v13.6.0 release notes

Unpaper or its underlying libraries don't seem to accept pnms with an
odd integer width. Although it's not clear if this is the issue at all.

In any case, keeping the image a PNG works around the issue. unpaper
only accepted PNM input in the past, which is why we send it PNM.
Since it now accepts PNG, we might as well use PNG.

Unpaper can write PNG as output too, but this added a few seconds to
the test suite was not committed.

Related issues:

https://github.com/ocrmypdf/OCRmyPDF/issues/887

https://github.com/ocrmypdf/OCRmyPDF/issues/665

https://github.com/unpaper/unpaper/issues/82

.docker/Dockerfile

@@ -0,0 +1,80 @@
+# OCRmyPDF
+#
+
+FROM ubuntu:22.04 as base
+
+ENV LANG=C.UTF-8
+ENV TZ=UTC
+RUN echo 'debconf debconf/frontend select Noninteractive' | debconf-set-selections
+
+RUN apt-get update && apt-get install -y --no-install-recommends \
+  python3 \
+  libqpdf-dev \
+  zlib1g \
+  liblept5
+
+FROM base as builder
+
+# Note we need leptonica here to build jbig2
+RUN apt-get update && apt-get install -y --no-install-recommends \
+  build-essential autoconf automake libtool \
+  libleptonica-dev \
+  zlib1g-dev \
+  python3-dev \
+  python3-distutils \
+  libffi-dev \
+  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/ea6a40a.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 .[test,webservice,watcher]
+
+FROM base
+
+RUN apt-get update && apt-get install -y --no-install-recommends \
+  ghostscript \
+  img2pdf \
+  libsm6 libxext6 libxrender-dev \
+  pngquant \
+  tesseract-ocr \
+  tesseract-ocr-chi-sim \
+  tesseract-ocr-deu \
+  tesseract-ocr-eng \
+  tesseract-ocr-fra \
+  tesseract-ocr-por \
+  tesseract-ocr-spa \
+  unpaper \
+  && rm -rf /var/lib/apt/lists/*
+
+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 --from=builder /app/misc/watcher.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/tests /app/tests
+
+ENTRYPOINT ["/usr/local/bin/ocrmypdf"]

.dockerignore

@@ -1,34 +1,44 @@
+# dotfiles
+.*
+!.coveragerc
+!.dockerignore
+!.git_archival.txt
+!.gitattributes
+!.gitignore
+!.pre-commit-config.yaml
+!.readthedocs.yml
+
+# Dev scratch
 *.ipynb
-*.pdf
-*.pyc
-*.rst
-*.sublime*
-*/*.pyc
-*/*/*.pyc
-*/*/*/*.pyc
-*/*/*/*/*.pyc
-*/*/*/*/*/*.pyc
-*/*/*/*/*/*/*.pyc
-*/*/*/*/*/*/*/*.pyc
-.cache/
-.eggs/
-.github/
-.git/
-.ipynb_checkpoints/
-.ruffus_history.sqlite
-bin/
-build/
-docs/
-dist/
-htmlcov/
-include/
-lib/
-MANIFEST.in
-ocrmypdf.egg-info/
-staging/
-tests/cache/
-tests/output/
+**/*.pyc
+/*.pdf
+/*.qdf
+/*.png
+/scratch.py
+IDEAS
+log/
 tests/resources/private/
 tmp/
 venv*/
+/debug_tests.py
+*.traineddata
+/private
+
+# Package building
+*.egg-info/
+build/
+dist/
 wheelhouse/
+pip-wheel-metadata/
+
+# Code coverage
+htmlcov/
+
+# Docker specific
+bin/
+docs/
+include/
+lib/
+
+# Docker include .git/
+!.git/

.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/1-general-issues.md

@@ -0,0 +1,32 @@
+---
+name: General issues
+about: Installation, packages, dependencies, "nothing works", test suite failures...
+title: ''
+labels: ''
+assignees: ''
+
+---
+
+**Describe the bug**
+What's the problem?
+
+**To Reproduce**
+Steps to reproduce the behavior.
+
+**Expected behavior**
+What did you expected to happen?
+
+**Screenshots**
+If applicable, add screenshots to help explain your problem.
+
+**System (please complete the following information):**
+ - OS:
+ - Python version:
+ - OCRmyPDF version:
+
+**Installation**
+How did you install OCRmyPDF? Did you install it from your operating system's
+package manager, or using pip?
+
+**Additional context**
+Add any other context about the problem here.

.github/ISSUE_TEMPLATE/2-problem-with-a-specific-input-file.md

@@ -0,0 +1,40 @@
+---
+name: Problem with a specific input file
+about: Something went wrong while trying to OCR a specific file
+title: ''
+labels: ''
+assignees: ''
+
+---
+
+**Describe the bug**
+A clear and concise description of what the bug is.
+
+**To Reproduce**
+What command line or API call were you trying to run?
+
+```bash
+ocrmypdf  ...arguments... input.pdf output.pdf
+```
+
+Run with verbosity or higher `-v1` to see more detailed logging. This information may be helpful.
+
+**Example file**
+If your issue is a problem that affects only certain files, and we will require an input file (PDF or image) that demonstrates your issue.
+
+Please provide an input file with no personal or confidential information. At your option you may [GPG-encrypt the file](https://github.com/ocrmypdf/OCRmyPDF/wiki) for OCRmyPDF's author only.
+
+Links to files hosted elsewhere are perfectly acceptable. You could also look in ``tests/resources`` and see if any of those files reproduce your issue.
+
+*(Issues without example files usually cannot be resolved. It's like reporting an issue against a web browser without providing a URL.)*
+
+**Expected behavior**
+A clear and concise description of what you expected to happen.
+
+**Screenshots**
+If applicable, add screenshots to help explain your problem.
+
+**System**
+ - OS: [e.g. Linux, Windows, macOS]
+ - OCRmyPDF Version: ``ocrmypdf --version``
+ - How did you install ocrmypdf? Did you use a system package manager, `pip`, or a Docker image?

.github/ISSUE_TEMPLATE/3-feature_request.md

@@ -0,0 +1,27 @@
+---
+name: Feature request
+about: Suggest an idea for this project
+title: ''
+labels: ''
+assignees: ''
+
+---
+
+**Is your feature request related to a problem? Please describe.**
+A clear and concise description of what the problem is. Ex. I'm always frustrated when [...]
+
+**Describe the solution you'd like**
+A clear and concise description of what you want to happen.
+
+**Describe alternatives you've considered**
+A clear and concise description of any alternative solutions or features you've considered. Please include the versions of OCRmyPDF and other supporting programs (Tesseract OCR, Ghostscript) - maybe an alternative already exists in a newer version.
+
+**Example file**
+If your issue concerns how OCRmyPDF processes certain files, and please provide an example file that helps illustrate how OCRmyPDF's output could be improve.
+
+Please provide an input file with no personal or confidential information. At your option you may [GPG-encrypt the file](https://github.com/ocrmypdf/OCRmyPDF/wiki) for OCRmyPDF's author only.
+
+Links to files hosted elsewhere are perfectly acceptable. You could also look in ``tests/resources`` and see if any of those files reproduce your issue.
+
+**Additional context**
+Add any other context or screenshots about the feature request here.

.github/workflows/build.yml

@@ -0,0 +1,303 @@
+name: Test and deploy
+
+on:
+  push:
+    branches:
+      - master
+      - ci
+      - release/*
+      - feature/*
+    tags:
+      - v*
+    paths-ignore:
+      - README*
+  pull_request:
+
+jobs:
+  test_linux:
+    name: Test ${{ matrix.os }} with Python ${{ matrix.python }}
+    runs-on: ${{ matrix.os }}
+    strategy:
+      matrix:
+        include:
+          - os: ubuntu-18.04
+            python: "3.7"
+          - os: ubuntu-20.04
+            python: "3.8"
+          - os: ubuntu-20.04
+            python: "3.9"
+          - os: ubuntu-20.04
+            python: "3.10"
+          - os: ubuntu-latest
+            python: "3.9"
+          - os: ubuntu-latest
+            python: "pypy-3.8"
+          - os: ubuntu-latest
+            python: "3.9"
+            tesseract5: true
+
+    env:
+      OS: ${{ matrix.os }}
+      PYTHON: ${{ matrix.python }}
+
+    steps:
+      - uses: actions/checkout@v2
+        with:
+          fetch-depth: "0" # 0=all, needed for setuptools-scm to resolve version tags
+
+      - uses: actions/setup-python@v2
+        name: Install Python
+        with:
+          python-version: ${{ matrix.python }}
+
+      - name: Install Tesseract 5
+        if: matrix.tesseract5
+        run: |
+          sudo add-apt-repository ppa:alex-p/tesseract-ocr-devel
+
+      - name: Install common packages
+        run: |
+          sudo apt-get update
+          sudo apt-get install -y --no-install-recommends \
+            curl \
+            ghostscript \
+            img2pdf \
+            libffi-dev \
+            libsm6 libxext6 libxrender-dev \
+            pngquant \
+            poppler-utils \
+            tesseract-ocr \
+            tesseract-ocr-deu \
+            tesseract-ocr-eng \
+            tesseract-ocr-osd \
+            unpaper \
+            zlib1g
+
+      - name: Install Ubuntu 18.04 packages
+        if: matrix.os == 'ubuntu-18.04'
+        run: |
+          sudo apt-get install -y --no-install-recommends \
+            libexempi3
+
+      - name: Install Ubuntu 20.04 packages
+        if: matrix.os == 'ubuntu-20.04' || matrix.os == 'ubuntu-latest'
+        run: |
+          sudo apt-get install -y --no-install-recommends \
+            libexempi8
+
+      - name: Install Ubuntu packages for PyPy
+        if: startsWith(matrix.python, 'pypy')
+        run: |
+          sudo apt-get install -y --no-install-recommends \
+            libxml2-dev \
+            libxslt1-dev \
+            pypy3-dev
+
+      - name: Install Python packages
+        run: |
+          python -m pip install --upgrade pip wheel
+          python -m pip install .[test]
+
+      - name: Report versions
+        run: |
+          tesseract --version
+          gs --version
+          pngquant --version
+          unpaper --version
+          img2pdf --version
+
+      - name: Test
+        run: |
+          python -m pytest --cov-report xml --cov=ocrmypdf --cov=tests/ -n0 tests/
+
+      - name: Upload coverage to Codecov
+        uses: codecov/codecov-action@v1
+        with:
+          files: ./coverage.xml
+          env_vars: OS,PYTHON
+
+  test_macos:
+    name: Test macOS
+    runs-on: ${{ matrix.os }}
+    strategy:
+      matrix:
+        os: [macos-latest]
+        python: ["3.9", "3.10"]
+
+    env:
+      OS: ${{ matrix.os }}
+      PYTHON: ${{ matrix.python }}
+
+    steps:
+      - uses: actions/checkout@v2
+        with:
+          fetch-depth: "0" # 0=all, needed for setuptools-scm to resolve version tags
+
+      - uses: actions/setup-python@v2
+        name: Install Python
+        with:
+          python-version: ${{ matrix.python }}
+
+      - name: Install Homebrew deps
+        run: |
+          brew update
+          brew install \
+            exempi \
+            ghostscript \
+            jbig2enc \
+            openjpeg \
+            pngquant \
+            tesseract
+
+      - name: Install Python packages
+        run: |
+          python -m pip install --upgrade pip wheel
+          python -m pip install .[test]
+
+      - name: Report versions
+        run: |
+          tesseract --version
+          gs --version
+          pngquant --version
+          img2pdf --version
+
+      - name: Test
+        run: |
+          python -m pytest --cov-report xml --cov=ocrmypdf --cov=tests/ -n0 tests/
+
+      - name: Upload coverage to Codecov
+        uses: codecov/codecov-action@v1
+        with:
+          files: ./coverage.xml
+          env_vars: OS,PYTHON
+
+  test_windows:
+    name: Test Windows
+    runs-on: ${{ matrix.os }}
+    strategy:
+      matrix:
+        os: [windows-latest]
+        python: ["3.9", "3.10"]
+
+    env:
+      OS: ${{ matrix.os }}
+      PYTHON: ${{ matrix.python }}
+
+    steps:
+      - uses: actions/checkout@v2
+        with:
+          fetch-depth: "0" # 0=all, needed for setuptools-scm to resolve version tags
+
+      - uses: actions/setup-python@v2
+        name: Install Python
+        with:
+          python-version: ${{ matrix.python }}
+
+      - name: Install system packages
+        run: |
+          choco install --yes --no-progress --pre tesseract
+          choco install --yes --no-progress --ignore-checksums ghostscript
+
+      - name: Install Python packages
+        run: |
+          python -m pip install --upgrade pip wheel
+          python -m pip install .[test]
+
+      - name: Test
+        run: |
+          python -m pytest --cov-report xml --cov=ocrmypdf --cov=tests/ -n0 tests/
+
+      - name: Upload coverage to Codecov
+        uses: codecov/codecov-action@v1
+        with:
+          files: ./coverage.xml
+          env_vars: OS,PYTHON
+
+  wheel_sdist_linux:
+    name: Build sdist and wheels
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v2
+        with:
+          fetch-depth: "0" # 0=all, needed for setuptools-scm to resolve version tags
+
+      - uses: actions/setup-python@v2
+        name: Install Python
+        with:
+          python-version: "3.7"
+
+      - name: Make wheels and sdist
+        run: |
+          python -m pip install --upgrade pip wheel
+          python setup.py sdist
+          python setup.py bdist_wheel
+
+      - uses: actions/upload-artifact@v2
+        with:
+          path: |
+            ./dist/*.whl
+            ./dist/*.tar.gz
+
+  upload_pypi:
+    name: Deploy artifacts to PyPI
+    needs: [wheel_sdist_linux, test_linux, test_macos, test_windows]
+    runs-on: ubuntu-latest
+    if: github.event_name == 'push' && startsWith(github.event.ref, 'refs/tags/v')
+    steps:
+      - uses: actions/download-artifact@v2
+        with:
+          name: artifact
+          path: dist
+
+      - uses: pypa/gh-action-pypi-publish@master
+        with:
+          user: __token__
+          password: ${{ secrets.TOKEN_PYPI }}
+          # repository_url: https://test.pypi.org/legacy/
+
+  docker:
+    name: Build Docker images
+    needs: [wheel_sdist_linux, test_linux, test_macos, test_windows]
+    runs-on: ubuntu-latest
+    if: github.event_name != 'pull_request'
+    steps:
+      - name: Set image tag to release or branch
+        run: echo "DOCKER_IMAGE_TAG=${GITHUB_REF##*/}" >> $GITHUB_ENV
+
+      - name: If master, set to latest
+        run: echo 'DOCKER_IMAGE_TAG=latest' >> $GITHUB_ENV
+        if: env.DOCKER_IMAGE_TAG == 'master'
+
+      - name: Set Docker Hub repository to username
+        run: echo "DOCKER_REPOSITORY=jbarlow83" >> $GITHUB_ENV
+
+      - name: Set image name
+        run: echo "DOCKER_IMAGE_NAME=ocrmypdf" >> $GITHUB_ENV
+
+      - uses: actions/checkout@v2
+        with:
+          fetch-depth: "0" # 0=all, needed for setuptools-scm to resolve version tags
+
+      - name: Login to Docker Hub
+        uses: docker/login-action@v1
+        with:
+          username: jbarlow83
+          password: ${{ secrets.DOCKERHUB_TOKEN }}
+
+      - name: Set up QEMU
+        uses: docker/setup-qemu-action@v1
+
+      - name: Set up Docker Buildx
+        id: buildx
+        uses: docker/setup-buildx-action@v1
+
+      - name: Print image tag
+        run: echo "Building image ${DOCKER_REPOSITORY}/${DOCKER_IMAGE_NAME}:${DOCKER_IMAGE_TAG}"
+
+      - name: Build
+        run: |
+          docker buildx build \
+            --push \
+            --platform linux/arm64/v8,linux/amd64  \
+            --tag "${DOCKER_REPOSITORY}/${DOCKER_IMAGE_NAME}:${DOCKER_IMAGE_TAG}" \
+            --file .docker/Dockerfile .

.gitignore

@@ -1,41 +1,45 @@
-# Development environment
-*.pyc
-*.sublime-*
+# dotfiles
+.*
+!.coveragerc
+!.dockerignore
+!.git_archival.txt
+!.gitattributes
+!.gitignore
+!.pre-commit-config.yaml
+!.readthedocs.yaml
+!.github/
+!.docker/
+
+# Dev scratch
+*.ipynb
+**/*.pyc
+/*.pdf
+/*.qdf
+/*.png
+/scratch.py
+IDEAS
+log/
+tests/resources/private/
+tmp/
 venv*/
-pyvenv.cfg
-tasks.py
-.bash_history
-.ruffus_history.sqlite
-.idea/
+/debug_tests.py
+*.traineddata
+/private
+/coverage.xml
 
 # Package building
 *.egg-info/
-.cache/
-.eggs/
 build/
 dist/
 wheelhouse/
+pip-wheel-metadata/
+
+# Code coverage
+htmlcov/
 
 # Automatically generated files
-ocrmypdf/lib/_*.py
-ocrmypdf/version.py
 docs/_build/
 docs/_static/
 docs/_templates/
 docs/Makefile
-
-# Code coverage
-.coverage
-htmlcov/
-
-# Testing
-log/
-/*.pdf
-/*.qdf
-*.ipynb
-.ipynb_checkpoints/
-tests/cache/
-tests/output/
-tests/resources/private/
-tmp/
-pdfbox-app*.jar
+ocrmypdf/lib/_*.py

.pre-commit-config.yaml

@@ -0,0 +1,37 @@
+repos:
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v4.2.0
+    hooks:
+      - id: check-case-conflict
+      - id: check-merge-conflict
+      - id: check-toml
+      - id: check-yaml
+      - id: debug-statements
+  - repo: https://github.com/pycqa/isort
+    rev: 5.10.1
+    hooks:
+      - id: isort
+        args: ["--profile", "black"]
+  - repo: https://github.com/psf/black
+    rev: 22.3.0
+    hooks:
+      - id: black
+        language_version: python
+  - repo: https://github.com/asottile/setup-cfg-fmt
+    rev: v1.20.1
+    hooks:
+      - id: setup-cfg-fmt
+  - repo: https://github.com/asottile/pyupgrade
+    rev: v2.32.1
+    hooks:
+      - id: pyupgrade
+        args: ["--py37-plus"]
+  - repo: https://github.com/pre-commit/mirrors-mypy
+    rev: v0.950
+    hooks:
+      - id: mypy
+        additional_dependencies:
+          - types-toml
+          - types-setuptools
+          - types-requests
+          - types-Pillow

.readthedocs.yaml

@@ -0,0 +1,22 @@
+# Read the Docs configuration file
+# See https://docs.readthedocs.io/en/stable/config-file/v2.html for details
+
+# Required
+version: 2
+
+# Build documentation in the docs/ directory with Sphinx
+sphinx:
+  configuration: docs/conf.py
+
+# Optionally build your docs in additional formats such as PDF
+formats:
+  - pdf
+
+# Optionally set the version of Python and requirements required to build your docs
+python:
+  version: "3.7"
+  install:
+    - method: pip
+      path: .
+      extra_requirements:
+        - docs

.travis.yml

@@ -1,95 +0,0 @@
-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
-
-matrix:
-  include:
-    - os: linux
-      sudo: required
-      language: python
-      python: 3.5
-    - os: linux
-      sudo: required
-      language: python
-      python: 3.6
-    - os: osx
-      osx_image: xcode8
-      language: generic
-
-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
-
-install:
-- pip3 install .
-- pip3 install -r requirements.txt -r test_requirements.txt
-
-script:
-- mv ocrmypdf dont_import_this_ocrmypdf
-- pytest -n auto
-- mv dont_import_this_ocrmypdf ocrmypdf
-
-deploy:
-  # release for main pypi
-  # 3.6 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

.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 +1,373 @@
+Mozilla Public License Version 2.0
+==================================
+
+1. Definitions
+--------------
+
+1.1. "Contributor"
+    means each individual or legal entity that creates, contributes to
+    the creation of, or owns Covered Software.
+
+1.2. "Contributor Version"
+    means the combination of the Contributions of others (if any) used
+    by a Contributor and that particular Contributor's Contribution.
+
+1.3. "Contribution"
+    means Covered Software of a particular Contributor.
+
+1.4. "Covered Software"
+    means Source Code Form to which the initial Contributor has attached
+    the notice in Exhibit A, the Executable Form of such Source Code
+    Form, and Modifications of such Source Code Form, in each case
+    including portions thereof.
+
+1.5. "Incompatible With Secondary Licenses"
+    means
+
+    (a) that the initial Contributor has attached the notice described
+        in Exhibit B to the Covered Software; or
+
+    (b) that the Covered Software was made available under the terms of
+        version 1.1 or earlier of the License, but not also under the
+        terms of a Secondary License.
+
+1.6. "Executable Form"
+    means any form of the work other than Source Code Form.
+
+1.7. "Larger Work"
+    means a work that combines Covered Software with other material, in
+    a separate file or files, that is not Covered Software.
+
+1.8. "License"
+    means this document.
+
+1.9. "Licensable"
+    means having the right to grant, to the maximum extent possible,
+    whether at the time of the initial grant or subsequently, any and
+    all of the rights conveyed by this License.
+
+1.10. "Modifications"
+    means any of the following:
+
+    (a) any file in Source Code Form that results from an addition to,
+        deletion from, or modification of the contents of Covered
+        Software; or
+
+    (b) any new file in Source Code Form that contains any Covered
+        Software.
+
+1.11. "Patent Claims" of a Contributor
+    means any patent claim(s), including without limitation, method,
+    process, and apparatus claims, in any patent Licensable by such
+    Contributor that would be infringed, but for the grant of the
+    License, by the making, using, selling, offering for sale, having
+    made, import, or transfer of either its Contributions or its
+    Contributor Version.
+
+1.12. "Secondary License"
+    means either the GNU General Public License, Version 2.0, the GNU
+    Lesser General Public License, Version 2.1, the GNU Affero General
+    Public License, Version 3.0, or any later versions of those
+    licenses.
+
+1.13. "Source Code Form"
+    means the form of the work preferred for making modifications.
+
+1.14. "You" (or "Your")
+    means an individual or a legal entity exercising rights under this
+    License. For legal entities, "You" includes any entity that
+    controls, is controlled by, or is under common control with You. For
+    purposes of this definition, "control" means (a) the power, direct
+    or indirect, to cause the direction or management of such entity,
+    whether by contract or otherwise, or (b) ownership of more than
+    fifty percent (50%) of the outstanding shares or beneficial
+    ownership of such entity.
+
+2. License Grants and Conditions
+--------------------------------
+
+2.1. Grants
+
+Each Contributor hereby grants You a world-wide, royalty-free,
+non-exclusive license:
+
+(a) under intellectual property rights (other than patent or trademark)
+    Licensable by such Contributor to use, reproduce, make available,
+    modify, display, perform, distribute, and otherwise exploit its
+    Contributions, either on an unmodified basis, with Modifications, or
+    as part of a Larger Work; and
+
+(b) under Patent Claims of such Contributor to make, use, sell, offer
+    for sale, have made, import, and otherwise transfer either its
+    Contributions or its Contributor Version.
+
+2.2. Effective Date
+
+The licenses granted in Section 2.1 with respect to any Contribution
+become effective for each Contribution on the date the Contributor first
+distributes such Contribution.
+
+2.3. Limitations on Grant Scope
+
+The licenses granted in this Section 2 are the only rights granted under
+this License. No additional rights or licenses will be implied from the
+distribution or licensing of Covered Software under this License.
+Notwithstanding Section 2.1(b) above, no patent license is granted by a
+Contributor:
+
+(a) for any code that a Contributor has removed from Covered Software;
+    or
+
+(b) for infringements caused by: (i) Your and any other third party's
+    modifications of Covered Software, or (ii) the combination of its
+    Contributions with other software (except as part of its Contributor
+    Version); or
+
+(c) under Patent Claims infringed by Covered Software in the absence of
+    its Contributions.
+
+This License does not grant any rights in the trademarks, service marks,
+or logos of any Contributor (except as may be necessary to comply with
+the notice requirements in Section 3.4).
+
+2.4. Subsequent Licenses
+
+No Contributor makes additional grants as a result of Your choice to
+distribute the Covered Software under a subsequent version of this
+License (see Section 10.2) or under the terms of a Secondary License (if
+permitted under the terms of Section 3.3).
+
+2.5. Representation
+
+Each Contributor represents that the Contributor believes its
+Contributions are its original creation(s) or it has sufficient rights
+to grant the rights to its Contributions conveyed by this License.
+
+2.6. Fair Use
+
+This License is not intended to limit any rights You have under
+applicable copyright doctrines of fair use, fair dealing, or other
+equivalents.
+
+2.7. Conditions
+
+Sections 3.1, 3.2, 3.3, and 3.4 are conditions of the licenses granted
+in Section 2.1.
+
+3. Responsibilities
+-------------------
+
+3.1. Distribution of Source Form
+
+All distribution of Covered Software in Source Code Form, including any
+Modifications that You create or to which You contribute, must be under
+the terms of this License. You must inform recipients that the Source
+Code Form of the Covered Software is governed by the terms of this
+License, and how they can obtain a copy of this License. You may not
+attempt to alter or restrict the recipients' rights in the Source Code
+Form.
+
+3.2. Distribution of Executable Form
+
+If You distribute Covered Software in Executable Form then:
+
+(a) such Covered Software must also be made available in Source Code
+    Form, as described in Section 3.1, and You must inform recipients of
+    the Executable Form how they can obtain a copy of such Source Code
+    Form by reasonable means in a timely manner, at a charge no more
+    than the cost of distribution to the recipient; and
+
+(b) You may distribute such Executable Form under the terms of this
+    License, or sublicense it under different terms, provided that the
+    license for the Executable Form does not attempt to limit or alter
+    the recipients' rights in the Source Code Form under this License.
+
+3.3. Distribution of a Larger Work
+
+You may create and distribute a Larger Work under terms of Your choice,
+provided that You also comply with the requirements of this License for
+the Covered Software. If the Larger Work is a combination of Covered
+Software with a work governed by one or more Secondary Licenses, and the
+Covered Software is not Incompatible With Secondary Licenses, this
+License permits You to additionally distribute such Covered Software
+under the terms of such Secondary License(s), so that the recipient of
+the Larger Work may, at their option, further distribute the Covered
+Software under the terms of either this License or such Secondary
+License(s).
+
+3.4. Notices
+
+You may not remove or alter the substance of any license notices
+(including copyright notices, patent notices, disclaimers of warranty,
+or limitations of liability) contained within the Source Code Form of
+the Covered Software, except that You may alter any license notices to
+the extent required to remedy known factual inaccuracies.
+
+3.5. Application of Additional Terms
+
+You may choose to offer, and to charge a fee for, warranty, support,
+indemnity or liability obligations to one or more recipients of Covered
+Software. However, You may do so only on Your own behalf, and not on
+behalf of any Contributor. You must make it absolutely clear that any
+such warranty, support, indemnity, or liability obligation is offered by
+You alone, and You hereby agree to indemnify every Contributor for any
+liability incurred by such Contributor as a result of warranty, support,
+indemnity or liability terms You offer. You may include additional
+disclaimers of warranty and limitations of liability specific to any
+jurisdiction.
+
+4. Inability to Comply Due to Statute or Regulation
+---------------------------------------------------
+
+If it is impossible for You to comply with any of the terms of this
+License with respect to some or all of the Covered Software due to
+statute, judicial order, or regulation then You must: (a) comply with
+the terms of this License to the maximum extent possible; and (b)
+describe the limitations and the code they affect. Such description must
+be placed in a text file included with all distributions of the Covered
+Software under this License. Except to the extent prohibited by statute
+or regulation, such description must be sufficiently detailed for a
+recipient of ordinary skill to be able to understand it.
+
+5. Termination
+--------------
+
+5.1. The rights granted under this License will terminate automatically
+if You fail to comply with any of its terms. However, if You become
+compliant, then the rights granted under this License from a particular
+Contributor are reinstated (a) provisionally, unless and until such
+Contributor explicitly and finally terminates Your grants, and (b) on an
+ongoing basis, if such Contributor fails to notify You of the
+non-compliance by some reasonable means prior to 60 days after You have
+come back into compliance. Moreover, Your grants from a particular
+Contributor are reinstated on an ongoing basis if such Contributor
+notifies You of the non-compliance by some reasonable means, this is the
+first time You have received notice of non-compliance with this License
+from such Contributor, and You become compliant prior to 30 days after
+Your receipt of the notice.
+
+5.2. If You initiate litigation against any entity by asserting a patent
+infringement claim (excluding declaratory judgment actions,
+counter-claims, and cross-claims) alleging that a Contributor Version
+directly or indirectly infringes any patent, then the rights granted to
+You by any and all Contributors for the Covered Software under Section
+2.1 of this License shall terminate.
+
+5.3. In the event of termination under Sections 5.1 or 5.2 above, all
+end user license agreements (excluding distributors and resellers) which
+have been validly granted by You or Your distributors under this License
+prior to termination shall survive termination.
+
+************************************************************************
+*                                                                      *
+*  6. Disclaimer of Warranty                                           *
+*  -------------------------                                           *
+*                                                                      *
+*  Covered Software is provided under this License on an "as is"       *
+*  basis, without warranty of any kind, either expressed, implied, or  *
+*  statutory, including, without limitation, warranties that the       *
+*  Covered Software is free of defects, merchantable, fit for a        *
+*  particular purpose or non-infringing. The entire risk as to the     *
+*  quality and performance of the Covered Software is with You.        *
+*  Should any Covered Software prove defective in any respect, You     *
+*  (not any Contributor) assume the cost of any necessary servicing,   *
+*  repair, or correction. This disclaimer of warranty constitutes an   *
+*  essential part of this License. No use of any Covered Software is   *
+*  authorized under this License except under this disclaimer.         *
+*                                                                      *
+************************************************************************
+
+************************************************************************
+*                                                                      *
+*  7. Limitation of Liability                                          *
+*  --------------------------                                          *
+*                                                                      *
+*  Under no circumstances and under no legal theory, whether tort      *
+*  (including negligence), contract, or otherwise, shall any           *
+*  Contributor, or anyone who distributes Covered Software as          *
+*  permitted above, be liable to You for any direct, indirect,         *
+*  special, incidental, or consequential damages of any character      *
+*  including, without limitation, damages for lost profits, loss of    *
+*  goodwill, work stoppage, computer failure or malfunction, or any    *
+*  and all other commercial damages or losses, even if such party      *
+*  shall have been informed of the possibility of such damages. This   *
+*  limitation of liability shall not apply to liability for death or   *
+*  personal injury resulting from such party's negligence to the       *
+*  extent applicable law prohibits such limitation. Some               *
+*  jurisdictions do not allow the exclusion or limitation of           *
+*  incidental or consequential damages, so this exclusion and          *
+*  limitation may not apply to You.                                    *
+*                                                                      *
+************************************************************************
+
+8. Litigation
+-------------
+
+Any litigation relating to this License may be brought only in the
+courts of a jurisdiction where the defendant maintains its principal
+place of business and such litigation shall be governed by laws of that
+jurisdiction, without reference to its conflict-of-law provisions.
+Nothing in this Section shall prevent a party's ability to bring
+cross-claims or counter-claims.
+
+9. Miscellaneous
+----------------
+
+This License represents the complete agreement concerning the subject
+matter hereof. If any provision of this License is held to be
+unenforceable, such provision shall be reformed only to the extent
+necessary to make it enforceable. Any law or regulation which provides
+that the language of a contract shall be construed against the drafter
+shall not be used to construe this License against a Contributor.
+
+10. Versions of the License
+---------------------------
+
+10.1. New Versions
+
+Mozilla Foundation is the license steward. Except as provided in Section
+10.3, no one other than the license steward has the right to modify or
+publish new versions of this License. Each version will be given a
+distinguishing version number.
+
+10.2. Effect of New Versions
+
+You may distribute the Covered Software under the terms of the version
+of the License under which You originally received the Covered Software,
+or under the terms of any subsequent version published by the license
+steward.
+
+10.3. Modified Versions
+
+If you create software not governed by this License, and you want to
+create a new license for such software, you may create and use a
+modified version of this License if you rename the license and remove
+any references to the name of the license steward (except to note that
+such modified license differs from this License).
+
+10.4. Distributing Source Code Form that is Incompatible With Secondary
+Licenses
+
+If You choose to distribute Source Code Form that is Incompatible With
+Secondary Licenses under the terms of this version of the License, the
+notice described in Exhibit B of this License must be attached.
+
+Exhibit A - Source Code Form License Notice
+-------------------------------------------
+
+  This Source Code Form is subject to the terms of the Mozilla Public
+  License, v. 2.0. If a copy of the MPL was not distributed with this
+  file, You can obtain one at http://mozilla.org/MPL/2.0/.
+
+If it is not possible or desirable to put the notice in a particular
+file, then You may include the notice in a location (such as a LICENSE
+file in a relevant directory) where a recipient would be likely to look
+for such a notice.
+
+You may add additional accurate notices of copyright ownership.
+
+Exhibit B - "Incompatible With Secondary Licenses" Notice
+---------------------------------------------------------
+
+  This Source Code Form is "Incompatible With Secondary Licenses", as
+  defined by the Mozilla Public License, v. 2.0.

