Jobs: big jobs stuck in queue. Added Cancel, Resubmit

This commit is contained in:
Jim Lancaster
2026-08-04 09:03:51 -05:00
parent 759d4c2434
commit 6c6589d8ff
11 changed files with 1126 additions and 124 deletions
+156
View File
@@ -13,6 +13,8 @@ from transcription.db.models import JobStatus
from transcription.db.models import Source
from transcription.services.documents import DocumentService
from transcription.services.jobs import JobDeleteBlockedError
from transcription.services.jobs import JobCancelBlockedError
from transcription.services.jobs import JobResubmitBlockedError
from transcription.services.jobs import JobService
@@ -224,3 +226,157 @@ class TestJobService:
with pytest.raises(ValueError):
await job_service.read_job(job_id=job.id)
@pytest.mark.asyncio
async def test_cancel_job_marks_non_transcribed_sources_failed(
self,
job_service: JobService,
document_service: DocumentService,
):
document = Document(id=uuid4(), name="cancel-job-doc")
await document_service.create_document(document=document)
job = Job(document_id=document.id, status=JobStatus.QUEUED)
await job_service.create_job(job=job)
async with job_service._session_scope() as session:
source_one = Source(
document_id=document.id,
page_number=1,
upload_name="cancel-1.jpg",
filename="stored-cancel-1.jpg",
file_path="/uploads/stored-cancel-1.jpg",
)
source_two = Source(
document_id=document.id,
page_number=2,
upload_name="cancel-2.jpg",
filename="stored-cancel-2.jpg",
file_path="/uploads/stored-cancel-2.jpg",
)
session.add(source_one)
session.add(source_two)
await session.flush()
session.add(
JobSource(
job_id=job.id,
source_id=source_one.id,
status=JobSourceStatus.TRANSCRIBED,
raw_transcription="done",
)
)
session.add(
JobSource(
job_id=job.id,
source_id=source_two.id,
status=JobSourceStatus.PENDING,
)
)
await session.commit()
cancelled = await job_service.cancel_job(job_id=job.id)
assert cancelled.status == JobStatus.FAILED
refreshed = await job_service.read_job(job_id=job.id)
statuses = {item.status for item in refreshed.job_sources}
assert JobSourceStatus.TRANSCRIBED in statuses
assert JobSourceStatus.FAILED in statuses
pending_entry = next(item for item in refreshed.job_sources if item.status == JobSourceStatus.FAILED)
assert pending_entry.error_detail == "Cancelled by user"
@pytest.mark.asyncio
async def test_resubmit_non_transcribed_sources_resets_only_non_transcribed(
self,
job_service: JobService,
document_service: DocumentService,
):
document = Document(id=uuid4(), name="resubmit-job-doc")
await document_service.create_document(document=document)
job = Job(document_id=document.id, status=JobStatus.FAILED)
await job_service.create_job(job=job)
async with job_service._session_scope() as session:
source_one = Source(
document_id=document.id,
page_number=1,
upload_name="resubmit-1.jpg",
filename="stored-resubmit-1.jpg",
file_path="/uploads/stored-resubmit-1.jpg",
raw_transcription="existing text",
)
source_two = Source(
document_id=document.id,
page_number=2,
upload_name="resubmit-2.jpg",
filename="stored-resubmit-2.jpg",
file_path="/uploads/stored-resubmit-2.jpg",
raw_transcription="done text",
)
session.add(source_one)
session.add(source_two)
await session.flush()
session.add(
JobSource(
job_id=job.id,
source_id=source_one.id,
status=JobSourceStatus.FAILED,
raw_transcription=None,
error_detail="prior error",
)
)
session.add(
JobSource(
job_id=job.id,
source_id=source_two.id,
status=JobSourceStatus.TRANSCRIBED,
raw_transcription="done text",
)
)
await session.commit()
count = await job_service.resubmit_non_transcribed_sources(job_id=job.id)
assert count == 1
refreshed = await job_service.read_job(job_id=job.id)
assert refreshed.status == JobStatus.QUEUED
failed_entry = next(item for item in refreshed.job_sources if item.source is not None and item.source.page_number == 1)
transcribed_entry = next(item for item in refreshed.job_sources if item.source is not None and item.source.page_number == 2)
assert failed_entry.status == JobSourceStatus.PENDING
assert failed_entry.error_detail is None
assert failed_entry.source is not None
assert failed_entry.source.raw_transcription is None
assert transcribed_entry.status == JobSourceStatus.TRANSCRIBED
@pytest.mark.asyncio
async def test_resubmit_non_transcribed_sources_blocks_when_processing(
self,
job_service: JobService,
document_service: DocumentService,
):
document = Document(id=uuid4(), name="resubmit-blocked-doc")
await document_service.create_document(document=document)
job = Job(document_id=document.id, status=JobStatus.PROCESSING)
await job_service.create_job(job=job)
with pytest.raises(JobResubmitBlockedError):
await job_service.resubmit_non_transcribed_sources(job_id=job.id)
@pytest.mark.asyncio
async def test_cancel_job_blocks_transcribed_terminal_jobs(
self,
job_service: JobService,
document_service: DocumentService,
):
document = Document(id=uuid4(), name="cancel-blocked-doc")
await document_service.create_document(document=document)
job = Job(document_id=document.id, status=JobStatus.TRANSCRIBED)
await job_service.create_job(job=job)
with pytest.raises(JobCancelBlockedError):
await job_service.cancel_job(job_id=job.id)
@@ -154,3 +154,54 @@ class TestTranscriptionServiceRevisionUpsert:
with pytest.raises(SourceDeleteBlockedError):
await transcriptions.delete_source_from_job_context(job_id=job_one.id, source_id=source.id)
@pytest.mark.asyncio
async def test_delete_unlinked_source_succeeds(self, default_session_factory):
documents = DocumentService(session_factory=default_session_factory)
transcriptions = TranscriptionService(session_factory=default_session_factory)
document = Document(id=uuid4(), name="delete-unlinked-source")
await documents.create_document(document=document)
source = Source(
document_id=document.id,
page_number=1,
upload_name="orphan.jpg",
filename="orphan.jpg",
file_path="uploads/orphan.jpg",
)
await transcriptions.create_source(source=source)
await transcriptions.delete_unlinked_source(source_id=source.id)
with pytest.raises(TranscriptionNotFoundError):
await transcriptions.read_source(source.id)
@pytest.mark.asyncio
async def test_delete_unlinked_source_blocks_when_linked(self, default_session_factory):
documents = DocumentService(session_factory=default_session_factory)
jobs = JobService(session_factory=default_session_factory)
transcriptions = TranscriptionService(session_factory=default_session_factory)
document = Document(id=uuid4(), name="delete-unlinked-blocked")
await documents.create_document(document=document)
job = Job(document_id=document.id, status=JobStatus.QUEUED)
await jobs.create_job(job=job)
source = Source(
document_id=document.id,
page_number=1,
upload_name="linked.jpg",
filename="linked.jpg",
file_path="uploads/linked.jpg",
)
async with transcriptions._session_scope() as session:
session.add(source)
await session.flush()
session.add(JobSource(job_id=job.id, source_id=source.id, status=JobSourceStatus.PENDING))
await session.commit()
await session.refresh(source)
with pytest.raises(SourceDeleteBlockedError):
await transcriptions.delete_unlinked_source(source_id=source.id)