there were a lot of events recorded by gharchive.org of which 2,457,288 were push events containing 3,714,607 commit messages that amount to 305,850,747 characters filtered with words.py@e23d022007... to these 63 messages:
Servant of Wrath
Records and Instability
Dash speed up
Fuck you I'll space indent all I like
There was some fuckin lint in this PR
God damned there's a lot of lint in here
Faction Check
Sprite update, minor bug fixes
Floating and Gun and Acid
Minor Records
Small update
Unnerfs resists
AoE hit fix
Gun update real
more res should mean less talk
Pixel Fix
Sound... Fix?
Broke the staff's legs, fuck those guys.
lmfao audio pains
Gun Rename, Spawn nerf
NO MORE FRIENDS FROM GUN
Faction change
acid tweak
LINT!
SW Code and Balance
SoW Temp commit
Scuff-Fix
SoW bonk update
Hermit range increase and ranged damage decrease
visual fix
Ending adjustments
I forgot to carry the 4
Give slimes their sex back (not the ERP one) (#14380)
Gives back the ability for slimes to have a definitive sex. Cosmetic/visual things such as emotes/other stuff use the person's sex and not the gender and I feel like that the removal of slime's having sexes was just to show that the species refactor could handle unsexed species.
Media
- I have added screenshots/videos to this PR showcasing its changes ingame, or this PR does not require an ingame showcase
Changelog
🆑 eclips_e
- fix: Male and female slimes now scream and laugh properly
add dirs command to std lib (#8368)
Prototype replacement for enter, n, p, exit built-ins
implemented as scripts in standard library.
MVP-level capabilities (rough hack), for feedback please. Not intended
to merge and ship as is.
(Description of your pull request goes here. Provide examples and/or screenshots if your changes affect the user experience.)
New command in standard library
〉use ~/src/rust/nushell/crates/nu-utils/standard_library/dirs.nu
---------------------------------------------- /home/bobhy ----------------------------------------------
〉help dirs
module dirs.nu -- maintain list of remembered directories + navigate them
todo:
* expand relative to absolute paths (or relative to some prefix?)
* what if user does `cd` by hand?
Module: dirs
Exported commands:
add (dirs add), drop, next (dirs next), prev (dirs prev), show (dirs show)
This module exports environment.
---------------------------------------------- /home/bobhy ----------------------------------------------
〉dirs add ~/src/rust/nushell /etc ~/.cargo
-------------------------------------- /home/bobhy/src/rust/nushell --------------------------------------
〉dirs next 2
------------------------------------------- /home/bobhy/.cargo -------------------------------------------
〉dirs show
╭───┬─────────┬────────────────────╮
│ # │ current │ path │
├───┼─────────┼────────────────────┤
│ 0 │ │ /home/bobhy │
│ 1 │ │ ~/src/rust/nushell │
│ 2 │ │ /etc │
│ 3 │ ==> │ ~/.cargo │
╰───┴─────────┴────────────────────╯
------------------------------------------- /home/bobhy/.cargo -------------------------------------------
〉dirs drop
---------------------------------------------- /home/bobhy ----------------------------------------------
〉dirs show
╭───┬─────────┬────────────────────╮
│ # │ current │ path │
├───┼─────────┼────────────────────┤
│ 0 │ ==> │ /home/bobhy │
│ 1 │ │ ~/src/rust/nushell │
│ 2 │ │ /etc │
╰───┴─────────┴────────────────────╯
---------------------------------------------- /home/bobhy ----------------------------------------------
〉Haven't even looked at stdlib tests.nu yet.
Other todos:
- address module todos.
- integrate into std lib, rather than as standalone module. Somehow
arrange for
use .../standard_library/std.nuto load this module without having to put all the source instd.nu? - Maybe command should be
std dirs ...? - what else do
enterandexitdo that this should do? Then deprecate those commands.
Don't forget to add tests that cover your changes.
Make sure you've run and fixed any issues with these commands:
cargo fmt --all -- --checkto check standard code formatting (cargo fmt --allapplies these changes)cargo clippy --workspace -- -D warnings -D clippy::unwrap_used -A clippy::needless_collectto check that you're using the standard code stylecargo test --workspaceto check that all tests pass
If your PR had any user-facing changes, update the documentation after the PR is merged, if necessary. This will help us keep the docs up to date.
Fix entering a ghosted xeno not removing ghostize sleep. (#2076)
Fix entering a ghosted xeno not removing ghostize sleep.
This sucks ass! Let me wake up!!!!! can KILL you if you enter a xeno in a difficult situation!!!!!!
Screenshots & Videos
Put screenshots and videos here with an empty line between the
screenshots and the <details> tags.
🆑 fix: Fix entering a ghosted xeno not removing ghostize sleep. /🆑
[MIRROR] You can't instantly resist out of an unlocked labor camp teleporter if you are handcuffed [MDB IGNORE] (#19855)
- You can't instantly resist out of an unlocked labor camp teleporter if you are handcuffed (#73983)
If you are restrained, and placed into an unlocked labor camp teleporter, you cannot instantly resist out of it. However the resist timer is cut in half while unlocked.
Getting someone into the gulag teleporter is an incredibly un-necessary pain in the rear because simply spamming resist turns it into a game where you have to shove them in, then really quick go over to the computer and slam the lock button. This is... kinda lame. A lot of new player security officers get got by this, and I think it's sad. Inb4 "Skill issue"
🆑 Melbert balance: If you are handcuffed, you can't instantly resist out of an unlocked labor camp teleporter (however, resist time is halved). /🆑
- You can't instantly resist out of an unlocked labor camp teleporter if you are handcuffed
Co-authored-by: MrMelbert [email protected]
[MIRROR] All hail The Pickle Jar, harbringer of better crafting [MDB IGNORE] (#19866)
- All hail The Pickle Jar, harbringer of better crafting (#73939)
Fixes #73841
It is the 12th of March, 2023. Around 3am. I have published a Pull Request which involves circuits, and got reminded of my low GBP. I go into the issues tab to see if there's anything someone of my low skill caliber could tackle. I see it; Pickles. "How hard could I be?" I ask myself, foolishly unaware of the dangers that would soon overcome me. Surely it must've been a mistype, I thought. Surely someone accidentally confused pickles and cucumbers. "Wait, the pickles are supposed to be created on the jar when the jar is created", I say foolishly. "Wait, its putting the ingredients used for the jar in the jar, that doesn't explain why the pickles aren't there though", I say foolishly "Wait, whoever tried fixing this earlier fucking qdel'd the beaker and called it a day????", I say, foolishly.
Anyways I changed how the crafting menu distincts between categories, instead of checking whether or not the path is for food, it checks the actual categories themselves (why didn't it do this already), meaning that you can have non-food items on the food tab if it has a food category. Did this by adding a list that includes all crafting categories, so in the future when adding new categories you'll have to add them twice, which sucks, but oh well.
Also added a new variable to craftable items, which makes it so that you can not delete a container's contents if you so wish (why was this the default).
All this so that when you craft pickles, it actually crafts pickles instead of cucumbers.
I spent hours on this, its 6:30am as I'm typing this. I'm tired. Fucking pickles.
Super duper ultra thanks to FinalPotato for guiding me and suffering with me through this and teaching me so much about DM and BYOND. I cannot emphasize just how helpful and awesome they were thank you thank you thank you <3
Bug fixing be good
🆑 fix: The jar of pickles, after millenia, finally actually contains pickles. All hail the jar of pickles. /🆑
- All hail The Pickle Jar, harbringer of better crafting
Co-authored-by: TheSmallBlue [email protected]
Reworks trashbags slightly (#73761)
I'm a bit sad about the state of trashbags. They're very clunky to use, so they almost never get touched. S depressing. Let's try and fix that.
Let's make em fit in the belt slot (again), but as a tradeoff we'll make it harder to pull one thing from your bag. We'll give it a say, 1.5 second delay, so you can't quickdraw from em. If you try and dump them out into something else, we'll throw any spillover on the ground below you
I'm also doing some general code cleanup here. Making procs more readable, vars more direct, removing some old legacy stuff. I've added a remove_single proc to hook into via subtype, which takes a mob as input. this has required placing extra requirement on some helper procs, but fortunately it's not something they're unable to meet.
My hope is this will make garbage bags usable without being stupid.
I don't see these get used at all, cause they're a pain to carry around. They got gimped because people were using them as infinite storage for shotgun shells and other small items. I've made using them for this sort of thing hard and slow, so I think we oughta be fine. If not I'll do some more touching, maybe give the autodrop a delay.
🆑 balance: The janitor's trashbag now fits on his belt. In exchange, taking something out of it sends a visible message, and has a delay. /🆑
Co-authored-by: san7890 [email protected]
Polishes some side sources of light and color (#73936)
Circuit floors glow! but it looks like crap cause it's dim and the colors are washed out. I'd like to make them look nicer. Let's make them more intense and longer range, and change the colors over to more vivid replacements.
While I'm here, these should really use power and turn on and off based off that. Simple enough to do, just need to hook into a signal (and add a setter for turf area, which cleans up other code too).
Desklamps look bad. They're fullwhite, have a way too large range.Crummy. Let's lower their lightrange from 5 to 3.5, and make the ornate ones warmer, and the more utilitarian ones cooler. The clown one can be yellow because it's funny
I'm renaming a color define here so I'm touching more files then you'd expect
Increases the light range of request consoles, status displays, newscasters, and air alarms (keycard machines too, when they're awaiting input at least) Increases the brightness of air alarms, I think they should be on par with apcs, should be able to tell when they're good/bad. Increases the brightness of vending machines (I want them to light up the tiles around them very lightly, I think it's a vibe)
Fixes a bug with ai status displays where they'd display an emissive even if they didn't have anything on their screen, looking stupid. This was decently easy but required a define. Looked really bad tho
Pretty
Circuit Floors
Old
New
Desk Lights
Old
New
The niknack changes are more minor so I'm not gonna grab photos for them. I can if you'd like but I don't think it's necessary. Mostly a vibes in dark spaces sorta thing
🆑 add: I made circuit floors brighter and more vivid. add: Made air alarms, vending machines, newscasters, request consoles, status displays and keycard machines slightly "brighter" (larger light range, tho I did make air alarms a bit brighter too) add: Tweaked desklamps. Lower range, and each type gets its own coloring instead of just fullwhite. fix: AI displays are no longer always emissive, they'll stop doing it if they aren't displaying anything. Hopefully this'll look nicer /🆑
I added the line, angels are holy.
And got rid of, god is beautiful.
[MIRROR] Starlight Polish (Space is blue!) [MDB IGNORE] (#19059)
- Starlight Polish (Space is blue!) (#72886)
Adds support to underlays to realize_overlays Ensures decals properly handle plane offsets Fixes space lighting double applying if it's changeturf'd into. this will be important later Makes solar vis_contents block emissives as expected Moves transit tube overlays to update_overlays, adds emissive blockers to them
An expansion on render_target based emissive blockers. They allow us to hijack an object's appearance and draw it somewhere else, or even modify it, THEN draw it somewhere else. They chain quite nicely
Fixes shuttles deleting z holder objects
The core idea here goes like this: We make space glow, and give its overlays some color
This way, the tile and space parallax remain fullbright, along with anything that doesn't block emissives, but anything that does block emissives will instead get shaded the color of starlight
This requires a bit of extra work, see later
This is done automatically with render relays, which now support specifiying layer and color (Need to make an editor for these one of these days)
The emissive blocking floor stuff requires making a second render plate to prevent double scaling
Also adds some new layering defines for lighting, and ensures all turf lights have a layer. We'll get to this soon
We color them the same as starlight, by taking advantage of space being emissive This means that things in space that block emissive will block it correctly and be colored blue by the light overlay, but space itself will remain fullbright
This does require redefining what always_lit means, but nothing but cordons use that so it's fineee
Glass tiles that sit above space will now shine light with matching color to the glasses color. This includes mat tiles.
Glass tiles (not mat because they have no alpha) also only partially block emissives. Adds a new proc that uses render steps to acomplish this, essentially we're cutting out bits below X alpha and drawing what remains as an emissive.
Essentially, alongside displaying space as an underlay, we also display a light overlay colored like starlight. That starlight overlay gets masked to only be visible in bits that do not contain any alpha.
We also mask the turf lighting to not go into bits that have no alpha, to ensure we get the effect we want. This is done with that lighting layer thing I mentioned earlier.
I want it output in order of overlay, sub overlay suboverlay, next overlay Need to use insert for that
Pretty! Also having space be emissive is a very very good way to test for fucked emissive blockers (If it's broken why are we even drawing the overlay) I know for a fact mob blockers on lizards and socks are kinda yorked, I think there's more
Old
New
🆑 add: Space now makes things in it starlight faintly blue fix: Glass floors that display space now properly let space shine through them, rather then hiding it in the dark add: Glass floors above space now glow faintly depending on their glass type /🆑
Co-authored-by: Zephyr [email protected]
-
update modular
-
Update _decal.dm
-
Update _decal.dm
Co-authored-by: LemonInTheDark [email protected] Co-authored-by: Zephyr [email protected] Co-authored-by: Tom [email protected] Co-authored-by: lessthanthree [email protected]
Move Go binaries to /usr/bin (#287)
Issue aws-controllers-k8s/community#1640
TL;DR: Prow was mounting test-infra code volume into $GOPATH
causing the deletion of kind and controller-gen binaries that are
installed in $GOPATH/bin
Yesterday, i embarked on a wild 7 hour journey to fix a bug that had
been causing prow jobs to fail with the error message "Kind not found".