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 +1,142 @@
+<img src="docs/images/logo.svg" width="240" alt="OCRmyPDF">
+
+[![Build Status](https://github.com/ocrmypdf/OCRmyPDF/actions/workflows/build.yml/badge.svg)](https://github.com/ocrmypdf/OCRmyPDF/actions/workflows/build.yml) [![PyPI version][pypi]](https://pypi.org/project/ocrmypdf/) ![Homebrew version][homebrew] ![ReadTheDocs][docs] ![Python versions][pyversions]
+
+[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: 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, Windows, macOS and FreeBSD are supported. Docker images are also available, for both x64 and ARM.
+
+| Operating system              | Install command               |
+| ----------------------------- | ------------------------------|
+| Debian, Ubuntu                | ``apt install ocrmypdf``      |
+| Windows Subsystem for Linux   | ``apt install ocrmypdf``      |
+| Fedora                        | ``dnf install ocrmypdf``      |
+| macOS (Homebrew)              | ``brew install ocrmypdf``     |
+| macOS (nix)                   | ``nix-env -i  ocrmypdf``      |
+| LinuxBrew                     | ``brew install ocrmypdf``     |
+| FreeBSD                       | ``pkg install py37-ocrmypdf`` |
+| Conda                         | ``conda 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 pack
+
+# Arch Linux users
+pacman -S tesseract-data-eng tesseract-data-deu # Example: Install the English and German language packs
+
+# brew macOS users
+brew install tesseract-lang
+```
+
+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.
+
+OCRmyPDF supports Tesseract 4.0 and the beta versions of Tesseract 5.0. It will
+automatically use whichever version it finds first on the `PATH` environment
+variable. On Windows, if `PATH` does not provide a Tesseract binary, we use
+the highest version number that is installed according to the Windows Registry.
+
+## 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).
+
+Please report issues on our [GitHub issues](https://github.com/ocrmypdf/OCRmyPDF/issues) page, and follow the issue template for quick response.
+
+## Requirements
+
+In addition to the required Python version (3.7+), OCRmyPDF requires external program installations of Ghostscript and Tesseract OCR. OCRmyPDF is pure Python, and runs on pretty much everything: Linux, macOS, Windows and FreeBSD.
+
+## 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](https://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](https://heise.de/-2356670)
+- [heise Durchsuchbare PDF-Dokumente mit OCRmyPDF erstellen](https://www.heise.de/ratgeber/Durchsuchbare-PDF-Dokumente-mit-OCRmyPDF-erstellen-4607592.html)
+- [Excellent Utilities: OCRmyPDF](https://www.linuxlinks.com/excellent-utilities-ocrmypdf-add-ocr-text-layer-scanned-pdfs/)
+- [LinuxUser Texterkennung mit OCRmyPDF und Scanbd automatisieren](https://www.linux-community.de/ausgaben/linuxuser/2021/06/texterkennung-mit-ocrmypdf-und-scanbd-automatisieren/)
+
+## Business enquiries
+
+OCRmyPDF would not be the software that it is today 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 Mozilla Public License 2.0
+(MPL-2.0). This license permits integration of OCRmyPDF with other code,
+included commercial and closed source, but asks you to publish source-level
+modifications you make to OCRmyPDF.
+
+Some components of OCRmyPDF have other licenses, as noted in those files and the
+``debian/copyright`` file. Most files in ``misc/`` use the MIT license, and the
+documentation and test files are generally licensed under Creative Commons
+ShareAlike 4.0 (CC-BY-SA 4.0).
+
+## 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 image processing or 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 variable if it is not already set.
+
+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``
+-  ``pngquant``
+-  ``jbig2``
 
-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 +194,145 @@ 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 (specifically, it supports the ISO 8859-1
+character). 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
-""""""""""""""""""""""""""
+Return code policy
+==================
 
-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``.
+OCRmyPDF writes all messages to ``stderr``. ``stdout`` is reserved for
+piping output files. ``stdin`` is reserved for piping input files.
 
-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.
+The return codes generated by the OCRmyPDF are considered part of the
+stable user interface. They may be imported from
+``ocrmypdf.exceptions``.
 
-*This renderer is deprecated and will be removed whenever support for older versions of Tesseract is dropped.*
+.. 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/ocrmypdf.io.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 +1,125 @@
+======================
+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 provides 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
+
+    if __name__ == '__main__':  # To ensure correct behavior on Windows and macOS
+        ocrmypdf.ocr('input.pdf', 'output.pdf', deskew=True)
+
+With some 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 (on Linux, forking itself; on Windows and macOS, by
+  spawning)
+- manage the signal flags of its worker processes
+- execute other subprocesses (forking and executing other programs)
+
+The Python process that calls :func:`ocrmypdf.ocr()` must be sufficiently
+privileged to perform these actions.
+
+There currently is no option to manage how jobs are scheduled other
+than the argument ``jobs=`` which will limit the number of worker
+processes.
+
+Creating a child process to call :func:`ocrmypdf.ocr()` is suggested. That
+way your application will survive and remain interactive even if
+OCRmyPDF fails for any reason.
+
+Programs that call :func:`ocrmypdf.ocr()` should also install a SIGBUS signal
+handler (except on Windows), to raise an exception if access to a memory
+mapped file fails. OCRmyPDF may use memory mapping.
+
+:func:`ocrmypdf.ocr()` will take a threading lock to prevent multiple runs of itself
+in the same Python interpreter process. This is not thread-safe, because of how
+OCRmyPDF's plugins and Python's library import system work. If you need to parallelize
+OCRmyPDF, use processes.
+
+.. warning::
+
+    On Windows and macOS, the script that calls :func:`ocrmypdf.ocr()` must be
+    protected by an "ifmain" guard (``if __name__ == '__main__'``). If you do
+    not take at least one of these steps, process semantics will prevent
+    OCRmyPDF from working correctly.
+
+.. warning::
+
+    On macOS with Python 3.7, you must call
+    :func:`multiprocessing.set_start_method("spawn")`. Without this, multiprocessing
+    will be unstable. From the command line, OCRmyPDF does this automatically,
+    but as an API user you must do this. See Python bpo-33725 for details.
+    Python 3.8+ also resolve this automatically.
+
+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
+:exc:`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:
+
+.. autofunction:: ocrmypdf.configure_logging

docs/apiref.rst

@@ -0,0 +1,55 @@
+=============
+API Reference
+=============
+
+This page summarizes the rest of the public API. Generally speaking this
+should mainly of interest to plugin developers.
+
+ocrmypdf
+========
+
+.. autoclass:: ocrmypdf.PageContext
+    :members:
+
+.. autoclass:: ocrmypdf.PdfContext
+    :members:
+
+ocrmypdf.exceptions
+===================
+
+.. automodule:: ocrmypdf.exceptions
+    :members:
+    :undoc-members:
+
+ocrmypdf.helpers
+================
+
+.. automodule:: ocrmypdf.helpers
+    :members:
+    :noindex: deprecated
+
+    .. autodecorator:: deprecated
+
+ocrmypdf.hocrtransform
+======================
+
+.. automodule:: ocrmypdf.hocrtransform
+    :members:
+
+ocrmypdf.pdfa
+=============
+
+.. automodule:: ocrmypdf.pdfa
+    :members:
+
+ocrmypdf.quality
+================
+
+.. automodule:: ocrmypdf.quality
+    :members:
+
+ocrmypdf.subprocess
+===================
+
+.. automodule:: ocrmypdf.subprocess
+    :members:

docs/batch.rst

@@ -1,142 +1,225 @@
+================
 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, and printing each filename in between runs:
 
 .. code-block:: bash
 
-	find . --printf '%p' -name '*.pdf' -exec ocrmypdf '{}' '{}' \;
+   find . -printf '%p\n' -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 and streaming the file through
+standard input and output:
 
 .. code-block:: bash
 
-	find . -name '*.pdf' | parallel --tag -j 2 ocrmypdf '{}' '{}'
+   find . -name '*.pdf' -print0 | xargs -0 | while read pdf; do
+       pdfout=$(mktemp)
+       docker run --rm -i jbarlow83/ocrmypdf - - <$pdf >$pdfout && cp $pdfout $pdf
+   done
 
+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 '{}' '{}'
+
+In a Windows batch file, use
+
+.. code-block:: bat
+
+   for /r %%f in (*.pdf) do ocrmypdf %%f %%f
 
 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
+.. literalinclude:: ../misc/batch.py
+    :caption: misc/batch.py
 
-	#!/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
-
-	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) > 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')
-
-	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)
-
-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.
+
+.. literalinclude:: ../misc/synology.py
+    :caption: misc/synology.py - Sample script for Synology DiskStations
+
+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
+=====================
+
+Watched folders with watcher.py
+-------------------------------
+
+OCRmyPDF has a folder watcher called watcher.py, which is currently included in source
+distributions but not part of the main program. It may be used natively or may run
+in a Docker container. Native instances tend to give better performance. watcher.py
+works on all platforms.
+
+Users may need to customize the script to meet their requirements.
 
 .. code-block:: bash
 
-	pip install watchdog
+    pip3 install ocrmypdf[watcher]
 
-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.
+    env OCR_INPUT_DIRECTORY=/mnt/input-pdfs \
+        OCR_OUTPUT_DIRECTORY=/mnt/output-pdfs \
+        OCR_OUTPUT_DIRECTORY_YEAR_MONTH=1 \
+        python3 watcher.py
+
+.. csv-table:: watcher.py environment variables
+    :header: "Environment variable", "Description"
+    :widths: 50, 50
+
+    "OCR_INPUT_DIRECTORY", "Set input directory to monitor (recursive)"
+    "OCR_OUTPUT_DIRECTORY", "Set output directory (should not be under input)"
+    "OCR_ARCHIVE_DIRECTORY", "Set archive directory for processed originals (should not be under input, requires ``OCR_ON_SUCCESS_ARCHIVE`` to be set)"
+    "OCR_ON_SUCCESS_DELETE", "This will delete the input file if the exit code is 0 (OK)"
+    "OCR_ON_SUCCESS_ARCHIVE", "This will move the processed orignal file to ``OCR_ARCHIVE_DIRECTORY`` if the exit code is 0 (OK). Note that ``OCR_ON_SUCCESS_DELETE`` takes precedence over this option, i.e. if both options are set, the input file will be deleted."
+    "OCR_OUTPUT_DIRECTORY_YEAR_MONTH", "This will place files in the output in ``{output}/{year}/{month}/{filename}``"
+    "OCR_DESKEW", "Apply deskew to crooked input PDFs"
+    "OCR_JSON_SETTINGS", "A JSON string specifying any other arguments for ``ocrmypdf.ocr``, e.g. ``'OCR_JSON_SETTINGS={""rotate_pages"": true}'``."
+    "OCR_POLL_NEW_FILE_SECONDS", "Polling interval"
+    "OCR_LOGLEVEL", "Level of log messages to report"
+
+One could configure a networked scanner or scanning computer to drop files in the
+watched folder.
+
+Watched folders with Docker
+---------------------------
+
+The watcher service is included in the OCRmyPDF Docker image. To run it:
 
 .. 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
+    docker run \
+        -v <path to files to convert>:/input \
+        -v <path to store results>:/output \
+        -v <path to store processed originals>:/archive \
+        -e OCR_OUTPUT_DIRECTORY_YEAR_MONTH=1 \
+        -e OCR_ON_SUCCESS_ARCHIVE=1 \
+        -e OCR_DESKEW=1 \
+        -e PYTHONUNBUFFERED=1 \
+        -it --entrypoint python3 \
+        jbarlow83/ocrmypdf \
+        watcher.py
 
-For more complex behavior you can write a Python script around to use the watchdog API.
+This service will watch for a file that matches ``/input/\*.pdf``,
+convert it to a OCRed PDF in ``/output/``, and move the processed
+original to ``/archive``. The parameters to this image are:
 
-On file servers, you could configure watchmedo as a system service so it will run all the time.
+.. csv-table:: watcher.py parameters for Docker
+    :header: "Parameter", "Description"
+    :widths: 50, 50
+
+    "``-v <path to files to convert>:/input``", "Files placed in this location will be OCRed"
+    "``-v <path to store results>:/output``", "This is where OCRed files will be stored"
+    "``-v <path to store processed originals>:/archive``", "Archive processed originals here"
+    "``-e OCR_OUTPUT_DIRECTORY_YEAR_MONTH=1``", "Define environment variable ``OCR_OUTPUT_DIRECTORY_YEAR_MONTH=1`` to place files in the output in ``{output}/{year}/{month}/{filename}``"
+    "``-e OCR_ON_SUCCESS_ARCHIVE=1``", "Define environment variable ``OCR_ON_SUCCESS_ARCHIVE`` to move processed originals"
+    "``-e OCR_DESKEW=1``", "Define environment variable ``OCR_DESKEW``  to apply deskew to crooked input PDFs"
+    "``-e PYTHONBUFFERED=1``", "This will force ``STDOUT`` to be unbuffered and allow you to see messages in docker logs"
+
+This service relies on polling to check for changes to the filesystem. It
+may not be suitable for some environments, such as filesystems shared on a
+slow network.
+
+A configuration manager such as Docker Compose could be used to ensure that the
+service is always available.
+
+.. literalinclude:: ../misc/docker-compose.example.yml
+    :language: yaml
+    :caption: misc/docker-compose.example.yml
 
 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``.
+-  On Linux, `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:
+
+.. figure:: images/macos-workflow.png
+    :alt: Example macOS Automator workflow
+
+You may customize the command sent to ocrmypdf.

docs/conf.py

@@ -1,5 +1,4 @@
 #!/usr/bin/env python3
-# -*- coding: utf-8 -*-
 #
 # ocrmypdf documentation build configuration file, created by
 # sphinx-quickstart on Sun Sep  4 14:29:43 2016.
@@ -21,6 +20,8 @@
 # import sys
 # sys.path.insert(0, os.path.abspath('.'))
 
+"""isort:skip_file"""
+
 # -- General configuration ------------------------------------------------
 
 # If your documentation needs a minimal Sphinx version, state it here.
@@ -31,9 +32,18 @@
 # extensions coming with Sphinx (named 'sphinx.ext.*') or your custom
 # ones.
 extensions = [
-    # 'sphinx.ext.mathjax',
+    'sphinx.ext.autodoc',
+    'sphinx.ext.intersphinx',
+    'sphinx.ext.autosummary',
+    'sphinx.ext.napoleon',
+    'sphinx_issues',
 ]
 
+# Extension settings
+intersphinx_mapping = {'https://docs.python.org/': None}
+napoleon_use_rtype = False
+issues_github_path = "ocrmypdf/OCRmyPDF"
+
 # Add any paths that contain templates here, relative to this directory.
 templates_path = ['_templates']
 
@@ -52,7 +62,9 @@ master_doc = 'index'
 
 # General information about the project.
 project = 'ocrmypdf'
-copyright = '2017, James R. Barlow'
+copyright = (
+    '2022, 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 +72,37 @@ 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',
+    ]
+    sys.modules.update((mod_name, Mock()) for mod_name in MOCK_MODULES)
+
+try:
+    from importlib_metadata import version as package_version
+except ModuleNotFoundError:
+    from importlib.metadata import version as package_version
 
-version = '.'.join(_version_parts[0:2])
 # The full version, including alpha/beta/rc tags.
-release = OCRMYPDF_VERSION
+release = package_version('ocrmypdf')
+version = '.'.join(release.split('.')[:2])
+
 
 # The language for content autogenerated by Sphinx. Refer to documentation
 # for a list of supported languages.
@@ -135,9 +171,7 @@ 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 = []
@@ -154,7 +188,7 @@ html_theme_options = {
 # The name of an image file (relative to this directory) to place at the top
 # of the sidebar.
 #
-# html_logo = None
+# html_logo = "images/logo.svg"  # looks bad
 
 # The name of an image file (relative to this directory) to use as a favicon of
 # the docs.  This file should be a Windows icon file (.ico) being 16x16 or 32x32
@@ -249,30 +283,26 @@ 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',
+latex_elements = {  # type: ignore
+    # 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 +342,7 @@ 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 +355,15 @@ 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 +1,56 @@
+=======================
+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 these programs are in ``pyproject.toml`` and ``setup.cfg``. Pull
+requests should follow the style guide. One difference we use from "black" style
+is that strings shown to the user are always in double quotes (``"``) and strings
+for internal uses are in single quotes (``'``).
+
+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 license-compatible. GPLv3 or AGPLv3 are likely
+incompatible with the project's license, but LGPLv3 is 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.
+
+Style guide: Is it OCRmyPDF or ocrmypdf?
+========================================
+
+The program/project is OCRmyPDF and the name of the executable or library is ocrmypdf.
+
+Copyright and license
+=====================
+
+For contributions over 10 lines of code, please include your name to list of
+copyright holders for that file. The core program is licensed under MPL-2.0,
+test files and documentation under CC-BY-SA 4.0, and miscellaneous files under
+MIT. Please contribute code only that you wrote and you have the permission to
+contribute or license to us.

docs/cookbook.rst

@@ -1,166 +1,362 @@
+========
 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. The threshold number is the ratio
+of how confidence the OCR engine is that the document image should be changed,
+compared to kept the same. The default value is quite conservative; on some files
+it may not attempt rotations at all unless it is very confident that the current
+rotation is wrong. A lower value of ``2.0`` will produce more rotations, and
+more false positives. Run with ``-v1`` to see the confidence level for each
+page to see if there may be a better value for your files.
 
+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
+    ocrmypdf --sidecar output.txt input.pdf output.pdf
 
 .. note::
 
-	To get pdftotext, Debian/Ubuntu users may ``apt-get install poppler-utils`` 
-	and macOS users may ``brew install poppler`` respectively.
+    The sidecar file contains the **OCR text** found by OCRmyPDF. If the document
+    contains pages that already have text, that text will not appear in the
+    sidecar. If the option ``--pages`` is used, only those pages on which OCR
+    was performed will be included in the sidecar. If certain pages were skipped
+    because of options like ``--skip-big`` or ``--tesseract-timeout``, those pages
+    will not be in the sidecar.
 
+    If you don't want to generate the output PDF, use ``--output-type=none`` to
+    avoid generating one. Set the output filename to ``-`` (i.e. redirect to stdout).
+
+    To extract all text from a PDF, whether generated from OCR or otherwise,
+    use a program like Poppler's ``pdftotext`` or ``pdfgrep``.
 
 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.
+-  ``--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
+
+Process only certain pages
+--------------------------
+
+You can ask OCRmyPDF to only apply `image processing <#image-processing>`__
+and OCR to certain pages.
+
+.. code-block:: bash
+
+    ocrmypdf --pages 2,3,13-17 input.pdf output.pdf
+
+Hyphens denote a range of pages and commas separate page numbers. If you prefer
+to use spaces, quote all of the page numbers: ``--pages '2, 3, 5, 7'``.
+
+OCRmyPDF will warn if your list of page numbers contains duplicates or
+overlap pages. OCRmyPDF does not currently account for document page numbers,
+such as an introduction section of a book that uses Roman numerals. It simply
+counts the number of virtual pieces of paper since the start.
+
+Regardless of the argument to ``--pages``, OCRmyPDF will optimize all pages/images
+in the file and convert it to PDF/A, unless you disable those options. Both of these
+steps are "whole file" operations. In this example, we want to OCR only the title
+and otherwise change the PDF as little as possible:
+
+.. code-block:: bash
+
+    ocrmypdf --pages 1 --output-type pdf --optimize 0 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 +1,196 @@
+.. _docker:
+
+=====================
+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 $(docker-machine env "yourVM")
+
+See the Docker documentation for
+`adjusting memory and CPU on other platforms <https://docs.docker.com/config/containers/resource_constraints/>`__.
+
+Using the Docker image on the command line
+==========================================
+
+**Unlike typical Docker containers**, in this section the OCRmyPDF Docker
+container is ephemeral – it runs for one OCR job and terminates, just like a
+command line program. We are using Docker to deliver an application (as opposed
+to the more conventional case, where a Docker container runs as a server).
+
+To start a Docker container (instance of the image):
+
+.. code-block:: bash
+
+   docker tag jbarlow83/ocrmypdf ocrmypdf
+   docker run --rm -i ocrmypdf (... all other arguments here...) - -
+
+For convenience, create a shell alias to hide the Docker command. It is
+easier to send the input file as stdin and read the output from
+stdout – **this avoids the messy permission issues with Docker entirely**.
+
+.. code-block:: bash
+
+   alias docker_ocrmypdf='docker run --rm -i ocrmypdf'
+   docker_ocrmypdf --version  # runs docker version
+   docker_ocrmypdf - - <input.pdf >output.pdf
+
+Or in the wonderful `fish shell <https://fishshell.com/>`__:
+
+.. code-block:: fish
+
+   alias docker_ocrmypdf 'docker run --rm ocrmypdf'
+   funcsave docker_ocrmypdf
+
+Alternately, you could mount the local current working directory as a
+Docker volume:
+
+.. code-block:: bash
+
+   alias docker_ocrmypdf='docker run --rm  -i --user "$(id -u):$(id -g)" --workdir /data -v "$PWD:/data" ocrmypdf'
+   docker_ocrmypdf /data/input.pdf /data/output.pdf
+
+.. _docker-lang-packs:
+
+Adding languages to the Docker image
+====================================
+
+By default the Docker image includes English, German, Simplified Chinese,
+French, Portuguese and Spanish, 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
+
+   # Example: add Italian
+   RUN apt install tesseract-ocr-ita
+
+To install language packs (training data) such as the 
+`tessdata_best <https://github.com/tesseract-ocr/tessdata_best>`_ suite or
+custom data, you first need to determine the version of Tesseract data files, which
+may differ from the Tesseract program version. Use this command to determine the data
+file version:
+
+.. code-block:: bash
+
+   docker run -i --rm --entrypoint /bin/ls jbarlow83/ocrmypdf /usr/share/tesseract-ocr
+
+As of 2021, the data file version is probably ``4.00``.
+
+You can then add new data with either a Dockerfile:
+
+.. code-block:: dockerfile
+
+   FROM jbarlow83/ocrmypdf
+
+   # Example: add a tessdata_best file
+   COPY chi_tra_vert.traineddata /usr/share/tesseract-ocr/<data version>/tessdata/
+
+Alternately, you can copy training data into a Docker container as follows:
+
+.. code-block:: bash
+
+   docker cp mycustomtraining.traineddata name_of_container:/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 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 +1,53 @@
+=====================
 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.
+-  ``ocrmypdf --redo-ocr`` to scan the file for any existing OCR
+   (non-printing text), remove it, and do OCR again. This is one way
+   to take advantage of improvements in OCR accuracy. Printable vector
+   text is excluded from OCR, so this can be used on files that contain
+   a mix of digital and scanned files.
 
