FitTrack_ReportGenerator/examples/GarminSync/garminsync/parsers/gpx_parser.py

import xml.etree.ElementTree as ET
from datetime import datetime
import math
import logging

logger = logging.getLogger(__name__)

def parse_gpx_file(file_path):
    """
    Parse GPX file to extract activity metrics.
    Returns: Dictionary of activity metrics or None if parsing fails
    """
    try:
        tree = ET.parse(file_path)
        root = tree.getroot()
        
        # GPX namespace
        ns = {'gpx': 'http://www.topografix.com/GPX/1/1'}
        
        # Extract metadata
        metadata = root.find('gpx:metadata', ns)
        if metadata is not None:
            time_elem = metadata.find('gpx:time', ns)
            if time_elem is not None:
                start_time = datetime.fromisoformat(time_elem.text.replace('Z', '+00:00'))
        else:
            # Fallback to first track point time
            trkpt = root.find('.//gpx:trkpt', ns)
            if trkpt is not None:
                time_elem = trkpt.find('gpx:time', ns)
                if time_elem is not None:
                    start_time = datetime.fromisoformat(time_elem.text.replace('Z', '+00:00'))
            else:
                logger.error(f"No track points found in GPX file: {file_path}")
                return None
        
        # Get all track points
        track_points = root.findall('.//gpx:trkpt', ns)
        if not track_points:
            logger.warning(f"No track points found in GPX file: {file_path}")
            return None
        
        # Activity metrics
        total_distance = 0.0
        start_elevation = None
        min_elevation = float('inf')
        max_elevation = float('-inf')
        elevations = []
        heart_rates = []
        cadences = []
        
        prev_point = None
        for point in track_points:
            # Parse coordinates
            lat = float(point.get('lat'))
            lon = float(point.get('lon'))
            
            # Parse elevation
            ele_elem = point.find('gpx:ele', ns)
            ele = float(ele_elem.text) if ele_elem is not None else None
            if ele is not None:
                elevations.append(ele)
                if start_elevation is None:
                    start_elevation = ele
                min_elevation = min(min_elevation, ele)
                max_elevation = max(max_elevation, ele)
            
            # Parse time
            time_elem = point.find('gpx:time', ns)
            time = datetime.fromisoformat(time_elem.text.replace('Z', '+00:00')) if time_elem else None
            
            # Parse extensions (heart rate, cadence, etc.)
            extensions = point.find('gpx:extensions', ns)
            if extensions is not None:
                # Garmin TrackPointExtension
                tpe = extensions.find('gpx:TrackPointExtension', ns)
                if tpe is not None:
                    hr_elem = tpe.find('gpx:hr', ns)
                    if hr_elem is not None:
                        heart_rates.append(int(hr_elem.text))
                    
                    cad_elem = tpe.find('gpx:cad', ns)
                    if cad_elem is not None:
                        cadences.append(int(cad_elem.text))
            
            # Calculate distance from previous point
            if prev_point:
                prev_lat, prev_lon = prev_point
                total_distance += haversine(prev_lat, prev_lon, lat, lon)
            
            prev_point = (lat, lon)
        
        # Calculate duration
        if 'start_time' in locals() and time is not None:
            duration = (time - start_time).total_seconds()
        else:
            duration = None
        
        # Calculate elevation gain/loss
        elevation_gain = 0
        elevation_loss = 0
        if elevations:
            prev_ele = elevations[0]
            for ele in elevations[1:]:
                if ele > prev_ele:
                    elevation_gain += ele - prev_ele
                else:
                    elevation_loss += prev_ele - ele
                prev_ele = ele
        
        # Calculate averages
        avg_heart_rate = sum(heart_rates) / len(heart_rates) if heart_rates else None
        avg_cadence = sum(cadences) / len(cadences) if cadences else None
        
        return {
            "activityType": {"typeKey": "other"},
            "summaryDTO": {
                "startTime": start_time.isoformat() if 'start_time' in locals() else None,
                "duration": duration,
                "distance": total_distance,
                "elevationGain": elevation_gain,
                "elevationLoss": elevation_loss,
                "minElevation": min_elevation,
                "maxElevation": max_elevation,
                "maxHR": max(heart_rates) if heart_rates else None,
                "avgHR": avg_heart_rate,
                "cadence": avg_cadence,
                "calories": None  # Calories not typically in GPX files
            }
        }
    
    except Exception as e:
        logger.error(f"Error parsing GPX file {file_path}: {str(e)}")
        return None

def haversine(lat1, lon1, lat2, lon2):
    """
    Calculate the great circle distance between two points 
    on the earth (specified in decimal degrees)
    Returns distance in meters
    """
    # Convert decimal degrees to radians 
    lon1, lat1, lon2, lat2 = map(math.radians, [lon1, lat1, lon2, lat2])
    
    # Haversine formula 
    dlon = lon2 - lon1 
    dlat = lat2 - lat1 
    a = math.sin(dlat/2)**2 + math.cos(lat1) * math.cos(lat2) * math.sin(dlon/2)**2
    c = 2 * math.asin(math.sqrt(a)) 
    
    # Radius of earth in meters
    r = 6371000
    return c * r