about summary refs log tree commit diff
path: root/uploader/genotypes/collector_job.py
blob: f70c5ecec16ccb0c21ad8f3c8aacfad692e8a8d0 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
"""Read and validate genotype file-statistics collector jobs."""
import json
from typing import Any, Mapping


class InvalidCollectorJob(Exception):
    """Raised when a job is not a valid, completed genotype-stats job."""


def file_stats(
        job: Mapping[str, Any],
        species_id: int,
        population_id: int,
        dataset_id: int
) -> dict:
    """Return the FileStats recorded by a completed collector job.

    Raises ``InvalidCollectorJob`` if the job is not a completed
    ``genotype-file-stats`` job for the given species/population/dataset, or if
    its recorded output cannot be parsed.
    """
    metadata = job.get("metadata", {})
    if metadata.get("job-type") != "genotype-file-stats":
        raise InvalidCollectorJob(
            "The job is not a genotype file statistics collection job.")
    if metadata.get("status") != "completed":
        raise InvalidCollectorJob(
            "The file statistics collection job has not completed.")
    for key, expected in (("species_id", species_id),
                          ("population_id", population_id),
                          ("dataset_id", dataset_id)):
        if str(metadata.get(key)) != str(expected):
            raise InvalidCollectorJob(
                "The file statistics collection job belongs to a different "
                "dataset.")
    try:
        return json.loads(job.get("stdout") or "")
    except (TypeError, ValueError) as _exc:
        raise InvalidCollectorJob(
            f"Could not read the file statistics from the job: {_exc}") from _exc