"""The reader contract, held for every module of `plugins/readers/`. Per module: it declares `READS`, the declaration matches its functions, and its rows state what the declaration says and nothing it denies. No network: fixtures stand in for the host. A fixture a declaration needs and that is missing fails the test with the path to add. Fixtures, in `tests/fixtures/ats/` for boards and `tests/fixtures/search/` for searches, named after the module: - `-places.`: one listing answer, required of every reader. 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. Under `places="many"` at least one role is at two or more places. - `.` and `-teaser.`: more listing answers, read the same way; the teaser one is required under `text="excerpt"` or `teaser=True`. - `-detail*.` and `-places-detail.`: what `detail`'s requests return, one of them required under `text="detail"`. Only `_runner.DETAIL_FIELDS` of the answer count, as at run time; the places of `-places-detail` replace those of the `-places` rows. - `.slug`: optional, the slug the fixtures are read with, one line; `acme` without it. A search's saved params are `SEARCH_PARAMS` below. Between them the listing and detail answers show every field the reader declares `stated` (or `figures`, `line`, `trusted`, `listed`): a real fixture that happens to lack one is filled from what the per-host test already builds (Pinpoint's and HiBob's pay, SmartRecruiters' levels). """ 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 app.prep.hosts import TABLES # noqa: E402 from plugins import readers # noqa: E402 from plugins.readers import Ask, Fields, Filters, Key, Reads # noqa: E402 from plugins.readers import _contract # noqa: E402 from plugins.readers._runner import DETAIL_FIELDS # noqa: E402 BOARD_FIXTURES = ROOT / "tests" / "fixtures" / "ats" SEARCH_FIXTURES = ROOT / "tests" / "fixtures" / "search" #: A search's saved params, which its `page` reads; `{}` for the rest. SEARCH_PARAMS: dict[str, dict[str, Any]] = {"adzuna": {"q": "backend", "country": "de"}} #: The readers whose listing states no date and whose `posted` comes from #: `detail` alone: the date exists only for roles the enrich stage read. POSTED_BY_DETAIL = frozenset({"bamboohr", "gem", "rippling"}) #: The fields a host states in its own words, which `app.prep` maps through #: the host's table in `app/prep/hosts/.py`. WORD_FIELDS = ("seniority", "employment") def _folder(name: str) -> Path: return SEARCH_FIXTURES if name in readers.PROVIDERS else BOARD_FIXTURES def _fixtures(name: str, pattern: str) -> list[Path]: return sorted(p for p in _folder(name).glob(pattern.format(name=name)) if p.suffix not in (".slug",)) def _fixture(name: str, kind: str) -> Path | None: found = _fixtures(name, f"{{name}}-{kind}.*") return found[0] if found else None def _need(name: str, kind: str, why: str) -> Path: """The fixture `-.*`, or a failure naming the file to add.""" found = _fixture(name, kind) if found is None: folder = _folder(name).relative_to(ROOT) pytest.fail(f"add {folder}/{name}-{kind}.: {why}") return found def _slug(name: str) -> str: path = _folder(name) / f"{name}.slug" return path.read_text(encoding="utf-8").strip() if path.exists() else "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, ask: Ask | 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 or 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 _ask(name: str) -> Ask: return Ask(params=SEARCH_PARAMS.get(name, {})) def listing_rows(name: str) -> list[dict[str, Any]]: """Every row of the reader's listing fixtures; the `-places` rows with the places of `-places-detail` where there is one.""" module, slug = readers.READERS[name], _slug(name) places = _need(name, "places", "one listing answer of the host") detail = _fixture(name, "places-detail") rows = read_fixture(module, places.read_bytes(), slug, detail.read_bytes() if detail else None, _ask(name)) for path in _fixtures(name, "{name}.*") + _fixtures(name, "{name}-teaser.*"): rows += read_fixture(module, path.read_bytes(), slug, ask=_ask(name)) return rows def detail_rows(name: str, listed: list[dict[str, Any]]) -> list[dict[str, Any]]: """What `detail` hands over for the first listed role, once per detail fixture, cut to `DETAIL_FIELDS` as the runner cuts it.""" module = readers.READERS[name] if module.READS.text != "detail": return [] paths = _fixtures(name, "{name}-detail*.*") + _fixtures(name, "{name}-places-detail.