The bug was introduced after a recent update that bumped the Go compiler
to 1.19. I found the investigation to this bug to be both interesting
and frustrating, so i wanted to share some key takeways with the
community:
The patch that introduced Go 1.19 also modified a go get command
into a go install command (because of this deprecation notice:
https://go.dev/doc/go-get-install-deprecation), which technically should
not have caused any issues. I tried restarting the e2e jobs in various
repositories to figure out whether the error was only related to one
controller or code-generator only, but all the repositories that execute
e2e tests were affected.
First, i started suspecting that thee go install command was not
working properly or had not been used correctly. I experiemented with it
locally, using various combinations of GOPATH and GOBIN, however, i
learned that the Go compiler is sophisticated enough to always put
downloaded binaries under GOBIN or GOPATH/bin. I then wondered if
the PATH variable didn't include the GOBIN path, which is supposed
to contain the kind and controller-gen binaries. I spent some time
reading the Dockerfiles and testing scripts, but they all set GOPATH
and always included a GOBIN in the PATH variable.
I also suspected that the issue may be related to the containers, but experimentations with "Go containers" and environement variables manipulation did not yield any results. I also tried building minimal DOckerfiles to try to reproduce the issue, but that also did not give any clues.
At this point, I suspected the container image it self. I build an image
locally and ran a shell inside it, but everythin g looked fine. THe
kind and controller-gen binaries were present and the PATH and
GOPATH variables were properly set. I then suspect that we may have a
corrupted published image in ECR, but pulling the image and running the
same commands revealed that the image was fine.
I then took a break from experimenting with Go/Docker/Envvars and tried
to spin some prowjobs with v0.0.10 and v0.0.9 (the last two versions
that were still using Go 1.17) of the integration tests image. This
confirmed that the issue was only with v0.0.11.
So, I decided to investigate further and logged in the Prow production
cluster. My first attempt was to restart a job and try to "exec bash" in
it, but the jobs failed to quickly for that to be possible. I then ran
a custom prow job (with v0.0.11 integration image tag) but with a
sleep 10000 command. When looking inside, there were no kind or
controller-gen binaries, i searched the entire file system, they were
nowhere to be found, grep, find, name it all.. nada. I then execute a
go install sigs.k8s.io/[email protected]", and bam, it worked, the binary
was here again. The same thing happened with controller-gen. So for now
we know that we ship images with all the necessary binaries and when a
prow job starts, they disapear...
To isolate the problem further, i created a ProwJob resource and
copied the Pod (spawned by Prow) spec and metadata into a different
file. Running the same commands used previously proved that indeed
something is wrong with the pod spec, causing the binaries to disapear.
And when a file disppears it reminds me of my college years, where i
epically failed to use symbolic links, which is a bit similar (at least
from a UX point) to volume mounts in the Docker world.
So, i decided to check the volume mounts, and to my not-surprise, I found this:
- mountPath: /home/prow/go
name: codeYes... Prow is mounting the test-infra source code into GOPATH
(/home/prow/go in prow jobs) ! Which is the parent directory of
GOBIN where we install the binaries. And it all makes sense now.
Mounting code into this directory overrides the existing volume and
deletes everything existing in GOPATH including the binaries we
installed before.
The Dockerfile was missing the mv commands that puts kind and
controller-gen in /usr/bin. To fix this issue, I added the missing
mv command to the docker file and published and new integration
image v0.0.12.
Anyways, investigating the source of the volume mount led me to the Prow
presets configurations. Presets are a set of configurations (volume
mounts, environement variables, etc...) that are used for jobs with
specific labels in their metadata. I tried to play with this in our Prow
cluster, but quickly stoped when it was a bit risky and could break
other components too. While digging into test-infra pod-util package i
learned that the code volume is not coming from our defined presets and
is a default preset coming from Prow it self - the /home/prow/go value
is harded-coded in prow/pod-utils/decorate/podspec.go#L54. I'm not
sure whether we can override this value.
Anyways, for now, i'm just gonna implement a quick fix that moves the
binaries to /usr/bin instead of leaving them inside GOBIN. Ideally
we should either choose a new directory go GOPATH that is different
from $HOME/go or find a solution that will let the code and our
binaries coexist in the same place. Either of them requires a lot of
changes and can agressively break some our prow components/scripts.
@jljaco is currently workng on creating a staging cluster, which will provide us a safe environementto test and experiment with new configurations. This will allow us to try out new changes without having to woryy about potentially impacting the production environement.
Signed-off-by: Amine Hilaly [email protected]
By submitting this pull request, I confirm that my contribution is made under the terms of the Apache 2.0 license.
Makes "forced" opening and closing of doors way more sane (#73699)
The gist is that people thought that this was a boolean value, which was
fucked up. It's not a boolean value, it accepts anything between 0 and
2. So, let's re-arrange the checks and framework, give it some
descriptive defines, just so people know what the fuck "2" actually
does. DOOR_DEFAULT_CHECKS (0) does stuff normally,
DOOR_FORCED_CHECKS 1 typically just checking if we aren't emagged shut
or something (i suppose it could happen), and DOOR_BYPASS_CHECKS (2)
means that we just get the fucking door open if it isn't physically
sealed shut/open somehow.
I don't know if forced has ever been a boolean, but for some reason
people thought it was.
I also enforced boolean returns instead of passing back null. This did not matter for close() but i think it's silly to have a TRUE/null dichotomy so that was also touched up.
Much better to read, less confusing, less stupid. It's been irritating me for a while now, so let's just implement it now. Had to make a few awkward concessions in order to fit this into the current code framework, but it should be a lot nicer. I also shuffled the order of some code around because certain placements didn't make any sense (early returns not being in the right spot for an early return).
Nothing that should concern players.
Lowers nightvision threshold to work for mesons, fixes not being able to examine stuff lit by overlay lights (#73712)
Might be a bit low, but part of that is because it's kinda bad at figuring color, rgb isn't really balanced in that respect
Fixes not being able to see stuff under the light of a lamp
Overlay lights don't set lumen, which leads to stupid when you try and check with ONLY it It worked before because the mob has THEIR luminosity set, which then "glowed" out
That doesn't work here cause yaknow I removed our uses of byond lighting (except for errant view() calls) so this is the best I've got
Closes #73548
🆑 fix: Examining in the dark is less wonk now, sorry bout that /🆑
Little Mistake but i fixed this mistake
Hi! I'm Rico. Your Friend.
FYI, I'm going to your github profile to hint some creativity. I'm Interested with your Readme.md! But, i found Little mistake from your information. Just Little, Not Big!
I hope you can be great front-end developer! I'm Sorry if my english is bad:(
Best Regard, Enrique
Life is one big road with lots of signs. So when you riding through the ruts, don't complicate your mind. Flee from hate, mischief and jealousy. Don't bury your thoughts, put your vision to reality. Wake Up and Live!
refactor device grant, reset password actually sends a code now smh, better email messages and experimental ww support (fuck your implementation and empty tokens...)
Signed-off-by: TukanDev [email protected]
The friends room is now more complete looking
(need to figure out which other two paintings to put in and need to connect shit but this is a start)
Update base for Update on "aot autograd refactor: make all synthetic base logic layered in a single location"
This refactor doesn't significantly change LoC in aot autograd, but I think this nets out to making it clearer (interested in peoples' thoughts).
The idea is that I tried to re-write the part of aot autograd that deals with synthetic bases in a layered way, similar to how Ed wrote the logic for dedup'ing inputs: it happens in one place, and all of the downstream transformation in aot autograd don't have to worry about it.
Specifically, I added a new function aot_wrapper_synthetic_base, similar to the existing aot_wrapper_dedupe.
The benefit: none of the other code in aot autograd needs to think about synthetic bases (previously, synthetic base code was intertwined in several places).
The downsides: there are two.
(1) aot_wrapper_synthetic_base() needs to have its own epilogue. There is one particularly hairy case, where factoring the synthetic base logic to a single location was painful: If you have two inputs that alias each other, where one gets a data mutation, and the other gets a metadata mutation.
Ordinarily, metadata mutations are handled by the runtime epilogue, in create_runtime_wrapper. However, now that things are factored this way, the runtime wrapper operates only on synthetic bases instead of operating on the original inputs. For data mutations, it is fine to apply the data mutation to the synthetic base instead of the original input alias. But for metadata mutations, we need to apply the metadata mutation directly to the original inputs.
The way that I handled this was by tracking which inputs slot into this specific case (part of a synthetic base, and get metadata mutations), and updateing the flat_fn() that we pass downstream to return these updated inputs as extra outputs. From the perspective of downstream logic, these are real user outputs, that it can treat like any other user outputs. aot_wrapper_synthetic_base will know to grab these extra outputs and use them to apply the metadata mutations.
This was pretty annoying, but has the benefit that all of that logic is encapsulated entirely in aot_wrapper_synthetic_base().
(2) input mutations are now performed on the synthetic base instead of the individual aliases.
You can see the original code comment here for details. We used to do the optimized thing in this case, and now we do the less optimized thing (copying the entire synthetic base, instead of the potentially smaller alias).
To be fair, we had no data showing that this optimization was showing improvements on any models in practice. I also think that the main reason anyone would ever run across this problem is because of a graph break - so if you care about perf, you probably want to avoid the extra graph breaks to begin with. I haven't added any warnings for this, but we probably could depending on what people think.
[ghstack-poisoned]
Station Trait: Spider Infestation (#73893)
Hate having your cables eaten by mice? Nanotrasen have heard your complaints and settled on a natural, organic, and eco-friendly solution.
When this station trait is active, roundstart and event mouse spawns have a chance to instead be replaced with duct spiders (both will exist, it doesn't remove mice). Duct spiders are largely harmless to humans, actively hunt other maintenance creatures (such as mice), and have only one tiny downside.
These mobs can also sometimes be spawned by a minor scrubber clog event.
As a side note, all spider basic mobs with AI (except Araneus) will now try to automatically fill a small area around them with webs.
Also I made it so that mobs will ignore their random_walking behaviour
if they're engaged in a do_after, just in case.
Adds a little bit of variety to things which can slightly annoy you in maintenance. Spiders will automatically make places they live in look like spiders live there.
🆑 add: A station trait which sometimes populates maintenance with small spiders. You can wear them as a hat if you wanted to have a spider on your head for some reason. add: Spider mobs will automatically start webbing up their environment. /🆑
comments.html: refactor so that something can be sanely changed in it
the comments.html template (along with submission.html) has numerous undesirable properties which i will describe now. unless you are very familiar with the codebase, it can be extremely difficult to grok.
this is pretty insane as there is nothing fundamentally complex about the goal of comments.html: return a component that shows a username and info, reports if any, comment content, and actions a user can take.
this behemeoth was initially 886 lines in the old version of this codebase, and this is with awards and a lot of other cruft removed. anyway, the maintainability of this file is about on par with some legacy application that keels over and dies if you sneeze vaguely in its direction.
the nicest thing i can say about it is that it isn't currently crashing.
anyway some of the problems include:
- large, splittable components, are not split into separate files.
this makes it incredibly difficult to find or make changes across the template and makes it nearly impossible to find or change a specific thing.
this is most easily exemplified in the modals, which should by all accounts be separate templates, just inlined into comments.html.
- the nesting is oftentimes incorrect.
inexplicably, probably out of laziness from when the code was first written, things will end up fully left aligned, while multiple layers deep into a nesting context.
if an if statement or an endif is changed, it is incredibly difficult to figure out where the error was. you can't trust the nesting.
- multiple repeated checks for things that are always true.
this is probably a symptom of the above two problems but it's very noticeable once you fix the nesting. for example there is a block near the very top of the actions bar which checks for parent_submission which effectively checks "is this in a post" (this commit won't complain about parent_submission checks but i do have opinions on those).
all of the action buttons further down the chain also check for parent_submission, or even check inconsistently (by using if c.post) within this context this is a completely unnecessary check in this context.
while it is potentially useful (and in fact because #251 requires we dismantle the assumption a little bit) to have these checks now, the fact that they were initially added shows that when the code was all initial written, there was little care into thinking about comment state.
- mobile actions are duplicated and duplicated inline.
i actually do find it probably pretty hard to support this normally given the codebase's DOM so whatever, duplicate the things, but if we're going to do that, inlining it into the middle of an incredibly long template is really difficult to comprehend as a design decision.
...anyway yeah this PR intends to fix these problems and enable work to be done on #251. this is a "perfect is the enemy of good" commit. it doesn't change much fundamental and is not intended to erase the sins of the original file, but at least make it maintainable.
this also fixes a minor bug with #473 where the GIF modal was left in by accident.
BACKPORT: signal: add pidfd_send_signal() syscall
The kill() syscall operates on process identifiers (pid). After a process has exited its pid can be reused by another process. If a caller sends a signal to a reused pid it will end up signaling the wrong process. This issue has often surfaced and there has been a push to address this problem [1].
This patch uses file descriptors (fd) from proc/ as stable handles on struct pid. Even if a pid is recycled the handle will not change. The fd can be used to send signals to the process it refers to. Thus, the new syscall pidfd_send_signal() is introduced to solve this problem. Instead of pids it operates on process fds (pidfd).
/* prototype and argument /* long pidfd_send_signal(int pidfd, int sig, siginfo_t *info, unsigned int flags);
/* syscall number 424 */ The syscall number was chosen to be 424 to align with Arnd's rework in his y2038 to minimize merge conflicts (cf. [25]).