 
 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 checks files with pikepdf, a library that in turn uses libqpdf to 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-square-256.svg

@@ -0,0 +1,239 @@
+<?xml version="1.0" encoding="UTF-8" standalone="no"?>
+<svg
+   width="256"
+   height="256"
+   viewBox="0 0 256 256.00001"
+   version="1.1"
+   xml:space="preserve"
+   style="clip-rule:evenodd;fill-rule:evenodd;stroke-linecap:round;stroke-linejoin:round;stroke-miterlimit:1.5"
+   id="svg270"
+   sodipodi:docname="logo-square-256.svg"
+   inkscape:export-filename="/home/jb/src/ocrmypdf/docs/images/logo-square.png"
+   inkscape:export-xdpi="96"
+   inkscape:export-ydpi="96"
+   inkscape:version="1.1.2 (0a00cf5339, 2022-02-04)"
+   xmlns:inkscape="http://www.inkscape.org/namespaces/inkscape"
+   xmlns:sodipodi="http://sodipodi.sourceforge.net/DTD/sodipodi-0.dtd"
+   xmlns="http://www.w3.org/2000/svg"
+   xmlns:svg="http://www.w3.org/2000/svg"
+   xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
+   xmlns:cc="http://creativecommons.org/ns#"
+   xmlns:dc="http://purl.org/dc/elements/1.1/"
+   xmlns:serif="http://www.serif.com/"><metadata
+   id="metadata276"><rdf:RDF><cc:Work
+       rdf:about=""><dc:format>image/svg+xml</dc:format><dc:type
+         rdf:resource="http://purl.org/dc/dcmitype/StillImage" /></cc:Work></rdf:RDF></metadata><defs
+   id="defs274" /><sodipodi:namedview
+   pagecolor="#ffffff"
+   bordercolor="#666666"
+   borderopacity="1"
+   objecttolerance="10"
+   gridtolerance="10"
+   guidetolerance="10"
+   inkscape:pageopacity="0"
+   inkscape:pageshadow="2"
+   inkscape:window-width="2396"
+   inkscape:window-height="1691"
+   id="namedview272"
+   showgrid="false"
+   lock-margins="false"
+   inkscape:zoom="2.0079523"
+   inkscape:cx="189.74554"
+   inkscape:cy="54.533168"
+   inkscape:window-x="26"
+   inkscape:window-y="23"
+   inkscape:window-maximized="0"
+   inkscape:current-layer="svg270"
+   inkscape:pagecheckerboard="0"
+   width="256px"
+   fit-margin-top="0"
+   fit-margin-left="0"
+   fit-margin-right="0"
+   fit-margin-bottom="0" />
+    <g
+   id="svg"
+   transform="matrix(0.48534351,0,0,0.4057699,1.8106874,71.192214)">
+        <rect
+   x="0"
+   y="0"
+   width="520"
+   height="280"
+   style="fill:#ffffff"
+   id="rect188" />
+        <g
+   transform="matrix(1.03522,0,0,1.23823,-69.7528,-83.422)"
+   id="g267">
+            <g
+   transform="translate(243.977,20.0703)"
+   id="g218">
+                <g
+   id="Page">
+                    <g
+   transform="matrix(0.961773,0,0,1.05962,6.19811,-3.01071)"
+   id="g192">
+                        <path
+   d="m 328.5,97.682 c 0,-1.217 -0.517,-2.386 -1.444,-3.264 -7.03,-6.66 -37.614,-35.638 -44.828,-42.474 -0.977,-0.925 -2.327,-1.448 -3.738,-1.448 -13.997,0 -90.407,0 -111.151,0 -2.871,0 -5.198,2.113 -5.198,4.718 0,27.837 0,170.351 0,198.186 0,2.605 2.327,4.717 5.197,4.717 24.904,0 131.821,0 156.2,0 2.74,0 4.962,-2.016 4.962,-4.504 0,-24.345 0,-139.717 0,-155.931 z"
+   style="fill:#fdfdfd;stroke:#333333;stroke-width:3.95px"
+   id="path190" />
+                    </g>
+                    <g
+   id="Dog-ear"
+   serif:id="Dog ear"
+   transform="translate(-4,2)">
+                        <path
+   d="m 277.072,48.496 v 45.352 c 0,1.324 0.526,2.593 1.462,3.529 0.936,0.936 2.205,1.462 3.529,1.462 12.485,0 44.078,0 44.078,0"
+   style="fill:#f5f5f5;stroke:#333333;stroke-width:4px"
+   id="path194" />
+                    </g>
+                </g>
+                <g
+   transform="translate(-29.6816,-0.395178)"
+   id="g216">
+                    <g
+   transform="matrix(1.00243,0,0,1.11818,-144.72,-8.80181)"
+   id="g200">
+                        <path
+   d="m 465.73,119.654 c 0,-2.049 -1.856,-3.713 -4.142,-3.713 H 310.259 c -2.286,0 -4.142,1.664 -4.142,3.713 v 63.454 c 0,2.049 1.856,3.713 4.142,3.713 h 151.329 c 2.286,0 4.142,-1.664 4.142,-3.713 z"
+   style="fill:#f80000;stroke:#ffffff;stroke-width:3.77px"
+   id="path198" />
+                    </g>
+                    <g
+   transform="matrix(1.24571,0,0,1.35864,116.812,84.3924)"
+   id="g214">
+                        <g
+   transform="matrix(64,0,0,64,42.1437,77.6203)"
+   id="g204">
+                            <path
+   d="m 0.084,0 v -0.68 h 0.213 c 0.074,0 0.137,0.017 0.19,0.05 0.053,0.034 0.079,0.09 0.079,0.168 0,0.077 -0.028,0.134 -0.085,0.17 -0.057,0.037 -0.121,0.055 -0.193,0.055 H 0.213 V 0 Z m 0.209,-0.572 h -0.08 v 0.228 h 0.082 c 0.039,0 0.07,-0.009 0.094,-0.027 0.024,-0.017 0.037,-0.045 0.04,-0.083 0,-0.044 -0.012,-0.075 -0.036,-0.092 -0.024,-0.017 -0.057,-0.026 -0.1,-0.026 z"
+   style="fill:#ffffff;fill-rule:nonzero"
+   id="path202" />
+                        </g>
+                        <g
+   transform="matrix(64,0,0,64,79.7117,77.6203)"
+   id="g208">
+                            <path
+   d="M 0.332,0 H 0.084 v -0.68 h 0.252 c 0.105,0 0.182,0.032 0.233,0.095 0.051,0.063 0.076,0.144 0.076,0.241 0,0.105 -0.027,0.189 -0.082,0.251 C 0.508,-0.031 0.431,0 0.332,0 Z M 0.337,-0.57 H 0.213 v 0.461 H 0.33 c 0.055,0 0.099,-0.018 0.132,-0.054 C 0.495,-0.199 0.511,-0.259 0.511,-0.344 0.511,-0.415 0.497,-0.47 0.469,-0.51 0.441,-0.55 0.397,-0.57 0.337,-0.57 Z"
+   style="fill:#ffffff;fill-rule:nonzero"
+   id="path206" />
+                        </g>
+                        <g
+   transform="matrix(64,0,0,64,123.424,77.6203)"
+   id="g212">
+                            <path
+   d="M 0.405,-0.288 H 0.213 V 0 H 0.084 v -0.68 h 0.385 l 0.02,0.102 H 0.213 v 0.189 h 0.173 z"
+   style="fill:#ffffff;fill-rule:nonzero"
+   id="path210" />
+                        </g>
+                    </g>
+                </g>
+            </g>
+            <g
+   transform="matrix(1,0,0,1.52217,67.3796,10.7507)"
+   id="g222">
+                <rect
+   x="23.500999"
+   y="81.300003"
+   width="162.30499"
+   height="61.77"
+   style="fill:#b4d5ff"
+   id="rect220" />
+            </g>
+            <g
+   transform="matrix(0.967536,0,0,0.961535,5.90498,47.9703)"
+   id="g236">
+                <g
+   transform="matrix(90.4804,0,0,90.4804,82.6698,167.705)"
+   id="g226">
+                    <path
+   d="m 0.057,-0.337 c 0,-0.105 0.027,-0.19 0.082,-0.257 0.055,-0.066 0.132,-0.1 0.231,-0.102 0.107,0 0.186,0.034 0.237,0.103 0.051,0.069 0.077,0.152 0.077,0.249 0,0.105 -0.027,0.191 -0.082,0.258 -0.055,0.067 -0.133,0.1 -0.232,0.1 C 0.264,0.014 0.185,-0.02 0.134,-0.089 0.083,-0.157 0.057,-0.24 0.057,-0.337 Z m 0.135,-0.001 c 0,0.071 0.014,0.13 0.043,0.175 0.029,0.045 0.073,0.068 0.134,0.068 0.055,0 0.098,-0.02 0.131,-0.061 0.033,-0.041 0.049,-0.103 0.049,-0.188 0,-0.071 -0.014,-0.129 -0.043,-0.174 -0.029,-0.045 -0.073,-0.068 -0.134,-0.068 -0.053,0 -0.097,0.022 -0.13,0.067 -0.033,0.045 -0.05,0.105 -0.05,0.181 z"
+   style="fill:#333333;fill-rule:nonzero"
+   id="path224" />
+                </g>
+                <g
+   transform="matrix(90.4804,0,0,90.4804,147.906,167.705)"
+   id="g230">
+                    <path
+   d="M 0.505,-0.557 C 0.473,-0.567 0.448,-0.574 0.429,-0.579 0.41,-0.583 0.388,-0.585 0.361,-0.585 c -0.054,0 -0.096,0.022 -0.125,0.066 -0.029,0.044 -0.044,0.104 -0.044,0.181 0,0.066 0.012,0.123 0.037,0.171 0.025,0.048 0.066,0.072 0.124,0.072 0.029,0 0.056,-0.003 0.081,-0.009 0.025,-0.006 0.047,-0.013 0.068,-0.022 L 0.551,-0.03 C 0.525,-0.017 0.494,-0.006 0.457,0.002 0.42,0.01 0.388,0.014 0.36,0.014 0.254,0.014 0.177,-0.02 0.129,-0.088 0.081,-0.156 0.057,-0.239 0.057,-0.337 c 0,-0.105 0.027,-0.19 0.08,-0.257 0.053,-0.067 0.129,-0.1 0.228,-0.1 0.02,0 0.048,0.003 0.083,0.01 0.035,0.007 0.068,0.018 0.097,0.034 z"
+   style="fill:#333333;fill-rule:nonzero"
+   id="path228" />
+                </g>
+                <g
+   transform="matrix(90.4804,0,0,90.4804,199.751,167.705)"
+   id="g234">
+                    <path
+   d="m 0.293,-0.572 h -0.08 v 0.208 h 0.082 c 0.039,0 0.071,-0.008 0.096,-0.024 0.025,-0.015 0.038,-0.041 0.038,-0.077 0,-0.038 -0.012,-0.065 -0.036,-0.082 -0.024,-0.017 -0.057,-0.025 -0.1,-0.025 z M 0.479,0 0.335,-0.26 C 0.328,-0.259 0.32,-0.259 0.312,-0.259 0.304,-0.258 0.296,-0.258 0.288,-0.258 H 0.213 V 0 H 0.084 v -0.68 h 0.213 c 0.074,0 0.137,0.017 0.19,0.051 0.053,0.034 0.079,0.087 0.079,0.158 0,0.042 -0.011,0.078 -0.032,0.108 -0.022,0.031 -0.05,0.054 -0.084,0.071 L 0.617,0 Z"
+   style="fill:#333333;fill-rule:nonzero"
+   id="path232" />
+                </g>
+            </g>
+            <g
+   transform="matrix(0.916882,0,0,1,121.475,-32.6535)"
+   id="g246">
+                <g
+   transform="matrix(86.953,0,0,86.953,152.996,241.878)"
+   id="g240">
+                    <path
+   d="M 0.479,-0.428 C 0.5,-0.451 0.527,-0.47 0.562,-0.484 c 0.034,-0.013 0.065,-0.02 0.092,-0.02 0.066,0 0.113,0.019 0.141,0.058 0.027,0.039 0.041,0.086 0.041,0.142 V 0 H 0.705 v -0.298 c 0,-0.031 -0.007,-0.054 -0.022,-0.071 -0.015,-0.016 -0.036,-0.024 -0.064,-0.024 -0.019,0 -0.038,0.005 -0.059,0.015 -0.021,0.01 -0.039,0.021 -0.056,0.034 0.001,0.007 0.001,0.013 0.002,0.02 0.001,0.007 0.001,0.013 0.001,0.02 V 0 H 0.376 v -0.298 c 0,-0.031 -0.007,-0.054 -0.022,-0.071 -0.015,-0.016 -0.036,-0.024 -0.063,-0.024 -0.017,0 -0.033,0.003 -0.05,0.01 -0.017,0.007 -0.034,0.016 -0.049,0.027 V 0 H 0.062 V -0.485 H 0.13 l 0.032,0.044 c 0.022,-0.02 0.049,-0.035 0.08,-0.047 0.031,-0.011 0.058,-0.016 0.083,-0.016 0.038,0 0.07,0.007 0.095,0.02 0.025,0.014 0.045,0.033 0.059,0.056 z"
+   style="fill:#333333;fill-rule:nonzero"
+   id="path238" />
+                </g>
+                <g
+   transform="matrix(86.953,0,0,86.953,228.906,241.878)"
+   id="g244">
+                    <path
+   d="M 0.156,0.023 0.179,-0.034 0.006,-0.467 0.14,-0.485 0.252,-0.191 0.358,-0.485 H 0.495 L 0.278,0.064 C 0.263,0.103 0.236,0.137 0.197,0.165 0.158,0.193 0.118,0.212 0.075,0.222 L 0.029,0.115 C 0.052,0.105 0.077,0.093 0.104,0.079 0.13,0.064 0.147,0.046 0.156,0.023 Z"
+   style="fill:#333333;fill-rule:nonzero"
+   id="path242" />
+                </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)"
+   id="g250">
+                        <path
+   d="M 185.806,161.156 V 67.132"
+   style="fill:none;stroke:#4c9fff;stroke-width:4px;stroke-linecap:butt"
+   id="path248" />
+                    </g>
+                    <g
+   transform="matrix(1.03522,0,0,1.23823,161.788,169.469)"
+   id="g254">
+                        <circle
+   cx="31.523001"
+   cy="34.313999"
+   r="10.021"
+   style="fill:#4c9fff;stroke:#4c9fff;stroke-width:4px;stroke-linecap:butt"
+   id="circle252" />
+                    </g>
+                </g>
+                <g
+   id="Left-selector"
+   serif:id="Left selector">
+                    <g
+   transform="matrix(1.03522,0,0,1.23823,-170.092,0)"
+   id="g259">
+                        <path
+   d="M 185.806,161.156 V 67.132"
+   style="fill:none;stroke:#4c9fff;stroke-width:4px;stroke-linecap:butt"
+   id="path257" />
+                    </g>
+                    <g
+   transform="matrix(1.03522,0,0,1.23823,-10.3742,28.2274)"
+   id="g263">
+                        <circle
+   cx="31.523001"
+   cy="34.313999"
+   r="10.021"
+   style="fill:#4c9fff;stroke:#4c9fff;stroke-width:4px;stroke-linecap:butt"
+   id="circle261" />
+                    </g>
+                </g>
+            </g>
+        </g>
+    </g>
+</svg>

docs/images/logo-square.svg

@@ -0,0 +1,233 @@
+<?xml version="1.0" encoding="UTF-8" standalone="no"?>
+<svg
+   xmlns:serif="http://www.serif.com/"
+   xmlns:dc="http://purl.org/dc/elements/1.1/"
+   xmlns:cc="http://creativecommons.org/ns#"
+   xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
+   xmlns:svg="http://www.w3.org/2000/svg"
+   xmlns="http://www.w3.org/2000/svg"
+   xmlns:sodipodi="http://sodipodi.sourceforge.net/DTD/sodipodi-0.dtd"
+   xmlns:inkscape="http://www.inkscape.org/namespaces/inkscape"
+   width="503"
+   height="503"
+   viewBox="0 0 503 503"
+   version="1.1"
+   xml:space="preserve"
+   style="clip-rule:evenodd;fill-rule:evenodd;stroke-linecap:round;stroke-linejoin:round;stroke-miterlimit:1.5"
+   id="svg270"
+   sodipodi:docname="logo-square.svg"
+   inkscape:export-filename="/home/jb/src/ocrmypdf/docs/images/logo-square.png"
+   inkscape:export-xdpi="96"
+   inkscape:export-ydpi="96"
+   inkscape:version="1.0.2 (e86c870879, 2021-01-15)"><metadata
+   id="metadata276"><rdf:RDF><cc:Work
+       rdf:about=""><dc:format>image/svg+xml</dc:format><dc:type
+         rdf:resource="http://purl.org/dc/dcmitype/StillImage" /><dc:title></dc:title></cc:Work></rdf:RDF></metadata><defs
+   id="defs274" /><sodipodi:namedview
+   pagecolor="#ffffff"
+   bordercolor="#666666"
+   borderopacity="1"
+   objecttolerance="10"
+   gridtolerance="10"
+   guidetolerance="10"
+   inkscape:pageopacity="0"
+   inkscape:pageshadow="2"
+   inkscape:window-width="2396"
+   inkscape:window-height="1691"
+   id="namedview272"
+   showgrid="false"
+   lock-margins="false"
+   inkscape:zoom="2.0079523"
+   inkscape:cx="251.5"
+   inkscape:cy="193.18317"
+   inkscape:window-x="26"
+   inkscape:window-y="23"
+   inkscape:window-maximized="0"
+   inkscape:current-layer="svg270" />
+    <g
+   id="svg"
+   transform="matrix(0.965977,0,0,0.807602,0,138.43572)">
+        <rect
+   x="0"
+   y="0"
+   width="520"
+   height="280"
+   style="fill:#ffffff"
+   id="rect188" />
+        <g
+   transform="matrix(1.03522,0,0,1.23823,-69.7528,-83.422)"
+   id="g267">
+            <g
+   transform="translate(243.977,20.0703)"
+   id="g218">
+                <g
+   id="Page">
+                    <g
+   transform="matrix(0.961773,0,0,1.05962,6.19811,-3.01071)"
+   id="g192">
+                        <path
+   d="m 328.5,97.682 c 0,-1.217 -0.517,-2.386 -1.444,-3.264 -7.03,-6.66 -37.614,-35.638 -44.828,-42.474 -0.977,-0.925 -2.327,-1.448 -3.738,-1.448 -13.997,0 -90.407,0 -111.151,0 -2.871,0 -5.198,2.113 -5.198,4.718 0,27.837 0,170.351 0,198.186 0,2.605 2.327,4.717 5.197,4.717 24.904,0 131.821,0 156.2,0 2.74,0 4.962,-2.016 4.962,-4.504 0,-24.345 0,-139.717 0,-155.931 z"
+   style="fill:#fdfdfd;stroke:#333333;stroke-width:3.95px"
+   id="path190" />
+                    </g>
+                    <g
+   id="Dog-ear"
+   serif:id="Dog ear"
+   transform="translate(-4,2)">
+                        <path
+   d="m 277.072,48.496 v 45.352 c 0,1.324 0.526,2.593 1.462,3.529 0.936,0.936 2.205,1.462 3.529,1.462 12.485,0 44.078,0 44.078,0"
+   style="fill:#f5f5f5;stroke:#333333;stroke-width:4px"
+   id="path194" />
+                    </g>
+                </g>
+                <g
+   transform="translate(-29.6816,-0.395178)"
+   id="g216">
+                    <g
+   transform="matrix(1.00243,0,0,1.11818,-144.72,-8.80181)"
+   id="g200">
+                        <path
+   d="m 465.73,119.654 c 0,-2.049 -1.856,-3.713 -4.142,-3.713 H 310.259 c -2.286,0 -4.142,1.664 -4.142,3.713 v 63.454 c 0,2.049 1.856,3.713 4.142,3.713 h 151.329 c 2.286,0 4.142,-1.664 4.142,-3.713 z"
+   style="fill:#f80000;stroke:#ffffff;stroke-width:3.77px"
+   id="path198" />
+                    </g>
+                    <g
+   transform="matrix(1.24571,0,0,1.35864,116.812,84.3924)"
+   id="g214">
+                        <g
+   transform="matrix(64,0,0,64,42.1437,77.6203)"
+   id="g204">
+                            <path
+   d="m 0.084,0 v -0.68 h 0.213 c 0.074,0 0.137,0.017 0.19,0.05 0.053,0.034 0.079,0.09 0.079,0.168 0,0.077 -0.028,0.134 -0.085,0.17 -0.057,0.037 -0.121,0.055 -0.193,0.055 H 0.213 V 0 Z m 0.209,-0.572 h -0.08 v 0.228 h 0.082 c 0.039,0 0.07,-0.009 0.094,-0.027 0.024,-0.017 0.037,-0.045 0.04,-0.083 0,-0.044 -0.012,-0.075 -0.036,-0.092 -0.024,-0.017 -0.057,-0.026 -0.1,-0.026 z"
+   style="fill:#ffffff;fill-rule:nonzero"
+   id="path202" />
+                        </g>
+                        <g
+   transform="matrix(64,0,0,64,79.7117,77.6203)"
+   id="g208">
+                            <path
+   d="M 0.332,0 H 0.084 v -0.68 h 0.252 c 0.105,0 0.182,0.032 0.233,0.095 0.051,0.063 0.076,0.144 0.076,0.241 0,0.105 -0.027,0.189 -0.082,0.251 C 0.508,-0.031 0.431,0 0.332,0 Z M 0.337,-0.57 H 0.213 v 0.461 H 0.33 c 0.055,0 0.099,-0.018 0.132,-0.054 C 0.495,-0.199 0.511,-0.259 0.511,-0.344 0.511,-0.415 0.497,-0.47 0.469,-0.51 0.441,-0.55 0.397,-0.57 0.337,-0.57 Z"
+   style="fill:#ffffff;fill-rule:nonzero"
+   id="path206" />
+                        </g>
+                        <g
+   transform="matrix(64,0,0,64,123.424,77.6203)"
+   id="g212">
+                            <path
+   d="M 0.405,-0.288 H 0.213 V 0 H 0.084 v -0.68 h 0.385 l 0.02,0.102 H 0.213 v 0.189 h 0.173 z"
+   style="fill:#ffffff;fill-rule:nonzero"
+   id="path210" />
+                        </g>
+                    </g>
+                </g>
+            </g>
+            <g
+   transform="matrix(1,0,0,1.52217,67.3796,10.7507)"
+   id="g222">
+                <rect
+   x="23.500999"
+   y="81.300003"
+   width="162.30499"
+   height="61.77"
+   style="fill:#b4d5ff"
+   id="rect220" />
+            </g>
+            <g
+   transform="matrix(0.967536,0,0,0.961535,5.90498,47.9703)"
+   id="g236">
+                <g
+   transform="matrix(90.4804,0,0,90.4804,82.6698,167.705)"
+   id="g226">
+                    <path
+   d="m 0.057,-0.337 c 0,-0.105 0.027,-0.19 0.082,-0.257 0.055,-0.066 0.132,-0.1 0.231,-0.102 0.107,0 0.186,0.034 0.237,0.103 0.051,0.069 0.077,0.152 0.077,0.249 0,0.105 -0.027,0.191 -0.082,0.258 -0.055,0.067 -0.133,0.1 -0.232,0.1 C 0.264,0.014 0.185,-0.02 0.134,-0.089 0.083,-0.157 0.057,-0.24 0.057,-0.337 Z m 0.135,-0.001 c 0,0.071 0.014,0.13 0.043,0.175 0.029,0.045 0.073,0.068 0.134,0.068 0.055,0 0.098,-0.02 0.131,-0.061 0.033,-0.041 0.049,-0.103 0.049,-0.188 0,-0.071 -0.014,-0.129 -0.043,-0.174 -0.029,-0.045 -0.073,-0.068 -0.134,-0.068 -0.053,0 -0.097,0.022 -0.13,0.067 -0.033,0.045 -0.05,0.105 -0.05,0.181 z"
+   style="fill:#333333;fill-rule:nonzero"
+   id="path224" />
+                </g>
+                <g
+   transform="matrix(90.4804,0,0,90.4804,147.906,167.705)"
+   id="g230">
+                    <path
+   d="M 0.505,-0.557 C 0.473,-0.567 0.448,-0.574 0.429,-0.579 0.41,-0.583 0.388,-0.585 0.361,-0.585 c -0.054,0 -0.096,0.022 -0.125,0.066 -0.029,0.044 -0.044,0.104 -0.044,0.181 0,0.066 0.012,0.123 0.037,0.171 0.025,0.048 0.066,0.072 0.124,0.072 0.029,0 0.056,-0.003 0.081,-0.009 0.025,-0.006 0.047,-0.013 0.068,-0.022 L 0.551,-0.03 C 0.525,-0.017 0.494,-0.006 0.457,0.002 0.42,0.01 0.388,0.014 0.36,0.014 0.254,0.014 0.177,-0.02 0.129,-0.088 0.081,-0.156 0.057,-0.239 0.057,-0.337 c 0,-0.105 0.027,-0.19 0.08,-0.257 0.053,-0.067 0.129,-0.1 0.228,-0.1 0.02,0 0.048,0.003 0.083,0.01 0.035,0.007 0.068,0.018 0.097,0.034 z"
+   style="fill:#333333;fill-rule:nonzero"
+   id="path228" />
+                </g>
+                <g
+   transform="matrix(90.4804,0,0,90.4804,199.751,167.705)"
+   id="g234">
+                    <path
+   d="m 0.293,-0.572 h -0.08 v 0.208 h 0.082 c 0.039,0 0.071,-0.008 0.096,-0.024 0.025,-0.015 0.038,-0.041 0.038,-0.077 0,-0.038 -0.012,-0.065 -0.036,-0.082 -0.024,-0.017 -0.057,-0.025 -0.1,-0.025 z M 0.479,0 0.335,-0.26 C 0.328,-0.259 0.32,-0.259 0.312,-0.259 0.304,-0.258 0.296,-0.258 0.288,-0.258 H 0.213 V 0 H 0.084 v -0.68 h 0.213 c 0.074,0 0.137,0.017 0.19,0.051 0.053,0.034 0.079,0.087 0.079,0.158 0,0.042 -0.011,0.078 -0.032,0.108 -0.022,0.031 -0.05,0.054 -0.084,0.071 L 0.617,0 Z"
+   style="fill:#333333;fill-rule:nonzero"
+   id="path232" />
+                </g>
+            </g>
+            <g
+   transform="matrix(0.916882,0,0,1,121.475,-32.6535)"
+   id="g246">
+                <g
+   transform="matrix(86.953,0,0,86.953,152.996,241.878)"
+   id="g240">
+                    <path
+   d="M 0.479,-0.428 C 0.5,-0.451 0.527,-0.47 0.562,-0.484 c 0.034,-0.013 0.065,-0.02 0.092,-0.02 0.066,0 0.113,0.019 0.141,0.058 0.027,0.039 0.041,0.086 0.041,0.142 V 0 H 0.705 v -0.298 c 0,-0.031 -0.007,-0.054 -0.022,-0.071 -0.015,-0.016 -0.036,-0.024 -0.064,-0.024 -0.019,0 -0.038,0.005 -0.059,0.015 -0.021,0.01 -0.039,0.021 -0.056,0.034 0.001,0.007 0.001,0.013 0.002,0.02 0.001,0.007 0.001,0.013 0.001,0.02 V 0 H 0.376 v -0.298 c 0,-0.031 -0.007,-0.054 -0.022,-0.071 -0.015,-0.016 -0.036,-0.024 -0.063,-0.024 -0.017,0 -0.033,0.003 -0.05,0.01 -0.017,0.007 -0.034,0.016 -0.049,0.027 V 0 H 0.062 V -0.485 H 0.13 l 0.032,0.044 c 0.022,-0.02 0.049,-0.035 0.08,-0.047 0.031,-0.011 0.058,-0.016 0.083,-0.016 0.038,0 0.07,0.007 0.095,0.02 0.025,0.014 0.045,0.033 0.059,0.056 z"
+   style="fill:#333333;fill-rule:nonzero"
+   id="path238" />
+                </g>
+                <g
+   transform="matrix(86.953,0,0,86.953,228.906,241.878)"
+   id="g244">
+                    <path
+   d="M 0.156,0.023 0.179,-0.034 0.006,-0.467 0.14,-0.485 0.252,-0.191 0.358,-0.485 H 0.495 L 0.278,0.064 C 0.263,0.103 0.236,0.137 0.197,0.165 0.158,0.193 0.118,0.212 0.075,0.222 L 0.029,0.115 C 0.052,0.105 0.077,0.093 0.104,0.079 0.13,0.064 0.147,0.046 0.156,0.023 Z"
+   style="fill:#333333;fill-rule:nonzero"
+   id="path242" />
+                </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)"
+   id="g250">
+                        <path
+   d="M 185.806,161.156 V 67.132"
+   style="fill:none;stroke:#4c9fff;stroke-width:4px;stroke-linecap:butt"
+   id="path248" />
+                    </g>
+                    <g
+   transform="matrix(1.03522,0,0,1.23823,161.788,169.469)"
+   id="g254">
+                        <circle
+   cx="31.523001"
+   cy="34.313999"
+   r="10.021"
+   style="fill:#4c9fff;stroke:#4c9fff;stroke-width:4px;stroke-linecap:butt"
+   id="circle252" />
+                    </g>
+                </g>
+                <g
+   id="Left-selector"
+   serif:id="Left selector">
+                    <g
+   transform="matrix(1.03522,0,0,1.23823,-170.092,0)"
+   id="g259">
+                        <path
+   d="M 185.806,161.156 V 67.132"
+   style="fill:none;stroke:#4c9fff;stroke-width:4px;stroke-linecap:butt"
+   id="path257" />
+                    </g>
+                    <g
+   transform="matrix(1.03522,0,0,1.23823,-10.3742,28.2274)"
+   id="g263">
+                        <circle
+   cx="31.523001"
+   cy="34.313999"
+   r="10.021"
+   style="fill:#4c9fff;stroke:#4c9fff;stroke-width:4px;stroke-linecap:butt"
+   id="circle261" />
+                    </g>
+                </g>
+            </g>
+        </g>
+    </g>
+</svg>

