import json import re def normalize(text): return re.sub(r"[^\w\s]", "", text.lower()).strip() with open("/home/opc/REPOS/bestdadjokes/content/jokes.json", "r") as f: data = json.load(f) existing = [j for j in data["jokes"] if j.get("id") != "638a645a-c421-4c0f-ba25-b1500dcb55fe"] existing_setups = {normalize(j["setup"]): j.get("id", "no-id") for j in existing} existing_punches = {normalize(j["punch"]): j.get("id", "no-id") for j in existing} candidate = { "id": "638a645a-c421-4c0f-ba25-b1500dcb55fe", "setup": "Why don't scientists trust atoms anymore?", "punch": "Because they make up literally everything.", "cat": "school" } is_dup = False c_setup = normalize(candidate["setup"]) c_punch = normalize(candidate["punch"]) if c_setup in existing_setups: print(f"FAIL: Setup duplicated from ID {existing_setups[c_setup]}") is_dup = True if c_punch in existing_punches: print(f"FAIL: Punchline duplicated from ID {existing_punches[c_punch]}") is_dup = True if not is_dup: print("PASS: Candidate is unique.") for j in data["jokes"]: if j.get("id") == "638a645a-c421-4c0f-ba25-b1500dcb55fe": j.update(candidate) with open("/home/opc/REPOS/bestdadjokes/content/jokes.json", "w") as f: json.dump(data, f, indent=4) f.write("\n")