documents and simplifies how .env and .user-groups are passed to the images

.gitignore

@@ -1,3 +1,5 @@
+user-groups.dev.yaml
+user-groups.yaml
 orchestration.yaml
 my-archives
 *.pyc
@@ -24,3 +26,4 @@ local_archive_test
 *db-wal
 *db-shm
 copy-files.sh
+temp/

README.md

@@ -2,8 +2,43 @@
 
 [![CI](https://github.com/bellingcat/auto-archiver-api/workflows/CI/badge.svg)](https://github.com/bellingcat/auto-archiver-api/actions/workflows/ci.yaml)
 
-An api that uses celery workers to process URL archive requests via [bellingcat/auto-archiver](https://github.com/bellingcat/auto-archiver), it allows authentication via Google OAuth Apps and enables CORS, everything runs on docker but development can be done without docker (except for redis).
+A web API that uses celery workers to process URL archive requests via [bellingcat/auto-archiver](https://github.com/bellingcat/auto-archiver), it allows authentication via Google OAuth Apps and enables CORS, everything runs on docker but development can be done without docker (except for redis).
 
+### setup
+To properly set up the API you need to install `docker` and to edit 2 files:
+1. a `.env` to configure the API, stays at the root level
+2. a `user-groups.yaml` to manage user permissions
+Do not commit those files, they are .gitignored by default.
+
+We have examples for both of those, and here's how to set them up whether you're in development or production:
+
+#### setup for DEVELOPMENT
+```bash
+# copy and modify the .env.dev file according to your needs
+cp .env.example .env.dev
+# copy the user-groups.example.yaml and modify it accordingly
+cp user-groups.example.yaml user-groups.dev.yaml
+# run the APP, make sure VPNs are off
+make dev
+# check it's running by calling the health endpoint
+curl 'http://localhost:8004/health'
+# > {"status":"ok"}
+```
+now go to http://localhost:8004/docs#/ and you should see the API documentation
+
+#### setup for PRODUCTION
+```bash
+# copy and modify the .env.prod file according to your needs
+cp .env.example .env.prod
+# copy the user-groups.example.yaml and modify it accordingly
+cp user-groups.example.yaml user-groups.yaml
+# deploy the app
+make prod
+# check it's running by calling the health endpoint
+curl 'http://localhost:8004/health'
+# > {"status":"ok"}
+```
+now go to http://localhost:8004/docs#/ and you should see the API documentation
 
 ## User, Domains, Groups, and permissions management
 there are 2 ways to access the API
@@ -97,6 +132,16 @@ orchestrators:
 
 ## Database migrations
 check https://alembic.sqlalchemy.org/en/latest/tutorial.html#the-migration-environment
+```bash
+# set the env variables
+export ENVIRONMENT_FILE=.env.alembic
+# create a new migration with description in app/migrations
+poetry run alembic revision -m "create account table"
+# perform all migrations
+poetry run alembic upgrade head
+# downgrade by one migration
+poetry run alembic downgrade -1
+```
 
 * create migrations with `alembic revision -m "create account table"`
 * if running in the normal pipenv environment use `PIPENV_DOTENV_LOCATION=.env.alembic pipenv run` followed by:
@@ -127,16 +172,12 @@ curl -XPOST -H "Authorization: Bearer GOOGLE_OAUTH_TOKEN" -H "Content-type: appl
 
 ### Testing
 ```bash
-# can be done from top level but let's do it from the src folder for consistency with CI etc
+# set the testing environment variables
-cd src
+export ENVIRONMENT_FILE=.env.test
 # run tests and generate coverage
-PYTHONPATH=. PIPENV_DOTENV_LOCATION=.env.test pipenv run coverage run -m pytest -vv --disable-warnings --color=yes tests/  && pipenv run coverage html
+poetry run coverage run -m pytest -vv --disable-warnings --color=yes app/tests/
-
 # get coverage report in command line
-pipenv run coverage report
+poetry run coverage report
-
+# get coverage report in HTML format
-# get coverage HTML
+poetry run coverage html
-pipenv run coverage html
-
-# > open/run server on htmlcov/index.html to navigate through line coverage
 ```

app/example.user-groups.yaml

@@ -1,18 +0,0 @@
-# email-level group access
-users:
-  email1@example.com:
-    - group1
-    - group2
-  email2@example.com:
-    - group2
-  email3@example-no-group.com:
-
-# domain-level group access (taken from the emails)
-domains:
-  example.com:
-    - group3
-
-orchestrators:
-  group1: secrets/orchestration-group1.yaml
-  group2: secrets/orchestration-group2.yaml
-  default: secrets/orchestration-default.yaml

docker-compose.dev.yml

@@ -4,7 +4,8 @@ services:
     restart: "no"
     env_file: .env.dev
     volumes:
-      - ./app:/aa-api/app # for --reload to work
+      - ./app/web:/aa-api/app/web # for --reload to work
+      - ./app/shared:/aa-api/app/shared # for --reload to work
     environment:
       - ENVIRONMENT_FILE=.env.dev
       - SERVE_LOCAL_ARCHIVE=/aa-api/app/local_archive # See orchestration.yaml local_storage.save_to
@@ -18,7 +19,8 @@ services:
     restart: "no"
     env_file: .env.dev
     volumes:
-      - ./app:/aa-api/app # for watchmedo
+      - ./app/worker:/aa-api/app/worker # for watchmedo to work
+      - ./app/shared:/aa-api/app/shared # for watchmedo to work
 
   redis:
     restart: "no"

docker-compose.yml

@@ -19,6 +19,7 @@ services:
     volumes:
       - ./logs:/aa-api/logs
       - ./database:/aa-api/database
+      - ./secrets:/aa-api/secrets
     depends_on:
       - redis
     healthcheck:
@@ -37,6 +38,7 @@ services:
     volumes:
       - ./logs:/aa-api/logs
       - ./database:/aa-api/database
+      - ./secrets:/aa-api/secrets
       - /var/run/docker.sock:/var/run/docker.sock
       - crawls:/crawls # BROWSERTRIX_HOME_HOST:BROWSERTRIX_HOME_CONTAINER, do not change /crawls
     environment:

web.Dockerfile

@@ -13,11 +13,10 @@ RUN pip install --no-cache-dir poetry
 COPY pyproject.toml poetry.lock README.md .
 RUN poetry install --with web --no-interaction --no-ansi --no-cache
 
-# Copy the application code
+# Copy the application code and configurations
 COPY alembic.ini ./
-COPY .env* ./app/
-COPY ./secrets/ ./secrets/
 COPY ./app/ ./app/
+COPY user-groups.* ./app/
 
 # Run the FastAPI app with Uvicorn
 ENTRYPOINT ["poetry", "run"]

worker.Dockerfile

@@ -27,8 +27,7 @@ RUN ./poetry-venv/bin/poetry install --without dev --no-root --no-cache
 
 # copy source code and .env files over
 COPY alembic.ini ./
-COPY .env* ./app/
-COPY ./secrets/ ./secrets/
 COPY ./app/ ./app/
+COPY user-groups.* ./app/
 
 ENTRYPOINT ["./poetry-venv/bin/poetry", "run"]