analyze_drl_patterns.py

import glob
import re

def analyze_drls():
    files = glob.glob("ACCESS-NYC-Rules/accessnyc/rules/S2R*.drl")
    files.sort()
    
    patterns = {}
    
    print(f"Analyzing {len(files)} files...")
    
    for filepath in files:
        with open(filepath, 'r') as f:
            content = f.read()
            
        # Extract 'when' block
        match = re.search(r'when\s+(.*?)\s+then', content, re.DOTALL)
        if match:
            condition_block = match.group(1).strip()
            # Normalize whitespace
            condition_block = re.sub(r'\s+', ' ', condition_block)
            
            # Simple classification based on objects used
            objects = set(re.findall(r'([A-Z][a-zA-Z0-9]+)\(', condition_block))
            obj_key = ", ".join(sorted(list(objects)))
            
            if obj_key not in patterns:
                patterns[obj_key] = []
            patterns[obj_key].append(dict(file=filepath, condition=condition_block))
            
    print("\n--- Pattern Report ---")
    for key, items in patterns.items():
        print(f"\nPattern: [{key}] - {len(items)} files")
        # Print first example
        print(f"Example ({items[0]['file']}):")
        print(f"  {items[0]['condition'][:200]}...")

if __name__ == "__main__":
    analyze_drls()