang <wxiaoguang@gmail.com>
Co-authored-by: silverwind <me@silverwind.io>
The merge request file viewer has a button for copying the file path,
but it is not always convenient. Often, you only want to copy the file
name, which is currently not possible. This change request adds this
capability.
---------
Signed-off-by: wxiaoguang <wxiaoguang@gmail.com>
Co-authored-by: a.kiselev <a.kiselev@reglab.ru>
Co-authored-by: wxiaoguang <wxiaoguang@gmail.com>
This pull request updates the handling of issue label events in
workflows to distinguish between label additions and deletions,
introduces corresponding test cases, and extends the `IssuePayload`
structure to support this functionality.
### Enhancements to issue label event handling:
* Updated `matchIssuesEvent` in `modules/actions/workflows.go` to
differentiate between "labeled" and "unlabeled" events based on whether
labels were added or removed.
* Added a new field, `RemovedLabels`, to the `IssuePayload` struct in
`modules/structs/hook.go` to track labels that were removed during an
issue event.
### Testing improvements:
* Added `TestMatchIssuesEvent` in `modules/actions/workflows_test.go` to
cover scenarios such as label addition, label deletion, and label
clearing, ensuring the correct event type is triggered.
---------
Co-authored-by: Lunny Xiao <xiaolunwen@gmail.com>
Commit 6a97ab0af4 reworked team permission
application. The introduced logic overrode the unitModes for *every*
team a user is in, max(...) the current value and the team value
together.
The logic completely fails in case the team does not have a unit for the
specific unit type defined, in which case the logic inserted the
minimumVisibility, overriding any previous aggregation of access modes
for the unit.
This is resolved by simply always merging the unit access mode of the
team as it will simply default to None in case the team does not have a
permission defined for the unit, which will be swallowed by the max(..)
call in favour of the previous aggregated permission.
Enable the [same paste
features](https://github.com/github/paste-markdown#paste-markdown-objects)
that GitHub has, notably the ability to paste text containing HTML links
and have them automatically turn into Markdown links. As far as I can
tell, previous paste features all work as expected.
---------
Signed-off-by: silverwind <me@silverwind.io>
Time Estimate field is not included in the issue modification webhooks
or issue API endpoints.
This PR fixes the field for the API.
---------
Signed-off-by: Gnanakeethan Balasubramaniam <gnanakeethan@users.noreply.github.com>
Signed-off-by: Gnanakeethan Balasubramaniam <gnanakeethan@cloudparallax.com>
- `type-fest` is replaced by our own types
- `@stylistic/eslint-plugin-js` is no longer in use, it was replaced
with `@stylistic/eslint-plugin`
- `@types/license-checker-webpack-plugin` does not apply to our forked
version and has a type stub
Update eslint and all plugins. Many plugins still do not ship type
definitions so I had to add stubs. Also, I had to put a few typescript
error expectations because if some unknown error in the types.
`eslint-plugin-no-jquery` is disabled because it's not compatible with
eslint 9 flat config
(https://github.com/wikimedia/eslint-plugin-no-jquery/issues/311).
Given that this bundler is almost a drop-in replacement to webpack, it
might be worth switching. So far it seems everything is working, but
more testing is needed, so I'm setting draft.
- Dev build time is reduced from 10s to 5s
- Prod build time is reduced from 16s to 10s
- JS output size is reduced from 21.3MB to 19.8MB
- CSS output size is increased from 778kB to 818kB
When running `gitea dump`, don't store the contents of
`data/repo-archive` in the output.
These archives can easily be regenerated from the repository data, and
does not need to be backed up.
Fixes#35450
---
<s>Added a `--skip-repo-archive` flag to the `gitea dump` command.
Enabling this flag will exclude the contents of `data/repo-archive` from
the dump. The implementation is similar to the other `--skip-*` flags
that excludes directories from `data`.</s>
Signed-off-by: h7x4 <h7x4@nani.wtf>
Co-authored-by: Lunny Xiao <xiaolunwen@gmail.com>
See https://github.com/actions/setup-node/releases/tag/v5.0.0
Caching is now enabled by default when `packageManager` is present in
package.json, and we have that. `cache-dependency-path` is unneccesary
because the action will automatically detect it.
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>
fixes#30565
When using git with a gitea hosted repository, the HTTP-Transport did
honor the user and repository redirects, which are created when renaming
a user or repo and also when transferring ownership of a repo to a
different organization. This is extremely helpful, as repo URLs remain
stable and do not have to be migrated on each client's worktree and
other places, e.g. CI at once.
The SSH transport - which I favor - did not know of these redirections
and I implemented a lookup during the `serv` command.
gofumpt now
[supports](https://github.com/mvdan/gofumpt/releases/tag/v0.9.0) the
[ignore](https://tip.golang.org/ref/mod#go-mod-file-ignore) directive
added in go 1.25, make use of it which speeds up `make fmt` by around
30%. Likely this also has similar speed gains in other go-related
commands which use the `./...` pattern.
