Enable lossless reconstruction for —pdf-renderer tess4 where appropriate
This commit is contained in:
@@ -290,7 +290,7 @@ def check_options_output(options, log):
|
||||
"--pdf-renderer=tesseract.")
|
||||
|
||||
lossless_reconstruction = False
|
||||
if options.pdf_renderer == 'hocr':
|
||||
if options.pdf_renderer in ('hocr', 'tess4'):
|
||||
if not any((options.deskew, options.clean_final, options.force_ocr,
|
||||
options.remove_background)):
|
||||
lossless_reconstruction = True
|
||||
|
||||
@@ -97,3 +97,17 @@ def test_skip_pages_does_not_replicate(
|
||||
|
||||
for n in range(len(info_in)):
|
||||
assert info[n]['width_inches'] == info_in[n]['width_inches']
|
||||
|
||||
|
||||
def test_content_preservation(ensure_tess4, resources, outpdf):
|
||||
infile = resources / 'masks.pdf'
|
||||
|
||||
check_ocrmypdf(
|
||||
infile,
|
||||
outpdf, '--pdf-renderer', 'tess4', '--tesseract-timeout', '0',
|
||||
env=ensure_tess4
|
||||
)
|
||||
|
||||
info = pageinfo.pdf_get_all_pageinfo(str(outpdf))
|
||||
page = info[0]
|
||||
assert len(page['images']) > 1, "masked were rasterized"
|
||||
Reference in New Issue
Block a user