Skip testing oom killer on Python 3.12

Need to investigate further if there's a safe way to do this test.

.docker/Dockerfile

@@ -1,5 +1,5 @@
-# OCRmyPDF
+# SPDX-FileCopyrightText: 2022 James R. Barlow
-#
+# SPDX-License-Identifier: MPL-2.0
 
 FROM ubuntu:22.04 as base
 
@@ -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"]

.docker/Dockerfile.alpine

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

.dockerignore

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

.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 +1,55 @@
+name: Installation, packaging, dependencies
+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!
+
+        If your issue involves using OCRmyPDF on specific file(s) and not getting
+        good results, this is the *wrong* issue template. Please use the recommended
+        template to ensure we have enough information to help.
+  - 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/ocrmypdf/OCRmyPDF/wiki) for OCRmyPDF's author only.
-
-Links to files hosted elsewhere are perfectly acceptable. You could also look in ``tests/resources`` and see if any of those files reproduce your issue.
-
-*(Issues without example files usually cannot be resolved. It's like reporting an issue against a web browser without providing a URL.)*
-
-**Expected behavior**
-A clear and concise description of what you expected to happen.
-
-**Screenshots**
-If applicable, add screenshots to help explain your problem.
-
-**System**
- - OS: [e.g. Linux, Windows, macOS]
- - OCRmyPDF Version: ``ocrmypdf --version``
- - How did you install ocrmypdf? Did you use a system package manager, `pip`, or a Docker image?

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

@@ -0,0 +1,75 @@
+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.
+
+        If you cannot provide a test file, we probably won't be able to help with the issue.
+        PDF is a complex file format, and there may be technical details in the PDF that are
+        causing the issue. There's really no substitute for a test file.
+
+        We understand files may contain personal or sensitive information. Here are some options:
+        - Try reproducing the issue with a file from the test suite. (See tests/resources)
+        - Try to create another file in the same way as your private file.
+        - Encrypt the file to OCRmyPDF's private GPG key.
+        - Use ``qpdf --json yourfile.pdf`` to produce a JSON representation of your file that
+          omits personal information.
+
+  - 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/ocrmypdf/OCRmyPDF/wiki) for OCRmyPDF's author only.
-
-Links to files hosted elsewhere are perfectly acceptable. You could also look in ``tests/resources`` and see if any of those files reproduce your issue.
-
-**Additional context**
-Add any other context or screenshots about the feature request here.

.github/dependabot.yml

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

.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/*
@@ -20,40 +22,38 @@ jobs:
     strategy:
       matrix:
         include:
-          - os: ubuntu-18.04
+          - os: ubuntu-22.04
-            python: "3.7"
+            python: "3.10"
-          - os: ubuntu-20.04
+          - os: ubuntu-22.04
-            python: "3.8"
+            python: "3.11"
-          - os: ubuntu-20.04
+          - os: ubuntu-22.04
-            python: "3.9"
-          - os: ubuntu-20.04
             python: "3.10"
-          - os: ubuntu-latest
-            python: "3.9"
-          - os: ubuntu-latest
-            python: "pypy-3.8"
-          - os: ubuntu-latest
-            python: "3.9"
             tesseract5: true
+          - os: ubuntu-latest
+            python: "3.12"
+            tesseract5: true
+          # - os: ubuntu-latest
+          #   python: "pypy3.10"
 
     env:
       OS: ${{ matrix.os }}
       PYTHON: ${{ matrix.python }}
 
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
         with:
           fetch-depth: "0" # 0=all, needed for setuptools-scm to resolve version tags
 
-      - uses: actions/setup-python@v4
+      - uses: actions/setup-python@v5
-        name: Install Python
+        name: Setup Python
         with:
           python-version: ${{ matrix.python }}
+          cache: "pip"
 
       - name: Install Tesseract 5
         if: matrix.tesseract5
         run: |
-          sudo add-apt-repository ppa:alex-p/tesseract-ocr-devel
+          sudo add-apt-repository -y ppa:alex-p/tesseract-ocr-devel
 
       - name: Install common packages
         run: |
@@ -62,6 +62,7 @@ jobs:
             curl \
             ghostscript \
             img2pdf \
+            libexempi8 \
             libffi-dev \
             libsm6 libxext6 libxrender-dev \
             pngquant \
@@ -73,18 +74,6 @@ 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: |
@@ -96,7 +85,7 @@ 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: |
@@ -122,23 +111,19 @@ jobs:
     strategy:
       matrix:
         os: [macos-latest]
-        python: ["3.9", "3.10"]
+        python: ["3.10", "3.11", "3.12"]
 
     env:
       OS: ${{ matrix.os }}
       PYTHON: ${{ matrix.python }}
 
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
         with:
           fetch-depth: "0" # 0=all, needed for setuptools-scm to resolve version tags
 
-      - uses: actions/setup-python@v4
-        name: Install Python
-        with:
-          python-version: ${{ matrix.python }}
-
       - name: Install Homebrew deps
+        continue-on-error: true
         run: |
           brew update
           brew install \
@@ -146,13 +131,20 @@ jobs:
             ghostscript \
             jbig2enc \
             openjpeg \
+            openssl \
             pngquant \
             tesseract
 
+      - uses: actions/setup-python@v5
+        name: Setup Python
+        with:
+          python-version: ${{ matrix.python }}
+          cache: "pip"
+
       - name: Install Python packages
         run: |
           python -m pip install --upgrade pip wheel
-          python -m pip install .[test]
+          python -m pip install --prefer-binary .[test]
 
       - name: Report versions
         run: |
@@ -177,21 +169,22 @@ jobs:
     strategy:
       matrix:
         os: [windows-latest]
-        python: ["3.9", "3.10"]
+        python: ["3.10", "3.11", "3.12"]
 
     env:
       OS: ${{ matrix.os }}
       PYTHON: ${{ matrix.python }}
 
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
         with:
           fetch-depth: "0" # 0=all, needed for setuptools-scm to resolve version tags
 
-      - uses: actions/setup-python@v4
+      - uses: actions/setup-python@v5
-        name: Install Python
+        name: Setup Python
         with:
           python-version: ${{ matrix.python }}
+          cache: "pip"
 
       - name: Install system packages
         run: |
@@ -201,7 +194,7 @@ 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: Test
         run: |
@@ -217,23 +210,24 @@ jobs:
     name: Build sdist and wheels
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
         with:
           fetch-depth: "0" # 0=all, needed for setuptools-scm to resolve version tags
 
-      - uses: actions/setup-python@v4
+      - uses: actions/setup-python@v5
-        name: Install Python
+        name: Setup Python
         with:
-          python-version: "3.7"
+          python-version: "3.10"
+          cache: "pip"
 
       - name: Make wheels and sdist
         run: |
-          python -m pip install --upgrade pip wheel
+          python -m pip install --upgrade pip wheel build
-          python setup.py sdist
+          python -m build --sdist --wheel
-          python setup.py bdist_wheel
 
-      - uses: actions/upload-artifact@v3
+      - uses: actions/upload-artifact@v4
         with:
+          name: artifact
           path: |
             ./dist/*.whl
             ./dist/*.tar.gz
@@ -242,21 +236,47 @@ 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@v3
+      - uses: actions/download-artifact@v4
         with:
           name: artifact
           path: dist
 
-      - uses: pypa/gh-action-pypi-publish@master
+      - name: Publish to PyPI
-        with:
+        uses: pypa/gh-action-pypi-publish@release/v1
-          user: __token__
-          password: ${{ secrets.TOKEN_PYPI }}
-          # repository_url: https://test.pypi.org/legacy/
 
-  docker:
+  create_release:
-    name: Build Docker images
+    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@v4
+        with:
+          name: artifact
+          path: dist
+
+      - name: Create Release
+        id: create-release
+        uses: shogo82148/actions-create-release@v1
+
+      - name: Upload Assets
+        uses: shogo82148/actions-upload-release-asset@v1
+        with:
+          upload_url: ${{ steps.create-release.outputs.upload_url }}
+          asset_path: |
+            ./dist/*.whl
+            ./dist/*.tar.gz
+
+  docker_ubuntu:
+    name: Build Ubuntu-based Docker image
     needs: [wheel_sdist_linux, test_linux, test_macos, test_windows]
     runs-on: ubuntu-latest
     if: github.event_name != 'pull_request'
@@ -264,9 +284,9 @@ jobs:
       - name: Set image tag to release or branch
         run: echo "DOCKER_IMAGE_TAG=${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
@@ -274,22 +294,22 @@ jobs:
       - name: Set image name
         run: echo "DOCKER_IMAGE_NAME=ocrmypdf" >> $GITHUB_ENV
 
-      - uses: actions/checkout@v3
+      - 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@v2
+        uses: docker/login-action@v3
         with:
           username: jbarlow83
           password: ${{ secrets.DOCKERHUB_TOKEN }}
 
       - name: Set up QEMU
-        uses: docker/setup-qemu-action@v2
+        uses: docker/setup-qemu-action@v3
 
       - name: Set up Docker Buildx
         id: buildx
-        uses: docker/setup-buildx-action@v2
+        uses: docker/setup-buildx-action@v3
 
       - name: Print image tag
         run: echo "Building image ${DOCKER_REPOSITORY}/${DOCKER_IMAGE_NAME}:${DOCKER_IMAGE_TAG}"
@@ -300,4 +320,52 @@ jobs:
             --push \
             --platform linux/arm64/v8,linux/amd64  \
             --tag "${DOCKER_REPOSITORY}/${DOCKER_IMAGE_NAME}:${DOCKER_IMAGE_TAG}" \
+            --tag "${DOCKER_REPOSITORY}/${DOCKER_IMAGE_NAME}-ubuntu:${DOCKER_IMAGE_TAG}" \
             --file .docker/Dockerfile .
+
+  docker_alpine:
+    name: Build Alpine-based Docker images
+    needs: [wheel_sdist_linux, test_linux, test_macos, test_windows]
+    runs-on: ubuntu-latest
+    if: github.event_name != 'pull_request'
+    steps:
+      - name: Set image tag to release or branch
+        run: echo "DOCKER_IMAGE_TAG=${GITHUB_REF##*/}" >> $GITHUB_ENV
+
+      - name: If main, set to latest
+        run: echo 'DOCKER_IMAGE_TAG=latest' >> $GITHUB_ENV
+        if: env.DOCKER_IMAGE_TAG == 'main'
+
+      - name: Set Docker Hub repository to username
+        run: echo "DOCKER_REPOSITORY=jbarlow83" >> $GITHUB_ENV
+
+      - name: Set image name
+        run: echo "DOCKER_IMAGE_NAME=ocrmypdf-alpine" >> $GITHUB_ENV
+
+      - uses: actions/checkout@v4
+        with:
+          fetch-depth: "0" # 0=all, needed for setuptools-scm to resolve version tags
+
+      - name: Login to Docker Hub
+        uses: docker/login-action@v3
+        with:
+          username: jbarlow83
+          password: ${{ secrets.DOCKERHUB_TOKEN }}
+
+      - name: Set up QEMU
+        uses: docker/setup-qemu-action@v3
+
+      - name: Set up Docker Buildx
+        id: buildx
+        uses: docker/setup-buildx-action@v3
+
+      - name: Print image tag
+        run: echo "Building image ${DOCKER_REPOSITORY}/${DOCKER_IMAGE_NAME}:${DOCKER_IMAGE_TAG}"
+
+      - name: Build
+        run: |
+          docker buildx build \
+            --push \
+            --platform linux/amd64  \
+            --tag "${DOCKER_REPOSITORY}/${DOCKER_IMAGE_NAME}:${DOCKER_IMAGE_TAG}" \
+            --file .docker/Dockerfile.alpine .

.gitignore

@@ -1,14 +1,15 @@
+# SPDX-FileCopyrightText: 2022 James R. Barlow
+# SPDX-License-Identifier: CC-BY-SA-4.0
+
 # dotfiles
-.*
+.coverage
-!.coveragerc
+.venv*/
-!.dockerignore
+.tox/
-!.git_archival.txt
+.vscode/
-!.gitattributes
+.hypothesis/
-!.gitignore
+.ipynb_checkpoints/
-!.pre-commit-config.yaml
+.mypy_cache/
-!.readthedocs.yaml
+.pytest_cache/
-!.github/
-!.docker/
 
 # 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: v4.3.0
+    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
+  - repo: https://github.com/charliermarsh/ruff-pre-commit
-    rev: 5.10.1
+    rev: "v0.0.261"
     hooks:
-      - id: isort
+      - id: ruff
-        args: ["--profile", "black", "-a", "from __future__ import annotations"]
+        files: "src/.*\\.pyi?$"
+        args: [--fix, --exit-non-zero-on-fix]
   - repo: https://github.com/psf/black
-    rev: 22.6.0
+    rev: 23.3.0
     hooks:
       - id: black
         language_version: python
-  - repo: https://github.com/asottile/setup-cfg-fmt
-    rev: v1.20.2
-    hooks:
-      - id: setup-cfg-fmt
-  - repo: https://github.com/asottile/pyupgrade
-    rev: v2.37.2
-    hooks:
-      - id: pyupgrade
-        args: ["--py37-plus"]
   - repo: https://github.com/pre-commit/mirrors-mypy
-    rev: v0.971
+    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: "3.10"
+
 python:
-  version: "3.7"
   install:
     - method: pip
       path: .

.reuse/dep5

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

README.md

@@ -1,3 +1,7 @@
+<!-- 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/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]
@@ -35,8 +39,10 @@ ocrmypdf                      # it's a scriptable command line program
 - 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
+- Scales properly to handle files with thousands of pages.
-- Battle-tested on millions of PDFs
+- 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/).
 
@@ -64,9 +70,9 @@ Linux, Windows, macOS and FreeBSD are supported. Docker images are also availabl
 | Windows Subsystem for Linux   | ``apt install ocrmypdf``      |
 | Fedora                        | ``dnf install ocrmypdf``      |
 | macOS (Homebrew)              | ``brew install ocrmypdf``     |
-| macOS (nix)                   | ``nix-env -i  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``     |
 
@@ -92,10 +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
+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.
-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
 
@@ -111,7 +114,7 @@ Please report issues on our [GitHub issues](https://github.com/ocrmypdf/OCRmyPDF
 
 ## 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
 
@@ -122,6 +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
 

docs/advanced.rst

@@ -10,7 +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
@@ -47,8 +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
+   file and produce one file; errors will result if this assumption is not
-   result in errors.
+   met.
 
 .. note::
 
@@ -82,14 +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
+images, discarding any hidden OCR text, rasterizing any printable
-text. This is useful for redoing OCR, for fixing OCR text with a damaged
+text, and flattening form fields or interactive objects into their visual
-character map (text is selectable but not searchable), and destroying
+representation. This is useful for redoing OCR, for fixing OCR text
-redacted information. Any forms and vector graphics will be rasterized
+with a damaged character map (text is selectable but not searchable),
-as well.
+and destroying redacted information.
 
 Time and image size limits
 --------------------------
@@ -104,13 +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
+-------------------
+
+Tesseract has internal limits on the size
+of images it will process. If you issue
+``--tesseract-downsample-large-images``, OCRmyPDF will downsample images
+to fit Tesseract limits. (The limits are usually entered only for scanned
+images of oversized media, such as large maps or blueprints exceeding
+110 cm or 43 inches in either dimension, and at high DPI.)
+
+``--tesseract-downsample-above Npixels`` adjusts the threshold at which images
+will be downsampled. By default, only images that exceed any of Tesseract's
+internal limits are downsampled.
+
+You will also need to set ``--tesseract-timeout`` high enough to allow
+for processing.
+
+Only the image sent for OCR is downsampled. The original image is
+preserved.
+
+.. code-block:: bash
+
+    # Allow 600 seconds for OCR on huge images
+    ocrmypdf --tesseract-timeout 600 \
+        --tesseract-downsample-large-images \
+        bigfile.pdf output.pdf
+
+    # Downsample images above 5000 pixels on the longest dimension to
+    # 5000 pixels
+    ocrmypdf --tesseract-timeout 120 \
+        --tesseract-downsample-large-images \
+        --tesseract-downsample-above 5000 \
+        bigfile.pdf output_downsampled_ocr.pdf
+
+
 Overriding default tesseract
 ----------------------------
 
@@ -154,13 +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
+Changing Tesseract configuration variables
 ------------------------------------------
 
-You can override tesseract's default `control
+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
@@ -200,46 +239,77 @@ rendering
 OCRmyPDF has these PDF renderers: ``sandwich`` and ``hocr``. The
 renderer may be selected using ``--pdf-renderer``. The default is
 ``auto`` which lets OCRmyPDF select the renderer to use. Currently,
-``auto`` always selects ``sandwich``.
+``auto`` always selects ``hocr``.
+
+The ``hocr`` renderer
+---------------------
+
+.. versionchanged:: 16.0.0
+
+In both renderers, a text-only layer is rendered and sandwiched (overlaid)
+on to either the original PDF page, or newly rasterized version of the
+original PDF page (when ``--force-ocr`` is used). In this way, loss
+of PDF information is generally avoided. (You may need to disable PDF/A
+conversion and optimization to eliminate all lossy transformations.)
+
+The current approach used by the new hOCR renderer is a re-implementation
+of Tesseract's PDF renderer, using the same Glyphless font and general
+ideas, but fixing many technical issues that impeded it. The new hocr
+provides better text placement accuracy, avoids issues with word
+segmentation, and provides better positioning of skewed text.
+
+Using the experimental API, it is also possible to edit the OCR output
+from Tesseract, using any tool that is capable of editing hOCR files.
+
+Older versions of this renderer did not support non-Latin languages, but
+it is now universal.
 
 The ``sandwich`` renderer
 -------------------------
 
-The ``sandwich`` renderer uses Tesseract's new text-only PDF feature,
+The ``sandwich`` renderer uses Tesseract's text-only PDF feature,
-which produces a PDF page that lays out the OCR in invisible text. This
+which produces a PDF page that lays out the OCR in invisible text.
-page is then "sandwiched" onto the original PDF page, allowing lossless
-application of OCR even to PDF pages that contain other vector objects.
 
-Currently this is the best renderer for most uses, however it is
+Currently some problematic PDF viewers like Mozilla PDF.js and macOS
-implemented in Tesseract so OCRmyPDF cannot influence it. Currently some
+Preview have problems with segmenting its text output, and
-problematic PDF viewers like Mozilla PDF.js and macOS Preview have
+mightrunseveralwordstogether. It also does not implement right to left
-problems with segmenting its text output, and
+fonts (Arabic, Hebrew, Persian). The output of this renderer cannot
-mightrunseveralwordstogether.
+be edited. The sandwich renderer is retained for testing.
 
 When image preprocessing features like ``--deskew`` are used, the
 original PDF will be rendered as a full page and the OCR layer will be
 placed on top.
 
-The ``hocr`` renderer
+Rendering and rasterizing options
----------------------
+=================================
 
-The ``hocr`` renderer works with older versions of Tesseract. The image
+.. versionadded:: 14.3.0
-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. (You may
-need to disable PDF/A conversion nad optimization to eliminate all
-lossy transformations.)
 
-Unlike ``sandwich`` this renderer is implemented within OCRmyPDF; anyone
+The ``--continue-on-soft-render-error`` option allows OCRmyPDF to
-looking to customize how OCR is presented should look here. A major
+proceed if a page cannot be rasterized/rendered. This is useful if you are
-disadvantage of this renderer is it not capable of correctly handling
+trying to get the best possible OCR from a PDF that is not well-formed,
-text outside the Latin alphabet (specifically, it supports the ISO 8859-1
+and you are willing to accept some pages that may not visually match the
-character). Pull requests to improve the situation are welcome.
+input, and that may not OCR well.
 
-Currently, this renderer has the best compatibility with Mozilla's
+Color conversion strategy
-PDF.js viewer.
+=========================
 
-This works in all versions of Tesseract.
+.. versionadded:: 15.0.0
+
+OCRmyPDF uses Ghostscript to convert PDF to PDF/A. In some cases, this
+conversion requires color conversion. The default strategy is to convert
+using the ``LeaveColorUnchanged`` strategy, which preserves the original
+color space wherever possible (some rare color spaces might still be
+converted).
+
+Usually document scanners produce PDFs in the sRGB color space, and do
+not need to be converted, so the default strategy is appropriate.
+
+Suppose that you have a document that was prepared for professional
+printing in a Separation or CMYK color space, and text was converted to
+curves. In this case, you may want to use a different color conversion
+strategy. The ``--color-conversion-strategy`` option allows you to select a
+different strategy, such as ``RGB``.
 
 Return code policy
 ==================
@@ -299,16 +369,31 @@ 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
+If the ``--keep-temporary-files`` (``-k```) argument is issued on the
-the temporary folder and print the location, whether it succeeded or
+command line, OCRmyPDF will keep the temporary folder and print the location,
-failed (provided the Python interpreter did not crash). An example
+whether it succeeded or failed. An example message is:
-message is:
 
 .. code-block:: none
 

docs/api.rst

@@ -39,9 +39,7 @@ Parent process requirements
 The :func:`ocrmypdf.ocr` function runs OCRmyPDF similar to command line
 execution. To do this, it will:
 
-- create a monitoring thread
+- create worker processes or threads
-- create worker processes (on Linux, forking itself; on Windows and macOS, by
-  spawning)
 - manage the signal flags of its worker processes
 - execute other subprocesses (forking and executing other programs)
 
@@ -54,7 +52,19 @@ processes.
 
 Creating a child process to call :func:`ocrmypdf.ocr()` is suggested. That
 way your application will survive and remain interactive even if
-OCRmyPDF fails for any reason.
+OCRmyPDF fails for any reason. For example:
+
+.. code-block:: python
+
+    from multiprocessing import Process
+
+    def ocrmypdf_process():
+        ocrmypdf.ocr('input.pdf', 'output.pdf')
+
+    def call_ocrmypdf_from_my_app():
+        p = Process(target=ocrmypdf_process)
+        p.start()
+        p.join()
 
 Programs that call :func:`ocrmypdf.ocr()` should also install a SIGBUS signal
 handler (except on Windows), to raise an exception if access to a memory
@@ -72,14 +82,6 @@ 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
 -------
 
@@ -97,12 +99,21 @@ your use case.
 Progress monitoring
 -------------------
 
-OCRmyPDF uses the ``tqdm`` package to implement its progress bars.
+OCRmyPDF uses the ``rich`` package to implement its progress bars.
 :func:`ocrmypdf.configure_logging` will set up logging output to
 ``sys.stderr`` in a way that is compatible with the display of the
 progress bar. Use ``ocrmypdf.ocr(...progress_bar=False)`` to disable
 the progress bar.
 
+Standard output
+---------------
+
+OCRmyPDF is strict about not writing to standard output so that
+users can safely use it in a pipeline and produce a valid output
+file. A caller application will have to ensure it does not write to
+standard output either, if it wants to be compatible with this
+behavior and support piping to a file.
+
 Exceptions
 ----------
 
@@ -112,18 +123,4 @@ exceptions, some exceptions related to multiprocessing, and
 handler. OCRmyPDF will clean up its temporary files and worker processes
 automatically when an exception occurs.
 
