fpu-barometer-admin 0.3.0__py3-none-any.whl

fpu_barometer_admin/__init__.py

@@ -0,0 +1,6 @@
+"""FPU Admin backend/admin implementation package."""
+
+from .runners import DatasetRunner, DatasetRunResult
+
+__version__ = "0.3.0"
+__all__ = ["DatasetRunner", "DatasetRunResult"]

fpu_barometer_admin/cli/__init__.py

@@ -0,0 +1,5 @@
+"""Command-line interface for FPU admin pipeline."""
+
+from .commands import cli
+
+__all__ = ["cli"]

fpu_barometer_admin/cli/commands.py

@@ -0,0 +1,199 @@
+"""CLI commands for the canonical FPU admin package."""
+
+from __future__ import annotations
+
+import os
+from pathlib import Path
+
+import click
+
+from fpu_barometer_admin.cli.deploy import (
+    AzureCodeRedeployConfig,
+    AzureDeployConfig,
+    deploy_azure,
+    redeploy_azure_code,
+)
+from fpu_barometer_admin.runners import DatasetRunner
+from fpu_barometer_admin.runners.seed import seed_gdelt_processed_artifact
+from fpu_barometer_admin.storage import create_storage_runtime_from_env
+
+
+@click.group()
+@click.option("--data-path", default="./data", help="Path to data directory")
+@click.pass_context
+def cli(ctx: click.Context, data_path: str):
+    """FPU Admin command line interface."""
+    ctx.ensure_object(dict)
+    runtime_env = dict(os.environ)
+    runtime_env["FPU_DATA_PATH"] = str(Path(data_path))
+    ctx.obj["runtime_env"] = runtime_env
+
+
+@cli.command("deploy-azure")
+@click.option("--resource-group", default="fpu-research-rg", show_default=True)
+@click.option("--location", default="westeurope", show_default=True)
+@click.option("--environment", default="prod", show_default=True)
+@click.option("--storage-container", default="datasets", show_default=True)
+@click.option(
+    "--project-root",
+    type=click.Path(file_okay=False, path_type=Path),
+    default=None,
+    help="Project root containing pyproject.toml. Auto-detected when omitted.",
+)
+@click.option("--python-version", default="3.10", show_default=True)
+def deploy_azure_command(
+    resource_group: str,
+    location: str,
+    environment: str,
+    storage_container: str,
+    project_root: Path | None,
+    python_version: str,
+):
+    """Deploy Barometer's Azure Functions API and Blob storage."""
+
+    result = deploy_azure(
+        AzureDeployConfig(
+            resource_group=resource_group,
+            location=location,
+            environment=environment,
+            storage_container=storage_container,
+            project_root=project_root,
+            python_version=python_version,
+        )
+    )
+    click.echo(f"function_app={result.function_app}")
+    click.echo(f"function_app_url={result.function_app_url}")
+    click.echo(f"storage_account={result.storage_account}")
+    click.echo(f"storage_container={result.storage_container}")
+    click.echo(f"config_path={result.config_path}")
+
+
+@cli.command("redeploy-azure-code")
+@click.option("--resource-group", default=None, help="Existing Azure resource group.")
+@click.option("--function-app", default=None, help="Existing Azure Function App name.")
+@click.option(
+    "--project-root",
+    type=click.Path(file_okay=False, path_type=Path),
+    default=None,
+    help="Project root containing pyproject.toml. Auto-detected when omitted.",
+)
+@click.option("--scheduler-cron", default="0 15 2 * * *", show_default=True)
+def redeploy_azure_code_command(
+    resource_group: str | None,
+    function_app: str | None,
+    project_root: Path | None,
+    scheduler_cron: str,
+):
+    """Redeploy code to an existing Azure Function App without touching storage."""
+
+    result = redeploy_azure_code(
+        AzureCodeRedeployConfig(
+            resource_group=resource_group,
+            function_app=function_app,
+            project_root=project_root,
+            scheduler_cron=scheduler_cron,
+        )
+    )
+    click.echo(f"function_app={result.function_app}")
