Circuit-Forge/circuitforge-core
5
0
Fork 0
Code Issues 5 Pull requests Projects Releases 8 Packages Wiki Activity Actions 2

test(documents): add OCR fallback and edge case tests for PDFExtractor

Browse source
This commit is contained in:
pyr0ball 2026-05-04 08:45:53 -07:00
parent 408ab64c55
commit ac45067ae7
1 changed files with 7 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

7
tests/test_documents/test_pdf.py
View file

@ -98,3 +98,10 @@ def test_chunk_pages_ocr_failure_returns_empty_chunk():
assert chunks[0].text == "" assert chunks[0].text == ""
assert chunks[0].source == "ocr" assert chunks[0].source == "ocr"
assert chunks[0].word_count == 0 assert chunks[0].word_count == 0
def test_chunk_pages_empty_pdf_returns_empty_list():
with patch("circuitforge_core.documents.pdf.pdfplumber") as mock_pl:
mock_pl.open.return_value = _mock_pdf([])
chunks = PDFExtractor().chunk_pages("/fake/empty.pdf")
assert chunks == []