precompute_depth.py

#!/usr/bin/env python3
"""
Pre-compute depth analysis data and save as JSON
This runs once and caches the results
"""
import json
import sys
import os

def find_deepest_path(item):
    path = []
    designation = item.get('designations', [{}])[0].get('designation', 'Unnamed Element')
    path.append({'type': 'Element', 'name': designation})
    
    steward = item.get('stewardOrg', {}).get('name', 'Unknown Steward')
    path.append({'type': 'Steward', 'name': steward})
    
    if item.get('classification'):
        for cls in item['classification']:
            if cls.get('elements'):
                for elem in cls['elements']:
                    if elem.get('name'):
                        path.append({'type': 'Classification', 'name': elem['name']})
    
    if item.get('dataElementConcept') and item['dataElementConcept'].get('concepts'):
        for concept in item['dataElementConcept']['concepts']:
            path.append({'type': 'Concept', 'name': concept.get('name', 'Unknown')})
    
    if item.get('property') and item['property'].get('concepts'):
        for prop in item['property']['concepts']:
            path.append({'type': 'Property', 'name': prop.get('name', 'Unknown')})
    
    return len(path), path

def main():
    print("Loading SearchExport.json...")
    with open('SearchExport.json', 'r', encoding='utf-8') as f:
        data = json.load(f)
    
    print(f"Analyzing {len(data)} items...")
    
    max_depth = 0
    deepest_paths = []
    depth_distribution = {}
    all_paths = []
    
    for i, item in enumerate(data):
        depth, path = find_deepest_path(item)
        designation = item.get('designations', [{}])[0].get('designation', 'Unnamed Element')
        
        path_data = {
            'index': i,
            'depth': depth,
            'designation': designation,
            'path': path
        }
        all_paths.append(path_data)
        
        if depth > max_depth:
            max_depth = depth
            deepest_paths = [path_data]
        elif depth == max_depth:
            deepest_paths.append(path_data)
        
        depth_distribution[depth] = depth_distribution.get(depth, 0) + 1
        
        if (i + 1) % 5000 == 0:
            print(f"  Processed {i + 1}/{len(data)} items...")
    
    # Sort all paths by depth descending, take top 50
    all_paths.sort(key=lambda x: x['depth'], reverse=True)
    top_paths = all_paths[:50]
    
    # Calculate average depth
    total_depth = sum(d * count for d, count in depth_distribution.items())
    total_items = len(data)
    avg_depth = total_depth / total_items if total_items > 0 else 0
    
    # Prepare chart data
    depths = sorted(depth_distribution.keys())
    chart_labels = [f'Depth {d}' for d in depths]
    chart_data = [depth_distribution[d] for d in depths]
    
    result = {
        'total_items': total_items,
        'max_depth': max_depth,
        'avg_depth': round(avg_depth, 2),
        'deepest_count': len(deepest_paths),
        'depth_distribution': depth_distribution,
        'chart_labels': chart_labels,
        'chart_data': chart_data,
        'deepest_paths': top_paths
    }
    
    # Save to file
    output_file = 'depth_analysis_data.json'
    with open(output_file, 'w', encoding='utf-8') as f:
        json.dump(result, f, indent=2, ensure_ascii=False)
    
    print(f"\nAnalysis complete!")
    print(f"  Total items: {total_items:,}")
    print(f"  Max depth: {max_depth}")
    print(f"  Avg depth: {avg_depth:.2f}")
    print(f"  Items at max depth: {len(deepest_paths)}")
    print(f"\nSaved to: {output_file}")

if __name__ == '__main__':
    main()