v9.1.1 release notes

Smaller download, needed for manylinux2010.

.coveragerc

@@ -0,0 +1,25 @@
+# Coverage isn't really compatible with subprocesses so results are unreliable
+
+[paths]
+source =
+	src
+	*/site-packages
+
+[run]
+branch = true
+parallel = true
+source =
+	src/ocrmypdf
+	tests
+omit =
+	tests/spoof/*
+
+[report]
+exclude_lines =
+	pragma: no cover
+	def __repr__
+	raise AssertionError
+	raise NotImplementedError
+	if 0:
+	if False:
+	if __name__ == .__main__.:

.docker/Dockerfile

@@ -0,0 +1,79 @@
+# OCRmyPDF
+#
+FROM ubuntu:19.10 as base
+
+FROM base as builder
+
+ENV LANG=C.UTF-8
+
+RUN apt-get update && apt-get install -y --no-install-recommends \
+  build-essential autoconf automake libtool \
+  libleptonica-dev \
+  zlib1g-dev \
+  python3 \
+  python3-distutils \
+  ca-certificates \
+  curl \
+  git
+
+# Get the latest pip (Ubuntu version doesn't support manylinux2010)
+RUN \
+  curl https://bootstrap.pypa.io/get-pip.py | python3
+
+# Compile and install jbig2
+# Needs libleptonica-dev, zlib1g-dev
+RUN \
+  mkdir jbig2 \
+  && curl -L https://github.com/agl/jbig2enc/archive/0.29.tar.gz | \
+  tar xz -C jbig2 --strip-components=1 \
+  && cd jbig2 \
+  && ./autogen.sh && ./configure && make && make install \
+  && cd .. \
+  && rm -rf jbig2
+
+COPY . /app
+
+WORKDIR /app
+
+RUN pip3 install --no-cache-dir \
+  -r requirements/main.txt \
+  -r requirements/webservice.txt \
+  -r requirements/test.txt \
+  .
+
+FROM base
+
+ENV LANG=C.UTF-8
+
+RUN apt-get update && apt-get install -y --no-install-recommends \
+  ghostscript \
+  img2pdf \
+  liblept5 \
+  libsm6 libxext6 libxrender-dev \
+  zlib1g \
+  pngquant \
+  python3 \
+  qpdf \
+  tesseract-ocr \
+  tesseract-ocr-chi-sim \
+  tesseract-ocr-deu \
+  tesseract-ocr-eng \
+  tesseract-ocr-fra \
+  tesseract-ocr-por \
+  tesseract-ocr-spa \
+  unpaper
+
+WORKDIR /app
+
+COPY --from=builder /usr/local/lib/ /usr/local/lib/
+COPY --from=builder /usr/local/bin/ /usr/local/bin/
+
+COPY --from=builder /app/misc/webservice.py /app/
+
+# Copy minimal project files to get the test suite.
+COPY --from=builder /app/setup.cfg /app/setup.py /app/README.md /app/
+COPY --from=builder /app/requirements /app/requirements
+COPY --from=builder /app/tests /app/tests
+COPY --from=builder /app/src /app/src
+
+ENTRYPOINT ["/usr/local/bin/ocrmypdf"]

.dockerignore

@@ -3,18 +3,9 @@
 *.pyc
 *.rst
 *.sublime*
-*/*.pyc
-*/*/*.pyc
-*/*/*/*.pyc
-*/*/*/*/*.pyc
-*/*/*/*/*/*.pyc
-*/*/*/*/*/*/*.pyc
-*/*/*/*/*/*/*/*.pyc
-.cache/
-.eggs/
-.github/
-.git/
-.ipynb_checkpoints/
+**/*.pyc
+.*/
+!.git/
 .ruffus_history.sqlite
 bin/
 build/

.gitattributes

@@ -8,6 +8,7 @@
 *.PDF	binary
 *.png	binary
 *.jpg	binary
-
+*.bin   binary
+*.afdesign  binary
 
 .git_archival.txt  export-subst

.github/FUNDING.yml

@@ -0,0 +1,12 @@
+# These are supported funding model platforms
+
+github: # Replace with up to 4 GitHub Sponsors-enabled usernames e.g., [user1, user2]
+patreon: # Replace with a single Patreon username
+open_collective: james-barlow
+ko_fi: # Replace with a single Ko-fi username
+tidelift: # Replace with a single Tidelift platform-name/package-name e.g., npm/babel
+community_bridge: # Replace with a single Community Bridge project-name e.g., cloud-foundry
+liberapay: # Replace with a single Liberapay username
+issuehunt: # Replace with a single IssueHunt username
+otechie: # Replace with a single Otechie username
+custom: # Replace with up to 4 custom sponsorship URLs e.g., ['link1', 'link2']

.github/ISSUE_TEMPLATE

@@ -1,3 +0,0 @@
-Please include the command line and (if needed) a test file with your issue report.
-
-If possible, please use a test file that we can include in future test cases (no personal information, no copyrighted material).

.github/issue_template.md

@@ -0,0 +1,33 @@
+**Describe the issue**
+A clear and concise description of what the issue is.
+
+**To Reproduce**
+What command line were you trying to run?
+
+```bash
+ocrmypdf  ...arguments... input.pdf output.pdf
+```
+
+**Example file**
+Please include an example *input* PDF (or image). The input file is more helpful.
+
+Please check any or all that apply about the test file:
+
+- [ ] This is the input file
+- [ ] The file contains no personal or confidential information
+- [ ] I am the copyright holder for this file
+- [ ] I permit this file to be included in the OCRmyPDF test suite under the CC-BY-SA 4.0 license
+- [ ] I am not the copyright holder, but this file is available under a free software license
+
+Files that are not free for inclusion in this project are quite welcome, but we like to collect free files for our test suite when possible. Please do *not* submit files with confidential information. At your option you may encrypt files for OCRmyPDF's author only.
+
+**Expected behavior**
+A clear and concise description of what you expected to happen. Include screenshots if applicable.
+
+**System:**
+
+- OS: [e.g. Linux, macOS]
+- OCRmyPDF Version: [e.g. v7.4.0]
+
+**Additional context**
+Add any other context about the problem here.

.gitignore

@@ -1,41 +1,46 @@
 # Development environment
+.bash_history
+.pylintrc
+.pytest_cache/
+.ruffus_history.sqlite
+.venv*/
 *.pyc
 *.sublime-*
-venv*/
-pyvenv.cfg
-tasks.py
-.bash_history
-.ruffus_history.sqlite
-.idea/
+*.DS_Store
 
 # Package building
-*.egg-info/
-.cache/
 .eggs/
+*.egg-info/
 build/
 dist/
 wheelhouse/
+pip-wheel-metadata/
 
 # Automatically generated files
-ocrmypdf/lib/_*.py
-ocrmypdf/version.py
 docs/_build/
 docs/_static/
 docs/_templates/
 docs/Makefile
+ocrmypdf/lib/_*.py
 
 # Code coverage
-.coverage
+.coverage*
 htmlcov/
 
 # Testing
-log/
+.ipynb_checkpoints/
+.vscode/
+*.ipynb
+*.profile
 /*.pdf
 /*.qdf
-*.ipynb
-.ipynb_checkpoints/
-tests/cache/
+/*.png
+/scratch.py
+IDEAS
+log/
 tests/output/
 tests/resources/private/
 tmp/
-pdfbox-app*.jar
+/debug_tests.py
+*.traineddata
+/private

.pre-commit-config.yaml

@@ -0,0 +1,6 @@
+repos:
+-   repo: https://github.com/ambv/black
+    rev: stable
+    hooks:
+    - id: black
+      language_version: python3.7

.readthedocs.yml

@@ -0,0 +1,10 @@
+build:
+  image: latest
+
+python:
+  version: 3.6
+
+formats:
+  - pdf
+
+requirements_file: requirements/main.txt

.travis.yml

@@ -1,95 +1,161 @@
-dist: trusty
-language: python
 cache:
   pip: true
   directories:
-  - packages
-  - tests/cache
-  - $HOME/Library/Caches/Homebrew
-
-env:
-  global:
-    - secure: "oyX5xesoHD7qcDXKIxMyGZPi+H/WxcvfFkaviEmq84K1DDyHk48+9e92IKgrw8/lcTADnEo/AgVKfnhCPflFimk1xTkgaK4sUg1WLI2YjmaHcwl5SlBHa2rN3uGBwy1hyP92qyv/mMc9R59NtRJ8u76lbn6eN9wi7lkFWdE6BTw="  # DOCKERHUB_OCRMYPDF_TOKEN
-    - secure: "WlyII8YLsiUUyLtEA563GvEZmbneDb/T8q/P1uNbyQ2ps1U82tH0nSUV2CspSMxOFtZzPHCrRvnAmuTYKshBj+GNnBb1J9FKQmFwF+4NPeqsFdUkQ1NeeCmfIRShuNC3Otg2GGwj4Zssdg+QnVy43t2L11qizzfY+lY+MVzAYcM="  # DOCKERHUB_OCRMYPDF_TESS4_TOKEN
-    - secure: "hsf6MT+n2x3OiDM2fQyJZdV0/PWYmv81LdVqC6cfnHBE/8N3DloJRqQ7WfO14TxhiK9PEC7MpyCj0lSabUHEO7gSH6Vks6I1asoSkt8S9/bSMlhT4hei+pwVpeGEiU5xHVATNjY+D919VC3IFvc3XmjT74h/2SLhaZ+jhEmDggM="  # HOMEBREW_OCRMYPDF_TOKEN
+    - $HOME/Library/Caches/Homebrew
 
 matrix:
   include:
     - os: linux
+      dist: trusty
       sudo: required
       language: python
-      python: 3.5
+      python: "3.6"
+      env:
+        - DIST=trusty
+        - MINIMAL=true
+      addons:
+        apt:
+          update: true
+          sources:
+            - sourceline: "ppa:alex-p/tesseract-ocr"
+            - sourceline: "ppa:vshn/ghostscript"
+          packages:
+            - ghostscript
+            - libffi-dev
+            - qpdf
+            - tesseract-ocr
+            - tesseract-ocr-deu
+            - tesseract-ocr-eng
+            - tesseract-ocr-fra
+      before_install: |
+        pip3 install --upgrade pip
+        pip3 install --upgrade wheel
     - os: linux
+      dist: trusty
       sudo: required
       language: python
-      python: 3.6
+      python: "3.6"
+      env:
+        - DIST=trusty
+      addons:
+        apt:
+          update: true
+          sources:
+            - sourceline: "ppa:alex-p/tesseract-ocr"
+            - sourceline: "ppa:heyarje/libav-11"
+            - sourceline: "ppa:vshn/ghostscript"
+          packages:
+            - ghostscript
+            - libavcodec56
+            - libavformat56
+            - libavutil54
+            - libffi-dev
+            - qpdf
+            - tesseract-ocr
+            - tesseract-ocr-deu
+            - tesseract-ocr-eng
+            - tesseract-ocr-fra
+            - libexempi3 # --- optional extras from here ---
+            - pngquant
+            - poppler-utils
+      before_install: |
+        mkdir -p bin packages
+        pip3 install --upgrade pip
+        pip3 install --upgrade wheel
+    - os: linux
+      dist: xenial
+      sudo: required
+      language: python
+      python: "3.7"
+      env:
+        - DIST=xenial
+      addons:
+        apt:
+          update: true
+          sources:
+            - sourceline: "ppa:alex-p/tesseract-ocr"
+          packages:
+            - ghostscript
+            - libexempi3
+            - libffi-dev
+            - pngquant
+            - poppler-utils
+            - qpdf
+            - tesseract-ocr
+            - tesseract-ocr-deu
+            - tesseract-ocr-eng
+            - tesseract-ocr-fra
+            - unpaper
+    - os: linux
+      dist: bionic
+      sudo: required
+      language: python
+      python: "3.8"
+      env:
+        - DIST=bionic
+      addons:
+        apt:
+          update: true
+          sources:
+            - sourceline: "ppa:alex-p/tesseract-ocr"
+          packages:
+            - ghostscript
+            - libexempi3
+            - libffi-dev
+            - pngquant
+            - poppler-utils
+            - qpdf
+            - tesseract-ocr
+            - tesseract-ocr-deu
+            - tesseract-ocr-eng
+            - tesseract-ocr-fra
+            - unpaper
     - os: osx
-      osx_image: xcode8
       language: generic
+      addons:
+        homebrew:
+          update: true
+          packages:
+            - exempi
+            - ghostscript
+            - jbig2enc
+            - leptonica
+            - openjpeg
+            - pngquant
+            - python
+            - qpdf
+            - tesseract
+            - unpaper
+      before_install: |
+        pip3 install --upgrade pip
+        pip3 install wheel
 
 before_cache:
-- rm -f $HOME/.cache/pip/log/debug.log
-
-before_install: |
-  if [[ "$TRAVIS_OS_NAME" == "linux" ]]; then
-    bash .travis/linux_before_install.sh
-  elif [[ "$TRAVIS_OS_NAME" == "osx" ]]; then
-    bash .travis/osx_before_install.sh
-  fi
+  - rm -f $HOME/.cache/pip/log/debug.log
 
 install:
-- pip3 install .
-- pip3 install -r requirements.txt -r test_requirements.txt
+  - mkdir -p bin
+  - export PATH=$PWD/bin:$PATH
+  - pip3 install -r requirements/main.txt -r requirements/test.txt .
 
 script:
-- mv ocrmypdf dont_import_this_ocrmypdf
-- pytest -n auto
-- mv dont_import_this_ocrmypdf ocrmypdf
+  - tesseract --version
+  - qpdf --version
+  - pytest -n auto
 
 deploy:
   # release for main pypi
-  # 3.6 is considered the build leader and does the deploy, otherwise there is
+  # 3.7 is considered the build leader and does the deploy, otherwise there is
   # a race and all versions will try to deploy
   # OTOH if we ever need separate binary wheels then each version needs its
   # own deploy
-- provider: pypi
-  server: https://upload.pypi.org/legacy/
-  user: ocrmypdf-travis
-  password:
-    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.pypi.org/legacy/
-  user: ocrmypdf-travis
-  password:
-    secure: "DTFOmmNL6olA0+yXvp4u9jXZlZeqrJsJ0526jzqf4a3gZ6jnGTq5UI6WzRsslSyoMMfXKtHQebqHM6ogSgCZinyZ3ufHJo8fn9brxbEc2gsiWkbj5o3bGwdWMT1vNNE7XW0VCpw87rZ1EEwjl4FJHFudMlPR1yfU5+uq0k0PACo="
-  distributions: "sdist"
-  on:
-    branch: develop
-    tags: false
-    condition: $TRAVIS_OS_NAME == "osx"
-  skip_upload_docs: true
-
-  # null deploy for osx
-  # we really just want to run after_deploy *after* pypi upload is done, but
-  # after_deploy on runs if a given box deployed
-- provider: script
-  script: /usr/bin/true
-  on:
-    branch: master
-    condition: $TRAVIS_OS_NAME == "osx"
-
-after_deploy: |
-  if [[ "$TRAVIS_OS_NAME" == "osx" ]]; then
-    bash .travis/osx_brew.sh
-  elif [[ "$TRAVIS_PYTHON_VERSION" == "3.6" && "$TRAVIS_OS_NAME" == "linux" ]]; then
-    curl -H "Content-Type: application/json" --data '{"build": true}' -X POST https://registry.hub.docker.com/u/jbarlow83/ocrmypdf/trigger/$DOCKERHUB_OCRMYPDF_TOKEN/
-    curl -H "Content-Type: application/json" --data '{"build": true}' -X POST https://registry.hub.docker.com/u/jbarlow83/ocrmypdf-tess4/trigger/$DOCKERHUB_OCRMYPDF_TESS4_TOKEN/
-  fi
+  - provider: pypi
+    user: ocrmypdf-travis
+    password:
+      secure: "DTFOmmNL6olA0+yXvp4u9jXZlZeqrJsJ0526jzqf4a3gZ6jnGTq5UI6WzRsslSyoMMfXKtHQebqHM6ogSgCZinyZ3ufHJo8fn9brxbEc2gsiWkbj5o3bGwdWMT1vNNE7XW0VCpw87rZ1EEwjl4FJHFudMlPR1yfU5+uq0k0PACo="
+    distributions: "sdist bdist_wheel"
+    on:
+      branch: master
+      tags: true
+      condition: $TRAVIS_PYTHON_VERSION == "3.7" && $TRAVIS_OS_NAME == "linux"
+    skip_upload_docs: true

.travis/autobrew.py

@@ -1,80 +0,0 @@
-#!/usr/bin/env python3
-# © 2016 James R. Barlow: github.com/jbarlow83
-
-from string import Template
-from subprocess import run, PIPE
-import re
-
-recipe_template = Template("""
-class Ocrmypdf < Formula
-  include Language::Python::Virtualenv
-
-  desc "Adds an OCR text layer to scanned PDF files"
-  homepage "https://github.com/jbarlow83/OCRmyPDF"
-  ${ocrmypdf_url}
-  ${ocrmypdf_sha256}
-
-  depends_on :python3
-  depends_on :x11  # Pillow needs XQuartz
-  depends_on "pkg-config" => :build
-  depends_on "libffi"
-  depends_on "tesseract"
-  depends_on "ghostscript"
-  depends_on "unpaper"
-  depends_on "qpdf"
-
-  # For Pillow source install
-  depends_on "openjpeg"
-  depends_on "freetype"
-  depends_on "libpng"
-  depends_on "libjpeg"
-  depends_on "webp"
-  depends_on "little-cms2"
-
-${resources}
-  def install
-    ENV.append ["SETUPTOOLS_SCM_PRETEND_VERSION"], "v${ocrmypdf_version}"
-    ENV.each do |key, value|
-      puts "#{key}:#{value}"
-    end
-    virtualenv_install_with_resources
-  end
-
-  test do
-    # `test do` will create, run in and delete a temporary directory.
-    #
-    # The installed folder is not in the path, so use the entire path to any
-    # executables being tested: `system "#{bin}/program", "do", "something"`.
-    system "#{bin}/ocrmypdf", "--version"
-  end
-end
-""")
-
-def main():
-    p = run(['poet', '--single', 'ocrmypdf'],
-            encoding='utf-8', stdout=PIPE, check=True)
-
-    ocrmypdf_lines = p.stdout.splitlines()
-    ocrmypdf_url = ocrmypdf_lines[1].strip()
-    ocrmypdf_sha256 = ocrmypdf_lines[2].strip()
-
-    ocrmypdf_version = re.search(
-        r'ocrmypdf-(.+)\.tar.*', ocrmypdf_url).group(1)
-    print(f"Autobrewing {ocrmypdf_version}")
-
-    p = run(['poet', '--resources', 'ocrmypdf'],
-            encoding='utf-8', stdout=PIPE, check=True)
-
-    poet_resources = p.stdout
-
-    # Remove the duplicate "ocrmypdf" resource block
-    all_resources = poet_resources.split('resource')
-    kept_resources = [block for block in all_resources if 'ocrmypdf' not in block]
-    resources = 'resource'.join(kept_resources)
-
-    with open('ocrmypdf.rb', 'w') as out:
-        out.write(recipe_template.substitute(**locals()))
-
-
-if __name__ == '__main__':
-    main()

.travis/linux_before_install.sh

@@ -1,31 +0,0 @@
-#!/bin/bash
-# © 2017 James R. Barlow: github.com/jbarlow83
-set -euo pipefail
-set -x
-
-sudo add-apt-repository ppa:vshn/ghostscript -y
-sudo add-apt-repository ppa:heyarje/libav-11 -y
-sudo apt-get update -qq
-sudo apt-get install -y \
-	ghostscript \
-	qpdf \
-	poppler-utils \
-	libavformat56 \
-	libavcodec56 \
-	libavutil54 \
-	libffi-dev
-
-sudo add-apt-repository ppa:alex-p/tesseract-ocr -y
-
-sudo apt-get update
-sudo apt-get autoremove -y
-sudo apt-get install -y --no-install-recommends \
-		tesseract-ocr \
-		tesseract-ocr-eng \
-		tesseract-ocr-fra \
-		tesseract-ocr-deu
-
-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
-sudo dpkg -i packages/unpaper_6.1-1.deb

.travis/osx_before_install.sh

@@ -1,17 +0,0 @@
-#!/bin/bash
-# © 2017 James R. Barlow: github.com/jbarlow83
-set -euo pipefail
-set -x
-
-brew update
-
-brew install openjpeg jbig2dec libtiff     # image libraries
-brew install qpdf
-brew install ghostscript
-brew install python3
-brew install libxml2 libffi leptonica
-brew install unpaper   # optional
-brew install tesseract
-
-pip3 install --upgrade pip
-pip3 install wheel

.travis/osx_brew.sh

@@ -1,21 +0,0 @@
-#!/bin/bash
-# © 2017 James R. Barlow: github.com/jbarlow83
-set -euo pipefail
-set -x
-
-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

Dockerfile

@@ -1,54 +0,0 @@
-# OCRmyPDF
-#
-# VERSION               4.4.2
-FROM      ubuntu:16.10
-MAINTAINER James R. Barlow <jim@purplerock.ca>
-
-RUN apt-get update && apt-get install -y --no-install-recommends \
-  software-properties-common python-software-properties \
-  python3-wheel \
-  python3-reportlab \
-  python3-venv \
-  ghostscript \
-  qpdf \
-  poppler-utils \
-  unpaper \
-  libffi-dev \ 
-  tesseract-ocr \
-  tesseract-ocr-eng \
-  tesseract-ocr-fra \
-  tesseract-ocr-spa \
-  tesseract-ocr-deu
-
-RUN python3 -m venv --system-site-packages /appenv
-
-# This installs the latest binary wheel instead of the code in the current
-# folder. Installing from source will fail, apparently because cffi needs
-# build-essentials (gcc) to do a source installation 
-# (i.e. "pip install ."). It's unclear to me why this is the case.
-RUN . /appenv/bin/activate; \
-  pip install --upgrade pip \
-  && pip install ocrmypdf
-
-# Now copy the application in, mainly to get the test suite.
-# Do this now to make the best use of Docker cache.
-COPY . /application
-RUN . /appenv/bin/activate; \
-  pip install -r /application/test_requirements.txt
-
-# Remove the junk, including the source version of application since it was
-# already installed
-RUN rm -rf /tmp/* /var/tmp/* /root/* /application/ocrmypdf \
-  && apt-get autoremove -y \
-  && apt-get autoclean -y
-
-RUN useradd docker \
-  && mkdir /home/docker \
-  && chown docker:docker /home/docker
-
-USER docker
-WORKDIR /home/docker
-
-# Must use array form of ENTRYPOINT
-# Non-array form does not append other arguments, because that is "intuitive"
-ENTRYPOINT ["/application/docker-wrapper.sh"]

Dockerfile.polyglot

@@ -1,19 +0,0 @@
-# OCRmyPDF polyglot
-#
-# VERSION               4.4.2
-FROM      jbarlow83/ocrmypdf:latest
-MAINTAINER James R. Barlow <jim@purplerock.ca>
-
-USER root
-
-# Update system and install our dependencies
-RUN apt-get update && apt-get install -y --no-install-recommends \
-  tesseract-ocr-all 
-
-RUN apt-get autoremove -y && apt-get clean -y
-
-USER docker
-
-# Must use array form of ENTRYPOINT
-# Non-array form does not append other arguments, because that is "intuitive"
-ENTRYPOINT ["/application/docker-wrapper.sh"]

Dockerfile.tess4

@@ -1,64 +0,0 @@
-# OCRmyPDF
-#
-# VERSION               4.4.2
-FROM 	ubuntu:16.10
-MAINTAINER James R. Barlow <jim@purplerock.ca>
-
-RUN apt-get update && apt-get install -y --no-install-recommends \
-  software-properties-common python-software-properties \
-  python3-wheel \
-  python3-reportlab \
-  python3-venv \
-  ghostscript \
-  qpdf \
-  poppler-utils \
-  unpaper \
-  libffi-dev
-
-RUN add-apt-repository ppa:alex-p/tesseract-ocr
-
-RUN apt-get update \
-	&& apt-get autoremove -y \
-	&& apt-get install -y --no-install-recommends \
-		tesseract-ocr \
-		tesseract-ocr-eng \
-		tesseract-ocr-fra \
-		tesseract-ocr-deu \
-		tesseract-ocr-spa \
-		tesseract-ocr-por \
-		tesseract-ocr-ara \
-		tesseract-ocr-rus \
-		tesseract-ocr-chi-sim 
-
-RUN python3 -m venv --system-site-packages /appenv
-
-# This installs the latest binary wheel instead of the code in the current
-# folder. Installing from source will fail, apparently because cffi needs
-# build-essentials (gcc) to do a source installation 
-# (i.e. "pip install ."). It's unclear to me why this is the case.
-RUN . /appenv/bin/activate; \
-  pip install --upgrade pip \
-  && pip install ocrmypdf
-
-# Now copy the application in, mainly to get the test suite.
-# Do this now to make the best use of Docker cache.
-COPY . /application
-RUN . /appenv/bin/activate; \
-  pip install -r /application/test_requirements.txt
-
-# Remove the junk, including the source version of application since it was
-# already installed
-RUN rm -rf /tmp/* /var/tmp/* /root/* /application/ocrmypdf \
-  && apt-get autoremove -y \
-  && apt-get autoclean -y
-
-RUN useradd docker \
-  && mkdir /home/docker \
-  && chown docker:docker /home/docker
-
-USER docker
-WORKDIR /home/docker
-
-# Must use array form of ENTRYPOINT
-# Non-array form does not append other arguments, because that is "intuitive"
-ENTRYPOINT ["/application/docker-wrapper.sh"]

LICENSE

@@ -0,0 +1,674 @@
+                    GNU GENERAL PUBLIC LICENSE
+                       Version 3, 29 June 2007
+
+ Copyright (C) 2007 Free Software Foundation, Inc. <https://fsf.org/>
+ Everyone is permitted to copy and distribute verbatim copies
+ of this license document, but changing it is not allowed.
+
+                            Preamble
+
+  The GNU General Public License is a free, copyleft license for
+software and other kinds of works.
+
+  The licenses for most software and other practical works are designed
+to take away your freedom to share and change the works.  By contrast,
+the GNU General Public License is intended to guarantee your freedom to
+share and change all versions of a program--to make sure it remains free
+software for all its users.  We, the Free Software Foundation, use the
+GNU General Public License for most of our software; it applies also to
+any other work released this way by its authors.  You can apply it to
+your programs, too.
+
+  When we speak of free software, we are referring to freedom, not
+price.  Our General Public Licenses are designed to make sure that you
+have the freedom to distribute copies of free software (and charge for
+them if you wish), that you receive source code or can get it if you
+want it, that you can change the software or use pieces of it in new
+free programs, and that you know you can do these things.
+
+  To protect your rights, we need to prevent others from denying you
+these rights or asking you to surrender the rights.  Therefore, you have
+certain responsibilities if you distribute copies of the software, or if
+you modify it: responsibilities to respect the freedom of others.
+
+  For example, if you distribute copies of such a program, whether
+gratis or for a fee, you must pass on to the recipients the same
+freedoms that you received.  You must make sure that they, too, receive
+or can get the source code.  And you must show them these terms so they
+know their rights.
+
+  Developers that use the GNU GPL protect your rights with two steps:
+(1) assert copyright on the software, and (2) offer you this License
+giving you legal permission to copy, distribute and/or modify it.
+
+  For the developers' and authors' protection, the GPL clearly explains
+that there is no warranty for this free software.  For both users' and
+authors' sake, the GPL requires that modified versions be marked as
+changed, so that their problems will not be attributed erroneously to
+authors of previous versions.
+
+  Some devices are designed to deny users access to install or run
+modified versions of the software inside them, although the manufacturer
+can do so.  This is fundamentally incompatible with the aim of
+protecting users' freedom to change the software.  The systematic
+pattern of such abuse occurs in the area of products for individuals to
+use, which is precisely where it is most unacceptable.  Therefore, we
+have designed this version of the GPL to prohibit the practice for those
+products.  If such problems arise substantially in other domains, we
+stand ready to extend this provision to those domains in future versions
+of the GPL, as needed to protect the freedom of users.
+
+  Finally, every program is threatened constantly by software patents.
+States should not allow patents to restrict development and use of
+software on general-purpose computers, but in those that do, we wish to
+avoid the special danger that patents applied to a free program could
+make it effectively proprietary.  To prevent this, the GPL assures that
+patents cannot be used to render the program non-free.
+
+  The precise terms and conditions for copying, distribution and
+modification follow.
+
+                       TERMS AND CONDITIONS
+
+  0. Definitions.
+
+  "This License" refers to version 3 of the GNU General Public License.
+
+  "Copyright" also means copyright-like laws that apply to other kinds of
+works, such as semiconductor masks.
+
+  "The Program" refers to any copyrightable work licensed under this
+License.  Each licensee is addressed as "you".  "Licensees" and
+"recipients" may be individuals or organizations.
+
+  To "modify" a work means to copy from or adapt all or part of the work
+in a fashion requiring copyright permission, other than the making of an
+exact copy.  The resulting work is called a "modified version" of the
+earlier work or a work "based on" the earlier work.
+
+  A "covered work" means either the unmodified Program or a work based
+on the Program.
+
+  To "propagate" a work means to do anything with it that, without
+permission, would make you directly or secondarily liable for
+infringement under applicable copyright law, except executing it on a
+computer or modifying a private copy.  Propagation includes copying,
+distribution (with or without modification), making available to the
+public, and in some countries other activities as well.
+
+  To "convey" a work means any kind of propagation that enables other
+parties to make or receive copies.  Mere interaction with a user through
+a computer network, with no transfer of a copy, is not conveying.
+
+  An interactive user interface displays "Appropriate Legal Notices"
+to the extent that it includes a convenient and prominently visible
+feature that (1) displays an appropriate copyright notice, and (2)
+tells the user that there is no warranty for the work (except to the
+extent that warranties are provided), that licensees may convey the
+work under this License, and how to view a copy of this License.  If
+the interface presents a list of user commands or options, such as a
+menu, a prominent item in the list meets this criterion.
+
+  1. Source Code.
+
+  The "source code" for a work means the preferred form of the work
+for making modifications to it.  "Object code" means any non-source
+form of a work.
+
+  A "Standard Interface" means an interface that either is an official
+standard defined by a recognized standards body, or, in the case of
+interfaces specified for a particular programming language, one that
+is widely used among developers working in that language.
+
+  The "System Libraries" of an executable work include anything, other
+than the work as a whole, that (a) is included in the normal form of
+packaging a Major Component, but which is not part of that Major
+Component, and (b) serves only to enable use of the work with that
+Major Component, or to implement a Standard Interface for which an
+implementation is available to the public in source code form.  A
+"Major Component", in this context, means a major essential component
+(kernel, window system, and so on) of the specific operating system
+(if any) on which the executable work runs, or a compiler used to
+produce the work, or an object code interpreter used to run it.
+
+  The "Corresponding Source" for a work in object code form means all
+the source code needed to generate, install, and (for an executable
+work) run the object code and to modify the work, including scripts to
+control those activities.  However, it does not include the work's
+System Libraries, or general-purpose tools or generally available free
+programs which are used unmodified in performing those activities but
+which are not part of the work.  For example, Corresponding Source
+includes interface definition files associated with source files for
+the work, and the source code for shared libraries and dynamically
+linked subprograms that the work is specifically designed to require,
+such as by intimate data communication or control flow between those
+subprograms and other parts of the work.
+
+  The Corresponding Source need not include anything that users
+can regenerate automatically from other parts of the Corresponding
+Source.
+
+  The Corresponding Source for a work in source code form is that
+same work.
+
+  2. Basic Permissions.
+
+  All rights granted under this License are granted for the term of
+copyright on the Program, and are irrevocable provided the stated
+conditions are met.  This License explicitly affirms your unlimited
+permission to run the unmodified Program.  The output from running a
+covered work is covered by this License only if the output, given its
+content, constitutes a covered work.  This License acknowledges your
+rights of fair use or other equivalent, as provided by copyright law.
+
+  You may make, run and propagate covered works that you do not
+convey, without conditions so long as your license otherwise remains
+in force.  You may convey covered works to others for the sole purpose
+of having them make modifications exclusively for you, or provide you
+with facilities for running those works, provided that you comply with
+the terms of this License in conveying all material for which you do
+not control copyright.  Those thus making or running the covered works
+for you must do so exclusively on your behalf, under your direction
+and control, on terms that prohibit them from making any copies of
+your copyrighted material outside their relationship with you.
+
+  Conveying under any other circumstances is permitted solely under
+the conditions stated below.  Sublicensing is not allowed; section 10
+makes it unnecessary.
+
+  3. Protecting Users' Legal Rights From Anti-Circumvention Law.
+
+  No covered work shall be deemed part of an effective technological
+measure under any applicable law fulfilling obligations under article
+11 of the WIPO copyright treaty adopted on 20 December 1996, or
+similar laws prohibiting or restricting circumvention of such
+measures.
+
+  When you convey a covered work, you waive any legal power to forbid
+circumvention of technological measures to the extent such circumvention
+is effected by exercising rights under this License with respect to
+the covered work, and you disclaim any intention to limit operation or
+modification of the work as a means of enforcing, against the work's
+users, your or third parties' legal rights to forbid circumvention of
+technological measures.
+
+  4. Conveying Verbatim Copies.
+
+  You may convey verbatim copies of the Program's source code as you
+receive it, in any medium, provided that you conspicuously and
+appropriately publish on each copy an appropriate copyright notice;
+keep intact all notices stating that this License and any
+non-permissive terms added in accord with section 7 apply to the code;
+keep intact all notices of the absence of any warranty; and give all
+recipients a copy of this License along with the Program.
+
+  You may charge any price or no price for each copy that you convey,
+and you may offer support or warranty protection for a fee.
+
+  5. Conveying Modified Source Versions.
+
+  You may convey a work based on the Program, or the modifications to
+produce it from the Program, in the form of source code under the
+terms of section 4, provided that you also meet all of these conditions:
+
+    a) The work must carry prominent notices stating that you modified
+    it, and giving a relevant date.
+
+    b) The work must carry prominent notices stating that it is
+    released under this License and any conditions added under section
+    7.  This requirement modifies the requirement in section 4 to
+    "keep intact all notices".
+
+    c) You must license the entire work, as a whole, under this
+    License to anyone who comes into possession of a copy.  This
+    License will therefore apply, along with any applicable section 7
+    additional terms, to the whole of the work, and all its parts,
+    regardless of how they are packaged.  This License gives no
+    permission to license the work in any other way, but it does not
+    invalidate such permission if you have separately received it.
+
+    d) If the work has interactive user interfaces, each must display
+    Appropriate Legal Notices; however, if the Program has interactive
+    interfaces that do not display Appropriate Legal Notices, your
+    work need not make them do so.
+
+  A compilation of a covered work with other separate and independent
+works, which are not by their nature extensions of the covered work,
+and which are not combined with it such as to form a larger program,
+in or on a volume of a storage or distribution medium, is called an
+"aggregate" if the compilation and its resulting copyright are not
+used to limit the access or legal rights of the compilation's users
+beyond what the individual works permit.  Inclusion of a covered work
+in an aggregate does not cause this License to apply to the other
+parts of the aggregate.
+
+  6. Conveying Non-Source Forms.
+
+  You may convey a covered work in object code form under the terms
+of sections 4 and 5, provided that you also convey the
+machine-readable Corresponding Source under the terms of this License,
+in one of these ways:
+
+    a) Convey the object code in, or embodied in, a physical product
+    (including a physical distribution medium), accompanied by the
+    Corresponding Source fixed on a durable physical medium
+    customarily used for software interchange.
+
+    b) Convey the object code in, or embodied in, a physical product
+    (including a physical distribution medium), accompanied by a
+    written offer, valid for at least three years and valid for as
+    long as you offer spare parts or customer support for that product
+    model, to give anyone who possesses the object code either (1) a
+    copy of the Corresponding Source for all the software in the
+    product that is covered by this License, on a durable physical
+    medium customarily used for software interchange, for a price no
+    more than your reasonable cost of physically performing this
+    conveying of source, or (2) access to copy the
+    Corresponding Source from a network server at no charge.
+
+    c) Convey individual copies of the object code with a copy of the
+    written offer to provide the Corresponding Source.  This
+    alternative is allowed only occasionally and noncommercially, and
+    only if you received the object code with such an offer, in accord
+    with subsection 6b.
+
+    d) Convey the object code by offering access from a designated
+    place (gratis or for a charge), and offer equivalent access to the
+    Corresponding Source in the same way through the same place at no
+    further charge.  You need not require recipients to copy the
+    Corresponding Source along with the object code.  If the place to
+    copy the object code is a network server, the Corresponding Source
+    may be on a different server (operated by you or a third party)
+    that supports equivalent copying facilities, provided you maintain
+    clear directions next to the object code saying where to find the
+    Corresponding Source.  Regardless of what server hosts the
+    Corresponding Source, you remain obligated to ensure that it is
+    available for as long as needed to satisfy these requirements.
+
+    e) Convey the object code using peer-to-peer transmission, provided
+    you inform other peers where the object code and Corresponding
+    Source of the work are being offered to the general public at no
+    charge under subsection 6d.
+
+  A separable portion of the object code, whose source code is excluded
+from the Corresponding Source as a System Library, need not be
+included in conveying the object code work.
+
+  A "User Product" is either (1) a "consumer product", which means any
+tangible personal property which is normally used for personal, family,
+or household purposes, or (2) anything designed or sold for incorporation
+into a dwelling.  In determining whether a product is a consumer product,
+doubtful cases shall be resolved in favor of coverage.  For a particular
+product received by a particular user, "normally used" refers to a
+typical or common use of that class of product, regardless of the status
+of the particular user or of the way in which the particular user
+actually uses, or expects or is expected to use, the product.  A product
+is a consumer product regardless of whether the product has substantial
+commercial, industrial or non-consumer uses, unless such uses represent
+the only significant mode of use of the product.
+
+  "Installation Information" for a User Product means any methods,
+procedures, authorization keys, or other information required to install
+and execute modified versions of a covered work in that User Product from
+a modified version of its Corresponding Source.  The information must
+suffice to ensure that the continued functioning of the modified object
+code is in no case prevented or interfered with solely because
+modification has been made.
+
+  If you convey an object code work under this section in, or with, or
+specifically for use in, a User Product, and the conveying occurs as
+part of a transaction in which the right of possession and use of the
+User Product is transferred to the recipient in perpetuity or for a
+fixed term (regardless of how the transaction is characterized), the
+Corresponding Source conveyed under this section must be accompanied
+by the Installation Information.  But this requirement does not apply
+if neither you nor any third party retains the ability to install
+modified object code on the User Product (for example, the work has
+been installed in ROM).
+
+  The requirement to provide Installation Information does not include a
+requirement to continue to provide support service, warranty, or updates
+for a work that has been modified or installed by the recipient, or for
+the User Product in which it has been modified or installed.  Access to a
+network may be denied when the modification itself materially and
+adversely affects the operation of the network or violates the rules and
+protocols for communication across the network.
+
+  Corresponding Source conveyed, and Installation Information provided,
+in accord with this section must be in a format that is publicly
+documented (and with an implementation available to the public in
+source code form), and must require no special password or key for
+unpacking, reading or copying.
+
+  7. Additional Terms.
+
+  "Additional permissions" are terms that supplement the terms of this
+License by making exceptions from one or more of its conditions.
+Additional permissions that are applicable to the entire Program shall
+be treated as though they were included in this License, to the extent
+that they are valid under applicable law.  If additional permissions
+apply only to part of the Program, that part may be used separately
+under those permissions, but the entire Program remains governed by
+this License without regard to the additional permissions.
+
+  When you convey a copy of a covered work, you may at your option
+remove any additional permissions from that copy, or from any part of
+it.  (Additional permissions may be written to require their own
+removal in certain cases when you modify the work.)  You may place
+additional permissions on material, added by you to a covered work,
+for which you have or can give appropriate copyright permission.
+
+  Notwithstanding any other provision of this License, for material you
+add to a covered work, you may (if authorized by the copyright holders of
+that material) supplement the terms of this License with terms:
+
+    a) Disclaiming warranty or limiting liability differently from the
+    terms of sections 15 and 16 of this License; or
+
+    b) Requiring preservation of specified reasonable legal notices or
+    author attributions in that material or in the Appropriate Legal
+    Notices displayed by works containing it; or
+
+    c) Prohibiting misrepresentation of the origin of that material, or
+    requiring that modified versions of such material be marked in
+    reasonable ways as different from the original version; or
+
+    d) Limiting the use for publicity purposes of names of licensors or
+    authors of the material; or
+
+    e) Declining to grant rights under trademark law for use of some
+    trade names, trademarks, or service marks; or
+
+    f) Requiring indemnification of licensors and authors of that
+    material by anyone who conveys the material (or modified versions of
+    it) with contractual assumptions of liability to the recipient, for
+    any liability that these contractual assumptions directly impose on
+    those licensors and authors.
+
+  All other non-permissive additional terms are considered "further
+restrictions" within the meaning of section 10.  If the Program as you
+received it, or any part of it, contains a notice stating that it is
+governed by this License along with a term that is a further
+restriction, you may remove that term.  If a license document contains
+a further restriction but permits relicensing or conveying under this
+License, you may add to a covered work material governed by the terms
+of that license document, provided that the further restriction does
+not survive such relicensing or conveying.
+
+  If you add terms to a covered work in accord with this section, you
+must place, in the relevant source files, a statement of the
+additional terms that apply to those files, or a notice indicating
+where to find the applicable terms.
+
+  Additional terms, permissive or non-permissive, may be stated in the
+form of a separately written license, or stated as exceptions;
+the above requirements apply either way.
+
+  8. Termination.
+
+  You may not propagate or modify a covered work except as expressly
+provided under this License.  Any attempt otherwise to propagate or
+modify it is void, and will automatically terminate your rights under
+this License (including any patent licenses granted under the third
+paragraph of section 11).
+
+  However, if you cease all violation of this License, then your
+license from a particular copyright holder is reinstated (a)
+provisionally, unless and until the copyright holder explicitly and
+finally terminates your license, and (b) permanently, if the copyright
+holder fails to notify you of the violation by some reasonable means
+prior to 60 days after the cessation.
+
+  Moreover, your license from a particular copyright holder is
+reinstated permanently if the copyright holder notifies you of the
+violation by some reasonable means, this is the first time you have
+received notice of violation of this License (for any work) from that
+copyright holder, and you cure the violation prior to 30 days after
+your receipt of the notice.
+
+  Termination of your rights under this section does not terminate the
+licenses of parties who have received copies or rights from you under
+this License.  If your rights have been terminated and not permanently
+reinstated, you do not qualify to receive new licenses for the same
+material under section 10.
+
+  9. Acceptance Not Required for Having Copies.
+
+  You are not required to accept this License in order to receive or
+run a copy of the Program.  Ancillary propagation of a covered work
+occurring solely as a consequence of using peer-to-peer transmission
+to receive a copy likewise does not require acceptance.  However,
+nothing other than this License grants you permission to propagate or
+modify any covered work.  These actions infringe copyright if you do
+not accept this License.  Therefore, by modifying or propagating a
+covered work, you indicate your acceptance of this License to do so.
+
+  10. Automatic Licensing of Downstream Recipients.
+
+  Each time you convey a covered work, the recipient automatically
+receives a license from the original licensors, to run, modify and
+propagate that work, subject to this License.  You are not responsible
+for enforcing compliance by third parties with this License.
+
+  An "entity transaction" is a transaction transferring control of an
+organization, or substantially all assets of one, or subdividing an
+organization, or merging organizations.  If propagation of a covered
+work results from an entity transaction, each party to that
+transaction who receives a copy of the work also receives whatever
+licenses to the work the party's predecessor in interest had or could
+give under the previous paragraph, plus a right to possession of the
+Corresponding Source of the work from the predecessor in interest, if
+the predecessor has it or can get it with reasonable efforts.
+
+  You may not impose any further restrictions on the exercise of the
+rights granted or affirmed under this License.  For example, you may
+not impose a license fee, royalty, or other charge for exercise of
+rights granted under this License, and you may not initiate litigation
+(including a cross-claim or counterclaim in a lawsuit) alleging that
+any patent claim is infringed by making, using, selling, offering for
+sale, or importing the Program or any portion of it.
+
+  11. Patents.
+
+  A "contributor" is a copyright holder who authorizes use under this
+License of the Program or a work on which the Program is based.  The
+work thus licensed is called the contributor's "contributor version".
+
+  A contributor's "essential patent claims" are all patent claims
+owned or controlled by the contributor, whether already acquired or
+hereafter acquired, that would be infringed by some manner, permitted
+by this License, of making, using, or selling its contributor version,
+but do not include claims that would be infringed only as a
+consequence of further modification of the contributor version.  For
+purposes of this definition, "control" includes the right to grant
+patent sublicenses in a manner consistent with the requirements of
+this License.
+
+  Each contributor grants you a non-exclusive, worldwide, royalty-free
+patent license under the contributor's essential patent claims, to
+make, use, sell, offer for sale, import and otherwise run, modify and
+propagate the contents of its contributor version.
+
+  In the following three paragraphs, a "patent license" is any express
+agreement or commitment, however denominated, not to enforce a patent
+(such as an express permission to practice a patent or covenant not to
+sue for patent infringement).  To "grant" such a patent license to a
+party means to make such an agreement or commitment not to enforce a
+patent against the party.
+
+  If you convey a covered work, knowingly relying on a patent license,
+and the Corresponding Source of the work is not available for anyone
+to copy, free of charge and under the terms of this License, through a
+publicly available network server or other readily accessible means,
+then you must either (1) cause the Corresponding Source to be so
+available, or (2) arrange to deprive yourself of the benefit of the
+patent license for this particular work, or (3) arrange, in a manner
+consistent with the requirements of this License, to extend the patent
+license to downstream recipients.  "Knowingly relying" means you have
+actual knowledge that, but for the patent license, your conveying the
+covered work in a country, or your recipient's use of the covered work
+in a country, would infringe one or more identifiable patents in that
+country that you have reason to believe are valid.
+
+  If, pursuant to or in connection with a single transaction or
+arrangement, you convey, or propagate by procuring conveyance of, a
+covered work, and grant a patent license to some of the parties
+receiving the covered work authorizing them to use, propagate, modify
+or convey a specific copy of the covered work, then the patent license
+you grant is automatically extended to all recipients of the covered
+work and works based on it.
+
+  A patent license is "discriminatory" if it does not include within
+the scope of its coverage, prohibits the exercise of, or is
+conditioned on the non-exercise of one or more of the rights that are
+specifically granted under this License.  You may not convey a covered
+work if you are a party to an arrangement with a third party that is
+in the business of distributing software, under which you make payment
+to the third party based on the extent of your activity of conveying
+the work, and under which the third party grants, to any of the
+parties who would receive the covered work from you, a discriminatory
+patent license (a) in connection with copies of the covered work
+conveyed by you (or copies made from those copies), or (b) primarily
+for and in connection with specific products or compilations that
+contain the covered work, unless you entered into that arrangement,
+or that patent license was granted, prior to 28 March 2007.
+
+  Nothing in this License shall be construed as excluding or limiting
+any implied license or other defenses to infringement that may
+otherwise be available to you under applicable patent law.
+
+  12. No Surrender of Others' Freedom.
+
+  If conditions are imposed on you (whether by court order, agreement or
+otherwise) that contradict the conditions of this License, they do not
+excuse you from the conditions of this License.  If you cannot convey a
+covered work so as to satisfy simultaneously your obligations under this
+License and any other pertinent obligations, then as a consequence you may
+not convey it at all.  For example, if you agree to terms that obligate you
+to collect a royalty for further conveying from those to whom you convey
+the Program, the only way you could satisfy both those terms and this
+License would be to refrain entirely from conveying the Program.
+
+  13. Use with the GNU Affero General Public License.
+
+  Notwithstanding any other provision of this License, you have
+permission to link or combine any covered work with a work licensed
+under version 3 of the GNU Affero General Public License into a single
+combined work, and to convey the resulting work.  The terms of this
+License will continue to apply to the part which is the covered work,
+but the special requirements of the GNU Affero General Public License,
+section 13, concerning interaction through a network will apply to the
+combination as such.
+
+  14. Revised Versions of this License.
+
+  The Free Software Foundation may publish revised and/or new versions of
+the GNU General Public License from time to time.  Such new versions will
+be similar in spirit to the present version, but may differ in detail to
+address new problems or concerns.
+
+  Each version is given a distinguishing version number.  If the
+Program specifies that a certain numbered version of the GNU General
+Public License "or any later version" applies to it, you have the
+option of following the terms and conditions either of that numbered
+version or of any later version published by the Free Software
+Foundation.  If the Program does not specify a version number of the
+GNU General Public License, you may choose any version ever published
+by the Free Software Foundation.
+
+  If the Program specifies that a proxy can decide which future
+versions of the GNU General Public License can be used, that proxy's
+public statement of acceptance of a version permanently authorizes you
+to choose that version for the Program.
+
+  Later license versions may give you additional or different
+permissions.  However, no additional obligations are imposed on any
+author or copyright holder as a result of your choosing to follow a
+later version.
+
+  15. Disclaimer of Warranty.
+
+  THERE IS NO WARRANTY FOR THE PROGRAM, TO THE EXTENT PERMITTED BY
+APPLICABLE LAW.  EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT
+HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY
+OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO,
+THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
+PURPOSE.  THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE PROGRAM
+IS WITH YOU.  SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF
+ALL NECESSARY SERVICING, REPAIR OR CORRECTION.
+
+  16. Limitation of Liability.
+
+  IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING
+WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MODIFIES AND/OR CONVEYS
+THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES, INCLUDING ANY
+GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING OUT OF THE
+USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED TO LOSS OF
+DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD
+PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER PROGRAMS),
+EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF
+SUCH DAMAGES.
+
+  17. Interpretation of Sections 15 and 16.
+
+  If the disclaimer of warranty and limitation of liability provided
+above cannot be given local legal effect according to their terms,
+reviewing courts shall apply local law that most closely approximates
+an absolute waiver of all civil liability in connection with the
+Program, unless a warranty or assumption of liability accompanies a
+copy of the Program in return for a fee.
+
+                     END OF TERMS AND CONDITIONS
+
+            How to Apply These Terms to Your New Programs
+
+  If you develop a new program, and you want it to be of the greatest
+possible use to the public, the best way to achieve this is to make it
+free software which everyone can redistribute and change under these terms.
+
+  To do so, attach the following notices to the program.  It is safest
+to attach them to the start of each source file to most effectively
+state the exclusion of warranty; and each file should have at least
+the "copyright" line and a pointer to where the full notice is found.
+
+    <one line to give the program's name and a brief idea of what it does.>
+    Copyright (C) <year>  <name of author>
+
+    This program is free software: you can redistribute it and/or modify
+    it under the terms of the GNU General Public License as published by
+    the Free Software Foundation, either version 3 of the License, or
+    (at your option) any later version.
+
+    This program is distributed in the hope that it will be useful,
+    but WITHOUT ANY WARRANTY; without even the implied warranty of
+    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+    GNU General Public License for more details.
+
+    You should have received a copy of the GNU General Public License
+    along with this program.  If not, see <https://www.gnu.org/licenses/>.
+
+Also add information on how to contact you by electronic and paper mail.
+
+  If the program does terminal interaction, make it output a short
+notice like this when it starts in an interactive mode:
+
+    <program>  Copyright (C) <year>  <name of author>
+    This program comes with ABSOLUTELY NO WARRANTY; for details type `show w'.
+    This is free software, and you are welcome to redistribute it
+    under certain conditions; type `show c' for details.
+
+The hypothetical commands `show w' and `show c' should show the appropriate
+parts of the General Public License.  Of course, your program's commands
+might be different; for a GUI interface, you would use an "about box".
+
+  You should also get your employer (if you work as a programmer) or school,
+if any, to sign a "copyright disclaimer" for the program, if necessary.
+For more information on this, and how to apply and follow the GNU GPL, see
+<https://www.gnu.org/licenses/>.
+
+  The GNU General Public License does not permit incorporating your program
+into proprietary programs.  If your program is a subroutine library, you
+may consider it more useful to permit linking proprietary applications with
+the library.  If this is what you want to do, use the GNU Lesser General
+Public License instead of this License.  But first, please read
+<https://www.gnu.org/licenses/why-not-lgpl.html>.

LICENSE.rst

@@ -1,20 +0,0 @@
-Copyright (c) 2013-2016, The OCRmyPDF Authors
-
-Permission is hereby granted, free of charge, to any person obtaining a
-copy of this software and associated documentation files (the
-"Software"), to deal in the Software without restriction, including
-without limitation the rights to use, copy, modify, merge, publish,
-distribute, sublicense, and/or sell copies of the Software, and to
-permit persons to whom the Software is furnished to do so, subject to
-the following conditions:
-
-The above copyright notice and this permission notice shall be included
-in all copies or substantial portions of the Software.
-
-THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS
-OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
-MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
-IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY
-CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT,
-TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE
-SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

MANIFEST.in

@@ -1,48 +0,0 @@
-# requirements
-include requirements.txt
-include test_requirements.txt
-include dev_requirements.txt
-
-# git
-include .git_archival.txt
-
-# docker
-include Dockerfile
-include Dockerfile.polyglot
-include .dockerignore
-
-# tests
-include pytest.ini
-recursive-include tests *.jpg
-recursive-include tests *.png
-recursive-include tests *.pdf
-recursive-include tests *.py
-recursive-include tests *.rst
-recursive-include tests *.txt
-recursive-exclude tests/output *
-recursive-exclude tests/output_pageinfo *
-recursive-exclude tests/resources/private *
-recursive-exclude tests/cache *
-
-# documentation
-include *.rst
-include pipeline.svg
-recursive-exclude .github * 
-recursive-include docs *.py
-recursive-include docs *.rst
-recursive-include docs *.svg
-recursive-exclude docs/_build *
-
-
-# support files
-recursive-include ocrmypdf/data *
-include *.py
-exclude tasks.py
-
-# code
-recursive-include ocrmypdf *.py
-exclude ocrmypdf/lib/_leptonica.py
-include OCRmyPDF.sh
-include docker-wrapper.sh
-
-

README.md

@@ -0,0 +1,152 @@
+<img src="docs/images/logo.svg" width="240" alt="OCRmyPDF">
+
+[![Travis build status][travis]](https://travis-ci.org/jbarlow83/OCRmyPDF) [![PyPI version][pypi]](https://pypi.org/project/ocrmypdf/) ![Homebrew version][homebrew] ![ReadTheDocs][docs] ![Python versions][pyversions]
+
+[travis]: https://travis-ci.org/jbarlow83/OCRmyPDF.svg?branch=master "Travis build status"
+
+[pypi]: https://img.shields.io/pypi/v/ocrmypdf.svg "PyPI version"
+
+[homebrew]: https://img.shields.io/homebrew/v/ocrmypdf.svg "Homebrew version"
+
+[docs]: https://readthedocs.org/projects/ocrmypdf/badge/?version=latest "RTD"
+
+[pyversions]: https://img.shields.io/pypi/pyversions/ocrmypdf "Supported Python versions"
+
+OCRmyPDF adds an OCR text layer to scanned PDF files, allowing them to be searched or copy-pasted.
+
+```bash
+ocrmypdf                      # it's a scriptable command line program
+   -l eng+fra                 # it supports multiple languages
+   --rotate-pages             # it can fix pages that are misrotated
+   --deskew                   # it can deskew crooked PDFs!
+   --title "My PDF"           # it can change output metadata
+   --jobs 4                   # it uses multiple cores by default
+   --output-type pdfa         # it produces PDF/A by default
+   input_scanned.pdf          # takes PDF input (or images)
+   output_searchable.pdf      # produces validated PDF output
+```
+
+[See the release notes for details on the latest changes](https://ocrmypdf.readthedocs.io/en/latest/release_notes.html).
+
+Main features
+-------------
+
+- Generates a searchable [PDF/A](https://en.wikipedia.org/?title=PDF/A) file from a regular PDF
+- Places OCR text accurately below the image to ease copy / paste
+- Keeps the exact resolution of the original embedded images
+- When possible, inserts OCR information as a "lossless" operation without disrupting any other content
+- Optimizes PDF images, often producing files smaller than the input file
+- If requested deskews and/or cleans the image before performing OCR
+- Validates input and output files
+- Distributes work across all available CPU cores
+- Uses [Tesseract OCR](https://github.com/tesseract-ocr/tesseract) engine to recognize more than [100 languages](https://github.com/tesseract-ocr/tessdata)
+- Scales properly to handle files with thousands of pages
+- Battle-tested on millions of PDFs
+
+For details: please consult the [documentation](https://ocrmypdf.readthedocs.io/en/latest/).
+
+Motivation
+----------
+
+I searched the web for a free command line tool to OCR PDF files on Linux/UNIX: I found many, but none of them were really satisfying.
+
+- Either they produced PDF files with misplaced text under the image (making copy/paste impossible)
+- Or they did not handle accents and multilingual characters
+- Or they changed the resolution of the embedded images
+- Or they generated ridiculously large PDF files
+- Or they crashed when trying to OCR
+- Or they did not produce valid PDF files
+- On top of that none of them produced PDF/A files (format dedicated for long time storage)
+
+...so I decided to develop my own tool.
+
+Installation
+------------
+
+Linux, UNIX, and macOS are supported. Windows is not directly supported but there is a Docker image available that runs on Windows.
+
+Users of Debian 9 or later or Ubuntu 16.10 or later may simply
+
+```bash
+apt-get install ocrmypdf
+```
+
+and users of Fedora 29 or later may simply
+
+```bash
+dnf install ocrmypdf
+```
+
+and macOS users with Homebrew may simply
+
+```bash
+brew install ocrmypdf
+```
+
+For everyone else, [see our documentation](https://ocrmypdf.readthedocs.io/en/latest/installation.html) for installation steps.
+
+Languages
+---------
+
+OCRmyPDF uses Tesseract for OCR, and relies on its language packs. For Linux users, you can often find packages that provide language packs:
+
+```bash
+# Display a list of all Tesseract language packs
+apt-cache search tesseract-ocr
+
+# Debian/Ubuntu users
+apt-get install tesseract-ocr-chi-sim  # Example: Install Chinese Simplified language back
+```
+
+You can then pass the `-l LANG` argument to OCRmyPDF to give a hint as to what languages it should search for. Multiple languages can be requested.
+
+Documentation and support
+-------------------------
+
+Once ocrmypdf is installed, the built-in help which explains the command syntax and options can be accessed via:
+
+```bash
+ocrmypdf --help
+```
+
+Our [documentation is served on Read the Docs](https://ocrmypdf.readthedocs.io/en/latest/index.html).
+
+If you detect an issue, please:
+
+- Check whether your issue is already known
+- If no problem report exists on github, please create one here: <https://github.com/jbarlow83/OCRmyPDF/issues>
+- Describe your problem thoroughly
+- Append the console output of the script when running the debug mode (`-v 1` option)
+- If possible provide your input PDF file as well as the content of the temporary folder (using a file sharing service like Dropbox)
+
+Requirements
+------------
+
+In addition to the required Python version (3.6+), OCRmyPDF requires external program installations of Ghostscript, Tesseract OCR, QPDF, and Leptonica. ocrmypdf is pure Python, but uses CFFI to portably generate library bindings.
+
+Press & Media
+-------------
+
+- [Going paperless with OCRmyPDF](https://medium.com/@ikirichenko/going-paperless-with-ocrmypdf-e2f36143f46a)
+- [Converting a scanned document into a compressed searchable PDF with redactions](https://medium.com/@treyharris/converting-a-scanned-document-into-a-compressed-searchable-pdf-with-redactions-63f61c34fe4c)
+- [c't 1-2014, page 59](http://heise.de/-2279695): Detailed presentation of OCRmyPDF v1.0 in the leading German IT magazine c't
+- [heise Open Source, 09/2014: Texterkennung mit OCRmyPDF](http://heise.de/-2356670)
+
+Business enquiries
+------------------
+
+OCRmyPDF would not be the software that it is today is without companies and users choosing to provide support for feature development and consulting enquiries. We are happy to discuss all enquiries, whether for extending the existing feature set, or integrating OCRmyPDF into a larger system.
+
+License
+-------
+
+The OCRmyPDF software is licensed under the GNU GPLv3. Certain files are covered by other licenses, as noted in their source files.
+
+The license for each test file varies, and is noted in tests/resources/README.rst. The documentation is licensed under Creative Commons Attribution-ShareAlike 4.0 (CC-BY-SA 4.0).
+
+OCRmyPDF versions prior to 6.0 were distributed under the MIT License.
+
+Disclaimer
+----------
+
+The software is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.

README.rst

@@ -1,132 +0,0 @@
-OCRmyPDF
-========
-
-.. image:: https://travis-ci.org/jbarlow83/OCRmyPDF.svg?branch=master
-    :target: https://travis-ci.org/jbarlow83/OCRmyPDF
-
-OCRmyPDF adds an OCR text layer to scanned PDF files, allowing them to
-be searched or copy-pasted.
-
-.. code-block:: bash
-
-   ocrmypdf                      # it's a scriptable command line program
-      -l eng+fra                 # it supports multiple languages
-      --rotate-pages             # it can fix pages that are misrotated
-      --deskew                   # it can deskew crooked PDFs!
-      --title "My PDF"           # it can change output metadata
-      --jobs 4                   # it uses multiple cores by default
-      --output-type pdfa         # it produces PDF/A by default
-      input_scanned.pdf          # takes PDF input (or images)
-      output_searchable.pdf      # produces validated PDF output
-
-
-Main features
--------------
-
--  Generates a searchable
-   `PDF/A <https://en.wikipedia.org/?title=PDF/A>`_ file from a regular PDF
--  Places OCR text accurately below the image to ease copy / paste
--  Keeps the exact resolution of the original embedded images
--  When possible, inserts OCR information as a "lossless" operation without rendering vector information
--  Keeps file size about the same
--  If requested deskews and/or cleans the image before performing OCR
--  Validates input and output files
--  Provides debug mode to enable easy verification of the OCR results
--  Processes pages in parallel when more than one CPU core is
-   available
--  Uses `Tesseract OCR <https://github.com/tesseract-ocr/tesseract>`_ engine
--  Supports more than `100 languages <https://github.com/tesseract-ocr/tessdata>`_ recognized by Tesseract
--  Battle-tested on thousands of PDFs, a test suite and continuous integration
-
-For details: please consult the `documentation <https://ocrmypdf.readthedocs.io/en/latest/>`_.
-
-Motivation
-----------
-
-I searched the web for a free command line tool to OCR PDF files on
-Linux/UNIX: I found many, but none of them were really satisfying.
-
--  Either they produced PDF files with misplaced text under the image (making copy/paste impossible) 
--  Or they did not handle accents and multilingual characters
--  Or they changed the resolution of the embedded images
--  Or they generated ridiculously large PDF files
--  Or they crashed when trying to OCR some of my PDF files
--  Or they did not produce valid PDF files (even though they were readable with my current PDF reader)
--  On top of that none of them produced PDF/A files (format dedicated for long time storage)
-
-...so I decided to develop my own tool (using various existing scripts
-as an inspiration). 
-
-Installation
-------------
-
-Linux, UNIX, and macOS are supported. Windows is not directly supported but there is a Docker image available that runs on Windows.
-
-Users of Debian 9 or later or Ubuntu 16.10 or later may simply
-
-.. code-block:: bash
-
-   apt-get install ocrmypdf
-
-and macOS users may simply
-
-.. code-block:: bash
-
-   brew tap jbarlow83/ocrmypdf
-   brew install ocrmypdf
-
-For everyone else, `see our documentation <https://ocrmypdf.readthedocs.io/en/latest/installation.html>`_ for installation steps.
-
-Languages
----------
-
-OCRmyPDF uses Tesseract for OCR, and relies on its language packs. For Linux users,
-you can often find packages that provide language packs:
-
-.. code-block:: bash
-
-   # Display a list of all Tesseract language packs
-   apt-cache search tesseract-ocr
-
-   # Debian/Ubuntu users
-   apt-get install tesseract-ocr-chi-sim  # Example: Install Chinese Simplified language back
-   
-You can then pass the ``-l LANG`` argument to OCRmyPDF to give a hint as to what languages it should search for. Multiple
-languages can be requested.
-
-Documentation and support
--------------------------
-
-Once ocrmypdf is installed, the built-in help which explains the command syntax and options can be accessed via:
-
-.. code-block:: bash
-
-   ocrmypdf --help
-
-Our `documentation is served on Read the Docs <https://ocrmypdf.readthedocs.io/en/latest/index.html>`_.
-
-If you detect an issue, please:
-
--  Check whether your issue is already known
--  If no problem report exists on github, please create one here:
-   https://github.com/jbarlow83/OCRmyPDF/issues
--  Describe your problem thoroughly
--  Append the console output of the script when running the debug mode
-   (``-v 1`` option)
--  If possible provide your input PDF file as well as the content of the
-   temporary folder (using a file sharing service like Dropbox)
-
-Press & Media
--------------
-
--  `c't 1-2014, page 59 <http://heise.de/-2279695>`_:
-   Detailed presentation of OCRmyPDF v1.0 in the leading German IT
-   magazine c't
--  `heise Open Source, 09/2014: Texterkennung mit
-   OCRmyPDF <http://heise.de/-2356670>`_
-
-Disclaimer
-----------
-
-The software is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR
-CONDITIONS OF ANY KIND, either express or implied.

dev_requirements.txt

@@ -1,10 +0,0 @@
-check-manifest >= 0.35
-twine >= 1.8.1
-coverage >= 4.4
-pytest-xdist >= 1.16.0
-GitPython == 2.1.3
-
-# Known good versions: 1.11.1
-# Known broken versions: 1.15.0
-setuptools-scm == 1.11.1
-setuptools-scm-git-archive == 1.0

docker-wrapper.sh

@@ -1,5 +0,0 @@
-#!/bin/bash
-
-. /appenv/bin/activate
-cd /home/docker
-exec ocrmypdf "$@"

docs/advanced.rst

@@ -1,91 +1,192 @@
+=================
 Advanced features
 =================
 
-Control of OCR options
-----------------------
+Control of unpaper
+==================
 
-OCRmyPDF provides many features to control the behavior of the OCR engine, Tesseract.
+OCRmyPDF uses ``unpaper`` to provide the implementation of the
+``--clean`` and ``--clean-final`` arguments.
+`unpaper <https://github.com/Flameeyes/unpaper/blob/master/doc/basic-concepts.md>`__
+provides a variety of image processing filters to improve images.
+
+By default, OCRmyPDF uses only ``unpaper`` arguments that were found to
+be safe to use on almost all files without having to inspect every page
+of the file afterwards. This is particularly true when only ``--clean``
+is used, since that instructs OCRmyPDF to only clean the image before
+OCR and not the final image.
+
+However, if you wish to use the more aggressive options in ``unpaper``,
+you may use ``--unpaper-args '...'`` to override the OCRmyPDF's defaults
+and forward other arguments to unpaper. This option will forward
+arguments to ``unpaper`` without any knowledge of what that program
+considers to be valid arguments. The string of arguments must be quoted
+as shown in the examples below. No filename arguments may be included.
+OCRmyPDF will assume it can append input and output filename of
+intermediate images to the ``--unpaper-args`` string.
+
+In this example, we tell ``unpaper`` to expect two pages of text on a
+sheet (image), such as occurs when two facing pages of a book are
+scanned. ``unpaper`` uses this information to deskew each independently
+and clean up the margins of both.
+
+.. code-block:: bash
+
+    ocrmypdf --clean --clean-final --unpaper-args '--layout double' input.pdf output.pdf
+    ocrmypdf --clean --clean-final --unpaper-args '--layout double --no-noisefilter' input.pdf output.pdf
+
+.. warning::
+
+   Some ``unpaper`` features will reposition text within the image.
+   ``--clean-final`` is recommended to avoid this issue.
+
+.. warning::
+
+   Some ``unpaper`` features cause multiple input or output files to be
+   consumed or produced. OCRmyPDF requires ``unpaper`` to consume one
+   file and produce one file. An deviation from that condition will
+   result in errors.
+
+.. note::
+
+   ``unpaper`` uses uncompressed PBM/PGM/PPM files for its intermediate
+   files. For large images or documents, it can take a lot of temporary
+   disk space.
+
+Control of OCR options
+======================
+
+OCRmyPDF provides many features to control the behavior of the OCR
+engine, Tesseract.
 
 When OCR is skipped
-"""""""""""""""""""
+-------------------
 
-If a page in a PDF seems to have text, by default OCRmyPDF will exit without modifying the PDF. This is to ensure that PDFs that were previously OCRed or were "born digital" rather than scanned are not processed. 
+If a page in a PDF seems to have text, by default OCRmyPDF will exit
+without modifying the PDF. This is to ensure that PDFs that were
+previously OCRed or were "born digital" rather than scanned are not
+processed.
 
-If ``--skip-text`` is issued, then no OCR will be performed on pages that already have text. The page will be copied to the output. This may be useful for documents that contain both "born digital" and scanned content, or to use OCRmyPDF to normalize and convert to PDF/A regardless of their contents.
+If ``--skip-text`` is issued, then no OCR will be performed on pages
+that already have text. The page will be copied to the output. This may
+be useful for documents that contain both "born digital" and scanned
+content, or to use OCRmyPDF to normalize and convert to PDF/A regardless
+of their contents.
 
-If ``--force-ocr`` is issued, then all pages will be rasterized to images, discarding any hidden OCR text, and rasterizing any printable text. This is useful for redoing OCR, for fixing OCR text with a damaged character map (text is selectable but not searchable), and destroying redacted information.
+If ``--redo-ocr`` is issued, then a detailed text analysis is performed.
+Text is categorized as either visible or invisible. Invisible text (OCR)
+is stripped out. Then an image of each page is created with visible text
+masked out. The page image is sent for OCR, and any additional text is
+inserted as OCR. If a file contains a mix of text and bitmap images that
+contain text, OCRmyPDF will locate the additional text in images without
+disrupting the existing text.
 
+If ``--force-ocr`` is issued, then all pages will be rasterized to
+images, discarding any hidden OCR text, and rasterizing any printable
+text. This is useful for redoing OCR, for fixing OCR text with a damaged
+character map (text is selectable but not searchable), and destroying
+redacted information. Any forms and vector graphics will be rasterized
+as well.
 
 Time and image size limits
-""""""""""""""""""""""""""
+--------------------------
 
-By default, OCRmyPDF permits tesseract to run for only three minutes (180 seconds) per page. This is usually more than enough time to find all text on a reasonably sized page with modern hardware. 
+By default, OCRmyPDF permits tesseract to run for three minutes (180
+seconds) per page. This is usually more than enough time to find all
+text on a reasonably sized page with modern hardware.
 
-If a page is skipped, it will be inserted without OCR. If preprocessing was requested, the preprocessed image layer will be inserted.
+If a page is skipped, it will be inserted without OCR. If preprocessing
+was requested, the preprocessed image layer will be inserted.
 
-If you want to adjust the amount of time spent on OCR, change ``--tesseract-timeout``.  You can also automatically skip images that exceed a certain number of megapixels with ``--skip-big``. (A 300 DPI, 8.5×11" page is 8.4 megapixels.)
+If you want to adjust the amount of time spent on OCR, change
+``--tesseract-timeout``. You can also automatically skip images that
+exceed a certain number of megapixels with ``--skip-big``. (A 300 DPI,
+8.5×11" page is 8.4 megapixels.)
 
 .. code-block:: bash
 
-	# Allow 300 seconds for OCR; skip any page larger than 50 megapixels
-	ocrmypdf --tesseract-timeout 300 --skip-big 50 bigfile.pdf output.pdf
+    # Allow 300 seconds for OCR; skip any page larger than 50 megapixels
+    ocrmypdf --tesseract-timeout 300 --skip-big 50 bigfile.pdf output.pdf
 
 Overriding default tesseract
-""""""""""""""""""""""""""""
+----------------------------
 
-OCRmyPDF checks the environment variable ``OCRMYPDF_TESSERACT`` for the full path *to the tesseract executable* first. 
+OCRmyPDF checks the system ``PATH`` for the ``tesseract`` binary.
 
-For example, if you are testing tesseract 4.00 and don't wish to disturb your tesseract 3.04 installation, you can launch OCRmyPDF as follows:
+Some relevant environment variables that influence Tesseract's behavior
+include:
+
+.. envvar:: TESSDATA_PREFIX
+
+   Overrides the path to Tesseract's data files. This can allow
+   simultaneous installation of the "best" and "fast" training data
+   sets. OCRmyPDF does not manage this environment variable.
+
+.. envvar:: OMP_THREAD_LIMIT
+
+   Controls the number of threads Tesseract will use. OCRmyPDF will
+   manage this environment if it is not already set. (Currently, it will
+   set it to 1 because this gives the best results in testing.)
+
+For example, if you have a development build of Tesseract don't wish to
+use the system installation, you can launch OCRmyPDF as follows:
 
 .. code-block:: bash
 
-	env \
-		OCRMYPDF_TESSERACT=/home/user/src/tesseract4/api/tesseract \
-		TESSDATA_PREFIX=/home/user/src/tesseract4 \
-		ocrmypdf --tesseract-oem 2 input.pdf output.pdf
+    env \
+        PATH=/home/user/src/tesseract/api:$PATH \
+        TESSDATA_PREFIX=/home/user/src/tesseract \
+        ocrmypdf input.pdf output.pdf
 
-* ``TESSDATA_PREFIX`` directs tesseract 4.0 to use LSTM training data. This is a tesseract environment variable.
-* ``--tesseract-oem 1`` requests tesseract 4.0's new LSTM engine. (Tesseract 4.0 only.)
+In this example ``TESSDATA_PREFIX`` is required to redirect Tesseract to
+an alternate folder for its "tessdata" files.
 
 Overriding other support programs
-"""""""""""""""""""""""""""""""""
+---------------------------------
 
 In addition to tesseract, OCRmyPDF uses the following external binaries:
 
-* ``gs`` (Ghostscript)
-* ``unpaper``
-* ``qpdf``
+-  ``gs`` (Ghostscript)
+-  ``unpaper``
+-  ``qpdf``
 
-In each case OCRmyPDF will check the environment variable ``OCRMYPDF_{program}`` before asking the system to find ``{program}`` on the PATH. For example, you could redirect OCRmyPDF to ``OCRMYPDF_GS`` to override Ghostscript.
+In each case OCRmyPDF will search the ``PATH`` environment variable to
+locate the binaries.
 
 Changing tesseract configuration variables
-""""""""""""""""""""""""""""""""""""""""""
+------------------------------------------
 
-You can override tesseract's default `control parameters <https://github.com/tesseract-ocr/tesseract/wiki/ControlParams>`_ with a configuration file.
+You can override tesseract's default `control
+parameters <https://github.com/tesseract-ocr/tesseract/wiki/ControlParams>`__
+with a configuration file.
 
-As an example, this configuration will disable Tesseract's dictionary for current language. Normally the dictionary is helpful for interpolating words that are unclear, but it may interfere with OCR if the document does not contain many words (for example, a list of part numbers).
+As an example, this configuration will disable Tesseract's dictionary
+for current language. Normally the dictionary is helpful for
+interpolating words that are unclear, but it may interfere with OCR if
+the document does not contain many words (for example, a list of part
+numbers).
 
 Create a file named "no-dict.cfg" with these contents:
 
 ::
 
-	load_system_dawg 0
-	language_model_penalty_non_dict_word 0
-	language_model_penalty_non_freq_dict_word 0
+    load_system_dawg 0
+    language_model_penalty_non_dict_word 0
+    language_model_penalty_non_freq_dict_word 0
 
 then run ocrmypdf as follows (along with any other desired arguments):
 
 .. code-block:: bash
 
-	ocrmypdf --tesseract-config no-dict.cfg input.pdf output.pdf
+    ocrmypdf --tesseract-config no-dict.cfg input.pdf output.pdf
 
 .. warning::
 
-	Some combinations of control parameters will break Tesseract or break assumptions that OCRmyPDF makes about Tesseract's output.
-
+   Some combinations of control parameters will break Tesseract or break
+   assumptions that OCRmyPDF makes about Tesseract's output.
 
 Changing the PDF renderer
--------------------------
+=========================
 
 rasterizing
   Converting a PDF to an image for display.
@@ -93,30 +194,151 @@ rasterizing
 rendering
   Creating a new PDF from other data (such as an existing PDF).
 
-
-OCRmyPDF has three PDF renderers: ``sandwich``, ``hocr``, ``tesseract``. The renderer may be selected using ``--pdf-renderer``. The default is ``auto`` which lets OCRmyPDF select the renderer to use. Currently, ``auto`` selects ``sandwich`` for Tesseract 3.05.01, and newer, ``hocr`` for older versions of Tesseract.
+OCRmyPDF has these PDF renderers: ``sandwich`` and ``hocr``. The
+renderer may be selected using ``--pdf-renderer``. The default is
+``auto`` which lets OCRmyPDF select the renderer to use. Currently,
+``auto`` always selects ``sandwich``.
 
