We wanted to be able to use the IAM role provided by the EC2 instance
metadata in order to access S3 via the Minio configuration. To do this,
a new credentials chain is added that will check the following locations
for credentials when an access key is not provided. In priority order,
they are:
1. MINIO_ prefixed environment variables
2. AWS_ prefixed environment variables
3. a minio credentials file
4. an aws credentials file
5. EC2 instance metadata
(cherry picked from commit c0880e7695346997c6a93f05cd01634cb3ad03ee)
Conflicts:
docs/content/administration/config-cheat-sheet.en-us.md
does not exist in Forgejo
This PR split the `Board` into two parts. One is the struct has been
renamed to `Column` and the second we have a `Template Type`.
But to make it easier to review, this PR will not change the database
schemas, they are just renames. The database schema changes could be in
future PRs.
---------
Co-authored-by: silverwind <me@silverwind.io>
Co-authored-by: yp05327 <576951401@qq.com>
(cherry picked from commit 98751108b11dc748cc99230ca0fc1acfdf2c8929)
Conflicts:
docs/content/administration/config-cheat-sheet.en-us.md
docs/content/index.en-us.md
docs/content/installation/comparison.en-us.md
docs/content/usage/permissions.en-us.md
non existent files
options/locale/locale_en-US.ini
routers/web/web.go
templates/repo/header.tmpl
templates/repo/settings/options.tmpl
trivial context conflicts
Fix#25897Fix#30322#29464 cannot handle some complex `if` conditions correctly because it
only checks `always()` literally. In fact, it's not easy to evaluate the
`if` condition on the Gitea side because evaluating it requires a series
of contexts. But act_runner is able to evaluate the `if` condition
before running the job (for more information, see
[`gitea/act`](517d11c671/pkg/runner/run_context.go (L739-L753)))
. So we can use act_runner to check the `if` condition.
In this PR, how to handle a blocked job depends on its `needs` and `if`:
- If not all jobs in `needs` completed successfully and the job's `if`
is empty, set the job status to `StatusSkipped`
- In other cases, the job status will be set to `StatusWaiting`, and
then act_runner will check the `if` condition and run the job if the
condition is met
(cherry picked from commit 31a0c4dfb4156a7b4d856cceae1e61c7fc1a4a1b)
- make sure margins are all consistent and good, elements are not too close or too apart
- this also applies to "Show commit body" button
- remove unused code. The class `commit-status-link` doesn't exist in templates, nor I could find it on any related pages in case it's generated in runtime
## Preview
Reviewed-on: https://codeberg.org/forgejo/forgejo/pulls/3948
Reviewed-by: Beowulf <beowulf@noreply.codeberg.org>
Use the same padding horizontally and vertically, so the views like readme look a bit nicer. Just slightly adjusted two values, nothing really test-able here.
## Motivation
I came to the conclusion that they should be the same myself, later I checked GitHub and it turned out to also use the same paddings. I would like to notice that the padding here (2em = 32px) is the same as GitHub uses too.
I find this as a logical UI change because the paddings are usually same on both axis across the UI (like on PR sidebar).
Also updated paddings for when the files are shown in profile, but copied the `1.5em` that GitHub uses. This, once again, makes sense, because the overview markdown isn't the primary content, or as primary as the readme on the repo is, taking the full usable width.
## Preview
https://codeberg.org/attachments/55f6685c-1978-410a-a17b-9fac91f0642e
---
https://codeberg.org/attachments/d9016a1c-13cf-4ea6-a8e4-2619d93f3560
## Note
`.non-diff-file-content .plain-text` is left untouched with `1em 2em`, because the plaintext seems to add it's own margins, so it would make it look worse.
Reviewed-on: https://codeberg.org/forgejo/forgejo/pulls/3944
Reviewed-by: Otto <otto@codeberg.org>
Reviewed-by: Beowulf <beowulf@noreply.codeberg.org>
Remove CSS code that was made unused by some changes in Gitea. I was working on a layout change here but was bothered a bit by these. I dug a bit into the git history to find out how they were made unused but it's relatively uneasy.
- remove rule that was setting `width: 100%;`: the exactly same selector setting this exact value is duplicated below
- remove rules with `followers` in selectors: we don't use this class in templates (would be nice if someone double-checks)
- my editor forced EoF fix
Reviewed-on: https://codeberg.org/forgejo/forgejo/pulls/3937
Reviewed-by: Beowulf <beowulf@noreply.codeberg.org>
When performing migrations, and need to remap external users to local
ones, when no local mapping is possible, map the external user to Ghost,
rather than the user who initiated the migration.
Mapping the external user to the migration initiator has the potential
of breaking assumptions elsewhere, like only having one review per pull
request per user. Mapping these migrated, locally unavailable users to
Ghost makes sure these - often hidden - assumptions do not break.
Fixes#3860.
Signed-off-by: Gergely Nagy <forgejo@gergo.csillger.hu>
When installing Forgejo via the on-line installer, force
DisableRegistration to true, to discourage creating instances with open
registration. Because open registration requires constant vigil to fight
off spammers of all kinds, it is not a great default. It should be a
conscious decision. This change is made in an effort to make the choice
of running an instance with open registration a conscious choice, rather
than simply the default.
Partially addresses #3925.
Signed-off-by: Gergely Nagy <forgejo@gergo.csillger.hu>
Having an instance with open registration requires work, otherwise it
will be overrun by spammers of all kinds. Yet, the setting to disable
open registration on the installation page is hidden behind "optional
settings", a place hardly anyone ever looks.
To improve the situation, lift the setting out of that, and place it
more prominently, just above the update checker setting.
Partially addresses #3925.
Signed-off-by: Gergely Nagy <forgejo@gergo.csillger.hu>
Following gitea#28981, set `X-Forgejo-Sender` and `X-Forgejo-Recipient`
to the username of the respective users, rather than their display name.
The username is more appropriate for these headers, for filtering
purposes. The display name is already included in the From header.
Signed-off-by: Gergely Nagy <forgejo@gergo.csillger.hu>
Cherry-pick of 2ced31e81d adapted to Forgejo releases UI.
Percentage-based `border-radius` [creates undesirable
ellipse](https://jsfiddle.net/silverwind/j9ko5wnt/4/) on non-square
content. Instead, use pixel value and use same wording `full` like
tailwind does, but increast to 99999px over their 9999px.
(cherry picked from commit 2ced31e81dd9e45659660c1abff529d0192fd8ed)
Rowan Bohde