-Programs that call OCRmyPDF should consider trapping KeyboardInterrupt
-so that they allow OCR to terminate with the whole program terminating.
-
 When OCRmyPDF succeeds conditionally, it returns an integer exit code.
-
-Reference
----------
-
-.. autofunction:: ocrmypdf.ocr
-
-.. autoclass:: ocrmypdf.Verbosity
-    :members:
-    :undoc-members:
-
-.. autofunction:: ocrmypdf.configure_logging

docs/apiref.rst

@@ -3,11 +3,11 @@
 .. SPDX-License-Identifier: CC-BY-SA-4.0
 
 =============
-API Reference
+API reference
 =============
 
 This page summarizes the rest of the public API. Generally speaking this
-should mainly of interest to plugin developers.
+should be mainly of interest to plugin developers.
 
 ocrmypdf
 ========
@@ -18,6 +18,18 @@ ocrmypdf
 .. autoclass:: ocrmypdf.PdfContext
     :members:
 
+.. autoclass:: ocrmypdf.Verbosity
+    :members:
+    :undoc-members:
+
+.. autofunction:: ocrmypdf.configure_logging
+
+.. autofunction:: ocrmypdf.ocr
+
+.. autofunction:: ocrmypdf.pdf_to_hocr
+
+.. autofunction:: ocrmypdf.hocr_to_ocr_pdf
+
 ocrmypdf.exceptions
 ===================
 

docs/batch.rst

@@ -21,8 +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
+This command will run ``ocrmypdf`` on all files named ``*.pdf`` in the
-current directory and write them to the previous created ``output/``
+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
@@ -46,16 +46,6 @@ place, and printing each filename in between runs:
 
    find . -printf '%p\n' -name '*.pdf' -exec ocrmypdf '{}' '{}' \;
 
-Alternatively, with a Docker container and streaming the file 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
-
 This only runs one ``ocrmypdf`` process at a time. This variation uses
 ``find`` to create a directory list and ``parallel`` to parallelize runs
 of ``ocrmypdf``, again updating files in place.
@@ -70,6 +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
 -------------
 
@@ -88,9 +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
+At the time this script was written, it only worked for x86-based Synology
-products use ARM or Power processors and do not support Docker. Further
+products. It is not known if it will work on ARM-based Synology products.
-adjustments might be needed to deal with the Synology's relatively
+Further adjustments might be needed to deal with the Synology's relatively
 limited CPU and RAM.
 
 .. literalinclude:: ../misc/synology.py
@@ -133,7 +132,7 @@ Users may need to customize the script to meet their requirements.
     "OCR_OUTPUT_DIRECTORY", "Set output directory (should not be under input)"
     "OCR_ARCHIVE_DIRECTORY", "Set archive directory for processed originals (should not be under input, requires ``OCR_ON_SUCCESS_ARCHIVE`` to be set)"
     "OCR_ON_SUCCESS_DELETE", "This will delete the input file if the exit code is 0 (OK)"
-    "OCR_ON_SUCCESS_ARCHIVE", "This will move the processed orignal file to ``OCR_ARCHIVE_DIRECTORY`` if the exit code is 0 (OK). Note that ``OCR_ON_SUCCESS_DELETE`` takes precedence over this option, i.e. if both options are set, the input file will be deleted."
+    "OCR_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}'``."
@@ -151,32 +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 \
+        --volume <path to files to convert>:/input \
-        -v <path to store results>:/output \
+        --volume <path to store results>:/output \
-        -v <path to store processed originals>:/archive \
+        --volume <path to store processed originals>:/processed \
-        -e OCR_OUTPUT_DIRECTORY_YEAR_MONTH=1 \
+        --env OCR_OUTPUT_DIRECTORY_YEAR_MONTH=1 \
-        -e OCR_ON_SUCCESS_ARCHIVE=1 \
+        --env OCR_ON_SUCCESS_ARCHIVE=1 \
-        -e OCR_DESKEW=1 \
+        --env OCR_DESKEW=1 \
-        -e PYTHONUNBUFFERED=1 \
+        --env PYTHONUNBUFFERED=1 \
-        -it --entrypoint python3 \
+        --interactive --tty --entrypoint python3 \
         jbarlow83/ocrmypdf \
         watcher.py
 
 This service will watch for a file that matches ``/input/\*.pdf``,
 convert it to a OCRed PDF in ``/output/``, and move the processed
-original to ``/archive``. The parameters to this image are:
+original to ``/processed``. 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"
+    "``--volume <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"
+    "``--volume <path to store results>:/output``", "This is where OCRed files will be stored"
-    "``-v <path to store processed originals>:/archive``", "Archive processed originals here"
+    "``--volume <path to store processed originals>:/processed``", "Archive processed originals here"
-    "``-e OCR_OUTPUT_DIRECTORY_YEAR_MONTH=1``", "Define environment variable ``OCR_OUTPUT_DIRECTORY_YEAR_MONTH=1`` to place files in the output in ``{output}/{year}/{month}/{filename}``"
+    "``--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}``"
-    "``-e OCR_ON_SUCCESS_ARCHIVE=1``", "Define environment variable ``OCR_ON_SUCCESS_ARCHIVE`` to move processed originals"
+    "``--env OCR_ON_SUCCESS_ARCHIVE=1``", "Define environment variable ``OCR_ON_SUCCESS_ARCHIVE`` to move processed originals"
-    "``-e OCR_DESKEW=1``", "Define environment variable ``OCR_DESKEW``  to apply deskew to crooked input PDFs"
+    "``--env OCR_DESKEW=1``", "Define environment variable ``OCR_DESKEW``  to apply deskew to crooked input PDFs"
-    "``-e PYTHONBUFFERED=1``", "This will force ``STDOUT`` to be unbuffered and allow you to see messages in docker logs"
+    "``--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 +1,92 @@
+.. SPDX-FileCopyrightText: 2023 James R. Barlow
+..
+.. SPDX-License-Identifier: CC-BY-SA-4.0
+
+
+.. _ocr-service:
+
+==================
+Online deployments
+==================
+
+OCRmyPDF is designed to be used as a command line tool, but it can be
+used in a web service. This document describes some considerations for
+doing so.
+
+A basic web service implementation is provided in the source code
+repository, as ``misc/webservice.py``. It is only demonstration quality
+and is not intended for production use.
+
+OCRmyPDF is not designed for use as a public web service where a
+malicious user could upload a chosen PDF. In particular, it is not
+necessarily secure against PDF malware or PDFs that cause denial of
+service. For further discussino of security, see :ref:`security`.
+
+OCRmyPDF relies on Ghostscript, and therefore, if deployed
+online one should be prepared to comply with Ghostscript's Affero GPL
+license, and any other licenses.
+
+Setting aside these concerns, a side effect of OCRmyPDF is that it may
+incidentally sanitize PDFs containing certain types of malware. It
+repairs the PDF with pikepdf/libqpdf, which could correct malformed PDF
+structures that are part of an attack. When PDF/A output is selected
+(the default), the input PDF is partially reconstructed by Ghostscript.
+When ``--force-ocr`` is used, all pages are rasterized and reconverted
+to PDF, which could remove malware in embedded images.
+
+Limiting CPU usage
+------------------
+
+OCRmyPDF will attempt to use all available CPUs and storage, so
+executing ``nice ocrmypdf`` or limiting the number of jobs with the
+``--jobs`` argument may ensure the server remains responsive. Another option
+would be to run OCRmyPDF jobs inside a Docker container, a virtual machine,
+or a cloud instance, which can impose its own limits on CPU usage and be
+terminated "from orbit" if it fails to complete.
+
+Temporary storage requirements
+------------------------------
+
+OCRmyPDF will use a large amount of temporary storage for its work,
+proportional to the total number of pixels needed to rasterize the PDF.
+The raster image of a 8.5×11" color page at 300 DPI takes 25 MB
+uncompressed; OCRmyPDF saves its intermediates as PNG, but that still
+means it requires about 9 MB per intermediate based on average
+compression ratios. Multiple intermediates per page are also required,
+depending on the command line given. A rule of thumb would be to allow
+100 MB of temporary storage per page in a file – meaning that a small
+cloud servers or small VM partitions should be provisioned with plenty
+of extra space, if say, a 500 page file might be sent.
+
+To change the temporary directory, see :ref:`tmpdir`.
+
+On Amazon Web Services or other cloud vendors, consider setting your
+temporary directory to `empheral
+storage <https://docs.aws.amazon.com/AWSEC2/latest/UserGuide/InstanceStorage.html>`__.
+
+Timeouts
+--------
+
+To prevent excessively long OCR jobs consider setting
+``--tesseract-timeout`` and/or ``--skip-big`` arguments. ``--skip-big``
+is particularly helpful if your PDFs include documents such as reports
+on standard page sizes with large images attached - often large images
+are not worth OCR'ing anyway.
+
+Document management systems
+---------------------------
+
+If you are looking for a full document management system, consider
+`paperless-ngx <https://github.com/paperless-ngx/paperless-ngx>`__,
+which is a web application that uses OCRmyPDF to automatically OCR and
+archive documents.
+
+Commercial OCR alternatives
+---------------------------
+
+The author also provides professional services that include OCR and
+building databases around PDFs, and is happy to provide consultation.
+
+Abbyy Cloud OCR is viable commercial alternative with a web services
+API. Amazon Textract, Google Cloud Vision, and Microsoft Azure
+Computer Vision provide advanced OCR but have less PDF rendering capability.

docs/conf.py

@@ -2,6 +2,8 @@
 # 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.
 #
@@ -22,8 +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.
@@ -65,7 +65,7 @@ master_doc = 'index'
 # General information about the project.
 project = 'ocrmypdf'
 copyright = (
-    '2022, 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'
 
@@ -76,6 +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'
 
@@ -96,10 +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

@@ -18,8 +18,8 @@ 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
+settings for these programs are in ``pyproject.toml``. Pull
 requests should follow the style guide. One difference we use from "black" style
 is that strings shown to the user are always in double quotes (``"``) and strings
 for internal uses are in single quotes (``'``).
@@ -29,12 +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.
@@ -43,7 +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?
 ========================================
@@ -53,8 +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
+MIT, with a few minor exceptions. Please contribute only content that you own
-contribute or license to us.
+or have the right to contribute under these licenses.

docs/cookbook.rst

@@ -231,13 +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 without performing OCR (by causing OCR to time out). This works
-processing or PDF/A conversion.
+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
 --------------------------------------
 
@@ -261,9 +268,10 @@ 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/images
 in the file and convert it to PDF/A, unless you disable those options. Both of these
@@ -283,7 +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
@@ -360,7 +368,7 @@ 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
 
@@ -372,3 +380,17 @@ Some users may consider enabling lossy JBIG2. See: :ref:`jbig2-lossy`.
 
     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

@@ -8,17 +8,16 @@
 OCRmyPDF Docker image
 =====================
 
-OCRmyPDF is also available in a Docker image that packages recent
+OCRmyPDF is also available in Docker images that packages recent
 versions of all dependencies.
 
 For users who already have Docker installed this may be an easy and
-convenient option. However, it is less performant than a system
+convenient option.
-installation and may require Docker engine configuration.
 
-OCRmyPDF needs a generous amount of RAM, CPU cores, temporary storage
+On platforms other than Linux, Docker runs in a virtual machine, and so may
-space, whether running in a Docker container or on its own. It may be
+be less performant. You may also want to adjust the Docker virtual machine's
-necessary to ensure the container is provisioned with additional
+memory and CPU allocation. On Linux, the Docker image runs natively and
-resources.
+performance is comparable to a system installation.
 
 .. _docker-install:
 
@@ -35,28 +34,37 @@ execute the image:
 
    docker run hello-world
 
-The recommended OCRmyPDF Docker image is currently named ``ocrmypdf``:
+.. list-table:: Docker images
+   :width: 30 20 50
+   :header-rows: 1
+
+   * - Image
+     - Architecture
+     - Description
+   * - ``jbarlow83/ocrmypdf-alpine``
+     - x86_64 only
+     - Recommended image, based on Alpine Linux.
+   * - ``jbarlow83/ocrmypdf-ubuntu``
+     - x86_64 and arm64
+     - Alternate image, based on Ubuntu. When the Alpine image is considered
+       stable and available for arm64, this image will be deprecated.
+   * - ``jbarlow83/ocrmypdf``
+     - x86_64 and arm64
+     - Currently an alias for ocrmypdf-ubuntu. When the Alpine image is
+       considered stable and available for arm64, this name point to the
+       Alpine image. If you don't about the difference between Alpine and
+       Ubuntu, use this image.
+
+To install:
 
 .. code-block:: bash
 
-   docker pull jbarlow83/ocrmypdf
+   docker pull jbarlow83/ocrmypdf-alpine
 
+The ``ocrmypdf`` image is also available, but is deprecated and will be removed
+in the future.
 
-OCRmyPDF will use all available CPU cores. By default, the VirtualBox
+OCRmyPDF will use all available CPU cores. See the Docker documentation for
-machine instance on Windows and macOS has only a single CPU core
-enabled. Use the VirtualBox Manager to determine the name of your Docker
-engine host, and then follow these optional steps to enable multiple
-CPUs:
-
-.. code-block:: bash
-
-   # Optional step for Mac OS X users
-   docker-machine stop "yourVM"
-   VBoxManage modifyvm "yourVM" --cpus 2  # or whatever number of core is desired
-   docker-machine start "yourVM"
-   eval $(docker-machine env "yourVM")
-
-See the Docker documentation for
 `adjusting memory and CPU on other platforms <https://docs.docker.com/config/containers/resource_constraints/>`__.
 
 Using the Docker image on the command line
@@ -66,6 +74,8 @@ Using the Docker image on the command line
 container is ephemeral – it runs for one OCR job and terminates, just like a
 command line program. We are using Docker to deliver an application (as opposed
 to the more conventional case, where a Docker container runs as a server).
+For that reason we usually use the ``--rm`` argument to delete the container
+when it exits.
 
 To start a Docker container (instance of the image):
 
@@ -116,7 +126,7 @@ Dockerfile based on the public one.
    # Example: add Italian
    RUN apt install tesseract-ocr-ita
 
-To install language packs (training data) such as the 
+To install language packs (training data) such as the
 `tessdata_best <https://github.com/tesseract-ocr/tessdata_best>`_ suite or
 custom data, you first need to determine the version of Tesseract data files, which
 may differ from the Tesseract program version. Use this command to determine the data
@@ -132,17 +142,35 @@ You can then add new data with either a Dockerfile:
 
 .. code-block:: dockerfile
 
-   FROM jbarlow83/ocrmypdf
+   FROM jbarlow83/ocrmypdf:{TAG}
 
    # Example: add a tessdata_best file
    COPY chi_tra_vert.traineddata /usr/share/tesseract-ocr/<data version>/tessdata/
 
+When creating your own image, you should always pin a specific version of the
+OCRmyPDF Docker image. This ensures that your image will not break when a new
+version of OCRmyPDF is released.
+
 Alternately, you can copy training data into a Docker container as follows:
 
 .. code-block:: bash
 
    docker cp mycustomtraining.traineddata name_of_container:/usr/share/tesseract-ocr/<tesseract version>/tessdata/
 
+Extending the Docker image
+==========================
+
+You can extend the Docker image with your own customizations, similar to the way
+it is extended to add language packs.
+
+Note that the Docker image is subject to change at any time. For example, the base
+image may be updated to a newer version of Ubuntu or Debian. Such changes will be
+noted in the release notes but might occur at minor versions releases, unless the
+way a "casual" user of the Docker image is affected.
+
+If you extend the Docker image, you should pin a specific version of the OCRmyPDF
+Docker image.
+
 Executing the test suite
 ========================
 
@@ -150,16 +178,16 @@ The OCRmyPDF test suite is installed with image. To run it:
 
 .. code-block:: bash
 
-   docker run --entrypoint python3  jbarlow83/ocrmypdf -m pytest
+   docker run --rm --entrypoint python  jbarlow83/ocrmypdf -m pytest
 
 Accessing the shell
 ===================
 
-To use the bash shell in the Docker image:
+To use the shell in the Docker image:
 
 .. code-block:: bash
 
-   docker run -it --entrypoint bash  jbarlow83/ocrmypdf
+   docker run -it --entrypoint sh  jbarlow83/ocrmypdf
 
 Using the OCRmyPDF web service wrapper
 ======================================
@@ -169,7 +197,10 @@ service. The webservice may be launched as follows:
 
 .. code-block:: bash
 
-   docker run --entrypoint python3 -p 5000:5000  jbarlow83/ocrmypdf webservice.py
+   docker run --entrypoint python -p 5000:5000  jbarlow83/ocrmypdf webservice.py
+
+We omit the ``--rm`` parameter so that the container will not be
+automatically deleted when it exits.
 
 This will configure the machine to listen on port 5000. On Linux machines
 this is port 5000 of localhost. On macOS or Windows machines running

docs/index.rst

@@ -12,7 +12,7 @@ files, allowing them to be searched.
 
 PDF is the best format for storing and exchanging scanned documents.
 Unfortunately, PDFs can be difficult to modify. OCRmyPDF makes it easy to apply
-image processing and OCR to existing PDFs.
+image processing and OCR (recognized, searchable text) to existing PDFs.
 
 .. toctree::
    :maxdepth: 1
@@ -20,7 +20,6 @@ image processing and OCR to existing PDFs.
    introduction
    release_notes
    installation
-   optimizer
    languages
    jbig2
 
@@ -29,9 +28,11 @@ image processing and OCR to existing PDFs.
    :maxdepth: 2
 
    cookbook
+   optimizer
    docker
    advanced
    batch
+   cloud
    performance
    pdfsecurity
    errors
@@ -43,6 +44,7 @@ image processing and OCR to existing PDFs.
    api
    plugins
    apiref
+   design_notes
    contributing
    maintainers
 

docs/installation.rst

@@ -21,7 +21,7 @@ These platforms have one-liner installs:
 +-------------------------------+-----------------------------------------+
 | Windows Subsystem for Linux   | ``apt install ocrmypdf``                |
 +-------------------------------+-----------------------------------------+
-| Fedora                        | ``dnf install ocrmypdf``                |
+| Fedora                        | ``dnf install ocrmypdf tesseract-osd``  |
 +-------------------------------+-----------------------------------------+
 | macOS                         | ``brew install ocrmypdf``               |
 +-------------------------------+-----------------------------------------+
@@ -44,7 +44,7 @@ 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-11| image:: https://repology.org/badge/version-for-repo/debian_11/ocrmypdf.svg
@@ -56,9 +56,6 @@ Debian and Ubuntu 18.04 or newer
 .. |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
 
@@ -72,15 +69,14 @@ Debian and Ubuntu 18.04 or newer
 +-----------------------------------------------+
 | |deb-11| |deb-12| |deb-unstable|              |
 +-----------------------------------------------+
-| |ubu-1804| |ubu-2004| |ubu-2204|              |
+| |ubu-2004| |ubu-2204|                         |
 +-----------------------------------------------+
 
-Users of Debian 9 ("stretch") or later, or Ubuntu 18.04 or later, including users
+Users of Debian or Ubuntu may simply
-of Windows Subsystem for Linux, 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
@@ -103,11 +99,11 @@ For full details on version availability for your platform, check the
 Fedora
 ------
 
-.. |fedora-35| image:: https://repology.org/badge/version-for-repo/fedora_35/ocrmypdf.svg
+.. |fedora-37| image:: https://repology.org/badge/version-for-repo/fedora_37/ocrmypdf.svg
-    :alt: Fedora 35
+    :alt: Fedora 37
 
-.. |fedora-36| image:: https://repology.org/badge/version-for-repo/fedora_36/ocrmypdf.svg
+.. |fedora-38| image:: https://repology.org/badge/version-for-repo/fedora_38/ocrmypdf.svg
-    :alt: Fedora 36
+    :alt: Fedora 38
 
 .. |fedora-rawhide| image:: https://repology.org/badge/version-for-repo/fedora_rawhide/ocrmypdf.svg
     :alt: Fedore Rawhide
@@ -117,14 +113,14 @@ Fedora
 +-----------------------------------------------+
 | |latest|                                      |
 +-----------------------------------------------+
-| |fedora-35| |fedora-36| |fedora-rawhide|      |
+| |fedora-37| |fedora-38| |fedora-rawhide|      |
 +-----------------------------------------------+
 
-Users of Fedora 29 or later may simply
+Users of Fedora 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>`__.
@@ -159,7 +155,7 @@ user, follow these steps:
 
 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.
+or open a new shell, or manually adjust your PATH.
 
 To add JBIG2 encoding, see :ref:`jbig2`.
 
@@ -198,46 +194,6 @@ To install for the current user only:
 
 To add JBIG2 encoding, see :ref:`jbig2`.
 
-Ubuntu 18.04 LTS
-----------------
-
-Ubuntu 18.04 includes ocrmypdf 6.1.2 - you can install that with ``apt``, but
-it is quite old now. To install a more recent version, uninstall the old version
-of ocrmypdf, and install the following dependencies:
-
-.. code-block:: bash
-
-    sudo apt-get -y remove ocrmypdf
-    sudo apt-get -y update
-    sudo apt-get -y install \
-        ghostscript \
-        icc-profiles-free \
-        libxml2 \
-        pngquant \
-        python3-distutils \
-        python3-pkg-resources \
-        python3-reportlab \
-        qpdf \
-        tesseract-ocr \
-        zlib1g \
-        unpaper
-
-We will need a newer version of ``pip`` then was available for Ubuntu 18.04:
-
-.. code-block:: bash
-
-    wget https://bootstrap.pypa.io/get-pip.py && python3 get-pip.py
-
-Then install the most recent ocrmypdf for the local user and set the
-user's ``PATH`` to check for the user's Python packages.
-
-.. code-block:: bash
-
-    export PATH=$HOME/.local/bin:$PATH
-    python3 -m pip install --user ocrmypdf
-
-To add JBIG2 encoding, see :ref:`jbig2`.
-
 Arch Linux (AUR)
 ----------------
 
@@ -318,6 +274,21 @@ To install OCRmyPDF for Alpine Linux:
 
     apk add ocrmypdf
 
+Gentoo Linux
+------------
+
+.. image:: https://repology.org/badge/version-for-repo/gentoo_ovl_guru/ocrmypdf.svg
+    :alt: Gentoo Linux
+    :target: https://repology.org/metapackage/ocrmypdf
+
+To install OCRmyPDF on Gentoo Linux, use the following commands:
+
+.. code-block:: bash
+
+    eselect repository enable guru
+    emaint sync --repo guru
+    emerge --ask app-text/OCRmyPDF
+
 Other Linux packages
 --------------------
 
@@ -336,7 +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:
@@ -387,18 +358,12 @@ Update the homebrew 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
 
     pip install --user ocrmypdf
 
-or system-wide:
-
-.. code-block:: bash
-
-    pip install ocrmypdf
-
 The command line program should now be available:
 
 .. code-block:: bash
@@ -417,31 +382,35 @@ Native Windows
 
 You must install the following for Windows:
 
-* Python 3.7 (64-bit) or later
+* Python 64-bit
-* Tesseract 4.0 or later
+* Tesseract 64-bit
-* Ghostscript 9.50 or later
+* Ghostscript 64-bit
 
-Using the `Chocolatey <https://chocolatey.org/>`_ package manager, install the
+Using the `winget <https://docs.microsoft.com/en-us/windows/package-manager/winget/>`_
-following when running in an Administrator command prompt:
+package manager:
+
+* ``winget install -e --id Python.Python.3.11``
+* ``winget install -e --id UB-Mannheim.TesseractOCR``
+
+You will need to install Ghostscript manually, `since it does not support automated
+installs anymore <https://artifex.com/news/ghostscript-10.01.0-disabling-silent-install-option>`_.
+
+* `Ghostscript download page <https://ghostscript.com/releases/gsdnld.html>`_.`
+
+(Or alternately, using the `Chocolatey <https://chocolatey.org/>`_ package manager, install
+the following when running in an Administrator command prompt):
 
 * ``choco install python3``
 * ``choco install --pre tesseract``
-* ``choco install ghostscript``
 * ``choco install pngquant`` (optional)
 
-The commands above will install Python 3.x (latest version), Tesseract, Ghostscript
+Either set of commands will install the required software. At the moment there is no
-and pngquant. Chocolatey may also need to install the Windows Visual C++ Runtime
+single command to install Windows.
-DLLs or other Windows patches, and may require a reboot.
 