In addition to the pidfd and signal argument it takes an additional siginfo_t and flags argument. If the siginfo_t argument is NULL then pidfd_send_signal() is equivalent to kill(, ). If it is not NULL pidfd_send_signal() is equivalent to rt_sigqueueinfo(). The flags argument is added to allow for future extensions of this syscall. It currently needs to be passed as 0. Failing to do so will cause EINVAL.
/* pidfd_send_signal() replaces multiple pid-based syscalls */ The pidfd_send_signal() syscall currently takes on the job of rt_sigqueueinfo(2) and parts of the functionality of kill(2), Namely, when a positive pid is passed to kill(2). It will however be possible to also replace tgkill(2) and rt_tgsigqueueinfo(2) if this syscall is extended.
/* sending signals to threads (tid) and process groups (pgid) */ Specifically, the pidfd_send_signal() syscall does currently not operate on process groups or threads. This is left for future extensions. In order to extend the syscall to allow sending signal to threads and process groups appropriately named flags (e.g. PIDFD_TYPE_PGID, and PIDFD_TYPE_TID) should be added. This implies that the flags argument will determine what is signaled and not the file descriptor itself. Put in other words, grouping in this api is a property of the flags argument not a property of the file descriptor (cf. [13]). Clarification for this has been requested by Eric (cf. [19]). When appropriate extensions through the flags argument are added then pidfd_send_signal() can additionally replace the part of kill(2) which operates on process groups as well as the tgkill(2) and rt_tgsigqueueinfo(2) syscalls. How such an extension could be implemented has been very roughly sketched in [14], [15], and [16]. However, this should not be taken as a commitment to a particular implementation. There might be better ways to do it. Right now this is intentionally left out to keep this patchset as simple as possible (cf. [4]).
/* naming */ The syscall had various names throughout iterations of this patchset:
- procfd_signal()
- procfd_send_signal()
- taskfd_send_signal() In the last round of reviews it was pointed out that given that if the flags argument decides the scope of the signal instead of different types of fds it might make sense to either settle for "procfd_" or "pidfd_" as prefix. The community was willing to accept either (cf. [17] and [18]). Given that one developer expressed strong preference for the "pidfd_" prefix (cf. [13]) and with other developers less opinionated about the name we should settle for "pidfd_" to avoid further bikeshedding.
The "_send_signal" suffix was chosen to reflect the fact that the syscall takes on the job of multiple syscalls. It is therefore intentional that the name is not reminiscent of neither kill(2) nor rt_sigqueueinfo(2). Not the fomer because it might imply that pidfd_send_signal() is a replacement for kill(2), and not the latter because it is a hassle to remember the correct spelling - especially for non-native speakers - and because it is not descriptive enough of what the syscall actually does. The name "pidfd_send_signal" makes it very clear that its job is to send signals.
/* zombies */ Zombies can be signaled just as any other process. No special error will be reported since a zombie state is an unreliable state (cf. [3]). However, this can be added as an extension through the @flags argument if the need ever arises.
/* cross-namespace signals */ The patch currently enforces that the signaler and signalee either are in the same pid namespace or that the signaler's pid namespace is an ancestor of the signalee's pid namespace. This is done for the sake of simplicity and because it is unclear to what values certain members of struct siginfo_t would need to be set to (cf. [5], [6]).
/* compat syscalls */ It became clear that we would like to avoid adding compat syscalls (cf. [7]). The compat syscall handling is now done in kernel/signal.c itself by adding __copy_siginfo_from_user_generic() which lets us avoid compat syscalls (cf. [8]). It should be noted that the addition of __copy_siginfo_from_user_any() is caused by a bug in the original implementation of rt_sigqueueinfo(2) (cf. 12). With upcoming rework for syscall handling things might improve significantly (cf. [11]) and __copy_siginfo_from_user_any() will not gain any additional callers.
/* testing */ This patch was tested on x64 and x86.
/* userspace usage */ An asciinema recording for the basic functionality can be found under [9]. With this patch a process can be killed via:
#define _GNU_SOURCE #include <errno.h> #include <fcntl.h> #include <signal.h> #include <stdio.h> #include <stdlib.h> #include <string.h> #include <sys/stat.h> #include <sys/syscall.h> #include <sys/types.h> #include <unistd.h>
static inline int do_pidfd_send_signal(int pidfd, int sig, siginfo_t *info, unsigned int flags) { #ifdef __NR_pidfd_send_signal return syscall(__NR_pidfd_send_signal, pidfd, sig, info, flags); #else return -ENOSYS; #endif }
int main(int argc, char *argv[]) { int fd, ret, saved_errno, sig;
if (argc < 3)
exit(EXIT_FAILURE);
fd = open(argv[1], O_DIRECTORY | O_CLOEXEC);
if (fd < 0) {
printf("%s - Failed to open \"%s\"\n", strerror(errno), argv[1]);
exit(EXIT_FAILURE);
}
sig = atoi(argv[2]);
printf("Sending signal %d to process %s\n", sig, argv[1]);
ret = do_pidfd_send_signal(fd, sig, NULL, 0);
saved_errno = errno;
close(fd);
errno = saved_errno;
if (ret < 0) {
printf("%s - Failed to send signal %d to process %s\n",
strerror(errno), sig, argv[1]);
exit(EXIT_FAILURE);
}
exit(EXIT_SUCCESS);
}
/* Q&A
- Given that it seems the same questions get asked again by people who are
- late to the party it makes sense to add a Q&A section to the commit
- message so it's hopefully easier to avoid duplicate threads.
- For the sake of progress please consider these arguments settled unless
- there is a new point that desperately needs to be addressed. Please make
- sure to check the links to the threads in this commit message whether
- this has not already been covered. */ Q-01: (Florian Weimer [20], Andrew Morton [21]) What happens when the target process has exited? A-01: Sending the signal will fail with ESRCH (cf. [22]).
Q-02: (Andrew Morton [21]) Is the task_struct pinned by the fd? A-02: No. A reference to struct pid is kept. struct pid - as far as I understand - was created exactly for the reason to not require to pin struct task_struct (cf. [22]).
Q-03: (Andrew Morton [21]) Does the entire procfs directory remain visible? Just one entry within it? A-03: The same thing that happens right now when you hold a file descriptor to /proc/ open (cf. [22]).
Q-04: (Andrew Morton [21]) Does the pid remain reserved? A-04: No. This patchset guarantees a stable handle not that pids are not recycled (cf. [22]).
Q-05: (Andrew Morton [21]) Do attempts to signal that fd return errors? A-05: See {Q,A}-01.
Q-06: (Andrew Morton [22]) Is there a cleaner way of obtaining the fd? Another syscall perhaps. A-06: Userspace can already trivially retrieve file descriptors from procfs so this is something that we will need to support anyway. Hence, there's no immediate need to add another syscalls just to make pidfd_send_signal() not dependent on the presence of procfs. However, adding a syscalls to get such file descriptors is planned for a future patchset (cf. [22]).
Q-07: (Andrew Morton [21] and others) This fd-for-a-process sounds like a handy thing and people may well think up other uses for it in the future, probably unrelated to signals. Are the code and the interface designed to permit such future applications? A-07: Yes (cf. [22]).
Q-08: (Andrew Morton [21] and others) Now I think about it, why a new syscall? This thing is looking rather like an ioctl? A-08: This has been extensively discussed. It was agreed that a syscall is preferred for a variety or reasons. Here are just a few taken from prior threads. Syscalls are safer than ioctl()s especially when signaling to fds. Processes are a core kernel concept so a syscall seems more appropriate. The layout of the syscall with its four arguments would require the addition of a custom struct for the ioctl() thereby causing at least the same amount or even more complexity for userspace than a simple syscall. The new syscall will replace multiple other pid-based syscalls (see description above). The file-descriptors-for-processes concept introduced with this syscall will be extended with other syscalls in the future. See also [22], [23] and various other threads already linked in here.
Q-09: (Florian Weimer [24]) What happens if you use the new interface with an O_PATH descriptor? A-09: pidfds opened as O_PATH fds cannot be used to send signals to a process (cf. [2]). Signaling processes through pidfds is the equivalent of writing to a file. Thus, this is not an operation that operates "purely at the file descriptor level" as required by the open(2) manpage. See also [4].
/* References */ [1]: https://lore.kernel.org/lkml/[email protected]/ [2]: https://lore.kernel.org/lkml/[email protected]/ [3]: https://lore.kernel.org/lkml/[email protected]/ [4]: https://lore.kernel.org/lkml/[email protected]/ [5]: https://lore.kernel.org/lkml/[email protected]/ [6]: https://lore.kernel.org/lkml/[email protected]/ [7]: https://lore.kernel.org/lkml/[email protected]/ [8]: https://lore.kernel.org/lkml/[email protected]/ [9]: https://asciinema.org/a/IQjuCHew6bnq1cr78yuMv16cy [11]: https://lore.kernel.org/lkml/[email protected]/ [12]: https://lore.kernel.org/lkml/[email protected]/ [13]: https://lore.kernel.org/lkml/[email protected]/ [14]: https://lore.kernel.org/lkml/[email protected]/ [15]: https://lore.kernel.org/lkml/[email protected]/ [16]: https://lore.kernel.org/lkml/[email protected]/ [17]: https://lore.kernel.org/lkml/CAGXu5jL8PciZAXvOvCeCU3wKUEB_dU-O3q0tDw4uB_ojMvDEew@mail.gmail.com/ [18]: https://lore.kernel.org/lkml/[email protected]/ [19]: https://lore.kernel.org/lkml/[email protected]/ [20]: https://lore.kernel.org/lkml/[email protected]/ [21]: https://lore.kernel.org/lkml/[email protected]/ [22]: https://lore.kernel.org/lkml/[email protected]/ [23]: https://lwn.net/Articles/773459/ [24]: https://lore.kernel.org/lkml/[email protected]/ [25]: https://lore.kernel.org/lkml/CAK8P3a0ej9NcJM8wXNPbcGUyOUZYX+VLoDFdbenW3s3114oQZw@mail.gmail.com/
Cc: "Eric W. Biederman" [email protected] Cc: Jann Horn [email protected] Cc: Andy Lutomirsky [email protected] Cc: Andrew Morton [email protected] Cc: Oleg Nesterov [email protected] Cc: Al Viro [email protected] Cc: Florian Weimer [email protected] Signed-off-by: Christian Brauner [email protected] Reviewed-by: Tycho Andersen [email protected] Reviewed-by: Kees Cook [email protected] Reviewed-by: David Howells [email protected] Acked-by: Arnd Bergmann [email protected] Acked-by: Thomas Gleixner [email protected] Acked-by: Serge Hallyn [email protected] Acked-by: Aleksa Sarai [email protected]
(cherry picked from commit 3eb39f47934f9d5a3027fe00d906a45fe3a15fad)
Conflicts: arch/x86/entry/syscalls/syscall_32.tbl - trivial manual merge arch/x86/entry/syscalls/syscall_64.tbl - trivial manual merge include/linux/proc_fs.h - trivial manual merge include/linux/syscalls.h - trivial manual merge include/uapi/asm-generic/unistd.h - trivial manual merge kernel/signal.c - struct kernel_siginfo does not exist in 4.14 kernel/sys_ni.c - cond_syscall is used instead of COND_SYSCALL arch/x86/entry/syscalls/syscall_32.tbl arch/x86/entry/syscalls/syscall_64.tbl
(1. manual merges because of 4.14 differences 2. change prepare_kill_siginfo() to use struct siginfo instead of kernel_siginfo 3. use copy_from_user() instead of copy_siginfo_from_user() in copy_siginfo_from_user_any() 4. replaced COND_SYSCALL with cond_syscall 5. Removed __ia32_sys_pidfd_send_signal in arch/x86/entry/syscalls/syscall_32.tbl. 6. Replaced __x64_sys_pidfd_send_signal with sys_pidfd_send_signal in arch/x86/entry/syscalls/syscall_64.tbl.)
Bug: 135608568 Test: test program using syscall(__NR_pidfd_send_signal,..) to send SIGKILL Change-Id: I34da11c63ac8cafb0353d9af24c820cef519ec27 Signed-off-by: Suren Baghdasaryan [email protected] Signed-off-by: electimon [email protected]
Error handling
oh god, C. I'm preventing accidentally wrapping and it still takes negatives so that's good but the conversion x_x There's probably a library function that does what I want but I did it myself so I'm pretty happy with that. C, my love, you're beautiful, but occasionally very annoying
chore: switch to yarn v3 (#1752)
NPM got somehow broken more than usual and its no longer possible to install the dependencies in CI. We were struggling with NPM for quite some time (especially after we moved to turborepo). I’ve been advocating for yarn since my first days here, been using it for last ~5 years on a daily basis and it never did anything wrong to me, so I hope this will be the right step and a smooth transition for all the collaborators.
What to expect? Since we require node 16, we can leverage corepack, a
new tool shipped with newer node versions (btw developed by yarn
maintainers). This means you just need to run corepack enable and yarn
should be available in your workspace. In case of some problems, you can
try running corepack prepare yarn@stable --activate, but it shouldn’t
be needed. Note that we use corepack instead of commiting yarn binary
to the git repo - that is the reason why .yarn folder is gitignored.
Initially we will start with a conservative setup, using a node linker,
so there will be the good node_modules folder we are all used to. I’d
like to experiment with the advanced features as well, mainly in the
project templates, as it could greatly improve the build times (we could
even skip the install step completely).
With that said, we will be still using NPM inside our E2E tests, to be
sure the project can be safely installed with NPM. This change should
affect only the collaborators, not our users. Ideally we should test
other package managers via CI too, so we are sure pnpm works as well,
or maybe even bun.
