Improve find expressions/options

This file is a bloody workaround.  AppImages require a dir icon.
When started to build this AppImage there was no logo at the github repo of OCRmyPDF.
Now the build script uses/converts the OCRmyPDF logo to use it as dir icon.

.docker/Dockerfile

@@ -1,89 +0,0 @@
-# SPDX-FileCopyrightText: 2022 James R. Barlow
-# SPDX-License-Identifier: MPL-2.0
-
-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 \
-  libcairo2-dev \
-  pkg-config
-
-# 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
-
-# For Tesseract 5
-RUN apt-get update && apt-get install -y --no-install-recommends \
-  software-properties-common gpg-agent
-RUN add-apt-repository -y ppa:alex-p/tesseract-ocr-devel
-
-RUN apt-get update && apt-get install -y --no-install-recommends \
-  ghostscript \
-  fonts-droid-fallback \
-  jbig2dec \
-  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/pyproject.toml /app/README.md /app/
-COPY --from=builder /app/tests /app/tests
-
-ENTRYPOINT ["/usr/local/bin/ocrmypdf"]

.docker/Dockerfile.alpine

@@ -1,83 +0,0 @@
-# SPDX-FileCopyrightText: 2023 James R. Barlow
-# SPDX-License-Identifier: MPL-2.0
-
-FROM alpine:3.18 as base
-
-ENV LANG=C.UTF-8
-ENV TZ=UTC
-
-RUN apk add --no-cache \
-    python3 \
-    zlib
-
-FROM base as builder
-
-RUN apk add --no-cache \
-    ca-certificates \
-    git \
-    python3-dev \
-    py3-pip
-
-# On arm64, we need to build cffi from source.
-ARG TARGETPLATFORM
-
-RUN if [ "${TARGETPLATFORM}" == "linux/arm64" ]; then \
-    apk add --no-cache \
-    build-base \
-    autoconf \
-    automake \
-    libtool \
-    zlib-dev \
-    libffi-dev \
-    cairo-dev \
-    pkgconfig \
-    ;  \
-    fi
-
-COPY . /app
-
-WORKDIR /app
-
-RUN python3 -m venv .venv
-
-RUN source .venv/bin/activate \
-    && python3 -m pip install --no-cache-dir --upgrade pip \
-    && python3 -m pip install --no-cache-dir wheel \
-    && python3 -m pip install --no-cache-dir .[test,webservice,watcher]
-
-FROM base
-
-RUN apk add --no-cache \
-    ghostscript \
-    jbig2dec \
-    jbig2enc \
-    pngquant \
-    tesseract-ocr \
-    tesseract-ocr-data-chi_sim \
-    tesseract-ocr-data-deu \
-    tesseract-ocr-data-eng \
-    tesseract-ocr-data-fra \
-    tesseract-ocr-data-osd \
-    tesseract-ocr-data-por \
-    tesseract-ocr-data-spa \
-    ttf-droid \
-    unpaper \
-    && rm -rf /var/cache/apk/*
-
-WORKDIR /app
-
-COPY --from=builder /usr/local/lib/ /usr/local/lib/
-COPY --from=builder /usr/local/bin/ /usr/local/bin/
-
-COPY --from=builder /app/.venv/ /app/.venv/
-
-COPY --from=builder /app/misc/webservice.py /app/
-COPY --from=builder /app/misc/watcher.py /app/
-
-# Copy minimal project files to get the test suite.
-COPY --from=builder /app/pyproject.toml /app/README.md /app/
-COPY --from=builder /app/tests /app/tests
-
-ENV PATH="/app/.venv/bin:${PATH}"
-
-ENTRYPOINT ["/app/.venv/bin/ocrmypdf"]

.dockerignore

@@ -1,47 +0,0 @@
-# SPDX-FileCopyrightText: 2022 James R. Barlow
-# SPDX-License-Identifier: MPL-2.0
-
-# dotfiles
-.*
-!.coveragerc
-!.dockerignore
-!.git_archival.txt
-!.gitattributes
-!.gitignore
-!.pre-commit-config.yaml
-!.readthedocs.yml
-
-# Dev scratch
-*.ipynb
-**/*.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/

.git_archival.txt

@@ -1,4 +0,0 @@
-node: $Format:%H$
-node-date: $Format:%cI$
-describe-name: $Format:%(describe:tags=true)$
-ref-names: $Format:%D$

.gitattributes

@@ -1,17 +0,0 @@
-# SPDX-FileCopyrightText: 2022 James R. Barlow
-# SPDX-License-Identifier: MPL-2.0
-
-# Always use Unix convention for new lines
-* text eol=lf
-
-# These files are binary and should be left untouched
-# (binary is a macro for -text -diff)
-*.jar	binary
-*.pdf	binary
-*.PDF	binary
-*.png	binary
-*.jpg	binary
-*.bin   binary
-*.afdesign  binary
-
-.git_archival.txt  export-subst

.github/FUNDING.yml

@@ -1,15 +0,0 @@
-# SPDX-FileCopyrightText: 2022 James R. Barlow
-# SPDX-License-Identifier: MPL-2.0
-
-# 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-bug-report-general.yml

@@ -1,51 +0,0 @@
-name: General issues
-description: Installation, packages, dependencies, "nothing works", test suite failures...
-title: "[Bug]: "
-labels: ["bug", "triage"]
-assignees:
-  - jbarlow83
-body:
-  - type: markdown
-    attributes:
-      value: |
-        Thanks for taking the time to fill out this bug report!
-  - type: textarea
-    id: what-happened
-    attributes:
-      label: What were you trying to do?
-      description: Also tell us, what did you expect to happen?
-      placeholder: Tell us what you see!
-    validations:
-      required: true
-  - type: dropdown
-    id: packaging-system
-    attributes:
-      label: Where are you installing from?
-      multiple: true
-      options:
-        - PyPI (pip, poetry, pipx, etc.)
-        - Linux package manager (apt, dnf, etc.)
-        - Wndows package manager (chocolatey, etc.)
-        - Homebrew
-        - Docker container
-        - Ubuntu snap
-        - Conda
-        - source build
-    validations:
-      required: true
-  - type: dropdown
-    id: operating-system
-    attributes:
-      label: What operating system are you working on?
-      multiple: true
-      options:
-        - Linux
-        - Windows
-        - macOS
-        - BSD
-  - type: textarea
-    id: logs
-    attributes:
-      label: Relevant log output
-      description: Please copy and paste any relevant log output. This will be automatically formatted into code, so no need for backticks.
-      render: plain text

.github/ISSUE_TEMPLATE/2-problem-with-specific-file.yml

@@ -1,62 +0,0 @@
-name: Problem with specific file
-description: Something went wrong while trying to OCR a specific file
-title: "[Bug]: "
-labels: ["bug", "triage"]
-assignees:
-  - jbarlow83
-body:
-  - type: markdown
-    attributes:
-      value: |
-        Thanks for taking the time to describe this issue with a particular file.
-  - type: textarea
-    id: what-happened
-    attributes:
-      label: Describe the bug
-      description: A clear and concise description of what the bug is.
-      placeholder: Tell us what you see!
-    validations:
-      required: true
-  - type: textarea
-    id: reproduce
-    attributes:
-      label: Steps to reproduce
-      description: Please include steps to reproduce
-      value: |
-        1. Run ocrmypdf -v1 ...arguments... input.pdf output.pdf
-        2. Open output.pdf
-        3. ...
-      render: plain text
-  - type: textarea
-    id: files
-    attributes:
-      label: Files
-      description: Please attach the input and output files, or any screenshots that may be helpful.
-      placeholder: Drag and drop files here
-  - type: dropdown
-    id: packaging-system
-    attributes:
-      label: How did you download and install the software?
-      multiple: true
-      options:
-        - PyPI (pip, poetry, pipx, etc.)
-        - Linux package manager (apt, dnf, etc.)
-        - Windows package manager (chocolatey, etc.)
-        - Homebrew
-        - Docker container
-        - Ubuntu snap
-        - Conda
-        - source build
-  - type: input
-    id: version
-    attributes:
-      label: OCRmyPDF version
-      description: Paste "ocrmypdf --version" here
-      placeholder: ocrmypdf --version
-  - type: textarea
-    id: logs
-    attributes:
-      label: Relevant log output
-      description: Please copy and paste any relevant log output. This will be automatically formatted into code, so no need for backticks.
-      placeholder: Run OCRmyPDF with verbosity `-v1` to get more detailed logging output.
-      render: plain text

.github/ISSUE_TEMPLATE/3-feature-request.yml

@@ -1,12 +0,0 @@
-name: Feature request
-description: Suggest an idea for this project
-title: "[Feature]: "
-labels: ["enhancement", "triage"]
-assignees:
-  - jbarlow83
-body:
-  - type: textarea
-    id: feature
-    attributes:
-      label: Describe the proposed feature
-      description: A clear and concise description of what the desired is.

.github/dependabot.yml

@@ -1,14 +0,0 @@
-# SPDX-FileCopyrightText: 2022 James R. Barlow
-# SPDX-License-Identifier: MPL-2.0
-
-# To get started with Dependabot version updates, you'll need to specify which
-# package ecosystems to update and where the package manifests are located.
-# Please see the documentation for all configuration options:
-# https://docs.github.com/github/administering-a-repository/configuration-options-for-dependency-updates
-
-version: 2
-updates:
-  - package-ecosystem: "github-actions" # See documentation for possible values
-    directory: "/" # Location of package manifests
-    schedule:
-      interval: "weekly"

.github/workflows/build.yml

@@ -1,370 +0,0 @@
-# SPDX-FileCopyrightText: 2022 James R. Barlow
-# SPDX-License-Identifier: MPL-2.0
-name: Test and deploy
-
-on:
-  push:
-    branches:
-      - main
-      - 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-22.04
-            python: "3.10"
-          - os: ubuntu-22.04
-            python: "3.11"
-          - os: ubuntu-22.04
-            python: "3.10"
-            tesseract5: true
-          - os: ubuntu-latest
-            python: "3.12"
-            tesseract5: true
-          # - os: ubuntu-latest
-          #   python: "pypy3.10"
-
-    env:
-      OS: ${{ matrix.os }}
-      PYTHON: ${{ matrix.python }}
-
-    steps:
-      - uses: actions/checkout@v4
-        with:
-          fetch-depth: "0" # 0=all, needed for setuptools-scm to resolve version tags
-
-      - uses: actions/setup-python@v4
-        name: Setup Python
-        with:
-          python-version: ${{ matrix.python }}
-          cache: "pip"
-
-      - name: Install Tesseract 5
-        if: matrix.tesseract5
-        run: |
-          sudo add-apt-repository -y 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 \
-            libexempi8 \
-            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 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 --prefer-binary .[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@v3
-        with:
-          files: ./coverage.xml
-          env_vars: OS,PYTHON
-
-  test_macos:
-    name: Test macOS
-    runs-on: ${{ matrix.os }}
-    strategy:
-      matrix:
-        os: [macos-latest]
-        python: ["3.10", "3.11", "3.12"]
-
-    env:
-      OS: ${{ matrix.os }}
-      PYTHON: ${{ matrix.python }}
-
-    steps:
-      - uses: actions/checkout@v4
-        with:
-          fetch-depth: "0" # 0=all, needed for setuptools-scm to resolve version tags
-
-      - name: Install Homebrew deps
-        continue-on-error: true
-        run: |
-          brew update
-          brew install \
-            exempi \
-            ghostscript \
-            jbig2enc \
-            openjpeg \
-            openssl \
-            pngquant \
-            tesseract
-
-      - uses: actions/setup-python@v4
-        name: Setup Python
-        with:
-          python-version: ${{ matrix.python }}
-          cache: "pip"
-
-      - name: Install Python packages
-        run: |
-          python -m pip install --upgrade pip wheel
-          python -m pip install --prefer-binary .[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@v3
-        with:
-          files: ./coverage.xml
-          env_vars: OS,PYTHON
-
-  test_windows:
-    name: Test Windows
-    runs-on: ${{ matrix.os }}
-    strategy:
-      matrix:
-        os: [windows-latest]
-        python: ["3.10", "3.11", "3.12"]
-
-    env:
-      OS: ${{ matrix.os }}
-      PYTHON: ${{ matrix.python }}
-
-    steps:
-      - uses: actions/checkout@v4
-        with:
-          fetch-depth: "0" # 0=all, needed for setuptools-scm to resolve version tags
-
-      - uses: actions/setup-python@v4
-        name: Setup Python
-        with:
-          python-version: ${{ matrix.python }}
-          cache: "pip"
-
-      - 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 --prefer-binary .[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@v3
-        with:
-          files: ./coverage.xml
-          env_vars: OS,PYTHON
-
-  wheel_sdist_linux:
-    name: Build sdist and wheels
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@v4
-        with:
-          fetch-depth: "0" # 0=all, needed for setuptools-scm to resolve version tags
-
-      - uses: actions/setup-python@v4
-        name: Setup Python
-        with:
-          python-version: "3.10"
-          cache: "pip"
-
-      - name: Make wheels and sdist
-        run: |
-          python -m pip install --upgrade pip wheel build
-          python -m build --sdist --wheel
-
-      - uses: actions/upload-artifact@v3
-        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
-    environment: release
-    permissions:
-      id-token: write  # mandatory for PyPI publishing
-    if: github.event_name == 'push' && startsWith(github.event.ref, 'refs/tags/v')
-    steps:
-      - uses: actions/download-artifact@v3
-        with:
-          name: artifact
-          path: dist
-
-      - name: Publish to PyPI
-        uses: pypa/gh-action-pypi-publish@release/v1
-
-  create_release:
-    name: Create GitHub release
-    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')
-    permissions:
-      # Required to create a release
-      contents: write
-    steps:
-      - uses: actions/download-artifact@v3
-        with:
-          name: artifact
-          path: dist
-
-      - name: Create Release
-        id: create-release
-        uses: shogo82148/actions-create-release@v1
-
-      - name: Upload Assets
-        uses: shogo82148/actions-upload-release-asset@v1
-        with:
-          upload_url: ${{ steps.create-release.outputs.upload_url }}
-          asset_path: |
-            ./dist/*.whl
-            ./dist/*.tar.gz
-
-  docker_ubuntu:
-    name: Build Ubuntu-based Docker image
-    needs: [wheel_sdist_linux, test_linux, test_macos, test_windows]
-    runs-on: ubuntu-latest
-    if: github.event_name != 'pull_request'
-    steps:
-      - name: Set image tag to release or branch
-        run: echo "DOCKER_IMAGE_TAG=${GITHUB_REF##*/}" >> $GITHUB_ENV
-
-      - name: If main, set to latest
-        run: echo 'DOCKER_IMAGE_TAG=latest' >> $GITHUB_ENV
-        if: env.DOCKER_IMAGE_TAG == 'main'
-
-      - 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@v4
-        with:
-          fetch-depth: "0" # 0=all, needed for setuptools-scm to resolve version tags
-
-      - name: Login to Docker Hub
-        uses: docker/login-action@v3
-        with:
-          username: jbarlow83
-          password: ${{ secrets.DOCKERHUB_TOKEN }}
-
-      - name: Set up QEMU
-        uses: docker/setup-qemu-action@v3
-
-      - name: Set up Docker Buildx
-        id: buildx
-        uses: docker/setup-buildx-action@v3
-
-      - 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}" \
-            --tag "${DOCKER_REPOSITORY}/${DOCKER_IMAGE_NAME}-ubuntu:${DOCKER_IMAGE_TAG}" \
-            --file .docker/Dockerfile .
-
-  docker_alpine:
-    name: Build Alpine-based Docker images
-    needs: [wheel_sdist_linux, test_linux, test_macos, test_windows]
-    runs-on: ubuntu-latest
-    if: github.event_name != 'pull_request'
-    steps:
-      - name: Set image tag to release or branch
-        run: echo "DOCKER_IMAGE_TAG=${GITHUB_REF##*/}" >> $GITHUB_ENV
-
-      - name: If main, set to latest
-        run: echo 'DOCKER_IMAGE_TAG=latest' >> $GITHUB_ENV
-        if: env.DOCKER_IMAGE_TAG == 'main'
-
-      - name: Set Docker Hub repository to username
-        run: echo "DOCKER_REPOSITORY=jbarlow83" >> $GITHUB_ENV
-
-      - name: Set image name
-        run: echo "DOCKER_IMAGE_NAME=ocrmypdf-alpine" >> $GITHUB_ENV
-
-      - uses: actions/checkout@v4
-        with:
-          fetch-depth: "0" # 0=all, needed for setuptools-scm to resolve version tags
-
-      - name: Login to Docker Hub
-        uses: docker/login-action@v3
-        with:
-          username: jbarlow83
-          password: ${{ secrets.DOCKERHUB_TOKEN }}
-
-      - name: Set up QEMU
-        uses: docker/setup-qemu-action@v3
-
-      - name: Set up Docker Buildx
-        id: buildx
-        uses: docker/setup-buildx-action@v3
-
-      - name: Print image tag
-        run: echo "Building image ${DOCKER_REPOSITORY}/${DOCKER_IMAGE_NAME}:${DOCKER_IMAGE_TAG}"
-
-      - name: Build
-        run: |
-          docker buildx build \
-            --push \
-            --platform linux/amd64  \
-            --tag "${DOCKER_REPOSITORY}/${DOCKER_IMAGE_NAME}:${DOCKER_IMAGE_TAG}" \
-            --file .docker/Dockerfile.alpine .

.gitignore

@@ -1,46 +0,0 @@
-# SPDX-FileCopyrightText: 2022 James R. Barlow
-# SPDX-License-Identifier: CC-BY-SA-4.0
-
-# dotfiles
-.coverage
-.venv*/
-.tox/
-.vscode/
-.hypothesis/
-.ipynb_checkpoints/
-.mypy_cache/
-.pytest_cache/
-
-# Dev scratch
-*.ipynb
-**/*.pyc
-/*.pdf
-/*.qdf
-/*.png
-/scratch.py
-IDEAS
-log/
-tests/resources/private/
-tmp/
-venv*/
-/debug_tests.py
-*.traineddata
-/private
-/coverage.xml
-/issuepdf
-
-# Package building
-*.egg-info/
-build/
-dist/
-wheelhouse/
-pip-wheel-metadata/
-
-# Code coverage
-htmlcov/
-
-# Automatically generated files
-docs/_build/
-docs/_static/
-docs/_templates/
-docs/Makefile

.pre-commit-config.yaml

@@ -1,32 +0,0 @@
-# SPDX-FileCopyrightText: 2022 James R. Barlow
-# SPDX-License-Identifier: MPL-2.0
-
-repos:
-  - repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v4.4.0
-    hooks:
-      - id: check-case-conflict
-      - id: check-merge-conflict
-      - id: check-toml
-      - id: check-yaml
-      - id: debug-statements
-  - repo: https://github.com/charliermarsh/ruff-pre-commit
-    rev: "v0.0.261"
-    hooks:
-      - id: ruff
-        files: "src/.*\\.pyi?$"
-        args: [--fix, --exit-non-zero-on-fix]
-  - repo: https://github.com/psf/black
-    rev: 23.3.0
-    hooks:
-      - id: black
-        language_version: python
-  - repo: https://github.com/pre-commit/mirrors-mypy
-    rev: v1.2.0
-    hooks:
-      - id: mypy
-        additional_dependencies:
-          - types-toml
-          - types-setuptools
-          - types-requests
-          - types-Pillow

.readthedocs.yaml

@@ -1,29 +0,0 @@
-# SPDX-FileCopyrightText: 2022 James R. Barlow
-# SPDX-License-Identifier: MPL-2.0
-
-# 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
-build:
-  os: ubuntu-22.04
-  tools:
-    python: "3.10"
-
-python:
-  install:
-    - method: pip
-      path: .
-      extra_requirements:
-        - docs

.reuse/dep5

@@ -1,140 +0,0 @@
-Format: https://www.debian.org/doc/packaging-manuals/copyright-format/1.0/
-Upstream-Name: OCRmyPDF
-Upstream-Contact: James R. Barlow <james@purplerock.ca>
-Source: https://github.com/ocrmypdf/OCRmyPDF
-
-Files:
- .git_archival.txt
- docs/images/logo-social.png
- docs/images/logo-square-256.svg
- docs/images/logo-square.png
- docs/images/logo-square.svg
- docs/images/logo.svg
-Copyright: (C) 2022 James R. Barlow
-License: MPL-2.0
-
-Files:
- .github/ISSUE_TEMPLATE/*.yml
- docs/images/macos-workflow.png
-Copyright: (C) 2023 James R. Barlow
-License: CC-BY-SA-4.0
-
-Files:
- tests/resources/acroform.pdf
- tests/resources/aspect.pdf
- tests/resources/blank.pdf
- tests/resources/cmyk.pdf
- tests/resources/crom.png
- tests/resources/enormous.pdf
- tests/resources/formxobject.pdf
- tests/resources/francais.pdf
- tests/resources/hugemono.pdf
- tests/resources/invalid.pdf
- tests/resources/kcs.pdf
- tests/resources/livecycle.pdf
- tests/resources/meta.pdf
- tests/resources/missing_docinfo.pdf
- tests/resources/negzero.pdf
- tests/resources/no_contents.pdf
- tests/resources/tagged*
- tests/resources/toc.pdf
- tests/resources/trivial.pdf
- tests/resources/truetype_font_nomapping.pdf
- tests/resources/type3_font_nomapping.pdf
-Copyright: (C) 2023 James R. Barlow
-License: CC-BY-SA-4.0
-
-Files:
- tests/resources/graph.pdf
- tests/resources/graph_ocred.pdf
-Copyright: (C) 2012 SmokeyJoe
-License: GFDL-1.2-or-later or CC-BY-SA-3.0
-
-Files: tests/resources/c02-22.pdf
- tests/resources/multipage.pdf
-Copyright: Public domain
-License: public-domain
- Copyright on these files has expired.
-
-Files: docs/images/bitmap_vs_svg.svg
-Copyright: (C) 2006 Yug
-License: CC-BY-SA-2.5
-
-Files: tests/cache/*
-Copyright: (C) 2022 James R. Barlow
-License: CC-BY-SA-4.0
-
-Files: tests/resources/linn.png
- tests/resources/linn.pdf
- tests/resources/linn.txt
- tests/resources/ccitt.pdf
- tests/resources/cardinal.pdf
- tests/resources/jbig2.pdf
- tests/resources/jbig2_baddevicen.pdf
- tests/resources/skew.pdf
- tests/resources/rotated_skew.pdf
- tests/resources/poster.pdf
-Copyright: (C) 1985 Forat Electronics
-License: GFDL-1.2-or-later or CC-BY-SA-3.0
-
-Files: tests/resources/lichtenstein.pdf
-Copyright: (C) 2001 Andreas Tille
- (C) 2007 Alessio Damato
-License: GFDL-1.2-or-later or CC-BY-SA-3.0
-
-Files: tests/resources/masks.pdf
-Copyright: held by the contributors to the German Wikipedia article "Linux"
- see: https://de.wikipedia.org/w/index.php?title=Linux&action=history
- (masks.pdf generated from Wikipedia article as of 2016-08-24)
-License: CC-BY-SA-3.0
-
-Files: tests/resources/epson.pdf
-Copyright: held by the contributors to the Wikipedia article "Optical character recognition"
- see: https://en.wikipedia.org/w/index.php?title=Optical_character_recognition&action=history
- (epson.pdf generated from Wikipedia article as of 2016-09-14)
-License: CC-BY-SA-3.0
-
-Files: tests/resources/typewriter.png tests/resources/2400dpi.pdf
-Copyright: (C) 2005 Ellywa
-License: GFDL-1.2-or-later or CC-BY-SA-1.0 or CC-BY-SA-2.0 or CC-BY-SA-2.5 or CC-BY-SA-3.0
-Comment:
- Obtained from: https://commons.wikimedia.org/wiki/File:Triumph.typewriter_text_Linzensoep.gif
-
-Files: tests/resources/overlay.pdf
-Copyright: (C) 2017 Max Anderson
-License: MIT
-
-Files:
- tests/resources/baiona*.png
- tests/resources/baiona*.jpg
- tests/resources/link.pdf
- tests/resources/palette.pdf
-Copyright: (C) 2014 Euskaldunaa
-License: CC-BY-SA-4.0
-
-Files: tests/resources/vector.pdf
-Copyright: (C) 2018 Catscratch
-License: MIT
-
-Files: src/ocrmypdf/data/sRGB.icc
-Copyright:  Kai-Uwe Behrmann <www.behrmann.name>
-            Marti Maria <www.littlecms.com>
-            Photogamut <www.photogamut.org>
-            Graeme Gill <www.argyllcms.com>
-            ColorSolutions <www.basICColor.com>
-License: Zlib
-
-Files: src/ocrmypdf/data/pdf.ttf
-Copyright: (C) 2014 Ray Smith
- (C) 2015 Ken Sharp
- (C) 2016 James R. Barlow
- (C) 2016 Jeff Breidenbach
- (C) 2017 Zdenko Podobný
-License: Apache-2.0
-
-Files: tests/resources/3small.pdf
-Copyright: (C) 2014 Euskaldunaa
- (C) 2017 James R. Barlow
- (C) 2005 Ellywa
-License: CC-BY-SA-4.0 and (GFDL-1.2-or-later or CC-BY-SA-1.0 or CC-BY-SA-2.0 or CC-BY-SA-2.5 or CC-BY-SA-3.0)
-Comment: concatenation of baiona_gray.png, crom.png and typewriter.png/2400dpi.pdf

.travis.yml

@@ -0,0 +1,29 @@
+
+language: generic
+sudo: required
+dist: trusty
+
+before_install:
+  - sudo add-apt-repository ppa:heyarje/libav-11 -y
+  - sudo add-apt-repository ppa:alex-p/tesseract-ocr -y
+  - sudo add-apt-repository ppa:evl.ms/evil -y  # for a newer version (2.5.0) of pngquant
+  - sudo apt-get update -qq
+  - sudo apt-get install libleptonica-dev -y    # required to build jbig2enc
+  - sudo apt-get install zlib1g-dev -y          # required to build jbig2enc
+ # - sudo apt-get install imagemagick -y         # required to convert logo to desktop icon
+
+script:
+  - export OCRMYPDF_VERSION=8.3.2
+  - bash build-appimage.sh
+  # remove previous installed libraries to ensure that the tests use the libraries of the AppImage
+  - sudo apt-get remove libleptonica-dev zlib1g-dev -y
+  - bash test/test-appimage.sh
+  - wget https://github.com/probonopd/uploadtool/raw/master/upload.sh
+
+after_success:
+  - bash upload.sh OCRmyPDF*.AppImage
+
+branches:
+  except:
+    # Do not build tags that we create when we upload to GitHub Releases
+    - /^(?i:continuous)/

LICENSE

@@ -1,373 +0,0 @@
-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.

LICENSES/AGPL-3.0-or-later.txt

@@ -1,235 +0,0 @@
-GNU AFFERO GENERAL PUBLIC LICENSE
-Version 3, 19 November 2007
-
-Copyright (C) 2007 Free Software Foundation, Inc. <http://fsf.org/>
-
-Everyone is permitted to copy and distribute verbatim copies of this license document, but changing it is not allowed.
-
-                            Preamble
-
-The GNU Affero General Public License is a free, copyleft license for software and other kinds of works, specifically designed to ensure cooperation with the community in the case of network server software.
-
-The licenses for most software and other practical works are designed to take away your freedom to share and change the works.  By contrast, our General Public Licenses are intended to guarantee your freedom to share and change all versions of a program--to make sure it remains free software for all its users.
-
-When we speak of free software, we are referring to freedom, not price.  Our General Public Licenses are designed to make sure that you have the freedom to distribute copies of free software (and charge for them if you wish), that you receive source code or can get it if you want it, that you can change the software or use pieces of it in new free programs, and that you know you can do these things.
-
-Developers that use our General Public Licenses protect your rights with two steps: (1) assert copyright on the software, and (2) offer you this License which gives you legal permission to copy, distribute and/or modify the software.
-
-A secondary benefit of defending all users' freedom is that improvements made in alternate versions of the program, if they receive widespread use, become available for other developers to incorporate.  Many developers of free software are heartened and encouraged by the resulting cooperation.  However, in the case of software used on network servers, this result may fail to come about. The GNU General Public License permits making a modified version and letting the public access it on a server without ever releasing its source code to the public.
-
-The GNU Affero General Public License is designed specifically to ensure that, in such cases, the modified source code becomes available to the community.  It requires the operator of a network server to provide the source code of the modified version running there to the users of that server.  Therefore, public use of a modified version, on a publicly accessible server, gives the public access to the source code of the modified version.
-
-An older license, called the Affero General Public License and published by Affero, was designed to accomplish similar goals.  This is a different license, not a version of the Affero GPL, but Affero has released a new version of the Affero GPL which permits relicensing under this license.
-
-The precise terms and conditions for copying, distribution and modification follow.
-
-                       TERMS AND CONDITIONS
-
-0. Definitions.
-
-"This License" refers to version 3 of the GNU Affero General Public License.
-
-"Copyright" also means copyright-like laws that apply to other kinds of works, such as semiconductor masks.
-
-"The Program" refers to any copyrightable work licensed under this License.  Each licensee is addressed as "you".  "Licensees" and "recipients" may be individuals or organizations.
-
-To "modify" a work means to copy from or adapt all or part of the work in a fashion requiring copyright permission, other than the making of an exact copy.  The resulting work is called a "modified version" of the earlier work or a work "based on" the earlier work.
-
-A "covered work" means either the unmodified Program or a work based on the Program.
-
-To "propagate" a work means to do anything with it that, without permission, would make you directly or secondarily liable for infringement under applicable copyright law, except executing it on a computer or modifying a private copy.  Propagation includes copying, distribution (with or without modification), making available to the public, and in some countries other activities as well.
-
-To "convey" a work means any kind of propagation that enables other parties to make or receive copies.  Mere interaction with a user through a computer network, with no transfer of a copy, is not conveying.
-
-An interactive user interface displays "Appropriate Legal Notices" to the extent that it includes a convenient and prominently visible feature that (1) displays an appropriate copyright notice, and (2) tells the user that there is no warranty for the work (except to the extent that warranties are provided), that licensees may convey the work under this License, and how to view a copy of this License.  If the interface presents a list of user commands or options, such as a menu, a prominent item in the list meets this criterion.
-
-1. Source Code.
-The "source code" for a work means the preferred form of the work for making modifications to it.  "Object code" means any non-source form of a work.
-
-A "Standard Interface" means an interface that either is an official standard defined by a recognized standards body, or, in the case of interfaces specified for a particular programming language, one that is widely used among developers working in that language.
-
-The "System Libraries" of an executable work include anything, other than the work as a whole, that (a) is included in the normal form of packaging a Major Component, but which is not part of that Major Component, and (b) serves only to enable use of the work with that Major Component, or to implement a Standard Interface for which an implementation is available to the public in source code form.  A "Major Component", in this context, means a major essential component (kernel, window system, and so on) of the specific operating system (if any) on which the executable work runs, or a compiler used to produce the work, or an object code interpreter used to run it.
-
-The "Corresponding Source" for a work in object code form means all the source code needed to generate, install, and (for an executable work) run the object code and to modify the work, including scripts to control those activities.  However, it does not include the work's System Libraries, or general-purpose tools or generally available free programs which are used unmodified in performing those activities but which are not part of the work.  For example, Corresponding Source includes interface definition files associated with source files for the work, and the source code for shared libraries and dynamically linked subprograms that the work is specifically designed to require, such as by intimate data communication or control flow between those
-subprograms and other parts of the work.
-
-The Corresponding Source need not include anything that users can regenerate automatically from other parts of the Corresponding Source.
-
-The Corresponding Source for a work in source code form is that same work.
-
-2. Basic Permissions.
-All rights granted under this License are granted for the term of copyright on the Program, and are irrevocable provided the stated conditions are met.  This License explicitly affirms your unlimited permission to run the unmodified Program.  The output from running a covered work is covered by this License only if the output, given its content, constitutes a covered work.  This License acknowledges your rights of fair use or other equivalent, as provided by copyright law.
-
-You may make, run and propagate covered works that you do not convey, without conditions so long as your license otherwise remains in force.  You may convey covered works to others for the sole purpose of having them make modifications exclusively for you, or provide you with facilities for running those works, provided that you comply with the terms of this License in conveying all material for which you do not control copyright.  Those thus making or running the covered works for you must do so exclusively on your behalf, under your direction and control, on terms that prohibit them from making any copies of your copyrighted material outside their relationship with you.
-
-Conveying under any other circumstances is permitted solely under the conditions stated below.  Sublicensing is not allowed; section 10 makes it unnecessary.
-
-3. Protecting Users' Legal Rights From Anti-Circumvention Law.
-No covered work shall be deemed part of an effective technological measure under any applicable law fulfilling obligations under article 11 of the WIPO copyright treaty adopted on 20 December 1996, or similar laws prohibiting or restricting circumvention of such measures.
-
-When you convey a covered work, you waive any legal power to forbid circumvention of technological measures to the extent such circumvention is effected by exercising rights under this License with respect to the covered work, and you disclaim any intention to limit operation or modification of the work as a means of enforcing, against the work's users, your or third parties' legal rights to forbid circumvention of technological measures.
-
-4. Conveying Verbatim Copies.
-You may convey verbatim copies of the Program's source code as you receive it, in any medium, provided that you conspicuously and appropriately publish on each copy an appropriate copyright notice; keep intact all notices stating that this License and any non-permissive terms added in accord with section 7 apply to the code; keep intact all notices of the absence of any warranty; and give all recipients a copy of this License along with the Program.
-
-You may charge any price or no price for each copy that you convey, and you may offer support or warranty protection for a fee.
-
-5. Conveying Modified Source Versions.
-You may convey a work based on the Program, or the modifications to produce it from the Program, in the form of source code under the terms of section 4, provided that you also meet all of these conditions:
-
-    a) The work must carry prominent notices stating that you modified it, and giving a relevant date.
-
-    b) The work must carry prominent notices stating that it is released under this License and any conditions added under section 7.  This requirement modifies the requirement in section 4 to "keep intact all notices".
-
-    c) You must license the entire work, as a whole, under this License to anyone who comes into possession of a copy.  This License will therefore apply, along with any applicable section 7 additional terms, to the whole of the work, and all its parts, regardless of how they are packaged.  This License gives no permission to license the work in any other way, but it does not invalidate such permission if you have separately received it.
-
-    d) If the work has interactive user interfaces, each must display Appropriate Legal Notices; however, if the Program has interactive interfaces that do not display Appropriate Legal Notices, your work need not make them do so.
-
-A compilation of a covered work with other separate and independent works, which are not by their nature extensions of the covered work, and which are not combined with it such as to form a larger program, in or on a volume of a storage or distribution medium, is called an "aggregate" if the compilation and its resulting copyright are not used to limit the access or legal rights of the compilation's users beyond what the individual works permit.  Inclusion of a covered work in an aggregate does not cause this License to apply to the other parts of the aggregate.
-
-6. Conveying Non-Source Forms.
-You may convey a covered work in object code form under the terms of sections 4 and 5, provided that you also convey the machine-readable Corresponding Source under the terms of this License, in one of these ways:
-
-    a) Convey the object code in, or embodied in, a physical product (including a physical distribution medium), accompanied by the Corresponding Source fixed on a durable physical medium customarily used for software interchange.
-
-    b) Convey the object code in, or embodied in, a physical product (including a physical distribution medium), accompanied by a written offer, valid for at least three years and valid for as long as you offer spare parts or customer support for that product model, to give anyone who possesses the object code either (1) a copy of the Corresponding Source for all the software in the product that is covered by this License, on a durable physical medium customarily used for software interchange, for a price no more than your reasonable cost of physically performing this conveying of source, or (2) access to copy the Corresponding Source from a network server at no charge.
-
-    c) Convey individual copies of the object code with a copy of the written offer to provide the Corresponding Source.  This alternative is allowed only occasionally and noncommercially, and only if you received the object code with such an offer, in accord with subsection 6b.
-
-    d) Convey the object code by offering access from a designated place (gratis or for a charge), and offer equivalent access to the Corresponding Source in the same way through the same place at no further charge.  You need not require recipients to copy the Corresponding Source along with the object code.  If the place to copy the object code is a network server, the Corresponding Source may be on a different server (operated by you or a third party) that supports equivalent copying facilities, provided you maintain clear directions next to the object code saying where to find the Corresponding Source.  Regardless of what server hosts the Corresponding Source, you remain obligated to ensure that it is available for as long as needed to satisfy these requirements.
-
-    e) Convey the object code using peer-to-peer transmission, provided you inform other peers where the object code and Corresponding Source of the work are being offered to the general public at no charge under subsection 6d.
-
-A separable portion of the object code, whose source code is excluded from the Corresponding Source as a System Library, need not be included in conveying the object code work.
-
-A "User Product" is either (1) a "consumer product", which means any tangible personal property which is normally used for personal, family, or household purposes, or (2) anything designed or sold for incorporation into a dwelling.  In determining whether a product is a consumer product, doubtful cases shall be resolved in favor of coverage.  For a particular product received by a particular user, "normally used" refers to a typical or common use of that class of product, regardless of the status of the particular user or of the way in which the particular user actually uses, or expects or is expected to use, the product.  A product is a consumer product regardless of whether the product has substantial commercial, industrial or non-consumer uses, unless such uses represent the only significant mode of use of the product.
-
-"Installation Information" for a User Product means any methods, procedures, authorization keys, or other information required to install and execute modified versions of a covered work in that User Product from a modified version of its Corresponding Source.  The information must suffice to ensure that the continued functioning of the modified object code is in no case prevented or interfered with solely because modification has been made.
-
-If you convey an object code work under this section in, or with, or specifically for use in, a User Product, and the conveying occurs as part of a transaction in which the right of possession and use of the User Product is transferred to the recipient in perpetuity or for a fixed term (regardless of how the transaction is characterized), the Corresponding Source conveyed under this section must be accompanied by the Installation Information.  But this requirement does not apply if neither you nor any third party retains the ability to install modified object code on the User Product (for example, the work has been installed in ROM).
-
-The requirement to provide Installation Information does not include a requirement to continue to provide support service, warranty, or updates for a work that has been modified or installed by the recipient, or for the User Product in which it has been modified or installed.  Access to a network may be denied when the modification itself materially and adversely affects the operation of the network or violates the rules and protocols for communication across the network.
-
-Corresponding Source conveyed, and Installation Information provided, in accord with this section must be in a format that is publicly documented (and with an implementation available to the public in source code form), and must require no special password or key for unpacking, reading or copying.
-
-7. Additional Terms.
-"Additional permissions" are terms that supplement the terms of this License by making exceptions from one or more of its conditions. Additional permissions that are applicable to the entire Program shall be treated as though they were included in this License, to the extent that they are valid under applicable law.  If additional permissions apply only to part of the Program, that part may be used separately under those permissions, but the entire Program remains governed by this License without regard to the additional permissions.
-
-When you convey a copy of a covered work, you may at your option remove any additional permissions from that copy, or from any part of it.  (Additional permissions may be written to require their own removal in certain cases when you modify the work.)  You may place additional permissions on material, added by you to a covered work, for which you have or can give appropriate copyright permission.
-
-Notwithstanding any other provision of this License, for material you add to a covered work, you may (if authorized by the copyright holders of that material) supplement the terms of this License with terms:
-
-    a) Disclaiming warranty or limiting liability differently from the terms of sections 15 and 16 of this License; or
-
-    b) Requiring preservation of specified reasonable legal notices or author attributions in that material or in the Appropriate Legal Notices displayed by works containing it; or
-
-    c) Prohibiting misrepresentation of the origin of that material, or requiring that modified versions of such material be marked in reasonable ways as different from the original version; or
-
-    d) Limiting the use for publicity purposes of names of licensors or authors of the material; or
-
-    e) Declining to grant rights under trademark law for use of some trade names, trademarks, or service marks; or
-
-    f) Requiring indemnification of licensors and authors of that material by anyone who conveys the material (or modified versions of it) with contractual assumptions of liability to the recipient, for any liability that these contractual assumptions directly impose on those licensors and authors.
-
-All other non-permissive additional terms are considered "further restrictions" within the meaning of section 10.  If the Program as you received it, or any part of it, contains a notice stating that it is governed by this License along with a term that is a further restriction, you may remove that term.  If a license document contains a further restriction but permits relicensing or conveying under this License, you may add to a covered work material governed by the terms of that license document, provided that the further restriction does not survive such relicensing or conveying.
-
-If you add terms to a covered work in accord with this section, you must place, in the relevant source files, a statement of the additional terms that apply to those files, or a notice indicating where to find the applicable terms.
-
-Additional terms, permissive or non-permissive, may be stated in the form of a separately written license, or stated as exceptions; the above requirements apply either way.
-
-8. Termination.
-
-You may not propagate or modify a covered work except as expressly provided under this License.  Any attempt otherwise to propagate or modify it is void, and will automatically terminate your rights under this License (including any patent licenses granted under the third paragraph of section 11).
-
-However, if you cease all violation of this License, then your license from a particular copyright holder is reinstated (a) provisionally, unless and until the copyright holder explicitly and finally terminates your license, and (b) permanently, if the copyright holder fails to notify you of the violation by some reasonable means prior to 60 days after the cessation.
-
-Moreover, your license from a particular copyright holder is reinstated permanently if the copyright holder notifies you of the violation by some reasonable means, this is the first time you have received notice of violation of this License (for any work) from that copyright holder, and you cure the violation prior to 30 days after your receipt of the notice.
-
-Termination of your rights under this section does not terminate the licenses of parties who have received copies or rights from you under this License.  If your rights have been terminated and not permanently reinstated, you do not qualify to receive new licenses for the same material under section 10.
-
-9. Acceptance Not Required for Having Copies.
-
-You are not required to accept this License in order to receive or run a copy of the Program.  Ancillary propagation of a covered work occurring solely as a consequence of using peer-to-peer transmission to receive a copy likewise does not require acceptance.  However, nothing other than this License grants you permission to propagate or modify any covered work.  These actions infringe copyright if you do not accept this License.  Therefore, by modifying or propagating a covered work, you indicate your acceptance of this License to do so.
-
-10. Automatic Licensing of Downstream Recipients.
-
-Each time you convey a covered work, the recipient automatically receives a license from the original licensors, to run, modify and propagate that work, subject to this License.  You are not responsible for enforcing compliance by third parties with this License.
-
-An "entity transaction" is a transaction transferring control of an organization, or substantially all assets of one, or subdividing an organization, or merging organizations.  If propagation of a covered work results from an entity transaction, each party to that transaction who receives a copy of the work also receives whatever licenses to the work the party's predecessor in interest had or could give under the previous paragraph, plus a right to possession of the Corresponding Source of the work from the predecessor in interest, if the predecessor has it or can get it with reasonable efforts.
-
-You may not impose any further restrictions on the exercise of the rights granted or affirmed under this License.  For example, you may not impose a license fee, royalty, or other charge for exercise of rights granted under this License, and you may not initiate litigation (including a cross-claim or counterclaim in a lawsuit) alleging that any patent claim is infringed by making, using, selling, offering for sale, or importing the Program or any portion of it.
-
-11. Patents.
-
-A "contributor" is a copyright holder who authorizes use under this License of the Program or a work on which the Program is based.  The work thus licensed is called the contributor's "contributor version".
-
-A contributor's "essential patent claims" are all patent claims owned or controlled by the contributor, whether already acquired or hereafter acquired, that would be infringed by some manner, permitted by this License, of making, using, or selling its contributor version, but do not include claims that would be infringed only as a consequence of further modification of the contributor version.  For purposes of this definition, "control" includes the right to grant patent sublicenses in a manner consistent with the requirements of this License.
-
-Each contributor grants you a non-exclusive, worldwide, royalty-free patent license under the contributor's essential patent claims, to make, use, sell, offer for sale, import and otherwise run, modify and propagate the contents of its contributor version.
-
-In the following three paragraphs, a "patent license" is any express agreement or commitment, however denominated, not to enforce a patent (such as an express permission to practice a patent or covenant not to sue for patent infringement).  To "grant" such a patent license to a party means to make such an agreement or commitment not to enforce a patent against the party.
-
-If you convey a covered work, knowingly relying on a patent license, and the Corresponding Source of the work is not available for anyone to copy, free of charge and under the terms of this License, through a publicly available network server or other readily accessible means, then you must either (1) cause the Corresponding Source to be so available, or (2) arrange to deprive yourself of the benefit of the patent license for this particular work, or (3) arrange, in a manner consistent with the requirements of this License, to extend the patent
-license to downstream recipients.  "Knowingly relying" means you have actual knowledge that, but for the patent license, your conveying the covered work in a country, or your recipient's use of the covered work in a country, would infringe one or more identifiable patents in that country that you have reason to believe are valid.
-
-If, pursuant to or in connection with a single transaction or arrangement, you convey, or propagate by procuring conveyance of, a covered work, and grant a patent license to some of the parties receiving the covered work authorizing them to use, propagate, modify or convey a specific copy of the covered work, then the patent license you grant is automatically extended to all recipients of the covered work and works based on it.
-
-A patent license is "discriminatory" if it does not include within the scope of its coverage, prohibits the exercise of, or is conditioned on the non-exercise of one or more of the rights that are specifically granted under this License.  You may not convey a covered work if you are a party to an arrangement with a third party that is in the business of distributing software, under which you make payment to the third party based on the extent of your activity of conveying the work, and under which the third party grants, to any of the parties who would receive the covered work from you, a discriminatory patent license (a) in connection with copies of the covered work conveyed by you (or copies made from those copies), or (b) primarily for and in connection with specific products or compilations that contain the covered work, unless you entered into that arrangement, or that patent license was granted, prior to 28 March 2007.
-
-Nothing in this License shall be construed as excluding or limiting any implied license or other defenses to infringement that may otherwise be available to you under applicable patent law.
-
-12. No Surrender of Others' Freedom.
-
-If conditions are imposed on you (whether by court order, agreement or otherwise) that contradict the conditions of this License, they do not excuse you from the conditions of this License.  If you cannot convey a covered work so as to satisfy simultaneously your obligations under this License and any other pertinent obligations, then as a consequence you may
-not convey it at all.  For example, if you agree to terms that obligate you to collect a royalty for further conveying from those to whom you convey the Program, the only way you could satisfy both those terms and this License would be to refrain entirely from conveying the Program.
-
-13. Remote Network Interaction; Use with the GNU General Public License.
-
-Notwithstanding any other provision of this License, if you modify the Program, your modified version must prominently offer all users interacting with it remotely through a computer network (if your version supports such interaction) an opportunity to receive the Corresponding Source of your version by providing access to the Corresponding Source from a network server at no charge, through some standard or customary means of facilitating copying of software.  This Corresponding Source shall include the Corresponding Source for any work covered by version 3 of the GNU General Public License that is incorporated pursuant to the following paragraph.
-
-Notwithstanding any other provision of this License, you have permission to link or combine any covered work with a work licensed under version 3 of the GNU General Public License into a single combined work, and to convey the resulting work.  The terms of this License will continue to apply to the part which is the covered work, but the work with which it is combined will remain governed by version 3 of the GNU General Public License.
-
-14. Revised Versions of this License.
-
-The Free Software Foundation may publish revised and/or new versions of the GNU Affero General Public License from time to time.  Such new versions will be similar in spirit to the present version, but may differ in detail to address new problems or concerns.
-
-Each version is given a distinguishing version number.  If the Program specifies that a certain numbered version of the GNU Affero General Public License "or any later version" applies to it, you have the option of following the terms and conditions either of that numbered version or of any later version published by the Free Software Foundation.  If the Program does not specify a version number of the GNU Affero General Public License, you may choose any version ever published by the Free Software Foundation.
-
-If the Program specifies that a proxy can decide which future versions of the GNU Affero General Public License can be used, that proxy's public statement of acceptance of a version permanently authorizes you to choose that version for the Program.
-
-Later license versions may give you additional or different permissions.  However, no additional obligations are imposed on any author or copyright holder as a result of your choosing to follow a later version.
-
-15. Disclaimer of Warranty.
-
-THERE IS NO WARRANTY FOR THE PROGRAM, TO THE EXTENT PERMITTED BY APPLICABLE LAW.  EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE.  THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE PROGRAM IS WITH YOU.  SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF ALL NECESSARY SERVICING, REPAIR OR CORRECTION.
-
-16. Limitation of Liability.
-
-IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MODIFIES AND/OR CONVEYS THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES, INCLUDING ANY GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING OUT OF THE USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED TO LOSS OF DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER PROGRAMS), EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF SUCH DAMAGES.
-
-17. Interpretation of Sections 15 and 16.
-
-If the disclaimer of warranty and limitation of liability provided above cannot be given local legal effect according to their terms, reviewing courts shall apply local law that most closely approximates an absolute waiver of all civil liability in connection with the Program, unless a warranty or assumption of liability accompanies a copy of the Program in return for a fee.
-
-END OF TERMS AND CONDITIONS
-
-            How to Apply These Terms to Your New Programs
-
-If you develop a new program, and you want it to be of the greatest possible use to the public, the best way to achieve this is to make it free software which everyone can redistribute and change under these terms.
-
-To do so, attach the following notices to the program.  It is safest to attach them to the start of each source file to most effectively state the exclusion of warranty; and each file should have at least the "copyright" line and a pointer to where the full notice is found.
-
-     <one line to give the program's name and a brief idea of what it does.>
-     Copyright (C) <year>  <name of author>
-
-     This program is free software: you can redistribute it and/or modify it under the terms of the GNU 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 <http://www.gnu.org/licenses/>.
-
-Also add information on how to contact you by electronic and paper mail.
-
-If your software can interact with users remotely through a computer network, you should also make sure that it provides a way for users to get its source.  For example, if your program is a web application, its interface could display a "Source" link that leads users to an archive of the code.  There are many ways you could offer source, and different solutions will be better for different programs; see section 13 for the specific requirements.
-
-You should also get your employer (if you work as a programmer) or school, if any, to sign a "copyright disclaimer" for the program, if necessary. For more information on this, and how to apply and follow the GNU AGPL, see <http://www.gnu.org/licenses/>.

