diff --git a/document-parser/domain/ports.py b/document-parser/domain/ports.py index 562c567..bc36c9b 100644 --- a/document-parser/domain/ports.py +++ b/document-parser/domain/ports.py @@ -6,9 +6,10 @@ Infrastructure adapters (local Docling, Docling Serve, etc.) implement these. from __future__ import annotations -from typing import Protocol +from typing import TYPE_CHECKING, Protocol -from domain.value_objects import ConversionOptions, ConversionResult +if TYPE_CHECKING: + from domain.value_objects import ConversionOptions, ConversionResult class DocumentConverter(Protocol): diff --git a/document-parser/infra/serve_converter.py b/document-parser/infra/serve_converter.py index 34fc4ef..635e8fb 100644 --- a/document-parser/infra/serve_converter.py +++ b/document-parser/infra/serve_converter.py @@ -214,16 +214,17 @@ def _extract_bbox(bbox_data: dict, page_height: float) -> list[float]: if not isinstance(bbox_data, dict): return [0.0, 0.0, 0.0, 0.0] - l = bbox_data.get("l", 0.0) - t = bbox_data.get("t", 0.0) - r = bbox_data.get("r", 0.0) - b = bbox_data.get("b", 0.0) + left = bbox_data.get("l", 0.0) + top = bbox_data.get("t", 0.0) + right = bbox_data.get("r", 0.0) + bottom = bbox_data.get("b", 0.0) coord_origin = bbox_data.get("coord_origin", "TOPLEFT") if coord_origin == "BOTTOMLEFT": - # Convert: top = page_height - old_top, bottom = page_height - old_bottom - new_t = page_height - b - new_b = page_height - t - t, b = new_t, new_b + # In BOTTOMLEFT: top has higher y, bottom has lower y + # In TOPLEFT: flip both — new_top = page_height - old_top + new_top = page_height - top + new_bottom = page_height - bottom + top, bottom = new_top, new_bottom - return [l, t, r, b] + return [left, top, right, bottom] diff --git a/document-parser/services/analysis_service.py b/document-parser/services/analysis_service.py index 8759ef3..6f7f543 100644 --- a/document-parser/services/analysis_service.py +++ b/document-parser/services/analysis_service.py @@ -10,10 +10,13 @@ import asyncio import json import logging from dataclasses import asdict +from typing import TYPE_CHECKING from domain.models import AnalysisJob -from domain.ports import DocumentConverter from domain.value_objects import ConversionOptions, ConversionResult + +if TYPE_CHECKING: + from domain.ports import DocumentConverter from persistence import analysis_repo, document_repo logger = logging.getLogger(__name__) diff --git a/document-parser/tests/test_pipeline_options.py b/document-parser/tests/test_pipeline_options.py index 39ec84b..f402fdc 100644 --- a/document-parser/tests/test_pipeline_options.py +++ b/document-parser/tests/test_pipeline_options.py @@ -14,6 +14,8 @@ from docling.datamodel.pipeline_options import ( from domain.value_objects import ConversionOptions from infra.local_converter import ( _build_docling_converter as build_converter, +) +from infra.local_converter import ( _convert_sync as convert_document, ) @@ -457,13 +459,15 @@ class TestAnalysisEndpointPipelineOptions: @pytest.fixture def client(self): from fastapi.testclient import TestClient + from main import app return TestClient(app, raise_server_exceptions=False) @pytest.fixture def mock_svc(self, client): - from main import app from unittest.mock import MagicMock + + from main import app mock = MagicMock() original = getattr(app.state, "analysis_service", None) app.state.analysis_service = mock diff --git a/document-parser/tests/test_serve_converter.py b/document-parser/tests/test_serve_converter.py index 31f73c0..b9c4b36 100644 --- a/document-parser/tests/test_serve_converter.py +++ b/document-parser/tests/test_serve_converter.py @@ -8,16 +8,14 @@ from unittest.mock import AsyncMock, MagicMock, patch import httpx import pytest -from domain.value_objects import ConversionOptions, ConversionResult, PageDetail, PageElement +from domain.value_objects import ConversionOptions, ConversionResult from infra.serve_converter import ( ServeConverter, _build_form_data, _extract_bbox, - _extract_pages_from_docling_document, _parse_response, ) - # --------------------------------------------------------------------------- # Unit tests — form data building # --------------------------------------------------------------------------- @@ -182,8 +180,9 @@ class TestExtractBbox: assert bbox == [10, 20, 100, 50] def test_bottomleft_conversion(self): - bbox = _extract_bbox({"l": 10, "t": 742, "r": 100, "b": 772, "coord_origin": "BOTTOMLEFT"}, 792.0) - # new_t = 792 - 772 = 20, new_b = 792 - 742 = 50 + # In BOTTOMLEFT: t (top of box) has higher y than b (bottom of box) + bbox = _extract_bbox({"l": 10, "t": 772, "r": 100, "b": 742, "coord_origin": "BOTTOMLEFT"}, 792.0) + # new_top = 792 - 772 = 20, new_bottom = 792 - 742 = 50 assert bbox == [10, 20, 100, 50] def test_missing_coord_origin_defaults_topleft(self): @@ -308,9 +307,9 @@ class TestServeConverterConvert: conv = ServeConverter(base_url="http://localhost:5001") - with patch("infra.serve_converter.httpx.AsyncClient", return_value=mock_client): - with pytest.raises(httpx.HTTPStatusError): - await conv.convert(str(test_file), ConversionOptions()) + with patch("infra.serve_converter.httpx.AsyncClient", return_value=mock_client), \ + pytest.raises(httpx.HTTPStatusError): + await conv.convert(str(test_file), ConversionOptions()) @pytest.mark.asyncio async def test_health_check_success(self):