 You may then use ``pip`` to install ocrmypdf. (This can performed by a user or
 Administrator.):
 
-* ``pip install ocrmypdf``
+* ``python3 -m pip install ocrmypdf``
-
-Chocolatey automatically selects appropriate versions of these applications. If you
-are installing them manually, please install 64-bit versions of all applications for
-64-bit Windows, or 32-bit versions of all applications for 32-bit Windows. Mixing
-the "bitness" of these programs will lead to errors.
 
 OCRmyPDF will check the Windows Registry and standard locations in your Program Files
 for third party software it needs (specifically, Tesseract and Ghostscript). To
@@ -453,9 +422,13 @@ to change the PATH.
 
     As of early 2021, users have reported problems with the Microsoft Store version of
     Python and OCRmyPDF. These issues affect many other third party Python packages.
-    Please download Python from Python.org or Chocolatey instead, and do not use the
+    Please download Python from Python.org or a package manager instead of the
     Microsoft Store version.
 
+.. warning::
+
+    32-bit Windows is not supported.
+
 Windows Subsystem for Linux
 ---------------------------
 
@@ -481,7 +454,7 @@ Cygwin64
 
 First install the the following prerequisite Cygwin packages using ``setup-x86_64.exe``::
 
-    python37 (or later)
+    python310 (or later)
     python3?-devel
     python3?-pip
     python3?-lxml
@@ -490,7 +463,7 @@ First install the the following prerequisite Cygwin packages using ``setup-x86_6
        (where 3? means match the version of python3 you installed)
 
     gcc-g++
-    ghostscript (<=9.50 or >=9.52-2 see note below)
+    ghostscript
     libexempi3
     libexempi-devel
     libffi6
@@ -501,13 +474,6 @@ First install the the following prerequisite Cygwin packages using ``setup-x86_6
     tesseract-ocr
     tesseract-ocr-devel
 
-.. note::
-
-    The Cygwin package for Ghostscript in versions 9.52 and
-    9.52-1 contained a bug that caused an exception to occur when
-    ocrmypdf invoked gs.  Make sure you have either 9.50 (or earlier)
-    or 9.52-2 (or later).
-
 Then open a Cygwin terminal (i.e. ``mintty``), run the following commands. Note
 that if you are using the version of ``pip`` that was installed with the Cygwin
 Python package, the command name will be ``pip3``.  If you have since updated
@@ -559,21 +525,6 @@ 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
@@ -592,21 +543,6 @@ try:
 You should then be able to run ``ocrmypdf --version`` and see that the
 latest version was located.
 
-Since ``pip install --user`` does not work correctly on some platforms,
-notably Ubuntu 16.04 and older, and the Homebrew version of Python,
-instead use this for a system wide installation:
-
-.. code-block:: bash
-
-    pip 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
 -------------------------------------
 
@@ -616,13 +552,16 @@ manager. ``pip`` cannot provide them.
 
 The following versions are required:
 
--  Python 3.7 or newer
+-  Python 3.10 or newer
--  Ghostscript 9.23 or newer
+-  Ghostscript 9.55 or newer
--  Tesseract 4.0.0 or newer
+-  Tesseract 4.1.1 or newer
 -  jbig2enc 0.29 or newer
 -  pngquant 2.5 or newer
 -  unpaper 6.1
 
+We recommend 64-bit versions of all software. (32-bit versions are not
+supported, although on Linux, they may still work.)
+
 jbig2enc, pngquant, and unpaper are optional. If missing certain
 features are disabled. OCRmyPDF will discover them as soon as they are
 available.
@@ -649,7 +588,7 @@ 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 3.10 or newer installed, you can install
 from source. When the ``pip`` installer runs, it will alert you if
 dependencies are missing.
 
@@ -678,9 +617,9 @@ system-wide:
 
 .. code-block:: bash
 
-    git clone -b master https://github.com/ocrmypdf/OCRmyPDF.git
+    git clone -b main https://github.com/ocrmypdf/OCRmyPDF.git
-    python3 -m venv
+    python3 -m venv .venv
-    source venv/bin/activate
+    source .venv/bin/activate
     cd OCRmyPDF
     pip install .
 
@@ -705,9 +644,9 @@ To install all of the development and test requirements:
 
 .. code-block:: bash
 
-    git clone -b master https://github.com/ocrmypdf/OCRmyPDF.git
+    git clone -b main https://github.com/ocrmypdf/OCRmyPDF.git
-    python -m venv
+    python -m .venv
-    source venv/bin/activate
+    source .venv/bin/activate
     cd OCRmyPDF
     pip install -e .[test]
 
@@ -728,3 +667,18 @@ To manually install the ``bash`` completion, copy
 To manually install the ``fish`` completion, copy
 ``misc/completion/ocrmypdf.fish`` to
 ``~/.config/fish/completions/ocrmypdf.fish``.
+
+Note on 32-bit support
+======================
+
+Many Python libraries no longer 32-bit binary wheels for Linux. This
+includes many of the libraries that OCRmyPDF depends on, such as
+Pillow. The easiest way to express this to end users is to say we don't
+support 32-bit Linux.
+
+However, if your Linux distribution still supports 32-bit binaries, you
+can still install and use OCRmyPDF. A warning message will appear.
+In practice, OCRmyPDF may need more than 32-bit memory space to run when
+large documents are processed, so there are practical limitations to what
+users can accomplish with it. Still, for the common use case of an 32-bit
+ARM NAS or Raspberry Pi processing small documents, it should work.

docs/introduction.rst

@@ -6,23 +6,23 @@
 Introduction
 ============
 
-OCRmyPDF is an application and library that adds text "layers" to images
+OCRmyPDF is a Python application and library that adds text "layers" to images in
-in PDFs, making scanned image PDFs searchable. It uses OCR to guess what text
+PDFs, making scanned image PDFs searchable. It uses OCR to guess the text
-is contained in images. It is written in Python. OCRmyPDF supports plugins
+contained in images. OCRmyPDF also supports plugins
-that allow customization of its processing steps, and is very tolerant of
+that enable customization of its processing steps, and it is highly tolerant
-PDFs that contain scanned images and "born digital" content that needs no
+of PDFs containing scanned images and "born digital" content that doesn't
-text recognition.
+require text recognition.
 
 About OCR
 =========
 
 `Optical character
 recognition <https://en.wikipedia.org/wiki/Optical_character_recognition>`__
-is technology that converts images of typed or handwritten text, such as
+is a technology that converts images of typed or handwritten text, such as
-in a scanned document, to computer text that can be selected, searched and copied.
+in a scanned document, into computer text that can be selected, searched and copied.
 
 OCRmyPDF uses
-`Tesseract <https://github.com/tesseract-ocr/tesseract>`__, the best
+`Tesseract <https://github.com/tesseract-ocr/tesseract>`__, a widely
 available open source OCR engine, to perform OCR.
 
 .. _raster-vector:
@@ -30,19 +30,19 @@ available open source OCR engine, to perform OCR.
 About PDFs
 ==========
 
-PDFs are page description files that attempts to preserve a layout
+PDFs are page description files that attempt to preserve a layout
 exactly. They contain `vector
 graphics <http://vector-conversions.com/vectorizing/raster_vs_vector.html>`__
-that can contain raster objects such as scanned images. Because PDFs can
+that can contain raster objects, such as scanned images. Because PDFs can
 contain multiple pages (unlike many image formats) and can contain fonts
-and text, it is a good format for exchanging scanned documents.
+and text, they are a suitable format for exchanging scanned documents.
 
 |image|
 
-A PDF page might contain multiple images, even if it only appears to
+A PDF page may contain multiple images, even if it appears to have only
-have one image. Some scanners or scanning software will segment pages
+one image. Some scanners or scanning software may segment pages into
-into monochromatic text and color regions for example, to improve the
+monochromatic text and color regions, for example, to enhance the compression
-compression ratio and appearance of the page.
+ratio and appearance of the page.
 
 Rasterizing a PDF is the process of generating corresponding raster images.
 OCR engines like Tesseract work with images, not scalable vector graphics
@@ -54,148 +54,131 @@ About PDF/A
 `PDF/A <https://en.wikipedia.org/wiki/PDF/A>`__ is an ISO-standardized
 subset of the full PDF specification that is designed for archiving (the
 'A' stands for Archive). PDF/A differs from PDF primarily by omitting
-features that would make it difficult to read the file in the future,
+features that could complicate future file readability,
 such as embedded Javascript, video, audio and references to external
 fonts. All fonts and resources needed to interpret the PDF must be
 contained within it. Because PDF/A disables Javascript and other types
-of embedded content, it is probably more secure.
+of embedded content, it is likely more secure.
 
 There are various conformance levels and versions, such as "PDF/A-2b".
 
-Generally speaking, the best format for scanned documents is PDF/A. Some
+In general, the preferred format for scanned documents is PDF/A. Some
 governments and jurisdictions, US Courts in particular, `mandate the use
 of PDF/A <https://pdfblog.com/2012/02/13/what-is-pdfa/>`__ for scanned
 documents.
 
-Since most people who scan documents are interested in reading them
+Since most individuals scanning documents aim for long-term readability,
-indefinitely into the future, OCRmyPDF generates PDF/A-2b by default.
+OCRmyPDF defaults to generating PDF/A-2b.
 
-PDF/A has a few drawbacks. Some PDF viewers include an alert that the
+PDF/A does have a few drawbacks. Some PDF viewers display an alert
-file is a PDF/A, which may confuse some users. It also tends to produce
+indicating that the file is in PDF/A format, which may confuse some users.
-larger files than PDF, because it embeds certain resources even if they
+Additionally, it tends to result in larger files than standard PDFs because
-are commonly available. PDF/A files can be digitally signed, but may not
+it embeds certain resources, even if they are widely available. PDF/A
-be encrypted, to ensure they can be read in the future. Fortunately,
+files can be digitally signed but may not be encrypted to ensure future
-converting from PDF/A to a regular PDF is trivial, and any PDF viewer
+readability. Fortunately, converting from PDF/A to a regular PDF is
-can view PDF/A.
+straightforward, and any PDF viewer can handle PDF/A files.
 
 What OCRmyPDF does
 ==================
 
-OCRmyPDF analyzes each page of a PDF to determine the colorspace and
+OCRmyPDF analyzes each page of a PDF to determine the required colorspace
-resolution (DPI) needed to capture all of the information on that page
+and resolution (DPI) for capturing all the information on that page without
-without losing content. It uses
+losing content. It uses
-`Ghostscript <http://ghostscript.com/>`__ to rasterize the page, and
+`Ghostscript <http://ghostscript.com/>`__ to rasterize each page and subsequently
-then performs on OCR the rasterized image to create an OCR "layer".
+performs OCR on the rasterized image to generate an OCR "layer." This layer
-The layer is then grafted back onto the original PDF.
+is then integrated back into the original PDF.
 
-While one can use a program like Ghostscript or ImageMagick to get an
+While it is possible to use a program like Ghostscript or ImageMagick to
-image and put the image through Tesseract, that actually creates a new
+obtain an image and then run that image through Tesseract OCR, this process
-PDF and many details may be lost. OCRmyPDF can produce a minimally
+actually generates a new PDF, potentially resulting in the loss of various
-changed PDF as output.
+details (such as the document's metadata). In contrast, OCRmyPDF can produce
+a minimally altered PDF as the output.
 
-OCRmyPDF also provides some image processing options, like deskew, which
+OCRmyPDF also offers several image processing options, such as deskew, which
-improves the appearance of files and quality of OCR. When these are used,
+enhances the visual quality of files and the accuracy of OCR. When these
-the OCR layer is grafted onto the processed image instead.
+options are utilized, the OCR layer is integrated into the processed image.
 
-By default, OCRmyPDF produces archival PDFs – PDF/A, which are a
+By default, OCRmyPDF generates archival PDFs in the PDF/A format, which is
-stricter subset of PDF features designed for long term archives. If
+a more rigid subset of PDF features designed for long-term archives. If you
-regular PDFs are desired, this can be disabled with
+prefer regular PDFs, you can disable this feature using the
-``--output-type pdf``.
+``--output-type pdf`` option.
 
 Why you shouldn't do this manually
 ==================================
 
 A PDF is similar to an HTML file, in that it contains document structure
-along with images. Sometimes a PDF does nothing more than present a full
+along with images. While some PDFs may solely display a full-page image,
-page image, but often there is additional content that would be lost.
+they often contain additional content that would be forfeited if not preserved.
 
-A manual process could work like either of these:
+A manual process could take one of these approaches:
 
-1. Rasterize each page as an image, OCR the images, and combine the
+1. Rasterize each page as an image, perform OCR on the images, and then merge the
-   output into a PDF. This preserves the layout of each page, but
+   output into a PDF. This method preserves the layout of each page, but
-   resamples all images (possibly losing quality, increasing file size,
+   resamples all images potentially leading to quality loss, increased file size,
-   introducing compression artifacts, etc.).
+   and the introduction of compression artifacts, among other issues.
-2. Extract each image, OCR, and combine the output into a PDF. This
+2. Extract each image, OCR, and combine the output into a PDF. This approach
-   loses the context in which images are used in the PDF, meaning that
+   loses the context in which images are used in the PDF, potentially resulting
-   cropping, rotation and scaling of pages may be lost. Some scanned
+   in loss of information related to scaling and position of images. Some scanned
-   PDFs use multiple images segmented into black and white, grayscale
+   PDFs contain multiple images segmented into black and white, grayscale
    and color regions, with stencil masks to prevent overlap, as this can
-   enhance the appearance of a file while reducing file size. Clearly,
+   enhance the appearance of a file while reducing file size.
-   reassembling these images will be easy. This also loses and text or
+   Reassembling these images can be challenging, and risks losing vector art
-   vector art on any pages in a PDF with both scanned and pure digital
+   or text that is not part of an image.
-   content.
 
-In the case of a PDF that is nothing other than a container of images
+In cases where a PDF solely serves as a container for images without any
-(no rotation, scaling, cropping, one image per page), the second
+rotation, scaling, or cropping, the second approach can be lossless.
-approach can be lossless.
 
-OCRmyPDF uses several strategies depending on input options and the
+OCRmyPDF uses various strategies depending on input options and the input PDF
-input PDF itself, but generally speaking it rasterizes a page for OCR
+itself. Generally, it rasterizes a page for OCR and then integrates the OCR
-and then grafts the OCR back onto the original. As such it can handle
+data back into the original PDF. This approach allows it to handle complex
-complex PDFs and still preserve their contents as much as possible.
+PDFs and preserve their content as much as possible.
 
-OCRmyPDF also supports a many, many edge cases that have cropped over
+Furthermore, OCRmyPDF supports a wide range of edge cases that have emerged
-several years of development. We support PDF features like images inside
+during several years of development. It accommodates PDF features like
-of Form XObjects, and pages with UserUnit scaling. We support rare image
+images within Form XObjects and pages with UserUnit scaling. It also
-formats like non-monochrome 1-bit images. We warn about files you may
+supports less common image formats like non-monochrome 1-bit images and
-not to OCR. Thanks to pikepdf and QPDF, we auto-repair PDFs that are
+provides warnings about files you may not want to OCR. Thanks to tools
-damaged. (Not that you need to know what any of these are! You should be
+like pikepdf and QPDF, it can auto-repair damaged PDFs. You don't need to
-able to throw any PDF at it.)
+understand the intricacies of these issues; you should be able to use
+OCRmyPDF with any PDF file, and expect reasonable results.
 
 Limitations
 ===========
 
-OCRmyPDF is limited by the Tesseract OCR engine. As such it experiences
+OCRmyPDF is subject to limitations imposed by the Tesseract OCR engine.
-these limitations, as do any other programs that rely on Tesseract:
+These limitations are inherent to any software relying on Tesseract:
 
--  The OCR is not as accurate as commercial OCR solutions.
+-  The OCR accuracy may not match that of commercial OCR solutions.
--  It is not capable of recognizing handwriting.
+-  It is incapable of recognizing handwriting.
--  It may find gibberish and report this as OCR output.
+-  It may detect gibberish and report it as OCR output.
--  If a document contains languages outside of those given in the
+-  Results may be subpar when a document contains languages not specified
-   ``-l LANG`` arguments, results may be poor.
+   in the ``-l LANG`` argument.
--  It is not always good at analyzing the natural reading order of
+-  Tesseract may struggle to analyze the natural reading order of documents.
-   documents. For example, it may fail to recognize that a document
+   For instance, it might fail to recognize two columns in a document and
-   contains two columns, and may try to join text across columns.
+   attempt to join text across columns.
--  Poor quality scans may produce poor quality OCR. Garbage in, garbage
+-  Poor quality scans can result in subpar OCR quality. In other words, the
-   out.
+   quality of the OCR output depends on the quality of the input.
--  It does not expose information about what font family text belongs
+-  Tesseract does not provide information about the font family to which text
-   to.
+   belongs.
-
+-  Tesseract does not divide text into paragraphs or headings. It only provides
-OCRmyPDF is also limited by the PDF specification:
+   the text and its bounding box. As such, the generated PDF does not
-
+   contain any information about the document's structure.
--  PDF encodes the position of text glyphs but does not encode document
-   structure. There is no markup that divides a document in sections,
-   paragraphs, sentences, or even words (since blank spaces are not
-   represented). As such all elements of document structure including
-   the spaces between words must be derived heuristically. Some PDF
-   viewers do a better job of this than others.
--  Because some popular open source PDF viewers have a particularly hard
-   time with spaces between words, OCRmyPDF appends a space to each text
-   element as a workaround (when using ``--pdf-renderer hocr``). While
-   this mixes document structure with graphical information that ideally
-   should be left to the PDF viewer to interpret, it improves
-   compatibility with some viewers and does not cause problems for
-   better ones.
 
 Ghostscript also imposes some limitations:
 
--  PDFs containing JBIG2-encoded content will be converted to CCITT
+-  PDFs containing JPEG 2000-encoded content may be converted to JPEG
-   Group4 encoding, which has lower compression ratios, if Ghostscript
-   PDF/A is enabled.
--  PDFs containing JPEG 2000-encoded content will be converted to JPEG
    encoding, which may introduce compression artifacts, if Ghostscript
    PDF/A is enabled.
--  Ghostscript may transcode grayscale and color images, either lossy to
+-  Ghostscript may transcode grayscale and color images, potentially
-   lossless or lossless to lossy, based on an internal algorithm. This
+   lossily, based on an internal algorithm. This
    behavior can be suppressed by setting ``--pdfa-image-compression`` to
    ``jpeg`` or ``lossless`` to set all images to one type or the other.
-   Ghostscript has no option to maintain the input image's format.
+   Ghostscript lacks an option to maintain the input image's format.
-   (Ghostscript 9.25+ can copy JPEG images without transcoding them;
+   (Modern Ghostscript can copy JPEG images without transcoding them.)
-   earlier versions will transcode.)
 -  Ghostscript's PDF/A conversion removes any XMP metadata that is not
    one of the standard XMP metadata namespaces for PDFs. In particular,
-   PRISM Metdata is removed.
+   PRISM Metadata is removed.
--  Ghostscript's PDF/A conversion seems to remove or deactivate
+-  Ghostscript's PDF/A conversion may remove or deactivate
    hyperlinks and other active content.
 
 You can use ``--output-type pdf`` to disable PDF/A conversion and produce
@@ -203,7 +186,7 @@ a standard, non-archival PDF.
 
 Regarding OCRmyPDF itself:
 
--  PDFs that use transparency are not currently represented in the test
+-  PDFs using transparency are not currently represented in the test
    suite
 
 Similar programs
@@ -211,11 +194,7 @@ Similar programs
 
 To the author's knowledge, OCRmyPDF is the most feature-rich and
 thoroughly tested command line OCR PDF conversion tool. If it does not
-meet your needs, contributions and suggestions are welcome. If not,
+meet your needs, contributions and suggestions are welcome.
-consider one of these similar open source programs:
-
--  pdf2pdfocr
--  pdfsandwich
 
 Ghostscript recently added three "pdfocr" output devices. They work by
 rasterizing all content and converting all pages to a single colour space.
@@ -223,16 +202,19 @@ rasterizing all content and converting all pages to a single colour space.
 Web front-ends
 ==============
 
-The Docker image ``ocrmypdf`` provides a web service front-end
+The Docker image of OCRmyPDF provides a web service front-end
-that allows files to submitted over HTTP and the results "downloaded".
+that allows files to submitted over HTTP, and the results can be downloaded.
-This is an HTTP server intended to simplify web services deployments; it
+This is an HTTP server intended to demonstrate how OCRmyPDF can be
-is not intended to be deployed on the public internet and no real
+integrated into a web service. It is not intended to be deployed on the
-security measures to speak of.
+public internet and does not provide any security measures.
 
 In addition, the following third-party integrations are available:
 
+-  `Paperless-ngx <https://docs.paperless-ngx.com/>`__ is a free software
+   document management system that uses OCRmyPDF to perform OCR on
+   uploaded documents.
 -  `Nextcloud OCR <https://github.com/janis91/ocr>`__ is a free software
-   plugin for the Nextcloud private cloud software
+   plugin for the Nextcloud private cloud software.
 
 OCRmyPDF is not designed to be secure against malware-bearing PDFs (see
 `Using OCRmyPDF online <ocr-service>`__). Users should ensure they

docs/jbig2.rst

@@ -14,17 +14,20 @@ expired as of 2017, but it is possible that unknown patents exist.
 
 JBIG2 encoding is recommended for OCRmyPDF and is used to losslessly
 create smaller PDFs. If JBIG2 encoding is not available, lower quality
-encodings will be used.
+CCITT encoding will be used for monochrome images.
 
 JBIG2 decoding is not patented and is performed automatically by most
 PDF viewers. It is widely supported and has been part of the PDF
 specification since 2001.
 
-On macOS, Homebrew packages jbig2enc and OCRmyPDF includes it by
+JBIG encoding is automatically provided by these OCRmyPDF packages:
-default. The Docker image for OCRmyPDF also builds its own JBIG2 encoder
+- Docker image (both Ubuntu and Alpine)
-from source.
+- Snap package
+- ArchLinux AUR package
+- Alpine Linux package
+- Homebrew on macOS
 
-For all other Linux, you must build a JBIG2 encoder from source:
+For all other platforms, you would need to build the JBIG2 encoder from source:
 
 .. code-block:: bash
 
@@ -37,26 +40,36 @@ 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.
+are packaged as libtool and libleptonica-dev. On Fedora (35) they are packaged
+as libtool and leptonica-devel.
 
 Lossy mode JBIG2
 ================
 
-OCRmyPDF provides lossy mode JBIG2 as an advanced feature. Users should
+OCRmyPDF provides lossy mode JBIG2 as an advanced and potentially dangerous
+feature. Users should
 `review the technical concerns with JBIG2 in lossy
 mode <https://en.wikipedia.org/wiki/JBIG2#Disadvantages>`__
-and decide if this feature is acceptable for their use case.
+and decide if this feature is acceptable for their use case. In general,
+this mode should not be used for archival purposes, should not be used when
+the original document is not available or will be destroyed, and should
+not be used when numbers present in the document are important, because
+there is a risk of 6/8 and 8/6 substitution errors.
 
 JBIG2 lossy mode does achieve higher compression ratios than any other
 monochrome (bitonal) compression technology; for large text documents
 the savings are considerable. JBIG2 lossless still gives great
 compression ratios and is a major improvement over the older CCITT G4
-standard. As explained above, there is some risk of substitution errors.
+standard.
 
 To turn on JBIG2 lossy mode, add the argument ``--jbig2-lossy``.
 ``--optimize {1,2,3}`` are necessary for the argument to take effect
 also required. Also, a JBIG2 encoder must be installed as described in
 the previous section.
 