LICENSES/CC-BY-SA-1.0.txt

@@ -1,81 +0,0 @@
-Creative Commons Attribution-ShareAlike 1.0
-
- CREATIVE COMMONS CORPORATION IS NOT A LAW FIRM AND DOES NOT PROVIDE LEGAL SERVICES. DISTRIBUTION OF THIS DRAFT LICENSE DOES NOT CREATE AN ATTORNEY-CLIENT RELATIONSHIP. CREATIVE COMMONS PROVIDES THIS INFORMATION ON AN "AS-IS" BASIS. CREATIVE COMMONS MAKES NO WARRANTIES REGARDING THE INFORMATION PROVIDED, AND DISCLAIMS LIABILITY FOR DAMAGES RESULTING FROM ITS USE.
-
-License
-
-THE WORK (AS DEFINED BELOW) IS PROVIDED UNDER THE TERMS OF THIS CREATIVE COMMONS PUBLIC LICENSE ("CCPL" OR "LICENSE"). THE WORK IS PROTECTED BY COPYRIGHT AND/OR OTHER APPLICABLE LAW. ANY USE OF THE WORK OTHER THAN AS AUTHORIZED UNDER THIS LICENSE IS PROHIBITED.
-
-BY EXERCISING ANY RIGHTS TO THE WORK PROVIDED HERE, YOU ACCEPT AND AGREE TO BE BOUND BY THE TERMS OF THIS LICENSE. THE LICENSOR GRANTS YOU THE RIGHTS CONTAINED HERE IN CONSIDERATION OF YOUR ACCEPTANCE OF SUCH TERMS AND CONDITIONS.
-
-1. Definitions
-
-     a. "Collective Work" means a work, such as a periodical issue, anthology or encyclopedia, in which the Work in its entirety in unmodified form, along with a number of other contributions, constituting separate and independent works in themselves, are assembled into a collective whole. A work that constitutes a Collective Work will not be considered a Derivative Work (as defined below) for the purposes of this License.
-
-     b. "Derivative Work" means a work based upon the Work or upon the Work and other pre-existing works, such as a translation, musical arrangement, dramatization, fictionalization, motion picture version, sound recording, art reproduction, abridgment, condensation, or any other form in which the Work may be recast, transformed, or adapted, except that a work that constitutes a Collective Work will not be considered a Derivative Work for the purpose of this License.
-
-     c. "Licensor" means the individual or entity that offers the Work under the terms of this License.
-
-     d. "Original Author" means the individual or entity who created the Work.
-
-     e. "Work" means the copyrightable work of authorship offered under the terms of this License.
-
-     f. "You" means an individual or entity exercising rights under this License who has not previously violated the terms of this License with respect to the Work, or who has received express permission from the Licensor to exercise rights under this License despite a previous violation.
-
-2. Fair Use Rights. Nothing in this license is intended to reduce, limit, or restrict any rights arising from fair use, first sale or other limitations on the exclusive rights of the copyright owner under copyright law or other applicable laws.
-
-3. License Grant. Subject to the terms and conditions of this License, Licensor hereby grants You a worldwide, royalty-free, non-exclusive, perpetual (for the duration of the applicable copyright) license to exercise the rights in the Work as stated below:
-
-     a. to reproduce the Work, to incorporate the Work into one or more Collective Works, and to reproduce the Work as incorporated in the Collective Works;
-
-     b. to create and reproduce Derivative Works;
-
-     c. to distribute copies or phonorecords of, display publicly, perform publicly, and perform publicly by means of a digital audio transmission the Work including as incorporated in Collective Works;
-
-     d. to distribute copies or phonorecords of, display publicly, perform publicly, and perform publicly by means of a digital audio transmission Derivative Works;
-
-The above rights may be exercised in all media and formats whether now known or hereafter devised. The above rights include the right to make such modifications as are technically necessary to exercise the rights in other media and formats. All rights not expressly granted by Licensor are hereby reserved.
-
-4. Restrictions. The license granted in Section 3 above is expressly made subject to and limited by the following restrictions:
-
-     a. You may distribute, publicly display, publicly perform, or publicly digitally perform the Work only under the terms of this License, and You must include a copy of, or the Uniform Resource Identifier for, this License with every copy or phonorecord of the Work You distribute, publicly display, publicly perform, or publicly digitally perform. You may not offer or impose any terms on the Work that alter or restrict the terms of this License or the recipients' exercise of the rights granted hereunder. You may not sublicense the Work. You must keep intact all notices that refer to this License and to the disclaimer of warranties. You may not distribute, publicly display, publicly perform, or publicly digitally perform the Work with any technological measures that control access or use of the Work in a manner inconsistent with the terms of this License Agreement. The above applies to the Work as incorporated in a Collective Work, but this does not require the Collective Work apart from the Work itself to be made subject to the terms of this License. If You create a Collective Work, upon notice from any Licensor You must, to the extent practicable, remove from the Collective Work any reference to such Licensor or the Original Author, as requested. If You create a Derivative Work, upon notice from any Licensor You must, to the extent practicable, remove from the Derivative Work any reference to such Licensor or the Original Author, as requested.
-
-     b. You may distribute, publicly display, publicly perform, or publicly digitally perform a Derivative Work only under the terms of this License, and You must include a copy of, or the Uniform Resource Identifier for, this License with every copy or phonorecord of each Derivative Work You distribute, publicly display, publicly perform, or publicly digitally perform. You may not offer or impose any terms on the Derivative Works that alter or restrict the terms of this License or the recipients' exercise of the rights granted hereunder, and You must keep intact all notices that refer to this License and to the disclaimer of warranties. You may not distribute, publicly display, publicly perform, or publicly digitally perform the Derivative Work with any technological measures that control access or use of the Work in a manner inconsistent with the terms of this License Agreement. The above applies to the Derivative Work as incorporated in a Collective Work, but this does not require the Collective Work apart from the Derivative Work itself to be made subject to the terms of this License.
-
-     c. If you distribute, publicly display, publicly perform, or publicly digitally perform the Work or any Derivative Works or Collective Works, You must keep intact all copyright notices for the Work and give the Original Author credit reasonable to the medium or means You are utilizing by conveying the name (or pseudonym if applicable) of the Original Author if supplied; the title of the Work if supplied; in the case of a Derivative Work, a credit identifying the use of the Work in the Derivative Work (e.g., "French translation of the Work by Original Author," or "Screenplay based on original Work by Original Author"). Such credit may be implemented in any reasonable manner; provided, however, that in the case of a Derivative Work or Collective Work, at a minimum such credit will appear where any other comparable authorship credit appears and in a manner at least as prominent as such other comparable authorship credit.
-
-5. Representations, Warranties and Disclaimer
-
-     a. By offering the Work for public release under this License, Licensor represents and warrants that, to the best of Licensor's knowledge after reasonable inquiry:
-
-           i. Licensor has secured all rights in the Work necessary to grant the license rights hereunder and to permit the lawful exercise of the rights granted hereunder without You having any obligation to pay any royalties, compulsory license fees, residuals or any other payments;
-
-          ii. The Work does not infringe the copyright, trademark, publicity rights, common law rights or any other right of any third party or constitute defamation, invasion of privacy or other tortious injury to any third party.
-
-     b. EXCEPT AS EXPRESSLY STATED IN THIS LICENSE OR OTHERWISE AGREED IN WRITING OR REQUIRED BY APPLICABLE LAW, THE WORK IS LICENSED ON AN "AS IS" BASIS, WITHOUT WARRANTIES OF ANY KIND, EITHER EXPRESS OR IMPLIED INCLUDING, WITHOUT LIMITATION, ANY WARRANTIES REGARDING THE CONTENTS OR ACCURACY OF THE WORK.
-
-6. Limitation on Liability. EXCEPT TO THE EXTENT REQUIRED BY APPLICABLE LAW, AND EXCEPT FOR DAMAGES ARISING FROM LIABILITY TO A THIRD PARTY RESULTING FROM BREACH OF THE WARRANTIES IN SECTION 5, IN NO EVENT WILL LICENSOR BE LIABLE TO YOU ON ANY LEGAL THEORY FOR ANY SPECIAL, INCIDENTAL, CONSEQUENTIAL, PUNITIVE OR EXEMPLARY DAMAGES ARISING OUT OF THIS LICENSE OR THE USE OF THE WORK, EVEN IF LICENSOR HAS BEEN ADVISED OF THE POSSIBILITY OF SUCH DAMAGES.
-
-7. Termination
-
-     a. This License and the rights granted hereunder will terminate automatically upon any breach by You of the terms of this License. Individuals or entities who have received Derivative Works or Collective Works from You under this License, however, will not have their licenses terminated provided such individuals or entities remain in full compliance with those licenses. Sections 1, 2, 5, 6, 7, and 8 will survive any termination of this License.
-
-     b. Subject to the above terms and conditions, the license granted here is perpetual (for the duration of the applicable copyright in the Work). Notwithstanding the above, Licensor reserves the right to release the Work under different license terms or to stop distributing the Work at any time; provided, however that any such election will not serve to withdraw this License (or any other license that has been, or is required to be, granted under the terms of this License), and this License will continue in full force and effect unless terminated as stated above.
-
-8. Miscellaneous
-
-     a. Each time You distribute or publicly digitally perform the Work or a Collective Work, the Licensor offers to the recipient a license to the Work on the same terms and conditions as the license granted to You under this License.
-
-     b. Each time You distribute or publicly digitally perform a Derivative Work, Licensor offers to the recipient a license to the original Work on the same terms and conditions as the license granted to You under this License.
-
-     c. If any provision of this License is invalid or unenforceable under applicable law, it shall not affect the validity or enforceability of the remainder of the terms of this License, and without further action by the parties to this agreement, such provision shall be reformed to the minimum extent necessary to make such provision valid and enforceable.
-
-     d. No term or provision of this License shall be deemed waived and no breach consented to unless such waiver or consent shall be in writing and signed by the party to be charged with such waiver or consent.
-
-     e. This License constitutes the entire agreement between the parties with respect to the Work licensed here. There are no understandings, agreements or representations with respect to the Work not specified here. Licensor shall not be bound by any additional provisions that may appear in any communication from You. This License may not be modified without the mutual written agreement of the Licensor and You.
-
-Creative Commons is not a party to this License, and makes no warranty whatsoever in connection with the Work. Creative Commons will not be liable to You or any party on any legal theory for any damages whatsoever, including without limitation any general, special, incidental or consequential damages arising in connection to this license. Notwithstanding the foregoing two (2) sentences, if Creative Commons has expressly identified itself as the Licensor hereunder, it shall have all rights and obligations of Licensor.
-
-Except for the limited purpose of indicating to the public that the Work is licensed under the CCPL, neither party will use the trademark "Creative Commons" or any related trademark or logo of Creative Commons without the prior written consent of Creative Commons. Any permitted use will be in compliance with Creative Commons' then-current trademark usage guidelines, as may be published on its website or otherwise made available upon request from time to time.
-
-Creative Commons may be contacted at http://creativecommons.org/.

LICENSES/CC-BY-SA-2.0.txt

@@ -1,85 +0,0 @@
-Creative Commons Attribution-ShareAlike 2.0
-
- CREATIVE COMMONS CORPORATION IS NOT A LAW FIRM AND DOES NOT PROVIDE LEGAL SERVICES. DISTRIBUTION OF THIS LICENSE DOES NOT CREATE AN ATTORNEY-CLIENT RELATIONSHIP. CREATIVE COMMONS PROVIDES THIS INFORMATION ON AN "AS-IS" BASIS. CREATIVE COMMONS MAKES NO WARRANTIES REGARDING THE INFORMATION PROVIDED, AND DISCLAIMS LIABILITY FOR DAMAGES RESULTING FROM ITS USE.
-
-License
-
-THE WORK (AS DEFINED BELOW) IS PROVIDED UNDER THE TERMS OF THIS CREATIVE COMMONS PUBLIC LICENSE ("CCPL" OR "LICENSE"). THE WORK IS PROTECTED BY COPYRIGHT AND/OR OTHER APPLICABLE LAW. ANY USE OF THE WORK OTHER THAN AS AUTHORIZED UNDER THIS LICENSE OR COPYRIGHT LAW IS PROHIBITED.
-
-BY EXERCISING ANY RIGHTS TO THE WORK PROVIDED HERE, YOU ACCEPT AND AGREE TO BE BOUND BY THE TERMS OF THIS LICENSE. THE LICENSOR GRANTS YOU THE RIGHTS CONTAINED HERE IN CONSIDERATION OF YOUR ACCEPTANCE OF SUCH TERMS AND CONDITIONS.
-
-1. Definitions
-
-     a. "Collective Work" means a work, such as a periodical issue, anthology or encyclopedia, in which the Work in its entirety in unmodified form, along with a number of other contributions, constituting separate and independent works in themselves, are assembled into a collective whole. A work that constitutes a Collective Work will not be considered a Derivative Work (as defined below) for the purposes of this License.
-
-     b. "Derivative Work" means a work based upon the Work or upon the Work and other pre-existing works, such as a translation, musical arrangement, dramatization, fictionalization, motion picture version, sound recording, art reproduction, abridgment, condensation, or any other form in which the Work may be recast, transformed, or adapted, except that a work that constitutes a Collective Work will not be considered a Derivative Work for the purpose of this License. For the avoidance of doubt, where the Work is a musical composition or sound recording, the synchronization of the Work in timed-relation with a moving image ("synching") will be considered a Derivative Work for the purpose of this License.
-
-     c. "Licensor" means the individual or entity that offers the Work under the terms of this License.
-
-     d. "Original Author" means the individual or entity who created the Work.
-
-     e. "Work" means the copyrightable work of authorship offered under the terms of this License.
-
-     f. "You" means an individual or entity exercising rights under this License who has not previously violated the terms of this License with respect to the Work, or who has received express permission from the Licensor to exercise rights under this License despite a previous violation.
-
-     g. "License Elements" means the following high-level license attributes as selected by Licensor and indicated in the title of this License: Attribution, ShareAlike.
-
-2. Fair Use Rights. Nothing in this license is intended to reduce, limit, or restrict any rights arising from fair use, first sale or other limitations on the exclusive rights of the copyright owner under copyright law or other applicable laws.
-
-3. License Grant. Subject to the terms and conditions of this License, Licensor hereby grants You a worldwide, royalty-free, non-exclusive, perpetual (for the duration of the applicable copyright) license to exercise the rights in the Work as stated below:
-
-     a. to reproduce the Work, to incorporate the Work into one or more Collective Works, and to reproduce the Work as incorporated in the Collective Works;
-
-     b. to create and reproduce Derivative Works;
-
-     c. to distribute copies or phonorecords of, display publicly, perform publicly, and perform publicly by means of a digital audio transmission the Work including as incorporated in Collective Works;
-
-     d. to distribute copies or phonorecords of, display publicly, perform publicly, and perform publicly by means of a digital audio transmission Derivative Works.
-
-     e. For the avoidance of doubt, where the work is a musical composition:
-
-          i. Performance Royalties Under Blanket Licenses. Licensor waives the exclusive right to collect, whether individually or via a performance rights society (e.g. ASCAP, BMI, SESAC), royalties for the public performance or public digital performance (e.g. webcast) of the Work.
-
-          ii. Mechanical Rights and Statutory Royalties. Licensor waives the exclusive right to collect, whether individually or via a music rights society or designated agent (e.g. Harry Fox Agency), royalties for any phonorecord You create from the Work ("cover version") and distribute, subject to the compulsory license created by 17 USC Section 115 of the US Copyright Act (or the equivalent in other jurisdictions).
-
-     f. Webcasting Rights and Statutory Royalties. For the avoidance of doubt, where the Work is a sound recording, Licensor waives the exclusive right to collect, whether individually or via a performance-rights society (e.g. SoundExchange), royalties for the public digital performance (e.g. webcast) of the Work, subject to the compulsory license created by 17 USC Section 114 of the US Copyright Act (or the equivalent in other jurisdictions).
-
-The above rights may be exercised in all media and formats whether now known or hereafter devised. The above rights include the right to make such modifications as are technically necessary to exercise the rights in other media and formats. All rights not expressly granted by Licensor are hereby reserved.
-
-4. Restrictions. The license granted in Section 3 above is expressly made subject to and limited by the following restrictions:
-
-     a. You may distribute, publicly display, publicly perform, or publicly digitally perform the Work only under the terms of this License, and You must include a copy of, or the Uniform Resource Identifier for, this License with every copy or phonorecord of the Work You distribute, publicly display, publicly perform, or publicly digitally perform. You may not offer or impose any terms on the Work that alter or restrict the terms of this License or the recipients' exercise of the rights granted hereunder. You may not sublicense the Work. You must keep intact all notices that refer to this License and to the disclaimer of warranties. You may not distribute, publicly display, publicly perform, or publicly digitally perform the Work with any technological measures that control access or use of the Work in a manner inconsistent with the terms of this License Agreement. The above applies to the Work as incorporated in a Collective Work, but this does not require the Collective Work apart from the Work itself to be made subject to the terms of this License. If You create a Collective Work, upon notice from any Licensor You must, to the extent practicable, remove from the Collective Work any reference to such Licensor or the Original Author, as requested. If You create a Derivative Work, upon notice from any Licensor You must, to the extent practicable, remove from the Derivative Work any reference to such Licensor or the Original Author, as requested.
-
-     b. You may distribute, publicly display, publicly perform, or publicly digitally perform a Derivative Work only under the terms of this License, a later version of this License with the same License Elements as this License, or a Creative Commons iCommons license that contains the same License Elements as this License (e.g. Attribution-ShareAlike 2.0 Japan). You must include a copy of, or the Uniform Resource Identifier for, this License or other license specified in the previous sentence with every copy or phonorecord of each Derivative Work You distribute, publicly display, publicly perform, or publicly digitally perform. You may not offer or impose any terms on the Derivative Works that alter or restrict the terms of this License or the recipients' exercise of the rights granted hereunder, and You must keep intact all notices that refer to this License and to the disclaimer of warranties. You may not distribute, publicly display, publicly perform, or publicly digitally perform the Derivative Work with any technological measures that control access or use of the Work in a manner inconsistent with the terms of this License Agreement. The above applies to the Derivative Work as incorporated in a Collective Work, but this does not require the Collective Work apart from the Derivative Work itself to be made subject to the terms of this License.
-
-     c. If you distribute, publicly display, publicly perform, or publicly digitally perform the Work or any Derivative Works or Collective Works, You must keep intact all copyright notices for the Work and give the Original Author credit reasonable to the medium or means You are utilizing by conveying the name (or pseudonym if applicable) of the Original Author if supplied; the title of the Work if supplied; to the extent reasonably practicable, the Uniform Resource Identifier, if any, that Licensor specifies to be associated with the Work, unless such URI does not refer to the copyright notice or licensing information for the Work; and in the case of a Derivative Work, a credit identifying the use of the Work in the Derivative Work (e.g., "French translation of the Work by Original Author," or "Screenplay based on original Work by Original Author"). Such credit may be implemented in any reasonable manner; provided, however, that in the case of a Derivative Work or Collective Work, at a minimum such credit will appear where any other comparable authorship credit appears and in a manner at least as prominent as such other comparable authorship credit.
-
-5. Representations, Warranties and Disclaimer
-
-UNLESS OTHERWISE AGREED TO BY THE PARTIES IN WRITING, LICENSOR OFFERS THE WORK AS-IS AND MAKES NO REPRESENTATIONS OR WARRANTIES OF ANY KIND CONCERNING THE MATERIALS, EXPRESS, IMPLIED, STATUTORY OR OTHERWISE, INCLUDING, WITHOUT LIMITATION, WARRANTIES OF TITLE, MERCHANTIBILITY, FITNESS FOR A PARTICULAR PURPOSE, NONINFRINGEMENT, OR THE ABSENCE OF LATENT OR OTHER DEFECTS, ACCURACY, OR THE PRESENCE OF ABSENCE OF ERRORS, WHETHER OR NOT DISCOVERABLE. SOME JURISDICTIONS DO NOT ALLOW THE EXCLUSION OF IMPLIED WARRANTIES, SO SUCH EXCLUSION MAY NOT APPLY TO YOU.
-
-6. Limitation on Liability. EXCEPT TO THE EXTENT REQUIRED BY APPLICABLE LAW, IN NO EVENT WILL LICENSOR BE LIABLE TO YOU ON ANY LEGAL THEORY FOR ANY SPECIAL, INCIDENTAL, CONSEQUENTIAL, PUNITIVE OR EXEMPLARY DAMAGES ARISING OUT OF THIS LICENSE OR THE USE OF THE WORK, EVEN IF LICENSOR HAS BEEN ADVISED OF THE POSSIBILITY OF SUCH DAMAGES.
-
-7. Termination
-
-     a. This License and the rights granted hereunder will terminate automatically upon any breach by You of the terms of this License. Individuals or entities who have received Derivative Works or Collective Works from You under this License, however, will not have their licenses terminated provided such individuals or entities remain in full compliance with those licenses. Sections 1, 2, 5, 6, 7, and 8 will survive any termination of this License.
-
-     b. Subject to the above terms and conditions, the license granted here is perpetual (for the duration of the applicable copyright in the Work). Notwithstanding the above, Licensor reserves the right to release the Work under different license terms or to stop distributing the Work at any time; provided, however that any such election will not serve to withdraw this License (or any other license that has been, or is required to be, granted under the terms of this License), and this License will continue in full force and effect unless terminated as stated above.
-
-8. Miscellaneous
-
-     a. Each time You distribute or publicly digitally perform the Work or a Collective Work, the Licensor offers to the recipient a license to the Work on the same terms and conditions as the license granted to You under this License.
-
-     b. Each time You distribute or publicly digitally perform a Derivative Work, Licensor offers to the recipient a license to the original Work on the same terms and conditions as the license granted to You under this License.
-
-     c. If any provision of this License is invalid or unenforceable under applicable law, it shall not affect the validity or enforceability of the remainder of the terms of this License, and without further action by the parties to this agreement, such provision shall be reformed to the minimum extent necessary to make such provision valid and enforceable.
-
-     d. No term or provision of this License shall be deemed waived and no breach consented to unless such waiver or consent shall be in writing and signed by the party to be charged with such waiver or consent.
-
-     e. This License constitutes the entire agreement between the parties with respect to the Work licensed here. There are no understandings, agreements or representations with respect to the Work not specified here. Licensor shall not be bound by any additional provisions that may appear in any communication from You. This License may not be modified without the mutual written agreement of the Licensor and You.
-
-Creative Commons is not a party to this License, and makes no warranty whatsoever in connection with the Work. Creative Commons will not be liable to You or any party on any legal theory for any damages whatsoever, including without limitation any general, special, incidental or consequential damages arising in connection to this license. Notwithstanding the foregoing two (2) sentences, if Creative Commons has expressly identified itself as the Licensor hereunder, it shall have all rights and obligations of Licensor.
-
-Except for the limited purpose of indicating to the public that the Work is licensed under the CCPL, neither party will use the trademark "Creative Commons" or any related trademark or logo of Creative Commons without the prior written consent of Creative Commons. Any permitted use will be in compliance with Creative Commons' then-current trademark usage guidelines, as may be published on its website or otherwise made available upon request from time to time.
-
-Creative Commons may be contacted at http://creativecommons.org/.

LICENSES/CC-BY-SA-2.5.txt

@@ -1,85 +0,0 @@
-Creative Commons Attribution-ShareAlike 2.5
-
- CREATIVE COMMONS CORPORATION IS NOT A LAW FIRM AND DOES NOT PROVIDE LEGAL SERVICES. DISTRIBUTION OF THIS LICENSE DOES NOT CREATE AN ATTORNEY-CLIENT RELATIONSHIP. CREATIVE COMMONS PROVIDES THIS INFORMATION ON AN "AS-IS" BASIS. CREATIVE COMMONS MAKES NO WARRANTIES REGARDING THE INFORMATION PROVIDED, AND DISCLAIMS LIABILITY FOR DAMAGES RESULTING FROM ITS USE.
-
-License
-
-THE WORK (AS DEFINED BELOW) IS PROVIDED UNDER THE TERMS OF THIS CREATIVE COMMONS PUBLIC LICENSE ("CCPL" OR "LICENSE"). THE WORK IS PROTECTED BY COPYRIGHT AND/OR OTHER APPLICABLE LAW. ANY USE OF THE WORK OTHER THAN AS AUTHORIZED UNDER THIS LICENSE OR COPYRIGHT LAW IS PROHIBITED.
-
-BY EXERCISING ANY RIGHTS TO THE WORK PROVIDED HERE, YOU ACCEPT AND AGREE TO BE BOUND BY THE TERMS OF THIS LICENSE. THE LICENSOR GRANTS YOU THE RIGHTS CONTAINED HERE IN CONSIDERATION OF YOUR ACCEPTANCE OF SUCH TERMS AND CONDITIONS.
-
-1. Definitions
-
-     a. "Collective Work" means a work, such as a periodical issue, anthology or encyclopedia, in which the Work in its entirety in unmodified form, along with a number of other contributions, constituting separate and independent works in themselves, are assembled into a collective whole. A work that constitutes a Collective Work will not be considered a Derivative Work (as defined below) for the purposes of this License.
-
-     b. "Derivative Work" means a work based upon the Work or upon the Work and other pre-existing works, such as a translation, musical arrangement, dramatization, fictionalization, motion picture version, sound recording, art reproduction, abridgment, condensation, or any other form in which the Work may be recast, transformed, or adapted, except that a work that constitutes a Collective Work will not be considered a Derivative Work for the purpose of this License. For the avoidance of doubt, where the Work is a musical composition or sound recording, the synchronization of the Work in timed-relation with a moving image ("synching") will be considered a Derivative Work for the purpose of this License.
-
-     c. "Licensor" means the individual or entity that offers the Work under the terms of this License.
-
-     d. "Original Author" means the individual or entity who created the Work.
-
-     e. "Work" means the copyrightable work of authorship offered under the terms of this License.
-
-     f. "You" means an individual or entity exercising rights under this License who has not previously violated the terms of this License with respect to the Work, or who has received express permission from the Licensor to exercise rights under this License despite a previous violation.
-
-     g. "License Elements" means the following high-level license attributes as selected by Licensor and indicated in the title of this License: Attribution, ShareAlike.
-
-2. Fair Use Rights. Nothing in this license is intended to reduce, limit, or restrict any rights arising from fair use, first sale or other limitations on the exclusive rights of the copyright owner under copyright law or other applicable laws.
-
-3. License Grant. Subject to the terms and conditions of this License, Licensor hereby grants You a worldwide, royalty-free, non-exclusive, perpetual (for the duration of the applicable copyright) license to exercise the rights in the Work as stated below:
-
-     a. to reproduce the Work, to incorporate the Work into one or more Collective Works, and to reproduce the Work as incorporated in the Collective Works;
-
-     b. to create and reproduce Derivative Works;
-
-     c. to distribute copies or phonorecords of, display publicly, perform publicly, and perform publicly by means of a digital audio transmission the Work including as incorporated in Collective Works;
-
-     d. to distribute copies or phonorecords of, display publicly, perform publicly, and perform publicly by means of a digital audio transmission Derivative Works.
-
-     e. For the avoidance of doubt, where the work is a musical composition:
-
-          i. Performance Royalties Under Blanket Licenses. Licensor waives the exclusive right to collect, whether individually or via a performance rights society (e.g. ASCAP, BMI, SESAC), royalties for the public performance or public digital performance (e.g. webcast) of the Work.
-
-          ii. Mechanical Rights and Statutory Royalties. Licensor waives the exclusive right to collect, whether individually or via a music rights society or designated agent (e.g. Harry Fox Agency), royalties for any phonorecord You create from the Work ("cover version") and distribute, subject to the compulsory license created by 17 USC Section 115 of the US Copyright Act (or the equivalent in other jurisdictions).
-
-     f. Webcasting Rights and Statutory Royalties. For the avoidance of doubt, where the Work is a sound recording, Licensor waives the exclusive right to collect, whether individually or via a performance-rights society (e.g. SoundExchange), royalties for the public digital performance (e.g. webcast) of the Work, subject to the compulsory license created by 17 USC Section 114 of the US Copyright Act (or the equivalent in other jurisdictions).
-
-The above rights may be exercised in all media and formats whether now known or hereafter devised. The above rights include the right to make such modifications as are technically necessary to exercise the rights in other media and formats. All rights not expressly granted by Licensor are hereby reserved.
-
-4. Restrictions. The license granted in Section 3 above is expressly made subject to and limited by the following restrictions:
-
-     a. You may distribute, publicly display, publicly perform, or publicly digitally perform the Work only under the terms of this License, and You must include a copy of, or the Uniform Resource Identifier for, this License with every copy or phonorecord of the Work You distribute, publicly display, publicly perform, or publicly digitally perform. You may not offer or impose any terms on the Work that alter or restrict the terms of this License or the recipients' exercise of the rights granted hereunder. You may not sublicense the Work. You must keep intact all notices that refer to this License and to the disclaimer of warranties. You may not distribute, publicly display, publicly perform, or publicly digitally perform the Work with any technological measures that control access or use of the Work in a manner inconsistent with the terms of this License Agreement. The above applies to the Work as incorporated in a Collective Work, but this does not require the Collective Work apart from the Work itself to be made subject to the terms of this License. If You create a Collective Work, upon notice from any Licensor You must, to the extent practicable, remove from the Collective Work any credit as required by clause 4(c), as requested. If You create a Derivative Work, upon notice from any Licensor You must, to the extent practicable, remove from the Derivative Work any credit as required by clause 4(c), as requested.
-
-     b. You may distribute, publicly display, publicly perform, or publicly digitally perform a Derivative Work only under the terms of this License, a later version of this License with the same License Elements as this License, or a Creative Commons iCommons license that contains the same License Elements as this License (e.g. Attribution-ShareAlike 2.5 Japan). You must include a copy of, or the Uniform Resource Identifier for, this License or other license specified in the previous sentence with every copy or phonorecord of each Derivative Work You distribute, publicly display, publicly perform, or publicly digitally perform. You may not offer or impose any terms on the Derivative Works that alter or restrict the terms of this License or the recipients' exercise of the rights granted hereunder, and You must keep intact all notices that refer to this License and to the disclaimer of warranties. You may not distribute, publicly display, publicly perform, or publicly digitally perform the Derivative Work with any technological measures that control access or use of the Work in a manner inconsistent with the terms of this License Agreement. The above applies to the Derivative Work as incorporated in a Collective Work, but this does not require the Collective Work apart from the Derivative Work itself to be made subject to the terms of this License.
-
-     c. If you distribute, publicly display, publicly perform, or publicly digitally perform the Work or any Derivative Works or Collective Works, You must keep intact all copyright notices for the Work and provide, reasonable to the medium or means You are utilizing: (i) the name of the Original Author (or pseudonym, if applicable) if supplied, and/or (ii) if the Original Author and/or Licensor designate another party or parties (e.g. a sponsor institute, publishing entity, journal) for attribution in Licensor's copyright notice, terms of service or by other reasonable means, the name of such party or parties; the title of the Work if supplied; to the extent reasonably practicable, the Uniform Resource Identifier, if any, that Licensor specifies to be associated with the Work, unless such URI does not refer to the copyright notice or licensing information for the Work; and in the case of a Derivative Work, a credit identifying the use of the Work in the Derivative Work (e.g., "French translation of the Work by Original Author," or "Screenplay based on original Work by Original Author"). Such credit may be implemented in any reasonable manner; provided, however, that in the case of a Derivative Work or Collective Work, at a minimum such credit will appear where any other comparable authorship credit appears and in a manner at least as prominent as such other comparable authorship credit.
-
-5. Representations, Warranties and Disclaimer
-
-UNLESS OTHERWISE AGREED TO BY THE PARTIES IN WRITING, LICENSOR OFFERS THE WORK AS-IS AND MAKES NO REPRESENTATIONS OR WARRANTIES OF ANY KIND CONCERNING THE MATERIALS, EXPRESS, IMPLIED, STATUTORY OR OTHERWISE, INCLUDING, WITHOUT LIMITATION, WARRANTIES OF TITLE, MERCHANTIBILITY, FITNESS FOR A PARTICULAR PURPOSE, NONINFRINGEMENT, OR THE ABSENCE OF LATENT OR OTHER DEFECTS, ACCURACY, OR THE PRESENCE OF ABSENCE OF ERRORS, WHETHER OR NOT DISCOVERABLE. SOME JURISDICTIONS DO NOT ALLOW THE EXCLUSION OF IMPLIED WARRANTIES, SO SUCH EXCLUSION MAY NOT APPLY TO YOU.
-
-6. Limitation on Liability. EXCEPT TO THE EXTENT REQUIRED BY APPLICABLE LAW, IN NO EVENT WILL LICENSOR BE LIABLE TO YOU ON ANY LEGAL THEORY FOR ANY SPECIAL, INCIDENTAL, CONSEQUENTIAL, PUNITIVE OR EXEMPLARY DAMAGES ARISING OUT OF THIS LICENSE OR THE USE OF THE WORK, EVEN IF LICENSOR HAS BEEN ADVISED OF THE POSSIBILITY OF SUCH DAMAGES.
-
-7. Termination
-
-     a. This License and the rights granted hereunder will terminate automatically upon any breach by You of the terms of this License. Individuals or entities who have received Derivative Works or Collective Works from You under this License, however, will not have their licenses terminated provided such individuals or entities remain in full compliance with those licenses. Sections 1, 2, 5, 6, 7, and 8 will survive any termination of this License.
-
-     b. Subject to the above terms and conditions, the license granted here is perpetual (for the duration of the applicable copyright in the Work). Notwithstanding the above, Licensor reserves the right to release the Work under different license terms or to stop distributing the Work at any time; provided, however that any such election will not serve to withdraw this License (or any other license that has been, or is required to be, granted under the terms of this License), and this License will continue in full force and effect unless terminated as stated above.
-
-8. Miscellaneous
-
-     a. Each time You distribute or publicly digitally perform the Work or a Collective Work, the Licensor offers to the recipient a license to the Work on the same terms and conditions as the license granted to You under this License.
-
-     b. Each time You distribute or publicly digitally perform a Derivative Work, Licensor offers to the recipient a license to the original Work on the same terms and conditions as the license granted to You under this License.
-
-     c. If any provision of this License is invalid or unenforceable under applicable law, it shall not affect the validity or enforceability of the remainder of the terms of this License, and without further action by the parties to this agreement, such provision shall be reformed to the minimum extent necessary to make such provision valid and enforceable.
-
-     d. No term or provision of this License shall be deemed waived and no breach consented to unless such waiver or consent shall be in writing and signed by the party to be charged with such waiver or consent.
-
-     e. This License constitutes the entire agreement between the parties with respect to the Work licensed here. There are no understandings, agreements or representations with respect to the Work not specified here. Licensor shall not be bound by any additional provisions that may appear in any communication from You. This License may not be modified without the mutual written agreement of the Licensor and You.
-
-Creative Commons is not a party to this License, and makes no warranty whatsoever in connection with the Work. Creative Commons will not be liable to You or any party on any legal theory for any damages whatsoever, including without limitation any general, special, incidental or consequential damages arising in connection to this license. Notwithstanding the foregoing two (2) sentences, if Creative Commons has expressly identified itself as the Licensor hereunder, it shall have all rights and obligations of Licensor.
-
-Except for the limited purpose of indicating to the public that the Work is licensed under the CCPL, neither party will use the trademark "Creative Commons" or any related trademark or logo of Creative Commons without the prior written consent of Creative Commons. Any permitted use will be in compliance with Creative Commons' then-current trademark usage guidelines, as may be published on its website or otherwise made available upon request from time to time.
-
-Creative Commons may be contacted at http://creativecommons.org/.

LICENSES/CC-BY-SA-3.0.txt

@@ -1,99 +0,0 @@
-Creative Commons Attribution-ShareAlike 3.0 Unported
-
- CREATIVE COMMONS CORPORATION IS NOT A LAW FIRM AND DOES NOT PROVIDE LEGAL SERVICES. DISTRIBUTION OF THIS LICENSE DOES NOT CREATE AN ATTORNEY-CLIENT RELATIONSHIP. CREATIVE COMMONS PROVIDES THIS INFORMATION ON AN "AS-IS" BASIS. CREATIVE COMMONS MAKES NO WARRANTIES REGARDING THE INFORMATION PROVIDED, AND DISCLAIMS LIABILITY FOR DAMAGES RESULTING FROM ITS USE.
-
-License
-
-THE WORK (AS DEFINED BELOW) IS PROVIDED UNDER THE TERMS OF THIS CREATIVE COMMONS PUBLIC LICENSE ("CCPL" OR "LICENSE"). THE WORK IS PROTECTED BY COPYRIGHT AND/OR OTHER APPLICABLE LAW. ANY USE OF THE WORK OTHER THAN AS AUTHORIZED UNDER THIS LICENSE OR COPYRIGHT LAW IS PROHIBITED.
-
-BY EXERCISING ANY RIGHTS TO THE WORK PROVIDED HERE, YOU ACCEPT AND AGREE TO BE BOUND BY THE TERMS OF THIS LICENSE. TO THE EXTENT THIS LICENSE MAY BE CONSIDERED TO BE A CONTRACT, THE LICENSOR GRANTS YOU THE RIGHTS CONTAINED HERE IN CONSIDERATION OF YOUR ACCEPTANCE OF SUCH TERMS AND CONDITIONS.
-
-1. Definitions
-
-     a. "Adaptation" means a work based upon the Work, or upon the Work and other pre-existing works, such as a translation, adaptation, derivative work, arrangement of music or other alterations of a literary or artistic work, or phonogram or performance and includes cinematographic adaptations or any other form in which the Work may be recast, transformed, or adapted including in any form recognizably derived from the original, except that a work that constitutes a Collection will not be considered an Adaptation for the purpose of this License. For the avoidance of doubt, where the Work is a musical work, performance or phonogram, the synchronization of the Work in timed-relation with a moving image ("synching") will be considered an Adaptation for the purpose of this License.
-
-     b. "Collection" means a collection of literary or artistic works, such as encyclopedias and anthologies, or performances, phonograms or broadcasts, or other works or subject matter other than works listed in Section 1(f) below, which, by reason of the selection and arrangement of their contents, constitute intellectual creations, in which the Work is included in its entirety in unmodified form along with one or more other contributions, each constituting separate and independent works in themselves, which together are assembled into a collective whole. A work that constitutes a Collection will not be considered an Adaptation (as defined below) for the purposes of this License.
-
-     c. "Creative Commons Compatible License" means a license that is listed at http://creativecommons.org/compatiblelicenses that has been approved by Creative Commons as being essentially equivalent to this License, including, at a minimum, because that license: (i) contains terms that have the same purpose, meaning and effect as the License Elements of this License; and, (ii) explicitly permits the relicensing of adaptations of works made available under that license under this License or a Creative Commons jurisdiction license with the same License Elements as this License.
-
-     d. "Distribute" means to make available to the public the original and copies of the Work or Adaptation, as appropriate, through sale or other transfer of ownership.
-
-     e. "License Elements" means the following high-level license attributes as selected by Licensor and indicated in the title of this License: Attribution, ShareAlike.
-
-     f. "Licensor" means the individual, individuals, entity or entities that offer(s) the Work under the terms of this License.
-
-     g. "Original Author" means, in the case of a literary or artistic work, the individual, individuals, entity or entities who created the Work or if no individual or entity can be identified, the publisher; and in addition (i) in the case of a performance the actors, singers, musicians, dancers, and other persons who act, sing, deliver, declaim, play in, interpret or otherwise perform literary or artistic works or expressions of folklore; (ii) in the case of a phonogram the producer being the person or legal entity who first fixes the sounds of a performance or other sounds; and, (iii) in the case of broadcasts, the organization that transmits the broadcast.
-
-     h. "Work" means the literary and/or artistic work offered under the terms of this License including without limitation any production in the literary, scientific and artistic domain, whatever may be the mode or form of its expression including digital form, such as a book, pamphlet and other writing; a lecture, address, sermon or other work of the same nature; a dramatic or dramatico-musical work; a choreographic work or entertainment in dumb show; a musical composition with or without words; a cinematographic work to which are assimilated works expressed by a process analogous to cinematography; a work of drawing, painting, architecture, sculpture, engraving or lithography; a photographic work to which are assimilated works expressed by a process analogous to photography; a work of applied art; an illustration, map, plan, sketch or three-dimensional work relative to geography, topography, architecture or science; a performance; a broadcast; a phonogram; a compilation of data to the extent it is protected as a copyrightable work; or a work performed by a variety or circus performer to the extent it is not otherwise considered a literary or artistic work.
-
-     i. "You" means an individual or entity exercising rights under this License who has not previously violated the terms of this License with respect to the Work, or who has received express permission from the Licensor to exercise rights under this License despite a previous violation.
-
-     j. "Publicly Perform" means to perform public recitations of the Work and to communicate to the public those public recitations, by any means or process, including by wire or wireless means or public digital performances; to make available to the public Works in such a way that members of the public may access these Works from a place and at a place individually chosen by them; to perform the Work to the public by any means or process and the communication to the public of the performances of the Work, including by public digital performance; to broadcast and rebroadcast the Work by any means including signs, sounds or images.
-
-     k. "Reproduce" means to make copies of the Work by any means including without limitation by sound or visual recordings and the right of fixation and reproducing fixations of the Work, including storage of a protected performance or phonogram in digital form or other electronic medium.
-
-2. Fair Dealing Rights. Nothing in this License is intended to reduce, limit, or restrict any uses free from copyright or rights arising from limitations or exceptions that are provided for in connection with the copyright protection under copyright law or other applicable laws.
-
-3. License Grant. Subject to the terms and conditions of this License, Licensor hereby grants You a worldwide, royalty-free, non-exclusive, perpetual (for the duration of the applicable copyright) license to exercise the rights in the Work as stated below:
-
-     a. to Reproduce the Work, to incorporate the Work into one or more Collections, and to Reproduce the Work as incorporated in the Collections;
-
-     b. to create and Reproduce Adaptations provided that any such Adaptation, including any translation in any medium, takes reasonable steps to clearly label, demarcate or otherwise identify that changes were made to the original Work. For example, a translation could be marked "The original work was translated from English to Spanish," or a modification could indicate "The original work has been modified.";
-
-     c. to Distribute and Publicly Perform the Work including as incorporated in Collections; and,
-
-     d. to Distribute and Publicly Perform Adaptations.
-
-     e. For the avoidance of doubt:
-
-          i. Non-waivable Compulsory License Schemes. In those jurisdictions in which the right to collect royalties through any statutory or compulsory licensing scheme cannot be waived, the Licensor reserves the exclusive right to collect such royalties for any exercise by You of the rights granted under this License;
-
-          ii. Waivable Compulsory License Schemes. In those jurisdictions in which the right to collect royalties through any statutory or compulsory licensing scheme can be waived, the Licensor waives the exclusive right to collect such royalties for any exercise by You of the rights granted under this License; and,
-
-          iii. Voluntary License Schemes. The Licensor waives the right to collect royalties, whether individually or, in the event that the Licensor is a member of a collecting society that administers voluntary licensing schemes, via that society, from any exercise by You of the rights granted under this License.
-
-The above rights may be exercised in all media and formats whether now known or hereafter devised. The above rights include the right to make such modifications as are technically necessary to exercise the rights in other media and formats. Subject to Section 8(f), all rights not expressly granted by Licensor are hereby reserved.
-
-4. Restrictions. The license granted in Section 3 above is expressly made subject to and limited by the following restrictions:
-
-     a. You may Distribute or Publicly Perform the Work only under the terms of this License. You must include a copy of, or the Uniform Resource Identifier (URI) for, this License with every copy of the Work You Distribute or Publicly Perform. You may not offer or impose any terms on the Work that restrict the terms of this License or the ability of the recipient of the Work to exercise the rights granted to that recipient under the terms of the License. You may not sublicense the Work. You must keep intact all notices that refer to this License and to the disclaimer of warranties with every copy of the Work You Distribute or Publicly Perform. When You Distribute or Publicly Perform the Work, You may not impose any effective technological measures on the Work that restrict the ability of a recipient of the Work from You to exercise the rights granted to that recipient under the terms of the License. This Section 4(a) applies to the Work as incorporated in a Collection, but this does not require the Collection apart from the Work itself to be made subject to the terms of this License. If You create a Collection, upon notice from any Licensor You must, to the extent practicable, remove from the Collection any credit as required by Section 4(c), as requested. If You create an Adaptation, upon notice from any Licensor You must, to the extent practicable, remove from the Adaptation any credit as required by Section 4(c), as requested.
-
-     b. You may Distribute or Publicly Perform an Adaptation only under the terms of: (i) this License; (ii) a later version of this License with the same License Elements as this License; (iii) a Creative Commons jurisdiction license (either this or a later license version) that contains the same License Elements as this License (e.g., Attribution-ShareAlike 3.0 US)); (iv) a Creative Commons Compatible License. If you license the Adaptation under one of the licenses mentioned in (iv), you must comply with the terms of that license. If you license the Adaptation under the terms of any of the licenses mentioned in (i), (ii) or (iii) (the "Applicable License"), you must comply with the terms of the Applicable License generally and the following provisions: (I) You must include a copy of, or the URI for, the Applicable License with every copy of each Adaptation You Distribute or Publicly Perform; (II) You may not offer or impose any terms on the Adaptation that restrict the terms of the Applicable License or the ability of the recipient of the Adaptation to exercise the rights granted to that recipient under the terms of the Applicable License; (III) You must keep intact all notices that refer to the Applicable License and to the disclaimer of warranties with every copy of the Work as included in the Adaptation You Distribute or Publicly Perform; (IV) when You Distribute or Publicly Perform the Adaptation, You may not impose any effective technological measures on the Adaptation that restrict the ability of a recipient of the Adaptation from You to exercise the rights granted to that recipient under the terms of the Applicable License. This Section 4(b) applies to the Adaptation as incorporated in a Collection, but this does not require the Collection apart from the Adaptation itself to be made subject to the terms of the Applicable License.
-
-     c. If You Distribute, or Publicly Perform the Work or any Adaptations or Collections, You must, unless a request has been made pursuant to Section 4(a), keep intact all copyright notices for the Work and provide, reasonable to the medium or means You are utilizing: (i) the name of the Original Author (or pseudonym, if applicable) if supplied, and/or if the Original Author and/or Licensor designate another party or parties (e.g., a sponsor institute, publishing entity, journal) for attribution ("Attribution Parties") in Licensor's copyright notice, terms of service or by other reasonable means, the name of such party or parties; (ii) the title of the Work if supplied; (iii) to the extent reasonably practicable, the URI, if any, that Licensor specifies to be associated with the Work, unless such URI does not refer to the copyright notice or licensing information for the Work; and (iv) , consistent with Ssection 3(b), in the case of an Adaptation, a credit identifying the use of the Work in the Adaptation (e.g., "French translation of the Work by Original Author," or "Screenplay based on original Work by Original Author"). The credit required by this Section 4(c) may be implemented in any reasonable manner; provided, however, that in the case of a Adaptation or Collection, at a minimum such credit will appear, if a credit for all contributing authors of the Adaptation or Collection appears, then as part of these credits and in a manner at least as prominent as the credits for the other contributing authors. For the avoidance of doubt, You may only use the credit required by this Section for the purpose of attribution in the manner set out above and, by exercising Your rights under this License, You may not implicitly or explicitly assert or imply any connection with, sponsorship or endorsement by the Original Author, Licensor and/or Attribution Parties, as appropriate, of You or Your use of the Work, without the separate, express prior written permission of the Original Author, Licensor and/or Attribution Parties.
-
-     d. Except as otherwise agreed in writing by the Licensor or as may be otherwise permitted by applicable law, if You Reproduce, Distribute or Publicly Perform the Work either by itself or as part of any Adaptations or Collections, You must not distort, mutilate, modify or take other derogatory action in relation to the Work which would be prejudicial to the Original Author's honor or reputation. Licensor agrees that in those jurisdictions (e.g. Japan), in which any exercise of the right granted in Section 3(b) of this License (the right to make Adaptations) would be deemed to be a distortion, mutilation, modification or other derogatory action prejudicial to the Original Author's honor and reputation, the Licensor will waive or not assert, as appropriate, this Section, to the fullest extent permitted by the applicable national law, to enable You to reasonably exercise Your right under Section 3(b) of this License (right to make Adaptations) but not otherwise.
-
-5. Representations, Warranties and Disclaimer
-
-UNLESS OTHERWISE MUTUALLY AGREED TO BY THE PARTIES IN WRITING, LICENSOR OFFERS THE WORK AS-IS AND MAKES NO REPRESENTATIONS OR WARRANTIES OF ANY KIND CONCERNING THE WORK, EXPRESS, IMPLIED, STATUTORY OR OTHERWISE, INCLUDING, WITHOUT LIMITATION, WARRANTIES OF TITLE, MERCHANTIBILITY, FITNESS FOR A PARTICULAR PURPOSE, NONINFRINGEMENT, OR THE ABSENCE OF LATENT OR OTHER DEFECTS, ACCURACY, OR THE PRESENCE OF ABSENCE OF ERRORS, WHETHER OR NOT DISCOVERABLE. SOME JURISDICTIONS DO NOT ALLOW THE EXCLUSION OF IMPLIED WARRANTIES, SO SUCH EXCLUSION MAY NOT APPLY TO YOU.
-
-6. Limitation on Liability. EXCEPT TO THE EXTENT REQUIRED BY APPLICABLE LAW, IN NO EVENT WILL LICENSOR BE LIABLE TO YOU ON ANY LEGAL THEORY FOR ANY SPECIAL, INCIDENTAL, CONSEQUENTIAL, PUNITIVE OR EXEMPLARY DAMAGES ARISING OUT OF THIS LICENSE OR THE USE OF THE WORK, EVEN IF LICENSOR HAS BEEN ADVISED OF THE POSSIBILITY OF SUCH DAMAGES.
-
-7. Termination
-
-     a. This License and the rights granted hereunder will terminate automatically upon any breach by You of the terms of this License. Individuals or entities who have received Adaptations or Collections from You under this License, however, will not have their licenses terminated provided such individuals or entities remain in full compliance with those licenses. Sections 1, 2, 5, 6, 7, and 8 will survive any termination of this License.
-
-     b. Subject to the above terms and conditions, the license granted here is perpetual (for the duration of the applicable copyright in the Work). Notwithstanding the above, Licensor reserves the right to release the Work under different license terms or to stop distributing the Work at any time; provided, however that any such election will not serve to withdraw this License (or any other license that has been, or is required to be, granted under the terms of this License), and this License will continue in full force and effect unless terminated as stated above.
-
-8. Miscellaneous
-
-     a. Each time You Distribute or Publicly Perform the Work or a Collection, the Licensor offers to the recipient a license to the Work on the same terms and conditions as the license granted to You under this License.
-
-     b. Each time You Distribute or Publicly Perform an Adaptation, Licensor offers to the recipient a license to the original Work on the same terms and conditions as the license granted to You under this License.
-
-     c. If any provision of this License is invalid or unenforceable under applicable law, it shall not affect the validity or enforceability of the remainder of the terms of this License, and without further action by the parties to this agreement, such provision shall be reformed to the minimum extent necessary to make such provision valid and enforceable.
-
-     d. No term or provision of this License shall be deemed waived and no breach consented to unless such waiver or consent shall be in writing and signed by the party to be charged with such waiver or consent.
-
-     e. This License constitutes the entire agreement between the parties with respect to the Work licensed here. There are no understandings, agreements or representations with respect to the Work not specified here. Licensor shall not be bound by any additional provisions that may appear in any communication from You. This License may not be modified without the mutual written agreement of the Licensor and You.
-
-     f. The rights granted under, and the subject matter referenced, in this License were drafted utilizing the terminology of the Berne Convention for the Protection of Literary and Artistic Works (as amended on September 28, 1979), the Rome Convention of 1961, the WIPO Copyright Treaty of 1996, the WIPO Performances and Phonograms Treaty of 1996 and the Universal Copyright Convention (as revised on July 24, 1971). These rights and subject matter take effect in the relevant jurisdiction in which the License terms are sought to be enforced according to the corresponding provisions of the implementation of those treaty provisions in the applicable national law. If the standard suite of rights granted under applicable copyright law includes additional rights not granted under this License, such additional rights are deemed to be included in the License; this License is not intended to restrict the license of any rights under applicable law.
-
-Creative Commons Notice
-
-Creative Commons is not a party to this License, and makes no warranty whatsoever in connection with the Work. Creative Commons will not be liable to You or any party on any legal theory for any damages whatsoever, including without limitation any general, special, incidental or consequential damages arising in connection to this license. Notwithstanding the foregoing two (2) sentences, if Creative Commons has expressly identified itself as the Licensor hereunder, it shall have all rights and obligations of Licensor.
-
-Except for the limited purpose of indicating to the public that the Work is licensed under the CCPL, Creative Commons does not authorize the use by either party of the trademark "Creative Commons" or any related trademark or logo of Creative Commons without the prior written consent of Creative Commons. Any permitted use will be in compliance with Creative Commons' then-current trademark usage guidelines, as may be published on its website or otherwise made available upon request from time to time. For the avoidance of doubt, this trademark restriction does not form part of the License.
-
-Creative Commons may be contacted at http://creativecommons.org/.

