RagingHungryPanda

Hey all, I've been trying to get up and running with Friendica in a docker container behind Nginx Proxy Manager and connected to a separate MariaDB container.

The scenario that I have is that the only combination I've gotten to work to connect to Friendica is to use the alpine docker image with the complete web server, as putting configs into separate nginx instances wasn't getting me anywhere. However, using the full image, I can get to the UI and do the install to set things that I already set in env variables(?) whatever.

But what happens is that when it goes to save, it fails to save to the DB and maria db says that it rejected the connection for unauthenticated user and unknown host (implying to me that it rejected the connection before it even pulled this info). But the thing is that I've been able to shell into the friendica container and connect to the MariaDB. I can use adminer and log in as the friendica user to the friendica db that I created. Has anyone run in to this?

I'm starting to wonder if I need to use actual MySQL, maybe? This is a very strange issue as I've been able to create the database, user with privileges, and log in as that user. The host name for the user is '%', so 'friendica'@'%'.

I'd appreciate any help that I could get there.

If you have any experience in this field, please include so in your reply. I've seen over time a lot of criticism over the peer review process and how journals hyper-exploit academics simply because the journals are able to monetize scarcity/exclusivity. I saw another post on it today and I thought, "what if this was federated?"

I was looking around and I see that there are writing portions of the process, such as pubpub or manubot that essentially use git and markdown - but that's not the main point as that's on the before end. What about on the review process?

Let's say there's software that's federated and can be run by anyone from individuals to universities and consortiums. When a user or team is ready to publish, they can "submit their work" for publishing, which would federate out as works pending publication.

This part's a different issue: how to handle reputation for who can review, but I think there are ways to do that and that's beyond the scope of this post as I imagine it could get pretty complicated and would require feedback from people actually in the industry.

The reviewers can submit comments and reviews back to the author via federation, but this time the process can be open instead of behind closed doors. The authors revise, comment, etc. At some point a determination is made that this work is "published."

This seems like a feasible premise. Just brainstorming, you would get history, open reviews, no one asking $1,000 to submit a publication that they then make bank on while you get scraps or nothing.

I could see a reputation system within a given field and/or overall, with certain users being "review board" or "reviewers" on their instance. There could also be additional reputation if, say, a group of universities creates consortiums for different fields and then that consortium "publishes" a work. There'd have to be additional process to block people from spamming works that aren't ready or whatever, but that's not really the point for now.

Am I barking up the wrong tree here? At first thought, it seems like there are ways to allow federation of research papers and peer review and to put a dent in the grip of technical journals.

Activity Pods is supposed to allow you to have one account across the fediverse and it's still in early dev. I do see that they have some docker images, but there's no descriptions on what they're for and their instructions involve running make scripts to get running.

I can do that inside of a docker container, but running TrueNas I'm limited to running those, which is fine, I can do that, but the other thing that seems a bit confusing is that it looks like they want you to define "shapes" for different services to communicate with.

It might just look more complicated than it is. Has anyone successfully gotten up and running with it?

And I'm making everyone go to my gotosocial post because the server is running, so I'm going to use it!

I have a gl-inet router on which I have an nginx config to send traffic to Nginx Proxy Manager and DDNS with cloudflare.

I'm trying to get some kind of local dns set up so that if I'm on the local network, traffic stays within the network. The problem that I'm running in to is SSL certificates. NPM (on the server) is handling those and I thought that what I could do is go into the AdGuard Home (on the gl-inet router) config and add a dns rewrite to point to the router and traffic would flow as it normally does.

This DOES work, technically. traceroute shows only one hop for any of my subdomains, ie files.mydomain.com.

But I cannot actually get access in a browser because the ssl certificates are not set up.

It seems like options are: manually copy certificates from the server to the router (not ideal), or don't do it at all. I notice that if I go to the service by ip address, it'll change the address to the domain name. Eg going to 192.168.8.111:30027 -> files.mydomain.com.

This isn't a HUGE deal, but it's not preferable. How have you all solved this?

Edit: I solved the issue in probably the most hilarious way. I was trying to get the forwarding and everything set up and then borked my routers firewall so bad I couldn't get to the outside at all, so I did a hard reset.

I then moved my admin UI ports up by one each (81/444), re-set up Goodcloud, ddns, Wireguard server on the router, then set up port forwarding for 80/443 on the router to 80/443 on the trunas server. I switched NPM to listen on those ports (since I moved the web UI to different ports), then added Adguard Home DNS rewrites. It's now all working as expected.

Local traffic only has one hop and is accessible without SSL warnings, and same for WAN traffic. Thank you all for the help!

Starting at midnight Thursday night through midnight Friday night, we will be joining with people across the country and beyond to demonstrate our collective outrage over the hostile takeover of our government by unelected billionaires and by those who put profits before people.  For one day, this Friday, we pledge not to buy anything from any major online or in-person retailers, and we pledge to refrain from using credit cards.  We recommend staying away from Facebook, Instagram, and “X.”   

This action began as a protest against those corporations who abandoned diversity, equity, and inclusion programs to placate a white supremacist administration.  Those corporations include Target, Citi Bank, Google, and Disney.  It quickly expanded into a “Buy Nothing Day,” with particular recognition of the role of finance capital.  The concept of Economic Blackout 2/28 has quickly spread on social media, propelled by activists, faith communities, students, and rank-and-file workers everywhere.  The movement goes beyond our borders. In Canada, consumers will target USA-based companies to protest Trump’s tariffs, and Mexicans will participate in the Latino Freeze Movement to protest US anti-immigrant and anti-DEI policies.

Please participate in this action! It is a simple act that we all can accomplish and that can quickly add up to a collective impact. 

Sign our pledge today!

In resistance,

National Board, CPUSA

I'm starting to get in to self hosting and am looking at self-hosted blog solutions. It looks like WriteFreely is the main fediverse blog platform, with Plume as second though I don't see it used much.

But that got me thinking that it'd be good to follow federated blogs and have some long form reading that I follow, like we did back when RSS was the main way of doing things.

But how do I actually find bloggers? It looks like WriteFreely can federate with Mastodon, but it doesn't look like there's a federated blogging platform like lemmy or mastodon. Is this correct? Where I can I go (other than Medium) to find blogs and bloggers in the fediverse?

I previously posted about an issue where the nginx container for the Collabora application logs a GET to /robots.txt every 10 seconds. I tried modifying the files in the container, but they were reset on restart. I also tried to run the container with --log-driver=none, but was unsuccessful. Despite being a software dev, I'm new to the homelab world and trunas.

I solved it by changing the docker image and then committing those changes. The change I made was to set access_log off; in the nginx config. I did it at the server root because I don't really care about those logs for this app, but it could be done on the location level.

Here's how I did it: Here's the reference SO post that I used: https://stackoverflow.com/a/74515438

What I did was I shelled into the image:

• sudo docker exec -it ix-collabora-nginx-1 bash
• apt update && apt install vim
• vi /etc/nginx/nginx.conf and add the access_log off;
  • if you're not familiar with vim, arrow key to the line you want then press 'a' to enter "append mode". Make your change, then esc, :wq!. You need the ! because the file is read only
• apt remove vim
• exit
• sudo docker commit <image id>
• sudo docker restart ix-collabora-nginx-1

I'm running TruNas Scale with a docker image for NextCloud and Collabora. Under Collabora, the nginx application is logging a GET to robots.txt about every second and I'm having a hard time filtering this out because it looks like the conf files for nginx get replaced on every restart. I also tried mounting my own version of the nginx.conf file, but that didn't reflect any changes.