The change in `build/code-batch-process.go` was introduced by `gofumpt`
because of this change:
> A new rule is introduced to "clothe" naked returns for the sake of
clarity. While there is nothing wrong with naming results in function
signatures, using lone return statements can be confusing to the reader.
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.
Migrate all JS config and tools to TS and fix a number of type issues.
This required Node.js 22.18.0 or greater where [type-stripping was
enabled](https://nodejs.org/en/blog/release/v22.18.0) by default.
Given that Node 22 is the current LTS, I think it's ok to assume that
the user has a recent version of it.
Webpack currently requires the `--disable-interpret` flag to work,
should be fixed eventually with
https://github.com/webpack/webpack-cli/issues/4525.
`fast-glob` is replaced by `fs.globSync`, available in Node 22.0.0 or
greater.
Use the WASM module of [`resvg-js`](https://github.com/thx/resvg-js) to
replace `fabric` and the problematic native `canvas` dependency. WASM
works cross-platform so we can include it in the main `package.json`.
- Moved mail templates to new directories.
- Added new devtest ymls.
- Embedded styles as much as possible.
- Added new translation keys for actions email.
---------
Signed-off-by: NorthRealm <155140859+NorthRealm@users.noreply.github.com>
Co-authored-by: delvh <dev.lh@web.de>
Default behaviour rejected all rows (Records) with more or fewer columns
(Fields) than the first row, preventing them from parsing at all and
silently hiding them. While RFC4180 section 2.4 says each line _should_
contain the same number of fields, enforcing this on the viewer is
unhelpful.
This pull request disables that validation, allowing the viewer to
render lines with fewer columns than the maximum number within the file.
As it's a simple HTML table, this works without additional changes (i.e.
no need to manually determine the maximum number of columns), but the
default appearance of rows with fewer columns may be undesirable to some
people, especially when using CSS that has `td {border-right: none}`.
<img width="1408" height="156" alt="Screenshot without cell right
borders"
src="https://github.com/user-attachments/assets/d4c19bbc-3fd2-4fd1-83a6-1125e953e95b"
/>
<img width="1397" height="158" alt="Screenshot with cell right borders"
src="https://github.com/user-attachments/assets/86aaafcb-d7e8-4228-99a8-7527c823a07c"
/>
Fixes#16559, #30358.
Unfortunately, retaining empty lines is less trivial, so the line
numbers on the leftmost column will still not match the source file
whenever those are present, though a future PR could address that.
imagemin-zopfli brings a lot of [vulnerable
dependencies](https://github.com/go-gitea/gitea/security/dependabot) and
it is unmaintained. The removal brings a size increase to these images,
but I think ultimately this size does not matter enough. I verified this
passes `pnpm audit` now.
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.
- ~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>
When sorting issues and pull requests by the nearest due date, the
issues and PRs without a due date are currently sorted _descending_ by
their creation date. This seems counter intuitive to me. When sorting by
nearest due date I want to see the issues/PRs in the order they should
be worked on. For issues/PRs without a due date that order should be
first come first served rather than last come first served.
This PR now changes the ordering of issues/PRs which don't have a due
date to _ascending_ by their creation date. So that the oldest is shown
first and the newest last.
This now also makes the sort order nearest due date a true opposite to
farthest due date. At farthest due date the newest is shown first and
the oldest last.
Co-authored-by: 6543 <6543@obermui.de>
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>
Fixes#35221, let the scanner's buffer grow up to 4x (256 kiB), and add an error check
---------
Signed-off-by: Fabian Meyer <fabian.meyer@lawo.com>
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>
Instance signing rule `pubkey` is described as "Only sign if the user
has a public key", however if the user only has SSH public keys, this
check will fail, as it only checks for GPG keys.
Changed the `pubkey` checks to call a helper `userHasPubkeys` which
sequentially checks for GPG, then SSH keys.
Related #34341
---------
Co-authored-by: wxiaoguang <wxiaoguang@gmail.com>
Entra ID users should use the OIDC oauth2 provider.
They will still be shown if the instance has a previous Azure AD source
configured.
---------
Co-authored-by: Lunny Xiao <xiaolunwen@gmail.com>
Exit `upgrade.sh` with status 0 (instead of status 1) when the installed
Gitea is already on the latest version and nothing needs to be done.
Fixes#35309
Addresses go version mismatch when using the devcontainer as a result of
[this
commit](793815adf7)
(bumps Go version from 1.24.5 to 1.24.6)
The current official devcontainer Go image used in this repository
(`1.24-bookworm`) uses 1.24.5 and sets GOTOOLCHAIN to local. This PR
overrides it to auto so that build commands automatically update to the
correct version.
---------
Signed-off-by: Jackson Stewart <jaxtew@pm.me>
Co-authored-by: techknowlogick <techknowlogick@gitea.com>
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.
