def test_create_or_update_jobs_with_git_error(tmp_work_dir):
repo_url = str(Path(__file__).parent.resolve() / "fixtures/git-repo")
bad_commit = "0" * 40
job_request = JobRequest(
id="123",
repo_url=repo_url,
commit=bad_commit,
branch="v1",
requested_actions=["generate_cohort"],
cancelled_actions=[],
workspace="1",
database_name="dummy",
original={},
)
create_or_update_jobs(job_request)
j = find_one(Job)
assert j.job_request_id == "123"
assert j.state == State.FAILED
assert j.repo_url == repo_url
assert j.commit == bad_commit
assert j.workspace == "1"
assert j.wait_for_job_ids is None
assert j.requires_outputs_from is None
assert j.run_command is None
assert j.output_spec is None
assert (j.status_message ==
f"GitError: Error fetching commit {bad_commit} from {repo_url}")
def test_create_or_update_jobs_with_git_error(tmp_work_dir):
repo_url = str(Path(__file__).parent.resolve() / "fixtures/git-repo")
job_request = JobRequest(
id="123",
repo_url=repo_url,
commit=None,
branch="no-such-branch",
requested_actions=["generate_cohort"],
workspace="1",
database_name="dummy",
original={},
)
create_or_update_jobs(job_request)
jobs = find_where(Job)
assert len(jobs) == 1
j = jobs[0]
assert j.job_request_id == "123"
assert j.state == State.FAILED
assert j.repo_url == repo_url
assert j.commit == None
assert j.workspace == "1"
assert j.wait_for_job_ids == None
assert j.requires_outputs_from == None
assert j.run_command == None
assert j.output_spec == None
assert (
j.status_message
== f"GitError: Error resolving ref 'no-such-branch' from {repo_url}"
)
def test_create_or_update_jobs(tmp_work_dir):
repo_url = str(Path(__file__).parent.resolve() / "fixtures/git-repo")
job_request = JobRequest(
id="123",
repo_url=repo_url,
commit=None,
branch="v1",
requested_actions=["generate_cohort"],
workspace="1",
database_name="dummy",
original={},
)
create_or_update_jobs(job_request)
jobs = find_where(Job)
assert len(jobs) == 1
j = jobs[0]
assert j.job_request_id == "123"
assert j.state == State.PENDING
assert j.repo_url == repo_url
assert j.commit == "d1e88b31cbe8f67c58f938adb5ee500d54a69764"
assert j.workspace == "1"
assert j.action == "generate_cohort"
assert j.wait_for_job_ids == []
assert j.requires_outputs_from == []
assert j.run_command == (
"cohortextractor:latest generate_cohort --expectations-population=1000"
" --output-dir=."
)
assert j.output_spec == {"highly_sensitive": {"cohort": "input.csv"}}
assert j.status_message == None
# Check no new jobs created from same JobRequest
create_or_update_jobs(job_request)
new_jobs = find_where(Job)
assert jobs == new_jobs
def test_job_request_from_remote_format():
remote_job_request = {
"identifier": "123",
"workspace": {
"name": "testing",
"repo": "https://github.com/opensafely/foo",
"branch": "master",
"db": "full",
},
"requested_actions": ["generate_cohort"],
"force_run_dependencies": True,
}
expected = JobRequest(
id="123",
repo_url="https://github.com/opensafely/foo",
commit=None,
branch="master",
workspace="testing",
database_name="full",
requested_actions=["generate_cohort"],
force_run_dependencies=True,
original=remote_job_request,
)
job_request = job_request_from_remote_format(remote_job_request)
assert job_request == expected
def job_request_factory(**kwargs):
if "id" not in kwargs:
kwargs["id"] = base64.b32encode(secrets.token_bytes(10)).decode("ascii").lower()
values = deepcopy(JOB_REQUEST_DEFAULTS)
values.update(kwargs)
job_request = JobRequest(**values)
insert(SavedJobRequest(id=job_request.id, original=job_request.original))
return job_request
def create_job_request_and_jobs(project_dir, actions, force_run_dependencies):
job_request = JobRequest(
id=random_id(),
repo_url=str(project_dir),
commit=None,
requested_actions=actions,
cancelled_actions=[],
workspace=project_dir.name,
database_name="dummy",
force_run_dependencies=force_run_dependencies,
# The default behaviour of refusing to run if a dependency has failed
# makes for an awkward workflow when iterating in development
force_run_failed=True,
branch="",
original={"created_by": getuser()},
)
project_file_path = project_dir / "project.yaml"
if not project_file_path.exists():
raise ProjectValidationError(
f"No project.yaml file found in {project_dir}")