Few API differences and quality of life improvements yarn brings:
npm install->yarnnpm install xxx->yarn add xxxnpm run ...->yarn …npx …->yarn …- no need to deal with the
--issue fromnpm run(propagating CLI params to the script) - powerful caching and sane lockfile format
lamp system that hurts my fucking head
god unreal is so annoying sometimes
[SDPA] Add an optional scale kwarg (#95259)
This PR adds an optional kwarg to torch torch.nn.functional.scaled_dot_product_attention() The new kwarg is a scaling factor that is applied after the [email protected] step of the computation. Made updates to the efficient kernel to support but flash and math were minimally updated to support as well.
Will reduce the complexity of: #94729 and has been asked for by a couple of users.
- As far as I know I did this the correct way and this both BC and FC compliant. However I always seem to break internal workloads so I would love if someone can advice I did this right?
- I named the optional arg 'scale'. This is probably dumb and I should name it 'scale_factor'. I will make this change but this is annoying and it will require someone thinking we should rename.
- 'scale' is interpreted as
[email protected] * (scale)
Pull Request resolved: pytorch/pytorch#95259 Approved by: https://github.com/cpuhrsch
Mashes several of the Whitesands Survivor Camp ruins into one extra large ruin (#1640)
Combines the whitesands surface camp adobe, farm, gunslingers, survivors, hunters and saloon into one massive, 59x59 ruin. Some various extra loot and changes have been made throughout, generally to improve the experience of digging through the trash for goodies. Changes the riot shotgun in the saloon to a double barrel shotgun. Also cleans up the various issues with the ruins, like walls under doors, or area passthroughs being used excessively over the outside of the ruins, resulting in them generating in the middle of mountains buried in the rock.
"Well, why didn't you add the drugstore?" The loot in it was too good. The stuff in there can really help a ship get on its feet, and I am not gonna deprive them of that just to shove it in an already packed massive ruin area. I'm not saying it doesn't need its own remap, just that it doesn't fit well with the other camps put into this ruin.
- I affirm that I have tested all of my proposed changes and that any issues found during tested have been addressed.
"a ruin that is tiny and sucks on purpose is still bad" and holy shit did most of the camps fit this criteria. Survivor, Gunslinger, and Hunter camp variants were the smallest ruins in the game next to the one that was just a single tumor, and constantly took up entire map generations just to be a massive dissapointment to any player that came across them. Or they would spawn in the middle of an acid lake. Either way this ruin is massive and should provide a breath of fresh air for scavengers and combat hungry miners alike.
Ingame, two pics due to view range not being large enough to get the
full thing at a good quality.
🆑 add: whitesands_surface_camp_combination, a survivor village comprised of smaller revamped whitesands camps all packaged in one ruin. can be found in the map catalogue. del: whitesands_surface_camp adobe, farm, gunslingers, survivors, hunters and saloon, for being tiny ruins that suck. /🆑
Co-authored-by: Bjarl [email protected]
Post-Revolutionary Fervor station trait, revolutionary bedsheets, and a megaphone (#73799)
Upon revolution success, the chosen headrev will now also receive a megaphone, and a "revolutionary bedsheet" repurposed from a stolen CC bedsheet to commemorate their success. The post-revs confusion and lack of command/security usually leads to an instantaneous, total breakdown in cohesion. It's every man for himself -- that's no way to run a commune! Just because the revolution has succeeded and nobody can see your big blue "R" anymore doesn't mean you can't be a leader!
This also adds a new revolution-themed negative station trait -- Post-Revolutionary Fervor. When present, this trait trashes the command areas at the start of the round. This means cracked windows, broken consoles, vendors getting knocked over, and the occasional dead greytider.
If you start cleaning at the start of the round, you might finish right as the next batch of revs decides to crop up.
Giving one of the headrevs a bigger voice and a cool cape (or uncool, depending on how you view the sprite) means that there's a chance for them to step up and try to keep the wheels on. Just remember -- Nobody is obligated to actually listen to this person, it's just a bedsheet.
Adds a neato station trait, which probably counts as command gameplay content.
🆑 Rhials add: The headrev who receives the revolutionary banner after a win will also receive a commemorative bedsheet and megaphone. add: Post-Revolutionary Fervor station trait. I hope you enjoy fixing broken computer screens. spriteadd: A revolutionary bedsheet. /🆑
stupid ass conflicts
how the fuck does it even work
Adds Just Like, a Ton of Clothes (#5048)
- Adds a wide array of clothes, listed below.
- My good friend Tech provided me with some sprite sheets when I was working on Ashlanders, requesting a hobo coat. Going through the sheets I found several different items I thought it would be fun to add to our expanding list of customization and fashion options. The list is huge so I'm just gonna itemize it here. As for attributions, as I understand it most of this is from a D&D server, and some from a 40k server.
- Two of the outfits, the Belial and Lilin items, are sprites crafted by our very own Doopy, as part of their Lindenoak line!
Costume Vendor
- Banana Costume
- Hashashin Costume
- Bard Hat
- Aquiline Enforcer Uniform
- Scavenging Sniper Set
- Spiral Hero Outfit
- Body Tape Wrapping
- Redcoat Uniform
- Despotic General Uniform
- Post-Revolution American Uniform
- Prussian Uniform
Suit Vendor
- Ragged Coat
- Spiral Hero Cloak
- Nerdy Shirt
Jumpsuit Vendor
- Toga
- Countess Dress
- Baroness Dress
- Revealing Cocktail Dress
- Belial Striped Shirt and Shorts
- Lilin Sash Dress
Shoes Vendor
- Utilitarian Shoes
Loadout
- Ragged Coat
- Spiral Hero Cloak
- Nerdy Shirt
- Bard Hat
- Utilitarian Shoes
- Toga
- Countess Dress
- Baroness Dress
- Scavenging Sniper Set
- Spiral Hero Outfit
- Body Tape Wrapping
- Revealing Cocktail Dress
- Belial Striped Shirt and Shorts
- Lilin Sash Dress
Medieval Armor Supply Crate
- Crimson Knight Armor
- Forest Knight Armor
- Hauberk
- Elite Paladin Armor, Helmet, and Boots
- Alternate Knight Helmet
Cryosuit Supply Crates (Under Voidsuit Menu)
- Cryosuit, Variants: Security, Engineering, Atmos, Mining
Crafting Menu
- Duraskull Helmet
Ashlander Specific Crafting Menu
- Ashen Vestment
- Ashen Tabard
Ashlander Spawn
- Priests now spawn with the Ashen Vestment.
Admin Spawn
- Actual armored versions of all new Knight sets.
- Utilitarian Military Helmet, Armor, and Boots.
🆑 add: Adds a wide array of new clothing items. Itemized in PR. #5408 /🆑
LICENCE
DO WHAT THE FUCK YOU WANT TO PUBLIC LICENSE
Version 2, December 2004
Copyright (C) 2004 Sam Hocevar [email protected]
Everyone is permitted to copy and distribute verbatim or modified copies of this license document, and changing it is allowed as long as the name is changed.
DO WHAT THE FUCK YOU WANT TO PUBLIC LICENSE
TERMS AND CONDITIONS FOR COPYING, DISTRIBUTION AND MODIFICATION
- You just DO WHAT THE FUCK YOU WANT TO.
RFC on the auto-arch and bininfo stuff
Rough idea/implementation of where I was thinking of going with this. Thoughts?
There are three main additions here:
In r2, you can now get the results of the iI command. Or at least the fields that I thought were useful for now.
In elf, the results of the above are broken into two fields and added to the class' API. elf.bininfo and elf.security are another private inner types that allow you to access the info as attributes and have special repr.
In arch, there is now a lookup_arch() function that retrieves one of the preconfigured Archs based on a tuple of arch_string, wordsize, and endianness from elf.bininfo. Elf automatically calls this on construction and stores the result in elf.arch.
In order to facilitate the lookup dict without having to respecify the Arch entries, I moved some things around and am doing some somewhat gross shit with importlib. On the bright side, I can now move the preconfigured Arch definitions to the top of the file.
[FIX] stock,purchase,mrp: accumulative security days
Usecase to reproduce:
- Set the warehouse as 3 steps receipt
- Put a security delay of 3 days for purchase
- Set a product with a vendor and 1 days as LT
- Replenish with the orderpoint
You expect to have a schedule date for tomorrow that contains all the product needed in the incoming 4 days.
Currenly the internal transfer from QC -> Stock is for tomorrow (ok). The transfer from Inpur -> QC is plan for 2 days in the past. (not ok) The PO date is plan for 5 days in the past. (not ok)
It happens because the system check at each stock.rule application if
purchase is part of the route. If it's then it applies the security lead
time. It's a mistake because we should apply it only the first time.
To fix it we directly set it when the orderpoint run and not during
stock.move creation.
However for MTO it's not that easy. We don't want to deliver too
early the customer. So we keep applying the delay during the
stock.move creation but only when it goes under the warehouse stock
location.
X-original-commit: 97f52bd40d97109a7983549d252476959ddceada Part-of: odoo/odoo#112325
module01 finished. Not gonna delete comments fuck you
Update README.md
Welcome to the XAMPP root directory index page!
We've created a visually appealing user interface that will auto sense any projects and directories created within the root page of your XAMPP server. Our index file replaces the vanilla XAMPP server index page, providing you with a more interactive and efficient way to manage your projects.
With our customized UI, you can easily navigate through your projects and directories, quickly find the files you need, and manage your server more effectively. We understand the importance of having an organized workspace, and our index page helps you achieve just that.
Our index page is designed to be user-friendly and intuitive, making it easy for beginners and experienced developers alike. We've incorporated a responsive design, so you can access it on any device, whether you're on your desktop computer or mobile phone.
We're confident that our XAMPP root directory index page will enhance your development experience and streamline your workflow. Try it out today and let us know what you think!
Makefile.lib: Lower kernel gzip compression to fastest
You're reading this - so you're trying to understand "JUST WHY OMG". That's already a good step.
First of all, this is a downstream kernel - always keep that in mind! Now, this kernel is targeting new very powerful Qualcomm platforms like SM8250 and the Sony Edo platform - which has a very fast UFS card.
Keep in mind that the bootloader sets the CPU at a frequency that is slightly faster than the "in the middle" ones, which is anyway not veeeery fast - but that's good, really. I agree.
So.. check this out: for Image.gz-dtb..... COMP_LEVEL SIZE 9 20116171 5 20220479 2 20940223 1 21231290
Remember again that we're loading from a UFS card and that we are loading ~1.1MB more out of a 20MB file. If you're smart enough you surely know already about RAM and CPU overhead of very high compression levels.
If you still disagree with what I just did, read this commit description another 20 times, or more, until you understand it. :)))
Signed-off-by: Tiktodz [email protected]
Fixed stupid Gazebo bullshit
To make it really simple, Gazebo has problems. Robot was turning slower than it should and that caused SLAM to diverge. That problem is now fixed but a shameful trick was used to achieve this.
power: Introduce OnePlus 3 fingerprintd thaw hack
Taken from Oneplus 3, this hack will make fingerprintd recover from suspend quickly.
Small fixes for newer kernels since we're coming from 3.10.108..
Change-Id: I0166e82d51a07439d15b41dbc03d7e751bfa783b Co-authored-by: Cyber Knight [email protected] [cyberknight777: forwardport and adapt to 4.14] Co-authored-by: Tashfin Shakeer Rhythm [email protected] [Tashar02: forwardport and adapt to 4.19 and xiaomi_sdm660's fp] Signed-off-by: Shreyansh Lodha [email protected] Signed-off-by: Pierre2324 [email protected] Signed-off-by: PainKiller3 [email protected] Signed-off-by: Dhruv [email protected] Signed-off-by: Cyber Knight [email protected] Signed-off-by: Tashfin Shakeer Rhythm [email protected] [ hridaya: Adapt for xiaomi_gauguin's fp ] Signed-off-by: hridaya [email protected]
Consolidates some XSS under hivecore (#2738)
Spawn pool and evo pods are removed and their functionality is umbrella'd under the hive core. Sprites still exist though.
"Roleplay" has become an increasingly more popular and touchy subject within the community as of recently. I, wholeheartedly agree, that roleplay is an important aspect of the game, and there are ways to improve it. One of these ways is through immersion. In this MR, it is intended to increase player immersion.
One of the most memorable and haunting scenes in Aliens was when they reached the hive and they found the bodies. This very unique and cinematic scene was often able to be replicated in CM, with the marines busting open the hive and finding all the chestbursted bodies of their comrades. Roleplaying this out was commonplace. "Dear God... what did they do to you..." or acting out in disgust are just a few of the many ways having bodies in the hive positively impacted the game.
XSS was a failed attempt at spicing up the xenomorph gameplay loop at the expense of immersion and should be at least somewhat reverted while keeping balance in mind. A brief discussion with many prominent xenomorph players, including those most experienced in queen, have not particularly expressed favor to XSS either.
To start, let us remember why XSS (xeno special structures - hive core, evo pods, morpher, pool, etc) was added.
https://docs.google.com/document/d/19_zDUmLdxpUzxj-GuWu7F4bSj4zBYzmZ39s_N5X7kQ0/edit
- This is the original development document for XSS. Let us examine the major points: 1.Introduce a way for Xenomorph players to recycle - This idea was never reached.
2.Reduce Xenomorph attrition - Grand objective was unsuccessful. Very little changed.
- Offer new avenues of play "by reducing the punishment of xenos dying"
- This never happened. Dying was still just as punishing, especially with facehug nerfs.
