fix: stream scan writes instead of accumulating in memory

src/order_bak/scan.py

@@ -1,10 +1,11 @@
+import csv
 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
+from order_bak.csv_utils import CSV_COLUMNS
 
 
 def scan_orders(
@@ -22,16 +23,26 @@ def scan_orders(
     paged = table.list_entities(results_per_page=page_size)
 
     total_scanned = 0
-    entities_batch: list[dict] = []
 
-    for page in paged.by_page():
+    with open(csv_path, "w", newline="") as f:
-        for entity in page:
+        writer = csv.DictWriter(f, fieldnames=CSV_COLUMNS)
-            entities_batch.append(entity)
+        writer.writeheader()
-            total_scanned += 1
 
-        if delay_ms > 0:
+        for page in paged.by_page():
-            time.sleep(delay_ms / 1000.0)
+            for entity in page:
+                writer.writerow({col: _fmt(entity.get(col)) for col in CSV_COLUMNS})
+                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
+
+
+def _fmt(val):
+    if val is None:
+        return ""
+    if isinstance(val, datetime):
+        return val.isoformat()
+    return str(val)