| import pytest |
|
|
| from dataloader import convert_uploaded_documents |
|
|
|
|
| def test_uploaded_markdown_and_text_are_formatted_without_disk_output(tmp_path): |
| markdown = tmp_path / "resume.md" |
| text = tmp_path / "projects.txt" |
| markdown.write_text("# Resume", encoding="utf-8") |
| text.write_text("Project work", encoding="utf-8") |
|
|
| profile = convert_uploaded_documents([str(markdown), str(text)]) |
|
|
| assert "# Source: resume" in profile |
| assert "# Resume" in profile |
| assert "# Source: projects" in profile |
| assert "Project work" in profile |
|
|
|
|
| def test_uploaded_pdf_is_converted_to_markdown(tmp_path, monkeypatch): |
| import sys |
| from types import SimpleNamespace |
|
|
| pdf = tmp_path / "resume.pdf" |
| pdf.write_bytes(b"fake pdf") |
|
|
| class FakeConverter: |
| def convert(self, path): |
| assert path == str(pdf) |
| return SimpleNamespace(markdown="# Converted resume") |
|
|
| monkeypatch.setitem( |
| sys.modules, "markitdown", SimpleNamespace(MarkItDown=FakeConverter) |
| ) |
|
|
| assert "# Converted resume" in convert_uploaded_documents([str(pdf)]) |
|
|
|
|
| @pytest.mark.parametrize("markitdown_result", ["", "raise"]) |
| def test_uploaded_pdf_falls_back_to_rapidocr(tmp_path, monkeypatch, markitdown_result): |
| import sys |
| from types import SimpleNamespace |
| import dataloader |
|
|
| pdf = tmp_path / "scanned.pdf" |
| pdf.write_bytes(b"fake pdf") |
|
|
| class FakeConverter: |
| def convert(self, _path): |
| if markitdown_result == "raise": |
| raise ValueError("No text layer") |
| return SimpleNamespace(markdown=" ") |
|
|
| class FakeBitmap: |
| def to_numpy(self): |
| return object() |
|
|
| class FakePage: |
| def render(self, scale): |
| assert scale == 2 |
| return FakeBitmap() |
|
|
| def close(self): |
| pass |
|
|
| class FakePdfDocument: |
| def __init__(self, path): |
| assert path == str(pdf) |
|
|
| def __len__(self): |
| return 2 |
|
|
| def __getitem__(self, _index): |
| return FakePage() |
|
|
| def close(self): |
| pass |
|
|
| class FakeOCR: |
| def __call__(self, _image): |
| return SimpleNamespace(txts=("recognized text",)) |
|
|
| monkeypatch.setitem( |
| sys.modules, "markitdown", SimpleNamespace(MarkItDown=FakeConverter) |
| ) |
| monkeypatch.setitem( |
| sys.modules, |
| "pypdfium2", |
| SimpleNamespace(PdfDocument=FakePdfDocument), |
| ) |
| dataloader._get_ocr_engine.cache_clear() |
| monkeypatch.setattr(dataloader, "_get_ocr_engine", FakeOCR) |
|
|
| profile = convert_uploaded_documents([str(pdf)]) |
|
|
| assert profile.count("recognized text") == 2 |
|
|
|
|
| def test_uploaded_unsupported_file_type_is_rejected(tmp_path): |
| unsupported = tmp_path / "profile.exe" |
| unsupported.write_text("not a document", encoding="utf-8") |
|
|
| with pytest.raises(ValueError, match="Unsupported file type"): |
| convert_uploaded_documents([str(unsupported)]) |
|
|
