All tweaks added

backend/app/services/fit_parser.py

@@ -1,21 +1,24 @@
 """
-Parses Garmin .fit files and GPX files into normalized activity data.
-Handles full Strava and Garmin data export archives.
+FIT and GPX file parser using:
+- Official Garmin FIT Python SDK (garmin-fit-sdk) for .fit files
+- gpxpy for .gpx files
+
+The official SDK correctly handles scale/offset, component expansion,
+semicircle-to-degree conversion, and HR message merging.
 """
-import os
-import zipfile
-import json
 import math
 from pathlib import Path
-from datetime import datetime, timezone
+from datetime import datetime, timezone, timedelta
 from typing import Optional
-import fitparse
 import gpxpy
 import polyline as polyline_lib
 
 
+FIT_EPOCH_S = 631065600
+
+
 def haversine_distance(lat1, lon1, lat2, lon2) -> float:
-    """Returns distance in metres between two GPS points."""
+    """Distance in metres between two GPS points."""
     R = 6371000
     phi1, phi2 = math.radians(lat1), math.radians(lat2)
     dphi = math.radians(lat2 - lat1)
@@ -24,106 +27,100 @@ def haversine_distance(lat1, lon1, lat2, lon2) -> float:
     return 2 * R * math.asin(math.sqrt(a))
 
 
-def semicircles_to_degrees(sc: int) -> float:
-    return sc * (180 / 2**31)
+def _safe_float(val) -> Optional[float]:
+    try:
+        return float(val) if val is not None else None
+    except (TypeError, ValueError):
+        return None
+
+
+def _bounding_box(coords: list) -> Optional[dict]:
+    if not coords:
+        return None
+    lats = [c[0] for c in coords]
+    lons = [c[1] for c in coords]
+    return {"min_lat": min(lats), "max_lat": max(lats),
+            "min_lon": min(lons), "max_lon": max(lons)}
 
 
 def parse_fit_file(filepath: str) -> dict:
-    """Parse a Garmin .fit file and return normalized activity dict."""
-    fit = fitparse.FitFile(filepath)
+    """Parse a Garmin .fit activity file using the official Garmin SDK."""
+    from garmin_fit_sdk import Decoder, Stream
 
-    data_points = []
-    laps = []
     session = {}
+    records = []
+    laps = []
 
-    for record in fit.get_messages():
-        name = record.name
+    def listener(mesg_num: int, msg: dict):
+        nonlocal session
+        if mesg_num == 18:   # session
+            session = msg
+        elif mesg_num == 20:  # record
+            records.append(msg)
+        elif mesg_num == 19:  # lap
+            laps.append(msg)
 
-        if name == "session":
-            for f in record:
-                session[f.name] = f.value
+    stream = Stream.from_file(filepath)
+    decoder = Decoder(stream)
+    decoder.read(
+        apply_scale_and_offset=True,
+        convert_datetimes_to_dates=True,
+        convert_types_to_strings=True,
+        enable_crc_check=False,
+        expand_sub_fields=True,
+        expand_components=True,
+        merge_heart_rates=True,
+        mesg_listener=listener,
+    )
 
-        elif name == "lap":
-            lap = {}
-            for f in record:
-                lap[f.name] = f.value
-            laps.append(lap)
-
-        elif name == "record":
-            point = {}
-            for f in record:
-                point[f.name] = f.value
-            if point:
-                # Convert semicircles to degrees
-                if "position_lat" in point and point["position_lat"] is not None:
-                    point["position_lat"] = semicircles_to_degrees(point["position_lat"])
-                if "position_long" in point and point["position_long"] is not None:
-                    point["position_long"] = semicircles_to_degrees(point["position_long"])
-                data_points.append(point)
-
-    # Build normalized output
+    # Map sport type
     sport = str(session.get("sport", "generic")).lower()
     sport_map = {
         "running": "running", "cycling": "cycling", "swimming": "swimming",
         "hiking": "hiking", "walking": "walking", "generic": "other",
         "open_water_swimming": "swimming", "trail_running": "running",
+        "e_biking": "cycling",
     }
     sport_type = sport_map.get(sport, sport)
 
     start_time = session.get("start_time")
-    if start_time and start_time.tzinfo is None:
+    if isinstance(start_time, datetime) and start_time.tzinfo is None:
         start_time = start_time.replace(tzinfo=timezone.utc)
 
-    # Build GPS track for polyline
+    # Build GPS track
     coords = [
-        (p["position_lat"], p["position_long"])
-        for p in data_points
-        if p.get("position_lat") is not None and p.get("position_long") is not None
+        (r["position_lat"], r["position_long"])
+        for r in records
+        if r.get("position_lat") is not None and r.get("position_long") is not None
     ]
-
     encoded_polyline = polyline_lib.encode(coords) if coords else None
     bounding_box = _bounding_box(coords)
 