LICENSES/CC-BY-SA-4.0.txt

@@ -1,170 +0,0 @@
-Creative Commons Attribution-ShareAlike 4.0 International
-
- Creative Commons Corporation (“Creative Commons”) is not a law firm and does not provide legal services or legal advice. Distribution of Creative Commons public licenses does not create a lawyer-client or other relationship. Creative Commons makes its licenses and related information available on an “as-is” basis. Creative Commons gives no warranties regarding its licenses, any material licensed under their terms and conditions, or any related information. Creative Commons disclaims all liability for damages resulting from their use to the fullest extent possible.
-
-Using Creative Commons Public Licenses
-
-Creative Commons public licenses provide a standard set of terms and conditions that creators and other rights holders may use to share original works of authorship and other material subject to copyright and certain other rights specified in the public license below. The following considerations are for informational purposes only, are not exhaustive, and do not form part of our licenses.
-
-Considerations for licensors: Our public licenses are intended for use by those authorized to give the public permission to use material in ways otherwise restricted by copyright and certain other rights. Our licenses are irrevocable. Licensors should read and understand the terms and conditions of the license they choose before applying it. Licensors should also secure all rights necessary before applying our licenses so that the public can reuse the material as expected. Licensors should clearly mark any material not subject to the license. This includes other CC-licensed material, or material used under an exception or limitation to copyright. More considerations for licensors.
-
-Considerations for the public: By using one of our public licenses, a licensor grants the public permission to use the licensed material under specified terms and conditions. If the licensor’s permission is not necessary for any reason–for example, because of any applicable exception or limitation to copyright–then that use is not regulated by the license. Our licenses grant only permissions under copyright and certain other rights that a licensor has authority to grant. Use of the licensed material may still be restricted for other reasons, including because others have copyright or other rights in the material. A licensor may make special requests, such as asking that all changes be marked or described.
-
-Although not required by our licenses, you are encouraged to respect those requests where reasonable. More considerations for the public.
-
-Creative Commons Attribution-ShareAlike 4.0 International Public License
-
-By exercising the Licensed Rights (defined below), You accept and agree to be bound by the terms and conditions of this Creative Commons Attribution-ShareAlike 4.0 International Public License ("Public License"). To the extent this Public License may be interpreted as a contract, You are granted the Licensed Rights in consideration of Your acceptance of these terms and conditions, and the Licensor grants You such rights in consideration of benefits the Licensor receives from making the Licensed Material available under these terms and conditions.
-
-Section 1 – Definitions.
-
-     a.	Adapted Material means material subject to Copyright and Similar Rights that is derived from or based upon the Licensed Material and in which the Licensed Material is translated, altered, arranged, transformed, or otherwise modified in a manner requiring permission under the Copyright and Similar Rights held by the Licensor. For purposes of this Public License, where the Licensed Material is a musical work, performance, or sound recording, Adapted Material is always produced where the Licensed Material is synched in timed relation with a moving image.
-
-     b.	Adapter's License means the license You apply to Your Copyright and Similar Rights in Your contributions to Adapted Material in accordance with the terms and conditions of this Public License.
-
-     c.	BY-SA Compatible License means a license listed at creativecommons.org/compatiblelicenses, approved by Creative Commons as essentially the equivalent of this Public License.
-
-     d.	Copyright and Similar Rights means copyright and/or similar rights closely related to copyright including, without limitation, performance, broadcast, sound recording, and Sui Generis Database Rights, without regard to how the rights are labeled or categorized. For purposes of this Public License, the rights specified in Section 2(b)(1)-(2) are not Copyright and Similar Rights.
-
-     e.	Effective Technological Measures means those measures that, in the absence of proper authority, may not be circumvented under laws fulfilling obligations under Article 11 of the WIPO Copyright Treaty adopted on December 20, 1996, and/or similar international agreements.
-
-     f.	Exceptions and Limitations means fair use, fair dealing, and/or any other exception or limitation to Copyright and Similar Rights that applies to Your use of the Licensed Material.
-
-     g.	License Elements means the license attributes listed in the name of a Creative Commons Public License. The License Elements of this Public License are Attribution and ShareAlike.
-
-     h.	Licensed Material means the artistic or literary work, database, or other material to which the Licensor applied this Public License.
-
-     i.	Licensed Rights means the rights granted to You subject to the terms and conditions of this Public License, which are limited to all Copyright and Similar Rights that apply to Your use of the Licensed Material and that the Licensor has authority to license.
-
-     j.	Licensor means the individual(s) or entity(ies) granting rights under this Public License.
-
-     k.	Share means to provide material to the public by any means or process that requires permission under the Licensed Rights, such as reproduction, public display, public performance, distribution, dissemination, communication, or importation, and to make material available to the public including in ways that members of the public may access the material from a place and at a time individually chosen by them.
-
-     l.	Sui Generis Database Rights means rights other than copyright resulting from Directive 96/9/EC of the European Parliament and of the Council of 11 March 1996 on the legal protection of databases, as amended and/or succeeded, as well as other essentially equivalent rights anywhere in the world.
-
-     m.	You means the individual or entity exercising the Licensed Rights under this Public License. Your has a corresponding meaning.
-
-Section 2 – Scope.
-
-     a.	License grant.
-
-          1. Subject to the terms and conditions of this Public License, the Licensor hereby grants You a worldwide, royalty-free, non-sublicensable, non-exclusive, irrevocable license to exercise the Licensed Rights in the Licensed Material to:
-
-               A. reproduce and Share the Licensed Material, in whole or in part; and
-
-               B. produce, reproduce, and Share Adapted Material.
-
-          2. Exceptions and Limitations. For the avoidance of doubt, where Exceptions and Limitations apply to Your use, this Public License does not apply, and You do not need to comply with its terms and conditions.
-
-          3. Term. The term of this Public License is specified in Section 6(a).
-
-          4. Media and formats; technical modifications allowed. The Licensor authorizes You to exercise the Licensed Rights in all media and formats whether now known or hereafter created, and to make technical modifications necessary to do so. The Licensor waives and/or agrees not to assert any right or authority to forbid You from making technical modifications necessary to exercise the Licensed Rights, including technical modifications necessary to circumvent Effective Technological Measures. For purposes of this Public License, simply making modifications authorized by this Section 2(a)(4) never produces Adapted Material.
-
-          5. Downstream recipients.
-
-               A. Offer from the Licensor – Licensed Material. Every recipient of the Licensed Material automatically receives an offer from the Licensor to exercise the Licensed Rights under the terms and conditions of this Public License.
-
-               B. Additional offer from the Licensor – Adapted Material. Every recipient of Adapted Material from You automatically receives an offer from the Licensor to exercise the Licensed Rights in the Adapted Material under the conditions of the Adapter’s License You apply.
-
-               C. No downstream restrictions. You may not offer or impose any additional or different terms or conditions on, or apply any Effective Technological Measures to, the Licensed Material if doing so restricts exercise of the Licensed Rights by any recipient of the Licensed Material.
-
-          6. No endorsement. Nothing in this Public License constitutes or may be construed as permission to assert or imply that You are, or that Your use of the Licensed Material is, connected with, or sponsored, endorsed, or granted official status by, the Licensor or others designated to receive attribution as provided in Section 3(a)(1)(A)(i).
-
-     b.	Other rights.
-
-          1. Moral rights, such as the right of integrity, are not licensed under this Public License, nor are publicity, privacy, and/or other similar personality rights; however, to the extent possible, the Licensor waives and/or agrees not to assert any such rights held by the Licensor to the limited extent necessary to allow You to exercise the Licensed Rights, but not otherwise.
-
-          2. Patent and trademark rights are not licensed under this Public License.
-
-          3. To the extent possible, the Licensor waives any right to collect royalties from You for the exercise of the Licensed Rights, whether directly or through a collecting society under any voluntary or waivable statutory or compulsory licensing scheme. In all other cases the Licensor expressly reserves any right to collect such royalties.
-
-Section 3 – License Conditions.
-
-Your exercise of the Licensed Rights is expressly made subject to the following conditions.
-
-     a.	Attribution.
-
-          1. If You Share the Licensed Material (including in modified form), You must:
-
-               A. retain the following if it is supplied by the Licensor with the Licensed Material:
-
-                    i.	identification of the creator(s) of the Licensed Material and any others designated to receive attribution, in any reasonable manner requested by the Licensor (including by pseudonym if designated);
-
-                    ii.	a copyright notice;
-
-                    iii. a notice that refers to this Public License;
-
-                    iv.	a notice that refers to the disclaimer of warranties;
-
-                    v.	a URI or hyperlink to the Licensed Material to the extent reasonably practicable;
-
-               B. indicate if You modified the Licensed Material and retain an indication of any previous modifications; and
-
-               C. indicate the Licensed Material is licensed under this Public License, and include the text of, or the URI or hyperlink to, this Public License.
-
-          2. You may satisfy the conditions in Section 3(a)(1) in any reasonable manner based on the medium, means, and context in which You Share the Licensed Material. For example, it may be reasonable to satisfy the conditions by providing a URI or hyperlink to a resource that includes the required information.
-
-          3. If requested by the Licensor, You must remove any of the information required by Section 3(a)(1)(A) to the extent reasonably practicable.
-
-     b.	ShareAlike.In addition to the conditions in Section 3(a), if You Share Adapted Material You produce, the following conditions also apply.
-
-          1. The Adapter’s License You apply must be a Creative Commons license with the same License Elements, this version or later, or a BY-SA Compatible License.
-
-          2. You must include the text of, or the URI or hyperlink to, the Adapter's License You apply. You may satisfy this condition in any reasonable manner based on the medium, means, and context in which You Share Adapted Material.
-
-          3. You may not offer or impose any additional or different terms or conditions on, or apply any Effective Technological Measures to, Adapted Material that restrict exercise of the rights granted under the Adapter's License You apply.
-
-Section 4 – Sui Generis Database Rights.
-
-Where the Licensed Rights include Sui Generis Database Rights that apply to Your use of the Licensed Material:
-
-     a.	for the avoidance of doubt, Section 2(a)(1) grants You the right to extract, reuse, reproduce, and Share all or a substantial portion of the contents of the database;
-
-     b.	if You include all or a substantial portion of the database contents in a database in which You have Sui Generis Database Rights, then the database in which You have Sui Generis Database Rights (but not its individual contents) is Adapted Material, including for purposes of Section 3(b); and
-
-     c.	You must comply with the conditions in Section 3(a) if You Share all or a substantial portion of the contents of the database.
-For the avoidance of doubt, this Section 4 supplements and does not replace Your obligations under this Public License where the Licensed Rights include other Copyright and Similar Rights.
-
-Section 5 – Disclaimer of Warranties and Limitation of Liability.
-
-     a.	Unless otherwise separately undertaken by the Licensor, to the extent possible, the Licensor offers the Licensed Material as-is and as-available, and makes no representations or warranties of any kind concerning the Licensed Material, whether express, implied, statutory, or other. This includes, without limitation, warranties of title, merchantability, fitness for a particular purpose, non-infringement, absence of latent or other defects, accuracy, or the presence or absence of errors, whether or not known or discoverable. Where disclaimers of warranties are not allowed in full or in part, this disclaimer may not apply to You.
-
-     b.	To the extent possible, in no event will the Licensor be liable to You on any legal theory (including, without limitation, negligence) or otherwise for any direct, special, indirect, incidental, consequential, punitive, exemplary, or other losses, costs, expenses, or damages arising out of this Public License or use of the Licensed Material, even if the Licensor has been advised of the possibility of such losses, costs, expenses, or damages. Where a limitation of liability is not allowed in full or in part, this limitation may not apply to You.
-
-     c.	The disclaimer of warranties and limitation of liability provided above shall be interpreted in a manner that, to the extent possible, most closely approximates an absolute disclaimer and waiver of all liability.
-
-Section 6 – Term and Termination.
-
-     a.	This Public License applies for the term of the Copyright and Similar Rights licensed here. However, if You fail to comply with this Public License, then Your rights under this Public License terminate automatically.
-
-     b.	Where Your right to use the Licensed Material has terminated under Section 6(a), it reinstates:
-
-          1. automatically as of the date the violation is cured, provided it is cured within 30 days of Your discovery of the violation; or
-
-          2. upon express reinstatement by the Licensor.
-
-     c.	For the avoidance of doubt, this Section 6(b) does not affect any right the Licensor may have to seek remedies for Your violations of this Public License.
-
-     d.	For the avoidance of doubt, the Licensor may also offer the Licensed Material under separate terms or conditions or stop distributing the Licensed Material at any time; however, doing so will not terminate this Public License.
-
-     e.	Sections 1, 5, 6, 7, and 8 survive termination of this Public License.
-
-Section 7 – Other Terms and Conditions.
-
-     a.	The Licensor shall not be bound by any additional or different terms or conditions communicated by You unless expressly agreed.
-
-     b.	Any arrangements, understandings, or agreements regarding the Licensed Material not stated herein are separate from and independent of the terms and conditions of this Public License.
-
-Section 8 – Interpretation.
-
-     a.	For the avoidance of doubt, this Public License does not, and shall not be interpreted to, reduce, limit, restrict, or impose conditions on any use of the Licensed Material that could lawfully be made without permission under this Public License.
-
-     b.	To the extent possible, if any provision of this Public License is deemed unenforceable, it shall be automatically reformed to the minimum extent necessary to make it enforceable. If the provision cannot be reformed, it shall be severed from this Public License without affecting the enforceability of the remaining terms and conditions.
-
-     c.	No term or condition of this Public License will be waived and no failure to comply consented to unless expressly agreed to by the Licensor.
-
-     d.	Nothing in this Public License constitutes or may be interpreted as a limitation upon, or waiver of, any privileges and immunities that apply to the Licensor or You, including from the legal processes of any jurisdiction or authority.
-
-Creative Commons is not a party to its public licenses. Notwithstanding, Creative Commons may elect to apply one of its public licenses to material it publishes and in those instances will be considered the “Licensor.” Except for the limited purpose of indicating that material is shared under a Creative Commons public license or as otherwise permitted by the Creative Commons policies published at creativecommons.org/policies, Creative Commons does not authorize the use of the trademark “Creative Commons” or any other trademark or logo of Creative Commons without its prior written consent including, without limitation, in connection with any unauthorized modifications to any of its public licenses or any other arrangements, understandings, or agreements concerning use of licensed material. For the avoidance of doubt, this paragraph does not form part of the public licenses.
-
-Creative Commons may be contacted at creativecommons.org.

LICENSES/GFDL-1.2-or-later.txt

@@ -1,130 +0,0 @@
-GNU Free Documentation License
-Version 1.2, November 2002
-
-Copyright (C) 2000,2001,2002 Free Software Foundation, Inc. 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
-
-Everyone is permitted to copy and distribute verbatim copies of this license document, but changing it is not allowed.
-
-0. PREAMBLE
-
-The purpose of this License is to make a manual, textbook, or other functional and useful document "free" in the sense of freedom: to assure everyone the effective freedom to copy and redistribute it, with or without modifying it, either commercially or noncommercially. Secondarily, this License preserves for the author and publisher a way to get credit for their work, while not being considered responsible for modifications made by others.
-
-This License is a kind of "copyleft", which means that derivative works of the document must themselves be free in the same sense. It complements the GNU General Public License, which is a copyleft license designed for free software.
-
-We have designed this License in order to use it for manuals for free software, because free software needs free documentation: a free program should come with manuals providing the same freedoms that the software does. But this License is not limited to software manuals; it can be used for any textual work, regardless of subject matter or whether it is published as a printed book. We recommend this License principally for works whose purpose is instruction or reference.
-
-1. APPLICABILITY AND DEFINITIONS
-
-This License applies to any manual or other work, in any medium, that contains a notice placed by the copyright holder saying it can be distributed under the terms of this License. Such a notice grants a world-wide, royalty-free license, unlimited in duration, to use that work under the conditions stated herein. The "Document", below, refers to any such manual or work. Any member of the public is a licensee, and is addressed as "you". You accept the license if you copy, modify or distribute the work in a way requiring permission under copyright law.
-
-A "Modified Version" of the Document means any work containing the Document or a portion of it, either copied verbatim, or with modifications and/or translated into another language.
-
-A "Secondary Section" is a named appendix or a front-matter section of the Document that deals exclusively with the relationship of the publishers or authors of the Document to the Document's overall subject (or to related matters) and contains nothing that could fall directly within that overall subject. (Thus, if the Document is in part a textbook of mathematics, a Secondary Section may not explain any mathematics.) The relationship could be a matter of historical connection with the subject or with related matters, or of legal, commercial, philosophical, ethical or political position regarding them.
-
-The "Invariant Sections" are certain Secondary Sections whose titles are designated, as being those of Invariant Sections, in the notice that says that the Document is released under this License. If a section does not fit the above definition of Secondary then it is not allowed to be designated as Invariant. The Document may contain zero Invariant Sections. If the Document does not identify any Invariant Sections then there are none.
-
-The "Cover Texts" are certain short passages of text that are listed, as Front-Cover Texts or Back-Cover Texts, in the notice that says that the Document is released under this License. A Front-Cover Text may be at most 5 words, and a Back-Cover Text may be at most 25 words.
-
-A "Transparent" copy of the Document means a machine-readable copy, represented in a format whose specification is available to the general public, that is suitable for revising the document straightforwardly with generic text editors or (for images composed of pixels) generic paint programs or (for drawings) some widely available drawing editor, and that is suitable for input to text formatters or for automatic translation to a variety of formats suitable for input to text formatters. A copy made in an otherwise Transparent file format whose markup, or absence of markup, has been arranged to thwart or discourage subsequent modification by readers is not Transparent. An image format is not Transparent if used for any substantial amount of text. A copy that is not "Transparent" is called "Opaque".
-
-Examples of suitable formats for Transparent copies include plain ASCII without markup, Texinfo input format, LaTeX input format, SGML or XML using a publicly available DTD, and standard-conforming simple HTML, PostScript or PDF designed for human modification. Examples of transparent image formats include PNG, XCF and JPG. Opaque formats include proprietary formats that can be read and edited only by proprietary word processors, SGML or XML for which the DTD and/or processing tools are not generally available, and the machine-generated HTML, PostScript or PDF produced by some word processors for output purposes only.
-
-The "Title Page" means, for a printed book, the title page itself, plus such following pages as are needed to hold, legibly, the material this License requires to appear in the title page. For works in formats which do not have any title page as such, "Title Page" means the text near the most prominent appearance of the work's title, preceding the beginning of the body of the text.
-
-A section "Entitled XYZ" means a named subunit of the Document whose title either is precisely XYZ or contains XYZ in parentheses following text that translates XYZ in another language. (Here XYZ stands for a specific section name mentioned below, such as "Acknowledgements", "Dedications", "Endorsements", or "History".) To "Preserve the Title" of such a section when you modify the Document means that it remains a section "Entitled XYZ" according to this definition.
-
-The Document may include Warranty Disclaimers next to the notice which states that this License applies to the Document. These Warranty Disclaimers are considered to be included by reference in this License, but only as regards disclaiming warranties: any other implication that these Warranty Disclaimers may have is void and has no effect on the meaning of this License.
-
-2. VERBATIM COPYING
-
-You may copy and distribute the Document in any medium, either commercially or noncommercially, provided that this License, the copyright notices, and the license notice saying this License applies to the Document are reproduced in all copies, and that you add no other conditions whatsoever to those of this License. You may not use technical measures to obstruct or control the reading or further copying of the copies you make or distribute. However, you may accept compensation in exchange for copies. If you distribute a large enough number of copies you must also follow the conditions in section 3.
-
-You may also lend copies, under the same conditions stated above, and you may publicly display copies.
-
-3. COPYING IN QUANTITY
-
-If you publish printed copies (or copies in media that commonly have printed covers) of the Document, numbering more than 100, and the Document's license notice requires Cover Texts, you must enclose the copies in covers that carry, clearly and legibly, all these Cover Texts: Front-Cover Texts on the front cover, and Back-Cover Texts on the back cover. Both covers must also clearly and legibly identify you as the publisher of these copies. The front cover must present the full title with all words of the title equally prominent and visible. You may add other material on the covers in addition. Copying with changes limited to the covers, as long as they preserve the title of the Document and satisfy these conditions, can be treated as verbatim copying in other respects.
-
-If the required texts for either cover are too voluminous to fit legibly, you should put the first ones listed (as many as fit reasonably) on the actual cover, and continue the rest onto adjacent pages.
-
-If you publish or distribute Opaque copies of the Document numbering more than 100, you must either include a machine-readable Transparent copy along with each Opaque copy, or state in or with each Opaque copy a computer-network location from which the general network-using public has access to download using public-standard network protocols a complete Transparent copy of the Document, free of added material. If you use the latter option, you must take reasonably prudent steps, when you begin distribution of Opaque copies in quantity, to ensure that this Transparent copy will remain thus accessible at the stated location until at least one year after the last time you distribute an Opaque copy (directly or through your agents or retailers) of that edition to the public.
-
-It is requested, but not required, that you contact the authors of the Document well before redistributing any large number of copies, to give them a chance to provide you with an updated version of the Document.
-
-4. MODIFICATIONS
-
-You may copy and distribute a Modified Version of the Document under the conditions of sections 2 and 3 above, provided that you release the Modified Version under precisely this License, with the Modified Version filling the role of the Document, thus licensing distribution and modification of the Modified Version to whoever possesses a copy of it. In addition, you must do these things in the Modified Version:
-
-     A. Use in the Title Page (and on the covers, if any) a title distinct from that of the Document, and from those of previous versions (which should, if there were any, be listed in the History section of the Document). You may use the same title as a previous version if the original publisher of that version gives permission.
-     B. List on the Title Page, as authors, one or more persons or entities responsible for authorship of the modifications in the Modified Version, together with at least five of the principal authors of the Document (all of its principal authors, if it has fewer than five), unless they release you from this requirement.
-     C. State on the Title page the name of the publisher of the Modified Version, as the publisher.
-     D. Preserve all the copyright notices of the Document.
-     E. Add an appropriate copyright notice for your modifications adjacent to the other copyright notices.
-     F. Include, immediately after the copyright notices, a license notice giving the public permission to use the Modified Version under the terms of this License, in the form shown in the Addendum below.
-     G. Preserve in that license notice the full lists of Invariant Sections and required Cover Texts given in the Document's license notice.
-     H. Include an unaltered copy of this License.
-     I. Preserve the section Entitled "History", Preserve its Title, and add to it an item stating at least the title, year, new authors, and publisher of the Modified Version as given on the Title Page. If there is no section Entitled "History" in the Document, create one stating the title, year, authors, and publisher of the Document as given on its Title Page, then add an item describing the Modified Version as stated in the previous sentence.
-     J. Preserve the network location, if any, given in the Document for public access to a Transparent copy of the Document, and likewise the network locations given in the Document for previous versions it was based on. These may be placed in the "History" section. You may omit a network location for a work that was published at least four years before the Document itself, or if the original publisher of the version it refers to gives permission.
-     K. For any section Entitled "Acknowledgements" or "Dedications", Preserve the Title of the section, and preserve in the section all the substance and tone of each of the contributor acknowledgements and/or dedications given therein.
-     L. Preserve all the Invariant Sections of the Document, unaltered in their text and in their titles. Section numbers or the equivalent are not considered part of the section titles.
-     M. Delete any section Entitled "Endorsements". Such a section may not be included in the Modified Version.
-     N. Do not retitle any existing section to be Entitled "Endorsements" or to conflict in title with any Invariant Section.
-     O. Preserve any Warranty Disclaimers.
-
-If the Modified Version includes new front-matter sections or appendices that qualify as Secondary Sections and contain no material copied from the Document, you may at your option designate some or all of these sections as invariant. To do this, add their titles to the list of Invariant Sections in the Modified Version's license notice. These titles must be distinct from any other section titles.
-
-You may add a section Entitled "Endorsements", provided it contains nothing but endorsements of your Modified Version by various parties--for example, statements of peer review or that the text has been approved by an organization as the authoritative definition of a standard.
-
-You may add a passage of up to five words as a Front-Cover Text, and a passage of up to 25 words as a Back-Cover Text, to the end of the list of Cover Texts in the Modified Version. Only one passage of Front-Cover Text and one of Back-Cover Text may be added by (or through arrangements made by) any one entity. If the Document already includes a cover text for the same cover, previously added by you or by arrangement made by the same entity you are acting on behalf of, you may not add another; but you may replace the old one, on explicit permission from the previous publisher that added the old one.
-
-The author(s) and publisher(s) of the Document do not by this License give permission to use their names for publicity for or to assert or imply endorsement of any Modified Version.
-
-5. COMBINING DOCUMENTS
-
-You may combine the Document with other documents released under this License, under the terms defined in section 4 above for modified versions, provided that you include in the combination all of the Invariant Sections of all of the original documents, unmodified, and list them all as Invariant Sections of your combined work in its license notice, and that you preserve all their Warranty Disclaimers.
-
-The combined work need only contain one copy of this License, and multiple identical Invariant Sections may be replaced with a single copy. If there are multiple Invariant Sections with the same name but different contents, make the title of each such section unique by adding at the end of it, in parentheses, the name of the original author or publisher of that section if known, or else a unique number. Make the same adjustment to the section titles in the list of Invariant Sections in the license notice of the combined work.
-
-In the combination, you must combine any sections Entitled "History" in the various original documents, forming one section Entitled "History"; likewise combine any sections Entitled "Acknowledgements", and any sections Entitled "Dedications". You must delete all sections Entitled "Endorsements".
-
-6. COLLECTIONS OF DOCUMENTS
-
-You may make a collection consisting of the Document and other documents released under this License, and replace the individual copies of this License in the various documents with a single copy that is included in the collection, provided that you follow the rules of this License for verbatim copying of each of the documents in all other respects.
-
-You may extract a single document from such a collection, and distribute it individually under this License, provided you insert a copy of this License into the extracted document, and follow this License in all other respects regarding verbatim copying of that document.
-
-7. AGGREGATION WITH INDEPENDENT WORKS
-
-A compilation of the Document or its derivatives with other separate and independent documents or works, in or on a volume of a storage or distribution medium, is called an "aggregate" if the copyright resulting from the compilation is not used to limit the legal rights of the compilation's users beyond what the individual works permit. When the Document is included in an aggregate, this License does not apply to the other works in the aggregate which are not themselves derivative works of the Document.
-
-If the Cover Text requirement of section 3 is applicable to these copies of the Document, then if the Document is less than one half of the entire aggregate, the Document's Cover Texts may be placed on covers that bracket the Document within the aggregate, or the electronic equivalent of covers if the Document is in electronic form. Otherwise they must appear on printed covers that bracket the whole aggregate.
-
-8. TRANSLATION
-
-Translation is considered a kind of modification, so you may distribute translations of the Document under the terms of section 4. Replacing Invariant Sections with translations requires special permission from their copyright holders, but you may include translations of some or all Invariant Sections in addition to the original versions of these Invariant Sections. You may include a translation of this License, and all the license notices in the Document, and any Warranty Disclaimers, provided that you also include the original English version of this License and the original versions of those notices and disclaimers. In case of a disagreement between the translation and the original version of this License or a notice or disclaimer, the original version will prevail.
-
-If a section in the Document is Entitled "Acknowledgements", "Dedications", or "History", the requirement (section 4) to Preserve its Title (section 1) will typically require changing the actual title.
-
-9. TERMINATION
-
-You may not copy, modify, sublicense, or distribute the Document except as expressly provided for under this License. Any other attempt to copy, modify, sublicense or distribute the Document is void, and will automatically terminate your rights under this License. However, parties who have received copies, or rights, from you under this License will not have their licenses terminated so long as such parties remain in full compliance.
-
-10. FUTURE REVISIONS OF THIS LICENSE
-
-The Free Software Foundation may publish new, revised versions of the GNU Free Documentation License from time to time. Such new versions will be similar in spirit to the present version, but may differ in detail to address new problems or concerns. See http://www.gnu.org/copyleft/.
-
-Each version of the License is given a distinguishing version number. If the Document specifies that a particular numbered version of this License "or any later version" applies to it, you have the option of following the terms and conditions either of that specified version or of any later version that has been published (not as a draft) by the Free Software Foundation. If the Document does not specify a version number of this License, you may choose any version ever published (not as a draft) by the Free Software Foundation.
-
-ADDENDUM: How to use this License for your documents
-
-To use this License in a document you have written, include a copy of the License in the document and put the following copyright and license notices just after the title page:
-
- Copyright (c) YEAR YOUR NAME. Permission is granted to copy, distribute and/or modify this document under the terms of the GNU Free Documentation License, Version 1.2 or any later version published by the Free Software Foundation; with no Invariant Sections, no Front-Cover Texts, and no Back-Cover Texts. A copy of the license is included in the section entitled "GNU Free Documentation License".
-
-If you have Invariant Sections, Front-Cover Texts and Back-Cover Texts, replace the "with...Texts." line with this:
-
- with the Invariant Sections being LIST THEIR TITLES, with the Front-Cover Texts being LIST, and with the Back-Cover Texts being LIST.
-
-If you have Invariant Sections without Cover Texts, or some other combination of the three, merge those two alternatives to suit the situation.
-
-If your document contains nontrivial examples of program code, we recommend releasing these examples in parallel under your choice of free software license, such as the GNU General Public License, to permit their use in free software.

LICENSES/MIT.txt

@@ -1,9 +0,0 @@
-MIT License
-
-Copyright (c) <year> <copyright holders>
-
-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.

LICENSES/MPL-2.0.txt

@@ -1,373 +0,0 @@
-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 https://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.

LICENSES/Zlib.txt

@@ -1,11 +0,0 @@
-zlib License
-
-This software is provided 'as-is', without any express or implied warranty.  In no event will the authors be held liable for any damages arising from the use of this software.
-
-Permission is granted to anyone to use this software for any purpose, including commercial applications, and to alter it and redistribute it freely, subject to the following restrictions:
-
-     1. The origin of this software must not be misrepresented; you must not claim that you wrote the original software. If you use this software in a product, an acknowledgment in the product documentation would be appreciated but is not required.
-
-     2. Altered source versions must be plainly marked as such, and must not be misrepresented as being the original software.
-
-     3. This notice may not be removed or altered from any source distribution.

README.md

@@ -1,142 +1,40 @@
-<!-- SPDX-FileCopyrightText: 2014 Julien Pfefferkorn -->
-<!-- SPDX-FileCopyrightText: 2015 James R. Barlow -->
-<!-- SPDX-License-Identifier: CC-BY-SA-4.0 -->
+# OCRmyPDF-AppImage  [![Build Status](https://travis-ci.com/FPille/OCRmyPDF-AppImage.svg?branch=master)](https://travis-ci.com/FPille/OCRmyPDF-AppImage)
+[AppImage][APPIMAGE] for [OCRmyPDF][OCRMYPDF]
 
-<img src="docs/images/logo.svg" width="240" alt="OCRmyPDF">
+## Usage
+Download OCRmyPDF*.AppImage, make it executable and run it.
+```
+wget https://github.com/FPille/OCRmyPDF-AppImage/releases/download/continuous/OCRmyPDF-8.3.2-x86_64.AppImage
+chmod +x OCRmyPDF*.AppImage
+./OCRmyPDF*.AppImage --help
+```  
+  
+  Beside OCRmyPDF additional command line programs can be run with this AppImage like:
+* ghostscript
+* img2pdf
+* pngquant
+* python3.6
+* qpdf
+* tesseract
+* unpaper  
 
