Update release notes and files

This reverts commit 162a47f98e.

.docker/Dockerfile

@@ -1,7 +1,7 @@
-# OCRmyPDF
-#
+# SPDX-FileCopyrightText: 2022 James R. Barlow
+# SPDX-License-Identifier: MPL-2.0
 
-FROM ubuntu:21.04 as base
+FROM ubuntu:22.04 as base
 
 ENV LANG=C.UTF-8
 ENV TZ=UTC
@@ -25,7 +25,9 @@ RUN apt-get update && apt-get install -y --no-install-recommends \
   libffi-dev \
   ca-certificates \
   curl \
-  git
+  git \
+  libcairo2-dev \
+  pkg-config
 
 # Get the latest pip (Ubuntu version doesn't support manylinux2010)
 RUN \
@@ -50,8 +52,15 @@ 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 \
@@ -74,7 +83,7 @@ COPY --from=builder /app/misc/webservice.py /app/
 COPY --from=builder /app/misc/watcher.py /app/
 
 # Copy minimal project files to get the test suite.
-COPY --from=builder /app/setup.cfg /app/setup.py /app/README.md /app/
+COPY --from=builder /app/pyproject.toml /app/README.md /app/
 COPY --from=builder /app/tests /app/tests
 
 ENTRYPOINT ["/usr/local/bin/ocrmypdf"]

.dockerignore

@@ -1,3 +1,6 @@
+# SPDX-FileCopyrightText: 2022 James R. Barlow
+# SPDX-License-Identifier: MPL-2.0
+
 # dotfiles
 .*
 !.coveragerc

.git_archival.txt

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

.gitattributes

@@ -1,3 +1,6 @@
+# SPDX-FileCopyrightText: 2022 James R. Barlow
+# SPDX-License-Identifier: MPL-2.0
+
 # Always use Unix convention for new lines
 * text eol=lf
 

.github/FUNDING.yml

@@ -1,3 +1,6 @@
+# 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]

.github/ISSUE_TEMPLATE/1-bug-report-general.yml

@@ -0,0 +1,51 @@
+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/1-general-issues.md

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

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

@@ -1,40 +0,0 @@
----
-name: Problem with a specific input file
-about: Something went wrong while trying to OCR a specific file
-title: ''
-labels: ''
-assignees: ''
-
----
-
-**Describe the bug**
-A clear and concise description of what the bug is.
-
-**To Reproduce**
-What command line or API call were you trying to run?
-
-```bash
-ocrmypdf  ...arguments... input.pdf output.pdf
-```
-
-Run with verbosity or higher `-v1` to see more detailed logging. This information may be helpful.
-
-**Example file**
-If your issue is a problem that affects only certain files, and we will require an input file (PDF or image) that demonstrates your issue.
-
-Please provide an input file with no personal or confidential information. At your option you may [GPG-encrypt the file](https://github.com/jbarlow83/OCRmyPDF/wiki) for OCRmyPDF's author only.
-
-Links to files hosted elsewhere are perfectly acceptable. You could also look in ``tests/resources`` and see if any of those files reproduce your issue.
-
-*(Issues without example files usually cannot be resolved. It's like reporting an issue against a web browser without providing a URL.)*
-
-**Expected behavior**
-A clear and concise description of what you expected to happen.
-
-**Screenshots**
-If applicable, add screenshots to help explain your problem.
-
-**System**
- - OS: [e.g. Linux, Windows, macOS]
- - OCRmyPDF Version: ``ocrmypdf --version``
- - How did you install ocrmypdf? Did you use a system package manager, `pip`, or a Docker image?

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

@@ -0,0 +1,62 @@
+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

@@ -0,0 +1,12 @@
+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/ISSUE_TEMPLATE/3-feature_request.md

@@ -1,27 +0,0 @@
----
-name: Feature request
-about: Suggest an idea for this project
-title: ''
-labels: ''
-assignees: ''
-
----
-
-**Is your feature request related to a problem? Please describe.**
-A clear and concise description of what the problem is. Ex. I'm always frustrated when [...]
-
-**Describe the solution you'd like**
-A clear and concise description of what you want to happen.
-
-**Describe alternatives you've considered**
-A clear and concise description of any alternative solutions or features you've considered. Please include the versions of OCRmyPDF and other supporting programs (Tesseract OCR, Ghostscript) - maybe an alternative already exists in a newer version.
-
-**Example file**
-If your issue concerns how OCRmyPDF processes certain files, and please provide an example file that helps illustrate how OCRmyPDF's output could be improve.
-
-Please provide an input file with no personal or confidential information. At your option you may [GPG-encrypt the file](https://github.com/jbarlow83/OCRmyPDF/wiki) for OCRmyPDF's author only.
-
-Links to files hosted elsewhere are perfectly acceptable. You could also look in ``tests/resources`` and see if any of those files reproduce your issue.
-
-**Additional context**
-Add any other context or screenshots about the feature request here.

.github/dependabot.yml

@@ -0,0 +1,14 @@
+# 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

@@ -1,9 +1,11 @@
+# SPDX-FileCopyrightText: 2022 James R. Barlow
+# SPDX-License-Identifier: MPL-2.0
 name: Test and deploy
 
 on:
   push:
     branches:
-      - master
+      - main
       - ci
       - release/*
       - feature/*
@@ -20,18 +22,16 @@ jobs:
     strategy:
       matrix:
         include:
-          - os: ubuntu-18.04
-            python: 3.7
-          - os: ubuntu-20.04
-            python: 3.8
-          - os: ubuntu-20.04
-            python: 3.9
-          - os: ubuntu-latest
-            python: 3.9
-          - os: ubuntu-latest
-            python: "pypy-3.7"
-          - os: ubuntu-latest
-            python: 3.9
+          - os: ubuntu-22.04
+            python: "3.9"
+          - os: ubuntu-22.04
+            python: "3.10"
+          - os: ubuntu-22.04
+            python: "3.11"
+          #- os: ubuntu-latest
+          #  python: "pypy3.9"
+          - os: ubuntu-22.04
+            python: "3.9"
             tesseract5: true
 
     env:
@@ -39,11 +39,11 @@ jobs:
       PYTHON: ${{ matrix.python }}
 
     steps:
-      - uses: actions/checkout@v2
+      - uses: actions/checkout@v4
         with:
           fetch-depth: "0" # 0=all, needed for setuptools-scm to resolve version tags
 
-      - uses: actions/setup-python@v2
+      - uses: actions/setup-python@v4
         name: Install Python
         with:
           python-version: ${{ matrix.python }}
@@ -60,6 +60,7 @@ jobs:
             curl \
             ghostscript \
             img2pdf \
+            libexempi8 \
             libffi-dev \
             libsm6 libxext6 libxrender-dev \
             pngquant \
@@ -71,18 +72,6 @@ jobs:
             unpaper \
             zlib1g
 
-      - name: Install Ubuntu 18.04 packages
-        if: matrix.os == 'ubuntu-18.04'
-        run: |
-          sudo apt-get install -y --no-install-recommends \
-            libexempi3
-
-      - name: Install Ubuntu 20.04 packages
-        if: matrix.os == 'ubuntu-20.04' || matrix.os == 'ubuntu-latest'
-        run: |
-          sudo apt-get install -y --no-install-recommends \
-            libexempi8
-
       - name: Install Ubuntu packages for PyPy
         if: startsWith(matrix.python, 'pypy')
         run: |
@@ -94,7 +83,7 @@ jobs:
       - name: Install Python packages
         run: |
           python -m pip install --upgrade pip wheel
-          python -m pip install .[test]
+          python -m pip install --prefer-binary .[test]
 
       - name: Report versions
         run: |
@@ -109,7 +98,7 @@ jobs:
           python -m pytest --cov-report xml --cov=ocrmypdf --cov=tests/ -n0 tests/
 
       - name: Upload coverage to Codecov
-        uses: codecov/codecov-action@v1
+        uses: codecov/codecov-action@v3
         with:
           files: ./coverage.xml
           env_vars: OS,PYTHON
@@ -120,23 +109,19 @@ jobs:
     strategy:
       matrix:
         os: [macos-latest]
-        python: ["3.9"]
+        python: ["3.10", "3.11"]
 
     env:
       OS: ${{ matrix.os }}
       PYTHON: ${{ matrix.python }}
 
     steps:
-      - uses: actions/checkout@v2
+      - uses: actions/checkout@v4
         with:
           fetch-depth: "0" # 0=all, needed for setuptools-scm to resolve version tags
 
-      - uses: actions/setup-python@v2
-        name: Install Python
-        with:
-          python-version: ${{ matrix.python }}
-
       - name: Install Homebrew deps
+        continue-on-error: true
         run: |
           brew update
           brew install \
@@ -147,10 +132,15 @@ jobs:
             pngquant \
             tesseract
 
+      - uses: actions/setup-python@v4
+        name: Install Python
+        with:
+          python-version: ${{ matrix.python }}
+
       - name: Install Python packages
         run: |
           python -m pip install --upgrade pip wheel
-          python -m pip install .[test]
+          python -m pip install --prefer-binary .[test]
 
       - name: Report versions
         run: |
@@ -164,7 +154,7 @@ jobs:
           python -m pytest --cov-report xml --cov=ocrmypdf --cov=tests/ -n0 tests/
 
       - name: Upload coverage to Codecov
-        uses: codecov/codecov-action@v1
+        uses: codecov/codecov-action@v3
         with:
           files: ./coverage.xml
           env_vars: OS,PYTHON
@@ -175,18 +165,18 @@ jobs:
     strategy:
       matrix:
         os: [windows-latest]
-        python: ["3.9"]
+        python: ["3.10", "3.11"]
 
     env:
       OS: ${{ matrix.os }}
       PYTHON: ${{ matrix.python }}
 
     steps:
-      - uses: actions/checkout@v2
+      - uses: actions/checkout@v4
         with:
           fetch-depth: "0" # 0=all, needed for setuptools-scm to resolve version tags
 
-      - uses: actions/setup-python@v2
+      - uses: actions/setup-python@v4
         name: Install Python
         with:
           python-version: ${{ matrix.python }}
@@ -194,19 +184,19 @@ jobs:
       - name: Install system packages
         run: |
           choco install --yes --no-progress --pre tesseract
-          choco install --yes --no-progress --ignore-checksums ghostscript pngquant
+          choco install --yes --no-progress --ignore-checksums ghostscript
 
       - name: Install Python packages
         run: |
           python -m pip install --upgrade pip wheel
-          python -m pip install .[test]
+          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@v1
+        uses: codecov/codecov-action@v3
         with:
           files: ./coverage.xml
           env_vars: OS,PYTHON
@@ -215,22 +205,21 @@ jobs:
     name: Build sdist and wheels
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v2
+      - uses: actions/checkout@v4
         with:
           fetch-depth: "0" # 0=all, needed for setuptools-scm to resolve version tags
 
-      - uses: actions/setup-python@v2
+      - uses: actions/setup-python@v4
         name: Install Python
         with:
-          python-version: "3.7"
+          python-version: "3.9"
 
       - name: Make wheels and sdist
         run: |
-          python -m pip install --upgrade pip wheel
-          python setup.py sdist
-          python setup.py bdist_wheel
+          python -m pip install --upgrade pip wheel build
+          python -m build --sdist --wheel
 
-      - uses: actions/upload-artifact@v2
+      - uses: actions/upload-artifact@v3
         with:
           path: |
             ./dist/*.whl
@@ -240,18 +229,44 @@ jobs:
     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@v2
+      - uses: actions/download-artifact@v3
         with:
           name: artifact
           path: dist
 
-      - uses: pypa/gh-action-pypi-publish@master
+      - 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:
-          user: __token__
-          password: ${{ secrets.TOKEN_PYPI }}
-          # repository_url: https://test.pypi.org/legacy/
+          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:
     name: Build Docker images
@@ -262,9 +277,9 @@ jobs:
       - name: Set image tag to release or branch
         run: echo "DOCKER_IMAGE_TAG=${GITHUB_REF##*/}" >> $GITHUB_ENV
 
-      - name: If master, set to latest
+      - name: If main, set to latest
         run: echo 'DOCKER_IMAGE_TAG=latest' >> $GITHUB_ENV
-        if: env.DOCKER_IMAGE_TAG == 'master'
+        if: env.DOCKER_IMAGE_TAG == 'main'
 
       - name: Set Docker Hub repository to username
         run: echo "DOCKER_REPOSITORY=jbarlow83" >> $GITHUB_ENV
@@ -272,22 +287,22 @@ jobs:
       - name: Set image name
         run: echo "DOCKER_IMAGE_NAME=ocrmypdf" >> $GITHUB_ENV
 
-      - uses: actions/checkout@v2
+      - 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@v1
+        uses: docker/login-action@v3
         with:
           username: jbarlow83
           password: ${{ secrets.DOCKERHUB_TOKEN }}
 
       - name: Set up QEMU
-        uses: docker/setup-qemu-action@v1
+        uses: docker/setup-qemu-action@v3
 
       - name: Set up Docker Buildx
         id: buildx
-        uses: docker/setup-buildx-action@v1
+        uses: docker/setup-buildx-action@v3
 
       - name: Print image tag
         run: echo "Building image ${DOCKER_REPOSITORY}/${DOCKER_IMAGE_NAME}:${DOCKER_IMAGE_TAG}"

.gitignore

@@ -1,14 +1,15 @@
+# SPDX-FileCopyrightText: 2022 James R. Barlow
+# SPDX-License-Identifier: CC-BY-SA-4.0
+
 # dotfiles
-.*
-!.coveragerc
-!.dockerignore
-!.git_archival.txt
-!.gitattributes
-!.gitignore
-!.pre-commit-config.yaml
-!.readthedocs.yaml
-!.github/
-!.docker/
+.coverage
+.venv*/
+.tox/
+.vscode/
+.hypothesis/
+.ipynb_checkpoints/
+.mypy_cache/
+.pytest_cache/
 
 # Dev scratch
 *.ipynb
@@ -26,6 +27,7 @@ venv*/
 *.traineddata
 /private
 /coverage.xml
+/issuepdf
 
 # Package building
 *.egg-info/
@@ -42,4 +44,3 @@ docs/_build/
 docs/_static/
 docs/_templates/
 docs/Makefile
-ocrmypdf/lib/_*.py

.pre-commit-config.yaml

@@ -1,33 +1,28 @@
+# SPDX-FileCopyrightText: 2022 James R. Barlow
+# SPDX-License-Identifier: MPL-2.0
+
 repos:
   - repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v4.0.1
+    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/pycqa/isort
-    rev: 5.9.3
+  - repo: https://github.com/charliermarsh/ruff-pre-commit
+    rev: "v0.0.261"
     hooks:
-      - id: isort
-        args: ["--profile", "black"]
+      - id: ruff
+        files: "src/.*\\.pyi?$"
+        args: [--fix, --exit-non-zero-on-fix]
   - repo: https://github.com/psf/black
-    rev: 21.9b0
+    rev: 23.3.0
     hooks:
       - id: black
         language_version: python
-  - repo: https://github.com/asottile/setup-cfg-fmt
-    rev: v1.19.0
-    hooks:
-      - id: setup-cfg-fmt
-  - repo: https://github.com/asottile/pyupgrade
-    rev: v2.29.0
-    hooks:
-      - id: pyupgrade
-        args: ["--py37-plus"]
   - repo: https://github.com/pre-commit/mirrors-mypy
-    rev: v0.910-1
+    rev: v1.2.0
     hooks:
       - id: mypy
         additional_dependencies:

.readthedocs.yaml

@@ -1,3 +1,6 @@
+# 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
 
@@ -13,8 +16,12 @@ formats:
   - pdf
 
 # Optionally set the version of Python and requirements required to build your docs
+build:
+  os: ubuntu-22.04
+  tools:
+    python: "3.9"
+
 python:
-  version: "3.7"
   install:
     - method: pip
       path: .

.reuse/dep5

@@ -0,0 +1,133 @@
+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
+ setup.cfg
+Copyright: (C) 2022 James R. Barlow
+License: MPL-2.0
+
+Files:
+ .github/ISSUE_TEMPLATE/*.md
+ docs/images/macos-workflow.png
+Copyright: (C) 2022 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/missing_docinfo.pdf
+ tests/resources/negzero.pdf
+ tests/resources/no_contents.pdf
+ tests/resources/toc.pdf
+ tests/resources/trivial.pdf
+ tests/resources/truetype_font_nomapping.pdf
+ tests/resources/type3_font_nomapping.pdf
+ misc/screencast/*
+Copyright: (C) 2022 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/congress.jpg
+ 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/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: 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

LICENSES/AGPL-3.0-or-later.txt

@@ -0,0 +1,235 @@
+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

@@ -0,0 +1,81 @@
+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

@@ -0,0 +1,85 @@
+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

@@ -0,0 +1,85 @@
+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

@@ -0,0 +1,99 @@
+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

@@ -0,0 +1,170 @@
+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

@@ -0,0 +1,130 @@
+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

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

@@ -0,0 +1,373 @@
+Mozilla Public License Version 2.0
+==================================
+
+1. Definitions
+--------------
+
+1.1. "Contributor"
+    means each individual or legal entity that creates, contributes to
+    the creation of, or owns Covered Software.
+
+1.2. "Contributor Version"
+    means the combination of the Contributions of others (if any) used
+    by a Contributor and that particular Contributor's Contribution.
+
+1.3. "Contribution"
+    means Covered Software of a particular Contributor.
+
+1.4. "Covered Software"
+    means Source Code Form to which the initial Contributor has attached
+    the notice in Exhibit A, the Executable Form of such Source Code
+    Form, and Modifications of such Source Code Form, in each case
+    including portions thereof.
+
+1.5. "Incompatible With Secondary Licenses"
+    means
+
+    (a) that the initial Contributor has attached the notice described
+        in Exhibit B to the Covered Software; or
+
+    (b) that the Covered Software was made available under the terms of
+        version 1.1 or earlier of the License, but not also under the
+        terms of a Secondary License.
+
+1.6. "Executable Form"
+    means any form of the work other than Source Code Form.
+
+1.7. "Larger Work"
+    means a work that combines Covered Software with other material, in 
+    a separate file or files, that is not Covered Software.
+
+1.8. "License"
+    means this document.
+
+1.9. "Licensable"
+    means having the right to grant, to the maximum extent possible,
+    whether at the time of the initial grant or subsequently, any and
+    all of the rights conveyed by this License.
+
+1.10. "Modifications"
+    means any of the following:
+
+    (a) any file in Source Code Form that results from an addition to,
+        deletion from, or modification of the contents of Covered
+        Software; or
+
+    (b) any new file in Source Code Form that contains any Covered
+        Software.
+
+1.11. "Patent Claims" of a Contributor
+    means any patent claim(s), including without limitation, method,
+    process, and apparatus claims, in any patent Licensable by such
+    Contributor that would be infringed, but for the grant of the
+    License, by the making, using, selling, offering for sale, having
+    made, import, or transfer of either its Contributions or its
+    Contributor Version.
+
+1.12. "Secondary License"
+    means either the GNU General Public License, Version 2.0, the GNU
+    Lesser General Public License, Version 2.1, the GNU Affero General
+    Public License, Version 3.0, or any later versions of those
+    licenses.
+
+1.13. "Source Code Form"
+    means the form of the work preferred for making modifications.
+
+1.14. "You" (or "Your")
+    means an individual or a legal entity exercising rights under this
+    License. For legal entities, "You" includes any entity that
+    controls, is controlled by, or is under common control with You. For
+    purposes of this definition, "control" means (a) the power, direct
+    or indirect, to cause the direction or management of such entity,
+    whether by contract or otherwise, or (b) ownership of more than
+    fifty percent (50%) of the outstanding shares or beneficial
+    ownership of such entity.
+
+2. License Grants and Conditions
+--------------------------------
+
+2.1. Grants
+
+Each Contributor hereby grants You a world-wide, royalty-free,
+non-exclusive license:
+
+(a) under intellectual property rights (other than patent or trademark)
+    Licensable by such Contributor to use, reproduce, make available,
+    modify, display, perform, distribute, and otherwise exploit its
+    Contributions, either on an unmodified basis, with Modifications, or
+    as part of a Larger Work; and
+
+(b) under Patent Claims of such Contributor to make, use, sell, offer
+    for sale, have made, import, and otherwise transfer either its
+    Contributions or its Contributor Version.
+
+2.2. Effective Date
+
+The licenses granted in Section 2.1 with respect to any Contribution
+become effective for each Contribution on the date the Contributor first
+distributes such Contribution.
+
+2.3. Limitations on Grant Scope
+
+The licenses granted in this Section 2 are the only rights granted under
+this License. No additional rights or licenses will be implied from the
+distribution or licensing of Covered Software under this License.
+Notwithstanding Section 2.1(b) above, no patent license is granted by a
+Contributor:
+
+(a) for any code that a Contributor has removed from Covered Software;
+    or
+
+(b) for infringements caused by: (i) Your and any other third party's
+    modifications of Covered Software, or (ii) the combination of its
+    Contributions with other software (except as part of its Contributor
+    Version); or
+
+(c) under Patent Claims infringed by Covered Software in the absence of
+    its Contributions.
+
+This License does not grant any rights in the trademarks, service marks,
+or logos of any Contributor (except as may be necessary to comply with
+the notice requirements in Section 3.4).
+
+2.4. Subsequent Licenses
+
+No Contributor makes additional grants as a result of Your choice to
+distribute the Covered Software under a subsequent version of this
+License (see Section 10.2) or under the terms of a Secondary License (if
+permitted under the terms of Section 3.3).
+
+2.5. Representation
+
+Each Contributor represents that the Contributor believes its
+Contributions are its original creation(s) or it has sufficient rights
+to grant the rights to its Contributions conveyed by this License.
+
+2.6. Fair Use
+
+This License is not intended to limit any rights You have under
+applicable copyright doctrines of fair use, fair dealing, or other
+equivalents.
+
+2.7. Conditions
+
+Sections 3.1, 3.2, 3.3, and 3.4 are conditions of the licenses granted
+in Section 2.1.
+
+3. Responsibilities
+-------------------
+
+3.1. Distribution of Source Form
+
+All distribution of Covered Software in Source Code Form, including any
+Modifications that You create or to which You contribute, must be under
+the terms of this License. You must inform recipients that the Source
+Code Form of the Covered Software is governed by the terms of this
+License, and how they can obtain a copy of this License. You may not
+attempt to alter or restrict the recipients' rights in the Source Code
+Form.
+
+3.2. Distribution of Executable Form
+
+If You distribute Covered Software in Executable Form then:
+
+(a) such Covered Software must also be made available in Source Code
+    Form, as described in Section 3.1, and You must inform recipients of
+    the Executable Form how they can obtain a copy of such Source Code
+    Form by reasonable means in a timely manner, at a charge no more
+    than the cost of distribution to the recipient; and
+
+(b) You may distribute such Executable Form under the terms of this
+    License, or sublicense it under different terms, provided that the
+    license for the Executable Form does not attempt to limit or alter
+    the recipients' rights in the Source Code Form under this License.
+
+3.3. Distribution of a Larger Work
+
+You may create and distribute a Larger Work under terms of Your choice,
+provided that You also comply with the requirements of this License for
+the Covered Software. If the Larger Work is a combination of Covered
+Software with a work governed by one or more Secondary Licenses, and the
+Covered Software is not Incompatible With Secondary Licenses, this
+License permits You to additionally distribute such Covered Software
+under the terms of such Secondary License(s), so that the recipient of
+the Larger Work may, at their option, further distribute the Covered
+Software under the terms of either this License or such Secondary
+License(s).
+
+3.4. Notices
+
+You may not remove or alter the substance of any license notices
+(including copyright notices, patent notices, disclaimers of warranty,
+or limitations of liability) contained within the Source Code Form of
+the Covered Software, except that You may alter any license notices to
+the extent required to remedy known factual inaccuracies.
+
+3.5. Application of Additional Terms
+
+You may choose to offer, and to charge a fee for, warranty, support,
+indemnity or liability obligations to one or more recipients of Covered
+Software. However, You may do so only on Your own behalf, and not on
+behalf of any Contributor. You must make it absolutely clear that any
+such warranty, support, indemnity, or liability obligation is offered by
+You alone, and You hereby agree to indemnify every Contributor for any
+liability incurred by such Contributor as a result of warranty, support,
+indemnity or liability terms You offer. You may include additional
+disclaimers of warranty and limitations of liability specific to any
+jurisdiction.
+
+4. Inability to Comply Due to Statute or Regulation
+---------------------------------------------------
+
+If it is impossible for You to comply with any of the terms of this
+License with respect to some or all of the Covered Software due to
+statute, judicial order, or regulation then You must: (a) comply with
+the terms of this License to the maximum extent possible; and (b)
+describe the limitations and the code they affect. Such description must
+be placed in a text file included with all distributions of the Covered
+Software under this License. Except to the extent prohibited by statute
+or regulation, such description must be sufficiently detailed for a
+recipient of ordinary skill to be able to understand it.
+
+5. Termination
+--------------
+
+5.1. The rights granted under this License will terminate automatically
+if You fail to comply with any of its terms. However, if You become
+compliant, then the rights granted under this License from a particular
+Contributor are reinstated (a) provisionally, unless and until such
+Contributor explicitly and finally terminates Your grants, and (b) on an
+ongoing basis, if such Contributor fails to notify You of the
+non-compliance by some reasonable means prior to 60 days after You have
+come back into compliance. Moreover, Your grants from a particular
+Contributor are reinstated on an ongoing basis if such Contributor
+notifies You of the non-compliance by some reasonable means, this is the
+first time You have received notice of non-compliance with this License
+from such Contributor, and You become compliant prior to 30 days after
+Your receipt of the notice.
+
+5.2. If You initiate litigation against any entity by asserting a patent
+infringement claim (excluding declaratory judgment actions,
+counter-claims, and cross-claims) alleging that a Contributor Version
+directly or indirectly infringes any patent, then the rights granted to
+You by any and all Contributors for the Covered Software under Section
+2.1 of this License shall terminate.
+
+5.3. In the event of termination under Sections 5.1 or 5.2 above, all
+end user license agreements (excluding distributors and resellers) which
+have been validly granted by You or Your distributors under this License
+prior to termination shall survive termination.
+
+************************************************************************
+*                                                                      *
+*  6. Disclaimer of Warranty                                           *
+*  -------------------------                                           *
+*                                                                      *
+*  Covered Software is provided under this License on an "as is"       *
+*  basis, without warranty of any kind, either expressed, implied, or  *
+*  statutory, including, without limitation, warranties that the       *
+*  Covered Software is free of defects, merchantable, fit for a        *
+*  particular purpose or non-infringing. The entire risk as to the     *
+*  quality and performance of the Covered Software is with You.        *
+*  Should any Covered Software prove defective in any respect, You     *
+*  (not any Contributor) assume the cost of any necessary servicing,   *
+*  repair, or correction. This disclaimer of warranty constitutes an   *
+*  essential part of this License. No use of any Covered Software is   *
+*  authorized under this License except under this disclaimer.         *
+*                                                                      *
+************************************************************************
+
+************************************************************************
+*                                                                      *
+*  7. Limitation of Liability                                          *
+*  --------------------------                                          *
+*                                                                      *
+*  Under no circumstances and under no legal theory, whether tort      *
+*  (including negligence), contract, or otherwise, shall any           *
+*  Contributor, or anyone who distributes Covered Software as          *
+*  permitted above, be liable to You for any direct, indirect,         *
+*  special, incidental, or consequential damages of any character      *
+*  including, without limitation, damages for lost profits, loss of    *
+*  goodwill, work stoppage, computer failure or malfunction, or any    *
+*  and all other commercial damages or losses, even if such party      *
+*  shall have been informed of the possibility of such damages. This   *
+*  limitation of liability shall not apply to liability for death or   *
+*  personal injury resulting from such party's negligence to the       *
+*  extent applicable law prohibits such limitation. Some               *
+*  jurisdictions do not allow the exclusion or limitation of           *
+*  incidental or consequential damages, so this exclusion and          *
+*  limitation may not apply to You.                                    *
+*                                                                      *
+************************************************************************
+
+8. Litigation
+-------------
+
+Any litigation relating to this License may be brought only in the
+courts of a jurisdiction where the defendant maintains its principal
+place of business and such litigation shall be governed by laws of that
+jurisdiction, without reference to its conflict-of-law provisions.
+Nothing in this Section shall prevent a party's ability to bring
+cross-claims or counter-claims.
+
+9. Miscellaneous
+----------------
+
+This License represents the complete agreement concerning the subject
+matter hereof. If any provision of this License is held to be
+unenforceable, such provision shall be reformed only to the extent
+necessary to make it enforceable. Any law or regulation which provides
+that the language of a contract shall be construed against the drafter
+shall not be used to construe this License against a Contributor.
+
+10. Versions of the License
+---------------------------
+
+10.1. New Versions
+
+Mozilla Foundation is the license steward. Except as provided in Section
+10.3, no one other than the license steward has the right to modify or
+publish new versions of this License. Each version will be given a
+distinguishing version number.
+
+10.2. Effect of New Versions
+
+You may distribute the Covered Software under the terms of the version
+of the License under which You originally received the Covered Software,
+or under the terms of any subsequent version published by the license
+steward.
+
+10.3. Modified Versions
+
+If you create software not governed by this License, and you want to
+create a new license for such software, you may create and use a
+modified version of this License if you rename the license and remove
+any references to the name of the license steward (except to note that
+such modified license differs from this License).
+
+10.4. Distributing Source Code Form that is Incompatible With Secondary
+Licenses
+
+If You choose to distribute Source Code Form that is Incompatible With
+Secondary Licenses under the terms of this version of the License, the
+notice described in Exhibit B of this License must be attached.
+
+Exhibit A - Source Code Form License Notice
+-------------------------------------------
+
+  This Source Code Form is subject to the terms of the Mozilla Public
+  License, v. 2.0. If a copy of the MPL was not distributed with this
+  file, You can obtain one at 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

@@ -0,0 +1,11 @@
+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

@@ -1,9 +1,11 @@
+<!-- SPDX-FileCopyrightText: 2014 Julien Pfefferkorn -->
+<!-- SPDX-FileCopyrightText: 2015 James R. Barlow -->
+<!-- SPDX-License-Identifier: CC-BY-SA-4.0 -->
+
 <img src="docs/images/logo.svg" width="240" alt="OCRmyPDF">
 
-[![Build Status](https://github.com/jbarlow83/OCRmyPDF/actions/workflows/build.yml/badge.svg)](https://github.com/jbarlow83/OCRmyPDF/actions/workflows/build.yml) [![PyPI version][pypi]](https://pypi.org/project/ocrmypdf/) ![Homebrew version][homebrew] ![ReadTheDocs][docs] ![Python versions][pyversions]
+[![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]
 
-[azure]: https://dev.azure.com/jim0585/ocrmypdf/_apis/build/status/jbarlow83.OCRmyPDF?branchName=master
-[travis]: https://travis-ci.org/jbarlow83/OCRmyPDF.svg?branch=master "Travis build status"
 [pypi]: https://img.shields.io/pypi/v/ocrmypdf.svg "PyPI version"
 [homebrew]: https://img.shields.io/homebrew/v/ocrmypdf.svg "Homebrew version"
 [docs]: https://readthedocs.org/projects/ocrmypdf/badge/?version=latest "RTD"
@@ -36,9 +38,12 @@ ocrmypdf                      # it's a scriptable command line program
 - 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
@@ -64,10 +69,12 @@ Linux, Windows, macOS and FreeBSD are supported. Docker images are also availabl
 | Debian, Ubuntu                | ``apt install ocrmypdf``      |
 | Windows Subsystem for Linux   | ``apt install ocrmypdf``      |
 | Fedora                        | ``dnf install ocrmypdf``      |
-| macOS                         | ``brew install ocrmypdf``     |
+| macOS (Homebrew)              | ``brew install ocrmypdf``     |
+| macOS (nix)                   | ``nix-env -i ocrmypdf``       |
 | LinuxBrew                     | ``brew install ocrmypdf``     |
-| FreeBSD                       | ``pkg install py37-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.
 
@@ -91,10 +98,7 @@ brew install tesseract-lang
 
 You can then pass the `-l LANG` argument to OCRmyPDF to give a hint as to what languages it should search for. Multiple languages can be requested.
 
-OCRmyPDF supports Tesseract 4.0 and the beta versions of Tesseract 5.0. It will
-automatically use whichever version it finds first on the `PATH` environment
-variable. On Windows, if `PATH` does not provide a Tesseract binary, we use
-the highest version number that is installed according to the Windows Registry.
+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
 
@@ -106,11 +110,11 @@ 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/jbarlow83/OCRmyPDF/issues) page, and follow the issue template for quick response.
+Please report issues on our [GitHub issues](https://github.com/ocrmypdf/OCRmyPDF/issues) page, and follow the issue template for quick response.
 
 ## Requirements
 
-In addition to the required Python version (3.7+), OCRmyPDF requires external program installations of Ghostscript and Tesseract OCR. OCRmyPDF is pure Python, and runs on pretty much everything: Linux, macOS, Windows and FreeBSD.
+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
 
@@ -121,6 +125,7 @@ In addition to the required Python version (3.7+), OCRmyPDF requires external pr
 - [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
 
@@ -128,15 +133,9 @@ OCRmyPDF would not be the software that it is today without companies and users
 
 ## 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.
+The OCRmyPDF software is licensed under the Mozilla Public License 2.0 (MPL-2.0). This license permits integration of OCRmyPDF with other code, included commercial and closed source, but asks you to publish source-level modifications you make to OCRmyPDF.
 
-Some components of OCRmyPDF have other licenses, as noted in those files and the
-``debian/copyright`` file. Most files in ``misc/`` use the MIT license, and the
-documentation and test files are generally licensed under Creative Commons
-ShareAlike 4.0 (CC-BY-SA 4.0).
+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
 

docs/advanced.rst

@@ -1,3 +1,6 @@
+.. SPDX-FileCopyrightText: 2022 James R. Barlow
+.. SPDX-License-Identifier: CC-BY-SA-4.0
+
 =================
 Advanced features
 =================
@@ -7,7 +10,7 @@ Control of unpaper
 
 OCRmyPDF uses ``unpaper`` to provide the implementation of the
 ``--clean`` and ``--clean-final`` arguments.
-`unpaper <https://github.com/Flameeyes/unpaper/blob/master/doc/basic-concepts.md>`__
+`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
@@ -44,8 +47,8 @@ and clean up the margins of both.
 
    Some ``unpaper`` features cause multiple input or output files to be
    consumed or produced. OCRmyPDF requires ``unpaper`` to consume one
-   file and produce one file. An deviation from that condition will
-   result in errors.
+   file and produce one file; errors will result if this assumption is not
+   met.
 
 .. note::
 
@@ -67,11 +70,11 @@ without modifying the PDF. This is to ensure that PDFs that were
 previously OCRed or were "born digital" rather than scanned are not
 processed.
 
