"""
解析后文件记录模型

存储上传文件解析后的每行原始数据，供已匹配列表等场景消费
"""

from typing import Any, Optional

from sqlalchemy import ForeignKey, Integer, String, JSON, Index
from sqlalchemy.orm import Mapped, mapped_column

from app.models.base import BaseModel


class ParsedFileRecord(BaseModel):
    """
    解析后文件记录

    每个上传文件解析后的一行原始数据对应一条记录
    """

    __tablename__ = "parsed_file_records"

    # 归属
    company_id: Mapped[int] = mapped_column(
        Integer, ForeignKey("companies.id"), nullable=False, index=True
    )
    task_id: Mapped[int] = mapped_column(
        Integer, ForeignKey("reconciliation_tasks.id"), nullable=False, index=True
    )
    uploaded_file_id: Mapped[int] = mapped_column(
        Integer, ForeignKey("uploaded_files.id"), nullable=False, index=True
    )

    # 数据桶/文件类型
    file_bucket: Mapped[str] = mapped_column(
        String(30), nullable=False, default="salary",
        comment="数据桶: salary / social_security / tax / bank / other"
    )

    # 行号
    row_index: Mapped[int] = mapped_column(Integer, nullable=False)

    # 原始行数据（JSON）
    raw_data: Mapped[dict[str, Any]] = mapped_column(JSON, nullable=False)

    # 标准化后数据（JSON）
    normalized_data: Mapped[dict[str, Any]] = mapped_column(JSON, nullable=True)

    # 员工标识（冗余存储，加速已匹配列表查询）
    employee_id: Mapped[Optional[str]] = mapped_column(String(100), nullable=True, index=True)
    employee_name: Mapped[Optional[str]] = mapped_column(String(200), nullable=True)

    __table_args__ = (
        Index("ix_parsed_file_records_task_bucket", "task_id", "file_bucket"),
    )

    def __repr__(self) -> str:
        return (
            f"<ParsedFileRecord(id={self.id}, task_id={self.task_id}, "
            f"file_bucket='{self.file_bucket}', row_index={self.row_index})>"
        )