1c1dceeee2
Ruff: declare adapter re-exports via __all__ in docling_extractor (F401) and sort the engine import block in the adapter test (I001). Pytest: engine-dependent tests now importorskip the pinned engine — CI installs light deps only and the engine repo is private, so they skip visibly there and run in Docker/dev envs with the engine. Verified: ruff clean; pytest 74 passed + 2 skipped without engine, 80 passed with the pinned engine v0.1.0 installed. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
32 lines
829 B
Python
32 lines
829 B
Python
"""LegacyHUB adapter for the shared Docling recognition engine."""
|
|
|
|
from __future__ import annotations
|
|
|
|
from pathlib import Path
|
|
|
|
from teamhub_document_recognition_engine import (
|
|
ExtractedBlock,
|
|
ExtractedFigure,
|
|
ExtractedPage,
|
|
ExtractedTable,
|
|
ExtractionResult,
|
|
)
|
|
from teamhub_document_recognition_engine import extract as _engine_extract
|
|
|
|
from app.config import settings
|
|
|
|
# Re-exported engine models: chunker, table/figure processors and tests import
|
|
# them from this adapter instead of depending on the engine package directly.
|
|
__all__ = [
|
|
"ExtractedBlock",
|
|
"ExtractedFigure",
|
|
"ExtractedPage",
|
|
"ExtractedTable",
|
|
"ExtractionResult",
|
|
"extract",
|
|
]
|
|
|
|
|
|
def extract(pdf_path: Path) -> ExtractionResult:
|
|
return _engine_extract(pdf_path, docling_ocr_enabled=settings.docling_ocr_enabled)
|