tests/test_categories.py

import pytest

from finbot.categories import CATEGORIES, categorise, coerce, is_valid, label


class TestCategorise:
    @pytest.mark.parametrize(
        "text,expected",
        [
            ("uber ride home", "transport"),
            ("netflix monthly", "subscriptions"),
            ("bigbasket order", "groceries"),
            ("swiggy dinner", "food_dining"),
            ("petrol pump", "fuel"),
            ("electricity bill", "utilities"),
            ("apollo pharmacy", "health"),
            ("bookmyshow tickets", "entertainment"),
            ("amazon order", "shopping"),
            ("atm withdrawal", "cash"),
            ("salary credited", "income"),
        ],
    )
    def test_keyword_hits(self, text, expected):
        category, confidence = categorise(text)
        assert category == expected
        assert confidence == 1.0

    def test_unknown_returns_other_with_zero_confidence(self):
        category, confidence = categorise("blorptastic widget")
        assert category == "other"
        assert confidence == 0.0

    def test_empty_input(self):
        assert categorise("") == ("other", 0.0)

    def test_specificity_order_fuel_beats_transport(self):
        # A petrol pump is fuel, even though it is transport-adjacent.
        assert categorise("indian oil petrol")[0] == "fuel"

    def test_specificity_order_subscription_beats_entertainment(self):
        assert categorise("netflix")[0] == "subscriptions"

    def test_word_boundaries_prevent_false_hits(self):
        # "cashew" must not match the "cash" keyword.
        assert categorise("cashew nuts")[0] != "cash"
        # "gasket" must not match "gas station".
        assert categorise("engine gasket")[0] != "fuel"

    def test_merchant_is_considered(self):
        category, _ = categorise("monthly charge", merchant="Spotify")
        assert category == "subscriptions"

    def test_case_insensitive(self):
        assert categorise("UBER RIDE")[0] == "transport"


class TestCoerce:
    @pytest.mark.parametrize(
        "raw,expected",
        [
            ("food_dining", "food_dining"),
            ("Food", "food_dining"),
            ("dining", "food_dining"),
            ("grocery", "groceries"),
            ("healthcare", "health"),
            ("Subscription", "subscriptions"),
            ("misc", "other"),
            ("", "other"),
            ("total nonsense", "other"),
        ],
    )
    def test_coerce(self, raw, expected):
        assert coerce(raw) == expected

    def test_every_result_is_a_valid_category(self):
        # A stray label from a model must never reach the ledger, or totals
        # fragment across categories that do not exist.
        for raw in ["", "???", "Investments", "food", "TRANSPORT", "x" * 200]:
            assert is_valid(coerce(raw))


class TestLabels:
    def test_every_category_has_a_label(self):
        for category in CATEGORIES:
            assert label(category)
            assert label(category) != category or "_" not in category