berlin-picnic-api/scripts/test_osm_processing.py

169 lines
5.3 KiB
Python

#!/usr/bin/env python3
"""
Test OSM processing with a small sample to verify it works.
"""
import json
import asyncio
import xml.etree.ElementTree as ET
from pathlib import Path
from datetime import datetime
import sys
import math
# Add the app directory to Python path
sys.path.append(str(Path(__file__).parent.parent))
from app.services.street_tree_service import StreetTreeService
from app.services.berlin_data_service import BerlinDataService
async def test_processing():
"""Test the processing with a small sample."""
print("🧪 Testing OSM processing with sample data...")
# Initialize services
tree_service = StreetTreeService()
berlin_data = BerlinDataService()
# Parse OSM file and get first 5 green spaces as test
osm_file = Path("app/data/osm-raw/berlin_green_spaces.osm")
if not osm_file.exists():
print("❌ OSM file not found")
return
tree = ET.parse(osm_file)
root = tree.getroot()
ways = root.findall('.//way')
print(f"📊 Found {len(ways)} total ways in OSM file")
# Process first 5 green spaces as test
sample_spaces = []
processed_count = 0
for way in ways:
if processed_count >= 5:
break
# Get tags
tags = {}
for tag in way.findall('tag'):
tags[tag.get('k')] = tag.get('v')
# Check if it's a green space
green_space_type = None
leisure = tags.get('leisure', '')
landuse = tags.get('landuse', '')
natural = tags.get('natural', '')
if leisure in ['park', 'garden', 'nature_reserve']:
green_space_type = leisure
elif landuse in ['forest', 'grass', 'park']:
green_space_type = landuse
elif natural in ['forest', 'wood']:
green_space_type = natural
if not green_space_type:
continue
# Get coordinates from first and last node to estimate center
nd_refs = [nd.get('ref') for nd in way.findall('nd')]
if len(nd_refs) < 3:
continue
# Find first node coordinates
first_node = root.find(f".//node[@id='{nd_refs[0]}']")
if first_node is None:
continue
lat = float(first_node.get('lat'))
lng = float(first_node.get('lon'))
# Simple space data
space_data = {
'id': f"test_{way.get('id')}",
'name': tags.get('name', f"Test {green_space_type} {processed_count + 1}"),
'fclass': green_space_type,
'lat': lat,
'lng': lng,
'area_sqm': 5000, # Default for test
'district': 'Test District'
}
sample_spaces.append(space_data)
processed_count += 1
print(f"🌳 Testing with {len(sample_spaces)} sample green spaces...")
# Test enhancement with real data
enhanced_spaces = []
for i, space_data in enumerate(sample_spaces, 1):
print(f"\n[{i}/{len(sample_spaces)}] Testing {space_data['name']}...")
try:
# Get real tree data
tree_response = await tree_service.get_trees_near_location(
space_data['lat'], space_data['lng'], radius_m=200
)
# Get real toilet data
nearby_toilets = await berlin_data.get_toilets_near_point(
space_data['lat'], space_data['lng'], 500
)
# Create enhanced data
enhanced_space = {
"id": space_data['id'],
"name": space_data['name'],
"type": "PARK",
"coordinates": {
"lat": space_data['lat'],
"lng": space_data['lng']
},
"tree_data": {
"total_trees": tree_response.metrics.total_trees,
"species_count": len(tree_response.metrics.dominant_species),
"dominant_species": tree_response.metrics.dominant_species
},
"toilet_accessibility": {
"nearby_toilets_count": len(nearby_toilets),
"nearest_distance_m": nearby_toilets[0]['distance_meters'] if nearby_toilets else None
}
}
enhanced_spaces.append(enhanced_space)
trees = tree_response.metrics.total_trees
toilets = len(nearby_toilets)
print(f"✅ Success: {trees} trees, {toilets} toilets nearby")
except Exception as e:
print(f"❌ Error: {e}")
# Save test results
output_file = Path("app/data/processed/test_green_spaces.json")
test_data = {
"test_results": enhanced_spaces,
"total_tested": len(enhanced_spaces),
"osm_ways_available": len(ways),
"processing_successful": True,
"timestamp": datetime.now().isoformat()
}
with open(output_file, 'w') as f:
json.dump(test_data, f, indent=2)
print(f"\n🎉 Test completed successfully!")
print(f"📁 Test results saved: {output_file}")
print(f"📊 Enhanced {len(enhanced_spaces)} sample spaces")
print(f"💡 Ready to process all {len(ways)} green spaces!")
return True
if __name__ == "__main__":
asyncio.run(test_processing())