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>
120 lines
5.2 KiB
Python
120 lines
5.2 KiB
Python
"""SmartRecruiters: the place, country, level and employment a posting states.
|
|
No network: the shapes are those of Bosch'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 desk.sources import strip_html # noqa: E402
|
|
from plugins.readers import Ask, _runner, smartrecruiters # noqa: E402
|
|
|
|
FIXTURES = ROOT / "tests" / "fixtures" / "ats"
|
|
|
|
|
|
def _posting(**fields: object) -> dict:
|
|
return {"id": "1", "name": "Engineer", "releasedDate": "2026-09-30T06:57:01.920Z",
|
|
"location": {"city": "Hatvan", "country": "hu", "remote": False,
|
|
"fullLocation": "Hatvan, , Hungary"}, **fields}
|
|
|
|
|
|
def _rows(*postings: dict) -> list[dict]:
|
|
return smartrecruiters.rows({"content": list(postings)}, "BoschGroup")
|
|
|
|
|
|
def test_the_declaration_says_what_the_list_gives() -> None:
|
|
reads = smartrecruiters.READS
|
|
assert (reads.listing, reads.page_size, reads.places, reads.text, reads.empty) == \
|
|
("paged", 100, "one", "detail", "suspect")
|
|
assert reads.fields.posted == "trusted" and reads.fields.seniority == "stated"
|
|
assert reads.robots.startswith("read though") and "owner to decide" in reads.robots
|
|
|
|
|
|
def test_page_reads_by_offset_and_takes_the_ask() -> None:
|
|
asked: list[str] = []
|
|
|
|
def get(url: str, **_: object) -> bytes:
|
|
asked.append(url)
|
|
return (FIXTURES / "smartrecruiters.json").read_bytes()
|
|
|
|
_data, results, total, cursor = smartrecruiters.page(get, "Acme", None, Ask())
|
|
assert asked == ["https://api.smartrecruiters.com/v1/companies/Acme/postings"
|
|
"?offset=0&limit=100"]
|
|
assert (len(results), total, cursor) == (2, 3, 2)
|
|
|
|
|
|
def test_the_place_is_one_clean_line_with_its_remote_flag_and_country() -> None:
|
|
[row] = _rows(_posting())
|
|
assert row["places"] == [{"text": "Hatvan, Hungary", "remote": False}] # ", ," gone
|
|
assert row["location"] == "Hatvan, Hungary" and row["country"] == "hu"
|
|
[remote] = _rows(_posting(location={"remote": True, "fullLocation": "Remote", "country": ""}))
|
|
assert remote["places"] == [{"text": "Remote", "remote": True}] and remote["country"] is None
|
|
[none] = _rows(_posting(location={}))
|
|
assert none["places"] == [] and none["location"] == ""
|
|
|
|
|
|
def test_the_stated_level_and_employment_are_the_hosts_words() -> None:
|
|
[row] = _rows(_posting(experienceLevel={"id": "internship", "label": "Internship"},
|
|
typeOfEmployment={"id": "intern", "label": "Intern"}))
|
|
assert (row["seniority"], row["employment"]) == ("internship", "intern")
|
|
[row] = _rows(_posting(experienceLevel={"id": "mid_senior_level"}))
|
|
assert row["seniority"] == "mid_senior_level"
|
|
[row] = _rows(_posting())
|
|
assert row["seniority"] is None and row["employment"] is None
|
|
|
|
|
|
def test_the_saved_page_still_reads() -> None:
|
|
data = json.loads((FIXTURES / "smartrecruiters.json").read_bytes())
|
|
assert [r["location"] for r in smartrecruiters.rows(data, "Acme")] == ["Berlin, Germany",
|
|
"Remote"]
|
|
|
|
|
|
def test_detail_reads_the_ad_without_the_company_blurb() -> None:
|
|
asked: list[str] = []
|
|
|
|
def get(url: str, **_: object) -> bytes:
|
|
asked.append(url)
|
|
return (FIXTURES / "smartrecruiters-detail.json").read_bytes()
|
|
|
|
found = smartrecruiters.detail(get, "deliveryhero", {"source_id": "744000151349134"})
|
|
assert asked == ["https://api.smartrecruiters.com/v1/companies/deliveryhero/postings/"
|
|
"744000151349134"]
|
|
assert set(found) == {"description"} and set(found) <= set(_runner.DETAIL_FIELDS)
|
|
text = found["description"]
|
|
data = json.loads((FIXTURES / "smartrecruiters-detail.json").read_bytes())
|
|
sections = data["jobAd"]["sections"]
|
|
assert data["jobAd"]["sections"]["companyDescription"]["text"]
|
|
assert strip_html(sections["companyDescription"]["text"])[:60] not in text
|
|
assert strip_html(sections["jobDescription"]["text"])[:60] in text
|
|
assert strip_html(sections["qualifications"]["text"])[-40:] in text
|
|
assert strip_html(sections["additionalInformation"]["text"])[-40:] in text
|
|
assert "<" not in text and " " not in text and len(text) > 1500
|
|
|
|
|
|
def test_detail_leaves_out_a_section_the_ad_lacks() -> None:
|
|
body = json.dumps({"jobAd": {"sections": {
|
|
"jobDescription": {"text": "<p>Build & run</p><ul><li>APIs</li></ul>"}}}}).encode()
|
|
assert smartrecruiters.detail(lambda url, **_: body, "Acme", {"source_id": "7"}) == \
|
|
{"description": "Build & run\n\u2022 APIs"}
|
|
|
|
|
|
@pytest.mark.parametrize("body", [b"{}", b'{"jobAd": {}}', b'{"jobAd": null}', b"[]"])
|
|
def test_detail_refuses_an_answer_that_is_not_a_posting(body: bytes) -> None:
|
|
with pytest.raises(ValueError, match="not a SmartRecruiters posting"):
|
|
smartrecruiters.detail(lambda url, **_: body, "Acme", {"source_id": "7"})
|
|
|
|
|
|
def test_detail_cannot_add_to_the_path() -> None:
|
|
asked: list[str] = []
|
|
smartrecruiters.detail(lambda url, **_: asked.append(url) or b'{"jobAd":{"sections":{}}}',
|
|
"Acme", {"source_id": "7/../x"})
|
|
assert asked == ["https://api.smartrecruiters.com/v1/companies/Acme/postings/7%2F..%2Fx"]
|