Files
hyungi 832ea72784 fix(publish): backfill 스크립트 after_id 페이징 루프 (overflow 누락 방지)
backfill_publish_* 가 단일 호출(after_id=0, limit=PAGE)이라 PAGE 초과분이 누락(경고만)됐다.
docstring 은 이미 페이지 반복을 명시했으나 스크립트가 미구현. 함수 반환을 (count, last_id)로
바꾸고 3 스크립트를 last_id 기반 while 루프로 전량 처리. PAGE=5000 bounded tx.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-29 13:22:36 +09:00

175 lines
7.1 KiB
Python

"""발행 outbox enqueue + 초기 백필 (docsrv-viewer-publish).
enqueue_publish: 저작/4-A 트랜잭션이 같은 session(=같은 Postgres tx)에서 호출 → caller commit
(P0-1 규율: 콘텐츠 변경과 outbox INSERT 원자성, dual-write 회피). payload/hash 스냅샷.
enqueue_question_publish: 문항 + (ready면)해설을 함께 적재. 저작 쓰기/4-A 완료/백필 공용.
backfill_publish_questions: 기존 active 문항을 bounded 로 1회 outbox 적재(초기 백필, P2-1 bounded page).
멱등 = 발행 워커의 (payload_hash, deleted) 디둡이 no-op 재투영 흡수(중복 enqueue 무해).
★주의: 저작 엔드포인트(study_questions create/update)·4-A 워커에서의 enqueue 결선은 P0-1b
(기존 hot 파일 수정이라 별 increment). 본 모듈은 호출 라이브러리 + 수동/백필 진입점.
"""
from __future__ import annotations
from typing import Any
from sqlalchemy import select
from sqlalchemy.ext.asyncio import AsyncSession
from models.published import PublishOutbox
from models.study_memo_card import StudyMemoCard
from models.study_memo_card_progress import StudyMemoCardProgress
from models.study_question import StudyQuestion
from models.study_topic import StudyTopic
from services.study.publish_projection import (
KIND_CARD,
KIND_CARD_PROGRESS,
KIND_EXPLANATION,
KIND_QUESTION,
KIND_TOPIC,
SCHEMA_VERSION,
payload_hash,
project_card,
project_card_progress,
project_explanation,
project_question,
project_topic,
)
async def enqueue_publish(
session: AsyncSession,
*,
kind: str,
source_id: int,
payload: dict[str, Any] | None,
deleted: bool = False,
) -> None:
"""outbox 1행 INSERT. caller 가 commit (저자 tx 동봉). deleted=True 면 tombstone(payload={})."""
body: dict[str, Any] = payload if payload is not None else {}
session.add(
PublishOutbox(
kind=kind,
source_id=source_id,
payload=body,
payload_hash=payload_hash(body),
schema_version=SCHEMA_VERSION,
deleted=deleted,
)
)
async def enqueue_question_publish(session: AsyncSession, q: Any) -> None:
"""문항 + (ready면)해설을 outbox 적재. caller commit."""
await enqueue_publish(session, kind=KIND_QUESTION, source_id=q.id, payload=project_question(q))
expl = project_explanation(q)
if expl is not None:
await enqueue_publish(session, kind=KIND_EXPLANATION, source_id=q.id, payload=expl)
async def backfill_publish_questions(session: AsyncSession, *, after_id: int = 0, limit: int = 200) -> tuple[int, int]:
"""active(미삭제) 문항을 id>after_id 부터 bounded 로 outbox 적재.
반환 = (enqueue 수, 마지막 처리 id). caller 는 수==limit 면 last_id 로 다음 페이지. caller commit.