OneDev migration: fix broken migration caused by various REST API
changes in OneDev 7.8.0 and later
- in REST urls use `~api` instead of `api`
- check minimum required OneDev version before starting migration
- required OneDev version is now 12.0.1
(older versions do not offer necessary API:
https://code.onedev.io/onedev/server/~issues/2491)
- support migrating OneDev subprojects (e.g.
http:/onedev.host/projectA/subProjectB)
- set milestone closed state if milestone is closed in OneDev
- moved memory allocation for milestone JSON decoding into for loop
(which gets 100 milestones per iteration) to fix wrong due dates when
having more than 100 milestones
Previously, when writing a inline code comment, the markup preview would
have incorrect font size of 16px. This fixes it to 14px and also
combines similar CSS rules into one.
I'm not a fan of this selector complexity, but it seems like a necessity
because standalone markup files render at 16px while comments render at
14px.
---------
Signed-off-by: silverwind <me@silverwind.io>
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.
similar to how we can enable/disable repos or issues on a repo add the
code unit as option to it.
affects
```
PATCH /repos/{owner}/{repo}
```
---
*Sponsored by Kithara Software GmbH*
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
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
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: wxiaoguang <wxiaoguang@gmail.com>
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
Issue: https://github.com/go-gitea/gitea/issues/9637
Changes introduced: I have clarified the problematic terms (owner and
parent) in all affected endpoints.
The changes were made to relevant:
- HTTP endpoint parameters' descriptions
- response/request models' fields
This MR is big, but most changes are the same. If you'd like me to break
this MR into several smaller ones, let me know :)
---------
Co-authored-by: wxiaoguang <wxiaoguang@gmail.com>
#35015
For easier review, the changes are split into separate commits by broad
category. The extended commit messages include brief summaries. I am
happy to make a separate pull request for each category if preferred.
While many of the changes are corrections, some are influenced by style.
In those cases I have aimed mainly for consistency throughout the file,
picking a style variant that I think is widely accepted and aids
clarity.
There are additional things that could be improved that I have not
touched. For example, contractions (phrasing variants such as "doesn't"
vs. "does not") could be made more consistent. Not sure how colloquial
or formal the maintainers would like the UI to be.
---------
Signed-off-by: Dominik Rubo <dr-1@posteo.net>
Co-authored-by: Dominik Rubo <dominik.rubo@posteo.net>
Co-authored-by: delvh <dev.lh@web.de>
Follow up #35096, fix#35095, fix#35115 and add more tests
The old code used some fragile behaviors which depend on the "nil"
receiver. This PR should be a complete fix for more edge cases.
Similar to how we have ignores for other tooling (eg vscode & IntelliJ)
we shouldn’t include these files in our repo. If they get added then
we’d have to maintain them and keep them up to date, and personally
there are too many tools to do that for.
"form" has an edge case: its `<input name=action>` element overwrites
the `action` property, we can only set attribute.
This PR makes `assignElementProperty` can handle such case, and add more
tests
This commit adds the "You recently pushed to branch X" alert also to PR
overview, as opposed to only the repository's home page.
GitHub also shows this alert on the PR list, as well as the home page.
---------
Co-authored-by: wxiaoguang <wxiaoguang@gmail.com>
Co-authored-by: Giteabot <teabot@gitea.io>
1. Enable
[`@typescript-eslint/no-unnecessary-type-conversion`](https://typescript-eslint.io/rules/no-unnecessary-type-conversion/),
I think the two cases that were hit are safe cases.
2. Disable `no-new-func`, `@typescript-eslint/no-implied-eval` does the
same but better.
Change the OpenAPI response of `ListWorkflowRuns` to `WorkflowRunsList`
like it is supposed to be.
---------
Signed-off-by: wxiaoguang <wxiaoguang@gmail.com>
Co-authored-by: wxiaoguang <wxiaoguang@gmail.com>
This PR prevents full reloads for the notifications list when changing a
notifications status (read, unread, pinned).
---------
Co-authored-by: Anton Bracke <anton.bracke@fastleansmart.com>
Co-authored-by: wxiaoguang <wxiaoguang@gmail.com>
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.
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.
Although we decided to "reduce the button amount" on the side bar, not
only one user reported that the "time tracker dropdown" is not easy to
use.
So the best we can do at the moment is: move the buttons to the sidebar
again.
Fix#34979
Fixes#21291, allowing icons and other missing attributes to appear for
NuGet packages from inside Visual Studio like they do with GitHub Nuget
packages.
Adds additional NuGet package information, particularly `IconURL`, to
bring the Gitea NuGet API more in-line with GitHub's NuGet API.
ref: https://learn.microsoft.com/en-us/nuget/api/search-query-service-resource
Fixed minor typos in CODE_OF_CONDUCT.md and README.md
I use the hashtag for a project at my university
---------
Signed-off-by: MrMars98 <Marcel.Lang98@googlemail.com>
1. Make "Issuer" strictly follow the spec (see comment)
2. Make "/.well-known/openid-configuration" respond 404 if the OAuth2
provider is not enabled.
