#!/usr/bin/env python3
"""Apply exact email/alias matches from a BARON-SSO export to the template."""

from __future__ import annotations

import argparse
import csv
import re
from collections import defaultdict
from pathlib import Path


EMAIL_RE = re.compile(r"[A-Z0-9._%+-]+@[A-Z0-9.-]+\.[A-Z]{2,}", re.IGNORECASE)
MATCH_COLUMNS = (
    "Email",
    "Meta:secondary_emails",
    "Meta:aliasEmails",
    "Meta:worksmobileAliasEmails",
    "Meta:sub_email",
    "Meta:external_sub_email",
    "Meta:source_login_id",
)


def emails(value: str | None) -> set[str]:
    return {match.lower() for match in EMAIL_RE.findall(value or "")}


def main() -> None:
    parser = argparse.ArgumentParser(description=__doc__)
    parser.add_argument("--users", type=Path, default=Path("users_export_20260805.csv"))
    parser.add_argument(
        "--template",
        type=Path,
        default=Path("scripts/generated/egbim_migration/identity_mapping_template.csv"),
    )
    parser.add_argument("--output", type=Path)
    args = parser.parse_args()
    output = args.output or args.template

    with args.users.open(encoding="utf-8-sig", newline="") as stream:
        users = list(csv.DictReader(stream))
    with args.template.open(encoding="utf-8", newline="") as stream:
        template = list(csv.DictReader(stream))

    index: dict[str, list[tuple[dict[str, str], str]]] = defaultdict(list)
    for user in users:
        for column in MATCH_COLUMNS:
            for identifier in emails(user.get(column)):
                index[identifier].append((user, column))

    resolved = 0
    ambiguous = 0
    unmatched = 0
    for row in template:
        identifier = row["legacy_identifier"].strip().lower()
        candidates = index.get(identifier, [])
        users_by_id = {user["user_id"]: (user, column) for user, column in candidates}
        if len(users_by_id) != 1:
            row["resolution_status"] = "AMBIGUOUS" if len(users_by_id) > 1 else "UNRESOLVED"
            row["notes"] = (
                "BARON-SSO export에서 동일 alias가 여러 사용자와 일치함"
                if len(users_by_id) > 1
                else "정확한 이메일/보조 이메일 일치 없음; 이름만으로 자동 매핑하지 않음"
            )
            if len(users_by_id) > 1:
                ambiguous += 1
            else:
                unmatched += 1
            continue

        user, matched_column = next(iter(users_by_id.values()))
        row["sso_subject"] = user.get("user_id", "")
        row["tenant_id"] = user.get("tenant_id", "")
        row["email"] = user.get("Email", "")
        row["name"] = user.get("Name", "")
        row["department"] = user.get("Meta:department") or user.get("JobTitle") or user.get("Position") or ""
        row["phone"] = user.get("Phone", "")
        row["resolution_status"] = "RESOLVED"
        row["notes"] = f"exact match: {matched_column}"
        resolved += 1

    with output.open("w", encoding="utf-8", newline="") as stream:
        writer = csv.DictWriter(stream, fieldnames=template[0].keys())
        writer.writeheader()
        writer.writerows(template)

    print(f"template_rows={len(template)} resolved={resolved} ambiguous={ambiguous} unmatched={unmatched}")
    print(f"output={output}")


if __name__ == "__main__":
    main()