 The ``sandwich`` renderer
-"""""""""""""""""""""""""
+-------------------------
 
-The ``sandwich`` renderer uses Tesseract's new text-only PDF feature, which produces a PDF page that lays out the OCR in invisible text. This page is then "sandwiched" onto the original PDF page, allowing lossless application of OCR even to PDF pages that contain other vector objects.
+The ``sandwich`` renderer uses Tesseract's new text-only PDF feature,
+which produces a PDF page that lays out the OCR in invisible text. This
+page is then "sandwiched" onto the original PDF page, allowing lossless
+application of OCR even to PDF pages that contain other vector objects.
 
-When image preprocessing features like ``--deskew`` are used, the original PDF will be rendered as a full page and the OCR layer will be placed on top.
+Currently this is the best renderer for most uses, however it is
+implemented in Tesseract so OCRmyPDF cannot influence it. Currently some
+problematic PDF viewers like Mozilla PDF.js and macOS Preview have
+problems with segmenting its text output, and
+mightrunseveralwordstogether.
 
-This renderer requires Tesseract 3.05.01 or newer.
+When image preprocessing features like ``--deskew`` are used, the
+original PDF will be rendered as a full page and the OCR layer will be
+placed on top.
 
 The ``hocr`` renderer
-"""""""""""""""""""""
+---------------------
 
-The ``hocr`` renderer works with older versions of Tesseract. The image layer is copied from the original PDF page if possible, avoiding potentially lossy transcoding or loss of other PDF information. If preprocessing is specified, then the image layer is a new PDF.
+The ``hocr`` renderer works with older versions of Tesseract. The image
+layer is copied from the original PDF page if possible, avoiding
+potentially lossy transcoding or loss of other PDF information. If
+preprocessing is specified, then the image layer is a new PDF.
+
+Unlike ``sandwich`` this renderer is implemented within OCRmyPDF; anyone
+looking to customize how OCR is presented should look here. A major
+disadvantage of this renderer is it not capable of correctly handling
+text outside the Latin alphabet. Pull requests to improve the situation
+are welcome.
+
+Currently, this renderer has the best compatibility with Mozilla's
+PDF.js viewer.
 
 This works in all versions of Tesseract.
 
 The ``tesseract`` renderer
-""""""""""""""""""""""""""
+--------------------------
 
-The ``tesseract`` renderer creates a PDF with the image and text layers precomposed, meaning that it always transcodes, loses image quality and rasterizes and vector objects. It does a better job on non-Latin text and document structure than ``hocr``.
+The ``tesseract`` renderer was removed. OCRmyPDF's new approach to text
+layer grafting makes it functionally equivalent to ``sandwich``.
 
-If a PDF created with this renderer using Tesseract versions older than 3.05.00 is then passed through Ghostscript's pdfwrite feature, the OCR text *may* be corrupted. The ``--output-type=pdfa`` argument will produce a warning in this situation.
+Return code policy
+==================
 
-*This renderer is deprecated and will be removed whenever support for older versions of Tesseract is dropped.*
+OCRmyPDF writes all messages to ``stderr``. ``stdout`` is reserved for
+piping output files. ``stdin`` is reserved for piping input files.
+
+The return codes generated by the OCRmyPDF are considered part of the
+stable user interface. They may be imported from
+``ocrmypdf.exceptions``.
+
+.. list-table:: Return codes
+    :widths: 5 35 60
+    :header-rows: 1
+
+    *	- Code
+        - Name
+        - Interpretation
+    *	- 0
+        - ``ExitCode.ok``
+        - Everything worked as expected.
+    *	- 1
+        - ``ExitCode.bad_args``
+        - Invalid arguments, exited with an error.
+    *	- 2
+        - ``ExitCode.input_file``
+        - The input file does not seem to be a valid PDF.
+    *	- 3
+        - ``ExitCode.missing_dependency``
+        - An external program required by OCRmyPDF is missing.
+    *	- 4
+        - ``ExitCode.invalid_output_pdf``
+        - An output file was created, but it does not seem to be a valid PDF. The file will be available.
+    *	- 5
+        - ``ExitCode.file_access_error``
+        - The user running OCRmyPDF does not have sufficient permissions to read the input file and write the output file.
+    *	- 6
+        - ``ExitCode.already_done_ocr``
+        - The file already appears to contain text so it may not need OCR. See output message.
+    *	- 7
+        - ``ExitCode.child_process_error``
+        - An error occurred in an external program (child process) and OCRmyPDF cannot continue.
+    *	- 8
+        - ``ExitCode.encrypted_pdf``
+        - The input PDF is encrypted. OCRmyPDF does not read encrypted PDFs. Use another program such as ``qpdf`` to remove encryption.
+    *	- 9
+        - ``ExitCode.invalid_config``
+        - A custom configuration file was forwarded to Tesseract using ``--tesseract-config``, and Tesseract rejected this file.
+    *   - 10
+        - ``ExitCode.pdfa_conversion_failed``
+        - A valid PDF was created, PDF/A conversion failed. The file will be available.
+    *	- 15
+        - ``ExitCode.other_error``
+        - Some other error occurred.
+    *	- 130
+        - ``ExitCode.ctrl_c``
+        - The program was interrupted by pressing Ctrl+C.
+
+
+Debugging the intermediate files
+================================
+
+OCRmyPDF normally saves its intermediate results to a temporary folder
+and deletes this folder when it exits, whether it succeeded or failed.
+
+If the ``-k`` argument is issued on the command line, OCRmyPDF will keep
+the temporary folder and print the location, whether it succeeded or
+failed (provided the Python interpreter did not crash). An example
+message is:
+
+.. code-block:: none
+
+    Temporary working files retained at:
+    /tmp/com.github.ocrmypdf.u20wpz07
+
+The organization of this folder is an implementation detail and subject
+to change between releases. However the general organization is that
+working files on a per page basis have the page number as a prefix
+(starting with page 1), an infix indicates the processing stage, and a
+suffix indicates the file type. Some important files include:
+
+-  ``_rasterize.png`` - what the input page looks like
+-  ``_ocr.png`` - the file that is sent to Tesseract for OCR; depending
+   on arguments this may differ from the presentation image
+-  ``_pp_deskew.png`` - the image, after deskewing
+-  ``_pp_clean.png`` - the image, after cleaning with unpaper
+-  ``_ocr_tess.pdf`` - the OCR file; appears as a blank page with invisible
+   text embedded
+-  ``_ocr_tess.txt`` - the OCR text (not necessarily all text on the page,
+   if the page is mixed format)
+-  ``fix_docinfo.pdf`` - a temporary file created to fix the PDF DocumentInfo
+   data structure
+-  ``graft_layers.pdf`` - the rendered PDF with OCR layers grafted on
+-  ``pdfa.pdf`` - ``graft_layers.pdf`` after conversion to PDF/A
+-  ``pdfa.ps`` - a PostScript file used by Ghostscript for PDF/A conversion
+-  ``optimize.pdf`` - the PDF generated before optimization
+-  ``optimize.out.pdf`` - the PDF generated by optimization
+-  ``origin`` - the input file
+-  ``origin.pdf`` - the input file or the input image converted to PDF
+-  ``images/*`` - images extracted during the optimization process; here
+   the prefix indicates a PDF object ID not a page number

docs/api.rst

@@ -0,0 +1,104 @@
+======================
+Using the OCRmyPDF API
+======================
+
+OCRmyPDF originated as a command line program and continues to have this
+legacy, but parts of it can be imported and used in other Python
+applications.
+
+Some applications may want to consider running ocrmypdf from a
+subprocess call anyway, as this provides isolation of its activities.
+
+Example
+=======
+
+OCRmyPDF one high-level function to run its main engine from an
+application. The parameters are symmetric to the command line arguments
+and largely have the same functions.
+
+.. code-block:: python
+
+    import ocrmypdf
+
+    ocrmypdf.ocr('input.pdf', 'output.pdf', deskew=True)
+
+With a few exceptions, all of the command line arguments are available
+and may be passed as equivalent keywords.
+
+A few differences are that ``verbose`` and ``quiet`` are not available.
+Instead, output should be managed by configuring logging.
+
+Parent process requirements
+---------------------------
+
+The :func:`ocrmypdf.ocr` function runs OCRmyPDF similar to command line
+execution. To do this, it will:
+
+- create a monitoring thread
+- create worker processes (forking itself)
+- manage the signal flags of worker processes
+- execute other subprocesses (forking and executing other programs)
+
+The Python process that calls ``ocrmypdf.ocr()`` must be sufficiently
+privileged to perform these actions. If it is not, ``ocrmypdf()`` will
+fail.
+
+There is no currently no option to manage how jobs are scheduled other
+than the argument ``jobs=`` which will limit the number of worker
+processes.
+
+Forking a child process to call ``ocrmypdf.ocr()`` is suggested. That
+way your application will survive and remain interactive even if
+OCRmyPDF does not.
+
+Logging
+-------
+
+OCRmyPDF will log under loggers named ``ocrmypdf``. In addition, it
+imports ``pdfminer`` and ``PIL``, both of which post log messages under
+those logging namespaces.
+
+You can configure the logging as desired for your application or call
+:func:`ocrmypdf.configure_logging` to configure logging the same way
+OCRmyPDF itself does. The command line parameters such as ``--quiet``
+and ``--verbose`` have no equivalents in the API; you must use the
+provided configuration function or do configuration in a way that suits
+your use case.
+
+Progress monitoring
+-------------------
+
+OCRmyPDF uses the ``tqdm`` package to implement its progress bars.
+:func:`ocrmypdf.configure_logging` will set up logging output to
+``sys.stderr`` in a way that is compatible with the display of the
+progress bar. Use ``ocrmypdf.ocr(...progress_bar=False)`` to disable
+the progress bar.
+
+Exceptions
+----------
+
+OCRmyPDF may throw standard Python exceptions, ``ocrmypdf.exceptions.*``
+exceptions, some exceptions related to multiprocessing, and
+``KeyboardInterrupt``. The parent process should provide an exception
+handler. OCRmyPDF will clean up its temporary files and worker processes
+automatically when an exception occurs.
+
+Programs that call OCRmyPDF should consider trapping KeyboardInterrupt
+so that they allow OCR to terminate with the whole program terminating.
+
+When OCRmyPDF succeeds conditionally, it returns an integer exit code.
+
+Reference
+---------
+
+.. autofunction:: ocrmypdf.ocr
+
+.. autoclass:: ocrmypdf.Verbosity
+    :members:
+    :undoc-members:
+
+.. autoclass:: ocrmypdf.ExitCode
+    :members:
+    :undoc-members:
+
+.. autofunction:: ocrmypdf.configure_logging

docs/batch.rst

@@ -1,142 +1,266 @@
+================
 Batch processing
 ================
 
-This article provides information about running OCRmyPDF on multiple files or configuring it as a service triggered by file system events.
+This article provides information about running OCRmyPDF on multiple
+files or configuring it as a service triggered by file system events.
 
 Batch jobs
-----------
+==========
 
-Consider using the excellent `GNU Parallel <https://www.gnu.org/software/parallel/>`_ to apply OCRmyPDF to multiple files at once.
+Consider using the excellent `GNU
+Parallel <https://www.gnu.org/software/parallel/>`__ to apply OCRmyPDF
+to multiple files at once.
 
-Both ``parallel`` and ``ocrmypdf`` will try to use all available processors. To maximize parallelism without overloading your system with processes, consider using ``parallel -j 2`` to limit parallel to running two jobs at once.
+Both ``parallel`` and ``ocrmypdf`` will try to use all available
+processors. To maximize parallelism without overloading your system with
+processes, consider using ``parallel -j 2`` to limit parallel to running
+two jobs at once.
 
-This command will run all ocrmypdf all files named ``*.pdf`` in the current directory and write them to the previous created ``output/`` folder. It will not search subdirectories.
+This command will run all ocrmypdf all files named ``*.pdf`` in the
+current directory and write them to the previous created ``output/``
+folder. It will not search subdirectories.
 
-The ``--tag`` argument tells parallel to print the filename as a prefix whenever a message is printed, so that one can trace any errors to the file that produced them.
+The ``--tag`` argument tells parallel to print the filename as a prefix
+whenever a message is printed, so that one can trace any errors to the
+file that produced them.
 
 .. code-block:: bash
 
-	parallel --tag -j 2 ocrmypdf '{}' 'output/{}' ::: *.pdf
+   parallel --tag -j 2 ocrmypdf '{}' 'output/{}' ::: *.pdf
+
+OCRmyPDF automatically repairs PDFs before parsing and gathering
+information from them.
 
 Directory trees
----------------
+===============
 
-This will walk through a directory tree and run OCR on all files in place, printing the output in a way that makes 
+This will walk through a directory tree and run OCR on all files in
+place, printing the output in a way that makes
 
 .. code-block:: bash
 
-	find . --printf '%p' -name '*.pdf' -exec ocrmypdf '{}' '{}' \;
+   find . -printf '%p' -name '*.pdf' -exec ocrmypdf '{}' '{}' \;
 
-This only runs one ``ocrmypdf`` process at a time. This variation uses ``find`` to create a directory list and ``parallel`` to parallelize runs of ``ocrmypdf``, again updating files in place.
+Alternatively, with a docker container (mounts a volume to the container
+where the PDFs are stored):
 
 .. code-block:: bash
 
-	find . -name '*.pdf' | parallel --tag -j 2 ocrmypdf '{}' '{}'
+   find . -printf '%p' -name '*.pdf' -exec docker run --rm -v <host dir>:<container dir> jbarlow83/ocrmypdf '<container dir>/{}' '<container dir>/{}' \;
 
+This only runs one ``ocrmypdf`` process at a time. This variation uses
+``find`` to create a directory list and ``parallel`` to parallelize runs
+of ``ocrmypdf``, again updating files in place.
+
+.. code-block:: bash
+
+   find . -name '*.pdf' | parallel --tag -j 2 ocrmypdf '{}' '{}'
 
 Sample script
-"""""""""""""
+-------------
 
-This user contributed script also provides an example of batch processing.
+This user contributed script also provides an example of batch
+processing.
 
 .. code-block:: python
 
-	#!/usr/bin/env python3
-	# Walk through directory tree, replacing all files with OCR'd version
-	# Contributed by DeliciousPickle@github
+   #!/usr/bin/env python3
+   # Walk through directory tree, replacing all files with OCR'd version
+   # Contributed by DeliciousPickle@github
 
-	import logging
-	import os
-	import subprocess
-	import sys
+   import logging
+   import os
+   import subprocess
+   import sys
 
-	script_dir = os.path.dirname(os.path.realpath(__file__))
-	print(script_dir + '/ocr-tree.py: Start')
+   script_dir = os.path.dirname(os.path.realpath(__file__))
+   print(script_dir + '/ocr-tree.py: Start')
 
-	if len(sys.argv) > 1:
-	    start_dir = sys.argv[1]
-	else:
-	    start_dir = '.'
+   if len(sys.argv) > 1:
+       start_dir = sys.argv[1]
+   else:
+       start_dir = '.'
 
-	if len(sys.argv) > 2:
-	    log_file = sys.argv[2]
-	else:
-	    log_file = script_dir + '/ocr-tree.log'
+   if len(sys.argv) > 2:
+       log_file = sys.argv[2]
+   else:
+       log_file = script_dir + '/ocr-tree.log'
 
-	logging.basicConfig(
-			level=logging.INFO, format='%(asctime)s %(message)s', 
-			filename=log_file, filemode='w')
+   logging.basicConfig(
+           level=logging.INFO, format='%(asctime)s %(message)s',
+           filename=log_file, filemode='w')
 
-	for dir_name, subdirs, file_list in os.walk(start_dir):
-	    logging.info('\n')
-	    logging.info(dir_name + '\n')
-	    os.chdir(dir_name)
-	    for filename in file_list:
-	        file_ext = os.path.splitext(filename)[1]
-	        if file_ext == '.pdf':
-	            full_path = dir_name + '/' + filename
-	            print(full_path)
-	            cmd = ["ocrmypdf",  "--deskew", filename, filename]
-	            logging.info(cmd)
-	            proc = subprocess.Popen(
-	            	cmd, stdout=subprocess.PIPE, stderr=subprocess.STDOUT)
-	            result = proc.stdout.read()
-	            if proc.returncode == 6:
-	                print("Skipped document because it already contained text")
-	            elif proc.returncode == 0:
-	                print("OCR complete")
-	            logging.info(result)
+   for dir_name, subdirs, file_list in os.walk(start_dir):
+       logging.info('\n')
+       logging.info(dir_name + '\n')
+       os.chdir(dir_name)
+       for filename in file_list:
+           file_ext = os.path.splitext(filename)[1]
+           if file_ext == '.pdf':
+               full_path = dir_name + '/' + filename
+               print(full_path)
+               cmd = ["ocrmypdf",  "--deskew", filename, filename]
+               logging.info(cmd)
+               proc = subprocess.run(
+                   cmd, stdout=subprocess.PIPE, stderr=subprocess.STDOUT)
+               result = proc.stdout
+               if proc.returncode == 6:
+                   print("Skipped document because it already contained text")
+               elif proc.returncode == 0:
+                   print("OCR complete")
+               logging.info(result)
 
-API
-"""
-
-OCRmyPDF is currently supported as a command line interface. Due to limitations in one of the libraries OCRmyPDF depends on, it is not yet usable as an API.
-
-
-Huge batch jobs
-"""""""""""""""
-
-If you have thousands of files to work with, contact the author.
-
-
-Hot (watched) folders
+Synology DiskStations
 ---------------------
 
-To set up a "hot folder" that will trigger OCR for every file inserted, use a program like Python `watchdog <https://pypi.python.org/pypi/watchdog>`_ (supports all major OS).
+Synology DiskStations (Network Attached Storage devices) can run the
+Docker image of OCRmyPDF if the Synology `Docker
+package <https://www.synology.com/en-global/dsm/packages/Docker>`__ is
+installed. Attached is a script to address particular quirks of using
+OCRmyPDF on one of these devices.
 
-One could then configure a scanner to automatically place scanned files in a hot folder, so that they will be queued for OCR and copied to the destination.
+This is only possible for x86-based Synology products. Some Synology
+products use ARM or Power processors and do not support Docker. Further
+adjustments might be needed to deal with the Synology's relatively
+limited CPU and RAM.
+
+.. code-block:: python
+
+   #!/bin/env python3
+   # Contributed by github.com/Enantiomerie
+
+   # script needs 2 arguments
+   # 1. source dir with *.pdf - default is location of script
+   # 2. move dir where *.pdf and *_OCR.pdf are moved to
+
+   import logging
+   import os
+   import subprocess
+   import sys
+   import time
+   import shutil
+
+   script_dir = os.path.dirname(os.path.realpath(__file__))
+   timestamp = time.strftime("%Y-%m-%d-%H%M_")
+   log_file = script_dir + '/' + timestamp + 'ocrmypdf.log'
+   logging.basicConfig(level=logging.INFO, format='%(asctime)s %(message)s', filename=log_file, filemode='w')
+
+   if len(sys.argv) > 1:
+       start_dir = sys.argv[1]
+   else:
+       start_dir = '.'
+
+   for dir_name, subdirs, file_list in os.walk(start_dir):
+       logging.info('\n')
+       logging.info(dir_name + '\n')
+       os.chdir(dir_name)
+       for filename in file_list:
+           file_ext = os.path.splitext(filename)[1]
+           if file_ext == '.pdf':
+               full_path = dir_name + '/' + filename
+               file_noext = os.path.splitext(filename)[0]
+               timestamp_OCR = time.strftime("%Y-%m-%d-%H%M_OCR_")
+               filename_OCR = timestamp_OCR + file_noext + '.pdf'
+               docker_mount = dir_name + ':/home/docker'
+   # create string for pdf processing
+   # diskstation needs a user:group docker:docker. find uid:gid of your diskstation docker:docker with id docker.
+   # use this uid:gid in -u flag
+   # rw rights for docker:docker at source dir are also necessary
+   # the script is processed as root user via chron
+               cmd = ['docker', 'run', '--rm', '-v', docker_mount, '-u=1030:65538', 'jbarlow83/ocrmypdf', , '--deskew' , filename, filename_OCR]
+               logging.info(cmd)
+               proc = subprocess.run(cmd, stdout=subprocess.PIPE, stderr=subprocess.STDOUT)
+               result = proc.stdout.read()
+               logging.info(result)
+               full_path_OCR = dir_name + '/' + filename_OCR
+               os.chmod(full_path_OCR, 0o666)
+               os.chmod(full_path, 0o666)
+               full_path_OCR_archive = sys.argv[2]
+               full_path_archive = sys.argv[2] + '/no_ocr'
+               shutil.move(full_path_OCR,full_path_OCR_archive)
+               shutil.move(full_path, full_path_archive)
+   logging.info('Finished.\n')
+
+Huge batch jobs
+---------------
+
+If you have thousands of files to work with, contact the author.
+Consulting work related to OCRmyPDF helps fund this open source project
+and all inquiries are appreciated.
+
+Hot (watched) folders
+=====================
+
+To set up a "hot folder" that will trigger OCR for every file inserted,
+use a program like Python
+`watchdog <https://pypi.python.org/pypi/watchdog>`__ (supports all major
+OS).
+
+One could then configure a scanner to automatically place scanned files
+in a hot folder, so that they will be queued for OCR and copied to the
+destination.
 
 .. code-block:: bash
 
-	pip install watchdog
+   pip install watchdog
 
-watchdog installs the command line program ``watchmedo``, which can be told to run ``ocrmypdf`` on any .pdf added to the current directory (``.``) and place the result in the previously created ``out/`` folder.
+watchdog installs the command line program ``watchmedo``, which can be
+told to run ``ocrmypdf`` on any .pdf added to the current directory
+(``.``) and place the result in the previously created ``out/`` folder.
 
 .. code-block:: bash
 
-	cd hot-folder
-	mkdir out
-	watchmedo shell-command \
-		--patterns="*.pdf" \
-		--ignore-directories \
-		--command='ocrmypdf "${watch_src_path}" "out/${watch_src_path}" ' \
-		.  # don't forget the final dot
+   cd hot-folder
+   mkdir out
+   watchmedo shell-command \
+       --patterns="*.pdf" \
+       --ignore-directories \
+       --command='ocrmypdf "${watch_src_path}" "out/${watch_src_path}" ' \
+       .  # don't forget the final dot
 
-For more complex behavior you can write a Python script around to use the watchdog API.
+For more complex behavior you can write a Python script around to use
+the watchdog API.
 
-On file servers, you could configure watchmedo as a system service so it will run all the time.
+On file servers, you could configure watchmedo as a system service so it
+will run all the time.
 
 Caveats
-"""""""
+-------
 
-* ``watchmedo`` may not work properly on a networked file system, depending on the capabilities of the file system client and server.
-* This simple recipe does not filter for the type of file system event, so file copies, deletes and moves, and directory operations, will all be sent to ocrmypdf, producing errors in several cases. Disable your watched folder if you are doing anything other than copying files to it.
-* If the source and destination directory are the same, watchmedo may create an infinite loop.
-* On BSD, FreeBSD and older versions of macOS, you may need to increase the number of file descriptors to monitor more files, using ``ulimit -n 1024`` to watch a folder of up to 1024 files.
+-  ``watchmedo`` may not work properly on a networked file system,
+   depending on the capabilities of the file system client and server.
+-  This simple recipe does not filter for the type of file system event,
+   so file copies, deletes and moves, and directory operations, will all
+   be sent to ocrmypdf, producing errors in several cases. Disable your
+   watched folder if you are doing anything other than copying files to
+   it.
+-  If the source and destination directory are the same, watchmedo may
+   create an infinite loop.
+-  On BSD, FreeBSD and older versions of macOS, you may need to increase
+   the number of file descriptors to monitor more files, using
+   ``ulimit -n 1024`` to watch a folder of up to 1024 files.
 
 Alternatives
-""""""""""""
+------------
 
-* `Watchman <https://facebook.github.io/watchman/>`_ is a more powerful alternative to ``watchmedo``.
+-  `systemd user services <https://wiki.archlinux.org/index.php/Systemd/User>`__
+   can be configured to automatically perform OCR on a collection of files.
 
+-  `Watchman <https://facebook.github.io/watchman/>`__ is a more
+   powerful alternative to ``watchmedo``.
 
+macOS Automator
+===============
+
+You can use the Automator app with macOS, to create a Workflow or Quick
+Action. Use a *Run Shell Script* action in your workflow. In the context
+of Automator, the ``PATH`` may be set differently your Terminal's
+``PATH``; you may need to explicitly set the PATH to include
+``ocrmypdf``. The following example may serve as a starting point:
+
+|Example macOS Automator script|
+
+You may customize the command sent to ocrmypdf.
+
+.. |Example macOS Automator script| image:: images/macos-workflow.png

docs/conf.py

@@ -30,9 +30,7 @@
 # Add any Sphinx extension module names here, as strings. They can be
 # extensions coming with Sphinx (named 'sphinx.ext.*') or your custom
 # ones.
-extensions = [
-    # 'sphinx.ext.mathjax',
-]
+extensions = ['sphinx.ext.napoleon']
 
 # Add any paths that contain templates here, relative to this directory.
 templates_path = ['_templates']
@@ -52,7 +50,9 @@ master_doc = 'index'
 
 # General information about the project.
 project = 'ocrmypdf'
-copyright = '2017, James R. Barlow'
+copyright = (
+    '2019, James R. Barlow. Licensed under Creative Commons Attribution-ShareAlike 4.0.'
+)
 author = 'James R. Barlow'
 
 # The version info for the project you're documenting, acts as replacement for
@@ -60,13 +60,35 @@ author = 'James R. Barlow'
 # built documents.
 #
 # The short X.Y version.
-from ocrmypdf import VERSION as OCRMYPDF_VERSION
 
-_version_parts = OCRMYPDF_VERSION.split('.')
+import os
+
+on_rtd = os.environ.get('READTHEDOCS') == 'True'
+
+if on_rtd:
+    # Help ReadTheDocs avoid having to install any binary extension modules
+    import sys
+    from unittest.mock import MagicMock
+
+    class Mock(MagicMock):
+        @classmethod
+        def __getattr__(cls, name):
+            return MagicMock()
+
+    MOCK_MODULES = [
+        'pikepdf',
+        'pikepdf.models',
+        'pikepdf.models.metadata',
+        'ocrmypdf.leptonica',
+    ]
+    sys.modules.update((mod_name, Mock()) for mod_name in MOCK_MODULES)
+
+
+from pkg_resources import get_distribution, DistributionNotFound
 
-version = '.'.join(_version_parts[0:2])
 # The full version, including alpha/beta/rc tags.
-release = OCRMYPDF_VERSION
+release = get_distribution('ocrmypdf').version
+version = '.'.join(release.split('.')[:2])
 
 # The language for content autogenerated by Sphinx. Refer to documentation
 # for a list of supported languages.
@@ -135,9 +157,7 @@ html_theme_path = [sphinx_rtd_theme.get_html_theme_path()]
 # further.  For a list of options available for each theme, see the
 # documentation.
 #
-html_theme_options = {
-    'display_version': False
-}
+html_theme_options = {'display_version': False}
 
 # Add any paths that contain custom themes here, relative to this directory.
 # html_theme_path = []
@@ -250,29 +270,25 @@ htmlhelp_basename = 'ocrmypdfdoc'
 # -- Options for LaTeX output ---------------------------------------------
 
 latex_elements = {
-     # The paper size ('letterpaper' or 'a4paper').
-     #
-     # 'papersize': 'letterpaper',
-
-     # The font size ('10pt', '11pt' or '12pt').
-     #
-     # 'pointsize': '10pt',
-
-     # Additional stuff for the LaTeX preamble.
-     #
-     # 'preamble': '',
-
-     # Latex figure (float) alignment
-     #
-     # 'figure_align': 'htbp',
+    # The paper size ('letterpaper' or 'a4paper').
+    #
+    # 'papersize': 'letterpaper',
+    # The font size ('10pt', '11pt' or '12pt').
+    #
+    # 'pointsize': '10pt',
+    # Additional stuff for the LaTeX preamble.
+    #
+    # 'preamble': '',
+    # Latex figure (float) alignment
+    #
+    # 'figure_align': 'htbp',
 }
 
 # Grouping the document tree into LaTeX files. List of tuples
 # (source start file, target name, title,
 #  author, documentclass [howto, manual, or own class]).
 latex_documents = [
-    (master_doc, 'ocrmypdf.tex', 'ocrmypdf Documentation',
-     'James R. Barlow', 'manual'),
+    (master_doc, 'ocrmypdf.tex', 'ocrmypdf Documentation', 'James R. Barlow', 'manual')
 ]
 
 # The name of an image file (relative to this directory) to place at the top of
@@ -312,10 +328,7 @@ latex_documents = [
 
 # One entry per manual page. List of tuples
 # (source start file, name, description, authors, manual section).
-man_pages = [
-    (master_doc, 'ocrmypdf', 'ocrmypdf Documentation',
-     [author], 1)
-]
+man_pages = [(master_doc, 'ocrmypdf', 'ocrmypdf Documentation', [author], 1)]
 
 # If true, show URL addresses after external links.
 #
@@ -328,9 +341,15 @@ man_pages = [
 # (source start file, target name, title, author,
 #  dir menu entry, description, category)
 texinfo_documents = [
-    (master_doc, 'ocrmypdf', 'ocrmypdf Documentation',
-     author, 'ocrmypdf', 'One line description of project.',
-     'Miscellaneous'),
+    (
+        master_doc,
+        'ocrmypdf',
+        'ocrmypdf Documentation',
+        author,
+        'ocrmypdf',
+        'One line description of project.',
+        'Miscellaneous',
+    )
 ]
 
 # Documents to append as an appendix to all manuals.

docs/contributing.rst

@@ -0,0 +1,38 @@
+=======================
+Contributing guidelines
+=======================
+
+Contributions are welcome!
+
+Big changes
+===========
+
+Please open a new issue to discuss or propose a major change. Not only is it fun
+to discuss big ideas, but we might save each other's time too. Perhaps some of the
+work you're contemplating is already half-done in a development branch.
+
+Code style
+==========
+
+We use PEP8, ``black`` for code formatting and ``isort`` for import sorting. The
+settings for programs are in ``pyproject.toml`` and ``setup.cfg``.
+
+Tests
+=====
+
+New features should come with tests that confirm their correctness.
+
+New Python dependencies
+=======================
+
+If you are proposing a change that will require a new Python dependency, we
+prefer dependencies that are already packaged by Debian or Red Hat. This makes
+life much easier for our downstream package maintainers.
+
+Python dependencies must also be GPLv3 compatible.
+
+New non-Python dependencies
+===========================
+
+OCRmyPDF uses several external programs (Tesseract, Ghostscript and others) for
+its functionality. In general we prefer to avoid adding new external programs.

docs/cookbook.rst

@@ -1,166 +1,317 @@
+========
 Cookbook
 ========
 
 Basic examples
---------------
+==============
 
 Help!
-"""""
+-----
 
 ocrmypdf has built-in help.
 
 .. code-block:: bash
 
-	ocrmypdf --help
-
+    ocrmypdf --help
 
 Add an OCR layer and convert to PDF/A
-"""""""""""""""""""""""""""""""""""""
+-------------------------------------
 
 .. code-block:: bash
 
-	ocrmypdf input.pdf output.pdf
+    ocrmypdf input.pdf output.pdf
 
 Add an OCR layer and output a standard PDF
-""""""""""""""""""""""""""""""""""""""""""
+------------------------------------------
 
 .. code-block:: bash
 
-	ocrmypdf --output-type pdf input.pdf output.pdf
+    ocrmypdf --output-type pdf input.pdf output.pdf
 
 Create a PDF/A with all color and grayscale images converted to JPEG
-""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""
+--------------------------------------------------------------------
 
 .. code-block:: bash
 
-	ocrmypdf --output-type pdfa --pdfa-image-compression jpeg input.pdf output.pdf
+    ocrmypdf --output-type pdfa --pdfa-image-compression jpeg input.pdf output.pdf
 
 Modify a file in place
-""""""""""""""""""""""
+----------------------
 
 The file will only be overwritten if OCRmyPDF is successful.
 
 .. code-block:: bash
 
-	ocrmypdf myfile.pdf myfile.pdf
+    ocrmypdf myfile.pdf myfile.pdf
 
 Correct page rotation
-"""""""""""""""""""""
+---------------------
 
-OCR will attempt to automatic correct the rotation of each page. This can help fix a scanning job that contains a mix of landscape and portrait pages.
+OCR will attempt to automatic correct the rotation of each page. This
+can help fix a scanning job that contains a mix of landscape and
+portrait pages.
 
 .. code-block:: bash
 
-	ocrmypdf --rotate-pages myfile.pdf myfile.pdf
+    ocrmypdf --rotate-pages myfile.pdf myfile.pdf
 
-You can increase (decrease) the parameter ``--rotate-pages-threshold`` to make page rotation more (less) aggressive.
+You can increase (decrease) the parameter ``--rotate-pages-threshold``
+to make page rotation more (less) aggressive.
 
+If the page is "just a little off horizontal", like a crooked picture,
+then you want ``--deskew``. ``--rotate-pages`` is for when the cardinal
+angle is wrong.
 
 OCR languages other than English
-""""""""""""""""""""""""""""""""
+--------------------------------
 
-By default OCRmyPDF assumes the document is English. 
+OCRmyPDF assumes the document is in English unless told otherwise. OCR
+quality may be poor if the wrong language is used.
 
 .. code-block:: bash
 
-	ocrmypdf -l fre LeParisien.pdf LeParisien.pdf
-	ocrmypdf -l eng+fre Bilingual-English-French.pdf Bilingual-English-French.pdf
+    ocrmypdf -l fra LeParisien.pdf LeParisien.pdf
+    ocrmypdf -l eng+fra Bilingual-English-French.pdf Bilingual-English-French.pdf
 
-Language packs must be installed for all languages specified. See :ref:`Installing additional language packs <lang-packs>`.
+Language packs must be installed for all languages specified. See
+:ref:`Installing additional language packs <lang-packs>`.
 
+Unfortunately, the Tesseract OCR engine has no ability to detect the
+language when it is unknown.
 
 Produce PDF and text file containing OCR text
-"""""""""""""""""""""""""""""""""""""""""""""
-
-This produces a file named "output.pdf" and a companion text file named "output.txt". The ``pdftotext`` program from 
-`Poppler <https://poppler.freedesktop.org/>`_ is used to extract text from the finished PDF.
+---------------------------------------------
 
+This produces a file named "output.pdf" and a companion text file named
+"output.txt".
 
 .. code-block:: bash
 
-	ocrmypdf input.pdf - | tee output.pdf | pdftotext - output.txt
-
-.. note::
-
-	To get pdftotext, Debian/Ubuntu users may ``apt-get install poppler-utils`` 
-	and macOS users may ``brew install poppler`` respectively.
-
+    ocrmypdf --sidecar output.txt input.pdf output.pdf
 
 OCR images, not PDFs
 --------------------
 
-Use a program like `img2pdf <https://gitlab.mister-muffin.de/josch/img2pdf>`_ to convert your images to PDFs, and then pipe the results to run ocrmypdf:
+Option: use Tesseract
+~~~~~~~~~~~~~~~~~~~~~
+
+If you are starting with images, you can just use Tesseract directly to
+convert images to PDFs:
 
 .. code-block:: bash
 
-	img2pdf my-images*.jpg | ocrmypdf - myfile.pdf
-
-``img2pdf`` also has features to control the position of images on a page, if desired.
-
-For convenience, OCRmyPDF can convert single images to PDFs on its own. If the resolution (dots per inch, DPI) of an image is not set or is incorrect, it can be overridden with ``--image-dpi``. (As 1 inch is 2.54 cm, 1 dpi = 0.39 dpcm).
+    tesseract my-image.jpg output-prefix pdf
 
 .. code-block:: bash
 
-	ocrmypdf --image-dpi 300 image.png myfile.pdf
+    # When there are multiple images
+    tesseract text-file-containing-list-of-image-filenames.txt output-prefix pdf
 
-If you have multiple images, you must use ``img2pdf`` to convert the images to PDF.
+Tesseract's PDF output is quite good – OCRmyPDF uses it internally, in
+some cases. However, OCRmyPDF has many features not available in
+Tesseract like image processing, metadata control, and PDF/A generation.
 
-.. note::
+Option: use img2pdf
+~~~~~~~~~~~~~~~~~~~
 
-    ImageMagick ``convert`` can also convert a group of images to PDF, but in the author's experience it takes a long time, transcodes unnecessarily and gives poor results.
-
-You can also use Tesseract 3.04+ directly to convert single page images or multi-page TIFFs to PDF:
+You can also use a program like
+`img2pdf <https://gitlab.mister-muffin.de/josch/img2pdf>`__ to convert
+your images to PDFs, and then pipe the results to run ocrmypdf. The
+``-`` tells ocrmypdf to read standard input.
 
 .. code-block:: bash
 
-	tesseract my-image.jpg output-prefix pdf 
+    img2pdf my-images*.jpg | ocrmypdf - myfile.pdf
+
+``img2pdf`` is recommended because it does an excellent job at
+generating PDFs without transcoding images.
+
+Option: use OCRmyPDF (single images only)
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+For convenience, OCRmyPDF can also convert single images to PDFs on its
+own. If the resolution (dots per inch, DPI) of an image is not set or is
+incorrect, it can be overridden with ``--image-dpi``. (As 1 inch is 2.54
+cm, 1 dpi = 0.39 dpcm).
+
+.. code-block:: bash
+
+    ocrmypdf --image-dpi 300 image.png myfile.pdf
+
+If you have multiple images, you must use ``img2pdf`` to convert the
+images to PDF.
+
+Not recommended
+~~~~~~~~~~~~~~~
+
+We caution against using ImageMagick or Ghostscript to convert images to
+PDF, since they may transcode images or produce downsampled images,
+sometimes without warning.
 
 Image processing
-----------------
+================
 
-OCRmyPDF perform some image processing on each page of a PDF, if desired.  The same processing is applied to each page.  It is suggested that the user review files after image processing as these commands might remove desirable content, especially from poor quality scans.
+OCRmyPDF perform some image processing on each page of a PDF, if
+desired. The same processing is applied to each page. It is suggested
+that the user review files after image processing as these commands
+might remove desirable content, especially from poor quality scans.
 
-* ``--rotate-pages`` attempts to determine the correct orientation for each page and rotates the page if necessary.
-
-* ``--remove-background`` attempts to detect and remove a noisy background from grayscale or color images.  Monochrome images are ignored. This should not be used on documents that contain color photos as it may remove them.
-
-* ``--deskew`` will correct pages were scanned at a skewed angle by rotating them back into place.  Skew determination and correction is performed using `Postl's variance of line sums <http://www.leptonica.com/skew-measurement.html>`_ algorithm as implemented in `Leptonica <http://www.leptonica.com/index.html>`_.
-  
-* ``--clean`` uses `unpaper <https://www.flameeyes.eu/projects/unpaper>`_ to clean up pages before OCR, but does not alter the final output.  This makes it less likely that OCR will try to find text in background noise.
-
-* ``--clean-final`` uses unpaper to clean up pages before OCR and inserts the page into the final output.  You will want to review each page to ensure that unpaper did not remove something important.
+-  ``--rotate-pages`` attempts to determine the correct orientation for
+   each page and rotates the page if necessary.
+-  ``--remove-background`` attempts to detect and remove a noisy
+   background from grayscale or color images. Monochrome images are
+   ignored. This should not be used on documents that contain color
+   photos as it may remove them.
+-  ``--deskew`` will correct pages were scanned at a skewed angle by
+   rotating them back into place. Skew determination and correction is
+   performed using `Postl's variance of line
+   sums <http://www.leptonica.org/skew-measurement.html>`__ algorithm as
+   implemented in `Leptonica <http://www.leptonica.org/index.html>`__.
+-  ``--clean`` uses
+   `unpaper <https://www.flameeyes.eu/projects/unpaper>`__ to clean up
+   pages before OCR, but does not alter the final output. This makes it
+   less likely that OCR will try to find text in background noise.
+-  ``--clean-final`` uses unpaper to clean up pages before OCR and
+   inserts the page into the final output. You will want to review each
+   page to ensure that unpaper did not remove something important.
 
 .. note::
 
-	In many cases image processing will rasterize PDF pages as images, potentially losing quality.
+   In many cases image processing will rasterize PDF pages as images,
+   potentially losing quality.
 
 .. warning::
 
-	``--clean-final`` and ``-remove-background`` may leave undesirable visual artifacts in some images where their algorithms have shortcomings. Files should be visually reviewed after using these options.
+   ``--clean-final`` and ``-remove-background`` may leave undesirable
+   visual artifacts in some images where their algorithms have
+   shortcomings. Files should be visually reviewed after using these
+   options.
 
-
-OCR and correct document skew (crooked scan)
-""""""""""""""""""""""""""""""""""""""""""""
+Example: OCR and correct document skew (crooked scan)
+-----------------------------------------------------
 
 Deskew:
 
 .. code-block:: bash
 
-	ocrmypdf --deskew input.pdf output.pdf
+    ocrmypdf --deskew input.pdf output.pdf
 
-Image processing commands can be combined. The order in which options are given does not matter. OCRmyPDF always applies the steps of the image processing pipeline in the same order (rotate, remove background, deskew, clean).
+Image processing commands can be combined. The order in which options
+are given does not matter. OCRmyPDF always applies the steps of the
+image processing pipeline in the same order (rotate, remove background,
+deskew, clean).
 
 .. code-block:: bash
 
-	ocrmypdf --deskew --clean --rotate-pages input.pdf output.pdf
+    ocrmypdf --deskew --clean --rotate-pages input.pdf output.pdf
 
+Don't actually OCR my PDF
+=========================
+
+If you set ``--tesseract-timeout 0`` OCRmyPDF will apply its image
+processing without performing OCR, if all you want to is to apply image
+processing or PDF/A conversion.
+
+.. code-block:: bash
+
+    ocrmypdf --tesseract-timeout=0 --remove-background input.pdf output.pdf
+
+Optimize images without performing OCR
+--------------------------------------
+
+You can also optimize all images without performing any OCR:
+
+.. code-block:: bash
+
+    ocrmypdf --tesseract-timeout=0 --optimize 3 --skip-text input.pdf output.pdf
+
+Redo existing OCR
+=================
+
+To redo OCR on a file OCRed with other OCR software or a previous
+version of OCRmyPDF and/or Tesseract, you may use the ``--redo-ocr``
+argument. (Normally, OCRmyPDF will exit with an error if asked to modify
+a file with OCR.)
+
+This may be helpful for users who want to take advantage of accuracy
+improvements in Tesseract 4.0 for files they previously OCRed with an
+earlier version of Tesseract and OCRmyPDF.
+
+.. code-block:: bash
+
+    ocrmypdf --redo-ocr input.pdf output.pdf
+
+This method will replace OCR without rasterizing, reducing quality or
+removing vector content. If a file contains a mix of pure digital text
+and OCR, digital text will be ignored and OCR will be replaced. As such
+this mode is incompatible with image processing options, since they
+alter the appearance of the file.
+
+In some cases, existing OCR cannot be detected or replaced. Files
+produced by OCRmyPDF v2.2 or earlier, for example, are internally
+represented as having visible text with an opaque image drawn on top.
+This situation cannot be detected.
+
+If ``--redo-ocr`` does not work, you can use ``--force-ocr``, which will
+force rasterization of all pages, potentially reducing quality or losing
+vector content.
 
 Improving OCR quality
----------------------
+=====================
 
-The `Image processing`_ features can improve OCR quality.
+The `Image processing <#image-processing>`__ features can improve OCR
+quality.
 
-Rotating pages and deskewing helps to ensure that the page orientation is correct before OCR begins. Removing the background and/or cleaning the page can also improve results. The ``--oversample DPI`` argument can be specified to resample images to higher resolution before attempting OCR; this can improve results as well.
+Rotating pages and deskewing helps to ensure that the page orientation
+is correct before OCR begins. Removing the background and/or cleaning
+the page can also improve results. The ``--oversample DPI`` argument can
+be specified to resample images to higher resolution before attempting
+OCR; this can improve results as well.
 
-OCR quality will suffer if the resolution of input images is not correct (since the range of pixel sizes that will be checked for possible fonts will also be incorrect).
+OCR quality will suffer if the resolution of input images is not correct
+(since the range of pixel sizes that will be checked for possible fonts
+will also be incorrect).
 
+PDF optimization
+================
+
+By default OCRmyPDF will attempt to perform lossless optimizations on
+the images inside PDFs after OCR is complete. Optimization is performed
+even if no OCR text is found.
+
+The ``--optimize N`` (short form ``-O``) argument controls optimization,
+where ``N`` ranges from 0 to 3 inclusive, analogous to the optimization
+levels in the GCC compiler.
+
+.. list-table::
+    :widths: auto
+    :header-rows: 1
+
+    *   - Level
+        - Comments
+    *   - ``--optimize 0``
+        - Disables optimization.
+    *   - ``--optimize 1``
+        - Enables lossless optimizations, such as transcoding images to more
+          efficient formats. Also compress other uncompressed objects in the
+          PDF and enables the more efficient "object streams" within the PDF.
+    *   - ``--optimize 2``
+        - All of the above, and enables lossy optimizations and color quantization.
+    *   - ``--optimize 3``
+        - All of the above, and enables more aggressive optimizations and targets lower image quality.
+
+Optimization is improved when a JBIG2 encoder is available and when
+``pngquant`` is installed. If either of these components are missing,
+then some types of images cannot be optimized.
+
+The types of optimization available may expand over time. By default,
+OCRmyPDF compresses data streams inside PDFs, and will change
+inefficient compression modes to more modern versions. A program like
+``qpdf`` can be used to change encodings, e.g. to inspect the internals
+fo a PDF.
+
+.. code-block:: bash
+
+    ocrmypdf --optimize 3 in.pdf out.pdf  # Make it small
+
+Some users may consider enabling lossy JBIG2. See: :ref:`jbig2-lossy`.

docs/docker.rst

@@ -0,0 +1,170 @@
+=====================
+OCRmyPDF Docker image
+=====================
+
+OCRmyPDF is also available in a Docker image that packages recent
+versions of all dependencies.
+
+For users who already have Docker installed this may be an easy and
+convenient option. However, it is less performant than a system
+installation and may require Docker engine configuration.
+
+OCRmyPDF needs a generous amount of RAM, CPU cores, temporary storage
+space, whether running in a Docker container or on its own. It may be
+necessary to ensure the container is provisioned with additional
+resources.
+
+.. _docker-install:
+
+Installing the Docker image
+===========================
+
+If you have `Docker <https://docs.docker.com/>`__ installed on your
+system, you can install a Docker image of the latest release.
+
+If you can run this command successfully, your system is ready to download and
+execute the image:
+
+.. code-block:: bash
+
+   docker run hello-world
+
+The recommended OCRmyPDF Docker image is currently named ``ocrmypdf``:
+
+.. code-block:: bash
+
+   docker pull jbarlow83/ocrmypdf
+
+
+OCRmyPDF will use all available CPU cores. By default, the VirtualBox
+machine instance on Windows and macOS has only a single CPU core
+enabled. Use the VirtualBox Manager to determine the name of your Docker
+engine host, and then follow these optional steps to enable multiple
+CPUs:
+
+.. code-block:: bash
+
+   # Optional step for Mac OS X users
+   docker-machine stop "yourVM"
+   VBoxManage modifyvm "yourVM" --cpus 2  # or whatever number of core is desired
+   docker-machine start "yourVM"
+   eval $(docker-machine env "yourVM")
+
+See the Docker documentation for
+`adjusting memory and CPU on other platforms <https://docs.docker.com/config/containers/resource_constraints/>`__.
+
+Using the Docker image on the command line
+==========================================
+
+**Unlike typical Docker containers**, in this mode we are using the
+OCRmyPDF Docker container is intended to be emphemeral – it runs for one
+OCR job and then terminates, just like a command line program. We are
+using Docker as a way of delivering an application, not a server.
+
+To start a Docker container (instance of the image):
+
+.. code-block:: bash
+
+   docker tag jbarlow83/ocrmypdf ocrmypdf
+   docker run --rm -i ocrmypdf (... all other arguments here...)
+
+For convenience, create a shell alias to hide the Docker command. It is
+easier to send the input file to file stdin and read the output from
+stdout – this avoids the occasionally messy permission issues with
+Docker entirely.
+
+.. code-block:: bash
+
+   alias ocrmypdf='docker run --rm -i ocrmypdf'
+   ocrmypdf --version  # runs docker version
+   ocrmypdf <input.pdf >output.pdf
+
+Or in the wonderful `fish shell <https://fishshell.com/>`__:
+
+.. code-block:: fish
+
+   alias ocrmypdf 'docker run --rm ocrmypdf'
+   funcsave ocrmypdf
+
+Alternately, you could mount the local current working directory as a
+Docker volume:
+
+.. code-block:: bash
+
+   docker run --rm -v $(pwd):/data ocrmypdf /data/input.pdf /data/output.pdf
+
+.. _docker-lang-packs:
+
+Adding languages to the Docker image
+====================================
+
+By default the Docker image includes English, German and Simplified
+Chinese, the most popular languages for OCRmyPDF users based on
+feedback. You may add other languages by creating a new Dockerfile based
+on the public one:
+
+.. code-block:: dockerfile
+
+   FROM jbarlow83/ocrmypdf
+
+   # Add French
+   RUN apt install tesseract-ocr-fra
+
+You can also copy training data to ``/usr/share/tesseract-ocr/<tesseract version>/tessdata``.
+
+Executing the test suite
+========================
+
+The OCRmyPDF test suite is installed with image. To run it:
+
+.. code-block:: bash
+
+   docker run --entrypoint python3  jbarlow83/ocrmypdf -m pytest
+
+Accessing the shell
+===================
+
+To use the bash shell in the Docker image:
+
+.. code-block:: bash
+
+   docker run -it --entrypoint bash  jbarlow83/ocrmypdf
+
+Using the OCRmyPDF web service wrapper
+======================================
+
+The OCRmyPDF Docker image includes an example, barebones HTTP web
+service. The webservice may be launched as follows:
+
+.. code-block:: bash
+
+   docker run --entrypoint python3 -p 5000:5000  jbarlow83/ocrmypdf webservice.py
+
+This will configure the machine to listen on port 5000. On Linux machines
+this is port 5000 of localhost. On macOS or Windows machines running
+Docker, this is port 5000 of the virtual machine that runs your Docker
+images. You can find its IP address using the command ``docker-machine ip``.
+
+Unlike command line usage this program will open a socket and wait for
+connections.
+
+.. warning::
+
+   The OCRmyPDF web service wrapper is intended for demonstration or
+   development. It provides no security, no authentication, no
+   protection against denial of service attacks, and no load balancing.
+   The default Flask WSGI server is used, which is intended for
+   development only. The server is single-threaded and so can respond to
+   only one client at a time. While running OCR, it cannot respond to
+   any other clients.
+
+Clients must keep their open connection while waiting for OCR to
+complete. This may entail setting a long timeout; this interface is more
+useful for internal HTTP API calls.
+
+Unlike the rest of OCRmyPDF, this web service is licensed under the
+Affero GPLv3 (AGPLv3) since Ghostscript, a dependency of OCRmyPDF, is
+also licensed in this way.
+
+In addition to the above, please read our
+:ref:`general remarks on using OCRmyPDF as a service <ocr-service>`.

docs/errors.rst

@@ -1,33 +1,47 @@
+=====================
 Common error messages
 =====================
 
 Page already has text
----------------------
+=====================
 
-.. code::
+.. code-block::
 
-	ERROR -    1: page already has text! – aborting (use --force-ocr to force OCR)
+   ERROR -    1: page already has text! – aborting (use --force-ocr to force OCR)
 
-You ran ocrmypdf on a file that already contains printable text or a hidden OCR text layer (it can't quite tell the difference). You probably don't want to do this, because the file is already searchable.
+You ran ocrmypdf on a file that already contains printable text or a
+hidden OCR text layer (it can't quite tell the difference). You probably
+don't want to do this, because the file is already searchable.
 
 As the error message suggests, your options are:
 
-- ``ocrmypdf --force-ocr`` to :ref:`rasterize <raster-vector>` all vector content and run OCR on the images. This is useful if a previous OCR program failed, or if the document contains a text watermark.
-
-- ``ocrmypdf --skip-text`` to skip OCR and other processing on any pages that contain text. Text pages will be copied into the output PDF without modification.
-
+-  ``ocrmypdf --force-ocr`` to :ref:`rasterize <raster-vector>` all
+   vector content and run OCR on the images. This is useful if a
+   previous OCR program failed, or if the document contains a text
+   watermark.
+-  ``ocrmypdf --skip-text`` to skip OCR and other processing on any
+   pages that contain text. Text pages will be copied into the output
+   PDF without modification.
 
 Input file 'filename' is not a valid PDF
-----------------------------------------
+========================================
 
-OCRmyPDF passes files through qpdf, a program that fixes errors in PDFs, before it tries to work on them. In most cases this happens because the PDF is corrupt and
-truncated (incomplete file copying) and not much can be done.
+OCRmyPDF passes files through qpdf, a program that fixes errors in PDFs,
+before it tries to work on them. In most cases this happens because the
+PDF is corrupt and truncated (incomplete file copying) and not much can
+be done.
 
-You can try rewriting the file with Ghostscript or pdftk:
+You can try rewriting the file with Ghostscript:
 
-- ``gs -o output.pdf -dSAFER -sDEVICE=pdfwrite input.pdf``
+.. code-block:: bash
 
-- ``pdftk input.pdf cat output output.pdf``
+    gs -o output.pdf -dSAFER -sDEVICE=pdfwrite input.pdf
 
-Sometimes Acrobat can repair PDFs with its `Preflight tool <https://helpx.adobe.com/acrobat/using/correcting-problem-areas-preflight-tool.html>`_.
+``pdftk`` can also rewrite PDFs:
 
+.. code-block:: bash
+
+    pdftk input.pdf cat output output.pdf
+
+Sometimes Acrobat can repair PDFs with its `Preflight
+tool <https://helpx.adobe.com/acrobat/using/correcting-problem-areas-preflight-tool.html>`__.

docs/images/logo.svg

@@ -0,0 +1,75 @@
+<?xml version="1.0" encoding="UTF-8" standalone="no"?>
+<!DOCTYPE svg PUBLIC "-//W3C//DTD SVG 1.1//EN" "http://www.w3.org/Graphics/SVG/1.1/DTD/svg11.dtd">
+<svg width="100%" height="100%" viewBox="0 0 503 227" version="1.1" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" xml:space="preserve" xmlns:serif="http://www.serif.com/" style="fill-rule:evenodd;clip-rule:evenodd;stroke-linecap:round;stroke-linejoin:round;stroke-miterlimit:1.5;">
+    <g id="svg" transform="matrix(0.965977,0,0,0.807602,0,0)">
+        <rect x="0" y="0" width="520" height="280" style="fill:white;"/>
+        <g transform="matrix(1.03522,0,0,1.23823,-69.7528,-83.422)">
+            <g transform="matrix(1,0,0,1,243.977,20.0703)">
+                <g id="Page">
+                    <g transform="matrix(0.961773,0,0,1.05962,6.19811,-3.01071)">
+                        <path d="M328.5,97.682C328.5,96.465 327.983,95.296 327.056,94.418C320.026,87.758 289.442,58.78 282.228,51.944C281.251,51.019 279.901,50.496 278.49,50.496C264.493,50.496 188.083,50.496 167.339,50.496C164.468,50.496 162.141,52.609 162.141,55.214C162.141,83.051 162.141,225.565 162.141,253.4C162.141,256.005 164.468,258.117 167.338,258.117C192.242,258.117 299.159,258.117 323.538,258.117C326.278,258.117 328.5,256.101 328.5,253.613C328.5,229.268 328.5,113.896 328.5,97.682Z" style="fill:rgb(253,253,253);stroke:rgb(51,51,51);stroke-width:3.95px;"/>
+                    </g>
+                    <g id="Dog-ear" serif:id="Dog ear" transform="matrix(1,0,0,1,-4,2)">
+                        <path d="M277.072,48.496L277.072,93.848C277.072,95.172 277.598,96.441 278.534,97.377C279.47,98.313 280.739,98.839 282.063,98.839C294.548,98.839 326.141,98.839 326.141,98.839" style="fill:rgb(245,245,245);stroke:rgb(51,51,51);stroke-width:4px;"/>
+                    </g>
+                </g>
+                <g transform="matrix(1,0,0,1,-29.6816,-0.395178)">
+                    <g transform="matrix(1.00243,0,0,1.11818,-144.72,-8.80181)">
+                        <path d="M465.73,119.654C465.73,117.605 463.874,115.941 461.588,115.941L310.259,115.941C307.973,115.941 306.117,117.605 306.117,119.654L306.117,183.108C306.117,185.157 307.973,186.821 310.259,186.821L461.588,186.821C463.874,186.821 465.73,185.157 465.73,183.108L465.73,119.654Z" style="fill:rgb(248,0,0);stroke:white;stroke-width:3.77px;"/>
+                    </g>
+                    <g transform="matrix(1.24571,0,0,1.35864,116.812,84.3924)">
+                        <g transform="matrix(64,0,0,64,42.1437,77.6203)">
+                            <path d="M0.084,0L0.084,-0.68L0.297,-0.68C0.371,-0.68 0.434,-0.663 0.487,-0.63C0.54,-0.596 0.566,-0.54 0.566,-0.462C0.566,-0.385 0.538,-0.328 0.481,-0.292C0.424,-0.255 0.36,-0.237 0.288,-0.237L0.213,-0.237L0.213,0L0.084,0ZM0.293,-0.572L0.213,-0.572L0.213,-0.344L0.295,-0.344C0.334,-0.344 0.365,-0.353 0.389,-0.371C0.413,-0.388 0.426,-0.416 0.429,-0.454C0.429,-0.498 0.417,-0.529 0.393,-0.546C0.369,-0.563 0.336,-0.572 0.293,-0.572Z" style="fill:white;fill-rule:nonzero;"/>
+                        </g>
+                        <g transform="matrix(64,0,0,64,79.7117,77.6203)">
+                            <path d="M0.332,0L0.084,0L0.084,-0.68L0.336,-0.68C0.441,-0.68 0.518,-0.648 0.569,-0.585C0.62,-0.522 0.645,-0.441 0.645,-0.344C0.645,-0.239 0.618,-0.155 0.563,-0.093C0.508,-0.031 0.431,0 0.332,0ZM0.337,-0.57L0.213,-0.57L0.213,-0.109L0.33,-0.109C0.385,-0.109 0.429,-0.127 0.462,-0.163C0.495,-0.199 0.511,-0.259 0.511,-0.344C0.511,-0.415 0.497,-0.47 0.469,-0.51C0.441,-0.55 0.397,-0.57 0.337,-0.57Z" style="fill:white;fill-rule:nonzero;"/>
+                        </g>
+                        <g transform="matrix(64,0,0,64,123.424,77.6203)">
+                            <path d="M0.405,-0.288L0.213,-0.288L0.213,0L0.084,0L0.084,-0.68L0.469,-0.68L0.489,-0.578L0.213,-0.578L0.213,-0.389L0.386,-0.389L0.405,-0.288Z" style="fill:white;fill-rule:nonzero;"/>
+                        </g>
+                    </g>
+                </g>
+            </g>
+            <g transform="matrix(1,0,0,1.52217,67.3796,10.7507)">
+                <rect x="23.501" y="81.3" width="162.305" height="61.77" style="fill:rgb(180,213,255);"/>
+            </g>
+            <g transform="matrix(0.967536,0,0,0.961535,5.90498,47.9703)">
+                <g transform="matrix(90.4804,0,0,90.4804,82.6698,167.705)">
+                    <path d="M0.057,-0.337C0.057,-0.442 0.084,-0.527 0.139,-0.594C0.194,-0.66 0.271,-0.694 0.37,-0.696C0.477,-0.696 0.556,-0.662 0.607,-0.593C0.658,-0.524 0.684,-0.441 0.684,-0.344C0.684,-0.239 0.657,-0.153 0.602,-0.086C0.547,-0.019 0.469,0.014 0.37,0.014C0.264,0.014 0.185,-0.02 0.134,-0.089C0.083,-0.157 0.057,-0.24 0.057,-0.337ZM0.192,-0.338C0.192,-0.267 0.206,-0.208 0.235,-0.163C0.264,-0.118 0.308,-0.095 0.369,-0.095C0.424,-0.095 0.467,-0.115 0.5,-0.156C0.533,-0.197 0.549,-0.259 0.549,-0.344C0.549,-0.415 0.535,-0.473 0.506,-0.518C0.477,-0.563 0.433,-0.586 0.372,-0.586C0.319,-0.586 0.275,-0.564 0.242,-0.519C0.209,-0.474 0.192,-0.414 0.192,-0.338Z" style="fill:rgb(51,51,51);fill-rule:nonzero;"/>
+                </g>
+                <g transform="matrix(90.4804,0,0,90.4804,147.906,167.705)">
+                    <path d="M0.505,-0.557C0.473,-0.567 0.448,-0.574 0.429,-0.579C0.41,-0.583 0.388,-0.585 0.361,-0.585C0.307,-0.585 0.265,-0.563 0.236,-0.519C0.207,-0.475 0.192,-0.415 0.192,-0.338C0.192,-0.272 0.204,-0.215 0.229,-0.167C0.254,-0.119 0.295,-0.095 0.353,-0.095C0.382,-0.095 0.409,-0.098 0.434,-0.104C0.459,-0.11 0.481,-0.117 0.502,-0.126L0.551,-0.03C0.525,-0.017 0.494,-0.006 0.457,0.002C0.42,0.01 0.388,0.014 0.36,0.014C0.254,0.014 0.177,-0.02 0.129,-0.088C0.081,-0.156 0.057,-0.239 0.057,-0.337C0.057,-0.442 0.084,-0.527 0.137,-0.594C0.19,-0.661 0.266,-0.694 0.365,-0.694C0.385,-0.694 0.413,-0.691 0.448,-0.684C0.483,-0.677 0.516,-0.666 0.545,-0.65L0.505,-0.557Z" style="fill:rgb(51,51,51);fill-rule:nonzero;"/>
+                </g>
+                <g transform="matrix(90.4804,0,0,90.4804,199.751,167.705)">
+                    <path d="M0.293,-0.572L0.213,-0.572L0.213,-0.364L0.295,-0.364C0.334,-0.364 0.366,-0.372 0.391,-0.388C0.416,-0.403 0.429,-0.429 0.429,-0.465C0.429,-0.503 0.417,-0.53 0.393,-0.547C0.369,-0.564 0.336,-0.572 0.293,-0.572ZM0.479,0L0.335,-0.26C0.328,-0.259 0.32,-0.259 0.312,-0.259C0.304,-0.258 0.296,-0.258 0.288,-0.258L0.213,-0.258L0.213,0L0.084,0L0.084,-0.68L0.297,-0.68C0.371,-0.68 0.434,-0.663 0.487,-0.629C0.54,-0.595 0.566,-0.542 0.566,-0.471C0.566,-0.429 0.555,-0.393 0.534,-0.363C0.512,-0.332 0.484,-0.309 0.45,-0.292L0.617,0L0.479,0Z" style="fill:rgb(51,51,51);fill-rule:nonzero;"/>
+                </g>
+            </g>
+            <g transform="matrix(0.916882,0,0,1,121.475,-32.6535)">
+                <g transform="matrix(86.953,0,0,86.953,152.996,241.878)">
+                    <path d="M0.479,-0.428C0.5,-0.451 0.527,-0.47 0.562,-0.484C0.596,-0.497 0.627,-0.504 0.654,-0.504C0.72,-0.504 0.767,-0.485 0.795,-0.446C0.822,-0.407 0.836,-0.36 0.836,-0.304L0.836,0L0.705,0L0.705,-0.298C0.705,-0.329 0.698,-0.352 0.683,-0.369C0.668,-0.385 0.647,-0.393 0.619,-0.393C0.6,-0.393 0.581,-0.388 0.56,-0.378C0.539,-0.368 0.521,-0.357 0.504,-0.344C0.505,-0.337 0.505,-0.331 0.506,-0.324C0.507,-0.317 0.507,-0.311 0.507,-0.304L0.507,0L0.376,0L0.376,-0.298C0.376,-0.329 0.369,-0.352 0.354,-0.369C0.339,-0.385 0.318,-0.393 0.291,-0.393C0.274,-0.393 0.258,-0.39 0.241,-0.383C0.224,-0.376 0.207,-0.367 0.192,-0.356L0.192,0L0.062,0L0.062,-0.485L0.13,-0.485L0.162,-0.441C0.184,-0.461 0.211,-0.476 0.242,-0.488C0.273,-0.499 0.3,-0.504 0.325,-0.504C0.363,-0.504 0.395,-0.497 0.42,-0.484C0.445,-0.47 0.465,-0.451 0.479,-0.428Z" style="fill:rgb(51,51,51);fill-rule:nonzero;"/>
+                </g>
+                <g transform="matrix(86.953,0,0,86.953,228.906,241.878)">
+                    <path d="M0.156,0.023L0.179,-0.034L0.006,-0.467L0.14,-0.485L0.252,-0.191L0.358,-0.485L0.495,-0.485L0.278,0.064C0.263,0.103 0.236,0.137 0.197,0.165C0.158,0.193 0.118,0.212 0.075,0.222L0.029,0.115C0.052,0.105 0.077,0.093 0.104,0.079C0.13,0.064 0.147,0.046 0.156,0.023Z" style="fill:rgb(51,51,51);fill-rule:nonzero;"/>
+                </g>
+            </g>
+            <g id="Selectors" transform="matrix(0.965977,0,0,0.807602,67.3796,67.3718)">
+                <g id="Right-selector" serif:id="Right selector">
+                    <g transform="matrix(1.03522,0,0,1.23823,2.07044,0)">
+                        <path d="M185.806,161.156L185.806,67.132" style="fill:none;stroke:rgb(76,159,255);stroke-width:4px;stroke-linecap:butt;"/>
+                    </g>
+                    <g transform="matrix(1.03522,0,0,1.23823,161.788,169.469)">
+                        <circle cx="31.523" cy="34.314" r="10.021" style="fill:rgb(76,159,255);stroke:rgb(76,159,255);stroke-width:4px;stroke-linecap:butt;"/>
+                    </g>
+                </g>
+                <g id="Left-selector" serif:id="Left selector">
+                    <g transform="matrix(1.03522,0,0,1.23823,-170.092,0)">
+                        <path d="M185.806,161.156L185.806,67.132" style="fill:none;stroke:rgb(76,159,255);stroke-width:4px;stroke-linecap:butt;"/>
+                    </g>
+                    <g transform="matrix(1.03522,0,0,1.23823,-10.3742,28.2274)">
+                        <circle cx="31.523" cy="34.314" r="10.021" style="fill:rgb(76,159,255);stroke:rgb(76,159,255);stroke-width:4px;stroke-linecap:butt;"/>
+                    </g>
+                </g>
+            </g>
+        </g>
+    </g>
+</svg>

docs/index.rst

@@ -1,15 +1,10 @@
-.. ocrmypdf documentation master file, created by
-   sphinx-quickstart on Sun Sep  4 14:29:43 2016.
-   You can adapt this file completely to your liking, but it should at least
-   contain the root `toctree` directive.
-
 OCRmyPDF documentation
 ======================
 
 OCRmyPDF adds an OCR text layer to scanned PDF files, allowing them to
 be searched.
 
-PDFs are the best format for scanned documents.  Unfortunately, PDFs can be difficult to work with. OCRmyPDF makes it easy to apply image processing and OCR to existing PDFs.
+PDF is the best format for storing and exchanging scanned documents.  Unfortunately, PDFs can be difficult to modify. OCRmyPDF makes it easy to apply image processing and OCR to existing PDFs.
 
 .. toctree::
    :maxdepth: 1
@@ -17,18 +12,27 @@ PDFs are the best format for scanned documents.  Unfortunately, PDFs can be diff
    introduction
    release_notes
    installation
+   optimizer
    languages
+   jbig2
 
 .. toctree::
    :caption: Usage
    :maxdepth: 2
 
    cookbook
+   docker
    advanced
    batch
    security
    errors
 
+.. toctree::
+   :caption: Developers
+   :maxdepth: 2
+
+   api
+   contributing
 
 Indices and tables
 ==================
@@ -36,4 +40,3 @@ Indices and tables
 * :ref:`genindex`
 * :ref:`modindex`
 * :ref:`search`
-

docs/installation.rst

@@ -1,131 +1,361 @@
-Installation
-============
+===================
+Installing OCRmyPDF
+===================
 
-OCRmyPDF requires Python 3.5 (or newer) and Tesseract 3.04 (or newer).
+.. |latest| image:: https://img.shields.io/pypi/v/ocrmypdf.svg
+    :alt: OCRmyPDF latest released version on PyPI
 
-Installing on Debian and Ubuntu 16.10 or newer
-----------------------------------------------
+|latest|
 
-Users of Debian 9 ("stretch") or later or Ubuntu 16.10 or later may simply
+The easiest way to install OCRmyPDF is to follow the steps for your operating
+system/platform, although sometimes this version may be out of date.
+
+If you want to use the latest version of OCRmyPDF, your best bet is to install
+the most recent version your platform provides, and then upgrade that version by
+installing the Python binary wheels.
+
+.. contents:: Platform-specific steps
+    :depth: 2
+    :local:
+
+Installing on Linux
+===================
+
+Debian and Ubuntu 18.04 or newer
+--------------------------------
+
+.. |deb-stable| image:: https://repology.org/badge/version-for-repo/debian_stable/ocrmypdf.svg
+    :alt: Debian 9 stable ("stretch")
+
+.. |deb-testing| image:: https://repology.org/badge/version-for-repo/debian_testing/ocrmypdf.svg
+    :alt: Debian 10 testing ("buster")
+
+.. |deb-unstable| image:: https://repology.org/badge/version-for-repo/debian_unstable/ocrmypdf.svg
+    :alt: Debian unstable
+
+.. |ubu-1804| image:: https://repology.org/badge/version-for-repo/ubuntu_18_04/ocrmypdf.svg
+    :alt: Ubuntu 18.04 LTS
+
+.. |ubu-1810| image:: https://repology.org/badge/version-for-repo/ubuntu_18_10/ocrmypdf.svg
+    :alt: Ubuntu 18.10
+
+.. |ubu-1904| image:: https://repology.org/badge/version-for-repo/ubuntu_19_04/ocrmypdf.svg
+    :alt: Ubuntu 19.04
+
+.. |ubu-1910| image:: https://repology.org/badge/version-for-repo/ubuntu_19_10/ocrmypdf.svg
+    :alt: Ubuntu 19.10
+
++-----------------------------------------------+
+| **OCRmyPDF versions in Debian & Ubuntu**      |
++-----------------------------------------------+
+| |latest|                                      |
++-----------------------------------------------+
+| |deb-stable| |deb-testing| |deb-unstable|     |
++-----------------------------------------------+
+| |ubu-1804| |ubu-1810| |ubu-1904| |ubu-1910|   |
++-----------------------------------------------+
+
+Users of Debian 9 ("stretch") or later or Ubuntu 18.04 or later may
+simply
 
 .. code-block:: bash
 
     apt-get install ocrmypdf
 
-Installing on macOS
--------------------
+As indicated in the table above, Debian and Ubuntu releases may lag
+behind the latest version. If the version available for your platform is
+out of date, you could opt to install the latest version from source.
+See `Installing HEAD revision from
+sources <#installing-head-revision-from-sources>`__. Ubuntu 16.10 to 17.10
+inclusive also had ocrmypdf, but these versions are end of life.
 