*") if not paths: _need(name, "detail", "what the role's own page answers, for text=\"detail\"") assert listed, f"{name}: the listing fixtures gave no role to read in detail" return [{key: value for key, value in module.detail(_answer(path.read_bytes()), _slug(name), dict(listed[0])).items() if key in DETAIL_FIELDS} for path in paths] 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 == "none" and found: out.append(f'{rid}: {len(found)} places under places="none"') 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') elif places != "none" and not any(row.get("places") for row in rows): out.append(f'no row has a place under places="{places}": declare "none"') return out def _states(rows: list[dict[str, Any]], key: str) -> bool: """Whether some row carries `key` with a value (False counts, "" does not).""" return any(row.get(key) not in (None, "", [], {}) for row in rows) def field_problems(reads: Reads, listing: list[dict[str, Any]], detail: list[dict[str, Any]], posted_by_detail: bool = False) -> list[str]: """What the rows get wrong about the declared `fields`, `text` and `teaser`: a trait that promises a key no row carries, or denies one a row carries.""" rows = listing + detail fields = reads.fields out: list[str] = [] figures = _states(rows, "salary_min") or _states(rows, "salary_max") line = _states(rows, "salary_text") if fields.pay == "figures" and not figures: out.append('pay="figures" and no row has salary_min or salary_max') if fields.pay == "line" and (figures or not line): out.append('pay="line" wants salary_text on some row and figures on none') if fields.pay == "none" and (figures or line): out.append('pay="none" and a row has pay') if fields.posted == "none" and _states(rows, "posted"): out.append('posted="none" and a row has posted') elif fields.posted != "none" and posted_by_detail: if _states(listing, "posted") or not _states(detail, "posted"): out.append(f'posted="{fields.posted}" by detail wants posted from detail only') elif fields.posted != "none" and not _states(listing, "posted"): out.append(f'posted="{fields.posted}" and no listed row has posted') for key in ("remote", "country", "seniority", "employment"): stated = getattr(fields, key) == "stated" if stated != _states(rows, key): out.append(f'{key}="{getattr(fields, key)}" and ' + ("no row has it" if stated else "a row has it")) text = {"listing": _states(listing, "description"), "detail": _states(detail, "description"), "excerpt": _states(listing, "teaser") and not _states(listing, "description"), "none": not _states(rows, "description")}[reads.text] if not text: out.append(f'text="{reads.text}" and the rows do not show it') teaser = reads.teaser or reads.text == "excerpt" if teaser != _states(listing if teaser else rows, "teaser"): out.append("teaser declared and no listed row has one" if teaser else "a row has a teaser the declaration does not name") return out # ------------------------------------------------------------ every module @pytest.mark.parametrize("name", readers.READERS) def test_a_declaration_matches_the_functions(name: str) -> None: module = readers.READERS[name] assert readers.problems(module, name) == [] assert name in (readers.PROVIDERS if module.READS.scope == "search" else readers.HOSTS) @pytest.mark.parametrize("name", readers.READERS) def test_a_reader_keeps_every_place(name: str) -> None: listed = listing_rows(name) assert listed, f"{name}: the listing fixtures gave no rows" answered = [{"source_id": f"detail {i}", "places": row["places"]} for i, row in enumerate(detail_rows(name, listed)) if "places" in row] assert place_problems(listed + answered, readers.READERS[name].READS.places) == [] @pytest.mark.parametrize("name", readers.READERS) def test_a_reader_states_what_it_declares(name: str) -> None: reads = readers.READERS[name].READS if reads.text == "excerpt" or reads.teaser: _need(name, "teaser", "a listing answer with a teaser") listed = listing_rows(name) assert field_problems(reads, listed, detail_rows(name, listed), name in POSTED_BY_DETAIL) == [] @pytest.mark.parametrize("name", [name for name, module in readers.READERS.items() if module.READS.listing == "paged" and module.READS.complete in ("stated", "end")]) def test_a_paged_reader_states_a_total_as_declared(name: str) -> None: """`complete="stated"`: the first page's total is an int; `"end"`: None, since the read ends on an empty page.""" module = readers.READERS[name] body = _need(name, "places", "one listing answer of the host").read_bytes() _decoded, _results, total, _cursor = module.page(_answer(body), _slug(name), None, _ask(name)) if module.READS.complete == "stated": assert isinstance(total, int) and not isinstance(total, bool), total else: assert total is None, total def test_the_posted_by_detail_list_names_only_readers_that_date_by_detail() -> None: for name in POSTED_BY_DETAIL: reads = readers.READERS[name].READS assert reads.text == "detail" and reads.fields.posted != "none", name # ------------------------------------------------------------ prep tables def test_every_prep_table_is_a_readers() -> None: assert set(TABLES) <= set(readers.READERS), set(TABLES) - set(readers.READERS) @pytest.mark.parametrize("name", readers.READERS) def test_a_reader_stating_words_has_a_table_for_them(name: str) -> None: """A host that states seniority or employment in its own words has a table for that field in `app/prep/hosts/.py`, even an empty one for a host whose words are already the app's (`words.lookup` then takes the word as it is). The table is where a word is known, so a host without