menekis/OCRmyPDF
Public Access
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Tell unpaper to use --layout none so it won't blank out multi column text

Browse Source
This commit is contained in:
James R. Barlow
2018-04-05 02:14:33 -07:00
parent 7f462c618b
commit 753e6274ab
2 changed files with 6 additions and 12 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/ocrmypdf/exec/unpaper.py
+1 -12
View File
@@ -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