DGC-306 keyword endpoints

.github/workflows/backend_ci.yml

@@ -0,0 +1,68 @@
+name: Backend CI
+concurrency:
+  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
+  cancel-in-progress: true
+# When this action will be executed
+on:
+  # Automatically trigger it when detected changes in repo
+  push:
+    branches:
+      - main
+    paths:
+      - "api/**"
+      - ".github/workflows/backend_ci.yml"
+  pull_request:
+    branches:
+      - main
+    paths:
+      - "api/**"
+      - ".github/workflows/backend_ci.yml"
+
+  # Allow manual trigger
+  workflow_dispatch:
+
+permissions:
+  contents: read
+  issues: read
+  checks: write
+  pull-requests: write
+
+jobs:
+  pytest:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Install Python
+        uses: actions/setup-python@v4
+        with:
+          python-version: 3.11
+
+      - name: Install poetry
+        uses: abatilo/actions-poetry@v2
+
+      - name: Setup a local virtual environment (if no poetry.toml file)
+        run: |
+          poetry config virtualenvs.create true --local
+          poetry config virtualenvs.in-project true --local
+
+      - name: Define a cache for the virtual environment based on the dependencies lock file
+        uses: actions/cache@v3
+        with:
+          path: ./api/.venv
+          key: venv-${{ hashFiles('poetry.lock') }}
+
+      - name: Install the project dependencies
+        working-directory: api
+        run: poetry install --with=dev
+
+      - name: Run Pytest
+        working-directory: api
+        run: poetry run pytest tests/ --junit-xml=test-results.xml
+
+      - name: Publish Test Results
+        uses: EnricoMi/publish-unit-test-result-action@v2
+        if: always()
+        with:
+          files: |
+            api/test-results.xml

api/Dockerfile

@@ -8,7 +8,7 @@
 # PYTHON-BASE
 # Sets up all our shared environment variables
 ################################
-FROM python:3.11-slim as python-base
+FROM python:3.11-slim AS python-base
 
     # python
 ENV PYTHONUNBUFFERED=1 \
@@ -44,7 +44,7 @@ ENV PATH="$POETRY_HOME/bin:$VENV_PATH/bin:$PATH"
 # BUILDER-BASE
 # Used to build deps + create our virtual environment
 ################################
-FROM python-base as builder-base
+FROM python-base AS builder-base
 RUN apt-get update \
     && apt-get install --no-install-recommends -y \
         # deps for installing poetry
@@ -72,7 +72,7 @@ RUN --mount=type=cache,target=/root/.cache \
 # DEVELOPMENT
 # Image used during development / testing
 ################################
-FROM python-base as development
+FROM python-base AS development
 ENV FASTAPI_ENV=development
 WORKDIR $PYSETUP_PATH
 

api/README.md

@@ -1,3 +1,47 @@
 # API
 
-This folder contains the API backend for the project. It is a FastAPI application that uses the stac-fastapi library to provide a STAC compliant API. It uses OpenSearch to store the STAC objects and Postgres to store information about users.
+This folder contains the API backend for the project. It is a FastAPI application that uses the stac-fastapi library to provide a STAC compliant API. It uses OpenSearch to store the STAC objects and Postgres to store information about users.
+
+The following Python libraries are used in this project:
+
+- [FastAPI](https://fastapi.tiangolo.com/)
+    - To generate the API including openapi documentation
+- [stac-fastapi-opensearch]
+    - The base Stac API backed by OpenSearch
+- [SQLAlchemy](https://www.sqlalchemy.org/)
+    - To interact with the Postgres database
+- [alembic](https://alembic.sqlalchemy.org/en/latest/)
+    - To manage database migrations
+- [sqlmodel](https://sqlmodel.tiangolo.com/)
+    - To define the database models that are Pydantic compatible allowing them to be returned by the FastAPI endpoints
+
+
+## Database
+
+To run the API you will need to have a Postgres database running. You can use the following command to start a Postgres database using Docker:
+
+```bash
+docker compose up postgres -d
+```
+
+This will start a Postgres database running on port 5432 with the username and password set to `postgres`.
+
+To create the database tables you can run the following command:
+
+```bash
+docker compose exec stac-api alembic upgrade head
+```
+
+### Migrations
+
+When developing new database models, you will need to create a new migration. You can do this by running the following command:
+ (replace `Add new table` with a description of the migration)
+```bash
+docker compose exec stac-api alembic revision --autogenerate -m "Add new table"
+```
+
+This will create a new migration file in the `alembic/versions` folder. You can then apply this migration by running:
+
+```bash
+docker compose exec stac-api alembic upgrade head
+```

