It is fine to use MockVariableValue to change a setting such as:
defer test.MockVariableValue(&setting.Mirror.Enabled, true)()
But when testing for errors and mocking a function, multiple variants
of the functions will be used, not just one. MockProtect a function
will make sure that when the test fails it always restores a sane
version of the function. For instance:
defer test.MockProtect(&mirror_service.AddPushMirrorRemote)()
mirror_service.AddPushMirrorRemote = mockOne
do some tests that may fail
mirror_service.AddPushMirrorRemote = mockTwo
do more tests that may fail
- rewrite a lot of hints on install page
- make sure checkboxes don't hide useful information behind hover
This is good for compactness but makes first-time installation more painful than it should be. BTW, this was inherited from Gogs.
- update related translation keys (will require Weblate sync to merge)
- make sure string locations in en-US.ini make sense. Unfortunately, makes viewing changes harder, but I've attached screenshots
## Preview
![](https://codeberg.org/attachments/b0d26013-5fd9-495c-b4c0-7919f9f6fbf4)
Reviewed-on: https://codeberg.org/forgejo/forgejo/pulls/3961
Reviewed-by: Otto <otto@codeberg.org>
- 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
![](/attachments/9cf6d73a-8132-4f30-8094-5687d7dd98e9)
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)