Order the hosts by a RANK per module, which restores the select's and the probes' order from before the modules
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
1 parent
75a389d725
commit
a9fb4397ac
11 files changed
+71
-8
No files matched your search
@@ -53,6 +53,10 @@ import re
|
|||||||
from collections.abc import Iterable
|
from collections.abc import Iterable
|
||||||
from types import ModuleType
|
from types import ModuleType
|
||||||
|
|
||||||
|
#: The rank of a module that states none: after the eight first hosts, whose
|
||||||
|
#: ranks (10 to 80) keep the order they had before there were modules.
|
||||||
|
DEFAULT_RANK = 100
|
||||||
|
|
||||||
#: What every host module defines.
|
#: What every host module defines.
|
||||||
REQUIRED = ("NAME", "LABEL", "PATTERNS", "slug_ok", "allowed", "careers_url")
|
REQUIRED = ("NAME", "LABEL", "PATTERNS", "slug_ok", "allowed", "careers_url")
|
||||||
|
|
||||||
@@ -72,6 +76,9 @@ def problems(module: ModuleType, name: str | None = None) -> list[str]:
|
|||||||
out.append("LABEL is not a non-empty string")
|
out.append("LABEL is not a non-empty string")
|
||||||
if not isinstance(getattr(module, "KEEP_CASE", False), bool):
|
if not isinstance(getattr(module, "KEEP_CASE", False), bool):
|
||||||
out.append("KEEP_CASE is not a bool")
|
out.append("KEEP_CASE is not a bool")
|
||||||
|
rank = getattr(module, "RANK", DEFAULT_RANK)
|
||||||
|
if not isinstance(rank, int) or isinstance(rank, bool):
|
||||||
|
out.append("RANK is not an int")
|
||||||
patterns = getattr(module, "PATTERNS", ())
|
patterns = getattr(module, "PATTERNS", ())
|
||||||
if isinstance(patterns, str) or not isinstance(patterns, Iterable):
|
if isinstance(patterns, str) or not isinstance(patterns, Iterable):
|
||||||
out.append("PATTERNS is not a tuple of strings")
|
out.append("PATTERNS is not a tuple of strings")
|
||||||
@@ -97,9 +104,9 @@ def problems(module: ModuleType, name: str | None = None) -> list[str]:
|
|||||||
|
|
||||||
def load(path: Iterable[str], package: str) -> dict[str, ModuleType]:
|
def load(path: Iterable[str], package: str) -> dict[str, ModuleType]:
|
||||||
"""`NAME -> module` for every module of `package` (found on `path`) whose
|
"""`NAME -> module` for every module of `package` (found on `path`) whose
|
||||||
name does not start with `_`, sorted by name. Raises ImportError naming
|
name does not start with `_`, in order of `(RANK, NAME)`. Raises
|
||||||
the first module that breaks the contract."""
|
ImportError naming the first module that breaks the contract."""
|
||||||
hosts: dict[str, ModuleType] = {}
|
modules: list[ModuleType] = []
|
||||||
for info in sorted(pkgutil.iter_modules(path), key=lambda info: info.name):
|
for info in sorted(pkgutil.iter_modules(path), key=lambda info: info.name):
|
||||||
if info.name.startswith("_"):
|
if info.name.startswith("_"):
|
||||||
continue
|
continue
|
||||||
@@ -107,9 +114,10 @@ def load(path: Iterable[str], package: str) -> dict[str, ModuleType]:
|
|||||||
if found := problems(module, info.name):
|
if found := problems(module, info.name):
|
||||||
raise ImportError(f"{package}.{info.name} breaks the host contract: "
|
raise ImportError(f"{package}.{info.name} breaks the host contract: "
|
||||||
+ "; ".join(found))
|
+ "; ".join(found))
|
||||||
hosts[module.NAME] = module
|
modules.append(module)
|
||||||
return hosts
|
modules.sort(key=lambda module: (getattr(module, "RANK", DEFAULT_RANK), module.NAME))
|
||||||
|
return {module.NAME: module for module in modules}
|
||||||
|
|
||||||
|
|
||||||
#: host -> its module, in order of name.
|
#: host -> its module, in order of `(RANK, NAME)`.