-A `Homebrew <https://brew.sh>`_ tap is available for macOS:
+For full details on version availability for your platform, check the
+`Debian Package Tracker <https://tracker.debian.org/pkg/ocrmypdf>`__ or
+`Ubuntu launchpad.net <https://launchpad.net/ocrmypdf>`__.
+
+.. note::
+
+   OCRmyPDF for Debian and Ubuntu currently omit the JBIG2 encoder.
+   OCRmyPDF works fine without it but will produce larger output files.
+   If you build jbig2enc from source, ocrmypdf 7.0.0 and later will
+   automatically detect it (specifically the ``jbig2`` binary) on the
+   ``PATH``. To add JBIG2 encoding, see :ref:`jbig2`.
+
+Fedora 29 or newer
+------------------
+
+.. |fedora-29| image:: https://repology.org/badge/version-for-repo/fedora_29/ocrmypdf.svg
+    :alt: Fedora 29
+
+.. |fedora-30| image:: https://repology.org/badge/version-for-repo/fedora_30/ocrmypdf.svg
+    :alt: Fedora 30
+
+.. |fedora-rawhide| image:: https://repology.org/badge/version-for-repo/fedora_rawhide/ocrmypdf.svg
+    :alt: Fedore Rawhide
+
++-----------------------------------------------+
+| **OCRmyPDF version**                          |
++-----------------------------------------------+
+| |latest|                                      |
++-----------------------------------------------+
+| |fedora-29| |fedora-30| |fedora-rawhide|      |
++-----------------------------------------------+
+
+Users of Fedora 29 later may simply
+
+.. code-block:: bash
+
+    dnf install ocrmypdf
+
+For full details on version availability, check the `Fedora Package
+Tracker <https://apps.fedoraproject.org/packages/ocrmypdf>`__.
+
+If the version available for your platform is out of date, you could opt
+to install the latest version from source. See `Installing HEAD revision
+from sources <#installing-head-revision-from-sources>`__.
+
+.. note::
+
+   OCRmyPDF for Fedora currently omits the JBIG2 encoder due to patent
+   issues. OCRmyPDF works fine without it but will produce larger output
+   files. If you build jbig2enc from source, ocrmypdf 7.0.0 and later
+   will automatically detect it on the ``PATH``. To add JBIG2 encoding,
+   see `Installing the JBIG2 encoder <jbig2>`__.
+
+.. _ubuntu-lts-latest:
+
+Installing the latest version on Ubuntu 18.04 LTS
+-------------------------------------------------
+
+Ubuntu 18.04 includes ocrmypdf 6.1.2. To install a more recent version,
+first install the system version to get most of the dependencies:
+
+.. code-block:: bash
+
+    sudo apt-get update
+    sudo apt-get install \
+        ocrmypdf
+
+There are a few system dependency changes since ocrmypdf 6.1.2. Let's
+get these, too.
+
+.. code-block:: bash
+
+    sudo apt-get install \
+        libxml2 \
+        pngquant
+
+We will need a newer version of ``pip`` then was available for Ubuntu 18.04:
+
+.. code-block:: bash
+
+    wget https://bootstrap.pypa.io/get-pip.py && python3 get-pip.py
+
+Then install the most recent ocrmypdf for the local user and set the
+user's ``PATH`` to check for the user's Python packages.
+
+.. code-block:: bash
+
+    export PATH=$HOME/.local/bin:$PATH
+    python3 -m pip install --user ocrmypdf
+
+To add JBIG2 encoding, see :ref:`jbig2`.
+
+Ubuntu 16.04 LTS
+----------------
+
+No package is available for Ubuntu 16.04. OCRmyPDF 8.0 and newer require
+Python 3.6. Ubuntu 16.04 ships Python 3.5, but you can install Python
+3.6 on it. Or, you can skip Python 3.6 and install OCRmyPDF 7.x or older
+- for that procedure, please see the installation documentation for the
+version of OCRmyPDF you plan to use.
+
+**Install system packages for OCRmyPDF**
+
+.. code-block:: bash
+
+    sudo apt-get update
+    sudo apt-get install -y software-properties-common python-software-properties
+    sudo add-apt-repository -y \
+        ppa:jonathonf/python-3.6 \
+        ppa:alex-p/tesseract-ocr
+    sudo apt-get update
+    sudo apt-get install -y \
+        ghostscript \
+        libexempi3 \
+        libffi6 \
+        pngquant \
+        python3.6 \
+        qpdf \
+        tesseract-ocr \
+        unpaper
+
+This will install a Python 3.6 binary at ``/usr/bin/python3.6``
+alongside the system's Python 3.5. Do not remove the system Python. This
+will also install Tesseract 4.0 from a PPA, since the version available
+in Ubuntu 16.04 is too old for OCRmyPDF.
+
+Now install pip for Python 3.6. This will install the Python 3.6 version
+of ``pip`` at ``/usr/local/bin/pip``.
+
+.. code-block:: bash
+
+    curl https://bootstrap.pypa.io/get-pip.py | sudo python3.6
+
+**Install OCRmyPDF**
+
+OCRmyPDF requires the locale to be set for UTF-8. **On some minimal
+Ubuntu installations systems**, it may be necessary to set the locale.
+
+.. code-block:: bash
+
+    # Optional: Only need to set these if they are not already set
+    export LC_ALL=C.UTF-8
+    export LANG=C.UTF-8
+
+Now install OCRmyPDF for the current user, and ensure that the ``PATH``
+environment variable contains ``$HOME/.local/bin``.
+
+.. code-block:: bash
+
+    export PATH=$HOME/.local/bin:$PATH
+    pip3 install --user ocrmypdf
+
+To add JBIG2 encoding, see :ref:`jbig2`.
+
+Ubuntu 14.04 LTS
+----------------
+
+Installing on Ubuntu 14.04 LTS (trusty) is more difficult than some
+other options, because of its age. Several backports are required. For
+explanations of some steps of this procedure, see the similar steps for
+Ubuntu 16.04.
+
+Install system dependencies:
+
+.. code-block:: bash
+
+    sudo apt-get update
+    sudo apt-get install \
+        software-properties-common python-software-properties \
+        zlib1g-dev \
+        libexempi3 \
+        libjpeg-dev \
+        libffi-dev \
+        pngquant \
+        qpdf
+
+We will need backports of Ghostscript 9.16, libav-11 (for unpaper 6.1),
+Tesseract 4.00 (alpha), and Python 3.6. This will replace Ghostscript
+and Tesseract 3.x on your system. Python 3.6 will be installed alongside
+the system Python 3.4.
+
+If you prefer to not modify your system in this matter, consider using a
+Docker container.
+
+.. code-block:: bash
+
+    sudo add-apt-repository ppa:vshn/ghostscript -y
+    sudo add-apt-repository ppa:heyarje/libav-11 -y
+    sudo add-apt-repository ppa:alex-p/tesseract-ocr -y
+    sudo add-apt-repository ppa:jonathonf/python-3.6 -y
+
+    sudo apt-get update
+
+    sudo apt-get install \
+        python3.6-dev \
+        ghostscript \
+        tesseract-ocr \
+        tesseract-ocr-eng \
+        libavformat56 libavcodec56 libavutil54 \
+        wget
+
+Now we need to install ``pip`` and let it install ocrmypdf:
+
+.. code-block:: bash
+
+    curl https://bootstrap.pypa.io/ez_setup.py -o - | python3.6 && python3.6 -m easy_install pip
+    pip3.6 install ocrmypdf
+
+The optional dependency ``unpaper`` is only available at 0.4.2 in Ubuntu 14.04,
+and no backports are available. Previously the author maintained a backported
+.deb package for unpaper 6.1, but since Ubuntu 14.04 is now end of life, this is
+not supported. As such, ``unpaper`` is not available on Ubuntu 14.04 or must by
+compiled by hand.
+
+To add JBIG2 encoding, see :ref:`jbig2`.
+
+ArchLinux (AUR)
+---------------
+
+.. image:: https://repology.org/badge/version-for-repo/aur/ocrmypdf.svg
+    :alt: ArchLinux
+    :target: https://repology.org/metapackage/ocrmypdf
+
+There is an `ArchLinux User Repository package for
+ocrmypdf <https://aur.archlinux.org/packages/ocrmypdf/>`__. You can use
+the following command.
+
+.. code-block:: bash
+
+    yaourt -S ocrmypdf
+
+If you have any difficulties with installation, check the repository
+package page.
+
+Other Linux packages
+--------------------
+
+See the
+`Repology <https://repology.org/metapackage/ocrmypdf/versions>`__ page.
+
+In general, first install the OCRmyPDF package for your system, then
+optionally use the procedure `Installing with Python
+pip <#installing-with-python-pip>`__ to install a more recent version.
+
+Installing on macOS
+===================
+
+Homebrew
+--------
+
+.. image:: https://img.shields.io/homebrew/v/ocrmypdf.svg
+    :alt: homebrew
+    :target: http://brewformulas.org/Ocrmypdf
+
+OCRmyPDF is now a standard `Homebrew <https://brew.sh>`__ formula. To
+install on macOS:
 
 .. code-block:: bash
 
-    brew tap jbarlow83/ocrmypdf
     brew install ocrmypdf
 
-
-.. warning::
-
-    Users who previously installed OCRmyPDF on macOS using ``pip install ocrmypdf`` should remove the pip version (``pip3 uninstall ocrmypdf``) before switching to the Homebrew version.
-
-.. _Docker-install:
-
-Installing the Docker image
----------------------------
-
-For many users, installing the Docker image will be easier than installing all of OCRmyPDF's dependencies. For Windows, it is the only option.
-
-If you have `Docker <https://docs.docker.com/>`_ installed on your system, you can install
-a Docker image of the latest release.
-
-Follow the Docker installation instructions for your platform.  If you can run this command
-successfully, your system is ready to download and execute the image:
+This will include only the English language pack. If you need other
+languages you can optionally install them all:
 
 .. code-block:: bash
 
-    docker run hello-world
-   
-OCRmyPDF will use all available CPU cores.  By default, the VirtualBox machine instance on Windows and macOS has only a single CPU core enabled. Use the VirtualBox Manager to determine the name of your Docker engine host, and then follow these optional steps to enable multiple CPUs:
+    brew install tesseract-lang  # Optional: Install all language packs
 
-.. code-block:: bash
+.. note::
 
-    # Optional step for Mac OS X users
-    docker-machine stop "yourVM"
-    VBoxManage modifyvm "yourVM" --cpus 2  # or whatever number of core is desired
-    docker-machine start "yourVM"
-    eval $(docker-machine env "yourVM")
+   Users who previously installed OCRmyPDF on macOS using
+   ``pip install ocrmypdf`` should remove the pip version
+   (``pip3 uninstall ocrmypdf``) before switching to the Homebrew
+   version.
 
-Assuming you have a Docker engine running, you can download one of the three available images:
-
-+-----------------------------+---------------------------------------------+---------------------------------------------------------------------------------+
-| Image name                  | Download command                            | Notes                                                                           |
-+-----------------------------+---------------------------------------------+---------------------------------------------------------------------------------+
-| ocrmypdf                    | ``docker pull jbarlow83/ocrmypdf``          | Latest ocrmypdf with Tesseract 3.04. Includes English, French, German, Spanish. |
-+-----------------------------+---------------------------------------------+---------------------------------------------------------------------------------+
-| ocrmypdf-polyglot           | ``docker pull jbarlow83/ocrmypdf-polyglot`` | As above, with all available language packs.                                    |
-+-----------------------------+---------------------------------------------+---------------------------------------------------------------------------------+
-| ocrmypdf-tess4              | ``docker pull jbarlow83/ocrmypdf-tess4``    | Latest ocrmypdf with Tesseract 4.00.00alpha and English, French, German,        |
-|                             |                                             | Spanish, Portuguese, Chinese Simplified, Arabic and Russian (the top 8).        |
-+-----------------------------+---------------------------------------------+---------------------------------------------------------------------------------+
-
-For example:
-
-.. code-block:: bash
-
-    docker pull jbarlow83/ocrmypdf-tess4
-
-Then tag it to give a more convenient name, just ocrmypdf:
-
-.. code-block:: bash
-
-    docker tag jbarlow83/ocrmypdf-tess4 ocrmypdf
-
-.. _docker-polyglot:
-
-The alternative "polyglot" image provides `all available language packs <https://github.com/tesseract-ocr/tesseract/blob/master/doc/tesseract.1.asc#languages>`_.
-
-You can then run ocrmypdf using the command:
-
-.. code-block:: bash
-
-    docker run --rm ocrmypdf --help
-  
-To execute the OCRmyPDF on a local file, you must `provide a writable volume to the Docker image <https://docs.docker.com/userguide/dockervolumes/>`_, and both the input and output file must be inside the writable volume.  This example command uses the current working directory as the writable volume:
-
-.. code-block:: bash
-
-    docker run --rm -v "$(pwd):/home/docker" <other docker arguments>   ocrmypdf <your arguments to ocrmypdf>
-
-In this worked example, the current working directory contains an input file called ``test.pdf`` and the output will go to ``output.pdf``: 
-
-.. code-block:: bash
-
-    docker run --rm -v "$(pwd):/home/docker"   ocrmypdf --skip-text test.pdf output.pdf
-
-.. note:: The working directory should be a writable local volume or Docker may not have permission to access it.
-
-Note that ``ocrmypdf`` has its own separate ``-v VERBOSITYLEVEL`` argument to control debug verbosity. All Docker arguments should before the ``ocrmypdf`` image name and all arguments to ``ocrmypdf`` should be listed after.
-
-For convenience, a shell alias can hide the docker command:
-
-.. code-block:: bash
-
-    alias ocrmypdf='docker run --rm -v "$(pwd):/home/docker" ocrmypdf'
-    ocrmypdf --version  # runs docker version
-
-Or in the wonderful `fish shell <https://fishshell.com/>`_:
-
-.. code-block:: fish
-
-    alias ocrmypdf 'docker run --rm -v (pwd):/home/docker ocrmypdf'
-    funcsave ocrmypdf
+.. note::
 
+   Users who previously installed OCRmyPDF from the private tap should
+   switch to the mainline version (``brew untap jbarlow83/ocrmypdf``)
+   and install from there.
 
 Manual installation on macOS
 ----------------------------
 
 These instructions probably work on all macOS supported by Homebrew.
 
-If it's not already present, `install Homebrew <http://brew.sh/>`_.
+If it's not already present, `install Homebrew <http://brew.sh/>`__.
 
 Update Homebrew:
 
@@ -133,39 +363,38 @@ Update Homebrew:
 
     brew update
 
-Install or upgrade the required Homebrew packages, if any are missing:
+Install or upgrade the required Homebrew packages, if any are missing.
+To do this, download the ``Brewfile`` that lists all of the dependencies
+to the current directory, and run ``brew bundle`` to process them
+(installing or upgrading as needed). ``Brewfile`` is a plain text file.
 
 .. code-block:: bash
 
-    brew install libpng openjpeg jbig2dec libtiff     # image libraries
-    brew install qpdf
-    brew install ghostscript
-    brew install python3
-    brew install libxml2 libffi leptonica
-    brew install unpaper   # optional
-   
-Python 3.5 and 3.6 are supported.
+    wget https://github.com/jbarlow83/OCRmyPDF/raw/master/.travis/Brewfile
+    brew bundle
 
-Install the required Tesseract OCR engine with the language packs you plan to use:
-   
-.. code-block:: bash
-
-    brew install tesseract                       # Option 1: for English, French, German, Spanish
+This will include the English, French, German and Spanish language
+packs. If you need other languages you can optionally install them all:
 
 .. _macos-all-languages:
 
-.. code-block:: bash
+   .. code-block:: bash
 
     brew install tesseract --with-all-languages  # Option 2: for all language packs
 
-Update the homebrew pip and install Pillow:
+Update the homebrew pip:
 
 .. code-block:: bash
 
     pip3 install --upgrade pip
-    pip3 install --upgrade pillow
 
-You can then install OCRmyPDF from PyPI:
+You can then install OCRmyPDF from PyPI, for the current user:
+
+.. code-block:: bash
+
+    pip3 install --user ocrmypdf
+
+or system-wide:
 
 .. code-block:: bash
 
@@ -177,165 +406,178 @@ The command line program should now be available:
 
     ocrmypdf --help
 
+Installing on FreeBSD
+=====================
 
-Installing on Ubuntu 16.04 LTS
-------------------------------
+.. image:: https://repology.org/badge/version-for-repo/freebsd/python:ocrmypdf.svg
+    :alt: FreeBSD
+    :target: https://repology.org/project/python:ocrmypdf/versions
 
-No package is currently available for Ubuntu 16.04, but you can install the dependencies manually:
+FreeBSD 11.2, 11.3, 12.0-RELEASE and 13.0-CURRENT are supported. Other
+versions likely work but have not been tested.
 
 .. code-block:: bash
 
-    sudo apt-get update
-    sudo apt-get install \
-        unpaper \
-        ghostscript \
-        tesseract-ocr \
-        qpdf \
-        python3-pip \
-        python3-cffi
+    pkg install py36-ocrmypdf
 
-If you wish install OCRmyPDF to the system Python, then install as follows (note this installs new packages
-into your system Python, which could interfere with other programs):
+To install a more recent version, you could attempt to first install the system
+version with ``pkg``, then use ``pip install --user ocrmypdf``.
 
-.. code-block:: bash
+Installing the Docker image
+===========================
 
-    sudo pip3 install ocrmypdf
-
-If you wish to install OCRmyPDF to a virtual environment to isolate the system Python, you can
-follow these steps.
-
-.. code-block:: bash
-
-    python3 -m venv venv-ocrmypdf
-    source venv-ocrmypdf/bin/activate
-    pip3 install ocrmypdf
-
-
-Installing on Ubuntu 14.04 LTS
-------------------------------
-
-Installing on Ubuntu 14.04 LTS (trusty) is more difficult than some other options, because of bugs in Python package installation and because OCRmyPDF depends on some packages newer than are available in the main distribution.
-
-Add new "apt" repositories needed for backports of Ghostscript 9.16, libav-11 (for unpaper 6.1) and Tesseract 4.00 (alpha). This will replace Ghostscript and Tesseract 3.x on your system. If you prefer to not modify your system in this matter, consider using a Docker container.
-
-.. code-block:: bash
-
-    sudo add-apt-repository ppa:vshn/ghostscript -y
-    sudo add-apt-repository ppa:heyarje/libav-11 -y
-    sudo add-apt-repository ppa:alex-p/tesseract-ocr
-
-Update apt-get:
-
-.. code-block:: bash
-
-    sudo apt-get update
-
-Install system dependencies:
-
-.. code-block:: bash
-
-    sudo apt-get install \
-        software-properties-common python-software-properties \
-        zlib1g-dev \
-        libjpeg-dev \
-        libffi-dev \
-        libavformat56 libavcodec56 libavutil54 \
-        ghostscript \
-        qpdf \
-        python3-pip \
-        python3-pil \
-        python3-pytest \
-        python3-reportlab \
-        python3-wheel \
-        python3-venv \
-        tesseract-ocr \
-        tesseract-ocr-eng
-
-If you wish install OCRmyPDF to the system Python, then install as follows (note this installs new packages
-into your system Python, which could interfere with other programs):
-
-.. code-block:: bash
-
-    sudo pip3 install ocrmypdf
-
-If you wish to install OCRmyPDF to a virtual environment to isolate the system Python, you can
-follow these steps.  This includes a workaround `for a known, unresolved issue in Ubuntu 14.04's ensurepip
-package <http://www.thefourtheye.in/2014/12/Python-venv-problem-with-ensurepip-in-Ubuntu.html>`_:
-
-.. code-block:: bash
-
-    sudo apt-get install python3-venv
-    python3 -m venv venv-ocrmypdf --without-pip
-    source venv-ocrmypdf/bin/activate
-    wget -O - -o /dev/null https://bootstrap.pypa.io/get-pip.py | python
-    deactivate
-    python3 -m venv --system-site-packages venv-ocrmypdf
-    source venv-ocrmypdf/bin/activate
-    pip install ocrmypdf
-
-These installation instructions omit the optional dependency ``unpaper``, which is only available at version 0.4.2 in Ubuntu 14.04. The author could not find a backport of ``unpaper``, and created a .deb package to do the job of installing unpaper 6.1 (for x86 64-bit only):
-
-.. code-block:: bash
-
-    wget -q 'https://www.dropbox.com/s/vaq0kbwi6e6au80/unpaper_6.1-1.deb?raw=1' -O unpaper_6.1-1.deb
-    sudo dpkg -i unpaper_6.1-1.deb
-
-
-Installing on ArchLinux
------------------------
-
-The author is aware of an `ArchLinux package for ocrmypdf <https://aur.archlinux.org/packages/ocrmypdf/>`_. It seems like the following command might work.
-
-.. code-block:: bash
-
-    pacman -S ocrmypdf
+For some users, installing the Docker image will be easier than
+installing all of OCRmyPDF's dependencies. For Windows, it is the only
+option.
 
+See `OCRmyPDF Docker Image <docker>`__ for more information.
 
 Installing on Windows
----------------------
+=====================
 
-Direct installation on Windows is not possible.  Install the _`Docker` container as described above.  Ensure that your command prompt can run the docker "hello world" container.
+Direct installation on Windows is not currently possible, but it works well in
+Windows Subsystem for Linux:
 
-Running on Windows
-~~~~~~~~~~~~~~~~~~
+#. Install Ubuntu 18.04 for Windows Subsystem for Linux, if not already installed.
+#. Follow the procedure to install :ref:`OCRmyPDF on Ubuntu 18.04 <ubuntu-lts-latest>`.
+#. Open the Windows command prompt and create a symlink:
 
-The command line syntax to run ocrmypdf from a command prompt will resemble:
+.. code-block:: powershell
 
-.. code-block:: bat
+    wsl sudo ln -s  /home/user/.local/bin/ocrmypdf /usr/local/bin/ocrmypdf
 
-    docker run -v /c/Users/sampleuser:/home/docker ocrmypdf --skip-text test.pdf output.pdf
+Then confirm that the expected version from PyPI (|latest|) is installed:
 
-where /c/Users/sampleuser is a Unix representation of the Windows path C:\\Users\\sampleuser, assuming a user named "sampleuser" is running ocrmypdf on a file in their home directory, and the files "test.pdf" and "output.pdf" are in the sampleuser folder. The Windows user must have read and write permissions.
+.. code-block:: powershell
 
-`Bash on Ubuntu on Windows <https://github.com/Microsoft/BashOnWindows>`_ should also be a viable route for running the OCRmyPDF Docker container.
+    wsl ocrmypdf --version
 
-Installing HEAD revision from sources
+You can then run OCRmyPDF in the Windows command prompt or Powershell, prefixing
+``wsl``, and call it from Windows programs or batch files.
+
+Why no native Windows?
+^^^^^^^^^^^^^^^^^^^^^^
+
+It would probably not be too difficult to port on Windows. The main
+reason this has been avoided is the difficulty of packaging and
+installing the various non-Python dependencies: Tesseract, QPDF,
+Ghostscript, Leptonica. Pull requests to add or improve Windows support
+would be quite welcome.
+
+Docker
+^^^^^^
+
+You can also :ref:`Install the Docker <docker-install>` container on Windows. Ensure that
+your command prompt can run the docker "hello world" container.
+
+Installing with Python pip
+==========================
+
+OCRmyPDF is delivered by PyPI because it is a convenient way to install
+the latest version. However, PyPI and ``pip`` cannot address the fact
+that ``ocrmypdf`` depends on certain non-Python system libraries and
+programs being instsalled.
+
+For best results, first install `your platform's
+version <https://repology.org/metapackage/ocrmypdf/versions>`__ of
+``ocrmypdf``, using the instructions elsewhere in this document. Then
+you can use ``pip`` to get the latest version if your platform version
+is out of date. Chances are that this will satisfy most dependencies.
+
+Use ``ocrmypdf --version`` to confirm what version was installed.
+
+Then you can install the latest OCRmyPDF from the Python wheels. First
+try:
+
+.. code-block:: bash
+
+    pip3 install --user ocrmypdf
+
+You should then be able to run ``ocrmypdf --version`` and see that the
+latest version was located.
+
+Since ``pip3 install --user`` does not work correctly on some platforms,
+notably Ubuntu 16.04 and older, and the Homebrew version of Python,
+instead use this for a system wide installation:
+
+.. code-block:: bash
+
+    pip3 install ocrmypdf
+
+Requirements for pip and HEAD install
 -------------------------------------
 
-If you have ``git`` and Python 3.5 or newer installed, you can install from source. When the ``pip`` installer runs,
-it will alert you if dependencies are missing.
+OCRmyPDF currently requires these external programs and libraries to be
+installed, and must be satisfied using the operating system package
+manager. ``pip`` cannot provide them.
 
-To install the HEAD revision from sources in the current Python 3 environment:
+-  Python 3.6 or newer
+-  Ghostscript 9.15 or newer
+-  qpdf 8.1.0 or newer
+-  Tesseract 4.0.0-beta or newer
+
+As of ocrmypdf 7.2.1, the following versions are recommended:
+
+-  Python 3.7 or 3.8
+-  Ghostscript 9.23 or newer
+-  qpdf 8.2.1
+-  Tesseract 4.0.0 or newer
+-  jbig2enc 0.29 or newer
+-  pngquant 2.5 or newer
+-  unpaper 6.1
+
+jbig2enc, pngquant, and unpaper are optional. If missing certain
+features are disabled. OCRmyPDF will discover them as soon as they are
+available.
+
+**jbig2enc**, if present, will be used to optimize the encoding of
+monochrome images. This can significantly reduce the file size of the
+output file. It is not required.
+`jbig2enc <https://github.com/agl/jbig2enc>`__ is not generally
+available for Ubuntu or Debian due to lingering concerns about patent
+issues, but can easily be built from source. To add JBIG2 encoding, see
+:ref:`jbig2`.
+
+**pngquant**, if present, is optionally used to optimize the encoding of
+PNG-style images in PDFs (actually, any that are that losslessly
+encoded) by lossily quantizing to a smaller color palette. It is only
+activated then the ``--optimize`` argument is ``2`` or ``3``.
+
+**unpaper**, if present, enables the ``--clean`` and ``--clean-final``
+command line options.
+
+These are in addition to the Python packaging dependencies, meaning that
+unfortunately, the ``pip install`` command cannot satisfy all of them.
+
+Installing HEAD revision from sources
+=====================================
+
+If you have ``git`` and Python 3.6 or newer installed, you can install
+from source. When the ``pip`` installer runs, it will alert you if
+dependencies are missing.
+
+If you prefer to build every from source, you will need to `build
+pikepdf from
+source <https://pikepdf.readthedocs.io/en/latest/installation.html#building-from-source>`__.
+First ensure you can build and install pikepdf.
+
+To install the HEAD revision from sources in the current Python 3
+environment:
 
 .. code-block:: bash
 
     pip3 install git+https://github.com/jbarlow83/OCRmyPDF.git
 
-Or, to install in `development mode <https://pythonhosted.org/setuptools/setuptools.html#development-mode>`_,  allowing customization of OCRmyPDF, use the ``-e`` flag:
+Or, to install in `development
+mode <https://pythonhosted.org/setuptools/setuptools.html#development-mode>`__,
+allowing customization of OCRmyPDF, use the ``-e`` flag:
 
 .. code-block:: bash
 
     pip3 install -e git+https://github.com/jbarlow83/OCRmyPDF.git
 
-On certain Linux distributions such as Ubuntu, you may need to use 
-run the install command as superuser:
-
-.. code-block:: bash
-
-    sudo pip3 install [-e] git+https://github.com/jbarlow83/OCRmyPDF.git
-
-Note that this will alter your system's Python distribution. If you prefer 
-to not install as superuser, you can install the package in a Python virtual environment:
+You may find it easiest to install in a virtual environment, rather than
+system-wide:
 
 .. code-block:: bash
 
@@ -345,7 +587,7 @@ to not install as superuser, you can install the package in a Python virtual env
     cd OCRmyPDF
     pip3 install .
 
-However, ``ocrmypdf`` will only be accessible on the system PATH after
+However, ``ocrmypdf`` will only be accessible on the system PATH when
 you activate the virtual environment.
 
 To run the program:
@@ -358,3 +600,35 @@ If not yet installed, the script will notify you about dependencies that
 need to be installed. The script requires specific versions of the
 dependencies. Older version than the ones mentioned in the release notes
 are likely not to be compatible to OCRmyPDF.
+
+For development
+---------------
+
+To install all of the development and test requirements:
+
+.. code-block:: bash
+
+    git clone -b master https://github.com/jbarlow83/OCRmyPDF.git
+    python3 -m venv
+    source venv/bin/activate
+    cd OCRmyPDF
+    pip install -e .
+    pip install -r requirements/dev.txt -r requirements/test.txt
+
+To add JBIG2 encoding, see :ref:`jbig2`.
+
+Shell completions
+=================
+
+Completions for ``bash`` and ``fish`` are available in the project's
+``misc/completion`` folder. The ``bash`` completions are likely ``zsh``
+compatible but this has not been confirmed. Package maintainers, please
+install these at the appropriate locations for your system.
+
+To manually install the ``bash`` completion, copy
+``misc/completion/ocrmypdf.bash`` to ``/etc/bash_completion.d/ocrmypdf``
+(rename the file).
+
+To manually install the ``fish`` completion, copy
+``misc/completion/ocrmypdf.fish`` to
+``~/.config/fish/completions/ocrmypdf.fish``.

docs/introduction.rst

@@ -1,109 +1,228 @@
+============
 Introduction
 ============
 
 OCRmyPDF is a Python 3 package that adds OCR layers to PDFs.
 
-
 About OCR
----------
+=========
 
-`Optical character recognition <https://en.wikipedia.org/wiki/Optical_character_recognition>`_ is technology that converts images of typed or handwritten text, such as in a scanned document, to computer text that can be searched and copied.
+`Optical character
+recognition <https://en.wikipedia.org/wiki/Optical_character_recognition>`__
+is technology that converts images of typed or handwritten text, such as
+in a scanned document, to computer text that can be searched and copied.
 
-OCRmyPDF uses `Tesseract <https://github.com/tesseract-ocr/tesseract>`_, the best available open source OCR engine, to perform OCR.
+OCRmyPDF uses
+`Tesseract <https://github.com/tesseract-ocr/tesseract>`__, the best
+available open source OCR engine, to perform OCR.
 
 .. _raster-vector:
 
 About PDFs
-----------
+==========
 
-PDFs are page description files that attempts to preserve a layout exactly. They can contain `vector graphic files <http://vector-conversions.com/vectorizing/raster_vs_vector.html>`_ that can contain raster objects such as scanned images. Because PDFs can contain multiple pages (unlike many image formats) and can contain fonts and text, it is a good formats for exchanging scanned documents.
+PDFs are page description files that attempts to preserve a layout
+exactly. They contain `vector
+graphics <http://vector-conversions.com/vectorizing/raster_vs_vector.html>`__
+that can contain raster objects such as scanned images. Because PDFs can
+contain multiple pages (unlike many image formats) and can contain fonts
+and text, it is a good formats for exchanging scanned documents.
 
-.. image:: bitmap_vs_svg.svg
+|image|
 
-A PDF page might contain multiple images, even if it only appears to have one image.  Some scanners or scanning software will segment pages into monochromatic text and color regions for example, to improve the compression ratio and appearance of the page.
-
-Rasterizing a PDF is the process of generating an image suitable for display or analyzing with an OCR engine.  OCR engines like Tesseract work with images, not vector objects.
+A PDF page might contain multiple images, even if it only appears to
+have one image. Some scanners or scanning software will segment pages
+into monochromatic text and color regions for example, to improve the
+compression ratio and appearance of the page.
 
+Rasterizing a PDF is the process of generating an image suitable for
+display or analyzing with an OCR engine. OCR engines like Tesseract work
+with images, not vector objects.
 
 About PDF/A
------------
+===========
 
-`PDF/A <https://en.wikipedia.org/wiki/PDF/A>`_ is an ISO-standardized subset of the full PDF specification that is designed for archiving (the 'A' stands for Archive).  PDF/A differs from PDF primarily by omitting features that would make it difficult to read the file in the future, such as embedded Javascript, video, audio and references to external fonts.  All fonts and resources needed to interpret the PDF must be contained within it. Because PDF/A disables Javascript and other types of embedded content, it is probably more secure.
+`PDF/A <https://en.wikipedia.org/wiki/PDF/A>`__ is an ISO-standardized
+subset of the full PDF specification that is designed for archiving (the
+'A' stands for Archive). PDF/A differs from PDF primarily by omitting
+features that would make it difficult to read the file in the future,
+such as embedded Javascript, video, audio and references to external
+fonts. All fonts and resources needed to interpret the PDF must be
+contained within it. Because PDF/A disables Javascript and other types
+of embedded content, it is probably more secure.
 
 There are various conformance levels and versions, such as "PDF/A-2b".
 
-Generally speaking, the best format for scanned documents is PDF/A. Some governments and jurisdictions, US Courts in particular, `mandate the use of PDF/A <https://pdfblog.com/2012/02/13/what-is-pdfa/>`_ for scanned documents.
+Generally speaking, the best format for scanned documents is PDF/A. Some
+governments and jurisdictions, US Courts in particular, `mandate the use
+of PDF/A <https://pdfblog.com/2012/02/13/what-is-pdfa/>`__ for scanned
+documents.
 
-Since most people who scan documents are interested in reading them indefinitely into the future, OCRmyPDF generates PDF/A-2b by default.
-
-PDF/A has a few drawbacks.  Some PDF viewers include an alert that the file is a PDF/A, which may confuse some users.  It also tends to produce larger files than PDF, because it embeds certain resources even if they are commonly available. PDF/A files can be digitally signed, but may not be encrypted, to ensure they can be read in the future.  Fortunately, converting from PDF/A to a regular PDF is trivial, and any PDF viewer can view PDF/A.
+Since most people who scan documents are interested in reading them
+indefinitely into the future, OCRmyPDF generates PDF/A-2b by default.
 
+PDF/A has a few drawbacks. Some PDF viewers include an alert that the
+file is a PDF/A, which may confuse some users. It also tends to produce
+larger files than PDF, because it embeds certain resources even if they
+are commonly available. PDF/A files can be digitally signed, but may not
+be encrypted, to ensure they can be read in the future. Fortunately,
+converting from PDF/A to a regular PDF is trivial, and any PDF viewer
+can view PDF/A.
 
 What OCRmyPDF does
-------------------
+==================
 
-OCRmyPDF analyzes each page of a PDF to determine the colorspace and resolution (DPI) needed to capture all of the information on that page without losing content.  It uses `Ghostscript <http://ghostscript.com/>`_ to rasterize the page, and then performs on OCR on the rasterized image.  It is not enough to simply extract the images from each page and run OCR on them individually.  Of course one could use Ghostscript or another PDF rasterizer and then pass the image to Tesseract.  OCRmyPDF automates this process and produces a minimally changed output file that contains the same information, colorspace and resolution.
+OCRmyPDF analyzes each page of a PDF to determine the colorspace and
+resolution (DPI) needed to capture all of the information on that page
+without losing content. It uses
+`Ghostscript <http://ghostscript.com/>`__ to rasterize the page, and
+then performs on OCR on the rasterized image to create an OCR "layer".
+The layer is then grafted back onto the original PDF.
 
-The Tesseract OCR engine can output 'hOCR' files, which are XML files that contain a description of the text it found on the page.  OCRmyPDF will render a new PDF that contains only the hidden text layer, and merge this with the original page.
+While one can use a program like Ghostscript or ImageMagick to get an
+image and put the image through Tesseract, that actually creates a new
+PDF and many details may be lost. OCRmyPDF can produce a minimally
+changed PDF as output.
 
-Alternately, OCRmyPDF can use the Tesseract OCR engine to directly output PDFs for each page, then merge them.
-
-By default, OCRmyPDF will convert the file to a PDF/A.  This behavior can be disabled with the ``--output-type pdf`` argument.
-
-Depending on the settings selected, OCRmyPDF may "graft" the OCR layer into the existing PDF, or reconstruct a visually equivalent new PDF.
+OCRmyPDF also some image processing options like deskew which improve
+the appearance of files and quality of OCR. When these are used, the OCR
+layer is grafted onto the processed image instead.
 
+By default, OCRmyPDF produces archival PDFs – PDF/A, which are a
+stricter subset of PDF features designed for long term archives. If
+regular PDFs are desired, this can be disabled with
+``--output-type pdf``.
 
 Why you shouldn't do this manually
-----------------------------------
+==================================
 
-A PDF is similar to an HTML file, in that it contains document structure along with images.  Sometimes a PDF does nothing more than present a full page image, but often there is additional content that would be lost.
+A PDF is similar to an HTML file, in that it contains document structure
+along with images. Sometimes a PDF does nothing more than present a full
+page image, but often there is additional content that would be lost.
 
 A manual process could work like either of these:
 
-1. Rasterize each page as an image, OCR the images, and combine the output into a PDF. This preserves the layout of each page, but resamples all images (possibly losing quality, increasing file size, introducing compression artifacts, etc.).
+1. Rasterize each page as an image, OCR the images, and combine the
+   output into a PDF. This preserves the layout of each page, but
+   resamples all images (possibly losing quality, increasing file size,
+   introducing compression artifacts, etc.).
+2. Extract each image, OCR, and combine the output into a PDF. This
+   loses the context in which images are used in the PDF, meaning that
+   cropping, rotation and scaling of pages may be lost. Some scanned
+   PDFs use multiple images segmented into black and white, grayscale
+   and color regions, with stencil masks to prevent overlap, as this can
+   enhance the appearance of a file while reducing file size. Clearly,
+   reassembling these images will be easy. This also loses and text or
+   vector art on any pages in a PDF with both scanned and pure digital
+   content.
 
-2. Extract each image, OCR, and combine the output into a PDF. This loses the context in which images are used in the PDF, meaning that cropping, rotation and scaling of pages may be lost. Some scanned PDFs use multiple images segmented into black and white, grayscale and color regions, with stencil masks to prevent overlap, as this can enhance the appearance of a file while reducing file size. Clearly, reassembling these images will be easy. This also loses and text or vector art on any pages in a PDF with both scanned and pure digital content.
+In the case of a PDF that is nothing other than a container of images
+(no rotation, scaling, cropping, one image per page), the second
+approach can be lossless.
 
-In the case of a PDF that is nothing other than a container of images (no rotation, scaling, cropping, one image per page), the second approach can be lossless.
-
-OCRmyPDF uses several strategies depending on input options and the input PDF itself, but generally speaking it rasterizes a page for OCR and then grafts the OCR back onto the original. As such it can handle complex PDFs and still preserve their contents as much as possible.
+OCRmyPDF uses several strategies depending on input options and the
+input PDF itself, but generally speaking it rasterizes a page for OCR
+and then grafts the OCR back onto the original. As such it can handle
+complex PDFs and still preserve their contents as much as possible.
 
+OCRmyPDF also supports a many, many edge cases that have cropped over
+several years of development. We support PDF features like images inside
+of Form XObjects, and pages with UserUnit scaling. We support rare image
+formats like non-monochrome 1-bit images. We warn about files you may
+not to OCR. Thanks to pikepdf and QPDF, we auto-repair PDFs that are
+damaged. (Not that you need to know what any of these are! You should be
+able to throw any PDF at it.)
 
 Limitations
------------
+===========
 
-OCRmyPDF is limited by the Tesseract OCR engine.  As such it experiences these limitations, as do any other programs that rely on Tesseract:
+OCRmyPDF is limited by the Tesseract OCR engine. As such it experiences
+these limitations, as do any other programs that rely on Tesseract:
+
+-  The OCR is not as accurate as commercial solutions such as Abbyy.
+-  It is not capable of recognizing handwriting.
+-  It may find gibberish and report this as OCR output.
+-  If a document contains languages outside of those given in the
+   ``-l LANG`` arguments, results may be poor.
+-  It is not always good at analyzing the natural reading order of
+   documents. For example, it may fail to recognize that a document
+   contains two columns, and may try to join text across columns.
+-  Poor quality scans may produce poor quality OCR. Garbage in, garbage
+   out.
+-  It does not expose information about what font family text belongs
+   to.
 
-* The OCR is not as accurate as commercial solutions such as Abbyy.
-* It is not capable of recognizing handwriting.
-* It may find gibberish and report this as OCR output.
-* If a document contains languages outside of those given in the ``-l LANG`` arguments, results may be poor.
-* It is not always good at analyzing the natural reading order of documents. For example, it may fail to recognize that a document contains two columns and join text across the columns.
-* Poor quality scans may produce poor quality OCR. Garbage in, garbage out.
-* PDFs that use transparent layers are not currently checked in the test suite, so they may not work correctly.
-  
 OCRmyPDF is also limited by the PDF specification:
 
-* PDF encodes the position of text glyphs but does not encode document structure.  There is no markup that divides a document in sections, paragraphs, sentences, or even words (since blank spaces are not represented). As such all elements of document structure including the spaces between words must be derived heuristically.  Some PDF viewers do a better job of this than others.
+-  PDF encodes the position of text glyphs but does not encode document
+   structure. There is no markup that divides a document in sections,
+   paragraphs, sentences, or even words (since blank spaces are not
+   represented). As such all elements of document structure including
+   the spaces between words must be derived heuristically. Some PDF
+   viewers do a better job of this than others.
+-  Because some popular open source PDF viewers have a particularly hard
+   time with spaces between words, OCRmyPDF appends a space to each text
+   element as a workaround (when using ``--pdf-renderer hocr``). While
+   this mixes document structure with graphical information that ideally
+   should be left to the PDF viewer to interpret, it improves
+   compatibility with some viewers and does not cause problems for
+   better ones.
 
 Ghostscript also imposes some limitations:
 
-* PDFs containing JBIG2-encoded content will be converted to CCITT Group4 encoding, which has lower compression ratios, if Ghostscript PDF/A is enabled.
-* PDFs containing JPEG 2000-encoded content will be converted to JPEG encoding, which may introduce compression artifacts, if Ghostscript PDF/A is enabled.
-* Ghostscript may transcode grayscale and color images, either lossy to lossless or lossless to lossy, based on an internal algorithm. This behavior can be suppressed by setting ``--pdfa-image-compression`` to ``jpeg`` or ``lossless`` to set all images to one type or the other. Ghostscript has no option to maintain the input image's format.
-  
-OCRmyPDF is currently not designed to be used as a Python API; it is designed to be run as a command line tool. ``import ocrmypf`` currently attempts to process the command line on ``sys.argv`` at import time so it has side effects that will interfere with its use as a package. The API it presents should not be considered stable.
+-  PDFs containing JBIG2-encoded content will be converted to CCITT
+   Group4 encoding, which has lower compression ratios, if Ghostscript
+   PDF/A is enabled.
+-  PDFs containing JPEG 2000-encoded content will be converted to JPEG
+   encoding, which may introduce compression artifacts, if Ghostscript
+   PDF/A is enabled.
+-  Ghostscript may transcode grayscale and color images, either lossy to
+   lossless or lossless to lossy, based on an internal algorithm. This
+   behavior can be suppressed by setting ``--pdfa-image-compression`` to
+   ``jpeg`` or ``lossless`` to set all images to one type or the other.
+   Ghostscript has no option to maintain the input image's format.
+   (Ghostscript 9.25+ can copy JPEG images without transcoding them;
+   earlier versions will transcode.)
+-  Ghostscript's PDF/A conversion removes any XMP metadata that is not
+   one of the standard XMP metadata namespaces for PDFs. In particular,
+   PRISM Metdata is removed.
 
+Regarding OCRmyPDF itself:
+
+-  PDFs that use transparency are not currently represented in the test
+   suite
 
 Similar programs
-----------------
+================
 
-To the author's knowledge, OCRmyPDF is the most feature-rich and thoroughly tested command line OCR PDF conversion tool. If it does not meet your needs, contributions and suggestions are welcome. If not, consider one of these similar open source programs:
+To the author's knowledge, OCRmyPDF is the most feature-rich and
+thoroughly tested command line OCR PDF conversion tool. If it does not
+meet your needs, contributions and suggestions are welcome. If not,
+consider one of these similar open source programs:
 
-* pdf2pdfocr
-* pdfsandwich
-* pypdfocr
-* pdfbeads
+-  pdf2pdfocr
+-  pdfsandwich
+-  pypdfocr
+-  pdfbeads
 
-If you are looking for a micro web-frontend for OCRmyPDF, consider the third-party `OCRmyPDF-web <https://github.com/sseemayer/OCRmyPDF-web>`_. Bear in mind that OCRmyPDF is not designed to be secure against malware-bearing PDFs (see `Using OCRmyPDF online`_).
+Web front-ends
+==============
 
+The Docker image ``ocrmypdf`` provides a web service front-end
+that allows files to submitted over HTTP and the results "downloaded".
+This is an HTTP server intended to simplify web services deployments; it
+is not intended to be deployed on the public internet and no real
+security measures to speak of.
+
+In addition, the following third-party integrations are available:
+
+-  `Nextcloud OCR <https://github.com/janis91/ocr>`__ is a free software
+   plugin for the Nextcloud private cloud software
+
+OCRmyPDF is not designed to be secure against malware-bearing PDFs (see
+`Using OCRmyPDF online <ocr-service>`__). Users should ensure they
+comply with OCRmyPDF's licenses and the licenses of all dependencies. In
+particular, OCRmyPDF requires Ghostscript, which is licensed under
+AGPLv3.
+
+.. |image| image:: images/bitmap_vs_svg.svg

docs/jbig2.rst

@@ -0,0 +1,55 @@
+.. _jbig2:
+
+============================
+Installing the JBIG2 encoder
+============================
+
+Most Linux distributions do not include a JBIG2 encoder since JBIG2
+encoding was patented for a long time. All known JBIG2 US patents have
+expired as of 2017, but it is possible that unknown patents exist.
+
+JBIG2 encoding is recommended for OCRmyPDF and is used to losslessly
+create smaller PDFs. If JBIG2 encoding not available, lower quality
+encodings will be used.
+
+JBIG2 decoding is not patented and is performed automatically by most
+PDF viewers. It is widely supported has been part of the PDF
+specification since 2001.
+
+On macOS, Homebrew packages jbig2enc and OCRmyPDF includes it by
+default. The Docker image for OCRmyPDF also builds its own JBIG2 encoder
+from source.
+
+For all other Linux, you must build a JBIG2 encoder from source:
+
+.. code-block:: bash
+
+   git clone https://github.com/agl/jbig2enc
+   cd jbig2enc
+   ./autogen.sh
+   ./configure && make
+   [sudo] make install
+
+.. _jbig2-lossy:
+
+Lossy mode JBIG2
+================
+
+OCRmyPDF provides lossy mode JBIG2 as an advanced feature. Users should
+`review the technical concerns with JBIG2 in lossy
+mode <https://abbyy.technology/en:kb:tip:jbig2_compression_and_ocr>`__
+and decide if this feature is acceptable for their use case.
+
+JBIG2 lossy mode does achieve higher compression ratios than any other
+monochrome (bitonal) compression technology; for large text documents
+the savings are considerable. JBIG2 lossless still gives great
+compression ratios and is a major improvement over the older CCITT G4
+standard. As explained above, there is some risk of substitution errors.
+
+To turn on JBIG2 lossy mode, add the argument ``--jbig2-lossy``.
+``--optimize {1,2,3}`` are necessary for the argument to take effect
+also required. Also, a JBIG2 encoder must be installed as described in
+the previous section.
+
+*Due to an oversight, ocrmypdf v7.0 and v7.1 used lossy mode by
+default.*

docs/languages.rst

@@ -1,48 +1,59 @@
 .. _lang-packs:
 
+====================================
 Installing additional language packs
 ====================================
 
-OCRmyPDF uses Tesseract for OCR, and relies on its language packs for languages other than English. 
+OCRmyPDF uses Tesseract for OCR, and relies on its language packs for
+languages other than English.
 
-Tesseract supports `most languages <https://github.com/tesseract-ocr/tesseract/blob/master/doc/tesseract.1.asc#languages>`_.
+Tesseract supports `most
+languages <https://github.com/tesseract-ocr/tesseract/blob/master/doc/tesseract.1.asc#languages>`__.
 
-For Linux users, you can often find packages that provide language packs:
+For Linux users, you can often find packages that provide language
+packs:
 
 Debian and Ubuntu users
------------------------
+=======================
 
 .. code-block:: bash
 
    # Display a list of all Tesseract language packs
    apt-cache search tesseract-ocr
 
-   # Debian/Ubuntu users
-   apt-get install tesseract-ocr-chi-sim  # Example: Install Chinese Simplified language back
-   
-You can then pass the ``-l LANG`` argument to OCRmyPDF to give a hint as to what languages it should search for. Multiple
-languages can be requested using either ``-l eng+fre`` (English and French) or ``-l eng -l fre``.
+   # Install Chinese Simplified language pack
+   apt-get install tesseract-ocr-chi-sim
 
-macOS users
------------
+You can then pass the ``-l LANG`` argument to OCRmyPDF to give a hint as
+to what languages it should search for. Multiple languages can be
+requested using either ``-l eng+fre`` (English and French) or
+``-l eng -l fre``.
 
-You can install additional language packs by :ref:`installing Tesseract using Homebrew with all language packs <macos-all-languages>`.
-
-Docker users
-------------
-
-Users of the Docker image may use the alternative :ref:`"polyglot" container <docker-polyglot>` which includes all languages.
-
-Known limitations
------------------
-
-As of v4.2, users of ocrmypdf working languages outside the Latin alphabet should use the following syntax:
+Fedora users
+============
 
 .. code-block:: bash
 
-	ocrmypdf -l eng+gre --output-type pdf --pdf-renderer tesseract
+   # Display a list of all Tesseract language packs
+   dnf search tesseract
 
-The reasons for this are:
+   # Install Chinese Simplified language pack
+   dnf install tesseract-langpack-chi_sim
 
-* The latest version of Ghostscript (9.19 as of this writing) has unfixed bugs in Unicode handling that generate invalid character maps, so Ghostscript cannot be used for PDF/A conversion
-* The default "hocr" PDF renderer does not handle Asian fonts properly
+You can then pass the ``-l LANG`` argument to OCRmyPDF to give a hint as
+to what languages it should search for. Multiple languages can be
+requested using either ``-l eng+fre`` (English and French) or
+``-l eng -l fre``.
+
+macOS users
+===========
+
+You can install additional language packs by
+:ref:`installing Tesseract using Homebrew with all language packs <macos-all-languages>`.
+
+Docker users
+============
+
+Users of the OCRmyPDF Docker image should install language packs into a
+derived Docker image as
+:ref:`described in that section <docker-lang-packs>`.

docs/optimizer.rst

@@ -0,0 +1,71 @@
+================
+PDF optimization
+================
+
+OCRmyPDF includes an image-oriented PDF optimizer. By default, the optimizer
+runs with safe settings with the goal of improving compression at no loss of
+quality. At higher optimization levels, lossy optimizations may be applied and
+tuned. Optimization occurs after OCR, and only if OCR succeeded.  It does not
+perform other possible optimizations such as deduplicating resources,
+consolidating fonts, simplifying vector drawings, or anything of that nature.
+
+Optimization ranges from ``-O0`` through ``-O3``, where ``0`` disables
+optimization and ``3`` implements all options. ``1``, the default, performs only
+safe and lossless optimizations. (This is similar to GCC's optimization
+parameter.) The exact type of optimizations performed will vary over time.
+
+Optimizations that always occurs
+================================
+
+OCRmyPDF will automatically replace obsolete or inferior compression schemes
+such as RLE or LZW with superior schemes such as Deflate and converting
+monochrome images to CCITT G4. Since this is harmless it always occurs and there
+is no way to disable it. Other non-image compressed objects are compressed as
+well.
+
+Fast web view
+=============
+
+OCRmyPDF automatically optimizes PDFs for "fast web view" in Adobe Acrobat's
+parlance, or equivalently, linearizes PDFs so that the resources they reference
+are presented in the order a viewer needs them for sequential display. This
+reduces the latency of viewing a PDF both online and from local storage. This
+actually slightly increases the file size.
+
+To disable this optimization and all others, use ``ocrmypdf --optimize 0 ...``
+or the shorthand ``-O0``.
+
+Lossless optimizations
+======================
+
+At optimization level ``-O1`` (the default), OCRmyPDF will also attempt lossless
+image optimization.
+
+If a JBIG2 encoder is available, then monochrome images will be converted to
+JBIG2, with the potential for huge savings on large black and white images,
+since JBIG2 is far more efficient than any other monochrome (bi-level)
+compression. (All known US patents related to JBIG2 have probably expired, but
+it remains the responsibility of the user to supply a JBIG2 encoder such as
+`jbig2enc <https://github.com/agl/jbig2enc>`__. OCRmyPDF does not implement
+JBIG2 encoding on its own.)
+
+OCRmyPDF currently does not attempt to recompress losslessly compressed objects
+more aggressively.
+
+Lossy optimizations
+===================
+
+At optimization level ``-O2`` and ``-O3``, OCRmyPDF will some attempt lossy
+image optimization.
+
+If ``pngquant`` is installed, OCRmyPDF will use it to perform quantize paletted
+images to reduce their size.
+
+The quality of JPEGs may be lowered, on the assumption that a lower quality
+image may be suitable for storage after OCR.
+
+It is not possible to optimize all image types. Uncommon image types may be
+skipped by the optimizer.
+
+OCRmyPDF provides :ref:`lossy mode JBIG2 <jbig2-lossy>` as an advanced feature
+that additional requires the argument ``--jbig2-lossy``.

