feat: scan command — full table scan to CSV with throttling

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

src/order_bak/cli.py

@@ -1,9 +1,30 @@
+from pathlib import Path
+
 import click
 
+from order_bak.config import load_config
+
 
 @click.group()
-def main():
+@click.option("--config", "-c", default="~/.config/order-bak/config.toml", type=click.Path())
-    pass
+@click.pass_context
+def main(ctx, config):
+    ctx.ensure_object(dict)
+    ctx.obj["config_path"] = Path(config).expanduser()
+
+
+@main.command()
+@click.pass_context
+def scan(ctx):
+    cfg = load_config(ctx.obj["config_path"])
+    from order_bak.scan import scan_orders
+
+    scan_orders(
+        connection_string=cfg.azure_connection_string,
+        page_size=cfg.scan_page_size,
+        delay_ms=cfg.scan_delay_ms,
+        scan_dir=cfg.scan_dir,
+    )
 
 
 if __name__ == "__main__":

src/order_bak/scan.py

@@ -0,0 +1,37 @@
+import time
+from datetime import datetime, timezone
+from pathlib import Path
+
+from azure.data.tables import TableClient
+
+from order_bak.csv_utils import CSV_COLUMNS, entity_to_row, write_csv
+
+
+def scan_orders(
+    connection_string: str,
+    page_size: int,
+    delay_ms: int,
+    scan_dir: Path,
+) -> Path:
+    table = TableClient.from_connection_string(connection_string, table_name="order")
+    scan_dir.mkdir(parents=True, exist_ok=True)
+
+    now = datetime.now(timezone.utc)
+    csv_path = scan_dir / f"scan-{now.strftime('%Y-%m-%d')}.csv"
+
+    paged = table.list_entities(results_per_page=page_size)
+
+    total_scanned = 0
+    entities_batch: list[dict] = []
+
+    for page in paged.by_page():
+        for entity in page:
+            entities_batch.append(entity)
+            total_scanned += 1
+
+        if delay_ms > 0:
+            time.sleep(delay_ms / 1000.0)
+
+    write_csv(csv_path, entities_batch)
+    print(f"Scan complete: {total_scanned} orders saved to {csv_path}")
+    return csv_path