|
||||||
HOSTS: dict[str, ModuleType] = load(__path__, __name__)
|
HOSTS: dict[str, ModuleType] = load(__path__, __name__)
|
||||||
@@ -17,6 +17,7 @@ from ._shared import Row, is_web_url, num, only, parse_dt, path_slug_ok, pay_lin
|
|||||||
|
|
||||||
NAME = "ashby"
|
NAME = "ashby"
|
||||||
LABEL = "Ashby"
|
LABEL = "Ashby"
|
||||||
|
RANK = 30
|
||||||
PATTERNS = (
|
PATTERNS = (
|
||||||
r"jobs\.ashbyhq\.com/([A-Za-z0-9_.-]+)",
|
r"jobs\.ashbyhq\.com/([A-Za-z0-9_.-]+)",
|
||||||
r"api\.ashbyhq\.com/posting-api/job-board/([A-Za-z0-9_.-]+)",
|
r"api\.ashbyhq\.com/posting-api/job-board/([A-Za-z0-9_.-]+)",
|
||||||
|
|||||||
@@ -17,6 +17,7 @@ from ._shared import Row, is_web_url, num, only, parse_dt, path_slug_ok, pay_lin
|
|||||||
|
|
||||||
NAME = "greenhouse"
|
NAME = "greenhouse"
|
||||||
LABEL = "Greenhouse"
|
LABEL = "Greenhouse"
|
||||||
|
RANK = 10
|
||||||
PATTERNS = (
|
PATTERNS = (
|
||||||
r"(?:boards|job-boards|api)\.(?:eu\.)?greenhouse\.io/(?:v1/boards/|embed/job_board\?[^\"'\s]*for=)?([A-Za-z0-9_-]+)",
|
r"(?:boards|job-boards|api)\.(?:eu\.)?greenhouse\.io/(?:v1/boards/|embed/job_board\?[^\"'\s]*for=)?([A-Za-z0-9_-]+)",
|
||||||
r"greenhouse\.io/embed/job_board/js\?for=([A-Za-z0-9_-]+)",
|
r"greenhouse\.io/embed/job_board/js\?for=([A-Za-z0-9_-]+)",
|
||||||
|
|||||||
@@ -25,6 +25,7 @@ from ._shared import Row, is_web_url, num, only, parse_dt, path_slug_ok, pay_lin
|
|||||||
|
|
||||||
NAME = "lever"
|
NAME = "lever"
|
||||||
LABEL = "Lever"
|
LABEL = "Lever"
|
||||||
|
RANK = 20
|
||||||
#: Two groups on the EU hosts, `eu` and the site, which discovery joins into
|
#: Two groups on the EU hosts, `eu` and the site, which discovery joins into
|
||||||
#: the slug `eu/<site>`.
|
#: the slug `eu/<site>`.
|
||||||
PATTERNS = (
|
PATTERNS = (
|
||||||
|
|||||||
@@ -16,6 +16,7 @@ from ._shared import Row, label_slug_ok, num, only, parse_dt, pay_line, yearly_a
|
|||||||
|
|
||||||
NAME = "personio"
|
NAME = "personio"
|
||||||
LABEL = "Personio"
|
LABEL = "Personio"
|
||||||
|
RANK = 70
|
||||||
PATTERNS = (r"https?://([a-z0-9-]+)\.jobs\.personio\.(?:de|com)",)
|
PATTERNS = (r"https?://([a-z0-9-]+)\.jobs\.personio\.(?:de|com)",)
|
||||||
|
|
||||||
#: Personio's `salaryInformation/type` spellings, to the plain period word
|
#: Personio's `salaryInformation/type` spellings, to the plain period word
|
||||||
|
|||||||
@@ -17,6 +17,7 @@ from ._shared import Row, is_web_url, label_slug_ok, num, only, parse_dt, pay_li
|
|||||||
|
|
||||||
NAME = "recruitee"
|
NAME = "recruitee"
|
||||||
LABEL = "Recruitee"
|
LABEL = "Recruitee"
|
||||||
|
RANK = 60
|
||||||
PATTERNS = (r"https?://([a-z0-9-]+)\.recruitee\.com",)
|
PATTERNS = (r"https?://([a-z0-9-]+)\.recruitee\.com",)
|
||||||
|
|
||||||
|
|
||||||
|
|||||||
@@ -15,6 +15,7 @@ from ._shared import Get, Page, Row, only, parse_dt, path_slug_ok
|
|||||||
|
|
||||||
NAME = "smartrecruiters"
|
NAME = "smartrecruiters"
|
||||||
LABEL = "SmartRecruiters"
|
LABEL = "SmartRecruiters"
|
||||||
|
RANK = 50
|
||||||
PATTERNS = (
|
PATTERNS = (
|
||||||
r"(?:jobs|careers|api)\.smartrecruiters\.com/(?:v1/companies/)?([A-Za-z0-9_-]+)",
|
r"(?:jobs|careers|api)\.smartrecruiters\.com/(?:v1/companies/)?([A-Za-z0-9_-]+)",
|
||||||
)
|
)
|
||||||
|
|||||||