Then by the way, remove the JSEscape template helper because it is not
needed any more.
* there is no bug of the "unique element id", but duplicate code, this
PR just merges the duplicate "element id" logic and move the function
from "fomaintic" to "dom"
* improve comments
* make "git commit graph" page update pagination links correctly
1. make our "route group pattern match" also update chi's RoutePattern
2. fix incorrect "NotFound" call in conda package
3. make ".flex-item .flex-item-main" has a general gap, then no need to
use `tw` tricks
4. improve the "test webhook" UI
Adds a tooltip to the commit counts when comparing branches, making it
easier for novice users to understand what the numbers mean.
Fixes#34867.
---------
Signed-off-by: wxiaoguang <wxiaoguang@gmail.com>
Co-authored-by: wxiaoguang <wxiaoguang@gmail.com>
See the comment. And due to the abuse, there is a regression: when the
modal is hidden, the form will be reset and it can't submit.
This PR fixes all problems: keep the modal with form open, and add
"loading" indicator.
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>
Issue: [link](https://github.com/go-gitea/gitea/issues/9637)
Changes introduced: I have clarified the problematic terms (`login`,
`login_name`, and `username`) in all affected endpoints.
The changes were made to relevant:
- HTTP endpoint parameters' descriptions
- response/request models' fields
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>
This variable is unused, occurs nowhere in the codebase. I can't
pinpoint the exact commit when it was last used, but I think it's unused
since the docs were moved out.
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>
This PR improves some `.vue` components by using `shallowRef instead of
ref`, which `should improve performance`. It's probably not significant,
but it's an improvement because Vue no longer deep watches the ref
(shallowRef). Also i used `useTemplateRef` instead of `ref`.
---------
Signed-off-by: wxiaoguang <wxiaoguang@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>
This PR adds a feature to direct users to appropriate pages after system
installation:
- If no admin credentials were provided during installation, redirect to
the registration page with a prominent notice about creating the first
administrative account
- If admin credentials were already set, redirect directly to the login
page
---------
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.
Converts the repo file tree items into `<a>` elements to have default
link behavior. Dynamic content load is still done when no special key is
pressed while clicking on an item.
---------
Co-authored-by: wxiaoguang <wxiaoguang@gmail.com>
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`
This adds a new field, "tag_message", that represents the message of the
annotated tag.
Resolves#31835.
---------
Co-authored-by: wxiaoguang <wxiaoguang@gmail.com>
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>
Currently, Gitea supports title and body query parameters when creating
new issues, allowing pre-filling those fields via URL parameters.
However, similar support for pull requests (PRs) does not exist.
This feature adds support for the title, body, and quick_pull query
parameters in the new pull request creation page. These parameters work
similarly to GitHub’s behavior, allowing users to pre-populate the PR
title and body, and optionally expand the PR creation form
automatically.
By supporting these query parameters, it improves the usability and
automation capabilities when creating pull requests via direct URLs,
aligning Gitea more closely with GitHub’s user experience.
---------
Co-authored-by: root <root@DESKTOP-UPANUTP>
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`.
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: wxiaoguang <wxiaoguang@gmail.com>
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.
Benefits:
1. smaller binary size (reduces more than 1MB)
2. better control of the assets details
3. fewer unmaintained dependencies
4. faster startup if the assets are not needed
5. won't hang up editors when open "bindata.go" by accident
* 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>
## Summary
Fix skipping of `paths` condition in workflows triggered by tag push
events.
## Details
- Ensure workflows triggered by tag pushes bypass the `paths` filter
check.
- Prevent incorrect skipping of workflows due to `paths` conditions on
tag pushes.
- Added and updated unit tests to verify correct behavior.
Close#34511Close#34590
Add comment ID to the footnote item's id attribute to ensure uniqueness.
---------
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.
The notification count is currently positioned using top/left
coordinates from its container's top/left corner. This works fine for
fixed-size containers like the bell icon.
This PR changes the positioning to use bottom/left coordinates from the
container's top/right corner instead. This improvement is needed when
placing notification counts on text that can vary in size due to
different languages or fonts.
The bell and stopwatch should look the same after this change.
---
*Sponsored by Kithara Software GmbH*
Co-authored-by: Marcel Haß <m.hass@kithara.com>
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
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.
Previously, pressing the down arrow key on the last item of a list would
incorrectly load the latest page when not release key. This commit
corrects the logic to ensure that the next page is loaded as intended.
`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>
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: wxiaoguang <wxiaoguang@gmail.com>
Fix the issue where the line-button fails to work after selecting a file
from the file tree.