-[![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
+Just use the program name as first parameter plus options:
+```
+./OCRmyPDF*.AppImage tesseract -v
+tesseract 4.1.0
+ leptonica-1.76.0
+  libjpeg 8d (libjpeg-turbo 1.3.0) : libpng 1.2.50 : libtiff 4.0.3 : zlib 1.2.11 : libwebp 0.4.0 : libopenjp2 2.3.0
+ Found AVX2
+ Found AVX
+ Found SSE
+```
+Or create a symlink for the corresponding program:
+```
+ln -s OCRmyPDF*.AppImage tesseract
+./tesseract --list-langs
 ```
 
-[See the release notes for details on the latest changes](https://ocrmypdf.readthedocs.io/en/latest/release_notes.html).
 
-## Main features
+[APPIMAGE]: https://appimage.org
+[OCRMYPDF]: https://github.com/jbarlow83/OCRmyPDF
 
-- 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)
-- Keeps your private data private.
-- Scales properly to handle files with thousands of pages.
-- Battle-tested on millions of PDFs.
-
-<img src="misc/screencast/demo.svg" alt="Demo of OCRmyPDF in a terminal session">
-
-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 py-ocrmypdf``   |
-| Conda                         | ``conda install ocrmypdf``    |
-| Ubuntu Snap                   | ``snap 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 4.1.1+. 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 (3.8+), 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/)
-- [Y Combinator discussion](https://news.ycombinator.com/item?id=32028752)
-
-## 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 indicated by standard SPDX license identifiers or the DEP5 copyright and licensing information file. Generally speaking, non-core code is licensed under MIT, and the documentation and test files are 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.

appimage/AppRun.sh

@@ -0,0 +1,105 @@
+#! /bin/bash
+
+HERE="$(dirname "$(readlink -f "${0}")")"
+
+export PATH="$HERE/usr/bin:$HERE/usr/local/bin:$HERE/usr/python/bin:$PATH"
+export LD_PRELOAD="$HERE/usr/lib/liblept.so.5"
+export LD_LIBRARY_PATH="$HERE/usr/lib:$HERE/usr/lib/x86_64-linux-gnu:$LD_LIBRARY_PATH"
+export TESSDATA_PREFIX="$HERE/usr/share/tesseract-ocr/4.00/tessdata"
+export GS_LIB="$HERE/usr/share/ghostscript/9.26/lib:$HERE/usr/share/ghostscript/9.26/Resource:$HERE/usr/share/ghostscript/9.26/Resource/Init"
+
+# Allow the AppImage to be symlinked to e.g., /usr/bin/commandname
+# or called with ./Some*.AppImage commandname ...
+# refer to https://github.com/AppImage/AppImageKit/wiki/Bundling-command-line-tools
+
+if [ ! -z "$APPIMAGE" ] ; then
+  BINARY_NAME=$(basename "$ARGV0")
+else
+  BINARY_NAME=$(basename "$0")
+  export APPDIR="$HERE"       # required for the wrapper scripts of linuxdeploy-plugin-python
+fi
+
+usage() {
+echo "
+==============================================================================
+                          AppImage for OCRmyPDF
+==============================================================================
+OCRmyPDF adds an OCR text layer to scanned PDF files, allowing them to be
+searched or copy-pasted.
+
+usage:
+$ARGV0 [ocrmypdf] [--help] [--list-programs]
+                                 [--list-licenses] [--show-license]
+
+ocrmypdf                    execute OCRmyPDF
+
+--help                      show this help message
+
+--list-programs             list all programs contained in this AppImage
+
+--list-licenses             list all licenses contained in this AppImage
+
+--show-license [LICENSE]    show content of license file
+"
+}
+
+if [ "$1" == "--help" ] ; then
+    usage
+    exit $?
+fi
+
+if [ "$1" == "--list-programs" ] ; then
+    pushd "$HERE"
+    echo ""
+    echo "Run \"$ARGV0\" with one of the following arguments to run the respective program."
+    echo ""
+    find . -type f -perm /111 ! -path '*/lib/*' -execdir basename {} ";" | sort -u | column
+    echo ""
+    exit $?
+fi
+
+if [ "$1" == "--list-licenses" ] ; then
+    pushd "$HERE"
+    echo ""
+    echo "Run \"$ARGV0\" with one of the following arguments to display the respective license file."
+    echo ""
+    find . -type f \( ! -path '*/tesseract-ocr-*' -o -path '*/tesseract-ocr-eng/*' \) \
+        \( -iname "license*" -o -iname "*copyright*" -o -iname "*copying*" \) -printf "--show-license %P\n" | sort | column
+    echo ""
+    exit $?
+fi
+
+if [ "$1" == "--show-license" ] ; then
+    pushd "$HERE"
+    shift
+    if [ -f "$1" ] ; then
+        less -N "$1"
+        exit $?
+    else
+        echo "\"$1\" is not a valid license file path."
+        exit 1
+    fi
+fi
+
+if [ ! -z "$1" ] && [ -e "$HERE/bin/$1" ] ; then
+    MAIN="$HERE/bin/$1" ; shift
+elif [ ! -z "$1" ] && [ -e "$HERE/usr/bin/$1" ] ; then
+    MAIN="$HERE/usr/bin/$1" ; shift
+elif [ ! -z "$1" ] && [ -e "$HERE/usr/python/bin/$1" ] ; then
+    MAIN="$HERE/usr/python/bin/$1" ; shift
+elif [ ! -z "$1" ] && [ -e "$HERE/usr/local/bin/$1" ] ; then
+    MAIN="$HERE/usr/local/bin/$1" ; shift
+elif [ -e "$HERE/bin/$BINARY_NAME" ] ; then
+    MAIN="$HERE/bin/$BINARY_NAME"
+elif [ -e "$HERE/usr/bin/$BINARY_NAME" ] ; then
+    MAIN="$HERE/usr/bin/$BINARY_NAME"
+elif [ -e "$HERE/usr/python/bin/$BINARY_NAME" ] ; then
+    MAIN="$HERE/usr/python/bin/$BINARY_NAME"
+elif [ -e "$HERE/usr/local/bin/$BINARY_NAME" ] ; then
+    MAIN="$HERE/usr/local/bin/$BINARY_NAME"
+else
+    usage
+    exit $?
+fi
+
+exec "${MAIN}" "$@"

build-appimage.sh

@@ -0,0 +1,120 @@
+#! /bin/bash
+
+set -x
+set -e
+
+# use RAM disk if possible
+if [ "$CI" == "" ] && [ -d /dev/shm ]; then
+    TEMP_BASE=/dev/shm
+else
+    TEMP_BASE=/tmp
+fi
+
+BUILD_DIR=$(mktemp -d -p "$TEMP_BASE" OCRmyPDF-AppImage-build-XXXXXX)
+
+cleanup () {
+    if [ -d "$BUILD_DIR" ]; then
+        rm -rf "$BUILD_DIR"
+    fi
+}
+
+trap cleanup EXIT
+
+# store repo root as variable
+REPO_ROOT=$(readlink -f "$(dirname "$(dirname "$0")")")
+OLD_CWD=$(readlink -f .)
+
+pushd "$BUILD_DIR"
+
+mkdir -p AppDir
+mkdir -p PackageDir
+mkdir -p jbig2
+
+# download linuxdeploy AppImage and linuxdeploy-plugin-python AppImage
+wget https://github.com/TheAssassin/linuxdeploy/releases/download/continuous/linuxdeploy-x86_64.AppImage
+# wget https://github.com/niess/linuxdeploy-plugin-python/releases/download/continuous/linuxdeploy-plugin-python-x86_64.AppImage
+
+# use adapted linuxdeploy-plugin-python instead of the original one (otherwise OCRmyPDF breaks)
+wget https://github.com/FPille/linuxdeploy-plugin-python/releases/download/continuous/linuxdeploy-plugin-python-x86_64.AppImage
+
+chmod +x linuxdeploy*.AppImage
+
+
+ARCH=$(uname -i)
+export ARCH
+
+
+# .desktop file
+cat > ocrmypdf.desktop <<\EOF
+[Desktop Entry]
+Name=ocrmypdf
+Type=Application
+Exec=ocrmypdf
+Icon=ocrmypdf
+Terminal=true
+Comment=OCRmyPDF adds an OCR text layer to scanned PDF files, allowing them to be searched
+Categories=Graphics;Scanning;OCR;
+EOF
+
+
+# download logo and convert it to desktop icon
+# requires Imagemagick (convert)
+wget https://raw.githubusercontent.com/jbarlow83/OCRmyPDF/master/docs/images/logo-social.png
+convert logo-social.png -resize 512x512\> -size 512x512 xc:white +swap -gravity center -composite ocrmypdf.png
+
+
+# download and intsall packages required by OCRmyPDF
+pushd PackageDir
+packages=(tesseract-ocr tesseract-ocr-all libavformat56 ghostscript qpdf pngquant)
+
+for i in "${packages[@]}"
+do
+    apt-get -d -o dir::cache="$PWD" -o Debug::NoLocking=1 --reinstall install "$i" -y
+done
+
+wget -q 'https://www.dropbox.com/s/vaq0kbwi6e6au80/unpaper_6.1-1.deb?raw=1' -O unpaper_6.1-1.deb
+
+find . -type f -name \*.deb -exec dpkg-deb -X {} "$BUILD_DIR"/AppDir \;
+popd
+
+
+# compile and install jbig2
+# requires libleptonica-dev, zlib1g-dev
+wget -q https://github.com/agl/jbig2enc/archive/0.29.tar.gz -O - | \
+     tar xz -C jbig2 --strip-components=1
+pushd jbig2
+./autogen.sh
+./configure --prefix="$BUILD_DIR"/AppDir/usr
+make && make install
+popd
+
+pushd "$BUILD_DIR"/AppDir
+# add some tools to AppDir
+#cp -f   /usr/bin/column     ./usr/bin/
+#cp -f   /bin/less           ./usr/bin/
+
+# remove unnecessary data from AppDir
+[ -d bin ] && rm -rf ./bin
+[ -d etc ] && rm -rf ./etc
+[ -d var ] && rm -rf ./var
+popd
+
+
+# export LD_LIBRARY_PATH so that dependencies of shared libraries can be deployed by linuxdeploy-x86_64.AppImage
+export LD_LIBRARY_PATH="$BUILD_DIR/AppDir/usr/lib:$BUILD_DIR/AppDir/usr/lib/x86_64-linux-gnu:$LD_LIBRARY_PATH"
+
+#OCRMYPDF_VERSION=8.3.2   # exported in .travis.yml file
+export PIP_REQUIREMENTS="ocrmypdf==$OCRMYPDF_VERSION"
+export VERSION="$OCRMYPDF_VERSION"
+export OUTPUT=OCRmyPDF-"$VERSION"-"$ARCH".AppImage
+export PYTHON_SOURCE=https://www.python.org/ftp/python/3.6.8/Python-3.6.8.tgz
+
+./linuxdeploy-x86_64.AppImage --appdir AppDir --plugin python \
+    -d ocrmypdf.desktop -i ocrmypdf.png \
+    --custom-apprun "$REPO_ROOT"/appimage/AppRun.sh --output appimage
+
+
+# move AppImage back to old CWD
+mv "$OUTPUT" "$OLD_CWD"/
+
+popd

docs/advanced.rst

@@ -1,428 +0,0 @@
-.. SPDX-FileCopyrightText: 2022 James R. Barlow
-.. SPDX-License-Identifier: CC-BY-SA-4.0
-
-=================
-Advanced features
-=================
-
-Control of unpaper
-==================
-
-OCRmyPDF uses ``unpaper`` to provide the implementation of the
-``--clean`` and ``--clean-final`` arguments.
-`unpaper <https://github.com/Flameeyes/unpaper/blob/main/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; errors will result if this assumption is not
-   met.
-
-.. 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 ``--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 ``--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. Some PDF OCR solutions render text as
-technically printable or visible in some way, perhaps by drawing it and
-then painting over it. OCRmyPDF cannot distinguish this type of OCR
-text from real text, so it will not be "redone".
-
-If ``--force-ocr`` is issued, then all pages will be rasterized to
-images, discarding any hidden OCR text, rasterizing any printable
-text, and flattening form fields or interactive objects into their visual
-representation. 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.
-
-Time and image size limits
---------------------------
-
-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 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 image 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
-
-OCR for huge images
--------------------
-
-Tesseract has internal limits on the size
-of images it will process. If you issue
-``--tesseract-downsample-large-images``, OCRmyPDF will downsample images
-to fit Tesseract limits. (The limits are usually entered only for scanned
-images of oversized media, such as large maps or blueprints exceeding
-110 cm or 43 inches in either dimension, and at high DPI.)
-
-``--tesseract-downsample-above Npixels`` adjusts the threshold at which images
-will be downsampled. By default, only images that exceed any of Tesseract's
-internal limits are downsampled.
-
-You will also need to set ``--tesseract-timeout`` high enough to allow
-for processing.
-
-Only the image sent for OCR is downsampled. The original image is
-preserved.
-
-.. code-block:: bash
-
-    # Allow 600 seconds for OCR on huge images
-    ocrmypdf --tesseract-timeout 600 \
-        --tesseract-downsample-large-images \
-        bigfile.pdf output.pdf
-
-    # Downsample images above 5000 pixels on the longest dimension to
-    # 5000 pixels
-    ocrmypdf --tesseract-timeout 120 \
-        --tesseract-downsample-large-images \
-        --tesseract-downsample-above 5000 \
-        bigfile.pdf output_downsampled_ocr.pdf
-
-
-Overriding default tesseract
-----------------------------
-
-OCRmyPDF checks the system ``PATH`` for the ``tesseract`` binary.
-
-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 \
-        PATH=/home/user/src/tesseract/api:$PATH \
-        TESSDATA_PREFIX=/home/user/src/tesseract \
-        ocrmypdf input.pdf output.pdf
-
-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``
--  ``pngquant``
--  ``jbig2``
-
-In each case OCRmyPDF will search the ``PATH`` environment variable to
-locate the binaries. By modifying the ``PATH`` environment variable, you
-can override the binaries that OCRmyPDF uses.
-
-Changing Tesseract configuration variables
-------------------------------------------
-
-You can override Tesseract's default `control
-parameters <https://tesseract-ocr.github.io/tessdoc/tess3/ControlParams.html>`__
-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).
-
-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
-
-then run ocrmypdf as follows (along with any other desired arguments):
-
-.. code-block:: bash
-
-    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.
-
-Changing the PDF renderer
-=========================
-
-rasterizing
-  Converting a PDF to an image for display.
-
-rendering
-  Creating a new PDF from other data (such as an existing PDF).
-
-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 ``hocr``.
-
-The ``hocr`` renderer
----------------------
-
-.. versionchanged:: 16.0.0
-
-In both renderers, a text-only layer is rendered and sandwiched (overlaid)
-on to either the original PDF page, or newly rasterized version of the
-original PDF page (when ``--force-ocr`` is used). In this way, loss
-of PDF information is generally avoided. (You may need to disable PDF/A
-conversion and optimization to eliminate all lossy transformations.)
-
-The current approach used by the new hOCR renderer is a re-implementation
-of Tesseract's PDF renderer, using the same Glyphless font and general
-ideas, but fixing many technical issues that impeded it. The new hocr
-provides better text placement accuracy, avoids issues with word
-segmentation, and provides better positioning of skewed text.
-
-Using the experimental API, it is also possible to edit the OCR output
-from Tesseract, using any tool that is capable of editing hOCR files.
-
-Older versions of this renderer did not support non-Latin languages, but
-it is now universal.
-
-The ``sandwich`` renderer
--------------------------
-
-The ``sandwich`` renderer uses Tesseract's text-only PDF feature,
-which produces a PDF page that lays out the OCR in invisible text.
-
-Currently some problematic PDF viewers like Mozilla PDF.js and macOS
-Preview have problems with segmenting its text output, and
-mightrunseveralwordstogether. It also does not implement right to left
-fonts (Arabic, Hebrew, Persian). The output of this renderer cannot
-be edited. The sandwich renderer is retained for testing.
-
-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.
-
-Rendering and rasterizing options
-=================================
-
-.. versionadded:: 14.3.0
-
-The ``--continue-on-soft-render-error`` option allows OCRmyPDF to
-proceed if a page cannot be rasterized/rendered. This is useful if you are
-trying to get the best possible OCR from a PDF that is not well-formed,
-and you are willing to accept some pages that may not visually match the
-input, and that may not OCR well.
-
-Color conversion strategy
-=========================
-
-.. versionadded:: 15.0.0
-
-OCRmyPDF uses Ghostscript to convert PDF to PDF/A. In some cases, this
-conversion requires color conversion. The default strategy is to convert
-using the ``LeaveColorUnchanged`` strategy, which preserves the original
-color space wherever possible (some rare color spaces might still be
-converted).
-
-Usually document scanners produce PDFs in the sRGB color space, and do
-not need to be converted, so the default strategy is appropriate.
-
-Suppose that you have a document that was prepared for professional
-printing in a Separation or CMYK color space, and text was converted to
-curves. In this case, you may want to use a different color conversion
-strategy. The ``--color-conversion-strategy`` option allows you to select a
-different strategy, such as ``RGB``.
-
-Return code policy
-==================
-
-OCRmyPDF writes all messages to ``stderr``. ``stdout`` is reserved for
-piping output files. ``stdin`` is reserved for piping input files.
-
-The return codes generated by the OCRmyPDF are considered part of the
-stable user interface. They may be imported from
-``ocrmypdf.exceptions``.
-
-.. list-table:: Return codes
-    :widths: 5 35 60
-    :header-rows: 1
-
-    *	- Code
-        - Name
-        - Interpretation
-    *	- 0
-        - ``ExitCode.ok``
-        - Everything worked as expected.
-    *	- 1
-        - ``ExitCode.bad_args``
-        - Invalid arguments, exited with an error.
-    *	- 2
-        - ``ExitCode.input_file``
-        - The input file does not seem to be a valid PDF.
-    *	- 3
-        - ``ExitCode.missing_dependency``
-        - An external program required by OCRmyPDF is missing.
-    *	- 4
-        - ``ExitCode.invalid_output_pdf``
-        - An output file was created, but it does not seem to be a valid PDF. The file will be available.
-    *	- 5
-        - ``ExitCode.file_access_error``
-        - The user running OCRmyPDF does not have sufficient permissions to read the input file and write the output file.
-    *	- 6
-        - ``ExitCode.already_done_ocr``
-        - The file already appears to contain text so it may not need OCR. See output message.
-    *	- 7
-        - ``ExitCode.child_process_error``
-        - An error occurred in an external program (child process) and OCRmyPDF cannot continue.
-    *	- 8
-        - ``ExitCode.encrypted_pdf``
-        - The input PDF is encrypted. OCRmyPDF does not read encrypted PDFs. Use another program such as ``qpdf`` to remove encryption.
-    *	- 9
-        - ``ExitCode.invalid_config``
-        - A custom configuration file was forwarded to Tesseract using ``--tesseract-config``, and Tesseract rejected this file.
-    *   - 10
-        - ``ExitCode.pdfa_conversion_failed``
-        - A valid PDF was created, PDF/A conversion failed. The file will be available.
-    *	- 15
-        - ``ExitCode.other_error``
-        - Some other error occurred.
-    *	- 130
-        - ``ExitCode.ctrl_c``
-        - The program was interrupted by pressing Ctrl+C.
-
-
-.. _tmpdir:
-
-Changing temporary storage location
-===================================
-
-OCRmyPDF generates many temporary files during processing.
-
-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 Windows, the ``TEMP`` environment variable is used instead.
-
-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 ``--keep-temporary-files`` (``-k```) argument is issued on the
-command line, OCRmyPDF will keep the temporary folder and print the location,
-whether it succeeded or failed. 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

@@ -1,126 +0,0 @@
-.. SPDX-FileCopyrightText: 2022 James R. Barlow
-..
-.. SPDX-License-Identifier: CC-BY-SA-4.0
-
-======================
-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 worker processes or threads
-- 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. For example:
-
-.. code-block:: python
-
-    from multiprocessing import Process
-
-    def ocrmypdf_process():
-        ocrmypdf.ocr('input.pdf', 'output.pdf')
-
-    def call_ocrmypdf_from_my_app():
-        p = Process(target=ocrmypdf_process)
-        p.start()
-        p.join()
-
-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.
-
-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 ``rich`` 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.
-
-Standard output
----------------
-
-OCRmyPDF is strict about not writing to standard output so that
-users can safely use it in a pipeline and produce a valid output
-file. A caller application will have to ensure it does not write to
-standard output either, if it wants to be compatible with this
-behavior and support piping to a file.
-
-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.
-
-When OCRmyPDF succeeds conditionally, it returns an integer exit code.

docs/apiref.rst

@@ -1,71 +0,0 @@
-.. SPDX-FileCopyrightText: 2022 James R. Barlow
-..
-.. SPDX-License-Identifier: CC-BY-SA-4.0
-
-=============
-API reference
-=============
-
-This page summarizes the rest of the public API. Generally speaking this
-should be mainly of interest to plugin developers.
-
-ocrmypdf
-========
-
-.. autoclass:: ocrmypdf.PageContext
-    :members:
-
-.. autoclass:: ocrmypdf.PdfContext
-    :members:
-
-.. autoclass:: ocrmypdf.Verbosity
-    :members:
-    :undoc-members:
-
-.. autofunction:: ocrmypdf.configure_logging
-
-.. autofunction:: ocrmypdf.ocr
-
-.. autofunction:: ocrmypdf.pdf_to_hocr
-
-.. autofunction:: ocrmypdf.hocr_to_ocr_pdf
-
-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

@@ -1,228 +0,0 @@
-.. SPDX-FileCopyrightText: 2022 James R. Barlow
-..
-.. SPDX-License-Identifier: CC-BY-SA-4.0
-
-================
-Batch processing
-================
-
-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.
-
-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 ``ocrmypdf`` on all files named ``*.pdf`` in the
-current directory and write them to the previously 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.
-
-.. code-block:: bash
-
-   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, and printing each filename in between runs:
-
-.. code-block:: bash
-
-   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.
-
-.. 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
-
-With a Docker container, you will need to stream through standard input and output:
-
-.. code-block:: bash
-
-   find . -name '*.pdf' -print0 | xargs -0 | while read pdf; do
-       pdfout=$(mktemp)
-       docker run --rm -i jbarlow83/ocrmypdf - - <$pdf >$pdfout && cp $pdfout $pdf
-   done
-
-Sample script
--------------
-
-This user contributed script also provides an example of batch
-processing.
-
-.. literalinclude:: ../misc/batch.py
-    :caption: misc/batch.py
-
-Synology DiskStations
----------------------
-
-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.
-
-At the time this script was written, it only worked for x86-based Synology
-products. It is not known if it will work on ARM-based Synology products.
-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
-
-    pip3 install ocrmypdf[watcher]
-
-    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 original 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
-
-    docker run \
-        --volume <path to files to convert>:/input \
-        --volume <path to store results>:/output \
-        --volume <path to store processed originals>:/processed \
-        --env OCR_OUTPUT_DIRECTORY_YEAR_MONTH=1 \
-        --env OCR_ON_SUCCESS_ARCHIVE=1 \
-        --env OCR_DESKEW=1 \
-        --env PYTHONUNBUFFERED=1 \
-        --interactive --tty --entrypoint python3 \
-        jbarlow83/ocrmypdf \
-        watcher.py
-
-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 ``/processed``. The parameters to this image are:
-
-.. csv-table:: watcher.py parameters for Docker
-    :header: "Parameter", "Description"
-    :widths: 50, 50
-
-    "``--volume <path to files to convert>:/input``", "Files placed in this location will be OCRed"
-    "``--volume <path to store results>:/output``", "This is where OCRed files will be stored"
-    "``--volume <path to store processed originals>:/processed``", "Archive processed originals here"
-    "``--env 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}``"
-    "``--env OCR_ON_SUCCESS_ARCHIVE=1``", "Define environment variable ``OCR_ON_SUCCESS_ARCHIVE`` to move processed originals"
-    "``--env OCR_DESKEW=1``", "Define environment variable ``OCR_DESKEW``  to apply deskew to crooked input PDFs"
-    "``--env 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.
-
-Alternatives
-------------
-
--  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/cloud.rst

@@ -1,92 +0,0 @@
-.. SPDX-FileCopyrightText: 2023 James R. Barlow
-..
-.. SPDX-License-Identifier: CC-BY-SA-4.0
-
-
-.. _ocr-service:
-
-==================
-Online deployments
-==================
-
-OCRmyPDF is designed to be used as a command line tool, but it can be
-used in a web service. This document describes some considerations for
-doing so.
-
-A basic web service implementation is provided in the source code
-repository, as ``misc/webservice.py``. It is only demonstration quality
-and is not intended for production use.
-
-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. For further discussino of security, see :ref:`security`.
-
-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.
-
-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
-``--jobs`` argument may ensure the server remains responsive. 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 change the temporary directory, see :ref:`tmpdir`.
-
-On Amazon Web Services or other cloud vendors, consider setting your
-temporary directory 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.
-
-Document management systems
----------------------------
-
-If you are looking for a full document management system, consider
-`paperless-ngx <https://github.com/paperless-ngx/paperless-ngx>`__,
-which is a web application that uses OCRmyPDF to automatically OCR and
-archive documents.
-
-Commercial OCR 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.

docs/conf.py

@@ -1,382 +0,0 @@
-#!/usr/bin/env python3
-# SPDX-FileCopyrightText: 2022 James R. Barlow
-# SPDX-License-Identifier: CC-BY-SA-4.0
-
-# ruff: noqa: E402
-
-# ocrmypdf documentation build configuration file, created by
-# sphinx-quickstart on Sun Sep  4 14:29:43 2016.
-#
-# This file is execfile()d with the current directory set to its
-# containing dir.
-#
-# Note that not all possible configuration values are present in this
-# autogenerated file.
-#
-# All configuration values have a default; values that are commented out
-# serve to show the default.
-
-# If extensions (or modules to document with autodoc) are in another directory,
-# add these directories to sys.path here. If the directory is relative to the
-# documentation root, use os.path.abspath to make it absolute, like shown here.
-#
-# import os
-# import sys
-# sys.path.insert(0, os.path.abspath('.'))
-
-# -- General configuration ------------------------------------------------
-
-# If your documentation needs a minimal Sphinx version, state it here.
-#
-# needs_sphinx = '1.0'
-
-# Add any Sphinx extension module names here, as strings. They can be
-# extensions coming with Sphinx (named 'sphinx.ext.*') or your custom
-# ones.
-extensions = [
-    'sphinx.ext.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']
-
-# The suffix(es) of source filenames.
-# You can specify multiple suffix as a list of string:
-#
-# source_suffix = ['.rst', '.md']
-source_suffix = '.rst'
-
-# The encoding of source files.
-#
-# source_encoding = 'utf-8-sig'
-
-# The master toctree document.
-master_doc = 'index'
-
-# General information about the project.
-project = 'ocrmypdf'
-copyright = (
-    '2023, 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
-# |version| and |release|, also used in various other places throughout the
-# built documents.
-#
-# The short X.Y version.
-
-import os
-from importlib.metadata import version as package_version
-
-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)
-
-
-# The full version, including alpha/beta/rc tags.
-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.
-#
-# This is also used if you do content translation via gettext catalogs.
-# Usually you set "language" from the command line for these cases.
-language = None
-
-# There are two options for replacing |today|: either, you set today to some
-# non-false value, then it is used:
-#
-# today = ''
-#
-# Else, today_fmt is used as the format for a strftime call.
-#
-today_fmt = '%Y-%m-%d'
-
-# List of patterns, relative to source directory, that match files and
-# directories to ignore when looking for source files.
-# This patterns also effect to html_static_path and html_extra_path
-exclude_patterns = ['_build', 'Thumbs.db', '.DS_Store']
-
-# The reST default role (used for this markup: `text`) to use for all
-# documents.
-#
-# default_role = None
-
-# If true, '()' will be appended to :func: etc. cross-reference text.
-#
-# add_function_parentheses = True
-
-# If true, the current module name will be prepended to all description
-# unit titles (such as .. function::).
-#
-# add_module_names = True
-
-# If true, sectionauthor and moduleauthor directives will be shown in the
-# output. They are ignored by default.
-#
-# show_authors = False
-
-# The name of the Pygments (syntax highlighting) style to use.
-pygments_style = 'sphinx'
-
-# A list of ignored prefixes for module index sorting.
-# modindex_common_prefix = []
-
-# If true, keep warnings as "system message" paragraphs in the built documents.
-# keep_warnings = False
-
-# If true, `todo` and `todoList` produce output, else they produce nothing.
-todo_include_todos = False
-
-
-# -- Options for HTML output ----------------------------------------------
-
-import sphinx_rtd_theme
-
-# The theme to use for HTML and HTML Help pages.  See the documentation for
-# a list of builtin themes.
-#
-html_theme = 'sphinx_rtd_theme'
-html_theme_path = [sphinx_rtd_theme.get_html_theme_path()]
-
-# Theme options are theme-specific and customize the look and feel of a theme
-# further.  For a list of options available for each theme, see the
-# documentation.
-#
-html_theme_options = {'display_version': False}
-
-# Add any paths that contain custom themes here, relative to this directory.
-# html_theme_path = []
-
-# The name for this set of Sphinx documents.
-# "<project> v<release> documentation" by default.
-#
-# html_title = 'ocrmypdf v4.2'
-
-# A shorter title for the navigation bar.  Default is the same as html_title.
-#
-# html_short_title = None
-
-# The name of an image file (relative to this directory) to place at the top
-# of the sidebar.
-#
-# 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
-# pixels large.
-#
-# html_favicon = None
-
-# Add any paths that contain custom static files (such as style sheets) here,
-# relative to this directory. They are copied after the builtin static files,
-# so a file named "default.css" will overwrite the builtin "default.css".
-html_static_path = ['_static']
-
-# Add any extra paths that contain custom files (such as robots.txt or
-# .htaccess) here, relative to this directory. These files are copied
-# directly to the root of the documentation.
-#
-# html_extra_path = []
-
-# If not None, a 'Last updated on:' timestamp is inserted at every page
-# bottom, using the given strftime format.
-# The empty string is equivalent to '%b %d, %Y'.
-#
-# html_last_updated_fmt = None
-
-# If true, SmartyPants will be used to convert quotes and dashes to
-# typographically correct entities.
-#
-# html_use_smartypants = True
-
-# Custom sidebar templates, maps document names to template names.
-#
-# html_sidebars = {}
-
-# Additional templates that should be rendered to pages, maps page names to
-# template names.
-#
-# html_additional_pages = {}
-
-# If false, no module index is generated.
-#
-# html_domain_indices = True
-
-# If false, no index is generated.
-#
-# html_use_index = True
-
-# If true, the index is split into individual pages for each letter.
-#
-# html_split_index = False
-
-# If true, links to the reST sources are added to the pages.
-#
-# html_show_sourcelink = True
-
-# If true, "Created using Sphinx" is shown in the HTML footer. Default is True.
-#
-# html_show_sphinx = True
-
-# If true, "(C) Copyright ..." is shown in the HTML footer. Default is True.
-#
-# html_show_copyright = True
-
-# If true, an OpenSearch description file will be output, and all pages will
-# contain a <link> tag referring to it.  The value of this option must be the
-# base URL from which the finished HTML is served.
-#
-# html_use_opensearch = ''
-
-# This is the file name suffix for HTML files (e.g. ".xhtml").
-# html_file_suffix = None
-
-# Language to be used for generating the HTML full-text search index.
-# Sphinx supports the following languages:
-#   'da', 'de', 'en', 'es', 'fi', 'fr', 'h', 'it', 'ja'
-#   'nl', 'no', 'pt', 'ro', 'r', 'sv', 'tr', 'zh'
-#
-# html_search_language = 'en'
-
-# A dictionary with options for the search language support, empty by default.
-# 'ja' uses this config value.
-# 'zh' user can custom change `jieba` dictionary path.
-#
-# html_search_options = {'type': 'default'}
-
-# The name of a javascript file (relative to the configuration directory) that
-# implements a search results scorer. If empty, the default will be used.
-#
-# html_search_scorer = 'scorer.js'
-
-# Output file base name for HTML help builder.
-htmlhelp_basename = 'ocrmypdfdoc'
-
-# -- Options for LaTeX output ---------------------------------------------
-
-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')
-]
-
-# The name of an image file (relative to this directory) to place at the top of
-# the title page.
-#
-# latex_logo = None
-
-# For "manual" documents, if this is true, then toplevel headings are parts,
-# not chapters.
-#
-# latex_use_parts = False
-
-# If true, show page references after internal links.
-#
-# latex_show_pagerefs = False
-
-# If true, show URL addresses after external links.
-#
-# latex_show_urls = False
-
-# Documents to append as an appendix to all manuals.
-#
-# latex_appendices = []
-
-# It false, will not define \strong, \code, 	itleref, \crossref ... but only
-# \sphinxstrong, ..., \sphinxtitleref, ... To help avoid clash with user added
-# packages.
-#
-# latex_keep_old_macro_names = True
-
-# If false, no module index is generated.
-#
-# latex_domain_indices = True
-
-
-# -- Options for manual page output ---------------------------------------
-
-# 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)]
-
-# If true, show URL addresses after external links.
-#
-# man_show_urls = False
-
-
-# -- Options for Texinfo output -------------------------------------------
-
-# Grouping the document tree into Texinfo files. List of tuples
-# (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',
-    )
-]
-
-# Documents to append as an appendix to all manuals.
-#
-# texinfo_appendices = []
-
-# If false, no module index is generated.
-#
-# texinfo_domain_indices = True
-
-# How to display URL addresses: 'footnote', 'no', or 'inline'.
-#
-# texinfo_show_urls = 'footnote'
-
-# If true, do not generate a @detailmenu in the "Top" node's menu.
-#
-# texinfo_no_detailmenu = False

docs/contributing.rst

@@ -1,77 +0,0 @@
-.. SPDX-FileCopyrightText: 2022 James R. Barlow
-..
-.. SPDX-License-Identifier: CC-BY-SA-4.0
-
-=======================
-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 ``ruff`` for everything else. The
-settings for these programs are in ``pyproject.toml``. 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 dependencies
-================
-
-If you are proposing a change that will require a new dependency, we
-prefer dependencies that are already packaged by Debian or Red Hat. This makes
-life much easier for our downstream package maintainers. A package that is only
-available on PyPI or GitHub, and not more widely packaged, may not be accepted.
-
-We are unlikely to accept a dependency on CUDA or other GPU-based libraries,
-because these are still difficult to package and install on many systems.
-We recommend implementing these changes as plugins.
-
-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,
-and if we are to add external programs, we prefer those that are already
-packaged by Debian or Red Hat.
-
-Plugins
-=======
-
-Some new features may be a good fit for a plugin. Plugins are a way to add
-features to OCRmyPDF without adding them to the core program. Plugins are
-installed separately from OCRmyPDF. They are written in Python and can be
-installed from PyPI. See the `plugin documentation <https://ocrmypdf.readthedocs.io/en/latest/plugins.html>`_.
-
-We are happy to link users to your plugin from the documentation.
-
-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 add 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, with a few minor exceptions. Please contribute only content that you own
-or have the right to contribute under these licenses.

docs/cookbook.rst

@@ -1,396 +0,0 @@
-.. SPDX-FileCopyrightText: 2022 James R. Barlow
-..
-.. SPDX-License-Identifier: CC-BY-SA-4.0
-
-========
-Cookbook
-========
-
-Basic examples
-==============
-
-Help!
------
-
-ocrmypdf has built-in help.
-
-.. code-block:: bash
-
-    ocrmypdf --help
-
-Add an OCR layer and convert to PDF/A
--------------------------------------
-
-.. code-block:: bash
-
-    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
-
-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
-
-Modify a file in place
-----------------------
-
-The file will only be overwritten if OCRmyPDF is successful.
-
-.. code-block:: bash
-
-    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.
-
-.. code-block:: bash
-
-    ocrmypdf --rotate-pages myfile.pdf myfile.pdf
-
-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
---------------------------------
-
-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 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>`.
-
-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".
-
-.. code-block:: bash
-
-    ocrmypdf --sidecar output.txt input.pdf output.pdf
-
-.. note::
-
-    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
---------------------
-
-Option: use Tesseract
-~~~~~~~~~~~~~~~~~~~~~
-
-If you are starting with images, you can just use Tesseract directly to
-convert images to PDFs:
-
-.. code-block:: bash
-
-    tesseract my-image.jpg output-prefix pdf
-
-.. code-block:: bash
-
-    # When there are multiple images
-    tesseract text-file-containing-list-of-image-filenames.txt output-prefix 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.
-
-Option: use img2pdf
-~~~~~~~~~~~~~~~~~~~
-
-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
-
-    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.
-
--  ``--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.
-
-.. 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.
-
-Example: OCR and correct document skew (crooked scan)
------------------------------------------------------
-
-Deskew:
-
-.. code-block:: bash
-
-    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).
-
-.. code-block:: bash
-
-    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 (by causing OCR to time out). This works
-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
-
-.. versionchanged:: v14.1.0
-
-    Prior to this version, ``--tesseract-timeout 0`` would prevent other
-    uses of Tesseract, such as deskewing, from working. This is no longer
-    the case. Use ``--tesseract-non-ocr-timeout`` to control the timeout
-    for non-OCR operations, if needed.
-
-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
-overlapping 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. If your list of
-pages is out of numerical order, OCRmyPDF will sort it for you.
-
-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 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 <#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.
-
-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.
-          (If ``--jbig2-lossy`` is issued, then lossy JBIG2 optimization is used.
-          The decision to use lossy JBIG2 is separate from standard optimization
-          settings.)
-    *   - ``--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
-for 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`.
-
-.. note::
-
-    Image processing and PDF/A conversion can also introduce lossy transformations
-    to your PDF images, even when ``--optimize 1`` is in use.
-
-
-Digitally signed PDFs
-=====================
-
-OCRmyPDF cannot preserve digital signatures in PDFs and also add to OCR to them.
-By default, it will refuse to modify a signed PDF regardless of other settings. You can
-override this behavior with ``--invalidate-digital-signatures``; as the name suggests,
-any digital signatures will be invalidated.
-
-OCRmyPDF cannot open documents that are encrypted with a digital certificate.
-
-Versions of OCRmyPDF prior to 14.4.0 would invalidate existing digital signatures
-without warning.

docs/design_notes.rst

@@ -1,32 +0,0 @@
-.. SPDX-FileCopyrightText: 2023 James R. Barlow
-.. SPDX-License-Identifier: CC-BY-SA-4.0
-
-============
-Design notes
-============
-
-Why doesn't OCRmyPDF use PyTesseract?
-=====================================
-
-PyTesseract is a Python wrapper around the Tesseract OCR engine. When OCRmyPDF was
-first written, PyTesseract used ABI bindings to call the Tesseract library. This
-was not a good fit for OCRmyPDF because ABI bindings can be fragile.
-
-PyTesseract has since evolved calling the Tesseract executable, abandoning the ABI
-approach and using the CLI instead, just like OCRmyPDF does. If it were written from
-scratch today, OCRmyPDF might use PyTesseract.
-
-PyTesseract has more features don't particularly need PDF output, but less features
-than OCRmyPDF's API for creating PDFs.
-
-What is ``executor()``?
-=======================
-
-OCRmyPDF uses a custom concurrent executor which can support either threads or
-processes with the same interface. This is useful because OCRmyPDF can use
-either threads or processes to parallelize work, whichever is more appropriate
-for the task at hand.
-
-The interface is currently private and subject to change. In particular, if
-experiments with asyncio and anyio are successful, the interface will change.
-

docs/docker.rst

@@ -1,231 +0,0 @@
-.. SPDX-FileCopyrightText: 2022 James R. Barlow
-..
-.. SPDX-License-Identifier: CC-BY-SA-4.0
-
-.. _docker:
-
-=====================
-OCRmyPDF Docker image
-=====================
-
-OCRmyPDF is also available in Docker images that packages recent
-versions of all dependencies.
-
-For users who already have Docker installed this may be an easy and
-convenient option.
-
-On platforms other than Linux, Docker runs in a virtual machine, and so may
-be less performant. You may also want to adjust the Docker virtual machine's
-memory and CPU allocation. On Linux, the Docker image runs natively and
-performance is comparable to a system installation.
-
-.. _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
-
-.. list-table:: Docker images
-   :width: 30 20 50
-   :header-rows: 1
-
-   * - Image
-     - Architecture
-     - Description
-   * - ``jbarlow83/ocrmypdf-alpine``
-     - x86_64 only
-     - Recommended image, based on Alpine Linux.
-   * - ``jbarlow83/ocrmypdf-ubuntu``
-     - x86_64 and arm64
-     - Alternate image, based on Ubuntu. When the Alpine image is considered
-       stable and available for arm64, this image will be deprecated.
-   * - ``jbarlow83/ocrmypdf``
-     - x86_64 and arm64
-     - Currently an alias for ocrmypdf-ubuntu. When the Alpine image is
-       considered stable and available for arm64, this name point to the
-       Alpine image. If you don't about the difference between Alpine and
-       Ubuntu, use this image.
-
-To install:
-
-.. code-block:: bash
-
-   docker pull jbarlow83/ocrmypdf-alpine
-
-The ``ocrmypdf`` image is also available, but is deprecated and will be removed
-in the future.
-
-OCRmyPDF will use all available CPU cores. 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).
-For that reason we usually use the ``--rm`` argument to delete the container
-when it exits.
-
-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:{TAG}
-
-   # Example: add a tessdata_best file
-   COPY chi_tra_vert.traineddata /usr/share/tesseract-ocr/<data version>/tessdata/
-
-When creating your own image, you should always pin a specific version of the
-OCRmyPDF Docker image. This ensures that your image will not break when a new
-version of OCRmyPDF is released.
-
-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/
-
-Extending the Docker image
-==========================
-
-You can extend the Docker image with your own customizations, similar to the way
-it is extended to add language packs.
-
-Note that the Docker image is subject to change at any time. For example, the base
-image may be updated to a newer version of Ubuntu or Debian. Such changes will be
-noted in the release notes but might occur at minor versions releases, unless the
-way a "casual" user of the Docker image is affected.
-
-If you extend the Docker image, you should pin a specific version of the OCRmyPDF
-Docker image.
-
-Executing the test suite
-========================
-
-The OCRmyPDF test suite is installed with image. To run it:
-
-.. code-block:: bash
-
-   docker run --rm --entrypoint python  jbarlow83/ocrmypdf -m pytest
-
-Accessing the shell
-===================
-
-To use the shell in the Docker image:
-
-.. code-block:: bash
-
-   docker run -it --entrypoint sh  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 python -p 5000:5000  jbarlow83/ocrmypdf webservice.py
-
-We omit the ``--rm`` parameter so that the container will not be
-automatically deleted when it exits.
-
-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

@@ -1,57 +0,0 @@
-.. SPDX-FileCopyrightText: 2022 James R. Barlow
-..
-.. SPDX-License-Identifier: CC-BY-SA-4.0
-
-=====================
-Common error messages
-=====================
-
-Page already has text
-=====================
-
-.. code-block::
-
-   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.
-
-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 --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 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:
-
-.. code-block:: bash
-
-    gs -o output.pdf -dSAFER -sDEVICE=pdfwrite input.pdf
-
-``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/bitmap_vs_svg.svg

@@ -1,35 +0,0 @@
-<?xml version="1.0" encoding="UTF-8"?>
-<svg xmlns="http://www.w3.org/2000/svg" width="100%" height="100%" viewBox="0 0 915 585" xmlns:xlink="http://www.w3.org/1999/xlink">
-<defs>
-<linearGradient id="b" y2="445" gradientUnits="userSpaceOnUse" y1="179" gradientTransform="translate(0 -2.06)" x2="-29.7" x1="322">
-<stop stop-color="#333" offset="0"/>
-<stop stop-color="#fff" stop-opacity="0" offset="1"/>
-</linearGradient>
-<linearGradient id="a" y2="414" gradientUnits="userSpaceOnUse" y1="159" x2="490" x1="815">
-<stop stop-color="#33f" offset="0"/>
-<stop stop-color="#3f3fff" stop-opacity="0" offset="1"/>
-</linearGradient>
-</defs>
-<path fill="url(#b)" d="m403 247c-12 115-135 122-368 123-4.3-1.07-7.32-7.33-6-41 76-37 151-124 167-236 93 123 201 40.9 207 154z"/>
-<g stroke-width="3.45" fill="none">
-<path stroke="#000" d="m11.8 11.8h411v411l-411 0.01v-411z"/>
-<path stroke="#448" d="m489 11.7h415v411h-415v-411z"/>
-</g>
-<path d="m876 244c-12 115-133 120-366 121-6-14-10-40-3-43 76-37.3 136-106 152-218 38 48 209 101 217 140z" fill="url(#a)"/>
-<g id="RasterLarge" transform="matrix(1.36 0 0 1.28 -161 -636)">
-<path fill="#999" d="m287 730h-30v-60h20v20h10v10h10v10h20v10h40v-10h20v-20h10v-20h-10v-10h-10v-10h-40v-10h-30v-10h-20v-10h-10v-10h-10v-60h10v-10h10v-10h10v-10h90v10h30v60h-20v-10h-10v-20h-10v-10h-20v-10h-30v10h-20v10h-10v20h10v20h30v10h30v10h30v10h10v10h10v10h10v60h-10v10h-10v10h-10v10h-100v-10z"/>
-<path fill="#555" d="m297 730h-30v-10h-10v-50h20v20h10v20h10 10v10h60v-10h10v-10h10v-40h-20v-10h-20v-10h-40v-10h-20v-10h-20v-20h-10v-50h10v-10h10v-10h20v-10h70v10h30v10h10v50h-20v-20h-10v-20h-20v-10h-50v10h-10v10h-10v30h10v10h20v10h30v10h30v10h20v10h10v10h10v50h-10v20h-10v10h-20v10h-80z"/>
-<path d="m307 730h-30v-10h-20v-50h20v30h10v10h10v10h70v-10h20v-50h-10v-10h-20v-10h-40v-10h-30v-10h-10v-10h-10v-20h-10v-30h10v-20h20v-10h20v-10h50v10h30v10h20v50h-20v-30h-10v-10h-10v-10h-70v10h-10v40h10v10h10v10h30v10h40v10h20v10h10v20h10v40h-10v20h-20v10h-30v10h-50v-10z"/>
-</g>
-<g font-size="40" font-family="sans-serif" text-anchor="middle">
-<g font-size="100">
-<text y="518" x="210">Raster</text>
-<text y="518" x="695" fill="#338">Vector</text>
-</g>
-<text y="563" x="210">.jpeg  .gif  .png</text>
-<text y="563" x="696" fill="#338">.svg</text>
-</g>
-<path id="VectorLarge" fill="#005" d="m661 294v-62.5l23.4 0.184c0.678 20.8 7.32 36.3 19.9 46.4 12.7 9.93 32.1 14.9 57.9 14.9 24.1 0 42.5-4.29 55.1-12.9 12.7-8.71 19.1-21.3 19.1-37.9 0-13.2-3.86-23.4-11.6-30.5-7.59-7.11-23.7-14-48.4-20.8l-40.1-10.9c-29-7.97-49.5-17.9-61.4-29.8-11.8-11.9-17.7-28.2-17.7-48.9 0-23.3 9.15-41.4 27.4-54.3 18.3-12.9 44-19.3 77.1-19.3 14.1 0 29.6 1.41 46.4 4.23 16.8 2.7 34.7 6.68 53.7 12v58.5h-23c-2.3-19.4-9.49-33.4-21.6-41.9-11.9-8.71-30.2-13.1-54.7-13.1-21.4 0-37.7 3.99-49 12-11.1 7.85-16.7 19.3-16.7 34.4 0 13.1 4.2 23.4 12.6 30.9 8.4 7.48 26.2 14.9 53.5 22.3l37.6 10.1c27.5 7.48 47.1 17 58.8 28.7 11.8 11.5 17.7 27 17.7 46.5 0 26.6-9.42 46.7-28.3 60.2s-46.9 20.2-84.2 20.2c-16.7 0-33.7-1.53-51-4.6-18-3-35-7-53-13z"/>
-<use xlink:href="#VectorLarge" transform="matrix(.17 0 0 .17 392 313)"/>
-<use xlink:href="#RasterLarge" transform="matrix(.173 0 0 .173 -8.25 314)" height="100%" width="100%" y="0" x="0"/>
-</svg>

docs/images/logo-square-256.svg

@@ -1,239 +0,0 @@
-<?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

@@ -1,233 +0,0 @@
-<?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

@@ -1,75 +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">
-<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

@@ -1,56 +0,0 @@
-.. SPDX-FileCopyrightText: 2022 James R. Barlow
-..
-.. SPDX-License-Identifier: CC-BY-SA-4.0
-
-OCRmyPDF documentation
-======================
-
-.. figure:: images/logo.svg
-
-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 (recognized, searchable text) to existing PDFs.
-
-.. toctree::
-   :maxdepth: 1
-
-   introduction
-   release_notes
-   installation
-   languages
-   jbig2
-
-.. toctree::
-   :caption: Usage
-   :maxdepth: 2
-
-   cookbook
-   optimizer
-   docker
-   advanced
-   batch
-   cloud
-   performance
-   pdfsecurity
-   errors
-
-.. toctree::
-   :caption: Developers
-   :maxdepth: 2
-
-   api
-   plugins
-   apiref
-   design_notes
-   contributing
-   maintainers
-
-Indices and tables
-==================
-
-* :ref:`genindex`
-* :ref:`modindex`
-* :ref:`search`

docs/installation.rst

@@ -1,684 +0,0 @@
-.. SPDX-FileCopyrightText: 2022 James R. Barlow
-..
-.. SPDX-License-Identifier: CC-BY-SA-4.0
-
-===================
-Installing OCRmyPDF
-===================
-
-.. |latest| image:: https://img.shields.io/pypi/v/ocrmypdf.svg
-    :alt: OCRmyPDF latest released version on PyPI
-
-|latest|
-
-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 tesseract-osd``  |
-+-------------------------------+-----------------------------------------+
-| 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 20.04 or newer
---------------------------------
-
-.. |deb-11| image:: https://repology.org/badge/version-for-repo/debian_11/ocrmypdf.svg
-    :alt: Debian 11
-
-.. |deb-12| image:: https://repology.org/badge/version-for-repo/debian_12/ocrmypdf.svg