+You can adjust the threshold for JBIG2 compression with the
+``--jbig2-threshold``. The default is 0.85, meaning that if two symbols
+are 85% similar, they will be compressed together.
+
 *Due to an oversight, ocrmypdf v7.0 and v7.1 used lossy mode by
 default.*

docs/languages.rst

@@ -12,22 +12,32 @@ 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
 are not, e.g. German is ``deu`` and French is ``fra``.
 
+Language packs (strictly speaking, Tesseract "traineddata" files) generally correspond
+to the language in question, but different language packs are used in certain
+situations. For German, the "Fraktur" language pack can assist with reading older
+materials in the Fraktur typeface family (``deu_frak``). Some communities have changed
+their script from Cyrillic to Latin; the Cyrillic version of Uzbek is available
+as ``uzb_cyrl`` and the Latin version is ``uzb``.
+
 After you have installed a language pack, you can use it with ``ocrmypdf -l <language>``,
 for example ``ocrmypdf -l spa``. For multilingual documents, you can specify
 all languages to be expected, e.g. ``ocrmypdf -l eng+fra`` for English and French.
 English is assumed by default unless other language(s) are specified.
 
 For Linux users, you can often find packages that provide language
-packs:
+packs.
 
-Debian and Ubuntu users
+Platform install steps
-=======================
+======================
+
+Debian and Ubuntu (apt)
+-----------------------
 
 .. code-block:: bash
 
@@ -42,8 +52,8 @@ to what languages it should search for. Multiple languages can be
 requested using either ``-l eng+fra`` (English and French) or
 ``-l eng -l fra``.
 
-Fedora users
+Fedora
-============
+------
 
 .. code-block:: bash
 
@@ -58,8 +68,8 @@ 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
+Gentoo
-============
+------
 
 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``.
@@ -70,13 +80,13 @@ This enables these languages for all packages (e.g. including aspell).
 
    # Display a list of all Tesseract language packs
    equery uses app-text/tessdata_fast
-   
+
    # Add English and German language support for Tesseract only
    echo 'app-text/tessdata_fast l10n_de l10n_en' >> /etc/portage/package.use
-   
+
-   # Add global English and German language support (the `l10n_` from equery has to be omited)
+   # 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
 
@@ -85,23 +95,31 @@ 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
+macOS
-===========
+-----
 
 You can install additional language packs by
 :ref:`installing Tesseract using Homebrew with all language packs <macos-all-languages>`.
 
-Docker users
+Docker
-============
+------
 
 Users of the OCRmyPDF Docker image should install language packs into a
 derived Docker image as
 :ref:`described in that section <docker-lang-packs>`.
 
-Windows users
+Windows
-=============
+-------
 
-The Tesseract installer provided by Chocolatey currently includes only English language. 
+The Tesseract installer provided by Chocolatey currently includes only English language.
-To install other languages, download the respective language pack (``.traineddata`` file) 
+To install other languages, download the respective language pack (``.traineddata`` file)
-from https://github.com/tesseract-ocr/tessdata/ and place it in 
+from https://github.com/tesseract-ocr/tessdata/ and place it in
 ``C:\\Program Files\\Tesseract-OCR\\tessdata`` (or wherever Tesseract OCR is installed).
+
+Custom language packs
+=====================
+
+If you have fine-tuned or trained Tesseract and generated custom trained data, you can
+copy your ``customlang.traineddata`` file into your Tesseract "tessdata" folder, and
+then use the ``-l customlang`` argument to tell OCRmyPDF to pass that language on to
+Tesseract.

docs/maintainers.rst

@@ -45,11 +45,6 @@ to indicate that your distribution modifies OCRmyPDF in some way.
 You can patch the ``__version__`` variable in ``src/ocrmypdf/_version.py`` if
 necessary.
 
-OCRmyPDF uses setuptools-scm-git-archive to ensure that tarballs downloaded from
-GitHub contain version information. Unfortunately, these tarballs are not always
-deterministic. See this
-`issue <https://github.com/ocrmypdf/OCRmyPDF/issues/841#issuecomment-936562696>`_.
-
 jbig2enc
 --------
 
@@ -61,4 +56,12 @@ improve OCRmyPDF's compression.
 Command line completions
 ------------------------
 
-Please ensure that command line completions are installed.
+Please ensure that command line completions are installed, as described in the
+installation documentation.
+
+32-bit Linux support
+--------------------
+
+If you maintain a Linux distribution that supports 32-bit x86 or ARM, OCRmyPDF
+should continue to work as long as all of its dependencies continue to be
+available in 32-bit form. Please note we do not test on 32-bit platforms.

docs/optimizer.rst

@@ -13,21 +13,40 @@ 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
+.. list-table:: Title
-optimization and ``3`` implements all options. ``1``, the default, performs only
+   :widths: 33 6 60
-safe and lossless optimizations. (This is similar to GCC's optimization
+   :header-rows: 1
-parameter.) The exact type of optimizations performed will vary over time.
 
-PDF optimization requires third-party, optional tools for certain optimizations.
+    * - Optimization level
-If these are not installed or cannot be found by OCRmyPDF, optimization will not
+      - Shorthand
-be as good.
+      - Description
+    * - ``--optimize 0``
+      - ``-O0``
+      - Disable most optimizations.
+    * - ``--optimize 1`` (default)
+      - ``-O1``
+      - Safe and lossless optimizations.
+    * - ``--optimize 2``
+      - ``-O2``
+      - Safe and lossy optimizations.
+    * - ``--optimize 3``
+      - ``-O3``
+      - Aggressive lossy optimizations.
+
+The exact type of optimizations performed will vary over time, and depend on
+the availability of third-party tools.
+
+Despite optimizations, OCRmyPDF might still increase the overall file size,
+since it must embed information about the recognized text, and depending on the
+settings chosen, may not be able to represent the output file as compactly as
+the input file.
 
 Optimizations that always occurs
 ================================
 
 OCRmyPDF will automatically replace obsolete or inferior compression schemes
-such as RLE or LZW with superior schemes such as Deflate and converting
+such as RLE or LZW with superior schemes such as Deflate, and convert
-monochrome images to CCITT G4. Since this is harmless it always occurs and there
+monochrome images to CCITT G4. Since this is lossless, it always occurs and there
 is no way to disable it. Other non-image compressed objects are compressed as
 well.
 
@@ -37,12 +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
+reduces the latency of viewing a PDF both online and from local storage, in
-actually slightly increases the file size.
+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

@@ -29,13 +29,9 @@ attack vectors.
 In short, PDFs `may contain
 viruses <https://security.stackexchange.com/questions/64052/can-a-pdf-file-contain-a-virus>`__.
 
-This
+If you do not trust a PDF or its source, do not open it or use OCRmyPDF
-`article <https://theinvisiblethings.blogspot.ca/2013/02/converting-untrusted-pdfs-into-trusted.html>`__
+on it. Consider using a Docker container or virtual machine to isolate
-describes a high-paranoia method which allows potentially hostile PDFs
+an untrusted PDF from your system.
-to be viewed and rasterized safely in a disposable virtual machine. A
-trusted PDF created in this manner is converted to images and loses all
-information making it searchable and losing all compression. OCRmyPDF
-could be used to restore searchability.
 
 How OCRmyPDF processes PDFs
 ===========================
@@ -43,11 +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
+scanners, are not well-formed files. QPDF makes it more likely that
-OCRmyPDF will succeed, but offers no security guarantees. qpdf is also
+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
@@ -58,109 +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:
+Password protected PDFs
-
+=======================
-Using OCRmyPDF online or as a service
-=====================================
-
-OCRmyPDF is not designed for use as a public web service where a
-malicious user could upload a chosen PDF. In particular, it is not
-necessarily secure against PDF malware or PDFs that cause denial of
-service. OCRmyPDF relies on Ghostscript, and therefore, if deployed
-online one should be prepared to comply with Ghostscript's Affero GPL
-license, and any other licenses.
-
-Setting aside these concerns, a side effect of OCRmyPDF is that it may
-incidentally sanitize PDFs containing certain types of malware. It
-repairs the PDF with pikepdf/libqpdf, which could correct malformed PDF
-structures that are part of an attack. When PDF/A output is selected
-(the default), the input PDF is partially reconstructed by Ghostscript.
-When ``--force-ocr`` is used, all pages are rasterized and reconverted
-to PDF, which could remove malware in embedded images.
-
-OCRmyPDF should be relatively safe to use in a trusted intranet, with
-some considerations:
-
-Limiting CPU usage
-------------------
-
-OCRmyPDF will attempt to use all available CPUs and storage, so
-executing ``nice ocrmypdf`` or limiting the number of jobs with the
-``-j`` argument may ensure the server remains available. Another option
-would be to run OCRmyPDF jobs inside a Docker container, a virtual machine,
-or a cloud instance, which can impose its own limits on CPU usage and be
-terminated "from orbit" if it fails to complete.
-
-Temporary storage requirements
-------------------------------
-
-OCRmyPDF will use a large amount of temporary storage for its work,
-proportional to the total number of pixels needed to rasterize the PDF.
-The raster image of a 8.5×11" color page at 300 DPI takes 25 MB
-uncompressed; OCRmyPDF saves its intermediates as PNG, but that still
-means it requires about 9 MB per intermediate based on average
-compression ratios. Multiple intermediates per page are also required,
-depending on the command line given. A rule of thumb would be to allow
-100 MB of temporary storage per page in a file – meaning that a small
-cloud servers or small VM partitions should be provisioned with plenty
-of extra space, if say, a 500 page file might be sent.
-
-To check temporary storage usage on actual files, run
-``ocrmypdf -k ...`` which will preserve and print the path to temporary
-storage when the job is done.
-
-To change where temporary files are stored, change the ``TMPDIR``
-environment variable for ocrmypdf's environment. (Python's
-``tempfile.gettempdir()`` returns the root directory in which temporary
-files will be stored.) For example, one could redirect ``TMPDIR`` to a
-large RAM disk to avoid wear on HDD/SSD and potentially improve
-performance. On Amazon Web Services, ``TMPDIR`` can be set to `empheral
-storage <https://docs.aws.amazon.com/AWSEC2/latest/UserGuide/InstanceStorage.html>`__.
-
-Timeouts
---------
-
-To prevent excessively long OCR jobs consider setting
-``--tesseract-timeout`` and/or ``--skip-big`` arguments. ``--skip-big``
-is particularly helpful if your PDFs include documents such as reports
-on standard page sizes with large images attached - often large images
-are not worth OCR'ing anyway.
-
-Commercial alternatives
------------------------
-
-The author also provides professional services that include OCR and
-building databases around PDFs, and is happy to provide consultation.
-
-Abbyy Cloud OCR is viable commercial alternative with a web services
-API. Amazon Textract, Google Cloud Vision, and Microsoft Azure 
-Computer Vision provide advanced OCR but have less PDF rendering capability.
-
-Password protection, digital signatures and certification
-=========================================================
 
 Password protected PDFs usually have two passwords, and owner and user
 password. When the user password is set to empty, PDF readers will open
-the file automatically and marked it as "(SECURED)". While not as
+the file automatically and mark it as "(SECURED)". Password security can
-reliable as a digital signature, this indicates that whoever set the
+also request certain restrictions on the PDF, but anyone can remove these
-password approved of the file at that time. When the user password is
+restrictions if they have either the owner *or* user password. Passwords
-set, the document cannot be viewed without the password.
+mainly present a barrier for casual users.
 
-Either way, OCRmyPDF does not remove passwords from PDFs and exits with
+OCRmyPDF cannot remove passwords from PDFs. If you want to remove a
-an error on encountering them.
+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
+.. code-block:: bash
-documents but the file can be converted to regular PDF.
+
+   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
+their authorship, approval or execution of a legal agreement. OCRmyPDF
-pdfbox (Java) have this capability as does Adobe Acrobat.
+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

@@ -17,7 +17,7 @@ If running OCRmyPDF quickly is your main goal, you can use settings such as:
 
 * ``--optimize 0`` to disable file size optimization
 * ``--output-type pdf`` to disable PDF/A generation
-* ``--fast-web-view 0`` to disable fast web view optimization
+* ``--fast-web-view 999999`` to disable fast web view optimization
 * ``--skip-big`` to skip large images, if some pages have large images
 
 You can also avoid:

docs/plugins.rst

@@ -76,20 +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
+    [project]
-    from setuptools import setup
+    name = "ocrmypdf-exampleplugin"
 
-    setup(
+    [project.entry-points."ocrmypdf"]
-        name="ocrmypdf-exampleplugin",
+    exampleplugin = "exampleplugin.pluginmodule"
-        packages=["exampleplugin"],
-        # the following makes a plugin available to pytest
-        entry_points={"ocrmypdf": ["exampleplugin = exampleplugin.pluginmodule"]},
-    )
 
 .. code-block:: ini
 
@@ -181,8 +177,13 @@ Custom command line arguments
 Execution and progress reporting
 --------------------------------
 
+.. autoclass:: ocrmypdf.pluginspec.ProgressBar
+    :members:
+    :special-members: __init__, __enter__, __exit__
+
 .. autoclass:: ocrmypdf.pluginspec.Executor
     :members:
+    :special-members: __call__
 
 .. autofunction:: ocrmypdf.pluginspec.get_logging_console
 

docs/release_notes.rst

@@ -20,6 +20,8 @@ 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.
 
+OCRmyPDF typically supports the three most recent Python versions.
+
 .. note::
 
    Attention maintainers: these release notes may be updated with information
@@ -28,6 +30,291 @@ tagged yet.
 
 .. |OCRmyPDF PyPI| image:: https://img.shields.io/pypi/v/ocrmypdf.svg
 
+
+v16.0.3
+=======
+
+-  Changed minimum required Ghostscript to 9.54, to support users of RHEL 9 and its
+   derivatives, since that is the latest version available there.
+-  Removed warning message about CVE-2023-43115, on the assumption that most
+   distributions have backported the patch by now.
+
+v16.0.2
+=======
+
+-  Temporarily changed PDF text renderer back to sandwich by default to address
+   regressions in macOS Preview.
+
+v16.0.1
+=======
+
+-  Fixed text rendering issue with new hOCR text renderer - extraneous byte order
+   marks.
+-  Tightened dependencies.
+
+v16.0.0
+=======
+
+-  Added OCR text renderer, combined the best ideas of Tesseract's PDF
+   generator and the older hOCR transformer renderer. The result is a hopefully
+   permanent fix for wordssmushedtogetherwithoutspaces issues in extracted text,
+   better registration/position of text on skewed baselines :issue:`1009`,
+   fixes to character output when the German Fraktur script is used :issue:`1191`,
+   proper rendering of right to left languages (Arabic, Hebrew, Persian) :issue:`1157`.
+   Asian languages may still have excessive word breaks compared to expectations.
+   The new renderer is the default; the old sandwich renderer is still available
+   using ``--pdf-renderer sandwich``; the old hOCR renderer is no more.
+-  The ``ocrmypdf.hocrtransform`` API has changed substantially.
+-  Support for Python 3.9 has been dropped. Python 3.10+ is now required.
+-  pikepdf >= 8.8.0 is now required.
+
+
+v15.4.4
+=======
+
+-  Fixed documentation for installing Ghostscript on Windows. :issue:`1198`
+-  Added warning message about security issue in older versions of Ghostscript.
+
+v15.4.3
+=======
+
+-  Fixed deprecation warning in pikepdf older than 8.7.1; pikepdf >= 8.7.1 is
+   now required.
+
+v15.4.2
+=======
+
+-  We now raise an exception on a certain class of PDFs that likely need an
+   explicit color conversion strategy selected to display correctly
+   for PDF/A conversion.
+-  Fixed an error that occurred while trying to write a log message after the
+   debug log handler was removed.
+
+v15.4.1
+=======
+
+-  Fixed misc/watcher.py regressions: accept ``--ocr-json-settings`` as either
+   filename or JSON string, as previously; and argument count mismatch.
+   :issue:`1183,1185`
+-  We no longer attempt to set /ProcSet in the PDF output, since this is an
+   obsolete PDF feature.
+-  Documentation improvements.
+
+v15.4.0
+=======
+
+-  Added new experimental APIs to support offline editing of the final text.
+   Specifically, one can now generate hOCR files with OCRmyPDF, edit them with
+   some other tool, and then finalize the PDF. They are experimental and
+   subject to change, including details of how the working folder is used.
+   There is no command line interface.
+-  Code reorganization: executors, progress bars, initialization and setup.
+-  Fixed test coverage in cases where the coverage tool did not properly trace
+   into threads or subprocesses. This code was still being tested but appeared
+   as not covered.
+-  In the test suite, reduced use of subprocesses and other techniques that
+   interfere with coverage measurement.
+-  Improved error check for when we appear to be running inside a snap container
+   and files are not available.
+-  Plugin specification now properly defines progress bars as a protocol rather
+   than defining them as "tqdm-like".
+-  We now default to using "forkserver" process creation on POSIX platforms
+   rather than fork, since this is method is more robust and avoids some
+   issues when threads are present.
+-  Fixed an instance where the user's request to ``--no-use-threads`` was ignored.
+-  If a PDF does not have language metadata on its top level object, we add
+   the OCR language.
+-  Replace some cryptic test error messages with more helpful ones.
+-  Debug messages for how OCRmyPDF picks the colorspace for a page are now
+   more descriptive.
+
+v15.3.1
+=======
+
+-  Fixed an issue with logging settings for misc/watcher.py introduced in the
+   previous release. :issue:`1180`
+-  We now attempt to preserve the input's extended attributes when creating
+   the output file.
+-  For some reason, the macOS build now needs OpenSSL explicitly installed.
+-  Updated documentation on Docker performance concerns.
+
+v15.3.0
+=======
+
+-  Update misc/watcher.py to improve command line interface using Typer, and
+   support ``.env`` specification of environment variables. Improved error
+   messages. Thanks to @mflagg2814 for the PR that prompted this improvement.
+-  Improved error message when a file cannot be read because we are running in
+   a snap container.
+
+v15.2.0
+=======
+
+-  Added a Docker image based on Alpine Linux. This image is smaller than the
+   Ubuntu-based image and may be useful in some situations. Currently hosted at
+   jbarlow83/ocrmypdf-alpine. Currently not available in ARM flavor.
+-  The Ubuntu Docker is now aliased to jbarlow83/ocrmypdf-ubuntu.
+-  Updated Docker documentation.
+
+v15.1.0
+=======
+
+-  We now require Pillow 10.0.1, due a serious security vulnerability in all earlier
+   versions of that dependency. The vulnerability concerns WebP images and could
+   be triggered in OCRmyPDF when creating a PDF from a malicious WebP image.
+-  Added some keyword arguments to ``ocrmypdf.ocr`` that were previously accepted
+   but undocumented.
+-  Documentation updates and typing improvements.
+
+v15.0.2
+=======
+
+-  Added Python 3.12 to test matrix.
+-  Updated documentation for notes on Python 3.12, 32-bit support and some new
+   features in v15.
+
+v15.0.1
+=======
+
+-  Wheels Python tag changed to py39.
+-  Marked as a expected fail a test that fails on recent Ghostscript versions.
+-  Clarified documentation and release notes around the extent of 32-bit support.
+-  Updated installation documentation to changes in v15.
+
+v15.0.0
+=======
+
+-  Dropped support for Python 3.8.
+-  Dropped support some older dependencies, specifically ``coloredlogs`` and
+   ``tqdm`` in favor of rich - see ``pyproject.toml`` for details.
+   Generally speaking, Ubuntu 22.04 is our new baseline system.
+-  Tightened version requirements for some dependencies.
+-  Dropped support for 32-bit Linux wheels. We strongly recommend 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 builds (e.g. Pillow), and we are
+   following suit. (Maintainers may still build 32-bit versions from source.)
+-  Changed to trusted release for PyPI publishing.
+-  pikepdf memory mapping is enabled again for improved performance, now that an
+   issue with feature in pikepdf is 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 for situations where a small portion of an image on a page is drawn
+   at high DPI (resolution). Previously, the entire page would be rasterized at the
+   highest resolution of any feature, 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 using
+   ``--color-conversion-strategy``. :issue:`1143`
+-  JBIG2 threshold for optimization is now configurable using
+   ``--jbig2-threshold``. :issue:`1133`
+
+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
 =======
 
@@ -681,7 +968,7 @@ 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

@@ -2,11 +2,18 @@
 # SPDX-FileCopyrightText: 2016 findingorder <https://github.com/findingorder>
 # SPDX-License-Identifier: MIT
 
+"""Example of using ocrmypdf as a library in a script.
+
+This script will recursively search a directory for PDF files and run OCR on
+them. It will log the results. It runs OCR on every file, even if it already
+has text. OCRmyPDF will detect files that already have text.
+
+You should edit this script to meet your needs.
+"""
+
 from __future__ import annotations
 
-# This script must be edited to meet your needs.
 import logging
-import os
 import sys
 from pathlib import Path
 

misc/completion/ocrmypdf.bash

@@ -6,52 +6,56 @@ set -o errexit
 
 __ocrmypdf_arguments()
 {
-    local arguments="--help                   (show help message)
+    local arguments="\
---language               (language(s) of the file to be OCRed)
+--help                          (show help message)
---image-dpi              (assume this DPI if input image DPI is unknown)
+--language                      (language(s) of the file to be OCRed)
---output-type            (select PDF output options)
+--image-dpi                     (assume this DPI if input image DPI is unknown)
---sidecar                (write OCR to text file)
+--output-type                   (select PDF output options)
---version                (print program version and exit)
+--sidecar                       (write OCR to text file)
---jobs                   (how many worker processes to use)
+--version                       (print program version and exit)
---quiet                  (suppress INFO messages)
+--jobs                          (how many worker processes to use)
---verbose                (set verbosity level)
+--quiet                         (suppress INFO messages)
---title                  (set metadata)
+--verbose                       (set verbosity level)
---author                 (set metadata)
+--title                         (set metadata)
---subject                (set metadata)
+--author                        (set metadata)
---keywords               (set metadata)
+--subject                       (set metadata)
---rotate-pages           (rotate pages to correct orientation)
+--keywords                      (set metadata)
---remove-background      (attempt to remove background from pages)
+--rotate-pages                  (rotate pages to correct orientation)
---deskew                 (fix small horizontal alignment skew)
+--remove-background             (attempt to remove background from pages)
---clean                  (clean document images before OCR)
+--deskew                        (fix small horizontal alignment skew)
---clean-final            (clean document images and keep result)
+--clean                         (clean document images before OCR)
---unpaper-args           (a quoted string of arguments to pass to unpaper)
+--clean-final                   (clean document images and keep result)
---oversample             (oversample images to this DPI)
+--unpaper-args                  (a quoted string of arguments to pass to unpaper)
---remove-vectors         (don\'t send vector objects to OCR)
+--oversample                    (oversample images to this DPI)
---threshold              (threshold images before OCR)
+--remove-vectors                (don\'t send vector objects to OCR)
---force-ocr              (OCR documents that already have printable text)
+--threshold                     (threshold images before OCR)
---skip-text              (skip OCR on any pages that already contain text)
+--force-ocr                     (OCR documents that already have printable text)
---redo-ocr               (redo OCR on any pages that seem to have OCR already)
+--skip-text                     (skip OCR on any pages that already contain text)
---skip-big               (skip OCR on pages larger than this many MPixels)
+--redo-ocr                      (redo OCR on any pages that seem to have OCR already)
---optimize               (select optimization level)
+--invalidate-digital-signatures (remove digital signatures from PDF)
---jpeg-quality           (JPEG quality [0..100])
+--skip-big                      (skip OCR on pages larger than this many MPixels)
---png-quality            (PNG quality [0..100])
+--optimize                      (select optimization level)
---jbig2-lossy            (enable lossy JBIG2 (see docs))
+--jpeg-quality                  (JPEG quality [0..100])
---pages                  (apply OCR to only the specified pages)
+--png-quality                   (PNG quality [0..100])
---max-image-mpixels      (image decompression bomb threshold)
+--jbig2-lossy                   (enable lossy JBIG2 (see docs))
---pdf-renderer           (select PDF renderer options)
+--jbig2-threshold               (set JBIG2 threshold (see docs))
---rotate-pages-threshold (page rotation confidence)
+--pages                         (apply OCR to only the specified pages)
---pdfa-image-compression (set PDF/A image compression options)
+--max-image-mpixels             (image decompression bomb threshold)
---fast-web-view          (if file size if above this amount in MB linearize PDF)
+--pdf-renderer                  (select PDF renderer options)
---plugin                 (name of plugin to import)
+--rotate-pages-threshold        (page rotation confidence)
---keep-temporary-files   (keep temporary files (debug)
+--pdfa-image-compression        (set PDF/A image compression options)
---tesseract-config       (set custom tesseract config file)
+--fast-web-view                 (if file size if above this amount in MB linearize PDF)
---tesseract-pagesegmode  (set tesseract --psm)
+--plugin                        (name of plugin to import)
---tesseract-oem          (set tesseract --oem)
+--keep-temporary-files          (keep temporary files (debug)
---tesseract-thresholding (set tesseract image thresholding)
+--tesseract-config              (set custom tesseract config file)
---tesseract-timeout      (maximum number of seconds to wait for OCR)
+--tesseract-pagesegmode         (set tesseract --psm)
---user-words             (specify location of user words file)
+--tesseract-oem                 (set tesseract --oem)
---user-patterns          (specify location of user patterns file)
+--tesseract-thresholding        (set tesseract image thresholding)
---no-progress-bar        (disable the progress bar)
+--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") )
@@ -191,6 +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()
 {
@@ -250,6 +268,10 @@ __ocrmypdf_check_previous()
             _filedir
             return 0
             ;;
+        --color-conversion-strategy)
+            __ocrmypdf_color-conversion-strategy
+            return 0
+            ;;
     esac
 
     return 1

misc/completion/ocrmypdf.fish

@@ -14,8 +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)"
 
