Every row carries places (Personio additionalOffices, Workable and Recruitee locations[], every SuccessFactors address, Workday's own read), the list teaser of Phenom and Oracle is kept in teaser, and the level, employment and country a host states are mapped. Workday "N Locations" and "Country - City", and Recruitee "Remote job", are no longer places. Phenom takes dateCreated as posted. robots_page and ROBOTS_ANY_CASE go; READS.robots records the decision. Signatures are feed_url(slug, ask) and page(get, slug, cursor, ask), with an empty Ask as the default so the runner of today still calls them. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
386 lines
17 KiB
Python
386 lines
17 KiB
Python
"""The reader contract, held for every module of `plugins/readers/`.
|
|
|
|
Per module: it declares `READS`, the declaration matches its functions, and
|
|
its rows keep what the contract says they keep. No network: fixtures stand
|
|
in for the host.
|
|
|
|
`UNDECLARED` lists the modules that do not declare `READS` yet; their tests
|
|
are marked xfail (not strict), and the planner removes a name once the
|
|
module declares. A module not in the list must pass.
|
|
|
|
Fixtures, in `tests/fixtures/ats/` for boards and `tests/fixtures/search/`
|
|
for searches, named after the module:
|
|
|
|
- `<name>-places.<ext>`: one listing answer with at least one role at two
|
|
or more places. For `listing="whole"` it is the body `parse` gets; for
|
|
`listing="paged"` it is what every request of the first `page` call
|
|
returns, and `rows` reads that page. Required by the test of a module
|
|
that declares `places="many"`, which is skipped until the fixture exists.
|
|
- `<name>-places-detail.<ext>`: optional, for a host whose places come from
|
|
the role's own page: what `detail`'s requests return; its `places` replace
|
|
the row's.
|
|
- `<name>-teaser.<ext>`: one listing answer with a teaser, read the same
|
|
way. Required by the test of a module with `text="excerpt"` or
|
|
`teaser=True`, skipped until it exists.
|
|
- `<name>.slug`: optional, the slug the fixtures are read with, one line;
|
|
`acme` without it.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import sys
|
|
import types
|
|
from collections.abc import Callable
|
|
from pathlib import Path
|
|
from typing import Any
|
|
|
|
import pydantic
|
|
import pytest
|
|
|
|
ROOT = Path(__file__).resolve().parents[1]
|
|
if str(ROOT) not in sys.path:
|
|
sys.path.insert(0, str(ROOT))
|
|
|
|
from plugins import readers # noqa: E402
|
|
from plugins.readers import Ask, Fields, Filters, Key, Reads # noqa: E402
|
|
from plugins.readers import _contract # noqa: E402
|
|
|
|
FIXTURE_DIRS = (ROOT / "tests" / "fixtures" / "ats", ROOT / "tests" / "fixtures" / "search")
|
|
|
|
#: The modules without `READS` yet. Shrinks as D1 (a to l), D2 (o to w) and
|
|
#: C (the search providers, which arrive declared) land.
|
|
UNDECLARED = frozenset({
|
|
"ashby", "bamboohr", "deel", "eightfold", "gem", "greenhouse", "hibob", "hrmanager",
|
|
"jibe", "jobylon", "lever",
|
|
})
|
|
|
|
|
|
def _params() -> list[Any]:
|
|
return [pytest.param(name, marks=pytest.mark.xfail(reason="no READS yet", strict=False))
|
|
if name in UNDECLARED else name for name in readers.READERS]
|
|
|
|
|
|
def _declared(name: str) -> tuple[types.ModuleType, Reads]:
|
|
module = readers.READERS[name]
|
|
reads = getattr(module, "READS", None)
|
|
assert isinstance(reads, Reads), f"{name} declares no READS"
|
|
return module, reads
|
|
|
|
|
|
def _fixture(name: str, kind: str) -> Path | None:
|
|
for folder in FIXTURE_DIRS:
|
|
found = sorted(folder.glob(f"{name}-{kind}.*"))
|
|
if found:
|
|
return found[0]
|
|
return None
|
|
|
|
|
|
def _slug(name: str) -> str:
|
|
for folder in FIXTURE_DIRS:
|
|
if (path := folder / f"{name}.slug").exists():
|
|
return path.read_text(encoding="utf-8").strip()
|
|
return "acme"
|
|
|
|
|
|
def _answer(body: bytes) -> Callable[..., bytes]:
|
|
return lambda url, **kwargs: body
|
|
|
|
|
|
def read_fixture(module: types.ModuleType, body: bytes, slug: str,
|
|
detail_body: bytes | None = None) -> list[dict[str, Any]]:
|
|
"""The rows `module` makes of one listing answer, as the runner reads
|
|
them: `parse` for a whole listing, the first `page` and its `rows` for a
|
|
paged one, and, given `detail_body`, each row's `places` from `detail`."""