-    :alt: Debian 12
-
-.. |deb-unstable| image:: https://repology.org/badge/version-for-repo/debian_unstable/ocrmypdf.svg
-    :alt: Debian unstable
-
-.. |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-11| |deb-12| |deb-unstable|              |
-+-----------------------------------------------+
-| |ubu-2004| |ubu-2204|                         |
-+-----------------------------------------------+
-
-Users of Debian or Ubuntu may simply
-
-.. code-block:: bash
-
-    apt install ocrmypdf
-
-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>`__.
-
-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-37| image:: https://repology.org/badge/version-for-repo/fedora_37/ocrmypdf.svg
-    :alt: Fedora 37
-
-.. |fedora-38| image:: https://repology.org/badge/version-for-repo/fedora_38/ocrmypdf.svg
-    :alt: Fedora 38
-
-.. |fedora-rawhide| image:: https://repology.org/badge/version-for-repo/fedora_rawhide/ocrmypdf.svg
-    :alt: Fedore Rawhide
-
-+-----------------------------------------------+
-| **OCRmyPDF version**                          |
-+-----------------------------------------------+
-| |latest|                                      |
-+-----------------------------------------------+
-| |fedora-37| |fedora-38| |fedora-rawhide|      |
-+-----------------------------------------------+
-
-Users of Fedora may simply
-
-.. code-block:: bash
-
-    dnf install ocrmypdf tesseract-osd
-
-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/$USER/.local/bin' which is not on PATH.``, you may need to re-login
-or open a new shell, or manually adjust your PATH.
-
-To add JBIG2 encoding, see :ref:`jbig2`.
-
-Ubuntu 20.04 LTS
-----------------
-
-Ubuntu 20.04 includes ocrmypdf 9.6.0 - you can install that with ``apt``. To
-install a more recent version, uninstall the system-provided version of
-ocrmypdf, and install the following dependencies:
-
-.. code-block:: bash
-
-    sudo apt-get -y remove ocrmypdf  # remove system ocrmypdf, if installed
-    sudo apt-get -y update
-    sudo apt-get -y install \
-        ghostscript \
-        icc-profiles-free \
-        libxml2 \
-        pngquant \
-        python3-pip \
-        tesseract-ocr \
-        zlib1g
-
-To install ocrmypdf for the system:
-
-.. code-block:: bash
-
-    pip3 install ocrmypdf
-
-To install for the current user only:
-
-.. code-block:: bash
-
-    export PATH=$HOME/.local/bin:$PATH
-    pip3 install --user ocrmypdf
-
-To add JBIG2 encoding, see :ref:`jbig2`.
-
-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
-
-Gentoo Linux
-------------
-
-.. image:: https://repology.org/badge/version-for-repo/gentoo_ovl_guru/ocrmypdf.svg
-    :alt: Gentoo Linux
-    :target: https://repology.org/metapackage/ocrmypdf
-
-To install OCRmyPDF on Gentoo Linux, use the following commands:
-
-.. code-block:: bash
-
-    eselect repository enable guru
-    emaint sync --repo guru
-    emerge --ask app-text/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: https://formulae.brew.sh/formula/ocrmypdf
-
-OCRmyPDF is now a standard `Homebrew <https://brew.sh>`__ formula. To
-install on macOS:
-
-.. code-block:: bash
-
-    brew install ocrmypdf
-
-This will include only the English language pack. If you need other
-languages you can optionally install them all:
-
-.. code-block:: bash
-
-    brew install tesseract-lang  # Optional: Install all language packs
-
-Manual installation on macOS
-----------------------------
-
-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/>`__.
-
-Update Homebrew:
-
-.. code-block:: bash
-
-    brew update
-
-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``.
-
-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
-
-    brew install tesseract-lang  # Option 2: for all language packs
-
-Update the homebrew pip:
-
-.. code-block:: bash
-
-    pip install --upgrade pip
-
-You can then install OCRmyPDF from PyPI for the current user:
-
-.. code-block:: bash
-
-    pip install --user ocrmypdf
-
-The command line program should now be available:
-
-.. code-block:: bash
-
-    ocrmypdf --help
-
-Installing on Windows
-=====================
-
-Native Windows
---------------
-
-.. note::
-
-    Administrator privileges will be required for some of these steps.
-
-You must install the following for Windows:
-
-* Python 64-bit
-* Tesseract 64-bit
-* Ghostscript 64-bit
-
-Using the `winget <https://docs.microsoft.com/en-us/windows/package-manager/winget/>`_
-package manager:
-
-* ``winget install -e --id Python.Python.3.11``
-* ``winget install -e --id UB-Mannheim.TesseractOCR``
-
-You will need to install Ghostscript manually, `since it does not support automated
-installs anymore <https://artifex.com/news/ghostscript-10.01.0-disabling-silent-install-option>`_.
-
-* `Ghostscript download page <https://ghostscript.com/releases/gsdnld.html>`_.`
-
-(Or alternately, 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 pngquant`` (optional)
-
-Either set of commands will install the required software. At the mmoment there is no
-single command to install Windows.
-
-You may then use ``pip`` to install ocrmypdf. (This can performed by a user or
-Administrator.):
-
-* ``python3 -m pip install ocrmypdf``
-
-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 a package manager instead of the
-    Microsoft Store version.
-
-.. warning::
-
-    32-bit Windows is not supported.
-
-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``::
-
-    python310 (or later)
-    python3?-devel
-    python3?-pip
-    python3?-lxml
-    python3?-imaging
-
-       (where 3? means match the version of python3 you installed)
-
-    gcc-g++
-    ghostscript
-    libexempi3
-    libexempi-devel
-    libffi6
-    libffi-devel
-    pngquant
-    qpdf
-    libqpdf-devel
-    tesseract-ocr
-    tesseract-ocr-devel
-
-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
-
-    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.
-
-Docker
-------
-
-You can also :ref:`Install the Docker <docker>` container on Windows. Ensure that
-your command prompt can run the docker "hello world" 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
-
-    pkg install textproc/py-ocrmypdf
-
-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.
-
-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
-
-    pip install --user ocrmypdf
-
-You should then be able to run ``ocrmypdf --version`` and see that the
-latest version was located.
-
-Requirements for pip and HEAD install
--------------------------------------
-
-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.
-
-The following versions are required:
-
--  Python 3.10 or newer
--  Ghostscript 9.55 or newer
--  Tesseract 4.1.1 or newer
--  jbig2enc 0.29 or newer
--  pngquant 2.5 or newer
--  unpaper 6.1
-
-We recommend 64-bit versions of all software. (32-bit versions are not
-supported, although on Linux, they may still work.)
-
-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 3.10 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
-
-    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:
-
-.. code-block:: bash
-
-    pip install -e git+https://github.com/ocrmypdf/OCRmyPDF.git
-
-You may find it easiest to install in a virtual environment, rather than
-system-wide:
-
-.. code-block:: bash
-
-    git clone -b main https://github.com/ocrmypdf/OCRmyPDF.git
-    python3 -m venv .venv
-    source .venv/bin/activate
-    cd OCRmyPDF
-    pip install .
-
-However, ``ocrmypdf`` will only be accessible on the system PATH when
-you activate the virtual environment.
-
-To run the program:
-
-.. code-block:: bash
-
-    ocrmypdf --help
-
-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 main 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``.
-
-Note on 32-bit support
-======================
-
-Many Python libraries no longer 32-bit binary wheels for Linux. This
-includes many of the libraries that OCRmyPDF depends on, such as
-Pillow. The easiest way to express this to end users is to say we don't
-support 32-bit Linux.
-
-However, if your Linux distribution still supports 32-bit binaries, you
-can still install and use OCRmyPDF. A warning message will appear.
-In practice, OCRmyPDF may need more than 32-bit memory space to run when
-large documents are processed, so there are practical limitations to what
-users can accomplish with it. Still, for the common use case of an 32-bit
-ARM NAS or Raspberry Pi processing small documents, it should work.

docs/introduction.rst

@@ -1,225 +0,0 @@
-.. SPDX-FileCopyrightText: 2022 James R. Barlow
-..
-.. SPDX-License-Identifier: CC-BY-SA-4.0
-
-============
-Introduction
-============
-
-OCRmyPDF is a Python application and library that adds text "layers" to images in
-PDFs, making scanned image PDFs searchable. It uses OCR to guess the text
-contained in images. OCRmyPDF also supports plugins
-that enable customization of its processing steps, and it is highly tolerant
-of PDFs containing scanned images and "born digital" content that doesn't
-require text recognition.
-
-About OCR
-=========
-
-`Optical character
-recognition <https://en.wikipedia.org/wiki/Optical_character_recognition>`__
-is a technology that converts images of typed or handwritten text, such as
-in a scanned document, into computer text that can be selected, searched and copied.
-
-OCRmyPDF uses
-`Tesseract <https://github.com/tesseract-ocr/tesseract>`__, a widely
-available open source OCR engine, to perform OCR.
-
-.. _raster-vector:
-
-About PDFs
-==========
-
-PDFs are page description files that attempt 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, they are a suitable format for exchanging scanned documents.
-
-|image|
-
-A PDF page may contain multiple images, even if it appears to have only
-one image. Some scanners or scanning software may segment pages into
-monochromatic text and color regions, for example, to enhance 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 could complicate future file readability,
-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 likely more secure.
-
-There are various conformance levels and versions, such as "PDF/A-2b".
-
-In general, the preferred 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 individuals scanning documents aim for long-term readability,
-OCRmyPDF defaults to generating PDF/A-2b.
-
-PDF/A does have a few drawbacks. Some PDF viewers display an alert
-indicating that the file is in PDF/A format, which may confuse some users.
-Additionally, it tends to result in larger files than standard PDFs because
-it embeds certain resources, even if they are widely available. PDF/A
-files can be digitally signed but may not be encrypted to ensure future
-readability. Fortunately, converting from PDF/A to a regular PDF is
-straightforward, and any PDF viewer can handle PDF/A files.
-
-What OCRmyPDF does
-==================
-
-OCRmyPDF analyzes each page of a PDF to determine the required colorspace
-and resolution (DPI) for capturing all the information on that page without
-losing content. It uses
-`Ghostscript <http://ghostscript.com/>`__ to rasterize each page and subsequently
-performs OCR on the rasterized image to generate an OCR "layer." This layer
-is then integrated back into the original PDF.
-
-While it is possible to use a program like Ghostscript or ImageMagick to
-obtain an image and then run that image through Tesseract OCR, this process
-actually generates a new PDF, potentially resulting in the loss of various
-details (such as the document's metadata). In contrast, OCRmyPDF can produce
-a minimally altered PDF as the output.
-
-OCRmyPDF also offers several image processing options, such as deskew, which
-enhances the visual quality of files and the accuracy of OCR. When these
-options are utilized, the OCR layer is integrated into the processed image.
-
-By default, OCRmyPDF generates archival PDFs in the PDF/A format, which is
-a more rigid subset of PDF features designed for long-term archives. If you
-prefer regular PDFs, you can disable this feature using the
-``--output-type pdf`` option.
-
-Why you shouldn't do this manually
-==================================
-
-A PDF is similar to an HTML file, in that it contains document structure
-along with images. While some PDFs may solely display a full-page image,
-they often contain additional content that would be forfeited if not preserved.
-
-A manual process could take one of these approaches:
-
-1. Rasterize each page as an image, perform OCR on the images, and then merge the
-   output into a PDF. This method preserves the layout of each page, but
-   resamples all images potentially leading to quality loss, increased file size,
-   and the introduction of compression artifacts, among other issues.
-2. Extract each image, OCR, and combine the output into a PDF. This approach
-   loses the context in which images are used in the PDF, potentially resulting
-   in loss of information related to scaling and position of images. Some scanned
-   PDFs contain 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.
-   Reassembling these images can be challenging, and risks losing vector art
-   or text that is not part of an image.
-
-In cases where a PDF solely serves as a container for images without any
-rotation, scaling, or cropping, the second approach can be lossless.
-
-OCRmyPDF uses various strategies depending on input options and the input PDF
-itself. Generally, it rasterizes a page for OCR and then integrates the OCR
-data back into the original PDF. This approach allows it to handle complex
-PDFs and preserve their content as much as possible.
-
-Furthermore, OCRmyPDF supports a wide range of edge cases that have emerged
-during several years of development. It accommodates PDF features like
-images within Form XObjects and pages with UserUnit scaling. It also
-supports less common image formats like non-monochrome 1-bit images and
-provides warnings about files you may not want to OCR. Thanks to tools
-like pikepdf and QPDF, it can auto-repair damaged PDFs. You don't need to
-understand the intricacies of these issues; you should be able to use
-OCRmyPDF with any PDF file, and expect reasonable results.
-
-Limitations
-===========
-
-OCRmyPDF is subject to limitations imposed by the Tesseract OCR engine.
-These limitations are inherent to any software relying on Tesseract:
-
--  The OCR accuracy may not match that of commercial OCR solutions.
--  It is incapable of recognizing handwriting.
--  It may detect gibberish and report it as OCR output.
--  Results may be subpar when a document contains languages not specified
-   in the ``-l LANG`` argument.
--  Tesseract may struggle to analyze the natural reading order of documents.
-   For instance, it might fail to recognize two columns in a document and
-   attempt to join text across columns.
--  Poor quality scans can result in subpar OCR quality. In other words, the
-   quality of the OCR output depends on the quality of the input.
--  Tesseract does not provide information about the font family to which text
-   belongs.
--  Tesseract does not divide text into paragraphs or headings. It only provides
-   the text and its bounding box. As such, the generated PDF does not
-   contain any information about the document's structure.
-
-Ghostscript also imposes some limitations:
-
--  PDFs containing JPEG 2000-encoded content may be converted to JPEG
-   encoding, which may introduce compression artifacts, if Ghostscript
-   PDF/A is enabled.
--  Ghostscript may transcode grayscale and color images, potentially
-   lossily, 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 lacks an option to maintain the input image's format.
-   (Modern Ghostscript can copy JPEG images without transcoding them.)
--  Ghostscript's PDF/A conversion removes any XMP metadata that is not
-   one of the standard XMP metadata namespaces for PDFs. In particular,
-   PRISM Metadata is removed.
--  Ghostscript's PDF/A conversion may 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 using 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.
-
-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 of OCRmyPDF provides a web service front-end
-that allows files to submitted over HTTP, and the results can be downloaded.
-This is an HTTP server intended to demonstrate how OCRmyPDF can be
-integrated into a web service. It is not intended to be deployed on the
-public internet and does not provide any security measures.
-
-In addition, the following third-party integrations are available:
-
--  `Paperless-ngx <https://docs.paperless-ngx.com/>`__ is a free software
-   document management system that uses OCRmyPDF to perform OCR on
-   uploaded documents.
--  `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

@@ -1,75 +0,0 @@
-.. SPDX-FileCopyrightText: 2022 James R. Barlow
-..
-.. SPDX-License-Identifier: CC-BY-SA-4.0
-
-.. _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
-CCITT encoding will be used for monochrome images.
-
-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.
-
-JBIG encoding is automatically provided by these OCRmyPDF packages:
-- Docker image (both Ubuntu and Alpine)
-- Snap package
-- ArchLinux AUR package
-- Alpine Linux package
-- Homebrew on macOS
-
-For all other platforms, you would need to build the 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. On Fedora (35) they are packaged
-as libtool and leptonica-devel.
-
-Lossy mode JBIG2
-================
-
-OCRmyPDF provides lossy mode JBIG2 as an advanced and potentially dangerous
-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. In general,
-this mode should not be used for archival purposes, should not be used when
-the original document is not available or will be destroyed, and should
-not be used when numbers present in the document are important, because
-there is a risk of 6/8 and 8/6 substitution errors.
-
-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.
-
-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.
-
-You can adjust the threshold for JBIG2 compression with the
-``--jbig2-threshold``. The default is 0.85, meaning that if two symbols
-are 85% similar, they will be compressed together.
-
-*Due to an oversight, ocrmypdf v7.0 and v7.1 used lossy mode by
-default.*

docs/languages.rst

@@ -1,107 +0,0 @@
-.. SPDX-FileCopyrightText: 2022 James R. Barlow
-..
-.. SPDX-License-Identifier: CC-BY-SA-4.0
-
-.. _lang-packs:
-
-====================================
-Installing additional language packs
-====================================
-
-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/main/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``.
-
-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
-
-   # Install Chinese Simplified language pack
-   apt-get install tesseract-ocr-chi-sim
-
-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``.
-
-Fedora users
-============
-
-.. code-block:: bash
-
-   # Display a list of all Tesseract language packs
-   dnf search tesseract
-
-   # Install Chinese Simplified language pack
-   dnf install tesseract-langpack-chi_sim
-
-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 omitted)
-   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

@@ -1,67 +0,0 @@
-.. SPDX-FileCopyrightText: 2022 James R. Barlow
-..
-.. SPDX-License-Identifier: CC-BY-SA-4.0
-
-================
-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.
-
-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, as described in the
-installation documentation.
-
-32-bit Linux support
---------------------
-
-If you maintain a Linux distribution that supports 32-bit x86 or ARM, OCRmyPDF
-should continue to work as long as all of its dependencies continue to be
-available in 32-bit form. Please note we do not test on 32-bit platforms.

docs/optimizer.rst

@@ -1,100 +0,0 @@
-.. SPDX-FileCopyrightText: 2022 James R. Barlow
-..
-.. SPDX-License-Identifier: CC-BY-SA-4.0
-
-================
-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.
-
-.. list-table:: Title
-   :widths: 33 6 60
-   :header-rows: 1
-
-    * - Optimization level
-      - Shorthand
-      - Description
-    * - ``--optimize 0``
-      - ``-O0``
-      - Disable most optimizations.
-    * - ``--optimize 1`` (default)
-      - ``-O1``
-      - Safe and lossless optimizations.
-    * - ``--optimize 2``
-      - ``-O2``
-      - Safe and lossy optimizations.
-    * - ``--optimize 3``
-      - ``-O3``
-      - Aggressive lossy optimizations.
-
-The exact type of optimizations performed will vary over time, and depend on
-the availability of third-party tools.
-
-Despite optimizations, OCRmyPDF might still increase the overall file size,
-since it must embed information about the recognized text, and depending on the
-settings chosen, may not be able to represent the output file as compactly as
-the input file.
-
-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 convert
-monochrome images to CCITT G4. Since this is lossless, 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, in
-exchange for a slight increase in file size.
-
-To disable this optimization and all others, use ``ocrmypdf --optimize 0 ...``
-or the shorthand ``-O0``.
-
-Adobe Acrobat might not report the file as being "fast web view".
-
-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

@@ -1,125 +0,0 @@
-.. SPDX-FileCopyrightText: 2022 James R. Barlow
-..
-.. SPDX-License-Identifier: CC-BY-SA-4.0
-
-===================
-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 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>`__.
-
-If you do not trust a PDF or its source, do not open it or use OCRmyPDF
-on it. Consider using a Docker container or virtual machine to isolate
-an untrusted PDF from your system.
-
-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.
-
-Password protected PDFs
-=======================
-
-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 mark it as "(SECURED)". Password security can
-also request certain restrictions on the PDF, but anyone can remove these
-restrictions if they have either the owner *or* user password. Passwords
-mainly present a barrier for casual users.
-
-OCRmyPDF cannot remove passwords from PDFs. If you want to remove a
-password from a PDF, you must use other software, such as ``qpdf``.
-
-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. To
-remove the password from a using QPDF, use:
-
-.. code-block:: bash
-
-   qpdf --decrypt --password='abc123' input.pdf no_password.pdf
-
-Then you can run OCRmyPDF on the file.
-
-In its default mode, OCRmyPDF generates PDF/A. Passwords may not be set on PDF/A
-documents. If you want to set a password on the output PDF, you must
-specify ``--output-type pdf``.
-
-Signature images
-================
-
-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.
-
-Digital signatures
-==================
-
-Important documents can be digitally signed and certified to attest to
-their authorship, approval or execution of a legal agreement. OCRmyPDF
-will detect signed PDFs and will not modify them, unless the
-``--invalidate-digital-signatures`` option is used, which will
-invalidate any signatures. (The signature may still be present in the PDF
-if opened, but PDF readers will not validate it.)
-
-A digital signature adds a cryptographic hash of the document to the
-document, so tamper protection is provided. That also precludes OCRmyPDF
-from modifying the document and preserving the signature.
-
-Digital signatures are not the same as a signature image. A digital
-signature is a cryptographic hash of the document that is encrypted with
-the author's private key. The signature is decrypted with the author's
-public key. The public key is usually distributed by a certificate
-authority. The signature is then verified by the PDF reader. If the
-document is modified, the signature will be invalidated.
-
-Certificate-encrypted PDFs
-==========================
-
-PDFs can be encrypted with a certificate. This is a more secure form of
-encryption than a password. The certificate is usually issued by a
-certificate authority. A certificate is used to encrypt the document using
-the public key for the benefit of a specific recipient who possesses
-the private key.
-
-OCRmyPDF cannot open certificate-encrypted PDFs. If you have the
-certificate, you can use other PDF software, such as Acrobat, to
-decrypt the PDF.

docs/performance.rst

@@ -1,26 +0,0 @@
-.. SPDX-FileCopyrightText: 2022 James R. Barlow
-..
-.. SPDX-License-Identifier: CC-BY-SA-4.0
-
-===========
-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/plugins.rst

@@ -1,235 +0,0 @@
-.. SPDX-FileCopyrightText: 2022 James R. Barlow
-..
-.. SPDX-License-Identifier: CC-BY-SA-4.0
-
-=======
-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 ``pyproject.toml`` would need to contain the following, for a plugin
-named ``ocrmypdf-exampleplugin``:
-
-.. code-block:: toml
-
-    [project]
-    name = "ocrmypdf-exampleplugin"
-
-    [project.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.
-
-
-Suppressing or overriding other plugins
----------------------------------------
-
-.. autofunction:: ocrmypdf.pluginspec.initialize
-
-Custom command line arguments
------------------------------
-
-.. autofunction:: ocrmypdf.pluginspec.add_options
-
-.. autofunction:: ocrmypdf.pluginspec.check_options
-
-Execution and progress reporting
---------------------------------
-
-.. autoclass:: ocrmypdf.pluginspec.ProgressBar
-    :members:
-    :special-members: __init__, __enter__, __exit__
-
-.. autoclass:: ocrmypdf.pluginspec.Executor
-    :members:
-    :special-members: __call__
-
-.. 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
-
-PDF optimization
-----------------
-
-.. autofunction:: ocrmypdf.pluginspec.optimize_pdf
-
-.. autofunction:: ocrmypdf.pluginspec.is_optimization_enabled

misc/batch.py

@@ -1,53 +0,0 @@
-#!/usr/bin/env python3
-# SPDX-FileCopyrightText: 2016 findingorder <https://github.com/findingorder>
-# SPDX-License-Identifier: MIT
-
-"""Example of using ocrmypdf as a library in a script.
-
-This script will recursively search a directory for PDF files and run OCR on
-them. It will log the results. It runs OCR on every file, even if it already
-has text. OCRmyPDF will detect files that already have text.
-
-You should edit this script to meet your needs.
-"""
-
-from __future__ import annotations
-
-import logging
-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

@@ -1,313 +0,0 @@
-# SPDX-FileCopyrightText: 2021 Frank Pille
-# SPDX-FileCopyrightText: 2020 Alex Willner
-# SPDX-License-Identifier: MIT
-
-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)
---invalidate-digital-signatures (remove digital signatures from PDF)
---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))
---jbig2-threshold               (set JBIG2 threshold (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)
---color-conversion-strategy     (select color conversion strategy)
-"
-
-    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_color-conversion-strategy()
-{
-    local choices="LeaveColorUnchanged (default)
-CMYK (convert to CMYK)
-Gray (convert to grayscale)
-RGB (convert to RGB)
-UseDeviceIndependentColor (convert with device independent color)"
-
-    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 )'}' -- "$cur" ) )
-            return 0
-            ;;
-        -v|--verbose)
-            __ocrmypdf_verbose
-            return 0
-            ;;
-        -O|--optimize)
-            __ocrmypdf_optimize
-            return 0
-            ;;
-        --pdf-renderer)
-            __ocrmypdf_pdf-renderer
-            return 0
-            ;;
-        --pdfa-image-compression)
-            __ocrmypdf_pdfa-image-compression
-            return 0
-            ;;
-        --tesseract-pagesegmode)
-            __ocrmypdf_tesseract-pagesegmode
-            return 0
-            ;;
-        --tesseract-oem)
-            __ocrmypdf_tesseract-oem
-            return 0
-            ;;
-        --tesseract-thresholding)
-            __ocrmypdf_tesseract-thresholding
-            return 0
-            ;;
-
-        --title|--author|--subject|--keywords|--unpaper-args|--pages|--plugin|\
-        --jpeg-quality|--png-quality|--image-dpi|--oversample|--skip-big|--max-image-mpixels|\
-        --tesseract-timeout|--rotate-pages-threshold|--fast-web-view)
-            # argument required but no completions available
-            return 0
-            ;;
-        --tesseract-config|--user-words|--user-patterns|--sidecar)
-            _filedir
-            return 0
-            ;;
-        --color-conversion-strategy)
-            __ocrmypdf_color-conversion-strategy
-            return 0
-            ;;
-    esac
-
-    return 1
-}
-
-_ocrmypdf()
-{
-    local OLDIFS="$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

@@ -1,156 +0,0 @@
-# SPDX-FileCopyrightText: 2022 James R. Barlow
-# SPDX-License-Identifier: MIT
-
-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-text -d "skip OCR on any pages that already contain text"
-complete -c ocrmypdf -l redo-ocr -d "redo OCR on any pages that seem to have OCR already"
-complete -c ocrmypdf -l invalidate-digital-signatures -d "invalidate digital signatures and allow OCR to proceed"
-
-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 jbig2-threshold -d "JBIG2 compression threshold (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"
-
-function __fish_ocrmypdf_color_conversion_strategy
-    echo -e "LeaveColorUnchanged\t"(_ "do not convert color spaces (default)")
-    echo -e "CMYK\t"(_ "convert all color spaces to CMYK")
-    echo -e "Gray\t"(_ "convert all color spaces to grayscale")
-    echo -e "RGB\t"(_ "convert all color spaces to RGB")
-    echo -e "UseDeviceIndependentColor\t"(_ "convert all color spaces to ICC-based color spaces")
-end
-
-complete -c ocrmypdf -x -l color-conversion-strategy -a '(__fish_ocrmypdf_color_conversion_strategy)' -d "set color conversion strategy"
-
-function __fish_ocrmypdf_input_file_given
-    set -l tokens (commandline -opc)
-    for token in $tokens
-        if string match -q -r '^-' -- $token
-            continue
-        end
-        if test -f "$token"
-            return 0
-        end
-    end
-    return 1
-end
-
-complete -c ocrmypdf -x -n 'not __fish_ocrmypdf_input_file_given' -a "(__fish_complete_suffix .pdf)" -d "input file"

misc/docker-compose.example.yml

@@ -1,17 +0,0 @@
-# SPDX-FileCopyrightText: 2022 James R. Barlow
-# SPDX-License-Identifier: MIT
----
-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

@@ -1,68 +0,0 @@
-# SPDX-FileCopyrightText: 2022 James R Barlow: https://github.com/jbarlow83
-# SPDX-License-Identifier: MIT
-
-"""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
-    )
-"""
-
-from __future__ import annotations
-
-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/screencast/README.md

@@ -1,31 +0,0 @@
-<!-- SPDX-License-Identifier: CC-BY-SA-4.0 -->
-
-To regenerate
-=============
-
-Using asciinema and svg-term (`npm install -g svg-term-cli`).
-
-Create `~/.config/asciinema/config` to disable prompt.
-
-```
-[record]
-
-command = fish --init-command 'alias fish_prompt="echo \>\ "'
-```
-
-Run asciinema
-
-```
-asciinema rec new_input.cast
-```
-
-Re-record faster version with fewer pauses
-
-```
-asciinema rec demo.cast -c "asciinema play new_input.cast --speed 2 --idle-time-limit 0.5"
-```
-
-Convert to SVG
-```
-svg-term --in=misc/screencast/demo.cast --out=misc/screencast/demo.svg --window
-```

misc/screencast/demo.cast

@@ -1,65 +0,0 @@
-{"version": 2, "width": 131, "height": 24, "timestamp": 1687247006, "env": {"SHELL": "/usr/bin/fish", "TERM": "xterm-256color"}}
-[0.103649, "o", "\u001b[?2004h\u001b]7; \u0007"]
-[0.104223, "o", "\u001b]0;fish  \u0007\u001b[30m\u001b(B\u001b[m\r> \u001b[K\r\u001b[C\u001b[C"]
-[0.604542, "o", "o\r\u001b[3C\b\u001b[38;2;255;0;0mo\r\u001b[3C\u001b[30m\u001b(B\u001b[m\u001b[38;2;85;85;85mcrmypdf multipage.pdf multipage_with_ocr.pdf\r\u001b[3C\u001b[30m\u001b(B\u001b[m"]
-[0.679571, "o", "\u001b[38;2;255;0;0mc\u001b[38;2;85;85;85mrmypdf multipage.pdf multipage_with_ocr.pdf\r\u001b[4C\u001b[30m\u001b(B\u001b[m"]
-[0.767271, "o", "\u001b[38;2;255;0;0mr\u001b[38;2;85;85;85mmypdf multipage.pdf multipage_with_ocr.pdf\r\u001b[5C\u001b[30m\u001b(B\u001b[m"]
-[0.814505, "o", "\u001b[38;2;255;0;0mm\u001b[38;2;85;85;85mypdf multipage.pdf multipage_with_ocr.pdf\r\u001b[6C\u001b[30m\u001b(B\u001b[m"]
-[0.938919, "o", "\u001b[38;2;255;0;0my\u001b[38;2;85;85;85mpdf multipage.pdf multipage_with_ocr.pdf\r\u001b[7C\u001b[30m\u001b(B\u001b[m"]
-[0.967347, "o", "\u001b[38;2;255;0;0mp\u001b[38;2;85;85;85mdf multipage.pdf multipage_with_ocr.pdf\r\u001b[8C\u001b[30m\u001b(B\u001b[m"]
-[1.009954, "o", "\u001b[38;2;255;0;0md\u001b[38;2;85;85;85mf multipage.pdf multipage_with_ocr.pdf\r\u001b[9C\u001b[30m\u001b(B\u001b[m"]
-[1.034488, "o", "\u001b[38;2;255;0;0mf\u001b[38;2;85;85;85m multipage.pdf multipage_with_ocr.pdf\r\u001b[10C\u001b[30m\u001b(B\u001b[m\b\b\b\b\b\b\b\b\u001b[38;2;0;95;215mocrmypdf\u001b[38;2;85;85;85m multipage.pdf multipage_with_ocr.pdf\r\u001b[10C\u001b[30m\u001b(B\u001b[m"]
-[1.069226, "o", "\u001b[38;2;0;95;215m \u001b[38;2;85;85;85mmultipage.pdf multipage_with_ocr.pdf\r\u001b[11C\u001b[30m\u001b(B\u001b[m\b \u001b[38;2;85;85;85mmultipage.pdf multipage_with_ocr.pdf\r\u001b[11C\u001b[30m\u001b(B\u001b[m"]
-[1.569682, "o", "-\u001b[K\r\u001b[12C\u001b[38;2;85;85;85m-version\r\u001b[12C\u001b[30m\u001b(B\u001b[m\b\u001b[38;2;0;175;255m-\u001b[38;2;85;85;85m-version\r\u001b[12C\u001b[30m\u001b(B\u001b[m"]
-[1.642096, "o", "\u001b[38;2;0;175;255m-\u001b[38;2;85;85;85mversion\r\u001b[13C\u001b[30m\u001b(B\u001b[m"]
-[1.71793, "o", "\u001b[38;2;0;175;255ms\u001b[30m\u001b(B\u001b[m\u001b[K\r\u001b[14C"]
-[1.771483, "o", "\u001b[38;2;0;175;255mk\r\u001b[15C\u001b[30m\u001b(B\u001b[m"]
-[1.864664, "o", "\u001b[38;2;0;175;255mi\r\u001b[16C\u001b[30m\u001b(B\u001b[m"]
-[1.876085, "o", "\u001b[38;2;0;175;255mp\r\u001b[17C\u001b[30m\u001b(B\u001b[m"]
-[2.092979, "o", "\u001b[38;2;0;175;255m-\r\u001b[18C\u001b[30m\u001b(B\u001b[m"]
-[2.138821, "o", "\u001b[38;2;0;175;255mt\r\u001b[19C\u001b[30m\u001b(B\u001b[m"]
-[2.18017, "o", "\u001b[38;2;0;175;255me\r\u001b[20C\u001b[30m\u001b(B\u001b[m"]
-[2.268222, "o", "\u001b[38;2;0;175;255mx\r\u001b[21C\u001b[30m\u001b(B\u001b[m"]
-[2.277031, "o", "\u001b[38;2;0;175;255mt\r\u001b[22C\u001b[30m\u001b(B\u001b[m"]
-[2.322469, "o", "\u001b[38;2;0;175;255m \r\u001b[23C\u001b[30m\u001b(B\u001b[m\b \r\u001b[23C"]
-[2.824696, "o", "m\r\u001b[24C\b\u001b[38;2;0;175;255m\u001b[4mm\r\u001b[24C\u001b[30m\u001b(B\u001b[m\u001b[38;2;85;85;85masks.pdf \r\u001b[24C\u001b[30m\u001b(B\u001b[m"]
-[2.923234, "o", "\u001b[38;2;0;175;255m\u001b[4mu\u001b[30m\u001b(B\u001b[m\u001b[K\r\u001b[25C\u001b[38;2;85;85;85mltipage.pdf \r\u001b[25C\u001b[30m\u001b(B\u001b[m"]
-[2.960685, "o", "\u001b[38;2;0;175;255m\u001b[4ml\u001b[38;2;85;85;85m\u001b[24mtipage.pdf \r\u001b[26C\u001b[30m\u001b(B\u001b[m"]
-[3.03365, "o", "\u001b[38;2;0;175;255m\u001b[4mt\u001b[38;2;85;85;85m\u001b[24mipage.pdf \r\u001b[27C\u001b[30m\u001b(B\u001b[m"]
-[3.479338, "o", "\u001b[38;2;0;175;255m\u001b[4mipage.pdf \r\u001b[37C\u001b[30m\u001b(B\u001b[m\b \r\u001b[37C"]
-[3.754818, "o", "m\r\u001b[38C\b\u001b[38;2;0;175;255m\u001b[4mm\r\u001b[38C\u001b[30m\u001b(B\u001b[m\u001b[38;2;85;85;85masks.pdf \r\u001b[38C\u001b[30m\u001b(B\u001b[m"]
-[3.873318, "o", "\u001b[38;2;0;175;255m\u001b[4mu\u001b[30m\u001b(B\u001b[m\u001b[K\r\u001b[39C\u001b[38;2;85;85;85mltipage.pdf \r\u001b[39C\u001b[30m\u001b(B\u001b[m"]
-[3.926829, "o", "\u001b[38;2;0;175;255m\u001b[4ml\u001b[38;2;85;85;85m\u001b[24mtipage.pdf \r\u001b[40C\u001b[30m\u001b(B\u001b[m"]
-[4.272251, "o", "\u001b[38;2;0;175;255m\u001b[4mtipage.pdf \r\u001b[51C\u001b[30m\u001b(B\u001b[m\b \r\u001b[51C"]
-[4.343464, "o", "\r\u001b[50C"]
-[4.416286, "o", "\r\u001b[49C"]
-[4.490574, "o", "\r\u001b[48C"]
-[4.564115, "o", "\r\u001b[47C"]
-[4.630398, "o", "\r\u001b[46C"]
-[4.76825, "o", "\u001b[38;2;0;175;255m\u001b[4m_.pd\u001b[30m\u001b(B\u001b[mf \r\u001b[47C\u001b[10D\u001b[38;2;0;175;255mmultipage_.pdf\u001b[30m\u001b(B\u001b[m \r\u001b[47C"]
-[5.012506, "o", "\u001b[38;2;0;175;255mo.pd\u001b[30m\u001b(B\u001b[mf \r\u001b[48C\u001b[3C\u001b[38;2;0;175;255mf\u001b[30m\u001b(B\u001b[m \r\u001b[48C"]
-[5.053615, "o", "\u001b[38;2;0;175;255mc.pd\u001b[30m\u001b(B\u001b[mf \r\u001b[49C\u001b[3C\u001b[38;2;0;175;255mf\u001b[30m\u001b(B\u001b[m \r\u001b[49C"]
-[5.103957, "o", "\u001b[38;2;0;175;255mr.pd\u001b[30m\u001b(B\u001b[mf \r\u001b[50C\u001b[3C\u001b[38;2;0;175;255mf\u001b[30m\u001b(B\u001b[m \r\u001b[50C"]
-[5.226183, "o", "\r\u001b[55C"]
-[5.728321, "o", "\r\n\u001b[30m\u001b(B\u001b[m\u001b[?2004l\u001b]0;ocrmypdf --skip-text multipage.pdf multipage_ocr.pdf  /home/jb/src/ocrmypdf/tests/resources\u0007\u001b[30m\u001b(B\u001b[m\r"]
-[5.801032, "o", "\rScanning contents:   0%|                                                                                   | 0/6 [00:00<?, ?page/s]"]
-[5.802664, "o", "\rScanning contents: 100%|█████████████████████████████████████████████████████████████████████████| 6/6 [00:00<00:00, 1270.68page/s]\r\n"]
-[5.802747, "o", "Start processing 6 pages concurrently\r\n"]
-[5.803488, "o", "\rOCR:   0%|                                                                                             | 0.0/6.0 [00:00<?, ?page/s]"]
-[5.804896, "o", "\r                                                                                                                                   \r    4 skipping all processing on this page\r\n\rOCR:   0%|                                                                                             | 0.0/6.0 [00:00<?, ?page/s]"]
-[5.896969, "o", "\rOCR:  25%|█████████████████████▎                                                               | 1.5/6.0 [00:00<00:00,  8.12page/s]"]
-[6.170021, "o", "\rOCR:  42%|███████████████████████████████████▍                                                 | 2.5/6.0 [00:00<00:01,  3.05page/s]"]
-[6.292338, "o", "\rOCR:  58%|█████████████████████████████████████████████████▌                                   | 3.5/6.0 [00:00<00:00,  3.39page/s]"]
-[6.586017, "o", "\rOCR:  75%|███████████████████████████████████████████████████████████████▊                     | 4.5/6.0 [00:01<00:00,  2.49page/s]"]
-[7.087058, "o", "\rOCR:  92%|█████████████████████████████████████████████████████████████████████████████▉       | 5.5/6.0 [00:06<00:00,  1.98s/page]\rOCR: 100%|█████████████████████████████████████████████████████████████████████████████████████| 6.0/6.0 [00:06<00:00,  1.09s/page]\r\nPostprocessing...\r\n"]
-[7.104927, "o", "\rPDF/A conversion:   0%|                                                                                    | 0/6 [00:00<?, ?page/s]"]
-[7.607392, "o", "\rPDF/A conversion:  50%|██████████████████████████████████████                                      | 3/6 [00:01<00:01,  1.61page/s]"]
-[7.653781, "o", "\rPDF/A conversion:  83%|███████████████████████████████████████████████████████████████▎            | 5/6 [00:01<00:00,  2.90page/s]"]
-[7.774532, "o", "\rPDF/A conversion: 100%|████████████████████████████████████████████████████████████████████████████| 6/6 [00:02<00:00,  2.71page/s]\r\n"]
-[7.778252, "o", "\u001b[33mSome input metadata could not be copied because it is not permitted in PDF/A. You may wish to examine the output PDF's XMP metadata.\u001b[0m\r\n"]
-[8.280789, "o", "\rRecompressing JPEGs: 0image [00:00, ?image/s]\rRecompressing JPEGs: 0image [00:00, ?image/s]\r\n\rDeflating JPEGs:   0%|                                                                                    | 0/4 [00:00<?, ?image/s]\rDeflating JPEGs: 100%|███████████████████████████████████████████████████████████████████████████| 4/4 [00:00<00:00, 238.28image/s]\r\n"]
-[8.28149, "o", "\rJBIG2: 0item [00:00, ?item/s]\rJBIG2: 0item [00:00, ?item/s]\r\n"]
-[8.289998, "o", "Image optimization ratio: 1.01 savings: 1.3%\r\nTotal file size ratio: 1.02 savings: 1.6%\r\n"]
-[8.291209, "o", "Output file is a PDF/A-2B (as expected)\r\n"]
-[8.361316, "o", "\u001b[2m⏎\u001b(B\u001b[m                                                                                                                                  \r⏎ \r\u001b[K\u001b[?2004h\u001b]0;fish /home/jb/src/ocrmypdf/tests/resources\u0007\u001b[30m\u001b(B\u001b[m> \u001b[K\r\u001b[C\u001b[C"]
-[8.862206, "o", "\r\n\u001b[30m\u001b(B\u001b[m\u001b[30m\u001b(B\u001b[m\u001b[?2004l"]

misc/synology.py

@@ -1,75 +0,0 @@
-#!/bin/env python3
-# SPDX-FileCopyrightText: 2017 Enantiomerie
-# SPDX-License-Identifier: MIT
-
-"""Example OCRmyPDF for Synology NAS."""
-
-from __future__ import annotations
-
-# 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',
-)
-
-start_dir = sys.argv[1] if len(sys.argv) > 1 else '.'
-
-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

@@ -1,334 +0,0 @@
-#!/usr/bin/env python3
-# SPDX-FileCopyrightText: 2019 Ian Alexander <https://github.com/ianalexander>
-# SPDX-FileCopyrightText: 2020 James R Barlow <https://github.com/jbarlow83>
-# SPDX-License-Identifier: MIT
-
-"""Watch a directory for new PDFs and OCR them."""
-
-# Do not enable annotations!
-# https://github.com/tiangolo/typer/discussions/598
-# from __future__ import annotations
-
-import json
-import logging
-import shutil
-import sys
-import time
-from datetime import datetime
-from enum import Enum
-from pathlib import Path
-from typing import Annotated, Any
-
-import pikepdf
-import typer
-from dotenv import load_dotenv
-from watchdog.events import PatternMatchingEventHandler
-from watchdog.observers import Observer
-from watchdog.observers.polling import PollingObserver
-
-import ocrmypdf
-
-load_dotenv()
-
-
-# pylint: disable=logging-format-interpolation
-app = typer.Typer(name="ocrmypdf-watcher")
-
-log = logging.getLogger('ocrmypdf-watcher')
-
-
-class LoggingLevelEnum(str, Enum):
-    """Enum for logging levels."""
-
-    DEBUG = "DEBUG"
-    INFO = "INFO"
-    WARNING = "WARNING"
-    ERROR = "ERROR"
-    CRITICAL = "CRITICAL"
-
-
-def get_output_dir(root: Path, basename: str, output_dir_year_month: bool) -> Path:
-    if output_dir_year_month:
-        today = datetime.today()
-        output_directory_year_month = 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 = root / basename
-    return output_path
-
-
-def wait_for_file_ready(
-    file_path: Path, poll_new_file_seconds: int, retries_loading_file: int
-):
-    # 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.
-
-    tries = retries_loading_file + 1
-    while tries:
-        try:
-            with pikepdf.Pdf.open(file_path) as pdf:
-                log.debug(f"{file_path} ready with {pdf.pages} pages")
-                return True
-        except (FileNotFoundError, OSError) 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)
-            tries -= 1
-        except pikepdf.PdfError as e:
-            log.info(f"File {file_path} is not full written yet")
-            log.debug("Exception was", exc_info=e)
-            time.sleep(poll_new_file_seconds)
-            tries -= 1
-
-    return False
-
-
-def execute_ocrmypdf(
-    *,
-    file_path: Path,
-    archive_dir: Path,
-    output_dir: Path,
-    ocrmypdf_kwargs: dict[str, Any],
-    on_success_delete: bool,
-    on_success_archive: bool,
-    poll_new_file_seconds: int,
-    retries_loading_file: int,
-    output_dir_year_month: bool,
-):
-    output_path = get_output_dir(output_dir, file_path.name, output_dir_year_month)
-
-    log.info("-" * 20)
-    log.info(f'New file: {file_path}. Waiting until fully written...')
-    if not wait_for_file_ready(file_path, poll_new_file_seconds, retries_loading_file):
-        log.info(f"Gave up waiting for {file_path} to become ready")
-        return
-    log.info(f'Attempting to OCRmyPDF to: {output_path}')
-
-    log.debug(
-        f'OCRmyPDF input_file={file_path} output_file={output_path} '
-        f'kwargs: {ocrmypdf_kwargs}'
-    )
-    exit_code = ocrmypdf.ocr(
-        input_file=file_path,
-        output_file=output_path,
-        **ocrmypdf_kwargs,
-    )
-    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_dir}')
-            shutil.move(file_path, f'{archive_dir}/{file_path.name}')
-        else:
-            log.info('OCR is done')
-    else:
-        log.info('OCR is done')
-
-
-class HandleObserverEvent(PatternMatchingEventHandler):
-    def __init__(
-        self,
-        patterns=None,
-        ignore_patterns=None,
-        ignore_directories=False,
-        case_sensitive=False,
-        settings={},
-    ):
-        super().__init__(
-            patterns=patterns,
-            ignore_patterns=ignore_patterns,
-            ignore_directories=ignore_directories,
-            case_sensitive=case_sensitive,
-        )
-        self._settings = settings
-
-    def on_any_event(self, event):
-        if event.event_type in ['created']:
-            execute_ocrmypdf(file_path=Path(event.src_path), **self._settings)
-
-
-@app.command()
-def main(
-    input_dir: Annotated[
-        Path,
-        typer.Argument(
-            envvar='OCR_INPUT_DIRECTORY',
-            exists=True,
-            file_okay=False,
-            dir_okay=True,
-            readable=True,
-            resolve_path=True,
-        ),
-    ] = '/input',
-    output_dir: Annotated[
-        Path,
-        typer.Argument(
-            envvar='OCR_OUTPUT_DIRECTORY',
-            exists=True,
-            file_okay=False,
-            dir_okay=True,
-            writable=True,
-            resolve_path=True,
-        ),
-    ] = '/output',
-    archive_dir: Annotated[
-        Path,
-        typer.Argument(
-            envvar='OCR_ARCHIVE_DIRECTORY',
-            exists=True,
-            file_okay=False,
-            dir_okay=True,
-            writable=True,
-            resolve_path=True,
-        ),
-    ] = '/processed',
-    output_dir_year_month: Annotated[
-        bool,
-        typer.Option(
-            envvar='OCR_OUTPUT_DIRECTORY_YEAR_MONTH',
-            help='Create a subdirectory in the output directory for each year and month',
-        ),
-    ] = False,
-    on_success_delete: Annotated[
-        bool,
-        typer.Option(
-            envvar='OCR_ON_SUCCESS_DELETE',
-            help='Delete the input file after successful OCR',
-        ),
-    ] = False,
-    on_success_archive: Annotated[
-        bool,
-        typer.Option(
-            envvar='OCR_ON_SUCCESS_ARCHIVE',
-            help='Archive the input file after successful OCR',
-        ),
-    ] = False,
-    deskew: Annotated[
-        bool,
-        typer.Option(
-            envvar='OCR_DESKEW',
-            help='Deskew the input file before OCR',
-        ),
-    ] = False,
-    ocr_json_settings: Annotated[
-        str,
-        typer.Option(
-            envvar='OCR_JSON_SETTINGS',
-            help='JSON settings to pass to OCRmyPDF (JSON string or file path)',
-        ),
-    ] = None,
-    poll_new_file_seconds: Annotated[
-        int,
-        typer.Option(
-            envvar='OCR_POLL_NEW_FILE_SECONDS',
-            help='Seconds to wait before polling a new file',
-            min=0,
-        ),
-    ] = 1,
-    use_polling: Annotated[
-        bool,
-        typer.Option(
-            envvar='OCR_USE_POLLING',
-            help='Use polling instead of filesystem events',
-        ),
-    ] = False,
-    retries_loading_file: Annotated[
-        int,
-        typer.Option(
-            envvar='OCR_RETRIES_LOADING_FILE',
-            help='Number of times to retry loading a file before giving up',
-            min=0,
-        ),
-    ] = 5,
-    loglevel: Annotated[
-        LoggingLevelEnum,
-        typer.Option(
-            envvar='OCR_LOGLEVEL',
-            help='Logging level',
-        ),
-    ] = LoggingLevelEnum.INFO,
-    patterns: Annotated[
-        str,
-        typer.Option(
-            envvar='OCR_PATTERNS',
-            help='File patterns to watch',
-        ),
-    ] = '*.pdf,*.PDF',
-):
-    ocrmypdf.configure_logging(
-        verbosity=(
-            ocrmypdf.Verbosity.default
-            if loglevel != LoggingLevelEnum.DEBUG
-            else ocrmypdf.Verbosity.debug
-        ),
-        manage_root_logger=True,
-    )
-    log.setLevel(loglevel.value)
-    log.info(
-        f"Starting OCRmyPDF watcher with config:\n"
-        f"Input Directory: {input_dir}\n"
-        f"Output Directory: {output_dir}\n"
-        f"Output Directory Year & Month: {output_dir_year_month}\n"
-        f"Archive Directory: {archive_dir}"
-    )
-    log.debug(
-        f"INPUT_DIRECTORY: {input_dir}\n"
-        f"OUTPUT_DIRECTORY: {output_dir}\n"
-        f"OUTPUT_DIRECTORY_YEAR_MONTH: {output_dir_year_month}\n"
-        f"ARCHIVE_DIRECTORY: {archive_dir}\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"RETRIES_LOADING_FILE: {retries_loading_file}\n"
-        f"USE_POLLING: {use_polling}\n"
-        f"LOGLEVEL: {loglevel.value}"
-    )
-
-    if ocr_json_settings and Path(ocr_json_settings).exists():
-        json_settings = json.loads(Path(ocr_json_settings).read_text())
-    else:
-        json_settings = json.loads(ocr_json_settings or '{}')
-
-    if 'input_file' in json_settings or 'output_file' in json_settings:
-        log.error(
-            'OCR_JSON_SETTINGS (--ocr-json-settings) may not specify input/output file'
-        )
-        sys.exit(1)
-
-    handler = HandleObserverEvent(
-        patterns=patterns.split(','),
-        settings={
-            'archive_dir': archive_dir,
-            'output_dir': output_dir,
-            'ocrmypdf_kwargs': json_settings | {'deskew': deskew},
-            'on_success_delete': on_success_delete,
-            'on_success_archive': on_success_archive,
-            'poll_new_file_seconds': poll_new_file_seconds,
-            'retries_loading_file': retries_loading_file,
-            'output_dir_year_month': output_dir_year_month,
-        },
-    )
-    if use_polling:
-        observer = PollingObserver()
-    else:
-        observer = Observer()
-    observer.schedule(handler, input_dir, recursive=True)
-    observer.start()
-    typer.echo(f"Watching {input_dir} for new PDFs. Press Ctrl+C to exit.")
-    try:
-        while True:
-            time.sleep(30)
-    except KeyboardInterrupt:
-        observer.stop()
-    observer.join()
-
-
-if __name__ == "__main__":
-    app()

misc/webservice.py

@@ -1,107 +0,0 @@
-#!/usr/bin/env python3
-# SPDX-FileCopyrightText: 2019 James R. Barlow
-# SPDX-License-Identifier: AGPL-3.0-or-later
-
-"""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.
-"""
-
-from __future__ import annotations
-
-import os
-import shlex
-from subprocess import 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", check=False)