@@ -83,6 +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"
@@ -128,4 +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

@@ -1,8 +1,7 @@
 # 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

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

@@ -2,6 +2,8 @@
 # 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.
@@ -25,10 +27,7 @@ logging.basicConfig(
     filemode='w',
 )
 
-if len(sys.argv) > 1:
+start_dir = sys.argv[1] if len(sys.argv) > 1 else '.'
-    start_dir = sys.argv[1]
-else:
-    start_dir = '.'
 
 for dir_name, _subdirs, file_list in os.walk(start_dir):
     logging.info(dir_name)

misc/watcher.py

@@ -3,165 +3,332 @@
 # SPDX-FileCopyrightText: 2020 James R Barlow <https://github.com/jbarlow83>
 # SPDX-License-Identifier: MIT
 
-from __future__ import annotations
+"""Watch a directory for new PDFs and OCR them."""
+
+# Do not enable annotations!
+# https://github.com/tiangolo/typer/discussions/598
+# from __future__ import annotations
 
 import json
 import logging
-import os
 import shutil
 import sys
 import time
 from datetime import datetime
+from enum import Enum
 from pathlib import Path
+from typing import Annotated, Any
 
 import pikepdf
+import typer
+from dotenv import load_dotenv
 from watchdog.events import PatternMatchingEventHandler
 from watchdog.observers import Observer
 from watchdog.observers.polling import PollingObserver
 
 import ocrmypdf
 
+load_dotenv()
+
+
 # pylint: disable=logging-format-interpolation
-
+app = typer.Typer(name="ocrmypdf-watcher")
-
-def getenv_bool(name: str, default: str = 'False'):
-    return os.getenv(name, default).lower() in ('true', 'yes', 'y', '1')
-
-
-INPUT_DIRECTORY = os.getenv('OCR_INPUT_DIRECTORY', '/input')
-OUTPUT_DIRECTORY = os.getenv('OCR_OUTPUT_DIRECTORY', '/output')
-ARCHIVE_DIRECTORY = os.getenv('OCR_ARCHIVE_DIRECTORY', '/processed')
-OUTPUT_DIRECTORY_YEAR_MONTH = getenv_bool('OCR_OUTPUT_DIRECTORY_YEAR_MONTH')
-ON_SUCCESS_DELETE = getenv_bool('OCR_ON_SUCCESS_DELETE')
-ON_SUCCESS_ARCHIVE = getenv_bool('OCR_ON_SUCCESS_ARCHIVE')
-DESKEW = getenv_bool('OCR_DESKEW')
-OCR_JSON_SETTINGS = json.loads(os.getenv('OCR_JSON_SETTINGS', '{}'))
-POLL_NEW_FILE_SECONDS = int(os.getenv('OCR_POLL_NEW_FILE_SECONDS', '1'))
-USE_POLLING = getenv_bool('OCR_USE_POLLING')
-LOGLEVEL = os.getenv('OCR_LOGLEVEL', 'INFO')
-PATTERNS = ['*.pdf', '*.PDF']
 
 log = logging.getLogger('ocrmypdf-watcher')
 
 
-def get_output_dir(root, basename):
+class LoggingLevelEnum(str, Enum):
-    if OUTPUT_DIRECTORY_YEAR_MONTH:
+    """Enum for logging levels."""
+
+    DEBUG = "DEBUG"
+    INFO = "INFO"
+    WARNING = "WARNING"
+    ERROR = "ERROR"
+    CRITICAL = "CRITICAL"
+
+
+def get_output_dir(root: Path, basename: str, output_dir_year_month: bool) -> Path:
+    if output_dir_year_month:
         today = datetime.today()
-        output_directory_year_month = (
+        output_directory_year_month = root / str(today.year) / f'{today.month:02d}'
-            Path(root) / str(today.year) / f'{today.month:02d}'
-        )
         if not output_directory_year_month.exists():
             output_directory_year_month.mkdir(parents=True, exist_ok=True)
         output_path = Path(output_directory_year_month) / basename
     else:
-        output_path = Path(OUTPUT_DIRECTORY) / basename
+        output_path = root / basename
     return output_path
 
 
-def wait_for_file_ready(file_path):
+def wait_for_file_ready(
+    file_path: Path, poll_new_file_seconds: int, retries_loading_file: int
+):
     # This loop waits to make sure that the file is completely loaded on
     # disk before attempting to read. Docker sometimes will publish the
     # watchdog event before the file is actually fully on disk, causing
     # pikepdf to fail.
 
-    retries = 5
+    tries = retries_loading_file + 1
-    while retries:
+    while tries:
         try:
-            pdf = pikepdf.open(file_path)
+            with pikepdf.Pdf.open(file_path) as pdf:
-        except (FileNotFoundError, pikepdf.PdfError) as e:
+                log.debug(f"{file_path} ready with {pdf.pages} pages")
+                return True
+        except (FileNotFoundError, OSError) as e:
             log.info(f"File {file_path} is not ready yet")
             log.debug("Exception was", exc_info=e)
-            time.sleep(POLL_NEW_FILE_SECONDS)
+            time.sleep(poll_new_file_seconds)
-            retries -= 1
+            tries -= 1
-        else:
+        except pikepdf.PdfError as e:
-            pdf.close()
+            log.info(f"File {file_path} is not full written yet")
-            return True
+            log.debug("Exception was", exc_info=e)
+            time.sleep(poll_new_file_seconds)
+            tries -= 1
 
     return False
 
 
-def execute_ocrmypdf(file_path):
+def execute_ocrmypdf(
-    file_path = Path(file_path)
+    *,
-    output_path = get_output_dir(OUTPUT_DIRECTORY, file_path.name)
+    file_path: Path,
+    archive_dir: Path,
+    output_dir: Path,
+    ocrmypdf_kwargs: dict[str, Any],
+    on_success_delete: bool,
+    on_success_archive: bool,
+    poll_new_file_seconds: int,
+    retries_loading_file: int,
+    output_dir_year_month: bool,
+):
+    output_path = get_output_dir(output_dir, file_path.name, output_dir_year_month)
 
     log.info("-" * 20)
-    log.info(f'New file: {file_path}. Waiting until fully loaded...')
+    log.info(f'New file: {file_path}. Waiting until fully written...')
-    if not wait_for_file_ready(file_path):
+    if not wait_for_file_ready(file_path, poll_new_file_seconds, retries_loading_file):
         log.info(f"Gave up waiting for {file_path} to become ready")
         return
     log.info(f'Attempting to OCRmyPDF to: {output_path}')
+
+    log.debug(
+        f'OCRmyPDF input_file={file_path} output_file={output_path} '
+        f'kwargs: {ocrmypdf_kwargs}'
+    )
     exit_code = ocrmypdf.ocr(
         input_file=file_path,
         output_file=output_path,
-        deskew=DESKEW,
+        **ocrmypdf_kwargs,
-        **OCR_JSON_SETTINGS,
     )
     if exit_code == 0:
-        if ON_SUCCESS_DELETE:
+        if on_success_delete:
             log.info(f'OCR is done. Deleting: {file_path}')
             file_path.unlink()
-        elif ON_SUCCESS_ARCHIVE:
+        elif on_success_archive:
-            log.info(f'OCR is done. Archiving {file_path.name} to {ARCHIVE_DIRECTORY}')
+            log.info(f'OCR is done. Archiving {file_path.name} to {archive_dir}')
-            shutil.move(file_path, f'{ARCHIVE_DIRECTORY}/{file_path.name}')
+            shutil.move(file_path, f'{archive_dir}/{file_path.name}')
+        else:
+            log.info('OCR is done')
     else:
         log.info('OCR is done')
 
 
 class HandleObserverEvent(PatternMatchingEventHandler):
+    def __init__(
+        self,
+        patterns=None,
+        ignore_patterns=None,
+        ignore_directories=False,
+        case_sensitive=False,
+        settings={},
+    ):
+        super().__init__(
+            patterns=patterns,
+            ignore_patterns=ignore_patterns,
+            ignore_directories=ignore_directories,
+            case_sensitive=case_sensitive,
+        )
+        self._settings = settings
+
     def on_any_event(self, event):
         if event.event_type in ['created']:
-            execute_ocrmypdf(event.src_path)
+            execute_ocrmypdf(file_path=Path(event.src_path), **self._settings)
 
 
-def main():
+@app.command()
+def main(
+    input_dir: Annotated[
+        Path,
+        typer.Argument(
+            envvar='OCR_INPUT_DIRECTORY',
+            exists=True,
+            file_okay=False,
+            dir_okay=True,
+            readable=True,
+            resolve_path=True,
+        ),
+    ] = '/input',
+    output_dir: Annotated[
+        Path,
+        typer.Argument(
+            envvar='OCR_OUTPUT_DIRECTORY',
+            exists=True,
+            file_okay=False,
+            dir_okay=True,
+            writable=True,
+            resolve_path=True,
+        ),
+    ] = '/output',
+    archive_dir: Annotated[
+        Path,
+        typer.Argument(
+            envvar='OCR_ARCHIVE_DIRECTORY',
+            exists=True,
+            file_okay=False,
+            dir_okay=True,
+            writable=True,
+            resolve_path=True,
+        ),
+    ] = '/processed',
+    output_dir_year_month: Annotated[
+        bool,
+        typer.Option(
+            envvar='OCR_OUTPUT_DIRECTORY_YEAR_MONTH',
+            help='Create a subdirectory in the output directory for each year and month',
+        ),
+    ] = False,
+    on_success_delete: Annotated[
+        bool,
+        typer.Option(
+            envvar='OCR_ON_SUCCESS_DELETE',
+            help='Delete the input file after successful OCR',
+        ),
+    ] = False,
+    on_success_archive: Annotated[
+        bool,
+        typer.Option(
+            envvar='OCR_ON_SUCCESS_ARCHIVE',
+            help='Archive the input file after successful OCR',
+        ),
+    ] = False,
+    deskew: Annotated[
+        bool,
+        typer.Option(
+            envvar='OCR_DESKEW',
+            help='Deskew the input file before OCR',
+        ),
+    ] = False,
+    ocr_json_settings: Annotated[
+        str,
+        typer.Option(
+            envvar='OCR_JSON_SETTINGS',
+            help='JSON settings to pass to OCRmyPDF (JSON string or file path)',
+        ),
+    ] = None,
+    poll_new_file_seconds: Annotated[
+        int,
+        typer.Option(
+            envvar='OCR_POLL_NEW_FILE_SECONDS',
+            help='Seconds to wait before polling a new file',
+            min=0,
+        ),
+    ] = 1,
+    use_polling: Annotated[
+        bool,
+        typer.Option(
+            envvar='OCR_USE_POLLING',
+            help='Use polling instead of filesystem events',
+        ),
+    ] = False,
+    retries_loading_file: Annotated[
+        int,
+        typer.Option(
+            envvar='OCR_RETRIES_LOADING_FILE',
+            help='Number of times to retry loading a file before giving up',
+            min=0,
+        ),
+    ] = 5,
+    loglevel: Annotated[
+        LoggingLevelEnum,
+        typer.Option(
+            envvar='OCR_LOGLEVEL',
+            help='Logging level',
+        ),
+    ] = LoggingLevelEnum.INFO,
+    patterns: Annotated[
+        str,
+        typer.Option(
+            envvar='OCR_PATTERNS',
+            help='File patterns to watch',
+        ),
+    ] = '*.pdf,*.PDF',
+):
     ocrmypdf.configure_logging(
         verbosity=(
             ocrmypdf.Verbosity.default
-            if LOGLEVEL != 'DEBUG'
+            if loglevel != LoggingLevelEnum.DEBUG
             else ocrmypdf.Verbosity.debug
         ),
         manage_root_logger=True,
     )
-    log.setLevel(LOGLEVEL)
+    log.setLevel(loglevel.value)
     log.info(
         f"Starting OCRmyPDF watcher with config:\n"
-        f"Input Directory: {INPUT_DIRECTORY}\n"
+        f"Input Directory: {input_dir}\n"
-        f"Output Directory: {OUTPUT_DIRECTORY}\n"
+        f"Output Directory: {output_dir}\n"
-        f"Output Directory Year & Month: {OUTPUT_DIRECTORY_YEAR_MONTH}\n"
+        f"Output Directory Year & Month: {output_dir_year_month}\n"
-        f"Archive Directory: {ARCHIVE_DIRECTORY}"
+        f"Archive Directory: {archive_dir}"
     )
     log.debug(
-        f"INPUT_DIRECTORY: {INPUT_DIRECTORY}\n"
+        f"INPUT_DIRECTORY: {input_dir}\n"
-        f"OUTPUT_DIRECTORY: {OUTPUT_DIRECTORY}\n"
+        f"OUTPUT_DIRECTORY: {output_dir}\n"
-        f"OUTPUT_DIRECTORY_YEAR_MONTH: {OUTPUT_DIRECTORY_YEAR_MONTH}\n"
+        f"OUTPUT_DIRECTORY_YEAR_MONTH: {output_dir_year_month}\n"
-        f"ARCHIVE_DIRECTORY: {ARCHIVE_DIRECTORY}\n"
+        f"ARCHIVE_DIRECTORY: {archive_dir}\n"
-        f"ON_SUCCESS_DELETE: {ON_SUCCESS_DELETE}\n"
+        f"ON_SUCCESS_DELETE: {on_success_delete}\n"
-        f"ON_SUCCESS_ARCHIVE: {ON_SUCCESS_ARCHIVE}\n"
+        f"ON_SUCCESS_ARCHIVE: {on_success_archive}\n"
-        f"DESKEW: {DESKEW}\n"
+        f"DESKEW: {deskew}\n"
-        f"ARGS: {OCR_JSON_SETTINGS}\n"
+        f"ARGS: {ocr_json_settings}\n"
-        f"POLL_NEW_FILE_SECONDS: {POLL_NEW_FILE_SECONDS}\n"
+        f"POLL_NEW_FILE_SECONDS: {poll_new_file_seconds}\n"
-        f"USE_POLLING: {USE_POLLING}\n"
+        f"RETRIES_LOADING_FILE: {retries_loading_file}\n"
-        f"LOGLEVEL: {LOGLEVEL}"
+        f"USE_POLLING: {use_polling}\n"
+        f"LOGLEVEL: {loglevel.value}"
     )
 
-    if 'input_file' in OCR_JSON_SETTINGS or 'output_file' in OCR_JSON_SETTINGS:
+    if ocr_json_settings and Path(ocr_json_settings).exists():
-        log.error('OCR_JSON_SETTINGS should not specify input file or output file')
+        json_settings = json.loads(Path(ocr_json_settings).read_text())
+    else:
+        json_settings = json.loads(ocr_json_settings or '{}')
+
+    if 'input_file' in json_settings or 'output_file' in json_settings:
+        log.error(
+            'OCR_JSON_SETTINGS (--ocr-json-settings) may not specify input/output file'
+        )
         sys.exit(1)
 
-    handler = HandleObserverEvent(patterns=PATTERNS)
+    handler = HandleObserverEvent(
-    if USE_POLLING:
+        patterns=patterns.split(','),
+        settings={
+            'archive_dir': archive_dir,
+            'output_dir': output_dir,
+            'ocrmypdf_kwargs': json_settings | {'deskew': deskew},
+            'on_success_delete': on_success_delete,
+            'on_success_archive': on_success_archive,
+            'poll_new_file_seconds': poll_new_file_seconds,
+            'retries_loading_file': retries_loading_file,
+            'output_dir_year_month': output_dir_year_month,
+        },
+    )
+    if use_polling:
         observer = PollingObserver()
     else:
         observer = Observer()
-    observer.schedule(handler, INPUT_DIRECTORY, recursive=True)
+    observer.schedule(handler, input_dir, recursive=True)
     observer.start()
+    typer.echo(f"Watching {input_dir} for new PDFs. Press Ctrl+C to exit.")
     try:
         while True:
-            time.sleep(1)
+            time.sleep(30)
     except KeyboardInterrupt:
         observer.stop()
     observer.join()
 
 
 if __name__ == "__main__":
-    main()
+    app()

misc/webservice.py

@@ -2,7 +2,7 @@
 # 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
@@ -15,7 +15,7 @@ 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
@@ -48,7 +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, capture_output=True, 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

@@ -1,16 +1,86 @@
+# SPDX-FileCopyrightText: 2022 James R. Barlow
+# SPDX-License-Identifier: MPL-2.0
 [build-system]
-requires = [
+requires = ["setuptools >= 61", "setuptools_scm[toml] >= 7.0.5", "wheel"]
-  "setuptools >= 52",
-  "setuptools_scm[toml] >= 7.0.5",
-  "wheel"
-]
 build-backend = "setuptools.build_meta"
 
+[project]
+name = "ocrmypdf"
+dynamic = ["version"]
+description = "OCRmyPDF adds an OCR text layer to scanned PDF files, allowing them to be searched"
+readme = "README.md"
+license = { text = "MPL-2.0" }
+requires-python = ">=3.10"
+dependencies = [
+  "Pillow>=10.0.1",
+  "deprecation>=2.1.0",
+  "img2pdf>=0.5",
+  "packaging>=20",
+  "pdfminer.six>=20220319",
+  "pikepdf>=8.10.1",
+  "pluggy>=1",
+  "rich>=13",
+]
+authors = [{ name = "James R. Barlow", email = "james@purplerock.ca" }]
+classifiers = [
+  "Development Status :: 5 - Production/Stable",
+  "Environment :: Console",
+  "Intended Audience :: End Users/Desktop",
+  "Intended Audience :: Science/Research",
+  "Intended Audience :: System Administrators",
+  "License :: OSI Approved :: Mozilla Public License 2.0 (MPL 2.0)",
+  "Operating System :: MacOS",
+  "Operating System :: Microsoft :: Windows",
+  "Operating System :: POSIX",
+  "Operating System :: POSIX :: BSD",
+  "Operating System :: POSIX :: Linux",
+  "Programming Language :: Python :: 3",
+  "Topic :: Scientific/Engineering :: Image Recognition",
+  "Topic :: Text Processing :: Indexing",
+  "Topic :: Text Processing :: Linguistic",
+]
+keywords = ["PDF", "OCR", "optical character recognition", "PDF/A", "scanning"]
+
+[project.urls]
+Documentation = "https://ocrmypdf.readthedocs.io/"
+Source = "https://github.com/ocrmypdf/OCRmyPDF"
+Tracker = "https://github.com/ocrmypdf/OCRmyPDF/issues"
+
+[project.optional-dependencies]
+docs = ["sphinx", "sphinx-issues", "sphinx-rtd-theme"]
+extended_test = ["PyMuPDF>=1.19.1"]
+test = [
+  "coverage[toml]>=6.2",
+  "hypothesis>=6.36.0",
+  "pytest>=6.2.5",
+  "pytest-cov>=3.0.0",
+  "pytest-xdist>=2.5.0",
+  "python-xmp-toolkit==2.0.1", # also requires apt-get install libexempi3
+  "reportlab>=3.6.8",
+  "types-Pillow",
+  "types-humanfriendly",
+]
+watcher = ["watchdog>=1.0.2", "typer[all]", "python-dotenv"]
+webservice = ["Flask>=2.0.1"]
+
+[project.scripts]
+ocrmypdf = "ocrmypdf.__main__:run"
+
+[tool.setuptools.package-data]
+ocrmypdf = ["data/sRGB.icc", "py.typed"]
+
+[tool.setuptools.packages.find]
+where = ["src"]
+namespaces = false
+
 [tool.setuptools_scm]
 
+[tool.distutils.bdist_wheel]
+python-tag = "py310"
+
 [tool.black]
 line-length = 88
-target-version = ["py37", "py38"]
+target-version = ["py310", "py311", "py312"]
 skip-string-normalization = true
 include = '\.pyi?$'
 exclude = '''
@@ -34,7 +104,8 @@ exclude = '''
 [tool.coverage.run]
 branch = true
 parallel = true
-concurrency = ["multiprocessing"]
+concurrency = ["multiprocessing", "thread"]
+sigterm = true
 
 [tool.coverage.paths]
 source = ["src/ocrmypdf"]
@@ -51,28 +122,7 @@ exclude_lines = [
   "if 0:",
   "if False:",
   "if __name__ == .__main__.:",
-  "if TYPE_CHECKING:"
+  "if TYPE_CHECKING:",
-]
-
-[tool.isort]
-profile = "black"
-known_first_party = "ocrmypdf"
-known_third_party = [
-  "PIL",
-  "flask",
-  "img2pdf",
-  "ocrmypdf",
-  "pdfminer",
-  "pikepdf",
-  "pkg_resources",
-  "pluggy",
-  "pytest",
-  "reportlab",
-  "setuptools",
-  "sphinx_rtd_theme",
-  "tqdm",
-  "watchdog",
-  "werkzeug"
 ]
 
 [tool.pytest.ini_options]
@@ -95,11 +145,29 @@ module = [
   'reportlab.*',
   'fitz',
   'libxmp.utils',
-  'importlib_metadata'
 ]
 ignore_missing_imports = true
 
-[tool.pylint.basic]
+[tool.ruff]
-good-names = ["i", "j", "k", "ex", "Run", "_", "e", "p", "im", "w", "h", "m", "x", "y", "a", "b", "fp", "n", "f", "s", "v", "q", "dx", "dy"]
+select = [
-logging-format-style = "old"
+  "D",    # pydocstyle
-disable = ["raw-checker-failed", "bad-inline-option", "locally-disabled", "file-ignored", "suppressed-message", "useless-suppression", "deprecated-pragma", "use-symbolic-message-instead", "logging-fstring-interpolation", "missing-function-docstring", "too-few-public-methods"]
+  "E",    # pycodestyle
+  "W",    # pycodestyle
+  "F",    # pyflakes
+  "I001", # isort
+  "UP",   # pyupgrade
+]
+target-version = "py310"
+
+[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

