From 753e6274ab236e9bbb78d5e948d01e8262b1419d Mon Sep 17 00:00:00 2001 From: "James R. Barlow" Date: Thu, 5 Apr 2018 02:14:33 -0700 Subject: [PATCH] Tell unpaper to use --layout none so it won't blank out multi column text --- docs/release_notes.rst | 5 +++++ src/ocrmypdf/exec/unpaper.py | 13 +------------ 2 files changed, 6 insertions(+), 12 deletions(-) diff --git a/docs/release_notes.rst b/docs/release_notes.rst index 017fae17..e7025514 100644 --- a/docs/release_notes.rst +++ b/docs/release_notes.rst @@ -5,6 +5,11 @@ OCRmyPDF uses `semantic versioning `_ 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 ------ diff --git a/src/ocrmypdf/exec/unpaper.py b/src/ocrmypdf/exec/unpaper.py index 2afea60b..6dd7edfe 100644 --- a/src/ocrmypdf/exec/unpaper.py +++ b/src/ocrmypdf/exec/unpaper.py @@ -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