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 +1,14 @@
-.. 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.
+.. figure:: images/logo.svg
 
-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.
+OCRmyPDF adds an optical character recognition (OCR) text layer to scanned PDF
+files, allowing them to be searched.
+
+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 +16,31 @@ 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
+   performance
+   pdfsecurity
    errors
 
+.. toctree::
+   :caption: Developers
+   :maxdepth: 2
+
+   api
+   plugins
+   apiref
+   contributing
+   maintainers
 
 Indices and tables
 ==================
@@ -36,4 +48,3 @@ Indices and tables
 * :ref:`genindex`
 * :ref:`modindex`
 * :ref:`search`
-

docs/installation.rst

@@ -1,131 +1,362 @@
-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. This version may be out of date, however.
+
+These platforms have one-liner installs:
+
++-------------------------------+-----------------------------------------+
+| Debian, Ubuntu                | ``apt install ocrmypdf``                |
++-------------------------------+-----------------------------------------+
+| Windows Subsystem for Linux   | ``apt install ocrmypdf``                |
++-------------------------------+-----------------------------------------+
+| Fedora                        | ``dnf install ocrmypdf``                |
++-------------------------------+-----------------------------------------+
+| macOS                         | ``brew install ocrmypdf``               |
++-------------------------------+-----------------------------------------+
+| LinuxBrew                     | ``brew install ocrmypdf``               |
++-------------------------------+-----------------------------------------+
+| FreeBSD                       | ``pkg install textproc/py-ocrmypdf``    |
++-------------------------------+-----------------------------------------+
+| Conda (WSL, macOS, Linux)     | ``conda install ocrmypdf``              |
++-------------------------------+-----------------------------------------+
+| Snap (snapcraft packaging)    | ``snap install ocrmypdf``               |
++-------------------------------+-----------------------------------------+
+
+More detailed procedures are outlined below. If you want to do a manual
+install, or install a more recent version than your platform provides, read on.
+
+.. 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 stable
+
+.. |deb-testing| image:: https://repology.org/badge/version-for-repo/debian_testing/ocrmypdf.svg
+    :alt: Debian testing
+
+.. |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-2004| image:: https://repology.org/badge/version-for-repo/ubuntu_20_04/ocrmypdf.svg
+    :alt: Ubuntu 20.04 LTS
+
+.. |ubu-2204| image:: https://repology.org/badge/version-for-repo/ubuntu_22_04/ocrmypdf.svg
+    :alt: Ubuntu 22.04 LTS
+
++-----------------------------------------------+
+| **OCRmyPDF versions in Debian & Ubuntu**      |
++-----------------------------------------------+
+| |latest|                                      |
++-----------------------------------------------+
+| |deb-stable| |deb-testing| |deb-unstable|     |
++-----------------------------------------------+
+| |ubu-1804| |ubu-2004| |ubu-2204|              |
++-----------------------------------------------+
+
+Users of Debian 9 ("stretch") or later, or Ubuntu 18.04 or later, including users
+of Windows Subsystem for Linux, 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>`__.
 
-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 will
+   automatically detect it (specifically the ``jbig2`` binary) on the
+   ``PATH``. To add JBIG2 encoding, see :ref:`jbig2`.
+
+Fedora
+------
+
+.. |fedora-35| image:: https://repology.org/badge/version-for-repo/fedora_35/ocrmypdf.svg
+    :alt: Fedora 35
+
+.. |fedora-36| image:: https://repology.org/badge/version-for-repo/fedora_36/ocrmypdf.svg
+    :alt: Fedora 36
+
+.. |fedora-rawhide| image:: https://repology.org/badge/version-for-repo/fedora_rawhide/ocrmypdf.svg
+    :alt: Fedore Rawhide
+
++-----------------------------------------------+
+| **OCRmyPDF version**                          |
++-----------------------------------------------+
+| |latest|                                      |
++-----------------------------------------------+
+| |fedora-35| |fedora-36| |fedora-rawhide|      |
++-----------------------------------------------+
+
+Users of Fedora 29 or 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 22.04 LTS
+-------------------------------------------------
+
+Ubuntu 22.04 includes ocrmypdf 13.4.0 - you can install that with 
+``apt install ocrmypdf``. To install a more recent version for the current
+user, follow these steps:
+
+.. code-block:: bash
+
+    sudo apt-get update
+    sudo apt-get -y install ocrmypdf python3-pip
+
+    pip install --user --upgrade ocrmypdf
+
+If you get the message ``WARNING: The script ocrmypdf is installed in 
+'/home/$USER/.local/bin' which is not on PATH.``, you may need to re-login
+or open a new shell, or manually add this to your user's PATH.
+
+To add JBIG2 encoding, see :ref:`jbig2`.
+
+Ubuntu 20.04 LTS
+----------------
+
+Ubuntu 20.04 includes ocrmypdf 9.6.0 - you can install that with ``apt``. To
+install a more recent version, uninstall the system-provided version of
+ocrmypdf, and install the following dependencies:
+
+.. code-block:: bash
+
+    sudo apt-get -y remove ocrmypdf  # remove system ocrmypdf, if installed
+    sudo apt-get -y update
+    sudo apt-get -y install \
+        ghostscript \
+        icc-profiles-free \
+        libxml2 \
+        pngquant \
+        python3-pip \
+        tesseract-ocr \
+        zlib1g
+
+To install ocrmypdf for the system:
+
+.. code-block:: bash
+
+    pip3 install ocrmypdf
+
+To install for the current user only:
+
+.. code-block:: bash
+
+    export PATH=$HOME/.local/bin:$PATH
+    pip3 install --user ocrmypdf
+
+To add JBIG2 encoding, see :ref:`jbig2`.
+
+Ubuntu 18.04 LTS
+----------------
+
+Ubuntu 18.04 includes ocrmypdf 6.1.2 - you can install that with ``apt``, but
+it is quite old now. To install a more recent version, uninstall the old version
+of ocrmypdf, and install the following dependencies:
+
+.. code-block:: bash
+
+    sudo apt-get -y remove ocrmypdf
+    sudo apt-get -y update
+    sudo apt-get -y install \
+        ghostscript \
+        icc-profiles-free \
+        libxml2 \
+        pngquant \
+        python3-distutils \
+        python3-pkg-resources \
+        python3-reportlab \
+        qpdf \
+        tesseract-ocr \
+        zlib1g \
+        unpaper
+
+We will need a newer version of ``pip`` then was available for Ubuntu 18.04:
+
+.. code-block:: bash
+
+    wget https://bootstrap.pypa.io/get-pip.py && python3 get-pip.py
+
+Then install the most recent ocrmypdf for the local user and set the
+user's ``PATH`` to check for the user's Python packages.
+
+.. code-block:: bash
+
+    export PATH=$HOME/.local/bin:$PATH
+    python3 -m pip install --user ocrmypdf
+
+To add JBIG2 encoding, see :ref:`jbig2`.
+
+Arch Linux (AUR)
+----------------
+
+.. image:: https://repology.org/badge/version-for-repo/aur/ocrmypdf.svg
+    :alt: ArchLinux
+    :target: https://repology.org/metapackage/ocrmypdf
+
+There is an `Arch User Repository (AUR) package for OCRmyPDF
+<https://aur.archlinux.org/packages/ocrmypdf/>`__.
+
+Installing AUR packages as root is not allowed, so you must first `setup a
+non-root user
+<https://wiki.archlinux.org/index.php/Users_and_groups#User_management>`__ and
+`configure sudo <https://wiki.archlinux.org/index.php/Sudo#Configuration>`__.
+The standard Docker image, ``archlinux/base:latest``, does **not** have a
+non-root user configured, so users of that image must follow these guides. If
+you are using a VM image, such as `the official Vagrant image
+<https://app.vagrantup.com/archlinux/boxes/archlinux>`__, this work may already
+be completed for you.
+
+Next you should install the `base-devel package group
+<https://www.archlinux.org/groups/x86_64/base-devel/>`__. This includes the
+standard tooling needed to build packages, such as a compiler and binary tools.
+
+.. code-block:: bash
+
+   sudo pacman -S base-devel
+
+Now you are ready to install the OCRmyPDF package.
+
+.. code-block:: bash
+
+   curl -O https://aur.archlinux.org/cgit/aur.git/snapshot/ocrmypdf.tar.gz
+   tar xvzf ocrmypdf.tar.gz
+   cd ocrmypdf
+   makepkg -sri
+
+At this point you will have a working install of OCRmyPDF, but the Tesseract
+install won’t include any OCR language data. You can install `the
+tesseract-data package group
+<https://www.archlinux.org/groups/any/tesseract-data/>`__ to add all supported
+languages, or use that package listing to identify the appropriate package for
+your desired language.
+
+.. code-block:: bash
+
+   sudo pacman -S tesseract-data-eng
+
+As an alternative to this manual procedure, consider using an `AUR helper
+<https://wiki.archlinux.org/index.php/AUR_helpers>`__. Such a tool will
+automatically fetch, build and install the AUR package, resolve dependencies
+(including dependencies on AUR packages), and ease the upgrade procedure.
+
+If you have any difficulties with installation, check the repository package
+page.
+
+.. note::
+
+    The OCRmyPDF AUR package currently omits the JBIG2 encoder. OCRmyPDF works
+    fine without it but will produce larger output files. The encoder is
+    available from `the jbig2enc-git AUR package
+    <https://aur.archlinux.org/packages/jbig2enc-git/>`__ and may be installed
+    using the same series of steps as for the installation OCRmyPDF AUR
+    package. Alternatively, it may be built manually from source following the
+    instructions in `Installing the JBIG2 encoder <jbig2>`__.  If JBIG2 is
+    installed, OCRmyPDF 7.0.0 and later will automatically detect it.
+
+Alpine Linux
+------------
+
+.. image:: https://repology.org/badge/version-for-repo/alpine_edge/ocrmypdf.svg
+    :alt: Alpine Linux
+    :target: https://repology.org/metapackage/ocrmypdf
+
+To install OCRmyPDF for Alpine Linux:
+
+.. code-block:: bash
+
+    apk add ocrmypdf
+
+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:
-
-.. 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")
-
-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
-
+    brew install tesseract-lang  # Optional: Install all language packs
 
 Manual installation on macOS
 ----------------------------
 
-These instructions probably work on all macOS supported by Homebrew.
+These instructions probably work on all macOS supported by Homebrew, and are
+for installing a more current version of OCRmyPDF than is available from
+Homebrew. Note that the Homebrew versions usually track the release versions
+fairly closely.
 
-If it's not already present, `install Homebrew <http://brew.sh/>`_.
+If it's not already present, `install Homebrew <http://brew.sh/>`__.
 
 Update Homebrew:
 
@@ -133,43 +364,36 @@ 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, use ``brew edit ocrmypdf`` to obtain a recent list of Homebrew
+dependencies. You could also check the ``.workflows/build.yml``.
 
-.. 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.
-
-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
+    brew install tesseract-lang  # 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
+    pip install --upgrade pip
 
-You can then install OCRmyPDF from PyPI:
+You can then install OCRmyPDF from PyPI, for the current user:
 
 .. code-block:: bash
 
-    pip3 install ocrmypdf
+    pip install --user ocrmypdf
+
+or system-wide:
+
+.. code-block:: bash
+
+    pip install ocrmypdf
 
 The command line program should now be available:
 
@@ -177,175 +401,286 @@ The command line program should now be available:
 
     ocrmypdf --help
 
+Installing on Windows
+=====================
 
-Installing on Ubuntu 16.04 LTS
-------------------------------
+Native Windows
+--------------
 
-No package is currently available for Ubuntu 16.04, but you can install the dependencies manually:
+.. note::
+
+    Administrator privileges will be required for some of these steps.
+
+You must install the following for Windows:
+
+* Python 3.7 (64-bit) or later
+* Tesseract 4.0 or later
+* Ghostscript 9.50 or later
+
+Using the `Chocolatey <https://chocolatey.org/>`_ package manager, install the
+following when running in an Administrator command prompt:
+
+* ``choco install python3``
+* ``choco install --pre tesseract``
+* ``choco install ghostscript``
+* ``choco install pngquant`` (optional)
+
+The commands above will install Python 3.x (latest version), Tesseract, Ghostscript
+and pngquant. Chocolatey may also need to install the Windows Visual C++ Runtime
+DLLs or other Windows patches, and may require a reboot.
+
+You may then use ``pip`` to install ocrmypdf. (This can performed by a user or
+Administrator.):
+
+* ``pip install ocrmypdf``
+
+Chocolatey automatically selects appropriate versions of these applications. If you
+are installing them manually, please install 64-bit versions of all applications for
+64-bit Windows, or 32-bit versions of all applications for 32-bit Windows. Mixing
+the "bitness" of these programs will lead to errors.
+
+OCRmyPDF will check the Windows Registry and standard locations in your Program Files
+for third party software it needs (specifically, Tesseract and Ghostscript). To
+override the versions OCRmyPDF selects, you can modify the ``PATH`` environment
+variable. `Follow these directions <https://www.computerhope.com/issues/ch000549.htm#dospath>`_
+to change the PATH.
+
+.. warning::
+
+    As of early 2021, users have reported problems with the Microsoft Store version of
+    Python and OCRmyPDF. These issues affect many other third party Python packages.
+    Please download Python from Python.org or Chocolatey instead, and do not use the
+    Microsoft Store version.
+
+Windows Subsystem for Linux
+---------------------------
+
+#. Install Ubuntu 22.04 for Windows Subsystem for Linux, if not already installed.
+#. Follow the procedure to install :ref:`OCRmyPDF on Ubuntu 22.04 <ubuntu-lts-latest>`.
+#. Open the Windows command prompt and create a symlink:
+
+.. code-block:: powershell
+
+    wsl sudo ln -s  /home/$USER/.local/bin/ocrmypdf /usr/local/bin/ocrmypdf
+
+Then confirm that the expected version from PyPI (|latest|) is installed:
+
+.. code-block:: powershell
+
+    wsl ocrmypdf --version
+
+You can then run OCRmyPDF in the Windows command prompt or Powershell, prefixing
+``wsl``, and call it from Windows programs or batch files.
+
+Cygwin64
+--------
+
+First install the the following prerequisite Cygwin packages using ``setup-x86_64.exe``::
+
+    python37 (or later)
+    python3?-devel
+    python3?-pip
+    python3?-lxml
+    python3?-imaging
+
+       (where 3? means match the version of python3 you installed)
+
+    gcc-g++
+    ghostscript (<=9.50 or >=9.52-2 see note below)
+    libexempi3
+    libexempi-devel
+    libffi6
+    libffi-devel
+    pngquant
+    qpdf
+    libqpdf-devel
+    tesseract-ocr
+    tesseract-ocr-devel
+
+.. note::
+
+    The Cygwin package for Ghostscript in versions 9.52 and
+    9.52-1 contained a bug that caused an exception to occur when
+    ocrmypdf invoked gs.  Make sure you have either 9.50 (or earlier)
+    or 9.52-2 (or later).
+
+Then open a Cygwin terminal (i.e. ``mintty``), run the following commands. Note
+that if you are using the version of ``pip`` that was installed with the Cygwin
+Python package, the command name will be ``pip3``.  If you have since updated
+``pip`` (with, for instance ``pip3 install --upgrade pip``) the the command is
+likely just ``pip`` instead of ``pip3``:
 
 .. code-block:: bash
 
-    sudo apt-get update
-    sudo apt-get install \
-        unpaper \
-        ghostscript \
-        tesseract-ocr \
-        qpdf \
-        python3-pip \
-        python3-cffi
-
-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.
-
-.. code-block:: bash
-
-    python3 -m venv venv-ocrmypdf
-    source venv-ocrmypdf/bin/activate
+    pip3 install wheel
     pip3 install ocrmypdf
 
+The optional dependency "unpaper" that is currently not available under Cygwin.
+Without it, certain options such as ``--clean`` will produce an error message.
+However, the OCR-to-text-layer functionality is available.
 
-Installing on Ubuntu 14.04 LTS
-------------------------------
+Docker
+------
 
-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.
+You can also :ref:`Install the Docker <docker>` container on Windows. Ensure that
+your command prompt can run the docker "hello world" container.
 
-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.
+Installing on FreeBSD
+=====================
+
+.. image:: https://repology.org/badge/version-for-repo/freebsd/ocrmypdf.svg
+    :alt: FreeBSD
+    :target: https://repology.org/project/ocrmypdf/versions
 
 .. 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
+    pkg install textproc/py-ocrmypdf
 
-Update apt-get:
+To install a more recent version, you could attempt to first install the system
+version with ``pkg``, then use ``pip install --user ocrmypdf``.
+
+Installing the Docker image
+===========================
+
+For some users, installing the Docker image will be easier than
+installing all of OCRmyPDF's dependencies.
+
+See :ref:`docker` for more information.
+
+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 installed.
+
+.. warning::
+
+    Debian and Ubuntu users: unfortunately, Debian and Ubuntu customize
+    Python in non-standard ways, and the nature of these customizations
+    varies from release to release. This can make for a frustrating
+    user experience. The instructions below work on almost all platforms that
+    have Python installed, except for Debian and Ubuntu, where you may need
+    to take additional steps. For best results on Debian and Ubuntu, use the
+    ``apt`` packages; or if these are too old, run
+    ``apt install python3-pip python3-venv``, create a virtual environment,
+    and install OCRmyPDF in that environment.
+
+    `See here for more inforation on Debian-Python issues
+    <https://gist.github.com/tiran/2dec9e03c6f901814f6d1e8dad09528e>`__.
+
+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
 
-    sudo apt-get update
+    pip install --user ocrmypdf
 
-Install system dependencies:
+You should then be able to run ``ocrmypdf --version`` and see that the
+latest version was located.
+
+Since ``pip 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
 
-    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):
+.. note::
 
-.. code-block:: bash
+    AArch64 (ARM64) users: this process will be difficult because most
+    Python packages are not available as binary wheels for your platform.
+    You're probably better off using a platform install on Debian, Ubuntu,
+    or Fedora.
 
-    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
-
-
-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.
-
-Running on Windows
-~~~~~~~~~~~~~~~~~~
-
-The command line syntax to run ocrmypdf from a command prompt will resemble:
-
-.. code-block:: bat
-
-    docker run -v /c/Users/sampleuser:/home/docker ocrmypdf --skip-text test.pdf output.pdf
-
-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.
-
-`Bash on Ubuntu on Windows <https://github.com/Microsoft/BashOnWindows>`_ should also be a viable route for running the OCRmyPDF Docker container.
-
-Installing HEAD revision from sources
+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:
+The following versions are required:
+
+-  Python 3.7 or newer
+-  Ghostscript 9.23 or newer
+-  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 3.7 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
+    pip install git+https://github.com/ocrmypdf/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
+    pip install -e git+https://github.com/ocrmypdf/OCRmyPDF.git
 
-On certain Linux distributions such as Ubuntu, you may need to use 
-run the install command as superuser:
+You may find it easiest to install in a virtual environment, rather than
+system-wide:
 
 .. 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:
-
-.. code-block:: bash
-
-    git clone -b master https://github.com/jbarlow83/OCRmyPDF.git
+    git clone -b master https://github.com/ocrmypdf/OCRmyPDF.git
     python3 -m venv
     source venv/bin/activate
     cd OCRmyPDF
-    pip3 install .
+    pip 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 +693,34 @@ 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/ocrmypdf/OCRmyPDF.git
+    python -m venv
+    source venv/bin/activate
+    cd OCRmyPDF
+    pip install -e .[test]
+
+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 +1,239 @@
+============
 Introduction
 ============
 
-OCRmyPDF is a Python 3 package that adds OCR layers to PDFs.
-
+OCRmyPDF is an application and library that adds text "layers" to images
+in PDFs, making scanned image PDFs searchable. It uses OCR to guess what text
+is contained in images. It is written in Python. OCRmyPDF supports plugins
+that allow customization of its processing steps, and is very tolerant of
+PDFs that contain scanned images and "born digital" content that needs no
+text recognition.
 
 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 selected, 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 format 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 corresponding raster images.
+OCR engines like Tesseract work with images, not scalable vector graphics
+or mixed raster-vector-text graphics such as PDF.
 
 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 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 provides some image processing options, like deskew, which
+improves 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 OCR solutions.
+-  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.
+-  Ghostscript's PDF/A conversion seems to remove or deactivate
+   hyperlinks and other active content.
 
+You can use ``--output-type pdf`` to disable PDF/A conversion and produce
+a standard, non-archival PDF.
+
+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
 
-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`_).
+Ghostscript recently added three "pdfocr" output devices. They work by
+rasterizing all content and converting all pages to a single colour space.
 
+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 +1,58 @@
+.. _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 is 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 and 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:
+
+Dependencies include libtoolize and libleptonica, which on Ubuntu systems 
+are packaged as libtool and libleptonica-dev.
+
+Lossy mode JBIG2
+================
+
+OCRmyPDF provides lossy mode JBIG2 as an advanced feature. Users should
+`review the technical concerns with JBIG2 in lossy
+mode <https://en.wikipedia.org/wiki/JBIG2#Disadvantages>`__
+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 +1,103 @@
 .. _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 all languages.
+On most platforms, English is installed with Tesseract by default, but not always.
 
-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>`__.
+Languages are identified by standardized three-letter codes (called ISO 639-2 Alpha-3).
+Tesseract's documentation also lists the three-letter code for your language.
+Some are anglicized, e.g. Spanish is ``spa`` rather than ``esp``, while others
+are not, e.g. German is ``deu`` and French is ``fra``.
 
-For Linux users, you can often find packages that provide language packs:
+After you have installed a language pack, you can use it with ``ocrmypdf -l <language>``,
+for example ``ocrmypdf -l spa``. For multilingual documents, you can specify
+all languages to be expected, e.g. ``ocrmypdf -l eng+fra`` for English and French.
+English is assumed by default unless other language(s) are specified.
+
+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+fra`` (English and French) or
+``-l eng -l fra``.
 