-    # Calculate cumulative distance if not in FIT
-    cumulative_dist = 0.0
-    prev_lat, prev_lon = None, None
+    # Normalize data points
     normalized_points = []
-    for p in data_points:
-        ts = p.get("timestamp")
-        if ts and ts.tzinfo is None:
+    for r in records:
+        ts = r.get("timestamp")
+        if isinstance(ts, datetime) and ts.tzinfo is None:
             ts = ts.replace(tzinfo=timezone.utc)
 
-        lat = p.get("position_lat")
-        lon = p.get("position_long")
-
-        dist = p.get("distance")
-        if dist is None and lat and lon and prev_lat and prev_lon:
-            cumulative_dist += haversine_distance(prev_lat, prev_lon, lat, lon)
-            dist = cumulative_dist
-        elif dist is not None:
-            cumulative_dist = float(dist)
-
-        if lat and lon:
-            prev_lat, prev_lon = lat, lon
-
         normalized_points.append({
             "timestamp": ts.isoformat() if ts else None,
-            "latitude": lat,
-            "longitude": lon,
-            "altitude_m": p.get("altitude"),
-            "heart_rate": p.get("heart_rate"),
-            "cadence": p.get("cadence"),
-            "speed_ms": p.get("speed"),
-            "power": p.get("power"),
-            "temperature_c": p.get("temperature"),
-            "distance_m": dist,
+            "latitude": r.get("position_lat"),
+            "longitude": r.get("position_long"),
+            "altitude_m": r.get("altitude") or r.get("enhanced_altitude"),
+            "heart_rate": r.get("heart_rate"),
+            "cadence": r.get("cadence") or r.get("fractional_cadence"),
+            "speed_ms": r.get("speed") or r.get("enhanced_speed"),
+            "power": r.get("power"),
+            "temperature_c": r.get("temperature"),
+            "distance_m": r.get("distance"),
         })
 
-    # Parse laps
+    # Normalize laps
     normalized_laps = []
     for i, lap in enumerate(laps):
         ls = lap.get("start_time")
-        if ls and ls.tzinfo is None:
+        if isinstance(ls, datetime) and ls.tzinfo is None:
             ls = ls.replace(tzinfo=timezone.utc)
         normalized_laps.append({
             "lap_number": i + 1,
@@ -132,13 +129,17 @@ def parse_fit_file(filepath: str) -> dict:
             "distance_m": _safe_float(lap.get("total_distance")),
             "avg_heart_rate": _safe_float(lap.get("avg_heart_rate")),
             "avg_cadence": _safe_float(lap.get("avg_cadence")),
-            "avg_speed_ms": _safe_float(lap.get("avg_speed")),
+            "avg_speed_ms": _safe_float(lap.get("avg_speed") or lap.get("enhanced_avg_speed")),
             "avg_power": _safe_float(lap.get("avg_power")),
         })
 
+    # Build activity name
+    name = session.get("sport", "Activity").title()
+    if start_time:
+        name += " " + start_time.strftime("%Y-%m-%d")
+
     return {
-        "name": session.get("sport", "Activity").title() + " " + (
-            start_time.strftime("%Y-%m-%d") if start_time else ""),
+        "name": name,
         "sport_type": sport_type,
         "start_time": start_time.isoformat() if start_time else None,
         "distance_m": _safe_float(session.get("total_distance")),
@@ -150,12 +151,12 @@ def parse_fit_file(filepath: str) -> dict:
         "avg_cadence": _safe_float(session.get("avg_cadence")),
         "avg_power": _safe_float(session.get("avg_power")),
         "normalized_power": _safe_float(session.get("normalized_power")),
-        "avg_speed_ms": _safe_float(session.get("avg_speed")),
-        "max_speed_ms": _safe_float(session.get("max_speed")),
+        "avg_speed_ms": _safe_float(session.get("avg_speed") or session.get("enhanced_avg_speed")),
+        "max_speed_ms": _safe_float(session.get("max_speed") or session.get("enhanced_max_speed")),
         "avg_temperature_c": _safe_float(session.get("avg_temperature")),
         "calories": _safe_float(session.get("total_calories")),
         "training_stress_score": _safe_float(session.get("training_stress_score")),
-        "vo2max_estimate": _safe_float(session.get("estimated_sweat_loss")),  # varies by device
+        "vo2max_estimate": _safe_float(session.get("total_training_effect")),
         "polyline": encoded_polyline,
         "bounding_box": bounding_box,
         "source_type": "fit",
@@ -165,13 +166,12 @@ def parse_fit_file(filepath: str) -> dict:
 
 
 def parse_gpx_file(filepath: str) -> dict:
-    """Parse a GPX file into normalized activity dict."""
+    """Parse a GPX file."""
     with open(filepath) as f:
         gpx = gpxpy.parse(f)
 
     data_points = []
     track = gpx.tracks[0] if gpx.tracks else None
-
     if not track:
         raise ValueError("No tracks found in GPX file")
 
@@ -204,7 +204,6 @@ def parse_gpx_file(filepath: str) -> dict:
                 "distance_m": None,
             })
 
