Compare commits

...
4 Commits
Author SHA1 Message Date
James R. Barlow 474b6b0500 v4.5.5 release notes 2017-04-28 15:27:41 -07:00
James R. Barlow 6c8c1d8173 Fix #154: KeyError ‘/Contents’ on blank pages with /Contents record 2017-04-28 15:22:05 -07:00
James R. Barlow 6a91fa637f Squash merge improvements to auto-homebrewing macOS version 2017-04-28 15:17:38 -07:00
Jakub Wilkandjbarlow83 2846fb4e31 Remove misplaced flags from re.sub() call (#153)
The 4th argument of re.sub() is maximum number of substitutions,
not flags.

Moreover, re.MULTILINE affects only semantics of ^ and $,
so it wouldn't have any effect on this regular expression.
2017-04-20 00:38:23 -07:00
6 changed files with 51 additions and 12 deletions
+1
View File
@@ -6,6 +6,7 @@ pyvenv.cfg
tasks.py
.bash_history
.ruffus_history.sqlite
.idea/
# Package building
*.egg-info/
+27 -11
View File
@@ -24,13 +24,18 @@ matrix:
- os: osx
osx_image: xcode8
language: generic
env:
- secure: "hsf6MT+n2x3OiDM2fQyJZdV0/PWYmv81LdVqC6cfnHBE/8N3DloJRqQ7WfO14TxhiK9PEC7MpyCj0lSabUHEO7gSH6Vks6I1asoSkt8S9/bSMlhT4hei+pwVpeGEiU5xHVATNjY+D919VC3IFvc3XmjT74h/2SLhaZ+jhEmDggM="
before_cache:
- rm -f $HOME/.cache/pip/log/debug.log
before_install:
- if [[ "$TRAVIS_OS_NAME" == "linux" ]]; then bash .travis/linux_before_install.sh ; fi
- if [[ "$TRAVIS_OS_NAME" == "osx" ]]; then bash .travis/osx_before_install.sh ; fi
before_install: |
if [[ "$TRAVIS_OS_NAME" == "linux" ]]; then
bash .travis/linux_before_install.sh
elif [[ "$TRAVIS_OS_NAME" == "osx" ]]; then
bash .travis/osx_before_install.sh
fi
install:
- pip3 install .
@@ -41,20 +46,31 @@ script:
- pytest
- mv dont_import_this_ocrmypdf ocrmypdf
after_success:
- if [[ "$TRAVIS_OS_NAME" == "osx" ]]; then bash .travis/osx_brew.sh ; fi
# See https://www.appneta.com/blog/pypi-deployment-with-travis-ci/ for
# steps to set up testpypi deploy for untagged builds if desired
deploy:
provider: pypi
# release for main pypi
- provider: pypi
user: ocrmypdf-travis
password:
secure: DTFOmmNL6olA0+yXvp4u9jXZlZeqrJsJ0526jzqf4a3gZ6jnGTq5UI6WzRsslSyoMMfXKtHQebqHM6ogSgCZinyZ3ufHJo8fn9brxbEc2gsiWkbj5o3bGwdWMT1vNNE7XW0VCpw87rZ1EEwjl4FJHFudMlPR1yfU5+uq0k0PACo=
secure: "DTFOmmNL6olA0+yXvp4u9jXZlZeqrJsJ0526jzqf4a3gZ6jnGTq5UI6WzRsslSyoMMfXKtHQebqHM6ogSgCZinyZ3ufHJo8fn9brxbEc2gsiWkbj5o3bGwdWMT1vNNE7XW0VCpw87rZ1EEwjl4FJHFudMlPR1yfU5+uq0k0PACo="
distributions: "sdist bdist_wheel"
on:
branch: master
tags: true
condition: $TRAVIS_PYTHON_VERSION == "3.6" && $TRAVIS_OS_NAME == "linux"
skip_upload_docs: true
# test pypi
- provider: pypi
server: https://testpypi.python.org/pypi
user: ocrmypdf-travis
password:
secure: "DTFOmmNL6olA0+yXvp4u9jXZlZeqrJsJ0526jzqf4a3gZ6jnGTq5UI6WzRsslSyoMMfXKtHQebqHM6ogSgCZinyZ3ufHJo8fn9brxbEc2gsiWkbj5o3bGwdWMT1vNNE7XW0VCpw87rZ1EEwjl4FJHFudMlPR1yfU5+uq0k0PACo="
distributions: "sdist"
on:
branch: develop
tags: false
condition: $TRAVIS_OS_NAME == "osx"
skip_upload_docs: true
after_deploy:
- if [[ "$TRAVIS_OS_NAME" == "osx" ]]; then bash .travis/osx_brew.sh ; fi
+12
View File
@@ -6,3 +6,15 @@ pip3 install homebrew-pypi-poet
python3 .travis/autobrew.py
cat ocrmypdf.rb
brew audit ocrmypdf.rb
# Important: disable debug output so token is hidden
set +x
git clone https://$HOMEBREW_OCRMYPDF_TOKEN@github.com/jbarlow83/homebrew-ocrmypdf.git
set -x
pushd homebrew-ocrmypdf
cp ../ocrmypdf.rb Formula/ocrmypdf.rb
git add Formula/ocrmypdf.rb
git commit -m "homebrew-ocrmypdf: automatic release $TRAVIS_BUILD_NUMBER $TRAVIS_TAG"
git push origin master
popd
+7
View File
@@ -4,6 +4,13 @@ Release notes
OCRmyPDF uses `semantic versioning <http://semver.org/>`_.
v4.5.5
------
- Automated update of macOS homebrew tap
- Fixed issue #154, KeyError '/Contents' when searching for text on blank pages that have no /Contents record
v4.5.4
------
+1 -1
View File
@@ -420,7 +420,7 @@ def available_cpu_count():
def cleanup_ruffus_error_message(msg):
msg = re.sub(r'\s+', r' ', msg, re.MULTILINE)
msg = re.sub(r'\s+', r' ', msg)
msg = re.sub(r"\((.+?)\)", r'\1', msg)
msg = msg.strip()
return msg
+3
View File
@@ -464,6 +464,9 @@ def _find_images(pdf, container, shorthand=None):
def _page_has_text(pdf, page):
if not '/Contents' in page:
return False
# Simple test
text = page.extractText()
if text.strip() != '':