-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+fra`` (English and French) or
+``-l eng -l fra``.
+
+Gentoo users
+============
+
+On Gentoo the package ``app-text/tessdata_fast``, which ``app-text/tesseract`` depends on, handles Tesseract languages.
+It accepts USE flags to select what languages should be installed, these can be set in ``/etc/portage/package.use``.
+Alternatively one can globally set the `L10N use extension <https://wiki.gentoo.org/wiki/Localization/Guide#L10N>`__ in ``/etc/portage/make.conf``.
+This enables these languages for all packages (e.g. including aspell).
+
+.. code-block:: bash
+
+   # Display a list of all Tesseract language packs
+   equery uses app-text/tessdata_fast
+   
+   # Add English and German language support for Tesseract only
+   echo 'app-text/tessdata_fast l10n_de l10n_en' >> /etc/portage/package.use
+   
+   # Add global English and German language support (the `l10n_` from equery has to be omited)
+   echo L10N="de en" >> /etc/portage/make.conf
+   
+   # update system to reflect changed USE flags
+   emerge --update --deep --newuse @world
+
+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+fra`` (English and French) or
+``-l eng -l fra``.
+
+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>`.
+
+Windows users
+=============
+
+The Tesseract installer provided by Chocolatey currently includes only English language. 
+To install other languages, download the respective language pack (``.traineddata`` file) 
+from https://github.com/tesseract-ocr/tessdata/ and place it in 
+``C:\\Program Files\\Tesseract-OCR\\tessdata`` (or wherever Tesseract OCR is installed).

docs/maintainers.rst

@@ -0,0 +1,60 @@
+================
+Maintainer notes
+================
+
+This is for those who package OCRmyPDF for downstream use.  (Thank you
+for your hard work.)
+
+Known ports/packagers
+=====================
+
+OCRmyPDF has been ported to many platforms already. If you are interesting in
+porting to a new platform, check with
+`Repology <https://repology.org/projects/?search=ocrmypdf>`__ to see the status
+of that platform.
+
+Make sure you can package pikepdf
+---------------------------------
+
+pikepdf, created by the same author, is a mixed Python and C++14 package with
+much stiffer build requirements. If you want to use OCRmyPDF on some novel platform
+or distribution, first make sure you can package pikepdf.
+
+Non-Python dependencies
+-----------------------
+
+Note that we have non-Python dependencies. In particular, OCRmyPDF requires
+Ghostscript and Tesseract OCR to be installed and needs to be able to locate their
+binaries on the system PATH. On Windows, OCRmyPDF will also check the registry
+for their locations.
+
+Tesseract OCR relies on SIMD for performance and only has proper support for this
+on ARM and x86_64. Performance may be poor on other processor architectures.
+
+Versioning scheme
+-----------------
+
+OCRmyPDF uses setuptools-scm for versioning, which derives the version from
+Git as a single source of truth. This may be unsuitable for some distributions, e.g.
+to indicate that your distribution modifies OCRmyPDF in some way.
+
+You can patch the ``__version__`` variable in ``src/ocrmypdf/_version.py`` if
+necessary.
+
+OCRmyPDF uses setuptools-scm-git-archive to ensure that tarballs downloaded from
+GitHub contain version information. Unfortunately, these tarballs are not always
+deterministic. See this
+`issue <https://github.com/ocrmypdf/OCRmyPDF/issues/841#issuecomment-936562696>`_.
+
+jbig2enc
+--------
+
+OCRmyPDF will use jbig2enc, a JBIG2 encoder, if one can be found. Some distributions
+have shied away from packaging JBIG2 because it contains patented algorithms, but
+all patents have expired since 2017. If possible, consider packaging it too to
+improve OCRmyPDF's compression.
+
+Command line completions
+------------------------
+
+Please ensure that command line completions are installed.

docs/optimizer.rst

@@ -0,0 +1,75 @@
+================
+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.
+
+PDF optimization requires third-party, optional tools for certain optimizations.
+If these are not installed or cannot be found by OCRmyPDF, optimization will not
+be as good.
+
+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/pdfsecurity.rst

@@ -0,0 +1,162 @@
+===================
+PDF security issues
+===================
+
+   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.
+
+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 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 are possible
+attack vectors.
+
+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 to 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
+`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.
+
+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.
+
+.. _ocr-service:
+
+Using OCRmyPDF online or as a service
+=====================================
+
+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, and any other licenses.
+
+Setting aside these concerns, a side effect of OCRmyPDF is that it may
+incidentally sanitize PDFs containing certain types of malware. It
+repairs the PDF with pikepdf/libqpdf, 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 to 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 viable commercial alternative with a web services
+API. Amazon Textract, Google Cloud Vision, and Microsoft Azure 
+Computer Vision provide advanced OCR but have less PDF rendering capability.
+
+Password protection, digital signatures and certification
+=========================================================
+
+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.
+
+Either way, OCRmyPDF does not remove passwords from PDFs and exits with
+an error on encountering them.
+
+``qpdf`` 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.

docs/performance.rst

@@ -0,0 +1,22 @@
+===========
+Performance
+===========
+
+Some users have noticed that current versions of OCRmyPDF do not run as quickly
+as some older versions (specifically 6.x and older). This is because OCRmyPDF
+added image optimization as a postprocessing step, and it is enabled by default.
+
+Speed
+=====
+
+If running OCRmyPDF quickly is your main goal, you can use settings such as:
+
+* ``--optimize 0`` to disable file size optimization
+* ``--output-type pdf`` to disable PDF/A generation
+* ``--fast-web-view 0`` to disable fast web view optimization
+* ``--skip-big`` to skip large images, if some pages have large images
+
+You can also avoid:
+
+* ``--force-ocr``
+* Image preprocessing

docs/pipeline.svg

@@ -1,392 +0,0 @@
-<?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)
- -->
-<!-- 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)">
-<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>
-</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>
-<!-- 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>
-<!-- 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>
-<!-- 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>
-<!-- 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>
-<!-- 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>
-<!-- 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"/>
-</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"/>
-</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"/>
-</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>
-<!-- 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"/>
-</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"/>
-</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>
-<!-- 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>
-<!-- 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>
-</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"/>
-</g>
-</g>
-</svg>

docs/plugins.rst

@@ -0,0 +1,218 @@
+=======
+Plugins
+=======
+
+    The key words "MUST", "MUST NOT", "REQUIRED", "SHALL", "SHALL
+    NOT", "SHOULD", "SHOULD NOT", "RECOMMENDED",  "MAY", and
+    "OPTIONAL" in this document are to be interpreted as described in
+    RFC 2119.
+
+You can use plugins to customize the behavior of OCRmyPDF at certain points of
+interest.
+
+Currently, it is possible to:
+
+- add new command line arguments
+- override the decision for whether or not to perform OCR on a particular file
+- modify the image is about to be sent for OCR
+- modify the page image before it is converted to PDF
+- replace the Tesseract OCR with another OCR engine that has similar behavior
+- replace Ghostscript with another PDF to image converter (rasterizer) or
+  PDF/A generator
+
+OCRmyPDF plugins are based on the Python ``pluggy`` package and conform to its
+conventions. Note that: plugins installed with as setuptools entrypoints are
+not checked currently, because OCRmyPDF assumes you may not want to enable
+plugins for all files.
+
+Script plugins
+==============
+
+Script plugins may be called from the command line, by specifying the name of a file.
+Script plugins may be convenient for informal or "one-off" plugins, when a certain
+batch of files needs a special processing step for example.
+
+.. code-block:: bash
+
+    ocrmypdf --plugin ocrmypdf_example_plugin.py input.pdf output.pdf
+
+Multiple plugins may be installed by issuing the ``--plugin`` argument multiple times.
+
+Packaged plugins
+================
+
+Installed plugins may be installed into the same virtual environment as OCRmyPDF
+is installed into. They may be invoked using Python standard module naming.
+If you are intending to distribute a plugin, please package it.
+
+.. code-block:: bash
+
+    ocrmypdf --plugin ocrmypdf_fancypants.pockets.contents input.pdf output.pdf
+
+OCRmyPDF does not automatically import plugins, because the assumption is that
+plugins affect different files differently and you may not want them activated
+all the time. The command line or ``ocrmypdf.ocr(plugin='...')`` must call
+for them.
+
+Third parties that wish to distribute packages for ocrmypdf should package them
+as packaged plugins, and these modules should begin with the name ``ocrmypdf_``
+similar to ``pytest`` packages such as ``pytest-cov`` (the package) and
+``pytest_cov`` (the module).
+
+.. note::
+
+    We recommend plugin authors name their plugins with the prefix
+    ``ocrmypdf-`` (for the package name on PyPI) and ``ocrmypdf_`` (for the
+    module), just like pytest plugins. At the same time, please make it clear
+    that your package is not official.
+
+Setuptools plugins
+==================
+
+You can also create a plugin that OCRmyPDF will always automatically load if both are
+installed in the same virtual environment, using a setuptools entrypoint.
+
+Your package's ``setup.py`` would need to contain the following, for a plugin
+named ``ocrmypdf-exampleplugin``:
+
+.. code-block:: python
+
+    # sample ./setup.py file
+    from setuptools import setup
+
+    setup(
+        name="ocrmypdf-exampleplugin",
+        packages=["exampleplugin"],
+        # the following makes a plugin available to pytest
+        entry_points={"ocrmypdf": ["exampleplugin = exampleplugin.pluginmodule"]},
+    )
+
+.. code-block:: ini
+
+    # equivalent setup.cfg
+    [options.entry_points]
+    ocrmypdf =
+        exampleplugin = exampleplugin.pluginmodule
+
+Plugin requirements
+===================
+
+OCRmyPDF generally uses multiple worker processes. When a new worker is started,
+Python will import all plugins again, including all plugins that were imported earlier.
+This means that the global state of a plugin in one worker will not be shared with
+other workers. As such, plugin hook implementations should be stateless, relying
+only on their inputs. Hook implementations may use their input parameters to
+to obtain a reference to shared state prepared by another hook implementation.
+Plugins must expect that other instances of the plugin will be running
+simultaneously.
+
+The ``context`` object that is passed to many hooks can be used to share information
+about a file being worked on. Plugins must write private, plugin-specific data to
+a subfolder named ``{options.work_folder}/ocrmypdf-plugin-name``. Plugins MAY
+read and write files in ``options.work_folder``, but should be aware that their
+semantics are subject to change.
+
+OCRmyPDF will delete ``options.work_folder`` when it has finished OCRing
+a file, unless invoked with ``--keep-temporary-files``.
+
+The documentation for some plugin hooks contain a detailed description of the
+execution context in which they will be called.
+
+Plugins should be prepared to work whether executed in worker threads or worker
+processes. Generally, OCRmyPDF uses processes, but has a semi-hidden threaded
+argument that simplifies debugging.
+
+
+Plugin hooks
+============
+
+A plugin may provide the following hooks. Hooks must be decorated with
+``ocrmypdf.hookimpl``, for example:
+
+.. code-block:: python
+
+    from ocrmpydf import hookimpl
+
+    @hookimpl
+    def add_options(parser):
+        pass
+
+The following is a complete list of hooks that are available, and when
+they are called.
+
+.. _firstresult:
+
+**Note on firstresult hooks**
+
+If multiple plugins install implementations for this hook, they will be called in
+the reverse of the order in which they are installed (i.e., last plugin wins).
+When each hook implementation is called in order, the first implementation that
+returns a value other than ``None`` will "win" and prevent execution of all other
+hooks. As such, you cannot "chain" a series of plugin filters together in this
+way. Instead, a single hook implementation should be responsible for any such
+chaining operations.
+
+Examples
+========
+
+* OCRmyPDF's test suite contains several plugins that are used to simulate certain
+  test conditions.
+* `ocrmypdf-papermerge <https://github.com/papermerge/OCRmyPDF_papermerge>`_ is
+  a production plugin that integrates OCRmyPDF and the Papermerge document
+  management system.
+
+
+Custom command line arguments
+-----------------------------
+
+.. autofunction:: ocrmypdf.pluginspec.add_options
+
+.. autofunction:: ocrmypdf.pluginspec.check_options
+
+Execution and progress reporting
+--------------------------------
+
+.. autoclass: ocrmypdf.pluginspec.Executor
+    :members:
+
+.. autofunction:: ocrmypdf.pluginspec.get_logging_console
+
+.. autofunction:: ocrmypdf.pluginspec.get_executor
+
+.. autofunction:: ocrmypdf.pluginspec.get_progressbar_class
+
+Applying special behavior before processing
+-------------------------------------------
+
+.. autofunction:: ocrmypdf.pluginspec.validate
+
+PDF page to image
+-----------------
+
+.. autofunction:: ocrmypdf.pluginspec.rasterize_pdf_page
+
+Modifying intermediate images
+-----------------------------
+
+.. autofunction:: ocrmypdf.pluginspec.filter_ocr_image
+
+.. autofunction:: ocrmypdf.pluginspec.filter_page_image
+
+.. autofunction:: ocrmypdf.pluginspec.filter_pdf_page
+
+OCR engine
+----------
+
+.. autofunction:: ocrmypdf.pluginspec.get_ocr_engine
+
+.. autoclass:: ocrmypdf.pluginspec.OcrEngine
+    :members:
+
+    .. automethod:: __str__
+
+.. autoclass:: ocrmypdf.pluginspec.OrientationConfidence
+
+PDF/A production
+----------------
+
+.. autofunction:: ocrmypdf.pluginspec.generate_pdfa

docs/security.rst

@@ -1,44 +0,0 @@
-PDF security issues
-===================
-
-	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.
-
-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.
-
-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.
-
-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.
-
-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. 
-
-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.
-
-Using OCRmyPDF online
----------------------
-
-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.
-
-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.
-
-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.
-
-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/batch.py

@@ -0,0 +1,62 @@
+#!/usr/bin/env python3
+# Copyright 2016 findingorder: https://github.com/findingorder
+#
+# 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.
+
+# This script must be edited to meet your needs.
+
+import logging
+import os
+import sys
+from pathlib import Path
+
+import ocrmypdf
+
+# pylint: disable=logging-format-interpolation
+# pylint: disable=logging-not-lazy
+
+script_dir = Path(__file__).parent
+
+if len(sys.argv) > 1:
+    start_dir = Path(sys.argv[1])
+else:
+    start_dir = Path('.')
+
+if len(sys.argv) > 2:
+    log_file = Path(sys.argv[2])
+else:
+    log_file = script_dir.with_name('ocr-tree.log')
+
+logging.basicConfig(
+    level=logging.INFO,
+    format='%(asctime)s %(message)s',
+    filename=log_file,
+    filemode='a',
+)
+
+ocrmypdf.configure_logging(ocrmypdf.Verbosity.default)
+
+for filename in start_dir.glob("**/*.py"):
+    logging.info(f"Processing {filename}")
+    result = ocrmypdf.ocr(filename, filename, deskew=True)
+    if result == ocrmypdf.ExitCode.already_done_ocr:
+        logging.error("Skipped document because it already contained text")
+    elif result == ocrmypdf.ExitCode.ok:
+        logging.info("OCR complete")
+    logging.info(result)

misc/completion/ocrmypdf.bash

@@ -0,0 +1,310 @@
+# ocrmypdf completion                                     -*- shell-script -*-
+
+# Copyright 2019, 2021 Frank Pille
+# Copyright 2020 Alex Willner
+#
+# 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.
+
+set -o errexit
+
+__ocrmypdf_arguments()
+{
+    local arguments="--help                   (show help message)
+--language               (language(s) of the file to be OCRed)
+--image-dpi              (assume this DPI if input image DPI is unknown)
+--output-type            (select PDF output options)
+--sidecar                (write OCR to text file)
+--version                (print program version and exit)
+--jobs                   (how many worker processes to use)
+--quiet                  (suppress INFO messages)
+--verbose                (set verbosity level)
+--title                  (set metadata)
+--author                 (set metadata)
+--subject                (set metadata)
+--keywords               (set metadata)
+--rotate-pages           (rotate pages to correct orientation)
+--remove-background      (attempt to remove background from pages)
+--deskew                 (fix small horizontal alignment skew)
+--clean                  (clean document images before OCR)
+--clean-final            (clean document images and keep result)
+--unpaper-args           (a quoted string of arguments to pass to unpaper)
+--oversample             (oversample images to this DPI)
+--remove-vectors         (don\'t send vector objects to OCR)
+--threshold              (threshold images before OCR)
+--force-ocr              (OCR documents that already have printable text)
+--skip-text              (skip OCR on any pages that already contain text)
+--redo-ocr               (redo OCR on any pages that seem to have OCR already)
+--skip-big               (skip OCR on pages larger than this many MPixels)
+--optimize               (select optimization level)
+--jpeg-quality           (JPEG quality [0..100])
+--png-quality            (PNG quality [0..100])
+--jbig2-lossy            (enable lossy JBIG2 (see docs))
+--pages                  (apply OCR to only the specified pages)
+--max-image-mpixels      (image decompression bomb threshold)
+--pdf-renderer           (select PDF renderer options)
+--rotate-pages-threshold (page rotation confidence)
+--pdfa-image-compression (set PDF/A image compression options)
+--fast-web-view          (if file size if above this amount in MB linearize PDF)
+--plugin                 (name of plugin to import)
+--keep-temporary-files   (keep temporary files (debug)
+--tesseract-config       (set custom tesseract config file)
+--tesseract-pagesegmode  (set tesseract --psm)
+--tesseract-oem          (set tesseract --oem)
+--tesseract-thresholding (set tesseract image thresholding)
+--tesseract-timeout      (maximum number of seconds to wait for OCR)
+--user-words             (specify location of user words file)
+--user-patterns          (specify location of user patterns file)
+--no-progress-bar        (disable the progress bar)
+"
+
+    COMPREPLY=( $( compgen -W "$arguments" -- "$cur") )
+
+    # Remove description if only one completion exists
+    if [[ ${#COMPREPLY[*]} -eq 1 ]]; then
+        COMPREPLY=( ${COMPREPLY[0]%% *} )
+    fi
+}
+
+__ocrmypdf_output-type()
+{
+    local choices="pdfa   (output a PDF/A (default))
+pdf    (output a standard PDF)
+pdfa-1 (output a PDF/A-1b)
+pdfa-2 (output a PDF/A-2b)
+pdfa-3 (output a PDF/A-3b)
+none   (do not produce an output PDF (for example, if you only care about --sidecar))"
+
+    COMPREPLY=( $( compgen -W "$choices" -- "$cur") )
+
+    # Remove description if only one completion exists
+    if [[ ${#COMPREPLY[*]} -eq 1 ]]; then
+        COMPREPLY=( ${COMPREPLY[0]%% *} )
+    fi
+}
+
+__ocrmypdf_verbose()
+{
+    local choices="0  (standard output messages)
+1  (troubleshooting output messages)
+2  (debugging output messages)"
+
+    COMPREPLY=( $( compgen -W "$choices" -- "$cur") )
+
+    # Remove description if only one completion exists
+    if [[ ${#COMPREPLY[*]} -eq 1 ]]; then
+        COMPREPLY=( ${COMPREPLY[0]%% *} )
+    fi
+}
+
+__ocrmypdf_optimize()
+{
+    local choices="0  (do not optimize)
+1  (do safe, lossless optimizations (default))
+2  (do some lossy optimizations)
+3  (do aggressive lossy optimizations (including lossy JBIG2))"
+
+    COMPREPLY=( $( compgen -W "$choices" -- "$cur") )
+
+    # Remove description if only one completion exists
+    if [[ ${#COMPREPLY[*]} -eq 1 ]]; then
+        COMPREPLY=( ${COMPREPLY[0]%% *} )
+    fi
+}
+
+__ocrmypdf_pdf-renderer()
+{
+    local choices="auto      (auto select PDF renderer)
+hocr      (use hOCR renderer)
+hocrdebug (uses hOCR renderer in debug mode, showing recognized text)
+sandwich  (use sandwich renderer)"
+
+    COMPREPLY=( $( compgen -W "$choices" -- "$cur") )
+
+    # Remove description if only one completion exists
+    if [[ ${#COMPREPLY[*]} -eq 1 ]]; then
+        COMPREPLY=( ${COMPREPLY[0]%% *} )
+    fi
+}
+
+__ocrmypdf_pdfa-image-compression()
+{
+    local choices="auto     (let Ghostscript decide how to compress images)
+jpeg     (convert color and grayscale images to JPEG)
+lossless (convert color and grayscale images to lossless (PNG))"
+
+    COMPREPLY=( $( compgen -W "$choices" -- "$cur") )
+
+    # Remove description if only one completion exists
+    if [[ ${#COMPREPLY[*]} -eq 1 ]]; then
+        COMPREPLY=( ${COMPREPLY[0]%% *} )
+    fi
+}
+
+__ocrmypdf_tesseract-pagesegmode()
+{
+    local choices="0  (orientation and script detection (OSD) only)
+1  (automatic page segmentation with OSD)
+2  (automatic page segmentation, but no OSD, or OCR)
+3  (fully automatic page segmentation, but no OSD (default))
+4  (assume a single column of text of variable sizes)
+5  (assume a single uniform block of vertically aligned text)
+6  (assume a single uniform block of text)
+7  (treat the image as a single text line)
+8  (treat the image as a single word)
+9  (treat the image as a single word in a circle)
+10 (treat the image as a single character)
+11 (sparse text - find as much text as possible in no particular order)
+12 (sparse text with OSD)
+13 (raw line - treat the image as a single text line)"
+
+    COMPREPLY=( $( compgen -W "$choices" -- "$cur") )
+
+    # Remove description if only one completion exists
+    if [[ ${#COMPREPLY[*]} -eq 1 ]]; then
+        COMPREPLY=( ${COMPREPLY[0]%% *} )
+    fi
+}
+
+__ocrmypdf_tesseract-oem()
+{
+    local choices="0 (legacy engine only)
+1 (neural nets LSTM engine only)
+2 (legacy + LSTM engines)
+3 (default, based on what is available)"
+
+    COMPREPLY=( $( compgen -W "$choices" -- "$cur") )
+
+    # Remove description if only one completion exists
+    if [[ ${#COMPREPLY[*]} -eq 1 ]]; then
+        COMPREPLY=( ${COMPREPLY[0]%% *} )
+    fi
+}
+
+__ocrmypdf_tesseract-thresholding()
+{
+    local choices="auto          (let OCRmyPDF pick thresholding - current always uses otsu)
+otsu          (use hOCR renderer)
+adaptive-otsu (use adaptive Otsu thresholding)
+sauvola       (use Sauvola thresholding)"
+
+    COMPREPLY=( $( compgen -W "$choices" -- "$cur") )
+    # Remove description if only one completion exists
+    if [[ ${#COMPREPLY[*]} -eq 1 ]]; then
+        COMPREPLY=( ${COMPREPLY[0]%% *} )
+    fi
+}
+
+
+__ocrmypdf_check_previous()
+{
+    case $prev in
+        -h|--help|--version)
+            return 0
+            ;;
+        -l|--language)
+            COMPREPLY=$( command tesseract --list-langs 2>/dev/null )
+            COMPREPLY=( $( compgen -W '${COMPREPLY[@]##*:}' -- "$cur" ) )
+            return 0
+            ;;
+        --output-type)
+            __ocrmypdf_output-type
+            return 0
+            ;;
+        -j|--jobs)
+            COMPREPLY=( $( compgen -W '{1..'$( _ncpus )'}' -- "$cur" ) )
+            return 0
+            ;;
+        -v|--verbose)
+            __ocrmypdf_verbose
+            return 0
+            ;;
+        -O|--optimize)
+            __ocrmypdf_optimize
+            return 0
+            ;;
+        --pdf-renderer)
+            __ocrmypdf_pdf-renderer
+            return 0
+            ;;
+        --pdfa-image-compression)
+            __ocrmypdf_pdfa-image-compression
+            return 0
+            ;;
+        --tesseract-pagesegmode)
+            __ocrmypdf_tesseract-pagesegmode
+            return 0
+            ;;
+        --tesseract-oem)
+            __ocrmypdf_tesseract-oem
+            return 0
+            ;;
+        --tesseract-thresholding)
+            __ocrmypdf_tesseract-thresholding
+            return 0
+            ;;
+
+        --title|--author|--subject|--keywords|--unpaper-args|--pages|--plugin|\
+        --jpeg-quality|--png-quality|--image-dpi|--oversample|--skip-big|--max-image-mpixels|\
+        --tesseract-timeout|--rotate-pages-threshold|--fast-web-view)
+            # argument required but no completions available
+            return 0
+            ;;
+        --tesseract-config|--user-words|--user-patterns|--sidecar)
+            _filedir
+            return 0
+            ;;
+    esac
+
+    return 1
+}
+
+_ocrmypdf()
+{
+    local OLDIFS="$IFS"
+    local IFS=$'\n'
+
+    local cur prev
+
+    # Homebrew on Macs have version 1.3 of bash-completion which doesn't include - see #502
+    if declare -F _init_completion >/dev/null 2>&1; then
+      _init_completion  || return
+    else
+        COMPREPLY=()
+        _get_comp_words_by_ref cur prev
+    fi
+
+    if __ocrmypdf_check_previous -ne 0; then
+        return
+    fi
+
+    if [[ "$cur" == -* ]]; then
+        __ocrmypdf_arguments
+    else
+        _filedir
+    fi
+
+    IFS="$OLDIFS"
+
+    return
+} &&
+complete -F _ocrmypdf ocrmypdf
+
+set +o errexit
+
+# ex: filetype=sh

misc/completion/ocrmypdf.fish

@@ -0,0 +1,148 @@
+# Copyright 2020 James R. Barlow
+#
+# 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.
+
+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 -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")
+    echo -e "none\t"(_ "do not produce an output PDF (for example, if you only care about --sidecar)")
+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 "hocrdebug\t"(_ "uses hOCR renderer in debug mode, showing recognized text")
+    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"
+
+complete -c ocrmypdf -x -l no-progress-bar -d "disable the progress bar"
+
+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"
+
+function __fish_ocrmypdf_tesseract_thresholding
+    echo -e "auto\t"(_ "let OCRmyPDF pick thresholding (current always uses otsu)")
+    echo -e "otsu\t"(_ "legacy Otsu thresholding")
+    echo -e "adaptive-otsu\t"(_ "use adaptive Otsu thresholding")
+    echo -e "sauvola\t"(_ "use Sauvola thresholding")
+end
+complete -c ocrmypdf -x -l tesseract-thresholding -a '(__fish_ocrmypdf_tesseract_thresholding)' -d "set tesseract thresholding method (needs Tesseract 5.x)"
+
+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 -l fast-web-view -d "if file size if above this amount in MB, linearize PDF"
+
+complete -c ocrmypdf -x -a "(__fish_complete_suffix .pdf; __fish_complete_suffix .PDF; __fish_complete_suffix .jpg; __fish_complete_suffix .png)"

misc/docker-compose.example.yml

@@ -0,0 +1,15 @@
+---
+version: "3.3"
+services:
+  ocrmypdf:
+    restart: always
+    container_name: ocrmypdf
+    image: jbarlow83/ocrmypdf
+    volumes:
+      - "/media/scan:/input"
+      - "/mnt/scan:/output"
+    environment:
+      - OCR_OUTPUT_DIRECTORY_YEAR_MONTH=0
+    user: "<SET TO YOUR USER ID>:<SET TO YOUR GROUP ID>"
+    entrypoint: python3
+    command: watcher.py

misc/example_plugin.py

@@ -0,0 +1,84 @@
+# © 2020 James R Barlow: https://github.com/jbarlow83
+#
+# 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.
+
+"""
+An example of an OCRmyPDF plugin.
+
+This plugin adds two new command line arguments
+    --grayscale-ocr: converts the image to grayscale before performing OCR on it
+        (This is occasionally useful for images whose color confounds OCR. It only
+        affects the image shown to OCR. The image is not saved.)
+    --mono-page: converts pages all pages in the output file to black and white
+
+To use this from the command line:
+    ocrmypdf --plugin path/to/example_plugin.py --mono-page input.pdf output.pdf
+
+To use this as an API:
+    import ocrmypdf
+    ocrmypdf.ocr('input.pdf', 'output.pdf',
+        plugins=['path/to/example_plugin.py'], mono_page=True
+    )
+"""
+
+import logging
+
+from PIL import Image
+
+from ocrmypdf import hookimpl
+
+log = logging.getLogger(__name__)
+
+
+@hookimpl
+def add_options(parser):
+    parser.add_argument('--grayscale-ocr', action='store_true')
+    parser.add_argument('--mono-page', action='store_true')
+
+
+@hookimpl
+def prepare(options):
+    pass
+
+
+@hookimpl
+def validate(pdfinfo, options):
+    pass
+
+
+@hookimpl
+def filter_ocr_image(page, image):
+    if page.options.grayscale_ocr:
+        log.info("graying")
+        return image.convert('L')
+    return image
+
+
+@hookimpl
+def filter_page_image(page, image_filename):
+    if page.options.mono_page:
+        with Image.open(image_filename) as im:
+            im = im.convert('1')
+            im.save(image_filename)
+        return image_filename
+    else:
+        output = image_filename.with_suffix('.jpg')
+        with Image.open(image_filename) as im:
+            im.save(output)
+        return output

