Dockerize local dev env and set up task queue

Working on dev deploy

Working on dev deployment

Fix typo

Try Procfile

Still working on dev deployment

Trying a new approach to dev deploy

Update imports in app context

ga

Revert

Add alembic to handle migrations

Fix alembic hookup to db

Formatting

Format alembic files

Trying to set up hot reloading

Tweak docker configuration

Add container and image names back to compose.yml

Fix alembic migrations

Working on Minio integration for local dev

Continue trying to get boto3 to connect to minio

Successfully test s3 interface

Successfully test s3 interface

Remove artifact

First data handling use case

Tweak message to user

Remove artifact

Add test case for new use case

Test example validation function

Add types to validation function

Format and add comments to Dockerfile

Refactor filename logic

Tweak fake/mock filename

Revert to previous storage handling method

Make small refinements to temp file handling

Change way task is initiated

Update Dockerfile so that root user no longer runs app and queue

Remove extraneous code

Update ingest use rcase to print out filename

Housekeeping re contracts for application services

Use data class for download result instead of anonymous tuple

Clean up docker files

Add example env file and update readme to let user know they need to set it up

.dockerignore

@@ -0,0 +1,25 @@
+# commonly generated files
+__pycache__
+*.pyc
+*.pyo
+.pytest_cache/
+.git
+.svn
+node_modules/
+dist/
+build/
+
+# IDE and editor configuration
+.idea/
+.vscode/
+.project
+.settings/
+
+# dependency management files
+Pipfile*
+
+# documentation
+documentation/
+
+# artifacts
+*.zip

.gitignore

@@ -165,5 +165,8 @@ cython_debug/
 # Development storage
 storage/
 
-# Development task queue
-celery_broker/
+# Test task queue
+control/
+
+# Zipped artifaces
+*.zip

Dockerfile

@@ -0,0 +1,36 @@
+# Setup Python
+FROM python:3.11-slim
+ENV PYTHONUNBUFFERED 1
+ENV PYTHONDONTWRITEBYTECODE 1
+
+# Create a non-root user to run the app
+RUN useradd --create-home --shell /bin/bash appuser
+
+# Update and install packages
+RUN apt-get update && apt-get install -y \
+    curl \
+    binutils \
+    build-essential \
+    gdal-bin \
+    libgdal-dev \
+    --no-install-recommends && rm -rf /var/lib/apt/lists/*
+
+# Set GDAL environment variables
+ENV CPLUS_INCLUDE_PATH=/usr/include/gdal \
+    C_INCLUDE_PATH=/usr/include/gdal \
+    GDAL_VERSION=3.6.2
+
+# Install GDAL Python bindings with the specified version
+RUN pip install GDAL==$GDAL_VERSION
+
+# Install Python Poetry for managing project dependencies in /opt/poetry
+RUN curl -sSL https://install.python-poetry.org | POETRY_HOME=/opt/poetry python3 -
+USER appuser
+ENV PATH="${PATH}:/opt/poetry/bin"
+
+# Install dependencies and start app
+WORKDIR /app
+COPY pyproject.toml poetry.lock ./
+RUN poetry install --only main
+COPY . .
+CMD ["/bin/sh", "start_local.sh"]

README.md

@@ -1,3 +1,44 @@
 # 10x National Address Database Collaboration Hub (NAD-CH)
 
-Coming soon!
+## Local Development
+
+Install [poetry](https://python-poetry.org/docs/#installation) so that you can
+run tests and scripts locally.
+
+Clone the repostiory:
+
+```bash
+git clone https://github.com/GSA-TTS/10x-nad-ch/
+```
+
+In order to set up a local development environment, you will need to download
+[Docker](https://www.docker.com/).
+
+To set the necessary environment variables, copy the `sample.env` file to a new
+file named `.env` in the same directory:
+
+```bash
+cp sample.env .env
+```
+
+Update all settings defaulted to `<add_a_key_here>`.
+
+Run the following command to build the app and start up its services:
+
+```bash
+docker compose up --build
+```
+
+To run database migrations:
+
+```bash
+docker exec nad-ch-dev-local poetry run alembic upgrade head
+```
+
+## Testing
+
+Run the test suite as follows:
+
+```bash
+poetry run test
+```

alembic.ini

@@ -0,0 +1,116 @@
+# A generic, single database configuration.
+
+[alembic]
+# path to migration scripts
+script_location = 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 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: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
+
+sqlalchemy.url = driver://user:pass@localhost/dbname
+
+
+[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

alembic/README

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

alembic/env.py

@@ -0,0 +1,79 @@
+from logging.config import fileConfig
+
+from sqlalchemy import engine_from_config
+from sqlalchemy import pool
+
+from alembic import context
+from nad_ch.config import DATABASE_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)
+
+config.set_main_option("sqlalchemy.url", DATABASE_URL)
+
+# add your model's MetaData object here
+# for 'autogenerate' support
+# from myapp import mymodel
+# target_metadata = mymodel.Base.metadata
+target_metadata = None
+
+# 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.
+
+    """
+    url = config.get_main_option("sqlalchemy.url")
+    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,
+    )
+
+    with connectable.connect() as connection:
+        context.configure(connection=connection, target_metadata=target_metadata)
+
+        with context.begin_transaction():
+            context.run_migrations()
+
+
+if context.is_offline_mode():
+    run_migrations_offline()
+else:
+    run_migrations_online()

alembic/script.py.mako

@@ -0,0 +1,26 @@
+"""${message}
+
+Revision ID: ${up_revision}
+Revises: ${down_revision | comma,n}
+Create Date: ${create_date}
+
+"""
+from typing import Sequence, Union
+
+from alembic import op
+import sqlalchemy as sa
+${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"}

alembic/versions/a6db87212637_create_data_providers_table.py

@@ -0,0 +1,44 @@
+"""create data_providers table
+
+Revision ID: a6db87212637
+Revises:
+Create Date: 2024-01-26 12:20:03.153358
+
+"""
+from typing import Sequence, Union
+
+from alembic import op
+import sqlalchemy as sa
+from sqlalchemy.sql import func
+
+
+# revision identifiers, used by Alembic.
+revision: str = "a6db87212637"
+down_revision: Union[str, None] = None
+branch_labels: Union[str, Sequence[str], None] = None
+depends_on: Union[str, Sequence[str], None] = None
+
+
+def upgrade():
+    op.create_table(
+        "data_providers",
+        sa.Column("id", sa.Integer, primary_key=True),
+        sa.Column(
+            "created_at",
+            sa.DateTime(timezone=True),
+            server_default=func.now(),
+            nullable=False,
+        ),
+        sa.Column(
+            "updated_at",
+            sa.DateTime(timezone=True),
+            server_default=func.now(),
+            onupdate=func.now(),
+            nullable=False,
+        ),
+        sa.Column("name", sa.String, nullable=False),
+    )
+
+
+def downgrade():
+    op.drop_table("data_providers")