@@ -20,6 +20,7 @@ from ._shared import Get, Page, Row, is_web_url, only, parse_dt
|
|||||||
|
|
||||||
NAME = "teamtailor"
|
NAME = "teamtailor"
|
||||||
LABEL = "Teamtailor"
|
LABEL = "Teamtailor"
|
||||||
|
RANK = 80
|
||||||
PATTERNS = (
|
PATTERNS = (
|
||||||
r"https?://([a-z0-9-]+)\.teamtailor\.com",
|
r"https?://([a-z0-9-]+)\.teamtailor\.com",
|
||||||
# No slug: a career site on the company's own domain, which only loads
|
# No slug: a career site on the company's own domain, which only loads
|
||||||
|
|||||||
@@ -15,6 +15,7 @@ from ._shared import Get, Page, Row, only, parse_dt, path_slug_ok
|
|||||||
|
|
||||||
NAME = "workable"
|
NAME = "workable"
|
||||||
LABEL = "Workable"
|
LABEL = "Workable"
|
||||||
|
RANK = 40
|
||||||
PATTERNS = (
|
PATTERNS = (
|
||||||
r"apply\.workable\.com/(?:api/v\d/accounts/)?([A-Za-z0-9_-]+)",
|
r"apply\.workable\.com/(?:api/v\d/accounts/)?([A-Za-z0-9_-]+)",
|
||||||
r"https?://(?!apply\.|www\.)([a-z0-9-]+)\.workable\.com",
|
r"https?://(?!apply\.|www\.)([a-z0-9-]+)\.workable\.com",
|
||||||
|
|||||||
+26
-2
@@ -28,10 +28,10 @@ FIXTURES = ROOT / "tests" / "fixtures" / "ats"
|
|||||||
|
|
||||||
# --------------------------------------------------------------- registry
|
# --------------------------------------------------------------- registry
|
||||||
|
|
||||||
def test_the_registry_finds_every_module_in_order_of_name() -> None:
|
def test_the_registry_finds_every_module() -> None:
|
||||||
names = sorted(p.stem for p in (ROOT / "plugins" / "atshosts").glob("*.py")
|
names = sorted(p.stem for p in (ROOT / "plugins" / "atshosts").glob("*.py")
|
||||||
if not p.stem.startswith("_"))
|
if not p.stem.startswith("_"))
|
||||||
assert list(atshosts.HOSTS) == names
|
assert sorted(atshosts.HOSTS) == names
|
||||||
assert set(names) >= {"greenhouse", "lever", "ashby", "workable", "smartrecruiters",
|
assert set(names) >= {"greenhouse", "lever", "ashby", "workable", "smartrecruiters",
|
||||||
"recruitee", "personio", "teamtailor"}
|
"recruitee", "personio", "teamtailor"}
|
||||||
assert all(not atshosts.problems(module, name) for name, module in atshosts.HOSTS.items())
|
assert all(not atshosts.problems(module, name) for name, module in atshosts.HOSTS.items())
|
||||||
@@ -71,6 +71,28 @@ def test_the_registry_loads_a_package_by_name_and_skips_private_modules(
|
|||||||
assert list(atshosts.load(path, "hostsok")) == ["alpha", "zeta"]
|
assert list(atshosts.load(path, "hostsok")) == ["alpha", "zeta"]
|
||||||
|
|
||||||
|
|
||||||
|
def test_the_registry_orders_by_rank_then_name(
|
||||||
|
tmp_path: Path, monkeypatch: pytest.MonkeyPatch) -> None:
|
||||||
|
path = _package(tmp_path, monkeypatch, "hostsranked", {
|
||||||
|
"alpha": _GOOD.format(name="alpha"), # the default, 100
|
||||||
|
"beta": _GOOD.format(name="beta") + "RANK = 5\n",
|
||||||
|
"gamma": _GOOD.format(name="gamma") + "RANK = 100\n"})
|
||||||
|
assert list(atshosts.load(path, "hostsranked")) == ["beta", "alpha", "gamma"]
|
||||||
|
|
||||||
|
|
||||||
|
def test_the_eight_first_hosts_keep_the_order_they_had_before_modules() -> None:
|
||||||
|
"""The Sources page's select opens on Greenhouse, which its hint names,
|
||||||
|
and a guessed slug on two hosts goes to the one probed first, as before."""