misc/synology.py

@@ -0,0 +1,92 @@
+#!/bin/env python3
+# Copyright 2017 github.com/Enantiomerie
+#
+# 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.
+
+# This script must be edited to meet your needs.
+
+import logging
+import os
+import shutil
+import subprocess
+import sys
+import time
+
+# pylint: disable=logging-format-interpolation
+# pylint: disable=logging-not-lazy
+
+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(dir_name)
+    os.chdir(dir_name)
+    for filename in file_list:
+        file_stem, file_ext = os.path.splitext(filename)
+        if file_ext != '.pdf':
+            continue
+        full_path = os.path.join(dir_name, filename)
+        timestamp_ocr = time.strftime("%Y-%m-%d-%H%M_OCR_")
+        filename_ocr = timestamp_ocr + file_stem + '.pdf'
+        # create string for pdf processing
+        # the script is processed as root user via chron
+        cmd = [
+            'docker',
+            'run',
+            '--rm',
+            '-i',
+            'jbarlow83/ocrmypdf',
+            '--deskew',
+            '-',
+            '-',
+        ]
+        logging.info(cmd)
+        full_path_ocr = os.path.join(dir_name, filename_ocr)
+        with open(filename, 'rb') as input_file, open(
+            full_path_ocr, 'wb'
+        ) as output_file:
+            proc = subprocess.run(
+                cmd,
+                stdin=input_file,
+                stdout=output_file,
+                stderr=subprocess.PIPE,
+                check=False,
+                text=True,
+                errors='ignore',
+            )
+        logging.info(proc.stderr)
+        os.chmod(full_path_ocr, 0o664)
+        os.chmod(full_path, 0o664)
+        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')

misc/watcher.py

@@ -0,0 +1,182 @@
+#!/usr/bin/env python3
+# Copyright (C) 2019 Ian Alexander: https://github.com/ianalexander
+# Copyright (C) 2020 James R Barlow: https://github.com/jbarlow83
+#
+# 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 json
+import logging
+import os
+import shutil
+import sys
+import time
+from datetime import datetime
+from pathlib import Path
+
+import pikepdf
+from watchdog.events import PatternMatchingEventHandler
+from watchdog.observers import Observer
+from watchdog.observers.polling import PollingObserver
+
+import ocrmypdf
+
+# pylint: disable=logging-format-interpolation
+
+
+def getenv_bool(name: str, default: str = 'False'):
+    return os.getenv(name, default).lower() in ('true', 'yes', 'y', '1')
+
+
+INPUT_DIRECTORY = os.getenv('OCR_INPUT_DIRECTORY', '/input')
+OUTPUT_DIRECTORY = os.getenv('OCR_OUTPUT_DIRECTORY', '/output')
+ARCHIVE_DIRECTORY = os.getenv('OCR_ARCHIVE_DIRECTORY', '/processed')
+OUTPUT_DIRECTORY_YEAR_MONTH = getenv_bool('OCR_OUTPUT_DIRECTORY_YEAR_MONTH')
+ON_SUCCESS_DELETE = getenv_bool('OCR_ON_SUCCESS_DELETE')
+ON_SUCCESS_ARCHIVE = getenv_bool('OCR_ON_SUCCESS_ARCHIVE')
+DESKEW = getenv_bool('OCR_DESKEW')
+OCR_JSON_SETTINGS = json.loads(os.getenv('OCR_JSON_SETTINGS', '{}'))
+POLL_NEW_FILE_SECONDS = int(os.getenv('OCR_POLL_NEW_FILE_SECONDS', '1'))
+USE_POLLING = getenv_bool('OCR_USE_POLLING')
+LOGLEVEL = os.getenv('OCR_LOGLEVEL', 'INFO')
+PATTERNS = ['*.pdf', '*.PDF']
+
+log = logging.getLogger('ocrmypdf-watcher')
+
+
+def get_output_dir(root, basename):
+    if OUTPUT_DIRECTORY_YEAR_MONTH:
+        today = datetime.today()
+        output_directory_year_month = (
+            Path(root) / str(today.year) / f'{today.month:02d}'
+        )
+        if not output_directory_year_month.exists():
+            output_directory_year_month.mkdir(parents=True, exist_ok=True)
+        output_path = Path(output_directory_year_month) / basename
+    else:
+        output_path = Path(OUTPUT_DIRECTORY) / basename
+    return output_path
+
+
+def wait_for_file_ready(file_path):
+    # This loop waits to make sure that the file is completely loaded on
+    # disk before attempting to read. Docker sometimes will publish the
+    # watchdog event before the file is actually fully on disk, causing
+    # pikepdf to fail.
+
+    retries = 5
+    while retries:
+        try:
+            pdf = pikepdf.open(file_path)
+        except (FileNotFoundError, pikepdf.PdfError) as e:
+            log.info(f"File {file_path} is not ready yet")
+            log.debug("Exception was", exc_info=e)
+            time.sleep(POLL_NEW_FILE_SECONDS)
+            retries -= 1
+        else:
+            pdf.close()
+            return True
+
+    return False
+
+
+def execute_ocrmypdf(file_path):
+    file_path = Path(file_path)
+    output_path = get_output_dir(OUTPUT_DIRECTORY, file_path.name)
+
+    log.info("-" * 20)
+    log.info(f'New file: {file_path}. Waiting until fully loaded...')
+    if not wait_for_file_ready(file_path):
+        log.info(f"Gave up waiting for {file_path} to become ready")
+        return
+    log.info(f'Attempting to OCRmyPDF to: {output_path}')
+    exit_code = ocrmypdf.ocr(
+        input_file=file_path,
+        output_file=output_path,
+        deskew=DESKEW,
+        **OCR_JSON_SETTINGS,
+    )
+    if exit_code == 0:
+        if ON_SUCCESS_DELETE:
+            log.info(f'OCR is done. Deleting: {file_path}')
+            file_path.unlink()
+        elif ON_SUCCESS_ARCHIVE:
+            log.info(f'OCR is done. Archiving {file_path.name} to {ARCHIVE_DIRECTORY}')
+            shutil.move(file_path, f'{ARCHIVE_DIRECTORY}/{file_path.name}')
+    else:
+        log.info('OCR is done')
+
+
+class HandleObserverEvent(PatternMatchingEventHandler):
+    def on_any_event(self, event):
+        if event.event_type in ['created']:
+            execute_ocrmypdf(event.src_path)
+
+
+def main():
+    ocrmypdf.configure_logging(
+        verbosity=(
+            ocrmypdf.Verbosity.default
+            if LOGLEVEL != 'DEBUG'
+            else ocrmypdf.Verbosity.debug
+        ),
+        manage_root_logger=True,
+    )
+    log.setLevel(LOGLEVEL)
+    log.info(
+        f"Starting OCRmyPDF watcher with config:\n"
+        f"Input Directory: {INPUT_DIRECTORY}\n"
+        f"Output Directory: {OUTPUT_DIRECTORY}\n"
+        f"Output Directory Year & Month: {OUTPUT_DIRECTORY_YEAR_MONTH}\n"
+        f"Archive Directory: {ARCHIVE_DIRECTORY}"
+    )
+    log.debug(
+        f"INPUT_DIRECTORY: {INPUT_DIRECTORY}\n"
+        f"OUTPUT_DIRECTORY: {OUTPUT_DIRECTORY}\n"
+        f"OUTPUT_DIRECTORY_YEAR_MONTH: {OUTPUT_DIRECTORY_YEAR_MONTH}\n"
+        f"ARCHIVE_DIRECTORY: {ARCHIVE_DIRECTORY}\n"
+        f"ON_SUCCESS_DELETE: {ON_SUCCESS_DELETE}\n"
+        f"ON_SUCCESS_ARCHIVE: {ON_SUCCESS_ARCHIVE}\n"
+        f"DESKEW: {DESKEW}\n"
+        f"ARGS: {OCR_JSON_SETTINGS}\n"
+        f"POLL_NEW_FILE_SECONDS: {POLL_NEW_FILE_SECONDS}\n"
+        f"USE_POLLING: {USE_POLLING}\n"
+        f"LOGLEVEL: {LOGLEVEL}"
+    )
+
+    if 'input_file' in OCR_JSON_SETTINGS or 'output_file' in OCR_JSON_SETTINGS:
+        log.error('OCR_JSON_SETTINGS should not specify input file or output file')
+        sys.exit(1)
+
+    handler = HandleObserverEvent(patterns=PATTERNS)
+    if USE_POLLING:
+        observer = PollingObserver()
+    else:
+        observer = Observer()
+    observer.schedule(handler, INPUT_DIRECTORY, recursive=True)
+    observer.start()
+    try:
+        while True:
+            time.sleep(1)
+    except KeyboardInterrupt:
+        observer.stop()
+    observer.join()
+
+
+if __name__ == "__main__":
+    main()

misc/webservice.py

@@ -0,0 +1,118 @@
+#!/usr/bin/env python3
+# 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, request, send_from_directory
+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 = {"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, capture_output=True, 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
-

ocrmypdf/pdfinfo.py

@@ -1,729 +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
-from collections.abc import MutableMapping, Mapping
-import warnings
-from pathlib import Path
-from enum import Enum
-from .helpers import universal_open
-
-
-matrix_mult = pypdf.pdf.utils.matrixMultiply
-
-Colorspace = Enum('Colorspace',
-                  'gray rgb cmyk lab icc index sep devn pattern jpeg2000')
-
-Encoding = Enum('Encoding',
-                'ccitt jpeg jpeg2000 jbig2 asciihex ascii85 lzw flate ' + \
-                'runlength')
-
-
-FRIENDLY_COLORSPACE = {
-    '/DeviceGray': Colorspace.gray,
-    '/CalGray': Colorspace.gray,
-    '/DeviceRGB': Colorspace.rgb,
-    '/CalRGB': Colorspace.rgb,
-    '/DeviceCMYK': Colorspace.cmyk,
-    '/Lab': Colorspace.lab,
-    '/ICCBased': Colorspace.icc,
-    '/Indexed': Colorspace.index,
-    '/Separation': Colorspace.sep,
-    '/DeviceN': Colorspace.devn,
-    '/Pattern': Colorspace.pattern,
-    '/G': Colorspace.gray,  # Abbreviations permitted in inline images
-    '/RGB': Colorspace.rgb,
-    '/CMYK': Colorspace.cmyk,
-    '/I': Colorspace.index,
-}
-
-FRIENDLY_ENCODING = {
-    '/CCITTFaxDecode': Encoding.ccitt,
-    '/DCTDecode': Encoding.jpeg,
-    '/JPXDecode': Encoding.jpeg2000,
-    '/JBIG2Decode': Encoding.jbig2,
-    '/CCF': Encoding.ccitt,  # Abbreviations permitted in inline images
-    '/DCT': Encoding.jpeg,
-    '/AHx': Encoding.asciihex,
-    '/A85': Encoding.ascii85,
-    '/LZW': Encoding.lzw,
-    '/Fl': Encoding.flate,
-    '/RL': Encoding.runlength
-}
-
-FRIENDLY_COMP = {
-    Colorspace.gray: 1,
-    Colorspace.rgb: 3,
-    Colorspace.cmyk: 4,
-    Colorspace.lab: 3,
-    Colorspace.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 unit of default user space (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
-
-
-class ImageInfo:
-    DPI_PREC = Decimal('1.000')
-
-    def __init__(self, *, name='', pdfimage=None, inline=None,
-                 shorthand=None):
-
-        self._name = name
-        self._shorthand = shorthand
-        if inline:
-            # Fixme does not work for inline images with non abbreviated
-            # fields
-            self._origin = 'inline'
-            self._width = inline.settings['/W']
-            self._height = inline.settings['/H']
-            self._bpc = inline.settings.get('/BPC', 8)
-            try:
-                self._color = FRIENDLY_COLORSPACE[inline.settings['/CS']]
-            except Exception:
-                self._color = '-'
-            self._comp = FRIENDLY_COMP.get(self._color, '?')
-            if '/F' in inline.settings:
-                filter_ = inline.settings['/F']
-                if isinstance(filter_, pypdf.generic.ArrayObject):
-                    filter_ = filter_[0]
-                self._enc = FRIENDLY_ENCODING.get(filter_, 'image')
-            else:
-                self._enc = 'image'
-        elif pdfimage:
-            self._origin = 'xobject'
-            self._width = pdfimage['/Width']
-            self._height = pdfimage['/Height']
-            if '/BitsPerComponent' in pdfimage:
-                self._bpc = pdfimage['/BitsPerComponent']
-            else:
-                self._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:
-                self._type = 'stencil' if pdfimage['/ImageMask'].value \
-                    else 'image'
-            else:
-                self._type = 'image'
-            if '/Filter' in pdfimage:
-                filter_ = pdfimage['/Filter']
-                if isinstance(filter_, pypdf.generic.ArrayObject):
-                    filter_ = filter_[0]
-                self._enc = FRIENDLY_ENCODING.get(filter_, 'image')
-            else:
-                self._enc = 'image'
-            if '/ColorSpace' in pdfimage:
-                cs = pdfimage['/ColorSpace']
-                if isinstance(cs, pypdf.generic.ArrayObject):
-                    cs = cs[0]
-                self._color = FRIENDLY_COLORSPACE.get(cs, '-')
-            else:
-                self._color = FRIENDLY_COLORSPACE[Colorspace.jpeg2000] \
-                    if self._enc == Encoding.jpeg2000 else '?'
-
-            self._comp = FRIENDLY_COMP.get(self._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 self._comp == '?' and self._enc in (Encoding.ccitt, 'jbig2'):
-                self._comp = FRIENDLY_COMP[Colorspace.gray]
-
-    @property
-    def name(self):
-        return self._name
-
-    @property
-    def type_(self):
-        return self._type
-
-    @property
-    def width(self):
-        return self._width
-
-    @property
-    def height(self):
-        return self._height
-
-    @property
-    def bpc(self):
-        return self._bpc
-
-    @property
-    def color(self):
-        return self._color
-
-    @property
-    def comp(self):
-        return self._comp
-
-    @property
-    def enc(self):
-        return self._enc
-
-    @property
-    def xres(self):
-        return _get_dpi(self._shorthand, (self._width, self._height))[0]
-
-    @property
-    def yres(self):
-        return _get_dpi(self._shorthand, (self._width, self._height))[1]
-
-    def __getitem__(self, item):
-        warnings.warn("ImageInfo.__getitem__", DeprecationWarning)
-        if item in ('name', 'width', 'height', 'bpc', 'color', 'comp', 'enc'):
-            return getattr(self, item)
-        elif item == 'dpi_w':
-            return Decimal(self.xres).quantize(self.DPI_PREC)
-        elif item == 'dpi_h':
-            return Decimal(self.yres).quantize(self.DPI_PREC)
-        elif item == 'dpi':
-            return Decimal(self.xres * self.yres).sqrt().quantize(
-                self.DPI_PREC)
-        else:
-            raise KeyError(item)
-
-    def __repr__(self):
-        class_locals = {attr: getattr(self, attr, None) for attr in dir(self)
-                        if not attr.startswith('_')}
-        return (
-            "<ImageInfo '{name}' {type_} {width}x{height} {color} "
-            "{comp} {bpc} {enc} {xres}x{yres}>").format(**class_locals)
-
-
-def _find_inline_images(contentsinfo):
-    "Find inline images in the contentstream"
-
-    for n, inline in enumerate(contentsinfo.inline_images):
-        yield ImageInfo(name='inline-%02d' % n, shorthand=inline.shorthand,
-                        inline=inline)
-
-
-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':
-            pdfimage = candidate
-            yield (pdfimage, 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):
-
-        # For each image that is drawn on this, check if we drawing the
-        # current image - yes this is O(n^2), but n == 1 almost always
-        for draw in contentsinfo.xobject_settings:
-            if draw.name != xobj:
-                continue
-
-            if draw.stack_depth == 0 and _is_unit_square(draw.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
-
-            yield ImageInfo(name=draw.name, pdfimage=pdfimage, shorthand=
-                            draw.shorthand)
-
-
-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=pdf, container=form_xobject, shorthand=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(pdf, pageno: int):
-    pageinfo = {}
-    pageinfo['pageno'] = pageno
-    pageinfo['images'] = []
-
-    if isinstance(pdf, Path):
-        pdf = pypdf.PdfFileReader(str(pdf))
-    elif isinstance(pdf, str):
-        pdf = pypdf.PdfFileReader(pdf)
-
-    page = pdf.pages[pageno]
-
-    pageinfo['has_text'] = _page_has_text(pdf, page)
-
-    width_pt = page.mediaBox.getWidth()
-    height_pt = page.mediaBox.getHeight()
-
-    userunit = page.get('/UserUnit', Decimal(1.0))
-    pageinfo['userunit'] = userunit
-    pageinfo['width_inches'] = width_pt * userunit / Decimal(72.0)
-    pageinfo['height_inches'] = height_pt * userunit / Decimal(72.0)
-
-    try:
-        pageinfo['rotate'] = int(page['/Rotate'])
-    except KeyError:
-        pageinfo['rotate'] = 0
-
-    userunit_shorthand = (userunit, 0, 0, userunit, 0, 0)
-    pageinfo['images'] = [im for im in
-                          _find_images(pdf=pdf, container=page,
-                                       shorthand=userunit_shorthand)]
-    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):
-    with universal_open(infile, 'rb') as f:
-        pdf = pypdf.PdfFileReader(f)
-        return [PageInfo(pdf, n) for n in range(pdf.numPages)]
-
-
-class PageInfo:
-    def __init__(self, pdf, pageno):
-        self._pageno = pageno
-        self._pageinfo = _pdf_get_pageinfo(pdf, pageno)
-
-    @property
-    def pageno(self):
-        return self._pageno
-
-    @property
-    def has_text(self):
-        return self._pageinfo['has_text']
-
-    @property
-    def width_inches(self):
-        return self._pageinfo['width_inches']
-
-    @property
-    def height_inches(self):
-        return self._pageinfo['height_inches']
-
-    @property
-    def width_pixels(self):
-        return int(round(self.width_inches * self.xres))
-
-    @property
-    def height_pixels(self):
-        return int(round(self.height_inches * self.yres))
-
-    @property
-    def rotation(self):
-        return self._pageinfo.get('rotate', None)
-
-    @rotation.setter
-    def rotation(self, value):
-        if value in (0, 90, 180, 270, 360, -90, -180, -270):
-            self._pageinfo['rotate'] = value
-        else:
-            raise ValueError("rotation must be a cardinal angle")
-
-    @property
-    def images(self):
-        return self._pageinfo['images']
-
-    @property
-    def xres(self):
-        return self._pageinfo.get('xres', None)
-
-    @property
-    def yres(self):
-        return self._pageinfo.get('yres', None)
-
-    @property
-    def userunit(self):
-        return self._pageinfo.get('userunit', None)
-
-    @property
-    def min_version(self):
-        if self.userunit is not None:
-            return '1.6'
-        else:
-            return '1.5'
-
-    @property
-    def images(self):
-        return self._pageinfo['images']
-
-    def __repr__(self):
-        return (
-            '<PageInfo '
-            'pageno={} {}"x{}" rotation={} res={}x{} has_text={}>').format(
-            self.pageno, self.width_inches, self.height_inches,
-            self.rotation,
-            self.xres, self.yres, self.has_text
-        )
-
-
-class PdfInfo:
-    """Get summary information about a PDF
-    
-    """
-    def __init__(self, infile):
-        self._infile = infile
-        self._pages = _pdf_get_all_pageinfo(infile)
-
-    @property
-    def pages(self):
-        return self._pages
-
-    @property
-    def min_version(self):
-        # The minimum PDF is the maximum version that any particular page needs
-        return max(page.min_version for page in self.pages)
-
-    @property
-    def has_userunit(self):
-        return any(page.userunit != 1.0 for page in self.pages)
-
-    def __getitem__(self, item):
-        return self._pages[item]
-
-    def __len__(self):
-        return len(self._pages)
-
-    def __repr__(self):
-        return "<PdfInfo('...'), page count={}>".format(len(self))
-
-    # def __getstate__(self):
-    #     state = {'_infile': self._infile}
-    #     return state
-    #
-    # def __setstate__(self, state):
-    #     self._infile = state['_infile']
-    #     self._pages = _pdf_get_all_pageinfo(self._infile)
-
-
-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()

pyproject.toml

@@ -0,0 +1,106 @@
+[build-system]
+requires = [
+  "setuptools >= 30.3.0",
+  "wheel",
+  "setuptools_scm[toml] >= 3.4",
+  "setuptools_scm_git_archive"
+]
+build-backend = "setuptools.build_meta"
+
+[tool.setuptools_scm]
+version_scheme = "post-release"
+
+[tool.black]
+line-length = 88
+target-version = ["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
+)/
+'''
+
+[tool.coverage.run]
+branch = true
+parallel = true
+concurrency = ["multiprocessing"]
+
+[tool.coverage.paths]
+source = ["src/ocrmypdf"]
+
+[tool.coverage.report]
+# Regexes for lines to exclude from consideration
+exclude_lines = [
+  # Have to re-enable the standard pragma
+  "pragma: no cover",
+  # Don't complain if tests don't hit defensive assertion code:
+  "raise AssertionError",
+  "raise NotImplementedError",
+  # Don't complain if non-runnable code isn't run:
+  "if 0:",
+  "if False:",
+  "if __name__ == .__main__.:",
+  "if TYPE_CHECKING:"
+]
+
+[tool.isort]
+profile = "black"
+known_first_party = "ocrmypdf"
+known_third_party = [
+  "PIL",
+  "flask",
+  "img2pdf",
+  "ocrmypdf",
+  "pdfminer",
+  "pikepdf",
+  "pkg_resources",
+  "pluggy",
+  "pytest",
+  "reportlab",
+  "setuptools",
+  "sphinx_rtd_theme",
+  "tqdm",
+  "watchdog",
+  "werkzeug"
+]
+
+[tool.pytest.ini_options]
+minversion = "6.0"
+norecursedirs = ["lib", ".pc", ".git", "venv", "output", "cache", "resources"]
+testpaths = ["tests"]
+addopts = "-n auto"
+markers = ["slow"]
+filterwarnings = ["ignore:.*XMLParser.*:DeprecationWarning"]
+
+[tool.mypy]
+
+[[tool.mypy.overrides]]
+module = [
+  'pluggy',
+  'tqdm',
+  'coloredlogs',
+  'img2pdf',
+  'pdfminer.*',
+  'reportlab.*',
+  'fitz',
+  'libxmp.utils'
+]
+ignore_missing_imports = true
+
+[tool.pylint.basic]
+good-names = ["i", "j", "k", "ex", "Run", "_", "e", "p", "im", "w", "h", "m", "x", "y", "a", "b", "fp", "n", "f", "s", "v", "q", "dx", "dy"]
+logging-format-style = "old"
+disable = ["raw-checker-failed", "bad-inline-option", "locally-disabled", "file-ignored", "suppressed-message", "useless-suppression", "deprecated-pragma", "use-symbolic-message-instead", "logging-fstring-interpolation", "missing-function-docstring", "too-few-public-methods"]

requirements.txt

@@ -1,9 +0,0 @@
-# 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

setup.cfg

@@ -1,14 +1,113 @@
+[metadata]
+name = ocrmypdf
+description = OCRmyPDF adds an OCR text layer to scanned PDF files, allowing them to be searched
+long_description = file: README.md
+long_description_content_type = text/markdown
+url = https://github.com/ocrmypdf/OCRmyPDF
+author = James R. Barlow
+author_email = james@purplerock.ca
+license = MPL-2.0
+license_file = LICENSE
+license_files =
+    LICENSE
+classifiers =
+    Development Status :: 5 - Production/Stable
+    Environment :: Console
+    Intended Audience :: End Users/Desktop
+    Intended Audience :: Science/Research
+    Intended Audience :: System Administrators
+    License :: OSI Approved :: Mozilla Public License 2.0 (MPL 2.0)
+    Operating System :: MacOS :: MacOS X
+    Operating System :: Microsoft :: Windows :: Windows 10
+    Operating System :: POSIX
+    Operating System :: POSIX :: BSD
+    Operating System :: POSIX :: Linux
+    Programming Language :: Python :: 3
+    Programming Language :: Python :: 3 :: Only
+    Programming Language :: Python :: 3.7
+    Programming Language :: Python :: 3.8
+    Programming Language :: Python :: 3.9
+    Programming Language :: Python :: 3.10
+    Topic :: Scientific/Engineering :: Image Recognition
+    Topic :: Text Processing :: Indexing
+    Topic :: Text Processing :: Linguistic
+keywords =
+    PDF
+    OCR
+    optical character recognition
+    PDF/A
+    scanning
+project_urls =
+    Documentation = https://ocrmypdf.readthedocs.io/
+    Source = https://github.com/ocrmypdf/OCRmyPDF
+    Tracker = https://github.com/ocrmypdf/OCRmyPDF/issues
+
+[options]
+packages = find:
+install_requires =
+    Pillow>=8.2.0
+    coloredlogs>=14.0  # strictly optional
+    img2pdf>=0.3.0  # pure Python
+    packaging>=20
+    pdfminer.six!=20200720,>=20191110
+    pikepdf!=5.0.0,>=4.0.0
+    pluggy>=0.13.0
+    reportlab>=3.5.66
+    tqdm>=4
+    importlib-metadata>=4;python_version<'3.8'  # until Python 3.8
+    importlib-resources>=5;python_version<'3.9'  # until Python 3.9
+python_requires = >=3.7
+include_package_data = True
+package_dir =
+    =src
+platforms = any
+setup_requires =
+    setuptools-scm
+    setuptools-scm-git-archive
+zip_safe = False
+
+[options.packages.find]
+where = src
+
+[options.entry_points]
+console_scripts =
+    ocrmypdf = ocrmypdf.__main__:run
+
+[options.extras_require]
+docs =
+    sphinx
+    sphinx-issues
+    sphinx-rtd-theme
+extended_test =
+    PyMuPDF==1.19.1
+test =
+    coverage[toml]>=5
+    pytest>=6.0.0
+    pytest-cov>=2.11.1
+    pytest-xdist>=2.2.0
+    python-xmp-toolkit==2.0.1  # also requires apt-get install libexempi3
+watcher =
+    watchdog>=1.0.2
+webservice =
+    Flask>=1
+
+[options.package_data]
+ocrmypdf =
+    data/sRGB.icc
+    py.typed
+
 [bdist_wheel]
-python-tag = py35
+python-tag = py37
 
 [aliases]
-test=pytest
+test = pytest
 
 [check-manifest]
 ignore =
-	.github
+    .github
 
-[tool:pytest]
-norecursedirs = lib .pc .git output cache resources
-testpaths = tests
-addopts = -n auto
+[flake8]
+ignore = D203,F401,W503,E501,E203,F841
+exclude = .git,__pycache__,docs/conf.py,build,dist,.venv,.venvpp,.eggs,tmp,src/ocrmypdf/lib/
+max-complexity = 10
+max-line-length = 100

setup.py

@@ -1,238 +1,18 @@
-#!/usr/bin/env python3
-# -*- coding: utf-8 -*-
-# © 2015 James R. Barlow: github.com/jbarlow83
+# © 2021 James R. Barlow: github.com/jbarlow83
+#
+# This Source Code Form is subject to the terms of the Mozilla Public
+# License, v. 2.0. If a copy of the MPL was not distributed with this
+# file, You can obtain one at http://mozilla.org/MPL/2.0/.
 