-If ``--skip-text`` is issued, then no OCR will be performed on pages
-that already have text. The page will be copied to the output. This may
-be useful for documents that contain both "born digital" and scanned
-content, or to use OCRmyPDF to normalize and convert to PDF/A regardless
-of their contents.
+If ``--skip-text`` is issued, then no image processing or OCR will be
+performed on pages that already have text. The page will be copied to
+the output. This may be useful for documents that contain both "born
+digital" and scanned content, or to use OCRmyPDF to normalize and
+convert to PDF/A regardless of their contents.
 
 If ``--redo-ocr`` is issued, then a detailed text analysis is performed.
 Text is categorized as either visible or invisible. Invisible text (OCR)
@@ -79,14 +82,17 @@ 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.
+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, and rasterizing any printable
-text. This is useful for redoing OCR, for fixing OCR text with a damaged
-character map (text is selectable but not searchable), and destroying
-redacted information. Any forms and vector graphics will be rasterized
-as well.
+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
 --------------------------
@@ -101,13 +107,48 @@ was requested, the preprocessed image layer will be inserted.
 If you want to adjust the amount of time spent on OCR, change
 ``--tesseract-timeout``. You can also automatically skip images that
 exceed a certain number of megapixels with ``--skip-big``. (A 300 DPI,
-8.5×11" page is 8.4 megapixels.)
+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
+-------------------
+
+Separate from these settings, 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`` 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
 ----------------------------
 
@@ -151,13 +192,14 @@ In addition to tesseract, OCRmyPDF uses the following external binaries:
 -  ``jbig2``
 
 In each case OCRmyPDF will search the ``PATH`` environment variable to
-locate the binaries.
+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://github.com/tesseract-ocr/tesseract/wiki/ControlParams>`__
+parameters <https://tesseract-ocr.github.io/tessdoc/tess3/ControlParams.html>`__
 with a configuration file.
 
 As an example, this configuration will disable Tesseract's dictionary
@@ -223,7 +265,9 @@ The ``hocr`` renderer
 The ``hocr`` renderer works with older versions of Tesseract. The image
 layer is copied from the original PDF page if possible, avoiding
 potentially lossy transcoding or loss of other PDF information. If
-preprocessing is specified, then the image layer is a new PDF.
+preprocessing is specified, then the image layer is a new PDF. (You may
+need to disable PDF/A conversion nad optimization to eliminate all
+lossy transformations.)
 
 Unlike ``sandwich`` this renderer is implemented within OCRmyPDF; anyone
 looking to customize how OCR is presented should look here. A major
@@ -236,6 +280,17 @@ PDF.js viewer.
 
 This works in all versions of Tesseract.
 
+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.
+
 Return code policy
 ==================
 
@@ -294,16 +349,31 @@ stable user interface. They may be imported from
         - 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 ``-k`` argument is issued on the command line, OCRmyPDF will keep
-the temporary folder and print the location, whether it succeeded or
-failed (provided the Python interpreter did not crash). An example
-message is:
+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
 

docs/api.rst

@@ -1,3 +1,7 @@
+.. SPDX-FileCopyrightText: 2022 James R. Barlow
+..
+.. SPDX-License-Identifier: CC-BY-SA-4.0
+
 ======================
 Using the OCRmyPDF API
 ======================
@@ -68,14 +72,6 @@ OCRmyPDF, use processes.
     not take at least one of these steps, process semantics will prevent
     OCRmyPDF from working correctly.
 
-.. warning::
-
-    On macOS with Python 3.7, you must call
-    :func:`multiprocessing.set_start_method("spawn")`. Without this, multiprocessing
-    will be unstable. From the command line, OCRmyPDF does this automatically,
-    but as an API user you must do this. See Python bpo-33725 for details.
-    Python 3.8+ also resolve this automatically.
-
 Logging
 -------
 

docs/apiref.rst

@@ -1,3 +1,7 @@
+.. SPDX-FileCopyrightText: 2022 James R. Barlow
+..
+.. SPDX-License-Identifier: CC-BY-SA-4.0
+
 =============
 API Reference
 =============

docs/batch.rst

@@ -1,3 +1,7 @@
+.. SPDX-FileCopyrightText: 2022 James R. Barlow
+..
+.. SPDX-License-Identifier: CC-BY-SA-4.0
+
 ================
 Batch processing
 ================
@@ -17,8 +21,8 @@ processors. To maximize parallelism without overloading your system with
 processes, consider using ``parallel -j 2`` to limit parallel to running
 two jobs at once.
 
-This command will run all ocrmypdf all files named ``*.pdf`` in the
-current directory and write them to the previous created ``output/``
+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
@@ -36,18 +40,11 @@ Directory trees
 ===============
 
 This will walk through a directory tree and run OCR on all files in
-place, printing the output in a way that makes
+place, and printing each filename in between runs:
 
 .. code-block:: bash
 
-   find . -printf '%p' -name '*.pdf' -exec ocrmypdf '{}' '{}' \;
-
-Alternatively, with a docker container (mounts a volume to the container
-where the PDFs are stored):
-
-.. code-block:: bash
-
-   find . -printf '%p' -name '*.pdf' -exec docker run --rm -v <host dir>:<container dir> jbarlow83/ocrmypdf '<container dir>/{}' '<container dir>/{}' \;
+   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
@@ -63,6 +60,15 @@ In a Windows batch file, use
 
    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
 -------------
 
@@ -81,9 +87,9 @@ 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.
 
-This is only possible for x86-based Synology products. Some Synology
-products use ARM or Power processors and do not support Docker. Further
-adjustments might be needed to deal with the Synology's relatively
+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
@@ -124,7 +130,9 @@ Users may need to customize the script to meet their requirements.
 
     "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}'``."
@@ -142,29 +150,32 @@ The watcher service is included in the OCRmyPDF Docker image. To run it:
 .. code-block:: bash
 
     docker run \
-        -v <path to files to convert>:/input \
-        -v <path to store results>:/output \
-        -e OCR_OUTPUT_DIRECTORY_YEAR_MONTH=1 \
-        -e OCR_ON_SUCCESS_DELETE=1 \
-        -e OCR_DESKEW=1 \
-        -e PYTHONUNBUFFERED=1 \
-        -it --entrypoint python3 \
+        --volume <path to files to convert>:/input \
+        --volume <path to store results>:/output \
+        --volume <path to store processed originals>:/archive \
+        --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`` and will
-convert it to a OCRed PDF in ``/output/``. The parameters to this image are:
+This service will watch for a file that matches ``/input/\*.pdf``,
+convert it to a OCRed PDF in ``/output/``, and move the processed
+original to ``/archive``. The parameters to this image are:
 
 .. csv-table:: watcher.py parameters for Docker
     :header: "Parameter", "Description"
     :widths: 50, 50
 
-    "``-v <path to files to convert>:/input``", "Files placed in this location will be OCRed"
-    "``-v <path to store results>:/output``", "This is where OCRed files will be stored"
-    "``-e OCR_OUTPUT_DIRECTORY_YEAR_MONTH=1``", "Define environment variable OCR_OUTPUT_DIRECTORY_YEAR_MONTH=1"
-    "``-e OCR_ON_SUCCESS_DELETE=1``", "Define environment variable"
-    "``-e OCR_DESKEW=1``", "Define environment variable"
-    "``-e PYTHONBUFFERED=1``", "This will force STDOUT to be unbuffered and allow you to see messages in docker logs"
+    "``--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>:/archive``", "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

docs/cloud.rst

@@ -0,0 +1,87 @@
+.. _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

@@ -1,5 +1,9 @@
 #!/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.
 #
@@ -20,8 +24,6 @@
 # import sys
 # sys.path.insert(0, os.path.abspath('.'))
 
-"""isort:skip_file"""
-
 # -- General configuration ------------------------------------------------
 
 # If your documentation needs a minimal Sphinx version, state it here.
@@ -42,7 +44,7 @@ extensions = [
 # Extension settings
 intersphinx_mapping = {'https://docs.python.org/': None}
 napoleon_use_rtype = False
-issues_github_path = "jbarlow83/OCRmyPDF"
+issues_github_path = "ocrmypdf/OCRmyPDF"
 
 # Add any paths that contain templates here, relative to this directory.
 templates_path = ['_templates']
@@ -63,7 +65,7 @@ master_doc = 'index'
 # General information about the project.
 project = 'ocrmypdf'
 copyright = (
-    '2021, James R. Barlow. Licensed under Creative Commons Attribution-ShareAlike 4.0.'
+    '2023, James R. Barlow. Licensed under Creative Commons Attribution-ShareAlike 4.0.'
 )
 author = 'James R. Barlow'
 
@@ -74,6 +76,7 @@ author = 'James R. Barlow'
 # The short X.Y version.
 
 import os
+from importlib.metadata import version as package_version
 
 on_rtd = os.environ.get('READTHEDOCS') == 'True'
 
@@ -94,10 +97,6 @@ if on_rtd:
     ]
     sys.modules.update((mod_name, Mock()) for mod_name in MOCK_MODULES)
 
-try:
-    from importlib_metadata import version as package_version
-except ModuleNotFoundError:
-    from importlib.metadata import version as package_version
 
 # The full version, including alpha/beta/rc tags.
 release = package_version('ocrmypdf')

docs/contributing.rst

@@ -1,3 +1,7 @@
+.. SPDX-FileCopyrightText: 2022 James R. Barlow
+..
+.. SPDX-License-Identifier: CC-BY-SA-4.0
+
 =======================
 Contributing guidelines
 =======================
@@ -14,7 +18,7 @@ work you're contemplating is already half-done in a development branch.
 Code style
 ==========
 
-We use PEP8, ``black`` for code formatting and ``isort`` for import sorting. The
+We use PEP8, ``black`` for code formatting and ``ruff`` for everything else. The
 settings for these programs are in ``pyproject.toml`` and ``setup.cfg``. Pull
 requests should follow the style guide. One difference we use from "black" style
 is that strings shown to the user are always in double quotes (``"``) and strings
@@ -25,12 +29,17 @@ Tests
 
 New features should come with tests that confirm their correctness.
 
-New Python dependencies
-=======================
+New dependencies
+================
 
-If you are proposing a change that will require a new Python dependency, we
+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.
+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.
@@ -39,7 +48,19 @@ 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.
+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?
 ========================================
@@ -49,8 +70,8 @@ The program/project is OCRmyPDF and the name of the executable or library is ocr
 Copyright and license
 =====================
 
-For contributions over 10 lines of code, please include your name to list of
+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. Please contribute code only that you wrote and you have the permission to
-contribute or license to us.
+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

@@ -1,3 +1,7 @@
+.. SPDX-FileCopyrightText: 2022 James R. Barlow
+..
+.. SPDX-License-Identifier: CC-BY-SA-4.0
+
 ========
 Cookbook
 ========
@@ -200,7 +204,7 @@ might remove desirable content, especially from poor quality scans.
 
 .. warning::
 
-   ``--clean-final`` and ``-remove-background`` may leave undesirable
+   ``--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.
@@ -227,13 +231,20 @@ Don't actually OCR my PDF
 =========================
 
 If you set ``--tesseract-timeout 0`` OCRmyPDF will apply its image
-processing without performing OCR, if all you want to is to apply image
-processing or PDF/A conversion.
+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
 --------------------------------------
 
@@ -243,10 +254,11 @@ You can also optimize all images without performing any OCR:
 
     ocrmypdf --tesseract-timeout=0 --optimize 3 --skip-text input.pdf output.pdf
 
-Perform OCR only certain pages
-------------------------------
+Process only certain pages
+--------------------------
 
-You can ask OCRmyPDF to only apply OCR to certain pages.
+You can ask OCRmyPDF to only apply `image processing <#image-processing>`__
+and OCR to certain pages.
 
 .. code-block:: bash
 
@@ -256,14 +268,15 @@ Hyphens denote a range of pages and commas separate page numbers. If you prefer
 to use spaces, quote all of the page numbers: ``--pages '2, 3, 5, 7'``.
 
 OCRmyPDF will warn if your list of page numbers contains duplicates or
-overlap pages. OCRmyPDF does not currently account for document page numbers,
+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.
+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 in
-the file and convert it to PDF/A, unless you disable those options. In this
-example, we want to OCR only the title and otherwise change the PDF as little
-as possible:
+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
 
@@ -278,7 +291,7 @@ argument. (Normally, OCRmyPDF will exit with an error if asked to modify
 a file with OCR.)
 
 This may be helpful for users who want to take advantage of accuracy
-improvements in Tesseract 4.0 for files they previously OCRed with an
+improvements in Tesseract for files they previously OCRed with an
 earlier version of Tesseract and OCRmyPDF.
 
 .. code-block:: bash
@@ -339,6 +352,9 @@ levels in the GCC compiler.
         - 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``
@@ -352,10 +368,29 @@ The types of optimization available may expand over time. By default,
 OCRmyPDF compresses data streams inside PDFs, and will change
 inefficient compression modes to more modern versions. A program like
 ``qpdf`` can be used to change encodings, e.g. to inspect the internals
-fo a PDF.
+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

@@ -0,0 +1,32 @@
+.. 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

@@ -1,3 +1,7 @@
+.. SPDX-FileCopyrightText: 2022 James R. Barlow
+..
+.. SPDX-License-Identifier: CC-BY-SA-4.0
+
 .. _docker:
 
 =====================
@@ -59,7 +63,7 @@ Using the Docker image on the command line
 ==========================================
 
 **Unlike typical Docker containers**, in this section the OCRmyPDF Docker
-container is emphemeral – it runs for one OCR job and terminates, just like a
+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).
 

docs/errors.rst

@@ -1,3 +1,7 @@
+.. SPDX-FileCopyrightText: 2022 James R. Barlow
+..
+.. SPDX-License-Identifier: CC-BY-SA-4.0
+
 =====================
 Common error messages
 =====================

docs/images/logo-square-256.svg

@@ -0,0 +1,239 @@
+<?xml version="1.0" encoding="UTF-8" standalone="no"?>
+<svg
+   width="256"
+   height="256"
+   viewBox="0 0 256 256.00001"
+   version="1.1"
+   xml:space="preserve"
+   style="clip-rule:evenodd;fill-rule:evenodd;stroke-linecap:round;stroke-linejoin:round;stroke-miterlimit:1.5"
+   id="svg270"
+   sodipodi:docname="logo-square-256.svg"
+   inkscape:export-filename="/home/jb/src/ocrmypdf/docs/images/logo-square.png"
+   inkscape:export-xdpi="96"
+   inkscape:export-ydpi="96"
+   inkscape:version="1.1.2 (0a00cf5339, 2022-02-04)"
+   xmlns:inkscape="http://www.inkscape.org/namespaces/inkscape"
+   xmlns:sodipodi="http://sodipodi.sourceforge.net/DTD/sodipodi-0.dtd"
+   xmlns="http://www.w3.org/2000/svg"
+   xmlns:svg="http://www.w3.org/2000/svg"
+   xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
+   xmlns:cc="http://creativecommons.org/ns#"
+   xmlns:dc="http://purl.org/dc/elements/1.1/"
+   xmlns:serif="http://www.serif.com/"><metadata
+   id="metadata276"><rdf:RDF><cc:Work
+       rdf:about=""><dc:format>image/svg+xml</dc:format><dc:type
+         rdf:resource="http://purl.org/dc/dcmitype/StillImage" /></cc:Work></rdf:RDF></metadata><defs
+   id="defs274" /><sodipodi:namedview
+   pagecolor="#ffffff"
+   bordercolor="#666666"
+   borderopacity="1"
+   objecttolerance="10"
+   gridtolerance="10"
+   guidetolerance="10"
+   inkscape:pageopacity="0"
+   inkscape:pageshadow="2"
+   inkscape:window-width="2396"
+   inkscape:window-height="1691"
+   id="namedview272"
+   showgrid="false"
+   lock-margins="false"
+   inkscape:zoom="2.0079523"
+   inkscape:cx="189.74554"
+   inkscape:cy="54.533168"
+   inkscape:window-x="26"
+   inkscape:window-y="23"
+   inkscape:window-maximized="0"
+   inkscape:current-layer="svg270"
+   inkscape:pagecheckerboard="0"
+   width="256px"
+   fit-margin-top="0"
+   fit-margin-left="0"
+   fit-margin-right="0"
+   fit-margin-bottom="0" />
+    <g
+   id="svg"
+   transform="matrix(0.48534351,0,0,0.4057699,1.8106874,71.192214)">
+        <rect
+   x="0"
+   y="0"
+   width="520"
+   height="280"
+   style="fill:#ffffff"
+   id="rect188" />
+        <g
+   transform="matrix(1.03522,0,0,1.23823,-69.7528,-83.422)"
+   id="g267">
+            <g
+   transform="translate(243.977,20.0703)"
+   id="g218">
+                <g
+   id="Page">
+                    <g
+   transform="matrix(0.961773,0,0,1.05962,6.19811,-3.01071)"
+   id="g192">
+                        <path
+   d="m 328.5,97.682 c 0,-1.217 -0.517,-2.386 -1.444,-3.264 -7.03,-6.66 -37.614,-35.638 -44.828,-42.474 -0.977,-0.925 -2.327,-1.448 -3.738,-1.448 -13.997,0 -90.407,0 -111.151,0 -2.871,0 -5.198,2.113 -5.198,4.718 0,27.837 0,170.351 0,198.186 0,2.605 2.327,4.717 5.197,4.717 24.904,0 131.821,0 156.2,0 2.74,0 4.962,-2.016 4.962,-4.504 0,-24.345 0,-139.717 0,-155.931 z"
+   style="fill:#fdfdfd;stroke:#333333;stroke-width:3.95px"
+   id="path190" />
+                    </g>
+                    <g
+   id="Dog-ear"
+   serif:id="Dog ear"
+   transform="translate(-4,2)">
+                        <path
+   d="m 277.072,48.496 v 45.352 c 0,1.324 0.526,2.593 1.462,3.529 0.936,0.936 2.205,1.462 3.529,1.462 12.485,0 44.078,0 44.078,0"
+   style="fill:#f5f5f5;stroke:#333333;stroke-width:4px"
+   id="path194" />
+                    </g>
+                </g>
+                <g
+   transform="translate(-29.6816,-0.395178)"
+   id="g216">
+                    <g
+   transform="matrix(1.00243,0,0,1.11818,-144.72,-8.80181)"
+   id="g200">
+                        <path
+   d="m 465.73,119.654 c 0,-2.049 -1.856,-3.713 -4.142,-3.713 H 310.259 c -2.286,0 -4.142,1.664 -4.142,3.713 v 63.454 c 0,2.049 1.856,3.713 4.142,3.713 h 151.329 c 2.286,0 4.142,-1.664 4.142,-3.713 z"
+   style="fill:#f80000;stroke:#ffffff;stroke-width:3.77px"
+   id="path198" />
+                    </g>
+                    <g
+   transform="matrix(1.24571,0,0,1.35864,116.812,84.3924)"
+   id="g214">
+                        <g
+   transform="matrix(64,0,0,64,42.1437,77.6203)"
+   id="g204">
+                            <path
+   d="m 0.084,0 v -0.68 h 0.213 c 0.074,0 0.137,0.017 0.19,0.05 0.053,0.034 0.079,0.09 0.079,0.168 0,0.077 -0.028,0.134 -0.085,0.17 -0.057,0.037 -0.121,0.055 -0.193,0.055 H 0.213 V 0 Z m 0.209,-0.572 h -0.08 v 0.228 h 0.082 c 0.039,0 0.07,-0.009 0.094,-0.027 0.024,-0.017 0.037,-0.045 0.04,-0.083 0,-0.044 -0.012,-0.075 -0.036,-0.092 -0.024,-0.017 -0.057,-0.026 -0.1,-0.026 z"
+   style="fill:#ffffff;fill-rule:nonzero"
+   id="path202" />
+                        </g>
+                        <g
+   transform="matrix(64,0,0,64,79.7117,77.6203)"
+   id="g208">
+                            <path
+   d="M 0.332,0 H 0.084 v -0.68 h 0.252 c 0.105,0 0.182,0.032 0.233,0.095 0.051,0.063 0.076,0.144 0.076,0.241 0,0.105 -0.027,0.189 -0.082,0.251 C 0.508,-0.031 0.431,0 0.332,0 Z M 0.337,-0.57 H 0.213 v 0.461 H 0.33 c 0.055,0 0.099,-0.018 0.132,-0.054 C 0.495,-0.199 0.511,-0.259 0.511,-0.344 0.511,-0.415 0.497,-0.47 0.469,-0.51 0.441,-0.55 0.397,-0.57 0.337,-0.57 Z"
+   style="fill:#ffffff;fill-rule:nonzero"
+   id="path206" />
+                        </g>
+                        <g
+   transform="matrix(64,0,0,64,123.424,77.6203)"
+   id="g212">
+                            <path
+   d="M 0.405,-0.288 H 0.213 V 0 H 0.084 v -0.68 h 0.385 l 0.02,0.102 H 0.213 v 0.189 h 0.173 z"
+   style="fill:#ffffff;fill-rule:nonzero"
+   id="path210" />
+                        </g>
+                    </g>
+                </g>
+            </g>
+            <g
+   transform="matrix(1,0,0,1.52217,67.3796,10.7507)"
+   id="g222">
+                <rect
+   x="23.500999"
+   y="81.300003"
+   width="162.30499"
+   height="61.77"
+   style="fill:#b4d5ff"
+   id="rect220" />
+            </g>
+            <g
+   transform="matrix(0.967536,0,0,0.961535,5.90498,47.9703)"
+   id="g236">
+                <g
+   transform="matrix(90.4804,0,0,90.4804,82.6698,167.705)"
+   id="g226">
+                    <path
+   d="m 0.057,-0.337 c 0,-0.105 0.027,-0.19 0.082,-0.257 0.055,-0.066 0.132,-0.1 0.231,-0.102 0.107,0 0.186,0.034 0.237,0.103 0.051,0.069 0.077,0.152 0.077,0.249 0,0.105 -0.027,0.191 -0.082,0.258 -0.055,0.067 -0.133,0.1 -0.232,0.1 C 0.264,0.014 0.185,-0.02 0.134,-0.089 0.083,-0.157 0.057,-0.24 0.057,-0.337 Z m 0.135,-0.001 c 0,0.071 0.014,0.13 0.043,0.175 0.029,0.045 0.073,0.068 0.134,0.068 0.055,0 0.098,-0.02 0.131,-0.061 0.033,-0.041 0.049,-0.103 0.049,-0.188 0,-0.071 -0.014,-0.129 -0.043,-0.174 -0.029,-0.045 -0.073,-0.068 -0.134,-0.068 -0.053,0 -0.097,0.022 -0.13,0.067 -0.033,0.045 -0.05,0.105 -0.05,0.181 z"
+   style="fill:#333333;fill-rule:nonzero"
+   id="path224" />
+                </g>
+                <g
+   transform="matrix(90.4804,0,0,90.4804,147.906,167.705)"
+   id="g230">
+                    <path
+   d="M 0.505,-0.557 C 0.473,-0.567 0.448,-0.574 0.429,-0.579 0.41,-0.583 0.388,-0.585 0.361,-0.585 c -0.054,0 -0.096,0.022 -0.125,0.066 -0.029,0.044 -0.044,0.104 -0.044,0.181 0,0.066 0.012,0.123 0.037,0.171 0.025,0.048 0.066,0.072 0.124,0.072 0.029,0 0.056,-0.003 0.081,-0.009 0.025,-0.006 0.047,-0.013 0.068,-0.022 L 0.551,-0.03 C 0.525,-0.017 0.494,-0.006 0.457,0.002 0.42,0.01 0.388,0.014 0.36,0.014 0.254,0.014 0.177,-0.02 0.129,-0.088 0.081,-0.156 0.057,-0.239 0.057,-0.337 c 0,-0.105 0.027,-0.19 0.08,-0.257 0.053,-0.067 0.129,-0.1 0.228,-0.1 0.02,0 0.048,0.003 0.083,0.01 0.035,0.007 0.068,0.018 0.097,0.034 z"
+   style="fill:#333333;fill-rule:nonzero"
+   id="path228" />
+                </g>
+                <g
+   transform="matrix(90.4804,0,0,90.4804,199.751,167.705)"
+   id="g234">
+                    <path
+   d="m 0.293,-0.572 h -0.08 v 0.208 h 0.082 c 0.039,0 0.071,-0.008 0.096,-0.024 0.025,-0.015 0.038,-0.041 0.038,-0.077 0,-0.038 -0.012,-0.065 -0.036,-0.082 -0.024,-0.017 -0.057,-0.025 -0.1,-0.025 z M 0.479,0 0.335,-0.26 C 0.328,-0.259 0.32,-0.259 0.312,-0.259 0.304,-0.258 0.296,-0.258 0.288,-0.258 H 0.213 V 0 H 0.084 v -0.68 h 0.213 c 0.074,0 0.137,0.017 0.19,0.051 0.053,0.034 0.079,0.087 0.079,0.158 0,0.042 -0.011,0.078 -0.032,0.108 -0.022,0.031 -0.05,0.054 -0.084,0.071 L 0.617,0 Z"
+   style="fill:#333333;fill-rule:nonzero"
+   id="path232" />
+                </g>
+            </g>
+            <g
+   transform="matrix(0.916882,0,0,1,121.475,-32.6535)"
+   id="g246">
+                <g
+   transform="matrix(86.953,0,0,86.953,152.996,241.878)"
+   id="g240">
+                    <path
+   d="M 0.479,-0.428 C 0.5,-0.451 0.527,-0.47 0.562,-0.484 c 0.034,-0.013 0.065,-0.02 0.092,-0.02 0.066,0 0.113,0.019 0.141,0.058 0.027,0.039 0.041,0.086 0.041,0.142 V 0 H 0.705 v -0.298 c 0,-0.031 -0.007,-0.054 -0.022,-0.071 -0.015,-0.016 -0.036,-0.024 -0.064,-0.024 -0.019,0 -0.038,0.005 -0.059,0.015 -0.021,0.01 -0.039,0.021 -0.056,0.034 0.001,0.007 0.001,0.013 0.002,0.02 0.001,0.007 0.001,0.013 0.001,0.02 V 0 H 0.376 v -0.298 c 0,-0.031 -0.007,-0.054 -0.022,-0.071 -0.015,-0.016 -0.036,-0.024 -0.063,-0.024 -0.017,0 -0.033,0.003 -0.05,0.01 -0.017,0.007 -0.034,0.016 -0.049,0.027 V 0 H 0.062 V -0.485 H 0.13 l 0.032,0.044 c 0.022,-0.02 0.049,-0.035 0.08,-0.047 0.031,-0.011 0.058,-0.016 0.083,-0.016 0.038,0 0.07,0.007 0.095,0.02 0.025,0.014 0.045,0.033 0.059,0.056 z"
+   style="fill:#333333;fill-rule:nonzero"
+   id="path238" />
+                </g>
+                <g
+   transform="matrix(86.953,0,0,86.953,228.906,241.878)"
+   id="g244">
+                    <path
+   d="M 0.156,0.023 0.179,-0.034 0.006,-0.467 0.14,-0.485 0.252,-0.191 0.358,-0.485 H 0.495 L 0.278,0.064 C 0.263,0.103 0.236,0.137 0.197,0.165 0.158,0.193 0.118,0.212 0.075,0.222 L 0.029,0.115 C 0.052,0.105 0.077,0.093 0.104,0.079 0.13,0.064 0.147,0.046 0.156,0.023 Z"
+   style="fill:#333333;fill-rule:nonzero"
+   id="path242" />
+                </g>
+            </g>
+            <g
+   id="Selectors"
+   transform="matrix(0.965977,0,0,0.807602,67.3796,67.3718)">
+                <g
+   id="Right-selector"
+   serif:id="Right selector">
+                    <g
+   transform="matrix(1.03522,0,0,1.23823,2.07044,0)"
+   id="g250">
+                        <path
+   d="M 185.806,161.156 V 67.132"
+   style="fill:none;stroke:#4c9fff;stroke-width:4px;stroke-linecap:butt"
+   id="path248" />
+                    </g>
+                    <g
+   transform="matrix(1.03522,0,0,1.23823,161.788,169.469)"
+   id="g254">
+                        <circle
+   cx="31.523001"
+   cy="34.313999"
+   r="10.021"
+   style="fill:#4c9fff;stroke:#4c9fff;stroke-width:4px;stroke-linecap:butt"
+   id="circle252" />
+                    </g>
+                </g>
+                <g
+   id="Left-selector"
+   serif:id="Left selector">
+                    <g
+   transform="matrix(1.03522,0,0,1.23823,-170.092,0)"
+   id="g259">
+                        <path
+   d="M 185.806,161.156 V 67.132"
+   style="fill:none;stroke:#4c9fff;stroke-width:4px;stroke-linecap:butt"
+   id="path257" />
+                    </g>
+                    <g
+   transform="matrix(1.03522,0,0,1.23823,-10.3742,28.2274)"
+   id="g263">
+                        <circle
+   cx="31.523001"
+   cy="34.313999"
+   r="10.021"
+   style="fill:#4c9fff;stroke:#4c9fff;stroke-width:4px;stroke-linecap:butt"
+   id="circle261" />
+                    </g>
+                </g>
+            </g>
+        </g>
+    </g>
+</svg>

docs/index.rst

@@ -1,3 +1,7 @@
+.. SPDX-FileCopyrightText: 2022 James R. Barlow
+..
+.. SPDX-License-Identifier: CC-BY-SA-4.0
+
 OCRmyPDF documentation
 ======================
 
@@ -16,7 +20,6 @@ image processing and OCR to existing PDFs.
    introduction
    release_notes
    installation
-   optimizer
    languages
    jbig2
 
@@ -25,9 +28,11 @@ image processing and OCR to existing PDFs.
    :maxdepth: 2
 
    cookbook
+   optimizer
    docker
    advanced
    batch
+   cloud
    performance
    pdfsecurity
    errors
@@ -39,6 +44,7 @@ image processing and OCR to existing PDFs.
    api
    plugins
    apiref
+   design_notes
    contributing
    maintainers
 

docs/installation.rst

@@ -1,3 +1,7 @@
+.. SPDX-FileCopyrightText: 2022 James R. Barlow
+..
+.. SPDX-License-Identifier: CC-BY-SA-4.0
+
 ===================
 Installing OCRmyPDF
 ===================
@@ -12,21 +16,23 @@ system/platform. This version may be out of date, however.
 
 These platforms have one-liner installs:
 
-+-------------------------------+-------------------------------+
-| Debian, Ubuntu                | ``apt install ocrmypdf``      |
-+-------------------------------+-------------------------------+
-| Windows Subsystem for Linux   | ``apt install ocrmypdf``      |
-+-------------------------------+-------------------------------+
-| Fedora                        | ``dnf install ocrmypdf``      |
-+-------------------------------+-------------------------------+
-| macOS                         | ``brew install ocrmypdf``     |
-+-------------------------------+-------------------------------+
-| LinuxBrew                     | ``brew install ocrmypdf``     |
-+-------------------------------+-------------------------------+
-| FreeBSD                       | ``pkg install py38-ocrmypdf`` |
-+-------------------------------+-------------------------------+
-| Conda (WSL, macOS, Linux)     | ``conda install ocrmypdf``    |
-+-------------------------------+-------------------------------+
++-------------------------------+-----------------------------------------+
+| 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.
@@ -38,50 +44,45 @@ install, or install a more recent version than your platform provides, read on.
 Installing on Linux
 ===================
 
-Debian and Ubuntu 18.04 or newer
+Debian and Ubuntu 20.04 or newer
 --------------------------------
 
-.. |deb-stable| image:: https://repology.org/badge/version-for-repo/debian_stable/ocrmypdf.svg
-    :alt: Debian 9 stable ("stretch")
+.. |deb-11| image:: https://repology.org/badge/version-for-repo/debian_11/ocrmypdf.svg
+    :alt: Debian 11
 
-.. |deb-testing| image:: https://repology.org/badge/version-for-repo/debian_testing/ocrmypdf.svg
-    :alt: Debian 10 testing ("buster")
+.. |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-1804| image:: https://repology.org/badge/version-for-repo/ubuntu_18_04/ocrmypdf.svg
-    :alt: Ubuntu 18.04 LTS
-
 .. |ubu-2004| image:: https://repology.org/badge/version-for-repo/ubuntu_20_04/ocrmypdf.svg
     :alt: Ubuntu 20.04 LTS
 
-.. |ubu-2110| image:: https://repology.org/badge/version-for-repo/ubuntu_21_10/ocrmypdf.svg
-    :alt: Ubuntu 21.10
+.. |ubu-2204| image:: https://repology.org/badge/version-for-repo/ubuntu_22_04/ocrmypdf.svg
+    :alt: Ubuntu 22.04 LTS
 
 +-----------------------------------------------+
 | **OCRmyPDF versions in Debian & Ubuntu**      |
 +-----------------------------------------------+
 | |latest|                                      |
 +-----------------------------------------------+
-| |deb-stable| |deb-testing| |deb-unstable|     |
+| |deb-11| |deb-12| |deb-unstable|              |
 +-----------------------------------------------+
-| |ubu-1804| |ubu-2004| |ubu-2110|              |
+| |ubu-2004| |ubu-2204|                         |
 +-----------------------------------------------+
 
-Users of Debian 9 ("stretch") or later, or Ubuntu 18.04 or later, including users
-of Windows Subsystem for Linux, may simply
+Users of Debian 11, or Ubuntu 20.04 LTS, or newer may simply
 
 .. code-block:: bash
 
-    apt-get install ocrmypdf
+    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>`__. Ubuntu 16.10 to 17.10
-inclusive also had ocrmypdf, but these versions are end of life.
+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
@@ -91,19 +92,19 @@ For full details on version availability for your platform, check the
 
    OCRmyPDF for Debian and Ubuntu currently omit the JBIG2 encoder.
    OCRmyPDF works fine without it but will produce larger output files.
-   If you build jbig2enc from source, ocrmypdf 7.0.0 and later will
+   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-34| image:: https://repology.org/badge/version-for-repo/fedora_34/ocrmypdf.svg
-    :alt: Fedora 34
-
 .. |fedora-35| image:: https://repology.org/badge/version-for-repo/fedora_35/ocrmypdf.svg
     :alt: Fedora 35
 
+.. |fedora-36| image:: https://repology.org/badge/version-for-repo/fedora_36/ocrmypdf.svg
+    :alt: Fedora 36
+
 .. |fedora-rawhide| image:: https://repology.org/badge/version-for-repo/fedora_rawhide/ocrmypdf.svg
     :alt: Fedore Rawhide
 
@@ -112,14 +113,14 @@ Fedora
 +-----------------------------------------------+
 | |latest|                                      |
 +-----------------------------------------------+
-| |fedora-34| |fedora-35| |fedora-rawhide|      |
+| |fedora-35| |fedora-36| |fedora-rawhide|      |
 +-----------------------------------------------+
 
 Users of Fedora 29 or later may simply
 
 .. code-block:: bash
 
-    dnf install ocrmypdf
+    dnf install ocrmypdf tesseract-osd
 
 For full details on version availability, check the `Fedora Package
 Tracker <https://apps.fedoraproject.org/packages/ocrmypdf>`__.
@@ -138,9 +139,29 @@ from sources <#installing-head-revision-from-sources>`__.
 
