Oliver Giertz
f0d10112ad
Published articles carried no category, so WordPress filed all of them under the catch-all "Allgemein" - 941 of 955 posts by the time this was noticed. The rules here mirror the one-off backfill of 2026-07-31 and reproduce its result on all 955 posts exactly. Matching is done on word boundaries rather than plain substrings, which otherwise filed a campsite in Klagenfurt under "Recht & Vorschriften" via the keyword "klage". German compounds opt in explicitly with a trailing "*". A clear discount signal takes precedence over the product topic, because product tags otherwise outnumber it. Unknown slugs are never auto-created: unlike tags, the category set is curated in WordPress, so a mismatch should surface rather than spawn a new category. Articles that match no rule stay uncategorised on purpose. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
61 lines
2.9 KiB
Python
61 lines
2.9 KiB
Python
import unittest
|
|
|
|
from backend.app.categorize import CATEGORY_SLUGS, category_slug, classify
|
|
|
|
|
|
class TestCategorize(unittest.TestCase):
|
|
def test_tags_decide_the_category(self) -> None:
|
|
self.assertEqual(
|
|
classify("Neuer Platz am Wasser", ["Campingplatz", "5-Sterne-Campingplätze"]),
|
|
"campingplaetze",
|
|
)
|
|
self.assertEqual(classify("Unterwegs im Norden", ["Nordsee", "Niedersachsen"]), "reiseziele")
|
|
self.assertEqual(classify("Update vom Van", ["Wohnmobil", "Truma", "Solar"]), "fahrzeug-technik")
|
|
|
|
def test_title_alone_is_enough(self) -> None:
|
|
self.assertEqual(classify("Dometic CFX5 45 im Test: Top-Kühlbox", []), "ausruestung-tests")
|
|
self.assertEqual(classify("Führerscheine müssen getauscht werden", []), "recht-vorschriften")
|
|
|
|
def test_discount_signal_beats_the_product_topic(self) -> None:
|
|
# Without the override this lands in "Ausruestung & Tests", because the
|
|
# product tags outnumber the single discount signal.
|
|
self.assertEqual(
|
|
classify("Campingzelte bei Amazon im Sale: bis zu 55 %", ["Zelte", "Schlafsack", "Rabatt"]),
|
|
"angebote-rabatte",
|
|
)
|
|
|
|
def test_keywords_respect_word_boundaries(self) -> None:
|
|
# "klage" must not match the city name "Klagenfurt" - plain substring
|
|
# matching filed this campsite opening under "Recht & Vorschriften".
|
|
self.assertEqual(
|
|
classify("Falkensteiner Camping Wörthersee startet in die erste Saison",
|
|
["Campingplatz", "Klagenfurt", "Saisonstart"]),
|
|
"campingplaetze",
|
|
)
|
|
|
|
def test_compound_nouns_only_match_with_opt_in(self) -> None:
|
|
# "campingplatz*" is marked as a compound, so this still matches.
|
|
self.assertEqual(classify("Was Campingplatzbetreiber jetzt planen", []), "campingplaetze")
|
|
|
|
def test_returns_none_when_nothing_matches(self) -> None:
|
|
self.assertIsNone(classify("Weihnachten 2021", ["Weihnachten"]))
|
|
self.assertIsNone(category_slug("Weihnachten 2021", ["Weihnachten"]))
|
|
|
|
def test_umlauts_and_entities_are_normalised(self) -> None:
|
|
self.assertEqual(classify("Stellplätze an der Küste", []), "stellplaetze")
|
|
self.assertEqual(classify("Ausr&uuml;stung", ["Schlafsack"]), "ausruestung-tests")
|
|
|
|
def test_renamed_categories_keep_their_original_slug(self) -> None:
|
|
# Both were renamed in WordPress but kept the indexed archive URL.
|
|
self.assertEqual(CATEGORY_SLUGS["fahrzeug-technik"], "fahrzeug")
|
|
self.assertEqual(CATEGORY_SLUGS["news-branche"], "news")
|
|
self.assertEqual(category_slug("Update vom Van", ["Wohnmobil", "Truma"]), "fahrzeug")
|
|
|
|
def test_every_rule_maps_to_a_known_slug(self) -> None:
|
|
self.assertEqual(len(CATEGORY_SLUGS), 11)
|
|
for key, slug in CATEGORY_SLUGS.items():
|
|
self.assertTrue(slug and slug.islower(), f"{key} has a suspicious slug: {slug!r}")
|
|
|
|
|
|
if __name__ == "__main__":
|
|
unittest.main()
|