|
|
reads: Reads = module.READS
|
|
if reads.listing == "whole":
|
|
rows = list(module.parse(body, slug))
|
|
else:
|
|
decoded, _results, _total, _cursor = module.page(_answer(body), slug, None, Ask())
|
|
rows = list(module.rows(decoded, slug))
|
|
if detail_body is not None:
|
|
for row in rows:
|
|
found = module.detail(_answer(detail_body), slug, row)
|
|
if "places" in found:
|
|
row["places"] = found["places"]
|
|
return rows
|
|
|
|
|
|
def place_problems(rows: list[dict[str, Any]], places: str) -> list[str]:
|
|
"""What rows get wrong about `places` under the declared trait."""
|
|
out = []
|
|
for row in rows:
|
|
found = row.get("places")
|
|
rid = row.get("source_id")
|
|
if not isinstance(found, list):
|
|
out.append(f"{rid}: places is not a list")
|
|
continue
|
|
for place in found:
|
|
if not (isinstance(place, dict) and set(place) == {"text", "remote"}
|
|
and isinstance(place["text"], str) and place["text"].strip()
|
|
and place["remote"] in (True, False, None)):
|
|
out.append(f"{rid}: {place!r} is not a Place")
|
|
if places in ("one", "copies") and len(found) > 1:
|
|
out.append(f'{rid}: {len(found)} places under places="{places}"')
|
|
if places == "many" and not any(len(row.get("places") or ()) >= 2 for row in rows):
|
|
out.append('no row has two places: a reader with places="many" keeps every place')
|
|
return out
|
|
|
|
|
|
# ------------------------------------------------------------ every module
|
|
|
|
def test_the_undeclared_list_names_only_readers() -> None:
|
|
assert set(readers.READERS) >= UNDECLARED
|
|
|
|
|
|
def test_undeclared_lists_the_modules_without_reads() -> None:
|
|
assert set(readers.undeclared()) == {name for name, module in readers.READERS.items()
|
|
if not hasattr(module, "READS")}
|
|
|
|
|
|
@pytest.mark.parametrize("name", _params())
|
|
def test_a_reader_declares_reads(name: str) -> None:
|
|
_declared(name)
|
|
|
|
|
|
@pytest.mark.parametrize("name", _params())
|
|
def test_a_declaration_matches_the_functions(name: str) -> None:
|
|
module, _reads = _declared(name)
|
|
assert readers.problems(module, name) == []
|
|
expected = "search" if module.READS.scope == "search" else "board"
|
|
assert name in (readers.PROVIDERS if expected == "search" else readers.HOSTS)
|
|
|
|
|
|
@pytest.mark.parametrize("name", _params())
|
|
def test_a_reader_keeps_every_place(name: str) -> None:
|
|
module, reads = _declared(name)
|
|
fixture = _fixture(name, "places")
|
|
if fixture is None:
|
|
if reads.places == "many":
|
|
pytest.skip(f"no fixture {name}-places.* yet")
|
|
pytest.skip(f'places="{reads.places}" and no fixture')
|
|
detail = _fixture(name, "places-detail")
|
|
rows = read_fixture(module, fixture.read_bytes(), _slug(name),
|
|
detail.read_bytes() if detail else None)
|
|
assert rows, f"{fixture.name} gave no rows"
|
|
assert place_problems(rows, reads.places) == []
|
|
|
|
|
|
@pytest.mark.parametrize("name", _params())
|
|
def test_a_reader_keeps_the_teaser(name: str) -> None:
|
|
module, reads = _declared(name)
|
|
if not (reads.text == "excerpt" or reads.teaser):
|
|
pytest.skip("the list carries no teaser")
|
|
fixture = _fixture(name, "teaser")
|
|
if fixture is None:
|
|
pytest.skip(f"no fixture {name}-teaser.* yet")
|
|