 .. _ubuntu-lts-latest:
 
-Installing the latest version on Ubuntu 20.04 LTS
+Installing the latest version on Ubuntu 22.04 LTS
 -------------------------------------------------
 
+Ubuntu 22.04 includes ocrmypdf 13.4.0 - you can install that with
+``apt install ocrmypdf``. To install a more recent version for the current
+user, follow these steps:
+
+.. code-block:: bash
+
+    sudo apt-get update
+    sudo apt-get -y install ocrmypdf python3-pip
+
+    pip install --user --upgrade ocrmypdf
+
+If you get the message ``WARNING: The script ocrmypdf is installed in
+'/home/$USER/.local/bin' which is not on PATH.``, you may need to re-login
+or open a new shell, or manually add this to your user's PATH.
+
+To add JBIG2 encoding, see :ref:`jbig2`.
+
+Ubuntu 20.04 LTS
+----------------
+
 Ubuntu 20.04 includes ocrmypdf 9.6.0 - you can install that with ``apt``. To
 install a more recent version, uninstall the system-provided version of
 ocrmypdf, and install the following dependencies:
@@ -171,44 +192,6 @@ To install for the current user only:
     export PATH=$HOME/.local/bin:$PATH
     pip3 install --user ocrmypdf
 
-Ubuntu 18.04 LTS
-----------------
-
-Ubuntu 18.04 includes ocrmypdf 6.1.2 - you can install that with ``apt``, but
-it is quite old now. To install a more recent version, uninstall the old version
-of ocrmypdf, and install the following dependencies:
-
-.. code-block:: bash
-
-    sudo apt-get -y remove ocrmypdf
-    sudo apt-get -y update
-    sudo apt-get -y install \
-        ghostscript \
-        icc-profiles-free \
-        libxml2 \
-        pngquant \
-        python3-distutils \
-        python3-pkg-resources \
-        python3-reportlab \
-        qpdf \
-        tesseract-ocr \
-        zlib1g \
-        unpaper
-
-We will need a newer version of ``pip`` then was available for Ubuntu 18.04:
-
-.. code-block:: bash
-
-    wget https://bootstrap.pypa.io/get-pip.py && python3 get-pip.py
-
-Then install the most recent ocrmypdf for the local user and set the
-user's ``PATH`` to check for the user's Python packages.
-
-.. code-block:: bash
-
-    export PATH=$HOME/.local/bin:$PATH
-    python3 -m pip install --user ocrmypdf
-
 To add JBIG2 encoding, see :ref:`jbig2`.
 
 Arch Linux (AUR)
@@ -291,45 +274,20 @@ To install OCRmyPDF for Alpine Linux:
 
     apk add ocrmypdf
 
-Mageia 7
---------
+Gentoo Linux
+------------
 
-There is no OS-level packaging available for Mageia, so you must install the
-dependencies:
+.. 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
 
-    # As root user
-    urpmi.update -a
-    urpmi \
-        ghostscript \
-        icc-profiles-openicc \
-        jbig2dec \
-        pngquant \
-        python3-pip \
-        python3-distutils-extra \
-        python3-pkg-resources \
-        python3-reportlab \
-        qpdf \
-        tesseract \
-        tesseract-osd \
-        tesseract-eng \
-        tesseract-fra
-
-To install ocrmypdf for the system:
-
-.. code-block:: bash
-
-    # As root user
-    pip3 install ocrmypdf
-    ldconfig
-
-Or, to install for the current user only:
-
-.. code-block:: bash
-
-    export PATH=$HOME/.local/bin:$PATH
-    pip3 install --user ocrmypdf
+    eselect repository enable guru
+    emaint sync --repo guru
+    emerge --ask app-text/OCRmyPDF
 
 Other Linux packages
 --------------------
@@ -349,7 +307,7 @@ Homebrew
 
 .. image:: https://img.shields.io/homebrew/v/ocrmypdf.svg
     :alt: homebrew
-    :target: http://brewformulas.org/Ocrmypdf
+    :target: https://formulae.brew.sh/formula/ocrmypdf
 
 OCRmyPDF is now a standard `Homebrew <https://brew.sh>`__ formula. To
 install on macOS:
@@ -365,19 +323,6 @@ languages you can optionally install them all:
 
     brew install tesseract-lang  # Optional: Install all language packs
 
-.. note::
-
-   Users who previously installed OCRmyPDF on macOS using
-   ``pip install ocrmypdf`` should remove the pip version
-   (``pip3 uninstall ocrmypdf``) before switching to the Homebrew
-   version.
-
-.. note::
-
-   Users who previously installed OCRmyPDF from the private tap should
-   switch to the mainline version (``brew untap jbarlow83/ocrmypdf``)
-   and install from there.
-
 Manual installation on macOS
 ----------------------------
 
@@ -411,19 +356,13 @@ Update the homebrew pip:
 
 .. code-block:: bash
 
-    pip3 install --upgrade pip
+    pip install --upgrade pip
 
-You can then install OCRmyPDF from PyPI, for the current user:
+You can then install OCRmyPDF from PyPI for the current user:
 
 .. code-block:: bash
 
-    pip3 install --user ocrmypdf
-
-or system-wide:
-
-.. code-block:: bash
-
-    pip3 install ocrmypdf
+    pip install --user ocrmypdf
 
 The command line program should now be available:
 
@@ -443,9 +382,9 @@ Native Windows
 
 You must install the following for Windows:
 
-* Python 3.7 (64-bit) or later
-* Tesseract 4.0 or later
-* Ghostscript 9.50 or later
+* Python 3.9 (64-bit) or later
+* Tesseract 4.1.1 (64-bit) or later
+* Ghostscript 9.50 (64-bit) or later
 
 Using the `Chocolatey <https://chocolatey.org/>`_ package manager, install the
 following when running in an Administrator command prompt:
@@ -464,10 +403,8 @@ Administrator.):
 
 * ``pip install ocrmypdf``
 
-Chocolatey automatically selects appropriate versions of these applications. If you
-are installing them manually, please install 64-bit versions of all applications for
-64-bit Windows, or 32-bit versions of all applications for 32-bit Windows. Mixing
-the "bitness" of these programs will lead to errors.
+Chocolatey automatically selects appropriate versions of these applications. Please make sure
+you are installing the 64-bit versions.
 
 OCRmyPDF will check the Windows Registry and standard locations in your Program Files
 for third party software it needs (specifically, Tesseract and Ghostscript). To
@@ -482,11 +419,15 @@ to change the PATH.
     Please download Python from Python.org or Chocolatey instead, and do not use the
     Microsoft Store version.
 
+.. warning::
+
+    32-bit Windows might work, but is not supported.
+
 Windows Subsystem for Linux
 ---------------------------
 
-#. Install Ubuntu 20.04 for Windows Subsystem for Linux, if not already installed.
-#. Follow the procedure to install :ref:`OCRmyPDF on Ubuntu 20.04 <ubuntu-lts-latest>`.
+#. 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
@@ -507,7 +448,7 @@ Cygwin64
 
 First install the the following prerequisite Cygwin packages using ``setup-x86_64.exe``::
 
-    python37 (or later)
+    python38 (or later)
     python3?-devel
     python3?-pip
     python3?-lxml
@@ -558,16 +499,13 @@ your command prompt can run the docker "hello world" container.
 Installing on FreeBSD
 =====================
 
-.. image:: https://repology.org/badge/version-for-repo/freebsd/python:ocrmypdf.svg
+.. image:: https://repology.org/badge/version-for-repo/freebsd/ocrmypdf.svg
     :alt: FreeBSD
-    :target: https://repology.org/project/python:ocrmypdf/versions
-
-FreeBSD 11.3, 12.0, 12.1-RELEASE and 13.0-CURRENT are supported. Other
-versions likely work but have not been tested.
+    :target: https://repology.org/project/ocrmypdf/versions
 
 .. code-block:: bash
 
-    pkg install py38-ocrmypdf
+    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``.
@@ -588,21 +526,6 @@ the latest version. However, PyPI and ``pip`` cannot address the fact
 that ``ocrmypdf`` depends on certain non-Python system libraries and
 programs being installed.
 
-.. warning::
-
-    Debian and Ubuntu users: unfortunately, Debian and Ubuntu customize
-    Python in non-standard ways, and the nature of these customizations
-    varies from release to release. This can make for a frustrating
-    user experience. The instructions below work on almost all platforms that
-    have Python installed, except for Debian and Ubuntu, where you may need
-    to take additional steps. For best results on Debian and Ubuntu, use the
-    ``apt`` packages; or if these are too old, run
-    ``apt install python3-pip python3-venv``, create a virtual environment,
-    and install OCRmyPDF in that environment.
-
-    `See here for more inforation on Debian-Python issues
-    <https://gist.github.com/tiran/2dec9e03c6f901814f6d1e8dad09528e>`__.
-
 For best results, first install `your platform's
 version <https://repology.org/metapackage/ocrmypdf/versions>`__ of
 ``ocrmypdf``, using the instructions elsewhere in this document. Then
@@ -616,26 +539,11 @@ try:
 
 .. code-block:: bash
 
-    pip3 install --user ocrmypdf
+    pip install --user ocrmypdf
 
 You should then be able to run ``ocrmypdf --version`` and see that the
 latest version was located.
 
-Since ``pip3 install --user`` does not work correctly on some platforms,
-notably Ubuntu 16.04 and older, and the Homebrew version of Python,
-instead use this for a system wide installation:
-
-.. code-block:: bash
-
-    pip3 install ocrmypdf
-
-.. note::
-
-    AArch64 (ARM64) users: this process will be difficult because most
-    Python packages are not available as binary wheels for your platform.
-    You're probably better off using a platform install on Debian, Ubuntu,
-    or Fedora.
-
 Requirements for pip and HEAD install
 -------------------------------------
 
@@ -643,15 +551,11 @@ 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.
 
--  Python 3.7 or newer
--  Ghostscript 9.15 or newer
--  Tesseract 4.0.0-beta or newer
-
-As of ocrmypdf 7.2.1, the following versions are recommended:
+The following versions are required:
 
 -  Python 3.9 or newer
--  Ghostscript 9.23 or newer
--  Tesseract 4.0.0 or newer
+-  Ghostscript 9.50 or newer
+-  Tesseract 4.1.1 or newer
 -  jbig2enc 0.29 or newer
 -  pngquant 2.5 or newer
 -  unpaper 6.1
@@ -682,7 +586,7 @@ unfortunately, the ``pip install`` command cannot satisfy all of them.
 Installing HEAD revision from sources
 =====================================
 
-If you have ``git`` and Python 3.7 or newer installed, you can install
+If you have ``git`` and Python 3.9 or newer installed, you can install
 from source. When the ``pip`` installer runs, it will alert you if
 dependencies are missing.
 
@@ -696,7 +600,7 @@ environment:
 
 .. code-block:: bash
 
-    pip3 install git+https://github.com/jbarlow83/OCRmyPDF.git
+    pip install git+https://github.com/ocrmypdf/OCRmyPDF.git
 
 Or, to install in `development
 mode <https://pythonhosted.org/setuptools/setuptools.html#development-mode>`__,
@@ -704,18 +608,18 @@ allowing customization of OCRmyPDF, use the ``-e`` flag:
 
 .. code-block:: bash
 
-    pip3 install -e git+https://github.com/jbarlow83/OCRmyPDF.git
+    pip install -e git+https://github.com/ocrmypdf/OCRmyPDF.git
 
 You may find it easiest to install in a virtual environment, rather than
 system-wide:
 
 .. code-block:: bash
 
-    git clone -b master https://github.com/jbarlow83/OCRmyPDF.git
-    python3 -m venv
-    source venv/bin/activate
+    git clone -b main https://github.com/ocrmypdf/OCRmyPDF.git
+    python3 -m venv .venv
+    source .venv/bin/activate
     cd OCRmyPDF
-    pip3 install .
+    pip install .
 
 However, ``ocrmypdf`` will only be accessible on the system PATH when
 you activate the virtual environment.
@@ -738,9 +642,9 @@ To install all of the development and test requirements:
 
 .. code-block:: bash
 
-    git clone -b master https://github.com/jbarlow83/OCRmyPDF.git
-    python3 -m venv
-    source venv/bin/activate
+    git clone -b main https://github.com/ocrmypdf/OCRmyPDF.git
+    python -m .venv
+    source .venv/bin/activate
     cd OCRmyPDF
     pip install -e .[test]
 

docs/introduction.rst

@@ -1,3 +1,7 @@
+.. SPDX-FileCopyrightText: 2022 James R. Barlow
+..
+.. SPDX-License-Identifier: CC-BY-SA-4.0
+
 ============
 Introduction
 ============
@@ -81,7 +85,7 @@ OCRmyPDF analyzes each page of a PDF to determine the colorspace and
 resolution (DPI) needed to capture all of the information on that page
 without losing content. It uses
 `Ghostscript <http://ghostscript.com/>`__ to rasterize the page, and
-then performs on OCR the rasterized image to create an OCR "layer".
+then performs OCR on the rasterized image to create an OCR "layer".
 The layer is then grafted back onto the original PDF.
 
 While one can use a program like Ghostscript or ImageMagick to get an
@@ -186,11 +190,10 @@ Ghostscript also imposes some limitations:
    behavior can be suppressed by setting ``--pdfa-image-compression`` to
    ``jpeg`` or ``lossless`` to set all images to one type or the other.
    Ghostscript has no option to maintain the input image's format.
-   (Ghostscript 9.25+ can copy JPEG images without transcoding them;
-   earlier versions will transcode.)
+   (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 Metdata is removed.
+   PRISM Metadata is removed.
 -  Ghostscript's PDF/A conversion seems to remove or deactivate
    hyperlinks and other active content.
 

docs/jbig2.rst

@@ -1,3 +1,7 @@
+.. SPDX-FileCopyrightText: 2022 James R. Barlow
+..
+.. SPDX-License-Identifier: CC-BY-SA-4.0
+
 .. _jbig2:
 
 ============================
@@ -32,6 +36,10 @@ For all other Linux, you must build a JBIG2 encoder from source:
 
 .. _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
 ================
 

docs/languages.rst

@@ -1,3 +1,7 @@
+.. SPDX-FileCopyrightText: 2022 James R. Barlow
+..
+.. SPDX-License-Identifier: CC-BY-SA-4.0
+
 .. _lang-packs:
 
 ====================================
@@ -8,7 +12,7 @@ OCRmyPDF uses Tesseract for OCR, and relies on its language packs for all langua
 On most platforms, English is installed with Tesseract by default, but not always.
 
 Tesseract supports `most
-languages <https://github.com/tesseract-ocr/tesseract/blob/master/doc/tesseract.1.asc#languages>`__.
+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
@@ -54,6 +58,33 @@ 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
 ===========
 
@@ -70,7 +101,7 @@ derived Docker image as
 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 
+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

@@ -1,8 +1,12 @@
+.. 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 
+This is for those who package OCRmyPDF for downstream use.  (Thank you
 for your hard work.)
 
 Known ports/packagers
@@ -25,7 +29,7 @@ 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 
+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
@@ -38,14 +42,9 @@ 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 
+You can patch the ``__version__`` variable in ``src/ocrmypdf/_version.py`` if
 necessary.
 
-OCRmyPDF uses setuptools-scm-git-archive to ensure that tarballs downloaded from
-GitHub contain version information. Unfortunately, these tarballs are not always
-deterministic. See this 
-`issue <https://github.com/jbarlow83/OCRmyPDF/issues/841#issuecomment-936562696>`_.
-
 jbig2enc
 --------
 

docs/optimizer.rst

@@ -1,3 +1,7 @@
+.. SPDX-FileCopyrightText: 2022 James R. Barlow
+..
+.. SPDX-License-Identifier: CC-BY-SA-4.0
+
 ================
 PDF optimization
 ================
@@ -9,14 +13,33 @@ tuned. Optimization occurs after OCR, and only if OCR succeeded.  It does not
 perform other possible optimizations such as deduplicating resources,
 consolidating fonts, simplifying vector drawings, or anything of that nature.
 
-Optimization ranges from ``-O0`` through ``-O3``, where ``0`` disables
-optimization and ``3`` implements all options. ``1``, the default, performs only
-safe and lossless optimizations. (This is similar to GCC's optimization
-parameter.) The exact type of optimizations performed will vary over time.
+.. list-table:: Title
+   :widths: 33 6 60
+   :header-rows: 1
 
-PDF optimization requires third-party, optional tools for certain optimizations.
-If these are not installed or cannot be found by OCRmyPDF, optimization will not
-be as good.
+    * - 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
 ================================
@@ -33,12 +56,14 @@ Fast web view
 OCRmyPDF automatically optimizes PDFs for "fast web view" in Adobe Acrobat's
 parlance, or equivalently, linearizes PDFs so that the resources they reference
 are presented in the order a viewer needs them for sequential display. This
-reduces the latency of viewing a PDF both online and from local storage. This
-actually slightly increases the file size.
+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
 ======================
 

docs/pdfsecurity.rst

@@ -1,3 +1,7 @@
+.. SPDX-FileCopyrightText: 2022 James R. Barlow
+..
+.. SPDX-License-Identifier: CC-BY-SA-4.0
+
 ===================
 PDF security issues
 ===================
@@ -25,13 +29,9 @@ attack vectors.
 In short, PDFs `may contain
 viruses <https://security.stackexchange.com/questions/64052/can-a-pdf-file-contain-a-virus>`__.
 
-This
-`article <https://theinvisiblethings.blogspot.ca/2013/02/converting-untrusted-pdfs-into-trusted.html>`__
-describes a high-paranoia method which allows potentially hostile PDFs
-to be viewed and rasterized safely in a disposable virtual machine. A
-trusted PDF created in this manner is converted to images and loses all
-information making it searchable and losing all compression. OCRmyPDF
-could be used to restore searchability.
+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
 ===========================
@@ -39,11 +39,11 @@ 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
+`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
+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
@@ -54,109 +54,72 @@ into the existing PDF or it may essentially reconstruct ("re-fry") a
 visually identical PDF that may be quite different at the binary level.
 That said, OCRmyPDF is not a tool designed for sanitizing PDFs.
 
-.. _ocr-service:
-
-Using OCRmyPDF online or as a service
-=====================================
-
-OCRmyPDF is not designed for use as a public web service where a
-malicious user could upload a chosen PDF. In particular, it is not
-necessarily secure against PDF malware or PDFs that cause denial of
-service. OCRmyPDF relies on Ghostscript, and therefore, if deployed
-online one should be prepared to comply with Ghostscript's Affero GPL
-license, and any other licenses.
-
-Setting aside these concerns, a side effect of OCRmyPDF is that it may
-incidentally sanitize PDFs containing certain types of malware. It
-repairs the PDF with pikepdf/libqpdf, which could correct malformed PDF
-structures that are part of an attack. When PDF/A output is selected
-(the default), the input PDF is partially reconstructed by Ghostscript.
-When ``--force-ocr`` is used, all pages are rasterized and reconverted
-to PDF, which could remove malware in embedded images.
-
-OCRmyPDF should be relatively safe to use in a trusted intranet, with
-some considerations:
-
-Limiting CPU usage
-------------------
-
-OCRmyPDF will attempt to use all available CPUs and storage, so
-executing ``nice ocrmypdf`` or limiting the number of jobs with the
-``-j`` argument may ensure the server remains available. Another option
-would be to run OCRmyPDF jobs inside a Docker container, a virtual machine,
-or a cloud instance, which can impose its own limits on CPU usage and be
-terminated "from orbit" if it fails to complete.
-
-Temporary storage requirements
-------------------------------
-
-OCRmyPDF will use a large amount of temporary storage for its work,
-proportional to the total number of pixels needed to rasterize the PDF.
-The raster image of a 8.5×11" color page at 300 DPI takes 25 MB
-uncompressed; OCRmyPDF saves its intermediates as PNG, but that still
-means it requires about 9 MB per intermediate based on average
-compression ratios. Multiple intermediates per page are also required,
-depending on the command line given. A rule of thumb would be to allow
-100 MB of temporary storage per page in a file – meaning that a small
-cloud servers or small VM partitions should be provisioned with plenty
-of extra space, if say, a 500 page file might be sent.
-
-To check temporary storage usage on actual files, run
-``ocrmypdf -k ...`` which will preserve and print the path to temporary
-storage when the job is done.
-
-To change where temporary files are stored, change the ``TMPDIR``
-environment variable for ocrmypdf's environment. (Python's
-``tempfile.gettempdir()`` returns the root directory in which temporary
-files will be stored.) For example, one could redirect ``TMPDIR`` to a
-large RAM disk to avoid wear on HDD/SSD and potentially improve
-performance. On Amazon Web Services, ``TMPDIR`` can be set to `empheral
-storage <https://docs.aws.amazon.com/AWSEC2/latest/UserGuide/InstanceStorage.html>`__.
-
-Timeouts
---------
-
-To prevent excessively long OCR jobs consider setting
-``--tesseract-timeout`` and/or ``--skip-big`` arguments. ``--skip-big``
-is particularly helpful if your PDFs include documents such as reports
-on standard page sizes with large images attached - often large images
-are not worth OCR'ing anyway.
-
-Commercial alternatives
------------------------
-
-The author also provides professional services that include OCR and
-building databases around PDFs, and is happy to provide consultation.
-
-Abbyy Cloud OCR is viable commercial alternative with a web services
-API. Amazon Textract, Google Cloud Vision, and Microsoft Azure 
-Computer Vision provide advanced OCR but have less PDF rendering capability.
-
-Password protection, digital signatures and certification
-=========================================================
+Password protected PDFs
+=======================
 
 Password protected PDFs usually have two passwords, and owner and user
 password. When the user password is set to empty, PDF readers will open
-the file automatically and marked it as "(SECURED)". While not as
-reliable as a digital signature, this indicates that whoever set the
-password approved of the file at that time. When the user password is
-set, the document cannot be viewed without the password.
+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.
 
-Either way, OCRmyPDF does not remove passwords from PDFs and exits with
-an error on encountering them.
+OCRmyPDF cannot remove passwords from PDFs. If you want to remove a
+password from a PDF, you must use other software, such as ``qpdf``.
 
-``qpdf`` can remove passwords. If the owner and user password are set, a
+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.
+password can be stripped, even if one does not have the owner password. To
+remove the password from a using QPDF, use:
 
-After OCR is applied, password protection is not permitted on PDF/A
-documents but the file can be converted to regular PDF.
+.. 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. OCRmyPDF cannot do this. Open source tools such as
-pdfbox (Java) have this capability as does Adobe Acrobat.
+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

@@ -1,3 +1,7 @@
+.. SPDX-FileCopyrightText: 2022 James R. Barlow
+..
+.. SPDX-License-Identifier: CC-BY-SA-4.0
+
 ===========
 Performance
 ===========

docs/plugins.rst

@@ -1,3 +1,7 @@
+.. SPDX-FileCopyrightText: 2022 James R. Barlow
+..
+.. SPDX-License-Identifier: CC-BY-SA-4.0
+
 =======
 Plugins
 =======
@@ -72,20 +76,16 @@ Setuptools plugins
 You can also create a plugin that OCRmyPDF will always automatically load if both are
 installed in the same virtual environment, using a setuptools entrypoint.
 
-Your package's ``setup.py`` would need to contain the following, for a plugin
+Your package's ``pyproject.toml`` would need to contain the following, for a plugin
 named ``ocrmypdf-exampleplugin``:
 
-.. code-block:: python
+.. code-block:: toml
 
-    # sample ./setup.py file
-    from setuptools import setup
+    [project]
+    name = "ocrmypdf-exampleplugin"
 
-    setup(
-        name="ocrmypdf-exampleplugin",
-        packages=["exampleplugin"],
-        # the following makes a plugin available to pytest
-        entry_points={"ocrmypdf": ["exampleplugin = exampleplugin.pluginmodule"]},
-    )
+    [project.entry-points."ocrmypdf"]
+    exampleplugin = "exampleplugin.pluginmodule"
 
 .. code-block:: ini
 
@@ -152,6 +152,21 @@ 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
 -----------------------------
 
@@ -162,7 +177,7 @@ Custom command line arguments
 Execution and progress reporting
 --------------------------------
 
-.. autoclass: ocrmypdf.pluginspec.Executor
+.. autoclass:: ocrmypdf.pluginspec.Executor
     :members:
 
 .. autofunction:: ocrmypdf.pluginspec.get_logging_console
@@ -206,3 +221,10 @@ PDF/A production
 ----------------
 
 .. autofunction:: ocrmypdf.pluginspec.generate_pdfa
+
+PDF optimization
+----------------
+
+.. autofunction:: ocrmypdf.pluginspec.optimize_pdf
+
+.. autofunction:: ocrmypdf.pluginspec.is_optimization_enabled

docs/release_notes.rst

@@ -1,3 +1,7 @@
+.. SPDX-FileCopyrightText: 2022 James R. Barlow
+..
+.. SPDX-License-Identifier: CC-BY-SA-4.0
+
 =============
 Release notes
 =============
@@ -12,11 +16,266 @@ may be unreliable. Use the API to depend on precise behavior.
 The public API may be useful in scripts that launch OCRmyPDF processes or that
 wish to use some of its features for working with PDFs.
 
+The most recent release of OCRmyPDF is |OCRmyPDF PyPI|. Any newer versions
+referred to in these notes may exist the main branch but have not been
+tagged yet.
+
 .. note::
 
-   Python 3.6 reaches end of life on December 23, 2021. We have already ended support
-   for Python 3.6 but might release fixes for critical issues if necessary before that
-   date.
+   Attention maintainers: these release notes may be updated with information
+   about a forthcoming release that has not been tagged yet. A release is only
+   official when it's tagged and posted to PyPI.
+
+.. |OCRmyPDF PyPI| image:: https://img.shields.io/pypi/v/ocrmypdf.svg
+
+v15.0.0
+=======
+
+-  Dropped support for Python 3.8.
+-  Dropped support many older dependencies - see ``pyproject.toml`` for details.
+   Generally speaking, Ubuntu 22.04 is our baseline system.
+-  Dropped support 32-bit Windows and Linux. You must use a 64-bit operating system,
+   and 64-bit versions of Python, Tesseract and Ghostscript to use OCRmyPDF. Many of
+   our dependencies are dropping 32-bit support (e.g. Pillow), and we are following
+   suit.
+-  Changed to trusted release for PyPI publishing.
+-  pikepdf memory mapping is enabled again for improved performance, now an issue
+   with pikepdf has been fixed.
+-  ``ocrmypdf.helpers.calculate_downsample`` previously had two variants, one
+   that took a ``PIL.Image`` and one that took a ``tuple[int, int]``. The latter
+   was removed.
+-  The snap version of ocrmypdf is now based on Ubuntu core22.
+-  We now account situations where a small portion of an image on a page reports a
+   high DPI (resolution). Previously, the entire page would be rasterized at the
+   highest resolution, which caused performance problems. Now, the page is rasterized
+   at a resolution based on the average DPI of the page, weighted by the area that
+   each feature occupies. Typically, small areas of high resolution in PDFs are
+   errors or quirks from the repeated use of assets and high resolution is not
+   beneficial. :issue:`1010,1104,1004,1079,1010`
+-  Ghostscript color conversion strategy is now configurable. :issue:`1143`
+
+v14.4.0
+=======
+
+-  Digitally signed PDFs are now detected. If the PDF is signed, OCRmyPDF will
+   refuse to modify it. Previously, only encrypted PDFs were detected, not
+   those that were signed but not encrypted. :issue:`1040`
+-  In addition, ``--invalidate-digital-signatures`` can be used to override the
+   above behavior and modify the PDF anyway. :issue:`1040`
+-  tqdm progress bars replaced with "rich" progress bars. The rich library is
+   a new dependency. Certain APIs that used tqdm are now deprecated and will
+   be removed in the next major release.
+-  Improved integration with GitHub Releases. Thanks to @stumpylog.
+
+v14.3.0
+=======
+
+-  Renamed master branch to main.
+-  Improve PDF rasterization accuracy by using the ``-dPDFSTOPONERROR`` option
+   to Ghostscript. Use ``--continue-on-soft-render-error`` if you want to render
+   the PDF anyway. The plugin specification was adjusted to support this feature;
+   plugin authors may want to adapt PDF rasterizing and rendering
+   plugins. :issue:`1083`
+-  The calculated deskew angle is now recorded in the logged output. :issue:`1101`
+-  Metadata can now be unset by setting a metadata type such as ``--title`` to an
+   empty string. :issue:`1117,1059`
+-  Fixed random order of languages due to use of a set. This may have caused output
+   to vary when multiple languages were set for OCR. :issue:`1113`
+-  Clarified the optimization ratio reported in the log output.
+-  Documentation improvements.
+
+v14.2.1
+=======
+
+-  Fixed :issue:`977`, where images inside Form XObjects were always excluded
+   from image optimization.
+
+v14.2.0
+=======
+
+-  Added ``--tesseract-downsample-above`` to downsample larger images even when
+   they do not exceed Tesseract's internal limits. This can be used to speed
+   up OCR, possibly sacrificing accuracy.
+-  Fixed resampling AttributeError on older Pillow. :issue:`1096`
+-  Removed an error about using Ghostscript on PDFs with that have the /UserUnit
+   feature in use. Previously, Ghostscript would fail to process these PDFs,
+   but in all supported versions it is now supported, so the error is no longer
+   needed.
+-  Improved documentation around installing other language packs for Tesseract.
+
+v14.1.0
+=======
+
+-  Added ``--tesseract-non-ocr-timeout``. This allows using Tesseract's deskew
+   and other non-OCR features while disabling OCR using ``--tesseract-timeout 0``.
+-  Added ``--tesseract-downsample-large-images``. This downsamples larges images
+   that exceed the maximum image size Tesseract can handle. Large images may still
+   take a long time to process, but this allows them to be processed if that
+   is desired.
+-  Fixed :issue:`1082`, an issue with snap packaged building.
+-  Change linter to ruff, fix lint errors, update documentation.
+
+v14.0.4
+=======
+
+-  Fixed :issue:`1066, 1075`, an exception when processing certain malformed PDFs.
+
+v14.0.3
+=======
+
+-  Fixed :issue:`1068`, avoid deleting /dev/null when running as root.
+-  Other documentation fixes.
+
+v14.0.2
+=======
+
+-  Fixed :issue:`1052`, an exception on attempting to process certain nonconforming PDFs.
+-  Explicitly documented that Windows 32-bit is no longer supported.
+-  Fixed source installation instructions.
+-  Other documentation fixes.
+
+v14.0.1
+=======
+
+-  Fixed some version checks done with smart version comparison.
+-  Added missing jbig2dec to Docker image.
+
+v14.0.0
+=======
+
+-  Dropped support for Python 3.7.
+-  Dropped support generally speaking, all dependencies older than what Ubuntu 20.04
+   provides.
+-  Ghostscript 9.50 or newer is now required. Shims to support old versions were
+   removed.
+-  Tesseract 4.1.1 or newer is now required. Shims to support old versions were
+   removed.
+-  Docker image now uses Tesseract 5.
+-  Dropped setup.cfg configuration for pyproject.toml.
+-  Removed deprecation exception PdfMergeFailedError.
+-  A few more public domain test files were removed or replaced. We are aiming for
+   100% compliance with SPDX and generally towards simplifying copyright.
+
+v13.7.0
+=======
+
+-  Fixed an exception when attempting to run and Tesseract is not installed.
+-  Changed to SPDX license tracking and information files.
+
+v13.6.2
+=======
+
+-  Added a shim to prevent an "error during error handling" for Python 3.7 and 3.8.
+-  Modernized some type annotations.
+-  Improved annotations on our _windows module to help IDEs and mypy figure out what
+   we're doing.
+
+v13.6.1
+=======
+
+-  Require setuptools-scm 7.0.5 to avoid possible issues with source distributions in
+   earlier versions of setuptools-scm.
+-  Suppress a spurious warning, improve tests, improve typing and other miscellany.
+
+v13.6.0
+=======
+
+-  Added a new ``initialize`` plugin hook, making it possible to suppress built-in
+   plugins more easily, among other possibilities.
+-  Fixed an issue where unpaper would exit with a "wrong stream" error, probably
+   related to images with an odd integer width. :issue:`887, 665`
+
+v13.5.0
+=======
+
+-  Added a new ``optimize_pdf`` plugin hook, making it possible to create plugins that
+   replace or enhance OCRmyPDF's PDF optimizer.
+-  Removed all max version restrictions. Our new policy is to blacklist known-bad releases
+   and only block known-bad versions of dependencies.
+-  The naming schema for object that holds all OCR text that OCRmyPDF inserts has
+   changed. This has always been an implementation detail (and remains so), but possibly,
+   someone was relying on it and would appreciate the heads-up.
+-  Cleanup.
+
+v13.4.7
+=======
+
+-  Fixed PermissionError when cleaning up temporary files in rare cases. :issue:`974`
+-  Fixed PermissionError when calling ``os.nice`` on platforms that lack it. :issue:`973`
+-  Suppressed some warnings from libxmp during tests.
+
+v13.4.6
+=======
+
+-  Convert error on corrupt ICC profiles into a warning. Thanks to @oscherler.
+
+v13.4.5
+=======
+
+-  Remove upper bound on pdfminer.six version.
+-  Documentation.
+
+v13.4.4
+=======
+
+-  Updated pdfminer.six version.
+-  Docker image changed to Ubuntu 22.04 now that it is released and provides the
+   dependencies we need. This seems more consistent than our recent change to
+   Debian.
+
+v13.4.3
+=======
+
+-  Fix error on pytest.skip() with older versions of pytest.
+-  Documentation updates.
+
+v13.4.2
+=======
+
+-  Worked around a
+   `major regression in Ghostscript 9.56.0 <https://bugs.ghostscript.com/show_bug.cgi?id=705187>`__
+   where **all OCR text is stripped out of the PDF**. It simply removes all text,
+   even generated by software other than OCRmyPDF. Fortunately, we can ask
+   Ghostscript 9.56.0 to use its old behavior that worked correctly for our purposes.
+   Users must avoid the combination (Ghostscript 9.56.0, ocrmypdf <13.4.2) since
+   older versions of OCRmyPDF have no way of detecting that this particular
+   version of Ghostscript removes all OCR text.
+-  Marked pdfminer 20220319 as supported.
+-  Fixed some deprecation warnings from recent versions of Pillow and pytest.
+-  Test suite now covers Python 3.10 (Python 3.10 worked fine before, but was not
+   being tested).
+-  Docker image now uses debian:bookworm-slim as the base image to fix the Docker
+   image build.
+
+v13.4.1
+=======
+
+-  Temporarily make threads rather than processes the default executor worker, due
+   to a persistent deadlock issue when processes are used. Add a new command line
+   argument ``--no-use-threads`` to disable this.
+
+v13.4.0
+=======
+
+-  Fixed test failures when using pikepdf 5.0.0.
+-  Various improvements to the optimizer. In particular, we now recognize PDF images
+   that are encoded with both deflate (PNG) and DCT (JPEG), and also produce PDF
+   with images compressed with deflate and DCT, since this often yields file size
+   improvements compared to plain DCT.
+
+v13.3.0
+=======
+
+-  Made a harmless but "scary" exception after failing to optimize an image less scary.
+-  Added a warning if a page image is too large for unpaper to clean. The image is
+   passed through without cleaning. This is due to a hard-coded limitation in a
+   C library used by unpaper so it cannot be rectified easily.
+-  We now use better default settings when calling img2pdf.
+-  We no longer try to optimize images that we failed to save in certain situations.
+-  We now account for some differences in text output from Tesseract 5 compared to
+   Tesseract 4.
+-  Better handling of Ghostscript producing empty images when attempting to rasterize
+   page images.
 