-    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)

pyproject.toml

@@ -1,173 +0,0 @@
-# SPDX-FileCopyrightText: 2022 James R. Barlow
-# SPDX-License-Identifier: MPL-2.0
-[build-system]
-requires = ["setuptools >= 61", "setuptools_scm[toml] >= 7.0.5", "wheel"]
-build-backend = "setuptools.build_meta"
-
-[project]
-name = "ocrmypdf"
-dynamic = ["version"]
-description = "OCRmyPDF adds an OCR text layer to scanned PDF files, allowing them to be searched"
-readme = "README.md"
-license = { text = "MPL-2.0" }
-requires-python = ">=3.10"
-dependencies = [
-  "Pillow>=10.0.1",
-  "deprecation>=2.1.0",
-  "img2pdf>=0.4.4",
-  "packaging>=20",
-  "pdfminer.six>=20220319",
-  "pikepdf>=8.8.0",
-  "pluggy>=0.13.0",
-  "rich>=13",
-]
-authors = [{ name = "James R. Barlow", email = "james@purplerock.ca" }]
-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",
-  "Operating System :: Microsoft :: Windows",
-  "Operating System :: POSIX",
-  "Operating System :: POSIX :: BSD",
-  "Operating System :: POSIX :: Linux",
-  "Programming Language :: Python :: 3",
-  "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"
-
-[project.optional-dependencies]
-docs = ["sphinx", "sphinx-issues", "sphinx-rtd-theme"]
-extended_test = ["PyMuPDF>=1.19.1"]
-test = [
-  "coverage[toml]>=6.2",
-  "hypothesis>=6.36.0",
-  "pytest>=6.2.5",
-  "pytest-cov>=3.0.0",
-  "pytest-xdist>=2.5.0",
-  "python-xmp-toolkit==2.0.1", # also requires apt-get install libexempi3
-  "reportlab>=3.6.8",
-  "types-Pillow",
-  "types-humanfriendly",
-]
-watcher = ["watchdog>=1.0.2", "typer[all]", "python-dotenv"]
-webservice = ["Flask>=2.0.1"]
-
-[project.scripts]
-ocrmypdf = "ocrmypdf.__main__:run"
-
-[tool.setuptools.package-data]
-ocrmypdf = ["data/sRGB.icc", "py.typed"]
-
-[tool.setuptools.packages.find]
-where = ["src"]
-namespaces = false
-
-[tool.setuptools_scm]
-
-[tool.distutils.bdist_wheel]
-python-tag = "py39"
-
-[tool.black]
-line-length = 88
-target-version = ["py39", "py310", "py311"]
-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", "thread"]
-sigterm = true
-
-[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.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.ruff]
-select = [
-  "D",    # pydocstyle
-  "E",    # pycodestyle
-  "W",    # pycodestyle
-  "F",    # pyflakes
-  "I001", # isort
-  "UP",   # pyupgrade
-]
-target-version = "py39"
-
-[tool.ruff.isort]
-known-first-party = ["ocrmypdf"]
-required-imports = ["from __future__ import annotations"]
-
-[tool.ruff.pydocstyle]
-convention = "google"
-
-[tool.ruff.per-file-ignores]
-"docs/conf.py" = ["D100", "D101", "D105"]
-"tests/*.py" = ["D100", "D101", "D102", "D103", "D105"]
-"misc/*.py" = ["D103", "D101", "D102"]
-"src/ocrmypdf/builtin_plugins/*.py" = ["D103", "D102", "D105"]

snapcraft.yaml

@@ -1,94 +0,0 @@
-# SPDX-FileCopyrightText: 2022 Alexander Langanke
-# SPDX-FileCopyrightText: 2022 James R. Barlow
-# SPDX-FileCopyrightText: 2023 林博仁(Buo-ren, Lin) <Buo.Ren.Lin@gmail.com>
-# SPDX-License-Identifier: MPL-2.0
-
-name: ocrmypdf
-title: OCRmyPDF
-base: core22
-version: git
-summary: OCRmyPDF adds a searchable text layer to scanned PDF files
-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/9.55/Resource/Init
-  GS_FONTPATH: $SNAP/usr/share/ghostscript/9.55/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
-
-  jbig2enc:
-    plugin: autotools
-    source: https://github.com/agl/jbig2enc.git
-    source-tag: "0.29"
-    build-packages:
-      - libleptonica-dev
-
-  ocrmypdf:
-    plugin: python
-    source: .
-
-    build-packages:
-      - python3-pip
-
-    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
-      - wheel
-
-    override-build: |
-      pip3 install --user dephell[full]
-      $HOME/.local/bin/dephell deps convert \
-          --from-path pyproject.toml \
-          --from-format pyproject \
-          --to-path setup.py \
-          --to-format setuppy
-      snapcraftctl build
-      ln -sf ../usr/lib/libsnapcraft-preload.so $SNAPCRAFT_PART_INSTALL/lib/libsnapcraft-preload.so

src/ocrmypdf/RELEASE.md

@@ -1,38 +0,0 @@
-<!-- SPDX-FileCopyrightText: 2022 James R. Barlow -->
-<!-- SPDX-License-Identifier: CC-BY-SA-4.0 -->
-
-# Release checklist
-
-## Patch release
-
-- Check `pytest`
-
-- Update release notes
-
-## Minor release
-
-## Major release
-
-- Run `pre-commit autoupdate`
-
-- Check README.md
-
-- Check pyproject.toml
-
-    - Are classifiers up to date?
-    - Is `python_requires` correct?
-    - Is it to drop support for older Pythons?
-    - 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

@@ -1,70 +0,0 @@
-# SPDX-FileCopyrightText: 2022 James R. Barlow
-# SPDX-License-Identifier: MPL-2.0
-
-"""Adds OCR layer to PDFs."""
-
-from __future__ import annotations
-
-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._pipelines._common import (
-    configure_debug_logging,
-)
-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,
-    PriorOcrFoundError,
-    SubprocessOutputError,
-    TesseractConfigError,
-    UnsupportedImageFormatError,
-)
-from ocrmypdf.pluginspec import OcrEngine, OrientationConfidence
-
-hookimpl = _HookimplMarker('ocrmypdf')
-
-
-__all__ = [
-    '__version__',
-    'BadArgsError',
-    'configure_debug_logging',
-    'configure_logging',
-    'DpiError',
-    'EncryptedPdfError',
-    'Executor',
-    'ExitCode',
-    'ExitCodeException',
-    'helpers',
-    'hocrtransform',
-    'hookimpl',
-    'InputFileError',
-    'MissingDependencyError',
-    'ocr',
-    'OcrEngine',
-    'OrientationConfidence',
-    'OutputFileAccessError',
-    'PageContext',
-    'pdfa',
-    'PdfContext',
-    'pdfinfo',
-    'PriorOcrFoundError',
-    'PROGRAM_NAME',
-    'SubprocessOutputError',
-    'TesseractConfigError',
-    'UnsupportedImageFormatError',
-    'Verbosity',
-]

src/ocrmypdf/__main__.py

@@ -1,83 +0,0 @@
-#!/usr/bin/env python3
-# SPDX-FileCopyrightText: 2022 James R. Barlow
-# SPDX-License-Identifier: MPL-2.0
-
-"""ocrmypdf command line entrypoint."""
-
-from __future__ import annotations
-
-import logging
-import multiprocessing
-import os
-import signal
-import sys
-from contextlib import suppress
-
-from ocrmypdf import __version__
-from ocrmypdf._pipelines.ocr import run_pipeline_cli
-from ocrmypdf._plugin_manager import get_parser_options_plugins
-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):
-    """Handle SIGBUS signals.
-
-    pikepdf, depending on configuration, may use mmap so SIGBUS is a
-    possibility.
-    """
-    raise InputFileError("Lost access to the input file")
-
-
-def run(args=None):
-    """Run the ocrmypdf command line interface."""
-    _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_cli(options=options, plugin_manager=plugin_manager)
-    return result
-
-
-if __name__ == '__main__':
-    multiprocessing.freeze_support()
-    if os.name == 'posix':
-        multiprocessing.set_start_method('forkserver')
-    sys.exit(run())

src/ocrmypdf/_concurrent.py

@@ -1,129 +0,0 @@
-# SPDX-FileCopyrightText: 2022 James R. Barlow
-# SPDX-License-Identifier: MPL-2.0
-
-"""OCRmyPDF concurrency abstractions."""
-
-from __future__ import annotations
-
-import threading
-from abc import ABC, abstractmethod
-from collections.abc import Iterable
-from typing import Any, Callable, TypeVar
-
-from ocrmypdf._progressbar import NullProgressBar, ProgressBar
-
-T = TypeVar('T')
-
-
-def _task_noop(*_args, **_kwargs):
-    return
-
-
-def _task_finished_noop(_result: Any, pbar: ProgressBar):
-    pbar.update()
-
-
-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,
-        progress_kwargs: dict,
-        worker_initializer: Callable | None = None,
-        task: Callable[..., T] | None = None,
-        task_arguments: Iterable | None = None,
-        task_finished: Callable[[T, ProgressBar], None] | None = 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.
-            progress_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_finished_noop
-        if not task:
-            task = _task_noop
-
-        with self.pool_lock:
-            self._execute(
-                use_threads=use_threads,
-                max_workers=max_workers,
-                progress_kwargs=progress_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,
-        progress_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,
-        progress_kwargs: dict,
-        worker_initializer: Callable,
-        task: Callable,
-        task_arguments: Iterable,
-        task_finished: Callable,
-    ):  # pylint: disable=unused-argument
-        with self.pbar_class(**progress_kwargs) as pbar:
-            for args in task_arguments:
-                result = task(*args)
-                task_finished(result, pbar)

src/ocrmypdf/_exec/__init__.py

@@ -1,6 +0,0 @@
-# SPDX-FileCopyrightText: 2022 James R. Barlow
-# SPDX-License-Identifier: MPL-2.0
-
-"""Manage third party executables."""
-
-from __future__ import annotations

src/ocrmypdf/_exec/ghostscript.py

@@ -1,296 +0,0 @@
-# SPDX-FileCopyrightText: 2022 James R. Barlow
-# SPDX-License-Identifier: MPL-2.0
-
-"""Interface to Ghostscript executable."""
-
-from __future__ import annotations
-
-import logging
-import os
-import re
-from collections import deque
-from io import BytesIO
-from os import fspath
-from pathlib import Path
-from subprocess import PIPE, CalledProcessError
-
-from packaging.version import Version
-from PIL import Image, UnidentifiedImageError
-
-from ocrmypdf.exceptions import ColorConversionNeededError, SubprocessOutputError
-from ocrmypdf.helpers import Resolution
-from ocrmypdf.subprocess import get_version, run, run_polling_stderr
-
-COLOR_CONVERSION_STRATEGIES = frozenset(
-    [
-        'CMYK',
-        'Gray',
-        'LeaveColorUnchanged',
-        'RGB',
-        'UseDeviceIndependentColor',
-    ]
-)
-# Ghostscript executable - gswin32c is not supported
-GS = 'gswin64c' if os.name == 'nt' else 'gs'
-
-
-log = logging.getLogger(__name__)
-
-
-class DuplicateFilter(logging.Filter):
-    """Filter out duplicate log messages.
-
-    A context window of default 5 messages is used to determine if a message is a
-    duplicate. This is because some Ghostscript messages are word wrapped.
-    """
-
-    def __init__(self, logger: logging.Logger, context_window=5):
-        self.window: deque[str] = deque([], maxlen=context_window)
-        self.logger = logger
-        self.levelno = logging.DEBUG
-        self.count = 0
-
-    def filter(self, record):
-        if record.msg in self.window:
-            self.count += 1
-            self.levelno = record.levelno
-            return False
-        else:
-            if self.count >= 1:
-                rep_msg = f"(suppressed {self.count} repeated lines)"
-                self.count = 0  # Avoid infinite recursion
-                self.logger.log(self.levelno, rep_msg)
-                self.window.clear()
-            self.window.append(record.msg)
-            return True
-
-
-log.addFilter(DuplicateFilter(log))
-
-
-def version() -> Version:
-    return Version(get_version(GS))
-
-
-def _gs_error_reported(stream) -> bool:
-    match = re.search(r'error', stream, flags=re.IGNORECASE)
-    return bool(match)
-
-
-def _gs_devicen_reported(stream) -> bool:
-    """Did Ghostscript warn about a DeviceN with inappropriate alternate?
-
-    If so, we need the user to select a color conversion, or the resulting PDF will
-    not present correctly in some PDF viewers.
-    """
-    match = re.search(
-        r'DeviceN.*inappropriate alternate',
-        stream,
-        flags=re.IGNORECASE | re.MULTILINE,
-    )
-    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: Resolution | None = None,
-    rotation: int | None = None,
-    filter_vector: bool = False,
-    stop_on_error: 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 [])
-        + (['-dPDFSTOPONERROR'] if stop_on_error 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(Image.Transpose.ROTATE_90)
-                elif rotation == 180:
-                    im = im.transpose(Image.Transpose.ROTATE_180)
-                elif rotation == 270:
-                    im = im.transpose(Image.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,
-    color_conversion_strategy: str,
-    pdf_version: str = '1.5',
-    pdfa_part: str = '2',
-    progressbar_class=None,
-    stop_on_error: bool = False,
-):
-    # 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",
-        ]
-
-    gs_version = version()
-    if gs_version == Version('9.56.0'):
-        # 9.56.0 breaks our OCR, should be fixed in 9.56.1
-        # https://bugs.ghostscript.com/show_bug.cgi?id=705187
-        compression_args.append('-dNEWPDF=false')
-
-    if os.name == 'nt':
-        # Windows has lots of fatal "permission denied" errors
-        stop_on_error = 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",
-            f"-dCompatibilityLevel={str(pdf_version)}",
-            "-sDEVICE=pdfwrite",
-            "-dAutoRotatePages=/None",
-            f"-sColorConversionStrategy={color_conversion_strategy}",
-        ]
-        + (['-dPDFSTOPONERROR'] if stop_on_error else [])
-        + compression_args
-        + [
-            "-dJPEGQ=95",
-            f"-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):
-            # Ghostscript outputs the pattern **** Error: ....  frequently.
-            # Occasionally the error message is spammed many times. We filter
-            # out duplicates of this message using the filter above. We use
-            # the **** pattern to split the stderr into parts.
-            for part in stderr.split('****'):
-                log.error(part)
-        if _gs_devicen_reported(stderr):
-            raise ColorConversionNeededError()

src/ocrmypdf/_exec/jbig2enc.py

@@ -1,51 +0,0 @@
-# SPDX-FileCopyrightText: 2022 James R. Barlow
-# SPDX-License-Identifier: MPL-2.0
-
-"""Interface to jbig2 executable."""
-
-from __future__ import annotations
-
-from subprocess import PIPE
-
-from packaging.version import Version
-
-from ocrmypdf.exceptions import MissingDependencyError
-from ocrmypdf.subprocess import get_version, run
-
-
-def version() -> Version:
-    return Version(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, threshold):
-    args = [
-        'jbig2',
-        '-b',
-        out_prefix,
-        '--symbol-mode',  # symbol mode (lossy)
-        '-t',
-        str(threshold),  # threshold
-        # '-r', # refinement mode (lossless symbol mode, currently disabled in
-        # jbig2)
-        '--pdf',
-    ]
-    args.extend(infiles)
-    proc = run(args, cwd=cwd, stdout=PIPE, stderr=PIPE)
-    proc.check_returncode()
-    return proc
-
-
-def convert_single(cwd, infile, outfile, threshold):
-    args = ['jbig2', '--pdf', '-t', str(threshold), infile]
-    with open(outfile, 'wb') as fstdout:
-        proc = run(args, cwd=cwd, stdout=fstdout, stderr=PIPE)
-    proc.check_returncode()
-    return proc

src/ocrmypdf/_exec/pngquant.py

@@ -1,52 +0,0 @@
-# SPDX-FileCopyrightText: 2022 James R. Barlow
-# SPDX-License-Identifier: MPL-2.0
-
-"""Interface to pngquant executable."""
-
-from __future__ import annotations
-
-from pathlib import Path
-from subprocess import PIPE
-
-from packaging.version import Version
-
-from ocrmypdf.exceptions import MissingDependencyError
-from ocrmypdf.subprocess import get_version, run
-
-
-def version() -> Version:
-    return Version(get_version('pngquant', regex=r'(\d+(\.\d+)*).*'))
-
-
-def available():
-    try:
-        version()
-    except MissingDependencyError:
-        return False
-    return True
-
-
-def quantize(input_file: Path, output_file: Path, quality_min: int, quality_max: int):
-    """Quantize a PNG image using pngquant.
-
-    Args:
-        input_file: Input PNG image
-        output_file: Output PNG image
-        quality_min: Minimum quality to use
-        quality_max: Maximum quality to use
-    """
-    with open(input_file, 'rb') 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)

src/ocrmypdf/_exec/tesseract.py

@@ -1,399 +0,0 @@
-# SPDX-FileCopyrightText: 2022 James R. Barlow
-# SPDX-License-Identifier: MPL-2.0
-
-"""Interface to Tesseract executable."""
-
-from __future__ import annotations
-
-import logging
-import re
-from contextlib import suppress
-from math import pi
-from os import fspath
-from pathlib import Path
-from subprocess import PIPE, STDOUT, CalledProcessError, TimeoutExpired
-
-from packaging.version import Version
-
-from ocrmypdf.exceptions import (
-    MissingDependencyError,
-    SubprocessOutputError,
-    TesseractConfigError,
-)
-from ocrmypdf.pluginspec import OrientationConfidence
-from ocrmypdf.subprocess import get_version, run
-
-log = logging.getLogger(__name__)
-
-
-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 idiosyncrasies."""
-
-    _regex = re.compile(
-        r"^\s*" + TESSERACT_VERSION_PATTERN + r"\s*$", re.VERBOSE | re.IGNORECASE
-    )
-
-
-def version() -> Version:
-    return TesseractVersion(get_version('tesseract', regex=r'tesseract\s(.+)'))
-
-
-def has_thresholding() -> bool:
-    """Does Tesseract have -c thresholding method capability?"""
-    return version() >= Version('5.0')
-
-
-def get_languages() -> set[str]:
-    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: int | None) -> 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: int | None, 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: int | None, 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
-    log.debug(f"Deskew angle: {deskew_degrees:.3f}")
-    return deskew_degrees
-
-
-def tesseract_log_output(stream: bytes) -> None:
-    tlog = TesseractLoggerAdapter(
-        log, extra=log.extra if hasattr(log, 'extra') else None  # type: ignore
-    )
-
-    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: float) -> None:
-    if timeout == 0:
-        return
-    log.warning("[tesseract] took too long to OCR - skipping")
-
-
-def _generate_null_hocr(output_hocr: Path, output_text: Path, image: Path) -> None:
-    """Produce an empty .hocr file.
-
-    Ensures page is the same size as the input image.
-    """
-    output_hocr.write_text('', 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,
-) -> None:
-    """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
-        with suppress(FileNotFoundError):
-            prefix.with_suffix('.txt').replace(output_text)
-
-
-def use_skip_page(output_pdf: Path, output_text: Path) -> None:
-    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,
-) -> None:
-    """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
-        with suppress(FileNotFoundError):
-            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

@@ -1,138 +0,0 @@
-# SPDX-FileCopyrightText: 2022 James R. Barlow
-# SPDX-License-Identifier: MPL-2.0
-
-"""Interface to unpaper executable."""
-
-from __future__ import annotations
-
-import logging
-import os
-import shlex
-import sys
-from collections.abc import Iterator
-from contextlib import contextmanager
-from decimal import Decimal
-from pathlib import Path
-from subprocess import PIPE, STDOUT
-from tempfile import TemporaryDirectory
-from typing import Union
-
-from packaging.version import Version
-from PIL import Image
-
-from ocrmypdf.exceptions import MissingDependencyError, SubprocessOutputError
-from ocrmypdf.subprocess import get_version, run
-
-# unpaper documentation:
-# https://github.com/Flameeyes/unpaper/blob/main/doc/basic-concepts.md
-
-
-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() -> Version:
-    return Version(get_version('unpaper'))
-
-
-@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)
-
-    with TemporaryDirectory(ignore_cleanup_errors=True) as tmpdir:
-        tmppath = Path(tmpdir)
-        # 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: list[str] | None = 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

@@ -1,319 +0,0 @@
-# SPDX-FileCopyrightText: 2022 James R. Barlow
-# SPDX-License-Identifier: MPL-2.0
-
-"""For grafting text-only PDF pages onto freeform PDF pages."""
-
-from __future__ import annotations
-
-import logging
-from contextlib import suppress
-from enum import Enum
-from pathlib import Path
-
-from pikepdf import (
-    Dictionary,
-    Matrix,
-    Name,
-    Operator,
-    Page,
-    Pdf,
-    PdfError,
-    Stream,
-    parse_content_stream,
-    unparse_content_stream,
-)
-
-from ocrmypdf._jobcontext import PdfContext
-
-
-class RenderMode(Enum):
-    ON_TOP = 0
-    UNDERNEATH = 1
-
-
-log = logging.getLogger(__name__)
-MAX_REPLACE_PAGES = 100
-
-
-def _ensure_dictionary(obj: Dictionary | Stream, name: Name):
-    if name not in obj:
-        obj[name] = Dictionary({})
-    return obj[name]
-
-
-def _update_resources(
-    *,
-    obj: Dictionary | Stream,
-    font: Dictionary | None,
-    font_key: Name | None,
-):
-    """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
-
-
-def strip_invisible_text(pdf: Pdf, page: 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: PdfContext):
-        self.context = context
-        self.path_base = context.origin
-
-        self.pdf_base = Pdf.open(self.path_base)
-        self.font: Dictionary | None = None
-        self.font_key: Name | None = None
-
-        self.pdfinfo = context.pdfinfo
-        self.output_file = context.get_path('graft_layers.pdf')
-
-        self.emplacements = 1
-        self.interim_count = 0
-        self.render_mode = RenderMode.UNDERNEATH
-
-    def graft_page(
-        self,
-        *,
-        pageno: int,
-        image: Path | None,
-        textpdf: Path | None,
-        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, retain=(Name.Parent,)
-                )
-                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}) -> "
-            f"{text_misaligned}"
-        )
-
-        if textpdf and self.font:
-            if self.font_key is None:
-                raise ValueError("Font key is not set")
-            # 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,
-                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) -> None:
-        """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.obj, font=self.font, font_key=self.font_key)
-
-        # 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.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: Path) -> tuple[Dictionary | None, Name | None]:
-        """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(
-                        Name.Font, Dictionary()
-                    )
-                except (AttributeError, IndexError, KeyError):
-                    return None, None
-                if not isinstance(pdf_text_fonts, Dictionary):
-                    log.warning("Page fonts are not stored in a dictionary")
-                    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 = Name(f)
-                        break
-                if pdf_text_font:
-                    font = self.pdf_base.copy_foreign(pdf_text_font)
-                if not isinstance(font, Dictionary):
-                    log.warning("Font is not a dictionary")
-                    font, font_key = None, None
-                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: Dictionary,
-        font_key: Name,
-        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 = pdf_text.pages[0].mediabox
-            wt, ht = mediabox[2] - mediabox[0], mediabox[3] - mediabox[1]
-
-            mediabox = base_page.mediabox
-            wp, hp = mediabox[2] - mediabox[0], mediabox[3] - mediabox[1]
-
-            translate = Matrix().translated(-wt / 2, -ht / 2)
-            untranslate = Matrix().translated(wp / 2, hp / 2)
-            corner = Matrix().translated(mediabox[0], mediabox[1])
-            # -rotation because the input is a clockwise angle and this formula
-            # uses CCW
-            text_rotation = -text_rotation % 360
-            rotate = Matrix().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 = Matrix().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. All transforms
-            # must be premultiplied so they are applied in reverse order here.
-            ctm = corner @ untranslate @ scale @ rotate @ translate
-
-            base_resources = _ensure_dictionary(base_page.obj, 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)
-
-            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=self.render_mode == RenderMode.ON_TOP
-            )
-
-            _update_resources(obj=base_page.obj, font=font, font_key=font_key)

src/ocrmypdf/_jobcontext.py

@@ -1,100 +0,0 @@
-# SPDX-FileCopyrightText: 2022 James R. Barlow
-# SPDX-License-Identifier: MPL-2.0
-
-"""Defines context objects that are passed to child processes/threads."""
-
-from __future__ import annotations
-
-import os
-from argparse import Namespace
-from collections.abc import Iterator
-from copy import copy
-from pathlib import Path
-
-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)
-
-    def get_page_context_args(self) -> Iterator[tuple[PageContext]]:
-        """Get all ``PageContext`` for this PDF packaged in tuple for args-splatting."""
-        npages = len(self.pdfinfo)
-        for n in range(npages):
-            yield (PageContext(self, n),)
-
-
-class PageContext:
-    """Holds our context for a page.
-
-    Must be pickle-able, 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

src/ocrmypdf/_logging.py

@@ -1,30 +0,0 @@
-# SPDX-FileCopyrightText: 2022 James R. Barlow
-# SPDX-License-Identifier: MPL-2.0
-
-"""Logging support classes."""
-
-from __future__ import annotations
-
-import logging
-
-from rich.console import Console
-from rich.logging import RichHandler
-
-
-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 RichLoggingHandler(RichHandler):
-    def __init__(self, console: Console, **kwargs):
-        super().__init__(
-            console=console, show_level=False, show_time=False, markup=True, **kwargs
-        )

src/ocrmypdf/_metadata.py

@@ -1,184 +0,0 @@
-# SPDX-FileCopyrightText: 2023 James R. Barlow
-# SPDX-License-Identifier: MPL-2.0
-
-"""OCRmyPDF page processing pipeline functions."""
-
-from __future__ import annotations
-
-import logging
-import os
-from datetime import datetime, timezone
-from pathlib import Path
-from typing import Any
-
-from pikepdf import Dictionary, Name, Pdf
-from pikepdf import __version__ as PIKEPDF_VERSION
-from pikepdf.models.metadata import PdfMetadata, encode_pdf_date
-
-from ocrmypdf._jobcontext import PdfContext
-from ocrmypdf._version import PROGRAM_NAME
-from ocrmypdf._version import __version__ as OCRMYPF_VERSION
-from ocrmypdf.languages import iso_639_2_from_3
-
-log = logging.getLogger(__name__)
-
-
-def get_docinfo(base_pdf: Pdf, context: PdfContext) -> dict[str, str]:
-    """Read the document info and store it in a dictionary."""
-    options = context.options
-
-    def from_document_info(key):
-        try:
-            s = base_pdf.docinfo[key]
-            return str(s)
-        except (KeyError, TypeError):
-            return ''
-
-    pdfmark = {
-        k: from_document_info(k)
-        for k in ('/Title', '/Author', '/Keywords', '/Subject', '/CreationDate')
-    }
-    if options.title:
-        pdfmark['/Title'] = options.title
-    if options.author:
-        pdfmark['/Author'] = options.author
-    if options.keywords:
-        pdfmark['/Keywords'] = options.keywords
-    if options.subject:
-        pdfmark['/Subject'] = options.subject
-
-    creator_tag = context.plugin_manager.hook.get_ocr_engine().creator_tag(options)
-
-    pdfmark['/Creator'] = f'{PROGRAM_NAME} {OCRMYPF_VERSION} / {creator_tag}'
-    pdfmark['/Producer'] = f'pikepdf {PIKEPDF_VERSION}'
-    pdfmark['/ModDate'] = encode_pdf_date(datetime.now(timezone.utc))
-    return pdfmark
-
-
-def report_on_metadata(options, missing):
-    if not missing:
-        return
-    if options.output_type.startswith('pdfa'):
-        log.warning(
-            "Some input metadata could not be copied because it is not "
-            "permitted in PDF/A. You may wish to examine the output "
-            "PDF's XMP metadata."
-        )
-        log.debug("The following metadata fields were not copied: %r", missing)
-    else:
-        log.error(
-            "Some input metadata could not be copied."
-            "You may wish to examine the output PDF's XMP metadata."
-        )
-        log.info("The following metadata fields were not copied: %r", missing)
-
-
-def repair_docinfo_nuls(pdf):
-    """If the DocumentInfo block contains NUL characters, remove them.
-
-    If the DocumentInfo block is malformed, log an error and continue.
-    """
-    modified = False
-    try:
-        if not isinstance(pdf.docinfo, Dictionary):
-            raise TypeError("DocumentInfo is not a dictionary")
-        for k, v in pdf.docinfo.items():
-            if isinstance(v, str) and b'\x00' in bytes(v):
-                pdf.docinfo[k] = bytes(v).replace(b'\x00', b'')
-                modified = True
-    except TypeError:
-        # TypeError can also be raised if dictionary items are unexpected types
-        log.error("File contains a malformed DocumentInfo block - continuing anyway.")
-    return modified
-
-
-def should_linearize(working_file: Path, context: PdfContext) -> bool:
-    """Determine whether the PDF should be linearized.
-
-    For smaller files, linearization is not worth the effort.
-    """
-    filesize = os.stat(working_file).st_size
-    if filesize > (context.options.fast_web_view * 1_000_000):
-        return True
-    return False
-
-
-def _fix_metadata(meta_original: PdfMetadata, meta_pdf: PdfMetadata):
-    # If xmp:CreateDate is missing, set it to the modify date to
-    # ensure consistency with Ghostscript.
-    if 'xmp:CreateDate' not in meta_pdf:
-        meta_pdf['xmp:CreateDate'] = meta_pdf.get('xmp:ModifyDate', '')
-    if meta_pdf.get('dc:title') == 'Untitled':
-        # Ghostscript likes to set title to Untitled if omitted from input.
-        # Reverse this, because PDF/A TechNote 0003:Metadata in PDF/A-1
-        # and the XMP Spec do not make this recommendation.
-        if 'dc:title' not in meta_original:
-            del meta_pdf['dc:title']
-
-
-def _unset_empty_metadata(meta: PdfMetadata, options):
-    """Unset metadata fields that were explicitly set to empty strings.
-
-    If the user explicitly specified an empty string for any of the
-    following, they should be unset and not reported as missing in
-    the output pdf. Note that some metadata fields use differing names
-    between PDF/A and PDF.
-    """
-    if options.title == '' and 'dc:title' in meta:
-        del meta['dc:title']  # PDF/A and PDF
-    if options.author == '':
-        if 'dc:creator' in meta:
-            del meta['dc:creator']  # PDF/A (Not xmp:CreatorTool)
-        if 'pdf:Author' in meta:
-            del meta['pdf:Author']  # PDF
-    if options.subject == '':
-        if 'dc:description' in meta:
-            del meta['dc:description']  # PDF/A
-        if 'dc:subject' in meta:
-            del meta['dc:subject']  # PDF
-    if options.keywords == '' and 'pdf:Keywords' in meta:
-        del meta['pdf:Keywords']  # PDF/A and PDF
-
-
-def _set_language(pdf: Pdf, languages: list[str]):
-    """Set the language of the PDF."""
-    if Name.Lang in pdf.Root or not languages:
-        return  # Already set or can't change
-    primary_language_iso639_3 = languages[0]
-    if not primary_language_iso639_3:
-        return
-    iso639_2 = iso_639_2_from_3(primary_language_iso639_3)
-    if not iso639_2:
-        return
-    pdf.Root.Lang = iso639_2
-
-
-def metadata_fixup(
-    working_file: Path, context: PdfContext, pdf_save_settings: dict[str, Any]
-) -> Path:
-    """Fix certain metadata fields after Ghostscript PDF/A conversion.
-
-    Also report on metadata in the input file that was not retained during
-    PDF/A conversion.
-    """
-    output_file = context.get_path('metafix.pdf')
-    options = context.options
-
-    with Pdf.open(context.origin) as original, Pdf.open(working_file) as pdf:
-        docinfo = get_docinfo(original, context)
-        with original.open_metadata(
-            set_pikepdf_as_editor=False, update_docinfo=False, strict=False
-        ) as meta_original, pdf.open_metadata() as meta_pdf:
-            meta_pdf.load_from_docinfo(
-                docinfo, delete_missing=False, raise_failure=False
-            )
-            _fix_metadata(meta_original, meta_pdf)
-            _unset_empty_metadata(meta_original, options)
-            _unset_empty_metadata(meta_pdf, options)
-            meta_missing = set(meta_original.keys()) - set(meta_pdf.keys())
-            report_on_metadata(options, meta_missing)
-
-        _set_language(pdf, options.languages)
-        pdf.save(output_file, **pdf_save_settings)
-
-    return output_file

src/ocrmypdf/_pipeline.py

@@ -1,994 +0,0 @@
-# SPDX-FileCopyrightText: 2018-2022 James R. Barlow
-# SPDX-FileCopyrightText: 2019 Martin Wind
-# SPDX-License-Identifier: MPL-2.0
-
-"""OCRmyPDF page processing pipeline functions."""
-
-from __future__ import annotations
-
-import logging
-import os
-import re
-import sys
-from collections.abc import Iterable, Iterator, Sequence
-from contextlib import suppress
-from pathlib import Path
-from shutil import copyfileobj, copystat
-from typing import Any, BinaryIO, TypeVar, cast
-
-import img2pdf
-import pikepdf
-from PIL import Image, ImageColor, ImageDraw
-
-from ocrmypdf._concurrent import Executor
-from ocrmypdf._exec import unpaper
-from ocrmypdf._jobcontext import PageContext, PdfContext
-from ocrmypdf._metadata import repair_docinfo_nuls
-from ocrmypdf.exceptions import (
-    DigitalSignatureError,
-    DpiError,
-    EncryptedPdfError,
-    InputFileError,
-    PriorOcrFoundError,
-    TaggedPDFError,
-    UnsupportedImageFormatError,
-)
-from ocrmypdf.helpers import IMG2PDF_KWARGS, Resolution, safe_symlink
-from ocrmypdf.hocrtransform import HocrTransform
-from ocrmypdf.pdfa import generate_pdfa_ps
-from ocrmypdf.pdfinfo import Colorspace, Encoding, PageInfo, PdfInfo
-from ocrmypdf.pluginspec import OrientationConfidence
-
-T = TypeVar("T")
-log = logging.getLogger(__name__)
-
-VECTOR_PAGE_DPI = 400
-
-
-def triage_image_file(input_file: Path, output_file: Path, options) -> None:
-    """Triage the input image file.
-
-    If the input file is an image, check its resolution and convert it to PDF.
-
-    Args:
-        input_file: The path to the input file.
-        output_file: The path to the output file.
-        options: An object containing the options passed to the OCRmyPDF command.
-
-    Raises:
-        UnsupportedImageFormatError: If the input file is not a supported image format.
-        DpiError: If the input image has no resolution (DPI) in its metadata or if the
-            resolution is not credible.
-    """
-    log.info("Input file is not a PDF, checking if it is an image...")
-    try:
-        im = Image.open(input_file)
-    except OSError as e:
-        # Recover the original filename
-        log.error(str(e).replace(str(input_file), str(options.input_file)))
-        raise UnsupportedImageFormatError() from e
-
-    with im:
-        log.info("Input file is an image")
-        if 'dpi' in im.info:
-            if im.info['dpi'] <= (96, 96) and not options.image_dpi:
-                log.info("Image size: (%d, %d)", *im.size)
-                log.info("Image resolution: (%d, %d)", *im.info['dpi'])
-                raise DpiError(
-                    "Input file is an image, but the resolution (DPI) is "
-                    "not credible.  Estimate the resolution at which the "
-                    "image was scanned and specify it using --image-dpi."
-                )
-        elif not options.image_dpi:
-            log.info("Image size: (%d, %d)", *im.size)
-            raise DpiError(
-                "Input file is an image, but has no resolution (DPI) "
-                "in its metadata.  Estimate the resolution at which "
-                "image was scanned and specify it using --image-dpi."
-            )
-
-        if im.mode in ('RGBA', 'LA'):
-            raise UnsupportedImageFormatError(
-                "The input image has an alpha channel. Remove the alpha "
-                "channel first."
-            )
-
-        if 'iccprofile' not in im.info:
-            if im.mode == 'RGB':
-                log.info("Input image has no ICC profile, assuming sRGB")
-            elif im.mode == 'CMYK':
-                raise UnsupportedImageFormatError(
-                    "Input CMYK image has no ICC profile, not usable"
-                )
-
-    try:
-        log.info("Image seems valid. Try converting to PDF...")
-        layout_fun = img2pdf.default_layout_fun
-        if options.image_dpi:
-            layout_fun = img2pdf.get_fixed_dpi_layout_fun(
-                Resolution(options.image_dpi, options.image_dpi)
-            )
-        with open(output_file, 'wb') as outf:
-            img2pdf.convert(
-                os.fspath(input_file),
-                layout_fun=layout_fun,
-                outputstream=outf,
-                **IMG2PDF_KWARGS,
-            )
-        log.info("Successfully converted to PDF, processing...")
-    except img2pdf.ImageOpenError as e:
-        raise UnsupportedImageFormatError() from e
-
-
-def _pdf_guess_version(input_file: Path, search_window=1024) -> str:
-    """Try to find version signature at start of file.
-
-    Not robust enough to deal with appended files.
-
-    Returns empty string if not found, indicating file is probably not PDF.
-    """
-    with open(input_file, 'rb') as f:
-        signature = f.read(search_window)
-    m = re.search(br'%PDF-(\d\.\d)', signature)
-    if m:
-        return m.group(1).decode('ascii')
-    return ''
-
-
-def triage(
-    original_filename: str, input_file: Path, output_file: Path, options
-) -> Path:
-    """Triage the input file. We can handle PDFs and images."""
-    try:
-        if _pdf_guess_version(input_file):
-            if options.image_dpi:
-                log.warning(
-                    "Argument --image-dpi is being ignored because the "
-                    "input file is a PDF, not an image."
-                )
-            # Origin file is a pdf create a symlink with pdf extension
-            safe_symlink(input_file, output_file)
-            return output_file
-    except OSError as e:
-        log.debug(f"Temporary file was at: {input_file}")
-        msg = str(e).replace(str(input_file), original_filename)
-        raise InputFileError(msg) from e
-
-    triage_image_file(input_file, output_file, options)
-    return output_file
-
-
-def get_pdfinfo(
-    input_file,
-    *,
-    executor: Executor,
-    detailed_analysis: bool = False,
-    progbar: bool = False,
-    max_workers: int | None = None,
-    use_threads: bool = True,
-    check_pages=None,
-) -> PdfInfo:
-    """Get the PDF info."""
-    try:
-        return PdfInfo(
-            input_file,
-            detailed_analysis=detailed_analysis,
-            progbar=progbar,
-            max_workers=max_workers,
-            use_threads=use_threads,
-            check_pages=check_pages,
-            executor=executor,
-        )
-    except pikepdf.PasswordError as e:
-        raise EncryptedPdfError() from e
-    except pikepdf.PdfError as e:
-        raise InputFileError() from e
-
-
-def validate_pdfinfo_options(context: PdfContext) -> None:
-    """Validate the PDF info options."""
-    pdfinfo = context.pdfinfo
-    options = context.options
-
-    if pdfinfo.needs_rendering:
-        raise InputFileError(
-            "This PDF contains dynamic XFA forms created by Adobe LiveCycle "
-            "Designer and can only be read by Adobe Acrobat or Adobe Reader."
-        )
-    if pdfinfo.has_signature:
-        if options.invalidate_digital_signatures:
-            log.warning("All digital signatures will be invalidated")
-        else:
-            raise DigitalSignatureError()
-    if pdfinfo.has_acroform:
-        if options.redo_ocr:
-            raise InputFileError(
-                "This PDF has a user fillable form. --redo-ocr is not "
-                "currently possible on such files."
-            )
-        else:
-            log.warning(
-                "This PDF has a fillable form. "
-                "Chances are it is a pure digital "
-                "document that does not need OCR."
-            )
-            if not options.force_ocr:
-                log.info(
-                    "Use the option --force-ocr to produce an image of the "
-                    "form and all filled form fields. The output PDF will be "
-                    "'flattened' and will no longer be fillable."
-                )
-    if pdfinfo.is_tagged:
-        if options.force_ocr or options.skip_text or options.redo_ocr:
-            log.warning(
-                "This PDF is marked as a Tagged PDF. This often indicates "
-                "that the PDF was generated from an office document and does "
-                "not need OCR. PDF pages processed by OCRmyPDF may not be "
-                "tagged correctly."
-            )
-        else:
-            raise TaggedPDFError()
-    context.plugin_manager.hook.validate(pdfinfo=pdfinfo, options=options)
-
-
-def _vector_page_dpi(pageinfo: PageInfo) -> int:
-    """Get a DPI to use for vector pages, if the page has vector content."""
-    return VECTOR_PAGE_DPI if pageinfo.has_vector or pageinfo.has_text else 0
-
-
-def get_page_square_dpi(
-    page_context: PageContext, image_dpi: Resolution | None = None
-) -> Resolution:
-    """Get the DPI when we require xres == yres, scaled to physical units.
-
-    Page DPI includes UserUnit scaling.
-    """
-    pageinfo = page_context.pageinfo
-    options = page_context.options
-    if not image_dpi:
-        image_dpi = pageinfo.dpi
-    xres = image_dpi.x or 0.0
-    yres = image_dpi.y or 0.0
-    userunit = float(pageinfo.userunit) or 1.0
-    units = float(
-        max(
-            (xres * userunit) or VECTOR_PAGE_DPI,
-            (yres * userunit) or VECTOR_PAGE_DPI,
-            _vector_page_dpi(pageinfo),
-            options.oversample or 0.0,
-        )
-    )
-    return Resolution(units, units)
-
-
-def get_canvas_square_dpi(
-    page_context: PageContext, image_dpi: Resolution | None = None
-) -> Resolution:
-    """Get the DPI when we require xres == yres, in Postscript units.
-
-    Canvas DPI is independent of PDF UserUnit scaling, which is
-    used to describe situations where the PDF user space is not 1:1 with
-    the physical units of the page.
-    """
-    pageinfo = page_context.pageinfo
-    options = page_context.options
-    if not image_dpi:
-        image_dpi = pageinfo.dpi
-    units = float(
-        max(
-            image_dpi.x or VECTOR_PAGE_DPI,
-            image_dpi.y or VECTOR_PAGE_DPI,
-            _vector_page_dpi(pageinfo),
-            options.oversample or 0.0,
-        )
-    )
-    return Resolution(units, units)
-
-
-def is_ocr_required(page_context: PageContext) -> bool:
-    """Check if the page needs to be OCR'd."""
-    pageinfo = page_context.pageinfo
-    options = page_context.options
-
-    ocr_required = True
-
-    if options.pages and pageinfo.pageno not in options.pages:
-        log.debug(f"skipped {pageinfo.pageno} as requested by --pages {options.pages}")
-        ocr_required = False
-    elif pageinfo.has_text:
-        if not options.force_ocr and not (options.skip_text or options.redo_ocr):
-            raise PriorOcrFoundError(
-                "page already has text! - aborting (use --force-ocr to force OCR; "
-                " see also help for the arguments --skip-text and --redo-ocr"
-            )
-        elif options.force_ocr:
-            log.info("page already has text! - rasterizing text and running OCR anyway")
-            ocr_required = True
-        elif options.redo_ocr:
-            if pageinfo.has_corrupt_text:
-                log.warning(
-                    "some text on this page cannot be mapped to characters: "
-                    "consider using --force-ocr instead"
-                )
-            else:
-                log.info("redoing OCR")
-            ocr_required = True
-        elif options.skip_text:
-            log.info("skipping all processing on this page")
-            ocr_required = False
-    elif not pageinfo.images and not options.lossless_reconstruction:
-        # We found a page with no images and no text. That means it may
-        # have vector art that the user wants to OCR. If we determined
-        # lossless reconstruction is not possible then we have to rasterize
-        # the image. So if OCR is being forced, take that to mean YES, go
-        # ahead and rasterize. If not forced, then pretend there's no text
-        # on the page at all so we don't lose anything.
-        # This could be made smarter by explicitly searching for vector art.
-        if options.force_ocr and options.oversample:
-            # The user really wants to reprocess this file
-            log.info(
-                "page has no images - "
-                f"rasterizing at {options.oversample} DPI because "
-                "--force-ocr --oversample was specified"
-            )
-        elif options.force_ocr:
-            # Warn the user they might not want to do this
-            log.warning(
-                "page has no images - "
-                "all vector content will be "
-                f"rasterized at {VECTOR_PAGE_DPI} DPI, losing some resolution and "
-                "likely increasing file size. Use --oversample to adjust the "
-                "DPI."
-            )
-        else:
-            log.info(
-                "page has no images - "
-                "skipping all processing on this page to avoid losing detail. "
-                "Use --force-ocr if you wish to perform OCR on pages that "
-                "have vector content."
-            )
-            ocr_required = False
-
-    if ocr_required and options.skip_big and pageinfo.images:
-        pixel_count = pageinfo.width_pixels * pageinfo.height_pixels
-        if pixel_count > (options.skip_big * 1_000_000):
-            ocr_required = False
-            log.warning(
-                "page too big, skipping OCR "
-                f"({(pixel_count / 1_000_000):.1f} MPixels > "
-                f"{options.skip_big:.1f} MPixels --skip-big)"
-            )
-    return ocr_required
-
-
-def rasterize_preview(input_file: Path, page_context: PageContext) -> Path:
-    """Generate a lower quality preview image."""
-    output_file = page_context.get_path('rasterize_preview.jpg')
-    canvas_dpi = Resolution(300.0, 300.0).take_min(
-        [get_canvas_square_dpi(page_context)]
-    )
-    page_dpi = Resolution(300.0, 300.0).take_min([get_page_square_dpi(page_context)])
-    page_context.plugin_manager.hook.rasterize_pdf_page(
-        input_file=input_file,
-        output_file=output_file,
-        raster_device='jpeggray',
-        raster_dpi=canvas_dpi,
-        pageno=page_context.pageinfo.pageno + 1,
-        page_dpi=page_dpi,
-        rotation=0,
-        filter_vector=False,
-        stop_on_soft_error=not page_context.options.continue_on_soft_render_error,
-    )
-    return output_file
-
-
-def describe_rotation(
-    page_context: PageContext, orient_conf: OrientationConfidence, correction: int
-) -> str:
-    """Describe the page rotation we are going to perform (or not perform)."""
-    direction = {0: '⇧', 90: '⇨', 180: '⇩', 270: '⇦'}
-    turns = {0: ' ', 90: '⬏', 180: '↻', 270: '⬑'}
-
-    existing_rotation = page_context.pageinfo.rotation
-    action = ''
-    if orient_conf.confidence >= page_context.options.rotate_pages_threshold:
-        if correction != 0:
-            action = 'will rotate ' + turns[correction]
-        else:
-            action = 'rotation appears correct'
-    else:
-        if correction != 0:
-            action = 'confidence too low to rotate'
-        else:
-            action = 'no change'
-
-    facing = ''
-
-    if existing_rotation != 0:
-        facing = f"with existing rotation {direction.get(existing_rotation, '?')}, "
-    facing += f"page is facing {direction.get(orient_conf.angle, '?')}"
-
-    return f"{facing}, confidence {orient_conf.confidence:.2f} - {action}"
-
-
-def get_orientation_correction(preview: Path, page_context: PageContext) -> int:
-    """Work out orientation correction for each page.
-
-    We ask Ghostscript to draw a preview page, which will rasterize with the
-    current /Rotate applied, and then ask OCR which way the page is
-    oriented. If the value of /Rotate is correct (e.g., a user already
-    manually fixed rotation), then OCR will say the page is pointing
-    up and the correction is zero. Otherwise, the orientation found by
-    OCR represents the clockwise rotation, or the counterclockwise
-    correction to rotation.
-
-    When we draw the real page for OCR, we rotate it by the CCW correction,
-    which points it (hopefully) upright. _graft.py takes care of the orienting
-    the image and text layers.
-    """
-    orient_conf = page_context.plugin_manager.hook.get_ocr_engine().get_orientation(
-        preview, page_context.options
-    )
-
-    correction = orient_conf.angle % 360
-    log.info(describe_rotation(page_context, orient_conf, correction))
-    if (
-        orient_conf.confidence >= page_context.options.rotate_pages_threshold
-        and correction != 0
-    ):
-        return correction
-
-    return 0
-
-
-def calculate_image_dpi(page_context: PageContext) -> Resolution:
-    """Calculate the DPI for the page image."""
-    pageinfo = page_context.pageinfo
-    dpi_profile = pageinfo.page_dpi_profile()
-    if dpi_profile and dpi_profile.average_to_max_dpi_ratio < 0.8:
-        image_dpi = Resolution(dpi_profile.weighted_dpi, dpi_profile.weighted_dpi)
-    else:
-        image_dpi = pageinfo.dpi
-    return image_dpi
-
-
-def calculate_raster_dpi(page_context: PageContext):
-    """Calculate the DPI for rasterization."""
-    # Produce the page image with square resolution or else deskew and OCR
-    # will not work properly.
-    image_dpi = calculate_image_dpi(page_context)
-    dpi_profile = page_context.pageinfo.page_dpi_profile()
-    canvas_dpi = get_canvas_square_dpi(page_context, image_dpi)
-    page_dpi = get_page_square_dpi(page_context, image_dpi)
-    if dpi_profile and dpi_profile.average_to_max_dpi_ratio < 0.8:
-        log.warning(
-            "Weight average image DPI is %0.1f, max DPI is %0.1f. "
-            "The discrepancy may indicate a high detail region on this page, "
-            "but could also indicate a problem with the input PDF file. "
