provenance/backend/tests/test_cleanup.py

"""Tree cleanup: preview/apply for deceased-by-year, gender-from-source, names."""

from tests.conftest import auth, register


async def _tree(client, email):
    h = auth(await register(client, email))
    tid = (await client.post("/api/v1/trees", json={"name": "T"}, headers=h)).json()["id"]
    return h, tid


async def _person(client, h, tid, given, surname=None):
    return (
        await client.post(
            f"/api/v1/trees/{tid}/persons", json={"given": given, "surname": surname}, headers=h
        )
    ).json()["id"]


async def _birth(client, h, tid, pid, year):
    await client.post(
        f"/api/v1/trees/{tid}/events",
        json={"event_type": "birth", "person_id": pid, "date_value": str(year)},
        headers=h,
    )


async def test_deceased_preview_and_apply(client):
    h, tid = await _tree(client, "cl-dec@example.com")
    old = await _person(client, h, tid, "Josias", "Moody")
    young = await _person(client, h, tid, "Kid", "Moody")
    await _birth(client, h, tid, old, 1900)
    await _birth(client, h, tid, young, 1990)

    prev = (
        await client.get(f"/api/v1/trees/{tid}/cleanup/deceased?born_on_or_before=1930", headers=h)
    ).json()
    assert [r["person_id"] for r in prev] == [old]

    r = await client.post(
        f"/api/v1/trees/{tid}/cleanup/deceased", json={"person_ids": [old]}, headers=h
    )
    assert r.status_code == 200 and r.json()["updated"] == 1
    assert (
        await client.get(f"/api/v1/trees/{tid}/persons/{old}", headers=h)
    ).json()["is_living"] is False
    # Re-preview no longer lists the now-deceased person.
    prev2 = (
        await client.get(f"/api/v1/trees/{tid}/cleanup/deceased?born_on_or_before=1930", headers=h)
    ).json()
    assert old not in [r["person_id"] for r in prev2]


async def test_gender_from_spouse_preview_and_apply(client):
    h, tid = await _tree(client, "cl-spouse@example.com")
    husband = (
        await client.post(
            f"/api/v1/trees/{tid}/persons",
            json={"given": "Otto", "surname": "Frey", "gender": "male"},
            headers=h,
        )
    ).json()["id"]
    wife = await _person(client, h, tid, "Bea", "Frey")  # no sex
    loner = await _person(client, h, tid, "Nyx", "Alone")  # no sex, no partner
    await client.post(
        f"/api/v1/trees/{tid}/relationships",
        json={"type": "partnership", "person_from_id": husband, "person_to_id": wife},
        headers=h,
    )

    prev = (await client.get(f"/api/v1/trees/{tid}/cleanup/gender/from-spouse", headers=h)).json()
    by = {r["person_id"]: r["proposed_gender"] for r in prev}
    assert by.get(wife) == "female"  # opposite of the confirmed-male husband
    assert loner not in by  # no known-sex partner → not proposed
    assert husband not in by  # already has a sex

    r = await client.post(
        f"/api/v1/trees/{tid}/cleanup/gender",
        json={"updates": [{"person_id": wife, "gender": "female"}]},
        headers=h,
    )
    assert r.status_code == 200 and r.json()["updated"] == 1
    assert (
        await client.get(f"/api/v1/trees/{tid}/persons/{wife}", headers=h)
    ).json()["gender"] == "female"

    # Once set, the wife is no longer proposed.
    prev2 = (await client.get(f"/api/v1/trees/{tid}/cleanup/gender/from-spouse", headers=h)).json()
    assert wife not in [r["person_id"] for r in prev2]


GED = b"""0 HEAD
0 @I1@ INDI
1 NAME Josias /Moody/
1 SEX M
0 @I2@ INDI
1 NAME Flora /Paul/
1 SEX F
0 TRLR
"""


async def test_gender_from_source(client):
    h, tid = await _tree(client, "cl-gen@example.com")
    await _person(client, h, tid, "Josias", "Moody")
    await _person(client, h, tid, "Flora", "Paul")
    await _person(client, h, tid, "Nobody", "Else")  # not in source

    prev = await client.post(
        f"/api/v1/trees/{tid}/cleanup/gender/preview",
        files={"file": ("src.ged", GED, "text/plain")},
        headers=h,
    )
    props = prev.json()
    by_name = {p["name"]: p["proposed_gender"] for p in props}
    assert by_name == {"Josias Moody": "male", "Flora Paul": "female"}

    updates = [{"person_id": p["person_id"], "gender": p["proposed_gender"]} for p in props]
    r = await client.post(
        f"/api/v1/trees/{tid}/cleanup/gender", json={"updates": updates}, headers=h
    )
    assert r.status_code == 200 and r.json()["updated"] == 2
    people = (await client.get(f"/api/v1/trees/{tid}/persons", headers=h)).json()
    genders = {p["primary_name"]: p["gender"] for p in people}
    assert genders["Josias Moody"] == "male" and genders["Flora Paul"] == "female"


async def test_guess_gender_from_first_name(client):
    h, tid = await _tree(client, "cl-guess@example.com")
    await _person(client, h, tid, "William", "Paul")  # male
    await _person(client, h, tid, "Flora", "Reier")  # female
    await _person(client, h, tid, "Marion", "Doe")  # ambiguous -> skipped
    # Already-gendered person is left alone even if guessable.
    gendered = await _person(client, h, tid, "James", "Known")
    await client.patch(
        f"/api/v1/trees/{tid}/persons/{gendered}", json={"gender": "male"}, headers=h
    )

    prev = (await client.get(f"/api/v1/trees/{tid}/cleanup/gender/guess", headers=h)).json()
    by = {p["name"]: p["proposed_gender"] for p in prev}
    assert by == {"William Paul": "male", "Flora Reier": "female"}

    updates = [{"person_id": p["person_id"], "gender": p["proposed_gender"]} for p in prev]
    r = await client.post(
        f"/api/v1/trees/{tid}/cleanup/gender", json={"updates": updates}, headers=h
    )
    assert r.status_code == 200 and r.json()["updated"] == 2


async def test_name_issues_preview_and_fix(client):
    h, tid = await _tree(client, "cl-name@example.com")
    # surname got a date; real surname landed in the given name.
    bad = await _person(client, h, tid, "Henry Paul", "1859")
    await _person(client, h, tid, "Normal", "Person")  # should not be flagged

    issues = (await client.get(f"/api/v1/trees/{tid}/cleanup/names", headers=h)).json()
    assert len(issues) == 1 and issues[0]["issue"] == "date_in_surname"
    name_id = issues[0]["name_id"]

    r = await client.post(
        f"/api/v1/trees/{tid}/cleanup/names",
        json={"edits": [{"name_id": name_id, "given": "Henry", "surname": "Paul"}]},
        headers=h,
    )
    assert r.status_code == 200 and r.json()["updated"] == 1
    person = (await client.get(f"/api/v1/trees/{tid}/persons/{bad}", headers=h)).json()
    assert person["primary_name"] == "Henry Paul"