rows = read_fixture(module, fixture.read_bytes(), _slug(name))
|
|
assert any(isinstance(row.get("teaser"), str) and row["teaser"].strip() for row in rows)
|
|
|
|
|
|
# ------------------------------------------------------------ the checks
|
|
|
|
def _reader(**functions: Any) -> Any:
|
|
module: Any = types.ModuleType("fake")
|
|
module.NAME, module.LABEL, module.PATTERNS = "fake", "Fake", (r"fake\.example/([a-z]+)",)
|
|
module.slug_ok = lambda slug: True
|
|
module.allowed = lambda slug: lambda host: host == "fake.example"
|
|
module.careers_url = lambda slug: "https://fake.example/" + slug
|
|
for name, function in functions.items():
|
|
setattr(module, name, function)
|
|
return module
|
|
|
|
|
|
def _whole(**functions: Any) -> Any:
|
|
return _reader(**{"feed_url": lambda slug, ask: "https://fake.example/" + slug,
|
|
"parse": lambda body, slug: []} | functions)
|
|
|
|
|
|
def _paged(**functions: Any) -> Any:
|
|
return _reader(**{"page": lambda get, slug, cursor, ask: (None, [], None, None),
|
|
"rows": lambda decoded, slug: []} | functions)
|
|
|
|
|
|
_ROBOTS = "read: no robots.txt rule on /api/ (checked 2026-09-30)"
|
|
|
|
|
|
def _reads(**traits: Any) -> Reads:
|
|
base: dict[str, Any] = {"scope": "board", "listing": "whole", "text": "listing",
|
|
"complete": "whole", "places": "one", "robots": _ROBOTS}
|
|
return Reads(**(base | traits))
|
|
|
|
|
|
def test_a_good_declaration_has_no_problems() -> None:
|
|
module = _whole()
|
|
module.READS = _reads()
|
|
assert readers.problems(module, "fake") == []
|
|
module = _paged(detail=lambda get, slug, row: {},
|
|
facets=lambda get, slug: {"country": {"DE": "1"}})
|
|
module.READS = _reads(listing="paged", page_size=20, ceiling=2000, text="detail",
|
|
teaser=True, complete="stated", filters=Filters(country="ids"),
|
|
places="many", fields=Fields(posted="listed", remote="stated"),
|
|
empty="suspect", title="provisional")
|
|
assert readers.problems(module, "fake") == []
|
|
|
|
|
|
def test_a_module_without_reads_is_checked_as_before() -> None:
|
|
module = _reader(feed_url=lambda slug: "", parse=lambda body, slug: [])
|
|
assert readers.problems(module, "fake") == []
|
|
assert readers.scope(module) == "board"
|
|
assert readers.undeclared({"fake": module}) == ["fake"]
|
|
|
|
|
|
@pytest.mark.parametrize(("module", "reads", "problem"), [
|
|
(_reader(feed_url=lambda slug, ask: "", parse=lambda b, s: []),
|
|
{"listing": "paged", "complete": "stated"}, 'listing="paged" without page and rows'),
|
|
(_paged(), {}, 'listing="whole" without feed_url and parse'),
|
|
(_whole(), {"complete": "stated"}, 'complete="whole" goes with listing="whole"'),
|
|
(_whole(), {"page_size": 20}, 'page_size and ceiling are for listing="paged"'),
|
|
(_paged(), {"listing": "paged", "complete": "end", "page_size": 100, "ceiling": 50},
|
|
"ceiling is below page_size"),
|
|
(_paged(fallback_url=lambda slug: ""), {"listing": "paged", "complete": "end"},
|
|
'fallback_url without listing="whole"'),
|
|
(_whole(), {"text": "detail"}, 'text="detail" without detail'),
|
|
(_whole(detail=lambda g, s, r: {}), {}, 'detail with text="listing"'),
|
|
(_whole(), {"teaser": True, "text": "excerpt"}, "teaser is for text=\"detail\""),
|
|