The spawn pool - The idea of the spawn pool was successful and has remained unchanged since. I would argue, however, it is not immersive. Xenomorphs do not have bright, glowing, acidic pools in their hives. (Yes I know there was a comic with a pool, and this is not how it was used)
Egg Morpher - These used to be TURRETS. They are no longer turrets, and their sprites have been broken for almost 4 years (the bodies put inside of them used to show their face in the little purple part) They are currently defunct facehugger reservoirs. I am in favor of removing them, but I would argue that is a balance issue (number of huggers in play)
Evolution Pod - It was intended for these to be able to be eaten in order to evolve. They haven't done this for years. Why do we still have them? They take up 18 spaces of precious hive weeds, provide light, (xenomorphs HATE light) and wherever a hive core is built, these are also built. We can just merge them with the hive core because there is no reason to have them anymore.
This PR currently completely removes the spawn pool and evolution pod from gameplay, while reimagining their functions for current balance. This PR is not intended to change balance in any way.
All functionality from the spawn pool in regards to "pooled" larva has been given to the hive core, and they are now called "burrowed" larva. Chestbursts now give two larva, this is to be kept with current balance of two xenos per capture.
Evopod functionality and evolution speed boost was merged with the hive core.
n/a
🆑 TheDonkified del: Evo pods and spawn pool are removed. add: Hive core directly affects evolution speed and is where burrowed larva spawn from now on. /🆑
Co-authored-by: Morrow [email protected] Co-authored-by: harryob [email protected]
hash-object: use fsck for object checks
Since c879daa237 (Make hash-object more robust against malformed objects, 2011-02-05), we've done some rudimentary checks against objects we're about to write by running them through our usual parsers for trees, commits, and tags.
These parsers catch some problems, but they are not nearly as careful as the fsck functions (which make sense; the parsers are designed to be fast and forgiving, bailing only when the input is unintelligible). We are better off doing the more thorough fsck checks when writing objects. Doing so at write time is much better than writing garbage only to find out later (after building more history atop it!) that fsck complains about it, or hosts with transfer.fsckObjects reject it.
This is obviously going to be a user-visible behavior change, and the test changes earlier in this series show the scope of the impact. But I'd argue that this is OK:
-
the documentation for hash-object is already vague about which checks we might do, saying that --literally will allow "any garbage[...] which might not otherwise pass standard object parsing or git-fsck checks". So we are already covered under the documented behavior.
-
users don't generally run hash-object anyway. There are a lot of spots in the tests that needed to be updated because creating garbage objects is something that Git's tests disproportionately do.
-
it's hard to imagine anyone thinking the new behavior is worse. Any object we reject would be a potential problem down the road for the user. And if they really want to create garbage, --literally is already the escape hatch they need.
Note that the change here is actually in index_mem(), which handles the HASH_FORMAT_CHECK flag passed by hash-object. That flag is also used by "git-replace --edit" to sanity-check the result. Covering that with more thorough checks likewise seems like a good thing.
Besides being more thorough, there are a few other bonuses:
-
we get rid of some questionable stack allocations of object structs. These don't seem to currently cause any problems in practice, but they subtly violate some of the assumptions made by the rest of the code (e.g., the "struct commit" we put on the stack and zero-initialize will not have a proper index from alloc_comit_index().
-
likewise, those parsed object structs are the source of some small memory leaks
-
the resulting messages are much better. For example:
[before] $ echo 'tree 123' | git hash-object -t commit --stdin error: bogus commit object 0000000000000000000000000000000000000000 fatal: corrupt commit
[after] $ echo 'tree 123' | git.compile hash-object -t commit --stdin error: object fails fsck: badTreeSha1: invalid 'tree' line format - bad sha1 fatal: refusing to create malformed object
Signed-off-by: Jeff King [email protected] Signed-off-by: Junio C Hamano [email protected]
... so actually, we all have the cough.
One thing that helped regaining some energy was the IGORRR concert last night. I think this fusion between metal and electronic breakbeat is just taking off. Oh, there is also a lot of opera singing in this tour. One interesting thing to see was the actual crowd of people. I've counted about 3 to 4,000 people, most of them probably coming for Igorrr, while the support bands like Amenra or "Freiheit" would normally attract metal-headz only, you know, those dark long-haired creatures that only come to death metal concerts and are never to be seen anywhere else. So, there where a couple of them to be recognized but all in all the crowd was a nice mixture of fans of multiple genres. And! The Igorrr guy could have played two hours more of jungle rythms at the end because the excitement was just exploding through the roof. Well, it wasn't possible of course because the venue has a clear contract and staff wants to go to sleep at some point. Very interesting in any case.
MagiFields are here! ↓ 🎨 ⚙️ 💔 🌐
- Collection level:
- to_magifields
- fields_class
- List view:
- ordering_fields_class
- table_fields_class
- to_magifields
- to_magi_ordering_fields
- to_magi_table_fields
- Deprecated:
- to_fields, ordering_fields, table_fields
- Item view:
- fields_suggest_edit
- to_magifields
- Comments and Share buttons are now part of buttons_per_item
- Deprecated:
- only_show_buttons in URL
- Collections migrated to MagiFields:
- Accounts: uses MagiLeaderboardPositionModelField
- Prizes: uses MagiICharacterModelField
- Fields itemview uses flexbox
- YouTube videos now show a thumbnail before loading and when the video is in a different language from English, it's gonna load the subtitles in that language (when available)
Faster loading of queries:
- Prefetch_together items:
- in item view only
- by limiting # of items loaded to: how many will be displayed + 1
- doesn't work for account item view as it's always loaded within user item view
- not loaded in high traffic mode (when logged out)
- Add/edit view:
- get_queryset gets called to make sure there's no N+1 issue when showing model choice selectors
Tab item view:
- display_style_table_show_open_button now defaults to True
Alt views:
- Alt views get "loaded" on startup (when magicollections get initiated):
- turned into OrderedDict
- Choices and visible choices get cached
- Alt views get added for collections set in FAVORITE_CHARACTERS_MODEL, OTHER_CHARACTERS_MODELS or BACKGROUNDS_MODEL
- Views with display_style "table" are now displayed using flex-box instead of table elements
Magicollections:
- New base class CommunityMainItemCollection, for magicollections expected to get filled by the community (smaller sites), as well as CommunitySubItemCollection and CommunityBaseEventCollection
- Utils makeCollectionCommunity
- New utils in views: has_method_been_overridden, uses_deprecated_to_fields, notTranslatedWarning
- show_item_buttons_as_icons now defaults to True
view_iconcan be set for each view. they're currently used in staff page "collections" and in buttons to add/edit.- List view:
- new method check_random_permissions
- deprecated: plain_default_ordering_list and plain_default_ordering
- deprecated: show_owner in request.GET
- Rewrite of ListView
- Parameters (request.GET or given to view function) wrapped in MagiQueryDict, allowing to handle both QueryDict and dict and wrapping the work of having multiple values, as well as determining wether the form was filled or not (ignoring known GET parameters not used in filters)
- ItemView:
- New option: show_owner
- New option: share_templates (Twitter/Instagram copy-pastable templates for community managers)
Forms:
requestmay not be set in your form, so your code needs to handle that- YouTubeVideoField now has modestbranding on and will suggest videos from the same channel only (at the end of the video playing)
Filter forms:
- Form will be instanciated on startup (when initializing collection objects) in order to cache some settings like suggest edit choices and filter details
- so they now need to work when request=None. it will crash on startup if request is used without checking if it's not None, making it easy to debug this change
- Presets:
- Presets now handle lists of values (ex: multiple activities tags!)
- When someone uses the sidebar to search/filter, if the selected filters match a preset, then it will redirect to that preset, adding a nice header + helps with SEO
- If a URL contains some filters but not all, the missing filters will be filled with default values (previously: empty value, which was an issue for activities for example)
- New utility method: foreach_merge_fields
- When filtering by foreign keys, multi-level relationships now work too ("__")
- Merged filters:
- Filters get unified. Ex: i_unit_i_subunit. If i_unit=3, then i_unit_i_subunit will be set to i_unit-3, and vice-versa
- The merged filters themself are now noop filters, and it's the original filters that do the work of filtering
- They now work with presets! (make sure your preset refers to the original field, not the merged field)
- Ordering fields show up right under search field (feedback that the "more" sections were assumed to be opened because of that field)
- New setting: ordering_show_relevant_fields (specify which fields to show, or [] for none)
Website settings:
- New settings: BACKGROUNDS_MODEL, BACKGROUNDS_FILTER, HAS_MANY_BACKGROUNDS, SHOW_BACKGROUND_NAME_ON_SELECTION, MAX_CACHED_BACKGROUNDS
- New settings: MANY_CHARACTERS_THRESHOLD, HAS_MANY_FAVORITE_CHARACTERS
- New settings: FEEDBACK_FORM_ANSWERS, EVENT_FEEDBACK_FORM, EVENT_FEEDBACK_FORM_ANSWERS, EVENT_PRIZES_FORM, EVENT_PRIZES_FORM_ANSWERS
Local settings:
- New: DEBUG_SHOW_QUERYSET, DEBUG_SHOW_MAGIFIELDS, DEBUG_SHOW_MAGIFIELDS_LIST
SEO:
- Json Ld now used on item view pages to describe the content of the page
- FAQ (Q&A style section for item views)
- Article (for activities + most items)
- Videos (if any YouTube video is linked)
Settings page:
- If there are too many backgrounds, instead of selecting your background from a modal popup, you'll have to select it from a separate section of the settings page. This section will link to the backgrounds page itself, with a special view that shows buttons to set a background.
- Default: 30 backgrounds. Can be changed with
MANY_BACKGROUNDS_THRESHOLD. If you want to always set from the background view, then you can set HAS_MANY_BACKGROUNDS to True.
- Default: 30 backgrounds. Can be changed with
- If there are too many characters that can be set as favorite, instead of selecting your favorites from a modal popup, there will be a separate section in the settings page that allows you to view and set your favorite characters. When you set your favorite characters, it actually opens the collection list view instead, with a special view that shows buttons to set as favorite. This works for both the main "FAVORITE_CHARACTERS" (as long as you set FAVORITE_CHARACTERS_MODEL) and any "OTHER_CHARACTERS" you set up.
- For FAVORITE_CHARACTERS: Default: 30 characters. Can be changed with MANY_CHARACTERS_THRESHOLD. If you want to always set from the list view regardless of how many characters there are, you can set HAS_MANY_FAVORITE_CHARACTERS to True.
- For OTHER_CHARACTERS: Default: value of MANY_CHARACTERS_THRESHOLD, which is 30. Can be changed by setting
many_thresholdin your dict that sets up the other characters setings. To show regardless of how many, you can sethas_manyin your dict.
- New link option: linktree
- Staff and contributors can now update their settings directly from the settings page (mostly translators languages)
Item model classes:
- New util: d_unicodes
- New setting can be set to True: IS_PERSON
- Caches:
total_caches don't needto_cachemethods, automatically retrieve total
- Can set {}AUTO_IMAGES to i, c_ and d_ fields to show an image. Can also specify: {}_AUTO_IMAGES_FROM_I to use int values and {}_AUTO_IMAGES_FOLDER to specify the folder name.
Suggest edit:
- suggest_edit_choices are now cached on startup (when initializing collection objects)
Utils:
- Global:
- failSafe
- recursiveCall
- isFullURL, getDomainFromURL
- hasValue
- getValueIfNotProperty
- validNullBoolOptions
- classproperty
- isRequestAjax
- getSiteName
- mergeDicts
- Collections / Models / items / queryset:
- getOwnerFromItem, getAddressFromOwner, getTwitterFromOwner
- getDescriptionFromItem
- getMagiCollectionFromModel
- reverseOrdering, reverseOrderingString, plainOrdering
- getAllModelRelatedFields
- fieldNameMatch
- getListURL, isPreset, unifyMergedFields
- prepareCache, will recursively transform any unsupported type into unicode, ensuring it never crashes
- getRelatedItemFromItem, getRelatedItemsFromItem, getVerboseNameOfRelatedField, getFilterFieldNameOfRelatedItem
- getAllModelFields, getAllModelRelatedFields
- getRelOptionsDict, setRelOptionsDefaults, getMaxShownForPrefetchedTogether
- getQuerysetFromModel
- getColOffset
- suggestFlaticonFromFieldName
- baseButton
- makeCollectionCommunity
- Translations (team A):
- Format translated strings using
__. Ex: __(('Hello, {username}!'), username=('Anonymous')) - Lowercase translated strings using
lowerTranslation. Ex: lowerTranslation(_('Cards')) - Join translated strings using
joinTranslation. Ex: joinTranslation([ _('A'), _('B'), ... ], separator=' ') - Translated name from an item or dict with
name+names(or other field names) withgetTranslatedNameLazy. Ex: getTranslatedNameLazy({ 'name': 'Maria', 'names': { 'ja': u'マリア' } }, language='ja') - getRomajiWithFallback
- getLanguageImage
- notTranslatedWarning
- Format translated strings using
- Characters / Badges:
- isValidCharacterPk, isValidCharacterNth, getCharacterEnglishNameFromPk, getCharactersHasMany, getCharactersKeys, getCharactersOtherExtraKey
- getCharactersUsersFavorites, isCharactersUserFavorite, setCharactersUserFavorite, unsetCharactersUserFavorite
- getMedalImage
- Seasons:
- adventCalendar now checks for date server-side too (not just client-side only)
- New utils: getAllCurrentSeasons, getValueInSeason, getVariableInSeason
- Json Ld:
- jsonLd, FAQjsonLd, articleJsonLd, authorJsonLd, articleJsonLdFromActivity, articleJsonLdFromItem, videoJsonLd
- Social media:
- tweetLength
- isTweetTooLong
- Database migration:
- Renamed:
- duplicate_translation → duplicateTranslations
- find_all_translations → findAllTranslations
- googleTranslateFixLanguage → rfc3066ToIso6392
- Updated:
- getEventStatus now works if you compare dates with date times
- listUnique new parameter: remove_empty=False
- addParametersToURL now works with anchors (keeps existing anchor if any, replacing it if given)
- redirectWhenNotAuthenticated now checks if request is None
- Rewrite of getModelOfRelatedItem
- formFieldFromOtherField now also copies MagiCircles specific values (in FORM_FIELDS_EXTRA_VALUES)
- newOrder works with dict and allows to add dict values when missing, with option insert_in_dict_when_missing.
