run_queries.py

import json

INDEX_FILE = "index.json"

def load_index():
    with open(INDEX_FILE, "r", encoding="utf-8") as f:
        return json.load(f)

def run_query(term, index):
    term = term.lower()
    return set(index["index"].get(term, {}).keys())

def main():
    data = load_index()

    # Queries
    sustainability_docs = run_query("sustainability", data)
    waste_docs = run_query("waste", data)

    # Stats
    both_docs = sustainability_docs.intersection(waste_docs)
    my_collection = sustainability_docs.union(waste_docs)

    # Report
    print("\n===== QUERY RESULTS =====")
    print(f"Sustainability docs: {len(sustainability_docs)}")
    print(f"Waste docs: {len(waste_docs)}")
    print(f"Documents in BOTH: {len(both_docs)}")

    # Save My-collection
    with open("my_collection.json", "w", encoding="utf-8") as f:
        json.dump(list(my_collection), f, indent=2)

    print("\nMy-collection saved to my_collection.json")
    print(f"Total documents in My-collection: {len(my_collection)}")

if __name__ == "__main__":
    main()