-            "Page image will be rendered at %0.1f DPI.",
-            dpi_profile.weighted_dpi,
-            dpi_profile.max_dpi,
-            canvas_dpi.to_scalar(),
-        )
-    return canvas_dpi, page_dpi
-
-
-def rasterize(
-    input_file: Path,
-    page_context: PageContext,
-    correction: int = 0,
-    output_tag: str = '',
-    remove_vectors: bool | None = None,
-) -> Path:
-    """Rasterize a PDF page to a PNG image.
-
-    Args:
-        input_file: The input PDF file path.
-        page_context: The page context object.
-        correction: The orientation correction angle. Defaults to 0.
-        output_tag: The output tag. Defaults to ''.
-        remove_vectors: Whether to remove vectors. Defaults to None, which means
-            the value from the page context options will be used. If the value
-            is True or False, it will override the page context options.
-
-    Returns:
-        Path: The output PNG file path.
-    """
-    colorspaces = ['pngmono', 'pnggray', 'png256', 'png16m']
-    device_idx = 0
-
-    if remove_vectors is None:
-        remove_vectors = page_context.options.remove_vectors
-
-    output_file = page_context.get_path(f'rasterize{output_tag}.png')
-    pageinfo = page_context.pageinfo
-
-    def at_least(colorspace):
-        return max(device_idx, colorspaces.index(colorspace))
-
-    for image in pageinfo.images:
-        if image.type_ != 'image':
-            continue  # ignore masks
-        if image.bpc > 1:
-            if image.color == Colorspace.index:
-                device_idx = at_least('png256')
-            elif image.color == Colorspace.gray:
-                device_idx = at_least('pnggray')
-            else:
-                device_idx = at_least('png16m')
-
-    if pageinfo.has_vector:
-        log.debug("Page has vector content, using png16m")
-        device_idx = at_least('png16m')
-
-    device = colorspaces[device_idx]
-
-    log.debug(f"Rasterize with {device}, rotation {correction}")
-
-    canvas_dpi, page_dpi = calculate_raster_dpi(page_context)
-
-    page_context.plugin_manager.hook.rasterize_pdf_page(
-        input_file=input_file,
-        output_file=output_file,
-        raster_device=device,
-        raster_dpi=canvas_dpi,
-        page_dpi=page_dpi,
-        pageno=pageinfo.pageno + 1,
-        rotation=correction,
-        filter_vector=remove_vectors,
-        stop_on_soft_error=not page_context.options.continue_on_soft_render_error,
-    )
-    return output_file
-
-
-def preprocess_remove_background(input_file: Path, page_context: PageContext) -> Path:
-    """Remove the background from the input image (temporarily disabled)."""
-    if any(image.bpc > 1 for image in page_context.pageinfo.images):
-        raise NotImplementedError("--remove-background is temporarily not implemented")
-        # output_file = page_context.get_path('pp_rm_bg.png')
-        # leptonica.remove_background(input_file, output_file)
-        # return output_file
-    log.info("background removal skipped on mono page")
-    return input_file
-
-
-def preprocess_deskew(input_file: Path, page_context: PageContext) -> Path:
-    """Deskews the input image using the OCR engine and saves the output to a file.
-
-    Args:
-        input_file: The input image file to deskew.
-        page_context: The context of the page being processed.
-
-    Returns:
-        Path: The path to the deskewed image file.
-    """
-    output_file = page_context.get_path('pp_deskew.png')
-    dpi = get_page_square_dpi(page_context, calculate_image_dpi(page_context))
-
-    ocr_engine = page_context.plugin_manager.hook.get_ocr_engine()
-    deskew_angle_degrees = ocr_engine.get_deskew(input_file, page_context.options)
-
-    with Image.open(input_file) as im:
-        # According to Pillow docs, .rotate() will automatically use Image.NEAREST
-        # resampling if image is mode '1' or 'P'
-        deskewed = im.rotate(
-            deskew_angle_degrees,
-            resample=Image.Resampling.BICUBIC,
-            fillcolor=ImageColor.getcolor('white', mode=im.mode),  # type: ignore
-        )
-        deskewed.save(output_file, dpi=dpi)
-
-    return output_file
-
-
-def preprocess_clean(input_file: Path, page_context: PageContext) -> Path:
-    """Clean the input image using unpaper."""
-    output_file = page_context.get_path('pp_clean.png')
-    dpi = get_page_square_dpi(page_context, calculate_image_dpi(page_context))
-    return unpaper.clean(
-        input_file,
-        output_file,
-        dpi=dpi.to_scalar(),
-        unpaper_args=page_context.options.unpaper_args,
-    )
-
-
-def create_ocr_image(image: Path, page_context: PageContext) -> Path:
-    """Create the image we send for OCR.
-
-    Might not be the same as the display image depending on preprocessing.
-    This image will never be shown to the user.
-    """
-    output_file = page_context.get_path('ocr.png')
-    options = page_context.options
-    with Image.open(image) as im:
-        log.debug('resolution %r', im.info['dpi'])
-
-        if not options.force_ocr:
-            # Do not mask text areas when forcing OCR, because we need to OCR
-            # all text areas
-            mask = None  # Exclude both visible and invisible text from OCR
-            if options.redo_ocr:
-                mask = True  # Mask visible text, but not invisible text
-
-            draw = ImageDraw.ImageDraw(im)
-            for textarea in page_context.pageinfo.get_textareas(
-                visible=mask, corrupt=None
-            ):
-                # Calculate resolution based on the image size and page dimensions
-                # without regard whatever resolution is in pageinfo (may differ or
-                # be None)
-                bbox = [float(v) for v in textarea]
-                xyscale = tuple(float(coord) / 72.0 for coord in im.info['dpi'])
-                pixcoords = (
-                    bbox[0] * xyscale[0],
-                    im.height - bbox[3] * xyscale[1],
-                    bbox[2] * xyscale[0],
-                    im.height - bbox[1] * xyscale[1],
-                )
-                log.debug('blanking %r', pixcoords)
-                draw.rectangle(pixcoords, fill='white')
-                # draw.rectangle(pixcoords, outline='pink')
-
-        filter_im = page_context.plugin_manager.hook.filter_ocr_image(
-            page=page_context, image=im
-        )
-        if filter_im is not None:
-            im = filter_im
-
-        # Pillow requires integer DPI
-        dpi = tuple(round(coord) for coord in im.info['dpi'])
-        im.save(output_file, dpi=dpi)
-    return output_file
-
-
-def ocr_engine_hocr(input_file: Path, page_context: PageContext) -> tuple[Path, Path]:
-    """Run the OCR engine and generate hOCR output."""
-    hocr_out = page_context.get_path('ocr_hocr.hocr')
-    hocr_text_out = page_context.get_path('ocr_hocr.txt')
-    options = page_context.options
-
-    ocr_engine = page_context.plugin_manager.hook.get_ocr_engine()
-    ocr_engine.generate_hocr(
-        input_file=input_file,
-        output_hocr=hocr_out,
-        output_text=hocr_text_out,
-        options=options,
-    )
-    return hocr_out, hocr_text_out
-
-
-def should_visible_page_image_use_jpg(pageinfo: PageInfo) -> bool:
-    """Determines whether the visible page image should be saved as a JPEG.
-
-    If all images were JPEGs originally, permit a JPEG as output.
-
-    Args:
-        pageinfo: The PageInfo object containing information about the page.
-
-    Returns:
-        A boolean indicating whether the visible page image should be saved as a JPEG.
-    """
-    return bool(pageinfo.images) and all(
-        im.enc == Encoding.jpeg for im in pageinfo.images
-    )
-
-
-def create_visible_page_jpg(image: Path, page_context: PageContext) -> Path:
-    """Create a visible page image in JPEG format.
-
-    This is intended to be used when all images on the page were originally JPEGs.
-    """
-    output_file = page_context.get_path('visible.jpg')
-    with Image.open(image) as im:
-        # At this point the image should be a .png, but deskew, unpaper
-        # might have removed the DPI information. In this case, fall back to
-        # square DPI used to rasterize. When the preview image was
-        # rasterized, it was also converted to square resolution, which is
-        # what we want to give to the OCR engine, so keep it square.
-        if 'dpi' in im.info:
-            dpi = Resolution(*im.info['dpi'])
-        else:
-            # Fallback to page-implied DPI
-            dpi = get_page_square_dpi(page_context, calculate_image_dpi(page_context))
-
-        # Pillow requires integer DPI
-        im.save(output_file, format='JPEG', dpi=dpi.to_int())
-    return output_file
-
-
-def create_pdf_page_from_image(
-    image: Path, page_context: PageContext, orientation_correction: int
-) -> Path:
-    """Create a PDF page from a page image."""
-    # We rasterize a square DPI version of each page because most image
-    # processing tools don't support rectangular DPI. Use the square DPI as it
-    # accurately describes the image. It would be possible to resample the image
-    # at this stage back to non-square DPI to more closely resemble the input,
-    # except that the hocr renderer does not understand non-square DPI. The
-    # sandwich renderer would be fine.
-    output_file = page_context.get_path('visible.pdf')
-
-    pageinfo = page_context.pageinfo
-    pagesize = 72.0 * float(pageinfo.width_inches), 72.0 * float(pageinfo.height_inches)
-    effective_rotation = (pageinfo.rotation - orientation_correction) % 360
-    if effective_rotation % 180 == 90:
-        pagesize = pagesize[1], pagesize[0]
-
-    # This create a single page PDF
-    with open(image, 'rb') as imfile, open(output_file, 'wb') as pdf:
-        log.debug('convert')
-
-        layout_fun = img2pdf.get_layout_fun(pagesize)
-        img2pdf.convert(
-            imfile, layout_fun=layout_fun, outputstream=pdf, **IMG2PDF_KWARGS
-        )
-        log.debug('convert done')
-
-    output_file = page_context.plugin_manager.hook.filter_pdf_page(
-        page=page_context, image_filename=image, output_pdf=output_file
-    )
-    return output_file
-
-
-def render_hocr_page(hocr: Path, page_context: PageContext) -> Path:
-    """Render the hOCR page to a PDF."""
-    options = page_context.options
-    output_file = page_context.get_path('ocr_hocr.pdf')
-    if hocr.stat().st_size == 0:
-        # If hOCR file is empty (skipped page marker), create an empty PDF file
-        output_file.touch()
-        return output_file
-
-    dpi = get_page_square_dpi(page_context, calculate_image_dpi(page_context))
-    debug_mode = options.pdf_renderer == 'hocrdebug'
-
-    HocrTransform(
-        hocr_filename=hocr,
-        dpi=dpi.to_scalar(),  # square
-        debug=debug_mode,
-    ).to_pdf(
-        out_filename=output_file,
-        image_filename=None,
-    )
-    return output_file
-
-
-def ocr_engine_textonly_pdf(
-    input_image: Path, page_context: PageContext
-) -> tuple[Path, Path]:
-    """Run the OCR engine and generate a text-only PDF (will look blank)."""
-    output_pdf = page_context.get_path('ocr_tess.pdf')
-    output_text = page_context.get_path('ocr_tess.txt')
-    options = page_context.options
-
-    ocr_engine = page_context.plugin_manager.hook.get_ocr_engine()
-    ocr_engine.generate_pdf(
-        input_file=input_image,
-        output_pdf=output_pdf,
-        output_text=output_text,
-        options=options,
-    )
-    return (output_pdf, output_text)
-
-
-def generate_postscript_stub(context: PdfContext) -> Path:
-    """Generates a PostScript file stub for the given PDF context.
-
-    Args:
-        context: The PDF context to generate the PostScript file stub for.
-
-    Returns:
-        Path: The path to the generated PostScript file stub.
-    """
-    output_file = context.get_path('pdfa.ps')
-    generate_pdfa_ps(output_file)
-    return output_file
-
-
-def convert_to_pdfa(input_pdf: Path, input_ps_stub: Path, context: PdfContext) -> Path:
-    """Converts the given PDF to PDF/A.
-
-    Args:
-        input_pdf: The input PDF file path (presumably not PDF/A).
-        input_ps_stub: The input PostScript file path, containing instructions
-            for the PDF/A generator to use.
-        context: The PDF context.
-    """
-    options = context.options
-    input_pdfinfo = context.pdfinfo
-    fix_docinfo_file = context.get_path('fix_docinfo.pdf')
-    output_file = context.get_path('pdfa.pdf')
-
-    # If the DocumentInfo record contains NUL characters, Ghostscript will
-    # produce XMP metadata which contains invalid XML entities (&#0;).
-    # NULs in DocumentInfo seem to be common since older Acrobats included them.
-    # pikepdf can deal with this, but we make the world a better place by
-    # stamping them out as soon as possible.
-    with pikepdf.open(input_pdf) as pdf_file:
-        if repair_docinfo_nuls(pdf_file):
-            pdf_file.save(fix_docinfo_file)
-        else:
-            safe_symlink(input_pdf, fix_docinfo_file)
-
-    context.plugin_manager.hook.generate_pdfa(
-        pdf_version=input_pdfinfo.min_version,
-        pdf_pages=[fix_docinfo_file],
-        pdfmark=input_ps_stub,
-        output_file=output_file,
-        context=context,
-        pdfa_part=options.output_type[-1],  # is pdfa-1, pdfa-2, or pdfa-3
-        progressbar_class=(
-            context.plugin_manager.hook.get_progressbar_class()
-            if options.progress_bar
-            else None
-        ),
-        stop_on_soft_error=not options.continue_on_soft_render_error,
-    )
-
-    return output_file
-
-
-def should_linearize(working_file: Path, context: PdfContext) -> bool:
-    """Determine whether the PDF should be linearized.
-
-    For smaller files, linearization is not worth the effort.
-    """
-    filesize = os.stat(working_file).st_size
-    if filesize > (context.options.fast_web_view * 1_000_000):
-        return True
-    return False
-
-
-def get_pdf_save_settings(output_type: str) -> dict[str, Any]:
-    """Get pikepdf.Pdf.save settings for the given output type.
-
-    Essentially, don't use features that are incompatible with a given
-    PDF/A specification.
-    """
-    if output_type == 'pdfa-1':
-        # Trigger recompression to ensure object streams are removed, because
-        # Acrobat complains about them in PDF/A-1b validation.
-        return dict(
-            preserve_pdfa=True,
-            compress_streams=True,
-            stream_decode_level=pikepdf.StreamDecodeLevel.generalized,
-            object_stream_mode=pikepdf.ObjectStreamMode.disable,
-        )
-    else:
-        return dict(
-            preserve_pdfa=True,
-            compress_streams=True,
-            object_stream_mode=(pikepdf.ObjectStreamMode.generate),
-        )
-
-
-def _file_size_ratio(
-    input_file: Path, output_file: Path
-) -> tuple[float | None, float | None]:
-    """Calculate ratio of input to output file sizes and percentage savings.
-
-    Args:
-        input_file (Path): The path to the input file.
-        output_file (Path): The path to the output file.
-
-    Returns:
-        tuple[float | None, float | None]: A tuple containing the file size
-        ratio and the percentage savings achieved by the output file size
-        compared to the input file size.
-    """
-    input_size = input_file.stat().st_size
-    output_size = output_file.stat().st_size
-    if output_size == 0:
-        return None, None
-    ratio = input_size / output_size
-    savings = 1 - output_size / input_size
-    return ratio, savings
-
-
-def optimize_pdf(
-    input_file: Path, context: PdfContext, executor: Executor
-) -> tuple[Path, Sequence[str]]:
-    """Optimize the given PDF file."""
-    output_file = context.get_path('optimize.pdf')
-    output_pdf, messages = context.plugin_manager.hook.optimize_pdf(
-        input_pdf=input_file,
-        output_pdf=output_file,
-        context=context,
-        executor=executor,
-        linearize=should_linearize(input_file, context),
-    )
-
-    ratio, savings = _file_size_ratio(input_file, output_file)
-    if ratio:
-        log.info(f"Image optimization ratio: {ratio:.2f} savings: {(savings):.1%}")
-    ratio, savings = _file_size_ratio(context.origin, output_file)
-    if ratio:
-        log.info(f"Total file size ratio: {ratio:.2f} savings: {(savings):.1%}")
-    return output_pdf, messages
-
-
-def enumerate_compress_ranges(
-    iterable: Iterable[T],
-) -> Iterator[tuple[tuple[int, int], T | None]]:
-    """Enumerate the ranges of non-empty elements in an iterable.
-
-    Compresses consecutive ranges of length 1 into single elements.
-
-    Args:
-        iterable: An iterable of elements to enumerate.
-
-    Yields:
-        A tuple containing a range of indices and the corresponding element.
-        If the element is None, the range represents a skipped range of indices.
-    """
-    skipped_from, index = None, None
-    for index, txt_file in enumerate(iterable):
-        index += 1
-        if txt_file:
-            if skipped_from is not None:
-                yield (skipped_from, index - 1), None
-                skipped_from = None
-            yield (index, index), txt_file
-        else:
-            if skipped_from is None:
-                skipped_from = index
-    if skipped_from is not None:
-        yield (skipped_from, index), None
-
-
-def merge_sidecars(txt_files: Iterable[Path | None], context: PdfContext) -> Path:
-    """Merge the page sidecar files into a single file.
-
-    Sidecar files are created by the OCR engine and contain the text for each
-    page in the PDF. This function merges the sidecar files into a single file
-    and returns the path to the merged file.
-    """
-    output_file = context.get_path('sidecar.txt')
-    with open(output_file, 'w', encoding="utf-8") as stream:
-        for (from_, to_), txt_file in enumerate_compress_ranges(txt_files):
-            if from_ != 1:
-                stream.write('\f')  # Form feed between pages for all pages after first
-            if txt_file:
-                txt = txt_file.read_text(encoding="utf-8")
-                # Some versions of Tesseract add a form feed at the end and
-                # others don't. Remove it if it exists, since we add one manually.
-                stream.write(txt.removesuffix('\f'))
-            else:
-                if from_ != to_:
-                    pages = f'{from_}-{to_}'
-                else:
-                    pages = f'{from_}'
-                stream.write(f'[OCR skipped on page(s) {pages}]')
-    return output_file
-
-
-def copy_final(
-    input_file: Path, output_file: str | Path | BinaryIO, original_file: Path | None
-) -> None:
-    """Copy the final temporary file to the output destination.
-
-    Args:
-        input_file (Path): The intermediate input file to copy.
-        output_file (str | Path | BinaryIO): The output file to copy to.
-        original_file: The original file to copy attributes from.
-
-    Returns:
-        None
-    """
-    log.debug('%s -> %s', input_file, output_file)
-    with input_file.open('rb') as input_stream:
-        if output_file == '-':
-            copyfileobj(input_stream, sys.stdout.buffer)  # type: ignore[misc]
-            sys.stdout.flush()
-        elif hasattr(output_file, 'writable'):
-            output_stream = cast(BinaryIO, output_file)
-            copyfileobj(input_stream, output_stream)  # type: ignore[misc]
-            with suppress(AttributeError):
-                output_stream.flush()
-        else:
-            # At this point we overwrite the output_file specified by the user
-            # use copyfileobj because then we use open() to create the file and
-            # get the appropriate umask, ownership, etc.
-            with open(output_file, 'w+b') as output_stream:
-                copyfileobj(input_stream, output_stream)

src/ocrmypdf/_pipelines/__init__.py

@@ -1,5 +0,0 @@
-# SPDX-FileCopyrightText: 2023 James R. Barlow
-# SPDX-License-Identifier: MPL-2.0
-
-
-from __future__ import annotations

src/ocrmypdf/_pipelines/_common.py

@@ -1,454 +0,0 @@
-# SPDX-FileCopyrightText: 2023 James R. Barlow
-# SPDX-License-Identifier: MPL-2.0
-
-from __future__ import annotations
-
-import argparse
-import json
-import logging
-import logging.handlers
-import os
-import shutil
-import sys
-import threading
-from collections.abc import Sequence
-from concurrent.futures.process import BrokenProcessPool
-from concurrent.futures.thread import BrokenThreadPool
-from contextlib import contextmanager
-from dataclasses import dataclass
-from pathlib import Path
-from typing import Callable, NamedTuple, cast
-
-import PIL
-
-from ocrmypdf._concurrent import Executor, setup_executor
-from ocrmypdf._jobcontext import PageContext, PdfContext
-from ocrmypdf._logging import PageNumberFilter
-from ocrmypdf._metadata import metadata_fixup
-from ocrmypdf._pipeline import (
-    convert_to_pdfa,
-    create_ocr_image,
-    create_pdf_page_from_image,
-    create_visible_page_jpg,
-    generate_postscript_stub,
-    get_orientation_correction,
-    get_pdf_save_settings,
-    optimize_pdf,
-    preprocess_clean,
-    preprocess_deskew,
-    preprocess_remove_background,
-    rasterize,
-    rasterize_preview,
-    should_linearize,
-    should_visible_page_image_use_jpg,
-)
-from ocrmypdf._plugin_manager import OcrmypdfPluginManager
-from ocrmypdf._validation import (
-    report_output_file_size,
-)
-from ocrmypdf.exceptions import ExitCode, ExitCodeException
-from ocrmypdf.helpers import (
-    available_cpu_count,
-    check_pdf,
-    pikepdf_enable_mmap,
-    samefile,
-)
-from ocrmypdf.pdfa import file_claims_pdfa
-
-log = logging.getLogger(__name__)
-tls = threading.local()
-tls.pageno = None
-
-
-def _set_logging_tls(tls):
-    """Inject current page number (when available) into log records."""
-    old_factory = logging.getLogRecordFactory()
-
-    def wrapper(*args, **kwargs):
-        record = old_factory(*args, **kwargs)
-        if hasattr(tls, 'pageno'):
-            record.pageno = tls.pageno
-        return record
-
-    logging.setLogRecordFactory(wrapper)
-
-
-_set_logging_tls(tls)
-
-
-def set_thread_pageno(pageno: int | None):
-    """Set page number (1-based) that the current thread is processing."""
-    tls.pageno = pageno
-
-
-class PageResult(NamedTuple):
-    """Result when a page is finished processing."""
-
-    pageno: int
-    """Page number, 0-based."""
-
-    pdf_page_from_image: Path | None = None
-    """Single page PDF from image."""
-
-    ocr: Path | None = None
-    """Single page OCR PDF."""
-
-    text: Path | None = None
-    """Single page text file."""
-
-    orientation_correction: int = 0
-    """Orientation correction in degrees."""
-
-
-@dataclass
-class HOCRResult:
-    """Result when hOCR is finished processing."""
-
-    pageno: int
-    """Page number, 0-based."""
-
-    pdf_page_from_image: Path | None = None
-    """Single page PDF from image."""
-
-    hocr: Path | None = None
-    """Single page hOCR file."""
-
-    textpdf: Path | None = None
-    """hOCR file after conversion to PDF."""
-
-    orientation_correction: int = 0
-    """Orientation correction in degrees."""
-
-    def __getstate__(self):
-        """Return state values to be pickled."""
-        return {
-            k: (
-                ('Path://' + str(v))
-                if k in ('pdf_page_from_image', 'hocr', 'textpdf') and v is not None
-                else v
-            )
-            for k, v in self.__dict__.items()
-        }
-
-    def __setstate__(self, state):
-        """Restore state from the unpickled state values."""
-        self.__dict__.update(
-            {
-                k: (
-                    Path(v.removeprefix('Path://'))
-                    if k in ('pdf_page_from_image', 'hocr', 'textpdf') and v is not None
-                    else v
-                )
-                for k, v in state.items()
-            }
-        )
-
-    @classmethod
-    def from_json(cls, json_str: str) -> HOCRResult:
-        """Create an instance from a dict."""
-        return cls(**json.loads(json_str))
-
-    def to_json(self) -> str:
-        """Serialize to a JSON string."""
-        return json.dumps(self.__getstate__())
-
-
-def configure_debug_logging(
-    log_filename: Path, prefix: str = ''
-) -> tuple[logging.FileHandler, Callable[[], None]]:
-    """Create a debug log file at a specified location.
-
-    Returns the log handler, and a function to remove the handler.
-
-    Args:
-        log_filename: Where to the put the log file.
-        prefix: The logging domain prefix that should be sent to the log.
-    """
-    log_file_handler = logging.FileHandler(log_filename, delay=True)
-    log_file_handler.setLevel(logging.DEBUG)
-    formatter = logging.Formatter(
-        '[%(asctime)s] - %(name)s - %(levelname)7s -%(pageno)s %(message)s'
-    )
-    log_file_handler.setFormatter(formatter)
-    log_file_handler.addFilter(PageNumberFilter())
-    logging.getLogger(prefix).addHandler(log_file_handler)
-
-    def remover():
-        try:
-            logging.getLogger(prefix).removeHandler(log_file_handler)
-            log_file_handler.close()
-        except OSError as e:
-            print(e, file=sys.stderr)
-
-    return log_file_handler, remover
-
-
-def worker_init(max_pixels: int) -> None:
-    """Initialize a worker thread or process."""
-    # In Windows, child process will not inherit our change to this value in
-    # the parent process, so ensure workers get it set. Not needed when running
-    # threaded, but harmless to set again.
-    PIL.Image.MAX_IMAGE_PIXELS = max_pixels
-    pikepdf_enable_mmap()
-
-
-@contextmanager
-def manage_debug_log_handler(
-    *,
-    options: argparse.Namespace,
-    work_folder: Path,
-):
-    remover = None
-    if (options.keep_temporary_files or options.verbose >= 1) and not os.environ.get(
-        'PYTEST_CURRENT_TEST', ''
-    ):
-        # Debug log for command line interface only with verbose output
-        # See https://github.com/pytest-dev/pytest/issues/5502 for why we skip this
-        # when pytest is running
-        _debug_log_handler, remover = configure_debug_logging(
-            work_folder / "debug.log", prefix=""
-        )  # pragma: no cover
-    try:
-        yield
-    finally:
-        if remover:
-            remover()
-
-
-@contextmanager
-def manage_work_folder(*, work_folder: Path, retain: bool, print_location: bool):
-    try:
-        yield work_folder
-    finally:
-        if retain:
-            if print_location:
-                print(
-                    f"Temporary working files retained at:\n{work_folder}",
-                    file=sys.stderr,
-                )
-        else:
-            shutil.rmtree(work_folder, ignore_errors=True)
-
-
-def cli_exception_handler(
-    fn: Callable[[argparse.Namespace, OcrmypdfPluginManager], ExitCode],
-    options: argparse.Namespace,
-    plugin_manager: OcrmypdfPluginManager,
-) -> ExitCode:
-    """Convert exceptions into command line error messages and exit codes.
-
-    When known exceptions are raised, the exception message is printed to stderr
-    and the program exits with a non-zero exit code. When unknown exceptions are
-    raised, the exception traceback is printed to stderr and the program exits
-    with a non-zero exit code.
-    """
-    try:
-        # We cannot use a generator and yield here, as would be the usual pattern
-        # for exception handling context managers, because we need to return an exit
-        # code.
-        return fn(options, plugin_manager)
-    except KeyboardInterrupt:
-        if options.verbose >= 1:
-            log.exception("KeyboardInterrupt")
-        else:
-            log.error("KeyboardInterrupt")
-        return ExitCode.ctrl_c
-    except ExitCodeException as e:
-        e = cast(ExitCodeException, e)
-        if options.verbose >= 1:
-            log.exception("ExitCodeException")
-        elif str(e):
-            log.error("%s: %s", type(e).__name__, str(e))
-        else:
-            log.error(type(e).__name__)
-        return e.exit_code
-    except PIL.Image.DecompressionBombError:
-        log.exception(
-            "A decompression bomb error was encountered while executing the "
-            "pipeline. Use the argument --max-image-mpixels to raise the maximum "
-            "image pixel limit."
-        )
-        return ExitCode.other_error
-    except (
-        BrokenProcessPool,
-        BrokenThreadPool,
-    ):
-        log.exception(
-            "A worker process was terminated unexpectedly. This is known to occur if "
-            "processing your file takes all available swap space and RAM. It may "
-            "help to try again with a smaller number of jobs, using the --jobs "
-            "argument."
-        )
-        return ExitCode.child_process_error
-    except Exception:  # pylint: disable=broad-except
-        log.exception("An exception occurred while executing the pipeline")
-        return ExitCode.other_error
-
-
-def setup_pipeline(
-    options: argparse.Namespace,
-    plugin_manager: OcrmypdfPluginManager,
-) -> Executor:
-    # 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()
-
-    pikepdf_enable_mmap()
-    executor = setup_executor(plugin_manager)
-    return executor
-
-
-def preprocess(
-    page_context: PageContext,
-    image: Path,
-    remove_background: bool,
-    deskew: bool,
-    clean: bool,
-) -> Path:
-    """Preprocess an image."""
-    if remove_background:
-        image = preprocess_remove_background(image, page_context)
-    if deskew:
-        image = preprocess_deskew(image, page_context)
-    if clean:
-        image = preprocess_clean(image, page_context)
-    return image
-
-
-def make_intermediate_images(
-    page_context: PageContext, orientation_correction: int
-) -> tuple[Path, Path | None]:
-    """Create intermediate and preprocessed images for OCR."""
-    options = page_context.options
-
-    ocr_image = preprocess_out = None
-    rasterize_out = rasterize(
-        page_context.origin,
-        page_context,
-        correction=orientation_correction,
-        remove_vectors=False,
-    )
-
-    if not any([options.clean, options.clean_final, options.remove_vectors]):
-        ocr_image = preprocess_out = preprocess(
-            page_context,
-            rasterize_out,
-            options.remove_background,
-            options.deskew,
-            clean=False,
-        )
-    else:
-        if not options.lossless_reconstruction:
-            preprocess_out = preprocess(
-                page_context,
-                rasterize_out,
-                options.remove_background,
-                options.deskew,
-                clean=options.clean_final,
-            )
-        if options.remove_vectors:
-            rasterize_ocr_out = rasterize(
-                page_context.origin,
-                page_context,
-                correction=orientation_correction,
-                remove_vectors=True,
-                output_tag='_ocr',
-            )
-        else:
-            rasterize_ocr_out = rasterize_out
-
-        if (
-            preprocess_out
-            and rasterize_ocr_out == rasterize_out
-            and options.clean == options.clean_final
-        ):
-            # Optimization: image for OCR is identical to presentation image
-            ocr_image = preprocess_out
-        else:
-            ocr_image = preprocess(
-                page_context,
-                rasterize_ocr_out,
-                options.remove_background,
-                options.deskew,
-                clean=options.clean,
-            )
-    return ocr_image, preprocess_out
-
-
-def process_page(page_context: PageContext) -> tuple[Path, Path | None, int]:
-    """Process page to create OCR image, visible page image and orientation."""
-    options = page_context.options
-    orientation_correction = 0
-    if options.rotate_pages:
-        # Rasterize
-        rasterize_preview_out = rasterize_preview(page_context.origin, page_context)
-        orientation_correction = get_orientation_correction(
-            rasterize_preview_out, page_context
-        )
-
-    ocr_image, preprocess_out = make_intermediate_images(
-        page_context, orientation_correction
-    )
-    ocr_image_out = create_ocr_image(ocr_image, page_context)
-
-    pdf_page_from_image_out = None
-    if not options.lossless_reconstruction:
-        assert preprocess_out
-        visible_image_out = preprocess_out
-        if should_visible_page_image_use_jpg(page_context.pageinfo):
-            visible_image_out = create_visible_page_jpg(visible_image_out, page_context)
-        filtered_image = page_context.plugin_manager.hook.filter_page_image(
-            page=page_context, image_filename=visible_image_out
-        )
-        if filtered_image is not None:  # None if no hook is present
-            visible_image_out = filtered_image
-        pdf_page_from_image_out = create_pdf_page_from_image(
-            visible_image_out, page_context, orientation_correction
-        )
-    return ocr_image_out, pdf_page_from_image_out, orientation_correction
-
-
-def postprocess(
-    pdf_file: Path, context: PdfContext, executor: Executor
-) -> tuple[Path, Sequence[str]]:
-    """Postprocess the PDF file."""
-    pdf_out = pdf_file
-    if context.options.output_type.startswith('pdfa'):
-        ps_stub_out = generate_postscript_stub(context)
-        pdf_out = convert_to_pdfa(pdf_out, ps_stub_out, context)
-
-    optimizing = context.plugin_manager.hook.is_optimization_enabled(context=context)
-    save_settings = get_pdf_save_settings(context.options.output_type)
-    save_settings['linearize'] = not optimizing and should_linearize(pdf_out, context)
-
-    pdf_out = metadata_fixup(pdf_out, context, pdf_save_settings=save_settings)
-    return optimize_pdf(pdf_out, context, executor)
-
-
-def report_output_pdf(options, start_input_file, optimize_messages) -> ExitCode:
-    if options.output_file == '-':
-        log.info("Output sent to stdout")
-    elif hasattr(options.output_file, 'writable') and options.output_file.writable():
-        log.info("Output written to stream")
-    elif samefile(options.output_file, Path(os.devnull)):
-        pass  # Say nothing when sending to dev null
-    else:
-        if options.output_type.startswith('pdfa'):
-            pdfa_info = file_claims_pdfa(options.output_file)
-            if pdfa_info['pass']:
-                log.info("Output file is a %s (as expected)", pdfa_info['conformance'])
-            else:
-                log.warning(
-                    "Output file is okay but is not PDF/A (seems to be %s)",
-                    pdfa_info['conformance'],
-                )
-                return ExitCode.pdfa_conversion_failed
-        if not check_pdf(options.output_file):
-            log.warning('Output file: The generated PDF is INVALID')
-            return ExitCode.invalid_output_pdf
-        report_output_file_size(
-            options, start_input_file, options.output_file, optimize_messages
-        )
-    return ExitCode.ok

src/ocrmypdf/_pipelines/hocr_to_ocr_pdf.py

@@ -1,134 +0,0 @@
-# SPDX-FileCopyrightText: 2019-2023 James R. Barlow
-# SPDX-FileCopyrightText: 2019 Martin Wind
-# SPDX-License-Identifier: MPL-2.0
-
-"""Implements the concurrent and page synchronous parts of the pipeline."""
-
-
-from __future__ import annotations
-
-import argparse
-import logging
-import logging.handlers
-from collections.abc import Sequence
-from functools import partial
-
-import PIL
-
-from ocrmypdf._concurrent import Executor
-from ocrmypdf._graft import OcrGrafter
-from ocrmypdf._jobcontext import PageContext, PdfContext
-from ocrmypdf._pipeline import (
-    copy_final,
-    get_pdfinfo,
-    render_hocr_page,
-)
-from ocrmypdf._pipelines._common import (
-    HOCRResult,
-    manage_work_folder,
-    postprocess,
-    report_output_pdf,
-    set_thread_pageno,
-    setup_pipeline,
-    worker_init,
-)
-from ocrmypdf._plugin_manager import OcrmypdfPluginManager
-from ocrmypdf._progressbar import ProgressBar
-from ocrmypdf.exceptions import ExitCode
-
-log = logging.getLogger(__name__)
-
-
-def _exec_hocrtransform_sync(page_context: PageContext) -> HOCRResult:
-    """Process each page."""
-    hocr_json = page_context.get_path('hocr.json')
-    if not hocr_json.exists():
-        # No hOCR file, so no OCR was performed on this page.
-        return HOCRResult(pageno=page_context.pageno)
-    hocr_result = HOCRResult.from_json(hocr_json.read_text())
-    hocr_result.textpdf = render_hocr_page(
-        page_context.get_path('ocr_hocr.hocr'), page_context
-    )
-    return hocr_result
-
-
-def exec_hocr_to_ocr_pdf(context: PdfContext, executor: Executor) -> Sequence[str]:
-    """Convert hOCR files to OCR PDF."""
-    # Run exec_page_sync on every page
-    options = context.options
-    max_workers = min(len(context.pdfinfo), options.jobs)
-    if max_workers > 1:
-        log.info("Continue processing %d pages concurrently", max_workers)
-
-    ocrgraft = OcrGrafter(context)
-
-    def graft_page(result: HOCRResult, pbar: ProgressBar):
-        """Graft text only PDF on to main PDF's page."""
-        try:
-            set_thread_pageno(result.pageno + 1)
-            pbar.update()
-            ocrgraft.graft_page(
-                pageno=result.pageno,
-                image=result.pdf_page_from_image,
-                textpdf=result.textpdf,
-                autorotate_correction=result.orientation_correction,
-            )
-            pbar.update()
-        finally:
-            set_thread_pageno(None)
-
-    executor(
-        use_threads=options.use_threads,
-        max_workers=max_workers,
-        progress_kwargs=dict(
-            total=(2 * len(context.pdfinfo)),
-            desc='Grafting hOCR to PDF',
-            unit='page',
-            unit_scale=0.5,
-            disable=not options.progress_bar,
-        ),
-        worker_initializer=partial(worker_init, PIL.Image.MAX_IMAGE_PIXELS),
-        task=_exec_hocrtransform_sync,
-        task_arguments=context.get_page_context_args(),
-        task_finished=graft_page,
-    )
-
-    pdf = ocrgraft.finalize()
-    messages: Sequence[str] = []
-    if options.output_type != 'none':
-        # PDF/A and metadata
-        log.info("Postprocessing...")
-        pdf, messages = postprocess(pdf, context, executor)
-
-        # Copy PDF file to destination (we don't know the input PDF file name)
-        copy_final(pdf, options.output_file, None)
-    return messages
-
-
-def run_hocr_to_ocr_pdf_pipeline(
-    options: argparse.Namespace,
-    *,
-    plugin_manager: OcrmypdfPluginManager,
-) -> ExitCode:
-    """Run pipeline to convert hOCR to final output PDF."""
-    with manage_work_folder(
-        work_folder=options.work_folder, retain=True, print_location=False
-    ) as work_folder:
-        executor = setup_pipeline(options, plugin_manager)
-        origin_pdf = work_folder / 'origin.pdf'
-
-        # Gather pdfinfo and create context
-        pdfinfo = get_pdfinfo(
-            origin_pdf,
-            executor=executor,
-            detailed_analysis=options.redo_ocr,
-            progbar=options.progress_bar,
-            max_workers=options.jobs,
-            use_threads=options.use_threads,
-            check_pages=options.pages,
-        )
-        context = PdfContext(options, work_folder, origin_pdf, pdfinfo, plugin_manager)
-        plugin_manager.hook.check_options(options=options)
-        optimize_messages = exec_hocr_to_ocr_pdf(context, executor)
-
-        return report_output_pdf(options, origin_pdf, optimize_messages)

src/ocrmypdf/_pipelines/ocr.py

@@ -1,225 +0,0 @@
-# SPDX-FileCopyrightText: 2019-2023 James R. Barlow
-# SPDX-FileCopyrightText: 2019 Martin Wind
-# SPDX-License-Identifier: MPL-2.0
-
-"""Implements the concurrent and page synchronous parts of the pipeline."""
-
-
-from __future__ import annotations
-
-import argparse
-import logging
-import logging.handlers
-from collections.abc import Sequence
-from functools import partial
-from pathlib import Path
-from tempfile import mkdtemp
-
-import PIL
-
-from ocrmypdf._concurrent import Executor
-from ocrmypdf._graft import OcrGrafter
-from ocrmypdf._jobcontext import PageContext, PdfContext
-from ocrmypdf._pipeline import (
-    copy_final,
-    get_pdfinfo,
-    is_ocr_required,
-    merge_sidecars,
-    ocr_engine_hocr,
-    ocr_engine_textonly_pdf,
-    render_hocr_page,
-    triage,
-    validate_pdfinfo_options,
-)
-from ocrmypdf._pipelines._common import (
-    PageResult,
-    cli_exception_handler,
-    manage_debug_log_handler,
-    manage_work_folder,
-    postprocess,
-    process_page,
-    report_output_pdf,
-    set_thread_pageno,
-    setup_pipeline,
-    worker_init,
-)
-from ocrmypdf._plugin_manager import OcrmypdfPluginManager
-from ocrmypdf._progressbar import ProgressBar
-from ocrmypdf._validation import (
-    check_requested_output_file,
-    create_input_file,
-)
-from ocrmypdf.exceptions import ExitCode
-
-log = logging.getLogger(__name__)
-
-
-def _image_to_ocr_text(
-    page_context: PageContext, ocr_image_out: Path
-) -> tuple[Path, Path]:
-    """Run OCR engine on image to create OCR PDF and text file."""
-    options = page_context.options
-    if options.pdf_renderer.startswith('hocr'):
-        hocr_out, text_out = ocr_engine_hocr(ocr_image_out, page_context)
-        ocr_out = render_hocr_page(hocr_out, page_context)
-    elif options.pdf_renderer == 'sandwich':
-        ocr_out, text_out = ocr_engine_textonly_pdf(ocr_image_out, page_context)
-    else:
-        raise NotImplementedError(f"pdf_renderer {options.pdf_renderer}")
-    return ocr_out, text_out
-
-
-def _exec_page_sync(page_context: PageContext) -> PageResult:
-    """Execute a pipeline for a single page synchronously."""
-    set_thread_pageno(page_context.pageno + 1)
-
-    if not is_ocr_required(page_context):
-        return PageResult(pageno=page_context.pageno)
-
-    ocr_image_out, pdf_page_from_image_out, orientation_correction = process_page(
-        page_context
-    )
-    ocr_out, text_out = _image_to_ocr_text(page_context, ocr_image_out)
-
-    return PageResult(
-        pageno=page_context.pageno,
-        pdf_page_from_image=pdf_page_from_image_out,
-        ocr=ocr_out,
-        text=text_out,
-        orientation_correction=orientation_correction,
-    )
-
-
-def exec_concurrent(context: PdfContext, executor: Executor) -> Sequence[str]:
-    """Execute the OCR pipeline concurrently."""
-    options = context.options
-    max_workers = min(len(context.pdfinfo), options.jobs)
-    if max_workers > 1:
-        log.info("Start processing %d pages concurrently", max_workers)
-
-    sidecars: list[Path | None] = [None] * len(context.pdfinfo)
-    ocrgraft = OcrGrafter(context)
-
-    def update_page(result: PageResult, pbar: ProgressBar):
-        """After OCR is complete for a page, update the PDF."""
-        try:
-            set_thread_pageno(result.pageno + 1)
-            sidecars[result.pageno] = result.text
-            pbar.update()
-            ocrgraft.graft_page(
-                pageno=result.pageno,
-                image=result.pdf_page_from_image,
-                textpdf=result.ocr,
-                autorotate_correction=result.orientation_correction,
-            )
-            pbar.update()
-        finally:
-            set_thread_pageno(None)
-
-    executor(
-        use_threads=options.use_threads,
-        max_workers=max_workers,
-        progress_kwargs=dict(
-            total=(2 * len(context.pdfinfo)),
-            desc='OCR' if options.tesseract_timeout > 0 else 'Image processing',
-            unit='page',
-            unit_scale=0.5,
-            disable=not options.progress_bar,
-        ),
-        worker_initializer=partial(worker_init, PIL.Image.MAX_IMAGE_PIXELS),
-        task=_exec_page_sync,
-        task_arguments=context.get_page_context_args(),
-        task_finished=update_page,
-    )
-
-    # Output sidecar text
-    if options.sidecar:
-        text = merge_sidecars(sidecars, context)
-        # Copy text file to destination
-        copy_final(text, options.sidecar, options.input_file)
-
-    # Merge layers to one single pdf
-    pdf = ocrgraft.finalize()
-
-    messages: Sequence[str] = []
-    if options.output_type != 'none':
-        # PDF/A and metadata
-        log.info("Postprocessing...")
-        pdf, messages = postprocess(pdf, context, executor)
-
-        # Copy PDF file to destination
-        copy_final(pdf, options.output_file, options.input_file)
-    return messages
-
-
-def _run_pipeline(
-    options: argparse.Namespace,
-    plugin_manager: OcrmypdfPluginManager,
-) -> ExitCode:
-    with manage_work_folder(
-        work_folder=Path(mkdtemp(prefix="ocrmypdf.io.")),
-        retain=options.keep_temporary_files,
-        print_location=options.keep_temporary_files,
-    ) as work_folder, manage_debug_log_handler(
-        options=options, work_folder=work_folder
-    ):
-        executor = setup_pipeline(options, plugin_manager)
-        check_requested_output_file(options)
-        start_input_file, original_filename = create_input_file(options, work_folder)
-
-        # Triage image or pdf
-        origin_pdf = triage(
-            original_filename, start_input_file, work_folder / 'origin.pdf', options
-        )
-
-        # Gather pdfinfo and create context
-        pdfinfo = get_pdfinfo(
-            origin_pdf,
-            executor=executor,
-            detailed_analysis=options.redo_ocr,
-            progbar=options.progress_bar,
-            max_workers=options.jobs,
-            use_threads=options.use_threads,
-            check_pages=options.pages,
-        )
-
-        context = PdfContext(options, work_folder, origin_pdf, pdfinfo, plugin_manager)
-
-        # Validate options are okay for this pdf
-        validate_pdfinfo_options(context)
-
-        # Execute the pipeline
-        optimize_messages = exec_concurrent(context, executor)
-
-        exitcode = report_output_pdf(options, start_input_file, optimize_messages)
-        return exitcode
-
-
-def run_pipeline_cli(
-    options: argparse.Namespace,
-    *,
-    plugin_manager: OcrmypdfPluginManager,
-) -> ExitCode:
-    """Run the OCR pipeline with command line exception handling.
-
-    Args:
-        options: The parsed command line options.
-        plugin_manager: The plugin manager to use. If not provided, one will be
-            created.
-    """
-    return cli_exception_handler(_run_pipeline, options, plugin_manager)
-
-
-def run_pipeline(
-    options: argparse.Namespace,
-    *,
-    plugin_manager: OcrmypdfPluginManager,
-) -> ExitCode:
-    """Run the OCR pipeline without command line exception handling.
-
-    Args:
-        options: The parsed command line options.
-        plugin_manager: The plugin manager to use. If not provided, one will be
-            created.
-    """
-    return _run_pipeline(options, plugin_manager)

src/ocrmypdf/_pipelines/pdf_to_hocr.py

@@ -1,116 +0,0 @@
-# SPDX-FileCopyrightText: 2019-2023 James R. Barlow
-# SPDX-FileCopyrightText: 2019 Martin Wind
-# SPDX-License-Identifier: MPL-2.0
-
-"""Implements the concurrent and page synchronous parts of the pipeline."""
-
-
-from __future__ import annotations
-
-import argparse
-import logging
-import logging.handlers
-import shutil
-from functools import partial
-
-import PIL
-
-from ocrmypdf._concurrent import Executor
-from ocrmypdf._jobcontext import PageContext, PdfContext
-from ocrmypdf._pipeline import (
-    get_pdfinfo,
-    is_ocr_required,
-    ocr_engine_hocr,
-    validate_pdfinfo_options,
-)
-from ocrmypdf._pipelines._common import (
-    HOCRResult,
-    manage_work_folder,
-    process_page,
-    set_thread_pageno,
-    setup_pipeline,
-    worker_init,
-)
-from ocrmypdf._plugin_manager import OcrmypdfPluginManager
-from ocrmypdf._validation import (
-    set_lossless_reconstruction,
-)
-
-log = logging.getLogger(__name__)
-
-
-def _exec_page_hocr_sync(page_context: PageContext) -> HOCRResult:
-    """Execute a pipeline for a single page hOCR."""
-    set_thread_pageno(page_context.pageno + 1)
-
-    if not is_ocr_required(page_context):
-        return HOCRResult(pageno=page_context.pageno)
-
-    ocr_image_out, pdf_page_from_image_out, orientation_correction = process_page(
-        page_context
-    )
-    hocr_out, _ = ocr_engine_hocr(ocr_image_out, page_context)
-
-    result = HOCRResult(
-        pageno=page_context.pageno,
-        pdf_page_from_image=pdf_page_from_image_out,
-        hocr=hocr_out,
-        orientation_correction=orientation_correction,
-    )
-    page_context.get_path('hocr.json').write_text(result.to_json())
-    return result
-
-
-def exec_pdf_to_hocr(context: PdfContext, executor: Executor) -> None:
-    """Execute the OCR pipeline concurrently and output hOCR."""
-    # Run exec_page_sync on every page
-    options = context.options
-    max_workers = min(len(context.pdfinfo), options.jobs)
-    if max_workers > 1:
-        log.info("Start processing %d pages concurrently", max_workers)
-
-    executor(
-        use_threads=options.use_threads,
-        max_workers=max_workers,
-        progress_kwargs=dict(
-            total=(2 * len(context.pdfinfo)),
-            desc='hOCR',
-            unit='page',
-            unit_scale=0.5,
-            disable=not options.progress_bar,
-        ),
-        worker_initializer=partial(worker_init, PIL.Image.MAX_IMAGE_PIXELS),
-        task=_exec_page_hocr_sync,
-        task_arguments=context.get_page_context_args(),
-    )
-
-
-def run_hocr_pipeline(
-    options: argparse.Namespace,
-    *,
-    plugin_manager: OcrmypdfPluginManager,
-) -> None:
-    """Run pipeline to output hOCR."""
-    with manage_work_folder(
-        work_folder=options.output_folder, retain=True, print_location=False
-    ) as work_folder:
-        executor = setup_pipeline(options, plugin_manager)
-        shutil.copy2(options.input_file, work_folder / 'origin.pdf')
-
-        # Gather pdfinfo and create context
-        pdfinfo = get_pdfinfo(
-            options.input_file,
-            executor=executor,
-            detailed_analysis=options.redo_ocr,
-            progbar=options.progress_bar,
-            max_workers=options.jobs,
-            use_threads=options.use_threads,
-            check_pages=options.pages,
-        )
-        context = PdfContext(
-            options, work_folder, options.input_file, pdfinfo, plugin_manager
-        )