|
||||||
|
first = ["greenhouse", "lever", "ashby", "workable", "smartrecruiters", "recruitee",
|
||||||
|
"personio", "teamtailor"]
|
||||||
|
assert list(ats.HOSTS)[:8] == first
|
||||||
|
assert ats.ATSSource.description.startswith(
|
||||||
|
"Company job boards: Greenhouse, Lever, Ashby, Workable, SmartRecruiters, "
|
||||||
|
"Recruitee, Personio, Teamtailor")
|
||||||
|
assert all(module.RANK < atshosts.DEFAULT_RANK
|
||||||
|
for name, module in atshosts.HOSTS.items() if name in first)
|
||||||
|
|
||||||
|
|
||||||
def test_the_registry_refuses_a_module_missing_a_required_name(
|
def test_the_registry_refuses_a_module_missing_a_required_name(
|
||||||
tmp_path: Path, monkeypatch: pytest.MonkeyPatch) -> None:
|
tmp_path: Path, monkeypatch: pytest.MonkeyPatch) -> None:
|
||||||
broken = _GOOD.format(name="broken").replace("def careers_url", "def not_careers_url")
|
broken = _GOOD.format(name="broken").replace("def careers_url", "def not_careers_url")
|
||||||
@@ -85,12 +107,14 @@ def test_the_contract_check_names_each_problem() -> None:
|
|||||||
module.slug_ok = module.allowed = module.careers_url = lambda slug: ""
|
module.slug_ok = module.allowed = module.careers_url = lambda slug: ""
|
||||||
module.page = lambda get, slug, cursor: None
|
module.page = lambda get, slug, cursor: None
|
||||||
module.probe_ok = lambda body: True
|
module.probe_ok = lambda body: True
|
||||||
|
module.RANK, module.KEEP_CASE = "1", "yes"
|
||||||
found = atshosts.problems(module, "odd")
|
found = atshosts.problems(module, "odd")
|
||||||
assert "NAME is 'other', not the module's name 'odd'" in found
|
assert "NAME is 'other', not the module's name 'odd'" in found
|
||||||
assert "LABEL is not a non-empty string" in found
|
assert "LABEL is not a non-empty string" in found
|
||||||
assert any(p.startswith("PATTERNS has '('") for p in found)
|
assert any(p.startswith("PATTERNS has '('") for p in found)
|
||||||
assert "page without rows" in found
|
assert "page without rows" in found
|
||||||
assert "probe_ok without probe_url" in found
|
assert "probe_ok without probe_url" in found
|
||||||
|
assert "RANK is not an int" in found and "KEEP_CASE is not a bool" in found
|
||||||
|
|
||||||
|
|
||||||
# ------------------------------------------------------------ the fetch
|
# ------------------------------------------------------------ the fetch
|
||||||
|
|||||||
@@ -268,6 +268,29 @@ def test_slug_probes_find_a_board_the_pages_never_link() -> None:
|
|||||||
assert found.evidence == "https://api.ashbyhq.com/posting-api/job-board/acme"
|
assert found.evidence == "https://api.ashbyhq.com/posting-api/job-board/acme"
|
||||||
|
|
||||||
|
|
||||||
|
@pytest.mark.parametrize(("boards", "found"), [
|
||||||
|
({("greenhouse", "acme"), ("ashby", "acme")}, "greenhouse:acme"),
|
||||||
|
({("lever", "acme"), ("ashby", "acme")}, "lever:acme"),
|
||||||
|
({("smartrecruiters", "acme"), ("personio", "acme")}, "smartrecruiters:acme"),
|
||||||
|
({("lever", "eu/acme"), ("personio", "acme")}, "lever:eu/acme"),
|
||||||
|
])
|
||||||
|
def test_a_slug_on_two_hosts_goes_to_the_one_probed_first(
|
||||||
|
boards: set[tuple[str, str]], found: str) -> None:
|
||||||
|
site = Site({}, boards=boards)
|
||||||
|
assert run(site).board == found
|
||||||
|
|
||||||
|
|
||||||
|
def test_the_probe_order_is_the_one_before_modules() -> None:
|
||||||
|
assert list(mod._PROBES)[:7] == ["greenhouse", "lever", "ashby", "smartrecruiters",
|
||||||
|
"recruitee", "personio", "teamtailor"]
|
||||||
|
site = Site({})
|
||||||
|
run(site)
|
||||||
|
assert site.probed[:8] == [("greenhouse", "acme"), ("lever", "acme"), ("lever", "eu/acme"),
|
||||||
|
("ashby", "acme"), ("smartrecruiters", "acme"),
|
||||||
|
("recruitee", "acme"), ("personio", "acme"),
|
||||||
|
("teamtailor", "acme")]
|
||||||
|
|
||||||
|
|
||||||
def test_a_lever_eu_board_is_found_by_its_probe() -> None:
|
def test_a_lever_eu_board_is_found_by_its_probe() -> None:
|
||||||
site = Site({"https://acme.com/": "<p>a script draws the jobs</p>"},
|
site = Site({"https://acme.com/": "<p>a script draws the jobs</p>"},
|
||||||
boards={("lever", "eu/acme")})
|
boards={("lever", "eu/acme")})
|
||||||
|
|||||||
Reference in new issue
Block a user