pdf-quiz-generator/backend/app/models/article.py
Daniel 831cb01650 feat: an article follows a topic, rather than copying it once
"Questions filed there later are not added" was the honest description of what
the previous commit built, and it was the wrong thing to build. "The Cardiology
article covers the Cardiology questions" is a standing statement about the
material, not a snapshot of who happened to be filed where on the afternoon
somebody pressed a button — and a copy stops being true the first time a
question is added, silently, with nothing on any screen to say so.

So the claim is now stored, and it is what writes the links:

* `question_article_links` is still the **only** table anything reads. No count,
  no QBank button, no mirror panel on a question, no AI Mode boost learns a
  second question to ask.
* `article_topic_claims` records *why* some of those rows exist, and is the one
  place that makes them — when the claim is staked, when a question is filed
  into the category (single, bulk, or on create), and on a half-hourly sweep
  that catches whatever bypassed both.

A link made this way is an ordinary row and can still be deleted by hand; a
sweep puts it back, which is the honest consequence of a standing claim.
Dropping the claim is how you stop it, and the panel now lists what an article
follows with two ways out — stop following and keep the links, or stop and
remove them.

Migration k1b2c3d4e5f6.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01TqXevQJhxFrM7jJg82cgZN
2026-09-12 19:57:06 +02:00