 v13.2.0
 =======
@@ -65,7 +324,7 @@ v13.0.0
    Tesseract 5.x has implemented improvements to thresholding, so this feature will be
    redundant anyway.
 -  ``--deskew`` was previous calculated by a Leptonica algorithm. We now use a feature
-   of Tesseract to term the appropriate the angle to deskew a page. The deskew angle
+   of Tesseract to find the appropriate the angle to deskew a page. The deskew angle
    according to Tesseract may differ from Leptonica's algorithm. At least in theory,
    Tesseract's deskew angle is informed by a more complex analysis than Leptonica,
    so this should improve results in general. We also use Pillow to perform the
@@ -550,7 +809,7 @@ v10.3.2
 v10.3.1
 =======
 
--  Fixed a number of test suite failures with pdfminer.six older than veresion 20200402.
+-  Fixed a number of test suite failures with pdfminer.six older than version 20200402.
 -  Enabled support for pdfminer.six 20200720.
 
 v10.3.0

misc/batch.py

@@ -1,28 +1,19 @@
 #!/usr/bin/env python3
-# Copyright 2016 findingorder: https://github.com/findingorder
-#
-# Permission is hereby granted, free of charge, to any person obtaining a copy
-# of this software and associated documentation files (the "Software"), to deal
-# in the Software without restriction, including without limitation the rights
-# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
-# copies of the Software, and to permit persons to whom the Software is
-# furnished to do so, subject to the following conditions:
-#
-# The above copyright notice and this permission notice shall be included in all
-# copies or substantial portions of the Software.
-#
-# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
-# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
-# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
-# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
-# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
-# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
-# SOFTWARE.
+# SPDX-FileCopyrightText: 2016 findingorder <https://github.com/findingorder>
+# SPDX-License-Identifier: MIT
 
-# This script must be edited to meet your needs.
+"""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 os
 import sys
 from pathlib import Path
 

misc/completion/ocrmypdf.bash

@@ -1,76 +1,61 @@
-# ocrmypdf completion                                     -*- shell-script -*-
-
-# Copyright 2019, 2021 Frank Pille
-# Copyright 2020 Alex Willner
-#
-# Permission is hereby granted, free of charge, to any person obtaining a copy
-# of this software and associated documentation files (the "Software"), to deal
-# in the Software without restriction, including without limitation the rights
-# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
-# copies of the Software, and to permit persons to whom the Software is
-# furnished to do so, subject to the following conditions:
-#
-# The above copyright notice and this permission notice shall be included in all
-# copies or substantial portions of the Software.
-#
-# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
-# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
-# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
-# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
-# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
-# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
-# SOFTWARE.
+# 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)
---skip-big               (skip OCR on pages larger than this many MPixels)
---optimize               (select optimization level)
---jpeg-quality           (JPEG quality [0..100])
---png-quality            (PNG quality [0..100])
---jbig2-lossy            (enable lossy JBIG2 (see docs))
---pages                  (apply OCR to only the specified pages)
---max-image-mpixels      (image decompression bomb threshold)
---pdf-renderer           (select PDF renderer options)
---rotate-pages-threshold (page rotation confidence)
---pdfa-image-compression (set PDF/A image compression options)
---fast-web-view          (if file size if above this amount in MB linearize PDF)
---plugin                 (name of plugin to import)
---keep-temporary-files   (keep temporary files (debug)
---tesseract-config       (set custom tesseract config file)
---tesseract-pagesegmode  (set tesseract --psm)
---tesseract-oem          (set tesseract --oem)
---tesseract-thresholding (set tesseract image thresholding)
---tesseract-timeout      (maximum number of seconds to wait for OCR)
---user-words             (specify location of user words file)
---user-patterns          (specify location of user patterns file)
---no-progress-bar        (disable the progress bar)
+    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") )
@@ -210,6 +195,20 @@ sauvola       (use Sauvola thresholding)"
     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()
 {
@@ -269,6 +268,10 @@ __ocrmypdf_check_previous()
             _filedir
             return 0
             ;;
+        --color-conversion-strategy)
+            __ocrmypdf_color-conversion-strategy
+            return 0
+            ;;
     esac
 
     return 1

misc/completion/ocrmypdf.fish

@@ -1,25 +1,8 @@
-# Copyright 2020 James R. Barlow
-#
-# Permission is hereby granted, free of charge, to any person obtaining a copy
-# of this software and associated documentation files (the "Software"), to deal
-# in the Software without restriction, including without limitation the rights
-# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
-# copies of the Software, and to permit persons to whom the Software is
-# furnished to do so, subject to the following conditions:
-#
-# The above copyright notice and this permission notice shall be included in all
-# copies or substantial portions of the Software.
-#
-# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
-# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
-# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
-# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
-# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
-# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
-# SOFTWARE.
+# 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 -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
@@ -31,8 +14,9 @@ complete -c ocrmypdf -s i -l clean-final -d "clean document images and keep resu
 complete -c ocrmypdf -l remove-vectors -d "don't send vector objects to OCR"
 
 complete -c ocrmypdf -s f -l force-ocr -d "OCR documents that already have printable text"
-complete -c ocrmypdf -s s -l skip-ocr -d "skip OCR on pages that text, otherwise try OCR"
+complete -c ocrmypdf -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)"
 
@@ -43,7 +27,7 @@ function __fish_ocrmypdf_languages
         echo $lang
     end
 end
-complete -c ocrmypdf -x -s l -l language -a '(__fish_ocrmypdf_languages)' -d "language"
+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"
 
@@ -100,6 +84,7 @@ complete -c ocrmypdf -x -l skip-big -d "skip OCR on pages larger than this many
 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"
@@ -145,4 +130,27 @@ complete -c ocrmypdf -r -l user-words -d "specify location of user words file"
 complete -c ocrmypdf -r -l user-patterns -d "specify location of user patterns file"
 complete -c ocrmypdf -x -l fast-web-view -d "if file size if above this amount in MB, linearize PDF"
 
-complete -c ocrmypdf -x -a "(__fish_complete_suffix .pdf; __fish_complete_suffix .PDF; __fish_complete_suffix .jpg; __fish_complete_suffix .png)"
+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

@@ -1,3 +1,5 @@
+# SPDX-FileCopyrightText: 2022 James R. Barlow
+# SPDX-License-Identifier: MIT
 ---
 version: "3.3"
 services:

misc/example_plugin.py

@@ -1,25 +1,7 @@
-# © 2020 James R Barlow: https://github.com/jbarlow83
-#
-# Permission is hereby granted, free of charge, to any person obtaining a copy
-# of this software and associated documentation files (the "Software"), to deal
-# in the Software without restriction, including without limitation the rights
-# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
-# copies of the Software, and to permit persons to whom the Software is
-# furnished to do so, subject to the following conditions:
-#
-# The above copyright notice and this permission notice shall be included in all
-# copies or substantial portions of the Software.
-#
-# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
-# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
-# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
-# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
-# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
-# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
-# SOFTWARE.
+# SPDX-FileCopyrightText: 2022 James R Barlow: https://github.com/jbarlow83
+# SPDX-License-Identifier: MIT
 
-"""
-An example of an OCRmyPDF plugin.
+"""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
@@ -37,6 +19,8 @@ To use this as an API:
     )
 """
 
+from __future__ import annotations
+
 import logging
 
 from PIL import Image

misc/screencast/README.md

@@ -0,0 +1,31 @@
+<!-- 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

@@ -0,0 +1,65 @@
+{"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

@@ -1,26 +1,12 @@
 #!/bin/env python3
-# Copyright 2017 github.com/Enantiomerie
-#
-# Permission is hereby granted, free of charge, to any person obtaining a copy
-# of this software and associated documentation files (the "Software"), to deal
-# in the Software without restriction, including without limitation the rights
-# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
-# copies of the Software, and to permit persons to whom the Software is
-# furnished to do so, subject to the following conditions:
-#
-# The above copyright notice and this permission notice shall be included in all
-# copies or substantial portions of the Software.
-#
-# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
-# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
-# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
-# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
-# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
-# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
-# SOFTWARE.
+# 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
@@ -41,10 +27,7 @@ logging.basicConfig(
     filemode='w',
 )
 
-if len(sys.argv) > 1:
-    start_dir = sys.argv[1]
-else:
-    start_dir = '.'
+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)

misc/watcher.py

@@ -1,28 +1,16 @@
 #!/usr/bin/env python3
-# Copyright (C) 2019 Ian Alexander: https://github.com/ianalexander
-# Copyright (C) 2020 James R Barlow: https://github.com/jbarlow83
-#
-# Permission is hereby granted, free of charge, to any person obtaining a copy
-# of this software and associated documentation files (the "Software"), to deal
-# in the Software without restriction, including without limitation the rights
-# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
-# copies of the Software, and to permit persons to whom the Software is
-# furnished to do so, subject to the following conditions:
-#
-# The above copyright notice and this permission notice shall be included in all
-# copies or substantial portions of the Software.
-#
-# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
-# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
-# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
-# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
-# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
-# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
-# SOFTWARE.
+# 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."""
+
+from __future__ import annotations
 
 import json
 import logging
 import os
+import shutil
 import sys
 import time
 from datetime import datetime
@@ -44,12 +32,15 @@ def getenv_bool(name: str, default: str = 'False'):
 
 INPUT_DIRECTORY = os.getenv('OCR_INPUT_DIRECTORY', '/input')
 OUTPUT_DIRECTORY = os.getenv('OCR_OUTPUT_DIRECTORY', '/output')
+ARCHIVE_DIRECTORY = os.getenv('OCR_ARCHIVE_DIRECTORY', '/processed')
 OUTPUT_DIRECTORY_YEAR_MONTH = getenv_bool('OCR_OUTPUT_DIRECTORY_YEAR_MONTH')
 ON_SUCCESS_DELETE = getenv_bool('OCR_ON_SUCCESS_DELETE')
+ON_SUCCESS_ARCHIVE = getenv_bool('OCR_ON_SUCCESS_ARCHIVE')
 DESKEW = getenv_bool('OCR_DESKEW')
 OCR_JSON_SETTINGS = json.loads(os.getenv('OCR_JSON_SETTINGS', '{}'))
 POLL_NEW_FILE_SECONDS = int(os.getenv('OCR_POLL_NEW_FILE_SECONDS', '1'))
 USE_POLLING = getenv_bool('OCR_USE_POLLING')
+RETRIES_LOADING_FILE = int(os.getenv('OCR_RETRIES_LOADING_FILE', '5'))
 LOGLEVEL = os.getenv('OCR_LOGLEVEL', 'INFO')
 PATTERNS = ['*.pdf', '*.PDF']
 
@@ -76,7 +67,7 @@ def wait_for_file_ready(file_path):
     # watchdog event before the file is actually fully on disk, causing
     # pikepdf to fail.
 
-    retries = 5
+    retries = RETRIES_LOADING_FILE
     while retries:
         try:
             pdf = pikepdf.open(file_path)
@@ -108,9 +99,15 @@ def execute_ocrmypdf(file_path):
         deskew=DESKEW,
         **OCR_JSON_SETTINGS,
     )
-    if exit_code == 0 and ON_SUCCESS_DELETE:
-        log.info(f'OCR is done. Deleting: {file_path}')
-        file_path.unlink()
+    if exit_code == 0:
+        if ON_SUCCESS_DELETE:
+            log.info(f'OCR is done. Deleting: {file_path}')
+            file_path.unlink()
+        elif ON_SUCCESS_ARCHIVE:
+            log.info(f'OCR is done. Archiving {file_path.name} to {ARCHIVE_DIRECTORY}')
+            shutil.move(file_path, f'{ARCHIVE_DIRECTORY}/{file_path.name}')
+        else:
+            log.info('OCR is done')
     else:
         log.info('OCR is done')
 
@@ -135,16 +132,20 @@ def main():
         f"Starting OCRmyPDF watcher with config:\n"
         f"Input Directory: {INPUT_DIRECTORY}\n"
         f"Output Directory: {OUTPUT_DIRECTORY}\n"
-        f"Output Directory Year & Month: {OUTPUT_DIRECTORY_YEAR_MONTH}"
+        f"Output Directory Year & Month: {OUTPUT_DIRECTORY_YEAR_MONTH}\n"
+        f"Archive Directory: {ARCHIVE_DIRECTORY}"
     )
     log.debug(
         f"INPUT_DIRECTORY: {INPUT_DIRECTORY}\n"
         f"OUTPUT_DIRECTORY: {OUTPUT_DIRECTORY}\n"
         f"OUTPUT_DIRECTORY_YEAR_MONTH: {OUTPUT_DIRECTORY_YEAR_MONTH}\n"
+        f"ARCHIVE_DIRECTORY: {ARCHIVE_DIRECTORY}\n"
         f"ON_SUCCESS_DELETE: {ON_SUCCESS_DELETE}\n"
+        f"ON_SUCCESS_ARCHIVE: {ON_SUCCESS_ARCHIVE}\n"
         f"DESKEW: {DESKEW}\n"
         f"ARGS: {OCR_JSON_SETTINGS}\n"
         f"POLL_NEW_FILE_SECONDS: {POLL_NEW_FILE_SECONDS}\n"
+        f"RETRIES_LOADING_FILE: {RETRIES_LOADING_FILE}\n"
         f"USE_POLLING: {USE_POLLING}\n"
         f"LOGLEVEL: {LOGLEVEL}"
     )

misc/webservice.py

@@ -1,21 +1,8 @@
 #!/usr/bin/env python3
-# webservice.py wrapper for OCRmyPDF
-# Copyright (C) 2019 James R. Barlow: github.com/jbarlow83
-#
-# This program is free software: you can redistribute it and/or modify
-# it under the terms of the GNU Affero General Public License as published by
-# the Free Software Foundation, either version 3 of the License, or
-# (at your option) any later version.
-#
-# This program is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# GNU Affero General Public License for more details.
-#
-# You should have received a copy of the GNU Affero General Public License
-# along with this program.  If not, see <https://www.gnu.org/licenses/>.
+# 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 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
@@ -24,9 +11,11 @@ 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 PIPE, run
+from subprocess import run
 from tempfile import TemporaryDirectory
 
 from flask import Flask, Response, request, send_from_directory
@@ -59,7 +48,7 @@ def do_ocrmypdf(file):
         return Response("--sidecar not supported", 501, mimetype='text/plain')
 
     ocrmypdf_args = ["ocrmypdf", *cmd_args, up_file, down_file]
-    proc = run(ocrmypdf_args, stdout=PIPE, stderr=PIPE, encoding="utf-8")
+    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')

pyproject.toml

@@ -1,18 +1,87 @@
+# SPDX-FileCopyrightText: 2022 James R. Barlow
+# SPDX-License-Identifier: MPL-2.0
 [build-system]
-requires = [
-  "setuptools >= 30.3.0",
-  "wheel",
-  "setuptools_scm[toml] >= 3.4",
-  "setuptools_scm_git_archive"
-]
+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 = ">=3.9"
+dependencies = [
+  "Pillow>=9.0.1",
+  "deprecation>=2.1.0",
+  "img2pdf>=0.4.4",
+  "packaging>=20",
+  "pdfminer.six>=20220319",
+  "pikepdf>=8",
+  "pluggy>=0.13.0",
+  "reportlab>=3.6.8",
+  "rich>=13",
+  "typing-extensions>=4;python_version<'3.10'",
+]
+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
+  "types-Pillow",
+  "types-humanfriendly",
+]
+watcher = ["watchdog>=1.0.2"]
+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]
-version_scheme = "post-release"
+
+[tool.distutils.bdist_wheel]
+python-tag = "py38"
 
 [tool.black]
 line-length = 88
-target-version = ["py37", "py38"]
+target-version = ["py38", "py39", "py310", "py311"]
 skip-string-normalization = true
 include = '\.pyi?$'
 exclude = '''
@@ -53,28 +122,7 @@ exclude_lines = [
   "if 0:",
   "if False:",
   "if __name__ == .__main__.:",
-  "if TYPE_CHECKING:"
-]
-
-[tool.isort]
-profile = "black"
-known_first_party = "ocrmypdf"
-known_third_party = [
-  "PIL",
-  "flask",
-  "img2pdf",
-  "ocrmypdf",
-  "pdfminer",
-  "pikepdf",
-  "pkg_resources",
-  "pluggy",
-  "pytest",
-  "reportlab",
-  "setuptools",
-  "sphinx_rtd_theme",
-  "tqdm",
-  "watchdog",
-  "werkzeug"
+  "if TYPE_CHECKING:",
 ]
 
 [tool.pytest.ini_options]
@@ -96,6 +144,30 @@ module = [
   'pdfminer.*',
   'reportlab.*',
   'fitz',
-  'libxmp.utils'
+  'libxmp.utils',
 ]
 ignore_missing_imports = true
+
+[tool.ruff]
+select = [
+  "D",    # pydocstyle
+  "E",    # pycodestyle
+  "W",    # pycodestyle
+  "F",    # pyflakes
+  "I001", # isort
+  "UP",   # pyupgrade
+]
+target-version = "py38"
+
+[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"]

setup.cfg

@@ -1,113 +0,0 @@
-[metadata]
-name = ocrmypdf
-description = OCRmyPDF adds an OCR text layer to scanned PDF files, allowing them to be searched
-long_description = file: README.md
-long_description_content_type = text/markdown
-url = https://github.com/jbarlow83/OCRmyPDF
-author = James R. Barlow
-author_email = james@purplerock.ca
-license = MPL-2.0
-license_file = LICENSE
-license_files =
-    LICENSE
-classifiers =
-    Development Status :: 5 - Production/Stable
-    Environment :: Console
-    Intended Audience :: End Users/Desktop
-    Intended Audience :: Science/Research
-    Intended Audience :: System Administrators
-    License :: OSI Approved :: Mozilla Public License 2.0 (MPL 2.0)
-    Operating System :: MacOS :: MacOS X
-    Operating System :: Microsoft :: Windows :: Windows 10
-    Operating System :: POSIX
-    Operating System :: POSIX :: BSD
-    Operating System :: POSIX :: Linux
-    Programming Language :: Python :: 3
-    Programming Language :: Python :: 3 :: Only
-    Programming Language :: Python :: 3.7
-    Programming Language :: Python :: 3.8
-    Programming Language :: Python :: 3.9
-    Programming Language :: Python :: 3.10
-    Topic :: Scientific/Engineering :: Image Recognition
-    Topic :: Text Processing :: Indexing
-    Topic :: Text Processing :: Linguistic
-keywords =
-    PDF
-    OCR
-    optical character recognition
-    PDF/A
-    scanning
-project_urls =
-    Documentation = https://ocrmypdf.readthedocs.io/
-    Source = https://github.com/jbarlow83/ocrmypdf
-    Tracker = https://github.com/jbarlow83/ocrmypdf/issues
-
-[options]
-packages = find:
-install_requires =
-    Pillow>=8.2.0
-    coloredlogs>=14.0  # strictly optional
-    img2pdf>=0.3.0,<0.5  # pure Python
-    packaging>=20
-    pdfminer.six!=20200720,>=20191110,<=20211012
-    pikepdf>=4.0.0
-    pluggy>=0.13.0,<2
-    reportlab>=3.5.66
-    tqdm>=4
-    importlib-metadata>=4;python_version<'3.8'  # until Python 3.8
-    importlib-resources>=5;python_version<'3.9'  # until Python 3.9
-python_requires = >=3.7
-include_package_data = True
-package_dir =
-    =src
-platforms = any
-setup_requires =
-    setuptools-scm
-    setuptools-scm-git-archive
-zip_safe = False
-
-[options.packages.find]
-where = src
-
-[options.entry_points]
-console_scripts =
-    ocrmypdf = ocrmypdf.__main__:run
-
-[options.extras_require]
-docs =
-    sphinx
-    sphinx-issues
-    sphinx-rtd-theme
-extended_test =
-    PyMuPDF==1.19.1
-test =
-    coverage[toml]>=5
-    pytest>=6.0.0
-    pytest-cov>=2.11.1
-    pytest-xdist>=2.2.0
-    python-xmp-toolkit==2.0.1  # also requires apt-get install libexempi3
-watcher =
-    watchdog>=1.0.2,<3
-webservice =
-    Flask>=1,<3
-
-[options.package_data]
-ocrmypdf =
-    data/sRGB.icc
-    py.typed
-
-[bdist_wheel]
-python-tag = py37
-
-[aliases]
-test = pytest
-
-[check-manifest]
-ignore =
-    .github
-
-[flake8]
-ignore = D203,F401,W503,E501,E203,F841
-exclude = .git,__pycache__,docs/conf.py,build,dist,.venv,.venvpp,.eggs,tmp,src/ocrmypdf/lib/
-max-complexity = 10
-max-line-length = 100

setup.py

@@ -1,17 +0,0 @@
-# © 2021 James R. Barlow: github.com/jbarlow83
-#
-# This Source Code Form is subject to the terms of the Mozilla Public
-# License, v. 2.0. If a copy of the MPL was not distributed with this
-# file, You can obtain one at http://mozilla.org/MPL/2.0/.
-
-
-from setuptools import setup
-
-# Minimal setup to support older setuptools/setuptools_scm
-setup(
-    setup_requires=[  # can be removed whenever we can drop pip 9 support
-        'setuptools_scm',  # so that version will work
-        'setuptools_scm_git_archive',  # enable version from github tarballs
-    ],
-    use_scm_version={'version_scheme': 'post-release'},
-)

snapcraft.yaml

@@ -0,0 +1,94 @@
+# 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

@@ -1,3 +1,6 @@
+<!-- SPDX-FileCopyrightText: 2022 James R. Barlow -->
+<!-- SPDX-License-Identifier: CC-BY-SA-4.0 -->
+
 # Release checklist
 
 ## Patch release
@@ -14,11 +17,11 @@
 
 - Check README.md
 
-- Check setup.py
+- Check pyproject.toml
 
     - Are classifiers up to date?
     - Is `python_requires` correct?
-    - Python 3.6 is EOL on December 2021-12. Could drop support then.
+    - Is it to drop support for older Pythons?
     - Can we tighten any `install_requires` dependencies?
 
 - Search for old version shims we can remove

src/ocrmypdf/__init__.py

@@ -1,9 +1,9 @@
-# © 2017 James R. Barlow: github.com/jbarlow83
-#
-# This Source Code Form is subject to the terms of the Mozilla Public
-# License, v. 2.0. If a copy of the MPL was not distributed with this
-# file, You can obtain one at http://mozilla.org/MPL/2.0/.
+# 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
 
@@ -21,7 +21,6 @@ from ocrmypdf.exceptions import (
     InputFileError,
     MissingDependencyError,
     OutputFileAccessError,
-    PdfMergeFailedError,
     PriorOcrFoundError,
     SubprocessOutputError,
     TesseractConfigError,
@@ -30,3 +29,33 @@ from ocrmypdf.exceptions import (
 from ocrmypdf.pluginspec import OcrEngine, OrientationConfidence
 
 hookimpl = _HookimplMarker('ocrmypdf')
+
+__all__ = [
+    '__version__',
+    'BadArgsError',
+    '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

@@ -1,16 +1,16 @@
 #!/usr/bin/env python3
-# © 2015-19 James R. Barlow: github.com/jbarlow83
-#
-# This Source Code Form is subject to the terms of the Mozilla Public
-# License, v. 2.0. If a copy of the MPL was not distributed with this
-# file, You can obtain one at http://mozilla.org/MPL/2.0/.
+# SPDX-FileCopyrightText: 2022 James R. Barlow
+# SPDX-License-Identifier: MPL-2.0
 
+"""ocrmypdf command line entrypoint."""
+
+from __future__ import annotations
 
 import logging
 import os
 import signal
 import sys
-from multiprocessing import set_start_method
+from contextlib import suppress
 
 from ocrmypdf import __version__
 from ocrmypdf._plugin_manager import get_parser_options_plugins
@@ -28,13 +28,19 @@ 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)
 
-    if hasattr(os, 'nice'):
+    with suppress(AttributeError, PermissionError):
         os.nice(5)
 
     verbosity = options.verbose
@@ -62,7 +68,7 @@ def run(args=None):
         log.error(e)
         return ExitCode.missing_dependency
 
-    if hasattr(signal, 'SIGBUS'):
+    with suppress(AttributeError, OSError):
         signal.signal(signal.SIGBUS, sigbus)
 
     result = run_pipeline(options=options, plugin_manager=plugin_manager)
@@ -70,6 +76,4 @@ def run(args=None):
 
 
 if __name__ == '__main__':
-    if sys.platform == 'darwin' and sys.version_info < (3, 8):
-        set_start_method('spawn')  # see python bpo-33725
     sys.exit(run())

src/ocrmypdf/_concurrent.py

@@ -1,12 +1,13 @@
-# © 2020 James R. Barlow: github.com/jbarlow83
-#
-# This Source Code Form is subject to the terms of the Mozilla Public
-# License, v. 2.0. If a copy of the MPL was not distributed with this
-# file, You can obtain one at http://mozilla.org/MPL/2.0/.
+# 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 typing import Callable, Iterable, Optional
+from typing import Callable, Iterable
 
 
 def _task_noop(*_args, **_kwargs):
@@ -14,6 +15,8 @@ def _task_noop(*_args, **_kwargs):
 
 
 class NullProgressBar:
+    """Progress bar API that takes no actions."""
+
     def __init__(self, **kwargs):
         pass
 
@@ -28,6 +31,8 @@ class NullProgressBar:
 
 
 class Executor(ABC):
+    """Abstract concurrent executor."""
+
     pool_lock = threading.Lock()
     pbar_class = NullProgressBar
 
@@ -41,13 +46,12 @@ class Executor(ABC):
         use_threads: bool,
         max_workers: int,
         tqdm_kwargs: dict,
-        worker_initializer: Optional[Callable] = None,
-        task: Optional[Callable] = None,
-        task_arguments: Optional[Iterable] = None,
-        task_finished: Optional[Callable] = None,
+        worker_initializer: Callable | None = None,
+        task: Callable | None = None,
+        task_arguments: Iterable | None = None,
+        task_finished: Callable | None = None,
     ) -> None:
-        """
-        Set up parallel execution and progress reporting.
+        """Set up parallel execution and progress reporting.
 
         Args:
             use_threads: If ``False``, the workload is the sort that will benefit from
@@ -55,7 +59,7 @@ class Executor(ABC):
                 heavily, and parallelizing it with threads is not expected to be
                 performant).
             max_workers: The maximum number of workers that should be run.
-            tdqm_kwargs: Arguments to set up the progress bar.
+            tqdm_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.
@@ -68,7 +72,6 @@ class Executor(ABC):
                 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:

src/ocrmypdf/_exec/__init__.py

@@ -1,8 +1,6 @@
-# © 2020 James R. Barlow: github.com/jbarlow83
-#
-# This Source Code Form is subject to the terms of the Mozilla Public
-# License, v. 2.0. If a copy of the MPL was not distributed with this
-# file, You can obtain one at http://mozilla.org/MPL/2.0/.
+# SPDX-FileCopyrightText: 2022 James R. Barlow
+# SPDX-License-Identifier: MPL-2.0
 
+"""Manage third party executables."""
 
-"""Manage third party executables"""
+from __future__ import annotations

src/ocrmypdf/_exec/ghostscript.py

@@ -1,11 +1,9 @@
-# © 2017 James R. Barlow: github.com/jbarlow83
-#
-# This Source Code Form is subject to the terms of the Mozilla Public
-# License, v. 2.0. If a copy of the MPL was not distributed with this
-# file, You can obtain one at http://mozilla.org/MPL/2.0/.
+# SPDX-FileCopyrightText: 2022 James R. Barlow
+# SPDX-License-Identifier: MPL-2.0
 
+"""Interface to Ghostscript executable."""
 
-"""Interface to Ghostscript executable"""
+from __future__ import annotations
 
 import logging
 import os
@@ -14,64 +12,71 @@ import sys
 from io import BytesIO
 from os import fspath
 from pathlib import Path
-from shutil import which
 from subprocess import PIPE, CalledProcessError
-from typing import Optional
 
-from PIL import Image
+from packaging.version import Version
+from PIL import Image, UnidentifiedImageError
 
-from ocrmypdf.exceptions import MissingDependencyError, SubprocessOutputError
+from ocrmypdf.exceptions import SubprocessOutputError
 from ocrmypdf.helpers import Resolution
 from ocrmypdf.subprocess import get_version, run, run_polling_stderr
 
+# Remove this workaround when we require Pillow >= 10
+try:
+    Transpose = Image.Transpose  # type: ignore
+except AttributeError:
+    # Pillow 9 shim
+    Transpose = Image  # type: ignore
+
+
+COLOR_CONVERSION_STRATEGIES = frozenset(
+    [
+        'CMYK',
+        'Gray',
+        'LeaveColorUnchanged',
+        'RGB',
+        'UseDeviceIndependentColor',
+    ]
+)
+
 log = logging.getLogger(__name__)
 
-missing_gs_error = """
----------------------------------------------------------------------
-This error normally occurs when ocrmypdf find can't Ghostscript.
-Please ensure Ghostscript is installed and its location is added to
-the system PATH environment variable.
 
-For details see:
-    https://ocrmypdf.readthedocs.io/en/latest/installation.html
----------------------------------------------------------------------
-"""
+class DuplicateFilter(logging.Filter):
+    """Filter out duplicate log messages."""
 
-# Most reliable what to get the bitness of Python interpreter, according to Python docs
-_is_64bit = sys.maxsize > 2 ** 32
+    def __init__(self, logger: logging.Logger):
+        self.last: logging.LogRecord | None = None
+        self.count = 0
+        self.logger = logger
 
-_gswin = None
-if os.name == 'nt':
-    if _is_64bit:
-        _gswin = 'gswin64c'
-    else:
-        _gswin = 'gswin32c'
-
-GS = _gswin if _gswin else 'gs'
-del _gswin
+    def filter(self, record):
+        if self.last and record.msg == self.last.msg:
+            self.count += 1
+            return False
+        else:
+            if self.count >= 1:
+                rep_msg = f"(previous message repeated {self.count} times)"
+                self.count = 0  # Avoid infinite recursion
+                self.logger.log(self.last.levelno, rep_msg)
+            self.last = record
+            return True
 
 
-def version():
-    return get_version(GS)
+log.addFilter(DuplicateFilter(log))
 
 
-def jpeg_passthrough_available() -> bool:
-    """Returns True if the installed version of Ghostscript supports JPEG passthru
+# Ghostscript executable - gswin32c is not supported
+GS = 'gswin64c' if os.name == 'nt' else 'gs'
 
-    Prior to 9.23, Ghostscript decoded and re-encoded JPEGs internally. In 9.23
-    it gained the ability to keep JPEGs unmodified. However, the 9.23
-    implementation was buggy and would deletes the last two bytes of images in
-    some cases, as reported here.
-    https://bugs.ghostscript.com/show_bug.cgi?id=699216
 
-    The issue was fixed for 9.24, hence that is the first version we consider
-    the feature available. (Ghostscript 9.24 has its own problems is blacklisted.)
-    """
-    return version() >= '9.24'
+def version() -> Version:
+    return Version(get_version(GS))
 
 
 def _gs_error_reported(stream) -> bool:
-    return True if re.search(r'error', stream, flags=re.IGNORECASE) else False
+    match = re.search(r'error', stream, flags=re.IGNORECASE)
+    return bool(match)
 
 
 def rasterize_pdf(
@@ -81,9 +86,10 @@ def rasterize_pdf(
     raster_device: str,
     raster_dpi: Resolution,
     pageno: int = 1,
-    page_dpi: Optional[Resolution] = None,
-    rotation: Optional[int] = None,
+    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)
@@ -104,10 +110,11 @@ def rasterize_pdf(
             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',
+            '-sstdout=%stderr',  # Literal %s, not string interpolation
             '-dAutoRotatePages=/None',  # Probably has no effect on raster
             '-f',
             fspath(input_file),
@@ -118,29 +125,38 @@ def rasterize_pdf(
         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')
+        raise SubprocessOutputError('Ghostscript rasterizing failed') from e
     else:
         stderr = p.stderr.decode(errors='replace')
         if _gs_error_reported(stderr):
             log.error(stderr)
 
-    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.ROTATE_90)
-            elif rotation == 180:
-                im = im.transpose(Image.ROTATE_180)
-            elif rotation == 270:
-                im = im.transpose(Image.ROTATE_270)
-            if rotation % 180 == 90:
-                page_dpi = page_dpi.flip_axis()
-        im.save(fspath(output_file), dpi=page_dpi)
+    try:
+        with Image.open(BytesIO(p.stdout)) as im:
+            if rotation is not None:
+                log.debug("Rotating output by %i", rotation)
+                # rotation is a clockwise angle and Image.ROTATE_* is
+                # counterclockwise so this cancels out the rotation
+                if rotation == 90:
+                    im = im.transpose(Transpose.ROTATE_90)
+                elif rotation == 180:
+                    im = im.transpose(Transpose.ROTATE_180)
+                elif rotation == 270:
+                    im = im.transpose(Transpose.ROTATE_270)
+                if rotation % 180 == 90:
+                    page_dpi = page_dpi.flip_axis()
+            im.save(fspath(output_file), dpi=page_dpi)
+    except UnidentifiedImageError:
+        log.error(
+            f"Ghostscript (using {raster_device} at {raster_dpi} dpi) produced "
+            "an invalid page image file."
+        )
+        raise
 
 
 class GhostscriptFollower:
+    """Parses the output of Ghostscript and uses it to update the progress bar."""
+
     re_process = re.compile(r"Processing pages \d+ through (\d+).")
     re_page = re.compile(r"Page (\d+)")
 
@@ -161,8 +177,7 @@ class GhostscriptFollower:
                 )
                 return
         else:
-            m = self.re_page.match(line.strip())
-            if m:
+            if self.re_page.match(line.strip()):
                 self.progressbar.update()
 
 
@@ -171,9 +186,11 @@ def generate_pdfa(
     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.
@@ -199,18 +216,15 @@ def generate_pdfa(
             "-dAutoFilterGrayImages=true",
         ]
 
-    strategy = 'LeaveColorUnchanged'
-    # Older versions of Ghostscript expect a leading slash in
-    # sColorConversionStrategy, newer ones should not have it. See Ghostscript
-    # git commit fe1c025d.
-    strategy = ('/' + strategy) if version() < '9.19' else strategy
+    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 version() == '9.23':
-        # 9.23: added JPEG passthrough as a new feature, but with a bug that
-        # incorrectly formats some images. Fixed as of 9.24. So we disable this
-        # feature for 9.23.
-        # https://bugs.ghostscript.com/show_bug.cgi?id=699216
-        compression_args.append('-dPassThroughJPEGImages=false')
+    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:
@@ -221,19 +235,20 @@ def generate_pdfa(
             "-dBATCH",
             "-dNOPAUSE",
             "-dSAFER",
-            "-dCompatibilityLevel=" + str(pdf_version),
+            f"-dCompatibilityLevel={str(pdf_version)}",
             "-sDEVICE=pdfwrite",
             "-dAutoRotatePages=/None",
-            "-sColorConversionStrategy=" + strategy,
+            f"-sColorConversionStrategy={color_conversion_strategy}",
         ]
+        + (['-dPDFSTOPONERROR'] if stop_on_error else [])
         + compression_args
         + [
             "-dJPEGQ=95",
-            "-dPDFA=" + pdfa_part,
+            f"-dPDFA={pdfa_part}",
             "-dPDFACompatibilityPolicy=1",
             "-o",
             "-",
-            "-sstdout=%stderr",
+            "-sstdout=%stderr",  # Literal %s, not string interpolation
         ]
     )
     args_gs.extend(fspath(s) for s in pdf_pages)  # Stringify Path objs
@@ -260,14 +275,9 @@ def generate_pdfa(
         # If there is an error we log the whole stderr, except for filtering
         # duplicates.
         if _gs_error_reported(stderr):
-            last_part = None
-            repcount = 0
+            # 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('****'):
-                if part != last_part:
-                    if repcount > 1:
-                        log.error(f"(previous error message repeated {repcount} times)")
-                        repcount = 0
-                    log.error(part)
-                else:
-                    repcount += 1
-                last_part = part
+                log.error(part)

src/ocrmypdf/_exec/jbig2enc.py

@@ -1,20 +1,20 @@
-# © 2018 James R. Barlow: github.com/jbarlow83
-#
-# This Source Code Form is subject to the terms of the Mozilla Public
-# License, v. 2.0. If a copy of the MPL was not distributed with this
-# file, You can obtain one at http://mozilla.org/MPL/2.0/.
+# SPDX-FileCopyrightText: 2022 James R. Barlow
+# SPDX-License-Identifier: MPL-2.0
 
+"""Interface to jbig2 executable."""
 