---------
Co-authored-by: wxiaoguang <wxiaoguang@gmail.com>
This PR adds "View workflow file" to Actions list page, and replaces the
redundant link.
Related #34530
---------
Co-authored-by: wxiaoguang <wxiaoguang@gmail.com>
This PR changes the `opts` argument in `SearchUsers()` 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>
- Change CreateVariable API response status from 204 No Content to 201
Created
- Update related integration tests to expect 201 Created instead of 204
No Content
## ⚠️ BREAKING ⚠️
Change the response status code of the Create Variable API under both
Org and Repo levels to `201` instead of 204.
API SDK: https://gitea.com/gitea/go-sdk/pulls/713
---------
Signed-off-by: Bo-Yi Wu <appleboy.tw@gmail.com>
Signed-off-by: appleboy <appleboy.tw@gmail.com>
Co-authored-by: delvh <dev.lh@web.de>
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
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.
* repository deletion, delete ephemeral runners with active tasks as
well skips regular cleanup
* user deletion, delete ephemeral runners with active tasks as well
skips regular cleanup
* delete ephemeral runners once status changes to done
* You no longer see used ephemeral runners after the task is done
* if you see one the cron job takes care of it
- Add support for filtering commits by date range via new "since" and
"until" parameters
- Update API endpoints and command logic to handle the new parameters
for fetching commits within given dates
- Extend API documentation and Swagger specs to describe the new "since"
and "until" query parameters
- Refactor related function signatures and implementations to accept and
pass "since" and "until" values
---------
Signed-off-by: appleboy <appleboy.tw@gmail.com>
Signed-off-by: Bo-Yi Wu <appleboy.tw@gmail.com>
This PR changes 3rd party notifications wording on a PR review that
requests changes and can be considered a follow up for #5858 to also fix
#5857 in 3rd party notifications.
The difference in the actual notification would be the following:
```diff
- Pull request review rejected
+ Pull request review changes requested
```
While this is a simple string change at first look, it has a deeper UX
meaning.
# Motivation
We could observe that some developers are hesitant to press the "Request
changes" button since their peers first see that their changes were
rejected, thus a more appropriate wording that also falls in line with
the meaning and UI would be beneficial.
## Meaning
Pressing the `Request changes` button in a PR review means that as a
reviewer you are willing to merge the general change in a PR if changes
requested review comments are implemented.
Rejecting a PR on the other hand would be equivalent with closing it
since that change isn't welcome at all (e.g. out of scope feature).
## Sync with UI
The UI button says `request changes` and the other options
## Considered Problems
This might break some automation for users who rely on string matching.
* 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: wxiaoguang <wxiaoguang@gmail.com>
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: wxiaoguang <wxiaoguang@gmail.com>
The "autofocus" was abused or misbehaved:
1. When users visit a page but they are not going to change a field,
then the field shouldn't get "autofocus"
* the "auth" / "user" page: in most cases, users do not want to change
the names
* see also the GitHub's "settings" page behavior.
2. There shouldn't be duplicate "autofocus" inputs in most cases, only
the first one focuses
3. When a panel is shown, the "autofocus" should get focus
* "add ssh key" panel
This PR fixes all these problems and by the way remove duplicate
"isElemHidden" function.
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
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: wxiaoguang <wxiaoguang@gmail.com>
This PR adds the label _state_ to the metric _gitea_users_. With the
change, _gitea_users_ would be reported like this:
```
...
# HELP gitea_users Number of Users
# TYPE gitea_users gauge
gitea_users{state="active"} 20
gitea_users{state="inactive"} 10
...
```
The metrics above would be from a Gitea instance with 30 user accounts.
20 of the accounts are active and 10 of the accounts are not active.
Resolve#34325
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
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
@@ -30,7 +30,7 @@ These are the values to which people in the Gitea community should aspire.
- **Be constructive.**
- Avoid derailing: stay on topic; if you want to talk about something else, start a new conversation.
- Avoid unconstructive criticism: don't merely decry the current state of affairs; offer—or at least solicit—suggestions as to how things may be improved.
- Avoid discussing potentially offensive or sensitive issues; this all too often leads to unnecessary conflict.
- Avoid microaggressions (brief and commonplace verbal, behavioral and environmental indignities that communicate hostile, derogatory or negative slights and insults to a person or group).
- **Be responsible.**
@@ -42,7 +42,7 @@ People are complicated. You should expect to be misunderstood and to misundersta
### Our Pledge
In the interest of fostering an open and welcoming environment, we as contributors and maintainers pledge to making participation in our project and our community a harassment-free experience for everyone, regardless of age, body size, disability, ethnicity, gender identity and expression, level of experience, education, socio-economic status, nationality, personal appearance, race, religion, or sexual identity and orientation.