one lists every word as unmapped. A table for a field the reader declares `none` is dead.""" fields = readers.READERS[name].READS.fields tables = TABLES.get(name, {}) for field in WORD_FIELDS: has = field in tables or (field == "employment" and "match" in tables) stated = getattr(fields, field) == "stated" assert has == stated, (f"{name}: {field}={getattr(fields, field)!r} " f"{'without' if stated else 'with'} a table in " f"app/prep/hosts/{name}.py") if "remote" in tables: assert fields.remote == "stated", f"{name}: a remote table and remote=\"none\"" # ------------------------------------------------------------ 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_fails() -> None: module = _reader(feed_url=lambda slug: "", parse=lambda body, slug: []) assert readers.problems(module, "fake") == [ "no READS: every reader declares what it reads"] @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"), (_whole(), {"robots": "read: robots.txt allows /api/"}, "robots has no date"), (_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 _search() -> Any: 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.PARAMS = {"q": "query", "where": "place"} module.clean_params = lambda params: dict(params) module.READS = _reads(scope="search", listing="paged", complete="never", filters=Filters(query="one", place="one"), key=Key(name="adzuna", fields=("app_id", "app_key"), env=("ADZUNA_APP_ID", "ADZUNA_APP_KEY"))) return module def test_a_search_needs_fewer_names_than_a_board() -> None: module = _search() assert readers.problems(module, "fake") == [] del module.READS assert "no careers_url" in readers.problems(module, "fake") def test_a_search_names_its_params_and_cleans_them() -> None: module = _search() del module.PARAMS, module.clean_params assert {"no PARAMS", "no clean_params"} <= set(readers.problems(module, "fake")) module = _search() module.PARAMS = {"q": "query", "area": "town"} assert readers.problems(module, "fake") == [ "PARAMS maps 'area' to 'town', not a filter dimension"] module = _search() module.clean_params = lambda: {} assert readers.problems(module, "fake") == ["clean_params does not take (params)"] def test_every_search_names_its_params() -> None: for name, module in readers.PROVIDERS.items(): declared = module.READS.filters.declared() assert "query" in module.PARAMS.values(), name assert set(module.PARAMS.values()) <= set(declared), name 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_holds_a_reader_that_states_none_to_none() -> None: assert place_problems([{"source_id": "1", "places": []}], "none") == [] assert place_problems([{"source_id": "1", "places": []}], "one") == [ 'no row has a place under places="one": declare "none"'] assert place_problems([{"source_id": "2", "places": [{"text": "Oslo", "remote": None}]}], "none") == ['2: 1 places under places="none"'] 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", 'no row has a place under places="one": declare "none"'] 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} # ------------------------------------------------------------ the field check def test_the_field_check_passes_rows_that_state_what_is_declared() -> None: reads = _reads(text="detail", teaser=True, listing="whole", fields=Fields(pay="figures", posted="trusted", remote="stated")) listed = [{"source_id": "1", "teaser": "Short.", "remote": False, "posted": "2026-09-30"}] detail = [{"description": "Long.", "salary_min": 50000}] assert field_problems(reads, listed, detail) == [] def test_the_field_check_names_a_promise_no_row_keeps_and_a_denial_a_row_breaks() -> None: reads = _reads(fields=Fields(pay="line", employment="stated")) listed = [{"source_id": "1", "description": "Text.", "salary_min": 1, "remote": "hybrid", "posted": "2026-09-30"}] assert field_problems(reads, listed, []) == [ 'pay="line" wants salary_text on some row and figures on none', 'posted="none" and a row has posted', 'remote="none" and a row has it', 'employment="stated" and no row has it'] def test_the_field_check_takes_a_date_from_detail_only_where_it_is_said() -> None: reads = _reads(text="detail", fields=Fields(posted="trusted")) listed = [{"source_id": "1"}] detail = [{"description": "Text.", "posted": "2026-09-30"}] assert field_problems(reads, listed, detail, posted_by_detail=True) == [] assert field_problems(reads, listed, detail) == [ 'posted="trusted" and no listed row has posted'] assert field_problems(reads, [*listed, {"posted": "2026-09-30"}], detail, posted_by_detail=True) == [ 'posted="trusted" by detail wants posted from detail only'] def test_the_field_check_holds_text_and_teaser_to_the_declaration() -> None: excerpt = _reads(text="excerpt") assert field_problems(excerpt, [{"teaser": "Short."}], []) == [] assert field_problems(excerpt, [{"teaser": "Short.", "description": "Long."}], []) == [ 'text="excerpt" and the rows do not show it'] assert field_problems(_reads(), [{"description": "Long.", "teaser": "Short."}], []) == [ "a row has a teaser the declaration does not name"]