- newOrder also allows
orderwith a list of keys (useful for dicts!) - csvToDict does't crash when a title is missing in the row (one row shorter for ex)
- makeBadgeImage takes either badge or badge_image + badge_rank
- staticFileURL/staticImageURL more permissive: only path required
- getColSize works with per_line = 8
- Deprecated:
- toCountDownField, eventToCountDownField
Javascript:
- better loading of countdown, timeago, timezone, markdown, githubwiki,
- Better loading of next pages with pagination: will append tables to avoid having tables with different width columns
- when you open a modal:
- it always shows the top of the modal
- tooltips get hidden properly
- when you close a modal:
- audio stops playing (if any in-modal audio)
Staff only changes:
- Collections view is prettier with "view_icon" displayed next to the links to the view
- edit_staff_status deprecated (the only way to change staff status is to set roles)
- Managers and desginers are now allowed to upload 2x
- New roles: Developer (Main), Wiki editor, Community entertainer (prizes)
- On profile, the button to edit user is now divided in multiple separate form depending on what you're trying to edit:
- Mark e-mail address invalid
- Edit roles
- Edit donator status
- And a separate form only accessible from reports, when you're editing a user that has been reported. It's separated in 2 forms: one for description, location and force remove avatar, and one for username/email
- When ordering users or accounts by most popular, will show reputation points ()
- Reports: can't lookup reports by staff (too heavy query)
- Profiles now show icons of staff roles under the avatar
Other:
- Link to "Contact us" in navbar (links to about page with anchor)
- Activities titles (for SEO and social media share) is now auto-retrieved from h1 to h5 titles
- fix bug with share_url in base account (was not a property)
- Add labels to _cache_leaderboard (now used)
- Tried my best to make sure untranslated strings show up with a warning in DEBUG mode so that developers notice it (mostly for model field names)
- post_news given to Managers as well
- icon_for_prefetched deprecated (not used by any site anyway)
- Dump model data for local import: make sure it doesn't print out useless things
- List of contest participants: new option --print-table
- CSS: new classes col-XX-special-8 and col-XX-offset-special, where XX is the size (xs, sm, md, lg), new class nowrap, new class padding5, stripes on staff-only stuff
- Better SEO tags in base header
- Remove Maji Love from list of sites
- Events now use new MagiFields stuff
- Bug fix: when ko-fi doesn't get loaded, don't crash
- Translations: Facebook/Reddit/Twitter/Instagram/YouTube are now translatable
- Bug fix: Markdown help text doesn't open in the same modal if the current form has been opened in a modal
- Rename website → app
- Rewrote default introduction (about page)
- Various bug fixes
Breaking changes:
New signature for:
-
MagiCollection.get_queryset(self, view=None, queryset=None, parameters={}, request=None):
-
All views get_queryset(self, queryset=None, parameters={}, request=None): This means we should be able to call
some_collection.get_queryset()without it failing because it relied on queryset, parameters or request. -
requestmay not be set in your form, so your code needs to handle that
"Act like a human"
This prompt makes chatGPT act like a human. Sometimes it's better to receive like-a-human answers instead of stuffy complicated texts. This is also useful because such smart texts are obviously generated by artificial intelligence, and prompt "Act like a human" allows one to get texts similar to human ones.
There are some simple examples:
-
Question: "What color is the sky?"
-
ChatGPT: "The color of the sky can vary depending on different factors such as the time of day, weather conditions, and geographic location. During the day, the sky is usually blue, but it can sometimes appear gray or even red during sunrise or sunset. At night, the sky is dark, but it can be illuminated by the moon and stars."
-
"Act like a human" prompt: "Blue."
-
Question: "Why is the grass green?"
-
ChatGPT: "Grass appears green to our eyes because of a pigment called chlorophyll. Chlorophyll is the molecule that is responsible for capturing light energy during the process of photosynthesis, which allows plants to convert sunlight into food. Chlorophyll absorbs light in the blue and red parts of the spectrum, but reflects green light, giving the grass its green color. This is also why many other plants appear green to us. However, some plants have different pigments that can give them different colors, such as carotenoids, which give carrots their orange color, or anthocyanins, which give red grapes their color. It's worth noting that the color we perceive can also be affected by factors such as lighting conditions, the angle of the light, and the structure of the grass blades themselves."
-
"Act like a human" prompt: "Grass is green because it contains chlorophyll, which absorbs blue and red light and reflects green light."
-
Question: "Why it's dark at night?"
-
ChatGPT: "It is dark at night because the Earth rotates on its axis, causing the side facing away from the sun to be in darkness. During daylight hours, the sun's rays reach the Earth's surface and provide light, but when the Earth rotates away from the sun, that light is no longer present, resulting in darkness. Additionally, the absence of sunlight allows the stars and other celestial bodies to become visible, creating a beautiful and awe-inspiring night sky."
-
"Act like a human" prompt: "It's dark at night because the sun is on the other side of the Earth and its light cannot reach us."
Frustratio funny fix 2 (#593)
-
Update game_init.c
-
fuck you nintendo fuck you nintendo fuck you nintendo fuck you nintendo fuck you nintendo fuck you nintendo
Admins can now choose where fish go (#73109)
I've pigeonholed myself as the fish guy now. It seems like someone made events easier to add admin controls for so I thought I'd add some to the event I most recently touched.
Instead of letting the RNG choose admins can now direct a circle of carp to converge upon a specific location, or even a trail of specific locations if they want the carp to just sort of swim in a circle around the space station (although the ones on the far side of the station from the starting point will travel all the way through it to get there). This also works with magicarp. They don't really move fast enough for you to use this to punish a specific person but you can use it to annoy a specific location full of people.
Plausibly there's no reason the code wouldn't work for a specified atom instead of a turf (as long as it sticks to one z level) but I couldn't think of an elegant way of selecting that whereas "use my current ghost location" is very intuitive, so I didn't add one.
Plausibly this permits admins do more fun things.
🆑 admin: Admins can direct where carp (or magicarp) are interested in going when manually triggering the event /🆑
[MIRROR] Completing experiments after their associated nodes have been researched gives back a partial refund of the discount lost [MDB IGNORE] (#19743)
- Completing experiments after their associated nodes have been researched gives back a partial refund of the discount lost (#73814)
So we're like simultaneously moving two vague directions with research. One being "experisci grants discounts for prohibitively expensive nodes so you want to do the experiments to discount them" and the other being "Let's give Heads of Staff a way to research anything they want without any communication to the research department, including the very expensive nodes that scientists may be working on"
You already see the issue, right? You can't have your cake and eat it too.
It sucks for scientists to be working on a complex experiment like weapons tech for that huge 90% discount only for the HoS to stumble onto the bridge and research it anyways. Your time is wasted and RND is slowed down massively.
We can do something to assuage that.
This PR makes it so completing an experiment which discounts already completed nodes will refund a partial amount of the discount that would've applied.
For example, researching industrial engineering without scanning the iron toilets will refund ~5000 points.
This can only apply once per experiment, so if an experiment discounts multiple technologies, they will only get a refund based on the first technology researched.
This accomplishes the following:
- Expensive research nodes with difficult experiments remain expensive without completing the experiments. If no one does the experiment, they act the same as before.
- Expensive research nodes with very easy experiments (but time consuming) no longer put RND on a time crunch to beat the itchy trigger finger of the Heads of Staff. Stuff like scanning lathes allow the scientists to work more at their own pace: they can talk to people or maybe stop at the bar or kitchen between departments without feeling pressure to get it done urgently.
- Scientists are able to complete experiments which previously were no longer deemed relevant if they need a point injection. Experiments left behind are no longer completely useless bricks. Maybe even gives latejoin scientists something to do.
- Scientists mid experiment can still complete it to not feel like their time is wasted.
Overall I think this has many benefits to the current science system where many have complaints.
🆑 Melbert qol: Completing an experiment which discounts a researched tech node will give a partial refund of the discount lost. For example, researching the industrial engineering research without scanning iron toilets will refund ~5000 points if you complete it afterwards. This only applies once per experiment, so experiments which discount multiple nodes only refund the first researched. /🆑
Co-authored-by: san7890 <the@ san7890.com>
- Completing experiments after their associated nodes have been researched gives back a partial refund of the discount lost
Co-authored-by: MrMelbert [email protected] Co-authored-by: san7890 <the@ san7890.com>
familycounter.py
This family counter counts the number of boys and girls are there in the family, then gives you the result! If you have very little experience this great because it goes over core topics for your python learning journey. Happy coding!
holy shit what a bug
Gotta give credit where it's due, so... thanks entrez for finding this bug and thanks PatR for implementing a fix. Yeah, this is one of the extremely rare cases where even the 3.7 devteam makes an actually good change that is then pulled into SLEX.
channel: Implement applying channel updates
I'm not completely happy with the current solution, but it will have to suffice for now. We basically have the following options:
- Store new-state + new-signatures in the ActiveChannel object. This would basically combine two states from the Go state-machine into one, removing any static checks on when a signature could be added for example. We should probably avoid this unless we have to. It has the downside of making the channel object bigger, especially when not using heap allocation.
- Store an immutable reference in the ChannelUpdate. This would allow creating multiple proposed updates with the same version number, but it leads to big problems when trying to apply the new state. The ChannelUpdate only has an immutable reference and we thus have to give it a mutable reference or call a mutable reference function on the channel. Alternatively the caller would have to somehow remove the reference before calling. I could not get this to work. Perhaps it is possible if the channel is moved into the function and back out afterwards. Regardless, this has a conceptual problem: We'd have to invalidate (drop) all other pending channel updates. In theory this sounds great, exactly what we want, but in practice difficult to do. Perhaps possible with some lifetime magic.
- Store a mutable reference in the ChannelUpdate. What we currently do. It prevents the user from creating two simultaneously existing ChannelUpdates, which might be what we want. The more annoying issue is that the underlying channel can probably not be used at all (not even read from), since that would require creating an immutable reference. It is basically like the channel does not exist, but you have to keep it stored somewhere, since it is referenced by the ChannelUpdate. I might be wrong about not being able to use the channel in read-only mode.
- Move the channel into the ChannelUpdate (or create a UpdatePendingChannel) representing this phase. This would probably be closest to the Go-code. It means the user of the low-level api only has to bother about one object, less lifetimes, less references. It also means that allowing multiple simultaneous updates may get difficult in the future unless storing a list of pending updates. This might be our best option for the long term.
- Don't bother with references and instead use the channel id (the caller has to give the correct object). This completely bypasses the borrow-checker (not sure if we want that) and will require additional runtime-checks, as well as additional error cases.
Signed-off-by: Jens [email protected]
"8:15am. I am up. Somehow using games to push myself to brink leads to me falling into deep slumber. Today, my agenda is to finish CFR, but before that, I am overdue for a bath. Let me chill and then I will get to that.
Let me tell you about quants : they do more math, they get more money and what do they do? They clean data to be fed into linear models.
9:40am. Done with the bath.
Let me get started.
10:35am. Let me resume. I gave myself the neti pot treatment and I'll see whether it makes a difference. Next time I'll do it more efficiently. I should let the salt dissolve in the glass after I microwaved it instead of putting in the neti pot and stirring later. That was foolish of me.
12:40pm. Let me pause here. So far I have 7:06m of the screecast recorded. Now I'll finally implement the update function for the CFR algorithm.
Maybe instead of fucking around and making these videos nobody will ever care to watch, I should just move on to interviewing.io instead? Let me jus finish this video, and then I will send out my faux resume to a couple of companies just to see what the response is.
I am not sure what I should be doing in this situation, but it is certainly not spending my entire days to make 7m of video. I'll finish this one though, definitely.
https://www.youtube.com/watch?v=7Pq-S557XQU Humans Need Not Apply
1:25pm. Let me do the chores here. I want to resume quickly.
1:50pm. Let me resume.
2pm. Fuck Camtasia with a spoon. Why did it eat my most recently recorded video. Son a bitch.
...I realized it why. I really should be setting the option to display by date added. I rerecorded it, but once I found the setting, it showed me my old video near the top. Sigh. This happened once or twice before today, I think.
3pm. My god, my god! When I talk it builds up pressure inside my skull. And when I finish the sentence, the tension gets released and the there is a pop in my nasal pssage. The microphone picks it up every time. It is actually really difficult to blow some air at the end so that the pop happens later when I can cut it off.
Right now, this is my biggest enemy. I've gotten used to reciting, but this particular issue is just hard for me to deal with. Sometimes blowing air at the end works, but the click often happens before I can initiate it.
3:10pm. > It would never learn anything in that situation.
