tests/test_locations.py

"""Location parsing tests."""

from coastwise.locations import location_context_from_model, location_candidates, parse_location


def test_parse_location_from_question_or_optional_beach_field():
    pacifica = parse_location("can I eat mussels from Pacifica today?", "")
    monterey = parse_location("what's the lingcod size?", "Monterey")
    blank = parse_location("what's the min size of lingcod?", "")
    unsupported = parse_location("what are trout rules?", "Lake Tahoe")

    assert pacifica.matched_place == "Pacifica"
    assert pacifica.region_key == "san_francisco"
    assert monterey.matched_place == "Monterey"
    assert monterey.region_key == "central"
    assert blank.confidence == "absent"
    assert "local" in (blank.warning or "").lower()
    assert unsupported.confidence == "unsupported"
    assert "california ocean" in (unsupported.warning or "").lower()


def test_parse_location_recognizes_half_moon_bay_for_public_queries():
    context = parse_location("is shellfish quarantine in half moon bay?", "")

    assert context.matched_place == "Half Moon Bay"
    assert context.region_key == "san_francisco"
    assert context.confidence == "recognized"


def test_location_candidates_include_official_regions_without_typo_alias_growth():
    candidates = location_candidates()

    assert candidates["Mendocino"] == "mendocino"
    assert candidates["Mendocino Ocean Region"] == "mendocino"
    assert "Mandocino" not in candidates


def test_location_context_from_validated_model_output():
    context = location_context_from_model(
        question="im in mandocino. is it legal to harvest dungenese crabs?",
        location_text="",
        location_name="Mendocino",
        region_key="mendocino",
    )

    assert context.matched_place == "Mendocino"
    assert context.region_key == "mendocino"
    assert context.confidence == "recognized"
    assert context.warning is None


def test_location_context_from_model_preserves_existing_alias_scope():
    context = location_context_from_model(
        question="can I eat mussels from pacifica today?",
        location_text="",
        location_name="Pacifica",
        region_key="san_francisco",
    )

    assert context.matched_place == "Pacifica"
    assert context.region_key == "san_francisco"
    assert context.area_or_scope == "San Francisco coast"


def test_location_context_from_missing_model_output_falls_back_to_parse_location():
    context = location_context_from_model(
        question="can I eat mussels from Pacifica today?",
        location_text="",
        location_name=None,
        region_key=None,
    )

    assert context.matched_place == "Pacifica"
    assert context.region_key == "san_francisco"
    assert context.area_or_scope == "San Francisco coast"


def test_location_context_from_model_name_region_mismatch_falls_back_to_parse_location():
    context = location_context_from_model(
        question="what's the lingcod size?",
        location_text="Monterey",
        location_name="Pacifica",
        region_key="central",
    )

    assert context.matched_place == "Monterey"
    assert context.region_key == "central"
    assert context.area_or_scope == "Central California ocean region"


def test_parse_location_fuzzy_matches_misspelled_mendocino():
    context = parse_location("im in mandocino. is it legal to harvest dungenese crabs?", "")

    assert context.matched_place == "Mendocino"
    assert context.region_key == "mendocino"


def test_parse_location_fuzzy_does_not_false_match_plain_species_question():
    context = parse_location("what's the min size of lingcod?", "")

    assert context.matched_place is None


def test_parse_location_recognizes_sf_abbreviation():
    context = parse_location("is it legal to catch lingcod in sf", "")

    assert context.matched_place == "San Francisco"
    assert context.region_key == "san_francisco"