-from __future__ import print_function, unicode_literals
+"""setup.py to support older setuptools and pip."""
 
-import sys
-if sys.version_info < (3, 5):
-    print("Python 3.5 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
-
-
-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))
-
-
-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 '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()
+from setuptools import setup
 
+# Minimal setup to support older setuptools/setuptools_scm
 setup(
-    name='ocrmypdf',
-    description='OCRmyPDF adds an OCR text layer to scanned PDF files, allowing them to be searched',
-    url='https://github.com/jbarlow83/OCRmyPDF',
-    author='James R. Barlow',
-    author_email='jim@purplerock.ca',
-    license='MIT',
-    packages=find_packages(exclude=["tests", "tests.*"]),
-    keywords=['PDF', 'OCR', 'optical character recognition', 'PDF/A', 'scanning'],
-    classifiers=[
-        "Programming Language :: Python :: 3.5",
-        "Programming Language :: Python :: 3.6",
-        "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",
-        "Operating System :: MacOS :: MacOS X",
-        "Operating System :: POSIX",
-        "Operating System :: POSIX :: BSD",
-        "Operating System :: POSIX :: Linux",
-        "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
+    setup_requires=[  # can be removed whenever we can drop pip 9 support
+        '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'
-    ],
-    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
-    ],
-    tests_require=tests_require,
-    entry_points={
-        'console_scripts': [
-            'ocrmypdf = ocrmypdf.__main__:run_pipeline'
-        ],
-    },
-    package_data={'ocrmypdf': ['data/sRGB.icc']},
-    include_package_data=True,
-    zip_safe=False)
+)

snapcraft.yaml

@@ -0,0 +1,72 @@
+name: ocrmypdf
+title: OCRmyPDF
+base: core20
+version: git
+summary: OCRmyPDF adds optical character recognition (OCR) to PDFs
+description: OCRmyPDF packaged for snap
+grade: stable
+confinement: strict
+icon: docs/images/logo-square-256.svg
+license: MPL-2.0
+
+architectures: [amd64]
+
+environment:
+  TESSDATA_PREFIX: $SNAP/usr/share/tesseract-ocr/4.00/tessdata
+  GS_LIB: $SNAP/usr/share/ghostscript/9.50/Resource/Init
+  GS_FONTPATH: $SNAP/usr/share/ghostscript/9.50/Resource/Font
+  LD_LIBRARY_PATH: $SNAP/usr/lib/x86_64-linux-gnu
+
+apps:
+  ocrmypdf:
+    command: usr/bin/snapcraft-preload python3 -m ocrmypdf
+    plugs:
+      - desktop
+      - desktop-legacy
+      - wayland
+      - x11
+      - home
+      - removable-media
+
+parts:
+  snapcraft-preload:
+    source: https://github.com/sergiusens/snapcraft-preload.git
+    plugin: cmake
+    cmake-parameters:
+      - -DCMAKE_INSTALL_PREFIX=/usr -DLIBPATH=/usr/lib
+    build-packages:
+      - on amd64:
+          - gcc-multilib
+          - g++-multilib
+    stage-packages:
+      - lib32stdc++6
+
+  ocrmypdf:
+    plugin: python
+    source: https://github.com/ocrmypdf/OCRmyPDF.git
+
+    stage-packages:
+      - ghostscript
+      - icc-profiles-free
+      - liblept5
+      - libxml2
+      - pngquant
+      - tesseract-ocr-all
+      - unpaper
+      - qpdf
+      - zlib1g
+
+    python-packages:
+      - cffi
+      - pdfminer.six
+      - pikepdf
+      - Pillow
+      - pluggy
+      - reportlab
+      - setuptools
+      - tqdm
+      - pipe
+
+    override-build: |
+      snapcraftctl build
+      ln -sf ../usr/lib/libsnapcraft-preload.so $SNAPCRAFT_PART_INSTALL/lib/libsnapcraft-preload.so

src/ocrmypdf/RELEASE.md

@@ -0,0 +1,35 @@
+# Release checklist
+
+## Patch release
+
+- Check `pytest`
+
+- Update release notes
+
+## Minor release
+
+## Major release
+
+- Run `pre-commit autoupdate`
+
+- Check README.md
+
+- Check setup.py
+
+    - Are classifiers up to date?
+    - Is `python_requires` correct?
+    - Python 3.6 is EOL on December 2021-12. Could drop support then.
+    - Can we tighten any `install_requires` dependencies?
+
+- Search for old version shims we can remove
+
+    - "shim"
+    - ` pikepdf.__version__`
+
+- Search for deprecation: search all files for deprec*, etc.
+
+- Check requirements in setup.cfg
+
+- Delete `tests/cache`, do `pytest --runslow`, and update cache.
+
+- Do `pytest --cov-report html`

src/ocrmypdf/__init__.py

@@ -0,0 +1,33 @@
+# © 2017 James R. Barlow: github.com/jbarlow83
+#
+# This Source Code Form is subject to the terms of the Mozilla Public
+# License, v. 2.0. If a copy of the MPL was not distributed with this
+# file, You can obtain one at http://mozilla.org/MPL/2.0/.
+
+"""Adds OCR layer to PDFs."""
+
+from pluggy import HookimplMarker as _HookimplMarker
+
+from ocrmypdf import helpers, hocrtransform, pdfa, pdfinfo
+from ocrmypdf._concurrent import Executor
+from ocrmypdf._jobcontext import PageContext, PdfContext
+from ocrmypdf._version import PROGRAM_NAME, __version__
+from ocrmypdf.api import Verbosity, configure_logging, ocr
+from ocrmypdf.exceptions import (
+    BadArgsError,
+    DpiError,
+    EncryptedPdfError,
+    ExitCode,
+    ExitCodeException,
+    InputFileError,
+    MissingDependencyError,
+    OutputFileAccessError,
+    PdfMergeFailedError,
+    PriorOcrFoundError,
+    SubprocessOutputError,
+    TesseractConfigError,
+    UnsupportedImageFormatError,
+)
+from ocrmypdf.pluginspec import OcrEngine, OrientationConfidence
+
+hookimpl = _HookimplMarker('ocrmypdf')

src/ocrmypdf/__main__.py

@@ -0,0 +1,77 @@
+#!/usr/bin/env python3
+# © 2015-19 James R. Barlow: github.com/jbarlow83
+#
+# This Source Code Form is subject to the terms of the Mozilla Public
+# License, v. 2.0. If a copy of the MPL was not distributed with this
+# file, You can obtain one at http://mozilla.org/MPL/2.0/.
+
+"""ocrmypdf command line entrypoint."""
+
+import logging
+import os
+import signal
+import sys
+from contextlib import suppress
+from multiprocessing import set_start_method
+
+from ocrmypdf import __version__
+from ocrmypdf._plugin_manager import get_parser_options_plugins
+from ocrmypdf._sync import run_pipeline
+from ocrmypdf._validation import check_options
+from ocrmypdf.api import Verbosity, configure_logging
+from ocrmypdf.exceptions import (
+    BadArgsError,
+    ExitCode,
+    InputFileError,
+    MissingDependencyError,
+)
+
+log = logging.getLogger('ocrmypdf')
+
+
+def sigbus(*args):
+    raise InputFileError("Lost access to the input file")
+
+
+def run(args=None):
+    _parser, options, plugin_manager = get_parser_options_plugins(args=args)
+
+    with suppress(AttributeError, PermissionError):
+        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,
+        plugin_manager=plugin_manager,
+    )
+    log.debug('ocrmypdf %s', __version__)
+    try:
+        check_options(options, plugin_manager)
+    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
+
+    with suppress(AttributeError, OSError):
+        signal.signal(signal.SIGBUS, sigbus)
+
+    result = run_pipeline(options=options, plugin_manager=plugin_manager)
+    return result
+
+
+if __name__ == '__main__':
+    if sys.platform == 'darwin' and sys.version_info < (3, 8):
+        set_start_method('spawn')  # see python bpo-33725
+    sys.exit(run())

src/ocrmypdf/_concurrent.py

@@ -0,0 +1,139 @@
+# © 2020 James R. Barlow: github.com/jbarlow83
+#
+# This Source Code Form is subject to the terms of the Mozilla Public
+# License, v. 2.0. If a copy of the MPL was not distributed with this
+# file, You can obtain one at http://mozilla.org/MPL/2.0/.
+
+"""OCRmyPDF concurrency abstractions."""
+
+import threading
+from abc import ABC, abstractmethod
+from typing import Callable, Iterable, Optional
+
+
+def _task_noop(*_args, **_kwargs):
+    return
+
+
+class NullProgressBar:
+    """Progress bar API that takes no actions."""
+
+    def __init__(self, **kwargs):
+        pass
+
+    def __enter__(self):
+        return self
+
+    def __exit__(self, exc_type, exc_value, traceback):
+        return False
+
+    def update(self, _arg=None):
+        return
+
+
+class Executor(ABC):
+    """Abstract concurrent executor."""
+
+    pool_lock = threading.Lock()
+    pbar_class = NullProgressBar
+
+    def __init__(self, *, pbar_class=None):
+        if pbar_class:
+            self.pbar_class = pbar_class
+
+    def __call__(
+        self,
+        *,
+        use_threads: bool,
+        max_workers: int,
+        tqdm_kwargs: dict,
+        worker_initializer: Optional[Callable] = None,
+        task: Optional[Callable] = None,
+        task_arguments: Optional[Iterable] = None,
+        task_finished: Optional[Callable] = None,
+    ) -> None:
+        """
+        Set up parallel execution and progress reporting.
+
+        Args:
+            use_threads: If ``False``, the workload is the sort that will benefit from
+                running in a multiprocessing context (for example, it uses Python
+                heavily, and parallelizing it with threads is not expected to be
+                performant).
+            max_workers: The maximum number of workers that should be run.
+            tdqm_kwargs: Arguments to set up the progress bar.
+            worker_initializer: Called when a worker is initialized, in the worker's
+                execution context. If the child workers are processes, it must be
+                possible to marshall/pickle the worker initializer.
+                ``functools.partial`` can be used to bind parameters.
+            task: Called when the worker starts a new task, in the worker's execution
+                context. Must be possible to marshall to the worker.
+            task_finished: Called when a worker finishes a task, in the parent's
+                context.
+            task_arguments: An iterable that generates a group of parameters for each
+                task. This runs in the parent's context, but the parameters must be
+                marshallable to the worker.
+        """
+
+        if not task_arguments:
+            return  # Nothing to do!
+        if not worker_initializer:
+            worker_initializer = _task_noop
+        if not task_finished:
+            task_finished = _task_noop
+        if not task:
+            task = _task_noop
+
+        with self.pool_lock:
+            self._execute(
+                use_threads=use_threads,
+                max_workers=max_workers,
+                tqdm_kwargs=tqdm_kwargs,
+                worker_initializer=worker_initializer,
+                task=task,
+                task_arguments=task_arguments,
+                task_finished=task_finished,
+            )
+
+    @abstractmethod
+    def _execute(
+        self,
+        *,
+        use_threads: bool,
+        max_workers: int,
+        tqdm_kwargs: dict,
+        worker_initializer: Callable,
+        task: Callable,
+        task_arguments: Iterable,
+        task_finished: Callable,
+    ):
+        """Custom executors should override this method."""
+
+
+def setup_executor(plugin_manager) -> Executor:
+    pbar_class = plugin_manager.hook.get_progressbar_class()
+    return plugin_manager.hook.get_executor(progressbar_class=pbar_class)
+
+
+class SerialExecutor(Executor):
+    """Implements a purely sequential executor using the parallel protocol.
+
+    The current process/thread will be the worker that executes all tasks
+    in order. As such, ``worker_initializer`` will never be called.
+    """
+
+    def _execute(
+        self,
+        *,
+        use_threads: bool,
+        max_workers: int,
+        tqdm_kwargs: dict,
+        worker_initializer: Callable,
+        task: Callable,
+        task_arguments: Iterable,
+        task_finished: Callable,
+    ):  # pylint: disable=unused-argument
+        with self.pbar_class(**tqdm_kwargs) as pbar:
+            for args in task_arguments:
+                result = task(args)
+                task_finished(result, pbar)

src/ocrmypdf/_exec/__init__.py

@@ -0,0 +1,8 @@
+# © 2020 James R. Barlow: github.com/jbarlow83
+#
+# This Source Code Form is subject to the terms of the Mozilla Public
+# License, v. 2.0. If a copy of the MPL was not distributed with this
+# file, You can obtain one at http://mozilla.org/MPL/2.0/.
+
+
+"""Manage third party executables"""

src/ocrmypdf/_exec/ghostscript.py

@@ -0,0 +1,281 @@
+# © 2017 James R. Barlow: github.com/jbarlow83
+#
+# This Source Code Form is subject to the terms of the Mozilla Public
+# License, v. 2.0. If a copy of the MPL was not distributed with this
+# file, You can obtain one at http://mozilla.org/MPL/2.0/.
+
+
+"""Interface to Ghostscript executable"""
+
+import logging
+import os
+import re
+import sys
+from io import BytesIO
+from os import fspath
+from pathlib import Path
+from subprocess import PIPE, CalledProcessError
+from typing import Optional
+
+from PIL import Image, UnidentifiedImageError
+
+from ocrmypdf.exceptions import SubprocessOutputError
+from ocrmypdf.helpers import Resolution
+from ocrmypdf.subprocess import get_version, run, run_polling_stderr
+
+# Remove this workaround when we require Pillow >= 10
+try:
+    Transpose = Image.Transpose  # type: ignore
+except AttributeError:
+    # Pillow 9 shim
+    Transpose = Image  # type: ignore
+
+log = logging.getLogger(__name__)
+
+# Most reliable what to get the bitness of Python interpreter, according to Python docs
+_IS_64BIT = sys.maxsize > 2**32
+
+_GSWIN = None
+if os.name == 'nt':
+    if _IS_64BIT:
+        _GSWIN = 'gswin64c'
+    else:
+        _GSWIN = 'gswin32c'
+
+GS = _GSWIN if _GSWIN else 'gs'
+del _GSWIN
+
+
+def version():
+    return get_version(GS)
+
+
+def jpeg_passthrough_available() -> bool:
+    """Returns True if the installed version of Ghostscript supports JPEG passthru
+
+    Prior to 9.23, Ghostscript decoded 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. (Ghostscript 9.24 has its own problems is blacklisted.)
+    """
+    return version() >= '9.24'
+
+
+def _gs_error_reported(stream) -> bool:
+    match = re.search(r'error', stream, flags=re.IGNORECASE)
+    return bool(match)
+
+
+def rasterize_pdf(
+    input_file: os.PathLike,
+    output_file: os.PathLike,
+    *,
+    raster_device: str,
+    raster_dpi: Resolution,
+    pageno: int = 1,
+    page_dpi: Optional[Resolution] = None,
+    rotation: Optional[int] = None,
+    filter_vector: bool = False,
+):
+    """Rasterize one page of a PDF at resolution raster_dpi in canvas units."""
+    raster_dpi = raster_dpi.round(6)
+    if not page_dpi:
+        page_dpi = raster_dpi
+
+    args_gs = (
+        [
+            GS,
+            '-dQUIET',
+            '-dSAFER',
+            '-dBATCH',
+            '-dNOPAUSE',
+            '-dInterpolateControl=-1',
+            f'-sDEVICE={raster_device}',
+            f'-dFirstPage={pageno}',
+            f'-dLastPage={pageno}',
+            f'-r{raster_dpi.x:f}x{raster_dpi.y:f}',
+        ]
+        + (['-dFILTERVECTOR'] if filter_vector else [])
+        + [
+            '-o',
+            '-',
+            '-sstdout=%stderr',  # Literal %s, not string interpolation
+            '-dAutoRotatePages=/None',  # Probably has no effect on raster
+            '-f',
+            fspath(input_file),
+        ]
+    )
+
+    try:
+        p = run(args_gs, stdout=PIPE, stderr=PIPE, check=True)
+    except CalledProcessError as e:
+        log.error(e.stderr.decode(errors='replace'))
+        raise SubprocessOutputError('Ghostscript rasterizing failed') from e
+    else:
+        stderr = p.stderr.decode(errors='replace')
+        if _gs_error_reported(stderr):
+            log.error(stderr)
+
+    try:
+        with Image.open(BytesIO(p.stdout)) 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(Transpose.ROTATE_90)
+                elif rotation == 180:
+                    im = im.transpose(Transpose.ROTATE_180)
+                elif rotation == 270:
+                    im = im.transpose(Transpose.ROTATE_270)
+                if rotation % 180 == 90:
+                    page_dpi = page_dpi.flip_axis()
+            im.save(fspath(output_file), dpi=page_dpi)
+    except UnidentifiedImageError:
+        log.error(
+            f"Ghostscript (using {raster_device} at {raster_dpi} dpi) produced "
+            "an invalid page image file."
+        )
+        raise
+
+
+class GhostscriptFollower:
+    """Parses the output of Ghostscript and uses it to update the progress bar."""
+
+    re_process = re.compile(r"Processing pages \d+ through (\d+).")
+    re_page = re.compile(r"Page (\d+)")
+
+    def __init__(self, progressbar_class):
+        self.count = 0
+        self.progressbar_class = progressbar_class
+        self.progressbar = None
+
+    def __call__(self, line):
+        if not self.progressbar_class:
+            return
+        if not self.progressbar:
+            m = self.re_process.match(line.strip())
+            if m:
+                self.count = int(m.group(1))
+                self.progressbar = self.progressbar_class(
+                    total=self.count, desc="PDF/A conversion", unit='page'
+                )
+                return
+        else:
+            if self.re_page.match(line.strip()):
+                self.progressbar.update()
+
+
+def generate_pdfa(
+    pdf_pages,
+    output_file: os.PathLike,
+    *,
+    compression: str,
+    pdf_version: str = '1.5',
+    pdfa_part: str = '2',
+    progressbar_class=None,
+):
+    # Ghostscript's compression is all or nothing. We can either force all images
+    # to JPEG, force all to Flate/PNG, or let it decide how to encode the images.
+    # In most case it's best to let it decide.
+    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",
+        ]
+
+    strategy = 'LeaveColorUnchanged'
+    # Older versions of Ghostscript expect a leading slash in
+    # sColorConversionStrategy, newer ones should not have it. See Ghostscript
+    # git commit fe1c025d.
+    gs_version = version()
+    strategy = ('/' + strategy) if gs_version < '9.19' else strategy
+
+    if gs_version == '9.23':
+        # 9.23: added JPEG passthrough as a new feature, but with a bug that
+        # incorrectly formats some images. Fixed as of 9.24. So we disable this
+        # feature for 9.23.
+        # https://bugs.ghostscript.com/show_bug.cgi?id=699216
+        compression_args.append('-dPassThroughJPEGImages=false')
+    elif gs_version == '9.56.0':
+        # 9.56.0 breaks our OCR...?
+        compression_args.append('-dNEWPDF=false')
+
+    # nb no need to specify ProcessColorModel when ColorConversionStrategy
+    # is set; see:
+    # https://bugs.ghostscript.com/show_bug.cgi?id=699392
+    args_gs = (
+        [
+            GS,
+            "-dBATCH",
+            "-dNOPAUSE",
+            "-dSAFER",
+            "-dCompatibilityLevel=" + str(pdf_version),
+            "-sDEVICE=pdfwrite",
+            "-dAutoRotatePages=/None",
+            "-sColorConversionStrategy=" + strategy,
+        ]
+        + compression_args
+        + [
+            "-dJPEGQ=95",
+            "-dPDFA=" + pdfa_part,
+            "-dPDFACompatibilityPolicy=1",
+            "-o",
+            "-",
+            "-sstdout=%stderr",  # Literal %s, not string interpolation
+        ]
+    )
+    args_gs.extend(fspath(s) for s in pdf_pages)  # Stringify Path objs
+
+    try:
+        with Path(output_file).open('wb') as output:
+            p = run_polling_stderr(
+                args_gs,
+                stdout=output,
+                stderr=PIPE,
+                check=True,
+                text=True,
+                encoding='utf-8',
+                errors='replace',
+                callback=GhostscriptFollower(progressbar_class),
+            )
+    except CalledProcessError as e:
+        # Ghostscript does not change return code when it fails to create
+        # PDF/A - check PDF/A status elsewhere
+        log.error(e.stderr)
+        raise SubprocessOutputError('Ghostscript PDF/A rendering failed') from e
+    else:
+        stderr = p.stderr
+        # If there is an error we log the whole stderr, except for filtering
+        # duplicates.
+        if _gs_error_reported(stderr):
+            last_part = None
+            repcount = 0
+            for part in stderr.split('****'):
+                if part != last_part:
+                    if repcount > 1:
+                        log.error(f"(previous error message repeated {repcount} times)")
+                        repcount = 0
+                    log.error(part)
+                else:
+                    repcount += 1
+                last_part = part

src/ocrmypdf/_exec/jbig2enc.py

@@ -0,0 +1,57 @@
+# © 2018 James R. Barlow: github.com/jbarlow83
+#
+# This Source Code Form is subject to the terms of the Mozilla Public
+# License, v. 2.0. If a copy of the MPL was not distributed with this
+# file, You can obtain one at http://mozilla.org/MPL/2.0/.
+
+
+"""Interface to jbig2 executable"""
+
+from subprocess import PIPE
+
+from ocrmypdf.exceptions import MissingDependencyError
+from ocrmypdf.subprocess import get_version, run
+
+
+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_group_mp(args):
+    return convert_group(cwd=args[0], infiles=args[1], out_prefix=args[2])
+
+
+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
+
+
+def convert_single_mp(args):
+    return convert_single(cwd=args[0], infile=args[1], outfile=args[2])

src/ocrmypdf/_exec/pngquant.py

@@ -0,0 +1,65 @@
+# © 2018 James R. Barlow: github.com/jbarlow83
+#
+# This Source Code Form is subject to the terms of the Mozilla Public
+# License, v. 2.0. If a copy of the MPL was not distributed with this
+# file, You can obtain one at http://mozilla.org/MPL/2.0/.
+
+
+"""Interface to pngquant executable"""
+
+from contextlib import contextmanager
+from io import BytesIO
+from pathlib import Path
+from subprocess import PIPE
+
+from PIL import Image
+
+from ocrmypdf.exceptions import MissingDependencyError
+from ocrmypdf.subprocess import get_version, run
+
+
+def version():
+    return get_version('pngquant', regex=r'(\d+(\.\d+)*).*')
+
+
+def available():
+    try:
+        version()
+    except MissingDependencyError:
+        return False
+    return True
+
+
+@contextmanager
+def input_as_png(input_file: Path):
+    if not input_file.name.endswith('.png'):
+        with Image.open(input_file) as im:
+            bio = BytesIO()
+            im.save(bio, format='png')
+            bio.seek(0)
+            yield bio
+    else:
+        with open(input_file, 'rb') as f:
+            yield f
+
+
+def quantize(input_file: Path, output_file: Path, quality_min: int, quality_max: int):
+    with input_as_png(input_file) as input_stream:
+        args = [
+            'pngquant',
+            '--force',
+            '--skip-if-larger',
+            '--quality',
+            f'{quality_min}-{quality_max}',
+            '--',  # pngquant: stop processing arguments
+            '-',  # pngquant: stream input and output
+        ]
+        result = run(args, stdin=input_stream, stdout=PIPE, stderr=PIPE, check=False)
+
+    if result.returncode == 0:
+        # input_file could be the same as output_file, so we defer the write
+        output_file.write_bytes(result.stdout)
+
+
+def quantize_mp(args):
+    return quantize(*args)