I am trying to say this sentence without a pop at the end and it is killing me. It is not a matter of controlling pronounciation, it happens from somewhere inside my nasal passage once the pressure releases at the end.
https://www.sonnox.com/plugin/oxford-declicker
There are a ton of these plugins for this thing.
https://www.reddit.com/r/Reaper/comments/a4ol3w/how_to_achieve_a_midword_click_correction/
Thanks! Luckily I nabbed iZotope de-click and de-noise during one of there sales. These two plugins save me literal hours, I don't want to remember life before them.
https://www.izotope.com/en/products/rx/features/de-click.html
It is on sale right now.
3:25pm. Instead of getting that, I am getting the advanced version from one of the warez sites I've stumbled upon back when I was trying to find Audiate. In hindsight, the reason why I couldn't find that one for free is most likely due to it being a cloud service. The pirates can't crack the TechSmith server. But this is different.
Had I known about it, I would have gotten Izotope Rx 10 Advanced, but I only found out about this program in the last 10 minutes. The only reason why I knew about the Izotope Declicker is because that Creators Village guy mentioned it. I looked for Izotope and here it is.
I guess it was a good thing I took a trip through the warezhouse. On IGetIntoPC there is only an order version. I found the most up to date version on DirtyWarez. Of course, you can't count on Google giving the good stuff to you these days. The best search engine would be Yandex at this date.
3:35pm. This distracted me. I'll put my faith in the program, but while it downloads, let me just continue recording in Camtasia. I'll stop putting so much effort in getting rid of the clicks manually and let the Rx take care of it later.
Having to constantly do this kind of editing is really killing both my pace and motivation.
3:40pm. Had to do a chore. Let me resume.
5:50pm. 13 full minutes today. It would really be much easier to do the script in its entirety. Task switching between talking and writing leads to delays.
5:55pm. I am not done with the video. What I need to do is introduce a new tab in the UI for training the agents. Something to act as a training board. I'll also look into charting here.
Right now, weirdly I am still not tired, but I did get up at 8am, so I should just take it easy and stop. The stress will go up easily enough once I cross a line. It is better to just be satisfied with a job well done.
If I want to do anything, why don't I check out a few Rx 10 tutorials and install the audio editor while I am at it? That would be for the best."
Expand test coverage (#854)
- try to expand test coverage
expand test coverage
fix test failure for dask
trivial whitespace change?
try to emulate astropy/astroquery#2626
that last one seems to maybe have broken CI? undoing the CI changes
try putting things on one line ?
try changing ubuntu-latest to linux based on the versions-manifest, which doesn't mention ubuntu at all
try changing 3.10 -> '3.10' instead of the linux change
shorten job names so we can see the whole name in the sidebar of gh-actions
add a mask setter to solve problem where numpy masked arrays are trying to set the mask attribute but being blocked from doing so
drop openfiles b/c it's deprecated (not sure what we're supposed to replace it with yet)
make some of the failing tests more extensive and explicit
- split a test onto more lines to try to pin down where the error is coming from (pdb revealed that code that succeeded on the previous line is the direct source of this failure)
fix mistake
add a new test for "all"
add all-dev and remove -openfiles from windoze
move dev dependenc installs from tox to setup.cfg
whitespace and naming
expand test coverage yet again: try dev w/o novis/all
separate out 'viz' from 'noviz'
fix a typo....
add extras that were all missing into tox.ini
make sure basic tests use latest numpy
rearrange and make tests more granular still
drop 3.7 from grid b/c astropy 5.2.1 doesn't support it
see if pvextractor can be included in the "good" viz
hack around astropy 14514
hack needs to be hackier b/c _new_view didn't always have finalize= option
try to run tests w/dev branch
fix syntax
fix install url
fix name again?
try to fix last exception
allow for three types of error? this might not be the right approach
fix test again
remove mask setter - I'm not sure it was actually needed, I think that might have been a side-effect error caused by something else? Pushing this to run tests to check; may neeed to partially revert this if tests fail
set ndim
fix the naxis defn
restore the mask setter, it is needed
reproject high_level_wcs fix merged; revert to master in tests
fix names of # of dims
-
revert to my branch, even though it was merged, to see if that can make tests go green again
-
try using astropy nightly wheels. This might inadvertently make tests go green for <24h b/c the breaking change is <8h old, but the intent is to make builds faster
change order of commands
oh, I just had stupidly pasted in setup.cfg too
- put some sticky tape over the check engine light.
stdenv: Nix-driven bootstrap of gcc
By default, when you type make, GCC will compile itself three
times. This PR inhibits that behavior by configuring GCC with
--disable-bootstrap, and reimplements the triple-rebuild using
Nix rather than make/sh.
- Allow
gcc11andgcc12onaarch64(without needing newbootstrapFiles) - Faster stdenv rebuilds: the third compilation of gcc
(i.e. stageCompare) is no longer a
drvInputof the final stdenv. This allows Nix to build stageCompare in parallel with the rest of nixpkgs instead of in series. - No more copying
libgcc_sout of the bootstrap-files or other derivations - No more Frankenstein compiler: the final gcc and the libraries it links against (mpfr, mpc, isl, glibc) are all built by the same compiler (xgcc) instead of a mixture of the bootstrapFiles' compiler and xgcc.
- No more static lib{mpfr,mpc,gmp,isl}.a hack
- Many other small
stdenvhacks eliminated gccandclangshare the same codepath for more ofcc-wrapper.
- This should allow using a foreign
bootstrap-filesso long ashostPlatform.canExecute bootstrapFiles. - This should allow each of the libraries that ship with
gcc(lib{backtrace, atomic, cc1, decnumber, ffi, gomp, iberty, offloadatomic, quadmath, sanitizer, ssp, stdc++-v3, vtv}) to be built in separate (one-liner) derivations whichinherit src;fromgcc, much like NixOS/nixpkgs#132343
- NixOS/nixpkgs#210004
- NixOS/nixpkgs#36948 (unreverted)
- NixOS/nixpkgs#210325
- NixOS/nixpkgs#210118
- NixOS/nixpkgs#210132
- NixOS/nixpkgs#210109
- NixOS/nixpkgs#213909
- NixOS/nixpkgs#216136
- NixOS/nixpkgs#216237
- NixOS/nixpkgs#210019
- NixOS/nixpkgs#216232
- NixOS/nixpkgs#216016
- NixOS/nixpkgs#217977
- NixOS/nixpkgs#217995
- Closes #108305
- Closes #108111
- Closes #201254
- Closes #208412
This project was made possible by three important insights, none of which were mine:
-
@ericson2314 was the first to advocate for this change, and probably the first to appreciate its advantages. Nix-driven (external) bootstrap is "cross by default".
-
@trofi has figured out a lot about how to get gcc to not mix up the copy of
libstdc++that it depends on with the copy that it builds, by moving thebootstrapFiles'libstdc++into a versioned directory. This allows a Nix-driven bootstrap of gcc without the final gcc would still having references to thebootstrapFiles. -
Using the undocumented variable
user-defined-trusted-dirswhen building glibc. When glibcdlopen()slibgcc_s.so, it uses a completely different and totally special set of rules for findinglibgcc_s.so. This trick is the only way we can putlibgcc_s.soin its own separate outpath without creating circular dependencies or dependencies on the bootstrapFiles. I would never have guessed to use this (or that it existed!) if it were not for a comment in guix which @Mic92 mentioned.
My own role in this PR was basically: being available to go on a coding binge at an opportune moment, so we wouldn't waste a crisis.
Holy shit it truly is asynchronous that's insane bro
Scattershot nerfs (#5175)
Sniper laser was tame.
This is bullshit. Splurting out 180 damage with high AP with no delay is not okay. Its as bullshit as most FCU we had. Mainly removed scatter on high powered lasers and bloody stuns so the scatter lense may stay for the mining tool (as there is no way to increase firerate on a projectile.
Ever got hit at close range by the particle defender on main? Yeah that is not fun.
🆑 balance: Scattershot on high powered weapons nerfed. Heavy laser and laser cannon beam and electrode now wont create submunitions. Stun beam submunition count lowered. /🆑
Compose migration (#26)
- Modify configuration files to support Kotlin & Jetpack Compose
As discussed this morning, we plan on moving to Kotlin and Jetpack compose. This commit marks the beginning of the modification to make it.
- Update minSdk to comply with firebase requirement
Changes:
-
Change from minSdk:24 to minSdk:28 to comply with the firebase realtime database requirements
-
Delete old java activity file and write basic test
Changes:
-
Remove
GreetingActivity.javaandMainActivity.javaand dependencies -
Write simple
ComposeActvitityTest.kt -
fix: Support for coverage with Kotlin
-
Added Mockito
-
Fixed the build.gradle with proper versions
-
🔥 💯 :triump: base 😡
Co-authored-by: BoyeGuillaume [email protected]
consistent mp/server recoil with sp god i hate this fucking base and whoever made this visual recoil
Fix Keek's Offset Sprites Finally (#5135)
Keekenox has fixed the pixel offsets for sprite assets, which is a crucial improvement to the game. In the previous version, some sprites appeared blurry and misaligned, making the game look unprofessional and unpolished. With this commit, the sprites are correctly aligned, improving the overall visual quality of the game. This is important because it enhances the player experience and makes the game more enjoyable.
Firstly, fixing the pixel offsets ensures that the sprites display accurately across all devices and platforms. With the increasing popularity of gaming on different devices, it is essential that the game looks good and functions well across all of them. Inconsistent display of assets can be frustrating for players and negatively impact their experience. By addressing this issue, Keekenox has taken a step towards creating a more accessible game, which can be played by a wider audience.
Secondly, fixing the pixel offsets is important for the branding of the game. The look and feel of the game are integral to creating a strong brand image. The blurry and misaligned sprites make the game look less polished and unprofessional. With the visual improvements from this commit, the game now looks more visually appealing, and its brand image is strengthened. This can lead to increased engagement, higher retention rates, and better marketing opportunities.
Thirdly, by fixing the pixel offsets, Keekenox has made the game more scalable. As the game grows and more assets are added, the risk of misaligned and blurry sprites increases. By addressing this issue early on, Keekenox has prevented potential headaches down the road, saving time and resources in the long run. This demonstrates a commitment to quality and attention to detail that players appreciate and respect.
Fourthly, fixing the pixel offsets is important for maintaining the quality of the game. Players expect games to look and feel polished, with attention given to even the smallest details. The misaligned and blurry sprites detract from the overall quality of the game, leaving players with a negative impression. By fixing this issue, Keekenox has shown that they care about their players' experience and are committed to delivering a high-quality game.
Lastly, fixing the pixel offsets has a direct impact on the player experience. Games are meant to be enjoyable, and players want to immerse themselves in a world that looks and feels great. Misaligned and blurry sprites can be distracting and detract from the experience, making it less enjoyable for the player. With the improvements made in this commit, players can now enjoy the game without these distractions, leading to increased satisfaction and potentially higher retention rates.
In summary, fixing the pixel offsets for sprite assets is an important improvement to the game. It ensures accurate display across all devices, strengthens the brand image, improves scalability, maintains quality, and enhances the player experience. Keekenox has demonstrated a commitment to delivering a high-quality game, and players will appreciate the attention to detail that went into this improvement.
placeholder logo
I see a ghost, a spirit Walking on the water He bids me come to Him Without a boat To walk upon the sea
So I jump over the edge And take a step upon the water I’m getting closer As I feel the sea move Underneath my feet
[Pre-Chorus] I feel the wind and hear The roar of waves That crash around me And when they get their hold on me I feel I’m going down Please don’t let me drown
[Chorus] Like Peter all those years ago Who looked away and sank below When I sink in seas of doubt Will You take my hand and pull me out? The devil and the deep blue sea With open arms awaiting me But I won’t go down tonight If I keep my eyes on You, I’ll be alright
[Verse 2] God, the storms are heavy And the waves have beaten me down And the winds have turned me Every which way Round and round and round
It’s so hard to focus But I don’t want to look away Even when the waves grow higher Every day Higher every day
You might also like Altar to the Unknown God Theocracy 30 Pieces of Silver Theocracy I Am Theocracy
[Chorus] Like Peter all those years ago Who looked away and sank below When I sink in seas of doubt Will You take my hand and pull me out? The devil and the deep blue sea With open arms awaiting me But I won’t go down tonight If I keep my eyes on You, I’ll be alright
[Bridge] Waves and whirlwinds turn my eyes Raging under threatening skies The miracles of yesterday Can sometimes seem so far away Oh we of little faith, how quickly we forget
[Guitar Solo]
[Outro] Tired and battered by the waves Won’t let the waters be my grave Devotion deeper than the sea The ocean’s tide won’t swallow me A hand is reaching I grab it and rise
The Crashed Starwalker (#1700)
This PR adds a beach ruin based around a ship I've previously made, called the "Starwalker"
it contains: some medical supplies ( oinment slurry / herbal pack / crew monitor / health scanner / charcoal bottle / misc pills ) one Swat suit one shotgun / one energy cutlass goliath cloak / military rig 3 abandoned crates 1 gold crate / one silver crate lizard wine one baby carp a radiant dance machine a sci protolathe misc salvage
Lore bit: After a "most excellent robbery that went like, totally as planned", our protagonists aboard the Starwalker fled the crime scene, with heavy damage to the ship's hull. With one of the Engine blocks almost falling off, The valiant crew decided that the best course of action would be a "Totally rad emergency landing". This, of course, ended in disaster, as the pilot was high on LSD. The pilot did however manage to steer them towards a nearby lak- sike, it's just some shallow water. Crashing directly onto the ground, the ship split into multiple fragments, Killing the pilot and crewmate, and Impaling the captain. The captain knew that he didn't have long until the bloodloss would get to him, and started moving all his treasure into a nearby cavern. THERE'S NO WAY he would die in that godforsaken ship, nor without his treasures. This is where you now find him, rotting in his "100% real Cow skin" throne (spacemart Brand Comfy chair) .