docs/pipeline.svg

@@ -1,392 +1,392 @@
 <?xml version="1.0" encoding="UTF-8" standalone="no"?>
 <!DOCTYPE svg PUBLIC "-//W3C//DTD SVG 1.1//EN"
  "http://www.w3.org/Graphics/SVG/1.1/DTD/svg11.dtd">
-<!-- Generated by graphviz version 2.38.0 (20140413.2041)
+<!-- Generated by graphviz version 2.40.1 (20161225.0304)
  -->
 <!-- Title: Pipeline: Pages: 1 -->
-<svg width="1544pt" height="1089pt"
- viewBox="0.00 0.00 1544.00 1089.14" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink">
-<g id="graph0" class="graph" transform="scale(1 1) rotate(0) translate(4 1085.14)">
+<svg width="1484pt" height="1277pt"
+ viewBox="0.00 0.00 1484.00 1277.20" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink">
+<g id="graph0" class="graph" transform="scale(1 1) rotate(0) translate(4 1273.1977)">
 <title>Pipeline:</title>
-<polygon fill="white" stroke="none" points="-4,4 -4,-1085.14 1540,-1085.14 1540,4 -4,4"/>
-<g id="clust1" class="cluster"><title>clustertasks</title>
-<polygon fill="none" stroke="black" points="8,-8 8,-1073.14 1528,-1073.14 1528,-8 8,-8"/>
-<text text-anchor="middle" x="768" y="-1045.14" font-family="Times,serif" font-size="30.00" fill="#ff3232">Pipeline:</text>
+<polygon fill="#ffffff" stroke="transparent" points="-4,4 -4,-1273.1977 1480,-1273.1977 1480,4 -4,4"/>
+<g id="clust1" class="cluster">
+<title>clustertasks</title>
+<polygon fill="none" stroke="#000000" points="8,-8 8,-1261.1977 1468,-1261.1977 1468,-8 8,-8"/>
+<text text-anchor="middle" x="738" y="-1233.1977" font-family="Times,serif" font-size="30.00" fill="#ff3232">Pipeline:</text>
 </g>
 <!-- t0 -->
-<g id="node1" class="node"><title>t0</title>
-<polygon fill="#efa03b" stroke="black" points="750.705,-1027.14 541.295,-1027.14 537.295,-1023.14 537.295,-991.141 746.705,-991.141 750.705,-995.141 750.705,-1027.14"/>
-<polyline fill="none" stroke="black" points="746.705,-1023.14 537.295,-1023.14 "/>
-<polyline fill="none" stroke="black" points="746.705,-1023.14 746.705,-991.141 "/>
-<polyline fill="none" stroke="black" points="746.705,-1023.14 750.705,-1027.14 "/>
-<text text-anchor="middle" x="644" y="-1003.14" font-family="Times,serif" font-size="20.00">ocrmypdf.pipeline.triage</text>
+<g id="node1" class="node">
+<title>t0</title>
+<polygon fill="#efa03b" stroke="#000000" points="1215.7053,-1215.1977 1006.2947,-1215.1977 1002.2947,-1211.1977 1002.2947,-1179.1977 1211.7053,-1179.1977 1215.7053,-1183.1977 1215.7053,-1215.1977"/>
+<polyline fill="none" stroke="#000000" points="1211.7053,-1211.1977 1002.2947,-1211.1977 "/>
+<polyline fill="none" stroke="#000000" points="1211.7053,-1211.1977 1211.7053,-1179.1977 "/>
+<polyline fill="none" stroke="#000000" points="1211.7053,-1211.1977 1215.7053,-1215.1977 "/>
+<text text-anchor="middle" x="1109" y="-1191.1977" font-family="Times,serif" font-size="20.00" fill="#000000">ocrmypdf.pipeline.triage</text>
 </g>
 <!-- t1 -->
-<g id="node2" class="node"><title>t1</title>
-<polygon fill="#efa03b" stroke="black" points="769.969,-969.141 522.031,-969.141 518.031,-965.141 518.031,-933.141 765.969,-933.141 769.969,-937.141 769.969,-969.141"/>
-<polyline fill="none" stroke="black" points="765.969,-965.141 518.031,-965.141 "/>
-<polyline fill="none" stroke="black" points="765.969,-965.141 765.969,-933.141 "/>
-<polyline fill="none" stroke="black" points="765.969,-965.141 769.969,-969.141 "/>
-<text text-anchor="middle" x="644" y="-945.141" font-family="Times,serif" font-size="20.00">ocrmypdf.pipeline.repair_pdf</text>
+<g id="node2" class="node">
+<title>t1</title>
+<polygon fill="#efa03b" stroke="#000000" points="1280.0433,-1157.1977 941.9567,-1157.1977 937.9567,-1153.1977 937.9567,-1121.1977 1276.0433,-1121.1977 1280.0433,-1125.1977 1280.0433,-1157.1977"/>
+<polyline fill="none" stroke="#000000" points="1276.0433,-1153.1977 937.9567,-1153.1977 "/>
+<polyline fill="none" stroke="#000000" points="1276.0433,-1153.1977 1276.0433,-1121.1977 "/>
+<polyline fill="none" stroke="#000000" points="1276.0433,-1153.1977 1280.0433,-1157.1977 "/>
+<text text-anchor="middle" x="1109" y="-1133.1977" font-family="Times,serif" font-size="20.00" fill="#000000">ocrmypdf.pipeline.repair_and_parse_pdf</text>
 </g>
 <!-- t0&#45;&gt;t1 -->
-<g id="edge1" class="edge"><title>t0&#45;&gt;t1</title>
-<path fill="none" stroke="#0044a0" d="M644,-991.035C644,-987.344 644,-983.354 644,-979.384"/>
-<polygon fill="#0044a0" stroke="#0044a0" points="647.5,-979.142 644,-969.142 640.5,-979.142 647.5,-979.142"/>
+<g id="edge1" class="edge">
+<title>t0&#45;&gt;t1</title>
+<path fill="none" stroke="#0044a0" d="M1109,-1179.1641C1109,-1175.4895 1109,-1171.5395 1109,-1167.604"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="1112.5001,-1167.4199 1109,-1157.4199 1105.5001,-1167.42 1112.5001,-1167.4199"/>
 </g>
 <!-- t2 -->
-<g id="node3" class="node"><title>t2</title>
-<polygon fill="#efa03b" stroke="black" points="869.82,-890.215 644,-907.116 418.18,-890.215 418.391,-862.869 869.609,-862.869 869.82,-890.215"/>
-<polygon fill="none" stroke="black" points="873.852,-893.922 644,-911.125 414.148,-893.922 414.419,-858.871 873.581,-858.871 873.852,-893.922"/>
-<text text-anchor="middle" x="644" y="-876.657" font-family="Times,serif" font-size="20.00">ocrmypdf.pipeline.split_pages</text>
+<g id="node3" class="node">
+<title>t2</title>
+<polygon fill="#efa03b" stroke="#000000" points="1030.0926,-1078.2732 785,-1095.1731 539.9074,-1078.2732 540.1362,-1050.9285 1029.8638,-1050.9285 1030.0926,-1078.2732"/>
+<polygon fill="none" stroke="#000000" points="1034.1249,-1082.0021 785,-1099.1801 535.8751,-1082.0021 536.1685,-1046.931 1033.8315,-1046.931 1034.1249,-1082.0021"/>
+<text text-anchor="middle" x="785" y="-1064.7153" font-family="Times,serif" font-size="20.00" fill="#000000">ocrmypdf.pipeline.marker_pages</text>
 </g>
 <!-- t1&#45;&gt;t2 -->
-<g id="edge2" class="edge"><title>t1&#45;&gt;t2</title>
-<path fill="none" stroke="#0044a0" d="M644,-933.019C644,-929.4 644,-925.445 644,-921.399"/>
-<polygon fill="#0044a0" stroke="#0044a0" points="647.5,-921.295 644,-911.295 640.5,-921.295 647.5,-921.295"/>
-</g>
-<!-- t18 -->
-<g id="node20" class="node"><title>t18</title>
-<polygon fill="#efa03b" stroke="black" points="383.516,-832.173 20.4844,-832.173 16.4844,-828.173 16.4844,-796.173 379.516,-796.173 383.516,-800.173 383.516,-832.173"/>
-<polyline fill="none" stroke="black" points="379.516,-828.173 16.4844,-828.173 "/>
-<polyline fill="none" stroke="black" points="379.516,-828.173 379.516,-796.173 "/>
-<polyline fill="none" stroke="black" points="379.516,-828.173 383.516,-832.173 "/>
-<text text-anchor="middle" x="200" y="-808.173" font-family="Times,serif" font-size="20.00">ocrmypdf.pipeline.generate_postscript_stub</text>
-</g>
-<!-- t1&#45;&gt;t18 -->
-<g id="edge29" class="edge"><title>t1&#45;&gt;t18</title>
-<path fill="none" stroke="#0044a0" d="M518.14,-936.259C481.198,-930.408 441.05,-922.284 405,-911.141 344.394,-892.407 278.709,-859.14 238.448,-837.118"/>
-<polygon fill="#0044a0" stroke="#0044a0" points="239.963,-833.956 229.517,-832.188 236.581,-840.085 239.963,-833.956"/>
-</g>
-<!-- t21 -->
-<g id="node22" class="node"><title>t21</title>
-<polygon fill="#efa03b" stroke="black" points="751.49,-156.424 963,-129.109 1174.51,-156.424 1174.31,-200.62 751.688,-200.62 751.49,-156.424"/>
-<polygon fill="none" stroke="black" points="747.474,-152.906 963,-125.073 1178.53,-152.906 1178.29,-204.623 747.705,-204.623 747.474,-152.906"/>
-<text text-anchor="middle" x="963" y="-162.639" font-family="Times,serif" font-size="20.00">ocrmypdf.pipeline.merge_pages_qpdf</text>
-</g>
-<!-- t1&#45;&gt;t21 -->
-<g id="edge39" class="edge"><title>t1&#45;&gt;t21</title>
-<path fill="none" stroke="#0044a0" d="M769.832,-943.539C1011.96,-929.143 1519,-890.056 1519,-815.173 1519,-815.173 1519,-815.173 1519,-309.173 1519,-237.474 1342.87,-202.283 1188.87,-185.216"/>
-<polygon fill="#0044a0" stroke="#0044a0" points="1189.08,-181.719 1178.76,-184.118 1188.32,-188.678 1189.08,-181.719"/>
-</g>
-<!-- t3 -->
-<g id="node4" class="node"><title>t3</title>
-<polygon fill="#efa03b" stroke="black" points="712.317,-832.173 405.683,-832.173 401.683,-828.173 401.683,-796.173 708.317,-796.173 712.317,-800.173 712.317,-832.173"/>
-<polyline fill="none" stroke="black" points="708.317,-828.173 401.683,-828.173 "/>
-<polyline fill="none" stroke="black" points="708.317,-828.173 708.317,-796.173 "/>
-<polyline fill="none" stroke="black" points="708.317,-828.173 712.317,-832.173 "/>
-<text text-anchor="middle" x="557" y="-808.173" font-family="Times,serif" font-size="20.00">ocrmypdf.pipeline.rasterize_preview</text>
-</g>
-<!-- t2&#45;&gt;t3 -->
-<g id="edge3" class="edge"><title>t2&#45;&gt;t3</title>
-<path fill="none" stroke="#0044a0" d="M614.06,-858.777C605.418,-852.173 595.983,-844.963 587.319,-838.342"/>
-<polygon fill="#0044a0" stroke="#0044a0" points="589.37,-835.504 579.299,-832.213 585.119,-841.066 589.37,-835.504"/>
-</g>
-<!-- t4 -->
-<g id="node5" class="node"><title>t4</title>
-<polygon fill="#efa03b" stroke="black" points="688.082,-774.173 429.918,-774.173 425.918,-770.173 425.918,-738.173 684.082,-738.173 688.082,-742.173 688.082,-774.173"/>
-<polyline fill="none" stroke="black" points="684.082,-770.173 425.918,-770.173 "/>
-<polyline fill="none" stroke="black" points="684.082,-770.173 684.082,-738.173 "/>
-<polyline fill="none" stroke="black" points="684.082,-770.173 688.082,-774.173 "/>
-<text text-anchor="middle" x="557" y="-750.173" font-family="Times,serif" font-size="20.00">ocrmypdf.pipeline.orient_page</text>
-</g>
-<!-- t2&#45;&gt;t4 -->
-<g id="edge5" class="edge"><title>t2&#45;&gt;t4</title>
-<path fill="none" stroke="#0044a0" d="M695.691,-858.661C705.833,-851.667 715.136,-842.912 721,-832.173 728.668,-818.13 730.919,-808.727 721,-796.173 714.915,-788.471 700.759,-782.127 683.18,-776.959"/>
-<polygon fill="#0044a0" stroke="#0044a0" points="683.659,-773.462 673.091,-774.208 681.817,-780.216 683.659,-773.462"/>
-</g>
-<!-- t3&#45;&gt;t4 -->
-<g id="edge4" class="edge"><title>t3&#45;&gt;t4</title>
-<path fill="none" stroke="#0044a0" d="M557,-796.066C557,-792.375 557,-788.385 557,-784.415"/>
-<polygon fill="#0044a0" stroke="#0044a0" points="560.5,-784.174 557,-774.174 553.5,-784.174 560.5,-784.174"/>
-</g>
-<!-- t5 -->
-<g id="node6" class="node"><title>t5</title>
-<polygon fill="#efa03b" stroke="black" points="1064.73,-716.173 689.268,-716.173 685.268,-712.173 685.268,-680.173 1060.73,-680.173 1064.73,-684.173 1064.73,-716.173"/>
-<polyline fill="none" stroke="black" points="1060.73,-712.173 685.268,-712.173 "/>
-<polyline fill="none" stroke="black" points="1060.73,-712.173 1060.73,-680.173 "/>
-<polyline fill="none" stroke="black" points="1060.73,-712.173 1064.73,-716.173 "/>
-<text text-anchor="middle" x="875" y="-692.173" font-family="Times,serif" font-size="20.00">ocrmypdf.pipeline.rasterize_with_ghostscript</text>
-</g>
-<!-- t4&#45;&gt;t5 -->
-<g id="edge6" class="edge"><title>t4&#45;&gt;t5</title>
-<path fill="none" stroke="#0044a0" d="M653.706,-738.143C689.783,-731.789 730.943,-724.541 767.902,-718.033"/>
-<polygon fill="#0044a0" stroke="#0044a0" points="768.965,-721.399 778.206,-716.218 767.751,-714.505 768.965,-721.399"/>
-</g>
-<!-- t15 -->
-<g id="node13" class="node"><title>t15</title>
-<polygon fill="#ff69b4" stroke="black" points="440.27,-396.173 59.7304,-396.173 55.7304,-392.173 55.7304,-360.173 436.27,-360.173 440.27,-364.173 440.27,-396.173"/>
-<polyline fill="none" stroke="black" points="436.27,-392.173 55.7304,-392.173 "/>
-<polyline fill="none" stroke="black" points="436.27,-392.173 436.27,-360.173 "/>
-<polyline fill="none" stroke="black" points="436.27,-392.173 440.27,-396.173 "/>
-<text text-anchor="middle" x="248" y="-372.173" font-family="Times,serif" font-size="20.00">ocrmypdf.pipeline.ocr_tesseract_textonly_pdf</text>
-</g>
-<!-- t4&#45;&gt;t15 -->
-<g id="edge14" class="edge"><title>t4&#45;&gt;t15</title>
-<path fill="none" stroke="#0044a0" d="M425.857,-745.263C361.241,-732.425 297,-703.891 297,-641.173 297,-641.173 297,-641.173 297,-523.173 297,-480.18 277.182,-433.63 262.754,-405.436"/>
-<polygon fill="#0044a0" stroke="#0044a0" points="265.677,-403.477 257.916,-396.265 259.486,-406.743 265.677,-403.477"/>
-</g>
-<!-- t12 -->
-<g id="node15" class="node"><title>t12</title>
-<polygon fill="#00cc66" stroke="black" points="781,-406.173 458.414,-378.173 781,-350.173 1103.59,-378.173 781,-406.173"/>
-<text text-anchor="middle" x="781" y="-372.173" font-family="Times,serif" font-size="20.00">ocrmypdf.pipeline.select_image_layer</text>
-</g>
-<!-- t4&#45;&gt;t12 -->
-<g id="edge20" class="edge"><title>t4&#45;&gt;t12</title>
-<path fill="none" stroke="#0044a0" d="M471.449,-738.167C421.018,-722.605 367,-693.681 367,-641.173 367,-641.173 367,-641.173 367,-523.173 367,-480.717 347.218,-458.43 377,-428.173 392.917,-412.001 494.592,-399.721 591.948,-391.499"/>
-<polygon fill="#0044a0" stroke="#0044a0" points="592.284,-394.983 601.96,-390.666 591.704,-388.007 592.284,-394.983"/>
-</g>
-<!-- t19 -->
-<g id="node18" class="node"><title>t19</title>
-<polygon fill="#efa03b" stroke="black" points="323.772,-270.173 78.2284,-270.173 74.2284,-266.173 74.2284,-234.173 319.772,-234.173 323.772,-238.173 323.772,-270.173"/>
-<polyline fill="none" stroke="black" points="319.772,-266.173 74.2284,-266.173 "/>
-<polyline fill="none" stroke="black" points="319.772,-266.173 319.772,-234.173 "/>
-<polyline fill="none" stroke="black" points="319.772,-266.173 323.772,-270.173 "/>
-<text text-anchor="middle" x="199" y="-246.173" font-family="Times,serif" font-size="20.00">ocrmypdf.pipeline.skip_page</text>
-</g>
-<!-- t4&#45;&gt;t19 -->
-<g id="edge26" class="edge"><title>t4&#45;&gt;t19</title>
-<path fill="none" stroke="#0044a0" d="M425.782,-752.078C271.736,-744.795 37,-720.655 37,-641.173 37,-641.173 37,-641.173 37,-377.173 37,-325.92 88.7624,-292.989 133.769,-274.043"/>
-<polygon fill="#0044a0" stroke="#0044a0" points="135.289,-277.203 143.249,-270.211 132.666,-270.713 135.289,-277.203"/>
-</g>
-<!-- t17 -->
-<g id="node19" class="node"><title>t17</title>
-<polygon fill="#66ccff" stroke="black" points="1499.67,-328.173 1094.33,-328.173 1090.33,-324.173 1090.33,-292.173 1495.67,-292.173 1499.67,-296.173 1499.67,-328.173"/>
-<polyline fill="none" stroke="black" points="1495.67,-324.173 1090.33,-324.173 "/>
-<polyline fill="none" stroke="black" points="1495.67,-324.173 1495.67,-292.173 "/>
-<polyline fill="none" stroke="black" points="1495.67,-324.173 1499.67,-328.173 "/>
-<text text-anchor="middle" x="1295" y="-304.173" font-family="Times,serif" font-size="20.00">ocrmypdf.pipeline.ocr_tesseract_and_render_pdf</text>
-</g>
-<!-- t4&#45;&gt;t17 -->
-<g id="edge28" class="edge"><title>t4&#45;&gt;t17</title>
-<path fill="none" stroke="#0044a0" d="M688.477,-752.611C947.521,-745.804 1499,-721.841 1499,-641.173 1499,-641.173 1499,-641.173 1499,-455.173 1499,-407.201 1508.25,-383.766 1474,-350.173 1465.98,-342.302 1448.74,-335.804 1427.99,-330.522"/>
-<polygon fill="#0044a0" stroke="#0044a0" points="1428.77,-327.11 1418.23,-328.18 1427.14,-333.917 1428.77,-327.11"/>
-</g>
-<!-- t6 -->
-<g id="node7" class="node"><title>t6</title>
-<polygon fill="#efa03b" stroke="black" points="1089.08,-658.173 664.92,-658.173 660.92,-654.173 660.92,-622.173 1085.08,-622.173 1089.08,-626.173 1089.08,-658.173"/>
-<polyline fill="none" stroke="black" points="1085.08,-654.173 660.92,-654.173 "/>
-<polyline fill="none" stroke="black" points="1085.08,-654.173 1085.08,-622.173 "/>
-<polyline fill="none" stroke="black" points="1085.08,-654.173 1089.08,-658.173 "/>
-<text text-anchor="middle" x="875" y="-634.173" font-family="Times,serif" font-size="20.00">ocrmypdf.pipeline.preprocess_remove_background</text>
-</g>
-<!-- t5&#45;&gt;t6 -->
-<g id="edge7" class="edge"><title>t5&#45;&gt;t6</title>
-<path fill="none" stroke="#0044a0" d="M875,-680.066C875,-676.375 875,-672.385 875,-668.415"/>
-<polygon fill="#0044a0" stroke="#0044a0" points="878.5,-668.174 875,-658.174 871.5,-668.174 878.5,-668.174"/>
-</g>
-<!-- t11 -->
-<g id="node14" class="node"><title>t11</title>
-<polygon fill="#efa03b" stroke="black" points="1096,-484.173 712.187,-456.173 1096,-428.173 1479.81,-456.173 1096,-484.173"/>
-<text text-anchor="middle" x="1096" y="-450.173" font-family="Times,serif" font-size="20.00">ocrmypdf.pipeline.select_visible_page_image</text>
-</g>
-<!-- t5&#45;&gt;t11 -->
-<g id="edge18" class="edge"><title>t5&#45;&gt;t11</title>
-<path fill="none" stroke="#0044a0" d="M1051.07,-680.0px8C1072.76,-674.712 1090.1,-667.576 1098,-658.173 1136.53,-612.317 1122.5,-537.602 1109.06,-493.335"/>
-<polygon fill="#0044a0" stroke="#0044a0" points="1112.33,-492.043 1105.96,-483.573 1105.65,-494.164 1112.33,-492.043"/>
-</g>
-<!-- t7 -->
-<g id="node8" class="node"><title>t7</title>
-<polygon fill="#efa03b" stroke="black" points="1039.68,-600.173 720.324,-600.173 716.324,-596.173 716.324,-564.173 1035.68,-564.173 1039.68,-568.173 1039.68,-600.173"/>
-<polyline fill="none" stroke="black" points="1035.68,-596.173 716.324,-596.173 "/>
-<polyline fill="none" stroke="black" points="1035.68,-596.173 1035.68,-564.173 "/>
-<polyline fill="none" stroke="black" points="1035.68,-596.173 1039.68,-600.173 "/>
-<text text-anchor="middle" x="878" y="-576.173" font-family="Times,serif" font-size="20.00">ocrmypdf.pipeline.preprocess_deskew</text>
-</g>
-<!-- t6&#45;&gt;t7 -->
-<g id="edge8" class="edge"><title>t6&#45;&gt;t7</title>
-<path fill="none" stroke="#0044a0" d="M875.916,-622.066C876.114,-618.375 876.328,-614.385 876.541,-610.415"/>
-<polygon fill="#0044a0" stroke="#0044a0" points="880.049,-610.347 877.089,-600.174 873.059,-609.972 880.049,-610.347"/>
-</g>
-<!-- t6&#45;&gt;t11 -->
-<g id="edge17" class="edge"><title>t6&#45;&gt;t11</title>
-<path fill="none" stroke="#0044a0" d="M990.695,-622.152C1016.54,-616.369 1039.2,-609.066 1049,-600.173 1078.78,-573.156 1089.74,-526.964 1093.74,-494.403"/>
-<polygon fill="#0044a0" stroke="#0044a0" points="1097.24,-494.666 1094.82,-484.351 1090.28,-493.924 1097.24,-494.666"/>
-</g>
-<!-- t8 -->
-<g id="node9" class="node"><title>t8</title>
-<polygon fill="#efa03b" stroke="black" points="1030.88,-542.173 729.117,-542.173 725.117,-538.173 725.117,-506.173 1026.88,-506.173 1030.88,-510.173 1030.88,-542.173"/>
-<polyline fill="none" stroke="black" points="1026.88,-538.173 725.117,-538.173 "/>
-<polyline fill="none" stroke="black" points="1026.88,-538.173 1026.88,-506.173 "/>
-<polyline fill="none" stroke="black" points="1026.88,-538.173 1030.88,-542.173 "/>
-<text text-anchor="middle" x="878" y="-518.173" font-family="Times,serif" font-size="20.00">ocrmypdf.pipeline.preprocess_clean</text>
-</g>
-<!-- t7&#45;&gt;t8 -->
-<g id="edge9" class="edge"><title>t7&#45;&gt;t8</title>
-<path fill="none" stroke="#0044a0" d="M878,-564.066C878,-560.375 878,-556.385 878,-552.415"/>
-<polygon fill="#0044a0" stroke="#0044a0" points="881.5,-552.174 878,-542.174 874.5,-552.174 881.5,-552.174"/>
-</g>
-<!-- t7&#45;&gt;t11 -->
-<g id="edge16" class="edge"><title>t7&#45;&gt;t11</title>
-<path fill="none" stroke="#0044a0" d="M995.441,-564.147C1011.26,-558.713 1026.62,-551.566 1040,-542.173 1057.45,-529.919 1070.89,-510.334 1080.22,-493.051"/>
-<polygon fill="#0044a0" stroke="#0044a0" points="1083.55,-494.243 1084.99,-483.747 1077.31,-491.053 1083.55,-494.243"/>
-</g>
-<!-- t9 -->
-<g id="node10" class="node"><title>t9</title>
-<polygon fill="#efa03b" stroke="black" points="694.109,-474.173 389.891,-474.173 385.891,-470.173 385.891,-438.173 690.109,-438.173 694.109,-442.173 694.109,-474.173"/>
-<polyline fill="none" stroke="black" points="690.109,-470.173 385.891,-470.173 "/>
-<polyline fill="none" stroke="black" points="690.109,-470.173 690.109,-438.173 "/>
-<polyline fill="none" stroke="black" points="690.109,-470.173 694.109,-474.173 "/>
-<text text-anchor="middle" x="540" y="-450.173" font-family="Times,serif" font-size="20.00">ocrmypdf.pipeline.select_ocr_image</text>
-</g>
-<!-- t8&#45;&gt;t9 -->
-<g id="edge10" class="edge"><title>t8&#45;&gt;t9</title>
-<path fill="none" stroke="#0044a0" d="M790.517,-506.09C743.487,-496.907 685.383,-485.561 636.976,-476.109"/>
-<polygon fill="#0044a0" stroke="#0044a0" points="637.602,-472.665 627.116,-474.183 636.26,-479.535 637.602,-472.665"/>
-</g>
-<!-- t8&#45;&gt;t11 -->
-<g id="edge15" class="edge"><title>t8&#45;&gt;t11</title>
-<path fill="none" stroke="#0044a0" d="M934.424,-506.09C958.693,-498.742 987.536,-490.01 1014.09,-481.971"/>
-<polygon fill="#0044a0" stroke="#0044a0" points="1015.2,-485.293 1023.75,-479.045 1013.17,-478.593 1015.2,-485.293"/>
-</g>
-<!-- t10 -->
-<g id="node11" class="node"><title>t10</title>
-<polygon fill="#00cc66" stroke="black" points="1440.1,-396.173 1125.9,-396.173 1121.9,-392.173 1121.9,-360.173 1436.1,-360.173 1440.1,-364.173 1440.1,-396.173"/>
-<polyline fill="none" stroke="black" points="1436.1,-392.173 1121.9,-392.173 "/>
-<polyline fill="none" stroke="black" points="1436.1,-392.173 1436.1,-360.173 "/>
-<polyline fill="none" stroke="black" points="1436.1,-392.173 1440.1,-396.173 "/>
-<text text-anchor="middle" x="1281" y="-372.173" font-family="Times,serif" font-size="20.00">ocrmypdf.pipeline.ocr_tesseract_hocr</text>
-</g>
-<!-- t9&#45;&gt;t10 -->
-<g id="edge11" class="edge"><title>t9&#45;&gt;t10</title>
-<path fill="none" stroke="#0044a0" d="M631.992,-438.111C655.104,-434.327 679.903,-430.697 703,-428.173 884.404,-408.343 931.549,-425.567 1113,-406.173 1133.45,-403.987 1155.2,-400.994 1176.03,-397.794"/>
-<polygon fill="#0044a0" stroke="#0044a0" points="1176.83,-401.211 1186.17,-396.209 1175.75,-394.295 1176.83,-401.211"/>
-</g>
-<!-- t9&#45;&gt;t15 -->
-<g id="edge13" class="edge"><title>t9&#45;&gt;t15</title>
-<path fill="none" stroke="#0044a0" d="M474.47,-438.117C429.651,-426.452 370.0px1,-410.957 323.342,-398.782"/>
-<polygon fill="#0044a0" stroke="#0044a0" points="324.123,-395.369 313.564,-396.237 322.36,-402.143 324.123,-395.369"/>
-</g>
-<!-- t13 -->
-<g id="node12" class="node"><title>t13</title>
-<polygon fill="#00cc66" stroke="black" points="683.043,-328.173 374.957,-328.173 370.957,-324.173 370.957,-292.173 679.043,-292.173 683.043,-296.173 683.043,-328.173"/>
-<polyline fill="none" stroke="black" points="679.043,-324.173 370.957,-324.173 "/>
-<polyline fill="none" stroke="black" points="679.043,-324.173 679.043,-292.173 "/>
-<polyline fill="none" stroke="black" points="679.043,-324.173 683.043,-328.173 "/>
-<text text-anchor="middle" x="527" y="-304.173" font-family="Times,serif" font-size="20.00">ocrmypdf.pipeline.render_hocr_page</text>
-</g>
-<!-- t10&#45;&gt;t13 -->
-<g id="edge12" class="edge"><title>t10&#45;&gt;t13</title>
-<path fill="none" stroke="#0044a0" d="M1186.17,-360.113C1162.35,-356.33 1136.79,-352.699 1113,-350.173 929.956,-330.738 880.531,-342.246 693.485,-328.255"/>
-<polygon fill="#0044a0" stroke="#0044a0" points="693.548,-324.75 683.311,-327.48 693.016,-331.73 693.548,-324.75"/>
-</g>
-<!-- t14 -->
-<g id="node17" class="node"><title>t14</title>
-<polygon fill="#00cc66" stroke="black" points="1072.92,-328.173 705.08,-328.173 701.08,-324.173 701.08,-292.173 1068.92,-292.173 1072.92,-296.173 1072.92,-328.173"/>
-<polyline fill="none" stroke="black" points="1068.92,-324.173 701.08,-324.173 "/>
-<polyline fill="none" stroke="black" points="1068.92,-324.173 1068.92,-292.173 "/>
-<polyline fill="none" stroke="black" points="1068.92,-324.173 1072.92,-328.173 "/>
-<text text-anchor="middle" x="887" y="-304.173" font-family="Times,serif" font-size="20.00">ocrmypdf.pipeline.render_hocr_debug_page</text>
-</g>
-<!-- t10&#45;&gt;t14 -->
-<g id="edge25" class="edge"><title>t10&#45;&gt;t14</title>
-<path fill="none" stroke="#0044a0" d="M1179.28,-360.133C1124,-350.873 1055.54,-339.405 998.77,-329.896"/>
-<polygon fill="#0044a0" stroke="#0044a0" points="999.118,-326.405 988.677,-328.205 997.962,-333.309 999.118,-326.405"/>
+<g id="edge2" class="edge">
+<title>t1&#45;&gt;t2</title>
+<path fill="none" stroke="#0044a0" d="M1023.449,-1121.1152C984.5695,-1112.8974 938.0675,-1103.0685 896.4957,-1094.2816"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="897.1066,-1090.8335 886.5989,-1092.1898 895.6589,-1097.6822 897.1066,-1090.8335"/>
 </g>
 <!-- t16 -->
-<g id="node16" class="node"><title>t16</title>
-<polygon fill="#00cc66" stroke="black" points="636.299,-270.173 345.701,-270.173 341.701,-266.173 341.701,-234.173 632.299,-234.173 636.299,-238.173 636.299,-270.173"/>
-<polyline fill="none" stroke="black" points="632.299,-266.173 341.701,-266.173 "/>
-<polyline fill="none" stroke="black" points="632.299,-266.173 632.299,-234.173 "/>
-<polyline fill="none" stroke="black" points="632.299,-266.173 636.299,-270.173 "/>
-<text text-anchor="middle" x="489" y="-246.173" font-family="Times,serif" font-size="20.00">ocrmypdf.pipeline.combine_layers</text>
+<g id="node17" class="node">
+<title>t16</title>
+<polygon fill="#00cc66" stroke="#000000" points="1215.5059,-328.1861 942.4941,-328.1861 938.4941,-324.1861 938.4941,-292.1861 1211.5059,-292.1861 1215.5059,-296.1861 1215.5059,-328.1861"/>
+<polyline fill="none" stroke="#000000" points="1211.5059,-324.1861 938.4941,-324.1861 "/>
+<polyline fill="none" stroke="#000000" points="1211.5059,-324.1861 1211.5059,-292.1861 "/>
+<polyline fill="none" stroke="#000000" points="1211.5059,-324.1861 1215.5059,-328.1861 "/>
+<text text-anchor="middle" x="1077" y="-304.1861" font-family="Times,serif" font-size="20.00" fill="#000000">ocrmypdf.pipeline.weave_layers</text>
 </g>
-<!-- t13&#45;&gt;t16 -->
-<g id="edge22" class="edge"><title>t13&#45;&gt;t16</title>
-<path fill="none" stroke="#0044a0" d="M515.392,-292.066C512.519,-287.833 509.379,-283.205 506.299,-278.666"/>
-<polygon fill="#0044a0" stroke="#0044a0" points="509.048,-276.483 500.537,-270.174 503.256,-280.414 509.048,-276.483"/>
+<!-- t1&#45;&gt;t16 -->
+<g id="edge24" class="edge">
+<title>t1&#45;&gt;t16</title>
+<path fill="none" stroke="#0044a0" d="M1097.2373,-1120.9576C1077.987,-1088.7184 1043.7317,-1019.7372 1063,-963.2656 1106.87,-834.6914 1482.8098,-573.3183 1409,-459.2656 1362.7595,-387.8137 1273.2613,-350.2799 1198.8305,-330.7528"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="1199.4555,-327.3005 1188.9015,-328.2301 1197.7316,-334.0849 1199.4555,-327.3005"/>
 </g>
-<!-- t15&#45;&gt;t16 -->
-<g id="edge21" class="edge"><title>t15&#45;&gt;t16</title>
-<path fill="none" stroke="#0044a0" d="M263.466,-359.936C281.645,-340.695 313.598,-309.935 347,-292.173 361.3,-284.568 377.219,-278.339 393.079,-273.27"/>
-<polygon fill="#0044a0" stroke="#0044a0" points="394.389,-276.53 402.932,-270.262 392.345,-269.835 394.389,-276.53"/>
+<!-- t17 -->
+<g id="node18" class="node">
+<title>t17</title>
+<polygon fill="#efa03b" stroke="#000000" points="1439.5156,-1009.7492 1076.4844,-1009.7492 1072.4844,-1005.7492 1072.4844,-973.7492 1435.5156,-973.7492 1439.5156,-977.7492 1439.5156,-1009.7492"/>
+<polyline fill="none" stroke="#000000" points="1435.5156,-1005.7492 1072.4844,-1005.7492 "/>
+<polyline fill="none" stroke="#000000" points="1435.5156,-1005.7492 1435.5156,-973.7492 "/>
+<polyline fill="none" stroke="#000000" points="1435.5156,-1005.7492 1439.5156,-1009.7492 "/>
+<text text-anchor="middle" x="1256" y="-985.7492" font-family="Times,serif" font-size="20.00" fill="#000000">ocrmypdf.pipeline.generate_postscript_stub</text>
 </g>
-<!-- t11&#45;&gt;t12 -->
-<g id="edge19" class="edge"><title>t11&#45;&gt;t12</title>
-<path fill="none" stroke="#0044a0" d="M1009.92,-434.405C967.591,-424.191 916.524,-411.87 873.373,-401.459"/>
-<polygon fill="#0044a0" stroke="#0044a0" points="873.983,-398.006 863.441,-399.063 872.341,-404.811 873.983,-398.006"/>
+<!-- t1&#45;&gt;t17 -->
+<g id="edge25" class="edge">
+<title>t1&#45;&gt;t17</title>
+<path fill="none" stroke="#0044a0" d="M1127.0251,-1121.1176C1153.0342,-1095.0292 1201.2007,-1046.7157 1230.7429,-1017.0834"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="1233.2458,-1019.5302 1237.8275,-1009.9772 1228.2885,-1014.5879 1233.2458,-1019.5302"/>
+</g>
+<!-- t18 -->
+<g id="node19" class="node">
+<title>t18</title>
+<polygon fill="#efa03b" stroke="#000000" points="1070.189,-214.4288 1263,-187.1099 1455.811,-214.4288 1455.631,-258.6317 1070.369,-258.6317 1070.189,-214.4288"/>
+<polygon fill="none" stroke="#000000" points="1066.1715,-210.9543 1263,-183.0662 1459.8285,-210.9543 1459.6181,-262.6353 1066.3819,-262.6353 1066.1715,-210.9543"/>
+<text text-anchor="middle" x="1263" y="-220.6461" font-family="Times,serif" font-size="20.00" fill="#000000">ocrmypdf.pipeline.metadata_fixup</text>
+</g>
+<!-- t1&#45;&gt;t18 -->
+<g id="edge28" class="edge">
+<title>t1&#45;&gt;t18</title>
+<path fill="none" stroke="#0044a0" d="M1241.1115,-1121.1192C1311.0076,-1105.2558 1393.5851,-1075.5895 1449,-1020.2329 1458.4922,-1010.7507 1459,-1005.1661 1459,-991.7492 1459,-991.7492 1459,-991.7492 1459,-393.7258 1459,-341.9727 1441.8377,-325.2216 1402,-292.1861 1390.9869,-283.0534 1378.4885,-274.871 1365.6104,-267.6415"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="1367.1079,-264.4723 1356.6476,-262.7888 1363.775,-270.6279 1367.1079,-264.4723"/>
+</g>
+<!-- t3 -->
+<g id="node4" class="node">
+<title>t3</title>
+<polygon fill="#efa03b" stroke="#000000" points="1015.5194,-999.3074 785,-1016.2081 554.4806,-999.3074 554.6958,-971.9616 1015.3042,-971.9616 1015.5194,-999.3074"/>
+<polygon fill="none" stroke="#000000" points="1019.5491,-1003.0204 785,-1020.2165 550.4509,-1003.0204 550.7267,-967.9639 1019.2733,-967.9639 1019.5491,-1003.0204"/>
+<text text-anchor="middle" x="785" y="-985.7492" font-family="Times,serif" font-size="20.00" fill="#000000">ocrmypdf.pipeline.ocr_or_skip</text>
+</g>
+<!-- t2&#45;&gt;t3 -->
+<g id="edge3" class="edge">
+<title>t2&#45;&gt;t3</title>
+<path fill="none" stroke="#0044a0" d="M785,-1046.5938C785,-1041.5635 785,-1036.139 785,-1030.7273"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="788.5001,-1030.4427 785,-1020.4427 781.5001,-1030.4428 788.5001,-1030.4427"/>
+</g>
+<!-- t4 -->
+<g id="node5" class="node">
+<title>t4</title>
+<polygon fill="#efa03b" stroke="#000000" points="889.3166,-941.2656 582.6834,-941.2656 578.6834,-937.2656 578.6834,-905.2656 885.3166,-905.2656 889.3166,-909.2656 889.3166,-941.2656"/>
+<polyline fill="none" stroke="#000000" points="885.3166,-937.2656 578.6834,-937.2656 "/>
+<polyline fill="none" stroke="#000000" points="885.3166,-937.2656 885.3166,-905.2656 "/>
+<polyline fill="none" stroke="#000000" points="885.3166,-937.2656 889.3166,-941.2656 "/>
+<text text-anchor="middle" x="734" y="-917.2656" font-family="Times,serif" font-size="20.00" fill="#000000">ocrmypdf.pipeline.rasterize_preview</text>
+</g>
+<!-- t3&#45;&gt;t4 -->
+<g id="edge4" class="edge">
+<title>t3&#45;&gt;t4</title>
+<path fill="none" stroke="#0044a0" d="M767.1627,-967.797C762.8396,-961.9919 758.1927,-955.7519 753.7858,-949.8343"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="756.3465,-947.4129 747.5666,-941.483 750.7323,-951.5939 756.3465,-947.4129"/>
+</g>
+<!-- t5 -->
+<g id="node6" class="node">
+<title>t5</title>
+<polygon fill="#efa03b" stroke="#000000" points="1028.0824,-883.2656 769.9176,-883.2656 765.9176,-879.2656 765.9176,-847.2656 1024.0824,-847.2656 1028.0824,-851.2656 1028.0824,-883.2656"/>
+<polyline fill="none" stroke="#000000" points="1024.0824,-879.2656 765.9176,-879.2656 "/>
+<polyline fill="none" stroke="#000000" points="1024.0824,-879.2656 1024.0824,-847.2656 "/>
+<polyline fill="none" stroke="#000000" points="1024.0824,-879.2656 1028.0824,-883.2656 "/>
+<text text-anchor="middle" x="897" y="-859.2656" font-family="Times,serif" font-size="20.00" fill="#000000">ocrmypdf.pipeline.orient_page</text>
+</g>
+<!-- t3&#45;&gt;t5 -->
+<g id="edge6" class="edge">
+<title>t3&#45;&gt;t5</title>
+<path fill="none" stroke="#0044a0" d="M869.1177,-967.8063C880.553,-961.0264 890.81,-952.3527 898,-941.2656 907.042,-927.3226 906.9457,-908.7053 904.5139,-893.387"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="907.914,-892.5383 902.5408,-883.4071 901.0469,-893.8961 907.914,-892.5383"/>
+</g>
+<!-- t4&#45;&gt;t5 -->
+<g id="edge5" class="edge">
+<title>t4&#45;&gt;t5</title>
+<path fill="none" stroke="#0044a0" d="M784.6807,-905.2319C801.0865,-899.3943 819.4462,-892.8614 836.4913,-886.7963"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="838.1026,-889.938 846.3506,-883.288 835.7559,-883.343 838.1026,-889.938"/>
+</g>
+<!-- t6 -->
+<g id="node7" class="node">
+<title>t6</title>
+<polygon fill="#efa03b" stroke="#000000" points="1064.7325,-825.2656 689.2675,-825.2656 685.2675,-821.2656 685.2675,-789.2656 1060.7325,-789.2656 1064.7325,-793.2656 1064.7325,-825.2656"/>
+<polyline fill="none" stroke="#000000" points="1060.7325,-821.2656 685.2675,-821.2656 "/>
+<polyline fill="none" stroke="#000000" points="1060.7325,-821.2656 1060.7325,-789.2656 "/>
+<polyline fill="none" stroke="#000000" points="1060.7325,-821.2656 1064.7325,-825.2656 "/>
+<text text-anchor="middle" x="875" y="-801.2656" font-family="Times,serif" font-size="20.00" fill="#000000">ocrmypdf.pipeline.rasterize_with_ghostscript</text>
+</g>
+<!-- t5&#45;&gt;t6 -->
+<g id="edge7" class="edge">
+<title>t5&#45;&gt;t6</title>
+<path fill="none" stroke="#0044a0" d="M890.1597,-847.2319C888.6839,-843.3412 887.0909,-839.1417 885.5115,-834.9776"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="888.731,-833.5965 881.9119,-825.4878 882.186,-836.0791 888.731,-833.5965"/>
+</g>
+<!-- t13 -->
+<g id="node16" class="node">
+<title>t13</title>
+<polygon fill="#00cc66" stroke="#000000" points="1077,-515.2656 754.4141,-487.2656 1077,-459.2656 1399.5859,-487.2656 1077,-515.2656"/>
+<text text-anchor="middle" x="1077" y="-481.2656" font-family="Times,serif" font-size="20.00" fill="#000000">ocrmypdf.pipeline.select_image_layer</text>
+</g>
+<!-- t5&#45;&gt;t13 -->
+<g id="edge20" class="edge">
+<title>t5&#45;&gt;t13</title>
+<path fill="none" stroke="#0044a0" d="M1000.2704,-847.241C1031.2359,-840.6873 1060.5415,-832.9862 1074,-825.2656 1114.0954,-802.2644 1145,-795.4899 1145,-749.2656 1145,-749.2656 1145,-749.2656 1145,-633.2656 1145,-590.368 1154.8687,-575.2844 1135,-537.2656 1131.571,-530.7041 1126.8893,-524.6314 1121.6622,-519.1451"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="1123.8989,-516.4405 1114.2626,-512.0367 1119.0494,-521.4885 1123.8989,-516.4405"/>
+</g>
+<!-- t7 -->
+<g id="node8" class="node">
+<title>t7</title>
+<polygon fill="#efa03b" stroke="#000000" points="856.0801,-767.2656 431.9199,-767.2656 427.9199,-763.2656 427.9199,-731.2656 852.0801,-731.2656 856.0801,-735.2656 856.0801,-767.2656"/>
+<polyline fill="none" stroke="#000000" points="852.0801,-763.2656 427.9199,-763.2656 "/>
+<polyline fill="none" stroke="#000000" points="852.0801,-763.2656 852.0801,-731.2656 "/>
+<polyline fill="none" stroke="#000000" points="852.0801,-763.2656 856.0801,-767.2656 "/>
+<text text-anchor="middle" x="642" y="-743.2656" font-family="Times,serif" font-size="20.00" fill="#000000">ocrmypdf.pipeline.preprocess_remove_background</text>
+</g>
+<!-- t6&#45;&gt;t7 -->
+<g id="edge8" class="edge">
+<title>t6&#45;&gt;t7</title>
+<path fill="none" stroke="#0044a0" d="M802.5546,-789.2319C777.7884,-783.067 749.9071,-776.1266 724.4138,-769.7806"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="724.95,-766.3073 714.4006,-767.288 723.259,-773.1 724.95,-766.3073"/>
+</g>
+<!-- t12 -->
+<g id="node15" class="node">
+<title>t12</title>
+<polygon fill="#efa03b" stroke="#000000" points="742,-593.2656 358.1874,-565.2656 742,-537.2656 1125.8126,-565.2656 742,-593.2656"/>
+<text text-anchor="middle" x="742" y="-559.2656" font-family="Times,serif" font-size="20.00" fill="#000000">ocrmypdf.pipeline.select_visible_page_image</text>
+</g>
+<!-- t6&#45;&gt;t12 -->
+<g id="edge18" class="edge">
+<title>t6&#45;&gt;t12</title>
+<path fill="none" stroke="#0044a0" d="M875.1443,-789.1129C874.6867,-773.2956 872.5831,-750.0189 865,-731.2656 844.2991,-680.0716 804.0126,-630.4165 775.1838,-598.9641"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="777.4937,-596.3085 768.1202,-591.3701 772.3682,-601.076 777.4937,-596.3085"/>
+</g>
+<!-- t8 -->
+<g id="node9" class="node">
+<title>t8</title>
+<polygon fill="#efa03b" stroke="#000000" points="732.6759,-709.2656 413.3241,-709.2656 409.3241,-705.2656 409.3241,-673.2656 728.6759,-673.2656 732.6759,-677.2656 732.6759,-709.2656"/>
+<polyline fill="none" stroke="#000000" points="728.6759,-705.2656 409.3241,-705.2656 "/>
+<polyline fill="none" stroke="#000000" points="728.6759,-705.2656 728.6759,-673.2656 "/>
+<polyline fill="none" stroke="#000000" points="728.6759,-705.2656 732.6759,-709.2656 "/>
+<text text-anchor="middle" x="571" y="-685.2656" font-family="Times,serif" font-size="20.00" fill="#000000">ocrmypdf.pipeline.preprocess_deskew</text>
+</g>
+<!-- t7&#45;&gt;t8 -->
+<g id="edge9" class="edge">
+<title>t7&#45;&gt;t8</title>
+<path fill="none" stroke="#0044a0" d="M619.9243,-731.2319C613.9709,-726.3685 607.4267,-721.0226 601.115,-715.8666"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="603.2653,-713.1037 593.3065,-709.4878 598.8367,-718.5248 603.2653,-713.1037"/>
+</g>
+<!-- t7&#45;&gt;t12 -->
+<g id="edge17" class="edge">
+<title>t7&#45;&gt;t12</title>
+<path fill="none" stroke="#0044a0" d="M717.0346,-731.1646C726.8757,-725.6884 735.7103,-718.5557 742,-709.2656 763.0291,-678.205 759.4083,-634.0888 752.8082,-602.8898"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="756.1481,-601.7976 750.487,-592.842 749.3278,-603.3733 756.1481,-601.7976"/>
+</g>
+<!-- t9 -->
+<g id="node10" class="node">
+<title>t9</title>
+<polygon fill="#efa03b" stroke="#000000" points="712.8828,-651.2656 411.1172,-651.2656 407.1172,-647.2656 407.1172,-615.2656 708.8828,-615.2656 712.8828,-619.2656 712.8828,-651.2656"/>
+<polyline fill="none" stroke="#000000" points="708.8828,-647.2656 407.1172,-647.2656 "/>
+<polyline fill="none" stroke="#000000" points="708.8828,-647.2656 708.8828,-615.2656 "/>
+<polyline fill="none" stroke="#000000" points="708.8828,-647.2656 712.8828,-651.2656 "/>
+<text text-anchor="middle" x="560" y="-627.2656" font-family="Times,serif" font-size="20.00" fill="#000000">ocrmypdf.pipeline.preprocess_clean</text>
+</g>
+<!-- t8&#45;&gt;t9 -->
+<g id="edge10" class="edge">
+<title>t8&#45;&gt;t9</title>
+<path fill="none" stroke="#0044a0" d="M567.5798,-673.2319C566.8624,-669.4493 566.0897,-665.3747 565.3216,-661.3247"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="568.7581,-660.6605 563.4559,-651.4878 561.8807,-661.9649 568.7581,-660.6605"/>
+</g>
+<!-- t8&#45;&gt;t12 -->
+<g id="edge16" class="edge">
+<title>t8&#45;&gt;t12</title>
+<path fill="none" stroke="#0044a0" d="M670.0045,-673.2618C693.2528,-667.2338 713.6919,-659.8307 722,-651.2656 734.1971,-638.6912 739.4901,-620.2051 741.6123,-603.5914"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="745.1041,-603.8427 742.5574,-593.5585 738.1349,-603.1862 745.1041,-603.8427"/>
+</g>
+<!-- t10 -->
+<g id="node11" class="node">
+<title>t10</title>
+<polygon fill="#efa03b" stroke="#000000" points="340.1094,-583.2656 35.8906,-583.2656 31.8906,-579.2656 31.8906,-547.2656 336.1094,-547.2656 340.1094,-551.2656 340.1094,-583.2656"/>
+<polyline fill="none" stroke="#000000" points="336.1094,-579.2656 31.8906,-579.2656 "/>
+<polyline fill="none" stroke="#000000" points="336.1094,-579.2656 336.1094,-547.2656 "/>
+<polyline fill="none" stroke="#000000" points="336.1094,-579.2656 340.1094,-583.2656 "/>
+<text text-anchor="middle" x="186" y="-559.2656" font-family="Times,serif" font-size="20.00" fill="#000000">ocrmypdf.pipeline.select_ocr_image</text>
+</g>
+<!-- t9&#45;&gt;t10 -->
+<g id="edge11" class="edge">
+<title>t9&#45;&gt;t10</title>
+<path fill="none" stroke="#0044a0" d="M460.7568,-615.2213C409.7279,-605.9434 347.4237,-594.6153 295.0537,-585.0935"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="295.5223,-581.6214 285.0575,-583.276 294.2701,-588.5085 295.5223,-581.6214"/>
+</g>
+<!-- t9&#45;&gt;t12 -->
+<g id="edge15" class="edge">
+<title>t9&#45;&gt;t12</title>
+<path fill="none" stroke="#0044a0" d="M608.2948,-615.2213C627.0226,-608.2242 648.8712,-600.0609 669.4134,-592.3859"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="670.9148,-595.5613 679.0573,-588.7826 668.4648,-589.004 670.9148,-595.5613"/>
+</g>
+<!-- t11 -->
+<g id="node12" class="node">
+<title>t11</title>
+<polygon fill="#00cc66" stroke="#000000" points="334.0996,-505.2656 19.9004,-505.2656 15.9004,-501.2656 15.9004,-469.2656 330.0996,-469.2656 334.0996,-473.2656 334.0996,-505.2656"/>
+<polyline fill="none" stroke="#000000" points="330.0996,-501.2656 15.9004,-501.2656 "/>
+<polyline fill="none" stroke="#000000" points="330.0996,-501.2656 330.0996,-469.2656 "/>
+<polyline fill="none" stroke="#000000" points="330.0996,-501.2656 334.0996,-505.2656 "/>
+<text text-anchor="middle" x="175" y="-481.2656" font-family="Times,serif" font-size="20.00" fill="#000000">ocrmypdf.pipeline.ocr_tesseract_hocr</text>
+</g>
+<!-- t10&#45;&gt;t11 -->
+<g id="edge12" class="edge">
+<title>t10&#45;&gt;t11</title>
+<path fill="none" stroke="#0044a0" d="M183.4487,-547.1748C182.1254,-537.7914 180.4788,-526.1154 178.9917,-515.5701"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="182.4378,-514.9417 177.5755,-505.5285 175.5064,-515.9193 182.4378,-514.9417"/>
+</g>
+<!-- t15 -->
+<g id="node14" class="node">
+<title>t15</title>
+<polygon fill="#ff69b4" stroke="#000000" points="736.2696,-505.2656 355.7304,-505.2656 351.7304,-501.2656 351.7304,-469.2656 732.2696,-469.2656 736.2696,-473.2656 736.2696,-505.2656"/>
+<polyline fill="none" stroke="#000000" points="732.2696,-501.2656 351.7304,-501.2656 "/>
+<polyline fill="none" stroke="#000000" points="732.2696,-501.2656 732.2696,-469.2656 "/>
+<polyline fill="none" stroke="#000000" points="732.2696,-501.2656 736.2696,-505.2656 "/>
+<text text-anchor="middle" x="544" y="-481.2656" font-family="Times,serif" font-size="20.00" fill="#000000">ocrmypdf.pipeline.ocr_tesseract_textonly_pdf</text>
+</g>
+<!-- t10&#45;&gt;t15 -->
+<g id="edge14" class="edge">
+<title>t10&#45;&gt;t15</title>
+<path fill="none" stroke="#0044a0" d="M269.0322,-547.1748C323.4947,-535.3086 394.7854,-519.776 451.1284,-507.5002"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="452.0829,-510.8744 461.1086,-505.3257 450.5927,-504.0348 452.0829,-510.8744"/>
+</g>
+<!-- t14 -->
+<g id="node13" class="node">
+<title>t14</title>
+<polygon fill="#00cc66" stroke="#000000" points="330.0433,-411.7258 21.9567,-411.7258 17.9567,-407.7258 17.9567,-375.7258 326.0433,-375.7258 330.0433,-379.7258 330.0433,-411.7258"/>
+<polyline fill="none" stroke="#000000" points="326.0433,-407.7258 17.9567,-407.7258 "/>
+<polyline fill="none" stroke="#000000" points="326.0433,-407.7258 326.0433,-375.7258 "/>
+<polyline fill="none" stroke="#000000" points="326.0433,-407.7258 330.0433,-411.7258 "/>
+<text text-anchor="middle" x="174" y="-387.7258" font-family="Times,serif" font-size="20.00" fill="#000000">ocrmypdf.pipeline.render_hocr_page</text>
 </g>
 <!-- t11&#45;&gt;t14 -->
-<g id="edge24" class="edge"><title>t11&#45;&gt;t14</title>
-<path fill="none" stroke="#0044a0" d="M1334.06,-445.464C1386.49,-438.209 1431.63,-426.12 1449,-406.173 1465.34,-387.403 1466.07,-368.289 1449,-350.173 1422.45,-321.987 1153.75,-330.0px 1083.05,-328.037"/>
-<polygon fill="#0044a0" stroke="#0044a0" points="1083,-324.531 1072.85,-327.564 1082.68,-331.524 1083,-324.531"/>
+<g id="edge13" class="edge">
+<title>t11&#45;&gt;t14</title>
+<path fill="none" stroke="#0044a0" d="M174.8072,-469.2302C174.6642,-455.8584 174.4666,-437.3702 174.3027,-422.0357"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="177.8024,-421.987 174.1956,-412.025 170.8028,-422.0619 177.8024,-421.987"/>
 </g>
-<!-- t11&#45;&gt;t17 -->
-<g id="edge27" class="edge"><title>t11&#45;&gt;t17</title>
-<path fill="none" stroke="#0044a0" d="M1278.64,-441.463C1364.44,-433.122 1450.86,-421.174 1464,-406.173 1480.4,-387.448 1479.49,-369.65 1464,-350.173 1457.83,-342.418 1443.67,-336.074 1426.02,-330.926"/>
-<polygon fill="#0044a0" stroke="#0044a0" points="1426.46,-327.418 1415.89,-328.188 1424.63,-334.176 1426.46,-327.418"/>
+<!-- t19 -->
+<g id="node22" class="node">
+<title>t19</title>
+<polygon fill="#efa03b" stroke="#000000" points="351.7205,-381.5085 545,-354.1897 738.2795,-381.5085 738.0991,-425.7112 351.9009,-425.7112 351.7205,-381.5085"/>
+<polygon fill="none" stroke="#000000" points="347.7033,-378.0329 545,-350.1463 742.2967,-378.0329 742.0858,-429.7148 347.9142,-429.7148 347.7033,-378.0329"/>
+<text text-anchor="middle" x="545" y="-387.7258" font-family="Times,serif" font-size="20.00" fill="#000000">ocrmypdf.pipeline.merge_sidecars</text>
 </g>
-<!-- t12&#45;&gt;t16 -->
-<g id="edge23" class="edge"><title>t12&#45;&gt;t16</title>
-<path fill="none" stroke="#0044a0" d="M624.426,-363.718C509.174,-353.04 370.992,-338.277 362,-328.173 351.364,-316.22 352.491,-305.04 362,-292.173 366.819,-285.651 372.71,-280.186 379.287,-275.609"/>
-<polygon fill="#0044a0" stroke="#0044a0" points="381.274,-278.496 387.956,-270.274 377.605,-272.534 381.274,-278.496"/>
+<!-- t11&#45;&gt;t19 -->
+<g id="edge32" class="edge">
+<title>t11&#45;&gt;t19</title>
+<path fill="none" stroke="#0044a0" d="M246.3397,-469.2302C287.966,-458.7066 342.1269,-445.0142 392.8772,-432.184"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="393.8058,-435.5594 402.6429,-429.7151 392.0901,-428.773 393.8058,-435.5594"/>
+</g>
+<!-- t14&#45;&gt;t16 -->
+<g id="edge22" class="edge">
+<title>t14&#45;&gt;t16</title>
+<path fill="none" stroke="#0044a0" d="M230.6615,-375.7128C262.2207,-366.4581 302.4172,-355.9425 339,-350.1861 448.3957,-332.9725 745.7869,-320.7866 927.9215,-314.6743"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="928.248,-318.1655 938.1258,-314.3342 928.0148,-311.1693 928.248,-318.1655"/>
+</g>
+<!-- t15&#45;&gt;t16 -->
+<g id="edge21" class="edge">
+<title>t15&#45;&gt;t16</title>
+<path fill="none" stroke="#0044a0" d="M630.0636,-469.2083C667.5329,-460.6467 711.76,-449.5912 751,-437.2656 850.4985,-406.0121 963.1653,-359.5222 1026.586,-332.2894"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="1028.1566,-335.4238 1035.9553,-328.2523 1025.3866,-328.9951 1028.1566,-335.4238"/>
+</g>
+<!-- t15&#45;&gt;t19 -->
+<g id="edge31" class="edge">
+<title>t15&#45;&gt;t19</title>
+<path fill="none" stroke="#0044a0" d="M544.1928,-469.2302C544.2822,-460.8687 544.393,-450.5066 544.5035,-440.166"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="548.006,-439.9443 544.6132,-429.9075 541.0064,-439.8694 548.006,-439.9443"/>
+</g>
+<!-- t12&#45;&gt;t13 -->
+<g id="edge19" class="edge">
+<title>t12&#45;&gt;t13</title>
+<path fill="none" stroke="#0044a0" d="M833.9833,-543.8486C879.0975,-533.3444 933.4556,-520.6879 979.3116,-510.0109"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="980.3156,-513.3709 989.2614,-507.6943 978.7282,-506.5532 980.3156,-513.3709"/>
+</g>
+<!-- t13&#45;&gt;t16 -->
+<g id="edge23" class="edge">
+<title>t13&#45;&gt;t16</title>
+<path fill="none" stroke="#0044a0" d="M1077,-459.2068C1077,-426.2624 1077,-371.9187 1077,-338.7552"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="1080.5001,-338.3818 1077,-328.3819 1073.5001,-338.3819 1080.5001,-338.3818"/>
+</g>
+<!-- t16&#45;&gt;t18 -->
+<g id="edge27" class="edge">
+<title>t16&#45;&gt;t18</title>
+<path fill="none" stroke="#0044a0" d="M1117.3592,-292.0592C1133.8695,-284.6437 1153.6803,-275.7459 1173.2953,-266.9361"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="1174.8979,-270.0531 1182.586,-262.7632 1172.0299,-263.6676 1174.8979,-270.0531"/>
+</g>
+<!-- t17&#45;&gt;t18 -->
+<g id="edge26" class="edge">
+<title>t17&#45;&gt;t18</title>
+<path fill="none" stroke="#0044a0" d="M1326.2292,-973.7283C1377.8362,-955.768 1439,-922.4247 1439,-865.2656 1439,-865.2656 1439,-865.2656 1439,-393.7258 1439,-338.7092 1393.2056,-296.3464 1348.3356,-268.0433"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="1350.0403,-264.9831 1339.6842,-262.7465 1346.3852,-270.9531 1350.0403,-264.9831"/>
 </g>
 <!-- t20 -->
-<g id="node21" class="node"><title>t20</title>
-<polygon fill="#efa03b" stroke="black" points="234.918,-156.426 480,-129.117 725.082,-156.426 724.853,-200.614 235.147,-200.614 234.918,-156.426"/>
-<polygon fill="none" stroke="black" points="230.903,-152.847 480,-125.09 729.097,-152.847 728.829,-204.616 231.171,-204.616 230.903,-152.847"/>
-<text text-anchor="middle" x="480" y="-162.639" font-family="Times,serif" font-size="20.00">ocrmypdf.pipeline.merge_pages_ghostscript</text>
-</g>
-<!-- t16&#45;&gt;t20 -->
-<g id="edge33" class="edge"><title>t16&#45;&gt;t20</title>
-<path fill="none" stroke="#0044a0" d="M487.091,-233.881C486.46,-228.165 485.726,-221.515 484.974,-214.703"/>
-<polygon fill="#0044a0" stroke="#0044a0" points="488.446,-214.253 483.87,-204.697 481.488,-215.021 488.446,-214.253"/>
-</g>
-<!-- t16&#45;&gt;t21 -->
-<g id="edge37" class="edge"><title>t16&#45;&gt;t21</title>
-<path fill="none" stroke="#0044a0" d="M602.543,-234.159C645.082,-227.582 693.805,-219.809 738,-212.173 748.572,-210.346 759.416,-208.431 770.357,-206.468"/>
-<polygon fill="#0044a0" stroke="#0044a0" points="771.206,-209.872 780.427,-204.653 769.964,-202.983 771.206,-209.872"/>
-</g>
-<!-- t14&#45;&gt;t20 -->
-<g id="edge34" class="edge"><title>t14&#45;&gt;t20</title>
-<path fill="none" stroke="#0044a0" d="M837.094,-292.063C776.411,-271.259 672.165,-235.52 591.922,-208.01"/>
-<polygon fill="#0044a0" stroke="#0044a0" points="592.855,-204.63 582.26,-204.697 590.584,-211.251 592.855,-204.63"/>
-</g>
-<!-- t14&#45;&gt;t21 -->
-<g id="edge38" class="edge"><title>t14&#45;&gt;t21</title>
-<path fill="none" stroke="#0044a0" d="M896.319,-292.063C906.85,-272.729 924.406,-240.497 938.861,-213.958"/>
-<polygon fill="#0044a0" stroke="#0044a0" points="942.118,-215.294 943.828,-204.838 935.971,-211.946 942.118,-215.294"/>
-</g>
-<!-- t19&#45;&gt;t20 -->
-<g id="edge30" class="edge"><title>t19&#45;&gt;t20</title>
-<path fill="none" stroke="#0044a0" d="M257.907,-234.081C284.597,-226.336 317.298,-216.848 349.316,-207.558"/>
-<polygon fill="#0044a0" stroke="#0044a0" points="350.595,-210.831 359.224,-204.683 348.645,-204.108 350.595,-210.831"/>
-</g>
-<!-- t19&#45;&gt;t21 -->
-<g id="edge35" class="edge"><title>t19&#45;&gt;t21</title>
-<path fill="none" stroke="#0044a0" d="M323.792,-235.042C326.891,-234.738 329.964,-234.447 333,-234.173 512.532,-217.929 559.043,-233.851 738,-212.173 751.869,-210.493 766.169,-208.472 780.522,-206.237"/>
-<polygon fill="#0044a0" stroke="#0044a0" points="781.136,-209.683 790.462,-204.657 780.037,-202.77 781.136,-209.683"/>
-</g>
-<!-- t17&#45;&gt;t20 -->
-<g id="edge32" class="edge"><title>t17&#45;&gt;t20</title>
-<path fill="none" stroke="#0044a0" d="M1195.47,-292.133C1071.63,-270.93 856.728,-234.138 694.688,-206.395"/>
-<polygon fill="#0044a0" stroke="#0044a0" points="695.028,-202.903 684.581,-204.665 693.846,-209.802 695.028,-202.903"/>
-</g>
-<!-- t17&#45;&gt;t21 -->
-<g id="edge36" class="edge"><title>t17&#45;&gt;t21</title>
-<path fill="none" stroke="#0044a0" d="M1254.29,-292.063C1205.19,-271.428 1121.13,-236.1 1055.9,-208.683"/>
-<polygon fill="#0044a0" stroke="#0044a0" points="1056.99,-205.345 1046.42,-204.697 1054.28,-211.799 1056.99,-205.345"/>
+<g id="node20" class="node">
+<title>t20</title>
+<polygon fill="#efa03b" stroke="#000000" points="1400.3184,-161.1062 1129.6816,-161.1062 1125.6816,-157.1062 1125.6816,-125.1062 1396.3184,-125.1062 1400.3184,-129.1062 1400.3184,-161.1062"/>
+<polyline fill="none" stroke="#000000" points="1396.3184,-157.1062 1125.6816,-157.1062 "/>
+<polyline fill="none" stroke="#000000" points="1396.3184,-157.1062 1396.3184,-125.1062 "/>
+<polyline fill="none" stroke="#000000" points="1396.3184,-157.1062 1400.3184,-161.1062 "/>
+<text text-anchor="middle" x="1263" y="-137.1062" font-family="Times,serif" font-size="20.00" fill="#000000">ocrmypdf.pipeline.optimize_pdf</text>
 </g>
 <!-- t18&#45;&gt;t20 -->
-<g id="edge31" class="edge"><title>t18&#45;&gt;t20</title>
-<path fill="none" stroke="#0044a0" d="M120.266,-796.105C70.9512,-780.34 17,-751.202 17,-699.173 17,-699.173 17,-699.173 17,-309.173 17,-269.597 31.8505,-255.79 65,-234.173 92.9782,-215.927 154.085,-202.475 221.024,-192.724"/>
-<polygon fill="#0044a0" stroke="#0044a0" points="221.533,-196.187 230.939,-191.311 220.546,-189.256 221.533,-196.187"/>
+<g id="edge29" class="edge">
+<title>t18&#45;&gt;t20</title>
+<path fill="none" stroke="#0044a0" d="M1263,-182.9188C1263,-179.129 1263,-175.3607 1263,-171.739"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="1266.5001,-171.4394 1263,-161.4394 1259.5001,-171.4394 1266.5001,-171.4394"/>
 </g>
-<!-- t22 -->
-<g id="node23" class="node"><title>t22</title>
-<polygon fill="#efa03b" stroke="black" points="554.065,-47.332 721,-20.0049 887.935,-47.332 887.779,-91.5483 554.221,-91.5483 554.065,-47.332"/>
-<polygon fill="none" stroke="black" points="550.054,-43.9306 721,-15.9468 891.946,-43.9306 891.764,-95.5532 550.236,-95.5532 550.054,-43.9306"/>
-<text text-anchor="middle" x="721" y="-53.5531" font-family="Times,serif" font-size="20.00">ocrmypdf.pipeline.copy_final</text>
+<!-- t21 -->
+<g id="node21" class="node">
+<title>t21</title>
+<polygon fill="#efa03b" stroke="#000000" points="1096.0652,-47.332 1263,-20.0049 1429.9348,-47.332 1429.779,-91.5483 1096.221,-91.5483 1096.0652,-47.332"/>
+<polygon fill="none" stroke="#000000" points="1092.0538,-43.9306 1263,-15.9468 1433.9462,-43.9306 1433.7643,-95.5532 1092.2357,-95.5532 1092.0538,-43.9306"/>
+<text text-anchor="middle" x="1263" y="-53.5531" font-family="Times,serif" font-size="20.00" fill="#000000">ocrmypdf.pipeline.copy_final</text>
 </g>
-<!-- t20&#45;&gt;t22 -->
-<g id="edge41" class="edge"><title>t20&#45;&gt;t22</title>
-<path fill="none" stroke="#0044a0" d="M556.585,-133.609C580.784,-122.857 607.72,-110.888 632.67,-99.8018"/>
-<polygon fill="#0044a0" stroke="#0044a0" points="634.408,-102.859 642.125,-95.6004 631.566,-96.4625 634.408,-102.859"/>
-</g>
-<!-- t21&#45;&gt;t22 -->
-<g id="edge40" class="edge"><title>t21&#45;&gt;t22</title>
-<path fill="none" stroke="#0044a0" d="M888.417,-134.636C863.556,-123.635 835.613,-111.27 809.783,-99.8401"/>
-<polygon fill="#0044a0" stroke="#0044a0" points="810.933,-96.5216 800.372,-95.6756 808.1,-102.923 810.933,-96.5216"/>
+<!-- t20&#45;&gt;t21 -->
+<g id="edge30" class="edge">
+<title>t20&#45;&gt;t21</title>
+<path fill="none" stroke="#0044a0" d="M1263,-124.9764C1263,-119.37 1263,-112.9163 1263,-106.2938"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="1266.5001,-105.8456 1263,-95.8457 1259.5001,-105.8457 1266.5001,-105.8456"/>
 </g>
 </g>
 </svg>

docs/plugins.rst

@@ -0,0 +1,24 @@
+=======
+Plugins
+=======
+
+You can use plugins to customize the behavior of OCRmyPDF at certain
+points of interest.
+
+Currently, it is possible to: - override the decision for whether or not
+to perform OCR on a particular file - modify the image is about to be
+sent for OCR
+
+How plugins are imported
+========================
+
+Plugins are imported on demand, by the OCRmyPDF worker process that
+needs to use them. As such, plugins cannot share state with each other,
+and will be imported many times, once for each worker process.
+
+Plugins currently cannot override the same hook.
+
+How plugins are invoked
+=======================
+
+Plugins may be called from the command line:

docs/security.rst

@@ -1,44 +1,162 @@
+===================
 PDF security issues
 ===================
 
-	OCRmyPDF should only be used on PDFs you trust. It is not designed to protect you against malware. 
+   OCRmyPDF should only be used on PDFs you trust. It is not designed to
+   protect you against malware.
 
-Recognizing that many users have an interest in handling PDFs and applying OCR to PDFs they did not generate themselves, this article discusses the security implications of PDFs and how users can protect themselves.
+Recognizing that many users have an interest in handling PDFs and
+applying OCR to PDFs they did not generate themselves, this article
+discusses the security implications of PDFs and how users can protect
+themselves.
 
 The disclaimer applies: this software has no warranties of any kind.
 
 PDFs may contain malware
-------------------------
+========================
 
-PDF is a rich, complex file format. The official PDF 1.7 specification, ISO 32000:2008, is hundreds of packages long and references several annexes each of which are similar in length. PDFs can contain video, audio, JavaScript and other programming, and forms. In some cases, they can open internet connections to pre-selected URLs. All of these possible attack vectors.
+PDF is a rich, complex file format. The official PDF 1.7 specification,
+ISO 32000:2008, is hundreds of pages long and references several annexes
+each of which are similar in length. PDFs can contain video, audio, XML,
+JavaScript and other programming, and forms. In some cases, they can
+open internet connections to pre-selected URLs. All of these possible
+attack vectors.
 
-In short, PDFs `may contain viruses <https://security.stackexchange.com/questions/64052/can-a-pdf-file-contain-a-virus>`_.
+In short, PDFs `may contain
+viruses <https://security.stackexchange.com/questions/64052/can-a-pdf-file-contain-a-virus>`__.
 
-This `article <https://theinvisiblethings.blogspot.ca/2013/02/converting-untrusted-pdfs-into-trusted.html>`_ describes a high-paranoia method which allows potentially hostile PDFs to be viewed and rasterized safely in a disposable virtual machine. A trusted PDF created in this manner is converted to images and loses all information making it searchable and losing all compression. OCRmyPDF could be used restore searchability.
+This
+`article <https://theinvisiblethings.blogspot.ca/2013/02/converting-untrusted-pdfs-into-trusted.html>`__
+describes a high-paranoia method which allows potentially hostile PDFs
+to be viewed and rasterized safely in a disposable virtual machine. A
+trusted PDF created in this manner is converted to images and loses all
+information making it searchable and losing all compression. OCRmyPDF
+could be used restore searchability.
 
 How OCRmyPDF processes PDFs
----------------------------
+===========================
 
-OCRmyPDF must open and interpret your PDF in order to insert an OCR layer. First, it runs all PDFs through `qpdf <https://github.com/qpdf/qpdf>`_, a program that repairs PDFs with syntax errors. This is done because, in the author's experience, a significant number of PDFs in the wild especially those created by scanners are not well-formed files. qpdf makes it more likely that OCRmyPDF will succeed, but offers no security guarantees. qpdf is also used to split the PDF into single page PDFs.
+OCRmyPDF must open and interpret your PDF in order to insert an OCR
+layer. First, it runs all PDFs through
+`pikepdf <https://github.com/pikepdf/pikepdf>`__, a library based on
+`qpdf <https://github.com/qpdf/qpdf>`__, a program that repairs PDFs
+with syntax errors. This is done because, in the author's experience, a
+significant number of PDFs in the wild especially those created by
+scanners are not well-formed files. qpdf makes it more likely that
+OCRmyPDF will succeed, but offers no security guarantees. qpdf is also
+used to split the PDF into single page PDFs.
 
-After qpdf, OCRmyPDF examines each page using `PyPDF2 <https://github.com/mstamy2/PyPDF2>`_. This library also has no warranties or guarantees.
+Finally, OCRmyPDF rasterizes each page of the PDF using
+`Ghostscript <http://ghostscript.com/>`__ in ``-dSAFER`` mode.
 
-Finally, OCRmyPDF rasterizes each page of the PDF using `Ghostscript <http://ghostscript.com/>`_ in ``-dSAFER`` mode. 
+Depending on the options specified, OCRmyPDF may graft the OCR layer
+into the existing PDF or it may essentially reconstruct ("re-fry") a
+visually identical PDF that may be quite different at the binary level.
+That said, OCRmyPDF is not a tool designed for sanitizing PDFs.
 
-Depending on the options specified, OCRmyPDF may graft the OCR layer into the existing PDF or it may essentially reconstruct ("re-fry") a visually identical PDF that may be quite different at the binary level. That said, OCRmyPDF is not a tool designed for sanitizing PDFs.
+.. _ocr-service:
 
-Using OCRmyPDF online
----------------------
+Using OCRmyPDF online or as a service
+=====================================
 
-OCRmyPDF is not designed to be deployed "as a service", in a setting where a user/attacker could upload a file for OCR processing online. It is not designed to be secure in this case.
+OCRmyPDF is not designed for use as a public web service where a
+malicious user could upload a chosen PDF. In particular, it is not
+necessarily secure against PDF malware or PDFs that cause denial of
+service. OCRmyPDF relies on Ghostscript, and therefore, if deployed
+online one should be prepared to comply with Ghostscript's Affero GPL
+license, OCRmyPDF's GPL license, and any other licenses.
 
-Abbyy Cloud OCR is a viable commercial alternative with a web services API. The author also provides professional services that include OCR and building databases around PDFs, and is happy to provide consultation.
+Setting aside these concerns, a side effect of OCRmyPDF is it may
+incidentally sanitize PDFs that contain certain types of malware. It
+runs ``qpdf`` to repair the PDF, which could correct malformed PDF
+structures that are part of an attack. When PDF/A output is selected
+(the default), the input PDF is partially reconstructed by Ghostscript.
+When ``--force-ocr`` is used, all pages are rasterized and reconverted
+to PDF, which could remove malware in embedded images.
+
+OCRmyPDF should be relatively safe to use in a trusted intranet, with
+some considerations:
+
+Limiting CPU usage
+------------------
+
+OCRmyPDF will attempt to use all available CPUs and storage, so
+executing ``nice ocrmypdf`` or limiting the number of jobs with the
+``-j`` argument may ensure the server remains available. Another option
+would be run OCRmyPDF jobs inside a Docker container, a virtual machine,
+or a cloud instance, which can impose its own limits on CPU usage and be
+terminated "from orbit" if it fails to complete.
+
+Temporary storage requirements
+------------------------------
+
+OCRmyPDF will use a large amount of temporary storage for its work,
+proportional to the total number of pixels needed to rasterize the PDF.
+The raster image of a 8.5×11" color page at 300 DPI takes 25 MB
+uncompressed; OCRmyPDF saves its intermediates as PNG, but that still
+means it requires about 9 MB per intermediate based on average
+compression ratios. Multiple intermediates per page are also required,
+depending on the command line given. A rule of thumb would be to allow
+100 MB of temporary storage per page in a file – meaning that a small
+cloud servers or small VM partitions should be provisioned with plenty
+of extra space, if say, a 500 page file might be sent.
+
+To check temporary storage usage on actual files, run
+``ocrmypdf -k ...`` which will preserve and print the path to temporary
+storage when the job is done.
+
+To change where temporary files are stored, change the ``TMPDIR``
+environment variable for ocrmypdf's environment. (Python's
+``tempfile.gettempdir()`` returns the root directory in which temporary
+files will be stored.) For example, one could redirect ``TMPDIR`` to a
+large RAM disk to avoid wear on HDD/SSD and potentially improve
+performance. On Amazon Web Services, ``TMPDIR`` can be set to `empheral
+storage <https://docs.aws.amazon.com/AWSEC2/latest/UserGuide/InstanceStorage.html>`__.
+
+Timeouts
+--------
+
+To prevent excessively long OCR jobs consider setting
+``--tesseract-timeout`` and/or ``--skip-big`` arguments. ``--skip-big``
+is particularly helpful if your PDFs include documents such as reports
+on standard page sizes with large images attached - often large images
+are not worth OCR'ing anyway.
+
+Commercial alternatives
+-----------------------
+
+The author also provides professional services that include OCR and
+building databases around PDFs, and is happy to provide consultation.
+
+Abbyy Cloud OCR is a viable commercial alternative with a web services
+API.
 
 Password protection, digital signatures and certification
----------------------------------------------------------
+=========================================================
 
-OCRmyPDF cannot remove password protection from a PDF. ``qpdf``, one of its dependencies, has this capability. After OCR is applied, password protection is not permitted on PDF/A documents but the file can be converted to regular PDF.
+Password protected PDFs usually have two passwords, and owner and user
+password. When the user password is set to empty, PDF readers will open
+the file automatically and marked it as "(SECURED)". While not as
+reliable as a digital signature, this indicates that whoever set the
+password approved of the file at that time. When the user password is
+set, the document cannot be viewed without the password.
 
-Many programs exist which are capable of inserting an image of someone's signature. On its own, this offers no security guarantees. It is trivial to remove the signature image and apply it to other files. This practice offers no real security.
+Either way, OCRmyPDF does not remove passwords from PDFs and exits with
+an error on encountering them.
 
-Important documents can be digitally signed and certified to attest to their authorship. OCRmyPDF cannot do this. Open source tools such as pdfbox (Java) have this capability as does Adobe Acrobat. 
+``qpdf``, one of OCRmyPDF's dependencies, can remove passwords. If the
+owner and user password are set, a password is required for ``qpdf``. If
+only the owner password is set, then the password can be stripped, even
+if one does not have the owner password.
+
+After OCR is applied, password protection is not permitted on PDF/A
+documents but the file can be converted to regular PDF.
+
+Many programs exist which are capable of inserting an image of someone's
+signature. On its own, this offers no security guarantees. It is trivial
+to remove the signature image and apply it to other files. This practice
+offers no real security.
+
+Important documents can be digitally signed and certified to attest to
+their authorship. OCRmyPDF cannot do this. Open source tools such as
+pdfbox (Java) have this capability as does Adobe Acrobat.

misc/completion/ocrmypdf.bash

@@ -0,0 +1,91 @@
+# ocrmypdf completion                                     -*- shell-script -*-
+
+set -o errexit
+
+_ocrmypdf()
+{
+    local cur prev cword words split
+    _init_completion -s || return
+
+    case $prev in
+        --version|-h|--help)
+            return
+            ;;
+        --user-words|--user-patterns|--tesseract-config)
+            _filedir
+            return
+            ;;
+        --output-type)
+            COMPREPLY=( $( compgen -W 'pdfa pdf pdfa-1 pdfa-2 pdfa-3' -- \
+                "$cur" ) )
+            return
+            ;;
+        --pdf-renderer)
+            COMPREPLY=( $( compgen -W 'auto hocr sandwich' -- "$cur" ) )
+            return
+            ;;
+        --pdfa-image-compression)
+            COMPREPLY=( $( compgen -W 'auto jpeg lossless' -- "$cur" ) )
+            return
+            ;;
+        -O|--optimize|--tesseract-oem)
+            COMPREPLY=( $( compgen -W '{0..3}' -- "$cur" ) )
+            return
+            ;;
+        --jpeg-quality|--png-quality)
+            COMPREPLY=( $( compgen -W '{0..100}' -- "$cur" ) )
+            return
+            ;;
+        -l|--language)
+            COMPREPLY=$( command tesseract --list-langs 2>/dev/null )
+            COMPREPLY=( $( compgen -W '${COMPREPLY[@]##*:}' -- "$cur" ) )
+            return
+            ;;
+        --image-dpi|--oversample|--skip-big|--max-image-mpixels|\
+        --tesseract-timeout|--rotate-pages-threshold)
+            COMPREPLY=( $( compgen -P "$cur" -W '{0..9}' ) )
+            return
+            ;;
+        -j|--jobs)
+            COMPREPLY=( $( compgen -W '{1..'$( _ncpus )'}' -- "$cur" ) )
+            return
+            ;;
+        -v|--verbose)
+            COMPREPLY=( $( compgen -W '{0..2}' -- "$cur" ) ) # max level ?
+            return
+            ;;
+        --tesseract-pagesegmode)
+            COMPREPLY=( $( compgen -W '{1..13}' -- "$cur" ) )
+            return
+            ;;
+        --sidecar|--title|--author|--subject|--keywords|--unpaper-args|--pages)
+            # argument required but no completions available
+            return
+            ;;
+    esac
+
+    $split && return
+
+    if [[ $cur == -* ]]; then
+        COMPREPLY=( $( compgen -W '--language --image-dpi --output-type
+            --sidecar --version --jobs --quiet --verbose --title --author
+            --subject --keywords --rotate-pages --remove-background --deskew
+            --clean --clean-final --unpaper-args --oversample --remove-vectors
+            --threshold --force-ocr --skip-text --redo-ocr
+            --skip-big --jpeg-quality --png-quality --jbig2-lossy
+            --max-image-mpixels --tesseract-config --tesseract-pagesegmode
+            --help --tesseract-oem --pdf-renderer --tesseract-timeout
+            --rotate-pages-threshold --pdfa-image-compression --user-words
+            --user-patterns --keep-temporary-files --output-type' \
+            --  "$cur" ) )
+        return
+    else
+        _filedir
+        return
+    fi
+} &&
+complete -F _ocrmypdf ocrmypdf
+
+set +o errexit
+
+# ex: filetype=sh

misc/completion/ocrmypdf.fish

@@ -0,0 +1,115 @@
+complete -c ocrmypdf -x -n '__fish_is_first_arg' -l version
+complete -c ocrmypdf -x -n '__fish_is_first_arg' -s h -s "?" -l help
+
+complete -c ocrmypdf -r -l sidecar -d "write OCR to text file"
+complete -c ocrmypdf -x -s q -l quiet
+
+complete -c ocrmypdf -s r -l rotate-pages -d "rotate pages to correct orientation"
+complete -c ocrmypdf -s d -l deskew -d "fix small horizontal alignment skew"
+complete -c ocrmypdf -s c -l clean -d "clean document images before OCR"
+complete -c ocrmypdf -s i -l clean-final -d "clean document images and keep result"
+complete -c ocrmypdf -l remove-vectors -d "don't send vector objects to OCR"
+complete -c ocrmypdf -l threshold -d "threshold images before OCR"
+
+complete -c ocrmypdf -s f -l force-ocr -d "OCR documents that already have printable text"
+complete -c ocrmypdf -s s -l skip-ocr -d "skip OCR on pages that text, otherwise try OCR"
+complete -c ocrmypdf -l redo-ocr -d "redo OCR on any pages that seem to have OCR already"
+
+complete -c ocrmypdf -s k -l keep-temporary-files -d "keep temporary files (debug)"
+
+function __fish_ocrmypdf_languages
+    set langs (tesseract --list-langs ^/dev/null)
+    set arr (string split '\n' $langs)
+    for lang in $arr[2..-1]
+        echo $lang
+    end
+end
+complete -c ocrmypdf -x -s l -l language -a '(__fish_ocrmypdf_languages)' -d "language"
+
+complete -c ocrmypdf -x -l image-dpi -d "assume this DPI if input image DPI is unknown"
+
+function __fish_ocrmypdf_output_type
+    echo -e "pdfa\t"(_ "output a PDF/A (default)")
+    echo -e "pdf\t"(_ "output a standard PDF")
+    echo -e "pdfa-1\t"(_ "output a PDF/A-1b")
+    echo -e "pdfa-2\t"(_ "output a PDF/A-2b")
+    echo -e "pdfa-3\t"(_ "output a PDF/A-3b")
+end
+complete -c ocrmypdf -x -l output-type -a '(__fish_ocrmypdf_output_type)' -d "select PDF output options"
+
+function __fish_ocrmypdf_pdf_renderer
+    echo -e "auto\t"(_ "auto select PDF renderer")
+    echo -e "hocr\t"(_ "use hocr renderer")
+    echo -e "sandwich\t"(_ "use sandwich renderer")
+end
+complete -c ocrmypdf -x -l pdf-renderer -a '(__fish_ocrmypdf_pdf_renderer)' -d "select PDF renderer options"
+
+function __fish_ocrmypdf_optimize
+    echo -e "0\t"(_ "do not optimize")
+    echo -e "1\t"(_ "do safe, lossless optimizations (default)")
+    echo -e "2\t"(_ "do some lossy optimizations")
+    echo -e "3\t"(_ "do aggressive lossy optimizations (including lossy JBIG2)")
+end
+complete -c ocrmypdf -x -s O -l optimize -a '(__fish_ocrmypdf_optimize)' -d "select optimization level"
+
+function __fish_ocrmypdf_verbose
+    echo -e "0\t"(_ "standard output messages")
+    echo -e "1\t"(_ "troubleshooting output messages")
+    echo -e "2\t"(_ "debugging output messages")
+end
+complete -c ocrmypdf -x -s v -l verbose -a '(__fish_ocrmypdf_verbose)' -d "set verbosity level"
+
+function __fish_ocrmypdf_pdfa_compression
+    echo -e "auto\t"(_ "let Ghostscript decide how to compress images")
+    echo -e "jpeg\t"(_ "convert color and grayscale images to JPEG")
+    echo -e "lossless\t"(_ "convert color and grayscale images to lossless (PNG)")
+end
+complete -c ocrmypdf -x -l pdfa-image-compression -a '(__fish_ocrmypdf_pdfa_compression)' -d "set PDF/A image compression options"
+
+complete -c ocrmypdf -x -s j -l jobs -d "how many worker processes to use"
+complete -c ocrmypdf -x -l title -d "set metadata"
+complete -c ocrmypdf -x -l author -d "set metadata"
+complete -c ocrmypdf -x -l subject -d "set metadata"
+complete -c ocrmypdf -x -l keywords -d "set metadata"
+complete -c ocrmypdf -x -l oversample -d "oversample images to this DPI"
+complete -c ocrmypdf -x -l skip-big -d "skip OCR on pages larger than this many MPixels"
+
+complete -c ocrmypdf -x -l jpeg-quality -d "JPEG quality [0..100]"
+complete -c ocrmypdf -x -l png-quality -d "PNG quality [0..100]"
+complete -c ocrmypdf -x -l jbig2-lossy -d "enable lossy JBIG2 (see docs)"
+complete -c ocrmypdf -x -l max-image-mpixels -d "image decompression bomb threshold"
+complete -c ocrmypdf -x -l pages -d "apply OCR to only the specified pages"
+complete -c ocrmypdf -x -l tesseract-config -d "set custom tesseract config file"
+
+function __fish_ocrmypdf_tesseract_pagesegmode
+  echo -e "0\t"(_ "orientation and script detection (OSD) only")
+  echo -e "1\t"(_ "automatic page segmentation with OSD")
+  echo -e "2\t"(_ "automatic page segmentation, but no OSD, or OCR")
+  echo -e "3\t"(_ "fully automatic page segmentation, but no OSD (default)")
+  echo -e "4\t"(_ "assume a single column of text of variable sizes")
+  echo -e "5\t"(_ "assume a single uniform block of vertically aligned text")
+  echo -e "6\t"(_ "assume a single uniform block of text")
+  echo -e "7\t"(_ "treat the image as a single text line")
+  echo -e "8\t"(_ "treat the image as a single word")
+  echo -e "9\t"(_ "treat the image as a single word in a circle")
+  echo -e "10\t"(_ "treat the image as a single character")
+  echo -e "11\t"(_ "sparse text - find as much text as possible in no particular order")
+  echo -e "12\t"(_ "sparse text with OSD")
+  echo -e "13\t"(_ "raw line - treat the image as a single text line")
+end
+complete -c ocrmypdf -x -l tesseract-pagesegmode -a '(__fish_ocrmypdf_tesseract_pagesegmode)' -d "set tesseract --psm"
+
+function __fish_ocrmypdf_tesseract_oem
+    echo -e "0\t"(_ "legacy engine only")
+    echo -e "1\t"(_ "neural nets LSTM engine only")
+    echo -e "2\t"(_ "legacy + LSTM engines")
+    echo -e "3\t"(_ "default, based on what is available")
+end
+complete -c ocrmypdf -x -l tesseract-oem -a '(__fish_ocrmypdf_tesseract_oem)' -d "set tesseract --oem"
+complete -c ocrmypdf -x -l tesseract-timeout -d "maximum number of seconds to wait for OCR"
+complete -c ocrmypdf -x -l rotate-pages-threshold -d "page rotation confidence"
+
+complete -c ocrmypdf -r -l user-words -d "specify location of user words file"
+complete -c ocrmypdf -r -l user-patterns -d "specify location of user patterns file"
+
+complete -c ocrmypdf -x -a "(__fish_complete_suffix .pdf)"

misc/webservice.py

@@ -0,0 +1,126 @@
+# webservice.py wrapper for OCRmyPDF
+# Copyright (C) 2019 James R. Barlow: github.com/jbarlow83
+#
+# This program is free software: you can redistribute it and/or modify
+# it under the terms of the GNU Affero General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU Affero General Public License for more details.
+#
+# You should have received a copy of the GNU Affero General Public License
+# along with this program.  If not, see <https://www.gnu.org/licenses/>.
+
+"""This is a simple web service/HTTP wrapper for OCRmyPDF
+
+This may be more convenient than the command line tool for some Docker users.
+Note that OCRmyPDF uses Ghostscript, which is licensed under AGPLv3+. While
+OCRmyPDF is under GPLv3, this file is distributed under the Affero GPLv3+ license,
+to emphasize that SaaS deployments should make sure they comply with
+Ghostscript's license as well as OCRmyPDF's.
+"""
+
+import os
+import shlex
+from subprocess import PIPE, run
+from tempfile import TemporaryDirectory
+
+from flask import (
+    Flask,
+    Response,
+    abort,
+    flash,
+    redirect,
+    request,
+    send_from_directory,
+    url_for,
+)
+from werkzeug.utils import secure_filename
+
+app = Flask(__name__)
+app.secret_key = "secret"
+app.config['MAX_CONTENT_LENGTH'] = 50_000_000
+app.config.from_envvar("OCRMYPDF_WEBSERVICE_SETTINGS", silent=True)
+
+ALLOWED_EXTENSIONS = set(["pdf"])
+
+
+def allowed_file(filename):
+    return "." in filename and filename.rsplit(".", 1)[1].lower() in ALLOWED_EXTENSIONS
+
+
+def do_ocrmypdf(file):
+    uploaddir = TemporaryDirectory(prefix="ocrmypdf-upload")
+    downloaddir = TemporaryDirectory(prefix="ocrmypdf-download")
+
+    filename = secure_filename(file.filename)
+    up_file = os.path.join(uploaddir.name, filename)
+    file.save(up_file)
+
+    down_file = os.path.join(downloaddir.name, filename)
+
+    cmd_args = [arg for arg in shlex.split(request.form["params"])]
+    if "--sidecar" in cmd_args:
+        return Response("--sidecar not supported", 501, mimetype='text/plain')
+
+    ocrmypdf_args = ["ocrmypdf", *cmd_args, up_file, down_file]
+    proc = run(ocrmypdf_args, stdout=PIPE, stderr=PIPE, encoding="utf-8")
+    if proc.returncode != 0:
+        stderr = proc.stderr
+        return Response(stderr, 400, mimetype='text/plain')
+
+    return send_from_directory(downloaddir.name, filename)
+
+
+@app.route("/", methods=["GET", "POST"])
+def upload_file():
+    if request.method == "POST":
+        if "file" not in request.files:
+            return Response("No file in POST", 400, mimetype='text/plain')
+        file = request.files["file"]
+        if file.filename == "":
+            return Response("Empty filename", 400, mimetype='text/plain')
+        if not allowed_file(file.filename):
+            return Response("Invalid filename", 400, mimetype='text/plain')
+        if file and allowed_file(file.filename):
+            return do_ocrmypdf(file)
+        return Response("Some other problem", 400, mimetype='text/plain')
+
+    return """
+    <!doctype html>
+    <title>OCRmyPDF webservice</title>
+    <h1>Upload a PDF (debug UI)</h1>
+    <form method=post enctype=multipart/form-data>
+      <label for="args">Command line parameters</label>
+      <input type=textbox name=params>
+      <label for="file">File to upload</label>
+      <input type=file name=file>
+      <input type=submit value=Upload>
+    </form>
+    <h4>Notice</h2>
+    <div style="font-size: 70%; max-width: 34em;">
+    <p>This is a webservice wrapper for OCRmyPDF.</p>
+    <p>Copyright 2019 James R. Barlow</p>
+    <p>This program is free software: you can redistribute it and/or modify
+    it under the terms of the GNU Affero General Public License as published by
+    the Free Software Foundation, either version 3 of the License, or
+    (at your option) any later version.
+    </p>
+    <p>This program is distributed in the hope that it will be useful,
+    but WITHOUT ANY WARRANTY; without even the implied warranty of
+    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+    GNU General Public License for more details.
+    </p>
+    <p>
+    You should have received a copy of the GNU Affero General Public License
+    along with this program.  If not, see &lt;http://www.gnu.org/licenses/&gt;.
+    </p>
+    </div>
+    """
+
+
+if __name__ == "__main__":
+    app.run(host='0.0.0.0', port=5000)

ocrmypdf/__init__.py

@@ -1,9 +0,0 @@
-# © 2017 James R. Barlow: github.com/jbarlow83
-
-import pkg_resources
-
-PROGRAM_NAME = 'ocrmypdf'
-
-VERSION = pkg_resources.get_distribution('ocrmypdf').version
-
-

