From 3de18ed6123db1517ed0dd364051554e9bda600b Mon Sep 17 00:00:00 2001 From: "James R. Barlow" Date: Tue, 25 Jan 2022 00:19:49 -0800 Subject: [PATCH] tesseract: account for more tesseract 5 output differences --- src/ocrmypdf/_exec/tesseract.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/src/ocrmypdf/_exec/tesseract.py b/src/ocrmypdf/_exec/tesseract.py index f2518cf0..04c556e4 100644 --- a/src/ocrmypdf/_exec/tesseract.py +++ b/src/ocrmypdf/_exec/tesseract.py @@ -344,7 +344,7 @@ def generate_hocr( _generate_null_hocr(output_hocr, output_text, input_file) except CalledProcessError as e: tesseract_log_output(e.output) - if b'Image too large' in e.output: + if b'Image too large' in e.output or b'Empty page!!' in e.output: _generate_null_hocr(output_hocr, output_text, input_file) return @@ -416,7 +416,7 @@ def generate_pdf( use_skip_page(output_pdf, output_text) except CalledProcessError as e: tesseract_log_output(e.output) - if b'Image too large' in e.output: + if b'Image too large' in e.output or b'Empty page!!' in e.output: use_skip_page(output_pdf, output_text) return raise SubprocessOutputError() from e