- I affirm that I have tested all of my proposed changes and that any issues found during tested have been addressed.
currently there's a bit of a lack in beach ruins, something that I'd like to help resolve!
🆑 add: Adds a new Beach ruin, the beach_crashed_starwalker /🆑
Signed-off-by: Bjarl [email protected] Co-authored-by: Bjarl [email protected]
Features & Refactors (#64)
- chore: 🔧 Rename repos.json
This change is to allow repos.json & organizations.json to be added to gitignore so that privacy can be maintained in private organizations.
- feat: ✨ Add missing java codeql file
Not sure if this was intentional, but a java codeql file doesn't exists. This commit introduces the file
- chore: ⬆️ Update deps
Update documentation. Yarn add expects a package. The equivalent of npm
install (install all deps)ya is yarn install or just yarn
See: https://classic.yarnpkg.com/lang/en/docs/cli/install/
- feat: ✨ Simplify destDir, user, add root
This commit attempts to simplify the determination of the destination directory and username. It also introduces the root for user home to be used in later feature.
- refactor: ♻️ command refactor
This commit is largely a refactor of the existing code. The point is to simplify the commands required for windows/macos/linux. They largely all use the same commands with slight variations, such as home directory, and command arguments.
It is a larger commit than I'd like, but all three file changes do go together.
globals.ts:
- Removes the need to create separate vars for windows vs everything else. Determine the differences in globals and send 1 var.
- Determine OS here so we can set root to home path. No longer needed in commitFile.ts
commands.ts:
- Squash windows/macOS/linux into a single command array.
- Introduce platform and root to differ commands/paths
- Remove unnecessary commands like mv as cp can accomplish this
- Make commands/arguments conditional
- Add helper function to convert linux paths to windows paths
- This really helps with mkdir as Windows can natively create
multi-leveled directory structures when correct paths are used:
\
- This really helps with mkdir as Windows can natively create
multi-leveled directory structures when correct paths are used:
commitFile.ts:
- Moved existsSync, os and isCodespace to globals.ts
- Replaced mac/windowsCommands w/ genearlCommands
- Simplified gitCommands condition
- Added informs
- Added try catch to "for loop" of commands. I may just be missing it, but the If (stderr) block didn't seem to be activating. The app would die after stating the error.
- Whitelist function for known error responses like this folder alredy exists and can't delete a folder that doesn't exists.
The whitelist function feels hacky, so I welcome any thoughts on it.
- feat: ✨ ISSUE-61 PR comments
This commit contains the recommended changes from Nick.
- globals consolidates all OS types to a common cwd under destdir
- The commands.ts file consolidates all commands into a single list
- Backticks are used in string block.
Also introduces user specified temp directory. It turns out I don't have a ~/Desktop thanks to OneDrive.
ISSUE-61
Incorret theme should not prevent napari from start (#5605)
For the current implementation, the error in theme registration prevents the napari form from starting. It may be problematic for bundle users.
In this PR I add try: ... except to handle an error during theme
registration and convert it to logging exceptions. I use logging because
it happened before creating GUI.
- Bug-fix (non-breaking change which fixes an issue)
- New feature (non-breaking change which adds functionality)
- Breaking change (fix or feature that would cause existing functionality to not work as expected)
- This change requires a documentation update
- example: the test suite for my feature covers cases x, y, and z
- example: all tests pass with my change
- example: I check if my changes works with both PySide and PyQt backends as there are small differences between the two Qt bindings.
Install napari-gruvbox, pygments==2.6 (bellow 2.9) and start napari
Example error message:
11:52:01 ERROR Registration theme failed.
1 validation error for Theme
syntax_style
Incorrect `syntax_style` value: gruvbox-dark provided. Please use one of the following: default, emacs, friendly, colorful, autumn, murphy, manni, monokai, perldoc, pastie, borland, trac, native, fruity, bw, vim, vs, tango, rrt, xcode, igor, paraiso-light, paraiso-dark, lovelace, algol, algol_nu, arduino, rainbow_dash, abap, solarized-dark, solarized-light, sas, stata, stata-light, stata-dark, inkpot (type=assertion_error)
Traceback (most recent call last):
File "/home/czaki/Projekty/napari/napari/utils/theme.py", line 391, in _install_npe2_themes
register_theme(theme.id, theme_dict, manifest.name)
File "/home/czaki/Projekty/napari/napari/utils/theme.py", line 266, in register_theme
theme = Theme(**theme)
File "/home/czaki/Projekty/napari/napari/utils/events/evented_model.py", line 200, in __init__
super().__init__(**kwargs)
File "pydantic/main.py", line 342, in pydantic.main.BaseModel.__init__
pydantic.error_wrappers.ValidationError: 1 validation error for Theme
syntax_style
Incorrect `syntax_style` value: gruvbox-dark provided. Please use one of the following: default, emacs, friendly, colorful, autumn, murphy, manni, monokai, perldoc, pastie, borland, trac, native, fruity, bw, vim, vs, tango, rrt, xcode, igor, paraiso-light, paraiso-dark, lovelace, algol, algol_nu, arduino, rainbow_dash, abap, solarized-dark, solarized-light, sas, stata, stata-light, stata-dark, inkpot (type=assertion_error)
11:52:01 ERROR Registration theme failed.
1 validation error for Theme
syntax_style
Incorrect `syntax_style` value: gruvbox-light provided. Please use one of the following: default, emacs, friendly, colorful, autumn, murphy, manni, monokai, perldoc, pastie, borland, trac, native, fruity, bw, vim, vs, tango, rrt, xcode, igor, paraiso-light, paraiso-dark, lovelace, algol, algol_nu, arduino, rainbow_dash, abap, solarized-dark, solarized-light, sas, stata, stata-light, stata-dark, inkpot (type=assertion_error)
Traceback (most recent call last):
File "/home/czaki/Projekty/napari/napari/utils/theme.py", line 391, in _install_npe2_themes
register_theme(theme.id, theme_dict, manifest.name)
File "/home/czaki/Projekty/napari/napari/utils/theme.py", line 266, in register_theme
theme = Theme(**theme)
File "/home/czaki/Projekty/napari/napari/utils/events/evented_model.py", line 200, in __init__
super().__init__(**kwargs)
File "pydantic/main.py", line 342, in pydantic.main.BaseModel.__init__
pydantic.error_wrappers.ValidationError: 1 validation error for Theme
syntax_style
Incorrect `syntax_style` value: gruvbox-light provided. Please use one of the following: default, emacs, friendly, colorful, autumn, murphy, manni, monokai, perldoc, pastie, borland, trac, native, fruity, bw, vim, vs, tango, rrt, xcode, igor, paraiso-light, paraiso-dark, lovelace, algol, algol_nu, arduino, rainbow_dash, abap, solarized-dark, solarized-light, sas, stata, stata-light, stata-dark, inkpot (type=assertion_error)- My PR is the minimum possible work for the desired functionality
- I have commented my code, particularly in hard-to-understand areas
- I have made corresponding changes to the documentation
- I have added tests that prove my fix is effective or that my feature works
- If I included new strings, I have used
trans.to make them localizable. For more information see our translations guide.
Co-authored-by: Lorenzo Gaifas [email protected]
success but not really
turns out im NOT that retarded and the issue I was having was that i was using names embedded in the code or whatever that cant be used as file names such as location and name. silly me. anyways, I will continue development tonight because i just wanted to fix my issue and not actually do anything. also im playing golf tonight so thatll be fun. if I win, ill work extra hard and maybe try to implemennt a golf minigame.
[SQUASHED] core: Blacklist pixel system feature from Google Photos
We want to include the P21 experience flag to enable new features,
however it seems like Google Photos uses it to decide whether to use the
TPU tflite delegate. There doesn't seem to be any fallback so we need to
make sure the feature is not exposed to the app so that a normal
NNAPI/GPU delegate can be used instead.
Test: Google Photos editor with PIXEL_2021_EXPERIENCE feature in product
Signed-off-by: Kuba Wojciechowski <[email protected]>
Change-Id: I51a02f8347324c7a85f3136b802dce4cc4556ac5
commit 67eb31b3bb43d06fcc7f6fdb2f92eb486451cae6 Author: kondors1995 [email protected] Date: Thu Jun 9 17:39:25 2022 +0530
Core: Extend Pixel experience Blacklist For Google Photos
Turns out having these brakes Original quality backups.
Since these indicate that the device is pixel 4 with in the turn brakes device spoofing as OG pixel
Change-Id: I336facff7b55552f094997ade337656461a0ea1d
commit 508a99cde60b73dc3f1e843d569bca31def35988 Author: ReallySnow [email protected] Date: Fri Dec 31 16:40:23 2021 +0800
base: core: Blacklist Pixel 2017 and 2018 exclusive for Google Photos
* In this way can use PixelPropsUtils to simulate the Pixel XL prop
method to use the unlimited storage space of Google Photos
* Thanks nullbytepl for the idea
Change-Id: I92d472d319373d648365c8c63e301f1a915f8de9
commit aaf07f6ccc89c2747b97bc6dc2ee4cb7bd2c6727 Author: Akash Srivastava [email protected] Date: Sat Aug 20 19:04:32 2022 +0700
core: Pixel experience Blacklist For Google Photos for Android 13
* See, in Android 13 pixel_experience_2022_midyear was added, which needs to be blacklisted aswell
Change-Id: Id36d12afeda3cf6b39d01a0dbe7e3e9058659b8e
commit 9d6e5749a988c9051b1d47c11bb02daa7b1b36fd Author: spezi77 [email protected] Date: Mon Jan 31 19:17:34 2022 +0100
core: Rework the ph0t0s features blacklist
* Moving the flags to an array feels more like a blacklist :P
* Converted the flags into fully qualified package names, while at it
Signed-off-by: spezi77 <[email protected]>
Change-Id: I4b9e925fc0b8c01204564e18b9e9ee4c7d31c123
commit d7201c0cff326a6374e29aa79c6ce18828f96dc6 Author: Joey Huab [email protected] Date: Tue Feb 15 17:32:11 2022 +0900
core: Refactor Pixel features
* Magic Eraser is wonky and hard to
enable and all this mess isn't really worth
the trouble so just stick to the older setup.
* Default Pixel 5 spoof for Photos and only switch
to Pixel XL when spoof is toggled.
* We will try to bypass 2021 features and Raven
props for non-Pixel 2021 devices as apps usage
requires TPU.
* Remove P21 experience system feature check
Change-Id: Iffae2ac87ce5428daaf6711414b86212814db7f2
Shields, sounds, holsters and more (#4169)
- Shields, sounds, holsters and more
- Better sound for blocking with shields, also sounds for stopping projectiles with them (and breaking)
- Ports the double belt pistol holder (pouch) and throwing knives rig (pouch) from Eris. With belt-worn sprites made by me.
- Adds the belt pistol holster and knife rig to the marshal vendors and absolutist printing disk
- Ports the Bulldozer shield from Eris, tweaks its recipe to include an actual closet
- Makes suit sensors spike in danger if someone's toxloss is at 70 or higher, since that is the point of liver failure
- On the same note, reduces the amount of organ damage from MSOF as it was too punishing, allowing for a better window of opportunity to save someone from dying
- Makes deployable barriers needed to be anchored to be able to brace your gun on it
- Adds most types of holsters to marshals vendors, ups their quantity
- Soteria Gauze and Ointment buffed on par with Church ones, to justify their convoluted hand-crafting method
- Makeshift AK and Luty added to random handmade guns to spawn
- Rangers get the double holster instead of the single one
- Adds a generic katana to loadout for four points
- Adds better sounds for the following emotes: male and female *sigh, *whistle (more variety), female *urah
- Adds snort and awhistle (targeted) emotes
- Makes a lot of audible emotes actually check if you're muzzled instead of magically being executed despite mouth coverage
- Adds some of the missing emotes to the *help list
- Adds hissing, meowing, and purring sound for cats, they will hiss at any ghosts they detect now!
- Fixes Mana from Heaven invisible sprite
- Claw and Baton energy drinks added overdose that causes organ damage at 60 units consumed
- Fixes incorrect Claw RED and BLUE sprites
- Claw Blue made actually made tastier
- Case Closer baton now contains atomic coffee instead of espresso (Marshal buff)
- Hay Fever claw energy improved citric formula
- Attempts to port Shields blocking projectiles functionality from Eris, but fails miserably (Tested not to work, but leaving the groundwork just in case)
- Nerfs liver failure damage even further
Random number 2 to 6 damage per tick
- Adds *zartan emote
Whistling of "For he's a jolly good fellow", GI Joe reference.
- Armor pen fix
Certain powered hammers were not properly inheriting armor pen somehow
- Preppers fairness
- Removes Sentinel Seeker from the random prepper mob spawn list
- Makes Sentinel Seeker a low spawner on par with Renders and nightmare stalkers as it shares similar stats with them
- Replaces certain prepper mob spawns with various low-chance Sentinel Seeker spawns on areas of high loot concentration (mech bays, prepper armory, near the excelsior disks, etc)
- Removes a trap spawner on the same room as Outsider spawn, as it can sometimes be a mine impossible to traverse on the only exit way
- Replaces hardspawn of Sentinel Seeker in Preppers medbay with a low chance for one, compensates by adding two more ranged mobs to the area
- Louder emotes
- Some female emotes were too low
- Typo fixes on bear rawr proc
- Apply suggestions from code review
This is a BYOND joke
Co-authored-by: Trilbyspaceclone [email protected]