Files
signal-platform/app/models/data_import_run.py
T

45 lines
2.0 KiB
Python

from datetime import date, datetime
from sqlalchemy import Date, DateTime, Index, String, Text
from sqlalchemy.orm import Mapped, mapped_column
from app.database import Base
class DataImportRun(Base):
"""One row per bulk-import attempt (SEC facts / Dolt earnings / Dolt stocks).
Lean audit record for the batch import framework: every attempt is logged,
whether it promoted, was a ``no_op`` (unchanged revision), was ``deferred``
for an expected retry, or ``failed``.
``row_counts`` and ``validation`` hold JSON strings (repo convention — see
``fundamental_data.unavailable_fields_json``), not JSONB; the validation
blob carries reconciliation/discrepancy summaries so no separate conflicts
table is needed. One run per source at a time is enforced at write time by a
Postgres advisory lock keyed by ``source``.
"""
__tablename__ = "data_import_runs"
__table_args__ = (
Index("ix_data_import_runs_source_started", "source", "started_at"),
)
id: Mapped[int] = mapped_column(primary_key=True)
# sec_facts | dolt_earnings | dolt_stocks
source: Mapped[str] = mapped_column(String(32), nullable=False)
# Dolt commit hash, or SEC archive SHA-256. Null until known.
revision: Mapped[str | None] = mapped_column(String(64), nullable=True)
# running | validated | promoted | no_op | deferred | failed
status: Mapped[str] = mapped_column(String(16), nullable=False)
source_max_date: Mapped[date | None] = mapped_column(Date, nullable=True)
row_counts_json: Mapped[str | None] = mapped_column(Text, nullable=True)
validation_json: Mapped[str | None] = mapped_column(Text, nullable=True)
started_at: Mapped[datetime] = mapped_column(
DateTime(timezone=True), default=datetime.utcnow, nullable=False
)
completed_at: Mapped[datetime | None] = mapped_column(
DateTime(timezone=True), nullable=True
)
# Failure detail, or the non-error reason when status is deferred.
error_details: Mapped[str | None] = mapped_column(Text, nullable=True)