In the interest of fostering an open and welcoming environment, we as contributors and maintainers pledge to make participation in our project and our community a harassment-free experience for everyone, regardless of age, body size, disability, ethnicity, gender identity and expression, level of experience, education, socio-economic status, nationality, personal appearance, race, religion, or sexual identity and orientation.
|``make test[\#SpecificTestName]`` | run unit test(s) | |
|``make test-sqlite[\#SpecificTestName]``| run [integration](tests/integration) test(s) for SQLite |[More details](tests/integration/README.md) |
|``make test-e2e-sqlite[\#SpecificTestName]``| run [end-to-end](tests/e2e) test(s) for SQLite | [More details](tests/e2e/README.md) |
## Translation
@@ -591,7 +591,7 @@ be reviewed by two maintainers and must pass the automatic tests.
## Releasing Gitea
- Let $vmaj, $vmin and $vpat be Major, Minor and Patch version numbers, $vpat should be rc1, rc2, 0, 1, ...... $vmaj.$vmin will be kept the same as milestones on github or gitea in future.
- Before releasing, confirm all the version's milestone issues or PRs has been resolved. Then discuss the release on Discord channel #maintainers and get agreed with almost all the owners and mergers. Or you can declare the version and if nobody against in about serval hours.
- Before releasing, confirm all the version's milestone issues or PRs has been resolved. Then discuss the release on Discord channel #maintainers and get agreed with almost all the owners and mergers. Or you can declare the version and if nobody is against it in about several hours.
- If this is a big version first you have to create PR for changelog on branch `main` with PRs with label `changelog` and after it has been merged do following steps:
- Create `-dev` tag as `git tag -s -F release.notes v$vmaj.$vmin.0-dev` and push the tag as `git push origin v$vmaj.$vmin.0-dev`.
- When CI has finished building tag then you have to create a new branch named `release/v$vmaj.$vmin`
# Use COPY but not "mount" because some directories like "node_modules" contain platform-depended contents and these directories need to be ignored.
# ".git" directory will be mounted later separately for getting version data.
# TODO: in the future, maybe we can pre-build the frontend assets on one platform and share them for different platforms, the benefit is that it won't be affected by webpack plugin compatibility problems, then the working directory can be fully mounted and the COPY is not needed.
@@ -52,7 +52,7 @@ or if SQLite support is required:
The `build` target is split into two sub-targets:
-`make backend` which requires [Go Stable](https://go.dev/dl/), the required version is defined in [go.mod](/go.mod).
-`make frontend` which requires [Node.js LTS](https://nodejs.org/en/download/) or greater.
-`make frontend` which requires [Node.js LTS](https://nodejs.org/en/download/) or greater and [pnpm](https://pnpm.io/installation).
Internet connectivity is required to download the go and npm modules. When building from the official source tarballs which include pre-built frontend files, the `frontend` target will not be triggered, making it possible to build without Node.js.
Translations are done through [Crowdin](https://translate.gitea.com). If you want to translate to a new language ask one of the managers in the Crowdin project to add a new language there.
Translations are done through [Crowdin](https://translate.gitea.com). If you want to translate to a new language, ask one of the managers in the Crowdin project to add a new language there.
You can also just create an issue for adding a language or ask on discord on the #translation channel. If you need context or find some translation issues, you can leave a comment on the string or ask on Discord. For general translation questions there is a section in the docs. Currently a bit empty but we hope to fill it as questions pop up.
You can also just create an issue for adding a language or ask on Discord on the #translation channel. If you need context or find some translation issues, you can leave a comment on the string or ask on Discord. For general translation questions there is a section in the docs. Currently a bit empty, but we hope to fill it as questions pop up.
Get more information from [documentation](https://docs.gitea.com/contributing/localization).