+    click.echo(f"function_app_url={result.function_app_url}")
+    click.echo(f"resource_group={result.resource_group}")
+    click.echo(f"scheduler_cron={result.scheduler_cron}")
+    click.echo(f"config_path={result.config_path}")
+
+
+@cli.command("seed-processed-artifact")
+@click.argument("dataset")
+@click.option(
+    "--processed-artifact",
+    "processed_path",
+    required=True,
+    type=click.Path(exists=True, dir_okay=False, path_type=Path),
+    help="Local canonical processed GDELT Event Parquet artifact to publish to Azure.",
+)
+@click.option(
+    "--watermark-after",
+    required=True,
+    help="Explicit GDELT watermark after the seeded period, as YYYYmmddHHMMSS.",
+)
+@click.option(
+    "--azure-storage-connection-string",
+    envvar="FPU_AZURE_STORAGE_CONNECTION_STRING",
+    required=True,
+    help="Azure Storage connection string for the target Barometer storage account.",
+)
+@click.option(
+    "--azure-storage-container",
+    envvar="FPU_AZURE_STORAGE_CONTAINER",
+    default="datasets",
+    show_default=True,
+    help="Azure Blob container containing Barometer dataset objects and catalog records.",
+)
+@click.pass_context
+def seed_processed_artifact(
+    ctx: click.Context,
+    dataset: str,
+    processed_path: Path,
+    watermark_after: str,
+    azure_storage_connection_string: str,
+    azure_storage_container: str,
+):
+    """Publish a local processed replacement artifact to Azure and update the catalog."""
+
+    if dataset != "gdelt":
+        raise click.BadParameter("only 'gdelt' is supported", param_hint="dataset")
+    if len(watermark_after) != 14 or not watermark_after.isdigit():
+        raise click.BadParameter(
+            "must be in YYYYmmddHHMMSS format", param_hint="--watermark-after"
+        )
+    if processed_path.suffix.lower() != ".parquet":
+        raise click.BadParameter(
+            "must point to a local processed .parquet file",
+            param_hint="--processed-artifact",
+        )
+
+    runtime_env = dict(ctx.obj["runtime_env"])
+    runtime_env["FPU_STORAGE_BACKEND"] = "azure"
+    runtime_env["FPU_AZURE_STORAGE_CONNECTION_STRING"] = azure_storage_connection_string
+    runtime_env["FPU_AZURE_STORAGE_CONTAINER"] = azure_storage_container
+    runtime = create_storage_runtime_from_env(runtime_env)
+    result = seed_gdelt_processed_artifact(
+        object_storage=runtime.object_storage,
+        catalog=runtime.create_catalog(),
+        processed_path=processed_path,
+        watermark_after=watermark_after,
+        reader_provider=runtime.get_reader,
+    )
+    for key, value in result.key_values():
+        click.echo(f"{key}={value}")
+    if result.status == "failed":
+        raise click.exceptions.Exit(1)
+    if result.status == "partial_success":
+        raise click.exceptions.Exit(3)
+
+
+@cli.command("run-acled-static")
+@click.pass_context
+def run_acled_static(ctx: click.Context):
+    """Run the static ACLED Dataset Runner tracer."""
+    runtime = create_storage_runtime_from_env(ctx.obj["runtime_env"])
+    with DatasetRunner.from_runtime(runtime) as runner:
+        result = runner.run_dataset("acled")
+
+    click.echo(f"status={result.status}")
+    click.echo(f"run_id={result.run_id}")
+    click.echo(f"version_id={result.version_id}")
+    click.echo(f"stages={','.join(result.stages)}")
+
+
+@cli.command("run-rr-static")
+@click.pass_context
+def run_rr_static(ctx: click.Context):
+    """Run the static RR Dataset Runner tracer."""
+    runtime = create_storage_runtime_from_env(ctx.obj["runtime_env"])
+    with DatasetRunner.from_runtime(runtime) as runner:
+        result = runner.run_dataset("rr")
+
+    click.echo(f"status={result.status}")
+    click.echo(f"run_id={result.run_id}")
+    click.echo(f"version_id={result.version_id}")
+    click.echo(f"stages={','.join(result.stages)}")