feat: backup command — filter scan CSV by state and date range

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

src/order_bak/backup.py

@@ -0,0 +1,44 @@
+import csv
+from collections import defaultdict
+from datetime import datetime
+from pathlib import Path
+
+from order_bak.csv_utils import CSV_COLUMNS, _parse_row
+
+
+def backup_orders(
+    scan_path: Path,
+    backup_dir: Path,
+    start: datetime,
+    end: datetime,
+) -> int:
+    backup_dir.mkdir(parents=True, exist_ok=True)
+
+    by_date: dict[str, list[dict]] = defaultdict(list)
+
+    with open(scan_path, newline="") as f:
+        reader = csv.DictReader(f)
+        for raw_row in reader:
+            entity = _parse_row(raw_row)
+            if entity["state"] != 1:
+                continue
+            order_time = entity["OrderTime"]
+            if order_time is None:
+                continue
+            if order_time < start or order_time >= end:
+                continue
+            date_key = order_time.strftime("%Y-%m-%d")
+            by_date[date_key].append(raw_row)
+
+    total = 0
+    for date_key, rows in sorted(by_date.items()):
+        csv_path = backup_dir / f"{date_key}.csv"
+        with open(csv_path, "w", newline="") as f:
+            writer = csv.DictWriter(f, fieldnames=CSV_COLUMNS)
+            writer.writeheader()
+            writer.writerows(rows)
+        total += len(rows)
+        print(f"  {date_key}: {len(rows)} orders")
+
+    print(f"Backup complete: {total} orders across {len(by_date)} days")
+    return total

src/order_bak/cli.py

@@ -1,3 +1,4 @@
+from datetime import timezone
 from pathlib import Path
 
 import click
@@ -27,5 +28,34 @@ def scan(ctx):
     )
 
 
+@main.command()
+@click.option("--start", required=True, type=click.DateTime(formats=["%Y-%m-%d"]), help="Start date (UTC, inclusive)")
+@click.option("--end", required=True, type=click.DateTime(formats=["%Y-%m-%d"]), help="End date (UTC, exclusive)")
+@click.option("--scan", "scan_path", default=None, type=click.Path(), help="Path to scan CSV (default: latest in scan_dir)")
+@click.pass_context
+def backup(ctx, start, end, scan_path):
+    cfg = load_config(ctx.obj["config_path"])
+    from order_bak.backup import backup_orders
+
+    if scan_path:
+        scan_file = Path(scan_path)
+    else:
+        scan_files = sorted(cfg.scan_dir.glob("scan-*.csv"))
+        if not scan_files:
+            click.echo("No scan files found in scan_dir")
+            raise SystemExit(1)
+        scan_file = scan_files[-1]
+
+    start_utc = start.replace(tzinfo=timezone.utc)
+    end_utc = end.replace(tzinfo=timezone.utc)
+
+    backup_orders(
+        scan_path=scan_file,
+        backup_dir=Path("./backups"),
+        start=start_utc,
+        end=end_utc,
+    )
+
+
 if __name__ == "__main__":
     main()

tests/test_backup.py

@@ -0,0 +1,58 @@
+from datetime import datetime, timezone
+from pathlib import Path
+
+from order_bak.csv_utils import write_csv
+from order_bak.backup import backup_orders
+
+
+def _make_entity(pk, rk, order_time, state, receive_time=None):
+    return {
+        "PartitionKey": pk,
+        "RowKey": rk,
+        "OrderTime": order_time,
+        "ReceiveTime": receive_time,
+        "revenue": 10.0,
+        "platformOrder": "plat1",
+        "prodCount": 1,
+        "pfId": pk,
+        "prodId": "prod1",
+        "prodPrice": 10.0,
+        "state": state,
+        "ver": 3,
+        "customData": None,
+    }
+
+
+def test_backup_filters_by_state_and_date(tmp_path):
+    scan_dir = tmp_path / "scan"
+    backup_dir = tmp_path / "backups"
+    scan_dir.mkdir()
+    backup_dir.mkdir()
+
+    entities = [
+        _make_entity("u1", "o1", datetime(2025, 1, 1, 10, tzinfo=timezone.utc), 1),
+        _make_entity("u2", "o2", datetime(2025, 1, 1, 12, tzinfo=timezone.utc), 0),  # Payed, skip
+        _make_entity("u3", "o3", datetime(2025, 1, 2, 8, tzinfo=timezone.utc), 1),
+        _make_entity("u4", "o4", datetime(2025, 1, 3, 8, tzinfo=timezone.utc), 1),  # outside range
+    ]
+    scan_csv = scan_dir / "scan-2025-01-03.csv"
+    write_csv(scan_csv, entities)
+
+    result = backup_orders(
+        scan_path=scan_csv,
+        backup_dir=backup_dir,
+        start=datetime(2025, 1, 1, tzinfo=timezone.utc),
+        end=datetime(2025, 1, 3, tzinfo=timezone.utc),
+    )
+
+    assert result == 2
+    jan1 = backup_dir / "2025-01-01.csv"
+    jan2 = backup_dir / "2025-01-02.csv"
+    assert jan1.exists()
+    assert jan2.exists()
+    assert not (backup_dir / "2025-01-03.csv").exists()
+
+    from order_bak.csv_utils import read_csv
+    jan1_rows = list(read_csv(jan1))
+    assert len(jan1_rows) == 1
+    assert jan1_rows[0]["RowKey"] == "o1"