def inspect_job(self,
job_id,
block_state=None,
output_commit=None,
full=None):
"""
Inspects a job with a given ID. Returns a `JobInfo`.
Params:
* `job_id`: The ID of the job to inspect.
* `block_state`: If true, block until the job completes.
* `output_commit`: An optional tuple, string, or `Commit` object
representing an output commit to filter on.
* `full`: If true, include worker status.
"""
return self._req(
Service.PPS,
"InspectJob",
job=pps_proto.Job(id=job_id),
block_state=block_state,
output_commit=commit_from(output_commit)
if output_commit is not None else None,
full=full,
)
def stop_job(self, job_id):
"""
Stops a job by its ID.
Params:
* `job_id`: The ID of the job to stop.
"""
return self._req(Service.PPS, "StopJob", job=pps_proto.Job(id=job_id))
def delete_job(self, job_id):
"""
Deletes a job by its ID.
Params:
* `job_id`: The ID of the job to delete.
"""
return self._req(Service.PPS,
"DeleteJob",
job=pps_proto.Job(id=job_id))
def inspect_datum(self, job_id, datum_id):
"""
Inspects a datum. Returns a `DatumInfo` object.
Params:
* `job_id`: The ID of the job.
* `datum_id`: The ID of the datum.
"""
return self._req(
Service.PPS,
"InspectDatum",
datum=pps_proto.Datum(id=datum_id, job=pps_proto.Job(id=job_id)),
)
def restart_datum(self, job_id, data_filters=None):
"""
Restarts a datum.
Params:
* `job_id`: The ID of the job.
* `data_filters`: An optional iterable of strings.
"""
return self._req(
Service.PPS,
"RestartDatum",
job=pps_proto.Job(id=job_id),
data_filters=data_filters,
)
def list_datum(self, job_id, page_size=None, page=None):
"""
Lists datums. Yields `ListDatumStreamResponse` objects.
Params:
* `job_id`: The ID of the job.
* `page_size`: An optional int specifying the size of the page.
* `page`: An optional int specifying the page number.
"""
return self._req(
Service.PPS,
"ListDatumStream",
job=pps_proto.Job(id=job_id),
page_size=page_size,
page=page,
)
def get_job_logs(
self,
job_id,
data_filters=None,
datum=None,
follow=None,
tail=None,
use_loki_backend=None,
since=None,
):
"""
Gets logs for a job. Yields `LogMessage` objects.
Params:
* `job_id`: A string representing a job to get logs of.
* `data_filters`: An optional iterable of strings specifying the names
of input files from which we want processing logs. This may contain
multiple files, to query pipelines that contain multiple inputs. Each
filter may be an absolute path of a file within a pps repo, or it may
be a hash for that file (to search for files at specific versions.)
* `datum`: An optional `Datum` object.
* `follow`: An optional bool specifying whether logs should continue to
stream forever.
* `tail`: An optional int. If nonzero, the number of lines from the end
of the logs to return. Note: tail applies per container, so you will
get tail * <number of pods> total lines back.
* `use_loki_backend`: Whether to use loki as a backend for fetching
logs. Requires a loki-enabled cluster.
* `since`: An optional `Duration` object specifying the start time for
returned logs
"""
return self._req(
Service.PPS,
"GetLogs",
job=pps_proto.Job(id=job_id),
data_filters=data_filters,
datum=datum,
follow=follow,
tail=tail,
use_loki_backend=use_loki_backend,
since=since,
)
def list_datum(self, job_id=None, page_size=None, page=None, input=None):
"""
Lists datums. Yields `ListDatumStreamResponse` objects.
Params:
* `job_id`: An optional int specifying the ID of a job. Exactly one of
`job_id` (real) or `input` (hypothetical) must be set.
* `page_size`: An optional int specifying the size of the page.
* `page`: An optional int specifying the page number.
* `input`: An optional `Input` object. If set in lieu of `job_id`,
list_datum returns the datums that would be given to a hypothetical
job that used `input` as its input spec. Exactly one of `job_id`
(real) or `input` (hypothetical) must be set.
"""
return self._req(
Service.PPS,
"ListDatumStream",
job=pps_proto.Job(id=job_id),
page_size=page_size,
page=page,
input=input,
)