-"""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():
-    return get_version('jbig2', regex=r'jbig2enc (\d+(\.\d+)*).*')
+def version() -> Version:
+    return Version(get_version('jbig2', regex=r'jbig2enc (\d+(\.\d+)*).*'))
 
 
 def available():
@@ -25,15 +25,17 @@ def available():
     return True
 
 
-def convert_group(*, cwd, infiles, out_prefix):
+def convert_group(*, cwd, infiles, out_prefix, threshold):
     args = [
         'jbig2',
         '-b',
         out_prefix,
-        '-s',  # symbol mode (lossy)
+        '--symbol-mode',  # symbol mode (lossy)
+        '-t',
+        str(threshold),  # threshold
         # '-r', # refinement mode (lossless symbol mode, currently disabled in
         # jbig2)
-        '-p',
+        '--pdf',
     ]
     args.extend(infiles)
     proc = run(args, cwd=cwd, stdout=PIPE, stderr=PIPE)
@@ -42,11 +44,13 @@ def convert_group(*, cwd, infiles, out_prefix):
 
 
 def convert_group_mp(args):
-    return convert_group(cwd=args[0], infiles=args[1], out_prefix=args[2])
+    return convert_group(
+        cwd=args[0], infiles=args[1], out_prefix=args[2], threshold=args[3]
+    )
 
 
-def convert_single(*, cwd, infile, outfile):
-    args = ['jbig2', '-p', infile]
+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()
@@ -54,4 +58,6 @@ def convert_single(*, cwd, infile, outfile):
 
 
 def convert_single_mp(args):
-    return convert_single(cwd=args[0], infile=args[1], outfile=args[2])
+    return convert_single(
+        cwd=args[0], infile=args[1], outfile=args[2], threshold=args[3]
+    )

src/ocrmypdf/_exec/pngquant.py

@@ -1,25 +1,24 @@
-# © 2018 James R. Barlow: github.com/jbarlow83
-#
-# This Source Code Form is subject to the terms of the Mozilla Public
-# License, v. 2.0. If a copy of the MPL was not distributed with this
-# file, You can obtain one at http://mozilla.org/MPL/2.0/.
+# SPDX-FileCopyrightText: 2022 James R. Barlow
+# SPDX-License-Identifier: MPL-2.0
 
+"""Interface to pngquant executable."""
 
-"""Interface to pngquant executable"""
+from __future__ import annotations
 
 from contextlib import contextmanager
 from io import BytesIO
 from pathlib import Path
 from subprocess import PIPE
 
+from packaging.version import Version
 from PIL import Image
 
 from ocrmypdf.exceptions import MissingDependencyError
 from ocrmypdf.subprocess import get_version, run
 
 
-def version():
-    return get_version('pngquant', regex=r'(\d+(\.\d+)*).*')
+def version() -> Version:
+    return Version(get_version('pngquant', regex=r'(\d+(\.\d+)*).*'))
 
 
 def available():

src/ocrmypdf/_exec/tesseract.py

@@ -1,11 +1,9 @@
-# © 2017 James R. Barlow: github.com/jbarlow83
-#
-# This Source Code Form is subject to the terms of the Mozilla Public
-# License, v. 2.0. If a copy of the MPL was not distributed with this
-# file, You can obtain one at http://mozilla.org/MPL/2.0/.
+# SPDX-FileCopyrightText: 2022 James R. Barlow
+# SPDX-License-Identifier: MPL-2.0
 
+"""Interface to Tesseract executable."""
 
-"""Interface to Tesseract executable"""
+from __future__ import annotations
 
 import logging
 import re
@@ -13,7 +11,6 @@ from math import pi
 from os import fspath
 from pathlib import Path
 from subprocess import PIPE, STDOUT, CalledProcessError, TimeoutExpired
-from typing import Dict, Iterator, List, Optional
 
 from packaging.version import Version
 from PIL import Image
@@ -36,17 +33,19 @@ HOCR_TEMPLATE = """<?xml version="1.0" encoding="UTF-8"?>
  <head>
   <title></title>
 <meta http-equiv="Content-Type" content="text/html;charset=utf-8" />
-  <meta name='ocr-system' content='tesseract 4.0.0' />
-  <meta name='ocr-capabilities' content='ocr_page ocr_carea ocr_par ocr_line ocrx_word ocrp_wconf'/>
+  <meta name='ocr-system' content='tesseract 4.1.1' />
+  <meta name='ocr-capabilities'
+    content='ocr_page ocr_carea ocr_par ocr_line ocrx_word ocrp_wconf'/>
 </head>
 <body>
-  <div class='ocr_page' id='page_1' title='image "_blank.png"; bbox 0 0 {0} {1}; ppageno 0'>
+  <div class='ocr_page' id='page_1'
+    title='image "_blank.png"; bbox 0 0 {0} {1}; ppageno 0'>
   </div>
  </body>
 </html>
 """
 
-TESSERACT_THRESHOLDING_METHODS: Dict[str, int] = {
+TESSERACT_THRESHOLDING_METHODS: dict[str, int] = {
     'auto': 0,
     'otsu': 0,
     'adaptive-otsu': 1,
@@ -55,9 +54,11 @@ TESSERACT_THRESHOLDING_METHODS: Dict[str, int] = {
 
 
 class TesseractLoggerAdapter(logging.LoggerAdapter):
+    """Prepend [tesseract] to messages emitted from tesseract."""
+
     def process(self, msg, kwargs):
         kwargs['extra'] = self.extra
-        return '[tesseract] %s' % (msg), kwargs
+        return f'[tesseract] {msg}', kwargs
 
 
 TESSERACT_VERSION_PATTERN = r"""
@@ -105,30 +106,23 @@ TESSERACT_VERSION_PATTERN = r"""
 
 
 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() -> str:
-    return get_version('tesseract', regex=r'tesseract\s(.+)')
+def version() -> Version:
+    return TesseractVersion(get_version('tesseract', regex=r'tesseract\s(.+)'))
 
 
-def has_user_words():
-    """Does Tesseract have --user-words capability?
-
-    Not available in 4.0, but available in 4.1. Also available in 3.x, but
-    we no longer support 3.x.
-    """
-    return version() >= '4.1'
-
-
-def has_thresholding():
+def has_thresholding() -> bool:
     """Does Tesseract have -c thresholding method capability?"""
-    return version() >= '5.0'
+    return version() >= Version('5.0')
 
 
-def get_languages():
+def get_languages() -> set[str]:
     def lang_error(output):
         msg = (
             "Tesseract failed to report available languages.\n"
@@ -159,7 +153,7 @@ def get_languages():
     return {lang.strip() for lang in rest}
 
 
-def tess_base_args(langs: List[str], engine_mode: Optional[int]) -> List[str]:
+def tess_base_args(langs: list[str], engine_mode: int | None) -> list[str]:
     args = ['tesseract']
     if langs:
         args.extend(['-l', '+'.join(langs)])
@@ -168,19 +162,19 @@ def tess_base_args(langs: List[str], engine_mode: Optional[int]) -> List[str]:
     return args
 
 
-def _parse_tesseract_output(binary_output: bytes) -> Dict[str, str]:
-    def g():
+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 {k: v for k, v in g()}
+    return dict(gen())
 
 
 def get_orientation(
-    input_file: Path, engine_mode: Optional[int], timeout: float
+    input_file: Path, engine_mode: int | None, timeout: float
 ) -> OrientationConfidence:
     args_tesseract = tess_base_args(['osd'], engine_mode) + [
         '--psm',
@@ -205,14 +199,14 @@ def get_orientation(
 
     osd = _parse_tesseract_output(p.stdout)
     angle = int(osd.get('Orientation in degrees', 0))
-    oc = OrientationConfidence(
+    orient_conf = OrientationConfidence(
         angle=angle, confidence=float(osd.get('Orientation confidence', 0))
     )
-    return oc
+    return orient_conf
 
 
 def get_deskew(
-    input_file: Path, languages: List[str], engine_mode: Optional[int], timeout: float
+    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) + [
@@ -239,12 +233,13 @@ def get_deskew(
     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):
+def tesseract_log_output(stream: bytes) -> None:
     tlog = TesseractLoggerAdapter(
-        log, extra=log.extra if hasattr(log, 'extra') else None
+        log, extra=log.extra if hasattr(log, 'extra') else None  # type: ignore
     )
 
     if not stream:
@@ -282,15 +277,17 @@ def tesseract_log_output(stream):
             tlog.info(line.strip())
 
 
-def page_timedout(timeout):
+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, output_text, image):
-    """Produce a .hocr file that reports no text detected on a page that is
-    the same size as the input image."""
+def _generate_null_hocr(output_hocr: Path, output_text: Path, image: Path) -> None:
+    """Produce a .hocr file that reports no text detected.
+
+    Ensures page is the same size as the input image.
+    """
     with Image.open(image) as im:
         w, h = im.size
 
@@ -303,15 +300,15 @@ def generate_hocr(
     input_file: Path,
     output_hocr: Path,
     output_text: Path,
-    languages: List[str],
+    languages: list[str],
     engine_mode: int,
-    tessconfig: List[str],
+    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('')
 
@@ -344,7 +341,7 @@ def generate_hocr(
         _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:
+        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
 
@@ -357,7 +354,7 @@ def generate_hocr(
             prefix.with_suffix('.txt').replace(output_text)
 
 
-def use_skip_page(output_pdf, 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
@@ -369,15 +366,15 @@ def generate_pdf(
     input_file: Path,
     output_pdf: Path,
     output_text: Path,
-    languages: List[str],
+    languages: list[str],
     engine_mode: int,
-    tessconfig: List[str],
+    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
@@ -416,7 +413,7 @@ def generate_pdf(
         use_skip_page(output_pdf, output_text)
     except CalledProcessError as e:
         tesseract_log_output(e.output)
-        if b'Image too large' in 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

src/ocrmypdf/_exec/unpaper.py

@@ -1,81 +1,131 @@
-# © 2015 James R. Barlow: github.com/jbarlow83
-#
-# This Source Code Form is subject to the terms of the Mozilla Public
-# License, v. 2.0. If a copy of the MPL was not distributed with this
-# file, You can obtain one at http://mozilla.org/MPL/2.0/.
+# SPDX-FileCopyrightText: 2022 James R. Barlow
+# SPDX-License-Identifier: MPL-2.0
 
+"""Interface to unpaper executable."""
 
-# unpaper documentation:
-# https://github.com/Flameeyes/unpaper/blob/master/doc/basic-concepts.md
-
-"""Interface to unpaper executable"""
+from __future__ import annotations
 
 import logging
 import os
 import shlex
+import sys
+from contextlib import contextmanager
 from decimal import Decimal
 from pathlib import Path
 from subprocess import PIPE, STDOUT
-from tempfile import TemporaryDirectory
-from typing import List, Optional, Tuple, Union
+from typing import Iterator, Union
 
+from packaging.version import Version
 from PIL import Image
 
 from ocrmypdf.exceptions import MissingDependencyError, SubprocessOutputError
-from ocrmypdf.subprocess import get_version
-from ocrmypdf.subprocess import run as external_run
+from ocrmypdf.subprocess import get_version, run
+
+# unpaper documentation:
+# https://github.com/Flameeyes/unpaper/blob/main/doc/basic-concepts.md
+
+
+if sys.version_info >= (3, 10):
+    from tempfile import TemporaryDirectory
+else:
+    from tempfile import TemporaryDirectory as _TemporaryDirectory
+
+    class TemporaryDirectory(_TemporaryDirectory):
+        """Shim to consume ignore_cleanup_errors kwarg on Python 3.9 and older.
+
+        The argument is consumed without action. If users are getting errors related
+        to temporary file cleanup, they should upgrade to Python 3.10 which properly
+        cleans up temporary directories on Windows.
+
+        See: https://github.com/python/cpython/pull/24793
+        """
+
+        def __init__(self, ignore_cleanup_errors=False, **kwargs):
+            super().__init__(**kwargs)
+
+    del _TemporaryDirectory
+
+
+UNPAPER_IMAGE_PIXEL_LIMIT = 256 * 1024 * 1024
 
 DecFloat = Union[Decimal, float]
 
 log = logging.getLogger(__name__)
 
 
-def version() -> str:
-    return get_version('unpaper')
+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 _setup_unpaper_io(tmpdir: Path, input_file: Path) -> Tuple[Path, Path]:
-    SUFFIXES = {'1': '.pbm', 'L': '.pgm', 'RGB': '.ppm'}
-    with Image.open(input_file) as im:
-        im_modified = False
-        if im.mode not in SUFFIXES:
-            log.info("Converting image to other colorspace")
-            try:
-                if im.mode == 'P' and len(im.getcolors()) == 2:
-                    im = im.convert(mode='1')
-                else:
-                    im = im.convert(mode='RGB')
-            except OSError as e:
-                raise MissingDependencyError(
-                    "Could not convert image with type " + im.mode
-                ) from e
-            else:
-                im_modified = True
+def version() -> Version:
+    return Version(get_version('unpaper'))
+
+
+SUPPORTED_MODES = {'1', 'L', 'RGB'}
+
+
+def _convert_image(im: Image.Image) -> tuple[Image.Image, bool]:
+    im_modified = False
+
+    if im.mode not in SUPPORTED_MODES:
+        log.info("Converting image to other colorspace")
         try:
-            suffix = SUFFIXES[im.mode]
-        except KeyError:
+            if im.mode == 'P' and len(im.getcolors()) == 2:
+                im = im.convert(mode='1')
+            else:
+                im = im.convert(mode='RGB')
+        except OSError as e:
+            raise MissingDependencyError(
+                "Could not convert image with type " + im.mode
+            ) from e
+        else:
+            im_modified = True
+        if im.mode not in SUPPORTED_MODES:
             raise MissingDependencyError(
                 "Failed to convert image to a supported format."
             ) from None
-
-        if im_modified or input_file.suffix != '.pnm':
-            input_pnm = tmpdir / 'input.pnm'
-            im.save(input_pnm, format='PPM')
-        else:
-            # No changes, PNG input, just use the file we already have
-            input_pnm = input_file
-        output_pnm = tmpdir / f'output{suffix}'
-    return input_pnm, output_pnm
+    return im, im_modified
 
 
-def run(
-    input_file: Path, output_file: Path, *, dpi: DecFloat, mode_args: List[str]
+@contextmanager
+def _setup_unpaper_io(input_file: Path) -> Iterator[tuple[Path, Path, Path]]:
+    with Image.open(input_file) as im:
+        if im.width * im.height >= UNPAPER_IMAGE_PIXEL_LIMIT:
+            raise UnpaperImageTooLargeError(w=im.width, h=im.height)
+        im, im_modified = _convert_image(im)
+
+        with TemporaryDirectory(ignore_cleanup_errors=True) as tmpdir:
+            tmppath = Path(tmpdir)
+            if im_modified or input_file.suffix != '.png':
+                input_png = tmppath / 'input.png'
+                im.save(input_png, format='PNG')
+            else:
+                # No changes, PNG input, just use the file we already have
+                input_png = input_file
+
+            # unpaper can write .png too, but it seems to write them slowly
+            # adds a few seconds to test suite - so just use pnm
+            output_pnm = tmppath / 'output.pnm'
+            yield input_png, output_pnm, tmppath
+
+
+def run_unpaper(
+    input_file: Path, output_file: Path, *, dpi: DecFloat, mode_args: list[str]
 ) -> None:
     args_unpaper = ['unpaper', '-v', '--dpi', str(round(dpi, 6))] + mode_args
 
-    with TemporaryDirectory() as tmpdir:
-        input_pnm, output_pnm = _setup_unpaper_io(Path(tmpdir), input_file)
-
+    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
@@ -83,8 +133,8 @@ def run(
         # 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_pnm), os.fspath(output_pnm)])
-        external_run(
+        args_unpaper.extend([os.fspath(input_png), os.fspath(output_pnm)])
+        run(
             args_unpaper,
             close_fds=True,
             check=True,
@@ -104,7 +154,7 @@ def run(
             ) from e
 
 
-def validate_custom_args(args: str) -> List[str]:
+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')
@@ -116,8 +166,8 @@ def clean(
     output_file: Path,
     *,
     dpi: DecFloat,
-    unpaper_args: Optional[List[str]] = None,
-):
+    unpaper_args: list[str] | None = None,
+) -> Path:
     default_args = [
         '--layout',
         'none',
@@ -131,4 +181,9 @@ def clean(
     ]
     if not unpaper_args:
         unpaper_args = default_args
-    run(input_file, output_file, dpi=dpi, mode_args=unpaper_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

@@ -1,22 +1,19 @@
-# © 2018 James R. Barlow: github.com/jbarlow83
-#
-# This Source Code Form is subject to the terms of the Mozilla Public
-# License, v. 2.0. If a copy of the MPL was not distributed with this
-# file, You can obtain one at http://mozilla.org/MPL/2.0/.
+# 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
-import uuid
 from contextlib import suppress
 from pathlib import Path
-from typing import Optional
 
 from pikepdf import (
     Dictionary,
     Name,
     Object,
     Operator,
-    Page,
     Pdf,
     PdfError,
     PdfMatrix,
@@ -40,7 +37,6 @@ def _update_resources(*, obj, font, font_key, procset):
 
     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:
@@ -81,6 +77,8 @@ def strip_invisible_text(pdf, page):
 
 
 class OcrGrafter:
+    """Manages grafting text-only PDFs onto regular PDFs."""
+
     def __init__(self, context):
         self.context = context
         self.path_base = context.origin
@@ -102,8 +100,8 @@ class OcrGrafter:
         self,
         *,
         pageno: int,
-        image: Optional[Path],
-        textpdf: Optional[Path],
+        image: Path | None,
+        textpdf: Path | None,
         autorotate_correction: int,
     ):
         if textpdf and not self.font:
@@ -132,7 +130,8 @@ class OcrGrafter:
         text_misaligned = (text_rotation - content_rotation) % 360
         log.debug(
             f"Text rotation: (text, autorotate, content) -> text misalignment = "
-            f"({text_rotation}, {autorotate_correction}, {content_rotation}) -> {text_misaligned}"
+            f"({text_rotation}, {autorotate_correction}, {content_rotation}) -> "
+            f"{text_misaligned}"
         )
 
         if textpdf and self.font:
@@ -167,7 +166,6 @@ class OcrGrafter:
         the font to page 1 even if page 1 doesn't use it, so we have a way to get it
         back.
         """
-
         page0 = self.pdf_base.pages[0]
         _update_resources(
             obj=page0, font=self.font, font_key=self.font_key, procset=self.procset
@@ -200,8 +198,7 @@ class OcrGrafter:
         return self.output_file
 
     def _find_font(self, text):
-        """Copy a font from the filename text into pdf_base"""
-
+        """Copy a font from the filename text into pdf_base."""
         font, font_key = None, None
         possible_font_names = ('/f-0-0', '/F1')
         try:
@@ -234,7 +231,8 @@ class OcrGrafter:
         text_rotation: int,
         strip_old_text: bool,
     ):
-        """Insert the text layer from text page 0 on to pdf_base at page_num"""
+        """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:
@@ -282,7 +280,7 @@ class OcrGrafter:
 
             base_resources = _ensure_dictionary(base_page, Name.Resources)
             base_xobjs = _ensure_dictionary(base_resources, Name.XObject)
-            text_xobj_name = Name('/' + str(uuid.uuid4()))
+            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

src/ocrmypdf/_jobcontext.py

@@ -1,9 +1,9 @@
-# © 2018 James R. Barlow: github.com/jbarlow83
-#
-# This Source Code Form is subject to the terms of the Mozilla Public
-# License, v. 2.0. If a copy of the MPL was not distributed with this
-# file, You can obtain one at http://mozilla.org/MPL/2.0/.
+# 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
 import shutil
@@ -49,7 +49,7 @@ class PdfContext:
         """
         return self.work_folder / name
 
-    def get_page_contexts(self) -> Iterator['PageContext']:
+    def get_page_contexts(self) -> Iterator[PageContext]:
         """Get all ``PageContext`` for this PDF."""
         npages = len(self.pdfinfo)
         for n in range(npages):
@@ -59,7 +59,7 @@ class PdfContext:
 class PageContext:
     """Holds our context for a page.
 
-    Must be pickable, so stores only intrinsic/simple data elements or those
+    Must be pickle-able, so stores only intrinsic/simple data elements or those
     capable of their serializing themselves via ``__getstate__``.
     """
 
@@ -83,7 +83,7 @@ class PageContext:
         The path will be based in a common temporary folder and have a prefix based
         on the page number.
         """
-        return self.work_folder / ("%06d_%s" % (self.pageno + 1, name))
+        return self.work_folder / f"{(self.pageno + 1):06d}_{name}"
 
     def __getstate__(self):
         state = self.__dict__.copy()

src/ocrmypdf/_logging.py

@@ -1,18 +1,28 @@
-# © 2020 James R. Barlow: github.com/jbarlow83
-#
-# This Source Code Form is subject to the terms of the Mozilla Public
-# License, v. 2.0. If a copy of the MPL was not distributed with this
-# file, You can obtain one at http://mozilla.org/MPL/2.0/.
+# SPDX-FileCopyrightText: 2022 James R. Barlow
+# SPDX-License-Identifier: MPL-2.0
 
+"""Logging support classes."""
+
+from __future__ import annotations
 
 import logging
-import sys
-from contextlib import suppress
 
-from tqdm import tqdm
+from rich.console import Console
+from rich.logging import RichHandler
+from rich.progress import (
+    BarColumn,
+    MofNCompleteColumn,
+    Progress,
+    TaskProgressColumn,
+    TextColumn,
+    TimeRemainingColumn,
+)
+from rich.table import Column
 
 
 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):
@@ -22,21 +32,61 @@ class PageNumberFilter(logging.Filter):
         return True
 
 
-class TqdmConsole:
-    """Wrapper to log messages in a way that is compatible with tqdm progress bar
+class RichLoggingHandler(RichHandler):
+    def __init__(self, console: Console, **kwargs):
+        super().__init__(
+            console=console, show_level=False, show_time=False, markup=True, **kwargs
+        )
 
-    This routes log messages through tqdm so that it can print them above the
-    progress bar, and then refresh the progress bar, rather than overwriting
-    it which looks messy.
-    """
 
-    def __init__(self, file):
-        self.file = file
+class RichTqdmProgressAdapter:
+    """Adapt tqdm API to rich progress bar."""
 
-    def write(self, msg):
-        # When no progress bar is active, tqdm.write() routes to print()
-        tqdm.write(msg.rstrip(), end='\n', file=self.file)
+    def __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 flush(self):
-        with suppress(AttributeError):
-            self.file.flush()
+    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/_pipeline.py

@@ -1,9 +1,10 @@
-# © 2016 James R. Barlow: github.com/jbarlow83
-#
-# This Source Code Form is subject to the terms of the Mozilla Public
-# License, v. 2.0. If a copy of the MPL was not distributed with this
-# file, You can obtain one at http://mozilla.org/MPL/2.0/.
+# 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
@@ -13,7 +14,7 @@ from contextlib import suppress
 from datetime import datetime, timezone
 from pathlib import Path
 from shutil import copyfileobj
-from typing import Dict, Iterable, Optional
+from typing import Any, BinaryIO, Iterable, Iterator, Sequence, cast
 
 import img2pdf
 import pikepdf
@@ -26,24 +27,46 @@ from ocrmypdf._jobcontext import PageContext, PdfContext
 from ocrmypdf._version import PROGRAM_NAME
 from ocrmypdf._version import __version__ as VERSION
 from ocrmypdf.exceptions import (
+    DigitalSignatureError,
     DpiError,
     EncryptedPdfError,
     InputFileError,
     PriorOcrFoundError,
     UnsupportedImageFormatError,
 )
-from ocrmypdf.helpers import Resolution, safe_symlink
+from ocrmypdf.helpers import IMG2PDF_KWARGS, Resolution, safe_symlink
 from ocrmypdf.hocrtransform import HocrTransform
-from ocrmypdf.optimize import optimize
 from ocrmypdf.pdfa import generate_pdfa_ps
-from ocrmypdf.pdfinfo import Colorspace, Encoding, PdfInfo
+from ocrmypdf.pdfinfo import Colorspace, Encoding, PageInfo, PdfInfo
+from ocrmypdf.pluginspec import OrientationConfidence
+
+# Remove this workaround when we require Pillow >= 10
+try:
+    BICUBIC = Image.Resampling.BICUBIC  # type: ignore
+except AttributeError:  # pragma: no cover
+    # Pillow 9 shim
+    BICUBIC = Image.BICUBIC  # type: ignore
 
 log = logging.getLogger(__name__)
 
 VECTOR_PAGE_DPI = 400
 
 
-def triage_image_file(input_file, output_file, options):
+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)
@@ -58,34 +81,32 @@ def triage_image_file(input_file, output_file, options):
             if im.info['dpi'] <= (96, 96) and not options.image_dpi:
                 log.info("Image size: (%d, %d)", *im.size)
                 log.info("Image resolution: (%d, %d)", *im.info['dpi'])
-                log.error(
+                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."
                 )
-                raise DpiError()
         elif not options.image_dpi:
             log.info("Image size: (%d, %d)", *im.size)
-            log.error(
+            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."
             )
-            raise DpiError()
 
         if im.mode in ('RGBA', 'LA'):
-            log.error(
+            raise UnsupportedImageFormatError(
                 "The input image has an alpha channel. Remove the alpha "
                 "channel first."
             )
-            raise UnsupportedImageFormatError()
 
         if 'iccprofile' not in im.info:
             if im.mode == 'RGB':
                 log.info("Input image has no ICC profile, assuming sRGB")
             elif im.mode == 'CMYK':
-                log.error("Input CMYK image has no ICC profile, not usable")
-                raise UnsupportedImageFormatError()
+                raise UnsupportedImageFormatError(
+                    "Input CMYK image has no ICC profile, not usable"
+                )
 
     try:
         log.info("Image seems valid. Try converting to PDF...")
@@ -98,32 +119,32 @@ def triage_image_file(input_file, output_file, options):
             img2pdf.convert(
                 os.fspath(input_file),
                 layout_fun=layout_fun,
-                with_pdfrw=False,
                 outputstream=outf,
+                **IMG2PDF_KWARGS,
             )
         log.info("Successfully converted to PDF, processing...")
     except img2pdf.ImageOpenError as e:
-        log.error(e)
         raise UnsupportedImageFormatError() from e
 
 
-def _pdf_guess_version(input_file, search_window=1024):
+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)
+        return m.group(1).decode('ascii')
     return ''
 
 
-def triage(original_filename, input_file, output_file, options):
+def triage(
+    original_filename: str, input_file: Path, output_file: Path, options
+) -> Path:
     try:
         if _pdf_guess_version(input_file):
             if options.image_dpi:
@@ -147,9 +168,9 @@ def get_pdfinfo(
     input_file,
     *,
     executor: Executor,
-    detailed_analysis=False,
-    progbar=False,
-    max_workers=None,
+    detailed_analysis: bool = False,
+    progbar: bool = False,
+    max_workers: int | None = None,
     check_pages=None,
 ) -> PdfInfo:
     try:
@@ -167,32 +188,26 @@ def get_pdfinfo(
         raise InputFileError() from e
 
 
-def validate_pdfinfo_options(context: PdfContext):
+def validate_pdfinfo_options(context: PdfContext) -> None:
     pdfinfo = context.pdfinfo
     options = context.options
 
     if pdfinfo.needs_rendering:
-        log.error(
+        raise InputFileError(
             "This PDF contains dynamic XFA forms created by Adobe LiveCycle "
             "Designer and can only be read by Adobe Acrobat or Adobe Reader."
         )
-        raise InputFileError()
-    if pdfinfo.has_userunit and options.output_type.startswith('pdfa'):
-        log.error(
-            "This input file uses a PDF feature that is not supported "
-            "by Ghostscript, so you cannot use --output-type=pdfa for this "
-            "file. (Specifically, it uses the PDF-1.6 /UserUnit feature to "
-            "support very large or small page sizes, and Ghostscript cannot "
-            "output these files.)  Use --output-type=pdf instead."
-        )
-        raise InputFileError()
+    if pdfinfo.has_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:
-            log.error(
+            raise InputFileError(
                 "This PDF has a user fillable form. --redo-ocr is not "
                 "currently possible on such files."
             )
-            raise InputFileError()
         else:
             log.warning(
                 "This PDF has a fillable form. "
@@ -208,29 +223,24 @@ def validate_pdfinfo_options(context: PdfContext):
     context.plugin_manager.hook.validate(pdfinfo=pdfinfo, options=options)
 
 
-def _vector_page_dpi(pageinfo):
-    return VECTOR_PAGE_DPI if pageinfo.has_vector or pageinfo.has_text else 0.0
+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_dpi(pageinfo, options):
-    "Get the DPI when nonsquare DPI is tolerable"
-    xres = max(
-        pageinfo.dpi.x or VECTOR_PAGE_DPI,
-        options.oversample or 0.0,
-        _vector_page_dpi(pageinfo),
-    )
-    yres = max(
-        pageinfo.dpi.y or VECTOR_PAGE_DPI,
-        options.oversample or 0,
-        _vector_page_dpi(pageinfo),
-    )
-    return Resolution(float(xres), float(yres))
+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.
 
