pdf-quiz-generator/backend/tests/test_global_search.py

"""One query across every corpus, on disposable SQLite; no network or AI.

The point of these tests is the boundary, not the ranking: a search page that
had its own idea of who may see what is how private content leaks.
"""
import unittest
from datetime import datetime

import test_quiz_builder as fixtures
from app.models.article import Article, ArticleSectionIndex
from app.models.flashcard import Flashcard, FlashcardDeck
from app.models.question import Question
from app.routers import search


class GlobalSearchTests(unittest.TestCase):
    def setUp(self):
        self.bank = fixtures.BuilderTests()
        self.bank.setUp()
        self.client = self.bank.client
        self.client.app.include_router(search.router, prefix='/search')
        self.db = self.bank.db

        self.db.add_all([
            Article(id=1, slug='febrile-seizures', title='Febrile seizures',
                    summary='A seizure with fever in a young child', content='Intro',
                    sections=[{"id": "a" * 32, "slug": "workup", "title": "Initial workup", "content": "Lumbar puncture"}],
                    status='published', user_id=3),
            Article(id=2, slug='draft-topic', title='Febrile draft', summary='Unpublished febrile notes',
                    sections=[], status='draft', user_id=3),
        ])
        self.db.add(ArticleSectionIndex(id=1, article_id=1, section_id='a' * 32,
                                        title='Initial workup', content='Lumbar puncture in a febrile infant'))
        self.db.add_all([
            FlashcardDeck(id=1, title='Mine', user_id=1),
            FlashcardDeck(id=2, title='Theirs', user_id=2),
        ])
        self.db.flush()
        self.db.add_all([
            Flashcard(id=1, deck_id=1, front='Febrile seizure duration', back='Under 15 minutes'),
            Flashcard(id=2, deck_id=2, front='Febrile seizure age', back='6 months to 5 years'),
        ])
        self.db.query(Question).filter(Question.id == 1).update(
            {"question_text": "A child with a febrile seizure lasting two minutes"})
        self.db.query(Question).filter(Question.id == 3).update(
            {"question_text": "A removed febrile seizure question",
             "deleted_at": datetime(2026, 1, 1)})
        self.db.commit()

    def tearDown(self):
        self.bank.tearDown()

    def find(self, q='febrile', **params):
        response = self.client.get('/search', params={'q': q, **params})
        self.assertEqual(response.status_code, 200, response.text)
        return response.json()

    def test_one_query_answers_from_every_corpus(self):
        self.bank.user = self.bank.owner
        data = self.find()
        self.assertEqual(data['query'], 'febrile')
        self.assertIn(1, [row['id'] for row in data['results']['article']])
        self.assertIn(1, [row['id'] for row in data['results']['question']])
        self.assertIn(1, [row['id'] for row in data['results']['flashcard']])
        self.assertEqual(data['total'], sum(len(v) for v in data['results'].values()))

    def test_a_section_hit_is_reported_under_its_article(self):
        self.bank.user = self.bank.owner
        article = next(row for row in self.find('lumbar')['results']['article'] if row['id'] == 1)
        # Ten sections of one article are one result with ten places to start,
        # not ten results burying everything else.
        self.assertEqual([s['title'] for s in article['sections']], ['Initial workup'])
        self.assertEqual(article['sections'][0]['section_id'], 'a' * 32)

    def test_drafts_stay_invisible_to_everyone_but_their_educator(self):
        self.bank.user = self.bank.owner
        self.assertNotIn(2, [row['id'] for row in self.find()['results']['article']])
        self.bank.user = self.bank.mod
        self.assertIn(2, [row['id'] for row in self.find()['results']['article']])

    def test_removed_questions_and_other_peoples_decks_are_not_searchable(self):
        self.bank.user = self.bank.peer
        data = self.find()
        # Question 3 has been removed from the bank.
        self.assertNotIn(3, [row['id'] for row in data['results']['question']])
        # Deck 1 belongs to the owner; the peer's search must not reach into it.
        self.assertNotIn(1, [row['id'] for row in data['results']['flashcard']])

    def test_a_query_too_short_to_mean_anything_asks_nothing(self):
        self.bank.user = self.bank.owner
        data = self.find('f')
        self.assertEqual(data['total'], 0)
        self.assertEqual(data['results']['article'], [])

    def test_kinds_narrows_the_answer(self):
        self.bank.user = self.bank.owner
        data = self.find(kinds='article')
        self.assertEqual(set(data['results']), {'article'})

    def test_a_snippet_shows_where_the_match_is_without_markup(self):
        self.db.query(Article).filter(Article.id == 1).update(
            {"summary": None, "content": "## Heading\n\nSee ![scan](/uploads/x.png) the **febrile** child."})
        self.db.commit()
        self.bank.user = self.bank.owner
        snippet = next(row for row in self.find()['results']['article'] if row['id'] == 1)['snippet']
        self.assertIn('febrile', snippet)
        self.assertNotIn('##', snippet)
        self.assertNotIn('/uploads/', snippet)

    def test_suggestions_prefer_a_prefix_and_respect_drafts(self):
        self.bank.user = self.bank.owner
        titles = [s['title'] for s in self.client.get(
            '/search/suggest', params={'q': 'febrile'}).json()['suggestions']]
        self.assertEqual(titles, ['Febrile seizures'])
        self.bank.user = self.bank.mod
        titles = [s['title'] for s in self.client.get(
            '/search/suggest', params={'q': 'febrile'}).json()['suggestions']]
        self.assertIn('Febrile draft', titles)
        self.assertEqual(self.client.get('/search/suggest', params={'q': 'f'}).json()['suggestions'], [])