Usage:"Username. DEPRECATED: use username instead",
},
&cli.StringFlag{
Name:"username",
Usage:"Username",
},
},
},
Required:true,
},
},
&cli.StringFlag{
Name:"username",
Usage:"Username",
Flags:[]cli.Flag{
&cli.StringFlag{
Name:"user-type",
Usage:"Set user's type: individual or bot",
Value:"individual",
},
&cli.StringFlag{
Name:"password",
Usage:"User password",
},
&cli.StringFlag{
Name:"email",
Usage:"User email address",
Required:true,
},
&cli.BoolFlag{
Name:"admin",
Usage:"User is an admin",
},
&cli.BoolFlag{
Name:"random-password",
Usage:"Generate a random password for the user",
},
&cli.BoolFlag{
Name:"must-change-password",
Usage:"User must change password after initial login, defaults to true for all users except the first one (can be disabled by --must-change-password=false)",
HideDefault:true,
},
&cli.IntFlag{
Name:"random-password-length",
Usage:"Length of the random password to be generated",
Value:12,
},
&cli.BoolFlag{
Name:"access-token",
Usage:"Generate access token for the user",
},
&cli.StringFlag{
Name:"access-token-name",
Usage:`Name of the generated access token`,
Value:"gitea-admin",
},
&cli.StringFlag{
Name:"access-token-scopes",
Usage:`Scopes of the generated access token, comma separated. Examples: "all", "public-only,read:issue", "write:repository,write:user"`,
Value:"all",
},
&cli.BoolFlag{
Name:"restricted",
Usage:"Make a restricted user account",
},
&cli.StringFlag{
Name:"fullname",
Usage:`The full, human-readable name of the user`,
},
},
&cli.StringFlag{
Name:"user-type",
Usage:"Set user's type: individual or bot",
Value:"individual",
},
&cli.StringFlag{
Name:"password",
Usage:"User password",
},
&cli.StringFlag{
Name:"email",
Usage:"User email address",
},
&cli.BoolFlag{
Name:"admin",
Usage:"User is an admin",
},
&cli.BoolFlag{
Name:"random-password",
Usage:"Generate a random password for the user",
},
&cli.BoolFlag{
Name:"must-change-password",
Usage:"User must change password after initial login, defaults to true for all users except the first one (can be disabled by --must-change-password=false)",
DisableDefaultText:true,
},
&cli.IntFlag{
Name:"random-password-length",
Usage:"Length of the random password to be generated",
Value:12,
},
&cli.BoolFlag{
Name:"access-token",
Usage:"Generate access token for the user",
},
&cli.StringFlag{
Name:"access-token-name",
Usage:`Name of the generated access token`,
Value:"gitea-admin",
},
&cli.StringFlag{
Name:"access-token-scopes",
Usage:`Scopes of the generated access token, comma separated. Examples: "all", "public-only,read:issue", "write:repository,write:user"`,
Value:"all",
},
&cli.BoolFlag{
Name:"restricted",
Usage:"Make a restricted user account",
},
&cli.StringFlag{
Name:"fullname",
Usage:`The full, human-readable name of the user`,
// PrepareConsoleLoggerLevel by default, use INFO level for console logger, but some sub-commands (for git/ssh protocol) shouldn't output any log to stdout.
// Any log appears in git stdout pipe will break the git protocol, eg: client can't push and hangs forever.
// "--config" flag is provided by global flags, and this flag is also used by "environment-to-ini" script wrapper
// "--in-place" is also used by "environment-to-ini" script wrapper for its old behavior: always overwrite the existing config file
&cli.BoolFlag{
Name:"in-place",
Usage:"Output to the same config file as input. This flag will be ignored if --out is set.",
},
&cli.StringFlag{
Name:"config-keep-keys",
Usage:"An INI template file containing keys for keeping. Only the keys defined in the INI template will be kept from old config. If not set, all keys will be kept.",
},
&cli.BoolFlag{
Name:"apply-env",
Usage:"Apply all GITEA__* variables from the environment to the config.",
Usage:"Diagnose and optionally fix problems, convert or re-create database tables",
Description:"A command to diagnose problems with the current Gitea instance according to the given configuration. Some problems can optionally be fixed by modifying the database or data storage.",
Subcommands:[]*cli.Command{
Commands:[]*cli.Command{
cmdDoctorCheck,
cmdRecreateTable,
cmdDoctorConvert,
@@ -93,16 +93,13 @@ You should back-up your database before doing this and ensure that your database
// cmdHelp is our own help subcommand with more information
// Keep in mind that the "./gitea help"(subcommand) is different from "./gitea --help"(flag), the flag doesn't parse the config or output "DEFAULT CONFIGURATION:" information
funccmdHelp()*cli.Command{
c:=&cli.Command{
Name:"help",
Aliases:[]string{"h"},
Usage:"Shows a list of commands or help for one command",
ArgsUsage:"[command]",
Action:func(c*cli.Context)(errerror){
lineage:=c.Lineage()// The order is from child to parent: help, doctor, Gitea, {Command:nil}
app.Name="gitea"// must be lower-cased because it appears in the "USAGE" section like "gitea doctor [command [command options]]"
app.Usage="A painless self-hosted Git service"
app.Description=`Gitea program contains "web" and other subcommands. If no subcommand is given, it starts the web server by default. Use "web" subcommand for more web server arguments, use other subcommands for other purposes.`
app.Version=appVer.Version+appVer.Extra
app.EnableBashCompletion=true
// these sub-commands need to use config file
app.EnableShellCompletion=true
app.Flags=[]cli.Flag{
&cli.StringFlag{
Name:"work-path",
Aliases:[]string{"w"},
TakesFile:true,
Usage:"Set Gitea's working path (defaults to the Gitea's binary directory)",
},
&cli.StringFlag{
Name:"config",
Aliases:[]string{"c"},
TakesFile:true,
Value:setting.CustomConf,
Usage:"Set custom config file (defaults to '{WorkPath}/custom/conf/app.ini')",
},
&cli.StringFlag{
Name:"custom-path",
Aliases:[]string{"C"},
TakesFile:true,
Usage:"Set custom path (defaults to '{WorkPath}/custom')",
},
}
// these sub-commands need to use a config file
subCmdWithConfig:=[]*cli.Command{
cmdHelp(),// the "help" sub-command was used to show the more information for "work path" and "custom config"
// The pprof server is for debug purpose only, it shouldn't be exposed on public network. At the moment it's not worth to introduce a configurable option for it.
