#!/usr/bin/env python3
"""Compare a business's own supplied listing details; no web requests."""
import json
import re
import sys
from urllib.parse import urlsplit

FIELDS = ("name", "address", "phone", "website")


def normalize(field, value):
    text = " ".join(str(value or "").split())
    if field == "phone":
        digits = re.sub(r"\D", "", text)
        return digits[1:] if len(digits) == 11 and digits.startswith("1") else digits
    if field == "website":
        host = (urlsplit(text).hostname or "").casefold()
        return host.removeprefix("www.")
    return text.casefold()


def audit(records):
    if not isinstance(records, list) or not records:
        raise ValueError("Provide a non-empty JSON list of listing records.")
    if any(not isinstance(row, dict) for row in records):
        raise ValueError("Each listing record must be a JSON object.")
    # The first record is the reference you have checked yourself.
    reference = records[0]
    issues = []
    for row in records:
        source = str(row.get("source") or "Unnamed source")
        for field in FIELDS:
            value = normalize(field, row.get(field))
            expected = normalize(field, reference.get(field))
            if not value:
                issues.append({"source": source, "field": field, "issue": "Missing or unusable value"})
            elif expected and value != expected:
                issues.append({"source": source, "field": field, "issue": "Differs from checked reference"})
    return issues


if __name__ == "__main__":
    if len(sys.argv) != 2:
        raise SystemExit("Usage: python3 listing_audit.py business-listings.json")
    with open(sys.argv[1], encoding="utf-8") as file:
        records = json.load(file)
    print(json.dumps(audit(records), indent=2, ensure_ascii=False))