-
-def get_page_square_dpi(pageinfo, options) -> Resolution:
-    "Get the DPI when we require xres == yres, scaled to physical units"
-    xres = pageinfo.dpi.x or 0.0
-    yres = pageinfo.dpi.y or 0.0
+    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(
@@ -243,12 +253,23 @@ def get_page_square_dpi(pageinfo, options) -> Resolution:
     return Resolution(units, units)
 
 
-def get_canvas_square_dpi(pageinfo, options) -> Resolution:
-    """Get the DPI when we require xres == yres, in Postscript 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(
-            (pageinfo.dpi.x) or VECTOR_PAGE_DPI,
-            (pageinfo.dpi.y) or VECTOR_PAGE_DPI,
+            image_dpi.x or VECTOR_PAGE_DPI,
+            image_dpi.y or VECTOR_PAGE_DPI,
             _vector_page_dpi(pageinfo),
             options.oversample or 0.0,
         )
@@ -256,7 +277,8 @@ def get_canvas_square_dpi(pageinfo, options) -> Resolution:
     return Resolution(units, units)
 
 
-def is_ocr_required(page_context: PageContext):
+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
 
@@ -306,8 +328,8 @@ def is_ocr_required(page_context: PageContext):
             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 "
+                f"rasterized at {VECTOR_PAGE_DPI} DPI, losing some resolution and "
+                "likely increasing file size. Use --oversample to adjust the "
                 "DPI."
             )
         else:
@@ -325,15 +347,19 @@ def is_ocr_required(page_context: PageContext):
             ocr_required = False
             log.warning(
                 "page too big, skipping OCR "
-                f"({(pixel_count / 1_000_000):.1f} MPixels > {options.skip_big:.1f} MPixels --skip-big)"
+                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):
+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 = get_canvas_square_dpi(page_context.pageinfo, page_context.options)
-    page_dpi = get_page_square_dpi(page_context.pageinfo, page_context.options)
+    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,
@@ -343,14 +369,15 @@ def rasterize_preview(input_file: Path, page_context: PageContext):
         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, correction: int):
-    """
-    Describe the page rotation we are going to perform.
-    """
+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: '⬑'}
 
@@ -376,8 +403,8 @@ def describe_rotation(page_context: PageContext, orient_conf, correction: int):
     return f"{facing}, confidence {orient_conf.confidence:.2f} - {action}"
 
 
-def get_orientation_correction(preview: Path, page_context: PageContext):
-    """Work out orientation correct for each page.
+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
@@ -391,7 +418,6 @@ def get_orientation_correction(preview: Path, page_context: PageContext):
     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
     )
@@ -407,13 +433,58 @@ def get_orientation_correction(preview: Path, page_context: PageContext):
     return 0
 
 
+def calculate_image_dpi(page_context: PageContext) -> Resolution:
+    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=None,
-):
+    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
 
@@ -423,8 +494,8 @@ def rasterize(
     output_file = page_context.get_path(f'rasterize{output_tag}.png')
     pageinfo = page_context.pageinfo
 
-    def at_least(cs):
-        return max(device_idx, colorspaces.index(cs))
+    def at_least(colorspace):
+        return max(device_idx, colorspaces.index(colorspace))
 
     for image in pageinfo.images:
         if image.type_ != 'image':
@@ -444,10 +515,7 @@ def rasterize(
 
     log.debug(f"Rasterize with {device}, rotation {correction}")
 
-    # Produce the page image with square resolution or else deskew and OCR
-    # will not work properly.
-    canvas_dpi = get_canvas_square_dpi(pageinfo, page_context.options)
-    page_dpi = get_page_square_dpi(pageinfo, page_context.options)
+    canvas_dpi, page_dpi = calculate_raster_dpi(page_context)
 
     page_context.plugin_manager.hook.rasterize_pdf_page(
         input_file=input_file,
@@ -458,24 +526,33 @@ def rasterize(
         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):
+def preprocess_remove_background(input_file: Path, page_context: PageContext) -> Path:
     if any(image.bpc > 1 for image in page_context.pageinfo.images):
-        output_file = page_context.get_path('pp_rm_bg.png')
-        # leptonica.remove_background(input_file, output_file)
         raise NotImplementedError("--remove-background is temporarily not implemented")
-        return output_file
-    else:
-        log.info("background removal skipped on mono page")
-        return input_file
+        # 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):
+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.pageinfo, page_context.options)
+    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)
@@ -484,30 +561,32 @@ def preprocess_deskew(input_file: Path, page_context: PageContext):
         # 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.BICUBIC, fillcolor='white'
+            deskew_angle_degrees,
+            resample=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):
+def preprocess_clean(input_file: Path, page_context: PageContext) -> Path:
     output_file = page_context.get_path('pp_clean.png')
-    dpi = get_page_square_dpi(page_context.pageinfo, page_context.options)
-    unpaper.clean(
+    dpi = get_page_square_dpi(page_context, calculate_image_dpi(page_context))
+    return unpaper.clean(
         input_file,
         output_file,
-        dpi=dpi.x,
+        dpi=dpi.to_scalar(),
         unpaper_args=page_context.options.unpaper_args,
     )
-    return output_file
 
 
-def create_ocr_image(image: Path, page_context: PageContext):
-    """Create the image we send for OCR. May not be the same as the display
-    image depending on preprocessing. This image will never be shown to the
-    user."""
+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:
@@ -551,7 +630,7 @@ def create_ocr_image(image: Path, page_context: PageContext):
     return output_file
 
 
-def ocr_engine_hocr(input_file: Path, page_context: PageContext):
+def ocr_engine_hocr(input_file: Path, page_context: PageContext) -> tuple[Path, Path]:
     hocr_out = page_context.get_path('ocr_hocr.hocr')
     hocr_text_out = page_context.get_path('ocr_hocr.txt')
     options = page_context.options
@@ -566,9 +645,20 @@ def ocr_engine_hocr(input_file: Path, page_context: PageContext):
     return (hocr_out, hocr_text_out)
 
 
-def should_visible_page_image_use_jpg(pageinfo):
-    # If all images were JPEGs originally, produce a JPEG as output
-    return pageinfo.images and all(im.enc == Encoding.jpeg for im in pageinfo.images)
+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:
@@ -583,7 +673,7 @@ def create_visible_page_jpg(image: Path, page_context: PageContext) -> Path:
             dpi = Resolution(*im.info['dpi'])
         else:
             # Fallback to page-implied DPI
-            dpi = get_page_square_dpi(page_context.pageinfo, page_context.options)
+            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())
@@ -591,8 +681,8 @@ def create_visible_page_jpg(image: Path, page_context: PageContext) -> Path:
 
 
 def create_pdf_page_from_image(
-    image: Path, page_context: PageContext, orientation_correction
-):
+    image: Path, page_context: PageContext, orientation_correction: int
+) -> Path:
     # 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
@@ -613,21 +703,20 @@ def create_pdf_page_from_image(
 
         layout_fun = img2pdf.get_layout_fun(pagesize)
         img2pdf.convert(
-            imfile, with_pdfrw=False, layout_fun=layout_fun, outputstream=pdf
+            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):
+def render_hocr_page(hocr: Path, page_context: PageContext) -> Path:
     options = page_context.options
     output_file = page_context.get_path('ocr_hocr.pdf')
-    dpi = get_page_square_dpi(page_context.pageinfo, options)
+    dpi = get_page_square_dpi(page_context, calculate_image_dpi(page_context))
     debug_mode = options.pdf_renderer == 'hocrdebug'
 
     hocrtransform = HocrTransform(hocr_filename=hocr, dpi=dpi.x)  # square
@@ -641,7 +730,9 @@ def render_hocr_page(hocr: Path, page_context: PageContext):
     return output_file
 
 
-def ocr_engine_textonly_pdf(input_image: Path, page_context: PageContext):
+def ocr_engine_textonly_pdf(
+    input_image: Path, page_context: PageContext
+) -> tuple[Path, Path]:
     output_pdf = page_context.get_path('ocr_tess.pdf')
     output_text = page_context.get_path('ocr_tess.txt')
     options = page_context.options
@@ -656,7 +747,7 @@ def ocr_engine_textonly_pdf(input_image: Path, page_context: PageContext):
     return (output_pdf, output_text)
 
 
-def get_docinfo(base_pdf: pikepdf.Pdf, context: PdfContext) -> Dict[str, str]:
+def get_docinfo(base_pdf: pikepdf.Pdf, context: PdfContext) -> dict[str, str]:
     options = context.options
 
     def from_document_info(key):
@@ -670,15 +761,14 @@ def get_docinfo(base_pdf: pikepdf.Pdf, context: PdfContext) -> Dict[str, str]:
         k: from_document_info(k)
         for k in ('/Title', '/Author', '/Keywords', '/Subject', '/CreationDate')
     }
-    if options is not None:
-        if options.title:
-            pdfmark['/Title'] = options.title
-        if options.author:
-            pdfmark['/Author'] = options.author
-        if options.keywords:
-            pdfmark['/Keywords'] = options.keywords
-        if options.subject:
-            pdfmark['/Subject'] = options.subject
+    if options.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)
 
@@ -688,13 +778,21 @@ def get_docinfo(base_pdf: pikepdf.Pdf, context: PdfContext) -> Dict[str, str]:
     return pdfmark
 
 
-def generate_postscript_stub(context: PdfContext):
+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):
+def convert_to_pdfa(input_pdf: Path, input_ps_stub: Path, context: PdfContext) -> Path:
     options = context.options
     input_pdfinfo = context.pdfinfo
     fix_docinfo_file = context.get_path('fix_docinfo.pdf')
@@ -705,21 +803,8 @@ def convert_to_pdfa(input_pdf: Path, input_ps_stub: Path, context: PdfContext):
     # NULs in DocumentInfo seem to be common since older Acrobats included them.
     # pikepdf can deal with this, but we make the world a better place by
     # stamping them out as soon as possible.
-    modified = False
     with pikepdf.open(input_pdf) as pdf_file:
-        try:
-            len(pdf_file.docinfo)
-        except TypeError:
-            log.error(
-                "File contains a malformed DocumentInfo block - continuing anyway"
-            )
-        else:
-            if pdf_file.docinfo:
-                for k, v in pdf_file.docinfo.items():
-                    if b'\x00' in bytes(v):
-                        pdf_file.docinfo[k] = bytes(v).replace(b'\x00', b'')
-                        modified = True
-        if modified:
+        if _repair_docinfo_nuls(pdf_file):
             pdf_file.save(fix_docinfo_file)
         else:
             safe_symlink(input_pdf, fix_docinfo_file)
@@ -729,26 +814,46 @@ def convert_to_pdfa(input_pdf: Path, input_ps_stub: Path, context: PdfContext):
         pdf_pages=[fix_docinfo_file],
         pdfmark=input_ps_stub,
         output_file=output_file,
-        compression=options.pdfa_image_compression,
+        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):
+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, pikepdf.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:
     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):
+def get_pdf_save_settings(output_type: str) -> dict[str, Any]:
     if output_type == 'pdfa-1':
         # Trigger recompression to ensure object streams are removed, because
         # Acrobat complains about them in PDF/A-1b validation.
@@ -766,7 +871,7 @@ def get_pdf_save_settings(output_type: str):
         )
 
 
-def metadata_fixup(working_file: Path, context: PdfContext):
+def metadata_fixup(working_file: Path, context: PdfContext) -> Path:
     output_file = context.get_path('metafix.pdf')
     options = context.options
 
@@ -789,49 +894,118 @@ def metadata_fixup(working_file: Path, context: PdfContext):
 
     with pikepdf.open(context.origin) as original, pikepdf.open(working_file) as pdf:
         docinfo = get_docinfo(original, context)
-        with pdf.open_metadata() as meta:
-            meta.load_from_docinfo(docinfo, delete_missing=False, raise_failure=False)
+        with pdf.open_metadata() as meta_pdf:
+            meta_pdf.load_from_docinfo(
+                docinfo, delete_missing=False, raise_failure=False
+            )
             # If xmp:CreateDate is missing, set it to the modify date to
-            # match Ghostscript, for consistency
-            if 'xmp:CreateDate' not in meta:
-                meta['xmp:CreateDate'] = meta.get('xmp:ModifyDate', '')
+            # ensure consistency with Ghostscript.
+            if 'xmp:CreateDate' not in meta_pdf:
+                meta_pdf['xmp:CreateDate'] = meta_pdf.get('xmp:ModifyDate', '')
 
             with original.open_metadata(
                 set_pikepdf_as_editor=False, update_docinfo=False, strict=False
             ) as meta_original:
-                if meta.get('dc:title') == 'Untitled':
+                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['dc:title']
-                missing = set(meta_original.keys()) - set(meta.keys())
-                report_on_metadata(missing)
+                        del meta_pdf['dc:title']
+                # 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.
+                for meta in [meta_pdf, meta_original]:
+                    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
+                meta_missing = set(meta_original.keys()) - set(meta_pdf.keys())
+                report_on_metadata(meta_missing)
 
+        optimizing = context.plugin_manager.hook.is_optimization_enabled(
+            context=context
+        )
         pdf.save(
             output_file,
             **get_pdf_save_settings(options.output_type),
             linearize=(  # Don't linearize if optimize() will be linearizing too
-                should_linearize(working_file, context)
-                if options.optimize == 0
-                else False
+                not optimizing and should_linearize(working_file, context)
             ),
         )
 
     return output_file
 
 
-def optimize_pdf(input_file: Path, context: PdfContext, executor: Executor):
+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]]:
     output_file = context.get_path('optimize.pdf')
-    save_settings = dict(
+    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),
-        **get_pdf_save_settings(context.options.output_type),
     )
-    optimize(input_file, output_file, context, save_settings, executor)
-    return output_file
+
+    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):
+def enumerate_compress_ranges(
+    iterable: Iterable,
+) -> Iterator[tuple[tuple[int, int], Any]]:
+    """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
@@ -847,11 +1021,11 @@ def enumerate_compress_ranges(iterable):
         yield (skipped_from, index), None
 
 
-def merge_sidecars(txt_files: Iterable[Optional[Path]], context: PdfContext):
+def merge_sidecars(txt_files: Iterable[Path | None], context: PdfContext) -> Path:
     output_file = context.get_path('sidecar.txt')
     with open(output_file, 'w', encoding="utf-8") as stream:
-        for (frm, to), txt_file in enumerate_compress_ranges(txt_files):
-            if frm != 1:
+        for (from_, to_), txt_file in enumerate_compress_ranges(txt_files):
+            if from_ != 1:
                 stream.write('\f')  # Form feed between pages
             if txt_file:
                 with open(txt_file, encoding="utf-8") as in_:
@@ -864,23 +1038,35 @@ def merge_sidecars(txt_files: Iterable[Optional[Path]], context: PdfContext):
                     else:
                         stream.write(txt)
             else:
-                if frm != to:
-                    pages = f'{frm}-{to}'
+                if from_ != to_:
+                    pages = f'{from_}-{to_}'
                 else:
-                    pages = f'{frm}'
+                    pages = f'{from_}'
                 stream.write(f'[OCR skipped on page(s) {pages}]')
     return output_file
 
 
-def copy_final(input_file, output_file, _context: PdfContext):
+def copy_final(
+    input_file: Path, output_file: str | Path | BinaryIO, _context: PdfContext
+) -> None:
+    """Copy the final temporary file to the output destination.
+
+    Args:
+        input_file (Path): The input file to copy.
+        output_file (str | Path | BinaryIO): The output file to copy to.
+        _context (PdfContext): The PDF context.
+
+    Returns:
+        None
+    """
     log.debug('%s -> %s', input_file, output_file)
-    with open(input_file, 'rb') as input_stream:
+    with input_file.open('rb') as input_stream:
         if output_file == '-':
-            copyfileobj(input_stream, sys.stdout.buffer)
+            copyfileobj(input_stream, sys.stdout.buffer)  # type: ignore[misc]
             sys.stdout.flush()
         elif hasattr(output_file, 'writable'):
-            output_stream = output_file
-            copyfileobj(input_stream, output_stream)
+            output_stream = cast(BinaryIO, output_file)
+            copyfileobj(input_stream, output_stream)  # type: ignore[misc]
             with suppress(AttributeError):
                 output_stream.flush()
         else:

src/ocrmypdf/_plugin_manager.py

@@ -1,9 +1,9 @@
-# © 2020 James R. Barlow: github.com/jbarlow83
-#
-# This Source Code Form is subject to the terms of the Mozilla Public
-# License, v. 2.0. If a copy of the MPL was not distributed with this
-# file, You can obtain one at http://mozilla.org/MPL/2.0/.
+# SPDX-FileCopyrightText: 2022 James R. Barlow
+# SPDX-License-Identifier: MPL-2.0
 
+"""Plugin manager using pluggy."""
+
+from __future__ import annotations
 
 import argparse
 import importlib
@@ -11,7 +11,7 @@ import importlib.util
 import pkgutil
 import sys
 from pathlib import Path
-from typing import List, Sequence, Tuple, Union
+from typing import Sequence
 
 import pluggy
 
@@ -33,7 +33,7 @@ class OcrmypdfPluginManager(pluggy.PluginManager):
     def __init__(
         self,
         *args,
-        plugins: List[Union[str, Path]],
+        plugins: list[str | Path],
         builtins: bool = True,
         **kwargs,
     ):
@@ -100,23 +100,30 @@ class OcrmypdfPluginManager(pluggy.PluginManager):
             self.register(module)
 
 
-def get_plugin_manager(plugins: List[Union[str, Path]], builtins=True):
-    pm = OcrmypdfPluginManager(
+def get_plugin_manager(
+    plugins: list[str | Path], builtins=True
+) -> OcrmypdfPluginManager:
+    return OcrmypdfPluginManager(
         project_name='ocrmypdf',
         plugins=plugins,
         builtins=builtins,
     )
-    return pm
 
 
 def get_parser_options_plugins(
     args: Sequence[str],
-) -> Tuple[argparse.ArgumentParser, argparse.Namespace, pluggy.PluginManager]:
+) -> 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/_sync.py

@@ -1,9 +1,11 @@
-# © 2016 James R. Barlow: github.com/jbarlow83
-#
-# This Source Code Form is subject to the terms of the Mozilla Public
-# License, v. 2.0. If a copy of the MPL was not distributed with this
-# file, You can obtain one at http://mozilla.org/MPL/2.0/.
+# SPDX-FileCopyrightText: 2019-2022 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
@@ -16,7 +18,7 @@ from concurrent.futures.thread import BrokenThreadPool
 from functools import partial
 from pathlib import Path
 from tempfile import mkdtemp
-from typing import List, NamedTuple, Optional, Tuple, cast
+from typing import NamedTuple, Sequence, cast
 
 import PIL
 
@@ -68,11 +70,13 @@ from ocrmypdf.pdfa import file_claims_pdfa
 log = logging.getLogger(__name__)
 
 
-class PageResult(NamedTuple):  # pylint: disable=inherit-non-class
+class PageResult(NamedTuple):
+    """Result when a page is finished processing."""
+
     pageno: int
-    pdf_page_from_image: Optional[Path]
-    ocr: Optional[Path]
-    text: Optional[Path]
+    pdf_page_from_image: Path | None
+    ocr: Path | None
+    text: Path | None
     orientation_correction: int
 
 
@@ -111,7 +115,7 @@ def preprocess(
 
 def make_intermediate_images(
     page_context: PageContext, orientation_correction: int
-) -> Tuple[Path, Optional[Path]]:
+) -> tuple[Path, Path | None]:
     options = page_context.options
 
     ocr_image = preprocess_out = None
@@ -203,7 +207,7 @@ def exec_page_sync(page_context: PageContext) -> PageResult:
         filtered_image = page_context.plugin_manager.hook.filter_page_image(
             page=page_context, image_filename=visible_image_out
         )
-        if filtered_image:
+        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
@@ -226,7 +230,9 @@ def exec_page_sync(page_context: PageContext) -> PageResult:
     )
 
 
-def post_process(pdf_file: Path, context: PdfContext, executor: Executor) -> Path:
+def post_process(
+    pdf_file: Path, context: PdfContext, executor: Executor
+) -> tuple[Path, Sequence[str]]:
     pdf_out = pdf_file
     if context.options.output_type.startswith('pdfa'):
         ps_stub_out = generate_postscript_stub(context)
@@ -244,16 +250,15 @@ def worker_init(max_pixels: int) -> None:
     pikepdf_enable_mmap()
 
 
-def exec_concurrent(context: PdfContext, executor: Executor) -> None:
-    """Execute the pipeline concurrently"""
-
+def exec_concurrent(context: PdfContext, executor: Executor) -> Sequence[str]:
+    """Execute the pipeline concurrently."""
     # Run exec_page_sync on every page context
     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[Optional[Path]] = [None] * len(context.pdfinfo)
+    sidecars: list[Path | None] = [None] * len(context.pdfinfo)
     ocrgraft = OcrGrafter(context)
 
     def update_page(result: PageResult, pbar):
@@ -296,20 +301,21 @@ def exec_concurrent(context: PdfContext, executor: Executor) -> None:
     # 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 = post_process(pdf, context, executor)
+        pdf, messages = post_process(pdf, context, executor)
 
         # Copy PDF file to destination
         copy_final(pdf, options.output_file, context)
+    return messages
 
 
 def configure_debug_logging(
     log_filename: Path, prefix: str = ''
 ) -> logging.FileHandler:
-    """
-    Create a debug log file at a specified location.
+    """Create a debug log file at a specified location.
 
     Arguments:
         log_filename: Where to the put the log file.
@@ -329,7 +335,7 @@ def configure_debug_logging(
 def run_pipeline(
     options: argparse.Namespace,
     *,
-    plugin_manager: Optional[OcrmypdfPluginManager],
+    plugin_manager: OcrmypdfPluginManager | None,
     api: bool = False,
 ) -> ExitCode:
     # Any changes to options will not take effect for options that are already
@@ -382,7 +388,7 @@ def run_pipeline(
         validate_pdfinfo_options(context)
 
         # Execute the pipeline
-        exec_concurrent(context, executor)
+        optimize_messages = exec_concurrent(context, executor)
 
         if options.output_file == '-':
             log.info("Output sent to stdout")
@@ -408,15 +414,17 @@ def run_pipeline(
             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)
+            report_output_file_size(
+                options, start_input_file, options.output_file, optimize_messages
+            )
 
-    except (KeyboardInterrupt if not api else NeverRaise):
+    except KeyboardInterrupt if not api else NeverRaise:
         if options.verbose >= 1:
             log.exception("KeyboardInterrupt")
         else:
             log.error("KeyboardInterrupt")
         return ExitCode.ctrl_c
-    except (ExitCodeException if not api else NeverRaise) as e:
+    except ExitCodeException if not api else NeverRaise as e:
         e = cast(ExitCodeException, e)
         if options.verbose >= 1:
             log.exception("ExitCodeException")
@@ -425,7 +433,7 @@ def run_pipeline(
         else:
             log.error(type(e).__name__)
         return e.exit_code
-    except (PIL.Image.DecompressionBombError if not api else NeverRaise) as e:
+    except PIL.Image.DecompressionBombError if not api else NeverRaise:
         log.exception(
             "A decompression bomb error was encountered while executing the "
             "pipeline. Use the argument --max-image-mpixels to raise the maximum "
@@ -435,7 +443,7 @@ def run_pipeline(
     except (
         BrokenProcessPool if not api else NeverRaise,
         BrokenThreadPool if not api else NeverRaise,
-    ) as e:
+    ):
         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 "
@@ -443,7 +451,7 @@ def run_pipeline(
             "argument."
         )
         return ExitCode.child_process_error
-    except (Exception if not api else NeverRaise):  # pylint: disable=broad-except
+    except Exception if not api else NeverRaise:  # pylint: disable=broad-except
         log.exception("An exception occurred while executing the pipeline")
         return ExitCode.other_error
     finally:

src/ocrmypdf/_validation.py

@@ -1,31 +1,33 @@
 #!/usr/bin/env python3
-# © 2015-17 James R. Barlow: github.com/jbarlow83
-#
-# This Source Code Form is subject to the terms of the Mozilla Public
-# License, v. 2.0. If a copy of the MPL was not distributed with this
-# file, You can obtain one at http://mozilla.org/MPL/2.0/.
+# 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 pathlib import Path
 from shutil import copyfileobj
-from typing import List, Set, Tuple
+from typing import Sequence
 
 import pikepdf
 import PIL
+from pluggy import PluginManager
 
-from ocrmypdf._exec import jbig2enc, pngquant, unpaper
+from ocrmypdf._exec import unpaper
 from ocrmypdf.exceptions import (
     BadArgsError,
     InputFileError,
     MissingDependencyError,
     OutputFileAccessError,
 )
-from ocrmypdf.helpers import is_file_writable, monotonic, safe_symlink, samefile
+from ocrmypdf.helpers import is_file_writable, monotonic, safe_symlink
 from ocrmypdf.hocrtransform import HOCR_OK_LANGS
 from ocrmypdf.subprocess import check_external_program
 
@@ -40,36 +42,48 @@ log = logging.getLogger(__name__)
 # --------
 
 
-def check_platform():
-    if os.name == 'nt' and sys.maxsize <= 2 ** 32:  # pragma: no cover
-        # 32-bit interpreter on Windows
+def check_platform() -> None:
+    if sys.maxsize <= 2**32:  # pragma: no cover
         log.error(
-            "You are running OCRmyPDF in a 32-bit (x86) Python interpreter."
+            "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, ocr_engine_languages):
+def check_options_languages(
+    options: Namespace, ocr_engine_languages: list[str]
+) -> None:
     if not options.languages:
-        options.languages = {DEFAULT_LANGUAGE}
+        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 = options.languages - ocr_engine_languages
+    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"
         )
-        msg += '\n'.join(lang for lang in missing_languages)
-        msg += '\nNote: most languages are identified by a 3-digit ISO 639-2 Code'
         raise MissingDependencyError(msg)
 
 
-def check_options_output(options):
-    is_latin = options.languages.issubset(HOCR_OK_LANGS)
+def check_options_output(options: Namespace) -> None:
+    is_latin = set(options.languages).issubset(HOCR_OK_LANGS)
 
     if options.pdf_renderer.startswith('hocr') and not is_latin:
         log.warning(
@@ -104,15 +118,13 @@ def check_options_output(options):
         )
 
 
-def check_options_sidecar(options):
+def check_options_sidecar(options: Namespace) -> None:
     if options.sidecar == '\0':
         if options.output_file == '-':
-            raise BadArgsError(
-                "--sidecar filename must be specified when output file is stdout."
-            )
+            raise BadArgsError("--sidecar filename needed when output file is stdout.")
         elif options.output_file == os.devnull:
             raise BadArgsError(
-                "--sidecar filename must be specified when output file is /dev/null or NUL."
+                "--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:
@@ -121,7 +133,7 @@ def check_options_sidecar(options):
         )
 
 
-def check_options_preprocessing(options):
+def check_options_preprocessing(options: Namespace) -> None:
     if options.clean_final:
         options.clean = True
     if options.unpaper_args and not options.clean:
@@ -132,7 +144,7 @@ def check_options_preprocessing(options):
             package='unpaper',
             version_checker=unpaper.version,
             need_version='6.1',
-            required_for=['--clean, --clean-final'],
+            required_for="--clean, --clean-final",  # Problem arguments
         )
         try:
             if options.unpaper_args:
@@ -143,16 +155,16 @@ def check_options_preprocessing(options):
             raise BadArgsError("--unpaper-args: " + str(e)) from e
 
 
-def _pages_from_ranges(ranges: str) -> Set[int]:
-    pages: List[int] = []
+def _pages_from_ranges(ranges: str) -> set[int]:
+    pages: list[int] = []
     page_groups = ranges.replace(' ', '').split(',')
-    for g in page_groups:
-        if not g:
+    for group in page_groups:
+        if not group:
             continue
         try:
-            start, end = g.split('-')
+            start, end = group.split('-')
         except ValueError:
-            pages.append(int(g) - 1)
+            pages.append(int(group) - 1)
         else:
             try:
                 new_pages = list(range(int(start) - 1, int(end)))
@@ -162,7 +174,7 @@ def _pages_from_ranges(ranges: str) -> Set[int]:
                     ) from None
                 pages.extend(new_pages)
             except ValueError:
-                raise BadArgsError(f"invalid page subrange '{g}'") from None
+                raise BadArgsError(f"invalid page subrange '{group}'") from None
 
     if not pages:
         raise BadArgsError(
@@ -182,7 +194,7 @@ def _pages_from_ranges(ranges: str) -> Set[int]:
     return set(pages)
 
 
-def check_options_ocr_behavior(options):
+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)
@@ -193,86 +205,47 @@ def check_options_ocr_behavior(options):
         options.pages = _pages_from_ranges(options.pages)
 
 
-def check_options_optimizing(options):
-    if options.optimize >= 2:
-        check_external_program(
-            program='pngquant',
-            package='pngquant',
-            version_checker=pngquant.version,
-            need_version='2.0.1',
-            required_for='--optimize {2,3}',
-        )
-
-    if options.optimize >= 2:
-        # Although we use JBIG2 for optimize=1, don't nag about it unless the
-        # user is asking for more optimization
-        check_external_program(
-            program='jbig2',
-            package='jbig2enc',
-            version_checker=jbig2enc.version,
-            need_version='0.28',
-            required_for='--optimize {2,3} | --jbig2-lossy',
-            recommended=True if not options.jbig2_lossy else False,
-        )
-
-    if options.optimize == 0 and any(
-        [options.jbig2_lossy, options.png_quality, options.jpeg_quality]
-    ):
-        log.warning(
-            "The arguments --jbig2-lossy, --png-quality, and --jpeg-quality "
-            "will be ignored because --optimize=0."
-        )
-
-
-def check_options_advanced(options):
-    if options.pdfa_image_compression != 'auto' and not options.output_type.startswith(
-        'pdfa'
-    ):
-        log.warning(
-            "--pdfa-image-compression argument only applies when "
-            "--output-type is one of 'pdfa', 'pdfa-1', or 'pdfa-2'"
-        )
-
-
-def check_options_metadata(options):
+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 c in s:
-            if unicodedata.category(c) == 'Co' or ord(c) >= 0x10000:
+        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: '{}' (U+{})".format(
-                        c, hex(ord(c))[2:].upper()
-                    )
+                    "an unsupported Unicode character: "
+                    f"{char} (U+{hexchar})"
                 )
 
 
-def check_options_pillow(options):
+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
+        PIL.Image.MAX_IMAGE_PIXELS = None  # type: ignore
 
 
-def _check_options(options, plugin_manager, ocr_engine_languages):
+def _check_plugin_invariant_options(options: Namespace) -> None:
     check_platform()
-    check_options_languages(options, ocr_engine_languages)
     check_options_metadata(options)
     check_options_output(options)
     check_options_sidecar(options)
     check_options_preprocessing(options)
     check_options_ocr_behavior(options)
-    check_options_optimizing(options)
-    check_options_advanced(options)
     check_options_pillow(options)
+
+
+def _check_plugin_options(options: Namespace, plugin_manager: PluginManager) -> None:
     plugin_manager.hook.check_options(options=options)
-
-
-def check_options(options, plugin_manager):
     ocr_engine_languages = plugin_manager.hook.get_ocr_engine().languages(options)
-    _check_options(options, plugin_manager, ocr_engine_languages)
+    check_options_languages(options, ocr_engine_languages)
 
 
-def create_input_file(options, work_folder: Path) -> Tuple[Path, str]:
+def check_options(options: Namespace, plugin_manager: PluginManager) -> None:
+    _check_plugin_invariant_options(options)
+    _check_plugin_options(options, plugin_manager)
+
+
+def create_input_file(options: Namespace, work_folder: Path) -> tuple[Path, str]:
     if options.input_file == '-':
         # stdin
         log.info('reading file from standard input')
@@ -293,7 +266,7 @@ def create_input_file(options, work_folder: Path) -> Tuple[Path, str]:
             target = work_folder / 'origin'
             safe_symlink(options.input_file, target)
             return target, os.fspath(options.input_file)
-        except FileNotFoundError:
+        except FileNotFoundError as e:
             msg = f"File not found - {options.input_file}"
             if Path('/.dockerenv').exists():  # pragma: no cover
                 msg += (
@@ -302,12 +275,13 @@ def create_input_file(options, work_folder: Path) -> Tuple[Path, str]:
                     "permissions correctly.\n"
                     "You may find it easier to use stdin/stdout:"
                     "\n"
-                    "\tdocker run -i --rm jbarlow83/ocrmypdf - - <input.pdf >output.pdf\n"
+                    "\tdocker run -i --rm jbarlow83/ocrmypdf - - <input.pdf >output.pdf"
+                    "\n"
                 )
-            raise InputFileError(msg)
+            raise InputFileError(msg) from e
 
 
-def check_requested_output_file(options):
+def check_requested_output_file(options: Namespace) -> None:
     if options.output_file == '-':
         if sys.stdout.isatty():
             raise BadArgsError(
@@ -324,7 +298,16 @@ def check_requested_output_file(options):
         )
 
 
-def report_output_file_size(options, input_file, output_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
@@ -333,9 +316,7 @@ def report_output_file_size(options, input_file, output_file):
     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
-        FILE_OVERHEAD = 4000
-        OCR_PER_PAGE_OVERHEAD = 3000
-        reasonable_overhead = FILE_OVERHEAD + OCR_PER_PAGE_OVERHEAD * len(p.pages)
+        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:
@@ -352,22 +333,11 @@ def report_output_file_size(options, input_file, output_file):
     for arg in image_preproc:
         if getattr(options, arg, False):
             reasons.append(
-                f"The argument --{arg.replace('_', '-')} was issued, causing transcoding."
+                f"--{arg.replace('_', '-')} was issued, causing transcoding."
             )
 
-    if options.optimize == 0:
-        reasons.append("Optimization was disabled.")
-    else:
-        image_optimizers = {
-            'jbig2': jbig2enc.available(),
-            'pngquant': pngquant.available(),
-        }
-        for name, available in image_optimizers.items():
-            if not available:
-                reasons.append(
-                    f"The optional dependency '{name}' was not found, so some image "
-                    f"optimizations could not be attempted."
-                )
+    reasons.extend(optimize_messages)
+
     if options.output_type.startswith('pdfa'):
         reasons.append("PDF/A conversion was enabled. (Try `--output-type pdf`.)")
     if options.plugins:

src/ocrmypdf/_version.py

@@ -1,14 +1,14 @@
-# © 2017 James R. Barlow: github.com/jbarlow83
-#
-# This Source Code Form is subject to the terms of the Mozilla Public
-# License, v. 2.0. If a copy of the MPL was not distributed with this
-# file, You can obtain one at http://mozilla.org/MPL/2.0/.
+# SPDX-FileCopyrightText: 2022 James R. Barlow
+# SPDX-License-Identifier: MPL-2.0
 
+"""Get version by introspecting package information.
 
-try:
-    from importlib_metadata import version as _package_version
-except ImportError:
-    from importlib.metadata import version as _package_version
+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'
 

src/ocrmypdf/api.py

@@ -1,33 +1,30 @@
-# © 2019 James R. Barlow: github.com/jbarlow83
-#
-# This Source Code Form is subject to the terms of the Mozilla Public
-# License, v. 2.0. If a copy of the MPL was not distributed with this
-# file, You can obtain one at http://mozilla.org/MPL/2.0/.
+# 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 enum import IntEnum
 from io import IOBase
 from pathlib import Path
-from typing import AnyStr, BinaryIO, Iterable, Optional, Union
+from typing import AnyStr, BinaryIO, Iterable, Union
 from warnings import warn
 
-from ocrmypdf._logging import PageNumberFilter, TqdmConsole
+import pluggy
+
+from ocrmypdf._logging import PageNumberFilter
 from ocrmypdf._plugin_manager import get_plugin_manager
 from ocrmypdf._sync import run_pipeline
 from ocrmypdf._validation import check_options
 from ocrmypdf.cli import ArgumentParser, get_parser
 from ocrmypdf.helpers import is_iterable_notstr
 
-try:
-    import coloredlogs
-except ModuleNotFoundError:
-    coloredlogs = None
-
-
 StrPath = Union[Path, AnyStr]
 PathOrIO = Union[BinaryIO, StrPath]
 
@@ -37,6 +34,7 @@ _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
@@ -48,7 +46,7 @@ def configure_logging(
     *,
     progress_bar_friendly: bool = True,
     manage_root_logger: bool = False,
-    plugin_manager=None,
+    plugin_manager: pluggy.PluginManager | None = None,
 ):
     """Set up logging.
 