-    # Calculate distance and elevation
     coords = [(p["latitude"], p["longitude"]) for p in data_points
               if p["latitude"] and p["longitude"]]
     encoded_polyline = polyline_lib.encode(coords) if coords else None
@@ -220,6 +219,7 @@ def parse_gpx_file(filepath: str) -> dict:
             prev = (p["latitude"], p["longitude"])
         p["distance_m"] = total_dist
 
+    # Elevation gain/loss
     uphill, downhill = 0.0, 0.0
     alts = [p["altitude_m"] for p in data_points if p["altitude_m"]]
     for i in range(1, len(alts)):
@@ -235,7 +235,7 @@ def parse_gpx_file(filepath: str) -> dict:
     end_dt = datetime.fromisoformat(data_points[-1]["timestamp"]) if data_points else None
     duration = (end_dt - start_dt).total_seconds() if (start_dt and end_dt) else None
 
-    sport = "running"  # GPX doesn't always include sport; default to running
+    sport = "running"
     if track.type:
         sport = track.type.lower()
 
@@ -266,76 +266,42 @@ def parse_gpx_file(filepath: str) -> dict:
     }
 
 
-def parse_strava_export(export_dir: str) -> list[dict]:
+def calculate_hr_zones(data_points: list, user_max_hr: float) -> dict:
     """
-    Parse a full Strava data export directory.
-    Structure: activities.csv + activities/ folder with .gpx/.fit.gz files
+    Calculate % time in each HR zone using the user's configured max HR.
+
+    Zones follow the standard 5-zone model as % of max HR:
+      Z1 Recovery:  < 60%
+      Z2 Base:      60 - 70%
+      Z3 Tempo:     70 - 80%
+      Z4 Threshold: 80 - 90%
+      Z5 Max:       > 90%
+
+    user_max_hr should be the user's actual physiological max HR, NOT the
+    highest HR recorded in this activity. Using activity max shifts all zones
+    upward and makes easy runs look harder than they are.
     """
-    activities = []
-    activities_dir = Path(export_dir) / "activities"
-
-    if not activities_dir.exists():
-        return activities
-
-    for fname in sorted(activities_dir.iterdir()):
-        if fname.suffix in (".fit", ".gpx"):
-            try:
-                if fname.suffix == ".fit":
-                    act = parse_fit_file(str(fname))
-                else:
-                    act = parse_gpx_file(str(fname))
-                act["source_type"] = "strava_" + fname.suffix[1:]
-                activities.append(act)
-            except Exception as e:
-                print(f"Error parsing {fname}: {e}")
-
-    return activities
-
-
-def calculate_hr_zones(data_points: list[dict], max_hr: float) -> dict:
-    """Calculate percentage of time spent in each HR zone."""
-    if not max_hr:
+    if not user_max_hr or user_max_hr < 100:
         return {}
 
-    zones = {"z1": 0, "z2": 0, "z3": 0, "z4": 0, "z5": 0}
-    zone_bounds = [0.5, 0.6, 0.7, 0.8, 0.9, 1.0]
+    zone_bounds = [0.0, 0.60, 0.70, 0.80, 0.90, 1.01]
+    zone_keys = ["z1", "z2", "z3", "z4", "z5"]
+    zones = {k: 0 for k in zone_keys}
     total = 0
 
     for p in data_points:
         hr = p.get("heart_rate")
-        if not hr:
+        if not hr or hr < 20:
             continue
-        pct = hr / max_hr
+        pct = hr / user_max_hr
         total += 1
-        if pct < zone_bounds[1]:
-            zones["z1"] += 1
-        elif pct < zone_bounds[2]:
-            zones["z2"] += 1
-        elif pct < zone_bounds[3]:
-            zones["z3"] += 1
-        elif pct < zone_bounds[4]:
-            zones["z4"] += 1
+        for i, key in enumerate(zone_keys):
+            if zone_bounds[i] <= pct < zone_bounds[i+1]:
+                zones[key] += 1
+                break
         else:
-            zones["z5"] += 1
+            zones["z5"] += 1  # anything above 90% goes to z5
 
     if total:
         return {k: round(v / total * 100, 1) for k, v in zones.items()}
     return {}
-
-
-def _safe_float(val) -> Optional[float]:
-    try:
-        return float(val) if val is not None else None
-    except (TypeError, ValueError):
-        return None
-
-
-def _bounding_box(coords: list[tuple]) -> Optional[dict]:
-    if not coords:
-        return None
-    lats = [c[0] for c in coords]
-    lons = [c[1] for c in coords]
-    return {
-        "min_lat": min(lats), "max_lat": max(lats),
-        "min_lon": min(lons), "max_lon": max(lons),
-    }

backend/app/services/wellness_parser.py

@@ -306,4 +306,4 @@ def parse_wellness_fit(file_path: str) -> dict:
             "sleep_awake_s": sleep_awake_s,
         }
 
-    return {"days": result, "error": None}
+    return {"days": result, "error": None}