spb/trouve-ka Public

1# Trouve-KA — tests du scoring Québec2# Author: Simon-Pierre Boucher3# Contact: contact@spboucher.ai45from trouveka.classifier import score_page6from trouveka.types import ParsedPage789def _page(**kwargs) -> ParsedPage:10    defaults = {"url": "https://example.com/page", "title": "", "body": ""}11    return ParsedPage(**(defaults | kwargs))121314def test_quebec_business_scores_high():15    page = _page(16        url="https://plomberiexyz.qc.ca/services",17        title="Plomberie XYZ — Plombier à Gatineau",18        description="Service de plomberie résidentielle en Outaouais",19        body="Plomberie XYZ dessert Gatineau et l'Outaouais. 123 rue Principale, Gatineau (Québec) J8X 3X3. "20             "Appelez-nous au 819-555-1234. Urgences 24h partout au Québec.",21        headings=["Plombier Gatineau", "Nos services"],22        language="fr",23    )24    signals = score_page(page, "plomberiexyz.qc.ca")25    assert signals.score > 0.726    assert "gatineau" in signals.locations27    assert "tld_quebec" in signals.reasons28    assert "code_postal_qc" in signals.reasons293031def test_ontario_business_scores_low():32    page = _page(33        url="https://ottawaplumbing.ca/",34        title="Ottawa Plumbing Services",35        description="Plumbing services in Ottawa, Ontario",36        body="We serve Ottawa, Kanata and Nepean. 456 Bank Street, Ottawa, ON K1S 3T4. Call 613-555-9999.",37        headings=["Plumbing Ottawa"],38        language="en",39    )40    signals = score_page(page, "ottawaplumbing.ca")41    assert signals.score < 0.2424344def test_nyt_article_about_montreal_gets_page_signal():45    # Un article international SUR Montréal : le domaine n'est pas québécois,46    # mais la page a un signal réel (page_quebec_score > 0, sans être maximal).47    page = _page(48        url="https://www.nytimes.com/2026/01/01/travel/montreal.html",49        title="36 Hours in Montreal",50        description="What to do in Montreal, Quebec's largest city",51        body="Montreal is the largest city in Quebec. From the Plateau-Mont-Royal to Old Montreal, "52             "the city offers poutine, festivals and more. Nearby Laval and Longueuil...",53        headings=["36 Hours in Montreal"],54        language="en",55    )56    signals = score_page(page, "nytimes.com")57    assert 0.2 < signals.score < 0.858    assert "montreal" in signals.locations596061def test_generic_english_page_scores_near_zero():62    page = _page(63        url="https://techblog.com/post",64        title="Understanding Rust lifetimes",65        body="Rust lifetimes are a way to express the scope of references in your program. " * 20,66        language="en",67    )68    signals = score_page(page, "techblog.com")69    assert signals.score < 0.1707172def test_french_alone_is_not_proof():73    # Une page française de France ne doit pas passer le seuil sur la langue seule74    page = _page(75        url="https://lemonde.fr/article",76        title="Actualités françaises",77        body="La France annonce de nouvelles mesures. Paris, Lyon et Marseille concernées. " * 10,78        language="fr",79    )80    signals = score_page(page, "lemonde.fr")81    assert signals.score < 0.3828384def test_score_saturates_below_one():85    body = "Montréal Québec Gatineau Sherbrooke Laval " * 100 + " H2X 1Y6 G1R 4S9 514-555-0000 Hydro-Québec"86    page = _page(url="https://x.qc.ca/", title="Montréal Québec", body=body, language="fr")87    signals = score_page(page, "x.qc.ca")88    assert 0.8 < signals.score <= 1.089