File size: 2,954 Bytes
532111b 9d8bbd6 532111b 9d8bbd6 532111b 9d8bbd6 532111b 9d8bbd6 532111b 9d8bbd6 532111b 9d8bbd6 532111b 9d8bbd6 532111b 9d8bbd6 532111b 9d8bbd6 532111b d7d27a3 9d8bbd6 532111b 9d8bbd6 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 | 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)])
|