// The pprof server is for debug purpose only, it shouldn't be exposed on public network. At the moment, it's not worth introducing a configurable option for it.
log.Info("Starting pprof server on localhost:6060")
<p>In general, Your Gitea Instance retains User Personal Information for as long as your account is active, or as needed to provide you service.</p>
<p>If you would like to cancel your account or delete your User Personal Information, you may do so in your user profile. We retain and use your information as necessary to comply with our legal obligations, resolve disputes, and enforce our agreements, but barring legal requirements, we will delete your full profile (within reason) within 90 days of your request. Feel free to contact our support to request erasure of the data we process on the bassis of consent within 30 days.</p>
<p>If you would like to cancel your account or delete your User Personal Information, you may do so in your user profile. We retain and use your information as necessary to comply with our legal obligations, resolve disputes, and enforce our agreements, but barring legal requirements, we will delete your full profile (within reason) within 90 days of your request. Feel free to contact our support to request erasure of the data we process on the basis of consent within 30 days.</p>
<p>After an account has been deleted, certain data, such as contributions to other Users' repositories and comments in others' issues, will remain. However, we will delete or de-identify your User Personal Information, including your username and email address, from the author field of issues, pull requests, and comments by associating them with a ghost user.</p>
;; GPG key to use to sign commits, Defaults to the default - that is the value of git config --get user.signingkey
;; GPG or SSH key to use to sign commits, Defaults to the default - that is the value of git config --get user.signingkey
;; Depending on the value of SIGNING_FORMAT this is either:
;; - openpgp: the GPG key ID
;; - ssh: the path to the ssh public key "/path/to/key.pub": where "/path/to/key" is the private key, use ssh-keygen -t ed25519 to generate a new key pair without password
;; run in the context of the RUN_USER
;; Switch to none to stop signing completely
;SIGNING_KEY = default
;;
;; If a SIGNING_KEY ID is provided and is not set to default, use the provided Name and Email address as the signer.
;; If a SIGNING_KEY ID is provided and is not set to default, use the provided Name and Email address as the signer and the signing format.
;; These should match a publicized name and email address for the key. (When SIGNING_KEY is default these are set to
;; the results of git config --get user.name and git config --get user.email respectively and can only be overridden
;; the results of git config --get user.name, git config --get user.email and git config --default openpgp --get gpg.format respectively and can only be overridden
;; by setting the SIGNING_KEY ID to the correct ID.)
;SIGNING_NAME =
;SIGNING_EMAIL =
;; SIGNING_FORMAT can be one of:
;; - openpgp (default): use GPG to sign commits
;; - ssh: use SSH to sign commits
;SIGNING_FORMAT = openpgp
;;
;; Sets the default trust model for repositories. Options are: collaborator, committer, collaboratorcommitter
;DEFAULT_TRUST_MODEL = collaborator
@@ -1227,6 +1235,13 @@ LEVEL = Info
;; - commitssigned: require that all the commits in the head branch are signed.
;; - approved: only sign when merging an approved pr to a protected branch
;; * sanitized: Sanitize the content and render it inside current page, default to only allow a few HTML tags and attributes. Customized sanitizer rules can be defined in [markup.sanitizer.*] .
;; * no-sanitizer: Disable the sanitizer and render the content inside current page. It's **insecure** and may lead to XSS attack if the content contains malicious code.
;; * iframe: Render the content in a separate standalone page and embed it into current page by iframe. The iframe is in sandbox mode with same-origin disabled, and the JS code are safely isolated from parent page.
;RENDER_CONTENT_MODE=sanitized
;RENDER_CONTENT_MODE = sanitized
;; The sandbox applied to the iframe and Content-Security-Policy header when RENDER_CONTENT_MODE is `iframe`.
;; It defaults to a safe set of "allow-*" restrictions (space separated).
;; You can also set it by your requirements or use "disabled" to disable the sandbox completely.
;; When set it, make sure there is no security risk:
;; * PDF-only content: generally safe to use "disabled", and it needs to be "disabled" because PDF only renders with no sandbox.
;; * HTML content with JS: if the "RENDER_COMMAND" can guarantee there is no XSS, then it is safe, otherwise, you need to fine tune the "allow-*" restrictions.
;RENDER_CONTENT_SANDBOX =
;; Whether post-process the rendered HTML content, including:
File diff suppressed because it is too large
Load Diff
Some files were not shown because too many files have changed in this diff
Show More
Reference in New Issue
Block a user
Blocking a user prevents them from interacting with repositories, such as opening or commenting on pull requests or issues. Learn more about blocking a user.