"""
rows = (
await session.execute(
select(StudyQuestion)
.where(StudyQuestion.deleted_at.is_(None), StudyQuestion.id > after_id)
.order_by(StudyQuestion.id.asc())
.limit(limit)
)
).scalars().all()
for q in rows:
await enqueue_question_publish(session, q)
return len(rows), (rows[-1].id if rows else after_id)
async def enqueue_topic_publish(session: AsyncSession, topic: Any) -> None:
"""주제 메타를 outbox 적재(S-1). caller commit. 저작 create/update 결선 + 백필 공용."""
await enqueue_publish(session, kind=KIND_TOPIC, source_id=topic.id, payload=project_topic(topic))
async def backfill_publish_topics(session: AsyncSession, *, after_id: int = 0, limit: int = 200) -> tuple[int, int]:
"""active(미삭제) 주제를 id>after_id 부터 bounded 로 outbox 적재(S-1 초기 백필).
반환 = (enqueue 수, 마지막 처리 id). caller 는 수==limit 면 last_id 로 다음 페이지. caller commit.
멱등 = 발행 워커의 (payload_hash, deleted) 디둡이 no-op 재투영 흡수(중복 enqueue 무해).
"""
rows = (
await session.execute(
select(StudyTopic)
.where(StudyTopic.deleted_at.is_(None), StudyTopic.id > after_id)
.order_by(StudyTopic.id.asc())
.limit(limit)
)
).scalars().all()
for t in rows:
await enqueue_topic_publish(session, t)
return len(rows), (rows[-1].id if rows else after_id)
async def enqueue_card_publish(session: AsyncSession, card: Any) -> None:
"""카드 상태 기반 발행/tombstone (S-2). caller commit.
검수완료(needs_review=False) & 미삭제 만 발행 — 그 외(검수대기 복귀·삭제·retire)는
tombstone(feed 1급 삭제 이벤트). 발행 자격이 카드 상태에 매여 있어 호출측은 '카드를
건드렸다'만 알면 되고 publish/tombstone 분기는 여기 단일화(경로별 가드 기억 회피).
"""
if card.deleted_at is not None or card.needs_review:
await enqueue_publish(session, kind=KIND_CARD, source_id=card.id, payload=None, deleted=True)
else:
await enqueue_publish(session, kind=KIND_CARD, source_id=card.id, payload=project_card(card))
async def backfill_publish_cards(session: AsyncSession, *, after_id: int = 0, limit: int = 200) -> tuple[int, int]:
"""검수완료(needs_review=False)·미삭제 카드를 id>after_id 부터 bounded 로 outbox 적재(S-2 초기 백필).
반환 = (enqueue 수, 마지막 처리 id). caller 는 수==limit 면 last_id 로 다음 페이지. 멱등 = 워커 디둡. caller commit.
"""
rows = (
await session.execute(
select(StudyMemoCard)
.where(
StudyMemoCard.deleted_at.is_(None),
StudyMemoCard.needs_review.is_(False),
StudyMemoCard.id > after_id,
)
.order_by(StudyMemoCard.id.asc())
.limit(limit)
)
).scalars().all()
for c in rows:
await enqueue_card_publish(session, c)
return len(rows), (rows[-1].id if rows else after_id)
async def enqueue_card_progress_publish(session: AsyncSession, progress: Any) -> None:
"""카드 SR progress row 발행(S-4). caller commit. rate_card 결과(ALL row, sentinel/terminal 포함)."""
await enqueue_publish(
session,
kind=KIND_CARD_PROGRESS,
source_id=progress.id,
payload=project_card_progress(progress),
)
async def backfill_publish_card_progress(session: AsyncSession, *, after_id: int = 0, limit: int = 200) -> tuple[int, int]:
"""모든 card progress row 를 id>after_id 부터 bounded 로 outbox 적재(S-4 초기 백필).
★필터 없음 = ALL row(due_at NULL sentinel·terminal 포함) — due-only 백필은 sentinel 누락.
반환 = (enqueue 수, 마지막 처리 id). caller 는 수==limit 면 last_id 로 다음 페이지. 멱등 = 워커 디둡. caller commit.
"""
rows = (
await session.execute(
select(StudyMemoCardProgress)
.where(StudyMemoCardProgress.id > after_id)
.order_by(StudyMemoCardProgress.id.asc())
.limit(limit)
)
).scalars().all()
for p in rows:
await enqueue_card_progress_publish(session, p)
return len(rows), (rows[-1].id if rows else after_id)