@@ -1,116 +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/ocrmypdf/OCRmyPDF
-author = James R. Barlow
-author_email = james@purplerock.ca
-license = MPL-2.0
-license_file = LICENSE
-license_files =
-    LICENSE
-classifiers =
-    Development Status :: 5 - Production/Stable
-    Environment :: Console
-    Intended Audience :: End Users/Desktop
-    Intended Audience :: Science/Research
-    Intended Audience :: System Administrators
-    License :: OSI Approved :: Mozilla Public License 2.0 (MPL 2.0)
-    Operating System :: MacOS :: MacOS X
-    Operating System :: Microsoft :: Windows :: Windows 10
-    Operating System :: POSIX
-    Operating System :: POSIX :: BSD
-    Operating System :: POSIX :: Linux
-    Programming Language :: Python :: 3
-    Programming Language :: Python :: 3 :: Only
-    Programming Language :: Python :: 3.7
-    Programming Language :: Python :: 3.8
-    Programming Language :: Python :: 3.9
-    Programming Language :: Python :: 3.10
-    Topic :: Scientific/Engineering :: Image Recognition
-    Topic :: Text Processing :: Indexing
-    Topic :: Text Processing :: Linguistic
-keywords =
-    PDF
-    OCR
-    optical character recognition
-    PDF/A
-    scanning
-project_urls =
-    Documentation = https://ocrmypdf.readthedocs.io/
-    Source = https://github.com/ocrmypdf/OCRmyPDF
-    Tracker = https://github.com/ocrmypdf/OCRmyPDF/issues
-
-[options]
-packages = find:
-install_requires =
-    Pillow>=8.2.0
-    coloredlogs>=14.0  # strictly optional
-    img2pdf>=0.3.0  # pure Python
-    packaging>=20
-    pdfminer.six!=20200720,>=20191110
-    pikepdf!=5.0.0,>=4.0.0
-    pluggy>=0.13.0
-    reportlab>=3.5.66
-    tqdm>=4
-    importlib-metadata>=4;python_version<'3.8'  # until Python 3.8
-    importlib-resources>=5;python_version<'3.9'  # until Python 3.9
-    typing-extensions>=4;python_version<'3.10'
-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
-    types-Pillow
-    types-humanfriendly
-watcher =
-    watchdog>=1.0.2
-webservice =
-    Flask>=1
-
-[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

@@ -1,10 +0,0 @@
-# SPDX-FileCopyrightText: 2022 James R. Barlow
-# SPDX-License-Identifier: MPL-2.0
-
-"""setup.py to support older setuptools and pip."""
-
-from __future__ import annotations
-
-from setuptools import setup
-
-setup()

snapcraft.yaml

@@ -1,8 +1,13 @@
+# 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: core20
+base: core22
 version: git
-summary: OCRmyPDF adds optical character recognition (OCR) to PDFs
+summary: OCRmyPDF adds a searchable text layer to scanned PDF files
 description: OCRmyPDF packaged for snap
 grade: stable
 confinement: strict
@@ -13,8 +18,8 @@ architectures: [amd64]
 
 environment:
   TESSDATA_PREFIX: $SNAP/usr/share/tesseract-ocr/4.00/tessdata
-  GS_LIB: $SNAP/usr/share/ghostscript/9.50/Resource/Init
+  GS_LIB: $SNAP/usr/share/ghostscript/9.55/Resource/Init
-  GS_FONTPATH: $SNAP/usr/share/ghostscript/9.50/Resource/Font
+  GS_FONTPATH: $SNAP/usr/share/ghostscript/9.55/Resource/Font
   LD_LIBRARY_PATH: $SNAP/usr/lib/x86_64-linux-gnu
 
 apps:
@@ -41,9 +46,19 @@ parts:
     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: https://github.com/ocrmypdf/OCRmyPDF.git
+    source: .
+
+    build-packages:
+      - python3-pip
 
     stage-packages:
       - ghostscript
@@ -66,7 +81,14 @@ parts:
       - 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

@@ -10,8 +10,15 @@ from pluggy import HookimplMarker as _HookimplMarker
 from ocrmypdf import helpers, hocrtransform, pdfa, pdfinfo
 from ocrmypdf._concurrent import Executor
 from ocrmypdf._jobcontext import PageContext, PdfContext
+from ocrmypdf._pipelines._common import (
+    configure_debug_logging,
+)
 from ocrmypdf._version import PROGRAM_NAME, __version__
-from ocrmypdf.api import Verbosity, configure_logging, ocr
+from ocrmypdf.api import (
+    Verbosity,
+    configure_logging,
+    ocr,
+)
 from ocrmypdf.exceptions import (
     BadArgsError,
     DpiError,
@@ -21,7 +28,6 @@ from ocrmypdf.exceptions import (
     InputFileError,
     MissingDependencyError,
     OutputFileAccessError,
-    PdfMergeFailedError,
     PriorOcrFoundError,
     SubprocessOutputError,
     TesseractConfigError,
@@ -30,3 +36,35 @@ from ocrmypdf.exceptions import (
 from ocrmypdf.pluginspec import OcrEngine, OrientationConfidence
 
 hookimpl = _HookimplMarker('ocrmypdf')
+
+
+__all__ = [
+    '__version__',
+    'BadArgsError',
+    'configure_debug_logging',
+    'configure_logging',
+    'DpiError',
+    'EncryptedPdfError',
+    'Executor',
+    'ExitCode',
+    'ExitCodeException',
+    'helpers',
+    'hocrtransform',
+    'hookimpl',
+    'InputFileError',
+    'MissingDependencyError',
+    'ocr',
+    'OcrEngine',
+    'OrientationConfidence',
+    'OutputFileAccessError',
+    'PageContext',
+    'pdfa',
+    'PdfContext',
+    'pdfinfo',
+    'PriorOcrFoundError',
+    'PROGRAM_NAME',
+    'SubprocessOutputError',
+    'TesseractConfigError',
+    'UnsupportedImageFormatError',
+    'Verbosity',
+]

src/ocrmypdf/__main__.py

@@ -7,15 +7,15 @@
 from __future__ import annotations
 
 import logging
+import multiprocessing
 import os
 import signal
 import sys
 from contextlib import suppress
-from multiprocessing import set_start_method
 
 from ocrmypdf import __version__
+from ocrmypdf._pipelines.ocr import run_pipeline_cli
 from ocrmypdf._plugin_manager import get_parser_options_plugins
-from ocrmypdf._sync import run_pipeline
 from ocrmypdf._validation import check_options
 from ocrmypdf.api import Verbosity, configure_logging
 from ocrmypdf.exceptions import (
@@ -29,10 +29,16 @@ log = logging.getLogger('ocrmypdf')
 
 
 def sigbus(*args):
+    """Handle SIGBUS signals.
+
+    pikepdf, depending on configuration, may use mmap so SIGBUS is a
+    possibility.
+    """
     raise InputFileError("Lost access to the input file")
 
 
 def run(args=None):
+    """Run the ocrmypdf command line interface."""
     _parser, options, plugin_manager = get_parser_options_plugins(args=args)
 
     with suppress(AttributeError, PermissionError):
@@ -66,11 +72,12 @@ def run(args=None):
     with suppress(AttributeError, OSError):
         signal.signal(signal.SIGBUS, sigbus)
 
-    result = run_pipeline(options=options, plugin_manager=plugin_manager)
+    result = run_pipeline_cli(options=options, plugin_manager=plugin_manager)
     return result
 
 
 if __name__ == '__main__':
-    if sys.platform == 'darwin' and sys.version_info < (3, 8):
+    multiprocessing.freeze_support()
-        set_start_method('spawn')  # see python bpo-33725
+    if os.name == 'posix':
+        multiprocessing.set_start_method('forkserver')
     sys.exit(run())

src/ocrmypdf/_concurrent.py

@@ -7,27 +7,20 @@ from __future__ import annotations
 
 import threading
 from abc import ABC, abstractmethod
-from typing import Callable, Iterable
+from collections.abc import Iterable
+from typing import Any, Callable, TypeVar
+
+from ocrmypdf._progressbar import NullProgressBar, ProgressBar
+
+T = TypeVar('T')
 
 
 def _task_noop(*_args, **_kwargs):
     return
 
 
-class NullProgressBar:
+def _task_finished_noop(_result: Any, pbar: ProgressBar):
-    """Progress bar API that takes no actions."""
+    pbar.update()
-
-    def __init__(self, **kwargs):
-        pass
-
-    def __enter__(self):
-        return self
-
-    def __exit__(self, exc_type, exc_value, traceback):
-        return False
-
-    def update(self, _arg=None):
-        return
 
 
 class Executor(ABC):
@@ -45,14 +38,13 @@ class Executor(ABC):
         *,
         use_threads: bool,
         max_workers: int,
-        tqdm_kwargs: dict,
+        progress_kwargs: dict,
         worker_initializer: Callable | None = None,
-        task: Callable | None = None,
+        task: Callable[..., T] | None = None,
         task_arguments: Iterable | None = None,
-        task_finished: Callable | None = None,
+        task_finished: Callable[[T, ProgressBar], None] | 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
@@ -60,7 +52,7 @@ 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.
+            progress_kwargs: Arguments to set up the progress bar.
             worker_initializer: Called when a worker is initialized, in the worker's
                 execution context. If the child workers are processes, it must be
                 possible to marshall/pickle the worker initializer.
@@ -73,13 +65,12 @@ 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:
             worker_initializer = _task_noop
         if not task_finished:
-            task_finished = _task_noop
+            task_finished = _task_finished_noop
         if not task:
             task = _task_noop
 
@@ -87,7 +78,7 @@ class Executor(ABC):
             self._execute(
                 use_threads=use_threads,
                 max_workers=max_workers,
-                tqdm_kwargs=tqdm_kwargs,
+                progress_kwargs=progress_kwargs,
                 worker_initializer=worker_initializer,
                 task=task,
                 task_arguments=task_arguments,
@@ -100,7 +91,7 @@ class Executor(ABC):
         *,
         use_threads: bool,
         max_workers: int,
-        tqdm_kwargs: dict,
+        progress_kwargs: dict,
         worker_initializer: Callable,
         task: Callable,
         task_arguments: Iterable,
@@ -126,13 +117,13 @@ class SerialExecutor(Executor):
         *,
         use_threads: bool,
         max_workers: int,
-        tqdm_kwargs: dict,
+        progress_kwargs: dict,
         worker_initializer: Callable,
         task: Callable,
         task_arguments: Iterable,
         task_finished: Callable,
     ):  # pylint: disable=unused-argument
-        with self.pbar_class(**tqdm_kwargs) as pbar:
+        with self.pbar_class(**progress_kwargs) as pbar:
             for args in task_arguments:
-                result = task(args)
+                result = task(*args)
                 task_finished(result, pbar)

src/ocrmypdf/_exec/__init__.py

@@ -1,6 +1,6 @@
 # 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

@@ -1,65 +1,75 @@
 # 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
 import re
-import sys
+from collections import deque
 from io import BytesIO
 from os import fspath
 from pathlib import Path
 from subprocess import PIPE, CalledProcessError
 
+from packaging.version import Version
 from PIL import Image, UnidentifiedImageError
 
-from ocrmypdf.exceptions import SubprocessOutputError
+from ocrmypdf.exceptions import ColorConversionNeededError, SubprocessOutputError
 from ocrmypdf.helpers import Resolution
 from ocrmypdf.subprocess import get_version, run, run_polling_stderr
 
-# Remove this workaround when we require Pillow >= 10
+COLOR_CONVERSION_STRATEGIES = frozenset(
-try:
+    [
-    Transpose = Image.Transpose  # type: ignore
+        'CMYK',
-except AttributeError:
+        'Gray',
-    # Pillow 9 shim
+        'LeaveColorUnchanged',
-    Transpose = Image  # type: ignore
+        'RGB',
+        'UseDeviceIndependentColor',
+    ]
+)
+# Ghostscript executable - gswin32c is not supported
+GS = 'gswin64c' if os.name == 'nt' else 'gs'
+
 
 log = logging.getLogger(__name__)
 
-# Most reliable what to get the bitness of Python interpreter, according to Python docs
-_IS_64BIT = sys.maxsize > 2**32
 
-_GSWIN = None
+class DuplicateFilter(logging.Filter):
-if os.name == 'nt':
+    """Filter out duplicate log messages.
-    if _IS_64BIT:
-        _GSWIN = 'gswin64c'
-    else:
-        _GSWIN = 'gswin32c'
 
-GS = _GSWIN if _GSWIN else 'gs'
+    A context window of default 5 messages is used to determine if a message is a
-del _GSWIN
+    duplicate. This is because some Ghostscript messages are word wrapped.
-
-
-def version():
-    return get_version(GS)
-
-
-def jpeg_passthrough_available() -> bool:
-    """Returns True if the installed version of Ghostscript supports JPEG passthru
-
-    Prior to 9.23, Ghostscript decoded and re-encoded JPEGs internally. In 9.23
-    it gained the ability to keep JPEGs unmodified. However, the 9.23
-    implementation was buggy and would deletes the last two bytes of images in
-    some cases, as reported here.
-    https://bugs.ghostscript.com/show_bug.cgi?id=699216
-
-    The issue was fixed for 9.24, hence that is the first version we consider
-    the feature available. (Ghostscript 9.24 has its own problems is blacklisted.)
     """
-    return version() >= '9.24'
+
+    def __init__(self, logger: logging.Logger, context_window=5):
+        self.window: deque[str] = deque([], maxlen=context_window)
+        self.logger = logger
+        self.levelno = logging.DEBUG
+        self.count = 0
+
+    def filter(self, record):
+        if record.msg in self.window:
+            self.count += 1
+            self.levelno = record.levelno
+            return False
+        else:
+            if self.count >= 1:
+                rep_msg = f"(suppressed {self.count} repeated lines)"
+                self.count = 0  # Avoid infinite recursion
+                self.logger.log(self.levelno, rep_msg)
+                self.window.clear()
+            self.window.append(record.msg)
+            return True
+
+
+log.addFilter(DuplicateFilter(log))
+
+
+def version() -> Version:
+    return Version(get_version(GS))
 
 
 def _gs_error_reported(stream) -> bool:
@@ -67,6 +77,20 @@ def _gs_error_reported(stream) -> bool:
     return bool(match)
 
 
+def _gs_devicen_reported(stream) -> bool:
+    """Did Ghostscript warn about a DeviceN with inappropriate alternate?
+
+    If so, we need the user to select a color conversion, or the resulting PDF will
+    not present correctly in some PDF viewers.
+    """
+    match = re.search(
+        r'DeviceN.*inappropriate alternate',
+        stream,
+        flags=re.IGNORECASE | re.MULTILINE,
+    )
+    return bool(match)
+
+
 def rasterize_pdf(
     input_file: os.PathLike,
     output_file: os.PathLike,
@@ -77,6 +101,7 @@ def rasterize_pdf(
     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)
@@ -97,6 +122,7 @@ 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',
             '-',
@@ -124,11 +150,11 @@ def rasterize_pdf(
                 # 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)
+                    im = im.transpose(Image.Transpose.ROTATE_90)
                 elif rotation == 180:
-                    im = im.transpose(Transpose.ROTATE_180)
+                    im = im.transpose(Image.Transpose.ROTATE_180)
                 elif rotation == 270:
-                    im = im.transpose(Transpose.ROTATE_270)
+                    im = im.transpose(Image.Transpose.ROTATE_270)
                 if rotation % 180 == 90:
                     page_dpi = page_dpi.flip_axis()
             im.save(fspath(output_file), dpi=page_dpi)
@@ -172,9 +198,11 @@ 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.
@@ -200,23 +228,16 @@ 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.
     gs_version = version()
-    strategy = ('/' + strategy) if gs_version < '9.19' else strategy
+    if gs_version == Version('9.56.0'):
-
+        # 9.56.0 breaks our OCR, should be fixed in 9.56.1
-    if gs_version == '9.23':
+        # https://bugs.ghostscript.com/show_bug.cgi?id=705187
-        # 9.23: added JPEG passthrough as a new feature, but with a bug that
-        # incorrectly formats some images. Fixed as of 9.24. So we disable this
-        # feature for 9.23.
-        # https://bugs.ghostscript.com/show_bug.cgi?id=699216
-        compression_args.append('-dPassThroughJPEGImages=false')
-    elif gs_version == '9.56.0':
-        # 9.56.0 breaks our OCR...?
         compression_args.append('-dNEWPDF=false')
 
+    if os.name == 'nt':
+        # Windows has lots of fatal "permission denied" errors
+        stop_on_error = False
+
     # nb no need to specify ProcessColorModel when ColorConversionStrategy
     # is set; see:
     # https://bugs.ghostscript.com/show_bug.cgi?id=699392
@@ -226,15 +247,16 @@ 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",
             "-",
@@ -242,7 +264,6 @@ def generate_pdfa(
         ]
     )
     args_gs.extend(fspath(s) for s in pdf_pages)  # Stringify Path objs
-
     try:
         with Path(output_file).open('wb') as output:
             p = run_polling_stderr(
@@ -265,14 +286,11 @@ 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
+            # Ghostscript outputs the pattern **** Error: ....  frequently.
-            repcount = 0
+            # 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:
+                log.error(part)
-                    if repcount > 1:
+        if _gs_devicen_reported(stderr):
-                        log.error(f"(previous error message repeated {repcount} times)")
+            raise ColorConversionNeededError()
-                        repcount = 0
-                    log.error(part)
-                else:
-                    repcount += 1
-                last_part = part

src/ocrmypdf/_exec/jbig2enc.py

@@ -1,18 +1,20 @@
 # 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():
+def version() -> Version:
-    return get_version('jbig2', regex=r'jbig2enc (\d+(\.\d+)*).*')
+    return Version(get_version('jbig2', regex=r'jbig2enc (\d+(\.\d+)*).*'))
 
 
 def available():
@@ -23,15 +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)
@@ -39,17 +43,9 @@ def convert_group(*, cwd, infiles, out_prefix):
     return proc
 
 
-def convert_group_mp(args):
+def convert_single(cwd, infile, outfile, threshold):
-    return convert_group(cwd=args[0], infiles=args[1], out_prefix=args[2])
+    args = ['jbig2', '--pdf', '-t', str(threshold), infile]
-
-
-def convert_single(*, cwd, infile, outfile):
-    args = ['jbig2', '-p', infile]
     with open(outfile, 'wb') as fstdout:
         proc = run(args, cwd=cwd, stdout=fstdout, stderr=PIPE)
     proc.check_returncode()
     return proc
-
-
-def convert_single_mp(args):
-    return convert_single(cwd=args[0], infile=args[1], outfile=args[2])

src/ocrmypdf/_exec/pngquant.py

@@ -1,23 +1,21 @@
 # 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 PIL import Image
+from packaging.version import Version
 
 from ocrmypdf.exceptions import MissingDependencyError
 from ocrmypdf.subprocess import get_version, run
 
 
-def version():
+def version() -> Version:
-    return get_version('pngquant', regex=r'(\d+(\.\d+)*).*')
+    return Version(get_version('pngquant', regex=r'(\d+(\.\d+)*).*'))
 
 
 def available():
@@ -28,21 +26,16 @@ def available():
     return True
 
 
-@contextmanager
-def input_as_png(input_file: Path):
-    if not input_file.name.endswith('.png'):
-        with Image.open(input_file) as im:
-            bio = BytesIO()
-            im.save(bio, format='png')
-            bio.seek(0)
-            yield bio
-    else:
-        with open(input_file, 'rb') as f:
-            yield f
-
-
 def quantize(input_file: Path, output_file: Path, quality_min: int, quality_max: int):
-    with input_as_png(input_file) as input_stream:
+    """Quantize a PNG image using pngquant.
+
+    Args:
+        input_file: Input PNG image
+        output_file: Output PNG image
+        quality_min: Minimum quality to use
+        quality_max: Maximum quality to use
+    """
+    with open(input_file, 'rb') as input_stream:
         args = [
             'pngquant',
             '--force',
@@ -57,7 +50,3 @@ def quantize(input_file: Path, output_file: Path, quality_min: int, quality_max:
     if result.returncode == 0:
         # input_file could be the same as output_file, so we defer the write
         output_file.write_bytes(result.stdout)
-
-
-def quantize_mp(args):
-    return quantize(*args)

src/ocrmypdf/_exec/tesseract.py

@@ -1,19 +1,19 @@
 # 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
+from contextlib import suppress
 from math import pi
 from os import fspath
 from pathlib import Path
 from subprocess import PIPE, STDOUT, CalledProcessError, TimeoutExpired
 
 from packaging.version import Version
-from PIL import Image
 
 from ocrmypdf.exceptions import (
     MissingDependencyError,
@@ -26,23 +26,6 @@ from ocrmypdf.subprocess import get_version, run
 log = logging.getLogger(__name__)
 
 
-HOCR_TEMPLATE = """<?xml version="1.0" encoding="UTF-8"?>
-<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN"
-    "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
-<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
- <head>
-  <title></title>
-<meta http-equiv="Content-Type" content="text/html;charset=utf-8" />
-  <meta name='ocr-system' content='tesseract 4.0.0' />
-  <meta name='ocr-capabilities' content='ocr_page ocr_carea ocr_par ocr_line ocrx_word ocrp_wconf'/>
-</head>
-<body>
-  <div class='ocr_page' id='page_1' title='image "_blank.png"; bbox 0 0 {0} {1}; ppageno 0'>
-  </div>
- </body>
-</html>
-"""
-
 TESSERACT_THRESHOLDING_METHODS: dict[str, int] = {
     'auto': 0,
     'otsu': 0,
@@ -52,7 +35,7 @@ TESSERACT_THRESHOLDING_METHODS: dict[str, int] = {
 
 
 class TesseractLoggerAdapter(logging.LoggerAdapter):
-    "Prepend [tesseract] to messages emitted from tesseract"
+    """Prepend [tesseract] to messages emitted from tesseract."""
 
     def process(self, msg, kwargs):
         kwargs['extra'] = self.extra
@@ -104,28 +87,20 @@ TESSERACT_VERSION_PATTERN = r"""
 
 
 class TesseractVersion(Version):
-    "Modify standard packaging.Version regex to support Tesseract idiosyncracies."
+    """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:
+def version() -> Version:
-    return get_version('tesseract', regex=r'tesseract\s(.+)')
+    return TesseractVersion(get_version('tesseract', regex=r'tesseract\s(.+)'))
-
-
-def has_user_words() -> bool:
-    """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() -> bool:
     """Does Tesseract have -c thresholding method capability?"""
-    return version() >= '5.0'
+    return version() >= Version('5.0')
 
 
 def get_languages() -> set[str]:
@@ -239,12 +214,13 @@ 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: 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:
@@ -289,12 +265,11 @@ def page_timedout(timeout: float) -> None:
 
 
 def _generate_null_hocr(output_hocr: Path, output_text: Path, image: Path) -> None:
-    """Produce a .hocr file that reports no text detected on a page that is
+    """Produce an empty .hocr file.
-    the same size as the input image."""
-    with Image.open(image) as im:
-        w, h = im.size
 
-    output_hocr.write_text(HOCR_TEMPLATE.format(w, h), encoding='utf-8')
+    Ensures page is the same size as the input image.
+    """
+    output_hocr.write_text('', encoding='utf-8')
     output_text.write_text('[skipped page]', encoding='utf-8')
 
 
@@ -353,7 +328,7 @@ def generate_hocr(
         tesseract_log_output(stdout)
         # The sidecar text file will get the suffix .txt; rename it to
         # whatever caller wants it named
-        if prefix.with_suffix('.txt').exists():
+        with suppress(FileNotFoundError):
             prefix.with_suffix('.txt').replace(output_text)
 
 
@@ -409,7 +384,7 @@ def generate_pdf(
     try:
         p = run(args_tesseract, stdout=PIPE, stderr=STDOUT, timeout=timeout, check=True)
         stdout = p.stdout
-        if prefix.with_suffix('.txt').exists():
+        with suppress(FileNotFoundError):
             prefix.with_suffix('.txt').replace(output_text)
     except TimeoutExpired:
         page_timedout(timeout)

src/ocrmypdf/_exec/unpaper.py

@@ -1,46 +1,30 @@
 # SPDX-FileCopyrightText: 2022 James R. Barlow
 # SPDX-License-Identifier: MPL-2.0
 
-from __future__ import annotations
+"""Interface to unpaper executable."""
 