168 lines
8.1 KiB
Python

from datetime import datetime
from sqlalchemy import (Boolean, Column, Integer, String, Text, JSON, DateTime,
ForeignKey, UniqueConstraint)
from sqlalchemy.orm import relationship
from app.database import Base
from app.models.embeddable import Embeddable
class Article(Base, Embeddable):
"""Educator-authored topic reading with stable section IDs for linking."""
__tablename__ = "articles"
id = Column(Integer, primary_key=True, index=True)
slug = Column(String(120), unique=True, nullable=False, index=True)
title = Column(String(300), nullable=False)
summary = Column(Text, nullable=True)
content = Column(Text, nullable=True) # Whole-article introduction (markdown).
# Stable subsections: [{"id": uuid-hex, "slug": "...", "title": "...", "content": "markdown"}].
sections = Column(JSON, nullable=False, default=list)
category_id = Column(Integer, ForeignKey("question_categories.id", ondelete="SET NULL"), nullable=True)
section_id = Column(Integer, ForeignKey("sections.id", ondelete="SET NULL"), nullable=True) # Optional PDF source range.
user_id = Column(Integer, ForeignKey("users.id", ondelete="SET NULL"), nullable=True)
status = Column(String, default="draft") # draft | in_review | published
submitted_at = Column(DateTime, nullable=True)
reviewed_at = Column(DateTime, nullable=True)
reviewed_by = Column(Integer, ForeignKey("users.id", ondelete="SET NULL"), nullable=True)
# Sources the article was written from. A list, not in-text markers.
references_json = Column(JSON, nullable=True)
# What wrote it, so a machine-written draft stays visibly one until an
# educator has been through it.
generated_by = Column(String(80), nullable=True)
generated_at = Column(DateTime, nullable=True)
# The first time this was published, and never cleared afterwards. It is
# what decides whether deleting is reversible: an article the world has
# seen goes to the trash, a draft nobody ever saw is simply gone.
first_published_at = Column(DateTime, nullable=True)
# In the trash. Set rather than deleted, so restoring is one click and not
# a database restore.
deleted_at = Column(DateTime, nullable=True)
deleted_by = Column(Integer, ForeignKey("users.id", ondelete="SET NULL"), nullable=True)
created_at = Column(DateTime, default=datetime.utcnow)
updated_at = Column(DateTime, default=datetime.utcnow, onupdate=datetime.utcnow)
category = relationship("QuestionCategory")
links = relationship("QuestionArticleLink", back_populates="article", cascade="all, delete-orphan")
class QuestionArticleLink(Base):
"""Question -> whole article or one stable section."""
__tablename__ = "question_article_links"
__table_args__ = (UniqueConstraint("question_id", "article_id", "section_id", name="uq_question_article_section"),)
id = Column(Integer, primary_key=True, index=True)
question_id = Column(Integer, ForeignKey("questions.id", ondelete="CASCADE"), nullable=False)
article_id = Column(Integer, ForeignKey("articles.id", ondelete="CASCADE"), nullable=False)
section_id = Column(String(64), nullable=True) # Article.sections[].id; None = whole article.
user_id = Column(Integer, ForeignKey("users.id", ondelete="SET NULL"), nullable=True)
created_at = Column(DateTime, default=datetime.utcnow)
article = relationship("Article", back_populates="links")
class ArticleTopicClaim(Base):
"""An article claims a category: every question filed there links to it.
The alternative was a one-off copy, and it was wrong for the thing people
actually do here. "The Cardiology article covers the Cardiology questions"
is a *standing* statement, not a snapshot of who was in the room in
September — and a copy quietly stops being true the first time somebody
files a new question, with nothing on any screen to say so.
So this table holds the claim, and `question_article_links` is still the
only thing anything reads. The rows are *materialised* from the claim:
made when it is staked, and made again for a question the moment it is
filed into the category. One source of truth to read, one place that
writes it.
A link made this way is an ordinary row and can be removed one at a time —
but re-syncing puts it back, which is the honest consequence of a standing
claim. Dropping the claim is how you stop it.
"""
__tablename__ = "article_topic_claims"
__table_args__ = (UniqueConstraint("article_id", "category_id", "section_id",
name="uq_article_topic_claim"),)
id = Column(Integer, primary_key=True, index=True)
article_id = Column(Integer, ForeignKey("articles.id", ondelete="CASCADE"), nullable=False, index=True)
category_id = Column(Integer, ForeignKey("question_categories.id", ondelete="CASCADE"), nullable=False, index=True)
#: Where the links land: a section of the article, or the whole of it.
section_id = Column(String(64), nullable=True)
#: Whether the claim reaches the category's subtopics, which is what an
#: educator usually means by the name of a discipline.
include_subtopics = Column(Boolean, nullable=False, default=True)
user_id = Column(Integer, ForeignKey("users.id", ondelete="SET NULL"), nullable=True)
created_at = Column(DateTime, default=datetime.utcnow)
class ArticleRevision(Base):
"""A snapshot of an article as it was before a save.
Kept for the same reason question versions are: an editor who breaks
something at 2am needs to get back to what was there, and a diff nobody can
reach is not a safety net.
"""
__tablename__ = "article_revisions"
id = Column(Integer, primary_key=True, index=True)
article_id = Column(Integer, ForeignKey("articles.id", ondelete="CASCADE"), nullable=False, index=True)
title = Column(String(300), nullable=False)
summary = Column(Text, nullable=True)
content = Column(Text, nullable=True)
sections = Column(JSON, nullable=False, default=list)
references_json = Column(JSON, nullable=True)
status = Column(String(20), nullable=True)
note = Column(String(200), nullable=True)
created_by = Column(Integer, ForeignKey("users.id", ondelete="SET NULL"), nullable=True)
created_at = Column(DateTime, default=datetime.utcnow)
class ArticleSlug(Base):
"""Every slug an article has ever had.
A cross-reference written today must survive a rename tomorrow. Old slugs
redirect rather than 404, so the author who renamed something does not
silently break every article that pointed at it.
"""
__tablename__ = "article_slugs"
id = Column(Integer, primary_key=True, index=True)
slug = Column(String(120), unique=True, nullable=False, index=True)
article_id = Column(Integer, ForeignKey("articles.id", ondelete="CASCADE"), nullable=False, index=True)
created_at = Column(DateTime, default=datetime.utcnow)
class ArticleView(Base):
"""Last time a learner opened an article — one row per user and article."""
__tablename__ = "article_views"
__table_args__ = (UniqueConstraint("user_id", "article_id", name="uq_article_view"),)
id = Column(Integer, primary_key=True, index=True)
user_id = Column(Integer, ForeignKey("users.id", ondelete="CASCADE"), nullable=False, index=True)
article_id = Column(Integer, ForeignKey("articles.id", ondelete="CASCADE"), nullable=False)
viewed_at = Column(DateTime, default=datetime.utcnow)
class ArticleSectionIndex(Base, Embeddable):
"""One row per article section, so retrieval can cite a section not a whole article.
Sections are stored in `Article.sections` as JSON; this is a projection of
them, rebuilt whenever the article is saved.
"""
__tablename__ = "article_section_index"
__table_args__ = (UniqueConstraint("article_id", "section_id", name="uq_article_section_index"),)
id = Column(Integer, primary_key=True, index=True)
article_id = Column(Integer, ForeignKey("articles.id", ondelete="CASCADE"), nullable=False, index=True)
section_id = Column(String(64), nullable=False)
title = Column(Text, nullable=True)
content = Column(Text, nullable=True)