ocrmypdf/__main__.py

@@ -1,755 +0,0 @@
-#!/usr/bin/env python3
-# © 2015-17 James R. Barlow: github.com/jbarlow83
-
-from contextlib import suppress
-from tempfile import mkdtemp
-from collections.abc import Sequence
-import sys
-import os
-import re
-import shutil
-import warnings
-import multiprocessing
-import atexit
-import textwrap
-import img2pdf
-import logging
-import argparse
-
-import PyPDF2 as pypdf
-from PIL import Image
-
-import ruffus.ruffus_exceptions as ruffus_exceptions
-import ruffus.cmdline as cmdline
-import ruffus.proxy_logger as proxy_logger
-
-from .pipeline import JobContext, JobContextManager, re_symlink, \
-    cleanup_working_files, build_pipeline
-from .pdfa import file_claims_pdfa
-from .helpers import is_iterable_notstr, re_symlink, is_file_writable
-from .exec import tesseract, qpdf
-from . import PROGRAM_NAME, VERSION
-
-from .exceptions import *
-from . import exceptions as ocrmypdf_exceptions
-
-warnings.simplefilter('ignore', pypdf.utils.PdfReadWarning)
-
-
-# -------------
-# External dependencies
-
-MINIMUM_TESS_VERSION = '3.04'
-
-
-def complain(message):
-    print(*textwrap.wrap(message), file=sys.stderr)
-
-
-# Hack to help debugger context find /usr/local/bin
-if 'IDE_PROJECT_ROOTS' in os.environ:
-    os.environ['PATH'] = '/usr/local/bin:' + os.environ['PATH']
-
-if tesseract.version() < MINIMUM_TESS_VERSION:
-    complain(
-        "Please install tesseract {0} or newer "
-        "(currently installed version is {1})".format(
-            MINIMUM_TESS_VERSION, tesseract.version()))
-    sys.exit(ExitCode.missing_dependency)
-
-# -------------
-# Parser
-
-parser = argparse.ArgumentParser(
-    prog=PROGRAM_NAME,
-    fromfile_prefix_chars='@',
-    formatter_class=argparse.RawDescriptionHelpFormatter,
-    description="""\
-Generates a searchable PDF or PDF/A from a regular PDF.
-
-OCRmyPDF rasterizes each page of the input PDF, optionally corrects page
-rotation and performs image processing, runs the Tesseract OCR engine on the
-image, and then creates a PDF from the OCR information.
-""",
-    epilog="""\
-OCRmyPDF attempts to keep the output file at about the same size.  If a file
-contains losslessly compressed images, and output file will be losslessly
-compressed as well.
-
-PDF is a page description file that attempts to preserve a layout exactly.
-A PDF can contain vector objects (such as text or lines) and raster objects
-(images).  A page might have multiple images.  OCRmyPDF is prepared to deal
-with the wide variety of PDFs that exist in the wild.
-
-When a PDF page contains text, OCRmyPDF assumes that the page has already
-been OCRed or is a "born digital" page that should not be OCRed.  The default
-behavior is to exit in this case without producing a file.  You can use the
-option --skip-text to ignore pages with text, or --force-ocr to rasterize
-all objects on the page and produce an image-only PDF as output.
-
-    ocrmypdf --skip-text file_with_some_text_pages.pdf output.pdf
-
-    ocrmypdf --force-ocr word_document.pdf output.pdf
-
-If you are concerned about long-term archiving of PDFs, use the default option
---output-type pdfa which converts the PDF to a standardized PDF/A-2b.  This
-converts images to sRGB colorspace, removes some features from the PDF such
-as Javascript or forms. If you want to minimize the number of changes made to
-your PDF, use --output-type pdf.
-
-If OCRmyPDF is given an image file as input, it will attempt to convert the
-image to a PDF before processing.  For more control over the conversion of
-images to PDF, use the Python package img2pdf or other image to PDF software.
-
-For example, this command uses img2pdf to convert all .png files beginning
-with the 'page' prefix to a PDF, fitting each image on A4-sized paper, and
-sending the result to OCRmyPDF through a pipe.  img2pdf is a dependency of
-ocrmypdf so it is already installed.
-
-    img2pdf --pagesize A4 page*.png | ocrmypdf - myfile.pdf
-
-Online documentation is located at:
-    https://ocrmypdf.readthedocs.io/en/latest/introduction.html
-
-""")
-
-parser.add_argument(
-    'input_file', metavar="input_pdf_or_image",
-    help="PDF file containing the images to be OCRed (or '-' to read from "
-         "standard input)")
-parser.add_argument(
-    'output_file', metavar="output_pdf",
-    help="Output searchable PDF file (or '-' to write to standard output). "
-         "Existing files will be ovewritten. If same as input file, the "
-         "input file will be updated only if processing is successful.")
-parser.add_argument(
-    '-l', '--language', action='append',
-    help="Language(s) of the file to be OCRed (see tesseract --list-langs for "
-         "all language packs installed in your system). Use -l eng+deu for "
-         "multiple languages.")
-parser.add_argument(
-    '--image-dpi', metavar='DPI', type=int,
-    help="For input image instead of PDF, use this DPI instead of file's.")
-parser.add_argument(
-    '--output-type', choices=['pdfa', 'pdf'], default='pdfa',
-    help="Choose output type. 'pdfa' creates a PDF/A-2b compliant file for "
-         "long term archiving (default, recommended) but may not suitable "
-         "for users who want their file altered as little as possible. 'pdfa' "
-         "also has problems with full Unicode text. 'pdf' attempts to "
-         "preserve file contents as much as possible.")
-
-# Use null string '\0' as sentinel to indicate the user supplied no argument,
-# since that is the only invalid character for filepaths on all platforms
-# bool('\0') is True in Python
-parser.add_argument(
-    '--sidecar', nargs='?', const='\0', default=None, metavar='FILE',
-    help="Generate sidecar text files that contain the same text recognized "
-         "by Tesseract. This may be useful for building a OCR text database. "
-         "If FILE is omitted, the sidecar file be named {output_file}.txt "
-         "If FILE is set to '-', the sidecar is written to stdout (a "
-         "convenient way to preview OCR quality). The output file and sidecar "
-         "may not both use stdout at the same time.")
-
-parser.add_argument(
-    '--version', action='version', version=VERSION,
-    help="Print program version and exit")
-
-jobcontrol = parser.add_argument_group(
-    "Job control options")
-jobcontrol.add_argument(
-    '-j', '--jobs', metavar='N', type=int,
-    help="Use up to N CPU cores simultaneously (default: use all).")
-jobcontrol.add_argument(
-    '-q', '--quiet', action='store_true', help="Suppress INFO messages")
-jobcontrol.add_argument(
-    '-v', '--verbose', const="+", default=[], nargs='?', action="append",
-    help="Print more verbose messages for each additional verbose level")
-
-metadata = parser.add_argument_group(
-    "Metadata options",
-    "Set output PDF/A metadata (default: copy input document's metadata)")
-metadata.add_argument(
-    '--title', type=str,
-    help="Set document title (place multiple words in quotes)")
-metadata.add_argument(
-    '--author', type=str,
-    help="Set document author")
-metadata.add_argument(
-    '--subject', type=str,
-    help="Set document subject description")
-metadata.add_argument(
-    '--keywords', type=str,
-    help="Set document keywords")
-
-preprocessing = parser.add_argument_group(
-    "Image preprocessing options",
-    "Options to improve the quality of the final PDF and OCR")
-preprocessing.add_argument(
-    '-r', '--rotate-pages', action='store_true',
-    help="Automatically rotate pages based on detected text orientation")
-preprocessing.add_argument(
-    '--remove-background', action='store_true',
-    help="Attempt to remove background from gray or color pages, setting it "
-         "to white ")
-preprocessing.add_argument(
-    '-d', '--deskew', action='store_true',
-    help="Deskew each page before performing OCR")
-preprocessing.add_argument(
-    '-c', '--clean', action='store_true',
-    help="Clean pages from scanning artifacts before performing OCR, and send "
-         "the cleaned page to OCR, but do not include the cleaned page in "
-         "the output")
-preprocessing.add_argument(
-    '-i', '--clean-final', action='store_true',
-    help="Clean page as above, and incorporate the cleaned image in the final "
-         "PDF.  Might remove desired content.")
-preprocessing.add_argument(
-    '--oversample', metavar='DPI', type=int, default=0,
-    help="Oversample images to at least the specified DPI, to improve OCR "
-         "results slightly")
-
-ocrsettings = parser.add_argument_group(
-    "OCR options",
-    "Control how OCR is applied")
-ocrsettings.add_argument(
-    '-f', '--force-ocr', action='store_true',
-    help="Rasterize any fonts or vector objects on each page, apply OCR, and "
-         "save the rastered output (this rewrites the PDF)")
-ocrsettings.add_argument(
-    '-s', '--skip-text', action='store_true',
-    help="Skip OCR on any pages that already contain text, but include the "
-         "page in final output; useful for PDFs that contain a mix of "
-         "images, text pages, and/or previously OCRed pages")
-# ocrsettings.add_argument(
-#     '--redo-ocr', action='store_true',
-#     help="removing any existing OCR text, but otherwise preserve mixed PDF "
-#          "pages")
-
-ocrsettings.add_argument(
-    '--skip-big', type=float, metavar='MPixels',
-    help="Skip OCR on pages larger than the specified amount of megapixels, "
-         "but include skipped pages in final output")
-
-advanced = parser.add_argument_group(
-    "Advanced",
-    "Advanced options to control Tesseract's OCR behavior")
-advanced.add_argument(
-    '--tesseract-config', action='append', metavar='CFG', default=[],
-    help="Additional Tesseract configuration files -- see documentation")
-advanced.add_argument(
-    '--tesseract-pagesegmode', action='store', type=int, metavar='PSM',
-    choices=range(0, 14),
-    help="Set Tesseract page segmentation mode (see tesseract --help)")
-advanced.add_argument(
-    '--tesseract-oem', action='store', type=int, metavar='MODE',
-    choices=range(0, 4),
-    help=("Set Tesseract 4.0 OCR engine mode: "
-         "0 - original Tesseract only; "
-         "1 - neural nets LSTM only; "
-         "2 - Tesseract + LSTM; "
-         "3 - default.")
-    )
-advanced.add_argument(
-    '--pdf-renderer',
-    choices=['auto', 'tesseract', 'hocr', 'tess4', 'sandwich'], default='auto',
-    help="Choose OCR PDF renderer - the default option is to let OCRmyPDF "
-         "choose."
-         "auto - let OCRmyPDF choose; "
-         "sandwich - default renderer for Tesseract 3.05.01 and newer; "
-         "hocr - default renderer for older versions of Tesseract; "
-         "tesseract - gives better results for non-Latin languages and "
-         "Tesseract older than 3.05.01 but has problems with some versions "
-         " of Ghostscript; deprecated"
-         "tess4 - deprecated alias for 'sandwich'"
-    )
-advanced.add_argument(
-    '--tesseract-timeout', default=180.0, type=float, metavar='SECONDS',
-    help='Give up on OCR after the timeout, but copy the preprocessed page '
-         'into the final output')
-advanced.add_argument(
-    '--rotate-pages-threshold', default=14.0, type=float, metavar='CONFIDENCE',
-    help="Only rotate pages when confidence is above this value (arbitrary "
-         "units reported by tesseract)")
-advanced.add_argument(
-    '--pdfa-image-compression', choices=['auto', 'jpeg', 'lossless'],
-    default='auto',
-    help="Specify how to compress images in the output PDF/A. 'auto' lets "
-         "OCRmyPDF decide.  'jpeg' changes all grayscale and color images to "
-         "JPEG compression.  'lossless' uses PNG-style lossless compression "
-         "for all images.  Monochrome images are always compressed using a "
-         "lossless codec.  Compression settings "
-         "are applied to all pages, including those for which OCR was "
-         "skipped.  Not supported for --output-type=pdf ; that setting "
-         "preserves the original compression of all images.")
-
-debugging = parser.add_argument_group(
-    "Debugging",
-    "Arguments to help with troubleshooting and debugging")
-debugging.add_argument(
-    '-k', '--keep-temporary-files', action='store_true',
-    help="Keep temporary files (helpful for debugging)")
-debugging.add_argument(
-    '-g', '--debug-rendering', action='store_true',
-    help="Render each page twice with debug information on second page")
-debugging.add_argument(
-    '--flowchart', type=str,
-    help="Generate the pipeline execution flowchart")
-
-
-def check_options_languages(options, _log):
-    if not options.language:
-        options.language = ['eng']  # Enforce English hegemony
-
-    # Support v2.x "eng+deu" language syntax
-    if '+' in options.language[0]:
-        options.language = options.language[0].split('+')
-
-    if not set(options.language).issubset(tesseract.languages()):
-        msg = (
-            "The installed version of tesseract does not have language "
-            "data for the following requested languages: \n")
-        for lang in (set(options.language) - tesseract.languages()):
-            msg += lang + '\n'
-        raise argparse.ArgumentError(None, msg)
-
-
-def check_options_output(options, log):
-    if options.pdf_renderer == 'auto':
-        if tesseract.has_textonly_pdf():
-            options.pdf_renderer = 'sandwich'
-        else:
-            options.pdf_renderer = 'hocr'
-
-    if options.pdf_renderer == 'tess4':
-        log.warning("The 'tess4' PDF renderer has been renamed to 'sandwich'. "
-                    "Please use --pdf-renderer=sandwich.")
-        options.pdf_renderer = 'sandwich'
-
-    if options.pdf_renderer == 'tesseract':
-        log.warning("The 'tesseract' PDF renderer is deprecated.")
-        if tesseract.version() < '3.05' and options.output_type == 'pdfa':
-            log.warning(
-                "For best results use --pdf-renderer=tesseract "
-                "--output-type=pdf to disable PDF/A generation via "
-                "Ghostscript, which is known to corrupt the OCR text of "
-                "some PDFs produced your version of Tesseract.")
-
-    if options.debug_rendering and options.pdf_renderer != 'hocr':
-        log.info(
-            "Ignoring --debug-rendering because it requires --pdf-renderer=hocr")
-
-    lossless_reconstruction = False
-    if options.pdf_renderer in ('hocr', 'sandwich'):
-        if not any((options.deskew, options.clean_final, options.force_ocr,
-                   options.remove_background)):
-            lossless_reconstruction = True
-    options.lossless_reconstruction = lossless_reconstruction
-
-
-def check_options_sidecar(options, log):
-    if options.sidecar == '\0':
-        if options.output_file == '-':
-            raise argparse.ArgumentError(
-                None,
-                "--sidecar filename must be specified when output file is "
-                "stdout.")
-        options.sidecar = options.output_file + '.txt'
-
-
-def check_options_preprocessing(options, log):
-    if any((options.clean, options.clean_final)):
-        from .exec import unpaper
-        try:
-            if unpaper.version() < '6.1':
-                raise MissingDependencyError(
-                    "The installed 'unpaper' is not supported. "
-                    "Install version 6.1 or newer.")
-        except FileNotFoundError:
-            raise MissingDependencyError(
-                "Install the 'unpaper' program to use --clean, --clean-final.")
-
-    if options.clean and \
-            not options.clean_final and \
-            options.pdf_renderer == 'tesseract':
-        log.info(
-            "Tesseract PDF renderer cannot render --clean pages without "
-            "also performing --clean-final, so --clean-final is assumed.")
-
-
-def check_options_ocr_behavior(options, log):
-    if options.force_ocr and options.skip_text:
-        raise argparse.ArgumentError(
-            None,
-            "Error: --force-ocr and --skip-text are mutually incompatible.")
-
-    # if options.redo_ocr and (options.skip_text or options.force_ocr):
-    #     raise argparse.ArgumentError(
-    #         "Error: --redo-ocr and other OCR options are incompatible.")
-
-    if set(options.language) & {'chi_sim', 'chi_tra'} and \
-            (options.pdf_renderer == 'hocr' or options.output_type == 'pdfa'):
-        log.warning(
-            "Your settings are known to cause problems with OCR of Chinese text. "
-            "Try adding these arguments: "
-            "    ocrmypdf --pdf-renderer tesseract --output-type pdf")
-
-
-def check_options_advanced(options, log):
-    if tesseract.v4():
-        log.info(
-            "Tesseract v4.x.alpha found. OCRmyPDF support is experimental.")
-    if options.tesseract_oem and not tesseract.v4():
-        log.warning(
-            "--tesseract-oem requires Tesseract 4.x -- argument ignored")
-    if options.pdf_renderer == 'tess4' and not tesseract.has_textonly_pdf():
-        raise MissingDependencyError(
-            "--pdf-renderer tess4 requires Tesseract 4.x "
-            "commit 3d9fb3b or later")
-    if options.pdfa_image_compression != 'auto' and \
-            options.output_type != 'pdfa':
-        log.warning(
-            "--pdfa-image-compression argument has no effect when "
-            "--output-type is not 'pdfa'"
-        )
-
-
-def check_options_metadata(options, log):
-    import unicodedata
-    metadata = [options.title, options.author, options.keywords,
-                options.subject]
-    for s in (m for m in metadata if m):
-        for c in s:
-            if unicodedata.category(c) == 'Co' or ord(c) >= 0x10000:
-                raise ValueError(
-                    "One of the metadata strings contains "
-                    "an unsupported Unicode character: '{}' (U+{})".format(
-                        c, hex(ord(c))[2:].upper()
-                ))
-
-
-def check_options(options, log):
-    try:
-        check_options_languages(options, log)
-        check_options_metadata(options, log)
-        check_options_output(options, log)
-        check_options_sidecar(options, log)
-        check_options_preprocessing(options, log)
-        check_options_ocr_behavior(options, log)
-        check_options_advanced(options, log)
-    except ValueError as e:
-        log.error(e)
-        sys.exit(ExitCode.bad_args)
-    except argparse.ArgumentError as e:
-        log.error(e)
-        sys.exit(ExitCode.bad_args)
-    except MissingDependencyError as e:
-        log.error(e)
-        sys.exit(ExitCode.missing_dependency)
-
-
-# ----------
-# Logging
-
-
-def logging_factory(logger_name, logger_args):
-    verbose = logger_args['verbose']
-    quiet = logger_args['quiet']
-
-    root_logger = logging.getLogger(logger_name)
-    root_logger.setLevel(logging.DEBUG)
-
-    handler = logging.StreamHandler(sys.stderr)
-    formatter_ = logging.Formatter("%(levelname)7s - %(message)s")
-    handler.setFormatter(formatter_)
-    if verbose:
-        handler.setLevel(logging.DEBUG)
-    elif quiet:
-        handler.setLevel(logging.WARNING)
-    else:
-        handler.setLevel(logging.INFO)
-    root_logger.addHandler(handler)
-    return root_logger
-
-
-def available_cpu_count():
-    try:
-        return multiprocessing.cpu_count()
-    except NotImplementedError:
-        pass
-
-    try:
-        import psutil
-        return psutil.cpu_count()
-    except (ImportError, AttributeError):
-        pass
-
-    complain(
-        "Could not get CPU count.  Assuming one (1) CPU."
-        "Use -j N to set manually.")
-    return 1
-
-
-def cleanup_ruffus_error_message(msg):
-    msg = re.sub(r'\s+', r' ', msg)
-    msg = re.sub(r"\((.+?)\)", r'\1', msg)
-    msg = msg.strip()
-    return msg
-
-
-def do_ruffus_exception(ruffus_five_tuple, options, log):
-    """Replace the elaborate ruffus stack trace with a user friendly
-    description of the error message that occurred."""
-
-    task_name, job_name, exc_name, exc_value, exc_stack = ruffus_five_tuple
-    if exc_name == 'builtins.SystemExit':
-        match = re.search(r"\.(.+?)\)", exc_value)
-        exit_code_name = match.groups()[0]
-        exit_code = getattr(ExitCode, exit_code_name, 'other_error')
-        return exit_code
-    elif exc_name == 'ruffus.ruffus_exceptions.MissingInputFileError':
-        log.error(cleanup_ruffus_error_message(exc_value))
-        return ExitCode.input_file
-    elif exc_name == 'builtins.TypeError':
-        # Even though repair_pdf will fail, ruffus will still try
-        # to call split_pages with no input files, likely due to a bug
-        if task_name == 'split_pages':
-            log.error("Input file '{0}' is not a valid PDF".format(
-                options.input_file))
-            return ExitCode.input_file
-    elif exc_name == 'builtins.KeyboardInterrupt':
-        log.error("Interrupted by user")
-        return ExitCode.ctrl_c
-    elif exc_name == 'subprocess.CalledProcessError':
-        # It's up to the subprocess handler to report something useful
-        msg = "Error occurred while running this command:"
-        log.error(msg + '\n' + exc_value)
-        return ExitCode.child_process_error
-    elif exc_name == 'ocrmypdf.exceptions.PdfMergeFailedError':
-        log.error(textwrap.dedent("""\
-            Failed to merge PDF image layer with OCR layer
-
-            Usually this happens because the input PDF file is mal-formed and
-            ocrmypdf cannot automatically correct the problem on its own.
-
-            Try using
-                ocrmypdf --pdf-renderer tesseract  [..other args..]
-            """))
-        return ExitCode.input_file
-    elif exc_name.startswith('ocrmypdf.exceptions.'):
-        base_exc_name = exc_name.replace('ocrmypdf.exceptions.', '')
-        exc_class = getattr(ocrmypdf_exceptions, base_exc_name)
-        return exc_class.exit_code
-    elif exc_name == 'PyPDF2.utils.PdfReadError' and \
-            'not been decrypted' in exc_value:
-        log.error(textwrap.dedent("""\
-            Input PDF uses either an encryption algorithm or a PDF security
-            handler that is not supported by ocrmypdf.
-
-            For information about this PDF's security use
-                qpdf --show-encryption [...input PDF...]
-
-            (Only algorithms "R = 1" and "R = 2" are supported.)
-
-            """))
-        return ExitCode.encrypted_pdf
-
-    if not options.verbose:
-        log.error(exc_stack)
-    return ExitCode.other_error
-
-
-def traverse_ruffus_exception(e_args, options, log):
-    """Walk through a RethrownJobError and find the first exception.
-
-    The exit code will be based on this, even if multiple exceptions occurred
-    at the same time."""
-
-    if isinstance(e_args, Sequence) and isinstance(e_args[0], str) and \
-            len(e_args) == 5:
-        return do_ruffus_exception(e_args, options, log)
-    elif is_iterable_notstr(e_args):
-        for exc in e_args:
-            return traverse_ruffus_exception(exc, options, log)
-
-
-def check_closed_streams(options):
-    """Work around Python issue with multiprocessing forking on closed streams
-
-    https://bugs.python.org/issue28326
-
-    Attempting to a fork/exec a new Python process when any of std{in,out,err}
-    are closed or not flushable for some reason may raise an exception.
-    Fix this by opening devnull if the handle seems to be closed.  Do this
-    globally to avoid tracking places all places that fork.
-
-    Seems to be specific to multiprocessing.Process not all Python process
-    forkers.
-
-    The error actually occurs when the stream object is not flushable,
-    but replacing an open stream object that is not flushable with
-    /dev/null is a bad idea since it will create a silent failure.  Replacing
-    a closed handle with /dev/null seems safe.
-
-    """
-
-    if sys.stderr is None:
-        sys.stderr = open(os.devnull, 'w')
-
-    if sys.stdin is None:
-        if options.input_file == '-':
-            print("Trying to read from stdin but stdin seems closed",
-                  file=sys.stderr)
-            return False
-        sys.stdin = open(os.devnull, 'r')
-
-    if sys.stdout is None:
-        if options.output_file == '-':
-            # Can't replace stdout if the user is piping
-            # If this case can even happen, it must be some kind of weird
-            # stream.
-            print(textwrap.dedent("""\
-                Output was set to stdout '-' but the stream attached to
-                stdout does not support the flush() system call.  This
-                will fail."""), file=sys.stderr)
-            return False
-        sys.stdout = open(os.devnull, 'w')
-
-    return True
-
-
-def run_pipeline():
-    options = parser.parse_args()
-    options.verbose_abbreviated_path = 1
-
-    if not check_closed_streams(options):
-        return ExitCode.bad_args
-
-    logger_args = {'verbose': options.verbose, 'quiet': options.quiet}
-
-    _log, _log_mutex = proxy_logger.make_shared_logger_and_proxy(
-        logging_factory, __name__, logger_args)
-    _log.debug('ocrmypdf ' + VERSION)
-    _log.debug('tesseract ' + tesseract.version())
-
-    check_options(options, _log)
-
-    # Any changes to options will not take effect for options that are already
-    # bound to function parameters in the pipeline. (For example
-    # options.input_file, options.pdf_renderer are already bound.)
-    if not options.jobs:
-        options.jobs = available_cpu_count()
-    try:
-        work_folder = mkdtemp(prefix="com.github.ocrmypdf.")
-        options.history_file = os.path.join(
-            work_folder, 'ruffus_history.sqlite')
-        start_input_file = os.path.join(
-            work_folder, 'origin')
-
-        if options.input_file == '-':
-            # stdin
-            _log.info('reading file from standard input')
-            with open(start_input_file, 'wb') as stream_buffer:
-                from shutil import copyfileobj
-                copyfileobj(sys.stdin.buffer, stream_buffer)
-        else:
-            try:
-                re_symlink(options.input_file, start_input_file, _log)
-            except FileNotFoundError:
-                _log.error("File not found - " + options.input_file)
-                return ExitCode.input_file
-
-        if options.output_file == '-':
-            if sys.stdout.isatty():
-                _log.error(textwrap.dedent("""\
-                    Output was set to stdout '-' but it looks like stdout
-                    is connected to a terminal.  Please redirect stdout to a
-                    file."""))
-                return ExitCode.bad_args
-        elif not is_file_writable(options.output_file):
-            _log.error(textwrap.dedent("""\
-                Output file location is not writable."""))
-            return ExitCode.file_access_error
-
-        manager = JobContextManager()
-        manager.register('JobContext', JobContext)
-        manager.start()
-
-        context = manager.JobContext()
-        context.set_options(options)
-        context.set_work_folder(work_folder)
-
-        build_pipeline(options, work_folder, _log, context)
-        atexit.register(cleanup_working_files, work_folder, options)
-        cmdline.run(options)
-    except ruffus_exceptions.RethrownJobError as e:
-        if options.verbose:
-            _log.debug(str(e))  # stringify exception so logger doesn't have to
-
-        # Ruffus flattens exception to 5 element tuples. Because of a bug
-        # in <= 2.6.3 it may present either the single:
-        #   (task, job, exc, value, stack)
-        # or something like:
-        #   [[(task, job, exc, value, stack)]]
-        #
-        # Generally cross-process exception marshalling doesn't work well
-        # and ruffus doesn't support because BaseException has its own
-        # implementation of __reduce__ that attempts to reconstruct the
-        # exception based on e.__init__(e.args).
-        #
-        # Attempting to log the exception directly marshalls it to the logger
-        # which is probably in another process, so it's better to log only
-        # data from the exception at this point.
-
-        exitcode = traverse_ruffus_exception(e.args, options, _log)
-        if exitcode is None:
-            _log.error("Unexpected ruffus exception: " + str(e))
-            _log.error(repr(e))
-            return ExitCode.other_error
-        else:
-            return exitcode
-    except ExitCodeException as e:
-        return e.exit_code
-    except Exception as e:
-        _log.error(e)
-        return ExitCode.other_error
-
-    if options.flowchart:
-        _log.info("Flowchart saved to {}".format(options.flowchart))
-    elif options.output_file != '-':
-        if options.output_type == 'pdfa':
-            pdfa_info = file_claims_pdfa(options.output_file)
-            if pdfa_info['pass']:
-                msg = 'Output file is a {} (as expected)'
-                _log.info(msg.format(pdfa_info['conformance']))
-            else:
-                msg = 'Output file is okay but is not PDF/A (seems to be {})'
-                _log.warning(msg.format(pdfa_info['conformance']))
-
-                return ExitCode.invalid_output_pdf
-        if not qpdf.check(options.output_file, _log):
-            _log.warning('Output file: The generated PDF is INVALID')
-            return ExitCode.invalid_output_pdf
-    else:
-        _log.info("Output sent to stdout")
-
-    pdfinfo = context.get_pdfinfo()
-    if options.verbose:
-        from pprint import pformat
-        _log.debug(pformat(pdfinfo))
-    direction = {0: 'n', 90: 'e',
-                 180: 's', 270: 'w'}
-    orientations = []
-    for n, page in enumerate(pdfinfo):
-        angle = pdfinfo[n].rotation or 0
-        if angle != 0:
-            orientations.append('{0}{1}'.format(
-                n + 1,
-                direction.get(angle, '')))
-    if orientations:
-        _log.info('Page orientations detected: ' + ' '.join(orientations))
-
-    return ExitCode.ok
-
-
-if __name__ == '__main__':
-    sys.exit(run_pipeline())

ocrmypdf/exceptions.py

@@ -1,59 +0,0 @@
-#!/usr/bin/env python3
-# © 2016 James R. Barlow: github.com/jbarlow83
-
-
-from enum import IntEnum
-
-class ExitCode(IntEnum):
-    ok = 0
-    bad_args = 1
-    input_file = 2
-    missing_dependency = 3
-    invalid_output_pdf = 4
-    file_access_error = 5
-    already_done_ocr = 6
-    child_process_error = 7
-    encrypted_pdf = 8
-    invalid_config = 9
-    other_error = 15
-    ctrl_c = 130
-
-
-class ExitCodeException(Exception):
-    pass
-
-
-class PdfMergeFailedError(ExitCodeException):
-    exit_code = ExitCode.input_file
-
-
-class MissingDependencyError(ExitCodeException):
-    exit_code = ExitCode.missing_dependency
-
-
-class UnsupportedImageFormatError(ExitCodeException):
-    exit_code = ExitCode.input_file
-
-
-class DpiError(ExitCodeException):
-    exit_code = ExitCode.input_file
-
-
-class PriorOcrFoundError(ExitCodeException):
-    exit_code = ExitCode.already_done_ocr
-
-
-class InputFileError(ExitCodeException):
-    exit_code = ExitCode.input_file
-
-
-class SubprocessOutputError(ExitCodeException):
-    exit_code = ExitCode.child_process_error
-
-
-class EncryptedPdfError(ExitCodeException):
-    exit_code = ExitCode.encrypted_pdf
-
-
-class TesseractConfigError(ExitCodeException):
-    exit_code = ExitCode.invalid_config

ocrmypdf/exec/__init__.py

@@ -1,11 +0,0 @@
-#!/usr/bin/env python3
-# © 2016 James R. Barlow: github.com/jbarlow83
-
-"""Wrappers to manage subprocess calls"""
-
-import os
-
-
-def get_program(name):
-    envvar = 'OCRMYPDF_' + name.upper()
-    return os.environ.get(envvar, name)

ocrmypdf/exec/ghostscript.py

@@ -1,167 +0,0 @@
-#!/usr/bin/env python3
-# © 2015 James R. Barlow: github.com/jbarlow83
-
-from tempfile import NamedTemporaryFile
-from subprocess import run, PIPE, STDOUT, CalledProcessError
-from shutil import copy
-from functools import lru_cache
-import re
-import sys
-from . import get_program
-from ..exceptions import SubprocessOutputError
-from PIL import Image
-
-
-@lru_cache(maxsize=1)
-def version():
-    args_gs = [
-        get_program('gs'),
-        '--version'
-    ]
-    try:
-        version = check_output(
-                args_gs, close_fds=True, universal_newlines=True,
-                stderr=STDOUT)
-    except CalledProcessError as e:
-        print("Could not find Ghostscript executable on system PATH.",
-              file=sys.stderr)
-        raise MissingDependencyError from e
-
-    return version.strip()
-
-
-def _gs_error_reported(stream):
-    return re.search(r'error', stream, flags=re.IGNORECASE)
-
-
-def rasterize_pdf(input_file, output_file, xres, yres, raster_device, log,
-                  pageno=1, page_dpi=None):
-    """
-    Rasterize one page of a PDF at resolution (xres, yres) in canvas units.
-    
-    The image is sized to match the integer pixels dimensions implied by 
-    (xres, yres) even if those numbers are noninteger. The image's DPI will
-     be overridden with the values in page_dpi.
-    
-    :param input_file: 
-    :param output_file: 
-    :param xres: resolution at which to rasterize page
-    :param yres: 
-    :param raster_device: 
-    :param log: 
-    :param pageno: page number to rasterize
-    :param page_dpi: resolution tuple (x, y) overriding output image DPI 
-    :return: 
-    """
-    res = xres, yres
-    int_res = round(xres), round(yres)
-    if not page_dpi:
-        page_dpi = res
-    with NamedTemporaryFile(delete=True) as tmp:
-        args_gs = [
-            get_program('gs'),
-            '-dQUIET',
-            '-dSAFER',
-            '-dBATCH',
-            '-dNOPAUSE',
-            '-sDEVICE=%s' % raster_device,
-            '-dFirstPage=%i' % pageno,
-            '-dLastPage=%i' % pageno,
-            '-o', tmp.name,
-            '-r{0}x{1}'.format(str(int_res[0]), str(int_res[1])),
-            input_file
-        ]
-
-        p = run(args_gs, stdout=PIPE, stderr=STDOUT,
-                universal_newlines=True)
-        if _gs_error_reported(p.stdout):
-            log.error(p.stdout)
-        else:
-            log.debug(p.stdout)
-
-        if p.returncode != 0:
-            log.error('Ghostscript rasterizing failed')
-            raise SubprocessOutputError()
-
-        # Ghostscript only accepts integers for output resolution
-        # if the resolution happens to be fractional, then the discrepancy
-        # would change the size of the output page, especially if the DPI
-        # is quite low. Resize the image to the expected size
-        tmp.seek(0)
-        with Image.open(tmp) as im:
-            expected_size = round(im.size[0] / int_res[0] * res[0]), \
-                            round(im.size[1] / int_res[1] * res[1])
-            if expected_size != im.size or page_dpi != (xres, yres):
-                log.debug(
-                    "Ghostscript: resize output image {} -> {}".format(
-                        im.size, expected_size))
-                im.resize(expected_size).save(output_file, dpi=page_dpi)
-            else:
-                copy(tmp.name, output_file)
-
-
-def generate_pdfa(pdf_pages, output_file, compression, log,
-                  threads=1, pdf_version='1.5'):
-    compression_args = []
-    if compression == 'jpeg':
-        compression_args = [
-            "-dAutoFilterColorImages=false",
-            "-dColorImageFilter=/DCTEncode",
-            "-dAutoFilterGrayImages=false",
-            "-dGrayImageFilter=/DCTEncode",
-        ]
-    elif compression == 'lossless':
-        compression_args = [
-            "-dAutoFilterColorImages=false",
-            "-dColorImageFilter=/FlateEncode",
-            "-dAutoFilterGrayImages=false",
-            "-dGrayImageFilter=/FlateEncode",
-        ]
-    else:
-        compression_args = [
-            "-dAutoFilterColorImages=true",
-            "-dAutoFilterGrayImages=true",
-        ]
-
-    with NamedTemporaryFile(delete=True) as gs_pdf:
-        args_gs = [
-            get_program("gs"),
-            "-dQUIET",
-            "-dBATCH",
-            "-dNOPAUSE",
-            "-dCompatibilityLevel=" + str(pdf_version),
-            "-dNumRenderingThreads=" + str(threads),
-            "-sDEVICE=pdfwrite",
-            "-dAutoRotatePages=/None",
-            "-sColorConversionStrategy=/RGB",
-            "-sProcessColorModel=DeviceRGB"
-        ] + compression_args + [
-            "-dJPEGQ=95",
-            "-dPDFA=2",
-            "-dPDFACompatibilityPolicy=1",
-            "-sOutputFile=" + gs_pdf.name,
-        ]
-        args_gs.extend(pdf_pages)
-        p = run(args_gs, stdout=PIPE, stderr=STDOUT,
-                universal_newlines=True)
-
-        if _gs_error_reported(p.stdout):
-            log.error(p.stdout)
-        elif 'overprint mode not set' in p.stdout:
-            # Unless someone is going to print PDF/A documents on a
-            # magical sRGB printer I can't see the removal of overprinting
-            # being a problem....
-            log.debug(
-                "Ghostscript had to remove PDF 'overprinting' from the "
-                "input file to complete PDF/A conversion. "
-                )
-        else:
-            log.debug(p.stdout)
-
-        if p.returncode == 0:
-            # Ghostscript does not change return code when it fails to create
-            # PDF/A - check PDF/A status elsewhere
-            copy(gs_pdf.name, output_file)
-        else:
-            log.error('Ghostscript PDF/A rendering failed')
-            raise SubprocessOutputError()

ocrmypdf/exec/qpdf.py

@@ -1,137 +0,0 @@
-#!/usr/bin/env python3
-# © 2015 James R. Barlow: github.com/jbarlow83
-
-from subprocess import CalledProcessError, STDOUT, PIPE, run, check_output
-from functools import lru_cache
-import sys
-import os
-import re
-
-from ..exceptions import InputFileError, SubprocessOutputError, \
-    MissingDependencyError, EncryptedPdfError
-from . import get_program
-
-
-@lru_cache(maxsize=1)
-def version():
-    args_qpdf = [
-        get_program('qpdf'),
-        '--version'
-    ]
-    try:
-        p = run(args_qpdf, universal_newlines=True, stderr=STDOUT,
-                stdout=PIPE)
-    except CalledProcessError as e:
-        print("Could not find qpdf executable on system PATH.",
-              file=sys.stderr)
-        raise MissingDependencyError() from e
-
-    qpdf_version = re.match(r'qpdf version (.+)', p.stdout).group(1)
-    return qpdf_version
-
-
-def check(input_file, log=None):
-    args_qpdf = [
-        get_program('qpdf'),
-        '--check',
-        input_file
-    ]
-
-    if log is None:
-        import logging as log
-
-    try:
-        check_output(args_qpdf, stderr=STDOUT, universal_newlines=True)
-    except CalledProcessError as e:
-        if e.returncode == 2:
-            log.error("{0}: not a valid PDF, and could not repair it.".format(
-                input_file))
-            log.error("Details:")
-            log.error(e.output)
-        elif e.returncode == 3:
-            log.info("qpdf --check returned warnings:")
-            log.info(e.output)
-        else:
-            log.warning(e.output)
-        return False
-    return True
-
-
-def _probably_encrypted(e):
-    """qpdf can report a false positive "file is encrypted" message for damaged
-    files - suppress this"""
-    return e.returncode == 2 and \
-        'invalid password' in e.output and \
-        'file is damaged' not in e.output
-
-
-def repair(input_file, output_file, log):
-    args_qpdf = [
-        get_program('qpdf'), input_file, output_file
-    ]
-    try:
-        check_output(args_qpdf, stderr=STDOUT, universal_newlines=True)
-    except CalledProcessError as e:
-        if e.returncode == 3 and e.output.find("operation succeeded"):
-            log.debug('qpdf found and fixed errors: ' + e.output)
-            log.debug(e.output)
-            return
-
-        if _probably_encrypted(e):
-            log.error("{0}: this PDF is password-protected - password must "
-                      "be removed for OCR".format(input_file))
-            raise EncryptedPdfError() from e
-        elif e.returncode == 2:
-            log.error("{0}: not a valid PDF, and could not repair it.".format(
-                      input_file))
-            log.error("Details: " + e.output)
-            raise InputFileError() from e
-        else:
-            log.error("{0}: unknown error".format(
-                      input_file))
-            log.error(e.output)
-            raise SubprocessOutputError() from e
-
-
-def get_npages(input_file, log):
-    try:
-        pages = check_output(
-            [get_program('qpdf'), '--show-npages', input_file],
-             universal_newlines=True, close_fds=True)
-    except CalledProcessError as e:
-        if e.returncode == 2 and e.output.find('No such file'):
-            log.error(e.output)
-            raise InputFileError() from e
-    return int(pages)
-
-
-def split_pages(input_file, work_folder, npages):
-    """Split multipage PDF into individual pages.
-
-    Incredibly enough, this multiple process approach is about 70 times
-    faster than using Ghostscript.
-    """
-    for n in range(int(npages)):
-        args_qpdf = [
-            get_program('qpdf'), input_file,
-            '--pages', input_file, '{0}'.format(n + 1), '--',
-            os.path.join(work_folder, '{0:06d}.page.pdf'.format(n + 1))
-        ]
-        run(args_qpdf, check=True)
-
-
-def merge(input_files, output_file, min_version=None):
-    """Merge the list of input files (all filenames) into the output file.
-
-    The input files may contain one or more pages.
-    """
-    version_arg = ['--min-version={}'.format(min_version)] \
-                  if min_version else []
-
-    args_qpdf = [
-        get_program('qpdf')
-    ] + version_arg + [
-        input_files[0], '--pages'
-    ] + input_files + ['--', output_file]
-    run(args_qpdf, check=True)
-

ocrmypdf/exec/tesseract.py

@@ -1,342 +0,0 @@
-#!/usr/bin/env python3
-# © 2015 James R. Barlow: github.com/jbarlow83
-
-import sys
-import os
-import re
-import shutil
-from functools import lru_cache
-from ..exceptions import MissingDependencyError, TesseractConfigError
-from ..helpers import page_number
-from . import get_program
-from collections import namedtuple
-from textwrap import dedent
-import PyPDF2 as pypdf
-
-from subprocess import Popen, PIPE, CalledProcessError, \
-    TimeoutExpired, check_output, STDOUT, DEVNULL
-
-
-OrientationConfidence = namedtuple(
-    'OrientationConfidence',
-    ('angle', 'confidence'))
-
-HOCR_TEMPLATE = """<?xml version="1.0" encoding="UTF-8"?>
-<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN"
-    "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
-<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
- <head>
-  <title></title>
-<meta http-equiv="Content-Type" content="text/html;charset=utf-8" />
-  <meta name='ocr-system' content='tesseract 3.05.00' />
-  <meta name='ocr-capabilities' content='ocr_page ocr_carea ocr_par ocr_line ocrx_word'/>
-</head>
-<body>
-  <div class='ocr_page' id='page_1' title='image "_blank.png"; bbox 0 0 {0} {1}; ppageno 0'>
-  </div>
- </body>
-</html>
-"""
-
-
-@lru_cache(maxsize=1)
-def version():
-    args_tess = [
-        get_program('tesseract'),
-        '--version'
-    ]
-    try:
-        versions = check_output(
-                args_tess, close_fds=True, universal_newlines=True,
-                stderr=STDOUT)
-    except CalledProcessError as e:
-        print("Could not find Tesseract executable on system PATH.",
-              file=sys.stderr)
-        raise MissingDependencyError from e
-
-    tesseract_version = re.match(r'tesseract\s(.+)', versions).group(1)
-    return tesseract_version
-
-
-def v4():
-    "Is this Tesseract v4.0?"
-    return (version() >= '4')
-
-
-@lru_cache(maxsize=1)
-def has_textonly_pdf():
-    """Does Tesseract have textonly_pdf capability?
-    
-    Available in 3.05.01, and v4.00.00alpha since January 2017. Best to 
-    parse the parameter list
-    """
-    args_tess = [
-        get_program('tesseract'),
-        '--print-parameters'
-    ]
-    try:
-        params = check_output(
-                args_tess, close_fds=True, universal_newlines=True,
-                stderr=STDOUT)
-    except CalledProcessError as e:
-        print("Could not --print-parameters from tesseract",
-              file=sys.stderr)
-        raise MissingDependencyError from e
-    if 'textonly_pdf' in params:
-        return True
-    return False
-
-
-def psm():
-    "If Tesseract 4.0, use argument --psm instead of -psm"
-    return '--psm' if v4() else '-psm'
-
-
-@lru_cache(maxsize=1)
-def languages():
-    args_tess = [
-        get_program('tesseract'),
-        '--list-langs'
-    ]
-    try:
-        langs = check_output(
-                args_tess, close_fds=True, universal_newlines=True,
-                stderr=STDOUT)
-    except CalledProcessError as e:
-        msg = dedent("""Tesseract failed to report available languages.
-        Output from Tesseract:
-        -----------
-        """)
-        msg += e.output
-        print(msg, file=sys.stderr)
-        raise MissingDependencyError from e
-    return set(lang.strip() for lang in langs.splitlines()[1:])
-
-
-def tess_base_args(languages, engine_mode):
-    args = [
-        get_program('tesseract'),
-    ]
-    if languages:
-        args.extend(['-l', '+'.join(languages)])
-    if engine_mode is not None and v4():
-        args.extend(['--oem', str(engine_mode)])
-    return args
-
-
-def get_orientation(input_file, language: list, engine_mode, timeout: float,
-                    log):
-    args_tesseract = tess_base_args(language, engine_mode) + [
-        psm(), '0',
-        input_file,
-        'stdout'
-    ]
-
-    try:
-        stdout = check_output(
-            args_tesseract, close_fds=True, stderr=STDOUT,
-            universal_newlines=True, timeout=timeout)
-    except TimeoutExpired:
-        return OrientationConfidence(angle=0, confidence=0.0)
-    except CalledProcessError as e:
-        tesseract_log_output(log, e.output, input_file)
-        if ('Too few characters. Skipping this page' in e.output or
-                'Image too large' in e.output):
-            return OrientationConfidence(0, 0)
-        raise e from e
-    else:
-        osd = {}
-        for line in stdout.splitlines():
-            line = line.strip()
-            parts = line.split(':', maxsplit=2)
-            if len(parts) == 2:
-                osd[parts[0].strip()] = parts[1].strip()
-
-        angle = int(osd.get('Orientation in degrees', 0))
-        if 'Orientation' in osd:
-            # Tesseract < 3.04.01
-            # reports "Orientation in degrees" as a counterclockwise angle
-            # We keep it clockwise
-            assert 'Rotate' not in osd
-            angle = -angle % 360
-        else:
-            # Tesseract == 3.04.01, hopefully also Tesseract > 3.04.01
-            # reports "Orientation in degrees" as a clockwise angle
-            assert 'Rotate' in osd
-
-        oc = OrientationConfidence(
-            angle=angle,
-            confidence=float(osd.get('Orientation confidence', 0)))
-        return oc
-
-
-def tesseract_log_output(log, stdout, input_file):
-    lines = stdout.splitlines()
-    prefix = "{0:4d}: [tesseract] ".format(page_number(input_file))
-    for line in lines:
-        if line.startswith("Tesseract Open Source"):
-            continue
-        elif line.startswith("Warning in pixReadMem"):
-            continue
-        elif 'diacritics' in line:
-            log.warning(prefix + "lots of diacritics - possibly poor OCR")
-        elif line.startswith('OSD: Weak margin'):
-            log.warning(prefix + "unsure about page orientation")
-        elif 'error' in line.lower() or 'exception' in line.lower():
-            log.error(prefix + line.strip())
-        elif 'warning' in line.lower():
-            log.warning(prefix + line.strip())
-        elif 'read_params_file' in line.lower():
-            log.error(prefix + line.strip())
-        else:
-            log.info(prefix + line.strip())
-
-
-def page_timedout(log, input_file):
-    prefix = "{0:4d}: [tesseract] ".format(page_number(input_file))
-    log.warning(prefix + " took too long to OCR - skipping")
-
-
-def _generate_null_hocr(output_hocr, output_sidecar, image):
-    """Produce a .hocr file that reports no text detected on a page that is
-    the same size as the input image."""
-    from PIL import Image
-
-    im = Image.open(image)
-    w, h = im.size
-
-    with open(output_hocr, 'w', encoding="utf-8") as f:
-        f.write(HOCR_TEMPLATE.format(w, h))
-    with open(output_sidecar, 'w', encoding='utf-8') as f:
-        f.write('[skipped page]')
-
-
-def generate_hocr(input_file, output_files, language: list, engine_mode,
-                  tessconfig: list,
-                  timeout: float, pagesegmode: int, log):
-
-    output_hocr = next(o for o in output_files if o.endswith('.hocr'))
-    output_sidecar = next(o for o in output_files if o.endswith('.txt'))
-    prefix = os.path.splitext(output_hocr)[0]
-
-    args_tesseract = tess_base_args(language, engine_mode)
-
-    if pagesegmode is not None:
-        args_tesseract.extend([psm(), str(pagesegmode)])
-
-    # Reminder: test suite tesseract spoofers will break after any changes
-    # to the number of order parameters here
-    # Tesseract 3.04 requires the order here to be "hocr txt" and will fail
-    # on "txt hocr"
-    args_tesseract.extend([
-        input_file,
-        prefix,
-        'hocr',
-        'txt'
-    ] + tessconfig)
-    try:
-        log.debug(args_tesseract)
-        stdout = check_output(
-            args_tesseract, close_fds=True, stderr=STDOUT,
-            universal_newlines=True, timeout=timeout)
-    except TimeoutExpired:
-        # Generate a HOCR file with no recognized text if tesseract times out
-        # Temporary workaround to hocrTransform not being able to function if
-        # it does not have a valid hOCR file.
-        page_timedout(log, input_file)
-        _generate_null_hocr(output_hocr, output_sidecar, input_file)
-    except CalledProcessError as e:
-        tesseract_log_output(log, e.output, input_file)
-        if 'read_params_file: parameter not found' in e.output:
-            raise TesseractConfigError() from e
-        if 'Image too large' in e.output:
-            _generate_null_hocr(output_hocr, output_sidecar, input_file)
-            return
-
-        raise e from e
-    else:
-        tesseract_log_output(log, stdout, input_file)
-        # The sidecar text file will get the suffix .txt; rename it to
-        # whatever caller wants it named
-        if os.path.exists(prefix + '.txt'):
-            shutil.move(prefix + '.txt', output_sidecar)
-
-
-def use_skip_page(text_only, skip_pdf, output_pdf, output_text):
-    with open(output_text, 'w') as f:
-        f.write('[skipped page]')
-
-    if not text_only:
-        os.symlink(skip_pdf, output_pdf)
-        return
-
-    # For text only we must create a blank page with dimensions identical
-    # to the skip page because this is equivalent to a page with no text
-
-    pdf_in = pypdf.PdfFileReader(skip_pdf)
-    page0 = pdf_in.pages[0]
-
-    with open(output_pdf, 'wb') as out:
-        pdf_out = pypdf.PdfFileWriter()
-        w, h = page0.mediaBox.getWidth(), page0.mediaBox.getHeight()
-        pdf_out.addBlankPage(w, h)
-        pdf_out.write(out)
-
-
-def generate_pdf(*, input_image, skip_pdf, output_pdf, output_text,
-                 language: list, engine_mode, text_only: bool,
-                 tessconfig: list, timeout: float, pagesegmode: int, log):
-    '''Use Tesseract to render a PDF.
-
-    input_image -- image to analyze
-    skip_pdf -- if we time out, use this file as output
-    output_pdf -- file to generate
-    output_text -- OCR text file
-    language -- list of languages to consider
-    engine_mode -- engine mode argument for tess v4
-    text_only -- enable tesseract text only mode?
-    tessconfig -- tesseract configuration
-    timeout -- timeout (seconds)
-    log -- logger object
-    '''
-
-    args_tesseract = tess_base_args(language, engine_mode)
-
-    if pagesegmode is not None:
-        args_tesseract.extend([psm(), str(pagesegmode)])
-
-    if text_only:
-        args_tesseract.extend(['-c', 'textonly_pdf=1'])
-
-    prefix = os.path.splitext(output_pdf)[0]  # Tesseract appends suffixes
-
-    # Reminder: test suite tesseract spoofers will break after any changes
-    # to the number of order parameters here
-    args_tesseract.extend([
-        input_image,
-        prefix,
-        'pdf',
-        'txt'
-    ] + tessconfig)
-
-    try:
-        log.debug(args_tesseract)
-        stdout = check_output(
-            args_tesseract, close_fds=True, stderr=STDOUT,
-            universal_newlines=True, timeout=timeout)
-        if os.path.exists(prefix + '.txt'):
-            shutil.move(prefix + '.txt', output_text)
-    except TimeoutExpired:
-        page_timedout(log, input_image)
-        use_skip_page(text_only, skip_pdf, output_pdf, output_text)
-    except CalledProcessError as e:
-        tesseract_log_output(log, e.output, input_image)
-        if 'read_params_file: parameter not found' in e.output:
-            raise TesseractConfigError() from e
-
-        if 'Image too large' in e.output:
-            use_skip_page(text_only, skip_pdf, output_pdf, output_text)
-            return
-        raise e from e
-    else:
-        tesseract_log_output(log, stdout, input_image)

ocrmypdf/exec/unpaper.py

@@ -1,105 +0,0 @@
-#!/usr/bin/env python3
-# © 2015 James R. Barlow: github.com/jbarlow83
-# unpaper documentation:
-# https://github.com/Flameeyes/unpaper/blob/master/doc/basic-concepts.md
-
-from subprocess import CalledProcessError, STDOUT, check_output, check_call
-from tempfile import NamedTemporaryFile
-import sys
-import os
-from functools import lru_cache
-from ..exceptions import MissingDependencyError
-from . import get_program
-
-
-@lru_cache(maxsize=1)
-def version():
-    args_unpaper = [
-        get_program('unpaper'),
-        '--version'
-    ]
-    version = check_output(
-        args_unpaper, close_fds=True, universal_newlines=True,
-        stderr=STDOUT, timeout=5)
-    return version.strip()
-
-
-try:
-    from PIL import Image
-except ImportError:
-    print("Could not find Python3 imaging library", file=sys.stderr)
-    raise
-
-
-def run(input_file, output_file, dpi, log, mode_args):
-    args_unpaper = [
-        get_program('unpaper'),
-        '-v',
-        '--dpi', str(dpi)
-    ] + mode_args
-
-    SUFFIXES = {'1': '.pbm', 'L': '.pgm', 'RGB': '.ppm'}
-
-    im = Image.open(input_file)
-    if im.mode not in SUFFIXES.keys():
-        log.info("Converting image to other colorspace")
-        try:
-            if im.mode == 'P' and len(im.getcolors()) == 2:
-                im = im.convert(mode='1')
-            else:
-                im = im.convert(mode='RGB')
-        except IOError as e:
-            log.error(
-                    "Could not convert image with type " + im.mode)
-            raise MissingDependencyError() from e
-
-    try:
-        suffix = SUFFIXES[im.mode]
-    except KeyError:
-        log.error(
-                "Failed to convert image to a supported format.")
-        raise MissingDependencyError() from e
-
-    with NamedTemporaryFile(suffix=suffix) as input_pnm, \
-            NamedTemporaryFile(suffix=suffix, mode="r+b") as output_pnm:
-        im.save(input_pnm, format='PPM')
-        im.close()
-
-        os.unlink(output_pnm.name)
-
-        args_unpaper.extend([input_pnm.name, output_pnm.name])
-        try:
-            stdout = check_output(
-                args_unpaper, close_fds=True,
-                universal_newlines=True, stderr=STDOUT,
-                )
-        except CalledProcessError as e:
-            log.debug(e.output)
-            raise e from e
-        else:
-            log.debug(stdout)
-            # unpaper sets dpi to 72
-            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, [
-        '--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-deskew',        # don't deskew
-    ])

ocrmypdf/helpers.py

@@ -1,88 +0,0 @@
-#!/usr/bin/env python3
-# © 2016 James R. Barlow: github.com/jbarlow83
-
-from functools import partial
-from collections.abc import Iterable
-from contextlib import suppress, contextmanager
-import sys
-import os
-
-
-def re_symlink(input_file, soft_link_name, log=None):
-    """
-    Helper function: relinks soft symbolic link if necessary
-    """
-
-    if log is None:
-        prdebug = partial(print, file=sys.stderr)
-    else:
-        prdebug = log.debug
-
-    # Guard against soft linking to oneself
-    if input_file == soft_link_name:
-        prdebug("Warning: No symbolic link made. You are using " +
-                "the original data directory as the working directory.")
-        return
-
-    # Soft link already exists: delete for relink?
-    if os.path.lexists(soft_link_name):
-        # do not delete or overwrite real (non-soft link) file
-        if not os.path.islink(soft_link_name):
-            raise FileExistsError(
-                "%s exists and is not a link" % soft_link_name)
-        try:
-            os.unlink(soft_link_name)
-        except:
-            prdebug("Can't unlink %s" % (soft_link_name))
-
-    if not os.path.exists(input_file):
-        raise FileNotFoundError(
-            "trying to create a broken symlink to %s" % input_file)
-
-    prdebug("os.symlink(%s, %s)" % (input_file, soft_link_name))
-
-    # Create symbolic link using absolute path
-    os.symlink(
-        os.path.abspath(input_file),
-        soft_link_name
-    )
-
-
-def is_iterable_notstr(thing):
-    return isinstance(thing, Iterable) and not isinstance(thing, str)
-
-
-def page_number(input_file):
-    return int(os.path.basename(input_file)[0:6])
-
-
-def is_file_writable(test_file):
-    """Intentionally racy test if target is writable.
-
-    We intend to write to the output file if and only if we succeed and
-    can replace it atomically. Before doing the OCR work, make sure
-    the location is writable.
-    """
-    if os.path.exists(test_file):
-        return os.access(
-            test_file, os.W_OK,
-            effective_ids=(os.access in os.supports_effective_ids))
-    else:
-        try:
-            fp = open(test_file, 'wb')
-        except OSError as e:
-            return False
-        else:
-            fp.close()
-            with suppress(OSError):
-                os.unlink(test_file)
-        return True
-
-
-@contextmanager
-def universal_open(p, *args, **kwargs):
-    "Work around Python 3.5's inability to open(pathlib.Path())"
-    try:
-        yield p.open(*args, **kwargs)
-    except AttributeError:
-        yield open(p, *args, **kwargs)

ocrmypdf/hocrtransform.py

@@ -1,230 +0,0 @@
-#!/usr/bin/env python3
-##############################################################################
-# Copyright (c) 2013-14: fritz-hh from Github
-#   (https://github.com/fritz-hh)
-#
-# Copyright (c) 2010: Jonathan Brinley from Github
-#   (https://github.com/jbrinley/HocrConverter)
-#   Initial version by Jonathan Brinley, jonathanbrinley@gmail.com
-##############################################################################
-from reportlab.pdfgen.canvas import Canvas
-from reportlab.lib.units import inch
-from xml.etree import ElementTree
-from PIL import Image
-from collections import namedtuple
-import re
-import argparse
-
-
-Rect = namedtuple('Rect', ['x1', 'y1', 'x2', 'y2'])
-
-
-class HocrTransformError(Exception):
-    pass
-
-
-class HocrTransform():
-
-    """
-    A class for converting documents from the hOCR format.
-    For details of the hOCR format, see:
-    http://docs.google.com/View?docid=dfxcv4vc_67g844kf
-    """
-
-    def __init__(self, hocrFileName, dpi):
-        self.dpi = dpi
-        self.boxPattern = re.compile(r'bbox((\s+\d+){4})')
-
-        self.hocr = ElementTree.parse(hocrFileName)
-
-        # if the hOCR file has a namespace, ElementTree requires its use to
-        # find elements
-        matches = re.match(r'({.*})html', self.hocr.getroot().tag)
-        self.xmlns = ''
-        if matches:
-            self.xmlns = matches.group(1)
-
-        # get dimension in pt (not pixel!!!!) of the OCRed image
-        self.width, self.height = None, None
-        for div in self.hocr.findall(
-                ".//%sdiv[@class='ocr_page']" % (self.xmlns)):
-            coords = self.element_coordinates(div)
-            pt_coords = self.pt_from_pixel(coords)
-            self.width = pt_coords.x2 - pt_coords.x1
-            self.height = pt_coords.y2 - pt_coords.y1
-            # there shouldn't be more than one, and if there is, we don't want
-            # it
-            break
-        if self.width is None or self.height is None:
-            raise HocrTransformError("hocr file is missing page dimensions")
-
-    def __str__(self):
-        """
-        Return the textual content of the HTML body
-        """
-        if self.hocr is None:
-            return ''
-        body = self.hocr.find(".//%sbody" % (self.xmlns))
-        if body:
-            return self._get_element_text(body)
-        else:
-            return ''
-
-    def _get_element_text(self, element):
-        """
-        Return the textual content of the element and its children
-        """
-        text = ''
-        if element.text is not None:
-            text += element.text
-        for child in element.getchildren():
-            text += self._get_element_text(child)
-        if element.tail is not None:
-            text += element.tail
-        return text
-
-    def element_coordinates(self, element):
-        """
-        Returns a tuple containing the coordinates of the bounding box around
-        an element
-        """
-        out = (0, 0, 0, 0)
-        if 'title' in element.attrib:
-            matches = self.boxPattern.search(element.attrib['title'])
-            if matches:
-                coords = matches.group(1).split()
-                out = Rect._make(int(coords[n]) for n in range(4))
-        return out
-
-    def pt_from_pixel(self, pxl):
-        """
-        Returns the quantity in PDF units (pt) given quantity in pixels
-        """
-        return Rect._make(
-            (c / self.dpi * inch) for c in pxl)
-
-    def replace_unsupported_chars(self, s):
-        """
-        Given an input string, returns the corresponding string that:
-        - is available in the helvetica facetype
-        - does not contain any ligature (to allow easy search in the PDF file)
-        """
-        # The 'u' before the character to replace indicates that it is a
-        # unicode character
-        s = s.replace(u"fl", "fl")
-        s = s.replace(u"fi", "fi")
-        return s
-
-    def to_pdf(self, outFileName, imageFileName=None, showBoundingboxes=False,
-               fontname="Helvetica", invisibleText=False):
-        """
-        Creates a PDF file with an image superimposed on top of the text.
-        Text is positioned according to the bounding box of the lines in
-        the hOCR file.
-        The image need not be identical to the image used to create the hOCR
-        file.
-        It can have a lower resolution, different color mode, etc.
-        """
-        # create the PDF file
-        # page size in points (1/72 in.)
-        pdf = Canvas(
-            outFileName, pagesize=(self.width, self.height), pageCompression=1)
-
-        # draw bounding box for each paragraph
-        # light blue for bounding box of paragraph
-        pdf.setStrokeColorRGB(0, 1, 1)
-        # light blue for bounding box of paragraph
-        pdf.setFillColorRGB(0, 1, 1)
-        pdf.setLineWidth(0)		# no line for bounding box
-        for elem in self.hocr.findall(
-                ".//%sp[@class='%s']" % (self.xmlns, "ocr_par")):
-
-            elemtxt = self._get_element_text(elem).rstrip()
-            if len(elemtxt) == 0:
-                continue
-
-            pxl_coords = self.element_coordinates(elem)
-            pt = self.pt_from_pixel(pxl_coords)
-
-            # draw the bbox border
-            if showBoundingboxes:
-                pdf.rect(
-                    pt.x1, self.height - pt.y2, pt.x2 - pt.x1, pt.y2 - pt.y1,
-                    fill=1)
-
-        # check if element with class 'ocrx_word' are available
-        # otherwise use 'ocr_line' as fallback
-        elemclass = "ocr_line"
-        if self.hocr.find(
-                ".//%sspan[@class='ocrx_word']" % (self.xmlns)) is not None:
-            elemclass = "ocrx_word"
-
-        # itterate all text elements
-        # light green for bounding box of word/line
-        pdf.setStrokeColorRGB(1, 0, 0)
-        pdf.setLineWidth(0.5)		# bounding box line width
-        pdf.setDash(6, 3)		# bounding box is dashed
-        pdf.setFillColorRGB(0, 0, 0)  # text in black
-        for elem in self.hocr.findall(
-                ".//%sspan[@class='%s']" % (self.xmlns, elemclass)):
-
-            elemtxt = self._get_element_text(elem).rstrip()
-
-            elemtxt = self.replace_unsupported_chars(elemtxt)
-
-            if len(elemtxt) == 0:
-                continue
-
-            pxl_coords = self.element_coordinates(elem)
-            pt = self.pt_from_pixel(pxl_coords)
-
-            # draw the bbox border
-            if showBoundingboxes:
-                pdf.rect(
-                    pt.x1, self.height - pt.y2, pt.x2 - pt.x1, pt.y2 - pt.y1,
-                    fill=0)
-
-            text = pdf.beginText()
-            fontsize = pt.y2 - pt.y1
-            text.setFont(fontname, fontsize)
-            if invisibleText:
-                text.setTextRenderMode(3)  # Invisible (indicates OCR text)
-
-            # set cursor to bottom left corner of bbox (adjust for dpi)
-            text.setTextOrigin(pt.x1, self.height - pt.y2)
-
-            # scale the width of the text to fill the width of the bbox
-            text.setHorizScale(
-                100 * (pt.x2 - pt.x1) / pdf.stringWidth(
-                    elemtxt, fontname, fontsize))
-
-            # write the text to the page
-            text.textLine(elemtxt)
-            pdf.drawText(text)
-
-        # put the image on the page, scaled to fill the page
-        if imageFileName is not None:
-            pdf.drawImage(imageFileName, 0, 0,
-                          width=self.width, height=self.height)
-
-        # finish up the page and save it
-        pdf.showPage()
-        pdf.save()
-
-
-if __name__ == "__main__":
-    parser = argparse.ArgumentParser(description='Convert hocr file to PDF')
-    parser.add_argument('-b', '--boundingboxes', action="store_true",
-                        default=False, help='Show bounding boxes borders')
-    parser.add_argument('-r', '--resolution', type=int,
-                        default=300,
-                        help='Resolution of the image that was OCRed')
-    parser.add_argument('-i', '--image', default=None,
-                        help='Path to the image to be placed above the text')
-    parser.add_argument('hocrfile', help='Path to the hocr file to be parsed')
-    parser.add_argument(
-        'outputfile', help='Path to the PDF file to be generated')
-    args = parser.parse_args()
-
-    hocr = HocrTransform(args.hocrfile, args.resolution)
-    hocr.to_pdf(args.outputfile, args.image, args.boundingboxes)

ocrmypdf/leptonica.py

@@ -1,598 +0,0 @@
-#!/usr/bin/env python3
-# -*- coding: utf-8 -*-
-#
-# © 2013-16: jbarlow83 from Github (https://github.com/jbarlow83)
-#
-# Python FFI wrapper for Leptonica library
-
-import argparse
-import sys
-import os
-import logging
-from tempfile import TemporaryFile
-from ctypes.util import find_library
-from .lib._leptonica import ffi
-from functools import lru_cache
-from enum import Enum
-
-lept = ffi.dlopen(find_library('lept'))
-
-logger = logging.getLogger(__name__)
-
-
-def stderr(*objs):
-    """Python 2/3 compatible print to stderr.
-    """
-    print("leptonica.py:", *objs, file=sys.stderr)
-
-
-class LeptonicaErrorTrap(object):
-    """Context manager to trap errors reported by Leptonica.
-
-    Leptonica's error return codes are unreliable to the point of being
-    almost useless.  It does, however, write errors to stderr provided that is
-    not disabled at its compile time.  Fortunately this is done using error
-    macros so it is very self-consistent.
-
-    This context manager redirects stderr to a temporary file which is then
-    read and parsed for error messages.  As a side benefit, debug messages
-    from Leptonica are also suppressed.
-
-    """
-    def __enter__(self):
-        from io import UnsupportedOperation
-        self.tmpfile = TemporaryFile()
-
-        # Save the old stderr, and redirect stderr to temporary file
-        sys.stderr.flush()
-        try:
-            self.copy_of_stderr = os.dup(sys.stderr.fileno())
-            os.dup2(self.tmpfile.fileno(), sys.stderr.fileno(),
-                    inheritable=False)
-        except UnsupportedOperation:
-            self.copy_of_stderr = None
-        return
-
-    def __exit__(self, exc_type, exc_value, traceback):
-        # Restore old stderr
-        sys.stderr.flush()
-        if self.copy_of_stderr is not None:
-            os.dup2(self.copy_of_stderr, sys.stderr.fileno())
-            os.close(self.copy_of_stderr)
-
-        # Get data from tmpfile (in with block to ensure it is closed)
-        with self.tmpfile as tmpfile:
-            tmpfile.seek(0)  # Cursor will be at end, so move back to beginning
-            leptonica_output = tmpfile.read().decode(errors='replace')
-
-        assert self.tmpfile.closed
-        assert not sys.stderr.closed
-
-        # If there are Python errors, let them bubble up
-        if exc_type:
-            logger.warning(leptonica_output)
-            return False
-
-        # If there are Leptonica errors, wrap them in Python excpetions
-        if 'Error' in leptonica_output:
-            if 'image file not found' in leptonica_output:
-                raise FileNotFoundError()
-            if 'pixWrite: stream not opened' in leptonica_output:
-                raise LeptonicaIOError()
-            raise LeptonicaError(leptonica_output)
-
-        return False
-
-
-class LeptonicaError(Exception):
-    pass
-
-
-class LeptonicaIOError(LeptonicaError):
-    pass
-
-
-class RemoveColormap(Enum):
-    to_binary = 0
-    to_grayscale = 1
-    to_full_color = 2
-    based_on_src = 3
-
-
-class Pix:
-    """Wrapper around leptonica's PIX object.
-
-    Leptonica uses referencing counting on PIX objects. Also, many Leptonica
-    functions return the original object with an increased reference count
-    if the operation had no effect (for example, image skew was found to be 0).
-    This has complications for memory management in Python. Whenever Leptonica
-    returns a PIX object (new or old), we wrap it in this class, which
-    registers it with the FFI garbage collector. pixDestroy() decrements the
-    reference count and only destroys when the last reference is removed.
-
-    Leptonica's reference counting is not threadsafe. This class can be used
-    in a threadsafe manner if a Python threading.Lock protects the data.
-
-    This class treats Pix objects as immutable.  All methods return new
-    modified objects.  This allows convenient chaining:
-
-    >>>   Pix.read('filename.jpg').scale((0.5, 0.5)).deskew().show()
-
-    """
-
-    def __init__(self, pix):
-        self._pix = ffi.gc(pix, Pix._pix_destroy)
-
-    def __repr__(self):
-        if self._pix:
-            s = "<leptonica.Pix image size={0}x{1} depth={2} at 0x{3:x}>"
-            return s.format(self._pix.w, self._pix.h, self._pix.d,
-                            int(ffi.cast("intptr_t", self._pix)))
-        else:
-            return "<leptonica.Pix image NULL>"
-
-    def _repr_png_(self):
-        """iPython display hook
-
-        returns png version of image
-        """
-
-        data = ffi.new('l_uint8 **')
-        size = ffi.new('size_t *')
-
-        err = lept.pixWriteMemPng(data, size, self._pix, 0)
-        if err != 0:
-            raise LeptonicaIOError("pixWriteMemPng")
-
-        char_data = ffi.cast('char *', data[0])
-        return ffi.buffer(char_data, size[0])[:]
-
-    def __getstate__(self):
-        data = ffi.new('l_uint32 **')
-        size = ffi.new('size_t *')
-
-        err = lept.pixSerializeToMemory(self._pix, data, size)
-        if err != 0:
-            raise LeptonicaIOError("pixSerializeToMemory")
-
-        char_data = ffi.cast('char *', data[0])
-
-        # Copy from C bytes to python bytes()
-        data_bytes = ffi.buffer(char_data, size[0])[:]
-
-        # Can now free C bytes
-        lept.lept_free(char_data)
-        return dict(data=data_bytes)
-
-    def __setstate__(self, state):
-        cdata_bytes = ffi.new('char[]', state['data'])
-        cdata_uint32 = ffi.cast('l_uint32 *', cdata_bytes)
-
-        pix = lept.pixDeserializeFromMemory(
-            cdata_uint32, len(state['data']))
-        Pix.__init__(self, pix)
-
-    def __eq__(self, other):
-        return self.__getstate__() == other.__getstate__()
-
-    @property
-    def width(self):
-        return self._pix.w
-
-    @property
-    def height(self):
-        return self._pix.h
-
-    @property
-    def depth(self):
-        return self._pix.d
-
-    @property
-    def size(self):
-        return (self._pix.w, self._pix.h)
-
-    @property
-    def info(self):
-        return {'dpi': (self._pix.xres, self._pix.yres)}
-
-    @property
-    def mode(self):
-        "Return mode like PIL.Image"
-        if self.depth == 1:
-            return '1'
-        elif self.depth >= 16:
-            return 'RGB'
-        elif not self._pix.colormap:
-            return 'L'
-        else:
-            return 'P'
-
-    @classmethod
-    def read(cls, filename):
-        """Load an image file into a PIX object.
-
-        Leptonica can load TIFF, PNM (PBM, PGM, PPM), PNG, and JPEG.  If
-        loading fails then the object will wrap a C null pointer.
-        """
-        with LeptonicaErrorTrap():
-            return cls(lept.pixRead(
-                filename.encode(sys.getfilesystemencoding())))
-
-    def write_implied_format(
-            self, filename, jpeg_quality=0, jpeg_progressive=0):
-        """Write pix to the filename, with the extension indicating format.
-
-        jpeg_quality -- quality (iff JPEG; 1 - 100, 0 for default)
-        jpeg_progressive -- (iff JPEG; 0 for baseline seq., 1 for progressive)
-        """
-        with LeptonicaErrorTrap():
-            lept.pixWriteImpliedFormat(
-                filename.encode(sys.getfilesystemencoding()),
-                self._pix, jpeg_quality, jpeg_progressive)
-
-    def topil(self):
-        "Returns a PIL.Image version of this Pix"
-        from PIL import Image
-
-        # Leptonica manages data in words, so it implicitly does an endian
-        # swap.  Tell Pillow about this when it reads the data.
-        pix = self
-        if sys.byteorder == 'little':
-            if self.mode == 'RGB':
-                raw_mode = 'XBGR'
-            elif self.mode == 'RGBA':
-                raw_mode = 'ABGR'
-            elif self.mode == '1':
-                raw_mode = '1;I'
-                pix = Pix(lept.pixEndianByteSwapNew(pix._pix))
-            else:
-                raw_mode = self.mode
-                pix = Pix(lept.pixEndianByteSwapNew(pix._pix))
-        else:
-            raw_mode = self.mode  # no endian swap needed
-
-        size = (pix._pix.w, pix._pix.h)
-        bytecount = pix._pix.wpl * 4 * pix._pix.h
-        buf = ffi.buffer(pix._pix.data, bytecount)
-        stride = pix._pix.wpl * 4
-
-        im = Image.frombytes(self.mode, size, buf, 'raw', raw_mode, stride)
-
-        return im
-
-    def show(self):
-        return self.topil().show()
-
-    def deskew(self, reduction_factor=0):
-        """Returns the deskewed pix object.
-
-        A clone of the original is returned when the algorithm cannot find a
-        skew angle with sufficient confidence.
-
-        reduction_factor -- amount to downsample (0 for default) when searching
-            for skew angle
-        """
-        with LeptonicaErrorTrap():
-            return Pix(lept.pixDeskew(self._pix, reduction_factor))
-
-    def scale(self, scale_xy):
-        "Returns the pix object rescaled according to the proportions given."
-        with LeptonicaErrorTrap():
-            return Pix(lept.pixScale(self._pix, scale_xy[0], scale_xy[1]))
-
-    def rotate180(self):
-        with LeptonicaErrorTrap():
-            return Pix(lept.pixRotate180(ffi.NULL, self._pix))
-
-    def rotate_orth(self, quads):
-        "Orthographic rotation, quads: 0-3, number of clockwise rotations"
-        with LeptonicaErrorTrap():
-            return Pix(lept.pixRotateOrth(self._pix, quads))
-
-    def find_skew(self):
-        """Returns a tuple (deskew angle in degrees, confidence value).
-
-        Returns (None, None) if no angle is available.
-        """
-        with LeptonicaErrorTrap():
-            angle = ffi.new('float *', 0.0)
-            confidence = ffi.new('float *', 0.0)
-            result = lept.pixFindSkew(self._pix, angle, confidence)
-            if result == 0:
-                return (angle[0], confidence[0])
-            else:
-                return (None, None)
-
-    def convert_rgb_to_luminance(self):
-        with LeptonicaErrorTrap():
-            gray_pix = lept.pixConvertRGBToLuminance(self._pix)
-            if gray_pix:
-                return Pix(gray_pix)
-            return None
-
-    def remove_colormap(self, removal_type):
-        """Remove a palette
-
-            removal_type - RemovalColormap()
-        """
-
-        with LeptonicaErrorTrap():
-            return Pix(lept.pixRemoveColormap(self._pix, removal_type))
-
-    def otsu_adaptive_threshold(
-            self, tile_size=(300, 300), kernel_size=(4, 4), scorefract=0.1):
-        with LeptonicaErrorTrap():
-            sx, sy = tile_size
-            smoothx, smoothy = kernel_size
-            p_pix = ffi.new('PIX **')
-
-            result = lept.pixOtsuAdaptiveThreshold(
-                self._pix,
-                sx, sy,
-                smoothx, smoothy,
-                scorefract,
-                ffi.NULL,
-                p_pix)
-            if result == 0:
-                return Pix(p_pix[0])
-            else:
-                return None
-
-    def otsu_threshold_on_background_norm(
-            self, mask=None, tile_size=(10, 15), thresh=100, mincount=50,
-            bgval=255, kernel_size=(2, 2), scorefract=0.1):
-        with LeptonicaErrorTrap():
-            sx, sy = tile_size
-            smoothx, smoothy = kernel_size
-            if mask is None:
-                mask = ffi.NULL
-            if isinstance(mask, Pix):
-                mask = mask._pix
-
-            thresh_pix = lept.pixOtsuThreshOnBackgroundNorm(
-                self._pix,
-                mask,
-                sx, sy,
-                thresh, mincount, bgval,
-                smoothx, smoothy,
-                scorefract,
-                ffi.NULL
-                )
-            if thresh_pix == ffi.NULL:
-                return None
-            return Pix(thresh_pix)
-
-    def crop_to_foreground(
-            self, threshold=128, mindist=70, erasedist=30, pagenum=0,
-            showmorph=0, display=0, pdfdir=ffi.NULL):
-        with LeptonicaErrorTrap():
-            cropbox = Box(lept.pixFindPageForeground(
-                self._pix,
-                threshold,
-                mindist,
-                erasedist,
-                pagenum,
-                showmorph,
-                display,
-                pdfdir))
-
-            print(repr(cropbox))
-
-            cropped_pix = lept.pixClipRectangle(
-                self._pix,
-                cropbox._box,
-                ffi.NULL)
-
-            return Pix(cropped_pix)
-
-    def clean_background_to_white(
-            self, mask=None, grayscale=None, gamma=1.0, black=0, white=255):
-        with LeptonicaErrorTrap():
-            return Pix(lept.pixCleanBackgroundToWhite(
-                self._pix,
-                mask or ffi.NULL,
-                grayscale or ffi.NULL,
-                gamma,
-                black,
-                white))
-
-    def gamma_trc(self, gamma=1.0, minval=0, maxval=255):
-        with LeptonicaErrorTrap():
-            return Pix(lept.pixGammaTRC(
-                ffi.NULL,
-                self._pix,
-                gamma,
-                minval,
-                maxval
-                ))
-
-    def background_norm(
-            self, mask=None, grayscale=None, tile_size=(10, 15), fg_threshold=60,
-            min_count=40, bg_val=200, smooth_kernel=(2, 1)):
-        with LeptonicaErrorTrap():
-            return Pix(lept.pixBackgroundNorm(
-                self._pix,
-                mask or ffi.NULL,
-                grayscale or ffi.NULL,
-                tile_size[0],
-                tile_size[1],
-                fg_threshold,
-                min_count,
-                bg_val,
-                smooth_kernel[0],
-                smooth_kernel[1]
-                ))
-
-    @staticmethod
-    @lru_cache(maxsize=1)
-    def make_pixel_sum_tab8():
-        return lept.makePixelSumTab8()
-
-    @staticmethod
-    def correlation_binary(pix1, pix2):
-        if get_leptonica_version() < 'leptonica-1.72':
-            # Older versions of Leptonica (pre-1.72) have a buggy
-            # implementation of pixCorrelationBinary that overflows on larger
-            # images.  Ubuntu trusty has 1.70. Ubuntu PPA
-            # ppa:rebuntu16/avidemux+unofficial has "leptonlib" 1.73.
-            pix1_count = ffi.new('l_int32 *')
-            pix2_count = ffi.new('l_int32 *')
-            pixn_count = ffi.new('l_int32 *')
-            tab8 = Pix.make_pixel_sum_tab8()
-
-            lept.pixCountPixels(pix1._pix, pix1_count, tab8)
-            lept.pixCountPixels(pix2._pix, pix2_count, tab8)
-            pixn = Pix(lept.pixAnd(ffi.NULL, pix1._pix, pix2._pix))
-            lept.pixCountPixels(pixn._pix, pixn_count, tab8)
-
-            # Python converts these int32s to larger units as needed
-            # to avoid overflow. Overflow happens easily here.
-            correlation = (
-                    (pixn_count[0] * pixn_count[0]) /
-                    (pix1_count[0] * pix2_count[0])
-                    )
-            return correlation
-        else:
-            correlation = ffi.new('float *', 0.0)
-            result = lept.pixCorrelationBinary(pix1._pix, pix2._pix,
-                                               correlation)
-            if result != 0:
-                raise LeptonicaError("Correlation failed")
-            return correlation[0]
-
-    @staticmethod
-    def _pix_destroy(pix):
-        p_pix = ffi.new('PIX **', pix)
-        lept.pixDestroy(p_pix)
-        # print('pix destroy ' + repr(pix))
-
-
-class Box:
-    """Wrapper around Leptonica's BOX objects.
-
-    See class Pix for notes about reference counting.
-    """
-
-    def __init__(self, box):
-        self._box = ffi.gc(box, Box._box_destroy)
-
-    def __repr__(self):
-        if self._box:
-            return '<leptonica.Box x={0} y={1} w={2} h={3}>'.format(
-                self.x, self.y, self.w, self.h)
-        return '<leptonica.Box NULL>'
-
-    @property
-    def x(self):
-        return self._box.x
-
-    @property
-    def y(self):
-        return self._box.y
-
-    @property
-    def w(self):
-        return self._box.w
-
-    @property
-    def h(self):
-        return self._box.h
-
-    @staticmethod
-    def _box_destroy(box):
-        p_box = ffi.new('BOX **', box)
-        lept.boxDestroy(p_box)
-
-
-@lru_cache(maxsize=1)
-def get_leptonica_version():
-    """Get Leptonica version string.
-
-    Caveat: Leptonica expects the caller to free this memory.  We don't,
-    since that would involve binding to libc to access libc.free(),
-    a pointless effort to reclaim 100 bytes of memory.
-    """
-    return ffi.string(lept.getLeptonicaVersion()).decode()
-
-
-def deskew(infile, outfile, dpi):
-    try:
-        pix_source = Pix.read(infile)
-    except LeptonicaIOError:
-        raise LeptonicaIOError("Failed to open file: %s" % infile)
-
-    if dpi < 150:
-        reduction_factor = 1  # Don't downsample too much if DPI is already low
-    else:
-        reduction_factor = 0  # Use default
-    pix_deskewed = pix_source.deskew(reduction_factor)
-
-    try:
-        pix_deskewed.write_implied_format(outfile)
-    except LeptonicaIOError:
-        raise LeptonicaIOError("Failed to open destination file: %s" % outfile)
-
-
-def remove_background(infile, outfile, tile_size=(40, 60), gamma=1.0,
-                      black_threshold=70, white_threshold=190):
-    try:
-        pix = Pix.read(infile)
-    except LeptonicaIOError:
-        raise LeptonicaIOError("Failed to open file: %s" % infile)
-
-    pix = pix.background_norm(tile_size=tile_size).gamma_trc(
-            gamma, black_threshold, white_threshold)
-
-    try:
-        pix.write_implied_format(outfile)
-    except LeptonicaIOError:
-        raise LeptonicaIOError("Failed to open destination file: %s" % outfile)
-
-
-if __name__ == '__main__':
-    parser = argparse.ArgumentParser(
-        description="Python wrapper to access Leptonica")
-
-    subparsers = parser.add_subparsers(title='commands',
-                                       description='supported operations')
-
-    parser_deskew = subparsers.add_parser('deskew')
-    parser_deskew.add_argument('-r', '--dpi', dest='dpi', action='store',
-                               type=int, default=300, help='input resolution')
-    parser_deskew.add_argument('infile', help='image to deskew')
-    parser_deskew.add_argument('outfile', help='deskewed output image')
-    parser_deskew.set_defaults(func=deskew)
-
-    args = parser.parse_args()
-
-    if get_leptonica_version() != u'leptonica-1.69':
-        print("Unexpected leptonica version: %s" % getLeptonicaVersion())
-
-    args.func(args)
-
-
-def test_skew_angle():
-    from PIL import Image, ImageDraw
-    from tempfile import NamedTemporaryFile
-
-    im = Image.new(mode='1', size=(1000, 1000), color=1)
-
-    draw = ImageDraw.Draw(im)
-    for n in range(20):
-        draw.line([(50, 25 + 50*n), (950, 25 + 50*n)], width=1)
-    del draw
-
-    test_angles = [0.1 * ang for ang in range(1, 10)] + \
-                  [float(ang) for ang in range(1, 7)]
-    test_angles += [-ang for ang in test_angles]
-    test_angles = sorted(test_angles)
-
-    for rotate_angle in test_angles:
-        rotated_im = im.rotate(rotate_angle)
-        with NamedTemporaryFile(prefix='lept-skew', suffix='.png', delete=True) as tmpfile:
-            rotated_im.save(tmpfile)
-            pix = pixRead(tmpfile.name)
-            angle, confidence = pixFindSkew(pix)
-            print('{0} {1}  {2}'.format(rotate_angle, angle, confidence), file=sys.stderr)
-
-