-# unpaper documentation:
+from __future__ import annotations
-# https://github.com/Flameeyes/unpaper/blob/master/doc/basic-concepts.md
-"""Interface to unpaper executable"""
 
 import logging
 import os
 import shlex
 import sys
+from collections.abc import Iterator
 from contextlib import contextmanager
 from decimal import Decimal
 from pathlib import Path
 from subprocess import PIPE, STDOUT
-from typing import Iterator, Union
+from tempfile import TemporaryDirectory
+from typing import Union
 
+from packaging.version import Version
 from PIL import Image
 
 from ocrmypdf.exceptions import MissingDependencyError, SubprocessOutputError
 from ocrmypdf.subprocess import get_version, run
 
-if sys.version_info >= (3, 10):
+# unpaper documentation:
-    from tempfile import TemporaryDirectory
+# https://github.com/Flameeyes/unpaper/blob/main/doc/basic-concepts.md
-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
@@ -65,34 +49,8 @@ class UnpaperImageTooLargeError(Exception):
         super().__init__(self.message)
 
 
-def version() -> str:
+def version() -> Version:
-    return get_version('unpaper')
+    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:
-            if im.mode == 'P' and len(im.getcolors()) == 2:
-                im = im.convert(mode='1')
-            else:
-                im = im.convert(mode='RGB')
-        except OSError as e:
-            raise MissingDependencyError(
-                "Could not convert image with type " + im.mode
-            ) from e
-        else:
-            im_modified = True
-        if im.mode not in SUPPORTED_MODES:
-            raise MissingDependencyError(
-                "Failed to convert image to a supported format."
-            ) from None
-    return im, im_modified
 
 
 @contextmanager
@@ -100,21 +58,15 @@ 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:
+    with TemporaryDirectory(ignore_cleanup_errors=True) as tmpdir:
-            tmppath = Path(tmpdir)
+        tmppath = Path(tmpdir)
-            if im_modified or input_file.suffix != '.png':
+        # No changes, PNG input, just use the file we already have
-                input_png = tmppath / 'input.png'
+        input_png = input_file
-                im.save(input_png, format='PNG')
+        # unpaper can write .png too, but it seems to write them slowly
-            else:
+        # adds a few seconds to test suite - so just use pnm
-                # No changes, PNG input, just use the file we already have
+        output_pnm = tmppath / 'output.pnm'
-                input_png = input_file
+        yield input_png, output_pnm, tmppath
-
-            # 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(

src/ocrmypdf/_graft.py

@@ -7,49 +7,57 @@ from __future__ import annotations
 
 import logging
 from contextlib import suppress
+from enum import Enum
 from pathlib import Path
 
 from pikepdf import (
     Dictionary,
+    Matrix,
     Name,
-    Object,
     Operator,
+    Page,
     Pdf,
     PdfError,
-    PdfMatrix,
     Stream,
     parse_content_stream,
     unparse_content_stream,
 )
 
+from ocrmypdf._jobcontext import PdfContext
+
+
+class RenderMode(Enum):
+    ON_TOP = 0
+    UNDERNEATH = 1
+
+
 log = logging.getLogger(__name__)
 MAX_REPLACE_PAGES = 100
 
 
-def _ensure_dictionary(obj, name):
+def _ensure_dictionary(obj: Dictionary | Stream, name: Name):
     if name not in obj:
         obj[name] = Dictionary({})
     return obj[name]
 
 
-def _update_resources(*, obj, font, font_key, procset):
+def _update_resources(
+    *,
+    obj: Dictionary | Stream,
+    font: Dictionary | None,
+    font_key: Name | None,
+):
     """Update this obj's fonts with a reference to the Glyphless font.
 
     obj can be a page or Form XObject.
     """
-
     resources = _ensure_dictionary(obj, Name.Resources)
     fonts = _ensure_dictionary(resources, Name.Font)
     if font_key is not None and font_key not in fonts:
         fonts[font_key] = font
 
-    # Reassign /ProcSet to one that just lists everything - ProcSet is
-    # obsolete and doesn't matter but recommended for old viewer support
-    if procset:
-        resources['/ProcSet'] = procset
 
-
+def strip_invisible_text(pdf: Pdf, page: Page):
-def strip_invisible_text(pdf, page):
     stream = []
     in_text_obj = False
     render_mode = 0
@@ -80,22 +88,20 @@ def strip_invisible_text(pdf, page):
 class OcrGrafter:
     """Manages grafting text-only PDFs onto regular PDFs."""
 
-    def __init__(self, context):
+    def __init__(self, context: PdfContext):
         self.context = context
         self.path_base = context.origin
 
         self.pdf_base = Pdf.open(self.path_base)
-        self.font, self.font_key = None, None
+        self.font: Dictionary | None = None
+        self.font_key: Name | None = None
 
         self.pdfinfo = context.pdfinfo
         self.output_file = context.get_path('graft_layers.pdf')
 
-        self.procset = self.pdf_base.make_indirect(
-            Object.parse(b'[ /PDF /Text /ImageB /ImageC /ImageI ]')
-        )
-
         self.emplacements = 1
         self.interim_count = 0
+        self.render_mode = RenderMode.UNDERNEATH
 
     def graft_page(
         self,
@@ -120,7 +126,9 @@ class OcrGrafter:
                 foreign_image_page = pdf_image.pages[0]
                 self.pdf_base.pages.append(foreign_image_page)
                 local_image_page = self.pdf_base.pages[-1]
-                self.pdf_base.pages[pageno].emplace(local_image_page)
+                self.pdf_base.pages[pageno].emplace(
+                    local_image_page, retain=(Name.Parent,)
+                )
                 del self.pdf_base.pages[-1]
             emplaced_page = True
 
@@ -131,10 +139,13 @@ 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:
+            if self.font_key is None:
+                raise ValueError("Font key is not set")
             # Graft the text layer onto this page, whether new or old, possibly
             # rotating the text layer by the amount is misaligned.
             strip_old = self.context.options.redo_ocr
@@ -144,7 +155,6 @@ class OcrGrafter:
                 font=self.font,
                 font_key=self.font_key,
                 text_rotation=text_misaligned,
-                procset=self.procset,
                 strip_old_text=strip_old,
             )
 
@@ -159,18 +169,15 @@ class OcrGrafter:
         if self.emplacements % MAX_REPLACE_PAGES == 0:
             self.save_and_reload()
 
-    def save_and_reload(self):
+    def save_and_reload(self) -> None:
         """Save and reload the Pdf.
 
         This will keep a lid on our memory usage for very large files. Attach
         the font to page 1 even if page 1 doesn't use it, so we have a way to get it
         back.
         """
-
         page0 = self.pdf_base.pages[0]
-        _update_resources(
+        _update_resources(obj=page0.obj, font=self.font, font_key=self.font_key)
-            obj=page0, font=self.font, font_key=self.font_key, procset=self.procset
-        )
 
         # We cannot read and write the same file, that will corrupt it
         # but we don't to keep more copies than we need to. Delete intermediates.
@@ -189,7 +196,6 @@ class OcrGrafter:
         self.pdf_base.close()
 
         self.pdf_base = Pdf.open(next_file)
-        self.procset = self.pdf_base.pages[0].Resources.ProcSet
         self.font, self.font_key = None, None  # Ensure we reacquire this information
         self.interim_count += 1
 
@@ -198,25 +204,32 @@ class OcrGrafter:
         self.pdf_base.close()
         return self.output_file
 
-    def _find_font(self, text):
+    def _find_font(self, text: Path) -> tuple[Dictionary | None, Name | None]:
-        """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:
             with Pdf.open(text) as pdf_text:
                 try:
-                    pdf_text_fonts = pdf_text.pages[0].Resources.get('/Font', {})
+                    pdf_text_fonts = pdf_text.pages[0].Resources.get(
+                        Name.Font, Dictionary()
+                    )
                 except (AttributeError, IndexError, KeyError):
                     return None, None
+                if not isinstance(pdf_text_fonts, Dictionary):
+                    log.warning("Page fonts are not stored in a dictionary")
+                    return None, None
                 pdf_text_font = None
                 for f in possible_font_names:
                     pdf_text_font = pdf_text_fonts.get(f, None)
                     if pdf_text_font is not None:
-                        font_key = f
+                        font_key = Name(f)
                         break
                 if pdf_text_font:
                     font = self.pdf_base.copy_foreign(pdf_text_font)
+                if not isinstance(font, Dictionary):
+                    log.warning("Font is not a dictionary")
+                    font, font_key = None, None
                 return font, font_key
         except (FileNotFoundError, PdfError):
             # PdfError occurs if a 0-length file is written e.g. due to OCR timeout
@@ -227,14 +240,12 @@ class OcrGrafter:
         *,
         page_num: int,
         textpdf: Path,
-        font: Object,
+        font: Dictionary,
-        font_key: Object,
+        font_key: Name,
-        procset: Object,
         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")
@@ -251,19 +262,19 @@ class OcrGrafter:
             # content may have a rotation applied. Wrap the text stream with a rotation
             # so it will be oriented the same way as the rest of the page content.
             # (Previous versions OCRmyPDF rotated the content layer to match the text.)
-            mediabox = [float(pdf_text.pages[0].MediaBox[v]) for v in range(4)]
+            mediabox = pdf_text.pages[0].mediabox
             wt, ht = mediabox[2] - mediabox[0], mediabox[3] - mediabox[1]
 
-            mediabox = [float(base_page.MediaBox[v]) for v in range(4)]
+            mediabox = base_page.mediabox
             wp, hp = mediabox[2] - mediabox[0], mediabox[3] - mediabox[1]
 
-            translate = PdfMatrix().translated(-wt / 2, -ht / 2)
+            translate = Matrix().translated(-wt / 2, -ht / 2)
-            untranslate = PdfMatrix().translated(wp / 2, hp / 2)
+            untranslate = Matrix().translated(wp / 2, hp / 2)
-            corner = PdfMatrix().translated(mediabox[0], mediabox[1])
+            corner = Matrix().translated(mediabox[0], mediabox[1])
             # -rotation because the input is a clockwise angle and this formula
             # uses CCW
             text_rotation = -text_rotation % 360
-            rotate = PdfMatrix().rotated(text_rotation)
+            rotate = Matrix().rotated(text_rotation)
 
             # Because of rounding of DPI, we might get a text layer that is not
             # identically sized to the target page. Scale to adjust. Normally this
@@ -274,14 +285,15 @@ class OcrGrafter:
             scale_y = hp / ht
 
             # log.debug('%r', scale_x, scale_y)
-            scale = PdfMatrix().scaled(scale_x, scale_y)
+            scale = Matrix().scaled(scale_x, scale_y)
 
             # Translate the text so it is centered at (0, 0), rotate it there, adjust
             # for a size different between initial and text PDF, then untranslate, and
-            # finally move the lower left corner to match the mediabox
+            # finally move the lower left corner to match the mediabox. All transforms
-            ctm = translate @ rotate @ scale @ untranslate @ corner
+            # must be premultiplied so they are applied in reverse order here.
+            ctm = corner @ untranslate @ scale @ rotate @ translate
 
-            base_resources = _ensure_dictionary(base_page, Name.Resources)
+            base_resources = _ensure_dictionary(base_page.obj, Name.Resources)
             base_xobjs = _ensure_dictionary(base_resources, Name.XObject)
             text_xobj_name = Name.random(prefix="OCR-")
             xobj = self.pdf_base.make_stream(pdf_text_contents)
@@ -290,9 +302,7 @@ class OcrGrafter:
             xobj.Subtype = Name.Form
             xobj.FormType = 1
             xobj.BBox = mediabox
-            _update_resources(
+            _update_resources(obj=xobj, font=font, font_key=font_key)
-                obj=xobj, font=font, font_key=font_key, procset=[Name.PDF]
-            )
 
             pdf_draw_xobj = (
                 (b'q %s cm\n' % ctm.encode()) + (b'%s Do\n' % text_xobj_name) + b'\nQ\n'
@@ -302,8 +312,8 @@ class OcrGrafter:
             if strip_old_text:
                 strip_invisible_text(self.pdf_base, base_page)
 
-            base_page.contents_add(new_text_layer, prepend=True)
+            base_page.contents_add(
-
+                new_text_layer, prepend=self.render_mode == RenderMode.ON_TOP
-            _update_resources(
-                obj=base_page, font=font, font_key=font_key, procset=procset
             )
+
+            _update_resources(obj=base_page.obj, font=font, font_key=font_key)

src/ocrmypdf/_jobcontext.py

@@ -6,12 +6,10 @@
 from __future__ import annotations
 
 import os
-import shutil
-import sys
 from argparse import Namespace
+from collections.abc import Iterator
 from copy import copy
 from pathlib import Path
-from typing import Iterator
 
 from pluggy import PluginManager
 
@@ -55,11 +53,17 @@ class PdfContext:
         for n in range(npages):
             yield PageContext(self, n)
 
+    def get_page_context_args(self) -> Iterator[tuple[PageContext]]:
+        """Get all ``PageContext`` for this PDF packaged in tuple for args-splatting."""
+        npages = len(self.pdfinfo)
+        for n in range(npages):
+            yield (PageContext(self, n),)
+
 
 class PageContext:
     """Holds our context for a page.
 
-    Must be 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__``.
     """
 
@@ -94,10 +98,3 @@ class PageContext:
         if not isinstance(state['options'].output_file, (str, bytes, os.PathLike)):
             state['options'].output_file = 'stream'
         return state
-
-
-def cleanup_working_files(work_folder: Path, options: Namespace):
-    if options.keep_temporary_files:
-        print(f"Temporary working files retained at:\n{work_folder}", file=sys.stderr)
-    else:
-        shutil.rmtree(work_folder, ignore_errors=True)

src/ocrmypdf/_logging.py

@@ -6,9 +6,9 @@
 from __future__ import annotations
 
 import logging
-from contextlib import suppress
 
-from tqdm import tqdm
+from rich.console import Console
+from rich.logging import RichHandler
 
 
 class PageNumberFilter(logging.Filter):
@@ -23,21 +23,8 @@ class PageNumberFilter(logging.Filter):
         return True
 
 
-class TqdmConsole:
+class RichLoggingHandler(RichHandler):
-    """Wrapper to log messages in a way that is compatible with tqdm progress bar
+    def __init__(self, console: Console, **kwargs):
-
+        super().__init__(
-    This routes log messages through tqdm so that it can print them above the
+            console=console, show_level=False, show_time=False, markup=True, **kwargs
-    progress bar, and then refresh the progress bar, rather than overwriting
+        )
-    it which looks messy.
-    """
-
-    def __init__(self, file):
-        self.file = file
-
-    def write(self, msg):
-        # When no progress bar is active, tqdm.write() routes to print()
-        tqdm.write(msg.rstrip(), end='\n', file=self.file)
-
-    def flush(self):
-        with suppress(AttributeError):
-            self.file.flush()

src/ocrmypdf/_metadata.py

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

src/ocrmypdf/_pipeline.py

@@ -1,4 +1,5 @@
-# SPDX-FileCopyrightText: 2022 James R. Barlow
+# SPDX-FileCopyrightText: 2018-2022 James R. Barlow
+# SPDX-FileCopyrightText: 2019 Martin Wind
 # SPDX-License-Identifier: MPL-2.0
 
 """OCRmyPDF page processing pipeline functions."""
@@ -9,47 +10,56 @@ import logging
 import os
 import re
 import sys
+from collections.abc import Iterable, Iterator, Sequence
 from contextlib import suppress
-from datetime import datetime, timezone
 from pathlib import Path
-from shutil import copyfileobj
+from shutil import copyfileobj, copystat
-from typing import Iterable
+from typing import Any, BinaryIO, TypeVar, cast
 
 import img2pdf
 import pikepdf
-from pikepdf.models.metadata import encode_pdf_date
 from PIL import Image, ImageColor, ImageDraw
 
 from ocrmypdf._concurrent import Executor
 from ocrmypdf._exec import unpaper
 from ocrmypdf._jobcontext import PageContext, PdfContext
-from ocrmypdf._version import PROGRAM_NAME
+from ocrmypdf._metadata import repair_docinfo_nuls
-from ocrmypdf._version import __version__ as VERSION
 from ocrmypdf.exceptions import (
+    DigitalSignatureError,
     DpiError,
     EncryptedPdfError,
     InputFileError,
     PriorOcrFoundError,
+    TaggedPDFError,
     UnsupportedImageFormatError,
 )
 from ocrmypdf.helpers import IMG2PDF_KWARGS, Resolution, safe_symlink
 from ocrmypdf.hocrtransform import HocrTransform
 from ocrmypdf.pdfa import generate_pdfa_ps
-from ocrmypdf.pdfinfo import Colorspace, Encoding, 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
 
+T = TypeVar("T")
 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)
@@ -64,34 +74,32 @@ 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...")
@@ -109,27 +117,28 @@ def triage_image_file(input_file, output_file, options):
             )
         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:
+    """Triage the input file. We can handle PDFs and images."""
     try:
         if _pdf_guess_version(input_file):
             if options.image_dpi:
@@ -153,17 +162,20 @@ def get_pdfinfo(
     input_file,
     *,
     executor: Executor,
-    detailed_analysis=False,
+    detailed_analysis: bool = False,
-    progbar=False,
+    progbar: bool = False,
-    max_workers=None,
+    max_workers: int | None = None,
+    use_threads: bool = True,
     check_pages=None,
 ) -> PdfInfo:
+    """Get the PDF info."""
     try:
         return PdfInfo(
             input_file,
             detailed_analysis=detailed_analysis,
             progbar=progbar,
             max_workers=max_workers,
+            use_threads=use_threads,
             check_pages=check_pages,
             executor=executor,
         )
@@ -173,32 +185,27 @@ def get_pdfinfo(
         raise InputFileError() from e
 
 
-def validate_pdfinfo_options(context: PdfContext):
+def validate_pdfinfo_options(context: PdfContext) -> None:
+    """Validate the PDF info options."""
     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_signature:
-    if pdfinfo.has_userunit and options.output_type.startswith('pdfa'):
+        if options.invalidate_digital_signatures:
-        log.error(
+            log.warning("All digital signatures will be invalidated")
-            "This input file uses a PDF feature that is not supported "
+        else:
-            "by Ghostscript, so you cannot use --output-type=pdfa for this "
+            raise DigitalSignatureError()
-            "file. (Specifically, it uses the PDF-1.6 /UserUnit feature to "
-            "support very large or small page sizes, and Ghostscript cannot "
-            "output these files.)  Use --output-type=pdf instead."
-        )
-        raise InputFileError()
     if pdfinfo.has_acroform:
         if options.redo_ocr:
-            log.error(
+            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. "
@@ -211,32 +218,37 @@ def validate_pdfinfo_options(context: PdfContext):
                     "form and all filled form fields. The output PDF will be "
                     "'flattened' and will no longer be fillable."
                 )
+    if pdfinfo.is_tagged:
+        if options.force_ocr or options.skip_text or options.redo_ocr:
+            log.warning(
+                "This PDF is marked as a Tagged PDF. This often indicates "
+                "that the PDF was generated from an office document and does "
+                "not need OCR. PDF pages processed by OCRmyPDF may not be "
+                "tagged correctly."
+            )
+        else:
+            raise TaggedPDFError()
     context.plugin_manager.hook.validate(pdfinfo=pdfinfo, options=options)
 
 
-def _vector_page_dpi(pageinfo):
+def _vector_page_dpi(pageinfo: PageInfo) -> int:
-    return VECTOR_PAGE_DPI if pageinfo.has_vector or pageinfo.has_text else 0.0
+    """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):
+def get_page_square_dpi(
-    "Get the DPI when nonsquare DPI is tolerable"
+    page_context: PageContext, image_dpi: Resolution | None = None
-    xres = max(
+) -> Resolution:
-        pageinfo.dpi.x or VECTOR_PAGE_DPI,
+    """Get the DPI when we require xres == yres, scaled to physical units.
-        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))
 
-
+    Page DPI includes UserUnit scaling.
-def get_page_square_dpi(pageinfo, options) -> Resolution:
+    """
-    "Get the DPI when we require xres == yres, scaled to physical units"
+    pageinfo = page_context.pageinfo
-    xres = pageinfo.dpi.x or 0.0
+    options = page_context.options
-    yres = pageinfo.dpi.y or 0.0
+    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(
@@ -249,12 +261,23 @@ def get_page_square_dpi(pageinfo, options) -> Resolution:
     return Resolution(units, units)
 
 
-def get_canvas_square_dpi(pageinfo, options) -> Resolution:
+def get_canvas_square_dpi(
-    """Get the DPI when we require xres == yres, in Postscript units"""
+    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,
+            image_dpi.x or VECTOR_PAGE_DPI,
-            (pageinfo.dpi.y) or VECTOR_PAGE_DPI,
+            image_dpi.y or VECTOR_PAGE_DPI,
             _vector_page_dpi(pageinfo),
             options.oversample or 0.0,
         )
@@ -262,7 +285,8 @@ 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
 
@@ -312,8 +336,8 @@ 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 "
+                f"rasterized at {VECTOR_PAGE_DPI} DPI, losing some resolution and "
-                "increasing file size. Use --oversample to adjust the "
+                "likely increasing file size. Use --oversample to adjust the "
                 "DPI."
             )
         else:
@@ -337,10 +361,13 @@ def is_ocr_required(page_context: PageContext):
     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)
+    canvas_dpi = Resolution(300.0, 300.0).take_min(
-    page_dpi = get_page_square_dpi(page_context.pageinfo, page_context.options)
+        [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,
@@ -350,14 +377,15 @@ 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):
+def describe_rotation(
-    """
+    page_context: PageContext, orient_conf: OrientationConfidence, correction: int
-    Describe the page rotation we are going to perform.
+) -> str:
-    """
+    """Describe the page rotation we are going to perform (or not perform)."""
     direction = {0: '⇧', 90: '⇨', 180: '⇩', 270: '⇦'}
     turns = {0: ' ', 90: '⬏', 180: '↻', 270: '⬑'}
 
@@ -383,8 +411,8 @@ 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):
+def get_orientation_correction(preview: Path, page_context: PageContext) -> int:
-    """Work out orientation correct for each page.
+    """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
@@ -398,7 +426,6 @@ 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
     )
@@ -414,13 +441,59 @@ def get_orientation_correction(preview: Path, page_context: PageContext):
     return 0
 
 
+def calculate_image_dpi(page_context: PageContext) -> Resolution:
+    """Calculate the DPI for the page image."""
+    pageinfo = page_context.pageinfo
+    dpi_profile = pageinfo.page_dpi_profile()
+    if dpi_profile and dpi_profile.average_to_max_dpi_ratio < 0.8:
+        image_dpi = Resolution(dpi_profile.weighted_dpi, dpi_profile.weighted_dpi)
+    else:
+        image_dpi = pageinfo.dpi
+    return image_dpi
+
+
+def calculate_raster_dpi(page_context: PageContext):
+    """Calculate the DPI for rasterization."""
+    # Produce the page image with square resolution or else deskew and OCR
+    # will not work properly.
+    image_dpi = calculate_image_dpi(page_context)
+    dpi_profile = page_context.pageinfo.page_dpi_profile()
+    canvas_dpi = get_canvas_square_dpi(page_context, image_dpi)
+    page_dpi = get_page_square_dpi(page_context, image_dpi)
+    if dpi_profile and dpi_profile.average_to_max_dpi_ratio < 0.8:
+        log.warning(
+            "Weight average image DPI is %0.1f, max DPI is %0.1f. "
+            "The discrepancy may indicate a high detail region on this page, "
+            "but could also indicate a problem with the input PDF file. "
+            "Page image will be rendered at %0.1f DPI.",
+            dpi_profile.weighted_dpi,
+            dpi_profile.max_dpi,
+            canvas_dpi.to_scalar(),
+        )
+    return canvas_dpi, page_dpi
+
+
 def rasterize(
     input_file: Path,
     page_context: PageContext,
     correction: int = 0,
     output_tag: str = '',
-    remove_vectors=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
 
@@ -445,16 +518,14 @@ def rasterize(
                 device_idx = at_least('png16m')
 
     if pageinfo.has_vector:
+        log.debug("Page has vector content, using png16m")
         device_idx = at_least('png16m')
 
     device = colorspaces[device_idx]
 
     log.debug(f"Rasterize with {device}, rotation {correction}")
 
-    # Produce the page image with square resolution or else deskew and OCR
+    canvas_dpi, page_dpi = calculate_raster_dpi(page_context)
-    # will not work properly.
-    canvas_dpi = get_canvas_square_dpi(pageinfo, page_context.options)
-    page_dpi = get_page_square_dpi(pageinfo, page_context.options)
 
     page_context.plugin_manager.hook.rasterize_pdf_page(
         input_file=input_file,
@@ -465,24 +536,34 @@ 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:
+    """Remove the background from the input image (temporarily disabled)."""
     if any(image.bpc > 1 for image in page_context.pageinfo.images):
         raise NotImplementedError("--remove-background is temporarily not implemented")
         # output_file = page_context.get_path('pp_rm_bg.png')
         # leptonica.remove_background(input_file, output_file)
         # return output_file
-    else:
+    log.info("background removal skipped on mono page")
-        log.info("background removal skipped on mono page")
+    return input_file
-        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)
@@ -492,7 +573,7 @@ def preprocess_deskew(input_file: Path, page_context: PageContext):
         # resampling if image is mode '1' or 'P'
         deskewed = im.rotate(
             deskew_angle_degrees,
-            resample=BICUBIC,
+            resample=Image.Resampling.BICUBIC,
             fillcolor=ImageColor.getcolor('white', mode=im.mode),  # type: ignore
         )
         deskewed.save(output_file, dpi=dpi)
@@ -500,22 +581,24 @@ def preprocess_deskew(input_file: Path, page_context: PageContext):
     return output_file
 
 
-def preprocess_clean(input_file: Path, page_context: PageContext):
+def preprocess_clean(input_file: Path, page_context: PageContext) -> Path:
+    """Clean the input image using unpaper."""
     output_file = page_context.get_path('pp_clean.png')
-    dpi = get_page_square_dpi(page_context.pageinfo, page_context.options)
+    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,
     )
 
 
-def create_ocr_image(image: Path, page_context: PageContext):
+def create_ocr_image(image: Path, page_context: PageContext) -> Path:
-    """Create the image we send for OCR. May not be the same as the display
+    """Create the image we send for OCR.
-    image depending on preprocessing. This image will never be shown to the
-    user."""
 
