mirror of
https://github.com/PR0M3TH3AN/unredact.git
synced 2026-10-27 08:40:29 +00:00
Alex-GilbertandClaude Opus 4.6
420e20a8cf
Add rasterize_pdf() that converts PDF pages to PIL images using pdf2image. Supports configurable DPI and page range selection. Includes tests verifying multi-page output, high-DPI dimensions, and single-page extraction. Co-Authored-By: Claude Opus 4.6 <[email protected]>
25 lines
684 B
Python
25 lines
684 B
Python
from pathlib import Path
|
|
|
|
from PIL import Image
|
|
|
|
from unredact.pipeline.rasterize import rasterize_pdf
|
|
|
|
|
|
def test_rasterize_returns_list_of_images(sample_pdf: Path):
|
|
pages = rasterize_pdf(sample_pdf)
|
|
assert len(pages) == 2 # EFTA00554620.pdf has 2 pages
|
|
assert all(isinstance(p, Image.Image) for p in pages)
|
|
|
|
|
|
def test_rasterize_high_dpi(sample_pdf: Path):
|
|
pages = rasterize_pdf(sample_pdf, dpi=300)
|
|
# At 300 DPI, a letter-size page is roughly 2550x3300
|
|
w, h = pages[0].size
|
|
assert w > 2000
|
|
assert h > 3000
|
|
|
|
|
|
def test_rasterize_single_page(sample_pdf: Path):
|
|
pages = rasterize_pdf(sample_pdf, first_page=1, last_page=1)
|
|
assert len(pages) == 1
|