"""检查 MySQL 数据字典和 Milvus NL2SQL 向量数量的一致性。"""
from __future__ import annotations

import asyncio
import sys
from pathlib import Path

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

from sqlalchemy import text

from config import database
from config.database.milvus import client
from config.database.mysql import get_session_factory
from config.settings import settings
from nl2sql.metadata import build_metadata_chunks
from nl2sql.milvus_collections import NL2SQL_COLLECTION
from model.base import Base
from scripts.sync_nl2sql_metadata import collect_orm_tables, merge_orm_metadata_rows


async def collect_consistency() -> dict:
    table_sql = text(
        "SELECT TABLE_NAME, TABLE_COMMENT, TABLE_TYPE FROM information_schema.tables WHERE TABLE_SCHEMA=:db"
    )
    column_sql = text(
        "SELECT TABLE_NAME, COLUMN_NAME, COLUMN_COMMENT, DATA_TYPE, IS_NULLABLE, ORDINAL_POSITION "
        "FROM information_schema.columns WHERE TABLE_SCHEMA=:db ORDER BY TABLE_NAME, ORDINAL_POSITION"
    )
    try:
        async with get_session_factory()() as session:
            tables = [dict(row) for row in (await session.execute(table_sql, {"db": settings.mysql.database})).mappings()]
            columns = [dict(row) for row in (await session.execute(column_sql, {"db": settings.mysql.database})).mappings()]
        # 与同步脚本保持同一口径：ORM 表是唯一权威名单，数据库中存在但
        # 未被 model/ 定义的表不应影响 NL2SQL 元数据一致性判断。
        orm_tables = collect_orm_tables()
        db_tables = {
            str(row.get("TABLE_NAME") or row.get("table_name") or "").strip()
            for row in tables
        }
        missing_tables = sorted(orm_tables - db_tables)
        expected_tables, expected_columns = merge_orm_metadata_rows(
            tables,
            columns,
            allowed_tables=orm_tables,
            missing_table_objects=(Base.metadata.tables[name] for name in missing_tables),
        )
        expected = len(build_metadata_chunks(expected_tables, expected_columns))
        rows = await client().query(
            collection_name=NL2SQL_COLLECTION,
            filter="is_valid == true and is_deprecated == false",
            output_fields=["id"],
        )
        actual = len(rows or [])
        return {"expected_chunks": expected, "actual_valid_vectors": actual, "consistent": expected == actual}
    finally:
        await database.mysql.dispose()
        await database.milvus.dispose()


if __name__ == "__main__":
    print(asyncio.run(collect_consistency()))