-        # Validate options are okay for this pdf
-        set_lossless_reconstruction(options)
-        validate_pdfinfo_options(context)
-        exec_pdf_to_hocr(context, executor)

src/ocrmypdf/_plugin_manager.py

@@ -1,129 +0,0 @@
-# SPDX-FileCopyrightText: 2022 James R. Barlow
-# SPDX-License-Identifier: MPL-2.0
-
-"""Plugin manager using pluggy."""
-
-from __future__ import annotations
-
-import argparse
-import importlib
-import importlib.util
-import pkgutil
-import sys
-from collections.abc import Sequence
-from pathlib import Path
-
-import pluggy
-
-import ocrmypdf.builtin_plugins
-from ocrmypdf import pluginspec
-from ocrmypdf.cli import get_parser, plugins_only_parser
-
-
-class OcrmypdfPluginManager(pluggy.PluginManager):
-    """pluggy.PluginManager that can fork.
-
-    Capable of reconstructing itself in child workers.
-
-    Arguments:
-        setup_func: callback that initializes the plugin manager with all
-            standard plugins
-    """
-
-    def __init__(
-        self,
-        *args,
-        plugins: Sequence[str | Path],
-        builtins: bool = True,
-        **kwargs,
-    ):
-        self.__init_args = args
-        self.__init_kwargs = kwargs
-        self.__plugins = plugins
-        self.__builtins = builtins
-        super().__init__(*args, **kwargs)
-        self.setup_plugins()
-
-    def __getstate__(self):
-        state = dict(
-            init_args=self.__init_args,
-            plugins=self.__plugins,
-            builtins=self.__builtins,
-            init_kwargs=self.__init_kwargs,
-        )
-        return state
-
-    def __setstate__(self, state):
-        self.__init__(
-            *state['init_args'],
-            plugins=state['plugins'],
-            builtins=state['builtins'],
-            **state['init_kwargs'],
-        )
-
-    def setup_plugins(self):
-        self.add_hookspecs(pluginspec)
-
-        # 1. Register builtins
-        if self.__builtins:
-            for module in sorted(
-                pkgutil.iter_modules(ocrmypdf.builtin_plugins.__path__)
-            ):
-                name = f'ocrmypdf.builtin_plugins.{module.name}'
-                module = importlib.import_module(name)
-                self.register(module)
-
-        # 2. Install semfree if needed
-        try:
-            # pylint: disable=import-outside-toplevel
-            from multiprocessing.synchronize import SemLock
-
-            del SemLock
-        except ImportError:
-            self.register(importlib.import_module('ocrmypdf.extra_plugins.semfree'))
-
-        # 3. Register setuptools plugins
-        self.load_setuptools_entrypoints('ocrmypdf')
-
-        # 4. Register plugins specified on command line
-        for name in self.__plugins:
-            if isinstance(name, Path) or name.endswith('.py'):
-                # Import by filename
-                module_name = Path(name).stem
-                spec = importlib.util.spec_from_file_location(module_name, name)
-                module = importlib.util.module_from_spec(spec)
-                sys.modules[module_name] = module
-                spec.loader.exec_module(module)
-            else:
-                # Import by dotted module name
-                module = importlib.import_module(name)
-            self.register(module)
-
-
-def get_plugin_manager(
-    plugins: Sequence[str | Path] | None = None, builtins=True
-) -> OcrmypdfPluginManager:
-    return OcrmypdfPluginManager(
-        project_name='ocrmypdf',
-        plugins=plugins if plugins is not None else [],
-        builtins=builtins,
-    )
-
-
-def get_parser_options_plugins(
-    args: Sequence[str],
-) -> tuple[argparse.ArgumentParser, argparse.Namespace, pluggy.PluginManager]:
-    pre_options, _unused = plugins_only_parser.parse_known_args(args=args)
-    plugin_manager = get_plugin_manager(pre_options.plugins)
-
-    parser = get_parser()
-    plugin_manager.hook.initialize(  # pylint: disable=no-member
-        plugin_manager=plugin_manager
-    )
-    plugin_manager.hook.add_options(parser=parser)  # pylint: disable=no-member
-
-    options = parser.parse_args(args=args)
-    return parser, options, plugin_manager
-
-
-__all__ = ['OcrmypdfPluginManager', 'get_plugin_manager', 'get_parser_options_plugins']

src/ocrmypdf/_progressbar.py

@@ -1,142 +0,0 @@
-# SPDX-FileCopyrightText: 2023 James R. Barlow
-# SPDX-License-Identifier: MPL-2.0
-
-"""Defines progress bar API."""
-
-from __future__ import annotations
-
-from typing import Protocol
-
-from rich.console import Console
-from rich.progress import (
-    BarColumn,
-    MofNCompleteColumn,
-    Progress,
-    TaskProgressColumn,
-    TextColumn,
-    TimeRemainingColumn,
-)
-from rich.table import Column
-
-
-class ProgressBar(Protocol):
-    """The protocol that OCRmyPDF expects progress bar classes to be compatible with.
-
-    In practice this could be used for any time of monitoring, not just a progress bar.
-
-    Calling the class should return a new progress bar object, which is activated
-    with ``__enter__`` and terminated with ``__exit__``. An update method is called
-    whenever the progress bar is updated. Progress bar objects will not be reused;
-    a new one will be created for each group of tasks.
-
-    The progress bar is held in the main process/thread and not updated by child
-    process/threads. When a child notifies the parent of completed work, the
-    parent updates the progress bar.
-
-    Progress bars should never write to ``sys.stdout``, or they will corrupt the
-    output if OCRmyPDF writes a PDF to standard output.
-
-    The type of events that OCRmyPDF reports to a progress bar may change in
-    minor releases.
-    """
-
-    def __init__(
-        self,
-        *,
-        total: int | float | None,
-        desc: str | None,
-        unit: str | None,
-        disable: bool = False,
-        **kwargs,
-    ):
-        """Initialize a progress bar.
-
-        *total* indicates the total number of work units. If None, the total
-        number of work units is unknown. If *disable* is True, the progress bar
-        should be disabled. *unit* is a description of the work unit.
-        *desc* is a description of the overall task to be performed.
-
-        Unrecognized keyword arguments must be ignored, as the list of keyword
-        arguments may grow with time.
-        """
-
-    def __enter__(self):
-        """Enter a progress bar context."""
-
-    def __exit__(self, *args):
-        """Exit a progress bar context."""
-
-    def update(self, n=1):
-        """Update the progress bar by an increment.
-
-        For use within a progress bar context.
-        """
-
-
-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 RichProgressBar:
-    """Display progress bar using rich."""
-
-    def __init__(
-        self,
-        *,
-        console: Console,
-        desc: str,
-        total: float | None = None,
-        unit: str | None = None,
-        unit_scale: float | None = 1.0,
-        disable: bool = False,
-        **kwargs,
-    ):
-        self.progress = Progress(
-            TextColumn(
-                "[progress.description]{task.description}",
-                table_column=Column(min_width=20),
-            ),
-            BarColumn(),
-            TaskProgressColumn(),
-            MofNCompleteColumn(),
-            TimeRemainingColumn(),
-            console=console,
-            auto_refresh=True,
-            redirect_stderr=True,
-            redirect_stdout=False,
-            disable=disable,
-            **kwargs,
-        )
-        self.unit_scale = unit_scale
-        self.progress_bar = self.progress.add_task(
-            desc,
-            total=total * self.unit_scale
-            if total is not None and self.unit_scale is not None
-            else None,
-            unit=unit,
-        )
-
-    def __enter__(self):
-        self.progress.start()
-        return self
-
-    def __exit__(self, exc_type, exc_value, traceback):
-        self.progress.refresh()
-        self.progress.stop()
-        return False
-
-    def update(self, value=None):
-        advance = self.unit_scale if value is None else value
-        self.progress.update(self.progress_bar, advance=advance)

src/ocrmypdf/_validation.py

@@ -1,368 +0,0 @@
-#!/usr/bin/env python3
-# SPDX-FileCopyrightText: 2022 James R. Barlow
-# SPDX-License-Identifier: MPL-2.0
-
-"""Validate a work order from API or command line."""
-
-from __future__ import annotations
-
-import locale
-import logging
-import os
-import sys
-import unicodedata
-from argparse import Namespace
-from collections.abc import Sequence
-from pathlib import Path
-from shutil import copyfileobj
-
-import pikepdf
-import PIL
-from pluggy import PluginManager
-
-from ocrmypdf._exec import unpaper
-from ocrmypdf.exceptions import (
-    BadArgsError,
-    InputFileError,
-    MissingDependencyError,
-    OutputFileAccessError,
-)
-from ocrmypdf.helpers import is_file_writable, monotonic, safe_symlink
-from ocrmypdf.subprocess import check_external_program
-
-# -------------
-# External dependencies
-
-DEFAULT_LANGUAGE = 'eng'  # Enforce English hegemony
-
-log = logging.getLogger(__name__)
-
-
-# --------
-
-
-def check_platform() -> None:
-    if sys.maxsize <= 2**32:  # pragma: no cover
-        log.warning(
-            "You are running OCRmyPDF in a 32-bit (x86) Python interpreter. "
-            "This is not supported. 32-bit does not have enough address space "
-            "to process large files. "
-            "Please use a 64-bit (x86-64) version of Python."
-        )
-
-
-def check_options_languages(
-    options: Namespace, ocr_engine_languages: list[str]
-) -> None:
-    if not options.languages:
-        options.languages = [DEFAULT_LANGUAGE]
-        system_lang = locale.getlocale()[0]
-        if system_lang and not system_lang.startswith('en'):
-            log.debug("No language specified; assuming --language %s", DEFAULT_LANGUAGE)
-    if not ocr_engine_languages:
-        return
-    missing_languages = set(options.languages) - set(ocr_engine_languages)
-    if missing_languages:
-        lang_text = '\n'.join(lang for lang in missing_languages)
-        msg = (
-            "OCR engine does not have language data for the following "
-            "requested languages: \n"
-            f"{lang_text}\n"
-            "Please install the appropriate language data for your OCR engine.\n"
-            "\n"
-            "See the online documentation for instructions:\n"
-            "    https://ocrmypdf.readthedocs.io/en/latest/languages.html\n"
-            "\n"
-            "Note: most languages are identified by a 3-letter ISO 639-2 Code.\n"
-            "For example, English is 'eng', German is 'deu', and Spanish is 'spa'.\n"
-            "Simplified Chinese is 'chi_sim' and Traditional Chinese is 'chi_tra'."
-            "\n"
-        )
-        raise MissingDependencyError(msg)
-
-
-def check_options_output(options: Namespace) -> None:
-    if options.output_type == 'none' and options.output_file not in (os.devnull, '-'):
-        raise BadArgsError(
-            "Since you specified `--output-type none`, the output file "
-            f"{options.output_file} cannot be produced. Set the output file to "
-            f"`-` to suppress this message."
-        )
-
-
-def set_lossless_reconstruction(options: Namespace) -> None:
-    lossless_reconstruction = False
-    if not any(
-        (
-            options.deskew,
-            options.clean_final,
-            options.force_ocr,
-            options.remove_background,
-        )
-    ):
-        lossless_reconstruction = True
-    options.lossless_reconstruction = lossless_reconstruction
-
-    if not options.lossless_reconstruction and options.redo_ocr:
-        raise BadArgsError(
-            "--redo-ocr is not currently compatible with --deskew, "
-            "--clean-final, and --remove-background"
-        )
-
-
-def check_options_sidecar(options: Namespace) -> None:
-    if options.sidecar == '\0':
-        if options.output_file == '-':
-            raise BadArgsError("--sidecar filename needed when output file is stdout.")
-        elif options.output_file == os.devnull:
-            raise BadArgsError(
-                "--sidecar filename needed when output file is /dev/null or NUL."
-            )
-        options.sidecar = options.output_file + '.txt'
-    if options.sidecar == options.input_file or options.sidecar == options.output_file:
-        raise BadArgsError(
-            "--sidecar file must be different from the input and output files"
-        )
-
-
-def check_options_preprocessing(options: Namespace) -> None:
-    if options.clean_final:
-        options.clean = True
-    if options.unpaper_args and not options.clean:
-        raise BadArgsError("--clean is required for --unpaper-args")
-    if options.clean:
-        check_external_program(
-            program='unpaper',
-            package='unpaper',
-            version_checker=unpaper.version,
-            need_version='6.1',
-            required_for="--clean, --clean-final",  # Problem arguments
-        )
-        try:
-            if options.unpaper_args:
-                options.unpaper_args = unpaper.validate_custom_args(
-                    options.unpaper_args
-                )
-        except Exception as e:
-            raise BadArgsError("--unpaper-args: " + str(e)) from e
-
-
-def _pages_from_ranges(ranges: str) -> set[int]:
-    pages: list[int] = []
-    page_groups = ranges.replace(' ', '').split(',')
-    for group in page_groups:
-        if not group:
-            continue
-        try:
-            start, end = group.split('-')
-        except ValueError:
-            pages.append(int(group) - 1)
-        else:
-            try:
-                new_pages = list(range(int(start) - 1, int(end)))
-                if not new_pages:
-                    raise BadArgsError(
-                        f"invalid page subrange '{start}-{end}'"
-                    ) from None
-                pages.extend(new_pages)
-            except ValueError:
-                raise BadArgsError(f"invalid page subrange '{group}'") from None
-
-    if not pages:
-        raise BadArgsError(
-            f"The string of page ranges '{ranges}' did not contain any recognizable "
-            f"page ranges."
-        )
-
-    if not monotonic(pages):
-        log.warning(
-            "List of pages to process contains duplicate pages, or pages that are "
-            "out of order"
-        )
-    if any(page < 0 for page in pages):
-        raise BadArgsError("pages refers to a page number less than 1")
-
-    log.debug("OCRing only these pages: %s", pages)
-    return set(pages)
-
-
-def check_options_ocr_behavior(options: Namespace) -> None:
-    exclusive_options = sum(
-        (1 if opt else 0)
-        for opt in (options.force_ocr, options.skip_text, options.redo_ocr)
-    )
-    if exclusive_options >= 2:
-        raise BadArgsError("Choose only one of --force-ocr, --skip-text, --redo-ocr.")
-    if options.pages:
-        options.pages = _pages_from_ranges(options.pages)
-
-
-def check_options_metadata(options: Namespace) -> None:
-    docinfo = [options.title, options.author, options.keywords, options.subject]
-    for s in (m for m in docinfo if m):
-        for char in s:
-            if unicodedata.category(char) == 'Co' or ord(char) >= 0x10000:
-                hexchar = hex(ord(char))[2:].upper()
-                raise ValueError(
-                    "One of the metadata strings contains "
-                    "an unsupported Unicode character: "
-                    f"{char} (U+{hexchar})"
-                )
-
-
-def check_options_pillow(options: Namespace) -> None:
-    PIL.Image.MAX_IMAGE_PIXELS = int(options.max_image_mpixels * 1_000_000)
-    if PIL.Image.MAX_IMAGE_PIXELS == 0:
-        PIL.Image.MAX_IMAGE_PIXELS = None  # type: ignore
-
-
-def _check_plugin_invariant_options(options: Namespace) -> None:
-    check_platform()
-    check_options_metadata(options)
-    check_options_output(options)
-    set_lossless_reconstruction(options)
-    check_options_sidecar(options)
-    check_options_preprocessing(options)
-    check_options_ocr_behavior(options)
-    check_options_pillow(options)
-
-
-def _check_plugin_options(options: Namespace, plugin_manager: PluginManager) -> None:
-    plugin_manager.hook.check_options(options=options)
-    ocr_engine_languages = plugin_manager.hook.get_ocr_engine().languages(options)
-    check_options_languages(options, ocr_engine_languages)
-
-
-def check_options(options: Namespace, plugin_manager: PluginManager) -> None:
-    _check_plugin_invariant_options(options)
-    _check_plugin_options(options, plugin_manager)
-
-
-def _in_docker():
-    return Path('/.dockerenv').exists()
-
-
-def _in_snap():
-    try:
-        cgroup_text = Path('/proc/self/cgroup').read_text()
-        return 'snap.ocrmypdf' in cgroup_text
-    except FileNotFoundError:
-        return False
-
-
-def create_input_file(options: Namespace, work_folder: Path) -> tuple[Path, str]:
-    if options.input_file == '-':
-        # stdin
-        log.info('reading file from standard input')
-        target = work_folder / 'stdin'
-        with open(target, 'wb') as stream_buffer:
-            copyfileobj(sys.stdin.buffer, stream_buffer)
-        return target, "stdin"
-    elif hasattr(options.input_file, 'readable'):
-        if not options.input_file.readable():
-            raise InputFileError("Input file stream is not readable")
-        log.info('reading file from input stream')
-        target = work_folder / 'stream'
-        with open(target, 'wb') as stream_buffer:
-            copyfileobj(options.input_file, stream_buffer)
-        return target, "stream"
-    else:
-        try:
-            target = work_folder / 'origin'
-            safe_symlink(options.input_file, target)
-            return target, os.fspath(options.input_file)
-        except FileNotFoundError as e:
-            msg = f"File not found - {options.input_file}"
-            if _in_docker():  # pragma: no cover
-                msg += (
-                    "\nDocker cannot access your working directory unless you "
-                    "explicitly share it with the Docker container and set up"
-                    "permissions correctly.\n"
-                    "You may find it easier to use stdin/stdout:"
-                    "\n"
-                    "\tdocker run -i --rm jbarlow83/ocrmypdf - - <input.pdf >output.pdf"
-                    "\n"
-                )
-            elif _in_snap():  # pragma: no cover
-                msg += (
-                    "\nSnap applications cannot access files outside of "
-                    "your home directory unless you explicitly allow it. "
-                    "You may find it easier to use stdin/stdout:"
-                    "\n"
-                    "\tsnap run ocrmypdf - - <input.pdf >output.pdf"
-                    "\n"
-                )
-            raise InputFileError(msg) from e
-
-
-def check_requested_output_file(options: Namespace) -> None:
-    if options.output_file == '-':
-        if sys.stdout.isatty():
-            raise BadArgsError(
-                "Output was set to stdout '-' but it looks like stdout "
-                "is connected to a terminal.  Please redirect stdout to a "
-                "file."
-            )
-    elif hasattr(options.output_file, 'writable'):
-        if not options.output_file.writable():
-            raise OutputFileAccessError("Output stream is not writable")
-    elif not is_file_writable(options.output_file):
-        raise OutputFileAccessError(
-            f"Output file location ({options.output_file}) is not a writable file."
-        )
-
-
-def report_output_file_size(
-    options: Namespace,
-    input_file: Path,
-    output_file: Path,
-    optimize_messages: Sequence[str] | None = None,
-    file_overhead: int = 4000,
-    page_overhead: int = 3000,
-) -> None:
-    if optimize_messages is None:
-        optimize_messages = []
-    try:
-        output_size = Path(output_file).stat().st_size
-        input_size = Path(input_file).stat().st_size
-    except FileNotFoundError:
-        return  # Outputting to stream or something
-    with pikepdf.open(output_file) as p:
-        # Overhead constants obtained by estimating amount of data added by OCR
-        # PDF/A conversion, and possible XMP metadata addition, with compression
-        reasonable_overhead = file_overhead + page_overhead * len(p.pages)
-    ratio = output_size / input_size
-    reasonable_ratio = output_size / (input_size + reasonable_overhead)
-    if reasonable_ratio < 1.35 or input_size < 25000:
-        return  # Seems fine
-
-    reasons = []
-    image_preproc = {
-        'deskew',
-        'clean_final',
-        'remove_background',
-        'oversample',
-        'force_ocr',
-    }
-    for arg in image_preproc:
-        if getattr(options, arg, False):
-            reasons.append(
-                f"--{arg.replace('_', '-')} was issued, causing transcoding."
-            )
-
-    reasons.extend(optimize_messages)
-
-    if options.output_type.startswith('pdfa'):
-        reasons.append("PDF/A conversion was enabled. (Try `--output-type pdf`.)")
-    if options.plugins:
-        reasons.append("Plugins were used.")
-
-    if reasons:
-        explanation = "Possible reasons for this include:\n" + '\n'.join(reasons) + "\n"
-    else:
-        explanation = "No reason for this increase is known.  Please report this issue."
-
-    log.warning(
-        f"The output file size is {ratio:.2f}× larger than the input file.\n"
-        f"{explanation}"
-    )

src/ocrmypdf/_version.py

@@ -1,16 +0,0 @@
-# SPDX-FileCopyrightText: 2022 James R. Barlow
-# SPDX-License-Identifier: MPL-2.0
-
-"""Get version by introspecting package information.
-
-OCRmyPDF uses setuptools_scm to derive version from git tags.
-"""
-
-from __future__ import annotations
-
-from importlib.metadata import version as _package_version
-
-PROGRAM_NAME = 'ocrmypdf'
-
-# Official PEP 396
-__version__ = _package_version('ocrmypdf')

src/ocrmypdf/api.py

@@ -1,552 +0,0 @@
-# SPDX-FileCopyrightText: 2022 James R. Barlow
-# SPDX-License-Identifier: MPL-2.0
-
-"""Functions for using ocrmypdf as an API."""
-
-from __future__ import annotations
-
-import logging
-import os
-import sys
-import threading
-from argparse import Namespace
-from collections.abc import Iterable, Sequence
-from enum import IntEnum
-from io import IOBase
-from pathlib import Path
-from typing import AnyStr, BinaryIO, Union
-from warnings import warn
-
-import pluggy
-
-from ocrmypdf._logging import PageNumberFilter
-from ocrmypdf._pipelines.hocr_to_ocr_pdf import run_hocr_to_ocr_pdf_pipeline
-from ocrmypdf._pipelines.ocr import run_pipeline, run_pipeline_cli
-from ocrmypdf._pipelines.pdf_to_hocr import run_hocr_pipeline
-from ocrmypdf._plugin_manager import get_plugin_manager
-from ocrmypdf._validation import check_options
-from ocrmypdf.cli import ArgumentParser, get_parser
-from ocrmypdf.helpers import is_iterable_notstr
-
-StrPath = Union[Path, AnyStr]
-PathOrIO = Union[BinaryIO, StrPath]
-
-# Installing plugins affects the global state of the Python interpreter,
-# so we need to use a lock to prevent multiple threads from installing
-# plugins at the same time.
-_api_lock = threading.Lock()
-
-
-class Verbosity(IntEnum):
-    """Verbosity level for configure_logging."""
-
-    # pylint: disable=invalid-name
-    quiet = -1  #: Suppress most messages
-    default = 0  #: Default level of logging
-    debug = 1  #: Output ocrmypdf debug messages
-    debug_all = 2  #: More detailed debugging from ocrmypdf and dependent modules
-
-
-def configure_logging(
-    verbosity: Verbosity,
-    *,
-    progress_bar_friendly: bool = True,
-    manage_root_logger: bool = False,
-    plugin_manager: pluggy.PluginManager | None = None,
-):
-    """Set up logging.
-
-    Before calling :func:`ocrmypdf.ocr()`, you can use this function to
-    configure logging if you want ocrmypdf's output to look like the ocrmypdf
-    command line interface. It will register log handlers, log filters, and
-    formatters, configure color logging to standard error, and adjust the log
-    levels of third party libraries. Details of this are fine-tuned and subject
-    to change. The ``verbosity`` argument is equivalent to the argument
-    ``--verbose`` and applies those settings. If you have a wrapper
-    script for ocrmypdf and you want it to be very similar to ocrmypdf, use this
-    function; if you are using ocrmypdf as part of an application that manages
-    its own logging, you probably do not want this function.
-
-    If this function is not called, ocrmypdf will not configure logging, and it
-    is up to the caller of ``ocrmypdf.ocr()`` to set up logging as it wishes using
-    the Python standard library's logging module. If this function is called,
-    the caller may of course make further adjustments to logging.
-
-    Regardless of whether this function is called, ocrmypdf will perform all of
-    its logging under the ``"ocrmypdf"`` logging namespace. In addition,
-    ocrmypdf imports pdfminer, which logs under ``"pdfminer"``. A library user
-    may wish to configure both; note that pdfminer is extremely chatty at the
-    log level ``logging.INFO``.
-
-    This function does not set up the ``debug.log`` log file that the command
-    line interface does at certain verbosity levels. Applications should configure
-    their own debug logging.
-
-    Args:
-        verbosity: Verbosity level.
-        progress_bar_friendly: If True (the default), install a custom log handler
-            that is compatible with progress bars and colored output.
-        manage_root_logger: Configure the process's root logger.
-        plugin_manager: The plugin manager, used for obtaining the custom log handler.
-
-    Returns:
-        The toplevel logger for ocrmypdf (or the root logger, if we are managing it).
-    """
-    prefix = '' if manage_root_logger else 'ocrmypdf'
-
-    log = logging.getLogger(prefix)
-    log.setLevel(logging.DEBUG)
-
-    console = None
-    if plugin_manager and progress_bar_friendly:
-        console = plugin_manager.hook.get_logging_console()
-
-    if not console:
-        console = logging.StreamHandler(stream=sys.stderr)
-
-    if verbosity < 0:
-        console.setLevel(logging.ERROR)
-    elif verbosity >= 1:
-        console.setLevel(logging.DEBUG)
-    else:
-        console.setLevel(logging.INFO)
-
-    console.addFilter(PageNumberFilter())
-
-    if verbosity >= 2:
-        fmt = '%(levelname)7s %(name)s -%(pageno)s %(message)s'
-    else:
-        fmt = '%(pageno)s%(message)s'
-
-    formatter = None
-
-    if not formatter:
-        formatter = logging.Formatter(fmt=fmt)
-
-    console.setFormatter(formatter)
-    log.addHandler(console)
-
-    if verbosity <= 1:
-        pdfminer_log = logging.getLogger('pdfminer')
-        pdfminer_log.setLevel(logging.ERROR)
-        pil_log = logging.getLogger('PIL')
-        pil_log.setLevel(logging.INFO)
-
-    if manage_root_logger:
-        logging.captureWarnings(True)
-
-    return log
-
-
-def _kwargs_to_cmdline(
-    *, defer_kwargs: set[str], **kwargs
-) -> tuple[list[str], dict[str, AnyStr]]:
-    """Convert kwargs to command line arguments."""
-    cmdline = []
-    deferred = {}
-    for arg, val in kwargs.items():
-        if val is None:
-            continue
-
-        # Skip arguments that are handled elsewhere
-        if arg in defer_kwargs:
-            deferred[arg] = val
-            continue
-
-        cmd_style_arg = arg.replace('_', '-')
-
-        # Booleans are special: add only if True, omit for False
-        if isinstance(val, bool):
-            if val:
-                cmdline.append(f"--{cmd_style_arg}")
-            continue
-
-        if is_iterable_notstr(val):
-            for elem in val:
-                cmdline.append(f"--{cmd_style_arg}")
-                cmdline.append(elem)
-            continue
-
-        # We have a parameter
-        cmdline.append(f"--{cmd_style_arg}")
-        if isinstance(val, (int, float)):
-            cmdline.append(str(val))
-        elif isinstance(val, str):
-            cmdline.append(val)
-        elif isinstance(val, Path):
-            cmdline.append(str(val))
-        else:
-            raise TypeError(f"{arg}: {val} ({type(val)})")
-    return cmdline, deferred
-
-
-def create_options(
-    *, input_file: PathOrIO, output_file: PathOrIO, parser: ArgumentParser, **kwargs
-) -> Namespace:
-    """Construct an options object from the input/output files and keyword arguments.
-
-    Args:
-        input_file: Input file path or file object.
-        output_file: Output file path or file object.
-        parser: ArgumentParser object.
-        **kwargs: Keyword arguments.
-
-    Returns:
-        argparse.Namespace: A Namespace object containing the parsed arguments.
-
-    Raises:
-        TypeError: If the type of a keyword argument is not supported.
-    """
-    cmdline, deferred = _kwargs_to_cmdline(
-        defer_kwargs={'progress_bar', 'plugins', 'parser', 'input_file', 'output_file'},
-        **kwargs,
-    )
-    if isinstance(input_file, (BinaryIO, IOBase)):
-        cmdline.append('stream://input_file')
-    else:
-        cmdline.append(os.fspath(input_file))
-    if isinstance(output_file, (BinaryIO, IOBase)):
-        cmdline.append('stream://output_file')
-    else:
-        cmdline.append(os.fspath(output_file))
-
-    parser.enable_api_mode()
-    options = parser.parse_args(cmdline)
-    for keyword, val in deferred.items():
-        setattr(options, keyword, val)
-
-    if options.input_file == 'stream://input_file':
-        options.input_file = input_file
-    if options.output_file == 'stream://output_file':
-        options.output_file = output_file
-
-    return options
-
-
-def ocr(  # noqa: D417
-    input_file: PathOrIO,
-    output_file: PathOrIO,
-    *,
-    language: Iterable[str] | None = None,
-    image_dpi: int | None = None,
-    output_type: str | None = None,
-    sidecar: StrPath | None = None,
-    jobs: int | None = None,
-    use_threads: bool | None = None,
-    title: str | None = None,
-    author: str | None = None,
-    subject: str | None = None,
-    keywords: str | None = None,
-    rotate_pages: bool | None = None,
-    remove_background: bool | None = None,
-    deskew: bool | None = None,
-    clean: bool | None = None,
-    clean_final: bool | None = None,
-    unpaper_args: str | None = None,
-    oversample: int | None = None,
-    remove_vectors: bool | None = None,
-    force_ocr: bool | None = None,
-    skip_text: bool | None = None,
-    redo_ocr: bool | None = None,
-    skip_big: float | None = None,
-    optimize: int | None = None,
-    jpg_quality: int | None = None,
-    png_quality: int | None = None,
-    jbig2_lossy: bool | None = None,
-    jbig2_page_group_size: int | None = None,
-    jbig2_threshold: float | None = None,
-    pages: str | None = None,
-    max_image_mpixels: float | None = None,
-    tesseract_config: Iterable[str] | None = None,
-    tesseract_pagesegmode: int | None = None,
-    tesseract_oem: int | None = None,
-    tesseract_thresholding: int | None = None,
-    pdf_renderer: str | None = None,
-    tesseract_timeout: float | None = None,
-    tesseract_non_ocr_timeout: float | None = None,
-    tesseract_downsample_above: int | None = None,
-    tesseract_downsample_large_images: bool | None = None,
-    rotate_pages_threshold: float | None = None,
-    pdfa_image_compression: str | None = None,
-    color_conversion_strategy: str | None = None,
-    user_words: os.PathLike | None = None,
-    user_patterns: os.PathLike | None = None,
-    fast_web_view: float | None = None,
-    continue_on_soft_render_error: bool | None = None,
-    invalidate_digital_signatures: bool | None = None,
-    plugins: Iterable[StrPath] | None = None,
-    plugin_manager=None,
-    keep_temporary_files: bool | None = None,
-    progress_bar: bool | None = None,
-    **kwargs,
-):
-    """Run OCRmyPDF on one PDF or image.
-
-    For most arguments, see documentation for the equivalent command line parameter.
-
-    This API takes a threading lock, because OCRmyPDF uses global state in particular
-    for the plugin system. The jobs parameter will be used to create a pool of
-    worker threads or processes at different times, subject to change. A Python
-    process can only run one OCRmyPDF task at a time.
-
-    To run parallelize instances OCRmyPDF, use separate Python processes to scale
-    horizontally. Generally speaking you should set jobs=sqrt(cpu_count) and run
-    sqrt(cpu_count) processes as a starting point. If you have files with a high page
-    count, run fewer processes and more jobs per process. If you have a lot of short
-    files, run more processes and fewer jobs per process.
-
-    A few specific arguments are discussed here:
-
-    Args:
-        use_threads: Use worker threads instead of processes. This reduces
-            performance but may make debugging easier since it is easier to set
-            breakpoints.
-        input_file: If a :class:`pathlib.Path`, ``str`` or ``bytes``, this is
-            interpreted as file system path to the input file. If the object
-            appears to be a readable stream (with methods such as ``.read()``
-            and ``.seek()``), the object will be read in its entirety and saved to
-            a temporary file. If ``input_file`` is  ``"-"``, standard input will be
-            read.
-        output_file: If a :class:`pathlib.Path`, ``str`` or ``bytes``, this is
-            interpreted as file system path to the output file. If the object
-            appears to be a writable stream (with methods such as ``.write()`` and
-            ``.seek()``), the output will be written to this stream. If
-            ``output_file`` is ``"-"``, the output will be written to ``sys.stdout``
-            (provided that standard output does not seem to be a terminal device).
-            When a stream is used as output, whether via a writable object or
-            ``"-"``, some final validation steps are not performed (we do not read
-            back the stream after it is written).
-
-    Raises:
-        ocrmypdf.MissingDependencyError: If a required dependency program is missing or
-            was not found on PATH.
-        ocrmypdf.UnsupportedImageFormatError: If the input file type was an image that
-            could not be read, or some other file type that is not a PDF.
-        ocrmypdf.DpiError: If the input file is an image, but the resolution of the
-            image is not credible (allowing it to proceed would cause poor OCR).
-        ocrmypdf.OutputFileAccessError: If an attempt to write to the intended output
-            file failed.
-        ocrmypdf.PriorOcrFoundError: If the input PDF seems to have OCR or digital
-            text already, and settings did not tell us to proceed.
-        ocrmypdf.InputFileError: Any other problem with the input file.
-        ocrmypdf.SubprocessOutputError: Any error related to executing a subprocess.
-        ocrmypdf.EncryptedPdfError: If the input PDF is encrypted (password protected).
-            OCRmyPDF does not remove passwords.
-        ocrmypdf.TesseractConfigError: If Tesseract reported its configuration was not
-            valid.
-
-    Returns:
-        :class:`ocrmypdf.ExitCode`
-    """
-    if plugins and plugin_manager:
-        raise ValueError("plugins= and plugin_manager are mutually exclusive")
-
-    if not plugins:
-        plugins = []
-    elif isinstance(plugins, (str, Path)):
-        plugins = [plugins]
-    else:
-        plugins = list(plugins)
-
-    # No new variable names should be assigned until these two steps are run
-    create_options_kwargs = {
-        k: v
-        for k, v in locals().items()
-        if k not in {'input_file', 'output_file', 'kwargs'}
-    }
-    create_options_kwargs.update(kwargs)
-
-    parser = get_parser()
-    with _api_lock:
-        if not plugin_manager:
-            plugin_manager = get_plugin_manager(plugins)
-        plugin_manager.hook.add_options(parser=parser)  # pylint: disable=no-member
-
-        if 'verbose' in kwargs:
-            warn("ocrmypdf.ocr(verbose=) is ignored. Use ocrmypdf.configure_logging().")
-
-        options = create_options(
-            input_file=input_file,
-            output_file=output_file,
-            parser=parser,
-            **create_options_kwargs,
-        )
-        check_options(options, plugin_manager)
-        return run_pipeline(options=options, plugin_manager=plugin_manager)
-
-
-def _pdf_to_hocr(  # noqa: D417
-    input_pdf: Path,
-    output_folder: Path,
-    *,
-    language: Iterable[str] | None = None,
-    image_dpi: int | None = None,
-    jobs: int | None = None,
-    use_threads: bool | None = None,
-    title: str | None = None,
-    author: str | None = None,
-    subject: str | None = None,
-    keywords: str | None = None,
-    rotate_pages: bool | None = None,
-    remove_background: bool | None = None,
-    deskew: bool | None = None,
-    clean: bool | None = None,
-    clean_final: bool | None = None,
-    unpaper_args: str | None = None,
-    oversample: int | None = None,
-    remove_vectors: bool | None = None,
-    force_ocr: bool | None = None,
-    skip_text: bool | None = None,
-    redo_ocr: bool | None = None,
-    skip_big: float | None = None,
-    pages: str | None = None,
-    max_image_mpixels: float | None = None,
-    tesseract_config: Iterable[str] | None = None,
-    tesseract_pagesegmode: int | None = None,
-    tesseract_oem: int | None = None,
-    tesseract_thresholding: int | None = None,
-    tesseract_timeout: float | None = None,
-    tesseract_non_ocr_timeout: float | None = None,
-    tesseract_downsample_above: int | None = None,
-    tesseract_downsample_large_images: bool | None = None,
-    rotate_pages_threshold: float | None = None,
-    user_words: os.PathLike | None = None,
-    user_patterns: os.PathLike | None = None,
-    continue_on_soft_render_error: bool | None = None,
-    invalidate_digital_signatures: bool | None = None,
-    plugin_manager=None,
-    plugins: Sequence[StrPath] | None = None,
-    keep_temporary_files: bool | None = None,
-    **kwargs,
-):
-    """Partially run OCRmyPDF and produces an output folder containing hOCR files.
-
-    Given a PDF file, this function will run OCRmyPDF up to the point where
-    the PDF is rasterized to images, OCRed, and the hOCR files are produced,
-    all of which are saved to the output folder. This is useful for applications
-    that want to provide an interface for users to edit the text before
-    rendering the final PDF.
-
-    Use :func:`hocr_to_ocr_pdf` to produce the final PDF.
-
-    For arguments not explicitly documented here, see documentation for the
-    equivalent command line parameter.
-
-    This API is **experimental** and subject to change.
-
-    Args:
-        input_pdf: Input PDF file path.
-        output_folder: Output folder path.
-        **kwargs: Keyword arguments.
-    """
-    # No new variable names should be assigned until these two steps are run
-    create_options_kwargs = {
-        k: v
-        for k, v in locals().items()
-        if k not in {'input_pdf', 'output_folder', 'kwargs'}
-    }
-    create_options_kwargs.update(kwargs)
-
-    parser = get_parser()
-
-    with _api_lock:
-        if not plugin_manager:
-            plugin_manager = get_plugin_manager(plugins)
-        plugin_manager.hook.add_options(parser=parser)  # pylint: disable=no-member
-
-        cmdline, deferred = _kwargs_to_cmdline(
-            defer_kwargs={'input_pdf', 'output_folder', 'plugins'},
-            **create_options_kwargs,
-        )
-        cmdline.append(str(input_pdf))
-        cmdline.append(str(output_folder))
-        parser.enable_api_mode()
-        options = parser.parse_args(cmdline)
-        for keyword, val in deferred.items():
-            setattr(options, keyword, val)
-        delattr(options, 'output_file')
-        setattr(options, 'output_folder', output_folder)
-
-        return run_hocr_pipeline(options=options, plugin_manager=plugin_manager)
-
-
-def _hocr_to_ocr_pdf(  # noqa: D417
-    work_folder: Path,
-    output_file: Path,
-    *,
-    jobs: int | None = None,
-    use_threads: bool | None = None,
-    optimize: int | None = None,
-    jpg_quality: int | None = None,
-    png_quality: int | None = None,
-    jbig2_lossy: bool | None = None,
-    jbig2_page_group_size: int | None = None,
-    jbig2_threshold: float | None = None,
-    pdfa_image_compression: str | None = None,
-    color_conversion_strategy: str | None = None,
-    fast_web_view: float | None = None,
-    plugin_manager=None,
-    plugins: Sequence[StrPath] | None = None,
-    **kwargs,
-):
-    """Run OCRmyPDF on a work folder and produce an output PDF.
-
-    After running :func:`pdf_to_hocr`, this function will run OCRmyPDF on the work
-    folder to produce an output PDF. This function consolidates any changes made
-    to the hOCR files in the work folder and produces a final PDF.
-
-    For arguments not explicitly documented here, see documentation for the
-    equivalent command line parameter.
-
-    This API is **experimental** and subject to change.
-
-    Args:
-        work_folder: Work folder path, as generated by :func:`pdf_to_hocr`.
-        output_file: Output PDF file path.
-        **kwargs: Keyword arguments.
-    """
-    # No new variable names should be assigned until these two steps are run
-    create_options_kwargs = {
-        k: v
-        for k, v in locals().items()
-        if k not in {'work_folder', 'output_pdf', 'kwargs'}
-    }
-    create_options_kwargs.update(kwargs)
-
-    parser = get_parser()
-
-    with _api_lock:
-        if not plugin_manager:
-            plugin_manager = get_plugin_manager(plugins)
-        plugin_manager.hook.add_options(parser=parser)  # pylint: disable=no-member
-
-        cmdline, deferred = _kwargs_to_cmdline(
-            defer_kwargs={'work_folder', 'output_file', 'plugins'},
-            **create_options_kwargs,
-        )
-        cmdline.append(str(work_folder))
-        cmdline.append(str(output_file))
-        parser.enable_api_mode()
-        options = parser.parse_args(cmdline)
-        for keyword, val in deferred.items():
-            setattr(options, keyword, val)
-        delattr(options, 'input_file')
-        setattr(options, 'work_folder', work_folder)
-
-        return run_hocr_to_ocr_pdf_pipeline(
-            options=options, plugin_manager=plugin_manager
-        )
-
-
-__all__ = [
-    'PageNumberFilter',
-    'Verbosity',
-    'check_options',
-    'configure_logging',
-    'create_options',
-    'get_parser',
-    'get_plugin_manager',
-    'ocr',
-    'run_pipeline',
-    'run_pipeline_cli',
-]

src/ocrmypdf/builtin_plugins/__init__.py

@@ -1,6 +0,0 @@
-# SPDX-FileCopyrightText: 2022 James R. Barlow
-# SPDX-License-Identifier: MPL-2.0
-
-"""Plugins in this package are automatically loaded by ocrmypdf."""
-
-from __future__ import annotations

src/ocrmypdf/builtin_plugins/concurrency.py

@@ -1,185 +0,0 @@
-# SPDX-FileCopyrightText: 2022 James R. Barlow
-# SPDX-License-Identifier: MPL-2.0
-"""OCRmyPDF's multiprocessing/multithreading abstraction layer."""
-
-from __future__ import annotations
-
-import logging
-import logging.handlers
-import multiprocessing
-import os
-import queue
-import signal
-import sys
-import threading
-from collections.abc import Iterable
-from concurrent.futures import ProcessPoolExecutor, ThreadPoolExecutor, as_completed
-from contextlib import suppress
-from typing import Callable, Union
-
-from rich.console import Console as RichConsole
-
-from ocrmypdf import Executor, hookimpl
-from ocrmypdf._logging import RichLoggingHandler
-from ocrmypdf._progressbar import RichProgressBar
-from ocrmypdf.exceptions import InputFileError
-from ocrmypdf.helpers import remove_all_log_handlers
-
-FuturesExecutorClass = Union[type[ThreadPoolExecutor], type[ProcessPoolExecutor]]
-Queue = Union[multiprocessing.Queue, queue.Queue]
-UserInit = Callable[[], None]
-WorkerInit = Callable[[Queue, UserInit, int], None]
-
-
-def log_listener(q: Queue):
-    """Listen to the worker processes and forward the messages to logging.
-
-    For simplicity this is a thread rather than a process. Only one process
-    should actually write to sys.stderr or whatever we're using, so if this is
-    made into a process the main application needs to be directed to it.
-
-    See:
-    https://docs.python.org/3/howto/logging-cookbook.html#logging-to-a-single-file-from-multiple-processes
-    """
-    while True:
-        try:
-            record = q.get()
-            if record is None:
-                break
-            logger = logging.getLogger(record.name)
-            logger.handle(record)
-        except Exception:  # pylint: disable=broad-except
-            import traceback  # pylint: disable=import-outside-toplevel
-
-            print("Logging problem", file=sys.stderr)
-            traceback.print_exc(file=sys.stderr)
-
-
-def process_sigbus(*args):
-    """Handle SIGBUS signal at the worker level."""
-    raise InputFileError("A worker process lost access to an input file")
-
-
-def process_init(q: Queue, user_init: UserInit, loglevel) -> None:
-    """Initialize a process pool worker."""
-    # Ignore SIGINT (our parent process will kill us gracefully)
-    signal.signal(signal.SIGINT, signal.SIG_IGN)
-
-    # Install SIGBUS handler (so our parent process can abort somewhat gracefully)
-    with suppress(AttributeError):  # Windows and Cygwin do not have SIGBUS
-        # Windows and Cygwin do not have pthread_sigmask or SIGBUS
-        signal.signal(signal.SIGBUS, process_sigbus)
-
-    # Remove any log handlers inherited from the parent process
-    root = logging.getLogger()
-    remove_all_log_handlers(root)
-
-    # Set up our single log handler to forward messages to the parent
-    root.setLevel(loglevel)
-    root.addHandler(logging.handlers.QueueHandler(q))
-
-    user_init()
-    return
-
-
-def thread_init(q: Queue, user_init: UserInit, loglevel) -> None:
-    """Begin a thread pool worker."""
-    del q  # unused but required argument
-    del loglevel  # unused but required argument
-    # As a thread, block SIGBUS so the main thread deals with it...
-    with suppress(AttributeError):
-        signal.pthread_sigmask(signal.SIG_BLOCK, {signal.SIGBUS})
-
-    user_init()
-    return
-
-
-class StandardExecutor(Executor):
-    """Standard OCRmyPDF concurrent task executor."""
-
-    def _execute(
-        self,
-        *,
-        use_threads: bool,
-        max_workers: int,
-        progress_kwargs: dict,
-        worker_initializer: Callable,
-        task: Callable,
-        task_arguments: Iterable,
-        task_finished: Callable,
-    ):
-        if use_threads:
-            log_queue: Queue = queue.Queue(-1)
-            executor_class: FuturesExecutorClass = ThreadPoolExecutor
-            initializer: WorkerInit = thread_init
-        else:
-            log_queue = multiprocessing.Queue(-1)
-            executor_class = ProcessPoolExecutor
-            initializer = process_init
-
-        # Regardless of whether we use_threads for worker processes, the log_listener
-        # must be a thread. Make sure we create the listener after the worker pool,
-        # so that it does not get forked into the workers.
-        # If use_threads is False, we are currently guilty of creating a thread before
-        # forking on Linux, which is not recommended. However, we take a big
-        # performance hit in pdfinfo if we can't fork. Long term solution is to
-        # replace most of this with an asyncio implementation, and probably to
-        # migrate some of pdfinfo into C++ or Rust.
-        listener = threading.Thread(target=log_listener, args=(log_queue,))
-        listener.start()
-
-        with self.pbar_class(**progress_kwargs) as pbar, executor_class(
-            max_workers=max_workers,
-            initializer=initializer,
-            initargs=(log_queue, worker_initializer, logging.getLogger("").level),
-        ) as executor:
-            futures = [executor.submit(task, *args) for args in task_arguments]
-            try:
-                for future in as_completed(futures):
-                    result = future.result()
-                    task_finished(result, pbar)
-            except KeyboardInterrupt:
-                # Terminate pool so we exit instantly
-                executor.shutdown(wait=False, cancel_futures=True)
-                raise
-            except Exception:
-                if not os.environ.get("PYTEST_CURRENT_TEST", ""):
-                    # Normally we shutdown without waiting for other child workers
-                    # on error, because there is no point in waiting for them. Their
-                    # results will be discard. But if the condition above is True,
-                    # then we are running in pytest, and we want everything to exit
-                    # as cleanly as possible so that we get good error messages.
-                    executor.shutdown(wait=False, cancel_futures=True)
-                raise
-            finally:
-                # Terminate log listener
-                log_queue.put_nowait(None)
-
-        # When the above succeeds, wait for the listener thread to exit. (If
-        # an exception occurs, we don't try to join, in case it deadlocks.)
-        listener.join()
-
-
-@hookimpl
-def get_executor(progressbar_class):
-    """Return the default executor."""
-    return StandardExecutor(pbar_class=progressbar_class)
-
-
-RICH_CONSOLE = RichConsole(stderr=True)
-
-
-@hookimpl
-def get_progressbar_class():
-    """Return the default progress bar class."""
-
-    def partial_RichProgressBar(*args, **kwargs):
-        return RichProgressBar(*args, **kwargs, console=RICH_CONSOLE)
-
-    return partial_RichProgressBar
-
-
-@hookimpl
-def get_logging_console():
-    """Return the default logging console handler."""
-    return RichLoggingHandler(console=RICH_CONSOLE)

src/ocrmypdf/builtin_plugins/default_filters.py

@@ -1,14 +0,0 @@
-# SPDX-FileCopyrightText: 2022 James R. Barlow
-# SPDX-License-Identifier: MPL-2.0
-"""OCRmyPDF automatically installs these filters as plugins."""
-
-from __future__ import annotations
-
-from ocrmypdf import hookimpl
-
-
-@hookimpl
-def filter_pdf_page(
-    page, image_filename, output_pdf
-):  # pylint: disable=unused-argument
-    return output_pdf