sientia-dataops-laborious-legacy/laborious/utils/connectors_config.py

import json
from os import getenv
from typing import Any


def _build_mlflow_tracking_url() -> str:
    """
    Compose a single tracking URI for ``SientiaMLflowRepository`` from host and port env vars.

    If ``MLFLOW_HOST`` already contains a port in the authority (e.g. ``http://tracker:80``),
    it is returned unchanged so operators can override port logic explicitly.

    Return:
        str: Full tracking URL (scheme + host [+ port]).
    """

    mlflow_host = getenv('MLFLOW_HOST', 'http://localhost').rstrip('/')
    mlflow_port = getenv('MLFLOW_PORT', '5080')

    # Host already includes an explicit port (e.g. http://tracker:80)
    host_after_scheme = mlflow_host.split('://', 1)[-1]
    if ':' in host_after_scheme:
        return mlflow_host

    return f'{mlflow_host}:{mlflow_port}'


def build_mlflow_config() -> dict[str, Any]:
    """
    Read MLflow tracking and registry credentials from the environment.

    Used by ``Activities`` when constructing ``SientiaMLflowRepository``. The ``url`` value is the
    same string workers and notebooks should use for ``MLFLOW_TRACKING_URI``-style clients.

    Environment Variables:
        MLFLOW_HOST: Host with scheme; port optional if MLFLOW_PORT is set (default: http://localhost)
        MLFLOW_PORT: Appended when host has no explicit port (default: 5080)
        MLFLOW_USERNAME: Basic-auth or service user (default: aignosi)
        MLFLOW_PASSWORD: Password or token (default: aignosi)

    Return:
        dict[str, Any]: ``url``, ``username``, ``password``.
    """
    return {
        'url': _build_mlflow_tracking_url(),
        'username': getenv('MLFLOW_USERNAME', 'aignosi'),
        'password': getenv('MLFLOW_PASSWORD', 'aignosi'),
    }


def build_plugin_store_config() -> dict[str, Any]:
    """
    Collect settings for ``PluginStore`` (Git-backed catalog + runtime install via pip).

    Mirrors the model-manager service: the worker passes these kwargs into ``PluginStore`` after
    ``install_runtime`` resolves wheels from the configured PyPI index. Missing optional env vars
    become ``None`` so the store can run without auth in local dev.

    Environment Variables:
        STORE_BASE_URL: Git HTTP(S) server (e.g. Gitea) base URL (default: http://localhost:3000)
        STORE_OWNER: Namespace or org owning the store repo (default: sientia)
        STORE_REPO: Repository name (default: model-library-store)
        STORE_BRANCH: Checkout branch; unset lets the client use default
        STORE_USERNAME / STORE_PASSWORD: HTTP basic credentials for Git fetch
        STORE_CACHE_TTL_SECONDS: Optional integer seconds for metadata cache TTL
        PYPI_SERVER: Index URL for ``pip install`` during runtime install (default: http://localhost:5000)
        PYPI_USERNAME / PYPI_PASSWORD: Optional index authentication

    Return:
        dict[str, Any]: Keys aligned with ``PluginStore`` constructor parameter names.
    """

    cache_ttl_seconds = getenv('STORE_CACHE_TTL_SECONDS')
    return {
        'base_url': getenv('STORE_BASE_URL', 'http://localhost:3000'),
        'owner': getenv('STORE_OWNER', 'sientia'),
        'repo': getenv('STORE_REPO', 'model-library-store'),
        'username': getenv('STORE_USERNAME'),
        'password': getenv('STORE_PASSWORD'),
        'branch': getenv('STORE_BRANCH'),
        'cache_ttl_seconds': int(cache_ttl_seconds) if cache_ttl_seconds else None,
        'pypi_index_url': getenv('PYPI_SERVER', 'http://localhost:5000'),
        'pypi_username': getenv('PYPI_USERNAME'),
        'pypi_password': getenv('PYPI_PASSWORD'),
    }


def build_opc_config() -> dict[str, Any]:
    """
    Build OPC server configuration from environment variables.

    This function constructs an OPC server configuration dictionary from
    environment variables. It supports both single server and multi-server
    configurations with flexible parameter handling.

    Environment Variables:
        OPC_CONFIG: JSON string containing multiple OPC server configurations
        OPC_ID: OPC server ID (fallback, default: 1)
        OPC_URL: Single OPC server URL (fallback, default: opc.tcp://localhost:4840)
        OPC_SERVER_URI: Single OPC server URI (fallback, default: opc.tcp://localhost:4840)
        OPC_CERT_PATH: Client certificate path (fallback, default: None)
        OPC_PRIVATE_KEY_PATH: Client private key path (fallback, default: None)
        OPC_SERVER_CERT_PATH: Server certificate path (fallback, default: None)
        OPC_RECONNECTION_INTERVAL: Reconnection interval in seconds (fallback, default: 120)

    Returns:
        dict: OPC server configuration dictionary
    """
    opc_raw = getenv('OPC_CONFIG', None)

    if opc_raw:
        return json.loads(opc_raw)

    return {
        getenv('OPC_ID', '1'): {
            'id': getenv('OPC_ID', '1'),
            'server_name': getenv('OPC_SERVER_NAME', 'default_server'),
            'url': getenv('OPC_URL', 'opc.tcp://localhost:4840'),
            'server_uri': getenv('OPC_SERVER_URI', 'opc.tcp://localhost:4840'),
            'cert_path': getenv('OPC_CERT_PATH', None),
            'private_key_path': getenv('OPC_PRIVATE_KEY_PATH', None),
            'server_cert_path': getenv('OPC_SERVER_CERT_PATH', None),
            'reconnection_interval': int(getenv('OPC_RECONNECTION_INTERVAL', '120')),
        }
    }


def build_minio_config() -> dict[str, Any]:
    """
    Build MinIO (S3-compatible) configuration from environment variables.

    Environment Variables:
        MINIO_ENDPOINT_URL: Host:port or URL for the S3 API (default: http://localhost:9000)
        MINIO_ACCESS_KEY: Access key (default: minioadmin)
        MINIO_SECRET_KEY: Secret key (default: minioadmin)
        MINIO_DEFAULT_BUCKET: Default bucket for Laborious payloads (default: laborious)
        MINIO_RETENTION_HOURS: Offloaded object retention window (default: 24)
        MINIO_SECURE: If ``true``, use HTTPS (default: false)

    Return:
        dict[str, Any]: Keys consumed by ``Activities`` / ``MinioRepository``.
    """
    return {
        'endpoint_url': getenv('MINIO_ENDPOINT_URL', 'http://localhost:9000'),
        'access_key': getenv('MINIO_ACCESS_KEY', 'minioadmin'),
        'secret_key': getenv('MINIO_SECRET_KEY', 'minioadmin'),
        'default_bucket': getenv('MINIO_DEFAULT_BUCKET', 'laborious'),
        'retention_hours': int(getenv('MINIO_RETENTION_HOURS', '24')),
        'secure': getenv('MINIO_SECURE', 'false') == 'true',
    }