feat(market-data): 优化同步并增加完整性检查

2026-08-11 11:20:13 +08:00
parent 3ce186f977
commit 7ce11543af
42 changed files with 4837 additions and 197 deletions
@@ -0,0 +1,90 @@
+"""Create independent market-data integrity check and issue tables."""
+
+from collections.abc import Sequence
+
+import sqlalchemy as sa
+from alembic import op
+
+revision: str = "0003_market_integrity_checks"
+down_revision: str | None = "0002_selection_results"
+branch_labels: str | Sequence[str] | None = None
+depends_on: str | Sequence[str] | None = None
+
+
+def upgrade() -> None:
+    """Create only check metadata; market facts remain untouched."""
+
+    op.create_table(
+        "market_integrity_check",
+        sa.Column("id", sa.String(36), primary_key=True),
+        sa.Column("status", sa.String(24), nullable=False),
+        sa.Column("window_start", sa.Date()),
+        sa.Column("window_end", sa.Date()),
+        sa.Column("target_count", sa.Integer(), nullable=False, server_default="0"),
+        sa.Column("checked_count", sa.Integer(), nullable=False, server_default="0"),
+        sa.Column("issue_count", sa.Integer(), nullable=False, server_default="0"),
+        sa.Column("error_type", sa.String(64)),
+        sa.Column("error_message", sa.Text()),
+        sa.Column(
+            "created_at",
+            sa.DateTime(timezone=True),
+            nullable=False,
+            server_default=sa.text("now()"),
+        ),
+        sa.Column(
+            "updated_at",
+            sa.DateTime(timezone=True),
+            nullable=False,
+            server_default=sa.text("now()"),
+        ),
+        sa.Column("finished_at", sa.DateTime(timezone=True)),
+    )
+    op.create_index(
+        "ix_market_integrity_check_status_created_at",
+        "market_integrity_check",
+        ["status", "created_at"],
+    )
+    # A partial unique index makes the running claim atomic under concurrent
+    # POST requests; stale recovery first moves an abandoned row to failed.
+    op.create_index(
+        "uq_market_integrity_check_running",
+        "market_integrity_check",
+        ["status"],
+        unique=True,
+        postgresql_where=sa.text("status = 'running'"),
+    )
+    op.create_table(
+        "market_integrity_issue",
+        sa.Column(
+            "check_id",
+            sa.String(36),
+            sa.ForeignKey("market_integrity_check.id", ondelete="CASCADE"),
+            nullable=False,
+        ),
+        sa.Column("issue_key", sa.String(64), nullable=False),
+        sa.Column("item_kind", sa.String(24), nullable=False),
+        sa.Column("item_key", sa.String(128), nullable=False),
+        sa.Column("issue_type", sa.String(64), nullable=False),
+        sa.Column("message", sa.Text(), nullable=False),
+        sa.Column(
+            "created_at",
+            sa.DateTime(timezone=True),
+            nullable=False,
+            server_default=sa.text("now()"),
+        ),
+        sa.PrimaryKeyConstraint("check_id", "issue_key"),
+    )
+    op.create_index("ix_market_integrity_issue_check_id", "market_integrity_issue", ["check_id"])
+
+
+def downgrade() -> None:
+    """Drop only the integrity report tables in dependency-safe order."""
+
+    op.drop_index("ix_market_integrity_issue_check_id", table_name="market_integrity_issue")
+    op.drop_table("market_integrity_issue")
+    op.drop_index("uq_market_integrity_check_running", table_name="market_integrity_check")
+    op.drop_index(
+        "ix_market_integrity_check_status_created_at",
+        table_name="market_integrity_check",
+    )
+    op.drop_table("market_integrity_check")