"keep data on the server" opt-in/out

bincio/extract/ingest.py

@@ -10,7 +10,6 @@ from __future__ import annotations
 import json
 from pathlib import Path
 from typing import Any, Optional
-
 from bincio.extract.models import ParsedActivity
 
 
@@ -67,6 +66,7 @@ def strava_sync(
     data_dir: Path,
     client_id: str,
     client_secret: str,
+    originals_dir: Optional[Path] = None,
 ) -> dict[str, Any]:
     """Fetch new Strava activities and ingest them into data_dir.
 
@@ -119,6 +119,12 @@ def strava_sync(
                 skipped += 1
                 continue
             streams = fetch_streams(token["access_token"], meta["id"])
+            if originals_dir is not None:
+                orig_path = originals_dir / f"{activity_id}.json"
+                orig_path.write_text(
+                    json.dumps({"meta": meta, "streams": streams}, indent=2),
+                    encoding="utf-8",
+                )
             parsed = strava_to_parsed(meta, streams)
             ingest_parsed(parsed, data_dir, privacy="public", rdp_epsilon=0.0001)
             imported += 1