"""清理 schema 与 ORM 模型的漂移

Revision ID: 0006_schema_model_drift_cleanup
Revises: 0005_prediction_status_and_stats_provenance
Create Date: 2026-09-15

背景(见代码审查报告 P1-1):
  0005 迁移在 predictions 表留下了 `cutoff_at` 列(删除语句被注释掉),
  但 ORM 模型 `Prediction` 中并无该字段 —— 这是一处会长期存在的 schema 漂移,
  而 alembic autogenerate 会持续建议 drop 它,造成噪声。

  同时 0005 创建的两个索引 `ix_match_stats_available_at` 与
  `ix_predictions_cutoff_at` 未在 ORM 声明,autogenerate 会建议删除它们 ——
  一旦被误删,数据血缘相关的时间过滤查询会退化为全表扫描。

本迁移做两件事:
  1. drop 掉幽灵列 predictions.cutoff_at(数据已由 prediction_cutoff_at 承载,
     迁移前先把非空值回填过去,避免丢数据)
  2. 显式重建这两个索引(幂等:先 drop if exists 再 create),使 DB 状态与
     修正后的 ORM 声明一致
"""
from typing import Sequence, Union

from alembic import op
import sqlalchemy as sa

# revision identifiers, used by Alembic.
revision: str = '0006_schema_model_drift_cleanup'
down_revision: Union[str, None] = '0005_prediction_status_and_stats_provenance'
branch_labels: Union[str, Sequence[str], None] = None
depends_on: Union[str, Sequence[str], None] = None


def upgrade() -> None:
    bind = op.get_bind()
    inspector = sa.inspect(bind)

    # --- 1. 幽灵列 cutoff_at: 先把数据回填到 prediction_cutoff_at 再删除 ---
    pred_cols = {c["name"] for c in inspector.get_columns("predictions")}
    if "cutoff_at" in pred_cols:
        if "prediction_cutoff_at" in pred_cols:
            # 仅回填尚未有值的行,避免覆盖更权威的数据
            op.execute(
                "UPDATE predictions "
                "SET prediction_cutoff_at = cutoff_at "
                "WHERE prediction_cutoff_at IS NULL AND cutoff_at IS NOT NULL"
            )
        op.drop_column("predictions", "cutoff_at")

    # --- 2. 与 ORM 声明对齐的索引(幂等重建) ---
    stats_idx = {i["name"] for i in inspector.get_indexes("match_stats")}
    if "ix_match_stats_available_at" not in stats_idx:
        op.create_index("ix_match_stats_available_at", "match_stats", ["available_at"])

    pred_idx = {i["name"] for i in inspector.get_indexes("predictions")}
    if "ix_predictions_cutoff_at" not in pred_idx:
        op.create_index(
            "ix_predictions_cutoff_at", "predictions", ["prediction_cutoff_at"]
        )


def downgrade() -> None:
    bind = op.get_bind()
    inspector = sa.inspect(bind)

    # 恢复幽灵列(与 0005 的最终状态一致:列存在但无值)
    pred_cols = {c["name"] for c in inspector.get_columns("predictions")}
    if "cutoff_at" not in pred_cols:
        op.add_column(
            "predictions",
            sa.Column("cutoff_at", sa.DateTime(timezone=True), nullable=True),
        )

    stats_idx = {i["name"] for i in inspector.get_indexes("match_stats")}
    if "ix_match_stats_available_at" in stats_idx:
        op.drop_index("ix_match_stats_available_at", table_name="match_stats")

    pred_idx = {i["name"] for i in inspector.get_indexes("predictions")}
    if "ix_predictions_cutoff_at" in pred_idx:
        op.drop_index("ix_predictions_cutoff_at", table_name="predictions")