@@ -88,7 +86,6 @@ def configure_logging(
     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)
@@ -115,17 +112,9 @@ def configure_logging(
     else:
         fmt = '%(pageno)s%(message)s'
 
-    use_colors = progress_bar_friendly
-    if not coloredlogs:
-        use_colors = False
-    if use_colors:
-        if os.name == 'nt':
-            use_colors = coloredlogs.enable_ansi_support()
-        if use_colors:
-            use_colors = coloredlogs.terminal_supports_colors()
-    if use_colors:
-        formatter = coloredlogs.ColoredFormatter(fmt=fmt)
-    else:
+    formatter = None
+
+    if not formatter:
         formatter = logging.Formatter(fmt=fmt)
 
     console.setFormatter(formatter)
@@ -145,7 +134,21 @@ def configure_logging(
 
 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 = []
 
@@ -193,7 +196,7 @@ def create_options(
     else:
         cmdline.append(os.fspath(output_file))
 
-    parser._api_mode = True
+    parser.enable_api_mode()
     options = parser.parse_args(cmdline)
     for keyword, val in deferred:
         setattr(options, keyword, val)
@@ -206,59 +209,73 @@ def create_options(
     return options
 
 
-def ocr(  # pylint: disable=unused-argument
+def ocr(  # noqa: ruff: disable=D417
     input_file: PathOrIO,
     output_file: PathOrIO,
     *,
-    language: Iterable[str] = None,
-    image_dpi: int = None,
-    output_type=None,
-    sidecar: Optional[StrPath] = None,
-    jobs: int = None,
-    use_threads: bool = None,
-    title: str = None,
-    author: str = None,
-    subject: str = None,
-    keywords: str = None,
-    rotate_pages: bool = None,
-    remove_background: bool = None,
-    deskew: bool = None,
-    clean: bool = None,
-    clean_final: bool = None,
-    unpaper_args: str = None,
-    oversample: int = None,
-    remove_vectors: bool = None,
-    force_ocr: bool = None,
-    skip_text: bool = None,
-    redo_ocr: bool = None,
-    skip_big: float = None,
-    optimize: int = None,
-    jpg_quality: int = None,
-    png_quality: int = None,
-    jbig2_lossy: bool = None,
-    jbig2_page_group_size: int = None,
-    pages: str = None,
-    max_image_mpixels: float = None,
-    tesseract_config: Iterable[str] = None,
-    tesseract_pagesegmode: int = None,
-    tesseract_oem: int = None,
-    tesseract_thresholding: int = None,
-    pdf_renderer=None,
-    tesseract_timeout: float = None,
-    rotate_pages_threshold: float = None,
-    pdfa_image_compression=None,
-    user_words: os.PathLike = None,
-    user_patterns: os.PathLike = None,
-    fast_web_view: float = None,
-    plugins: Iterable[StrPath] = None,
+    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,
+    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,
+    rotate_pages_threshold: float | None = None,
+    pdfa_image_compression: 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,
+    plugins: Iterable[StrPath] | None = None,
     plugin_manager=None,
-    keep_temporary_files: bool = None,
-    progress_bar: bool = 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:
@@ -280,9 +297,8 @@ def ocr(  # pylint: disable=unused-argument
             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.PdfMergeFailedError: If the input PDF is malformed, preventing merging
-            with the OCR layer.
         ocrmypdf.MissingDependencyError: If a required dependency program is missing or
             was not found on PATH.
         ocrmypdf.UnsupportedImageFormatError: If the input file type was an image that
@@ -295,7 +311,7 @@ def ocr(  # pylint: disable=unused-argument
             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.EncryptedPdfError: If the input PDF is encrypted (password protected).
             OCRmyPDF does not remove passwords.
         ocrmypdf.TesseractConfigError: If Tesseract reported its configuration was not
             valid.
@@ -339,7 +355,6 @@ def ocr(  # pylint: disable=unused-argument
 
 __all__ = [
     'PageNumberFilter',
-    'TqdmConsole',
     'Verbosity',
     'check_options',
     'configure_logging',

src/ocrmypdf/builtin_plugins/__init__.py

@@ -1,9 +1,6 @@
-# © 2020 James R. Barlow: github.com/jbarlow83
-#
-# This Source Code Form is subject to the terms of the Mozilla Public
-# License, v. 2.0. If a copy of the MPL was not distributed with this
-# file, You can obtain one at http://mozilla.org/MPL/2.0/.
+# SPDX-FileCopyrightText: 2022 James R. Barlow
+# SPDX-License-Identifier: MPL-2.0
 
-# This file exists only mark builtin_plugins as a package.
-# The plugin manager will not load it, so anything defined here may not be
-# processed as a module.
+"""Plugins in this package are automatically loaded by ocrmypdf."""
+
+from __future__ import annotations

src/ocrmypdf/builtin_plugins/concurrency.py

@@ -1,15 +1,8 @@
-# © 2020 James R. Barlow: github.com/jbarlow83
-#
-# This Source Code Form is subject to the terms of the Mozilla Public
-# License, v. 2.0. If a copy of the MPL was not distributed with this
-# file, You can obtain one at http://mozilla.org/MPL/2.0/.
-
-# © 2020 James R. Barlow: github.com/jbarlow83
-#
-# This Source Code Form is subject to the terms of the Mozilla Public
-# License, v. 2.0. If a copy of the MPL was not distributed with this
-# file, You can obtain one at http://mozilla.org/MPL/2.0/.
+# 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
@@ -21,13 +14,12 @@ import sys
 import threading
 from concurrent.futures import ProcessPoolExecutor, ThreadPoolExecutor, as_completed
 from contextlib import suppress
-from multiprocessing.pool import Pool, ThreadPool
 from typing import Callable, Iterable, Type, Union
 
-from tqdm import tqdm
+from rich.console import Console as RichConsole
 
 from ocrmypdf import Executor, hookimpl
-from ocrmypdf._logging import TqdmConsole
+from ocrmypdf._logging import RichLoggingHandler, RichTqdmProgressAdapter
 from ocrmypdf.exceptions import InputFileError
 from ocrmypdf.helpers import remove_all_log_handlers
 
@@ -38,15 +30,15 @@ WorkerInit = Callable[[Queue, UserInit, int], None]
 
 
 def log_listener(q: Queue):
-    """Listen to the worker processes and forward the messages to logging
+    """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
+    See:
+    https://docs.python.org/3/howto/logging-cookbook.html#logging-to-a-single-file-from-multiple-processes
     """
-
     while True:
         try:
             record = q.get()
@@ -62,12 +54,12 @@ def log_listener(q: Queue):
 
 
 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"""
-
+    """Initialize a process pool worker."""
     # Ignore SIGINT (our parent process will kill us gracefully)
     signal.signal(signal.SIGINT, signal.SIG_IGN)
 
@@ -76,7 +68,7 @@ def process_init(q: Queue, user_init: UserInit, loglevel) -> None:
         # Windows and Cygwin do not have pthread_sigmask or SIGBUS
         signal.signal(signal.SIGBUS, process_sigbus)
 
-    # Remove any log handlers that belong to the parent process
+    # Remove any log handlers inherited from the parent process
     root = logging.getLogger()
     remove_all_log_handlers(root)
 
@@ -89,6 +81,9 @@ def process_init(q: Queue, user_init: UserInit, loglevel) -> None:
 
 
 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})
@@ -98,6 +93,8 @@ def thread_init(q: Queue, user_init: UserInit, loglevel) -> None:
 
 
 class StandardExecutor(Executor):
+    """Standard OCRmyPDF concurrent task executor."""
+
     def _execute(
         self,
         *,
@@ -158,14 +155,24 @@ class StandardExecutor(Executor):
 
 @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 tqdm
+    """Return the default progress bar class."""
+
+    def partial_RichTqdmProgressAdapter(*args, **kwargs):
+        return RichTqdmProgressAdapter(*args, **kwargs, console=RICH_CONSOLE)
+
+    return partial_RichTqdmProgressAdapter
 
 
 @hookimpl
 def get_logging_console():
-    return logging.StreamHandler(stream=TqdmConsole(sys.stderr))
+    """Return the default logging console handler."""
+    return RichLoggingHandler(console=RICH_CONSOLE)

src/ocrmypdf/builtin_plugins/default_filters.py

@@ -1,8 +1,8 @@
-# © 2021 James R. Barlow: github.com/jbarlow83
-#
-# This Source Code Form is subject to the terms of the Mozilla Public
-# License, v. 2.0. If a copy of the MPL was not distributed with this
-# file, You can obtain one at http://mozilla.org/MPL/2.0/.
+# 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
 

src/ocrmypdf/builtin_plugins/ghostscript.py

@@ -1,56 +1,79 @@
-# © 2020 James R. Barlow: github.com/jbarlow83
-#
-# This Source Code Form is subject to the terms of the Mozilla Public
-# License, v. 2.0. If a copy of the MPL was not distributed with this
-# file, You can obtain one at http://mozilla.org/MPL/2.0/.
+# SPDX-FileCopyrightText: 2022 James R. Barlow
+# SPDX-License-Identifier: MPL-2.0
+"""Built-in plugin to implement PDF page rasterization and PDF/A production."""
 
+from __future__ import annotations
 
 import logging
 
 from ocrmypdf import hookimpl
 from ocrmypdf._exec import ghostscript
-from ocrmypdf._validation import HOCR_OK_LANGS
 from ocrmypdf.exceptions import MissingDependencyError
 from ocrmypdf.subprocess import check_external_program
 
 log = logging.getLogger(__name__)
 
+# Currently all blacklisted versions are lower than 9.55, so none need to
+# be added here. If a future version is blacklisted, add it here.
+BLACKLISTED_GS_VERSIONS: frozenset[str] = frozenset()
+
+
+@hookimpl
+def add_options(parser):
+    gs = parser.add_argument_group("Ghostscript", "Advanced control of Ghostscript")
+    gs.add_argument(
+        '--color-conversion-strategy',
+        action='store',
+        type=str,
+        metavar='STRATEGY',
+        choices=ghostscript.COLOR_CONVERSION_STRATEGIES,
+        default='LeaveColorUnchanged',
+        help="Set Ghostscript color conversion strategy",
+    )
+    gs.add_argument(
+        '--pdfa-image-compression',
+        choices=['auto', 'jpeg', 'lossless'],
+        default='auto',
+        help="Specify how to compress images in the output PDF/A. 'auto' lets "
+        "OCRmyPDF decide.  'jpeg' changes all grayscale and color images to "
+        "JPEG compression.  'lossless' uses PNG-style lossless compression "
+        "for all images.  Monochrome images are always compressed using a "
+        "lossless codec.  Compression settings "
+        "are applied to all pages, including those for which OCR was "
+        "skipped.  Not supported for --output-type=pdf ; that setting "
+        "preserves the original compression of all images.",
+    )
+
 
 @hookimpl
 def check_options(options):
+    """Check that the options are valid for this plugin."""
     check_external_program(
         program='gs',
         package='ghostscript',
         version_checker=ghostscript.version,
-        need_version='9.15',  # limited by Travis CI / Ubuntu 14.04 backports
+        need_version='9.55',  # Ubuntu 22.04's version
     )
     gs_version = ghostscript.version()
-    if gs_version in ('9.24', '9.51'):
+    if gs_version in BLACKLISTED_GS_VERSIONS:
         raise MissingDependencyError(
             f"Ghostscript {gs_version} contains serious regressions and is not "
             "supported. Please upgrade to a newer version, or downgrade to the "
             "previous version."
         )
 
-    # We have these constraints to check for.
-    # 1. Ghostscript < 9.20 mangles multibyte Unicode
-    # 2. hocr doesn't work on non-Latin languages (so don't select it)
-    is_latin = options.languages.issubset(HOCR_OK_LANGS)
-    if gs_version < '9.20' and options.output_type != 'pdf' and not is_latin:
-        # https://bugs.ghostscript.com/show_bug.cgi?id=696874
-        # Ghostscript < 9.20 fails to encode multibyte characters properly
-        log.warning(
-            f"The installed version of Ghostscript ({gs_version}) does not work "
-            "correctly with the OCR languages you specified. Use --output-type pdf or "
-            "upgrade to Ghostscript 9.20 or later to avoid this issue."
-        )
-
     if options.output_type == 'pdfa':
         options.output_type = 'pdfa-2'
-
-    if options.output_type == 'pdfa-3' and ghostscript.version() < '9.19':
-        raise MissingDependencyError(
-            "--output-type pdfa-3 requires Ghostscript 9.19 or later"
+    if options.color_conversion_strategy not in ghostscript.COLOR_CONVERSION_STRATEGIES:
+        raise ValueError(
+            f"Invalid color conversion strategy: {options.color_conversion_strategy}"
+        )
+    if options.pdfa_image_compression != 'auto' and not options.output_type.startswith(
+        'pdfa'
+    ):
+        log.warning(
+            "--pdfa-image-compression argument only applies when "
+            "--output-type is one of 'pdfa', 'pdfa-1', or 'pdfa-2'"
         )
 
 
@@ -64,7 +87,9 @@ def rasterize_pdf_page(
     page_dpi,
     rotation,
     filter_vector,
+    stop_on_soft_error,
 ):
+    """Rasterize a single page of a PDF file using Ghostscript."""
     ghostscript.rasterize_pdf(
         input_file,
         output_file,
@@ -74,6 +99,7 @@ def rasterize_pdf_page(
         page_dpi=page_dpi,
         rotation=rotation,
         filter_vector=filter_vector,
+        stop_on_error=stop_on_soft_error,
     )
     return output_file
 
@@ -83,17 +109,21 @@ def generate_pdfa(
     pdf_pages,
     pdfmark,
     output_file,
-    compression,
+    context,
     pdf_version,
     pdfa_part,
     progressbar_class,
+    stop_on_soft_error,
 ):
+    """Generate a PDF/A from the list of PDF pages and PDF/A metadata."""
     ghostscript.generate_pdfa(
         pdf_pages=[*pdf_pages, pdfmark],
         output_file=output_file,
-        compression=compression,
+        compression=context.options.pdfa_image_compression,
+        color_conversion_strategy=context.options.color_conversion_strategy,
         pdf_version=pdf_version,
         pdfa_part=pdfa_part,
         progressbar_class=progressbar_class,
+        stop_on_error=stop_on_soft_error,
     )
     return output_file

src/ocrmypdf/builtin_plugins/optimize.py

@@ -0,0 +1,165 @@
+# SPDX-FileCopyrightText: 2022 James R. Barlow
+# SPDX-License-Identifier: MPL-2.0
+"""Built-in plugin to implement PDF page optimization."""
+
+from __future__ import annotations
+
+import argparse
+import logging
+from pathlib import Path
+from typing import Sequence
+
+from ocrmypdf import Executor, PdfContext, hookimpl
+from ocrmypdf._exec import jbig2enc, pngquant
+from ocrmypdf._pipeline import get_pdf_save_settings
+from ocrmypdf.cli import numeric
+from ocrmypdf.optimize import optimize
+from ocrmypdf.subprocess import check_external_program
+
+log = logging.getLogger(__name__)
+
+
+@hookimpl
+def add_options(parser):
+    optimizing = parser.add_argument_group(
+        "Optimization options", "Control how the PDF is optimized after OCR"
+    )
+    optimizing.add_argument(
+        '-O',
+        '--optimize',
+        type=int,
+        choices=range(0, 4),
+        default=1,
+        help=(
+            "Control how PDF is optimized after processing:"
+            "0 - do not optimize; "
+            "1 - do safe, lossless optimizations (default); "
+            "2 - do lossy JPEG and JPEG2000 optimizations; "
+            "3 - do more aggressive lossy JPEG and JPEG2000 optimizations. "
+            "To enable lossy JBIG2, see --jbig2-lossy."
+        ),
+    )
+    optimizing.add_argument(
+        '--jpeg-quality',
+        type=numeric(int, 0, 100),
+        default=0,
+        metavar='Q',
+        help=(
+            "Adjust JPEG quality level for JPEG optimization. "
+            "100 is best quality and largest output size; "
+            "1 is lowest quality and smallest output; "
+            "0 uses the default."
+        ),
+    )
+    optimizing.add_argument(
+        '--jpg-quality',
+        type=numeric(int, 0, 100),
+        default=0,
+        metavar='Q',
+        dest='jpeg_quality',
+        help=argparse.SUPPRESS,  # Alias for --jpeg-quality
+    )
+    optimizing.add_argument(
+        '--png-quality',
+        type=numeric(int, 0, 100),
+        default=0,
+        metavar='Q',
+        help=(
+            "Adjust PNG quality level to use when quantizing PNGs. "
+            "Values have same meaning as with --jpeg-quality"
+        ),
+    )
+    optimizing.add_argument(
+        '--jbig2-lossy',
+        action='store_true',
+        help=(
+            "Enable JBIG2 lossy mode (better compression, not suitable for some "
+            "use cases - see documentation). Only takes effect if --optimize 1 or "
+            "higher is also enabled."
+        ),
+    )
+    optimizing.add_argument(
+        '--jbig2-page-group-size',
+        type=numeric(int, 1, 10000),
+        default=0,
+        metavar='N',
+        # Adjust number of pages to consider at once for JBIG2 compression
+        help=argparse.SUPPRESS,
+    )
+    optimizing.add_argument(
+        '--jbig2-threshold',
+        type=numeric(float, 0.4, 0.9),
+        default=0.85,
+        metavar='T',
+        help=(
+            "Adjust JBIG2 symbol code classification threshold "
+            "(default 0.85), range 0.4 to 0.9."
+        ),
+    )
+
+
+@hookimpl
+def check_options(options):
+    if options.optimize >= 2:
+        check_external_program(
+            program='pngquant',
+            package='pngquant',
+            version_checker=pngquant.version,
+            need_version='2.12.2',
+            required_for='--optimize {2,3}',
+        )
+
+    if options.optimize >= 2:
+        # Although we use JBIG2 for optimize=1, don't nag about it unless the
+        # user is asking for more optimization
+        check_external_program(
+            program='jbig2',
+            package='jbig2enc',
+            version_checker=jbig2enc.version,
+            need_version='0.28',
+            required_for='--optimize {2,3} | --jbig2-lossy',
+            recommended=True if not options.jbig2_lossy else False,
+        )
+
+    if options.optimize == 0 and any(
+        [options.jbig2_lossy, options.png_quality, options.jpeg_quality]
+    ):
+        log.warning(
+            "The arguments --jbig2-lossy, --png-quality, and --jpeg-quality "
+            "will be ignored because --optimize=0."
+        )
+
+
+@hookimpl
+def optimize_pdf(
+    input_pdf: Path,
+    output_pdf: Path,
+    context: PdfContext,
+    executor: Executor,
+    linearize: bool,
+) -> tuple[Path, Sequence[str]]:
+    save_settings = dict(
+        linearize=linearize,
+        **get_pdf_save_settings(context.options.output_type),
+    )
+    result_path = optimize(input_pdf, output_pdf, context, save_settings, executor)
+    messages = []
+    if context.options.optimize == 0:
+        messages.append("Optimization was disabled.")
+    else:
+        image_optimizers = {
+            'jbig2': jbig2enc.available(),
+            'pngquant': pngquant.available(),
+        }
+        for name, available in image_optimizers.items():
+            if not available:
+                messages.append(
+                    f"The optional dependency '{name}' was not found, so some image "
+                    f"optimizations could not be attempted."
+                )
+    return result_path, messages
+
+
+@hookimpl
+def is_optimization_enabled(context: PdfContext) -> bool:
+    return context.options.optimize != 0

src/ocrmypdf/builtin_plugins/tesseract_ocr.py

@@ -1,17 +1,21 @@
-# © 2020 James R. Barlow: github.com/jbarlow83
-#
-# This Source Code Form is subject to the terms of the Mozilla Public
-# License, v. 2.0. If a copy of the MPL was not distributed with this
-# file, You can obtain one at http://mozilla.org/MPL/2.0/.
+# SPDX-FileCopyrightText: 2022 James R. Barlow
+# SPDX-License-Identifier: MPL-2.0
+"""Built-in plugin to implement OCR using Tesseract."""
 
 
+from __future__ import annotations
+
 import logging
 import os
 
+from PIL import Image
+
 from ocrmypdf import hookimpl
 from ocrmypdf._exec import tesseract
+from ocrmypdf._jobcontext import PageContext
 from ocrmypdf.cli import numeric, str_to_int
 from ocrmypdf.helpers import clamp
+from ocrmypdf.imageops import calculate_downsample, downsample_image
 from ocrmypdf.pluginspec import OcrEngine
 from ocrmypdf.subprocess import check_external_program
 
@@ -26,7 +30,7 @@ def add_options(parser):
         action='append',
         metavar='CFG',
         default=[],
-        help="Additional Tesseract configuration files -- see documentation",
+        help="Additional Tesseract configuration files -- see documentation.",
     )
     tess.add_argument(
         '--tesseract-pagesegmode',
@@ -34,7 +38,7 @@ def add_options(parser):
         type=int,
         metavar='PSM',
         choices=range(0, 14),
-        help="Set Tesseract page segmentation mode (see tesseract --help)",
+        help="Set Tesseract page segmentation mode (see tesseract --help).",
     )
     tess.add_argument(
         '--tesseract-oem',
@@ -43,7 +47,7 @@ def add_options(parser):
         metavar='MODE',
         choices=range(0, 4),
         help=(
-            "Set Tesseract 4.0+ OCR engine mode: "
+            "Set Tesseract 4+ OCR engine mode: "
             "0 - original Tesseract only; "
             "1 - neural nets LSTM only; "
             "2 - Tesseract + LSTM; "
@@ -58,7 +62,7 @@ def add_options(parser):
         metavar='METHOD',
         help=(
             "Set Tesseract 5.0+ input image thresholding mode. This may improve OCR "
-            "results on low quality images or those that contain high constrast color. "
+            "results on low quality images or those that contain high contrast color. "
             "legacy-otsu is the Tesseract default; adaptive-otsu is an improved Otsu "
             "algorithm with improved sort for background color changes; sauvola is "
             "based on local standard deviation."
@@ -69,8 +73,51 @@ def add_options(parser):
         default=180.0,
         type=numeric(float, 0),
         metavar='SECONDS',
-        help='Give up on OCR after the timeout, but copy the preprocessed page '
-        'into the final output',
+        help=(
+            "Give up on OCR after the timeout, but copy the preprocessed page "
+            "into the final output. This timeout is only used when using Tesseract "
+            "for OCR. When Tesseract is used for other operations such as "
+            "deskewing and orientation, the timeout is controlled by "
+            "--tesseract-non-ocr-timeout."
+        ),
+    )
+    tess.add_argument(
+        '--tesseract-non-ocr-timeout',
+        default=180.0,
+        type=numeric(float, 0),
+        metavar='SECONDS',
+        help=(
+            "Give up on non-OCR operations such as deskewing and orientation "
+            "after timeout. This is a separate timeout from --tesseract-timeout "
+            "because these operations are not as expensive as OCR."
+        ),
+    )
+    tess.add_argument(
+        '--tesseract-downsample-large-images',
+        action='store_true',
+        help=(
+            "Downsample large images before OCR. Tesseract has an upper limit on the "
+            "size images it will support. If this argument is given, OCRmyPDF will "
+            "downsample large images to fit Tesseract. This may reduce OCR quality, "
+            "on large images the most desirable text is usually larger. If this "
+            "parameter is not supplied, Tesseract will error out and produce no OCR "
+            "on the page in question. This argument should be used with a high value "
+            "of --tesseract-timeout to ensure Tesseract has enough to time."
+        ),
+    )
+    tess.add_argument(
+        '--tesseract-downsample-above',
+        action='store',
+        type=numeric(int, 100, 32767),
+        default=32767,
+        help=(
+            "Downsample images larger than this size pixel size in either dimension "
+            "before OCR. --tesseract-downsample-large-images downsamples only when "
+            "an image exceeds Tesseract's internal limits. This argument causes "
+            "downsampling to occur when an image exceeds the given size. This may "
+            "reduce OCR quality, but on large images the most desirable text is "
+            "usually larger."
+        ),
     )
     tess.add_argument(
         '--user-words',
@@ -93,7 +140,7 @@ def check_options(options):
         program='tesseract',
         package={'linux': 'tesseract-ocr'},
         version_checker=tesseract.version,
-        need_version='4.0.0-beta.1',  # using backport for Travis CI
+        need_version='4.1.1',  # Ubuntu 22.04 version (also 20.04)
         version_parser=tesseract.TesseractVersion,
     )
 
@@ -101,11 +148,6 @@ def check_options(options):
     if options.pdf_renderer == 'auto':
         options.pdf_renderer = 'sandwich'
 
-    if not tesseract.has_user_words() and (options.user_words or options.user_patterns):
-        log.warning(
-            "Tesseract 4.0 (which you have installed) ignores --user-words and "
-            "--user-patterns, so these arguments have no effect."
-        )
     if not tesseract.has_thresholding() and options.tesseract_thresholding != 0:
         log.warning(
             "The installed version of Tesseract does not support changes to its "
@@ -136,11 +178,41 @@ def validate(pdfinfo, options):
         tess_threads = int(os.environ['OMP_THREAD_LIMIT'])
     log.debug("Using Tesseract OpenMP thread limit %d", tess_threads)
 
+    if (
+        options.tesseract_downsample_above != 32767
+        and not options.tesseract_downsample_large_images
+    ):
+        log.warning(
+            "The --tesseract-downsample-above argument will have no effect unless "
+            "--tesseract-downsample-large-images is also given."
+        )
+
+
+@hookimpl
+def filter_ocr_image(page: PageContext, image: Image.Image) -> Image.Image:
+    """Filter the image before OCR.
+
+    Tesseract cannot handle images with more than 32767 pixels in either axis,
+    or more than 2**31 bytes. This function resizes the image to fit within
+    those limits.
+    """
+    threshold = min(page.options.tesseract_downsample_above, 32767)
+
+    options = page.options
+    if options.tesseract_downsample_large_images:
+        size = calculate_downsample(
+            image, max_size=(threshold, threshold), max_bytes=(2**31) - 1
+        )
+        image = downsample_image(image, size)
+    return image
+
 
 class TesseractOcrEngine(OcrEngine):
+    """Implements OCR with Tesseract."""
+
     @staticmethod
     def version():
-        return tesseract.version()
+        return str(tesseract.version())
 
     @staticmethod
     def creator_tag(options):
@@ -159,7 +231,7 @@ class TesseractOcrEngine(OcrEngine):
         return tesseract.get_orientation(
             input_file,
             engine_mode=options.tesseract_oem,
-            timeout=options.tesseract_timeout,
+            timeout=options.tesseract_non_ocr_timeout,
         )
 
     @staticmethod
@@ -168,7 +240,7 @@ class TesseractOcrEngine(OcrEngine):
             input_file,
             languages=options.languages,
             engine_mode=options.tesseract_oem,
-            timeout=options.tesseract_timeout,
+            timeout=options.tesseract_non_ocr_timeout,
         )
 
     @staticmethod

src/ocrmypdf/cli.py

@@ -1,12 +1,12 @@
-# © 2015-19 James R. Barlow: github.com/jbarlow83
-#
-# This Source Code Form is subject to the terms of the Mozilla Public
-# License, v. 2.0. If a copy of the MPL was not distributed with this
-# file, You can obtain one at http://mozilla.org/MPL/2.0/.
+# SPDX-FileCopyrightText: 2022 James R. Barlow
+# SPDX-License-Identifier: MPL-2.0
 
+"""Command line interface customization and validation."""
+
+from __future__ import annotations
 
 import argparse
-from typing import Any, Callable, Mapping, Optional, TypeVar
+from typing import Any, Callable, Mapping, TypeVar
 
 from ocrmypdf._version import PROGRAM_NAME as _PROGRAM_NAME
 from ocrmypdf._version import __version__ as _VERSION
@@ -14,10 +14,12 @@ from ocrmypdf._version import __version__ as _VERSION
 T = TypeVar('T', int, float)
 
 
-def numeric(
-    basetype: Callable[[Any], T], min_: Optional[T] = None, max_: Optional[T] = None
-):
-    """Validator for numeric params"""
+def numeric(basetype: Callable[[Any], T], min_: T | None = None, max_: T | None = None):
+    """Validator for numeric command line parameters.
+
+    Stipulates that the value must be of type basetype (typically int or float), and
+    optionally, within the range [min_, max_].
+    """
     min_ = basetype(min_) if min_ is not None else None
     max_ = basetype(max_) if max_ is not None else None
 
@@ -42,22 +44,38 @@ def str_to_int(mapping: Mapping[str, int]):
         except KeyError:
             raise argparse.ArgumentTypeError(
                 f"{s!r} must be one of: {', '.join(mapping.keys())}"
-            )
+            ) from None
 
     return _str_to_int
 
 
 class ArgumentParser(argparse.ArgumentParser):
-    """Override parser's default behavior of calling sys.exit()
+    """Override parser's default behavior of calling sys.exit().
 
     https://stackoverflow.com/questions/5943249/python-argparse-and-controlling-overriding-the-exit-status-code
+
+    OCRmyPDF began as a CLI but eventually acquired an API. The API works inside out,
+    by synthesizing a command line argument. So we subclass the standard parser with
+    one that doesn't call sys.exit(). Obviously this is not the ideal way to do things
+    but it works for us.
     """
 
     def __init__(self, *args, **kwargs):
+        """Initialize the parser."""
         super().__init__(*args, **kwargs)
         self._api_mode = False
 
+    def enable_api_mode(self):
+        """Enable API mode.
+
+        When set, the parser will not call sys.exit() on error. OCRmyPDF was originally
+        a command line program, but now it has an API. The API works by synthesizing
+        command line arguments.
+        """
+        self._api_mode = True
+
     def error(self, message):
+        """Override the default argparse error behavior."""
         if not self._api_mode:
             super().error(message)
             return
@@ -65,20 +83,25 @@ class ArgumentParser(argparse.ArgumentParser):
 
 
 class LanguageSetAction(argparse.Action):
+    """Manages a list of languages."""
+
     def __init__(self, option_strings, dest, default=None, **kwargs):
+        """Initialize the action."""
         if default is None:
-            default = set()
+            default = list()
         super().__init__(option_strings, dest, default=default, **kwargs)
 
     def __call__(self, parser, namespace, values, option_string=None):
+        """Add a language to the set."""
         dest = getattr(namespace, self.dest)
         if '+' in values:
-            dest.update(lang for lang in values.split('+'))
+            [dest.append(lang) for lang in values.split('+')]
         else:
-            dest.add(values)
+            dest.append(values)
 
 
 def get_parser():
+    """Get the main CLI parser."""
     parser = ArgumentParser(
         prog=_PROGRAM_NAME,
         allow_abbrev=True,
@@ -142,7 +165,7 @@ Online documentation is located at:
         'output_file',
         metavar="output_pdf",
         help="Output searchable PDF file (or '-' to write to standard output). "
-        "Existing files will be ovewritten. If same as input file, the "
+        "Existing files will be overwritten. If same as input file, the "
         "input file will be updated only if processing is successful.",
     )
     parser.add_argument(
@@ -158,7 +181,9 @@ Online documentation is located at:
         '--image-dpi',
         metavar='DPI',
         type=int,
-        help="For input image instead of PDF, use this DPI instead of file's.",
+        help="When the input file is an image, not a PDF, use this DPI instead "
+        "of the DPI claimed by the input file. If the input does not claim a "
+        "sensible DPI, this option will be required.",
     )
     parser.add_argument(
         '--output-type',
@@ -228,7 +253,13 @@ Online documentation is located at:
         help=argparse.SUPPRESS,
     )
     jobcontrol.add_argument(
-        '--use-threads', action='store_true', help=argparse.SUPPRESS
+        '--use-threads', action='store_true', default=True, help=argparse.SUPPRESS
+    )
+    jobcontrol.add_argument(
+        '--no-use-threads',
+        action='store_false',
+        dest='use_threads',
+        help=argparse.SUPPRESS,
     )
 
     metadata = parser.add_argument_group(
@@ -334,71 +365,12 @@ Online documentation is located at:
         help="Skip OCR on pages larger than the specified amount of megapixels, "
         "but include skipped pages in final output",
     )
-
-    optimizing = parser.add_argument_group(
-        "Optimization options", "Control how the PDF is optimized after OCR"
-    )
-    optimizing.add_argument(
-        '-O',
-        '--optimize',
-        type=int,
-        choices=range(0, 4),
-        default=1,
-        help=(
-            "Control how PDF is optimized after processing:"
-            "0 - do not optimize; "
-            "1 - do safe, lossless optimizations (default); "
-            "2 - do lossy JPEG and JPEG2000 optimizations; "
-            "3 - do more aggressive lossy JPEG and JPEG2000 optimizations. "
-            "To enable lossy JBIG2, see --jbig2-lossy."
-        ),
-    )
-    optimizing.add_argument(
-        '--jpeg-quality',
-        type=numeric(int, 0, 100),
-        default=0,
-        metavar='Q',
-        help=(
-            "Adjust JPEG quality level for JPEG optimization. "
-            "100 is best quality and largest output size; "
-            "1 is lowest quality and smallest output; "
-            "0 uses the default."
-        ),
-    )
-    optimizing.add_argument(
-        '--jpg-quality',
-        type=numeric(int, 0, 100),
-        default=0,
-        metavar='Q',
-        dest='jpeg_quality',
-        help=argparse.SUPPRESS,  # Alias for --jpeg-quality
-    )
-    optimizing.add_argument(
-        '--png-quality',
-        type=numeric(int, 0, 100),
-        default=0,
-        metavar='Q',
-        help=(
-            "Adjust PNG quality level to use when quantizing PNGs. "
-            "Values have same meaning as with --jpeg-quality"
-        ),
-    )
-    optimizing.add_argument(
-        '--jbig2-lossy',
+    ocrsettings.add_argument(
+        '--invalidate-digital-signatures',
         action='store_true',
-        help=(
-            "Enable JBIG2 lossy mode (better compression, not suitable for some "
-            "use cases - see documentation). Only takes effect if --optimize 1 or "
-            "higher is also enabled."
-        ),
-    )
-    optimizing.add_argument(
-        '--jbig2-page-group-size',
-        type=numeric(int, 1, 10000),
-        default=0,
-        metavar='N',
-        # Adjust number of pages to consider at once for JBIG2 compression
-        help=argparse.SUPPRESS,
+        help="Normally, OCRmyPDF will refuse to OCR a PDF that has a digital "
+        "signature. This option allows OCR to proceed, but the digital signature "
+        "will be invalidated.",
     )
 
     advanced = parser.add_argument_group(
@@ -436,19 +408,6 @@ Online documentation is located at:
         help="Only rotate pages when confidence is above this value (arbitrary "
         "units reported by tesseract)",
     )
-    advanced.add_argument(
-        '--pdfa-image-compression',
-        choices=['auto', 'jpeg', 'lossless'],
-        default='auto',
-        help="Specify how to compress images in the output PDF/A. 'auto' lets "
-        "OCRmyPDF decide.  'jpeg' changes all grayscale and color images to "
-        "JPEG compression.  'lossless' uses PNG-style lossless compression "
-        "for all images.  Monochrome images are always compressed using a "
-        "lossless codec.  Compression settings "
-        "are applied to all pages, including those for which OCR was "
-        "skipped.  Not supported for --output-type=pdf ; that setting "
-        "preserves the original compression of all images.",
-    )
     advanced.add_argument(
         '--fast-web-view',
         type=numeric(float, 0),
@@ -461,6 +420,14 @@ Online documentation is located at:
         "which do not benefit. If the threshold is 0 it will be apply to all files. "
         "Set the threshold very high to disable.",
     )
+    advanced.add_argument(
+        '--continue-on-soft-render-error',
+        action='store_true',
+        help="Continue processing pages after a recoverable PDF rendering error. "
+        "A recoverable error is one that does not prevent the page from being "
+        "rendered, but may result in visual differences compared to the input "
+        "file. Missing fonts are a typical source of these errors.",
+    )
     advanced.add_argument(
         '--plugin',
         dest='plugins',

src/ocrmypdf/data/__init__.py

@@ -1,8 +1,5 @@
-# © 2021 James R. Barlow: github.com/jbarlow83
-#
-# This Source Code Form is subject to the terms of the Mozilla Public
-# License, v. 2.0. If a copy of the MPL was not distributed with this
-# file, You can obtain one at http://mozilla.org/MPL/2.0/.
-
-
+# SPDX-FileCopyrightText: 2022 James R. Barlow
+# SPDX-License-Identifier: MPL-2.0
 """Data files used to generate certain PDFs."""
+
+from __future__ import annotations

src/ocrmypdf/exceptions.py

@@ -1,15 +1,18 @@
-# © 2016 James R. Barlow: github.com/jbarlow83
-#
-# This Source Code Form is subject to the terms of the Mozilla Public
-# License, v. 2.0. If a copy of the MPL was not distributed with this
-# file, You can obtain one at http://mozilla.org/MPL/2.0/.
+# SPDX-FileCopyrightText: 2022 James R. Barlow
+# SPDX-License-Identifier: MPL-2.0
 
+"""OCRmyPDF's exceptions."""
+
+from __future__ import annotations
 
 from enum import IntEnum
 from textwrap import dedent
 
 
 class ExitCode(IntEnum):
+    """OCRmyPDF's exit codes."""
+
+    # pylint: disable=invalid-name
     ok = 0
     bad_args = 1
     input_file = 2
@@ -26,10 +29,13 @@ class ExitCode(IntEnum):
 
 
 class ExitCodeException(Exception):
+    """An exception which should return an exit code with sys.exit()."""
+
     exit_code = ExitCode.other_error
     message = ""
 
     def __str__(self):
+        """Return a string representation of the exception."""
         super_msg = super().__str__()  # Don't do str(super())
         if self.message:
             return self.message.format(super_msg)
@@ -37,56 +43,59 @@ class ExitCodeException(Exception):
 
 
 class BadArgsError(ExitCodeException):
+    """Invalid arguments on the command line or API."""
+
     exit_code = ExitCode.bad_args
 
 
-class PdfMergeFailedError(ExitCodeException):
-    exit_code = ExitCode.input_file
-    message = dedent(
-        '''\
-        Failed to merge PDF image layer with OCR layer
-
-        Usually this happens because the input PDF file is malformed and
-        ocrmypdf cannot automatically correct the problem on its own.
-
-        Try using
-            ocrmypdf --pdf-renderer sandwich  [..other args..]
-        '''
-    )
-
-
 class MissingDependencyError(ExitCodeException):
+    """A third-party dependency is missing."""
+
     exit_code = ExitCode.missing_dependency
 
 
 class UnsupportedImageFormatError(ExitCodeException):
+    """The image format is not supported."""
+
     exit_code = ExitCode.input_file
 
 
 class DpiError(ExitCodeException):
+    """Missing information about input image DPI."""
+
     exit_code = ExitCode.input_file
 
 
 class OutputFileAccessError(ExitCodeException):
+    """Cannot access the intended output file path."""
+
     exit_code = ExitCode.file_access_error
 
 
 class PriorOcrFoundError(ExitCodeException):
+    """This file already has OCR."""
+
     exit_code = ExitCode.already_done_ocr
 
 
 class InputFileError(ExitCodeException):
+    """Something is wrong with the input file."""
+
     exit_code = ExitCode.input_file
 
 
 class SubprocessOutputError(ExitCodeException):
+    """A subprocess returned an unexpected error."""
+
     exit_code = ExitCode.child_process_error
 
 
 class EncryptedPdfError(ExitCodeException):
+    """Input PDF is encrypted."""
+
     exit_code = ExitCode.encrypted_pdf
     message = dedent(
-        '''\
+        """\
         Input PDF is encrypted. The encryption must be removed to
         perform OCR.
 