ocrmypdf/lib/__init__.py

@@ -1,2 +0,0 @@
-"""Bindings to external libraries"""
-# © 2017 James R. Barlow: github.com/jbarlow83

ocrmypdf/lib/compile_leptonica.py

@@ -1,194 +0,0 @@
-# © 2017 James R. Barlow: github.com/jbarlow83
-
-from cffi import FFI
-
-ffibuilder = FFI()
-ffibuilder.set_source("ocrmypdf.lib._leptonica", None)
-ffibuilder.cdef("""
-typedef signed char             l_int8;
-typedef unsigned char           l_uint8;
-typedef short                   l_int16;
-typedef unsigned short          l_uint16;
-typedef int                     l_int32;
-typedef unsigned int            l_uint32;
-typedef float                   l_float32;
-typedef double                  l_float64;
-typedef long long               l_int64;
-typedef unsigned long long      l_uint64;
-
-struct Pix
-{
-    l_uint32             w;           /* width in pixels                   */
-    l_uint32             h;           /* height in pixels                  */
-    l_uint32             d;           /* depth in bits (bpp)               */
-    l_uint32             spp;         /* number of samples per pixel       */
-    l_uint32             wpl;         /* 32-bit words/line                 */
-    l_uint32             refcount;    /* reference count (1 if no clones)  */
-    l_int32              xres;        /* image res (ppi) in x direction    */
-                                      /* (use 0 if unknown)                */
-    l_int32              yres;        /* image res (ppi) in y direction    */
-                                      /* (use 0 if unknown)                */
-    l_int32              informat;    /* input file format, IFF_*          */
-    l_int32              special;     /* special instructions for I/O, etc */
-    char                *text;        /* text string associated with pix   */
-    struct PixColormap  *colormap;    /* colormap (may be null)            */
-    l_uint32            *data;        /* the image data                    */
-};
-typedef struct Pix PIX;
-
-struct PixColormap
-{
-    void            *array;     /* colormap table (array of RGBA_QUAD)     */
-    l_int32          depth;     /* of pix (1, 2, 4 or 8 bpp)               */
-    l_int32          nalloc;    /* number of color entries allocated       */
-    l_int32          n;         /* number of color entries used            */
-};
-typedef struct PixColormap  PIXCMAP;
-
-struct Box
-{
-    l_int32            x;
-    l_int32            y;
-    l_int32            w;
-    l_int32            h;
-    l_uint32           refcount;      /* reference count (1 if no clones)  */
-
-};
-typedef struct Box    BOX;
-
-""")
-
-ffibuilder.cdef("""
-PIX * pixRead ( const char *filename );
-PIX * pixScale ( PIX *pixs, l_float32 scalex, l_float32 scaley );
-l_int32 pixFindSkew ( PIX *pixs, l_float32 *pangle, l_float32 *pconf );
-l_int32 pixWriteImpliedFormat ( const char *filename, PIX *pix, l_int32 quality, l_int32 progressive );
-l_int32
-pixWriteMemPng(l_uint8  **pdata,
-               size_t    *psize,
-               PIX       *pix,
-               l_float32  gamma);
-
-void pixDestroy ( PIX **ppix );
-
-PIX *
-pixEndianByteSwapNew(PIX  *pixs);
-
-PIX * pixDeskew ( PIX *pixs, l_int32 redsearch );
-char * getLeptonicaVersion (  );
-l_int32 pixCorrelationBinary(PIX *pix1, PIX *pix2, l_float32 *pval);
-PIX *pixRotate180(PIX *pixd, PIX *pixs);
-PIX *
-pixRotateOrth(PIX     *pixs,
-              l_int32  quads);
-
-l_int32 pixCountPixels ( PIX *pix, l_int32 *pcount, l_int32 *tab8 );
-PIX * pixAnd ( PIX *pixd, PIX *pixs1, PIX *pixs2 );
-l_int32 * makePixelSumTab8 ( void );
-
-PIX * pixDeserializeFromMemory ( const l_uint32 *data, size_t nbytes );
-l_int32 pixSerializeToMemory ( PIX *pixs, l_uint32 **pdata, size_t *pnbytes );
-
-PIX * pixConvertRGBToLuminance(PIX *pixs);
-
-PIX * pixRemoveColormap(PIX *pixs, l_int32  type);
-
-l_int32
-pixOtsuAdaptiveThreshold(PIX       *pixs,
-                         l_int32    sx,
-                         l_int32    sy,
-                         l_int32    smoothx,
-                         l_int32    smoothy,
-                         l_float32  scorefract,
-                         PIX      **ppixth,
-                         PIX      **ppixd);
-
-PIX *
-pixOtsuThreshOnBackgroundNorm(PIX       *pixs,
-                              PIX       *pixim,
-                              l_int32    sx,
-                              l_int32    sy,
-                              l_int32    thresh,
-                              l_int32    mincount,
-                              l_int32    bgval,
-                              l_int32    smoothx,
-                              l_int32    smoothy,
-                              l_float32  scorefract,
-                              l_int32   *pthresh);
-
-PIX *
-pixCleanBackgroundToWhite(PIX       *pixs,
-                          PIX       *pixim,
-                          PIX       *pixg,
-                          l_float32  gamma,
-                          l_int32    blackval,
-                          l_int32    whiteval);
-
-BOX *
-pixFindPageForeground(PIX         *pixs,
-                      l_int32      threshold,
-                      l_int32      mindist,
-                      l_int32      erasedist,
-                      l_int32      pagenum,
-                      l_int32      showmorph,
-                      l_int32      display,
-                      const char  *pdfdir);
-
-PIX *
-pixClipRectangle(PIX   *pixs,
-                 BOX   *box,
-                 BOX  **pboxc);
-
-PIX *
-pixBackgroundNorm(PIX     *pixs,
-                  PIX     *pixim,
-                  PIX     *pixg,
-                  l_int32  sx,
-                  l_int32  sy,
-                  l_int32  thresh,
-                  l_int32  mincount,
-                  l_int32  bgval,
-                  l_int32  smoothx,
-                  l_int32  smoothy);
-
-PIX *
-pixGammaTRC(PIX       *pixd,
-            PIX       *pixs,
-            l_float32  gamma,
-            l_int32    minval,
-            l_int32    maxval);
-
-
-l_int32
-pixNumSignificantGrayColors(PIX       *pixs,
-                            l_int32    darkthresh,
-                            l_int32    lightthresh,
-                            l_float32  minfract,
-                            l_int32    factor,
-                            l_int32   *pncolors);
-
-l_int32
-pixColorFraction(PIX        *pixs,
-                 l_int32     darkthresh,
-                 l_int32     lightthresh,
-                 l_int32     diffthresh,
-                 l_int32     factor,
-                 l_float32  *ppixfract,
-                 l_float32  *pcolorfract);
-
-PIX *
-pixColorMagnitude(PIX     *pixs,
-                  l_int32  rwhite,
-                  l_int32  gwhite,
-                  l_int32  bwhite,
-                  l_int32  type);
-
-void
-boxDestroy(BOX  **pbox);
-
-void lept_free(void *ptr);
-""")
-
-
-if __name__ == '__main__':
-    ffibuilder.compile(verbose=True)

ocrmypdf/pageinfo.py

@@ -1,538 +0,0 @@
-#!/usr/bin/env python3
-# © 2015 James R. Barlow: github.com/jbarlow83
-
-from subprocess import Popen, PIPE
-from decimal import Decimal
-from math import hypot, isclose
-import re
-import sys
-import PyPDF2 as pypdf
-from collections import namedtuple
-import warnings
-
-
-warnings.warn("ocrmypdf.pageinfo is deprecated'; use ocrmypdf.pdfinfo",
-              DeprecationWarning)
-
-matrix_mult = pypdf.pdf.utils.matrixMultiply
-
-FRIENDLY_COLORSPACE = {
-    '/DeviceGray': 'gray',
-    '/CalGray': 'gray',
-    '/DeviceRGB': 'rgb',
-    '/CalRGB': 'rgb',
-    '/DeviceCMYK': 'cmyk',
-    '/Lab': 'lab',
-    '/ICCBased': 'icc',
-    '/Indexed': 'index',
-    '/Separation': 'sep',
-    '/DeviceN': 'devn',
-    '/Pattern': '-',
-    '/G': 'gray',  # Abbreviations permitted in inline images
-    '/RGB': 'rgb',
-    '/CMYK': 'cmyk',
-    '/I': 'index',
-}
-
-FRIENDLY_ENCODING = {
-    '/CCITTFaxDecode': 'ccitt',
-    '/DCTDecode': 'jpeg',
-    '/JPXDecode': 'jpx',
-    '/JBIG2Decode': 'jbig2',
-    '/CCF': 'ccitt',  # Abbreviations permitted in inline images
-    '/DCT': 'jpeg',
-    '/AHx': 'asciihex',
-    '/A85': 'ascii85',
-    '/LZW': 'lzw',
-    '/Fl': 'flate',
-    '/RL': 'runlength'
-}
-
-FRIENDLY_COMP = {
-    'gray': 1,
-    'rgb': 3,
-    'cmyk': 4,
-    'lab': 3,
-    'index': 1
-}
-
-
-UNIT_SQUARE = (1.0, 0.0, 0.0, 1.0, 0.0, 0.0)
-
-
-def _matrix_from_shorthand(shorthand):
-    """Convert from PDF matrix shorthand to full matrix
-
-    PDF 1.7 spec defines a shorthand for describing the entries of a matrix
-    since the last column is always (0, 0, 1).
-    """
-
-    a, b, c, d, e, f = map(float, shorthand)
-    return ((a, b, 0),
-            (c, d, 0),
-            (e, f, 1))
-
-
-def _shorthand_from_matrix(matrix):
-    """Convert from transformation matrix to PDF shorthand."""
-    a, b = matrix[0][0], matrix[0][1]
-    c, d = matrix[1][0], matrix[1][1]
-    e, f = matrix[2][0], matrix[2][1]
-    return tuple(map(float, (a, b, c, d, e, f)))
-
-
-def _is_unit_square(shorthand):
-    values = map(float, shorthand)
-    pairwise = zip(values, UNIT_SQUARE)
-    return all([isclose(a, b, rel_tol=1e-3) for a, b in pairwise])
-
-XobjectSettings = namedtuple('XobjectSettings',
-    ['name', 'shorthand', 'stack_depth'])
-
-InlineSettings = namedtuple('InlineSettings',
-    ['settings', 'shorthand', 'stack_depth'])
-
-ContentsInfo = namedtuple('ContentsInfo', ['xobject_settings', 'inline_images'])
-
-
-def _normalize_stack(operations):
-    """Fix runs of qQ's in the stack
-
-    For some reason PyPDF2 converts runs of qqq, QQ, QQQq, etc. into single
-    operations.  Break this silliness up and issue each stack operation
-    individually so we don't lose count.
-
-    """
-    for operands, command in operations:
-        if re.match(br'Q*q+$', command):   # Zero or more Q, one or more q
-            for char in command:           # Split into individual bytes
-                yield ([], bytes([char]))  # Yield individual bytes
-        else:
-            yield (operands, command)
-
-
-def _interpret_contents(contentstream, initial_shorthand=UNIT_SQUARE):
-    """Interpret the PDF content stream
-
-    The stack represents the state of the PDF graphics stack.  We are only
-    interested in the current transformation matrix (CTM) so we only track
-    this object; a full implementation would need to track many other items.
-
-    The CTM is initialized to the mapping from user space to device space.
-    PDF units are 1/72".  In a PDF viewer or printer this matrix is initialized
-    to the transformation to device space.  For example if set to
-    (1/72, 0, 0, 1/72, 0, 0) then all units would be calculated in inches.
-
-    Images are always considered to be (0, 0) -> (1, 1).  Before drawing an
-    image there should be a 'cm' that sets up an image coordinate system
-    where drawing from (0, 0) -> (1, 1) will draw on the desired area of the
-    page.
-
-    PDF units suit our needs so we initialize ctm to the identity matrix.
-
-    PyPDF2 replaces inline images with a fake "INLINE IMAGE" operator.
-
-    """
-
-    operations = contentstream.operations
-    stack = []
-    ctm = _matrix_from_shorthand(initial_shorthand)
-    xobject_settings = []
-    inline_images = []
-
-    for n, op in enumerate(_normalize_stack(operations)):
-        operands, command = op
-        if command == b'q':
-            stack.append(ctm)
-            if len(stack) > 32:
-                raise RuntimeError(
-                    "PDF graphics stack overflow, command %i" % n)
-        elif command == b'Q':
-            try:
-                ctm = stack.pop()
-            except IndexError:
-                raise RuntimeError(
-                    "PDF graphics stack underflow, command %i" % n)
-        elif command == b'cm':
-            ctm = matrix_mult(
-                _matrix_from_shorthand(operands), ctm)
-        elif command == b'Do':
-            image_name = operands[0]
-            settings = XobjectSettings(
-                name=image_name, shorthand=_shorthand_from_matrix(ctm),
-                stack_depth=len(stack))
-            xobject_settings.append(settings)
-        elif command == b'INLINE IMAGE':
-            settings = operands['settings']
-            inline = InlineSettings(
-                settings=settings, shorthand=_shorthand_from_matrix(ctm),
-                stack_depth=len(stack))
-            inline_images.append(inline)
-
-    return ContentsInfo(
-        xobject_settings=xobject_settings,
-        inline_images=inline_images)
-
-
-def _get_dpi(ctm_shorthand, image_size):
-    """Given the transformation matrix and image size, find the image DPI.
-
-    PDFs do not include image resolution information within image data.
-    Instead, the PDF page content stream describes the location where the
-    image will be rasterized, and the effective resolution is the ratio of the
-    pixel size to raster target size.
-
-    Normally a scanned PDF has the paper size set appropriately but this is
-    not guaranteed. The most common case is a cropped image will change the
-    page size (/CropBox) without altering the page content stream. That means
-    it is not sufficient to assume that the image fills the page, even though
-    that is the most common case.
-
-    A PDF image may be scaled (always), cropped, translated, rotated in place
-    to an arbitrary angle (rarely) and skewed. Only equal area mappings can
-    be expressed, that is, it is not necessary to consider distortions where
-    the effective DPI varies with position.
-
-    To determine the image scale, transform an offset axis vector v0 (0, 0),
-    width-axis vector v0 (1, 0), height-axis vector vh (0, 1) with the matrix,
-    which gives the dimensions of the image in PDF units. From there we can
-    compare to actual image dimensions. PDF uses
-    row vector * matrix_tranposed unlike the traditional
-    matrix * column vector.
-
-    The offset, width and height vectors can be combined in a matrix and
-    multiplied by the transform matrix. Then we want to calculated
-        magnitude(width_vector - offset_vector)
-    and
-        magnitude(height_vector - offset_vector)
-
-    When the above is worked out algebraically, the effect of translation
-    cancels out, and the vector magnitudes become functions of the nonzero
-    transformation matrix indices. The results of the derivation are used
-    in this code.
-
-    pdfimages -list does calculate the DPI in some way that is not completely
-    naive, but it does not get the DPI of rotated images right, so cannot be
-    used anymore to validate this. Photoshop works, or using Acrobat to
-    rotate the image back to normal.
-
-    It does not matter if the image is partially cropped, or even out of the
-    /MediaBox.
-
-    """
-
-    a, b, c, d, _, _ = ctm_shorthand
-
-    # Calculate the width and height of the image in PDF units
-    image_drawn_width = hypot(a, b)
-    image_drawn_height = hypot(c, d)
-
-    # The scale of the image is pixels per PDF unit (1/72")
-    scale_w = image_size[0] / image_drawn_width
-    scale_h = image_size[1] / image_drawn_height
-
-    # DPI = scale * 72
-    dpi_w = scale_w * 72.0
-    dpi_h = scale_h * 72.0
-
-    return (dpi_w, dpi_h)
-
-
-def _find_inline_images(contentsinfo):
-    "Find inline images in the contentstream"
-
-    for n, inline in enumerate(contentsinfo.inline_images):
-        image = {}
-        image['name'] = str('inline-%02d' % n)
-        image['width'] = inline.settings['/W']
-        image['height'] = inline.settings['/H']
-        if '/BPC' in inline.settings:
-            image['bpc'] = inline.settings['/BPC']
-        else:
-            image['bpc'] = 8
-        if '/CS' in inline.settings:
-            image['color'] = FRIENDLY_COLORSPACE.get(inline.settings['/CS'], '-')
-        else:
-            image['color'] = '-'
-        image['comp'] = FRIENDLY_COMP.get(image['color'], '?')
-        if '/F' in inline.settings:
-            filter_ = inline.settings['/F']
-            if isinstance(filter_, pypdf.generic.ArrayObject):
-                filter_ = filter_[0]
-            image['enc'] = FRIENDLY_ENCODING.get(filter_, 'image')
-        else:
-            image['enc'] = 'image'
-
-        dpi_w, dpi_h = _get_dpi(
-            inline.shorthand, (image['width'], image['height']))
-        image['dpi_w'], image['dpi_h'] = Decimal(dpi_w), Decimal(dpi_h)
-        yield image
-
-
-def _image_xobjects(container):
-    """Search for all XObject-based images in the container
-
-    Usually the container is a page, but it could also be a Form XObject
-    that contains images. Filter out the Form XObjects which are dealt with
-    elsewhere.
-
-    Generate a sequence of tuples (image, xobj container), where container,
-    where xobj is the name of the object and image is the object itself,
-    since the object does not know its own name.
-
-    """
-
-    if '/Resources' not in container:
-        return
-    resources = container['/Resources']
-    if '/XObject' not in resources:
-        return
-    for xobj in resources['/XObject']:
-        candidate = resources['/XObject'][xobj]
-        if candidate['/Subtype'] == '/Image':
-            image = candidate
-            yield (image, xobj)
-
-
-def _find_regular_images(container, contentsinfo):
-    """Find images stored in the container's /Resources /XObject
-
-    Usually the container is a page, but it could also be a Form XObject
-    that contains images.
-
-    Generates images with their DPI at time of drawing.
-
-    """
-
-    for pdfimage, xobj in _image_xobjects(container):
-        image = {}
-        image['name'] = xobj
-        image['width'] = pdfimage['/Width']
-        image['height'] = pdfimage['/Height']
-        if '/BitsPerComponent' in pdfimage:
-            image['bpc'] = pdfimage['/BitsPerComponent']
-        else:
-            image['bpc'] = 8
-
-        # Fixme: this is incorrectly treats explicit masks as stencil masks,
-        # but good enough for now. Explicit masks have /ImageMask true but are
-        # never called for in content stream, instead are drawn as a /Mask on
-        # other images. For our purposes finding out the details of /Mask
-        # will seldom matter.
-        if '/ImageMask' in pdfimage:
-            image['type'] = 'stencil' if pdfimage['/ImageMask'].value \
-                            else 'image'
-        else:
-            image['type'] = 'image'
-        if '/Filter' in pdfimage:
-            filter_ = pdfimage['/Filter']
-            if isinstance(filter_, pypdf.generic.ArrayObject):
-                filter_ = filter_[0]
-            image['enc'] = FRIENDLY_ENCODING.get(filter_, 'image')
-        else:
-            image['enc'] = 'image'
-        if '/ColorSpace' in pdfimage:
-            cs = pdfimage['/ColorSpace']
-            if isinstance(cs, pypdf.generic.ArrayObject):
-                cs = cs[0]
-            image['color'] = FRIENDLY_COLORSPACE.get(cs, '-')
-        else:
-            image['color'] = 'jpx' if image['enc'] == 'jpx' else '?'
-
-        image['comp'] = FRIENDLY_COMP.get(image['color'], '?')
-
-        # Bit of a hack... infer grayscale if component count is uncertain
-        # but encoding must be monochrome. This happens if a monochrome image
-        # has an ICC profile attached. Better solution would be to examine
-        # the ICC profile.
-        if image['comp'] == '?' and image['enc'] in ('ccitt', 'jbig2'):
-            image['comp'] = FRIENDLY_COMP['gray']
-
-        image['dpi_w'] = image['dpi_h'] = 0
-
-        for xobj in contentsinfo.xobject_settings:
-            # Loop in case the same image is display multiple times on a page
-            if xobj.name != image['name']:
-                continue
-
-            if xobj.stack_depth == 0 and _is_unit_square(xobj.shorthand):
-                # At least one PDF in the wild (and test suite) draws an image
-                # when the graphics stack depth is 0, meaning that the image
-                # gets drawn into a square of 1x1 PDF units (or 1/72",
-                # or 0.35 mm).  The equivalent DPI will be >100,000.  Exclude
-                # these from our DPI calculation for the page.
-                continue
-
-            dpi_w, dpi_h = _get_dpi(
-                xobj.shorthand, (image['width'], image['height']))
-
-            # When image is used multiple times take the highest DPI it is
-            # rendered at
-            image['dpi_w'] = max(dpi_w, image.get('dpi_w', 0))
-            image['dpi_h'] = max(dpi_h, image.get('dpi_h', 0))
-
-        DPI_PREC = Decimal('1.000')
-        dpi = Decimal(image['dpi_w'] * image['dpi_h']).sqrt()
-        image['dpi_w'] = Decimal(image['dpi_w']).quantize(DPI_PREC)
-        image['dpi_h'] = Decimal(image['dpi_h']).quantize(DPI_PREC)
-        image['dpi'] = dpi.quantize(DPI_PREC)
-        yield image
-
-
-def _find_form_xobject_images(pdf, container, contentsinfo):
-    """Find any images that are in Form XObjects in the container
-
-    The container may be a page, or a parent Form XObject.
-
-    """
-    if '/Resources' not in container:
-        return
-    resources = container['/Resources']
-    if '/XObject' not in resources:
-        return
-    for xobj in resources['/XObject']:
-        candidate = resources['/XObject'][xobj]
-        if candidate['/Subtype'] != '/Form':
-            continue
-
-        form_xobject = candidate
-        for settings in contentsinfo.xobject_settings:
-            if settings.name != xobj:
-                continue
-
-            # Find images once for each time this Form XObject is drawn.
-            # This could be optimized to cache the multiple drawing events
-            # but in practice both Form XObjects and multiple drawing of the
-            # same object are both very rare.
-            ctm_shorthand = settings.shorthand
-            yield from _find_images(pdf, form_xobject, ctm_shorthand)
-
-
-def _find_images(pdf, container, shorthand=None):
-    """Find all individual instances of images drawn in the container
-
-    Usually the container is a page, but it may also be a Form XObject.
-
-    On a typical page images are stored inline or as regular images
-    in an XObject.
-
-    Form XObjects may include inline images, XObject images,
-    and recursively, other Form XObjects; and also vector drawing commands.
-
-    Every instance of an image being drawn somewhere is flattened and
-    treated as a unique image, since if the same image is drawn multiple times
-    on one page it may be drawn at differing resolutions, and our objective
-    is to find the resolution at which the page can be rastered without
-    downsampling.
-
-    """
-
-    if container.get('/Type') == '/Page' and '/Contents' in container:
-        # For a /Page the content stream is attached to the page's /Contents
-        page = container
-        contentstream = pypdf.pdf.ContentStream(page.getContents(), pdf)
-        initial_shorthand = shorthand or UNIT_SQUARE
-    elif container.get('/Type') == '/XObject' and \
-            container['/Subtype'] == '/Form':
-        # For a Form XObject that content stream is attached to the XObject
-        contentstream = pypdf.pdf.ContentStream(container, pdf)
-
-        # Set the CTM to the state it was when the "Do" operator was
-        # encountered that is drawing this instance of the Form XObject
-        ctm = _matrix_from_shorthand(shorthand or UNIT_SQUARE)
-
-        # A Form XObject may provide its own matrix to map form space into
-        # user space. Get this if one exists
-        form_matrix = _matrix_from_shorthand(
-                container.get('/Matrix', UNIT_SQUARE))
-
-        # Concatenate form matrix with CTM to ensure CTM is correct for
-        # drawing this instance of the XObject
-        ctm = matrix_mult(form_matrix, ctm)
-        initial_shorthand = _shorthand_from_matrix(ctm)
-    else:
-        return
-
-    contentsinfo = _interpret_contents(contentstream, initial_shorthand)
-
-    yield from _find_inline_images(contentsinfo)
-    yield from _find_regular_images(container, contentsinfo)
-    yield from _find_form_xobject_images(pdf, container, contentsinfo)
-
-
-def _page_has_text(pdf, page):
-    if not '/Contents' in page:
-        return False
-
-    # Simple test
-    text = page.extractText()
-    if text.strip() != '':
-        return True
-
-    # More nuanced test to deal with quirks of Tesseract PDF generation
-    # Check if there's a Glyphless font
-    try:
-        font = page['/Resources']['/Font']
-    except KeyError:
-        pass
-    else:
-        font_objects = list(font.keys())
-        for font_object in font_objects:
-            basefont = font[font_object]['/BaseFont']
-            if basefont.endswith('GlyphLessFont'):
-                return True
-
-    return False
-
-
-def _pdf_get_pageinfo(infile, pageno: int):
-    pageinfo = {}
-    pageinfo['pageno'] = pageno
-    pageinfo['images'] = []
-
-    pdf = pypdf.PdfFileReader(infile)
-    page = pdf.pages[pageno]
-
-    pageinfo['has_text'] = _page_has_text(pdf, page)
-
-    width_pt = page.mediaBox.getWidth()
-    height_pt = page.mediaBox.getHeight()
-    pageinfo['width_inches'] = width_pt / Decimal(72.0)
-    pageinfo['height_inches'] = height_pt / Decimal(72.0)
-
-    try:
-        pageinfo['rotate'] = int(page['/Rotate'])
-    except KeyError:
-        pageinfo['rotate'] = 0
-
-    pageinfo['images'] = [im for im in
-                          _find_images(pdf, page)]
-    if pageinfo['images']:
-        xres = max(image['dpi_w'] for image in pageinfo['images'])
-        yres = max(image['dpi_h'] for image in pageinfo['images'])
-        pageinfo['xres'], pageinfo['yres'] = xres, yres
-        pageinfo['width_pixels'] = \
-            int(round(xres * pageinfo['width_inches']))
-        pageinfo['height_pixels'] = \
-            int(round(yres * pageinfo['height_inches']))
-
-    return pageinfo
-
-
-def pdf_get_all_pageinfo(infile):
-    pdf = pypdf.PdfFileReader(infile)
-    return [_pdf_get_pageinfo(infile, n) for n in range(pdf.numPages)]
-
-
-def main():
-    import argparse
-    parser = argparse.ArgumentParser()
-    parser.add_argument('infile')
-    args = parser.parse_args()
-    info = pdf_get_all_pageinfo(args.infile)
-    from pprint import pprint
-    pprint(info)
-
-
-if __name__ == '__main__':
-    main()

ocrmypdf/pdfa.py

@@ -1,163 +0,0 @@
-#!/usr/bin/env python3
-# © 2015 James R. Barlow: github.com/jbarlow83
-#
-# Generate a PDFA_def.ps file for Ghostscript >= 9.14
-
-from string import Template
-import codecs
-import pkg_resources
-import PyPDF2 as pypdf
-
-ICC_PROFILE_RELPATH = 'data/sRGB.icc'
-
-SRGB_ICC_PROFILE = pkg_resources.resource_filename(
-    'ocrmypdf', ICC_PROFILE_RELPATH)
-
-
-# This is a template written in PostScript which is needed to create PDF/A
-# files, from the Ghostscript documentation. Lines beginning with % are
-# comments. Python substitution variables have a '$' prefix.
-pdfa_def_template = u"""%!
-% This is derived from Ghostscript's template for creating a PDF/A document.
-% This is a small PostScript program that includes some necessary information
-% to create a PDF/A compliant file.
-
-% Define entries in the document Info dictionary :
-/ICCProfile ($icc_profile)
-def
-
-[$docinfo
-  /DOCINFO pdfmark
-
-% Define an ICC profile :
-
-[/_objdef {icc_PDFA} /type /stream /OBJ pdfmark
-[{icc_PDFA}
-<<
-  /N currentpagedevice /ProcessColorModel known {
-    currentpagedevice /ProcessColorModel get dup /DeviceGray eq
-    {pop 1} {
-      /DeviceRGB eq
-      {3}{4} ifelse
-    } ifelse
-  } {
-    (ERROR, unable to determine ProcessColorModel) == flush
-  } ifelse
->> /PUT pdfmark
-[{icc_PDFA} ICCProfile (r) file /PUT pdfmark
-
-% Define the output intent dictionary :
-
-[/_objdef {OutputIntent_PDFA} /type /dict /OBJ pdfmark
-[{OutputIntent_PDFA} <<
-  /Type /OutputIntent             % Must be so (the standard requires).
-  /S /GTS_PDFA1                   % Must be so (the standard requires).
-  /DestOutputProfile {icc_PDFA}            % Must be so (see above).
-  /OutputConditionIdentifier ($icc_identifier)
->> /PUT pdfmark
-[{Catalog} <</OutputIntents [ {OutputIntent_PDFA} ]>> /PUT pdfmark
-"""
-
-
-def encode_text_string(s: str) -> str:
-    '''Encode text string to hex string for use in a PDF
-
-    From PDF 32000-1:2008 a string object may be included in hexademical form
-    if it is enclosed in angle brackets.  For general Unicode the string should
-    be UTF-16 (big endian) with byte order marks.  Many strings including all
-    ASCII strings could be encoded as PdfDocEncoding literals provided
-    that certain Postscript sequences are escaped.  But it's far simpler to
-    encode everything as UTF-16.
-    '''
-
-    # Sometimes lazy C programmers leave their NULs at the end of strings they
-    # insert into PDFs
-    # tests/resources/aspect.pdf is one example (created by ImageMagick)
-    s = s.replace('\x00', '')
-
-    if s == '':
-        return ''
-
-    utf16_bytes = s.encode('utf-16be')
-    ascii_hex_bytes = codecs.encode(b'\xfe\xff' + utf16_bytes, 'hex')
-    ascii_hex_str = ascii_hex_bytes.decode('ascii').lower()
-    return ascii_hex_str
-
-
-def _get_pdfa_def(icc_profile, icc_identifier, pdfmark):
-    # Ghostscript <= 9.21 has a bug where null entries in DOCINFO might produce
-    # ERROR: VMerror (-25) on closing pdfwrite device.
-    # https://bugs.ghostscript.com/show_bug.cgi?id=697684
-    # Work around this by only adding keys that have a nontrivial value
-    docinfo_keys = ('/Title', '/Author', '/Subject', '/Creator', '/Keywords')
-    docinfo_line_template = '  {key} <{value}>'
-
-    def docinfo_gen():
-        for key in docinfo_keys:
-            if key in pdfmark and pdfmark[key].strip() != '':
-                line = docinfo_line_template.format(
-                    key=key, value=encode_text_string(pdfmark[key]))
-                yield line
-
-    docinfo = '\n'.join(docinfo_gen())
-
-    t = Template(pdfa_def_template)
-    result = t.substitute(icc_profile=icc_profile,
-                          icc_identifier=icc_identifier,
-                          docinfo=docinfo)
-    return result
-
-
-def generate_pdfa_ps(target_filename, pdfmark, icc='sRGB'):
-    if icc == 'sRGB':
-        icc_profile = SRGB_ICC_PROFILE
-    else:
-        raise NotImplementedError("Only supporting sRGB")
-
-    ps = _get_pdfa_def(icc_profile, icc, pdfmark)
-
-    # We should have encoded everything to pure ASCII by this point, and
-    # to be safe, only allow ASCII in PostScript
-    with open(target_filename, 'w', encoding='ascii') as f:
-        f.write(ps)
-
-
-def file_claims_pdfa(filename):
-    """Determines if the file claims to be PDF/A compliant
-
-    Checking if a file is a truly compliant PDF/A is a massive undertaking
-    that no open source tool does properly.  Some commercial tools are
-    generally reliable (Acrobat).
-
-    This checks if the XMP metadata contains a PDF/A marker.
-    """
-
-    pdf = pypdf.PdfFileReader(filename)
-    xmp = pdf.getXmpMetadata()
-
-    try:
-        pdfa_nodes = xmp.getNodesInNamespace(
-            aboutUri='',
-            namespace='http://www.aiim.org/pdfa/ns/id/')
-    except AttributeError:
-        return {'pass': False, 'output': 'pdf',
-                'conformance': 'No XMP metadata'}
-
-    pdfa_dict = {attr.localName: attr.value for attr in pdfa_nodes}
-    if not pdfa_dict:
-        return {'pass': False, 'output': 'pdf',
-                'conformance': 'No XMP metadata'}
-
-    part_conformance = pdfa_dict['part'] + pdfa_dict['conformance']
-    valid_part_conforms = {'1A', '1B', '2A', '2B', '2U', '3A', '3B', '3U'}
-
-    conformance = 'PDF/A-{}'.format(
-        part_conformance)
-
-    if part_conformance in valid_part_conforms:
-        pdfa_dict['pass'] = True
-        pdfa_dict['output'] = 'pdfa'
-    pdfa_dict['conformance'] = conformance
-
-    return pdfa_dict
-

pyproject.toml

@@ -0,0 +1,32 @@
+[build-system]
+requires = [
+  "setuptools >= 30.3.0",
+  "wheel",
+  "cffi",
+  "setuptools_scm",
+  "setuptools_scm_git_archive"
+]
+build-backend = "setuptools.build_meta"
+
+[tool.black]
+line-length = 88
+target-version = ["py36", "py37", "py38"]
+skip-string-normalization = true
+include = '\.pyi?$'
+exclude = '''
+/(
+    \.eggs
+  | \.git
+  | \.hg
+  | \.mypy_cache
+  | \.tox
+  | \.venv
+  | _build
+  | buck-out
+  | build
+  | dist
+  | docs
+  | misc
+  | \.egg-info
+)/
+'''

requirements/dev.txt

@@ -0,0 +1,2 @@
+twine >= 1.8.1
+coverage >= 4.5

requirements/main.txt

@@ -1,9 +1,10 @@
 # requirements.txt can be used to replicate the developer's build environment
 # setup.py lists a separate set of requirements that are looser to simplify
 # installation
-ruffus == 2.6.3
-Pillow == 4.1.1
-reportlab == 3.4.0
-PyPDF2 == 1.26.0
-img2pdf == 0.2.3
-cffi == 1.10.0
+cffi == 1.13.2
+img2pdf == 0.3.3
+pdfminer.six == 20191110
+pikepdf == 1.7.0
+Pillow >= 6.2.0
+reportlab == 3.5.32
+tqdm == 4.37.0

requirements/test.txt

@@ -0,0 +1,8 @@
+pytest >= 5.0.0
+pytest-helpers-namespace >= 2019.1.8
+pytest-xdist >= 1.29.0  # For DumpError fix
+pytest-cov >= 2.6.1
+python-xmp-toolkit == 2.0.1  # requires apt-get install libexempi3
+                     # or brew install exempi
+PyPDF2 >= 1.26.0
+#PyMuPDF == 1.13.4    # optional

requirements/webservice.txt

@@ -0,0 +1 @@
+Flask >= 1, < 2

setup.cfg

@@ -11,4 +11,17 @@ ignore =
 [tool:pytest]
 norecursedirs = lib .pc .git output cache resources
 testpaths = tests
-addopts = -n auto
+filterwarnings =
+	ignore:.*XMLParser.*:DeprecationWarning
+markers =
+	slow
+
+[isort]
+multi_line_output=3
+include_trailing_comma=True
+force_grid_wrap=0
+use_parentheses=True
+line_length=88
+
+[metadata]
+license_file = LICENSE

setup.py

@@ -1,208 +1,80 @@
 #!/usr/bin/env python3
 # -*- coding: utf-8 -*-
 # © 2015 James R. Barlow: github.com/jbarlow83
+#
+# This file is part of OCRmyPDF.
+#
+# OCRmyPDF is free software: you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# OCRmyPDF is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
 
 from __future__ import print_function, unicode_literals
 
 import sys
-if sys.version_info < (3, 5):
-    print("Python 3.5 or newer is required", file=sys.stderr)
+
+if sys.version_info < (3, 6):
+    print("Python 3.6 or newer is required", file=sys.stderr)
     sys.exit(1)
 
-from setuptools import setup, find_packages  # nopep8
-from subprocess import STDOUT, check_output, CalledProcessError  # nopep8
-from collections.abc import Mapping  # nopep8
-import re  # nopep8
+from setuptools import setup, find_packages
 
-
-missing_program = '''
-The program '{program}' could not be executed or was not found on your
-system PATH.
-'''
-
-unknown_version = '''
-OCRmyPDF requires '{program}' {need_version} or higher.  Your system has
-'{program}' but we cannot tell what version is installed.  Contact the
-package maintainer.
-'''
-
-old_version = '''
-OCRmyPDF requires '{program}' {need_version} or higher.  Your system appears
-to have {found_version}.  Please update this program.
-'''
-
-okay_its_optional = '''
-This program is OPTIONAL, so installation of OCRmyPDF can proceed, but
-some functionality may be missing.
-'''
-
-not_okay_its_required = '''
-This program is REQUIRED for OCRmyPDF to work.  Installation will abort.
-'''
-
-osx_install_advice = '''
-If you have homebrew installed, try these command to install the missing
-packages:
-    brew update
-    brew upgrade
-    brew install {package}
-'''
-
-linux_install_advice = '''
-On systems with the aptitude package manager (Debian, Ubuntu), try these
-commands:
-    sudo apt-get update
-    sudo apt-get install {package}
-
-On RPM-based systems (Red Hat, Fedora), search for instructions on
-installing the RPM for {program}.
-'''
-
-
-def get_platform():
-    if sys.platform.startswith('freebsd'):
-        return 'freebsd'
-    elif sys.platform.startswith('linux'):
-        return 'linux'
-    return sys.platform
-
-
-def _error_trailer(program, package, optional, **kwargs):
-    if optional:
-        print(okay_its_optional.format(**locals()), file=sys.stderr)
-    else:
-        print(not_okay_its_required.format(**locals()), file=sys.stderr)
-
-    if isinstance(package, Mapping):
-        package = package[get_platform()]
-
-    if get_platform() == 'darwin':
-        print(osx_install_advice.format(**locals()), file=sys.stderr)
-    elif get_platform() == 'linux':
-        print(linux_install_advice.format(**locals()), file=sys.stderr)
-
-
-def error_missing_program(
-        program,
-        package,
-        optional
-        ):
-    print(missing_program.format(**locals()), file=sys.stderr)
-    _error_trailer(**locals())
-
-
-def error_unknown_version(
-        program,
-        package,
-        optional,
-        need_version
-        ):
-    print(unknown_version.format(**locals()), file=sys.stderr)
-    _error_trailer(**locals())
-
-
-def error_old_version(
-        program,
-        package,
-        optional,
-        need_version,
-        found_version
-        ):
-    print(old_version.format(**locals()), file=sys.stderr)
-    _error_trailer(**locals())
-
-
-def check_external_program(
-        program,
-        need_version,
-        package,
-        version_check_args=['--version'],
-        version_scrape_regex=re.compile(r'(\d+\.\d+(?:\.\d+)?)'),
-        optional=False):
-
-    print('Checking for {program} >= {need_version}...'.format(
-            program=program, need_version=need_version))
-    try:
-        result = check_output(
-                [program] + version_check_args,
-                universal_newlines=True, stderr=STDOUT)
-    except (CalledProcessError, FileNotFoundError):
-        error_missing_program(program, package, optional)
-        if not optional:
-            sys.exit(1)
-        print('Continuing install without {program}'.format(program=program))
-        return
-
-    try:
-        found_version = version_scrape_regex.search(result).group(1)
-    except AttributeError:
-        error_unknown_version(program, package, optional, need_version)
-        sys.exit(1)
-
-    if found_version < need_version:
-        error_old_version(program, package, optional, need_version,
-                          found_version)
-
-    print('Found {program} {found_version}'.format(
-            program=program, found_version=found_version))
+# pylint: disable=w0613
 
 
 command = next((arg for arg in sys.argv[1:] if not arg.startswith('-')), '')
-forced = ('--force' in sys.argv)
-
-
-if not forced and command.startswith('install') or \
-        command in ['check', 'test', 'nosetests', 'easy_install']:
-    check_external_program(
-        program='tesseract',
-        need_version='3.04',  # using backport for Travis CI
-        package={'darwin': 'tesseract', 'linux': 'tesseract-ocr'}
-    )
-    check_external_program(
-        program='gs',
-        need_version='9.15',  # limited by Travis CI / Ubuntu 14.04 backports
-        package='ghostscript'
-    )
-    check_external_program(
-        program='unpaper',
-        need_version='6.1',   # latest sane version
-        package='unpaper',
-        optional=True
-    )
-    check_external_program(
-        program='qpdf',
-        need_version='5.1.1',   # limited by Travis CI / Ubuntu 14.04 backports
-        package='qpdf',
-        version_check_args=['--version']
-    )
-else:
-    print('Skipping external program tests because of --force')
+if command.startswith('install') or command in [
+    'check',
+    'test',
+    'nosetests',
+    'easy_install',
+]:
+    forced = '--force' in sys.argv
+    if forced:
+        print("The argument --force is deprecated. Please discontinue use.")
 
 
 if 'upload' in sys.argv[1:]:
     print('Use twine to upload the package - setup.py upload is insecure')
     sys.exit(1)
 
-tests_require = open('test_requirements.txt').read().splitlines()
+tests_require = open('requirements/test.txt', encoding='utf-8').read().splitlines()
+
+
+def readme():
+    with open('README.md', encoding='utf-8') as f:
+        return f.read()
+
 
 setup(
     name='ocrmypdf',
     description='OCRmyPDF adds an OCR text layer to scanned PDF files, allowing them to be searched',
+    long_description=readme(),
+    long_description_content_type='text/markdown',
     url='https://github.com/jbarlow83/OCRmyPDF',
     author='James R. Barlow',
     author_email='jim@purplerock.ca',
-    license='MIT',
-    packages=find_packages(exclude=["tests", "tests.*"]),
+    packages=find_packages('src', exclude=["tests", "tests.*"]),
+    package_dir={'': 'src'},
     keywords=['PDF', 'OCR', 'optical character recognition', 'PDF/A', 'scanning'],
     classifiers=[
-        "Programming Language :: Python :: 3.5",
         "Programming Language :: Python :: 3.6",
+        "Programming Language :: Python :: 3.7",
+        "Programming Language :: Python :: 3.8",
         "Development Status :: 5 - Production/Stable",
         "Environment :: Console",
         "Intended Audience :: End Users/Desktop",
         "Intended Audience :: Science/Research",
         "Intended Audience :: System Administrators",
-        "License :: OSI Approved :: MIT License",
+        "License :: OSI Approved :: GNU General Public License v3 (GPLv3)",
         "Operating System :: MacOS :: MacOS X",
         "Operating System :: POSIX",
         "Operating System :: POSIX :: BSD",
@@ -210,29 +82,34 @@ setup(
         "Topic :: Scientific/Engineering :: Image Recognition",
         "Topic :: Text Processing :: Indexing",
         "Topic :: Text Processing :: Linguistic",
-        ],
-    setup_requires=[
-        'setuptools_scm',       # so that version will work
-        'cffi>=1.9.1'           # to build the leptonica module
+    ],
+    python_requires=' >= 3.6',
+    setup_requires=[  # can be removed whenever we can drop pip 9 support
+        'cffi >= 1.9.1',  # to build the leptonica module
+        'pytest-runner',  # to enable python setup.py test
+        'setuptools_scm',  # so that version will work
+        'setuptools_scm_git_archive',  # enable version from github tarballs
     ],
     use_scm_version={'version_scheme': 'post-release'},
-    cffi_modules=[
-        'ocrmypdf/lib/compile_leptonica.py:ffibuilder'
-    ],
+    cffi_modules=['src/ocrmypdf/lib/compile_leptonica.py:ffibuilder'],
     install_requires=[
-        'ruffus==2.6.3',        # pinned - ocrmypdf implements a 2.6.3 workaround
-        'Pillow>=4.0.0',        # Pillow < 4 has BytesIO/TIFF bug w/img2pdf 0.2.3
-        'reportlab>=3.3.0',     # oldest released version with sane image handling
-        'PyPDF2>=1.26',         # pure Python, so track HEAD closely
-        'img2pdf>=0.2.3',       # pure Python, so track HEAD closely
-        'cffi>=1.9.1'           # must be a setup and install requirement
+        'chardet >= 3.0.4, < 4',  # unlisted requirement of pdfminer.six 20181108
+        'cffi >= 1.9.1',  # must be a setup and install requirement
+        'img2pdf >= 0.3.0, < 0.4',  # pure Python, so track HEAD closely
+        'pdfminer.six >= 20181108, <= 20191110',
+        'pikepdf >= 1.7.0, < 2',
+        'Pillow >= 6.2.0',
+        'reportlab >= 3.3.0',  # oldest released version with sane image handling
+        'tqdm >= 4',
     ],
     tests_require=tests_require,
-    entry_points={
-        'console_scripts': [
-            'ocrmypdf = ocrmypdf.__main__:run_pipeline'
-        ],
-    },
+    entry_points={'console_scripts': ['ocrmypdf = ocrmypdf.__main__:run']},
     package_data={'ocrmypdf': ['data/sRGB.icc']},
     include_package_data=True,
-    zip_safe=False)
+    zip_safe=False,
+    project_urls={
+        'Documentation': 'https://ocrmypdf.readthedocs.io/',
+        'Source': 'https://github.com/jbarlow83/ocrmypdf',
+        'Tracker': 'https://github.com/jbarlow83/ocrmypdf/issues',
+    },
+)

src/ocrmypdf/__init__.py

@@ -0,0 +1,34 @@
+# © 2017 James R. Barlow: github.com/jbarlow83
+#
+# This file is part of OCRmyPDF.
+#
+# OCRmyPDF is free software: you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# OCRmyPDF is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
+
+from . import helpers, hocrtransform, leptonica, pdfa, pdfinfo
+from ._version import PROGRAM_NAME, __version__
+from .api import Verbosity, configure_logging, ocr
+from .exceptions import (
+    BadArgsError,
+    DpiError,
+    EncryptedPdfError,
+    ExitCode,
+    InputFileError,
+    MissingDependencyError,
+    OutputFileAccessError,
+    PdfMergeFailedError,
+    PriorOcrFoundError,
+    SubprocessOutputError,
+    TesseractConfigError,
+    UnsupportedImageFormatError,
+)

src/ocrmypdf/__main__.py

@@ -0,0 +1,69 @@
+#!/usr/bin/env python3
+# © 2015-19 James R. Barlow: github.com/jbarlow83
+#
+# This file is part of OCRmyPDF.
+#
+# OCRmyPDF is free software: you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# OCRmyPDF is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
+
+import logging
+import os
+import sys
+
+from . import __version__
+from ._jobcontext import make_logger
+from ._sync import run_pipeline
+from ._validation import check_closed_streams, check_options
+from .api import Verbosity, configure_logging
+from .cli import parser
+from .exceptions import BadArgsError, ExitCode, MissingDependencyError
+
+
+def run(args=None):
+    options = parser.parse_args(args=args)
+
+    if not check_closed_streams(options):
+        return ExitCode.bad_args
+
+    if hasattr(os, 'nice'):
+        os.nice(5)
+
+    verbosity = options.verbose
+    if not os.isatty(sys.stderr.fileno()):
+        options.progress_bar = False
+    if options.quiet:
+        verbosity = Verbosity.quiet
+        options.progress_bar = False
+    configure_logging(
+        verbosity, progress_bar_friendly=options.progress_bar, manage_root_logger=True
+    )
+    log = make_logger('ocrmypdf')
+    log.debug('ocrmypdf ' + __version__)
+    try:
+        check_options(options)
+    except ValueError as e:
+        log.error(e)
+        return ExitCode.bad_args
+    except BadArgsError as e:
+        log.error(e)
+        return e.exit_code
+    except MissingDependencyError as e:
+        log.error(e)
+        return ExitCode.missing_dependency
+
+    result = run_pipeline(options=options)
+    return result
+
+
+if __name__ == '__main__':
+    sys.exit(run())

src/ocrmypdf/_graft.py

@@ -0,0 +1,284 @@
+# © 2018 James R. Barlow: github.com/jbarlow83
+#
+# This file is part of OCRmyPDF.
+#
+# OCRmyPDF is free software: you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# OCRmyPDF is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
+
+import os
+from contextlib import suppress
+from pathlib import Path
+
+import pikepdf
+
+MAX_REPLACE_PAGES = int(os.environ.get('_OCRMYPDF_MAX_REPLACE_PAGES', 100))
+
+
+def _update_page_resources(*, page, font, font_key, procset):
+    """Update this page's fonts with a reference to the Glyphless font"""
+
+    if '/Resources' not in page:
+        page['/Resources'] = pikepdf.Dictionary({})
+    resources = page['/Resources']
+    try:
+        fonts = resources['/Font']
+    except KeyError:
+        fonts = pikepdf.Dictionary({})
+    if font_key is not None and font_key not in fonts:
+        fonts[font_key] = font
+    resources['/Font'] = fonts
+
+    # Reassign /ProcSet to one that just lists everything - ProcSet is
+    # obsolete and doesn't matter but recommended for old viewer support
+    resources['/ProcSet'] = procset
+
+
+def strip_invisible_text(pdf, page):
+    stream = []
+    in_text_obj = False
+    render_mode = 0
+    text_objects = []
+
+    page.page_contents_coalesce()
+    for operands, operator in pikepdf.parse_content_stream(page, ''):
+        if not in_text_obj:
+            if operator == pikepdf.Operator('BT'):
+                in_text_obj = True
+                render_mode = 0
+                text_objects.append((operands, operator))
+            else:
+                stream.append((operands, operator))
+        else:
+            if operator == pikepdf.Operator('Tr'):
+                render_mode = operands[0]
+            text_objects.append((operands, operator))
+            if operator == pikepdf.Operator('ET'):
+                in_text_obj = False
+                if render_mode != 3:
+                    stream.extend(text_objects)
+                text_objects.clear()
+
+    def convert(op):
+        try:
+            return op.unparse()
+        except AttributeError:
+            return str(op).encode('ascii')
+
+    lines = []
+
+    for operands, operator in stream:
+        if operator == pikepdf.Operator('INLINE IMAGE'):
+            iim = operands[0]
+            line = iim.unparse()
+        else:
+            line = b' '.join(convert(op) for op in operands) + b' ' + operator.unparse()
+        lines.append(line)
+
+    content_stream = b'\n'.join(lines)
+    page.Contents = pikepdf.Stream(pdf, content_stream)
+
+
+def _graft_text_layer(
+    *, pdf_base, page_num, text, font, font_key, procset, rotation, strip_old_text, log
+):
+    """Insert the text layer from text page 0 on to pdf_base at page_num"""
+
+    log.debug("Grafting")
+    if Path(text).stat().st_size == 0:
+        return
+
+    # This is a pointer indicating a specific page in the base file
+    pdf_text = pikepdf.open(text)
+    pdf_text_contents = pdf_text.pages[0].Contents.read_bytes()
+
+    base_page = pdf_base.pages.p(page_num)
+
+    # The text page always will be oriented up by this stage but the original
+    # content may have a rotation applied. Wrap the text stream with a rotation
+    # so it will be oriented the same way as the rest of the page content.
+    # (Previous versions OCRmyPDF rotated the content layer to match the text.)
+    mediabox = [float(pdf_text.pages[0].MediaBox[v]) for v in range(4)]
+    wt, ht = mediabox[2] - mediabox[0], mediabox[3] - mediabox[1]
+
+    mediabox = [float(base_page.MediaBox[v]) for v in range(4)]
+    wp, hp = mediabox[2] - mediabox[0], mediabox[3] - mediabox[1]
+
+    translate = pikepdf.PdfMatrix().translated(-wt / 2, -ht / 2)
+    untranslate = pikepdf.PdfMatrix().translated(wp / 2, hp / 2)
+    corner = pikepdf.PdfMatrix().translated(mediabox[0], mediabox[1])
+    # -rotation because the input is a clockwise angle and this formula
+    # uses CCW
+    rotation = -rotation % 360
+    rotate = pikepdf.PdfMatrix().rotated(rotation)
+
+    # Because of rounding of DPI, we might get a text layer that is not
+    # identically sized to the target page. Scale to adjust. Normally this
+    # is within 0.998.
+    if rotation in (90, 270):
+        wt, ht = ht, wt
+    scale_x = wp / wt
+    scale_y = hp / ht
+
+    # log.debug('%r', scale_x, scale_y)
+    scale = pikepdf.PdfMatrix().scaled(scale_x, scale_y)
+
+    # Translate the text so it is centered at (0, 0), rotate it there, adjust
+    # for a size different between initial and text PDF, then untranslate, and
+    # finally move the lower left corner to match the mediabox
+    ctm = translate @ rotate @ scale @ untranslate @ corner
+
+    pdf_text_contents = b'q %s cm\n' % ctm.encode() + pdf_text_contents + b'\nQ\n'
+
+    new_text_layer = pikepdf.Stream(pdf_base, pdf_text_contents)
+
+    if strip_old_text:
+        strip_invisible_text(pdf_base, base_page)
+
+    base_page.page_contents_add(new_text_layer, prepend=True)
+
+    _update_page_resources(
+        page=base_page, font=font, font_key=font_key, procset=procset
+    )
+    pdf_text.close()
+
+
+def _find_font(text, pdf_base):
+    """Copy a font from the filename text into pdf_base"""
+
+    font, font_key = None, None
+    possible_font_names = ('/f-0-0', '/F1')
+    try:
+        with pikepdf.open(text) as pdf_text:
+            try:
+                pdf_text_fonts = pdf_text.pages[0].Resources.get('/Font', {})
+            except (AttributeError, IndexError, KeyError):
+                return None, None
+            for f in possible_font_names:
+                pdf_text_font = pdf_text_fonts.get(f, None)
+                if pdf_text_font is not None:
+                    font_key = f
+                    break
+            if pdf_text_font:
+                font = pdf_base.copy_foreign(pdf_text_font)
+            return font, font_key
+    except (FileNotFoundError, pikepdf.PdfError):
+        # PdfError occurs if a 0-length file is written e.g. due to OCR timeout
+        return None, None
+
+
+class OcrGrafter:
+    def __init__(self, context):
+        self.context = context
+        self.log = context.log
+        self.path_base = Path(context.origin).resolve()
+
+        self.pdf_base = pikepdf.open(self.path_base)
+        self.font, self.font_key = None, None
+
+        self.pdfinfo = context.pdfinfo
+        self.output_file = context.get_path('graft_layers.pdf')
+
+        self.procset = self.pdf_base.make_indirect(
+            pikepdf.Object.parse(b'[ /PDF /Text /ImageB /ImageC /ImageI ]')
+        )
+
+        self.emplacements = 1
+        self.interim_count = 0
+
+    def graft_page(self, page_result):
+        pageno, image, text, _sidecar, autorotate_correction = page_result
+        if text and not self.font:
+            self.font, self.font_key = _find_font(text, self.pdf_base)
+
+        emplaced_page = False
+        content_rotation = self.pdfinfo[pageno].rotation
+        path_image = Path(image).resolve() if image else None
+        if path_image is not None and path_image != self.path_base:
+            # We are updating the old page with a rasterized PDF of the new
+            # page (without changing objgen, to preserve references)
+            self.log.debug("Emplacement update")
+            with pikepdf.open(image) as pdf_image:
+                self.emplacements += 1
+                foreign_image_page = pdf_image.pages[0]
+                self.pdf_base.pages.append(foreign_image_page)
+                local_image_page = self.pdf_base.pages[-1]
+                self.pdf_base.pages[pageno].emplace(local_image_page)
+                del self.pdf_base.pages[-1]
+            emplaced_page = True
+
+        if emplaced_page:
+            content_rotation = autorotate_correction
+        text_rotation = autorotate_correction
+        text_misaligned = (text_rotation - content_rotation) % 360
+        self.log.debug(
+            f"Rotations for page {pageno}: [text, auto, misalign, content] = "
+            f"{text_rotation}, {autorotate_correction}, "
+            f"{text_misaligned}, {content_rotation}"
+        )
+
+        if text and self.font:
+            # Graft the text layer onto this page, whether new or old
+            strip_old = self.context.options.redo_ocr
+            _graft_text_layer(
+                pdf_base=self.pdf_base,
+                page_num=pageno + 1,
+                text=text,
+                font=self.font,
+                font_key=self.font_key,
+                rotation=text_misaligned,
+                procset=self.procset,
+                strip_old_text=strip_old,
+                log=self.log,
+            )
+
+        # Correct the rotation if applicable
+        self.pdf_base.pages[pageno].Rotate = (
+            content_rotation - autorotate_correction
+        ) % 360
+
+        if self.emplacements % MAX_REPLACE_PAGES == 0:
+            self.save_and_reload()
+
+    def save_and_reload(self):
+        # Periodically save and reload the Pdf object. This will keep a
+        # lid on our memory usage for very large files. Attach the font to
+        # page 1 even if page 1 doesn't use it, so we have a way to get it
+        # back.
+        page0 = self.pdf_base.pages[0]
+        _update_page_resources(
+            page=page0, font=self.font, font_key=self.font_key, procset=self.procset
+        )
+
+        # We cannot read and write the same file, that will corrupt it
+        # but we don't to keep more copies than we need to. Delete intermediates.
+        # {interim_count} is the opened file we were updateing
+        # {interim_count - 1} can be deleted
+        # {interim_count + 1} is the new file will produce and open
+        old_file = self.output_file + f'_working{self.interim_count - 1}.pdf'
+        if not self.context.options.keep_temporary_files:
+            with suppress(FileNotFoundError):
+                os.unlink(old_file)
+
+        next_file = self.output_file + f'_working{self.interim_count + 1}.pdf'
+        self.pdf_base.save(next_file)
+        self.pdf_base.close()
+
+        self.pdf_base = pikepdf.open(next_file)
+        self.procset = self.pdf_base.pages[0].Resources.ProcSet
+        self.font, self.font_key = None, None  # Ensure we reacquire this information
+        self.interim_count += 1
+
+    def finalize(self):
+        self.pdf_base.save(self.output_file)
+        self.pdf_base.close()
+        return self.output_file

src/ocrmypdf/_jobcontext.py

@@ -0,0 +1,124 @@
+# © 2018 James R. Barlow: github.com/jbarlow83
+#
+# This file is part of OCRmyPDF.
+#
+# OCRmyPDF is free software: you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# OCRmyPDF is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
+
+import logging
+import os
+import shutil
+import sys
+
+
+class PicklableLoggerMixin:
+    def __init__(self):
+        self._log = None
+
+    @property
+    def log(self):
+        if not self._log:
+            self._log = self.get_logger()
+        return self._log
+
+    def __getstate__(self):
+        # Python 3.6 is incapable of pickling a logger and marshalling it to another
+        # process (threading._RLock error), so we disconnect it before pickling,
+        # and create a new logger in the worker process.
+        state = self.__dict__.copy()
+        state['_log'] = None
+        return state
+
+
+class PDFContext(PicklableLoggerMixin):
+    """Holds our context for a particular run of the pipeline"""
+
+    def __init__(self, options, work_folder, origin, pdfinfo):
+        PicklableLoggerMixin.__init__(self)
+        self.options = options
+        self.work_folder = work_folder
+        self.origin = origin
+        self.pdfinfo = pdfinfo
+        if options:
+            self.name = os.path.basename(options.input_file)
+        else:
+            self.name = 'origin.pdf'
+        if self.name == '-':
+            self.name = 'stdin'
+
+    def get_logger(self):
+        return make_logger(self.options, filename=self.name)
+
+    def get_path(self, name):
+        return os.path.join(self.work_folder, name)
+
+    def get_page_contexts(self):
+        npages = len(self.pdfinfo)
+        for n in range(npages):
+            yield PageContext(self, n)
+
+
+class PageContext(PicklableLoggerMixin):
+    """Holds our context for a page
+
+    Must be pickable, so only store intrinsic/simple data elements
+    """
+
+    def __init__(self, pdf_context, pageno):
+        PicklableLoggerMixin.__init__(self)
+        self.work_folder = pdf_context.work_folder
+        self.origin = pdf_context.origin
+        self.options = pdf_context.options
+        self.name = pdf_context.name
+        self.pageno = pageno
+        self.pageinfo = pdf_context.pdfinfo[pageno]
+        self._log = None
+
+    def get_logger(self):
+        return make_logger(self.options, filename=self.name, page=self.pageno + 1)
+
+    def get_path(self, name):
+        return os.path.join(self.work_folder, "%06d_%s" % (self.pageno + 1, name))
+
+
+def cleanup_working_files(work_folder, options):
+    if options.keep_temporary_files:
+        print(f"Temporary working files retained at:\n{work_folder}", file=sys.stderr)
+    else:
+        shutil.rmtree(work_folder, ignore_errors=True)
+
+
+class LogNameAdapter(logging.LoggerAdapter):
+    def process(self, msg, kwargs):
+        # return '[%s] %s' % (self.extra['filename'], msg), kwargs
+        return '%s' % (msg,), kwargs
+
+
+class LogNamePageAdapter(logging.LoggerAdapter):
+    def process(self, msg, kwargs):
+        return (
+            #'[%s:%05u] %s' % (self.extra['filename'], self.extra['page'], msg),
+            '%4u: %s' % (self.extra['page'], msg),
+            kwargs,
+        )
+
+
+def make_logger(options=None, prefix='ocrmypdf', filename=None, page=None):
+    log = logging.getLogger(prefix)
+    if filename and page:
+        adapter = LogNamePageAdapter(log, dict(filename=filename, page=page))
+    elif filename:
+        adapter = LogNameAdapter(log, dict(filename=filename))
+    else:
+        adapter = log
+    return adapter

src/ocrmypdf/_pipeline.py

@@ -0,0 +1,818 @@
+# © 2016 James R. Barlow: github.com/jbarlow83
+#
+# This file is part of OCRmyPDF.
+#
+# OCRmyPDF is free software: you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# OCRmyPDF is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
+
+import os
+import re
+import sys
+from datetime import datetime, timezone
+from shutil import copyfileobj
+
+import img2pdf
+import pikepdf
+from pikepdf.models.metadata import encode_pdf_date
+from PIL import Image
+
+from . import leptonica
+from ._version import PROGRAM_NAME
+from ._version import __version__ as VERSION
+from .exceptions import (
+    DpiError,
+    EncryptedPdfError,
+    InputFileError,
+    PriorOcrFoundError,
+    UnsupportedImageFormatError,
+)
+from .exec import ghostscript, tesseract
+from .helpers import re_symlink
+from .hocrtransform import HocrTransform
+from .optimize import optimize
+from .pdfa import generate_pdfa_ps
+from .pdfinfo import Colorspace, PdfInfo
+
+VECTOR_PAGE_DPI = 400
+
+
+def triage_image_file(input_file, output_file, options, log):
+    try:
+        log.info("Input file is not a PDF, checking if it is an image...")
+        im = Image.open(input_file)
+    except EnvironmentError as e:
+        # Recover the original filename
+        log.error(str(e).replace(input_file, options.input_file))
+        raise UnsupportedImageFormatError() from e
+
+    with im:
+        log.info("Input file is an image")
+        if 'dpi' in im.info:
+            if im.info['dpi'] <= (96, 96) and not options.image_dpi:
+                log.info("Image size: (%d, %d)" % im.size)
+                log.info("Image resolution: (%d, %d)" % im.info['dpi'])
+                log.error(
+                    "Input file is an image, but the resolution (DPI) is "
+                    "not credible.  Estimate the resolution at which the "
+                    "image was scanned and specify it using --image-dpi."
+                )
+                raise DpiError()
+        elif not options.image_dpi:
+            log.info("Image size: (%d, %d)" % im.size)
+            log.error(
+                "Input file is an image, but has no resolution (DPI) "
+                "in its metadata.  Estimate the resolution at which "
+                "image was scanned and specify it using --image-dpi."
+            )
+            raise DpiError()
+
+        if im.mode in ('RGBA', 'LA'):
+            log.error(
+                "The input image has an alpha channel. Remove the alpha "
+                "channel first."
+            )
+            raise UnsupportedImageFormatError()
+
+        if 'iccprofile' not in im.info:
+            if im.mode == 'RGB':
+                log.info('Input image has no ICC profile, assuming sRGB')
+            elif im.mode == 'CMYK':
+                log.info('Input CMYK image has no ICC profile, not usable')
+                raise UnsupportedImageFormatError()
+
+    try:
+        log.info("Image seems valid. Try converting to PDF...")
+        layout_fun = img2pdf.default_layout_fun
+        if options.image_dpi:
+            layout_fun = img2pdf.get_fixed_dpi_layout_fun(
+                (options.image_dpi, options.image_dpi)
+            )
+        with open(output_file, 'wb') as outf:
+            img2pdf.convert(
+                input_file, layout_fun=layout_fun, with_pdfrw=False, outputstream=outf
+            )
+        log.info("Successfully converted to PDF, processing...")
+    except img2pdf.ImageOpenError as e:
+        log.error(e)
+        raise UnsupportedImageFormatError() from e
+
+
+def _pdf_guess_version(input_file, search_window=1024):
+    """Try to find version signature at start of file.
+
+    Not robust enough to deal with appended files.
+
+    Returns empty string if not found, indicating file is probably not PDF.
+    """
+
+    with open(input_file, 'rb') as f:
+        signature = f.read(search_window)
+    m = re.search(br'%PDF-(\d\.\d)', signature)
+    if m:
+        return m.group(1)
+    return ''
+
+
+def triage(input_file, output_file, options, log):
+    try:
+        if _pdf_guess_version(input_file):
+            if options.image_dpi:
+                log.warning(
+                    "Argument --image-dpi is being ignored because the "
+                    "input file is a PDF, not an image."
+                )
+            # Origin file is a pdf create a symlink with pdf extension
+            re_symlink(input_file, output_file)
+            return output_file
+    except EnvironmentError as e:
+        log.error(e)
+        raise InputFileError() from e
+
+    triage_image_file(input_file, output_file, options, log)
+    return output_file
+
+
+def get_pdfinfo(input_file, detailed_page_analysis=False, progbar=False):
+    try:
+        return PdfInfo(
+            input_file, detailed_page_analysis=detailed_page_analysis, progbar=progbar
+        )
+    except pikepdf.PasswordError:
+        raise EncryptedPdfError()
+    except pikepdf.PdfError:
+        raise InputFileError()
+
+
+def validate_pdfinfo_options(context):
+    log = context.log
+    pdfinfo = context.pdfinfo
+    options = context.options
+
+    if pdfinfo.needs_rendering:
+        log.error(
+            "This PDF contains dynamic XFA forms created by Adobe LiveCycle "
+            "Designer and can only be read by Adobe Acrobat or Adobe Reader."
+        )
+        raise InputFileError()
+    if pdfinfo.has_userunit and options.output_type.startswith('pdfa'):
+        log.error(
+            "This input file uses a PDF feature that is not supported "
+            "by Ghostscript, so you cannot use --output-type=pdfa for this "
+            "file. (Specifically, it uses the PDF-1.6 /UserUnit feature to "
+            "support very large or small page sizes, and Ghostscript cannot "
+            "output these files.)  Use --output-type=pdf instead."
+        )
+        raise InputFileError()
+    if pdfinfo.has_acroform:
+        if options.redo_ocr:
+            log.error(
+                "This PDF has a user fillable form. --redo-ocr is not "
+                "currently possible on such files."
+            )
+            raise InputFileError()
+        else:
+            log.warn(
+                "This PDF has a fillable form. "
+                "Chances are it is a pure digital "
+                "document that does not need OCR."
+            )
+            if not options.force_ocr:
+                log.info(
+                    "Use the option --force-ocr to produce an image of the "
+                    "form and all filled form fields. The output PDF will be "
+                    "'flattened' and will no longer be fillable."
+                )
+
+
+def get_page_dpi(pageinfo, options):
+    "Get the DPI when nonsquare DPI is tolerable"
+    xres = max(
+        pageinfo.xres or VECTOR_PAGE_DPI,
+        options.oversample or 0,
+        VECTOR_PAGE_DPI if pageinfo.has_vector else 0,
+    )
+    yres = max(
+        pageinfo.yres or VECTOR_PAGE_DPI,
+        options.oversample or 0,
+        VECTOR_PAGE_DPI if pageinfo.has_vector else 0,
+    )
+    return (float(xres), float(yres))
+
+
+def get_page_square_dpi(pageinfo, options):
+    "Get the DPI when we require xres == yres, scaled to physical units"
+    xres = pageinfo.xres or 0
+    yres = pageinfo.yres or 0
+    userunit = pageinfo.userunit or 1
+    return float(
+        max(
+            (xres * userunit) or VECTOR_PAGE_DPI,
+            (yres * userunit) or VECTOR_PAGE_DPI,
+            VECTOR_PAGE_DPI if pageinfo.has_vector else 0,
+            options.oversample or 0,
+        )
+    )
+
+
+def get_canvas_square_dpi(pageinfo, options):
+    """Get the DPI when we require xres == yres, in Postscript units"""
+    return float(
+        max(
+            (pageinfo.xres) or VECTOR_PAGE_DPI,
+            (pageinfo.yres) or VECTOR_PAGE_DPI,
+            VECTOR_PAGE_DPI if pageinfo.has_vector else 0,
+            options.oversample or 0,
+        )
+    )
+
+
+def is_ocr_required(page_context):
+    pageinfo = page_context.pageinfo
+    options = page_context.options
+    log = page_context.log
+
+    ocr_required = True
+
+    if options.pages and pageinfo.pageno not in options.pages:
+        log.debug(f"skipped {pageinfo.pageno} as requested by --pages {options.pages}")
+        ocr_required = False
+    elif pageinfo.has_text:
+        if not options.force_ocr and not (options.skip_text or options.redo_ocr):
+            raise PriorOcrFoundError(
+                "page already has text! - aborting (use --force-ocr to force OCR)"
+            )
+        elif options.force_ocr:
+            log.info("page already has text! - rasterizing text and running OCR anyway")
+            ocr_required = True
+        elif options.redo_ocr:
+            if pageinfo.has_corrupt_text:
+                log.warn(
+                    "some text on this page cannot be mapped to characters: "
+                    "consider using --force-ocr instead"
+                )
+            else:
+                log.info("redoing OCR")
+            ocr_required = True
+        elif options.skip_text:
+            log.info("skipping all processing on this page")
+            ocr_required = False
+    elif not pageinfo.images and not options.lossless_reconstruction:
+        # We found a page with no images and no text. That means it may
+        # have vector art that the user wants to OCR. If we determined
+        # lossless reconstruction is not possible then we have to rasterize
+        # the image. So if OCR is being forced, take that to mean YES, go
+        # ahead and rasterize. If not forced, then pretend there's no text
+        # on the page at all so we don't lose anything.
+        # This could be made smarter by explicitly searching for vector art.
+        if options.force_ocr and options.oversample:
+            # The user really wants to reprocess this file
+            log.info(
+                "page has no images - "
+                f"rasterizing at {options.oversample} DPI because "
+                "--force-ocr --oversample was specified"
+            )
+        elif options.force_ocr:
+            # Warn the user they might not want to do this
+            log.warn(
+                "page has no images - "
+                "all vector content will be "
+                f"rasterized at {VECTOR_PAGE_DPI} DPI, losing some resolution and likely "
+                "increasing file size. Use --oversample to adjust the "
+                "DPI."
+            )
+        else:
+            log.info(
+                "page has no images - "
+                "skipping all processing on this page to avoid losing detail. "
+                "Use --force-ocr if you wish to perform OCR on pages that "
+                "have vector content."
+            )
+            ocr_required = False
+
+    if ocr_required and options.skip_big and pageinfo.images:
+        pixel_count = pageinfo.width_pixels * pageinfo.height_pixels
+        if pixel_count > (options.skip_big * 1_000_000):
+            ocr_required = False
+            log.warn(
+                "page too big, skipping OCR "
+                f"({(pixel_count / 1_000_000):.1f} MPixels > {options.skip_big:.1f} MPixels --skip-big)"
+            )
+    return ocr_required
+
+
+def rasterize_preview(input_file, page_context):
+    output_file = page_context.get_path('rasterize_preview.jpg')
+    canvas_dpi = get_canvas_square_dpi(page_context.pageinfo, page_context.options)
+    page_dpi = get_page_square_dpi(page_context.pageinfo, page_context.options)
+    ghostscript.rasterize_pdf(
+        input_file,
+        output_file,
+        xres=canvas_dpi,
+        yres=canvas_dpi,
+        raster_device='jpeggray',
+        log=page_context.log,
+        page_dpi=(page_dpi, page_dpi),
+        pageno=page_context.pageinfo.pageno + 1,
+    )
+    return output_file
+
+
+def get_orientation_correction(preview, page_context):
+    """
+    Work out orientation correct for each page.
+
+    We ask Ghostscript to draw a preview page, which will rasterize with the
+    current /Rotate applied, and then ask Tesseract which way the page is
+    oriented. If the value of /Rotate is correct (e.g., a user already
+    manually fixed rotation), then Tesseract will say the page is pointing
+    up and the correction is zero. Otherwise, the orientation found by
+    Tesseract represents the clockwise rotation, or the counterclockwise
+    correction to rotation.
+
+    When we draw the real page for OCR, we rotate it by the CCW correction,
+    which points it (hopefully) upright. _graft.py takes care of the orienting
+    the image and text layers.
+
+    """
+
+    orient_conf = tesseract.get_orientation(
+        preview,
+        engine_mode=page_context.options.tesseract_oem,
+        timeout=page_context.options.tesseract_timeout,
+        log=page_context.log,
+        tesseract_env=page_context.options.tesseract_env,
+    )
+
+    direction = {0: '⇧', 90: '⇨', 180: '⇩', 270: '⇦'}
+
+    existing_rotation = page_context.pageinfo.rotation
+
+    correction = orient_conf.angle % 360
+
+    apply_correction = False
+    action = ''
+    if orient_conf.confidence >= page_context.options.rotate_pages_threshold:
+        if correction != 0:
+            apply_correction = True
+            action = ' - will rotate'
+        else:
+            action = ' - rotation appears correct'
+    else:
+        if correction != 0:
+            action = ' - confidence too low to rotate'
+        else:
+            action = ' - no change'
+
+    facing = ''
+    if existing_rotation != 0:
+        facing = 'with existing rotation {}, '.format(
+            direction.get(existing_rotation, '?')
+        )
+    facing += 'page is facing {}'.format(direction.get(orient_conf.angle, '?'))
+
+    page_context.log.debug(
+        '{pagenum:4d}: {facing}, confidence {conf:.2f}{action}'.format(
+            pagenum=page_context.pageinfo.pageno,
+            facing=facing,
+            conf=orient_conf.confidence,
+            action=action,
+        )
+    )
+
+    if apply_correction:
+        return correction
+    return 0
+
+
+def rasterize(
+    input_file, page_context, correction=0, output_tag='', remove_vectors=None
+):
+    colorspaces = ['pngmono', 'pnggray', 'png256', 'png16m']
+    device_idx = 0
+
+    if remove_vectors is None:
+        remove_vectors = page_context.options.remove_vectors
+
+    output_file = page_context.get_path(f'rasterize{output_tag}.png')
+    pageinfo = page_context.pageinfo
+
+    def at_least(cs):
+        return max(device_idx, colorspaces.index(cs))
+
+    for image in pageinfo.images:
+        if image.type_ != 'image':
+            continue  # ignore masks
+        if image.bpc > 1:
+            if image.color == Colorspace.index:
+                device_idx = at_least('png256')
+            elif image.color == Colorspace.gray:
+                device_idx = at_least('pnggray')
+            else:
+                device_idx = at_least('png16m')
+
+    if pageinfo.has_vector:
+        device_idx = at_least('png16m')
+
+    device = colorspaces[device_idx]
+
+    page_context.log.debug(f"Rasterize with {device}")
+
+    # Produce the page image with square resolution or else deskew and OCR
+    # will not work properly.
+    canvas_dpi = get_canvas_square_dpi(pageinfo, page_context.options)
+    page_dpi = get_page_square_dpi(pageinfo, page_context.options)
+
+    ghostscript.rasterize_pdf(
+        input_file,
+        output_file,
+        xres=canvas_dpi,
+        yres=canvas_dpi,
+        raster_device=device,
+        log=page_context.log,
+        page_dpi=(page_dpi, page_dpi),
+        pageno=pageinfo.pageno + 1,
+        rotation=correction,
+        filter_vector=remove_vectors,
+    )
+    return output_file
+
+
+def preprocess_remove_background(input_file, page_context):
+    if any(image.bpc > 1 for image in page_context.pageinfo.images):
+        output_file = page_context.get_path('pp_rm_bg.png')
+        leptonica.remove_background(input_file, output_file)
+        return output_file
+    else:
+        page_context.log.info("background removal skipped on mono page")
+        return input_file
+
+
+def preprocess_deskew(input_file, page_context):
+    output_file = page_context.get_path('pp_deskew.png')
+    dpi = get_page_square_dpi(page_context.pageinfo, page_context.options)
+    leptonica.deskew(input_file, output_file, dpi)
+    return output_file
+
+
+def preprocess_clean(input_file, page_context):
+    from .exec import unpaper
+
+    output_file = page_context.get_path('pp_clean.png')
+    dpi = get_page_square_dpi(page_context.pageinfo, page_context.options)
+    unpaper.clean(
+        input_file,
+        output_file,
+        dpi,
+        page_context.log,
+        page_context.options.unpaper_args,
+    )
+    return output_file
+
+
+def create_ocr_image(image, page_context):
+    """Create the image we send for OCR. May not be the same as the display
+    image depending on preprocessing. This image will never be shown to the
+    user."""
+
+    output_file = page_context.get_path('ocr.png')
+    options = page_context.options
+    with Image.open(image) as im:
+        from PIL import ImageColor
+        from PIL import ImageDraw
+
+        white = ImageColor.getcolor('#ffffff', im.mode)
+        # pink = ImageColor.getcolor('#ff0080', im.mode)
+        draw = ImageDraw.ImageDraw(im)
+
+        xres, yres = im.info['dpi']
+        page_context.log.debug('resolution %r %r' % (xres, yres))
+
+        if not options.force_ocr:
+            # Do not mask text areas when forcing OCR, because we need to OCR
+            # all text areas
+            mask = None  # Exclude both visible and invisible text from OCR
+            if options.redo_ocr:
+                mask = True  # Mask visible text, but not invisible text
+
+            for textarea in page_context.pageinfo.get_textareas(
+                visible=mask, corrupt=None
+            ):
+                # Calculate resolution based on the image size and page dimensions
+                # without regard whatever resolution is in pageinfo (may differ or
+                # be None)
+                bbox = [float(v) for v in textarea]
+                xscale, yscale = float(xres) / 72.0, float(yres) / 72.0
+                pixcoords = [
+                    bbox[0] * xscale,
+                    im.height - bbox[3] * yscale,
+                    bbox[2] * xscale,
+                    im.height - bbox[1] * yscale,
+                ]
+                pixcoords = [int(round(c)) for c in pixcoords]
+                page_context.log.debug('blanking %r', pixcoords)
+                draw.rectangle(pixcoords, fill=white)
+                # draw.rectangle(pixcoords, outline=pink)
+
+        if options.threshold:
+            pix = leptonica.Pix.frompil(im)
+            pix = pix.masked_threshold_on_background_norm()
+            im = pix.topil()
+
+        del draw
+        # Pillow requires integer DPI
+        dpi = round(xres), round(yres)
+        im.save(output_file, dpi=dpi)
+    return output_file
+
+
+def ocr_tesseract_hocr(input_file, page_context):
+    hocr_out = page_context.get_path('ocr_hocr.hocr')
+    hocr_text_out = page_context.get_path('ocr_hocr.txt')
+    options = page_context.options
+    tesseract.generate_hocr(
+        input_file=input_file,
+        output_files=[hocr_out, hocr_text_out],
+        language=options.language,
+        engine_mode=options.tesseract_oem,
+        tessconfig=options.tesseract_config,
+        timeout=options.tesseract_timeout,
+        pagesegmode=options.tesseract_pagesegmode,
+        user_words=options.user_words,
+        user_patterns=options.user_patterns,
+        tesseract_env=options.tesseract_env,
+        log=page_context.log,
+    )
+    return (hocr_out, hocr_text_out)
+
+
+def should_visible_page_image_use_jpg(pageinfo):
+    # If all images were JPEGs originally, produce a JPEG as output
+    return pageinfo.images and all(im.enc == 'jpeg' for im in pageinfo.images)
+
+
+def create_visible_page_jpg(image, page_context):
+    output_file = page_context.get_path('visible.jpg')
+    with Image.open(image) as im:
+        # At this point the image should be a .png, but deskew, unpaper
+        # might have removed the DPI information. In this case, fall back to
+        # square DPI used to rasterize. When the preview image was
+        # rasterized, it was also converted to square resolution, which is
+        # what we want to give tesseract, so keep it square.
+        fallback_dpi = get_page_square_dpi(page_context.pageinfo, page_context.options)
+        dpi = im.info.get('dpi', (fallback_dpi, fallback_dpi))
+
+        # Pillow requires integer DPI
+        dpi = round(dpi[0]), round(dpi[1])
+        im.save(output_file, format='JPEG', dpi=dpi)
+    return output_file
+
+
+def create_pdf_page_from_image(image, page_context):
+    # We rasterize a square DPI version of each page because most image
+    # processing tools don't support rectangular DPI. Use the square DPI as it
+    # accurately describes the image. It would be possible to resample the image
+    # at this stage back to non-square DPI to more closely resemble the input,
+    # except that the hocr renderer does not understand non-square DPI. The
+    # sandwich renderer would be fine.
+    output_file = page_context.get_path('visible.pdf')
+    dpi = get_page_square_dpi(page_context.pageinfo, page_context.options)
+    layout_fun = img2pdf.get_fixed_dpi_layout_fun((dpi, dpi))
+
+    # This create a single page PDF
+    with open(image, 'rb') as imfile, open(output_file, 'wb') as pdf:
+        page_context.log.debug('convert')
+        img2pdf.convert(
+            imfile, with_pdfrw=False, layout_fun=layout_fun, outputstream=pdf
+        )
+        page_context.log.debug('convert done')
+    return output_file
+
+
+def render_hocr_page(hocr, page_context):
+    output_file = page_context.get_path('ocr_hocr.pdf')
+    dpi = get_page_square_dpi(page_context.pageinfo, page_context.options)
+    hocrtransform = HocrTransform(hocr, dpi)
+    hocrtransform.to_pdf(
+        output_file,
+        imageFileName=None,
+        showBoundingboxes=False,
+        invisibleText=True,
+        interwordSpaces=True,
+    )
+    return output_file
+
+
+def ocr_tesseract_textonly_pdf(input_image, page_context):
+    output_pdf = page_context.get_path('ocr_tess.pdf')
+    output_text = page_context.get_path('ocr_tess.txt')
+    options = page_context.options
+    tesseract.generate_pdf(
+        input_image=input_image,
+        skip_pdf=None,
+        output_pdf=output_pdf,
+        output_text=output_text,
+        language=options.language,
+        engine_mode=options.tesseract_oem,
+        text_only=True,
+        tessconfig=options.tesseract_config,
+        timeout=options.tesseract_timeout,
+        pagesegmode=options.tesseract_pagesegmode,
+        user_words=options.user_words,
+        user_patterns=options.user_patterns,
+        tesseract_env=options.tesseract_env,
+        log=page_context.log,
+    )
+    return (output_pdf, output_text)
+
+
+def get_docinfo(base_pdf, options):
+    def from_document_info(key):
+        try:
+            s = base_pdf.docinfo[key]
+            return str(s)
+        except (KeyError, TypeError):
+            return ''
+
+    pdfmark = {
+        k: from_document_info(k)
+        for k in ('/Title', '/Author', '/Keywords', '/Subject', '/CreationDate')
+    }
+    renderer_tag = 'OCR'
+    if options is not None:
+        if options.title:
+            pdfmark['/Title'] = options.title
+        if options.author:
+            pdfmark['/Author'] = options.author
+        if options.keywords:
+            pdfmark['/Keywords'] = options.keywords
+        if options.subject:
+            pdfmark['/Subject'] = options.subject
+
+        if options.pdf_renderer == 'sandwich':
+            renderer_tag = 'OCR-PDF'
+
+    pdfmark['/Creator'] = (
+        f'{PROGRAM_NAME} {VERSION} / ' f'Tesseract {renderer_tag} {tesseract.version()}'
+    )
+    pdfmark['/Producer'] = f'pikepdf {pikepdf.__version__}'
+    if 'OCRMYPDF_CREATOR' in os.environ:
+        pdfmark['/Creator'] = os.environ['OCRMYPDF_CREATOR']
+    if 'OCRMYPDF_PRODUCER' in os.environ:
+        pdfmark['/Producer'] = os.environ['OCRMYPDF_PRODUCER']
+
+    pdfmark['/ModDate'] = encode_pdf_date(datetime.now(timezone.utc))
+    return pdfmark
+
+
+def generate_postscript_stub(context):
+    output_file = context.get_path('pdfa.ps')
+    generate_pdfa_ps(output_file)
+    return output_file
+
+
+def convert_to_pdfa(input_pdf, input_ps_stub, context):
+    options = context.options
+    input_pdfinfo = context.pdfinfo
+    fix_docinfo_file = context.get_path('fix_docinfo.pdf')
+    output_file = context.get_path('pdfa.pdf')
+
+    # If the DocumentInfo record contains NUL characters, Ghostscript will
+    # produce XMP metadata which contains invalid XML entities (&#0;).
+    # NULs in DocumentInfo seem to be common since older Acrobats included them.
+    # pikepdf can deal with this, but we make the world a better place by
+    # stamping them out as soon as possible.
+    modified = False
+    with pikepdf.open(input_pdf) as pdf_file:
+        if pdf_file.docinfo:
+            for k, v in pdf_file.docinfo.items():
+                if b'\x00' in bytes(v):
+                    pdf_file.docinfo[k] = bytes(v).replace(b'\x00', b'')
+                    modified = True
+        if modified:
+            pdf_file.save(fix_docinfo_file)
+        else:
+            os.symlink(input_pdf, fix_docinfo_file)
+
+    ghostscript.generate_pdfa(
+        pdf_version=input_pdfinfo.min_version,
+        pdf_pages=[fix_docinfo_file, input_ps_stub],
+        output_file=output_file,
+        compression=options.pdfa_image_compression,
+        log=context.log,
+        pdfa_part=options.output_type[-1],  # is pdfa-1, pdfa-2, or pdfa-3
+    )
+
+    return output_file
+
+
+def should_linearize(working_file, context):
+    filesize = os.stat(working_file).st_size
+    if filesize > (context.options.fast_web_view * 1_000_000):
+        return True
+    return False
+
+
+def metadata_fixup(working_file, context):
+    output_file = context.get_path('metafix.pdf')
+    options = context.options
+    original = pikepdf.open(context.origin)
+    docinfo = get_docinfo(original, options)
+    pdf = pikepdf.open(working_file)
+    with pdf.open_metadata() as meta:
+        meta.load_from_docinfo(docinfo, delete_missing=False)
+        # If xmp:CreateDate is missing, set it to the modify date to
+        # match Ghostscript, for consistency
+        if 'xmp:CreateDate' not in meta:
+            meta['xmp:CreateDate'] = meta.get('xmp:ModifyDate', '')
+
+        meta_original = original.open_metadata()
+        not_copied = set(meta_original.keys()) - set(meta.keys())
+        if not_copied:
+            if options.output_type.startswith('pdfa'):
+                context.log.warning(
+                    "Some input metadata could not be copied because it is not "
+                    "permitted in PDF/A. You may wish to examine the output "
+                    "PDF's XMP metadata."
+                )
+                context.log.debug(
+                    "The following metadata fields were not copied: %r", not_copied
+                )
+            else:
+                context.log.error(
+                    "Some input metadata could not be copied."
+                    "You may wish to examine the output PDF's XMP metadata."
+                )
+                context.log.info(
+                    "The following metadata fields were not copied: %r", not_copied
+                )
+    pdf.save(
+        output_file,
+        compress_streams=True,
+        preserve_pdfa=True,
+        object_stream_mode=pikepdf.ObjectStreamMode.generate,
+        linearize=(  # Don't linearize if optimize() will be linearizing too
+            should_linearize(working_file, context) if options.optimize == 0 else False
+        ),
+    )
+    original.close()
+    pdf.close()
+    return output_file
+
+
+def optimize_pdf(input_file, context):
+    output_file = context.get_path('optimize.pdf')
+    save_settings = dict(
+        compress_streams=True,
+        preserve_pdfa=True,
+        object_stream_mode=pikepdf.ObjectStreamMode.generate,
+        linearize=should_linearize(input_file, context),
+    )
+    optimize(input_file, output_file, context, save_settings)
+    return output_file
+
+
+def merge_sidecars(txt_files, context):
+    output_file = context.get_path('sidecar.txt')
+    with open(output_file, 'w', encoding="utf-8") as stream:
+        for page_num, txt_file in enumerate(txt_files):
+            if page_num != 0:
+                stream.write('\f')  # Form feed between pages
+            if txt_file:
+                with open(txt_file, 'r', encoding="utf-8") as in_:
+                    txt = in_.read()
+                    # Tesseract v4 alpha started adding form feeds in
+                    # commit aa6eb6b
+                    # No obvious way to detect what binaries will do this, so
+                    # for consistency just ignore its form feeds and insert our
+                    # own
+                    if txt.endswith('\f'):
+                        stream.write(txt[:-1])
+                    else:
+                        stream.write(txt)
+            else:
+                stream.write(f'[OCR skipped on page {(page_num + 1)}]')
+    return output_file
+
+
+def copy_final(input_file, output_file, context):
+    context.log.debug('%s -> %s', input_file, output_file)
+    with open(input_file, 'rb') as input_stream:
+        if output_file == '-':
+            copyfileobj(input_stream, sys.stdout.buffer)
+            sys.stdout.flush()
+        else:
+            # At this point we overwrite the output_file specified by the user
+            # use copyfileobj because then we use open() to create the file and
+            # get the appropriate umask, ownership, etc.
+            with open(output_file, 'wb') as output_stream:
+                copyfileobj(input_stream, output_stream)

