apunkt/SurfSense
1
0
Fork 0
mirror of https://github.com/MODSetter/SurfSense.git synced 2026-05-21 18:55:16 +02:00
Code Issues Projects Releases Packages Wiki Activity

chore: linting

Browse source
This commit is contained in:
DESKTOP-RTLN3BA\$punk 2026-05-15 17:33:44 -07:00
parent 219a5977b7
commit c187b04e82
25 changed files with 102 additions and 108 deletions
Download patch file Download diff file Expand all files Collapse all files

14
surfsense_backend/tests/unit/etl_pipeline/test_etl_pipeline_service.py
View file

@ -903,9 +903,7 @@ async def test_extract_pdf_without_vision_llm_skips_picture_descriptions(
describe_mock.assert_not_called()
async def test_extract_pdf_with_vision_llm_swallows_describe_failure(
tmp_path, mocker
):
async def test_extract_pdf_with_vision_llm_swallows_describe_failure(tmp_path, mocker):
"""A pypdf or vision LLM blow-up never fails the document upload."""
pdf_file = tmp_path / "report.pdf"
pdf_file.write_bytes(b"%PDF-1.4 fake content")
@ -976,9 +974,7 @@ async def test_extract_pdf_with_vision_llm_no_images_returns_parser_text(
# ---------------------------------------------------------------------------
async def test_extract_pdf_passes_ocr_runner_to_describe_pictures(
tmp_path, mocker
):
async def test_extract_pdf_passes_ocr_runner_to_describe_pictures(tmp_path, mocker):
"""The ETL service must wire an ocr_runner kwarg to describe_pictures."""
pdf_file = tmp_path / "report.pdf"
pdf_file.write_bytes(b"%PDF-1.4 fake content")
@ -1027,9 +1023,7 @@ async def test_extract_pdf_ocr_runner_invokes_document_parser_on_image(
mocker.patch("app.config.config.ETL_SERVICE", "DOCLING")
fake_docling = mocker.AsyncMock()
fake_docling.process_document.return_value = {
"content": "Slice 24 / 60 L R"
}
fake_docling.process_document.return_value = {"content": "Slice 24 / 60 L R"}
mocker.patch(
"app.services.docling_service.create_docling_service",
return_value=fake_docling,
@ -1074,7 +1068,7 @@ async def test_extract_pdf_ocr_runner_returns_empty_on_unsupported_image(
pdf_file = tmp_path / "report.pdf"
pdf_file.write_bytes(b"%PDF-1.4 fake content")
weird_image = tmp_path / "Im0.jp2" # JPEG2000, unlikely to be supported
weird_image.write_bytes(b"\x00\x00\x00\x0CjP" + b"\x00" * 50)
weird_image.write_bytes(b"\x00\x00\x00\x0cjP" + b"\x00" * 50)
mocker.patch("app.config.config.ETL_SERVICE", "DOCLING")

37
surfsense_backend/tests/unit/etl_pipeline/test_picture_describer.py
View file

@ -330,11 +330,17 @@ def test_inject_handles_multiple_images_in_order():
result = PictureExtractionResult(
descriptions=[
PictureDescription(
page_number=1, ordinal_in_page=0, name="Im0", sha256="aa",
page_number=1,
ordinal_in_page=0,
name="Im0",
sha256="aa",
description="Desc A",
),
PictureDescription(
page_number=2, ordinal_in_page=0, name="Im1", sha256="bb",
page_number=2,
ordinal_in_page=0,
name="Im1",
sha256="bb",
description="Desc B",
),
]
@ -511,9 +517,7 @@ async def test_describe_pictures_calls_ocr_runner_per_image(tmp_path, mocker):
assert by_name == {"Im0.jpeg": "OCR text A", "Im1.png": "OCR text B"}
async def test_describe_pictures_runs_vision_and_ocr_in_parallel(
tmp_path, mocker
):
async def test_describe_pictures_runs_vision_and_ocr_in_parallel(tmp_path, mocker):
"""Vision LLM and OCR run concurrently per image, not sequentially.
We verify this by recording call timestamps: if both finish within
@ -656,9 +660,7 @@ async def test_describe_pictures_vision_failure_with_ocr_runner_skips_image(
assert result.failed == 1
async def test_describe_pictures_no_ocr_runner_keeps_ocr_text_none(
tmp_path, mocker
):
async def test_describe_pictures_no_ocr_runner_keeps_ocr_text_none(tmp_path, mocker):
"""Backward compat: omitting ocr_runner produces description-only blocks."""
pdf_file = tmp_path / "report.pdf"
pdf_file.write_bytes(b"%PDF-1.4 fake")
@ -824,11 +826,17 @@ def test_inject_handles_multiple_figures_in_document_order():
result = PictureExtractionResult(
descriptions=[
PictureDescription(
page_number=1, ordinal_in_page=0, name="Im0", sha256="aa",
page_number=1,
ordinal_in_page=0,
name="Im0",
sha256="aa",
description="Description of chart A.",
),
PictureDescription(
page_number=2, ordinal_in_page=0, name="Im1", sha256="bb",
page_number=2,
ordinal_in_page=0,
name="Im1",
sha256="bb",
description="Description of chart B.",
),
]
@ -842,9 +850,7 @@ def test_inject_handles_multiple_figures_in_document_order():
assert out.count("</figure>") == 2
assert "Description of chart A." in out
assert "Description of chart B." in out
assert out.index("Description of chart A.") < out.index(
"Description of chart B."
)
assert out.index("Description of chart A.") < out.index("Description of chart B.")
# Each description appears AFTER its corresponding </figure>.
first_close = out.index("</figure>")
assert first_close < out.index("Description of chart A.")
@ -856,7 +862,7 @@ def test_inject_figures_with_attributes_and_nested_tags():
"""``<figure>`` with attributes and nested tags is matched and preserved."""
markdown = (
'<figure id="fig-3" class="chart">\n'
'<figcaption>Source: Pew Research</figcaption>\n'
"<figcaption>Source: Pew Research</figcaption>\n"
"<table><tr><td>Republican</td><td>57</td></tr></table>\n"
"</figure>\n"
)
@ -899,8 +905,7 @@ def test_inject_figures_more_descriptions_than_figures_returns_remaining():
def test_inject_figures_more_figures_than_descriptions_leaves_extras_untouched():
"""Two figures, one description -> first figure enriched, second left raw."""
markdown = (
"<figure>\nfigure 1 content\n</figure>\n"
"<figure>\nfigure 2 content\n</figure>\n"
"<figure>\nfigure 1 content\n</figure>\n<figure>\nfigure 2 content\n</figure>\n"
)
result = PictureExtractionResult(
descriptions=[_desc(name="Im0", description="Only description.")]