api/alembic.ini

@@ -0,0 +1,113 @@
+# A generic, single database configuration.
+
+[alembic]
+# path to migration scripts
+# Use forward slashes (/) also on windows to provide an os agnostic path
+script_location = dmsapi/alembic
+
+# template used to generate migration file names; The default value is %%(rev)s_%%(slug)s
+# Uncomment the line below if you want the files to be prepended with date and time
+# see https://alembic.sqlalchemy.org/en/latest/tutorial.html#editing-the-ini-file
+# for all available tokens
+# file_template = %%(year)d_%%(month).2d_%%(day).2d_%%(hour).2d%%(minute).2d-%%(rev)s_%%(slug)s
+
+# sys.path path, will be prepended to sys.path if present.
+# defaults to the current working directory.
+prepend_sys_path = .
+
+# timezone to use when rendering the date within the migration file
+# as well as the filename.
+# If specified, requires the python>=3.9 or backports.zoneinfo library.
+# Any required deps can installed by adding `alembic[tz]` to the pip requirements
+# string value is passed to ZoneInfo()
+# leave blank for localtime
+# timezone =
+
+# max length of characters to apply to the "slug" field
+# truncate_slug_length = 40
+
+# set to 'true' to run the environment during
+# the 'revision' command, regardless of autogenerate
+# revision_environment = false
+
+# set to 'true' to allow .pyc and .pyo files without
+# a source .py file to be detected as revisions in the
+# versions/ directory
+# sourceless = false
+
+# version location specification; This defaults
+# to dmsapi/alembic/versions.  When using multiple version
+# directories, initial revisions must be specified with --version-path.
+# The path separator used here should be the separator specified by "version_path_separator" below.
+# version_locations = %(here)s/bar:%(here)s/bat:dmsapi/alembic/versions
+
+# version path separator; As mentioned above, this is the character used to split
+# version_locations. The default within new alembic.ini files is "os", which uses os.pathsep.
+# If this key is omitted entirely, it falls back to the legacy behavior of splitting on spaces and/or commas.
+# Valid values for version_path_separator are:
+#
+# version_path_separator = :
+# version_path_separator = ;
+# version_path_separator = space
+version_path_separator = os  # Use os.pathsep. Default configuration used for new projects.
+
+# set to 'true' to search source files recursively
+# in each "version_locations" directory
+# new in Alembic version 1.10
+# recursive_version_locations = false
+
+# the output encoding used when revision files
+# are written from script.py.mako
+# output_encoding = utf-8
+
+[post_write_hooks]
+# post_write_hooks defines scripts or Python functions that are run
+# on newly generated revision scripts.  See the documentation for further
+# detail and examples
+
+# format using "black" - use the console_scripts runner, against the "black" entrypoint
+# hooks = black
+# black.type = console_scripts
+# black.entrypoint = black
+# black.options = -l 79 REVISION_SCRIPT_FILENAME
+
+# lint with attempts to fix using "ruff" - use the exec runner, execute a binary
+# hooks = ruff
+# ruff.type = exec
+# ruff.executable = %(here)s/.venv/bin/ruff
+# ruff.options = --fix REVISION_SCRIPT_FILENAME
+
+# Logging configuration
+[loggers]
+keys = root,sqlalchemy,alembic
+
+[handlers]
+keys = console
+
+[formatters]
+keys = generic
+
+[logger_root]
+level = WARN
+handlers = console
+qualname =
+
+[logger_sqlalchemy]
+level = WARN
+handlers =
+qualname = sqlalchemy.engine
+
+[logger_alembic]
+level = INFO
+handlers =
+qualname = alembic
+
+[handler_console]
+class = StreamHandler
+args = (sys.stderr,)
+level = NOTSET
+formatter = generic
+
+[formatter_generic]
+format = %(levelname)-5.5s [%(name)s] %(message)s
+datefmt = %H:%M:%S