@@ -95,10 +104,24 @@ class EncryptedPdfError(ExitCodeException):
 
         You can remove the encryption using
             qpdf --decrypt [--password=[password]] infilename
-        '''
+        """
+    )
+
+
+class DigitalSignatureError(ExitCodeException):
+    """PDF has a digital signature."""
+
+    exit_code = ExitCode.input_file
+    message = dedent(
+        """\
+        Input PDF has a digital signature. OCR would alter the document,
+        invalidating the signature.
+        """
     )
 
 
 class TesseractConfigError(ExitCodeException):
+    """Tesseract config can't be parsed."""
+
     exit_code = ExitCode.invalid_config
     message = "Error occurred while parsing a Tesseract configuration file"

src/ocrmypdf/extra_plugins/__init__.py

@@ -0,0 +1,9 @@
+# SPDX-FileCopyrightText: 2022 James R. Barlow
+#
+# SPDX-License-Identifier: MPL-2.0
+
+"""Extra plugins. These are not automatically inserted when ocrmypdf is run.
+
+You can use these plugins by specifying them on the command line, e.g.:
+ocrmypdf --plugin ocrmypdf.extra_plugins.semfree ...
+"""

src/ocrmypdf/extra_plugins/semfree.py

@@ -1,10 +1,5 @@
-# © 2021 James R. Barlow: github.com/jbarlow83
-#
-# This Source Code Form is subject to the terms of the Mozilla Public
-# License, v. 2.0. If a copy of the MPL was not distributed with this
-# file, You can obtain one at http://mozilla.org/MPL/2.0/.
-
-
+# SPDX-FileCopyrightText: 2022 James R. Barlow
+# SPDX-License-Identifier: MPL-2.0
 """Semaphore-free alternate executor.
 
 There are two popular environments that do not fully support the standard Python
@@ -17,9 +12,11 @@ worker communicates only with the main process.
 
 This is not without drawbacks. If the tasks are not "even" in size, which cannot
 be guaranteed, some workers may end up with too much work while others are idle.
-It is less efficient than the standard implementation, so not th edefault.
+It is less efficient than the standard implementation, so not the default.
 """
 
+from __future__ import annotations
+
 import logging
 import logging.handlers
 import signal
@@ -28,7 +25,7 @@ from enum import Enum, auto
 from itertools import islice, repeat, takewhile, zip_longest
 from multiprocessing import Pipe, Process
 from multiprocessing.connection import Connection, wait
-from typing import Callable, Iterable, Iterator, List
+from typing import Callable, Iterable, Iterator
 
 from ocrmypdf import Executor, hookimpl
 from ocrmypdf._concurrent import NullProgressBar
@@ -37,9 +34,11 @@ from ocrmypdf.helpers import remove_all_log_handlers
 
 
 class MessageType(Enum):
-    exception = auto()
-    result = auto()
-    complete = auto()
+    """Implement basic IPC messaging."""
+
+    exception = auto()  # pylint: disable=invalid-name
+    result = auto()  # pylint: disable=invalid-name
+    complete = auto()  # pylint: disable=invalid-name
 
 
 def split_every(n: int, iterable: Iterable) -> Iterator:
@@ -55,25 +54,29 @@ def split_every(n: int, iterable: Iterable) -> Iterator:
 
 
 def process_sigbus(*args):
+    """Handle SIGBUS signal at the worker level."""
     raise InputFileError("A worker process lost access to an input file")
 
 
 class ConnectionLogHandler(logging.handlers.QueueHandler):
+    """Handler used by child processes to forward log messages to parent."""
+
     def __init__(self, conn: Connection) -> None:
+        """Initialize the handler."""
         # sets the parent's queue to None - parent only touches queue
         # in enqueue() which we override
         super().__init__(None)  # type: ignore
         self.conn = conn
 
     def enqueue(self, record):
+        """Enqueue a log message."""
         self.conn.send(('log', record))
 
 
 def process_loop(
     conn: Connection, user_init: Callable[[], None], loglevel, task, task_args
 ):
-    """Initialize a process pool worker"""
-
+    """Initialize a process pool worker."""
     # 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
@@ -91,7 +94,7 @@ def process_loop(
     for args in task_args:
         try:
             result = task(args)
-        except Exception as e:
+        except Exception as e:  # pylint: disable=broad-except
             conn.send((MessageType.exception, e))
             break
         else:
@@ -103,6 +106,8 @@ def process_loop(
 
 
 class LambdaExecutor(Executor):
+    """Executor for AWS Lambda or similar environments that lack semaphores."""
+
     def _execute(
         self,
         *,
@@ -128,8 +133,8 @@ class LambdaExecutor(Executor):
         if not grouped_args:
             return
 
-        processes: List[Process] = []
-        connections: List[Connection] = []
+        processes: list[Process] = []
+        connections: list[Connection] = []
         for chunk in grouped_args:
             parent_conn, child_conn = Pipe()
 
@@ -153,24 +158,23 @@ class LambdaExecutor(Executor):
 
         with self.pbar_class(**tqdm_kwargs) as pbar:
             while connections:
-                for r in wait(connections):
-                    if not isinstance(r, Connection):
+                for result in wait(connections):
+                    if not isinstance(result, Connection):
                         raise NotImplementedError("We only support Connection()")
                     try:
-                        msg_type, msg = r.recv()
+                        msg_type, msg = result.recv()
                     except EOFError:
-                        connections.remove(r)
+                        connections.remove(result)
                         continue
 
                     if msg_type == MessageType.result:
-                        if task_finished:
-                            task_finished(msg, pbar)
+                        task_finished(msg, pbar)
                     elif msg_type == 'log':
                         record = msg
                         logger = logging.getLogger(record.name)
                         logger.handle(record)
                     elif msg_type == MessageType.complete:
-                        connections.remove(r)
+                        connections.remove(result)
                     elif msg_type == MessageType.exception:
                         for process in processes:
                             process.terminate()
@@ -182,14 +186,20 @@ class LambdaExecutor(Executor):
 
 @hookimpl
 def get_executor(progressbar_class):
+    """Return a LambdaExecutor instance."""
     return LambdaExecutor(pbar_class=progressbar_class)
 
 
 @hookimpl
 def get_logging_console():
+    """Return a logging.StreamHandler instance."""
     return logging.StreamHandler()
 
 
 @hookimpl
 def get_progressbar_class():
+    """Return a NullProgressBar instance.
+
+    This executor cannot use a progress bar.
+    """
     return NullProgressBar

src/ocrmypdf/helpers.py

@@ -1,46 +1,70 @@
-# © 2016 James R. Barlow: github.com/jbarlow83
-#
-# This Source Code Form is subject to the terms of the Mozilla Public
-# License, v. 2.0. If a copy of the MPL was not distributed with this
-# file, You can obtain one at http://mozilla.org/MPL/2.0/.
+# SPDX-FileCopyrightText: 2022 James R. Barlow
+# SPDX-License-Identifier: MPL-2.0
 
+"""Support functions."""
+
+from __future__ import annotations
 
 import logging
 import multiprocessing
 import os
 import shutil
 import warnings
-from collections import namedtuple
 from collections.abc import Iterable
 from contextlib import suppress
-from functools import wraps
+from decimal import Decimal
 from io import StringIO
 from math import isclose, isfinite
 from pathlib import Path
-from typing import Any, Sequence
+from statistics import harmonic_mean
+from typing import (
+    Any,
+    Callable,
+    Generic,
+    Sequence,
+    SupportsFloat,
+    SupportsRound,
+    TypeVar,
+)
 
+import img2pdf
 import pikepdf
 
 log = logging.getLogger(__name__)
 
+IMG2PDF_KWARGS = dict(engine=img2pdf.Engine.pikepdf, rotation=img2pdf.Rotation.ifvalid)
 
-class Resolution(namedtuple('Resolution', ('x', 'y'))):
+
+T = TypeVar('T', float, int, Decimal)
+
+
+class Resolution(Generic[T]):
     """The number of pixels per inch in each 2D direction.
 
     Resolution objects are considered "equal" for == purposes if they are
     equal to a reasonable tolerance.
     """
 
-    __slots__ = ()
+    x: T
+    y: T
+
+    __slots__ = ('x', 'y')
+
+    def __init__(self, x: T, y: T):
+        """Construct a Resolution object."""
+        self.x = x
+        self.y = y
 
     # rel_tol after converting from dpi to pixels per meter and saving
     # as integer with rounding, as many file formats
     CONVERSION_ERROR = 0.002
 
-    def round(self, ndigits: int):
+    def round(self, ndigits: int) -> Resolution:
+        """Round to ndigits after the decimal point."""
         return Resolution(round(self.x, ndigits), round(self.y, ndigits))
 
-    def to_int(self):
+    def to_int(self) -> Resolution[int]:
+        """Round to nearest integer."""
         return Resolution(int(round(self.x)), int(round(self.y)))
 
     @classmethod
@@ -49,31 +73,65 @@ class Resolution(namedtuple('Resolution', ('x', 'y'))):
 
     @property
     def is_square(self) -> bool:
+        """True if the resolution is square (x == y)."""
         return self._isclose(self.x, self.y)
 
     @property
     def is_finite(self) -> bool:
+        """True if both x and y are finite numbers."""
         return isfinite(self.x) and isfinite(self.y)
 
-    def take_max(self, vals, yvals=None):
-        if yvals is not None:
-            return Resolution(max(self.x, *vals), max(self.y, *yvals))
-        max_x, max_y = self.x, self.y
-        for x, y in vals:
-            max_x = max(x, max_x)
-            max_y = max(y, max_y)
-        return Resolution(max_x, max_y)
+    def to_scalar(self) -> float:
+        """Return the harmonic mean of x and y as a 1D approximation.
 
-    def flip_axis(self):
+        In most cases, Resolution is 2D, but typically it is "square" (x == y) and
+        can be approximated as a single number. When not square, the harmonic mean
+        is used to approximate the 2D resolution as a single number.
+        """
+        return harmonic_mean([float(self.x), float(self.y)])
+
+    def _take_minmax(
+        self, vals: Iterable[Any], yvals: Iterable[Any] | None, cmp: Callable
+    ) -> Resolution:
+        """Return a new Resolution object with the maximum resolution of inputs."""
+        if yvals is not None:
+            return Resolution(cmp(self.x, *vals), cmp(self.y, *yvals))
+        cmp_x, cmp_y = self.x, self.y
+        for x, y in vals:
+            cmp_x = cmp(x, cmp_x)
+            cmp_y = cmp(y, cmp_y)
+        return Resolution(cmp_x, cmp_y)
+
+    def take_max(
+        self, vals: Iterable[Any], yvals: Iterable[Any] | None = None
+    ) -> Resolution:
+        """Return a new Resolution object with the maximum resolution of inputs."""
+        return self._take_minmax(vals, yvals, max)
+
+    def take_min(
+        self, vals: Iterable[Any], yvals: Iterable[Any] | None = None
+    ) -> Resolution:
+        """Return a new Resolution object with the minimum resolution of inputs."""
+        return self._take_minmax(vals, yvals, min)
+
+    def flip_axis(self) -> Resolution[T]:
+        """Return a new Resolution object with x and y swapped."""
         return Resolution(self.y, self.x)
 
+    def __getitem__(self, idx: int | slice) -> T:
+        """Support [0] and [1] indexing."""
+        return (self.x, self.y)[idx]
+
     def __str__(self):
-        return f"{self.x:f}x{self.y:f}"
+        """Return a string representation of the resolution."""
+        return f"{self.x:f}×{self.y:f}"
 
     def __repr__(self):  # pragma: no cover
-        return f"Resolution({self.x}x{self.y} dpi)"
+        """Return a repr() of the resolution."""
+        return f"Resolution({self.x!r}, {self.y!r})"
 
     def __eq__(self, other):
+        """Return True if the resolution is equal to another resolution."""
         if isinstance(other, tuple) and len(other) == 2:
             other = Resolution(*other)
         if not isinstance(other, Resolution):
@@ -82,10 +140,10 @@ class Resolution(namedtuple('Resolution', ('x', 'y'))):
 
 
 class NeverRaise(Exception):
-    """An exception that is never raised"""
+    """An exception that is never raised."""
 
 
-def safe_symlink(input_file: os.PathLike, soft_link_name: os.PathLike):
+def safe_symlink(input_file: os.PathLike, soft_link_name: os.PathLike) -> None:
     """Create a symbolic link at ``soft_link_name``, which references ``input_file``.
 
     Think of this as copying ``input_file`` to ``soft_link_name`` with less overhead.
@@ -100,7 +158,7 @@ def safe_symlink(input_file: os.PathLike, soft_link_name: os.PathLike):
     # Guard against soft linking to oneself
     if input_file == soft_link_name:
         log.warning(
-            "No symbolic link created. You are using  the original data directory "
+            "No symbolic link created. You are using the original data directory "
             "as the working directory."
         )
         return
@@ -126,11 +184,15 @@ def safe_symlink(input_file: os.PathLike, soft_link_name: os.PathLike):
     os.symlink(os.path.abspath(input_file), soft_link_name)
 
 
-def samefile(f1: os.PathLike, f2: os.PathLike):
+def samefile(file1: os.PathLike, file2: os.PathLike) -> bool:
+    """Return True if two files are the same file.
+
+    Attempts to account for different relative paths to the same file.
+    """
     if os.name == 'nt':
-        return f1 == f2
+        return file1 == file2
     else:
-        return os.path.samefile(f1, f2)
+        return os.path.samefile(file1, file2)
 
 
 def is_iterable_notstr(thing: Any) -> bool:
@@ -138,13 +200,13 @@ def is_iterable_notstr(thing: Any) -> bool:
     return isinstance(thing, Iterable) and not isinstance(thing, str)
 
 
-def monotonic(L: Sequence) -> bool:
+def monotonic(seq: Sequence) -> bool:
     """Does this sequence increase monotonically?"""
-    return all(b > a for a, b in zip(L, L[1:]))
+    return all(b > a for a, b in zip(seq, seq[1:]))
 
 
 def page_number(input_file: os.PathLike) -> int:
-    """Get one-based page number implied by filename (000002.pdf -> 2)"""
+    """Get one-based page number implied by filename (000002.pdf -> 2)."""
     return int(os.path.basename(os.fspath(input_file))[0:6])
 
 
@@ -155,7 +217,7 @@ def available_cpu_count() -> int:
     except NotImplementedError:
         pass
     warnings.warn(
-        "Could not get CPU count.  Assuming one (1) CPU." "Use -j N to set manually."
+        "Could not get CPU count. Assuming one (1) CPU. Use -j N to set manually."
     )
     return 1
 
@@ -173,22 +235,22 @@ def is_file_writable(test_file: os.PathLike) -> bool:
             p = p.resolve(strict=False)
 
         # p.is_file() throws an exception in some cases
-        if p.exists() and p.is_file():
+        if p.exists() and (p.is_file() or p.samefile(os.devnull)):
             return os.access(
                 os.fspath(p),
                 os.W_OK,
                 effective_ids=(os.access in os.supports_effective_ids),
             )
+
+        try:
+            fp = p.open('wb')
+        except OSError:
+            return False
         else:
-            try:
-                fp = p.open('wb')
-            except OSError:
-                return False
-            else:
-                fp.close()
-                with suppress(OSError):
-                    p.unlink()
-            return True
+            fp.close()
+            with suppress(OSError):
+                p.unlink()
+        return True
     except (OSError, RuntimeError) as e:
         log.debug(e)
         log.error(str(e))
@@ -209,11 +271,19 @@ def check_pdf(input_file: Path) -> bool:
     else:
         with pdf:
             messages = pdf.check()
+            success = True
             for msg in messages:
                 if 'error' in msg.lower():
                     log.error(msg)
+                    success = False
+                elif (
+                    "/DecodeParms: operation for dictionary attempted on object "
+                    "of type null" in msg
+                ):
+                    pass  # Ignore/spurious warning
                 else:
                     log.warning(msg)
+                    success = False
 
             sio = StringIO()
             linearize_msgs = ''
@@ -228,48 +298,34 @@ def check_pdf(input_file: Path) -> bool:
                 if linearize_msgs:
                     log.warning(linearize_msgs)
 
-            if not messages and not linearize_msgs:
+            if success and not linearize_msgs:
                 return True
             return False
 
 
-def clamp(n, smallest, largest):  # mypy doesn't understand types for this
+def clamp(n: T, smallest: T, largest: T) -> T:
     """Clamps the value of ``n`` to between ``smallest`` and ``largest``."""
     return max(smallest, min(n, largest))
 
 
-def remove_all_log_handlers(logger):
-    "Remove all log handlers, usually used in a child process."
+def remove_all_log_handlers(logger: logging.Logger) -> None:
+    """Remove all log handlers, usually used in a child process.
+
+    The child process inherits the log handlers from the parent process when
+    a fork occurs. Typically we want to remove all log handlers in the child
+    process so that the child process can set up a single queue handler to
+    forward log messages to the parent process.
+    """
     for handler in logger.handlers[:]:
         logger.removeHandler(handler)
         handler.close()  # To ensure handlers with opened resources are released
 
 
-def pikepdf_enable_mmap():
-    # try:
-    #     if pikepdf._qpdf.set_access_default_mmap(True):
-    #         log.debug("pikepdf mmap enabled")
-    # except AttributeError:
-    #     log.debug("pikepdf mmap not available")
-    # We found a race condition probably related to pybind issue #2252 that can
-    # cause a crash. For now, disable pikepdf mmap to be on the safe side.
-    # Fix is not in pybind11 2.6.0
-    # log.debug("pikepdf mmap disabled")
-    return
-
-
-def deprecated(func):
-    """Warn that function is deprecated."""
-
-    @wraps(func)
-    def new_func(*args, **kwargs):
-        warnings.simplefilter('always', DeprecationWarning)  # turn off filter
-        warnings.warn(
-            f"Call to deprecated function {func.__name__}.",
-            category=DeprecationWarning,
-            stacklevel=2,
-        )
-        warnings.simplefilter('default', DeprecationWarning)  # reset filter
-        return func(*args, **kwargs)
-
-    return new_func
+def pikepdf_enable_mmap() -> None:
+    """Enable pikepdf mmap."""
+    try:
+        if pikepdf._core.set_access_default_mmap(True):
+            log.debug("pikepdf mmap enabled")
+    except AttributeError:
+        log.debug("pikepdf mmap not available")
+    log.debug("pikepdf mmap disabled")

src/ocrmypdf/hocrtransform.py

@@ -1,44 +1,31 @@
 #!/usr/bin/env python3
-#
-# Copyright (c) 2010, Jonathan Brinley
-#   Original version from: https://github.com/jbrinley/HocrConverter
-#
-# Copyright (c) 2013-14, Julien Pfefferkorn
-#   Modifications
-#
-# Copyright (c) 2015-16, James R. Barlow
-#   Set text to transparent
-#
-# Permission is hereby granted, free of charge, to any person obtaining a
-# copy of this software and associated documentation files (the
-# "Software"), to deal in the Software without restriction, including
-# without limitation the rights to use, copy, modify, merge, publish,
-# distribute, sublicense, and/or sell copies of the Software, and to
-# permit persons to whom the Software is furnished to do so, subject to
-# the following conditions:
-#
-# The above copyright notice and this permission notice shall be included
-# in all copies or substantial portions of the Software.
-#
-# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS
-# OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
-# MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
-# IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY
-# CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT,
-# TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE
-# SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
+# SPDX-FileCopyrightText: 2010 Jonathan Brinley
+# SPDX-FileCopyrightText: 2013-2014 Julien Pfefferkorn
+# SPDX-FileCopyrightText: 2022 James R. Barlow
+# SPDX-License-Identifier: MIT
+
+"""Transform .hocr and page image to text PDF."""
+
+from __future__ import annotations
 
 import argparse
 import os
 import re
+import warnings
 from math import atan, cos, sin
 from pathlib import Path
-from typing import Any, NamedTuple, Optional, Tuple, Union
+from typing import Any, NamedTuple
 from xml.etree import ElementTree
 
-from reportlab.lib.colors import black, cyan, magenta, red
-from reportlab.lib.units import inch
-from reportlab.pdfgen.canvas import Canvas
+with warnings.catch_warnings():
+    # reportlab uses deprecated load_module
+    # shim can be removed when we require reportlab >= 3.7
+    warnings.filterwarnings(
+        'ignore', category=DeprecationWarning, message=r".*load_module.*"
+    )
+    from reportlab.lib.colors import black, cyan, magenta, red
+    from reportlab.lib.units import inch
+    from reportlab.pdfgen.canvas import Canvas
 
 # According to Wikipedia these languages are supported in the ISO-8859-1 character
 # set, meaning reportlab can generate them and they are compatible with hocr,
@@ -99,7 +86,7 @@ HOCR_OK_LANGS = frozenset(
 Element = ElementTree.Element
 
 
-class Rect(NamedTuple):  # pylint: disable=inherit-non-class
+class Rect(NamedTuple):
     """A rectangle for managing PDF coordinates."""
 
     x1: Any
@@ -109,15 +96,14 @@ class Rect(NamedTuple):  # pylint: disable=inherit-non-class
 
 
 class HocrTransformError(Exception):
-    pass
+    """Error while applying hOCR transform."""
 
 
 class HocrTransform:
+    """A class for converting documents from the hOCR format.
 
-    """
-    A class for converting documents from the hOCR format.
     For details of the hOCR format, see:
-    http://kba.cloud/hocr-spec/
+    http://kba.cloud/hocr-spec/.
     """
 
     box_pattern = re.compile(r'bbox((\s+\d+){4})')
@@ -132,7 +118,8 @@ class HocrTransform:
         {'ff': 'ff', 'ffi': 'f‌f‌i', 'ffl': 'f‌f‌l', 'fi': 'fi', 'fl': 'fl'}
     )
 
-    def __init__(self, *, hocr_filename: Union[str, Path], dpi: float):
+    def __init__(self, *, hocr_filename: str | Path, dpi: float):
+        """Initialize the HocrTransform object."""
         self.dpi = dpi
         self.hocr = ElementTree.parse(os.fspath(hocr_filename))
 
@@ -157,9 +144,7 @@ class HocrTransform:
             raise HocrTransformError("hocr file is missing page dimensions")
 
     def __str__(self):  # pragma: no cover
-        """
-        Return the textual content of the HTML body
-        """
+        """Return the textual content of the HTML body."""
         if self.hocr is None:
             return ''
         body = self.hocr.find(self._child_xpath('body'))
@@ -169,9 +154,7 @@ class HocrTransform:
             return ''
 
     def _get_element_text(self, element: Element):
-        """
-        Return the textual content of the element and its children
-        """
+        """Return the textual content of the element and its children."""
         text = ''
         if element.text is not None:
             text += element.text
@@ -183,10 +166,7 @@ class HocrTransform:
 
     @classmethod
     def element_coordinates(cls, element: Element) -> Rect:
-        """
-        Returns a tuple containing the coordinates of the bounding box around
-        an element
-        """
+        """Get coordinates of the bounding box around an element."""
         out = Rect._make(0 for _ in range(4))
         if 'title' in element.attrib:
             matches = cls.box_pattern.search(element.attrib['title'])
@@ -196,10 +176,8 @@ class HocrTransform:
         return out
 
     @classmethod
-    def baseline(cls, element: Element) -> Tuple[float, float]:
-        """
-        Returns a tuple containing the baseline slope and intercept.
-        """
+    def baseline(cls, element: Element) -> tuple[float, float]:
+        """Get baseline's slope and intercept."""
         if 'title' in element.attrib:
             matches = cls.baseline_pattern.search(element.attrib['title'])
             if matches:
@@ -207,12 +185,10 @@ class HocrTransform:
         return (0.0, 0.0)
 
     def pt_from_pixel(self, pxl) -> Rect:
-        """
-        Returns the quantity in PDF units (pt) given quantity in pixels
-        """
+        """Returns the quantity in PDF units (pt) given quantity in pixels."""
         return Rect._make((c / self.dpi * inch) for c in pxl)
 
-    def _child_xpath(self, html_tag: str, html_class: Optional[str] = None) -> str:
+    def _child_xpath(self, html_tag: str, html_class: str | None = None) -> str:
         xpath = f".//{self.xmlns}{html_tag}"
         if html_class:
             xpath += f"[@class='{html_class}']"
@@ -220,33 +196,21 @@ class HocrTransform:
 
     @classmethod
     def replace_unsupported_chars(cls, s: str) -> str:
-        """
-        Given an input string, returns the corresponding string that:
-        * is available in the Helvetica facetype
-        * does not contain any ligature (to allow easy search in the PDF file)
-        """
+        """Replaces characters with those available in the Helvetica typeface."""
         return s.translate(cls.ligatures)
 
-    def topdown_position(self, element):
-        pxl_line_coords = self.element_coordinates(element)
-        line_box = self.pt_from_pixel(pxl_line_coords)
-        # Coordinates here are still in the hocr coordinate system, so 0 on the y axis
-        # is the top of the page and increasing values of y will move towards the
-        # bottom of the page.
-        return line_box.y2
-
     def to_pdf(
         self,
         *,
         out_filename: Path,
-        image_filename: Optional[Path] = None,
+        image_filename: Path | None = None,
         show_bounding_boxes: bool = False,
         fontname: str = "Helvetica",
         invisible_text: bool = False,
         interword_spaces: bool = False,
     ) -> None:
-        """
-        Creates a PDF file with an image superimposed on top of the text.
+        """Creates a PDF file with an image superimposed on top of the text.
+
         Text is positioned according to the bounding box of the lines in
         the hOCR file.
         The image need not be identical to the image used to create the hOCR
@@ -287,7 +251,7 @@ class HocrTransform:
                 continue
 
             pxl_coords = self.element_coordinates(elem)
-            pt = self.pt_from_pixel(pxl_coords)
+            pt = self.pt_from_pixel(pxl_coords)  # pylint: disable=invalid-name
 
             # draw the bbox border
             if show_bounding_boxes:  # pragma: no cover
@@ -337,12 +301,13 @@ class HocrTransform:
 
     @classmethod
     def polyval(cls, poly, x):  # pragma: no cover
+        """Calculate the value of a polynomial at a point."""
         return x * poly[0] + poly[1]
 
     def _do_line(
         self,
         pdf: Canvas,
-        line: Optional[Element],
+        line: Element | None,
         elemclass: str,
         fontname: str,
         invisible_text: bool,

src/ocrmypdf/imageops.py

@@ -0,0 +1,168 @@
+# SPDX-FileCopyrightText: 2023 James R. Barlow
+# SPDX-License-Identifier: MPL-2.0
+
+"""OCR-related image manipulation."""
+
+from __future__ import annotations
+
+import logging
+from math import floor, sqrt
+from typing import Optional, Tuple
+
+from PIL import Image
+
+# Remove this workaround when we require Pillow >= 9.1.0
+try:
+    Resampling = Image.Resampling  # type: ignore
+except AttributeError:
+    # Pillow 9 shim
+    Resampling = Image  # type: ignore
+
+
+# While from __future__ import annotations, we use singledispatch here, which
+# does not support annotations. Disable check about using old-style typing
+# until Python 3.10, OR when drop singledispatch in ocrmypdf 15.
+# ruff: noqa: UP006
+# ruff: noqa: UP007
+
+
+log = logging.getLogger(__name__)
+
+
+def bytes_per_pixel(mode: str) -> int:
+    """Return the number of padded bytes per pixel for a given PIL image mode.
+
+    In RGB mode we assume 4 bytes per pixel, which is the case for most
+    consumers.
+    """
+    if mode in ('1', 'L', 'P'):
+        return 1
+    if mode in ('LA', 'PA', 'La') or mode.startswith('I;16'):
+        return 2
+    return 4
+
+
+def _calculate_downsample(
+    image_size: Tuple[int, int],
+    bytes_per_pixel: int,
+    *,
+    max_size: Optional[Tuple[int, int]] = None,
+    max_pixels: Optional[int] = None,
+    max_bytes: Optional[int] = None,
+) -> Tuple[int, int]:
+    """Calculate image size required to downsample an image to fit limits.
+
+    If no limit is exceeded, the input image's size is returned.
+
+    Args:
+        image_size: Dimensions of image.
+        bytes_per_pixel: Number of bytes per pixel.
+        max_size: The maximum width and height of the image.
+        max_pixels: The maximum number of pixels in the image. Some image consumers
+            limit the total number of pixels as some value other than width*height.
+        max_bytes: The maximum number of bytes in the image. RGB is counted as 4
+            bytes; all other modes are counted as 1 byte.
+    """
+    size = image_size
+
+    if max_size is not None:
+        overage = max_size[0] / size[0], max_size[1] / size[1]
+        size_factor = min(overage)
+        if size_factor < 1.0:
+            log.debug("Resizing image to fit image dimensions limit")
+            size = floor(size[0] * size_factor), floor(size[1] * size_factor)
+            if size[0] == 0:
+                size = 1, min(size[1], max_size[1])
+            elif size[1] == 0:
+                size = min(size[0], max_size[0]), 1
+
+    if max_pixels is not None:
+        if size[0] * size[1] > max_pixels:
+            log.debug("Resizing image to fit image pixel limit")
+            pixels_factor = sqrt(max_pixels / (size[0] * size[1]))
+            size = floor(size[0] * pixels_factor), floor(size[1] * pixels_factor)
+
+    if max_bytes is not None:
+        bpp = bytes_per_pixel
+        # stride = bytes per line
+        stride = size[0] * bpp
+        height = size[1]
+        if stride * height > max_bytes:
+            log.debug("Resizing image to fit image byte size limit")
+            bytes_factor = sqrt(max_bytes / (stride * height))
+            scaled_stride = floor(stride * bytes_factor)
+            scaled_height = floor(height * bytes_factor)
+            if scaled_stride == 0:
+                scaled_stride = bpp
+                scaled_height = min(max_bytes // bpp, scaled_height)
+            if scaled_height == 0:
+                scaled_height = 1
+                scaled_stride = min(max_bytes // scaled_height, scaled_stride)
+            size = floor(scaled_stride / bpp), scaled_height
+
+    return size
+
+
+def calculate_downsample(
+    image: Image.Image,
+    *,
+    max_size: Optional[Tuple[int, int]] = None,
+    max_pixels: Optional[int] = None,
+    max_bytes: Optional[int] = None,
+) -> Tuple[int, int]:
+    """Calculate image size required to downsample an image to fit limits.
+
+    If no limit is exceeded, the input image's size is returned.
+
+    Args:
+        image: The image to downsample.
+        max_size: The maximum width and height of the image.
+        max_pixels: The maximum number of pixels in the image. Some image consumers
+            limit the total number of pixels as some value other than width*height.
+        max_bytes: The maximum number of bytes in the image. RGB is counted as 4
+            bytes; all other modes are counted as 1 byte.
+    """
+    return _calculate_downsample(
+        image.size,
+        bytes_per_pixel(image.mode),
+        max_size=max_size,
+        max_pixels=max_pixels,
+        max_bytes=max_bytes,
+    )
+
+
+def downsample_image(
+    image: Image.Image,
+    new_size: tuple[int, int],
+    *,
+    resample_mode: Image.Resampling = Resampling.BICUBIC,
+    reducing_gap: int = 3,
+) -> Image.Image:
+    """Downsample an image to fit within the given limits.
+
+    The DPI is adjusted to match the new size, which is how we can ensure the
+    OCR is positioned correctly.
+
+    Args:
+        image: The image to downsample
+        new_size: The new size of the image.
+        resample_mode: The resampling mode to use when downsampling.
+        reducing_gap: The reducing gap to use when downsampling (for larger
+            reductions).
+    """
+    if new_size == image.size:
+        return image
+
+    original_size = image.size
+    original_dpi = image.info['dpi']
+    image = image.resize(
+        new_size,
+        resample=resample_mode,
+        reducing_gap=reducing_gap,
+    )
+    image.info['dpi'] = (
+        round(original_dpi[0] * new_size[0] / original_size[0]),
+        round(original_dpi[1] * new_size[1] / original_size[1]),
+    )
+    log.debug(f"Rescaled image to {image.size} pixels and {image.info['dpi']} dpi")
+    return image