buzzn/core is the central server-side application of buzzn. It contains the business logic, storage and API for our client/frontend applications.
- buzzn/core
- Table of contents
- Application Architecture
- Bin-Scripts
- Useful rake tasks
- Beekeeper import
- How to deploy
- How to set up a development environment
- Misc admin info (may be outdated)
- Further links & documentation
See docs/application_architecture.md.
- bin/console - starts application with pry session
- bin/server - starts puma server
- bin/rake - runs rake with application bundler context
- bin/rspec - runs rspec with the current bundler context
- bin/reset_test_db - runs some rake tasks to reset test DB
- bin/example_data - runs some rake tasks to setup and seed DB for running local server
you can add ./bin to your PATH to simplely use console, server, rake or rspec.
To wire up some datasource of some registers with the discovergy API you need add the credentials in .env.local
DISCOVERGY_LOGIN= DISCOVERGY_PASSWORD=
| task name | description | source |
|---|---|---|
rake db:empty |
Resets the database without dropping the DB. Useful to reset DB when it has open connections. |
Buzzn custom |
rake db:seed:example_data |
Load an example localpool into the DB. It does not prepare/empty the DB, run rake db:empty beforehands if required. |
Buzzn custom |
rake db:dump:transfer |
Transfer relevant data from buzzn_core_development to DATABASE_DUMP_NAME | Buzzn custom |
rake deploy:staging |
Deploy the application to staging. | Buzzn custom |
rake deploy:production |
Deploy the application to production and create a new release tag. | Buzzn custom |
rake heroku:update_db:staging |
Import the beekeeper dump locally and push it to staging. | Buzzn custom |
rake heroku:pull_db:staging |
Fetch a postgres dump from staging to DATABASE_DUMP_NAME, for use with db:dump:transfer |
|
rake heroku:update_db:production |
Import the beekeeper dump locally and push it to production. | Buzzn custom |
rake heroku:pull_db:production |
Fetch a postgres dump from production to DATABASE_DUMP_NAME, for use with db:dump:transfer |
- checkout the branch
- run
reset_test_dbonce to ensure DB is prepared - run
rspec
- run
reset_test_dbonce to ensure DB is prepared - run
rspec path/to/spec_file
Our application has two kinds of data that we can pre-load ("seed"), setup and example data.
Setup data is essential for any deployment of our application to work. Among others, it loads the buzzn organization into the database (which has hard-coded references in the code as Organization.buzzn). It can be loaded by running rake db:seed:setup_data on the shell.
Example data contains an exemplary localpool, as well as contracts and their users, meters etc.. This data is completely optional and should not be loaded into the production system. We use it for demos or testing where we don't have real user-generated data. Load it into the database by running rake db:seed:example_data on the shell.
Use the list of example users to log in. Login is the email, the password always is Example123.
Note that creating a user account with the buzzn operator role (super user) is not part of the example data. Use the separate rake tasks db:seed:buzzn_operators or db:seed:buzzn_operator to create one.
Important: both rake tasks do not empty the database before running, so when there already is data in the system, there may be conflicts, causing the task to abort.
So if you know what you are doing, run rake db:empty first, to completely delete all data from the database.
- make sure your
.env.localhas the correct, safe DEFAULT_ACCOUNT_PASSWORD - load setup and example data into the local core DB (we need the user accounts)
rake db:empty db:seed:example_data
- get the latest beekeeper MySQL dumps ("minipool_..." and "buzzndb_2017-11-17_TT.zip")
- convert/load them into separate DBs in local postgres server
rake beekeeper:sql:mysql2postgres FILE=/absolute/path/to/minipooldb_2017-11-17_TT.ziprake beekeeper:sql:mysql2postgres FILE=/absolute/path/to/buzzndb_2017-11-17_TT.zip- make sure no table has any errors, (check summary table at the end)
- convert and import that data into the core DB:
rake beekeeper:import
- optionally upload the local core DB into the Heroku DB
heroku pg:resetheroku pg:push buzzn_development DATABASE_URL
We're running on Heroku, so you can deploy from Heroku's web interface if you want. To do it from the command line:
to switch maintenance mode off/on execute the rake tasks on heroku for staging
`heroku run rake maintenance:on -a buzzn-core-staging`
`heroku run rake maintenance:on -a buzzn-core-staging`
or for production
`heroku run rake maintenance:on --remote production`
`heroku run rake maintenance:off --remote production`
this is important when the DB structure changes and the code and DB have mismatch for some time during deployment.
Staging is deployed automatically for every green CI build on master.
To do it manually: rake deploy:staging.
Run rake deploy:production. This pushes the current branch to Heroku and sets a release tag on the git repo.
Note on the previous, docker-based system and deployment: the Dockerfiles and related code have been removed, use this git tag to get them back. The same tag is set in the console app.
See https://github.com/sstephenson/rbenv#installation
The required version number is found in file .ruby-version
imagemagick, postgresql, redis
for postgresql important on linux:
Edit the pg_hba.conf file /etc/postgresql/9.5/main/pg_hba.conf
Change all authentication methods to "trust" and restart Server.
use homebrew on a Mac
- Grab the source
git clone https://github.com/buzzn/core.git - Get dependencies
cd core gem install bundler bundle install - Create a
.env.development# Please keep the variables ordered alphabetically. # This file is for overrides of the .env file when running in development. ASSET_HOST=http://localhost:3000 DEFAULT_ACCOUNT_PASSWORD=Example123 DISPLAY_URL=http://localhost:2999 SESSION_INACTIVITY_TIMEOUT=31536000 # 1 yearPOSTGRES_HOST=localhost POSTGRES_USER=postgres POSTGRES_PASSWORD=secret POSTGRES_BASE=postgres://$POSTGRES_USER@$POSTGRES_HOST DATABASE_URL=$POSTGRES_BASE/buzzn_developmentREDIS_HOST=localhost REDIS_CACHE_URL=redis://$REDIS_HOST:6379/0 REDIS_SIDEKIQ_URL=redis://$REDIS_HOST:6379/1 MAIL_BACKEND=stdout DISCOVERGY_LOGIN=YOUR_DISCOVERGY_LOGIN_NAME DISCOVERGY_PASSWORD=YOUR_DISCOVERGY_PASSWORD
- Start postgres and and create a database and a user according to the entries of the previous
.env.developmentcreatedb -U postgres -h localhost buzzn_development pg_restore -h localhost -d buzzn_development -U postgres ./some_data.dump # Import some data if you already have any - Start redis
bin/server
RACK_ENV=test rake db:reset
guard
We run rubocop in CI to ensure consistent coding style and prevent error-prone syntax. Let your editor check the rules as well so you don't have to rely on CI.
Here's how to integrate it into editors:
- for SublimeText: https://packagecontrol.io/packages/SublimeLinter-rubocop
- for Atom: https://atom.io/packages/linter-rubocop
- for Emacs: https://github.com/bbatsov/rubocop-emacs
To run rubocop from the CLI, simply type rubocop.
Rubocop is smart enough to auto-corrrect most offenses by running rubocop -a
- For a section of code:
# rubocop:disable RuleName
some = Exception(to, the, rule)
# rubocop:enable RuleNameInstall the overcommit gem; it'll then use the .overcommit.yml file that's already checked in to run rubocop before pushing.
redis-server
remark: probably necessary to reinit database (rake db:init) to let sidekiq run properly
bundle exec sidekiq -r ./config/sidekiq.rb
The (very useful) Sidekiq Admin interface currently isn't set up. See Sidekiq's documentation on standalone installation for how to enable it.
rake sidekiq:kill
lol_dba db:find_indexes
brakeman