The readers flattened a posting's HTML into one line with strip_html, so sections and bullets ran together. _shared.html_text gives a line per paragraph, '• ' before a list item and '## ' before a heading; every reader's description goes through it, sections read per role get their own headings, and the reader pane draws the lines as h3, ul and p. Excerpts leave the marks out. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
111 lines
4.5 KiB
Python
111 lines
4.5 KiB
Python
"""Workable: every location of a role, the country and the hours it states.
|
|
No network: the fixture has the shape of Hugging Face's board, read on
|
|
2026-09-30."""
|
|
|
|
from __future__ import annotations
|
|
|
|
import json
|
|
import sys
|
|
from pathlib import Path
|
|
|
|
import pytest
|
|
|
|
|
|
ROOT = Path(__file__).resolve().parents[1]
|
|
if str(ROOT) not in sys.path:
|
|
sys.path.insert(0, str(ROOT))
|
|
|
|
from plugins.readers import Ask, _runner, workable # noqa: E402
|
|
from plugins.readers._shared import html_text # noqa: E402
|
|
|
|
FIXTURES = ROOT / "tests" / "fixtures" / "ats"
|
|
|
|
|
|
def _rows() -> list[dict]:
|
|
return workable.parse((FIXTURES / "workable-places.json").read_bytes(), "acme")
|
|
|
|
|
|
def test_the_declaration_says_what_the_list_gives() -> None:
|
|
reads = workable.READS
|
|
assert (reads.listing, reads.page_size, reads.places, reads.text) == \
|
|
("paged", 10, "many", "detail")
|
|
assert reads.fields.posted == "trusted" and reads.fields.employment == "stated"
|
|
assert "/api/v3/accounts/<slug>/jobs" in reads.robots
|
|
|
|
|
|
def test_page_takes_the_ask_and_posts_the_same_body() -> None:
|
|
sent: list[dict] = []
|
|
|
|
def get(url: str, *, method: str = "GET", payload: dict | None = None, **_: object) -> bytes:
|
|
sent.append({"url": url, "method": method, "payload": payload})
|
|
return b'{"total": 0, "results": []}'
|
|
|
|
workable.page(get, "acme", None, Ask())
|
|
workable.page(get, "acme", "tok", Ask())
|
|
assert [s["payload"] for s in sent] == [{}, {"token": "tok"}]
|
|
|
|
|
|
def test_every_location_of_a_role_is_a_place_once() -> None:
|
|
first, remote, oslo = _rows()
|
|
assert [p["text"] for p in first["places"]] == ["Berlin, Germany", "Munich, Bavaria, Germany",
|
|
"Paris, France"]
|
|
assert first["location"] == "Berlin, Germany; Munich, Bavaria, Germany; Paris, France"
|
|
assert "country" not in first # prep derives it from the places
|
|
assert [p["remote"] for p in first["places"]] == [False] * 3
|
|
assert remote["places"] == [{"text": "France", "remote": True}]
|
|
# A list-less answer (the older shape) still gives its one place.
|
|
assert oslo["places"] == [{"text": "Oslo, Norway", "remote": False}]
|
|
|
|
|
|
def test_the_stated_hours_are_the_hosts_word() -> None:
|
|
assert [r["employment"] for r in _rows()] == ["full", "part", "volunteer"]
|
|
|
|
|
|
def test_the_shape_of_a_real_list_answer_is_read() -> None:
|
|
data = json.loads((FIXTURES / "workable-places.json").read_bytes())
|
|
assert workable.rows(data, "acme")[0]["url"] == "https://apply.workable.com/acme/j/AAA111/"
|
|
|
|
|
|
def test_a_row_keeps_the_shortcode_the_detail_url_needs() -> None:
|
|
first, remote, oslo = _rows()
|
|
assert [r["source_id"] for r in (first, remote, oslo)] == ["8001", "8002", "8003"]
|
|
assert [r["shortcode"] for r in (first, remote, oslo)] == ["AAA111", "BBB222", "CCC333"]
|
|
|
|
|
|
def test_detail_reads_description_requirements_and_benefits() -> None:
|
|
asked: list[str] = []
|
|
body = (FIXTURES / "workable-detail.json").read_bytes()
|
|
|
|
def get(url: str, **_: object) -> bytes:
|
|
asked.append(url)
|
|
return body
|
|
|
|
row = {"source_id": "6125026", "shortcode": "DB4D7C0EC8"}
|
|
found = workable.detail(get, "huggingface", row)
|
|
assert asked == ["https://apply.workable.com/api/v2/accounts/huggingface/jobs/DB4D7C0EC8"]
|
|
assert set(found) == {"description"} and set(found) <= set(_runner.DETAIL_FIELDS)
|
|
text, data = found["description"], json.loads(body)
|
|
for key in ("description", "requirements", "benefits"):
|
|
assert html_text(data[key]) in text
|
|
assert text.index(html_text(data["description"])) < text.index(html_text(data["benefits"]))
|
|
assert "<" not in text and " " not in text and len(text) > 1500
|
|
|
|
|
|
def test_detail_joins_what_is_there_and_unescapes() -> None:
|
|
body = json.dumps({"description": "<p>Build & run</p>", "requirements": None,
|
|
"benefits": "<ul><li>Pension</li></ul>"}).encode()
|
|
assert workable.detail(lambda url, **_: body, "acme", {"shortcode": "AAA111"}) == \
|
|
{"description": "Build & run\n## Benefits\n\u2022 Pension"}
|
|
|
|
|
|
@pytest.mark.parametrize("body", [b"{}", b"[]", b'{"title": "x"}'])
|
|
def test_detail_refuses_an_answer_that_is_not_a_role(body: bytes) -> None:
|
|
with pytest.raises(ValueError, match="not a Workable role"):
|
|
workable.detail(lambda url, **_: body, "acme", {"shortcode": "AAA111"})
|
|
|
|
|
|
@pytest.mark.parametrize("row", [{}, {"shortcode": ""}, {"shortcode": "a/b"}, {"shortcode": ".."}])
|
|
def test_detail_needs_a_plain_shortcode(row: dict) -> None:
|
|
with pytest.raises(ValueError, match="shortcode"):
|
|
workable.detail(lambda url, **_: b"{}", "acme", row)
|