Cleanup: best-guess sex from first name (offline dictionary)

A "Guess from first name" option in the Cleanup gender section: a bundled,
curated given-name -> sex dictionary (weighted English + German for the first
real tree) proposes sex for people who don't have it set. Deterministic, offline,
no model. Genuinely ambiguous names (Marion, Frances, Jordan, …) are excluded
from both sets so they're left for a human. Reuses the existing preview/apply
gender flow, so every guess is reviewed before saving.

No migration. 56 backend tests pass; frontend builds.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
2026-06-08 10:30:35 -04:00
parent 7405ec762f
commit 6ec852a23a
7 changed files with 243 additions and 3 deletions
+22
View File
@@ -87,6 +87,28 @@ async def test_gender_from_source(client):
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.