"""Shared helpers: autocomplete-token mapping, uids, loading harvested forms."""
import glob
import gzip
import hashlib
import json

AC_MAP = {
    "username": "username", "email": "email", "current-password": "current-password",
    "new-password": "new-password", "one-time-code": "one-time-code",
    "tel": "tel", "tel-national": "tel", "tel-local": "tel", "tel-country-code": "tel", "tel-area-code": "tel",
    "tel-extension": "tel", "tel-local-prefix": "tel", "tel-local-suffix": "tel",
    "name": "name", "given-name": "given-name", "additional-name": "given-name", "family-name": "family-name",
    "organization": "organization", "street-address": "street-address", "address-line1": "street-address",
    "address-line2": "address-line2", "address-line3": "address-line2", "address-level2": "address-level2",
    "address-level1": "address-level1", "postal-code": "postal-code", "country": "country", "country-name": "country",
    "cc-name": "cc-name", "cc-given-name": "cc-name", "cc-family-name": "cc-name", "cc-number": "cc-number",
    "cc-exp": "cc-exp", "cc-exp-month": "cc-exp-month", "cc-exp-year": "cc-exp-year", "cc-csc": "cc-csc",
    "bday": "bday", "bday-day": "bday", "bday-month": "bday", "bday-year": "bday",
}
AC_SKIP = {"section-", "shipping", "billing", "home", "work", "mobile", "fax", "pager", "webauthn"}


def ac_label(ac: str):
    """Map an autocomplete attribute to a Zap field label, or None when it carries no field meaning."""
    toks = [t for t in (ac or "").lower().replace('"', "").split() if t]
    toks = [t for t in toks if not t.startswith("section-") and t not in AC_SKIP]
    if len(toks) != 1:
        return None
    return AC_MAP.get(toks[0])


def uid(row) -> str:
    return hashlib.sha1(f"{row['url']}#{row['fidx']}".encode()).hexdigest()[:16]


def load_forms(pattern):
    for path in sorted(glob.glob(pattern)):
        with gzip.open(path, "rt") as f:
            for line in f:
                row = json.loads(line)
                row["uid"] = uid(row)
                yield row