(_whole(), {"title": "provisional"}, 'title="provisional" without detail'),
|
|
(_whole(), {"filters": Filters(country="ids")}, "an ids filter (country) without facets"),
|
|
(_whole(facets=lambda g, s: {}), {"filters": Filters(country="one")},
|
|
"facets without an ids filter"),
|
|
(_whole(facets=lambda g, s: {}), {"filters": Filters(query="ids")},
|
|
'query cannot be "ids"'),
|
|
(_paged(), {"scope": "search", "listing": "paged", "complete": "end"},
|
|
'scope="search" needs complete="never" or "stated"'),
|
|
(_paged(), {"listing": "paged", "complete": "never"},
|
|
'scope="board" cannot be complete="never"'),
|
|
(_whole(), {"key": Key(name="Adzuna Key", fields=("app_id",))},
|
|
"key names no config entry"),
|
|
(_whole(), {"key": Key(name="adzuna", fields=())}, "key has no fields"),
|
|
(_whole(), {"key": Key(name="adzuna", fields=("app_id", "app_key"),
|
|
env=("ADZUNA_APP_ID",))},
|
|
"key.env does not match key.fields"),
|
|
(_whole(), {"robots": " "}, "robots is empty"),
|
|
(_reader(feed_url=lambda slug: "", parse=lambda b, s: []), {},
|
|
"feed_url does not take (slug, ask)"),
|
|
(_reader(page=lambda get, slug, cursor: None, rows=lambda d, s: []),
|
|
{"listing": "paged", "complete": "end"}, "page does not take (get, slug, cursor, ask)"),
|
|
])
|
|
def test_the_declaration_check_names_each_problem(
|
|
module: Any, reads: dict[str, Any], problem: str) -> None:
|
|
module.READS = _reads(**reads)
|
|
found = readers.problems(module, "fake")
|
|
assert any(p.startswith(problem) for p in found), found
|
|
|
|
|
|
def test_reads_that_is_not_a_reads_is_refused() -> None:
|
|
module = _whole()
|
|
module.READS = {"scope": "board"}
|
|
assert "READS is not a Reads" in readers.problems(module, "fake")
|
|
|
|
|
|
def test_a_search_needs_fewer_names_than_a_board() -> None:
|
|
module: Any = types.ModuleType("fake")
|
|
module.NAME, module.LABEL = "fake", "Fake"
|
|
module.allowed = lambda slug: lambda host: True
|
|
module.page = lambda get, slug, cursor, ask: (None, [], 0, None)
|
|
module.rows = lambda decoded, slug: []
|
|
module.READS = _reads(scope="search", listing="paged", complete="never",
|
|
filters=Filters(query="one"),
|
|
key=Key(name="adzuna", fields=("app_id", "app_key"),
|
|
env=("ADZUNA_APP_ID", "ADZUNA_APP_KEY")))
|
|
assert readers.problems(module, "fake") == []
|
|
assert readers.scope(module) == "search"
|
|
del module.READS
|
|
assert "no careers_url" in readers.problems(module, "fake")
|
|
|
|
|
|
def test_a_misspelt_trait_fails_where_it_is_declared() -> None:
|
|
with pytest.raises(pydantic.ValidationError):
|
|
_reads(listing="pages")
|
|
with pytest.raises(pydantic.ValidationError):
|
|
Filters(country="some")
|
|
with pytest.raises(pydantic.ValidationError):
|
|
_reads(robots=None)
|
|
with pytest.raises(pydantic.ValidationError):
|
|
Reads(scope="board", listing="whole", text="listing", complete="whole",
|
|
places="one") # type: ignore[call-arg] # robots is required
|
|
with pytest.raises(pydantic.ValidationError):
|
|
_reads(colour="blue") # extra keys are refused
|
|
|
|
|
|
def test_a_declaration_is_frozen() -> None:
|
|
reads = _reads()
|
|
with pytest.raises(pydantic.ValidationError):
|
|
reads.places = "many" # type: ignore[misc]
|
|
|
|
|
|