# NOTE: Similar but non-identical logic is implemented for running jobs in
# production in `jobrunner.create_or_update_jobs.create_jobs`. If you make
# changes below then consider what, if any, the appropriate corresponding
# changes might be for production jobs.
pipeline_config = load_pipeline(project_file_path)
latest_jobs = calculate_workspace_state(job_request.workspace)
# On the server out-of-band deletion of an existing output is considered an error, so we ignore that case when
# scheduling and allow jobs with missing dependencies to fail loudly when they are actually run. However for local
# running we should allow researchers to delete outputs on disk and automatically rerun the actions that create
# if they are needed. So here we check whether any files are missing for completed actions and, if so, treat them
# as though they had not been run -- this will automatically trigger a rerun.
latest_jobs_with_files_present = [
job for job in latest_jobs
if all_output_files_present(project_dir, job)
]
try:
if not actions:
raise UnknownActionError("At least one action must be supplied")
new_jobs = get_new_jobs_to_run(job_request, pipeline_config,
latest_jobs_with_files_present)
except UnknownActionError as e:
# Annotate the exception with a list of valid action names so we can
# show them to the user
e.valid_actions = [RUN_ALL_COMMAND] + pipeline_config.all_actions
raise e
assert_new_jobs_created(new_jobs, latest_jobs_with_files_present)
resolve_reusable_action_references(new_jobs)
insert_into_database(job_request, new_jobs)
return job_request, new_jobs
def make_job_request(action="generate_cohort", **kwargs):
job_request = JobRequest(
id=str(uuid.uuid4()),
repo_url="https://example.com/repo.git",
commit="abcdef0123456789",
workspace="1",
database_name="full",
requested_actions=[action],
original={},
)
for key, value in kwargs.items():
setattr(job_request, key, value)
return job_request
def job_request_from_remote_format(job_request):
"""
Convert a JobRequest as received from the job-server into our own internal
representation
"""
return JobRequest(
id=str(job_request["identifier"]),
repo_url=job_request["workspace"]["repo"],
commit=job_request["sha"],
branch=job_request["workspace"]["branch"],
requested_actions=job_request["requested_actions"],
cancelled_actions=job_request["cancelled_actions"],
workspace=job_request["workspace"]["name"],
database_name=job_request["workspace"]["db"],
force_run_dependencies=job_request["force_run_dependencies"],
original=job_request,
)
def make_job_request(action=None, actions=None, **kwargs):
assert not (actions and action)
if not actions:
if action:
actions = [action]
else:
actions = ["generate_cohort"]
job_request = JobRequest(
id=str(uuid.uuid4()),
repo_url="https://example.com/repo.git",
commit="abcdef0123456789",
workspace="1",
database_name="full",
requested_actions=actions,
cancelled_actions=[],
original={},
)
for key, value in kwargs.items():
setattr(job_request, key, value)
return job_request
def test_validate_job_request(params, exc_msg, monkeypatch):
monkeypatch.setattr("jobrunner.config.USING_DUMMY_DATA_BACKEND", False)
repo_url = str(Path(__file__).parent.resolve() / "fixtures/git-repo")
kwargs = dict(
id="123",
repo_url=repo_url,
# GIT_DIR=tests/fixtures/git-repo git rev-parse v1
commit="d1e88b31cbe8f67c58f938adb5ee500d54a69764",
branch="v1",
requested_actions=["generate_cohort"],
cancelled_actions=[],
workspace="1",
database_name="full", # note db from from job-server is 'full'
original={},
)
kwargs.update(params)
job_request = JobRequest(**kwargs)
with pytest.raises(JobRequestError, match=exc_msg):
validate_job_request(job_request)
import time
from jobrunner.models import Job, JobRequest
from jobrunner import log_utils, local_run
FROZEN_TIMESTAMP = 1608568119.1467905
FROZEN_TIMESTRING = datetime.utcfromtimestamp(FROZEN_TIMESTAMP).isoformat()
repo_url = "https://github.com/opensafely/project"
test_job = Job(id="id", action="action", repo_url=repo_url)
test_request = JobRequest(
id="request",
repo_url=repo_url,
workspace="workspace",
commit="commit",
requested_actions=["action"],
cancelled_actions=[],
database_name="dummy",
)
def test_formatting_filter():
record = logging.makeLogRecord({})
assert log_utils.formatting_filter(record)
assert record.action == ""
record = logging.makeLogRecord({"job": test_job})
assert log_utils.formatting_filter(record)
assert record.action == "action: "
assert record.tags == "project=project action=action id=id"