src/ocrmypdf/_sync.py

@@ -0,0 +1,380 @@
+# © 2016 James R. Barlow: github.com/jbarlow83
+#
+# This file is part of OCRmyPDF.
+#
+# OCRmyPDF is free software: you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# OCRmyPDF is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
+
+import logging
+import logging.handlers
+import multiprocessing
+import os
+import signal
+import sys
+import threading
+from collections import namedtuple
+from tempfile import mkdtemp
+
+from tqdm import tqdm
+
+from ._graft import OcrGrafter
+from ._jobcontext import PDFContext, cleanup_working_files, make_logger
+from ._pipeline import (
+    convert_to_pdfa,
+    copy_final,
+    create_ocr_image,
+    create_pdf_page_from_image,
+    create_visible_page_jpg,
+    generate_postscript_stub,
+    get_orientation_correction,
+    get_pdfinfo,
+    is_ocr_required,
+    merge_sidecars,
+    metadata_fixup,
+    ocr_tesseract_hocr,
+    ocr_tesseract_textonly_pdf,
+    optimize_pdf,
+    preprocess_clean,
+    preprocess_deskew,
+    preprocess_remove_background,
+    rasterize,
+    rasterize_preview,
+    render_hocr_page,
+    should_visible_page_image_use_jpg,
+    triage,
+    validate_pdfinfo_options,
+)
+from ._validation import (
+    check_requested_output_file,
+    create_input_file,
+    report_output_file_size,
+)
+from .exceptions import ExitCode, ExitCodeException
+from .exec import qpdf
+from .helpers import available_cpu_count
+from .pdfa import file_claims_pdfa
+
+PageResult = namedtuple(
+    'PageResult', 'pageno, pdf_page_from_image, ocr, text, orientation_correction'
+)
+
+
+def preprocess(page_context, image, remove_background, deskew, clean):
+    if remove_background:
+        image = preprocess_remove_background(image, page_context)
+    if deskew:
+        image = preprocess_deskew(image, page_context)
+    if clean:
+        image = preprocess_clean(image, page_context)
+    return image
+
+
+def exec_page_sync(page_context):
+    options = page_context.options
+    orientation_correction = 0
+    pdf_page_from_image_out = None
+    ocr_out = None
+    text_out = None
+    if is_ocr_required(page_context):
+        if options.rotate_pages:
+            # Rasterize
+            rasterize_preview_out = rasterize_preview(page_context.origin, page_context)
+            orientation_correction = get_orientation_correction(
+                rasterize_preview_out, page_context
+            )
+
+        rasterize_out = rasterize(
+            page_context.origin,
+            page_context,
+            correction=orientation_correction,
+            remove_vectors=False,
+        )
+
+        if not any([options.clean, options.clean_final, options.remove_vectors]):
+            ocr_image = preprocess_out = preprocess(
+                page_context,
+                rasterize_out,
+                options.remove_background,
+                options.deskew,
+                clean=False,
+            )
+        else:
+            if not options.lossless_reconstruction:
+                preprocess_out = preprocess(
+                    page_context,
+                    rasterize_out,
+                    options.remove_background,
+                    options.deskew,
+                    clean=options.clean_final,
+                )
+            if options.remove_vectors:
+                rasterize_ocr_out = rasterize(
+                    page_context.origin,
+                    page_context,
+                    correction=orientation_correction,
+                    remove_vectors=True,
+                    output_tag='_ocr',
+                )
+            else:
+                rasterize_ocr_out = rasterize_out
+            ocr_image = preprocess(
+                page_context,
+                rasterize_ocr_out,
+                options.remove_background,
+                options.deskew,
+                clean=options.clean,
+            )
+
+        ocr_image_out = create_ocr_image(ocr_image, page_context)
+
+        pdf_page_from_image_out = None
+        if not options.lossless_reconstruction:
+            visible_image_out = preprocess_out
+            if should_visible_page_image_use_jpg(page_context.pageinfo):
+                visible_image_out = create_visible_page_jpg(
+                    visible_image_out, page_context
+                )
+            pdf_page_from_image_out = create_pdf_page_from_image(
+                visible_image_out, page_context
+            )
+
+        if options.pdf_renderer == 'hocr':
+            (hocr_out, text_out) = ocr_tesseract_hocr(ocr_image_out, page_context)
+            ocr_out = render_hocr_page(hocr_out, page_context)
+
+        if options.pdf_renderer == 'sandwich':
+            (ocr_out, text_out) = ocr_tesseract_textonly_pdf(
+                ocr_image_out, page_context
+            )
+
+    return PageResult(
+        pageno=page_context.pageno,
+        pdf_page_from_image=pdf_page_from_image_out,
+        ocr=ocr_out,
+        text=text_out,
+        orientation_correction=orientation_correction,
+    )
+
+
+def post_process(pdf_file, context):
+    pdf_out = pdf_file
+    if context.options.output_type.startswith('pdfa'):
+        ps_stub_out = generate_postscript_stub(context)
+        pdf_out = convert_to_pdfa(pdf_out, ps_stub_out, context)
+
+    pdf_out = metadata_fixup(pdf_out, context)
+    return optimize_pdf(pdf_out, context)
+
+
+def worker_init(queue):
+    """Initialize a process pool worker"""
+
+    # Ignore SIGINT (our parent process will kill us gracefully)
+    signal.signal(signal.SIGINT, signal.SIG_IGN)
+
+    # Reconfigure the root logger for this process to send all messages to a queue
+    h = logging.handlers.QueueHandler(queue)
+    root = logging.getLogger()
+    root.handlers = []
+    root.addHandler(h)
+
+
+def worker_thread_init(_queue):
+    pass
+
+
+def log_listener(queue):
+    """Listen to the worker processes and forward the messages to logging
+
+    For simplicity this is a thread rather than a process. Only one process
+    should actually write to sys.stderr or whatever we're using, so if this is
+    made into a process the main application needs to be directed to it.
+
+    See https://docs.python.org/3/howto/logging-cookbook.html#logging-to-a-single-file-from-multiple-processes
+    """
+
+    while True:
+        try:
+            record = queue.get()
+            if record is None:
+                break
+            logger = logging.getLogger(record.name)
+            logger.handle(record)
+        except Exception:
+            import traceback
+
+            print("Logging problem", file=sys.stderr)
+            traceback.print_exc(file=sys.stderr)
+
+
+def exec_concurrent(context):
+    """Execute the pipeline concurrently"""
+
+    # Run exec_page_sync on every page context
+    max_workers = min(len(context.pdfinfo), context.options.jobs)
+    if max_workers > 1:
+        context.log.info("Start processing %d pages concurrent", max_workers)
+
+    # Tesseract 4.x can be multithreaded, and we also run multiple workers. We want
+    # to manage how many threads it uses to avoid creating total threads than cores.
+    # Performance testing shows we're better off
+    # parallelizing ocrmypdf and forcing Tesseract to be single threaded, which we
+    # get by setting the envvar OMP_THREAD_LIMIT to 1. But if the page count of the
+    # input file is small, then we allow Tesseract to use threads, subject to the
+    # constraint: (ocrmypdf workers) * (tesseract threads) <= max_workers.
+    # As of Tesseract 4.1, 3 threads is the most effective on a 4 core/8 thread system.
+    tess_threads = min(3, context.options.jobs // max_workers)
+    if context.options.tesseract_env is None:
+        context.options.tesseract_env = os.environ.copy()
+    context.options.tesseract_env.setdefault('OMP_THREAD_LIMIT', str(tess_threads))
+    if tess_threads > 1:
+        context.log.info("Using Tesseract OpenMP thread limit %d", tess_threads)
+
+    if context.options.use_threads:
+        from multiprocessing.dummy import Pool
+
+        initializer = worker_thread_init
+    else:
+        Pool = multiprocessing.Pool
+        initializer = worker_init
+
+    sidecars = [None] * len(context.pdfinfo)
+    ocrgraft = OcrGrafter(context)
+
+    log_queue = multiprocessing.Queue(-1)
+    listener = threading.Thread(target=log_listener, args=(log_queue,))
+    listener.start()
+    with tqdm(
+        total=(2 * len(context.pdfinfo)),
+        desc='OCR',
+        unit='page',
+        unit_scale=0.5,
+        disable=not context.options.progress_bar,
+    ) as pbar, Pool(
+        processes=max_workers, initializer=initializer, initargs=(log_queue,)
+    ) as pool:
+        results = pool.imap_unordered(exec_page_sync, context.get_page_contexts())
+        while True:
+            try:
+                page_result = results.next()
+                sidecars[page_result.pageno] = page_result.text
+                pbar.update()
+                ocrgraft.graft_page(page_result)
+                pbar.update()
+            except StopIteration:
+                break
+            except (Exception, KeyboardInterrupt):
+                pool.terminate()
+                log_queue.put_nowait(None)  # Terminate log listener
+                # Don't try listener.join() here, will deadlock
+                raise
+
+    log_queue.put_nowait(None)
+    listener.join()
+
+    # Output sidecar text
+    if context.options.sidecar:
+        text = merge_sidecars(sidecars, context)
+        # Copy text file to destination
+        copy_final(text, context.options.sidecar, context)
+
+    # Merge layers to one single pdf
+    pdf = ocrgraft.finalize()
+
+    # PDF/A and metadata
+    pdf = post_process(pdf, context)
+
+    # Copy PDF file to destination
+    copy_final(pdf, context.options.output_file, context)
+
+
+class NeverRaise(Exception):
+    """An exception that is never raised"""
+
+    pass  # pylint: disable=unnecessary-pass
+
+
+def run_pipeline(options, api=False):
+    log = make_logger(options, __name__)
+
+    # Any changes to options will not take effect for options that are already
+    # bound to function parameters in the pipeline. (For example
+    # options.input_file, options.pdf_renderer are already bound.)
+    if not options.jobs:
+        options.jobs = available_cpu_count()
+
+    work_folder = mkdtemp(prefix="com.github.ocrmypdf.")
+    try:
+        check_requested_output_file(options)
+        start_input_file = create_input_file(options, work_folder)
+
+        # Triage image or pdf
+        origin_pdf = triage(
+            start_input_file, os.path.join(work_folder, 'origin.pdf'), options, log
+        )
+
+        # Gather pdfinfo and create context
+        pdfinfo = get_pdfinfo(
+            origin_pdf,
+            detailed_page_analysis=options.redo_ocr,
+            progbar=options.progress_bar,
+        )
+        context = PDFContext(options, work_folder, origin_pdf, pdfinfo)
+
+        # Validate options are okay for this pdf
+        validate_pdfinfo_options(context)
+
+        # Execute the pipeline
+        exec_concurrent(context)
+
+        if options.output_file == '-':
+            log.info("Output sent to stdout")
+        elif os.path.samefile(options.output_file, os.devnull):
+            pass  # Say nothing when sending to dev null
+        else:
+            if options.output_type.startswith('pdfa'):
+                pdfa_info = file_claims_pdfa(options.output_file)
+                if pdfa_info['pass']:
+                    log.info(
+                        "Output file is a %s (as expected)", pdfa_info['conformance']
+                    )
+                else:
+                    log.warning(
+                        "Output file is okay but is not PDF/A (seems to be %s)",
+                        pdfa_info['conformance'],
+                    )
+                    return ExitCode.pdfa_conversion_failed
+            if not qpdf.check(options.output_file, log):
+                log.warning('Output file: The generated PDF is INVALID')
+                return ExitCode.invalid_output_pdf
+            report_output_file_size(options, start_input_file, options.output_file)
+
+    except (KeyboardInterrupt if not api else NeverRaise) as e:
+        if options.verbose >= 1:
+            log.exception("KeyboardInterrupt")
+        else:
+            log.error("KeyboardInterrupt")
+        return ExitCode.ctrl_c
+    except (ExitCodeException if not api else NeverRaise) as e:
+        if str(e):
+            log.error("%s: %s", type(e).__name__, str(e))
+        else:
+            log.error(type(e).__name__)
+        return e.exit_code
+    except (Exception if not api else NeverRaise) as e:
+        log.exception("An exception occurred while executing the pipeline")
+        return ExitCode.other_error
+    finally:
+        cleanup_working_files(work_folder, options)
+
+    return ExitCode.ok

src/ocrmypdf/_unicodefun.py

@@ -0,0 +1,118 @@
+# Copyright (c) 2014, Armin Ronacher
+#
+# Copyright (c) 2017, James R Barlow
+#
+# Some rights reserved.
+#
+# Redistribution and use in source and binary forms, with or without
+# modification, are permitted provided that the following conditions are
+# met:
+#
+#     * Redistributions of source code must retain the above copyright
+#       notice, this list of conditions and the following disclaimer.
+#
+#     * Redistributions in binary form must reproduce the above
+#       copyright notice, this list of conditions and the following
+#       disclaimer in the documentation and/or other materials provided
+#       with the distribution.
+#
+#     * The names of the contributors may not be used to endorse or
+#       promote products derived from this software without specific
+#       prior written permission.
+#
+# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+# "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+# LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+# A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+# OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+# SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+# LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+# DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+# THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+# (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+# OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+
+
+import codecs
+import os
+import sys
+
+
+def verify_python3_env():  # pragma: no cover
+    """Ensures that the environment is good for unicode on Python 3."""
+
+    # PEP 538 changes in Python 3.7 should make this wrangling unnecessary
+    if sys.version_info[0:3] >= (3, 7, 0):
+        return
+
+    try:
+        import locale
+
+        fs_enc = codecs.lookup(locale.getpreferredencoding()).name
+    except Exception:
+        fs_enc = 'ascii'
+    if fs_enc != 'ascii':
+        return
+
+    extra = ''
+    if os.name == 'posix':
+        import subprocess
+
+        rv = subprocess.run(
+            ['locale', '-a'], stdout=subprocess.PIPE, stderr=subprocess.PIPE
+        ).stdout
+        good_locales = set()
+        has_c_utf8 = False
+
+        # Make sure we're operating on text here.
+        if isinstance(rv, bytes):
+            rv = rv.decode('ascii', 'replace')
+
+        for line in rv.splitlines():
+            locale = line.strip()
+            if locale.lower().endswith(('.utf-8', '.utf8')):
+                good_locales.add(locale)
+                if locale.lower() in ('c.utf8', 'c.utf-8'):
+                    has_c_utf8 = True
+
+        extra += '\n\n'
+        if not good_locales:
+            extra += (
+                'Additional information: on this system no suitable UTF-8\n'
+                'locales were discovered.  This most likely requires resolving\n'
+                'by reconfiguring the locale system.'
+            )
+        elif has_c_utf8:
+            extra += (
+                'This system supports the C.UTF-8 locale which is recommended.\n'
+                'You might be able to resolve your issue by exporting the\n'
+                'following environment variables:\n\n'
+                '    export LC_ALL=C.UTF-8\n'
+                '    export LANG=C.UTF-8'
+            )
+        else:
+            extra += (
+                'This system lists a couple of UTF-8 supporting locales that\n'
+                'you can pick from.  The following suitable locales were\n'
+                'discovered: %s'
+            ) % ', '.join(sorted(good_locales))
+
+        bad_locale = None
+        for locale in os.environ.get('LC_ALL'), os.environ.get('LANG'):
+            if locale and locale.lower().endswith(('.utf-8', '.utf8')):
+                bad_locale = locale
+            if locale is not None:
+                break
+        if bad_locale is not None:
+            extra += (
+                '\nocrmypdf discovered that you exported a UTF-8 locale\n'
+                'but the locale system could not pick up from it because\n'
+                'it does not exist.  The exported locale is "%s" but it\n'
+                'is not supported'
+            ) % bad_locale
+
+    raise RuntimeError(
+        'ocrmypdf will abort further execution because Python 3 '
+        'was configured to use ASCII as encoding for the '
+        'environment.' + extra
+    )

src/ocrmypdf/_validation.py

@@ -0,0 +1,470 @@
+#!/usr/bin/env python3
+# © 2015-17 James R. Barlow: github.com/jbarlow83
+#
+# This file is part of OCRmyPDF.
+#
+# OCRmyPDF is free software: you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# OCRmyPDF is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
+
+
+import locale
+import logging
+import os
+import sys
+from pathlib import Path
+from shutil import copyfileobj
+
+import PIL
+
+from ._unicodefun import verify_python3_env
+from .exceptions import (
+    BadArgsError,
+    InputFileError,
+    MissingDependencyError,
+    OutputFileAccessError,
+)
+from .exec import (
+    check_external_program,
+    ghostscript,
+    jbig2enc,
+    pngquant,
+    qpdf,
+    tesseract,
+    unpaper,
+)
+from .helpers import is_file_writable, is_iterable_notstr, monotonic, re_symlink
+
+# -------------
+# External dependencies
+
+HOCR_OK_LANGS = frozenset(['eng', 'deu', 'spa', 'ita', 'por'])
+DEFAULT_LANGUAGE = 'eng'  # Enforce English hegemony
+
+log = logging.getLogger(__name__)
+
+
+# --------
+# Critical environment tests
+verify_python3_env()
+
+
+def check_options_languages(options):
+    if not options.language:
+        options.language = [DEFAULT_LANGUAGE]
+        system_lang = locale.getlocale()[0]
+        if system_lang and not system_lang.startswith('en'):
+            log.debug("No language specified; assuming --language %s", DEFAULT_LANGUAGE)
+
+    # Support v2.x "eng+deu" language syntax
+    if '+' in options.language[0]:
+        options.language = options.language[0].split('+')
+
+    languages = set(options.language)
+    if not languages.issubset(tesseract.languages()):
+        msg = (
+            "The installed version of tesseract does not have language "
+            "data for the following requested languages: \n"
+        )
+        for lang in languages - tesseract.languages():
+            msg += lang + '\n'
+        raise MissingDependencyError(msg)
+
+
+def check_options_output(options):
+    # We have these constraints to check for.
+    # 1. Ghostscript < 9.20 mangles multibyte Unicode
+    # 2. hocr doesn't work on non-Latin languages (so don't select it)
+
+    languages = set(options.language)
+    is_latin = languages.issubset(HOCR_OK_LANGS)
+
+    if options.pdf_renderer == 'hocr' and not is_latin:
+        msg = (
+            "The 'hocr' PDF renderer is known to cause problems with one "
+            "or more of the languages in your document.  Use "
+            "--pdf-renderer auto (the default) to avoid this issue."
+        )
+        log.warning(msg)
+
+    if ghostscript.version() < '9.20' and options.output_type != 'pdf' and not is_latin:
+        # https://bugs.ghostscript.com/show_bug.cgi?id=696874
+        # Ghostscript < 9.20 fails to encode multibyte characters properly
+        msg = (
+            "The installed version of Ghostscript does not work correctly "
+            "with the OCR languages you specified. Use --output-type pdf or "
+            "upgrade to Ghostscript 9.20 or later to avoid this issue."
+        )
+        msg += f"Found Ghostscript {ghostscript.version()}"
+        log.warning(msg)
+
+    # Decide on what renderer to use
+    if options.pdf_renderer == 'auto':
+        options.pdf_renderer = 'sandwich'
+
+    if options.pdf_renderer == 'sandwich' and not tesseract.has_textonly_pdf(
+        options.tesseract_env, languages
+    ):
+        raise MissingDependencyError(
+            "You are using an alpha version of Tesseract 4.0 that does not support "
+            "the textonly_pdf parameter. We don't support versions this old."
+        )
+
+    if options.output_type == 'pdfa':
+        options.output_type = 'pdfa-2'
+
+    if options.output_type == 'pdfa-3' and ghostscript.version() < '9.19':
+        raise MissingDependencyError(
+            "--output-type pdfa-3 requires Ghostscript 9.19 or later"
+        )
+
+    lossless_reconstruction = False
+    if not any(
+        (
+            options.deskew,
+            options.clean_final,
+            options.force_ocr,
+            options.remove_background,
+        )
+    ):
+        lossless_reconstruction = True
+    options.lossless_reconstruction = lossless_reconstruction
+
+    if not options.lossless_reconstruction and options.redo_ocr:
+        raise BadArgsError(
+            "--redo-ocr is not currently compatible with --deskew, "
+            "--clean-final, and --remove-background"
+        )
+
+
+def check_options_sidecar(options):
+    if options.sidecar == '\0':
+        if options.output_file == '-':
+            raise BadArgsError(
+                "--sidecar filename must be specified when output file is stdout."
+            )
+        options.sidecar = options.output_file + '.txt'
+
+
+def check_options_preprocessing(options):
+    if options.clean_final:
+        options.clean = True
+    if options.unpaper_args and not options.clean:
+        raise BadArgsError("--clean is required for --unpaper-args")
+    if options.clean:
+        check_external_program(
+            program='unpaper',
+            package='unpaper',
+            version_checker=unpaper.version,
+            need_version='6.1',
+            required_for=['--clean, --clean-final'],
+        )
+        try:
+            if options.unpaper_args:
+                options.unpaper_args = unpaper.validate_custom_args(
+                    options.unpaper_args
+                )
+        except Exception as e:
+            raise BadArgsError(str(e))
+
+
+def _pages_from_ranges(ranges):
+    if is_iterable_notstr(ranges):
+        return set(ranges)
+    pages = []
+    page_groups = ranges.replace(' ', '').split(',')
+    for g in page_groups:
+        if not g:
+            continue
+        try:
+            start, end = g.split('-')
+        except ValueError:
+            pages.append(int(g) - 1)
+        else:
+            try:
+                pages.extend(range(int(start) - 1, int(end)))
+            except ValueError:
+                raise BadArgsError("invalid page range")
+
+    if not monotonic(pages):
+        log.warning(
+            "List of pages to process contains duplicate pages, or pages that are "
+            "out of order"
+        )
+    if any(page < 0 for page in pages):
+        raise BadArgsError("pages refers to a page number less than 1")
+
+    log.debug("OCRing only these pages: %s", pages)
+    return set(pages)
+
+
+def check_options_ocr_behavior(options):
+    exclusive_options = sum(
+        [
+            (1 if opt else 0)
+            for opt in (options.force_ocr, options.skip_text, options.redo_ocr)
+        ]
+    )
+    if exclusive_options >= 2:
+        raise BadArgsError("Choose only one of --force-ocr, --skip-text, --redo-ocr.")
+    if options.pages and options.sidecar:
+        raise BadArgsError("--pages and --sidecar are mutually exclusive")
+    if options.pages:
+        options.pages = _pages_from_ranges(options.pages)
+
+
+def check_options_optimizing(options):
+    if options.optimize >= 2:
+        check_external_program(
+            program='pngquant',
+            package='pngquant',
+            version_checker=pngquant.version,
+            need_version='2.0.1',
+            required_for='--optimize {2,3}',
+        )
+
+    if options.optimize >= 2:
+        # Although we use JBIG2 for optimize=1, don't nag about it unless the
+        # user is asking for more optimization
+        check_external_program(
+            program='jbig2',
+            package='jbig2enc',
+            version_checker=jbig2enc.version,
+            need_version='0.28',
+            required_for='--optimize {2,3} | --jbig2-lossy',
+            recommended=True if not options.jbig2_lossy else False,
+        )
+
+    if options.optimize == 0 and any(
+        [options.jbig2_lossy, options.png_quality, options.jpeg_quality]
+    ):
+        log.warning(
+            "The arguments --jbig2-lossy, --png-quality, and --jpeg-quality "
+            "will be ignored because --optimize=0."
+        )
+
+
+def check_options_advanced(options):
+    if options.pdfa_image_compression != 'auto' and options.output_type.startswith(
+        'pdfa'
+    ):
+        log.warning(
+            "--pdfa-image-compression argument has no effect when "
+            "--output-type is not 'pdfa', 'pdfa-1', or 'pdfa-2'"
+        )
+    if not tesseract.has_user_words(options.tesseract_env) and (
+        options.user_words or options.user_patterns
+    ):
+        log.warning(
+            "Tesseract 4.0 ignores --user-words and --user-patterns, so these "
+            "arguments have no effect."
+        )
+
+
+def check_options_metadata(options):
+    import unicodedata
+
+    docinfo = [options.title, options.author, options.keywords, options.subject]
+    for s in (m for m in docinfo if m):
+        for c in s:
+            if unicodedata.category(c) == 'Co' or ord(c) >= 0x10000:
+                raise ValueError(
+                    "One of the metadata strings contains "
+                    "an unsupported Unicode character: '{}' (U+{})".format(
+                        c, hex(ord(c))[2:].upper()
+                    )
+                )
+
+
+def check_options_pillow(options):
+    PIL.Image.MAX_IMAGE_PIXELS = int(options.max_image_mpixels * 1_000_000)
+    if PIL.Image.MAX_IMAGE_PIXELS == 0:
+        PIL.Image.MAX_IMAGE_PIXELS = None
+
+
+def check_options(options):
+    check_options_languages(options)
+    check_options_metadata(options)
+    check_options_output(options)
+    check_options_sidecar(options)
+    check_options_preprocessing(options)
+    check_options_ocr_behavior(options)
+    check_options_optimizing(options)
+    check_options_advanced(options)
+    check_options_pillow(options)
+    check_dependency_versions(options)
+
+
+def check_closed_streams(options):
+    """Work around Python issue with multiprocessing forking on closed streams
+
+    https://bugs.python.org/issue28326
+
+    Attempting to a fork/exec a new Python process when any of std{in,out,err}
+    are closed or not flushable for some reason may raise an exception.
+    Fix this by opening devnull if the handle seems to be closed.  Do this
+    globally to avoid tracking places all places that fork.
+
+    Seems to be specific to multiprocessing.Process not all Python process
+    forkers.
+
+    The error actually occurs when the stream object is not flushable,
+    but replacing an open stream object that is not flushable with
+    /dev/null is a bad idea since it will create a silent failure.  Replacing
+    a closed handle with /dev/null seems safe.
+
+    """
+
+    if sys.version_info[0:3] >= (3, 6, 4):
+        return True  # Issued fixed in Python 3.6.4+
+
+    if sys.stderr is None:
+        sys.stderr = open(os.devnull, 'w')
+
+    if sys.stdin is None:
+        if options.input_file == '-':
+            log.error("Trying to read from stdin but stdin seems closed")
+            return False
+        sys.stdin = open(os.devnull, 'r')
+
+    if sys.stdout is None:
+        if options.output_file == '-':
+            # Can't replace stdout if the user is piping
+            # If this case can even happen, it must be some kind of weird
+            # stream.
+            log.error(
+                "Output was set to stdout '-' but the stream attached to "
+                "stdout does not support the flush() system call.  This "
+                "will fail."
+            )
+            return False
+        sys.stdout = open(os.devnull, 'w')
+
+    return True
+
+
+def log_page_orientations(pdfinfo):
+    direction = {0: 'n', 90: 'e', 180: 's', 270: 'w'}
+    orientations = []
+    for n, page in enumerate(pdfinfo):
+        angle = page.rotation or 0
+        if angle != 0:
+            orientations.append('{0}{1}'.format(n + 1, direction.get(angle, '')))
+    if orientations:
+        log.info('Page orientations detected: %s', ' '.join(orientations))
+
+
+def create_input_file(options, work_folder):
+    if options.input_file == '-':
+        # stdin
+        log.info('reading file from standard input')
+        target = os.path.join(work_folder, 'stdin')
+        with open(target, 'wb') as stream_buffer:
+            copyfileobj(sys.stdin.buffer, stream_buffer)
+        return target
+    else:
+        try:
+            target = os.path.join(work_folder, 'origin')
+            re_symlink(options.input_file, target)
+            return target
+        except FileNotFoundError:
+            raise InputFileError(f"File not found - {options.input_file}")
+
+
+def check_requested_output_file(options):
+    if options.output_file == '-':
+        if sys.stdout.isatty():
+            raise BadArgsError(
+                "Output was set to stdout '-' but it looks like stdout "
+                "is connected to a terminal.  Please redirect stdout to a "
+                "file."
+            )
+    elif not is_file_writable(options.output_file):
+        raise OutputFileAccessError(
+            f"Output file location ({options.output_file}) is not a writable file."
+        )
+
+
+def report_output_file_size(options, input_file, output_file):
+    try:
+        output_size = Path(output_file).stat().st_size
+        input_size = Path(input_file).stat().st_size
+    except FileNotFoundError:
+        return  # Outputting to stream or something
+    ratio = output_size / input_size
+    if ratio < 1.35 or input_size < 25000:
+        return  # Seems fine
+
+    reasons = []
+    image_preproc = {
+        'deskew',
+        'clean_final',
+        'remove_background',
+        'oversample',
+        'force_ocr',
+    }
+    for arg in image_preproc:
+        if getattr(options, arg, False):
+            reasons.append(
+                f"The argument --{arg.replace('_', '-')} was issued, causing transcoding."
+            )
+
+    if options.optimize == 0:
+        reasons.append("Optimization was disabled.")
+    else:
+        image_optimizers = {
+            'jbig2': jbig2enc.available(),
+            'pngquant': pngquant.available(),
+        }
+        for name, available in image_optimizers.items():
+            if not available:
+                reasons.append(
+                    f"The optional dependency '{name}' was not found, so some image "
+                    f"optimizations could not be attempted."
+                )
+
+    if reasons:
+        explanation = "Possible reasons for this include:\n" + '\n'.join(reasons) + "\n"
+    else:
+        explanation = "No reason for this increase is known.  Please report this issue."
+
+    log.warning(
+        f"The output file size is {ratio:.2f}× larger than the input file.\n"
+        f"{explanation}"
+    )
+
+
+def check_dependency_versions(options):
+    check_external_program(
+        program='tesseract',
+        package={'darwin': 'tesseract', 'linux': 'tesseract-ocr'},
+        version_checker=tesseract.version,
+        need_version='4.0.0',  # using backport for Travis CI
+    )
+    check_external_program(
+        program='gs',
+        package='ghostscript',
+        version_checker=ghostscript.version,
+        need_version='9.15',  # limited by Travis CI / Ubuntu 14.04 backports
+    )
+    if ghostscript.version() == '9.24':
+        raise MissingDependencyError(
+            "Ghostscript 9.24 contains serious regressions and is not "
+            "supported. Please upgrade to Ghostscript 9.25 or use an older "
+            "version."
+        )
+    check_external_program(
+        program='qpdf',
+        package='qpdf',
+        version_checker=qpdf.version,
+        need_version='8.0.2',
+    )

src/ocrmypdf/_version.py

@@ -0,0 +1,24 @@
+# © 2017 James R. Barlow: github.com/jbarlow83
+#
+# This file is part of OCRmyPDF.
+#
+# OCRmyPDF is free software: you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# OCRmyPDF is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
+
+
+import pkg_resources
+
+PROGRAM_NAME = 'ocrmypdf'
+
+# Official PEP 396
+__version__ = pkg_resources.get_distribution('ocrmypdf').version

src/ocrmypdf/api.py

@@ -0,0 +1,250 @@
+# © 2019 James R. Barlow: github.com/jbarlow83
+#
+# This file is part of OCRmyPDF.
+#
+# OCRmyPDF is free software: you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# OCRmyPDF is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
+
+import logging
+import os
+import sys
+from enum import IntEnum
+from pathlib import Path
+
+from tqdm import tqdm
+
+from ._sync import run_pipeline
+from ._validation import check_options
+from .cli import parser
+
+
+class TqdmConsole:
+    """Wrapper to log messages in a way that is compatible with tqdm progress bar"""
+
+    def __init__(self, file):
+        self.file = file
+        self.py36 = sys.version_info[0:2] == (3, 6)
+
+    def write(self, msg):
+        # When no progress bar is active, tqdm.write() routes to print()
+        if self.py36:
+            if msg.strip() != '':
+                tqdm.write(msg.rstrip(), end='\n', file=self.file)
+        else:
+            tqdm.write(msg.rstrip(), end='\n', file=self.file)
+
+    def flush(self):
+        if hasattr(self.file, "flush"):
+            self.file.flush()
+
+
+class Verbosity(IntEnum):
+    """Verbosity level for configure_logging."""
+
+    quiet = -1  #: Suppress most messages
+    default = 0  #: Default level of logging
+    debug = 1  #: Output ocrmypdf debug messages
+    debug_all = 2  #: More detailed debugging from ocrmypdf and dependent modules
+
+
+def configure_logging(verbosity, progress_bar_friendly=True, manage_root_logger=False):
+    """Set up logging.
+
+    Library users may wish to use this function if they want their log output to be
+    similar to ocrmypdf command line interface. If not used, the external application
+    should configure logging on its own.
+
+    ocrmypdf will perform all of its logging under the ``"ocrmypdf"`` logging namespace.
+    In addition, ocrmypdf imports pdfminer, which logs under ``"pdfminer"``. A library
+    user may wish to configure both; note that pdfminer is extremely chatty at the log
+    level ``logging.INFO``.
+
+    Library users may perform additional configuration afterwards.
+
+    Args:
+        verbosity (Verbosity): Verbosity level.
+        progress_bar_friendly (bool): Install the TqdmConsole log handler, which is
+            compatible with the tqdm progress bar; without this log messages will
+            overwrite the progress bar
+        manage_root_logger (bool): Configure the process's root logger, to ensure
+            all log output is sent through
+    """
+
+    prefix = '' if manage_root_logger else 'ocrmypdf'
+    log = logging.getLogger(prefix)
+    log.setLevel(logging.INFO)
+
+    if progress_bar_friendly:
+        console = logging.StreamHandler(stream=TqdmConsole(sys.stderr))
+    else:
+        console = logging.StreamHandler(stream=sys.stderr)
+
+    if verbosity < 0:
+        console.setLevel(logging.ERROR)
+    elif verbosity >= 1:
+        console.setLevel(logging.DEBUG)
+    else:
+        console.setLevel(logging.INFO)
+
+    formatter = logging.Formatter('%(levelname)7s - %(message)s')
+    if verbosity >= 1:
+        log.setLevel(logging.DEBUG)
+    if verbosity >= 2:
+        formatter = logging.Formatter('%(name)s - %(levelname)7s - %(message)s')
+
+    console.setFormatter(formatter)
+    log.addHandler(console)
+
+    if verbosity <= 1:
+        pdfminer_log = logging.getLogger('pdfminer')
+        pdfminer_log.setLevel(logging.ERROR)
+        pil_log = logging.getLogger('PIL')
+        pil_log.setLevel(logging.INFO)
+
+    if manage_root_logger:
+        logging.captureWarnings(True)
+
+
+def create_options(*, input_file, output_file, **kwargs):
+    cmdline = []
+    deferred = []
+
+    for arg, val in kwargs.items():
+        if val is None:
+            continue
+
+        # These arguments with special handling for which we bypass
+        # argparse
+        if arg in {'tesseract_env', 'progress_bar'}:
+            deferred.append((arg, val))
+            continue
+
+        cmd_style_arg = arg.replace('_', '-')
+
+        # Booleans are special: add only if True, omit for False
+        if isinstance(val, bool):
+            if val:
+                cmdline.append(f"--{cmd_style_arg}")
+            continue
+
+        # We have a parameter
+        cmdline.append(f"--{cmd_style_arg}")
+        if isinstance(val, (int, float)):
+            cmdline.append(str(val))
+        elif isinstance(val, str):
+            cmdline.append(val)
+        elif isinstance(val, Path):
+            cmdline.append(str(val))
+        else:
+            raise TypeError(f"{arg}: {val} ({type(val)})")
+
+    cmdline.append(str(input_file))
+    cmdline.append(str(output_file))
+
+    parser.api_mode = True
+    options = parser.parse_args(cmdline)
+    for keyword, val in deferred:
+        setattr(options, keyword, val)
+
+    # If we are running a Tesseract spoof, ensure it knows what the input file is
+    if os.environ.get('PYTEST_CURRENT_TEST') and options.tesseract_env:
+        options.tesseract_env['_OCRMYPDF_TEST_INFILE'] = input_file
+
+    return options
+
+
+def ocr(  # pylint: disable=unused-argument
+    input_file,
+    output_file,
+    *,
+    language=None,
+    image_dpi=None,
+    output_type=None,
+    sidecar=None,
+    jobs=None,
+    use_threads=None,
+    title=None,
+    author=None,
+    subject=None,
+    keywords=None,
+    rotate_pages=None,
+    remove_background=None,
+    deskew=None,
+    clean=None,
+    clean_final=None,
+    unpaper_args=None,
+    oversample=None,
+    remove_vectors=None,
+    threshold=None,
+    force_ocr=None,
+    skip_text=None,
+    redo_ocr=None,
+    skip_big=None,
+    optimize=None,
+    jpg_quality=None,
+    png_quality=None,
+    jbig2_lossy=None,
+    jbig2_page_group_size=None,
+    pages=None,
+    max_image_mpixels=None,
+    tesseract_config=None,
+    tesseract_pagesegmode=None,
+    tesseract_oem=None,
+    pdf_renderer=None,
+    tesseract_timeout=None,
+    rotate_pages_threshold=None,
+    pdfa_image_compression=None,
+    user_words=None,
+    user_patterns=None,
+    fast_web_view=None,
+    keep_temporary_files=None,
+    progress_bar=None,
+    tesseract_env=None,
+):
+    """Run OCRmyPDF on one PDF or image.
+
+    For most arguments, see documentation for the equivalent command line parameter.
+    A few specific arguments are discussed here:
+
+    Args:
+        use_threads (bool): Use worker threads instead of processes. This reduces
+            performance but may make debugging easier since it is easier to set
+            breakpoints.
+        tesseract_env (dict): Override environment variables for Tesseract
+    Raises:
+        ocrmypdf.PdfMergeFailedError: If the input PDF is malformed, preventing merging
+            with the OCR layer.
+        ocrmypdf.MissingDependencyError: If a required dependency program is missing or
+            was not found on PATH.
+        ocrmypdf.UnsupportedImageFormatError: If the input file type was an image that
+            could not be read, or some other file type that is not a PDF.
+        ocrmypdf.DpiError: If the input file is an image, but the resolution of the
+            image is not credible (allowing it to proceed would cause poor OCR).
+        ocrmypdf.OutputFileAccessError: If an attempt to write to the intended output
+            file failed.
+        ocrmypdf.PriorOcrFoundError: If the input PDF seems to have OCR or digital
+            text already, and settings did not tell us to proceed.
+        ocrmypdf.InputFileError: Any other problem with the input file.
+        ocrmypdf.SubprocessOutputError: Any error related to executing a subprocess.
+        ocrmypdf.EncryptedPdfERror: If the input PDF is encrypted (password protected).
+            OCRmyPDF does not remove passwords.
+        ocrmypdf.TesseractConfigError: If Tesseract reported its configuration was not
+            valid.
+
+    Returns:
+        :class:`ocrmypdf.ExitCode`
+    """
+
+    options = create_options(**locals())
+    check_options(options)
+    return run_pipeline(options, api=True)

src/ocrmypdf/cli.py

@@ -0,0 +1,491 @@
+# © 2015-19 James R. Barlow: github.com/jbarlow83
+#
+# This file is part of OCRmyPDF.
+#
+# OCRmyPDF is free software: you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# OCRmyPDF is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
+
+import argparse
+
+from ._version import PROGRAM_NAME as _PROGRAM_NAME
+from ._version import __version__ as _VERSION
+
+
+def numeric(basetype, min_=None, max_=None):
+    """Validator for numeric params"""
+    min_ = basetype(min_) if min_ is not None else None
+    max_ = basetype(max_) if max_ is not None else None
+
+    def _numeric(string):
+        value = basetype(string)
+        if (min_ is not None and value < min_) or (max_ is not None and value > max_):
+            msg = "%r not in valid range %r" % (string, (min_, max_))
+            raise argparse.ArgumentTypeError(msg)
+        return value
+
+    _numeric.__name__ = basetype.__name__
+    return _numeric
+
+
+class ArgumentParser(argparse.ArgumentParser):
+    """Override parser's default behavior of calling sys.exit()
+
+    https://stackoverflow.com/questions/5943249/python-argparse-and-controlling-overriding-the-exit-status-code
+    """
+
+    def __init__(self, *args, **kwargs):
+        super().__init__(*args, **kwargs)
+        self.api_mode = False
+
+    def error(self, message):
+        if not self.api_mode:
+            super().error(message)
+            return
+        raise ValueError(message)
+
+
+parser = ArgumentParser(
+    prog=_PROGRAM_NAME,
+    fromfile_prefix_chars='@',
+    formatter_class=argparse.RawDescriptionHelpFormatter,
+    description="""\
+Generates a searchable PDF or PDF/A from a regular PDF.
+
+OCRmyPDF rasterizes each page of the input PDF, optionally corrects page
+rotation and performs image processing, runs the Tesseract OCR engine on the
+image, and then creates a PDF from the OCR information.
+""",
+    epilog="""\
+OCRmyPDF attempts to keep the output file at about the same size.  If a file
+contains losslessly compressed images, and output file will be losslessly
+compressed as well.
+
+PDF is a page description file that attempts to preserve a layout exactly.
+A PDF can contain vector objects (such as text or lines) and raster objects
+(images).  A page might have multiple images.  OCRmyPDF is prepared to deal
+with the wide variety of PDFs that exist in the wild.
+
+When a PDF page contains text, OCRmyPDF assumes that the page has already
+been OCRed or is a "born digital" page that should not be OCRed.  The default
+behavior is to exit in this case without producing a file.  You can use the
+option --skip-text to ignore pages with text, or --force-ocr to rasterize
+all objects on the page and produce an image-only PDF as output.
+
+    ocrmypdf --skip-text file_with_some_text_pages.pdf output.pdf
+
+    ocrmypdf --force-ocr word_document.pdf output.pdf
+
+If you are concerned about long-term archiving of PDFs, use the default option
+--output-type pdfa which converts the PDF to a standardized PDF/A-2b.  This
+converts images to sRGB colorspace, removes some features from the PDF such
+as Javascript or forms. If you want to minimize the number of changes made to
+your PDF, use --output-type pdf.
+
+If OCRmyPDF is given an image file as input, it will attempt to convert the
+image to a PDF before processing.  For more control over the conversion of
+images to PDF, use the Python package img2pdf or other image to PDF software.
+
+For example, this command uses img2pdf to convert all .png files beginning
+with the 'page' prefix to a PDF, fitting each image on A4-sized paper, and
+sending the result to OCRmyPDF through a pipe.  img2pdf is a dependency of
+ocrmypdf so it is already installed.
+
+    img2pdf --pagesize A4 page*.png | ocrmypdf - myfile.pdf
+
+Online documentation is located at:
+    https://ocrmypdf.readthedocs.io/en/latest/introduction.html
+
+""",
+)
+
+parser.add_argument(
+    'input_file',
+    metavar="input_pdf_or_image",
+    help="PDF file containing the images to be OCRed (or '-' to read from "
+    "standard input)",
+)
+parser.add_argument(
+    'output_file',
+    metavar="output_pdf",
+    help="Output searchable PDF file (or '-' to write to standard output). "
+    "Existing files will be ovewritten. If same as input file, the "
+    "input file will be updated only if processing is successful.",
+)
+parser.add_argument(
+    '-l',
+    '--language',
+    action='append',
+    help="Language(s) of the file to be OCRed (see tesseract --list-langs for "
+    "all language packs installed in your system). Use -l eng+deu for "
+    "multiple languages.",
+)
+parser.add_argument(
+    '--image-dpi',
+    metavar='DPI',
+    type=int,
+    help="For input image instead of PDF, use this DPI instead of file's.",
+)
+parser.add_argument(
+    '--output-type',
+    choices=['pdfa', 'pdf', 'pdfa-1', 'pdfa-2', 'pdfa-3'],
+    default='pdfa',
+    help="Choose output type. 'pdfa' creates a PDF/A-2b compliant file for "
+    "long term archiving (default, recommended) but may not suitable "
+    "for users who want their file altered as little as possible. 'pdfa' "
+    "also has problems with full Unicode text. 'pdf' attempts to "
+    "preserve file contents as much as possible. 'pdf-a1' creates a "
+    "PDF/A1-b file. 'pdf-a2' is equivalent to 'pdfa'. 'pdf-a3' creates a "
+    "PDF/A3-b file.",
+)
+
+# Use null string '\0' as sentinel to indicate the user supplied no argument,
+# since that is the only invalid character for filepaths on all platforms
+# bool('\0') is True in Python
+parser.add_argument(
+    '--sidecar',
+    nargs='?',
+    const='\0',
+    default=None,
+    metavar='FILE',
+    help="Generate sidecar text files that contain the same text recognized "
+    "by Tesseract. This may be useful for building a OCR text database. "
+    "If FILE is omitted, the sidecar file be named {output_file}.txt "
+    "If FILE is set to '-', the sidecar is written to stdout (a "
+    "convenient way to preview OCR quality). The output file and sidecar "
+    "may not both use stdout at the same time.",
+)
+
+parser.add_argument(
+    '--version',
+    action='version',
+    version=_VERSION,
+    help="Print program version and exit",
+)
+
+jobcontrol = parser.add_argument_group("Job control options")
+jobcontrol.add_argument(
+    '-j',
+    '--jobs',
+    metavar='N',
+    type=numeric(int, 0, 256),
+    help="Use up to N CPU cores simultaneously (default: use all).",
+)
+jobcontrol.add_argument(
+    '-q', '--quiet', action='store_true', help="Suppress INFO messages"
+)
+jobcontrol.add_argument(
+    '-v',
+    '--verbose',
+    type=numeric(int, 0, 2),
+    default=0,
+    const=1,
+    nargs='?',
+    help="Print more verbose messages for each additional verbose level. Use "
+    "`-v 1` typically for much more detailed logging. Higher numbers "
+    "are probably only useful in debugging.",
+)
+jobcontrol.add_argument(
+    '--no-progress-bar',
+    action='store_false',
+    dest='progress_bar',
+    help=argparse.SUPPRESS,
+)
+jobcontrol.add_argument('--use-threads', action='store_true', help=argparse.SUPPRESS)
+
+metadata = parser.add_argument_group(
+    "Metadata options",
+    "Set output PDF/A metadata (default: copy input document's metadata)",
+)
+metadata.add_argument(
+    '--title', type=str, help="Set document title (place multiple words in quotes)"
+)
+metadata.add_argument('--author', type=str, help="Set document author")
+metadata.add_argument('--subject', type=str, help="Set document subject description")
+metadata.add_argument('--keywords', type=str, help="Set document keywords")
+
+preprocessing = parser.add_argument_group(
+    "Image preprocessing options",
+    "Options to improve the quality of the final PDF and OCR",
+)
+preprocessing.add_argument(
+    '-r',
+    '--rotate-pages',
+    action='store_true',
+    help="Automatically rotate pages based on detected text orientation",
+)
+preprocessing.add_argument(
+    '--remove-background',
+    action='store_true',
+    help="Attempt to remove background from gray or color pages, setting it "
+    "to white ",
+)
+preprocessing.add_argument(
+    '-d', '--deskew', action='store_true', help="Deskew each page before performing OCR"
+)
+preprocessing.add_argument(
+    '-c',
+    '--clean',
+    action='store_true',
+    help="Clean pages from scanning artifacts before performing OCR, and send "
+    "the cleaned page to OCR, but do not include the cleaned page in "
+    "the output",
+)
+preprocessing.add_argument(
+    '-i',
+    '--clean-final',
+    action='store_true',
+    help="Clean page as above, and incorporate the cleaned image in the final "
+    "PDF.  Might remove desired content.",
+)
+preprocessing.add_argument(
+    '--unpaper-args',
+    type=str,
+    default=None,
+    help="A quoted string of arguments to pass to unpaper. Requires --clean. "
+    "Example: --unpaper-args '--layout double'.",
+)
+preprocessing.add_argument(
+    '--oversample',
+    metavar='DPI',
+    type=numeric(int, 0, 5000),
+    default=0,
+    help="Oversample images to at least the specified DPI, to improve OCR "
+    "results slightly",
+)
+preprocessing.add_argument(
+    '--remove-vectors',
+    action='store_true',
+    help="EXPERIMENTAL. Mask out any vector objects in the PDF so that they "
+    "will not be included in OCR. This can eliminate false characters.",
+)
+preprocessing.add_argument(
+    '--threshold',
+    action='store_true',
+    help="EXPERIMENTAL. Threshold image to 1bpp before sending it to Tesseract for OCR. Can "
+    "improve OCR quality compared to Tesseract's thresholder.",
+)
+
+ocrsettings = parser.add_argument_group("OCR options", "Control how OCR is applied")
+ocrsettings.add_argument(
+    '-f',
+    '--force-ocr',
+    action='store_true',
+    help="Rasterize any text or vector objects on each page, apply OCR, and "
+    "save the rastered output (this rewrites the PDF)",
+)
+ocrsettings.add_argument(
+    '-s',
+    '--skip-text',
+    action='store_true',
+    help="Skip OCR on any pages that already contain text, but include the "
+    "page in final output; useful for PDFs that contain a mix of "
+    "images, text pages, and/or previously OCRed pages",
+)
+ocrsettings.add_argument(
+    '--redo-ocr',
+    action='store_true',
+    help="Attempt to detect and remove the hidden OCR layer from files that "
+    "were previously OCRed with OCRmyPDF or another program. Apply OCR "
+    "to text found in raster images. Existing visible text objects will "
+    "not be changed. If there is no existing OCR, OCR will be added.",
+)
+ocrsettings.add_argument(
+    '--skip-big',
+    type=numeric(float, 0, 5000),
+    metavar='MPixels',
+    help="Skip OCR on pages larger than the specified amount of megapixels, "
+    "but include skipped pages in final output",
+)
+
+optimizing = parser.add_argument_group(
+    "Optimization options", "Control how the PDF is optimized after OCR"
+)
+optimizing.add_argument(
+    '-O',
+    '--optimize',
+    type=int,
+    choices=range(0, 4),
+    default=1,
+    help=(
+        "Control how PDF is optimized after processing:"
+        "0 - do not optimize; "
+        "1 - do safe, lossless optimizations (default); "
+        "2 - do some lossy optimizations; "
+        "3 - do aggressive lossy optimizations (including lossy JBIG2)"
+    ),
+)
+optimizing.add_argument(
+    '--jpeg-quality',
+    type=numeric(int, 0, 100),
+    default=0,
+    metavar='Q',
+    help=(
+        "Adjust JPEG quality level for JPEG optimization. "
+        "100 is best quality and largest output size; "
+        "1 is lowest quality and smallest output; "
+        "0 uses the default."
+    ),
+)
+optimizing.add_argument(
+    '--jpg-quality',
+    type=numeric(int, 0, 100),
+    default=0,
+    metavar='Q',
+    dest='jpeg_quality',
+    help=argparse.SUPPRESS,  # Alias for --jpeg-quality
+)
+optimizing.add_argument(
+    '--png-quality',
+    type=numeric(int, 0, 100),
+    default=0,
+    metavar='Q',
+    help=(
+        "Adjust PNG quality level to use when quantizing PNGs. "
+        "Values have same meaning as with --jpeg-quality"
+    ),
+)
+optimizing.add_argument(
+    '--jbig2-lossy',
+    action='store_true',
+    help=(
+        "Enable JBIG2 lossy mode (better compression, not suitable for some "
+        "use cases - see documentation)."
+    ),
+)
+optimizing.add_argument(
+    '--jbig2-page-group-size',
+    type=numeric(int, 1, 10000),
+    default=0,
+    metavar='N',
+    # Adjust number of pages to consider at once for JBIG2 compression
+    help=argparse.SUPPRESS,
+)
+
+advanced = parser.add_argument_group(
+    "Advanced", "Advanced options to control Tesseract's OCR behavior"
+)
+advanced.add_argument(
+    '--pages',
+    type=str,
+    help="Limit OCR to the specified pages (ranges or comma separated), skipping others",
+)
+advanced.add_argument(
+    '--max-image-mpixels',
+    action='store',
+    type=numeric(float, 0),
+    metavar='MPixels',
+    help="Set maximum number of pixels to unpack before treating an image as a "
+    "decompression bomb",
+    default=128.0,
+)
+advanced.add_argument(
+    '--tesseract-config',
+    action='append',
+    metavar='CFG',
+    default=[],
+    help="Additional Tesseract configuration files -- see documentation",
+)
+advanced.add_argument(
+    '--tesseract-pagesegmode',
+    action='store',
+    type=int,
+    metavar='PSM',
+    choices=range(0, 14),
+    help="Set Tesseract page segmentation mode (see tesseract --help)",
+)
+advanced.add_argument(
+    '--tesseract-oem',
+    action='store',
+    type=int,
+    metavar='MODE',
+    choices=range(0, 4),
+    help=(
+        "Set Tesseract 4.0 OCR engine mode: "
+        "0 - original Tesseract only; "
+        "1 - neural nets LSTM only; "
+        "2 - Tesseract + LSTM; "
+        "3 - default."
+    ),
+)
+advanced.add_argument(
+    '--pdf-renderer',
+    choices=['auto', 'hocr', 'sandwich'],
+    default='auto',
+    help="Choose OCR PDF renderer - the default option is to let OCRmyPDF "
+    "choose.  See documentation for discussion.",
+)
+advanced.add_argument(
+    '--tesseract-timeout',
+    default=180.0,
+    type=numeric(float, 0),
+    metavar='SECONDS',
+    help='Give up on OCR after the timeout, but copy the preprocessed page '
+    'into the final output',
+)
+advanced.add_argument(
+    '--rotate-pages-threshold',
+    default=14.0,
+    type=numeric(float, 0, 1000),
+    metavar='CONFIDENCE',
+    help="Only rotate pages when confidence is above this value (arbitrary "
+    "units reported by tesseract)",
+)
+advanced.add_argument(
+    '--pdfa-image-compression',
+    choices=['auto', 'jpeg', 'lossless'],
+    default='auto',
+    help="Specify how to compress images in the output PDF/A. 'auto' lets "
+    "OCRmyPDF decide.  'jpeg' changes all grayscale and color images to "
+    "JPEG compression.  'lossless' uses PNG-style lossless compression "
+    "for all images.  Monochrome images are always compressed using a "
+    "lossless codec.  Compression settings "
+    "are applied to all pages, including those for which OCR was "
+    "skipped.  Not supported for --output-type=pdf ; that setting "
+    "preserves the original compression of all images.",
+)
+advanced.add_argument(
+    '--user-words',
+    metavar='FILE',
+    help="Specify the location of the Tesseract user words file. This is a "
+    "list of words Tesseract should consider while performing OCR in "
+    "addition to its standard language dictionaries. This can improve "
+    "OCR quality especially for specialized and technical documents.",
+)
+advanced.add_argument(
+    '--user-patterns',
+    metavar='FILE',
+    help="Specify the location of the Tesseract user patterns file.",
+)
+advanced.add_argument(
+    '--fast-web-view',
+    type=numeric(float, 0),
+    default=1.0,
+    metavar="MEGABYTES",
+    help="If the size of file is more than this threshold (in MB), then "
+    "linearize the PDF for fast web viewing. This allows the PDF to be "
+    "displayed before it is fully downloaded in web browsers, but increases "
+    "the space required slightly. By default we skip this for small files "
+    "which do not benefit. If the threshold is 0 it will be apply to all files. "
+    "Set the threshold very high to disable.",
+)
+
+debugging = parser.add_argument_group(
+    "Debugging", "Arguments to help with troubleshooting and debugging"
+)
+debugging.add_argument(
+    '-k',
+    '--keep-temporary-files',
+    action='store_true',
+    help="Keep temporary files (helpful for debugging)",
+)
+debugging.add_argument('--tesseract-env', type=str, help=argparse.SUPPRESS)

src/ocrmypdf/exceptions.py

@@ -0,0 +1,115 @@
+# © 2016 James R. Barlow: github.com/jbarlow83
+#
+# This file is part of OCRmyPDF.
+#
+# OCRmyPDF is free software: you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# OCRmyPDF is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
+
+
+from enum import IntEnum
+from textwrap import dedent
+
+
+class ExitCode(IntEnum):
+    ok = 0
+    bad_args = 1
+    input_file = 2
+    missing_dependency = 3
+    invalid_output_pdf = 4
+    file_access_error = 5
+    already_done_ocr = 6
+    child_process_error = 7
+    encrypted_pdf = 8
+    invalid_config = 9
+    pdfa_conversion_failed = 10
+    other_error = 15
+    ctrl_c = 130
+
+
+class ExitCodeException(Exception):
+    exit_code = ExitCode.other_error
+    message = ""
+
+    def __str__(self):
+        super_msg = super().__str__()  # Don't do str(super())
+        if self.message:
+            return self.message.format(super_msg)
+        return super_msg
+
+
+class BadArgsError(ExitCodeException):
+    exit_code = ExitCode.bad_args
+
+
+class PdfMergeFailedError(ExitCodeException):
+    exit_code = ExitCode.input_file
+    message = dedent(
+        '''\
+        Failed to merge PDF image layer with OCR layer
+
+        Usually this happens because the input PDF file is malformed and
+        ocrmypdf cannot automatically correct the problem on its own.
+
+        Try using
+            ocrmypdf --pdf-renderer sandwich  [..other args..]
+        '''
+    )
+
+
+class MissingDependencyError(ExitCodeException):
+    exit_code = ExitCode.missing_dependency
+
+
+class UnsupportedImageFormatError(ExitCodeException):
+    exit_code = ExitCode.input_file
+
+
+class DpiError(ExitCodeException):
+    exit_code = ExitCode.input_file
+
+
+class OutputFileAccessError(ExitCodeException):
+    exit_code = ExitCode.file_access_error
+
+
+class PriorOcrFoundError(ExitCodeException):
+    exit_code = ExitCode.already_done_ocr
+
+
+class InputFileError(ExitCodeException):
+    exit_code = ExitCode.input_file
+
+
+class SubprocessOutputError(ExitCodeException):
+    exit_code = ExitCode.child_process_error
+
+
+class EncryptedPdfError(ExitCodeException):
+    exit_code = ExitCode.encrypted_pdf
+    message = dedent(
+        '''\
+        Input PDF is encrypted. The encryption must be removed to
+        perform OCR.
+
+        For information about this PDF's security use
+            qpdf --show-encryption infilename
+
+        You can remove the encryption using
+            qpdf --decrypt [--password=[password]] infilename
+        '''
+    )
+
+
+class TesseractConfigError(ExitCodeException):
+    exit_code = ExitCode.invalid_config
+    message = "Error occurred while parsing a Tesseract configuration file"

src/ocrmypdf/exec/__init__.py

@@ -0,0 +1,177 @@
+# © 2016 James R. Barlow: github.com/jbarlow83
+#
+# This file is part of OCRmyPDF.
+#
+# OCRmyPDF is free software: you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# OCRmyPDF is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
+
+"""Wrappers to manage subprocess calls"""
+
+import logging
+import os
+import re
+import sys
+from collections.abc import Mapping
+from subprocess import PIPE, STDOUT, CalledProcessError, run
+
+from ..exceptions import ExitCode, MissingDependencyError
+
+log = logging.Logger(__name__)
+
+
+def get_version(program, *, version_arg='--version', regex=r'(\d+(\.\d+)*)', env=None):
+    "Get the version of the specified program"
+    args_prog = [program, version_arg]
+    try:
+        proc = run(
+            args_prog,
+            close_fds=True,
+            universal_newlines=True,
+            stdout=PIPE,
+            stderr=STDOUT,
+            check=True,
+            env=env,
+        )
+        output = proc.stdout
+    except FileNotFoundError as e:
+        raise MissingDependencyError(
+            f"Could not find program '{program}' on the PATH"
+        ) from e
+    except CalledProcessError as e:
+        if e.returncode != 0:
+            raise MissingDependencyError(
+                f"Ran program '{program}' but it exited with an error:\n{e.output}"
+            ) from e
+        raise MissingDependencyError(
+            f"Could not find program '{program}' on the PATH"
+        ) from e
+    try:
+        version = re.match(regex, output.strip()).group(1)
+    except AttributeError as e:
+        raise MissingDependencyError(
+            f"The program '{program}' did not report its version. "
+            f"Message was:\n{output}"
+        )
+
+    return version
+
+
+missing_program = '''
+The program '{program}' could not be executed or was not found on your
+system PATH.
+'''
+
+missing_optional_program = '''
+The program '{program}' could not be executed or was not found on your
+system PATH.  This program is required when you use the
+{required_for} arguments.  You could try omitting these arguments, or install
+the package.
+'''
+
+missing_recommend_program = '''
+The program '{program}' could not be executed or was not found on your
+system PATH.  This program is recommended when using the {required_for} arguments,
+but not required, so we will proceed.  For best results, install the program.
+'''
+
+old_version = '''
+OCRmyPDF requires '{program}' {need_version} or higher.  Your system appears
+to have {found_version}.  Please update this program.
+'''
+
+old_version_required_for = '''
+OCRmyPDF requires '{program}' {need_version} or higher when run with the
+{required_for} arguments.  If you omit these arguments, OCRmyPDF may be able to
+proceed.  For best results, install the program.
+'''
+
+osx_install_advice = '''
+If you have homebrew installed, try these command to install the missing
+package:
+    brew install {package}
+'''
+
+linux_install_advice = '''
+On systems with the aptitude package manager (Debian, Ubuntu), try these
+commands:
+    sudo apt-get update
+    sudo apt-get install {package}
+
+On RPM-based systems (Red Hat, Fedora), search for instructions on
+installing the RPM for {program}.
+'''
+
+
+def _get_platform():
+    if sys.platform.startswith('freebsd'):
+        return 'freebsd'
+    elif sys.platform.startswith('linux'):
+        return 'linux'
+    return sys.platform
+
+
+def _error_trailer(program, package, **kwargs):
+    if isinstance(package, Mapping):
+        package = package[_get_platform()]
+
+    if _get_platform() == 'darwin':
+        log.info(osx_install_advice.format(**locals()))
+    elif _get_platform() == 'linux':
+        log.info(linux_install_advice.format(**locals()))
+
+
+def _error_missing_program(program, package, required_for, recommended):
+    if required_for:
+        log.error(missing_optional_program.format(**locals()))
+    elif recommended:
+        log.info(missing_recommend_program.format(**locals()))
+    else:
+        log.error(missing_program.format(**locals()))
+    _error_trailer(**locals())
+
+
+def _error_old_version(program, package, need_version, found_version, required_for):
+    if required_for:
+        log.error(old_version_required_for.format(**locals()))
+    else:
+        log.error(old_version.format(**locals()))
+    _error_trailer(**locals())
+
+
+def check_external_program(
+    *,
+    program,
+    package,
+    version_checker,
+    need_version,
+    required_for=None,
+    recommended=False,
+    **kwargs,  # To consume log parameter
+):
+    if kwargs:
+        if not 'log' in kwargs:
+            log.warning('check_external_program(log=...) is deprecated')
+    try:
+        found_version = version_checker()
+    except (CalledProcessError, FileNotFoundError, MissingDependencyError):
+        _error_missing_program(program, package, required_for, recommended)
+        if not recommended:
+            raise MissingDependencyError()
+        return
+
+    if found_version < need_version:
+        _error_old_version(program, package, need_version, found_version, required_for)
+        if not recommended:
+            raise MissingDependencyError()
+
+    log.debug('Found %s %s', program, found_version)

