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>
