Files
transcription/tests/services/test_transcription_service.py
T
2026-08-01 16:17:38 -05:00

92 lines
3.7 KiB
Python

"""Tests for source revision behavior in TranscriptionService."""
from uuid import uuid4
import pytest
from transcription.db.models import Document
from transcription.db.models import Job
from transcription.db.models import JobSource
from transcription.db.models import JobSourceStatus
from transcription.db.models import JobStatus
from transcription.db.models import Source
from transcription.services.documents import DocumentService
from transcription.services.jobs import JobService
from transcription.services.transcription import TranscriptionService
@pytest.mark.integration
class TestTranscriptionServiceRevisionUpsert:
"""Verify page-level source revision semantics."""
@pytest.mark.asyncio
async def test_upsert_revision_creates_new_revision(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="revision-create")
await documents.create_document(document=document)
job = Job(document_id=document.id, status=JobStatus.TRANSCRIBED)
await jobs.create_job(job=job)
source = Source(
document_id=document.id,
page_number=1,
upload_name="source.jpg",
filename="source.jpg",
file_path="uploads/source.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)
revision = await transcriptions.upsert_revision_for_source(source_id=source.id, text="User revision")
fetched = await transcriptions.read_revision_by_source(source.id)
assert revision.id == source.id
assert revision.revised_text == "User revision"
assert fetched is not None
assert fetched.id == source.id
assert fetched.revised_text == "User revision"
@pytest.mark.asyncio
async def test_upsert_revision_updates_existing_single_revision(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="revision-update")
await documents.create_document(document=document)
job = Job(document_id=document.id, status=JobStatus.TRANSCRIBED)
await jobs.create_job(job=job)
source = Source(
document_id=document.id,
page_number=1,
upload_name="source.jpg",
filename="source.jpg",
file_path="uploads/source.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)
first = await transcriptions.upsert_revision_for_source(source_id=source.id, text="Revision v1")
second = await transcriptions.upsert_revision_for_source(source_id=source.id, text="Revision v2")
revisions = await transcriptions.list_revisions_by_job(job.id)
assert first.id == second.id
assert second.revised_text == "Revision v2"
assert len(revisions) == 1
assert revisions[0].id == first.id
assert revisions[0].revised_text == "Revision v2"