def test_the_loader_refuses_a_module_whose_declaration_breaks_the_contract(
|
|
tmp_path: Path, monkeypatch: pytest.MonkeyPatch) -> None:
|
|
package = tmp_path / "readersbad"
|
|
package.mkdir()
|
|
(package / "__init__.py").write_text("")
|
|
(package / "odd.py").write_text(
|
|
"from plugins.readers import Reads\n"
|
|
"NAME = 'odd'\nLABEL = 'Odd'\nPATTERNS = ()\n"
|
|
"def slug_ok(slug): return True\n"
|
|
"def allowed(slug): return lambda h: True\n"
|
|
"def careers_url(slug): return ''\n"
|
|
"def feed_url(slug, ask): return ''\n"
|
|
"def parse(body, slug): return []\n"
|
|
"READS = Reads(scope='board', listing='whole', text='detail', complete='whole',\n"
|
|
" places='many', robots='read (checked 2026-09-30)')\n")
|
|
monkeypatch.syspath_prepend(str(tmp_path))
|
|
with pytest.raises(ImportError, match=r'readersbad\.odd .*text="detail" without detail'):
|
|
readers.load([str(package)], "readersbad")
|
|
|
|
|
|
def test_filters_list_what_is_filtered() -> None:
|
|
assert Filters(country="one", query="many").declared() == {"country": "one",
|
|
"query": "many"}
|
|
|
|
|
|
# ------------------------------------------------------------ the fixture check
|
|
|
|
def _fake_many(rows: list[dict[str, Any]]) -> Any:
|
|
module = _reader(feed_url=lambda slug, ask: "", parse=lambda body, slug: rows)
|
|
module.READS = _reads(places="many")
|
|
return module
|
|
|
|
|
|
def test_the_place_check_passes_a_role_at_two_places() -> None:
|
|
rows = [{"source_id": "1", "places": [{"text": "Berlin", "remote": False},
|
|
{"text": "Remote (DE)", "remote": True}]}]
|
|
assert place_problems(read_fixture(_fake_many(rows), b"", "acme"), "many") == []
|
|
|
|
|
|
def test_the_place_check_fails_a_reader_that_drops_or_joins_places() -> None:
|
|
joined = [{"source_id": "1", "places": [{"text": "Berlin; Munich", "remote": None}]}]
|
|
assert place_problems(joined, "many") == [
|
|
'no row has two places: a reader with places="many" keeps every place']
|
|
assert place_problems([{"source_id": "2", "location": "Berlin"}], "one") == [
|
|
"2: places is not a list"]
|
|
assert place_problems([{"source_id": "3", "places": [("Berlin", False)]}], "one") == [
|
|
"3: ('Berlin', False) is not a Place"]
|
|
|
|
|
|
def test_the_fixture_reader_drives_a_paged_module_and_detail() -> None:
|
|
seen: list[bytes] = []
|
|
|
|
def page(get: Any, slug: str, cursor: Any, ask: Ask) -> Any:
|
|
seen.append(get("https://fake.example/list"))
|
|
return ([{"id": "1"}], [{"id": "1"}], 1, None)
|
|
|
|
module = _paged(page=page, rows=lambda decoded, slug: [{"source_id": d["id"], "places": []}
|
|
for d in decoded],
|
|
detail=lambda get, slug, row: {"places": [
|
|
{"text": get("https://fake.example/1").decode(), "remote": None},
|
|
{"text": "Munich", "remote": None}]})
|
|
module.READS = _reads(listing="paged", complete="stated", text="detail", places="many")
|
|
rows = read_fixture(module, b"Berlin", "acme", detail_body=b"Berlin")
|
|
assert seen == [b"Berlin"]
|
|
assert place_problems(rows, "many") == []
|
|
|
|
|
|
def test_the_contract_types_are_what_the_package_exports() -> None:
|
|
assert readers.Reads is _contract.Reads and readers.Row is _contract.Row
|
|
assert _contract.Place(text="Berlin", remote=None) == {"text": "Berlin", "remote": None}
|