From cc5578488abb71a3086e8f1a58b0a92b08242c93 Mon Sep 17 00:00:00 2001 From: "James R. Barlow" Date: Thu, 12 Oct 2017 12:45:18 -0700 Subject: [PATCH] Remove workaround for OSD crash and use explicit -l osd Suggested by amitdo in https://github.com/tesseract-ocr/tesseract/issues/1167 --- .travis/linux_before_install.sh | 8 -------- ocrmypdf/exec/tesseract.py | 2 +- 2 files changed, 1 insertion(+), 9 deletions(-) diff --git a/.travis/linux_before_install.sh b/.travis/linux_before_install.sh index 88f0ffa6..18730bd4 100644 --- a/.travis/linux_before_install.sh +++ b/.travis/linux_before_install.sh @@ -25,14 +25,6 @@ sudo apt-get install -y --no-install-recommends \ tesseract-ocr-fra \ tesseract-ocr-deu -# Workaround for https://github.com/tesseract-ocr/tesseract/issues/1167 -# Replace tesseract data installed by tesseract-ocr-eng with a known good version -sudo apt-get install -y wget -wget -q https://github.com/tesseract-ocr/tessdata/raw/master/eng.traineddata -O packages/eng.traineddata -sha1sum packages/eng.traineddata -sha1sum /usr/share/tesseract-ocr/4.00/tessdata/eng.traineddata -sudo cp packages/eng.traineddata /usr/share/tesseract-ocr/4.00/tessdata/eng.traineddata - pip install --upgrade pip mkdir -p packages [ -f packages/unpaper_6.1-1.deb ] || wget -q 'https://www.dropbox.com/s/vaq0kbwi6e6au80/unpaper_6.1-1.deb?raw=1' -O packages/unpaper_6.1-1.deb diff --git a/ocrmypdf/exec/tesseract.py b/ocrmypdf/exec/tesseract.py index ccea07e5..b488b22d 100644 --- a/ocrmypdf/exec/tesseract.py +++ b/ocrmypdf/exec/tesseract.py @@ -126,7 +126,7 @@ def tess_base_args(langs, engine_mode): def get_orientation(input_file, language: list, engine_mode, timeout: float, log): - args_tesseract = tess_base_args(language, engine_mode) + [ + args_tesseract = tess_base_args(['osd'], engine_mode) + [ psm(), '0', input_file, 'stdout'