src/ocrmypdf/exec/ghostscript.py

@@ -0,0 +1,305 @@
+# © 2017 James R. Barlow: github.com/jbarlow83
+#
+# This file is part of OCRmyPDF.
+#
+# OCRmyPDF is free software: you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# OCRmyPDF is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
+
+"""Interface to Ghostscript executable"""
+
+import logging
+import re
+import warnings
+from functools import lru_cache
+from os import fspath
+from shutil import copy
+from subprocess import PIPE, STDOUT, run
+from tempfile import NamedTemporaryFile
+
+from PIL import Image
+
+from ..exceptions import SubprocessOutputError
+from . import get_version
+
+gslog = logging.getLogger()
+
+
+@lru_cache(maxsize=1)
+def version():
+    return get_version('gs')
+
+
+def jpeg_passthrough_available():
+    """Returns True if the installed version of Ghostscript supports JPEG passthru
+
+    Prior to 9.23, Ghostscript decode and re-encoded JPEGs internally. In 9.23
+    it gained the ability to keep JPEGs unmodified. However, the 9.23
+    implementation was buggy and would deletes the last two bytes of images in
+    some cases, as reported here.
+    https://bugs.ghostscript.com/show_bug.cgi?id=699216
+
+    The issue was fixed for 9.24, hence that is the first version we consider
+    the feature available. (However, we don't use 9.24 at all, so the first
+    version that allows JPEG passthrough is 9.25.
+
+    """
+    return version() >= '9.24'
+
+
+def _gs_error_reported(stream):
+    return re.search(r'error', stream, flags=re.IGNORECASE)
+
+
+def extract_text(input_file, pageno=1):
+    """Use the txtwrite device to get text layout information out
+
+    For details on options of -dTextFormat see
+    https://www.ghostscript.com/doc/current/VectorDevices.htm#TXT
+
+    Format is like
+    <page>
+    <line>
+    <span bbox="left top right bottom" font="..." size="...">
+    <char bbox="...." c="X"/>
+
+    :param pageno: number of page to extract, or all pages if None
+    :return: XML-ish text representation in bytes
+    """
+
+    if pageno is not None:
+        pages = ['-dFirstPage=%i' % pageno, '-dLastPage=%i' % pageno]
+    else:
+        pages = []
+
+    args_gs = (
+        [
+            'gs',
+            '-dQUIET',
+            '-dSAFER',
+            '-dBATCH',
+            '-dNOPAUSE',
+            '-sDEVICE=txtwrite',
+            '-dTextFormat=0',
+        ]
+        + pages
+        + ['-o', '-', fspath(input_file)]
+    )
+
+    p = run(args_gs, stdout=PIPE, stderr=PIPE)
+    if p.returncode != 0:
+        raise SubprocessOutputError(
+            'Ghostscript text extraction failed\n%s\n%s\n%s'
+            % (input_file, p.stdout.decode(), p.stderr.decode())
+        )
+
+    return p.stdout
+
+
+def rasterize_pdf(
+    input_file,
+    output_file,
+    xres,
+    yres,
+    raster_device,
+    log,
+    pageno=1,
+    page_dpi=None,
+    rotation=None,
+    filter_vector=False,
+):
+    """Rasterize one page of a PDF at resolution (xres, yres) in canvas units.
+
+    The image is sized to match the integer pixels dimensions implied by
+    (xres, yres) even if those numbers are noninteger. The image's DPI will
+     be overridden with the values in page_dpi.
+
+    :param input_file: pathlike
+    :param output_file: pathlike
+    :param xres: resolution at which to rasterize page
+    :param yres:
+    :param raster_device:
+    :param log:
+    :param pageno: page number to rasterize (beginning at page 1)
+    :param page_dpi: resolution tuple (x, y) overriding output image DPI
+    :param rotation: 0, 90, 180, 270: clockwise angle to rotate page
+    :param filter_vector: if True, remove vector graphics objects
+    :return:
+    """
+    res = round(xres, 6), round(yres, 6)
+    if not page_dpi:
+        page_dpi = res
+    if not log:
+        log = gslog
+
+    with NamedTemporaryFile(delete=True) as tmp:
+        args_gs = (
+            [
+                'gs',
+                '-dQUIET',
+                '-dSAFER',
+                '-dBATCH',
+                '-dNOPAUSE',
+                f'-sDEVICE={raster_device}',
+                f'-dFirstPage={pageno}',
+                f'-dLastPage={pageno}',
+                f'-r{res[0]:f}x{res[1]:f}',
+            ]
+            + (['-dFILTERVECTOR'] if filter_vector else [])
+            + [
+                '-o',
+                tmp.name,
+                '-dAutoRotatePages=/None',  # Probably has no effect on raster
+                '-f',
+                fspath(input_file),
+            ]
+        )
+
+        log.debug(args_gs)
+        p = run(args_gs, stdout=PIPE, stderr=STDOUT, universal_newlines=True)
+        if _gs_error_reported(p.stdout):
+            log.error(p.stdout)
+        elif p.stdout:
+            log.debug(p.stdout)
+
+        if p.returncode != 0:
+            raise SubprocessOutputError('Ghostscript rasterizing failed')
+
+        tmp.seek(0)
+        with Image.open(tmp) as im:
+            if rotation is not None:
+                log.debug("Rotating output by %i", rotation)
+                # rotation is a clockwise angle and Image.ROTATE_* is
+                # counterclockwise so this cancels out the rotation
+                if rotation == 90:
+                    im = im.transpose(Image.ROTATE_90)
+                elif rotation == 180:
+                    im = im.transpose(Image.ROTATE_180)
+                elif rotation == 270:
+                    im = im.transpose(Image.ROTATE_270)
+                if rotation % 180 == 90:
+                    page_dpi = page_dpi[1], page_dpi[0]
+            im.save(fspath(output_file), dpi=page_dpi)
+
+
+def generate_pdfa(
+    pdf_pages,
+    output_file,
+    compression,
+    log,
+    threads=None,  # deprecated parameter
+    pdf_version='1.5',
+    pdfa_part='2',
+):
+    """Generate a PDF/A.
+
+    The pdf_pages, a list files, will be merged into output_file. One or more
+    PDF files may be merged. One of the files in this list must be a pdfmark
+    file that provides Ghostscript with details on how to perform the PDF/A
+    conversion. By default with we pick PDF/A-2b, but this works for 1 or 3.
+
+    compression can be 'jpeg', 'lossless', or an empty string. In 'jpeg',
+    Ghostscript is instructed to convert color and grayscale images to DCT
+    (JPEG encoding). In 'lossless' Ghostscript is told to convert images to
+    Flate (lossless/PNG). If the parameter is omitted Ghostscript is left to
+    make its own decisions about how to encode images; it appears to use a
+    heuristic to decide how to encode images. As of Ghostscript 9.25, we
+    support passthrough JPEG which allows Ghostscript to avoid transcoding
+    images entirely. (The feature was added in 9.23 but broken, and the 9.24
+    release of Ghostscript had regressions, so we don't support it until 9.25.)
+    """
+    if not log:
+        log = gslog
+    if threads is not None:
+        warnings.warn(
+            "use of deprecated parameter 'threads'", category=DeprecationWarning
+        )
+
+    compression_args = []
+    if compression == 'jpeg':
+        compression_args = [
+            "-dAutoFilterColorImages=false",
+            "-dColorImageFilter=/DCTEncode",
+            "-dAutoFilterGrayImages=false",
+            "-dGrayImageFilter=/DCTEncode",
+        ]
+    elif compression == 'lossless':
+        compression_args = [
+            "-dAutoFilterColorImages=false",
+            "-dColorImageFilter=/FlateEncode",
+            "-dAutoFilterGrayImages=false",
+            "-dGrayImageFilter=/FlateEncode",
+        ]
+    else:
+        compression_args = [
+            "-dAutoFilterColorImages=true",
+            "-dAutoFilterGrayImages=true",
+        ]
+
+    # Older versions of Ghostscript expect a leading slash in
+    # sColorConversionStrategy, newer ones should not have it. See Ghostscript
+    # git commit fe1c025d.
+    strategy = 'RGB' if version() >= '9.19' else '/RGB'
+
+    if version() == '9.23':
+        # 9.23: new feature JPEG passthrough is broken in some cases, best to
+        # disable it always
+        # https://bugs.ghostscript.com/show_bug.cgi?id=699216
+        compression_args.append('-dPassThroughJPEGImages=false')
+
+    with NamedTemporaryFile(delete=True) as gs_pdf:
+        # nb no need to specify ProcessColorModel when ColorConversionStrategy
+        # is set; see:
+        # https://bugs.ghostscript.com/show_bug.cgi?id=699392
+        args_gs = (
+            [
+                "gs",
+                "-dQUIET",
+                "-dBATCH",
+                "-dNOPAUSE",
+                "-dSAFER",
+                "-dCompatibilityLevel=" + str(pdf_version),
+                "-sDEVICE=pdfwrite",
+                "-dAutoRotatePages=/None",
+                "-sColorConversionStrategy=" + strategy,
+            ]
+            + compression_args
+            + [
+                "-dJPEGQ=95",
+                "-dPDFA=" + pdfa_part,
+                "-dPDFACompatibilityPolicy=1",
+                "-sOutputFile=" + gs_pdf.name,
+            ]
+        )
+        args_gs.extend(fspath(s) for s in pdf_pages)  # Stringify Path objs
+        log.debug(args_gs)
+        p = run(args_gs, stdout=PIPE, stderr=STDOUT, universal_newlines=True)
+
+        if _gs_error_reported(p.stdout):
+            log.error(p.stdout)
+        elif 'overprint mode not set' in p.stdout:
+            # Unless someone is going to print PDF/A documents on a
+            # magical sRGB printer I can't see the removal of overprinting
+            # being a problem....
+            log.debug(
+                "Ghostscript had to remove PDF 'overprinting' from the "
+                "input file to complete PDF/A conversion. "
+            )
+        else:
+            log.debug(p.stdout)
+
+        if p.returncode == 0:
+            # Ghostscript does not change return code when it fails to create
+            # PDF/A - check PDF/A status elsewhere
+            copy(gs_pdf.name, fspath(output_file))
+        else:
+            raise SubprocessOutputError('Ghostscript PDF/A rendering failed')

src/ocrmypdf/exec/jbig2enc.py

@@ -0,0 +1,61 @@
+# © 2018 James R. Barlow: github.com/jbarlow83
+#
+# This file is part of OCRmyPDF.
+#
+# OCRmyPDF is free software: you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# OCRmyPDF is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
+
+"""Interface to jbig2 executable"""
+
+from functools import lru_cache
+from subprocess import PIPE, run
+
+from ..exceptions import MissingDependencyError
+from . import get_version
+
+
+@lru_cache(maxsize=1)
+def version():
+    return get_version('jbig2', regex=r'jbig2enc (\d+(\.\d+)*).*')
+
+
+def available():
+    try:
+        version()
+    except MissingDependencyError:
+        return False
+    return True
+
+
+def convert_group(*, cwd, infiles, out_prefix):
+    args = [
+        'jbig2',
+        '-b',
+        out_prefix,
+        '-s',  # symbol mode (lossy)
+        # '-r', # refinement mode (lossless symbol mode, currently disabled in
+        # jbig2)
+        '-p',
+    ]
+    args.extend(infiles)
+    proc = run(args, cwd=cwd, stdout=PIPE, stderr=PIPE)
+    proc.check_returncode()
+    return proc
+
+
+def convert_single(*, cwd, infile, outfile):
+    args = ['jbig2', '-p', infile]
+    with open(outfile, 'wb') as fstdout:
+        proc = run(args, cwd=cwd, stdout=fstdout, stderr=PIPE)
+    proc.check_returncode()
+    return proc

src/ocrmypdf/exec/pngquant.py

@@ -0,0 +1,71 @@
+# © 2018 James R. Barlow: github.com/jbarlow83
+#
+# This file is part of OCRmyPDF.
+#
+# OCRmyPDF is free software: you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# OCRmyPDF is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
+
+"""Interface to pngquant executable"""
+
+from functools import lru_cache
+from subprocess import run
+from tempfile import NamedTemporaryFile
+
+from PIL import Image
+
+from ..exceptions import MissingDependencyError
+from . import get_version
+
+
+@lru_cache(maxsize=1)
+def version():
+    return get_version('pngquant', regex=r'(\d+(\.\d+)*).*')
+
+
+def available():
+    try:
+        version()
+    except MissingDependencyError:
+        return False
+    return True
+
+
+def quantize(input_file, output_file, quality_min, quality_max):
+    if input_file.endswith('.jpg'):
+        with Image.open(input_file) as im, NamedTemporaryFile(suffix='.png') as tmp:
+            im.save(tmp)
+            args = [
+                'pngquant',
+                '--force',
+                '--skip-if-larger',
+                '--output',
+                output_file,
+                '--quality',
+                f'{quality_min}-{quality_max}',
+                '--',
+                tmp.name,
+            ]
+            run(args)
+    else:
+        args = [
+            'pngquant',
+            '--force',
+            '--skip-if-larger',
+            '--output',
+            output_file,
+            '--quality',
+            f'{quality_min}-{quality_max}',
+            '--',
+            input_file,
+        ]
+        run(args)

src/ocrmypdf/exec/qpdf.py

@@ -0,0 +1,51 @@
+# © 2017 James R. Barlow: github.com/jbarlow83
+#
+# This file is part of OCRmyPDF.
+#
+# OCRmyPDF is free software: you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# OCRmyPDF is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
+
+"""Interface to qpdf executable"""
+
+from functools import lru_cache
+from os import fspath
+from subprocess import PIPE, STDOUT, CalledProcessError, run
+
+from . import get_version
+
+
+@lru_cache(maxsize=1)
+def version():
+    return get_version('qpdf', regex=r'qpdf version (.+)')
+
+
+def check(input_file, log=None):
+    args_qpdf = ['qpdf', '--check', fspath(input_file)]
+
+    if log is None:
+        import logging as log
+
+    try:
+        run(args_qpdf, stderr=STDOUT, stdout=PIPE, universal_newlines=True, check=True)
+    except CalledProcessError as e:
+        if e.returncode == 2:
+            log.error("%s: not a valid PDF, and could not repair it.", input_file)
+            log.error("Details:")
+            log.error(e.output)
+        elif e.returncode == 3:
+            log.info("qpdf --check returned warnings:")
+            log.info(e.output)
+        else:
+            log.warning(e.output)
+        return False
+    return True

src/ocrmypdf/exec/tesseract.py

@@ -0,0 +1,409 @@
+# © 2017 James R. Barlow: github.com/jbarlow83
+#
+# This file is part of OCRmyPDF.
+#
+# OCRmyPDF is free software: you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# OCRmyPDF is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
+
+"""Interface to Tesseract executable"""
+
+import os
+import shutil
+from collections import namedtuple
+from contextlib import suppress
+import logging
+from os import fspath
+from subprocess import PIPE, STDOUT, CalledProcessError, TimeoutExpired, run
+
+from ..exceptions import (
+    MissingDependencyError,
+    SubprocessOutputError,
+    TesseractConfigError,
+)
+from ..helpers import page_number
+from . import get_version
+
+OrientationConfidence = namedtuple('OrientationConfidence', ('angle', 'confidence'))
+
+HOCR_TEMPLATE = """<?xml version="1.0" encoding="UTF-8"?>
+<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN"
+    "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
+<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
+ <head>
+  <title></title>
+<meta http-equiv="Content-Type" content="text/html;charset=utf-8" />
+  <meta name='ocr-system' content='tesseract 4.0.0' />
+  <meta name='ocr-capabilities' content='ocr_page ocr_carea ocr_par ocr_line ocrx_word ocrp_wconf'/>
+</head>
+<body>
+  <div class='ocr_page' id='page_1' title='image "_blank.png"; bbox 0 0 {0} {1}; ppageno 0'>
+  </div>
+ </body>
+</html>
+"""
+
+
+class TesseractLoggerAdapter(logging.LoggerAdapter):
+    def process(self, msg, kwargs):
+        return '[tesseract] %s' % (msg), kwargs
+
+
+def version(tesseract_env=None):
+    return get_version('tesseract', regex=r'tesseract\s(.+)', env=tesseract_env)
+
+
+def v4(tesseract_env=None):
+    "Is this Tesseract v4.0?"
+    return version(tesseract_env) >= '4'
+
+
+def has_textonly_pdf(tesseract_env=None, langs=None):
+    """Does Tesseract have textonly_pdf capability?
+
+    Available in v4.00.00alpha since January 2017. Best to
+    parse the parameter list.
+    """
+    args_tess = tess_base_args(langs, engine_mode=None) + ['--print-parameters', 'pdf']
+    params = ''
+    try:
+        proc = run(
+            args_tess,
+            check=True,
+            universal_newlines=True,
+            stdout=PIPE,
+            stderr=STDOUT,
+            env=tesseract_env,
+        )
+        params = proc.stdout
+    except CalledProcessError as e:
+        raise MissingDependencyError(
+            "Could not --print-parameters from tesseract"
+        ) from e
+    if 'textonly_pdf' in params:
+        return True
+    return False
+
+
+def has_user_words(tesseract_env=None):
+    """Does Tesseract have --user-words capability?
+
+    Not available in 4.0, but available in 4.1. Also available in 3.x, but
+    we no longer support 3.x.
+    """
+    return version(tesseract_env) >= '4.1'
+
+
+def languages(tesseract_env=None):
+    def lang_error(output):
+        msg = (
+            "Tesseract failed to report available languages.\n"
+            "Output from Tesseract:\n"
+            "-----------\n"
+        )
+        msg += output
+        return msg
+
+    args_tess = ['tesseract', '--list-langs']
+    try:
+        proc = run(
+            args_tess,
+            universal_newlines=True,
+            stdout=PIPE,
+            stderr=STDOUT,
+            check=True,
+            env=tesseract_env,
+        )
+        output = proc.stdout
+    except CalledProcessError as e:
+        raise MissingDependencyError(lang_error(e.output)) from e
+
+    header, *rest = output.splitlines()
+    if not header.startswith('List of available languages'):
+        raise MissingDependencyError(lang_error(output))
+    return set(lang.strip() for lang in rest)
+
+
+def tess_base_args(langs, engine_mode):
+    args = ['tesseract']
+    if langs:
+        args.extend(['-l', '+'.join(langs)])
+    if engine_mode is not None and v4():
+        args.extend(['--oem', str(engine_mode)])
+    return args
+
+
+def get_orientation(input_file, engine_mode, timeout: float, log, tesseract_env=None):
+    args_tesseract = tess_base_args(['osd'], engine_mode) + [
+        '--psm',
+        '0',
+        fspath(input_file),
+        'stdout',
+    ]
+
+    try:
+        p = run(
+            args_tesseract,
+            stdout=PIPE,
+            stderr=STDOUT,
+            timeout=timeout,
+            check=True,
+            env=tesseract_env,
+        )
+        stdout = p.stdout
+    except TimeoutExpired:
+        return OrientationConfidence(angle=0, confidence=0.0)
+    except CalledProcessError as e:
+        tesseract_log_output(log, e.output, input_file)
+        if (
+            b'Too few characters. Skipping this page' in e.output
+            or b'Image too large' in e.output
+        ):
+            return OrientationConfidence(0, 0)
+        raise SubprocessOutputError() from e
+    else:
+        osd = {}
+        for line in stdout.decode().splitlines():
+            line = line.strip()
+            parts = line.split(':', maxsplit=2)
+            if len(parts) == 2:
+                osd[parts[0].strip()] = parts[1].strip()
+
+        angle = int(osd.get('Orientation in degrees', 0))
+        oc = OrientationConfidence(
+            angle=angle, confidence=float(osd.get('Orientation confidence', 0))
+        )
+        return oc
+
+
+def tesseract_log_output(mainlog, stdout, input_file):
+    log = TesseractLoggerAdapter(
+        mainlog, extra=mainlog.extra if hasattr(mainlog, 'extra') else None
+    )
+
+    try:
+        text = stdout.decode()
+    except UnicodeDecodeError:
+        log.error(
+            "command line output was not utf-8. "
+            + "This usually means Tesseract's language packs do not match "
+            "the installed version of Tesseract."
+        )
+        text = stdout.decode('utf-8', 'backslashreplace')
+
+    lines = text.splitlines()
+    for line in lines:
+        if line.startswith("Tesseract Open Source"):
+            continue
+        elif line.startswith("Warning in pixReadMem"):
+            continue
+        elif 'diacritics' in line:
+            log.warning("lots of diacritics - possibly poor OCR")
+        elif line.startswith('OSD: Weak margin'):
+            log.warning("unsure about page orientation")
+        elif 'Error in pixScanForForeground' in line:
+            pass  # Appears to be spurious/problem with nonwhite borders
+        elif 'Error in boxClipToRectangle' in line:
+            pass  # Always appears with pixScanForForeground message
+        elif 'parameter not found: ' in line.lower():
+            log.error(line.strip())
+            problem = line.split('found: ')[1]
+            raise TesseractConfigError(problem)
+        elif 'error' in line.lower() or 'exception' in line.lower():
+            log.error(line.strip())
+        elif 'warning' in line.lower():
+            log.warning(line.strip())
+        elif 'read_params_file' in line.lower():
+            log.error(line.strip())
+        else:
+            log.info(line.strip())
+
+
+def page_timedout(log, input_file, timeout):
+    if timeout == 0:
+        return
+    prefix = f"{(page_number(input_file)):4d}: [tesseract] "
+    log.warning(prefix + " took too long to OCR - skipping")
+
+
+def _generate_null_hocr(output_hocr, output_sidecar, image):
+    """Produce a .hocr file that reports no text detected on a page that is
+    the same size as the input image."""
+    from PIL import Image
+
+    with Image.open(image) as im:
+        w, h = im.size
+
+    with open(output_hocr, 'w', encoding="utf-8") as f:
+        f.write(HOCR_TEMPLATE.format(w, h))
+    with open(output_sidecar, 'w', encoding='utf-8') as f:
+        f.write('[skipped page]')
+
+
+def generate_hocr(
+    input_file,
+    output_files,
+    language: list,
+    engine_mode,
+    tessconfig: list,
+    timeout: float,
+    pagesegmode: int,
+    user_words,
+    user_patterns,
+    tesseract_env,
+    log,
+):
+
+    output_hocr = next(o for o in output_files if o.endswith('.hocr'))
+    output_sidecar = next(o for o in output_files if o.endswith('.txt'))
+    prefix = os.path.splitext(output_hocr)[0]
+
+    args_tesseract = tess_base_args(language, engine_mode)
+
+    if pagesegmode is not None:
+        args_tesseract.extend(['--psm', str(pagesegmode)])
+
+    if user_words:
+        args_tesseract.extend(['--user-words', user_words])
+
+    if user_patterns:
+        args_tesseract.extend(['--user-patterns', user_patterns])
+
+    if user_words or user_patterns:
+        args_tesseract.extend(['-c', 'lstm_use_matrix=1'])
+
+    # Reminder: test suite tesseract spoofers will break after any changes
+    # to the number of order parameters here
+    args_tesseract.extend([input_file, prefix, 'hocr', 'txt'] + tessconfig)
+    try:
+        log.debug(args_tesseract)
+        p = run(
+            args_tesseract,
+            stdout=PIPE,
+            stderr=STDOUT,
+            timeout=timeout,
+            check=True,
+            env=tesseract_env,
+        )
+        stdout = p.stdout
+    except TimeoutExpired:
+        # Generate a HOCR file with no recognized text if tesseract times out
+        # Temporary workaround to hocrTransform not being able to function if
+        # it does not have a valid hOCR file.
+        page_timedout(log, input_file, timeout)
+        _generate_null_hocr(output_hocr, output_sidecar, input_file)
+    except CalledProcessError as e:
+        tesseract_log_output(log, e.output, input_file)
+        if b'Image too large' in e.output:
+            _generate_null_hocr(output_hocr, output_sidecar, input_file)
+            return
+
+        raise SubprocessOutputError() from e
+    else:
+        tesseract_log_output(log, stdout, input_file)
+        # The sidecar text file will get the suffix .txt; rename it to
+        # whatever caller wants it named
+        if os.path.exists(prefix + '.txt'):
+            shutil.move(prefix + '.txt', output_sidecar)
+
+
+def use_skip_page(text_only, skip_pdf, output_pdf, output_text):
+    with open(output_text, 'w') as f:
+        f.write('[skipped page]')
+
+    if skip_pdf and not text_only:
+        # Substitute a "skipped page"
+        with suppress(FileNotFoundError):
+            os.remove(output_pdf)  # In case it was partially created
+        os.symlink(skip_pdf, output_pdf)
+        return
+
+    # Or normally, just write a 0 byte file to the output to indicate a skip
+    with open(output_pdf, 'wb') as out:
+        out.write(b'')
+
+
+def generate_pdf(
+    *,
+    input_image,
+    skip_pdf=None,
+    output_pdf,
+    output_text,
+    language: list,
+    engine_mode,
+    text_only: bool,
+    tessconfig: list,
+    timeout: float,
+    pagesegmode: int,
+    user_words,
+    user_patterns,
+    tesseract_env,
+    log,
+):
+    """Use Tesseract to render a PDF.
+
+    input_image -- image to analyze
+    skip_pdf -- if we time out, use this file as output
+    output_pdf -- file to generate
+    output_text -- OCR text file
+    language -- list of languages to consider
+    engine_mode -- engine mode argument for tess v4
+    text_only -- enable tesseract text only mode?
+    tessconfig -- tesseract configuration
+    timeout -- timeout (seconds)
+    log -- logger object
+    """
+
+    args_tesseract = tess_base_args(language, engine_mode)
+
+    if pagesegmode is not None:
+        args_tesseract.extend(['--psm', str(pagesegmode)])
+
+    if text_only and has_textonly_pdf(tesseract_env, language):
+        args_tesseract.extend(['-c', 'textonly_pdf=1'])
+
+    if user_words:
+        args_tesseract.extend(['--user-words', user_words])
+
+    if user_patterns:
+        args_tesseract.extend(['--user-patterns', user_patterns])
+
+    prefix = os.path.splitext(output_pdf)[0]  # Tesseract appends suffixes
+
+    # Reminder: test suite tesseract spoofers might break after any changes
+    # to the number of order parameters here
+
+    args_tesseract.extend([input_image, prefix, 'pdf', 'txt'] + tessconfig)
+    try:
+        log.debug(args_tesseract)
+        p = run(
+            args_tesseract,
+            stdout=PIPE,
+            stderr=STDOUT,
+            timeout=timeout,
+            check=True,
+            env=tesseract_env,
+        )
+        stdout = p.stdout
+        if os.path.exists(prefix + '.txt'):
+            shutil.move(prefix + '.txt', output_text)
+    except TimeoutExpired:
+        page_timedout(log, input_image, timeout)
+        use_skip_page(text_only, skip_pdf, output_pdf, output_text)
+    except CalledProcessError as e:
+        tesseract_log_output(log, e.output, input_image)
+        if b'Image too large' in e.output:
+            use_skip_page(text_only, skip_pdf, output_pdf, output_text)
+            return
+        raise SubprocessOutputError() from e
+    else:
+        tesseract_log_output(log, stdout, input_image)

src/ocrmypdf/exec/unpaper.py

@@ -0,0 +1,127 @@
+# © 2015 James R. Barlow: github.com/jbarlow83
+#
+# This file is part of OCRmyPDF.
+#
+# OCRmyPDF is free software: you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# OCRmyPDF is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
+
+# unpaper documentation:
+# https://github.com/Flameeyes/unpaper/blob/master/doc/basic-concepts.md
+
+"""Interface to unpaper executable"""
+
+import os
+import shlex
+import subprocess
+from functools import lru_cache
+from subprocess import PIPE, STDOUT, CalledProcessError
+from tempfile import TemporaryDirectory
+
+from PIL import Image
+
+from ..exceptions import MissingDependencyError, SubprocessOutputError
+from . import get_version
+
+
+@lru_cache(maxsize=1)
+def version():
+    return get_version('unpaper')
+
+
+def run(input_file, output_file, dpi, log, mode_args):
+    args_unpaper = ['unpaper', '-v', '--dpi', str(dpi)] + mode_args
+
+    SUFFIXES = {'1': '.pbm', 'L': '.pgm', 'RGB': '.ppm'}
+
+    with TemporaryDirectory() as tmpdir, Image.open(input_file) as im:
+        if im.mode not in SUFFIXES.keys():
+            log.info("Converting image to other colorspace")
+            try:
+                if im.mode == 'P' and len(im.getcolors()) == 2:
+                    im = im.convert(mode='1')
+                else:
+                    im = im.convert(mode='RGB')
+            except IOError as e:
+                im.close()
+                raise MissingDependencyError(
+                    "Could not convert image with type " + im.mode
+                ) from e
+
+        try:
+            suffix = SUFFIXES[im.mode]
+        except KeyError:
+            raise MissingDependencyError(
+                "Failed to convert image to a supported format."
+            ) from e
+
+        input_pnm = os.path.join(tmpdir, f'input{suffix}')
+        output_pnm = os.path.join(tmpdir, f'output{suffix}')
+        im.save(input_pnm, format='PPM')
+
+        # To prevent any shenanigans from accepting arbitrary parameters in
+        # --unpaper-args, we:
+        # 1) run with cwd set to a tmpdir with only unpaper's files
+        # 2) forbid the use of '/' in arguments, to prevent changing paths
+        # 3) append absolute paths for the input and output file
+        # This should ensure that a user cannot clobber some other file with
+        # their unpaper arguments (whether intentionally or otherwise)
+        args_unpaper.extend([input_pnm, output_pnm])
+        try:
+            proc = subprocess.run(
+                args_unpaper,
+                check=True,
+                close_fds=True,
+                universal_newlines=True,
+                stderr=STDOUT,
+                cwd=tmpdir,
+                stdout=PIPE,
+            )
+        except CalledProcessError as e:
+            log.debug(e.output)
+            raise e from e
+        else:
+            log.debug(proc.stdout)
+            # unpaper sets dpi to 72; fix this
+            try:
+                with Image.open(output_pnm) as imout:
+                    imout.save(output_file, dpi=(dpi, dpi))
+            except (FileNotFoundError, OSError):
+                raise SubprocessOutputError(
+                    "unpaper: failed to produce the expected output file. "
+                    + " Called with: "
+                    + str(args_unpaper)
+                ) from None
+
+
+def validate_custom_args(args: str):
+    unpaper_args = shlex.split(args)
+    if any('/' in arg for arg in unpaper_args):
+        raise ValueError('No filenames allowed in --unpaper-args')
+    return unpaper_args
+
+
+def clean(input_file, output_file, dpi, log, unpaper_args=None):
+    default_args = [
+        '--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
+        '--no-grayfilter',  # don't remove light gray areas
+        '--no-blackfilter',  # don't remove solid black areas
+        '--no-deskew',  # don't deskew
+    ]
+    if not unpaper_args:
+        unpaper_args = default_args
+    run(input_file, output_file, dpi, log, unpaper_args)

src/ocrmypdf/helpers.py

@@ -0,0 +1,139 @@
+# © 2016 James R. Barlow: github.com/jbarlow83
+#
+# This file is part of OCRmyPDF.
+#
+# OCRmyPDF is free software: you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# OCRmyPDF is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
+
+import logging
+import multiprocessing
+import os
+import warnings
+from collections.abc import Iterable
+from contextlib import suppress
+from functools import wraps
+from pathlib import Path
+
+log = logging.getLogger(__name__)
+
+
+def re_symlink(input_file, soft_link_name, *args, **kwargs):
+    """
+    Helper function: relinks soft symbolic link if necessary
+    """
+    if len(args) == 1 and isinstance(args[0], logging.Logger):
+        log.warning("Deprecated: re_symlink(,log)")
+    if 'log' in kwargs:
+        log.warning('Deprecated: re_symlink(...log=)')
+
+    input_file = os.fspath(input_file)
+    soft_link_name = os.fspath(soft_link_name)
+
+    # Guard against soft linking to oneself
+    if input_file == soft_link_name:
+        log.warning(
+            "No symbolic link made. You are using "
+            "the original data directory as the working directory."
+        )
+        return
+
+    # Soft link already exists: delete for relink?
+    if os.path.lexists(soft_link_name):
+        # do not delete or overwrite real (non-soft link) file
+        if not os.path.islink(soft_link_name):
+            raise FileExistsError(f"{soft_link_name} exists and is not a link")
+        try:
+            os.unlink(soft_link_name)
+        except OSError:
+            log.debug("Can't unlink %s", soft_link_name)
+
+    if not os.path.exists(input_file):
+        raise FileNotFoundError(f"trying to create a broken symlink to {input_file}")
+
+    log.debug("os.symlink(%s, %s)", input_file, soft_link_name)
+
+    # Create symbolic link using absolute path
+    os.symlink(os.path.abspath(input_file), soft_link_name)
+
+
+def is_iterable_notstr(thing):
+    return isinstance(thing, Iterable) and not isinstance(thing, str)
+
+
+def monotonic(L):
+    """Does list increase monotonically?"""
+    return all(b > a for a, b in zip(L, L[1:]))
+
+
+def page_number(input_file):
+    """Get one-based page number implied by filename (000002.pdf -> 2)"""
+    return int(os.path.basename(os.fspath(input_file))[0:6])
+
+
+def available_cpu_count():
+    try:
+        return multiprocessing.cpu_count()
+    except NotImplementedError:
+        pass
+    warnings.warn(
+        "Could not get CPU count.  Assuming one (1) CPU." "Use -j N to set manually."
+    )
+    return 1
+
+
+def is_file_writable(test_file):
+    """Intentionally racy test if target is writable.
+
+    We intend to write to the output file if and only if we succeed and
+    can replace it atomically. Before doing the OCR work, make sure
+    the location is writable.
+    """
+    p = Path(test_file)
+
+    if p.is_symlink():
+        p = p.resolve(strict=False)
+
+    # p.is_file() throws an exception in some cases
+    if p.exists() and p.is_file():
+        return os.access(
+            os.fspath(p),
+            os.W_OK,
+            effective_ids=(os.access in os.supports_effective_ids),
+        )
+    else:
+        try:
+            fp = p.open('wb')
+        except OSError:
+            return False
+        else:
+            fp.close()
+            with suppress(OSError):
+                p.unlink()
+        return True
+
+
+def deprecated(func):
+    """Warn that function is deprecated"""
+
+    @wraps(func)
+    def new_func(*args, **kwargs):
+        warnings.simplefilter('always', DeprecationWarning)  # turn off filter
+        warnings.warn(
+            "Call to deprecated function {}.".format(func.__name__),
+            category=DeprecationWarning,
+            stacklevel=2,
+        )
+        warnings.simplefilter('default', DeprecationWarning)  # reset filter
+        return func(*args, **kwargs)
+
+    return new_func

src/ocrmypdf/hocrtransform.py

@@ -0,0 +1,389 @@
+#!/usr/bin/env python3
+#
+# Copyright (c) 2010, Jonathan Brinley
+#   Original version from: https://github.com/jbrinley/HocrConverter
+#
+# Copyright (c) 2013-14, Julien Pfefferkorn
+#   Modifications
+#
+# Copyright (c) 2015-16, James R. Barlow
+#   Set text to transparent
+#
+# Permission is hereby granted, free of charge, to any person obtaining a
+# copy of this software and associated documentation files (the
+# "Software"), to deal in the Software without restriction, including
+# without limitation the rights to use, copy, modify, merge, publish,
+# distribute, sublicense, and/or sell copies of the Software, and to
+# permit persons to whom the Software is furnished to do so, subject to
+# the following conditions:
+#
+# The above copyright notice and this permission notice shall be included
+# in all copies or substantial portions of the Software.
+#
+# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS
+# OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+# MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
+# IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY
+# CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT,
+# TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE
+# SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
+
+import argparse
+import re
+from collections import namedtuple
+from math import atan, cos, sin
+from xml.etree import ElementTree
+
+from reportlab.lib.units import inch
+from reportlab.pdfgen.canvas import Canvas
+
+Rect = namedtuple('Rect', ['x1', 'y1', 'x2', 'y2'])
+
+
+class HocrTransformError(Exception):
+    pass
+
+
+class HocrTransform:
+
+    """
+    A class for converting documents from the hOCR format.
+    For details of the hOCR format, see:
+    http://kba.cloud/hocr-spec/
+    """
+
+    box_pattern = re.compile(r'bbox((\s+\d+){4})')
+    baseline_pattern = re.compile(
+        r'''
+        baseline \s+
+        ([\-\+]?\d*\.?\d*) \s+  # +/- decimal float
+        ([\-\+]?\d+)            # +/- int''',
+        re.VERBOSE,
+    )
+    ligatures = str.maketrans(
+        {'ff': 'ff', 'ffi': 'f‌f‌i', 'ffl': 'f‌f‌l', 'fi': 'fi', 'fl': 'fl'}
+    )
+
+    def __init__(self, hocrFileName, dpi):
+        self.dpi = dpi
+        self.hocr = ElementTree.parse(hocrFileName)
+
+        # if the hOCR file has a namespace, ElementTree requires its use to
+        # find elements
+        matches = re.match(r'({.*})html', self.hocr.getroot().tag)
+        self.xmlns = ''
+        if matches:
+            self.xmlns = matches.group(1)
+
+        # get dimension in pt (not pixel!!!!) of the OCRed image
+        self.width, self.height = None, None
+        for div in self.hocr.findall(".//%sdiv[@class='ocr_page']" % (self.xmlns)):
+            coords = self.element_coordinates(div)
+            pt_coords = self.pt_from_pixel(coords)
+            self.width = pt_coords.x2 - pt_coords.x1
+            self.height = pt_coords.y2 - pt_coords.y1
+            # there shouldn't be more than one, and if there is, we don't want
+            # it
+            break
+        if self.width is None or self.height is None:
+            raise HocrTransformError("hocr file is missing page dimensions")
+
+    def __str__(self):
+        """
+        Return the textual content of the HTML body
+        """
+        if self.hocr is None:
+            return ''
+        body = self.hocr.find(".//%sbody" % (self.xmlns))
+        if body:
+            return self._get_element_text(body)
+        else:
+            return ''
+
+    def _get_element_text(self, element):
+        """
+        Return the textual content of the element and its children
+        """
+        text = ''
+        if element.text is not None:
+            text += element.text
+        for child in element.getchildren():
+            text += self._get_element_text(child)
+        if element.tail is not None:
+            text += element.tail
+        return text
+
+    @classmethod
+    def element_coordinates(cls, element):
+        """
+        Returns a tuple containing the coordinates of the bounding box around
+        an element
+        """
+        out = (0, 0, 0, 0)
+        if 'title' in element.attrib:
+            matches = cls.box_pattern.search(element.attrib['title'])
+            if matches:
+                coords = matches.group(1).split()
+                out = Rect._make(int(coords[n]) for n in range(4))
+        return out
+
+    @classmethod
+    def baseline(cls, element):
+        """
+        Returns a tuple containing the baseline slope and intercept.
+        """
+        if 'title' in element.attrib:
+            matches = cls.baseline_pattern.search(element.attrib['title'])
+            if matches:
+                return float(matches.group(1)), int(matches.group(2))
+        return (0, 0)
+
+    def pt_from_pixel(self, pxl):
+        """
+        Returns the quantity in PDF units (pt) given quantity in pixels
+        """
+        return Rect._make((c / self.dpi * inch) for c in pxl)
+
+    @classmethod
+    def replace_unsupported_chars(cls, s):
+        """
+        Given an input string, returns the corresponding string that:
+        - is available in the helvetica facetype
+        - does not contain any ligature (to allow easy search in the PDF file)
+        """
+        return s.translate(cls.ligatures)
+
+    def to_pdf(
+        self,
+        outFileName,
+        imageFileName=None,
+        showBoundingboxes=False,
+        fontname="Helvetica",
+        invisibleText=False,
+        interwordSpaces=False,
+    ):
+        """
+        Creates a PDF file with an image superimposed on top of the text.
+        Text is positioned according to the bounding box of the lines in
+        the hOCR file.
+        The image need not be identical to the image used to create the hOCR
+        file.
+        It can have a lower resolution, different color mode, etc.
+        """
+        # create the PDF file
+        # page size in points (1/72 in.)
+        pdf = Canvas(outFileName, pagesize=(self.width, self.height), pageCompression=1)
+
+        # draw bounding box for each paragraph
+        # light blue for bounding box of paragraph
+        pdf.setStrokeColorRGB(0, 1, 1)
+        # light blue for bounding box of paragraph
+        pdf.setFillColorRGB(0, 1, 1)
+        pdf.setLineWidth(0)  # no line for bounding box
+        for elem in self.hocr.findall(".//%sp[@class='%s']" % (self.xmlns, "ocr_par")):
+
+            elemtxt = self._get_element_text(elem).rstrip()
+            if len(elemtxt) == 0:
+                continue
+
+            pxl_coords = self.element_coordinates(elem)
+            pt = self.pt_from_pixel(pxl_coords)
+
+            # draw the bbox border
+            if showBoundingboxes:
+                pdf.rect(
+                    pt.x1, self.height - pt.y2, pt.x2 - pt.x1, pt.y2 - pt.y1, fill=1
+                )
+
+        found_lines = False
+        for line in self.hocr.findall(
+            ".//%sspan[@class='%s']" % (self.xmlns, "ocr_line")
+        ):
+            found_lines = True
+            self._do_line(
+                pdf,
+                line,
+                "ocrx_word",
+                fontname,
+                invisibleText,
+                interwordSpaces,
+                showBoundingboxes,
+            )
+
+        if not found_lines:
+            # Tesseract did not report any lines (just words)
+            root = self.hocr.find(".//%sdiv[@class='%s']" % (self.xmlns, "ocr_page"))
+            self._do_line(
+                pdf,
+                root,
+                "ocrx_word",
+                fontname,
+                invisibleText,
+                interwordSpaces,
+                showBoundingboxes,
+            )
+        # put the image on the page, scaled to fill the page
+        if imageFileName is not None:
+            pdf.drawImage(imageFileName, 0, 0, width=self.width, height=self.height)
+
+        # finish up the page and save it
+        pdf.showPage()
+        pdf.save()
+
+    @classmethod
+    def polyval(cls, poly, x):
+        return x * poly[0] + poly[1]
+
+    def _do_line(
+        self,
+        pdf,
+        line,
+        elemclass,
+        fontname,
+        invisibleText,
+        interwordSpaces,
+        showBoundingboxes,
+    ):
+        pxl_line_coords = self.element_coordinates(line)
+        line_box = self.pt_from_pixel(pxl_line_coords)
+        line_height = line_box.y2 - line_box.y1
+
+        slope, pxl_intercept = self.baseline(line)
+        if abs(slope) < 0.005:
+            slope = 0.0
+        angle = atan(slope)
+        cos_a, sin_a = cos(angle), sin(angle)
+
+        text = pdf.beginText()
+        intercept = pxl_intercept / self.dpi * inch
+
+        # Don't allow the font to break out of the bounding box. Division by
+        # cos_a accounts for extra clearance between the glyph's vertical axis
+        # on a sloped baseline and the edge of the bounding box.
+        fontsize = (line_height - abs(intercept)) / cos_a
+        text.setFont(fontname, fontsize)
+        if invisibleText:
+            text.setTextRenderMode(3)  # Invisible (indicates OCR text)
+
+        # Intercept is normally negative, so this places it above the bottom
+        # of the line box
+        baseline_y2 = self.height - (line_box.y2 + intercept)
+
+        if showBoundingboxes:
+            # draw the baseline in magenta, dashed
+            pdf.setDash()
+            pdf.setStrokeColorRGB(0.95, 0.65, 0.95)
+            pdf.setLineWidth(0.5)
+            # negate slope because it is defined as a rise/run in pixel
+            # coordinates and page coordinates have the y axis flipped
+            pdf.line(
+                line_box.x1,
+                baseline_y2,
+                line_box.x2,
+                self.polyval((-slope, baseline_y2), line_box.x2 - line_box.x1),
+            )
+            # light green for bounding box of word/line
+            pdf.setDash(6, 3)
+            pdf.setStrokeColorRGB(1, 0, 0)
+
+        text.setTextTransform(cos_a, -sin_a, sin_a, cos_a, line_box.x1, baseline_y2)
+        pdf.setFillColorRGB(0, 0, 0)  # text in black
+
+        elements = line.findall(".//%sspan[@class='%s']" % (self.xmlns, elemclass))
+        for elem in elements:
+            elemtxt = self._get_element_text(elem).strip()
+            elemtxt = self.replace_unsupported_chars(elemtxt)
+            if elemtxt == '':
+                continue
+
+            pxl_coords = self.element_coordinates(elem)
+            box = self.pt_from_pixel(pxl_coords)
+            if interwordSpaces:
+                # if  `--interword-spaces` is true, append a space
+                # to the end of each text element to allow simpler PDF viewers
+                # such as PDF.js to better recognize words in search and copy
+                # and paste. Do not remove space from last word in line, even
+                # though it would look better, because it will interfere with
+                # naive text extraction. \n does not work either.
+                elemtxt += ' '
+                box = Rect._make(
+                    (
+                        box.x1,
+                        line_box.y1,
+                        box.x2 + pdf.stringWidth(' ', fontname, line_height),
+                        line_box.y2,
+                    )
+                )
+            box_width = box.x2 - box.x1
+            font_width = pdf.stringWidth(elemtxt, fontname, fontsize)
+
+            # draw the bbox border
+            if showBoundingboxes:
+                pdf.rect(
+                    box.x1, self.height - line_box.y2, box_width, line_height, fill=0
+                )
+
+            # Adjust relative position of cursor
+            # This is equivalent to:
+            #   text.setTextOrigin(pt.x1, self.height - line_box.y2)
+            # but the former generates a full text reposition matrix (Tm) in the
+            # content stream while this issues a "offset" (Td) command.
+            # .moveCursor() is relative to start of the text line, where the
+            # "text line" means whatever reportlab defines it as. Do not use
+            # use .getCursor(), since moveCursor() rather unintuitively plans
+            # its moves relative to .getStartOfLine().
+            # For skewed lines, in the text transform we set up a rotated
+            # coordinate system, so we don't have to account for the
+            # incremental offset. Surprisingly most PDF viewers can handle this.
+            cursor = text.getStartOfLine()
+            dx = box.x1 - cursor[0]
+            dy = baseline_y2 - cursor[1]
+            text.moveCursor(dx, dy)
+
+            # If reportlab tells us this word is 0 units wide, our best seems
+            # to be to suppress this text
+            if font_width > 0:
+                text.setHorizScale(100 * box_width / font_width)
+                text.textOut(elemtxt)
+        pdf.drawText(text)
+
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser(description='Convert hocr file to PDF')
+    parser.add_argument(
+        '-b',
+        '--boundingboxes',
+        action="store_true",
+        default=False,
+        help='Show bounding boxes borders',
+    )
+    parser.add_argument(
+        '-r',
+        '--resolution',
+        type=int,
+        default=300,
+        help='Resolution of the image that was OCRed',
+    )
+    parser.add_argument(
+        '-i',
+        '--image',
+        default=None,
+        help='Path to the image to be placed above the text',
+    )
+    parser.add_argument(
+        '--interword-spaces',
+        action='store_true',
+        default=False,
+        help='Add spaces between words',
+    )
+    parser.add_argument('hocrfile', help='Path to the hocr file to be parsed')
+    parser.add_argument('outputfile', help='Path to the PDF file to be generated')
+    args = parser.parse_args()
+
+    hocr = HocrTransform(args.hocrfile, args.resolution)
+    hocr.to_pdf(
+        args.outputfile,
+        args.image,
+        args.boundingboxes,
+        interwordSpaces=args.interword_spaces,
+    )

src/ocrmypdf/leptonica.py

@@ -0,0 +1,897 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+#
+# © 2013-16: jbarlow83 from Github (https://github.com/jbarlow83)
+#
+# This file is part of OCRmyPDF.
+#
+# OCRmyPDF is free software: you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# OCRmyPDF is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
+#
+# Python FFI wrapper for Leptonica library
+
+import argparse
+import logging
+import os
+import sys
+import warnings
+from collections.abc import Sequence
+from contextlib import suppress
+from ctypes.util import find_library
+from functools import lru_cache
+from io import BytesIO
+from os import fspath
+from tempfile import TemporaryFile
+
+from .lib._leptonica import ffi
+
+# pylint: disable=protected-access
+
+logger = logging.getLogger(__name__)
+
+lept = ffi.dlopen(find_library('lept'))
+lept.setMsgSeverity(lept.L_SEVERITY_WARNING)
+
+
+class _LeptonicaErrorTrap:
+    """
+    Context manager to trap errors reported by Leptonica.
+
+    Leptonica's error return codes don't provide much informatino about what
+    went wrong. Leptonica does, however, write more detailed errors to stderr
+    (provided this is not disabled at compile time). The Leptonica source
+    code is very consistent in its use of macros to generate errors.
+
+    This context manager redirects stderr to a temporary file which is then
+    read and parsed for error messages.  As a side benefit, debug messages
+    from Leptonica are also suppressed.
+
+    """
+
+    def __init__(self):
+        self.tmpfile = None
+        self.copy_of_stderr = -1
+        self.no_stderr = False
+
+    def __enter__(self):
+        from io import UnsupportedOperation
+
+        self.tmpfile = TemporaryFile()
+
+        # Save the old stderr, and redirect stderr to temporary file
+        with suppress(AttributeError):
+            sys.stderr.flush()
+        try:
+            self.copy_of_stderr = os.dup(sys.stderr.fileno())
+            os.dup2(self.tmpfile.fileno(), sys.stderr.fileno(), inheritable=False)
+        except AttributeError:
+            # We are in some unusual context where our Python process does not
+            # have a sys.stderr. Leptonica still expects to write to file
+            # descriptor 2, so we are going to ensure it is redirected.
+            self.copy_of_stderr = None
+            self.no_stderr = True
+            os.dup2(self.tmpfile.fileno(), 2, inheritable=False)
+        except UnsupportedOperation:
+            self.copy_of_stderr = None
+        return
+
+    def __exit__(self, exc_type, exc_value, traceback):
+        # Restore old stderr
+        with suppress(AttributeError):
+            sys.stderr.flush()
+
+        if self.copy_of_stderr is not None:
+            os.dup2(self.copy_of_stderr, sys.stderr.fileno())
+            os.close(self.copy_of_stderr)
+        if self.no_stderr:
+            os.close(2)
+
+        # Get data from tmpfile
+        self.tmpfile.seek(0)  # Cursor will be at end, so move back to beginning
+        leptonica_output = self.tmpfile.read().decode(errors='replace')
+        self.tmpfile.close()
+        # If there are Python errors, record them
+        if exc_type:
+            logger.warning(leptonica_output)
+
+        # If there are Leptonica errors, wrap them in Python excpetions
+        if 'Error' in leptonica_output:
+            if 'image file not found' in leptonica_output:
+                raise FileNotFoundError()
+            if 'pixWrite: stream not opened' in leptonica_output:
+                raise LeptonicaIOError()
+            if 'index not valid' in leptonica_output:
+                raise IndexError()
+            raise LeptonicaError(leptonica_output)
+
+        return False
+
+
+class LeptonicaError(Exception):
+    pass
+
+
+class LeptonicaIOError(LeptonicaError):
+    pass
+
+
+class LeptonicaObject:
+    """General wrapper for Leptonica objects
+
+    When Leptonica returns an object, we bundled it in a wrapper class, which
+    manages its memory. The wrapper class assumes that it will be calling some
+    sort of lept.thingDestroy() function when the instance is deleted. Most
+    Leptonica objects are reference counted, and destroy decrements the
+    refcount.
+
+    Most of the time, when Leptonica returns something, we wrap and it the job
+    is done. When wrapping objects that came from a Leptonica container, like
+    a PIXA returning PIX, the subclass must clone the object before passing it
+    here, to maintain the reference count.
+
+    CFFI ensures that the destroy function is called at garbage collection time
+    so we do not need to mess with __del__.
+    """
+
+    cdata_destroy = lambda cdata: None
+    LEPTONICA_TYPENAME = ''
+
+    def __init__(self, cdata):
+        if not cdata:
+            raise ValueError('Tried to wrap a NULL ' + self.LEPTONICA_TYPENAME)
+        self._cdata = ffi.gc(cdata, self._destroy)
+
+    @classmethod
+    def _destroy(cls, cdata):
+        """Destroy some cdata"""
+        # Leptonica API uses double-pointers for its destroy APIs to prevent
+        # dangling pointers. This means we need to put our single pointer,
+        # cdata, in a temporary CDATA**.
+        pp = ffi.new('{} **'.format(cls.LEPTONICA_TYPENAME), cdata)
+        cls.cdata_destroy(pp)
+
+
+class Pix(LeptonicaObject):
+    """
+    Wrapper around leptonica's PIX object.
+
+    Leptonica uses referencing counting on PIX objects. Also, many Leptonica
+    functions return the original object with an increased reference count
+    if the operation had no effect (for example, image skew was found to be 0).
+    This has complications for memory management in Python. Whenever Leptonica
+    returns a PIX object (new or old), we wrap it in this class, which
+    registers it with the FFI garbage collector. pixDestroy() decrements the
+    reference count and only destroys when the last reference is removed.
+
+    Leptonica's reference counting is not threadsafe. This class can be used
+    in a threadsafe manner if a Python threading.Lock protects the data.
+
+    This class treats Pix objects as immutable.  All methods return new
+    modified objects.  This allows convenient chaining:
+
+    >>>   Pix.open('filename.jpg').scale((0.5, 0.5)).deskew().show()
+    """
+
+    LEPTONICA_TYPENAME = "PIX"
+    cdata_destroy = lept.pixDestroy
+
+    def __repr__(self):
+        if self._cdata:
+            s = "<leptonica.Pix image size={0}x{1} depth={2}{4} at 0x{3:x}>"
+            return s.format(
+                self._cdata.w,
+                self._cdata.h,
+                self._cdata.d,
+                int(ffi.cast('intptr_t', self._cdata)),
+                '(colormapped)' if self._cdata.colormap else '',
+            )
+        else:
+            return "<leptonica.Pix image NULL>"
+
+    def _repr_png_(self):
+        """iPython display hook
+
+        returns png version of image
+        """
+
+        data = ffi.new('l_uint8 **')
+        size = ffi.new('size_t *')
+
+        err = lept.pixWriteMemPng(data, size, self._cdata, 0)
+        if err != 0:
+            raise LeptonicaIOError("pixWriteMemPng")
+
+        char_data = ffi.cast('char *', data[0])
+        return ffi.buffer(char_data, size[0])[:]
+
+    def __getstate__(self):
+        data = ffi.new('l_uint32 **')
+        size = ffi.new('size_t *')
+
+        err = lept.pixSerializeToMemory(self._cdata, data, size)
+        if err != 0:
+            raise LeptonicaIOError("pixSerializeToMemory")
+
+        char_data = ffi.cast('char *', data[0])
+
+        # Copy from C bytes to python bytes()
+        data_bytes = ffi.buffer(char_data, size[0])[:]
+
+        # Can now free C bytes
+        lept.lept_free(char_data)
+        return dict(data=data_bytes)
+
+    def __setstate__(self, state):
+        cdata_bytes = ffi.new('char[]', state['data'])
+        cdata_uint32 = ffi.cast('l_uint32 *', cdata_bytes)
+
+        pix = lept.pixDeserializeFromMemory(cdata_uint32, len(state['data']))
+        Pix.__init__(self, pix)
+
+    def __eq__(self, other):
+        if not isinstance(other, Pix):
+            return NotImplemented
+        same = ffi.new('l_int32 *', 0)
+        with _LeptonicaErrorTrap():
+            err = lept.pixEqual(self._cdata, other._cdata, same)
+            if err:
+                raise TypeError()
+        return bool(same[0])
+
+    @property
+    def width(self):
+        return self._cdata.w
+
+    @property
+    def height(self):
+        return self._cdata.h
+
+    @property
+    def depth(self):
+        return self._cdata.d
+
+    @property
+    def size(self):
+        return (self._cdata.w, self._cdata.h)
+
+    @property
+    def info(self):
+        return {'dpi': (self._cdata.xres, self._cdata.yres)}
+
+    @property
+    def mode(self):
+        "Return mode like PIL.Image"
+        if self.depth == 1:
+            return '1'
+        elif self.depth >= 16:
+            return 'RGB'
+        elif not self._cdata.colormap:
+            return 'L'
+        else:
+            return 'P'
+
+    @classmethod
+    def read(cls, path):
+        warnings.warn('Use Pix.open() instead', DeprecationWarning)
+        return cls.open(path)
+
+    @classmethod
+    def open(cls, path):
+        """Load an image file into a PIX object.
+
+        Leptonica can load TIFF, PNM (PBM, PGM, PPM), PNG, and JPEG.  If
+        loading fails then the object will wrap a C null pointer.
+        """
+        filename = fspath(path)
+        with _LeptonicaErrorTrap():
+            return cls(lept.pixRead(os.fsencode(filename)))
+
+    def write_implied_format(self, path, jpeg_quality=0, jpeg_progressive=0):
+        """Write pix to the filename, with the extension indicating format.
+
+        jpeg_quality -- quality (iff JPEG; 1 - 100, 0 for default)
+        jpeg_progressive -- (iff JPEG; 0 for baseline seq., 1 for progressive)
+        """
+        filename = fspath(path)
+        with _LeptonicaErrorTrap():
+            lept.pixWriteImpliedFormat(
+                os.fsencode(filename), self._cdata, jpeg_quality, jpeg_progressive
+            )
+
+    @classmethod
+    def frompil(self, pillow_image):
+        """Create a copy of a PIL.Image from this Pix"""
+        bio = BytesIO()
+        pillow_image.save(bio, format='png', compress_level=1)
+        py_buffer = bio.getbuffer()
+        c_buffer = ffi.from_buffer(py_buffer)
+        with _LeptonicaErrorTrap():
+            pix = Pix(lept.pixReadMem(c_buffer, len(c_buffer)))
+            return pix
+
+    def topil(self):
+        """Returns a PIL.Image version of this Pix"""
+        from PIL import Image
+
+        # Leptonica manages data in words, so it implicitly does an endian
+        # swap.  Tell Pillow about this when it reads the data.
+        pix = self
+        if sys.byteorder == 'little':
+            if self.mode == 'RGB':
+                raw_mode = 'XBGR'
+            elif self.mode == 'RGBA':
+                raw_mode = 'ABGR'
+            elif self.mode == '1':
+                raw_mode = '1;I'
+                pix = Pix(lept.pixEndianByteSwapNew(pix._cdata))
+            else:
+                raw_mode = self.mode
+                pix = Pix(lept.pixEndianByteSwapNew(pix._cdata))
+        else:
+            raw_mode = self.mode  # no endian swap needed
+
+        size = (pix._cdata.w, pix._cdata.h)
+        bytecount = pix._cdata.wpl * 4 * pix._cdata.h
+        buf = ffi.buffer(pix._cdata.data, bytecount)
+        stride = pix._cdata.wpl * 4
+
+        im = Image.frombytes(self.mode, size, buf, 'raw', raw_mode, stride)
+
+        return im
+
+    def show(self):
+        return self.topil().show()
+
+    def deskew(self, reduction_factor=0):
+        """Returns the deskewed pix object.
+
+        A clone of the original is returned when the algorithm cannot find a
+        skew angle with sufficient confidence.
+
+        reduction_factor -- amount to downsample (0 for default) when searching
+            for skew angle
+        """
+        with _LeptonicaErrorTrap():
+            return Pix(lept.pixDeskew(self._cdata, reduction_factor))
+
+    def scale(self, scale_xy):
+        "Returns the pix object rescaled according to the proportions given."
+        with _LeptonicaErrorTrap():
+            return Pix(lept.pixScale(self._cdata, scale_xy[0], scale_xy[1]))
+
+    def rotate180(self):
+        with _LeptonicaErrorTrap():
+            return Pix(lept.pixRotate180(ffi.NULL, self._cdata))
+
+    def rotate_orth(self, quads):
+        "Orthographic rotation, quads: 0-3, number of clockwise rotations"
+        with _LeptonicaErrorTrap():
+            return Pix(lept.pixRotateOrth(self._cdata, quads))
+
+    def find_skew(self):
+        """Returns a tuple (deskew angle in degrees, confidence value).
+
+        Returns (None, None) if no angle is available.
+        """
+        with _LeptonicaErrorTrap():
+            angle = ffi.new('float *', 0.0)
+            confidence = ffi.new('float *', 0.0)
+            result = lept.pixFindSkew(self._cdata, angle, confidence)
+            if result == 0:
+                return (angle[0], confidence[0])
+            else:
+                return (None, None)
+
+    def convert_rgb_to_luminance(self):
+        with _LeptonicaErrorTrap():
+            gray_pix = lept.pixConvertRGBToLuminance(self._cdata)
+            if gray_pix:
+                return Pix(gray_pix)
+            return None
+
+    def remove_colormap(self, removal_type):
+        """Remove a palette (colormap); if no colormap, returns a copy of this
+        image
+
+            removal_type - any of lept.REMOVE_CMAP_*
+
+        """
+        with _LeptonicaErrorTrap():
+            return Pix(
+                lept.pixRemoveColormapGeneral(self._cdata, removal_type, lept.L_COPY)
+            )
+
+    def otsu_adaptive_threshold(
+        self, tile_size=(300, 300), kernel_size=(4, 4), scorefract=0.1
+    ):
+        with _LeptonicaErrorTrap():
+            sx, sy = tile_size
+            smoothx, smoothy = kernel_size
+            p_pix = ffi.new('PIX **')
+
+            pix = Pix(lept.pixConvertTo8(self._cdata, 0))
+            result = lept.pixOtsuAdaptiveThreshold(
+                pix._cdata, sx, sy, smoothx, smoothy, scorefract, ffi.NULL, p_pix
+            )
+            if result == 0:
+                return Pix(p_pix[0])
+            else:
+                return None
+
+    def otsu_threshold_on_background_norm(
+        self,
+        mask=None,
+        tile_size=(10, 15),
+        thresh=100,
+        mincount=50,
+        bgval=255,
+        kernel_size=(2, 2),
+        scorefract=0.1,
+    ):
+        with _LeptonicaErrorTrap():
+            sx, sy = tile_size
+            smoothx, smoothy = kernel_size
+            mask = ffi.NULL
+            if isinstance(mask, Pix):
+                mask = mask._cdata
+
+            pix = Pix(lept.pixConvertTo8(self._cdata, 0))
+            thresh_pix = lept.pixOtsuThreshOnBackgroundNorm(
+                pix._cdata,
+                mask,
+                sx,
+                sy,
+                thresh,
+                mincount,
+                bgval,
+                smoothx,
+                smoothy,
+                scorefract,
+                ffi.NULL,
+            )
+            return Pix(thresh_pix)
+
+    def masked_threshold_on_background_norm(
+        self,
+        mask=None,
+        tile_size=(10, 15),
+        thresh=100,
+        mincount=50,
+        kernel_size=(2, 2),
+        scorefract=0.1,
+    ):
+        with _LeptonicaErrorTrap():
+            sx, sy = tile_size
+            smoothx, smoothy = kernel_size
+            mask = ffi.NULL
+            if isinstance(mask, Pix):
+                mask = mask._cdata
+
+            pix = Pix(lept.pixConvertTo8(self._cdata, 0))
+            thresh_pix = lept.pixMaskedThreshOnBackgroundNorm(
+                pix._cdata,
+                mask,
+                sx,
+                sy,
+                thresh,
+                mincount,
+                smoothx,
+                smoothy,
+                scorefract,
+                ffi.NULL,
+            )
+            return Pix(thresh_pix)
+
+    def crop_to_foreground(
+        self,
+        threshold=128,
+        mindist=70,
+        erasedist=30,
+        pagenum=0,
+        showmorph=0,
+        display=0,
+        pdfdir=ffi.NULL,
+    ):
+        with _LeptonicaErrorTrap():
+            cropbox = Box(
+                lept.pixFindPageForeground(
+                    self._cdata,
+                    threshold,
+                    mindist,
+                    erasedist,
+                    pagenum,
+                    showmorph,
+                    display,
+                    pdfdir,
+                )
+            )
+
+            cropped_pix = lept.pixClipRectangle(self._cdata, cropbox._cdata, ffi.NULL)
+
+            return Pix(cropped_pix)
+
+    def clean_background_to_white(
+        self, mask=None, grayscale=None, gamma=1.0, black=0, white=255
+    ):
+        with _LeptonicaErrorTrap():
+            return Pix(
+                lept.pixCleanBackgroundToWhite(
+                    self._cdata,
+                    mask or ffi.NULL,
+                    grayscale or ffi.NULL,
+                    gamma,
+                    black,
+                    white,
+                )
+            )
+
+    def gamma_trc(self, gamma=1.0, minval=0, maxval=255):
+        with _LeptonicaErrorTrap():
+            return Pix(lept.pixGammaTRC(ffi.NULL, self._cdata, gamma, minval, maxval))
+
+    def background_norm(
+        self,
+        mask=None,
+        grayscale=None,
+        tile_size=(10, 15),
+        fg_threshold=60,
+        min_count=40,
+        bg_val=200,
+        smooth_kernel=(2, 1),
+    ):
+        # Background norm doesn't work on color mapped Pix, so remove colormap
+        target_pix = self.remove_colormap(lept.REMOVE_CMAP_BASED_ON_SRC)
+        with _LeptonicaErrorTrap():
+            return Pix(
+                lept.pixBackgroundNorm(
+                    target_pix._cdata,
+                    mask or ffi.NULL,
+                    grayscale or ffi.NULL,
+                    tile_size[0],
+                    tile_size[1],
+                    fg_threshold,
+                    min_count,
+                    bg_val,
+                    smooth_kernel[0],
+                    smooth_kernel[1],
+                )
+            )
+
+    @staticmethod
+    @lru_cache(maxsize=1)
+    def make_pixel_sum_tab8():
+        return lept.makePixelSumTab8()
+
+    @staticmethod
+    def correlation_binary(pix1, pix2):
+        if get_leptonica_version() < 'leptonica-1.72':
+            # Older versions of Leptonica (pre-1.72) have a buggy
+            # implementation of pixCorrelationBinary that overflows on larger
+            # images.  Ubuntu 14.04/trusty has 1.70. Ubuntu PPA
+            # ppa:alex-p/tesseract-ocr has leptonlib 1.75.
+            raise LeptonicaError("Leptonica version is too old")
+
+        correlation = ffi.new('float *', 0.0)
+        result = lept.pixCorrelationBinary(pix1._cdata, pix2._cdata, correlation)
+        if result != 0:
+            raise LeptonicaError("Correlation failed")
+        return correlation[0]
+
+    def generate_pdf_ci_data(self, type_, quality):
+        "Convert to PDF data, with transcoding"
+        p_compdata = ffi.new('L_COMP_DATA **')
+        result = lept.pixGenerateCIData(self._cdata, type_, quality, 0, p_compdata)
+        if result != 0:
+            raise LeptonicaError("Generate PDF data failed")
+        return CompressedData(p_compdata[0])
+
+    def invert(self):
+        return Pix(lept.pixInvert(ffi.NULL, self._cdata))
+
+    def locate_barcodes(self):
+        try:
+            with _LeptonicaErrorTrap():
+                pix = Pix(lept.pixConvertTo8(self._cdata, 0))
+                pixa_candidates = PixArray(lept.pixExtractBarcodes(pix._cdata, 0))
+                if not pixa_candidates:
+                    return
+                sarray = StringArray(
+                    lept.pixReadBarcodes(
+                        pixa_candidates._cdata,
+                        lept.L_BF_ANY,
+                        lept.L_USE_WIDTHS,
+                        ffi.NULL,
+                        0,
+                    )
+                )
+        except (LeptonicaError, ValueError, IndexError):
+            return
+        finally:
+            leptonica_junk = ('junkpixt.png', 'junkpixt')
+            for junk in leptonica_junk:
+                with suppress(FileNotFoundError):
+                    os.unlink(junk)  # leptonica may produce this
+
+        for n, s in enumerate(sarray):
+            decoded = s.decode()
+            if decoded.strip() == '':
+                continue
+            box = pixa_candidates.get_box(n)
+            left, top = box.x, box.y
+            right, bottom = box.x + box.w, box.y + box.h
+            yield (decoded, (left, top, right, bottom))
+
+    def despeckle(self, size):
+        if size == 2:
+            speckle2 = """
+                oooo
+                oC o
+                o  o
+                oooo
+                """
+            sel1 = Sel.from_selstr(speckle2, 'speckle2')
+            sel2 = Sel.create_brick(2, 2, 0, 0, lept.SEL_HIT)
+        elif size == 3:
+            speckle3 = """
+                ooooo
+                oC  o
+                o   o
+                o   o
+                ooooo
+                """
+            sel1 = Sel.from_selstr(speckle3, 'speckle3')
+            sel2 = Sel.create_brick(3, 3, 0, 0, lept.SEL_HIT)
+        else:
+            raise ValueError(size)
+
+        pixhmt = Pix(lept.pixHMT(ffi.NULL, self._cdata, sel1._cdata))
+        pixdilated = Pix(lept.pixDilate(ffi.NULL, pixhmt._cdata, sel2._cdata))
+
+        pixsub = Pix(lept.pixSubtract(ffi.NULL, self._cdata, pixdilated._cdata))
+        return pixsub
+
+
+class CompressedData(LeptonicaObject):
+    """Wrapper for L_COMP_DATA - abstract compressed image data"""
+
+    LEPTONICA_TYPENAME = 'L_COMP_DATA'
+    cdata_destroy = lept.l_CIDataDestroy
+
+    @classmethod
+    def open(cls, path, jpeg_quality=75):
+        "Open compressed data, without transcoding"
+        filename = fspath(path)
+
+        p_compdata = ffi.new('L_COMP_DATA **')
+        result = lept.l_generateCIDataForPdf(
+            os.fsencode(filename), ffi.NULL, jpeg_quality, p_compdata
+        )
+        if result != 0:
+            raise LeptonicaError("CompressedData.open")
+        return CompressedData(p_compdata[0])
+
+    def __len__(self):
+        return self._cdata.nbytescomp
+
+    def read(self):
+        buf = ffi.buffer(self._cdata.datacomp, self._cdata.nbytescomp)
+        return bytes(buf)
+
+    def __getattr__(self, name):
+        if hasattr(self._cdata, name):
+            return getattr(self._cdata, name)
+        raise AttributeError(name)
+
+    def get_palette_pdf_string(self):
+        "Returns palette pre-formatted for use in PDF"
+        buflen = len('< ') + len(' rrggbb') * self._cdata.ncolors + len('>')
+        buf = ffi.buffer(self._cdata.cmapdatahex, buflen)
+        return bytes(buf)
+
+
+class PixArray(LeptonicaObject, Sequence):
+    """Wrapper around PIXA (array of PIX)"""
+
+    LEPTONICA_TYPENAME = 'PIXA'
+    cdata_destroy = lept.pixaDestroy
+
+    def __len__(self):
+        return self._cdata[0].n
+
+    def __getitem__(self, n):
+        with _LeptonicaErrorTrap():
+            return Pix(lept.pixaGetPix(self._cdata, n, lept.L_CLONE))
+
+    def get_box(self, n):
+        with _LeptonicaErrorTrap():
+            return Box(lept.pixaGetBox(self._cdata, n, lept.L_CLONE))
+
+
+class Box(LeptonicaObject):
+    """Wrapper around Leptonica's BOX objects (a pixel rectangle)
+
+    Uses x, y, w, h coordinates.
+    """
+
+    LEPTONICA_TYPENAME = 'BOX'
+    cdata_destroy = lept.boxDestroy
+
+    def __repr__(self):
+        if self._cdata:
+            return '<leptonica.Box x={0} y={1} w={2} h={3}>'.format(
+                self.x, self.y, self.w, self.h
+            )
+        return '<leptonica.Box NULL>'
+
+    @property
+    def x(self):
+        return self._cdata.x
+
+    @property
+    def y(self):
+        return self._cdata.y
+
+    @property
+    def w(self):
+        return self._cdata.w
+
+    @property
+    def h(self):
+        return self._cdata.h
+
+
+class BoxArray(LeptonicaObject, Sequence):
+    """Wrapper around Leptonica's BOXA (Array of BOX) objects."""
+
+    LEPTONICA_TYPENAME = 'BOXA'
+    cdata_destroy = lept.boxaDestroy
+
+    def __repr__(self):
+        if not self._cdata:
+            return '<BoxArray>'
+        boxes = (repr(box) for box in self)
+        return '<BoxArray [' + ', '.join(boxes) + ']>'
+
+    def __len__(self):
+        return self._cdata.n
+
+    def __getitem__(self, n):
+        if not isinstance(n, int):
+            raise TypeError('list indices must be integers')
+        if 0 <= n < len(self):
+            return Box(lept.boxaGetBox(self._cdata, n, lept.L_CLONE))
+        raise IndexError(n)
+
+
+class StringArray(LeptonicaObject, Sequence):
+    """Leptonica SARRAY/string array"""
+
+    LEPTONICA_TYPENAME = 'SARRAY'
+    cdata_destroy = lept.sarrayDestroy
+
+    def __len__(self):
+        return self._cdata.n
+
+    def __getitem__(self, n):
+        if 0 <= n < len(self):
+            return ffi.string(self._cdata.array[n])
+        raise IndexError(n)
+
+
+class Sel(LeptonicaObject):
+    """Leptonica 'sel'/selection element for hit-miss transform"""
+
+    LEPTONICA_TYPENAME = 'SEL'
+    cdata_destroy = lept.selDestroy
+
+    @classmethod
+    def from_selstr(cls, selstr, name):
+        # TODO this will strip a horizontal line of don't care's
+        lines = [line.strip() for line in selstr.split('\n') if line.strip()]
+        h = len(lines)
+        w = len(lines[0])
+        lengths = set(len(line) for line in lines)
+        if len(lengths) != 1:
+            raise ValueError("All lines in selstr must be same length")
+
+        repacked = ''.join(line.strip() for line in lines)
+        buf_selstr = ffi.from_buffer(repacked.encode('ascii'))
+        buf_name = ffi.from_buffer(name.encode('ascii'))
+        sel = lept.selCreateFromString(buf_selstr, h, w, buf_name)
+        return cls(sel)
+
+    @classmethod
+    def create_brick(cls, h, w, cy, cx, type_):
+        sel = lept.selCreateBrick(h, w, cy, cx, type_)
+        return cls(sel)
+
+    def __repr__(self):
+        selstr = ffi.gc(lept.selPrintToString(self._cdata), lept.lept_free)
+        return '<Sel \n' + ffi.string(selstr).decode('ascii') + '\n>'
+
+
+@lru_cache(maxsize=1)
+def get_leptonica_version():
+    """Get Leptonica version string.
+
+    Caveat: Leptonica expects the caller to free this memory.  We don't,
+    since that would involve binding to libc to access libc.free(),
+    a pointless effort to reclaim 100 bytes of memory.
+    """
+    return ffi.string(lept.getLeptonicaVersion()).decode()
+
+
+def deskew(infile, outfile, dpi):
+    try:
+        pix_source = Pix.open(infile)
+    except LeptonicaIOError:
+        raise LeptonicaIOError("Failed to open file: %s" % infile)
+
+    if dpi < 150:
+        reduction_factor = 1  # Don't downsample too much if DPI is already low
+    else:
+        reduction_factor = 0  # Use default
+    pix_deskewed = pix_source.deskew(reduction_factor)
+
+    try:
+        pix_deskewed.write_implied_format(outfile)
+    except LeptonicaIOError:
+        raise LeptonicaIOError("Failed to open destination file: %s" % outfile)
+
+
+def remove_background(
+    infile,
+    outfile,
+    tile_size=(40, 60),
+    gamma=1.0,
+    black_threshold=70,
+    white_threshold=190,
+):
+    try:
+        pix = Pix.open(infile)
+    except LeptonicaIOError:
+        raise LeptonicaIOError("Failed to open file: %s" % infile)
+
+    pix = pix.background_norm(tile_size=tile_size).gamma_trc(
+        gamma, black_threshold, white_threshold
+    )
+
+    try:
+        pix.write_implied_format(outfile)
+    except LeptonicaIOError:
+        raise LeptonicaIOError("Failed to open destination file: %s" % outfile)
+
+
+if __name__ == '__main__':
+    parser = argparse.ArgumentParser(description="Python wrapper to access Leptonica")
+
+    subparsers = parser.add_subparsers(
+        title='commands', description='supported operations'
+    )
+
+    parser_deskew = subparsers.add_parser('deskew')
+    parser_deskew.add_argument(
+        '-r',
+        '--dpi',
+        dest='dpi',
+        action='store',
+        type=int,
+        default=300,
+        help='input resolution',
+    )
+    parser_deskew.add_argument('infile', help='image to deskew')
+    parser_deskew.add_argument('outfile', help='deskewed output image')
+    parser_deskew.set_defaults(func=deskew)
+
+    args = parser.parse_args()
+    args.func(args)

src/ocrmypdf/lib/__init__.py

@@ -0,0 +1,18 @@
+# © 2017 James R. Barlow: github.com/jbarlow83
+#
+# This file is part of OCRmyPDF.
+#
+# OCRmyPDF is free software: you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# OCRmyPDF is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
+
+"""Bindings to external libraries"""