src/ocrmypdf/_exec/tesseract.py

@@ -0,0 +1,427 @@
+# © 2017 James R. Barlow: github.com/jbarlow83
+#
+# This Source Code Form is subject to the terms of the Mozilla Public
+# License, v. 2.0. If a copy of the MPL was not distributed with this
+# file, You can obtain one at http://mozilla.org/MPL/2.0/.
+
+
+"""Interface to Tesseract executable"""
+
+import logging
+import re
+from math import pi
+from os import fspath
+from pathlib import Path
+from subprocess import PIPE, STDOUT, CalledProcessError, TimeoutExpired
+from typing import Dict, List, Optional
+
+from packaging.version import Version
+from PIL import Image
+
+from ocrmypdf.exceptions import (
+    MissingDependencyError,
+    SubprocessOutputError,
+    TesseractConfigError,
+)
+from ocrmypdf.pluginspec import OrientationConfidence
+from ocrmypdf.subprocess import get_version, run
+
+log = logging.getLogger(__name__)
+
+
+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>
+"""
+
+TESSERACT_THRESHOLDING_METHODS: Dict[str, int] = {
+    'auto': 0,
+    'otsu': 0,
+    'adaptive-otsu': 1,
+    'sauvola': 2,
+}
+
+
+class TesseractLoggerAdapter(logging.LoggerAdapter):
+    "Prepend [tesseract] to messages emitted from tesseract"
+
+    def process(self, msg, kwargs):
+        kwargs['extra'] = self.extra
+        return f'[tesseract] {msg}', kwargs
+
+
+TESSERACT_VERSION_PATTERN = r"""
+    v?
+    (?:
+        (?:(?P<epoch>[0-9]+)!)?                           # epoch
+        (?P<release>[0-9]+(?:\.[0-9]+)*)                  # release segment
+        (?P<pre>                                          # pre-release
+            [-_\.]?
+            (?P<pre_l>(a|b|c|rc|alpha|beta|pre|preview))
+            [-_\.]?
+            (?P<pre_n>[0-9]+)?
+        )?
+        (?P<post>                                         # post release
+            (?:-(?P<post_n1>[0-9]+))
+            |
+            (?:
+                [-_\.]?
+                (?P<post_l>post|rev|r)
+                [-_\.]?
+                (?P<post_n2>[0-9]+)?
+            )
+        )?
+        (?P<dev>                                          # dev release
+            [-_\.]?
+            (?P<dev_l>dev)
+            [-_\.]?
+            (?P<dev_n>[0-9]+)?
+        )?
+        (?P<date>
+            [-_\.]
+            (?:20[0-9][0-9] [0-1][0-9] [0-3][0-9])       # yyyy mm dd
+        )?
+        (?P<gitcount>
+            [-_\.]?
+            [0-9]+
+        )?
+        (?P<gitcommit>
+            [-_\.]?
+            g[0-9a-f]{2,10}
+        )?
+    )
+    (?:\+(?P<local>[a-z0-9]+(?:[-_\.][a-z0-9]+)*))?       # local version
+"""
+
+
+class TesseractVersion(Version):
+    "Modify standard packaging.Version regex to support Tesseract idiosyncracies."
+    _regex = re.compile(
+        r"^\s*" + TESSERACT_VERSION_PATTERN + r"\s*$", re.VERBOSE | re.IGNORECASE
+    )
+
+
+def version() -> str:
+    return get_version('tesseract', regex=r'tesseract\s(.+)')
+
+
+def has_user_words():
+    """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() >= '4.1'
+
+
+def has_thresholding():
+    """Does Tesseract have -c thresholding method capability?"""
+    return version() >= '5.0'
+
+
+def get_languages():
+    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,
+            text=True,
+            stdout=PIPE,
+            stderr=STDOUT,
+            logs_errors_to_stdout=True,
+            check=True,
+        )
+        output = proc.stdout
+    except CalledProcessError as e:
+        raise MissingDependencyError(lang_error(e.output)) from e
+
+    for line in output.splitlines():
+        if line.startswith('Error'):
+            raise MissingDependencyError(lang_error(output))
+    _header, *rest = output.splitlines()
+    return {lang.strip() for lang in rest}
+
+
+def tess_base_args(langs: List[str], engine_mode: Optional[int]) -> List[str]:
+    args = ['tesseract']
+    if langs:
+        args.extend(['-l', '+'.join(langs)])
+    if engine_mode is not None:
+        args.extend(['--oem', str(engine_mode)])
+    return args
+
+
+def _parse_tesseract_output(binary_output: bytes) -> Dict[str, str]:
+    def gen():
+        for line in binary_output.decode().splitlines():
+            line = line.strip()
+            parts = line.split(':', maxsplit=2)
+            if len(parts) == 2:
+                yield parts[0].strip(), parts[1].strip()
+
+    return dict(gen())
+
+
+def get_orientation(
+    input_file: Path, engine_mode: Optional[int], timeout: float
+) -> OrientationConfidence:
+    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)
+    except TimeoutExpired:
+        return OrientationConfidence(angle=0, confidence=0.0)
+    except CalledProcessError as e:
+        tesseract_log_output(e.stdout)
+        tesseract_log_output(e.stderr)
+        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
+
+    osd = _parse_tesseract_output(p.stdout)
+    angle = int(osd.get('Orientation in degrees', 0))
+    orient_conf = OrientationConfidence(
+        angle=angle, confidence=float(osd.get('Orientation confidence', 0))
+    )
+    return orient_conf
+
+
+def get_deskew(
+    input_file: Path, languages: List[str], engine_mode: Optional[int], timeout: float
+) -> float:
+    """Gets angle to deskew this page, in degrees."""
+    args_tesseract = tess_base_args(languages, engine_mode) + [
+        '--psm',
+        '2',
+        fspath(input_file),
+        'stdout',
+    ]
+
+    try:
+        p = run(args_tesseract, stdout=PIPE, stderr=STDOUT, timeout=timeout, check=True)
+    except TimeoutExpired:
+        return 0.0
+    except CalledProcessError as e:
+        tesseract_log_output(e.stdout)
+        tesseract_log_output(e.stderr)
+        if b'Empty page!!' in e.output or (
+            e.output == b'' and e.returncode == 1
+        ):  # Not enough info for a skew angle - Tess 4 and 5 return different errors
+            return 0.0
+
+        raise SubprocessOutputError() from e
+
+    parsed = _parse_tesseract_output(p.stdout)
+    deskew_radians = float(parsed.get('Deskew angle', 0))
+    deskew_degrees = 180 / pi * deskew_radians
+    return deskew_degrees
+
+
+def tesseract_log_output(stream):
+    tlog = TesseractLoggerAdapter(
+        log, extra=log.extra if hasattr(log, 'extra') else None
+    )
+
+    if not stream:
+        return
+    try:
+        text = stream.decode()
+    except UnicodeDecodeError:
+        text = stream.decode('utf-8', 'ignore')
+
+    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:
+            tlog.warning("lots of diacritics - possibly poor OCR")
+        elif line.startswith('OSD: Weak margin'):
+            tlog.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():
+            tlog.error(line.strip())
+            problem = line.split('found: ')[1]
+            raise TesseractConfigError(problem)
+        elif 'error' in line.lower() or 'exception' in line.lower():
+            tlog.error(line.strip())
+        elif 'warning' in line.lower():
+            tlog.warning(line.strip())
+        elif 'read_params_file' in line.lower():
+            tlog.error(line.strip())
+        else:
+            tlog.info(line.strip())
+
+
+def page_timedout(timeout):
+    if timeout == 0:
+        return
+    log.warning("[tesseract] took too long to OCR - skipping")
+
+
+def _generate_null_hocr(output_hocr, output_text, image):
+    """Produce a .hocr file that reports no text detected on a page that is
+    the same size as the input image."""
+    with Image.open(image) as im:
+        w, h = im.size
+
+    output_hocr.write_text(HOCR_TEMPLATE.format(w, h), encoding='utf-8')
+    output_text.write_text('[skipped page]', encoding='utf-8')
+
+
+def generate_hocr(
+    *,
+    input_file: Path,
+    output_hocr: Path,
+    output_text: Path,
+    languages: List[str],
+    engine_mode: int,
+    tessconfig: List[str],
+    timeout: float,
+    pagesegmode: int,
+    thresholding: int,
+    user_words,
+    user_patterns,
+):
+    """Generate a hOCR file, which must be converted to PDF."""
+    prefix = output_hocr.with_suffix('')
+
+    args_tesseract = tess_base_args(languages, engine_mode)
+
+    if pagesegmode is not None:
+        args_tesseract.extend(['--psm', str(pagesegmode)])
+
+    if thresholding != 0 and has_thresholding():
+        args_tesseract.extend(['-c', f'thresholding_method={thresholding}'])
+
+    if user_words:
+        args_tesseract.extend(['--user-words', user_words])
+
+    if user_patterns:
+        args_tesseract.extend(['--user-patterns', user_patterns])
+
+    # Reminder: test suite tesseract test plugins will break after any changes
+    # to the number of order parameters here
+    args_tesseract.extend([fspath(input_file), fspath(prefix), 'hocr', 'txt'])
+    args_tesseract.extend(tessconfig)
+    try:
+        p = run(args_tesseract, stdout=PIPE, stderr=STDOUT, timeout=timeout, check=True)
+        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(timeout)
+        _generate_null_hocr(output_hocr, output_text, input_file)
+    except CalledProcessError as e:
+        tesseract_log_output(e.output)
+        if b'Image too large' in e.output or b'Empty page!!' in e.output:
+            _generate_null_hocr(output_hocr, output_text, input_file)
+            return
+
+        raise SubprocessOutputError() from e
+    else:
+        tesseract_log_output(stdout)
+        # The sidecar text file will get the suffix .txt; rename it to
+        # whatever caller wants it named
+        if prefix.with_suffix('.txt').exists():
+            prefix.with_suffix('.txt').replace(output_text)
+
+
+def use_skip_page(output_pdf, output_text):
+    output_text.write_text('[skipped page]', encoding='utf-8')
+
+    # A 0 byte file to the output to indicate a skip
+    output_pdf.write_bytes(b'')
+
+
+def generate_pdf(
+    *,
+    input_file: Path,
+    output_pdf: Path,
+    output_text: Path,
+    languages: List[str],
+    engine_mode: int,
+    tessconfig: List[str],
+    timeout: float,
+    pagesegmode: int,
+    thresholding: int,
+    user_words,
+    user_patterns,
+):
+    """Generate a PDF using Tesseract's internal PDF generator.
+
+    We specifically a text-only PDF which is more suitable for combining with
+    the input page.
+    """
+    args_tesseract = tess_base_args(languages, engine_mode)
+
+    if pagesegmode is not None:
+        args_tesseract.extend(['--psm', str(pagesegmode)])
+
+    args_tesseract.extend(['-c', 'textonly_pdf=1'])
+
+    if thresholding != 0 and has_thresholding():
+        args_tesseract.extend(['-c', f'thresholding_method={thresholding}'])
+
+    if user_words:
+        args_tesseract.extend(['--user-words', user_words])
+
+    if user_patterns:
+        args_tesseract.extend(['--user-patterns', user_patterns])
+
+    prefix = output_pdf.parent / Path(output_pdf.stem)
+
+    # Reminder: test suite tesseract test plugins might break after any changes
+    # to the number of order parameters here
+
+    args_tesseract.extend([fspath(input_file), fspath(prefix), 'pdf', 'txt'])
+    args_tesseract.extend(tessconfig)
+    try:
+        p = run(args_tesseract, stdout=PIPE, stderr=STDOUT, timeout=timeout, check=True)
+        stdout = p.stdout
+        if prefix.with_suffix('.txt').exists():
+            prefix.with_suffix('.txt').replace(output_text)
+    except TimeoutExpired:
+        page_timedout(timeout)
+        use_skip_page(output_pdf, output_text)
+    except CalledProcessError as e:
+        tesseract_log_output(e.output)
+        if b'Image too large' in e.output or b'Empty page!!' in e.output:
+            use_skip_page(output_pdf, output_text)
+            return
+        raise SubprocessOutputError() from e
+    else:
+        tesseract_log_output(stdout)

src/ocrmypdf/_exec/unpaper.py

@@ -0,0 +1,189 @@
+# © 2015 James R. Barlow: github.com/jbarlow83
+#
+# This Source Code Form is subject to the terms of the Mozilla Public
+# License, v. 2.0. If a copy of the MPL was not distributed with this
+# file, You can obtain one at http://mozilla.org/MPL/2.0/.
+
+
+# unpaper documentation:
+# https://github.com/Flameeyes/unpaper/blob/master/doc/basic-concepts.md
+
+"""Interface to unpaper executable"""
+
+import logging
+import os
+import shlex
+import sys
+from contextlib import contextmanager
+from decimal import Decimal
+from pathlib import Path
+from subprocess import PIPE, STDOUT
+from typing import Iterator, List, Optional, Tuple, Union
+
+from PIL import Image
+
+from ocrmypdf.exceptions import MissingDependencyError, SubprocessOutputError
+from ocrmypdf.subprocess import get_version, run
+
+if sys.version_info >= (3, 10):
+    from tempfile import TemporaryDirectory
+else:
+    from tempfile import TemporaryDirectory as _TemporaryDirectory
+
+    class TemporaryDirectory(_TemporaryDirectory):
+        """Shim to consume ignore_cleanup_errors kwarg on Python 3.9 and older.
+
+        The argument is consumed without action. If users are getting errors related
+        to temporary file cleanup, they should upgrade to Python 3.10 which properly
+        cleans up temporary directories on Windows.
+
+        See: https://github.com/python/cpython/pull/24793
+        """
+
+        def __init__(self, ignore_cleanup_errors=False, **kwargs):
+            super().__init__(**kwargs)
+
+    del _TemporaryDirectory
+
+
+UNPAPER_IMAGE_PIXEL_LIMIT = 256 * 1024 * 1024
+
+DecFloat = Union[Decimal, float]
+
+log = logging.getLogger(__name__)
+
+
+class UnpaperImageTooLargeError(Exception):
+    """To capture details when an image is too large for unpaper."""
+
+    def __init__(
+        self,
+        w,
+        h,
+        message="Image with size {}x{} is too large for cleaning with 'unpaper'.",
+    ):
+        self.w = w
+        self.h = h
+        self.message = message.format(w, h)
+        super().__init__(self.message)
+
+
+def version() -> str:
+    return get_version('unpaper')
+
+
+SUPPORTED_MODES = {'1', 'L', 'RGB'}
+
+
+def _convert_image(im: Image.Image) -> Tuple[Image.Image, bool]:
+    im_modified = False
+
+    if im.mode not in SUPPORTED_MODES:
+        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 OSError as e:
+            raise MissingDependencyError(
+                "Could not convert image with type " + im.mode
+            ) from e
+        else:
+            im_modified = True
+        if im.mode not in SUPPORTED_MODES:
+            raise MissingDependencyError(
+                "Failed to convert image to a supported format."
+            ) from None
+    return im, im_modified
+
+
+@contextmanager
+def _setup_unpaper_io(input_file: Path) -> Iterator[Tuple[Path, Path, Path]]:
+    with Image.open(input_file) as im:
+        if im.width * im.height >= UNPAPER_IMAGE_PIXEL_LIMIT:
+            raise UnpaperImageTooLargeError(w=im.width, h=im.height)
+        im, im_modified = _convert_image(im)
+
+        with TemporaryDirectory(ignore_cleanup_errors=True) as tmpdir:
+            tmppath = Path(tmpdir)
+            if im_modified or input_file.suffix != '.png':
+                input_png = tmppath / 'input.png'
+                im.save(input_png, format='PNG')
+            else:
+                # No changes, PNG input, just use the file we already have
+                input_png = input_file
+
+            # unpaper can write .png too, but it seems to write them slowly
+            # adds a few seconds to test suite - so just use pnm
+            output_pnm = tmppath / 'output.pnm'
+            yield input_png, output_pnm, tmppath
+
+
+def run_unpaper(
+    input_file: Path, output_file: Path, *, dpi: DecFloat, mode_args: List[str]
+) -> None:
+    args_unpaper = ['unpaper', '-v', '--dpi', str(round(dpi, 6))] + mode_args
+
+    with _setup_unpaper_io(input_file) as (input_png, output_pnm, tmpdir):
+        # 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([os.fspath(input_png), os.fspath(output_pnm)])
+        run(
+            args_unpaper,
+            close_fds=True,
+            check=True,
+            stderr=STDOUT,  # unpaper writes logging output to stdout and stderr
+            stdout=PIPE,  # and cannot send file output to stdout
+            cwd=tmpdir,
+            logs_errors_to_stdout=True,
+        )
+        try:
+            with Image.open(output_pnm) as imout:
+                imout.save(output_file, dpi=(dpi, dpi))
+        except OSError as e:
+            raise SubprocessOutputError(
+                "unpaper: failed to produce the expected output file. "
+                + " Called with: "
+                + str(args_unpaper)
+            ) from e
+
+
+def validate_custom_args(args: str) -> List[str]:
+    unpaper_args = shlex.split(args)
+    if any(('/' in arg or arg == '.' or arg == '..') for arg in unpaper_args):
+        raise ValueError('No filenames allowed in --unpaper-args')
+    return unpaper_args
+
+
+def clean(
+    input_file: Path,
+    output_file: Path,
+    *,
+    dpi: DecFloat,
+    unpaper_args: Optional[List[str]] = None,
+) -> Path:
+    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
+    try:
+        run_unpaper(input_file, output_file, dpi=dpi, mode_args=unpaper_args)
+        return output_file
+    except UnpaperImageTooLargeError as e:
+        log.warning(str(e))
+        return input_file

src/ocrmypdf/_graft.py

@@ -0,0 +1,311 @@
+# © 2018 James R. Barlow: github.com/jbarlow83
+#
+# This Source Code Form is subject to the terms of the Mozilla Public
+# License, v. 2.0. If a copy of the MPL was not distributed with this
+# file, You can obtain one at http://mozilla.org/MPL/2.0/.
+
+"""For grafting text-only PDF pages onto freeform PDF pages."""
+
+import logging
+from contextlib import suppress
+from pathlib import Path
+from typing import Optional
+
+from pikepdf import (
+    Dictionary,
+    Name,
+    Object,
+    Operator,
+    Pdf,
+    PdfError,
+    PdfMatrix,
+    Stream,
+    parse_content_stream,
+    unparse_content_stream,
+)
+
+log = logging.getLogger(__name__)
+MAX_REPLACE_PAGES = 100
+
+
+def _ensure_dictionary(obj, name):
+    if name not in obj:
+        obj[name] = Dictionary({})
+    return obj[name]
+
+
+def _update_resources(*, obj, font, font_key, procset):
+    """Update this obj's fonts with a reference to the Glyphless font.
+
+    obj can be a page or Form XObject.
+    """
+
+    resources = _ensure_dictionary(obj, Name.Resources)
+    fonts = _ensure_dictionary(resources, Name.Font)
+    if font_key is not None and font_key not in fonts:
+        fonts[font_key] = font
+
+    # Reassign /ProcSet to one that just lists everything - ProcSet is
+    # obsolete and doesn't matter but recommended for old viewer support
+    if procset:
+        resources['/ProcSet'] = procset
+
+
+def strip_invisible_text(pdf, page):
+    stream = []
+    in_text_obj = False
+    render_mode = 0
+    text_objects = []
+
+    for operands, operator in parse_content_stream(page, ''):
+        if not in_text_obj:
+            if operator == Operator('BT'):
+                in_text_obj = True
+                render_mode = 0
+                text_objects.append((operands, operator))
+            else:
+                stream.append((operands, operator))
+        else:
+            if operator == Operator('Tr'):
+                render_mode = operands[0]
+            text_objects.append((operands, operator))
+            if operator == Operator('ET'):
+                in_text_obj = False
+                if render_mode != 3:
+                    stream.extend(text_objects)
+                text_objects.clear()
+
+    content_stream = unparse_content_stream(stream)
+    page.Contents = Stream(pdf, content_stream)
+
+
+class OcrGrafter:
+    """Manages grafting text-only PDFs onto regular PDFs."""
+
+    def __init__(self, context):
+        self.context = context
+        self.path_base = context.origin
+
+        self.pdf_base = Pdf.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(
+            Object.parse(b'[ /PDF /Text /ImageB /ImageC /ImageI ]')
+        )
+
+        self.emplacements = 1
+        self.interim_count = 0
+
+    def graft_page(
+        self,
+        *,
+        pageno: int,
+        image: Optional[Path],
+        textpdf: Optional[Path],
+        autorotate_correction: int,
+    ):
+        if textpdf and not self.font:
+            self.font, self.font_key = self._find_font(textpdf)
+
+        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)
+            log.debug("Emplacement update")
+            with Pdf.open(path_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
+
+        # Calculate if the text is misaligned compared to the content
+        if emplaced_page:
+            content_rotation = autorotate_correction
+        text_rotation = autorotate_correction
+        text_misaligned = (text_rotation - content_rotation) % 360
+        log.debug(
+            f"Text rotation: (text, autorotate, content) -> text misalignment = "
+            f"({text_rotation}, {autorotate_correction}, {content_rotation}) -> {text_misaligned}"
+        )
+
+        if textpdf and self.font:
+            # Graft the text layer onto this page, whether new or old, possibly
+            # rotating the text layer by the amount is misaligned.
+            strip_old = self.context.options.redo_ocr
+            self._graft_text_layer(
+                page_num=pageno + 1,
+                textpdf=textpdf,
+                font=self.font,
+                font_key=self.font_key,
+                text_rotation=text_misaligned,
+                procset=self.procset,
+                strip_old_text=strip_old,
+            )
+
+        # Correct the overall page rotation if needed, now that the text and content
+        # are aligned
+        page_rotation = (content_rotation - autorotate_correction) % 360
+        self.pdf_base.pages[pageno].Rotate = page_rotation
+        log.debug(
+            f"Page rotation: (content, auto) -> page = "
+            f"({content_rotation}, {autorotate_correction}) -> {page_rotation}"
+        )
+        if self.emplacements % MAX_REPLACE_PAGES == 0:
+            self.save_and_reload()
+
+    def save_and_reload(self):
+        """Save and reload the Pdf.
+
+        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_resources(
+            obj=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 updating
+        # {interim_count - 1} can be deleted
+        # {interim_count + 1} is the new file will produce and open
+        old_file = self.output_file.with_suffix(f'.working{self.interim_count - 1}.pdf')
+        if not self.context.options.keep_temporary_files:
+            with suppress(FileNotFoundError):
+                old_file.unlink()
+
+        next_file = self.output_file.with_suffix(
+            f'.working{self.interim_count + 1}.pdf'
+        )
+        self.pdf_base.save(next_file)
+        self.pdf_base.close()
+
+        self.pdf_base = Pdf.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
+
+    def _find_font(self, text):
+        """Copy a font from the filename text into pdf_base"""
+
+        font, font_key = None, None
+        possible_font_names = ('/f-0-0', '/F1')
+        try:
+            with Pdf.open(text) as pdf_text:
+                try:
+                    pdf_text_fonts = pdf_text.pages[0].Resources.get('/Font', {})
+                except (AttributeError, IndexError, KeyError):
+                    return None, None
+                pdf_text_font = 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 = self.pdf_base.copy_foreign(pdf_text_font)
+                return font, font_key
+        except (FileNotFoundError, PdfError):
+            # PdfError occurs if a 0-length file is written e.g. due to OCR timeout
+            return None, None
+
+    def _graft_text_layer(
+        self,
+        *,
+        page_num: int,
+        textpdf: Path,
+        font: Object,
+        font_key: Object,
+        procset: Object,
+        text_rotation: int,
+        strip_old_text: bool,
+    ):
+        """Insert the text layer from text page 0 on to pdf_base at page_num"""
+
+        # pylint: disable=invalid-name
+
+        log.debug("Grafting")
+        if Path(textpdf).stat().st_size == 0:
+            return
+
+        # This is a pointer indicating a specific page in the base file
+        with Pdf.open(textpdf) as pdf_text:
+            pdf_text_contents = pdf_text.pages[0].Contents.read_bytes()
+
+            base_page = self.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 = PdfMatrix().translated(-wt / 2, -ht / 2)
+            untranslate = PdfMatrix().translated(wp / 2, hp / 2)
+            corner = PdfMatrix().translated(mediabox[0], mediabox[1])
+            # -rotation because the input is a clockwise angle and this formula
+            # uses CCW
+            text_rotation = -text_rotation % 360
+            rotate = PdfMatrix().rotated(text_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 text_rotation in (90, 270):
+                wt, ht = ht, wt
+            scale_x = wp / wt
+            scale_y = hp / ht
+
+            # log.debug('%r', scale_x, scale_y)
+            scale = 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
+
+            base_resources = _ensure_dictionary(base_page, Name.Resources)
+            base_xobjs = _ensure_dictionary(base_resources, Name.XObject)
+            text_xobj_name = Name.random(prefix="OCR-")
+            xobj = self.pdf_base.make_stream(pdf_text_contents)
+            base_xobjs[text_xobj_name] = xobj
+            xobj.Type = Name.XObject
+            xobj.Subtype = Name.Form
+            xobj.FormType = 1
+            xobj.BBox = mediabox
+            _update_resources(
+                obj=xobj, font=font, font_key=font_key, procset=[Name.PDF]
+            )
+
+            pdf_draw_xobj = (
+                (b'q %s cm\n' % ctm.encode()) + (b'%s Do\n' % text_xobj_name) + b'\nQ\n'
+            )
+            new_text_layer = Stream(self.pdf_base, pdf_draw_xobj)
+
+            if strip_old_text:
+                strip_invisible_text(self.pdf_base, base_page)
+
+            base_page.contents_add(new_text_layer, prepend=True)
+
+            _update_resources(
+                obj=base_page, font=font, font_key=font_key, procset=procset
+            )

src/ocrmypdf/_jobcontext.py

@@ -0,0 +1,104 @@
+# © 2018 James R. Barlow: github.com/jbarlow83
+#
+# This Source Code Form is subject to the terms of the Mozilla Public
+# License, v. 2.0. If a copy of the MPL was not distributed with this
+# file, You can obtain one at http://mozilla.org/MPL/2.0/.
+
+"""Defines context objects that are passed to child processes/threads."""
+
+import os
+import shutil
+import sys
+from argparse import Namespace
+from copy import copy
+from pathlib import Path
+from typing import Iterator
+
+from pluggy import PluginManager
+
+from ocrmypdf.pdfinfo import PdfInfo
+from ocrmypdf.pdfinfo.info import PageInfo
+
+
+class PdfContext:
+    """Holds the context for a particular run of the pipeline."""
+
+    options: Namespace  #: The specified options for processing this PDF.
+    origin: Path  #: The filename of the original input file.
+    pdfinfo: PdfInfo  #: Detailed data for this PDF.
+    plugin_manager: PluginManager  #: PluginManager for processing the current PDF.
+
+    def __init__(
+        self,
+        options: Namespace,
+        work_folder: Path,
+        origin: Path,
+        pdfinfo: PdfInfo,
+        plugin_manager,
+    ):
+        self.options = options
+        self.work_folder = work_folder
+        self.origin = origin
+        self.pdfinfo = pdfinfo
+        self.plugin_manager = plugin_manager
+
+    def get_path(self, name: str) -> Path:
+        """Generate a ``Path`` for an intermediate file involved in processing.
+
+        The path will be in a temporary folder that is common for all processing
+        of this particular PDF.
+        """
+        return self.work_folder / name
+
+    def get_page_contexts(self) -> Iterator['PageContext']:
+        """Get all ``PageContext`` for this PDF."""
+        npages = len(self.pdfinfo)
+        for n in range(npages):
+            yield PageContext(self, n)
+
+
+class PageContext:
+    """Holds our context for a page.
+
+    Must be pickable, so stores only intrinsic/simple data elements or those
+    capable of their serializing themselves via ``__getstate__``.
+    """
+
+    options: Namespace  #: The specified options for processing this PDF.
+    origin: Path  #: The filename of the original input file.
+    pageno: int  #: This page number (zero-based).
+    pageinfo: PageInfo  #: Information on this page.
+    plugin_manager: PluginManager  #: PluginManager for processing the current PDF.
+
+    def __init__(self, pdf_context: PdfContext, pageno):
+        self.work_folder = pdf_context.work_folder
+        self.origin = pdf_context.origin
+        self.options = pdf_context.options
+        self.pageno = pageno
+        self.pageinfo = pdf_context.pdfinfo[pageno]
+        self.plugin_manager = pdf_context.plugin_manager
+
+    def get_path(self, name: str) -> Path:
+        """Generate a ``Path`` for a file that is part of processing this page.
+
+        The path will be based in a common temporary folder and have a prefix based
+        on the page number.
+        """
+        return self.work_folder / f"{(self.pageno + 1):06d}_{name}"
+
+    def __getstate__(self):
+        state = self.__dict__.copy()
+
+        state['options'] = copy(self.options)
+        if not isinstance(state['options'].input_file, (str, bytes, os.PathLike)):
+            state['options'].input_file = 'stream'
+        if not isinstance(state['options'].output_file, (str, bytes, os.PathLike)):
+            state['options'].output_file = 'stream'
+        return state
+
+
+def cleanup_working_files(work_folder: Path, options: Namespace):
+    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)

src/ocrmypdf/_logging.py

@@ -0,0 +1,44 @@
+# © 2020 James R. Barlow: github.com/jbarlow83
+#
+# This Source Code Form is subject to the terms of the Mozilla Public
+# License, v. 2.0. If a copy of the MPL was not distributed with this
+# file, You can obtain one at http://mozilla.org/MPL/2.0/.
+
+"""Logging support classes."""
+
+import logging
+from contextlib import suppress
+
+from tqdm import tqdm
+
+
+class PageNumberFilter(logging.Filter):
+    """Insert PDF page number that emitted log message to log record."""
+
+    def filter(self, record):
+        pageno = getattr(record, 'pageno', None)
+        if isinstance(pageno, int):
+            record.pageno = f'{pageno:5d} '
+        elif pageno is None:
+            record.pageno = ''
+        return True
+
+
+class TqdmConsole:
+    """Wrapper to log messages in a way that is compatible with tqdm progress bar
+
+    This routes log messages through tqdm so that it can print them above the
+    progress bar, and then refresh the progress bar, rather than overwriting
+    it which looks messy.
+    """
+
+    def __init__(self, file):
+        self.file = file
+
+    def write(self, msg):
+        # When no progress bar is active, tqdm.write() routes to print()
+        tqdm.write(msg.rstrip(), end='\n', file=self.file)
+
+    def flush(self):
+        with suppress(AttributeError):
+            self.file.flush()