Tell unpaper to use --layout none so it won't blank out multi column text
This commit is contained in:
@@ -5,6 +5,11 @@ OCRmyPDF uses `semantic versioning <http://semver.org/>`_ for its command line i
|
||||
|
||||
The OCRmyPDF package itself does not contain a public API, although it is fairly stable and breaking changes are usually timed with a major release. A future release will clearly define the stable public API.
|
||||
|
||||
v6.1.4
|
||||
------
|
||||
|
||||
- Fix issue #248, ``--clean`` argument may remove OCR from left column of text on certain documents. We now set ``--layout none``.
|
||||
|
||||
v6.1.3
|
||||
------
|
||||
|
||||
|
||||
@@ -90,20 +90,9 @@ def run(input_file, output_file, dpi, log, mode_args):
|
||||
Image.open(output_pnm.name).save(output_file, dpi=(dpi, dpi))
|
||||
|
||||
|
||||
def deskew(input_file, output_file, dpi, log):
|
||||
run(input_file, output_file, dpi, log, [
|
||||
'--mask-scan-size', '100', # don't blank out narrow columns
|
||||
'--no-border-align', # don't align visible content to borders
|
||||
'--no-mask-center', # don't center visible content within page
|
||||
'--no-grayfilter', # don't remove light gray areas
|
||||
'--no-blackfilter', # don't remove solid black areas
|
||||
'--no-noisefilter', # don't remove salt and pepper noise
|
||||
'--no-blurfilter' # don't remove blurry objects/debris
|
||||
])
|
||||
|
||||
|
||||
def clean(input_file, output_file, dpi, log):
|
||||
run(input_file, output_file, dpi, log, [
|
||||
'--layout', 'none',
|
||||
'--mask-scan-size', '100', # don't blank out narrow columns
|
||||
'--no-border-align', # don't align visible content to borders
|
||||
'--no-mask-center', # don't center visible content within page
|
||||
|
||||
Reference in New Issue
Block a user