"""表存在性审计：`baseline_generated.sql` 声明的表 vs MySQL 实际表。

与另两个工具互补：
- `tools/audit_constraints.py`：唯一键 ↔ 文档基线、ORM 映射 ↔ 库列名；
- `tools/schema_fingerprint.py`：字段、索引与外键的结构指纹；
- 本脚本：表名集合与列存在性。

凭据来自 `.env` 的 `MYSQL_DSN`，不在脚本内硬编码口令。
"""

from __future__ import annotations

import re
import sys
from pathlib import Path
from urllib.parse import unquote, urlparse

import pymysql

ROOT = Path(__file__).resolve().parents[1]
sys.path.insert(0, str(ROOT))

SQL_FILE = ROOT / "alembic" / "baseline_generated.sql"
VERSIONS_DIR = ROOT / "alembic" / "versions"


def expected_tables() -> set[str]:
    text = SQL_FILE.read_text(encoding="utf-8")
    tables = set(re.findall(
        r"CREATE TABLE\s+(?:IF NOT EXISTS\s+)?`?([A-Za-z0-9_]+)`?",
        text,
        flags=re.IGNORECASE,
    ))
    for path in VERSIONS_DIR.glob("*.py"):
        tables.update(re.findall(
            r"CREATE TABLE\s+(?:IF NOT EXISTS\s+)?`?([A-Za-z0-9_]+)`?",
            path.read_text(encoding="utf-8"),
            flags=re.IGNORECASE,
        ))
    return tables


def mysql_connection() -> pymysql.Connection:
    from app.core.config import get_settings

    parsed = urlparse(get_settings().mysql_dsn.replace("mysql+asyncmy://", "mysql+pymysql://"))
    return pymysql.connect(
        host=parsed.hostname or "127.0.0.1",
        port=parsed.port or 3306,
        user=unquote(parsed.username or ""),
        password=unquote(parsed.password or ""),
        database=(parsed.path or "/").lstrip("/"),
        charset="utf8mb4",
    )


def main() -> None:
    connection = mysql_connection()
    database = connection.db.decode() if isinstance(connection.db, bytes) else connection.db
    with connection.cursor() as cursor:
        cursor.execute("SELECT table_name FROM information_schema.tables WHERE table_schema=%s", (database,))
        actual = {row[0] for row in cursor.fetchall()} - {"alembic_version"}
        expected = expected_tables()
        missing = expected - actual
        unexpected = actual - expected
        if missing or unexpected:
            raise SystemExit(f"table mismatch missing={sorted(missing)} unexpected={sorted(unexpected)}")
        cursor.execute(
            "SELECT table_name, column_name FROM information_schema.columns WHERE table_schema=%s",
            (database,),
        )
        actual_columns: dict[str, set[str]] = {}
        for table, column in cursor.fetchall():
            actual_columns.setdefault(table, set()).add(column)
        for table in sorted(expected):
            if not actual_columns.get(table):
                raise SystemExit(f"missing columns for {table}")
    connection.close()
    print(f"schema audit passed: {len(expected)} business tables, no missing or unexpected tables")
    return 0


if __name__ == "__main__":
    raise SystemExit(main())