election-game/backend/data/pipeline/tests/people/test_people_elections.py

247 lines
8.0 KiB
Python
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

"""2026 候選人名單與中選會選舉結果的解析。"""
from __future__ import annotations
import json
from collections.abc import Iterator
import pytest
from election_data.people.candidates import (
COUNTY,
MUNICIPAL,
article_html,
parse_elcand,
parse_press_release,
to_claim,
)
from election_data.people.cec_results import ElectionSpec, candidate_totals, load_at_large, load_election
pytestmark = pytest.mark.unit
PRESS_BODY = (
"<p>中央選舉委員會今(16)日舉行委員會議…</p>"
"<p>一、直轄市長候選人部分:受理登記計3人,均符合規定:</p>"
"<p>(一)臺北市3人:郭璽、沈伯洋、蔣萬安。</p>"
"<p>二、縣(市)長候選人部分:受理登記計4人,均符合規定:</p>"
"<p>(一)新竹縣2人:鄭朝方、徐欣瑩。</p>"
"<p>(二)嘉義市2人:黃宏成台灣阿成世界偉人財神總統、張啓楷。</p>"
"<p>三、直轄市議員候選人部分:受理登記計610人…</p>"
"<p>(一)臺北市不符合規定者計1人:某某…</p>"
)
def _api(body: str) -> dict:
content = json.dumps({"content": [{"blockType": "Text", "content": body}]}, ensure_ascii=False)
return {"code": 0, "data": {"content": content, "beginTime": "20261016"}}
def test_parse_press_release() -> None:
body, date = article_html(_api(PRESS_BODY))
entries = parse_press_release(body, "cec")
assert date == "2026-10-16"
assert [(e.county, e.name, e.office) for e in entries][:2] == [
("臺北市", "郭璽", MUNICIPAL),
("臺北市", "沈伯洋", MUNICIPAL),
]
assert sum(e.office == COUNTY for e in entries) == 4
assert "某某" not in {e.name for e in entries} # 議員段落不算
def test_parse_press_release_count_mismatch_raises() -> None:
with pytest.raises(ValueError, match="應有 3 人"):
parse_press_release(PRESS_BODY.replace("郭璽、", ""), "cec")
def test_parse_press_release_total_mismatch_raises() -> None:
with pytest.raises(ValueError, match="候選人應有"):
parse_press_release(PRESS_BODY.replace("受理登記計4人", "受理登記計5人"), "cec")
def test_parse_elcand_and_claim() -> None:
elbase = [["63", "000", "00", "000", "0000", "臺北市"]]
elpaty = [["1", "中國國民黨"], ["999", "無黨籍及未經政黨推薦"]]
elcand = [
[
"63",
"000",
"00",
"000",
"0000",
"1",
"甲某",
"999",
"2",
"0650515",
"61",
"臺北市",
"博士",
"N",
"",
"",
],
[
"63",
"000",
"00",
"000",
"0000",
"2",
"乙某",
"1",
"1",
"0671226",
"47",
"臺北市",
"博士",
"Y",
"",
"",
],
[
"63",
"000",
"00",
"000",
"0000",
"2",
"副手某",
"1",
"1",
"0600101",
"66",
"臺北市",
"碩士",
"N",
"",
"Y",
],
]
entries = parse_elcand(elcand, elbase, elpaty, MUNICIPAL, "elcand")
assert [e.name for e in entries] == ["甲某", "乙某"]
first, second = entries
assert (first.party, first.party_known, first.gender, first.birth_date) == (None, True, "F", "1976-05-15")
assert (second.number, second.party) == (2, "中國國民黨")
claim = to_claim(second, "2026-11-12")
assert claim.positions[0].title == "臺北市長候選人(號次 2)"
assert claim.party and claim.party.value == "中國國民黨"
assert claim.birth_date and claim.birth_date.value == "1978-12-26"
def test_parse_elcand_unknown_county_raises() -> None:
row = ["99", "999", "00", "000", "0000", "1", "某", "1", "1", "0650515", "61", "", "", "N", "", ""]
with pytest.raises(ValueError):
parse_elcand([row], [], [], COUNTY, "x")
def _ctks(
prv: str, city: str, area: str, town: str, vil: str, station: str, no: str, votes: int
) -> list[str]:
return [prv, city, area, town, vil, station, no, str(votes), "0", ""]
def test_candidate_totals_district_level_and_verification() -> None:
rows = [
_ctks("63", "000", "01", "000", "0000", "0000", "1", 30),
_ctks("63", "000", "01", "010", "0000", "0000", "1", 30), # 鄉鎮層級,不採用
_ctks("63", "000", "01", "010", "0001", "0001", "1", 10),
_ctks("63", "000", "01", "010", "0002", "0002", "1", 20),
]
assert candidate_totals(rows, national=False) == {("63", "000", "01", "1"): 30}
bad = [*rows[:-1], _ctks("63", "000", "01", "010", "0002", "0002", "1", 21)]
with pytest.raises(ValueError, match="不一致"):
candidate_totals(bad, national=False)
def test_candidate_totals_national() -> None:
rows = [
_ctks("00", "000", "00", "000", "0000", "0000", "1", 15),
_ctks("63", "000", "00", "000", "0000", "0000", "1", 15),
_ctks("63", "000", "01", "010", "0001", "0001", "1", 5),
_ctks("64", "000", "01", "010", "0001", "0002", "1", 10),
]
assert candidate_totals(rows, national=True) == {("00", "000", "00", "1"): 15}
class FakeArchive:
def __init__(self, tables: dict[str, list[list[str]]]) -> None:
self.tables = tables
def rows(self, folder: str, kind: str) -> Iterator[list[str]]:
yield from self.tables[kind]
def test_load_election_shares_and_district_labels() -> None:
archive = FakeArchive(
{
"elpaty": [["1", "中國國民黨"], ["16", "民主進步黨"]],
"elbase": [["10", "002", "00", "000", "0000", "宜蘭縣"]],
"elcand": [
[
"10",
"002",
"01",
"000",
"0000",
"1",
"甲",
"1",
"1",
"0600101",
"",
"",
"大學",
"N",
"",
"",
],
[
"10",
"002",
"01",
"000",
"0000",
"2",
"乙",
"16",
"2",
"0700101",
"",
"",
"碩士",
"Y",
"*",
"",
],
],
"elctks": [
_ctks("10", "002", "01", "000", "0000", "0000", "1", 40),
_ctks("10", "002", "01", "000", "0000", "0000", "2", 60),
_ctks("10", "002", "01", "010", "0001", "0001", "1", 40),
_ctks("10", "002", "01", "010", "0001", "0001", "2", 60),
],
}
)
spec = ElectionSpec("x", "2024 立法委員選舉(區域)", "legislator_district", None)
a, b = load_election(archive, spec) # type: ignore[arg-type]
assert (a.district, a.county, a.votes, a.share, a.elected) == ("宜蘭縣選舉區", "宜蘭縣", 40, 0.4, False)
assert (b.party, b.gender, b.birth_date, b.elected) == ("民主進步黨", "F", "1981-01-01", True)
def test_load_at_large_from_elrepm() -> None:
archive = FakeArchive(
{
"elpaty": [["1", "中國國民黨"]],
"elrepm": [["1", "1", "韓國瑜", "1", "0460617", "66", "新北市", "碩士", "N", "*"]],
}
)
(r,) = load_at_large(archive) # type: ignore[arg-type]
assert (r.name, r.party, r.gender, r.birth_date, r.votes, r.elected) == (
"韓國瑜",
"中國國民黨",
"M",
"1957-06-17",
None,
True,
)