api/dmsapi/alembic/README

@@ -0,0 +1 @@
+Generic single-database configuration.

api/dmsapi/alembic/env.py

@@ -0,0 +1,86 @@
+from logging.config import fileConfig
+
+from sqlalchemy import engine_from_config
+from sqlalchemy import pool
+
+from alembic import context
+from sqlmodel import SQLModel
+import dmsapi.database.models
+from dmsapi.app import settings
+
+url = settings.db_connection_url
+
+# this is the Alembic Config object, which provides
+# access to the values within the .ini file in use.
+config = context.config
+
+# Interpret the config file for Python logging.
+# This line sets up loggers basically.
+if config.config_file_name is not None:
+    fileConfig(config.config_file_name)
+
+# add your model's MetaData object here
+# for 'autogenerate' support
+# from myapp import mymodel
+# target_metadata = mymodel.Base.metadata
+target_metadata = SQLModel.metadata
+
+# other values from the config, defined by the needs of env.py,
+# can be acquired:
+# my_important_option = config.get_main_option("my_important_option")
+# ... etc.
+
+
+def run_migrations_offline() -> None:
+    """Run migrations in 'offline' mode.
+
+    This configures the context with just a URL
+    and not an Engine, though an Engine is acceptable
+    here as well.  By skipping the Engine creation
+    we don't even need a DBAPI to be available.
+
+    Calls to context.execute() here emit the given string to the
+    script output.
+
+    """
+    context.configure(
+        url=url,
+        target_metadata=target_metadata,
+        literal_binds=True,
+        dialect_opts={"paramstyle": "named"},
+    )
+
+    with context.begin_transaction():
+        context.run_migrations()
+
+
+def run_migrations_online() -> None:
+    """Run migrations in 'online' mode.
+
+    In this scenario we need to create an Engine
+    and associate a connection with the context.
+
+    """
+
+    connectable = engine_from_config(
+        config.get_section(config.config_ini_section, {}),
+        prefix="sqlalchemy.",
+        poolclass=pool.NullPool,
+        url=url,
+    )
+
+    with connectable.connect() as connection:
+        context.configure(
+            connection=connection,
+            target_metadata=target_metadata,
+            user_module_prefix="sqlmodel.",
+        )
+
+        with context.begin_transaction():
+            context.run_migrations()
+
+
+if context.is_offline_mode():
+    run_migrations_offline()
+else:
+    run_migrations_online()

api/dmsapi/alembic/script.py.mako

@@ -0,0 +1,27 @@
+"""${message}
+
+Revision ID: ${up_revision}
+Revises: ${down_revision | comma,n}
+Create Date: ${create_date}
+
+"""
+from typing import Sequence, Union
+
+from alembic import op
+import sqlalchemy as sa
+import sqlmodel
+${imports if imports else ""}
+
+# revision identifiers, used by Alembic.
+revision: str = ${repr(up_revision)}
+down_revision: Union[str, None] = ${repr(down_revision)}
+branch_labels: Union[str, Sequence[str], None] = ${repr(branch_labels)}
+depends_on: Union[str, Sequence[str], None] = ${repr(depends_on)}
+
+
+def upgrade() -> None:
+    ${upgrades if upgrades else "pass"}
+
+
+def downgrade() -> None:
+    ${downgrades if downgrades else "pass"}