backend: initial commit

bincio/extract/strava_csv.py

@@ -0,0 +1,55 @@
+"""Import metadata from Strava's activities.csv bulk export.
+
+Strava export columns we care about:
+  Activity ID, Activity Date, Activity Name, Activity Type,
+  Activity Description, Filename
+"""
+
+import csv
+import re
+from pathlib import Path
+from typing import Optional
+
+
+_STRAVA_DATE_FMTS = (
+    "%b %d, %Y, %I:%M:%S %p",  # "Jun 1, 2024, 7:30:12 AM"
+    "%Y-%m-%d %H:%M:%S",
+)
+
+
+class StravaMetadata:
+    """Maps original filename → Strava metadata."""
+
+    def __init__(self, csv_path: Path) -> None:
+        self._by_filename: dict[str, dict] = {}
+        self._load(csv_path)
+
+    def _load(self, path: Path) -> None:
+        with path.open(newline="", encoding="utf-8-sig") as f:
+            reader = csv.DictReader(f)
+            for row in reader:
+                filename = row.get("Filename", "").strip()
+                if not filename:
+                    continue
+                # Strava stores paths like "activities/12345.fit.gz"
+                basename = Path(filename).name
+                self._by_filename[basename] = row
+
+    def lookup(self, source_file: str) -> Optional[dict]:
+        """Return the Strava CSV row for a given source filename, or None."""
+        return self._by_filename.get(source_file)
+
+    def enrich(self, source_file: str, activity: object) -> None:
+        """Mutate a ParsedActivity with Strava metadata if found."""
+        row = self.lookup(source_file)
+        if row is None:
+            return
+
+        if not activity.title and row.get("Activity Name"):  # type: ignore[attr-defined]
+            activity.title = row["Activity Name"].strip()  # type: ignore[attr-defined]
+
+        if not activity.description and row.get("Activity Description"):  # type: ignore[attr-defined]
+            activity.description = row["Activity Description"].strip()  # type: ignore[attr-defined]
+
+        if not activity.strava_id and row.get("Activity ID"):  # type: ignore[attr-defined]
+            activity.strava_id = row["Activity ID"].strip()  # type: ignore[attr-defined]