+    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:
@@ -559,7 +642,8 @@ 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]:
+    """Run the OCR engine and generate hOCR output."""
     hocr_out = page_context.get_path('ocr_hocr.hocr')
     hocr_text_out = page_context.get_path('ocr_hocr.txt')
     options = page_context.options
@@ -571,15 +655,30 @@ def ocr_engine_hocr(input_file: Path, page_context: PageContext):
         output_text=hocr_text_out,
         options=options,
     )
-    return (hocr_out, hocr_text_out)
+    return hocr_out, hocr_text_out
 
 
-def should_visible_page_image_use_jpg(pageinfo):
+def should_visible_page_image_use_jpg(pageinfo: PageInfo) -> bool:
-    # If all images were JPEGs originally, produce a JPEG as output
+    """Determines whether the visible page image should be saved as a JPEG.
-    return pageinfo.images and all(im.enc == Encoding.jpeg for im in pageinfo.images)
+
+    If all images were JPEGs originally, permit a JPEG as output.
+
+    Args:
+        pageinfo: The PageInfo object containing information about the page.
+
+    Returns:
+        A boolean indicating whether the visible page image should be saved as a JPEG.
+    """
+    return bool(pageinfo.images) and all(
+        im.enc == Encoding.jpeg for im in pageinfo.images
+    )
 
 
 def create_visible_page_jpg(image: Path, page_context: PageContext) -> Path:
+    """Create a visible page image in JPEG format.
+
+    This is intended to be used when all images on the page were originally JPEGs.
+    """
     output_file = page_context.get_path('visible.jpg')
     with Image.open(image) as im:
         # At this point the image should be a .png, but deskew, unpaper
@@ -591,7 +690,7 @@ 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())
@@ -599,8 +698,9 @@ 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:
+    """Create a PDF page from a page image."""
     # We rasterize a square DPI version of each page because most image
     # processing tools don't support rectangular DPI. Use the square DPI as it
     # accurately describes the image. It would be possible to resample the image
@@ -628,28 +728,36 @@ def create_pdf_page_from_image(
     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:
+    """Render the hOCR page to a PDF."""
     options = page_context.options
     output_file = page_context.get_path('ocr_hocr.pdf')
-    dpi = get_page_square_dpi(page_context.pageinfo, options)
+    if hocr.stat().st_size == 0:
+        # If hOCR file is empty (skipped page marker), create an empty PDF file
+        output_file.touch()
+        return output_file
+
+    dpi = get_page_square_dpi(page_context, calculate_image_dpi(page_context))
     debug_mode = options.pdf_renderer == 'hocrdebug'
 
-    hocrtransform = HocrTransform(hocr_filename=hocr, dpi=dpi.x)  # square
+    HocrTransform(
-    hocrtransform.to_pdf(
+        hocr_filename=hocr,
+        dpi=dpi.to_scalar(),  # square
+        debug=debug_mode,
+    ).to_pdf(
         out_filename=output_file,
         image_filename=None,
-        show_bounding_boxes=False if not debug_mode else True,
-        invisible_text=True if not debug_mode else False,
-        interword_spaces=True,
     )
     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]:
+    """Run the OCR engine and generate a text-only PDF (will look blank)."""
     output_pdf = page_context.get_path('ocr_tess.pdf')
     output_text = page_context.get_path('ocr_tess.txt')
     options = page_context.options
@@ -664,44 +772,29 @@ 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 generate_postscript_stub(context: PdfContext) -> Path:
-    options = context.options
+    """Generates a PostScript file stub for the given PDF context.
 
-    def from_document_info(key):
+    Args:
-        try:
+        context: The PDF context to generate the PostScript file stub for.
-            s = base_pdf.docinfo[key]
-            return str(s)
-        except (KeyError, TypeError):
-            return ''
 
-    pdfmark = {
+    Returns:
-        k: from_document_info(k)
+        Path: The path to the generated PostScript file stub.
-        for k in ('/Title', '/Author', '/Keywords', '/Subject', '/CreationDate')
+    """
-    }
-    if options.title:
-        pdfmark['/Title'] = options.title
-    if options.author:
-        pdfmark['/Author'] = options.author
-    if options.keywords:
-        pdfmark['/Keywords'] = options.keywords
-    if options.subject:
-        pdfmark['/Subject'] = options.subject
-
-    creator_tag = context.plugin_manager.hook.get_ocr_engine().creator_tag(options)
-
-    pdfmark['/Creator'] = f'{PROGRAM_NAME} {VERSION} / {creator_tag}'
-    pdfmark['/Producer'] = f'pikepdf {pikepdf.__version__}'
-    pdfmark['/ModDate'] = encode_pdf_date(datetime.now(timezone.utc))
-    return pdfmark
-
-
-def generate_postscript_stub(context: PdfContext):
     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:
+    """Converts the given PDF to PDF/A.
+
+    Args:
+        input_pdf: The input PDF file path (presumably not PDF/A).
+        input_ps_stub: The input PostScript file path, containing instructions
+            for the PDF/A generator to use.
+        context: The PDF context.
+    """
     options = context.options
     input_pdfinfo = context.pdfinfo
     fix_docinfo_file = context.get_path('fix_docinfo.pdf')
@@ -712,21 +805,8 @@ 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:
+        if repair_docinfo_nuls(pdf_file):
-            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:
             pdf_file.save(fix_docinfo_file)
         else:
             safe_symlink(input_pdf, fix_docinfo_file)
@@ -736,26 +816,36 @@ 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 should_linearize(working_file: Path, context: PdfContext) -> bool:
+    """Determine whether the PDF should be linearized.
+
+    For smaller files, linearization is not worth the effort.
+    """
     filesize = os.stat(working_file).st_size
     if filesize > (context.options.fast_web_view * 1_000_000):
         return True
     return False
 
 
-def get_pdf_save_settings(output_type: str):
+def get_pdf_save_settings(output_type: str) -> dict[str, Any]:
+    """Get pikepdf.Pdf.save settings for the given output type.
+
+    Essentially, don't use features that are incompatible with a given
+    PDF/A specification.
+    """
     if output_type == 'pdfa-1':
         # Trigger recompression to ensure object streams are removed, because
         # Acrobat complains about them in PDF/A-1b validation.
@@ -773,63 +863,33 @@ def get_pdf_save_settings(output_type: str):
         )
 
 
-def metadata_fixup(working_file: Path, context: PdfContext):
+def _file_size_ratio(
-    output_file = context.get_path('metafix.pdf')
+    input_file: Path, output_file: Path
-    options = context.options
+) -> tuple[float | None, float | None]:
+    """Calculate ratio of input to output file sizes and percentage savings.
 
-    def report_on_metadata(missing):
+    Args:
-        if not missing:
+        input_file (Path): The path to the input file.
-            return
+        output_file (Path): The path to the output file.
-        if options.output_type.startswith('pdfa'):
-            log.warning(
-                "Some input metadata could not be copied because it is not "
-                "permitted in PDF/A. You may wish to examine the output "
-                "PDF's XMP metadata."
-            )
-            log.debug("The following metadata fields were not copied: %r", missing)
-        else:
-            log.error(
-                "Some input metadata could not be copied."
-                "You may wish to examine the output PDF's XMP metadata."
-            )
-            log.info("The following metadata fields were not copied: %r", missing)
 
-    with pikepdf.open(context.origin) as original, pikepdf.open(working_file) as pdf:
+    Returns:
-        docinfo = get_docinfo(original, context)
+        tuple[float | None, float | None]: A tuple containing the file size
-        with pdf.open_metadata() as meta:
+        ratio and the percentage savings achieved by the output file size
-            meta.load_from_docinfo(docinfo, delete_missing=False, raise_failure=False)
+        compared to the input file size.
-            # If xmp:CreateDate is missing, set it to the modify date to
+    """
-            # match Ghostscript, for consistency
+    input_size = input_file.stat().st_size
-            if 'xmp:CreateDate' not in meta:
+    output_size = output_file.stat().st_size
-                meta['xmp:CreateDate'] = meta.get('xmp:ModifyDate', '')
+    if output_size == 0:
-
+        return None, None
-            with original.open_metadata(
+    ratio = input_size / output_size
-                set_pikepdf_as_editor=False, update_docinfo=False, strict=False
+    savings = 1 - output_size / input_size
-            ) as meta_original:
+    return ratio, savings
-                if meta.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)
-
-        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
-                not optimizing and should_linearize(working_file, context)
-            ),
-        )
-
-    return output_file
 
 
-def optimize_pdf(input_file: Path, context: PdfContext, executor: Executor):
+def optimize_pdf(
+    input_file: Path, context: PdfContext, executor: Executor
+) -> tuple[Path, Sequence[str]]:
+    """Optimize the given PDF file."""
     output_file = context.get_path('optimize.pdf')
     output_pdf, messages = context.plugin_manager.hook.optimize_pdf(
         input_pdf=input_file,
@@ -839,17 +899,29 @@ def optimize_pdf(input_file: Path, context: PdfContext, executor: Executor):
         linearize=should_linearize(input_file, context),
     )
 
-    input_size = input_file.stat().st_size
+    ratio, savings = _file_size_ratio(input_file, output_file)
-    output_size = output_file.stat().st_size
+    if ratio:
-    if output_size > 0:
+        log.info(f"Image optimization ratio: {ratio:.2f} savings: {(savings):.1%}")
-        ratio = input_size / output_size
+    ratio, savings = _file_size_ratio(context.origin, output_file)
-        savings = 1 - output_size / input_size
+    if ratio:
-        log.info(f"Optimize ratio: {ratio:.2f} savings: {(savings):.1%}")
+        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[T],
+) -> Iterator[tuple[tuple[int, int], T | None]]:
+    """Enumerate the ranges of non-empty elements in an iterable.
+
+    Compresses consecutive ranges of length 1 into single elements.
+
+    Args:
+        iterable: An iterable of elements to enumerate.
+
+    Yields:
+        A tuple containing a range of indices and the corresponding element.
+        If the element is None, the range represents a skipped range of indices.
+    """
     skipped_from, index = None, None
     for index, txt_file in enumerate(iterable):
         index += 1
@@ -865,22 +937,23 @@ def enumerate_compress_ranges(iterable):
         yield (skipped_from, index), None
 
 
-def merge_sidecars(txt_files: Iterable[Path | None], context: PdfContext):
+def merge_sidecars(txt_files: Iterable[Path | None], context: PdfContext) -> Path:
+    """Merge the page sidecar files into a single file.
+
+    Sidecar files are created by the OCR engine and contain the text for each
+    page in the PDF. This function merges the sidecar files into a single file
+    and returns the path to the merged file.
+    """
     output_file = context.get_path('sidecar.txt')
     with open(output_file, 'w', encoding="utf-8") as stream:
         for (from_, to_), txt_file in enumerate_compress_ranges(txt_files):
             if from_ != 1:
-                stream.write('\f')  # Form feed between pages
+                stream.write('\f')  # Form feed between pages for all pages after first
             if txt_file:
-                with open(txt_file, encoding="utf-8") as in_:
+                txt = txt_file.read_text(encoding="utf-8")
-                    txt = in_.read()
+                # Some versions of Tesseract add a form feed at the end and
-                    # Some OCR engines (e.g. Tesseract v4 alpha) add form feeds
+                # others don't. Remove it if it exists, since we add one manually.
-                    # between pages, and some do not. For consistency, we ignore
+                stream.write(txt.removesuffix('\f'))
-                    # any added by the OCR engine and them on our own.
-                    if txt.endswith('\f'):
-                        stream.write(txt[:-1])
-                    else:
-                        stream.write(txt)
             else:
                 if from_ != to_:
                     pages = f'{from_}-{to_}'
@@ -890,20 +963,32 @@ def merge_sidecars(txt_files: Iterable[Path | None], context: PdfContext):
     return output_file
 
 
-def copy_final(input_file, output_file, _context: PdfContext):
+def copy_final(
+    input_file: Path, output_file: str | Path | BinaryIO, original_file: Path | None
+) -> None:
+    """Copy the final temporary file to the output destination.
+
+    Args:
+        input_file (Path): The intermediate input file to copy.
+        output_file (str | Path | BinaryIO): The output file to copy to.
+        original_file: The original file to copy attributes from.
+
+    Returns:
+        None
+    """
     log.debug('%s -> %s', input_file, output_file)
-    with 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
+            output_stream = cast(BinaryIO, output_file)
-            copyfileobj(input_stream, output_stream)
+            copyfileobj(input_stream, output_stream)  # type: ignore[misc]
             with suppress(AttributeError):
                 output_stream.flush()
         else:
             # At this point we overwrite the output_file specified by the user
             # use copyfileobj because then we use open() to create the file and
             # get the appropriate umask, ownership, etc.
-            with open(output_file, 'wb') as output_stream:
+            with open(output_file, 'w+b') as output_stream:
                 copyfileobj(input_stream, output_stream)

src/ocrmypdf/_pipelines/__init__.py

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

src/ocrmypdf/_pipelines/_common.py

@@ -1,64 +1,53 @@
-# SPDX-FileCopyrightText: 2022 James R. Barlow
+# SPDX-FileCopyrightText: 2023 James R. Barlow
 # SPDX-License-Identifier: MPL-2.0
 
-"""Implements the concurrent and page synchronous parts of the pipeline."""
-
-
 from __future__ import annotations
 
 import argparse
+import json
 import logging
 import logging.handlers
 import os
+import shutil
 import sys
 import threading
+from collections.abc import Sequence
 from concurrent.futures.process import BrokenProcessPool
 from concurrent.futures.thread import BrokenThreadPool
-from functools import partial
+from contextlib import contextmanager
+from dataclasses import dataclass
 from pathlib import Path
-from tempfile import mkdtemp
+from typing import Callable, NamedTuple, cast
-from typing import NamedTuple, Sequence, cast
 
 import PIL
 
 from ocrmypdf._concurrent import Executor, setup_executor
-from ocrmypdf._graft import OcrGrafter
+from ocrmypdf._jobcontext import PageContext, PdfContext
-from ocrmypdf._jobcontext import PageContext, PdfContext, cleanup_working_files
 from ocrmypdf._logging import PageNumberFilter
+from ocrmypdf._metadata import metadata_fixup
 from ocrmypdf._pipeline import (
     convert_to_pdfa,
-    copy_final,
     create_ocr_image,
     create_pdf_page_from_image,
     create_visible_page_jpg,
     generate_postscript_stub,
     get_orientation_correction,
-    get_pdfinfo,
+    get_pdf_save_settings,
-    is_ocr_required,
-    merge_sidecars,
-    metadata_fixup,
-    ocr_engine_hocr,
-    ocr_engine_textonly_pdf,
     optimize_pdf,
     preprocess_clean,
     preprocess_deskew,
     preprocess_remove_background,
     rasterize,
     rasterize_preview,
-    render_hocr_page,
+    should_linearize,
     should_visible_page_image_use_jpg,
-    triage,
-    validate_pdfinfo_options,
 )
-from ocrmypdf._plugin_manager import OcrmypdfPluginManager, get_plugin_manager
+from ocrmypdf._plugin_manager import OcrmypdfPluginManager
 from ocrmypdf._validation import (
-    check_requested_output_file,
-    create_input_file,
     report_output_file_size,
 )
 from ocrmypdf.exceptions import ExitCode, ExitCodeException
 from ocrmypdf.helpers import (
-    NeverRaise,
     available_cpu_count,
     check_pdf,
     pikepdf_enable_mmap,
@@ -67,33 +56,248 @@ from ocrmypdf.helpers import (
 from ocrmypdf.pdfa import file_claims_pdfa
 
 log = logging.getLogger(__name__)
+tls = threading.local()
+tls.pageno = None
+
+
+def _set_logging_tls(tls):
+    """Inject current page number (when available) into log records."""
+    old_factory = logging.getLogRecordFactory()
+
+    def wrapper(*args, **kwargs):
+        record = old_factory(*args, **kwargs)
+        if hasattr(tls, 'pageno'):
+            record.pageno = tls.pageno
+        return record
+
+    logging.setLogRecordFactory(wrapper)
+
+
+_set_logging_tls(tls)
+
+
+def set_thread_pageno(pageno: int | None):
+    """Set page number (1-based) that the current thread is processing."""
+    tls.pageno = pageno
 
 
 class PageResult(NamedTuple):
     """Result when a page is finished processing."""
 
     pageno: int
-    pdf_page_from_image: Path | None
+    """Page number, 0-based."""
-    ocr: Path | None
+
-    text: Path | None
+    pdf_page_from_image: Path | None = None
-    orientation_correction: int
+    """Single page PDF from image."""
+
+    ocr: Path | None = None
+    """Single page OCR PDF."""
+
+    text: Path | None = None
+    """Single page text file."""
+
+    orientation_correction: int = 0
+    """Orientation correction in degrees."""
 
 
-tls = threading.local()
+@dataclass
-tls.pageno = None
+class HOCRResult:
+    """Result when hOCR is finished processing."""
+
+    pageno: int
+    """Page number, 0-based."""
+
+    pdf_page_from_image: Path | None = None
+    """Single page PDF from image."""
+
+    hocr: Path | None = None
+    """Single page hOCR file."""
+
+    textpdf: Path | None = None
+    """hOCR file after conversion to PDF."""
+
+    orientation_correction: int = 0
+    """Orientation correction in degrees."""
+
+    def __getstate__(self):
+        """Return state values to be pickled."""
+        return {
+            k: (
+                ('Path://' + str(v))
+                if k in ('pdf_page_from_image', 'hocr', 'textpdf') and v is not None
+                else v
+            )
+            for k, v in self.__dict__.items()
+        }
+
+    def __setstate__(self, state):
+        """Restore state from the unpickled state values."""
+        self.__dict__.update(
+            {
+                k: (
+                    Path(v.removeprefix('Path://'))
+                    if k in ('pdf_page_from_image', 'hocr', 'textpdf') and v is not None
+                    else v
+                )
+                for k, v in state.items()
+            }
+        )
+
+    @classmethod
+    def from_json(cls, json_str: str) -> HOCRResult:
+        """Create an instance from a dict."""
+        return cls(**json.loads(json_str))
+
+    def to_json(self) -> str:
+        """Serialize to a JSON string."""
+        return json.dumps(self.__getstate__())
 
 
-old_factory = logging.getLogRecordFactory()
+def configure_debug_logging(
+    log_filename: Path, prefix: str = ''
+) -> tuple[logging.FileHandler, Callable[[], None]]:
+    """Create a debug log file at a specified location.
+
+    Returns the log handler, and a function to remove the handler.
+
+    Args:
+        log_filename: Where to the put the log file.
+        prefix: The logging domain prefix that should be sent to the log.
+    """
+    log_file_handler = logging.FileHandler(log_filename, delay=True)
+    log_file_handler.setLevel(logging.DEBUG)
+    formatter = logging.Formatter(
+        '[%(asctime)s] - %(name)s - %(levelname)7s -%(pageno)s %(message)s'
+    )
+    log_file_handler.setFormatter(formatter)
+    log_file_handler.addFilter(PageNumberFilter())
+    logging.getLogger(prefix).addHandler(log_file_handler)
+
+    def remover():
+        try:
+            logging.getLogger(prefix).removeHandler(log_file_handler)
+            log_file_handler.close()
+        except OSError as e:
+            print(e, file=sys.stderr)
+
+    return log_file_handler, remover
 
 
-def record_factory(*args, **kwargs):
+def worker_init(max_pixels: int) -> None:
-    record = old_factory(*args, **kwargs)
+    """Initialize a worker thread or process."""
-    if hasattr(tls, 'pageno'):
+    # In Windows, child process will not inherit our change to this value in
-        record.pageno = tls.pageno
+    # the parent process, so ensure workers get it set. Not needed when running
-    return record
+    # threaded, but harmless to set again.
+    PIL.Image.MAX_IMAGE_PIXELS = max_pixels
+    pikepdf_enable_mmap()
 
 
-logging.setLogRecordFactory(record_factory)
+@contextmanager
+def manage_debug_log_handler(
+    *,
+    options: argparse.Namespace,
+    work_folder: Path,
+):
+    remover = None
+    if (options.keep_temporary_files or options.verbose >= 1) and not os.environ.get(
+        'PYTEST_CURRENT_TEST', ''
+    ):
+        # Debug log for command line interface only with verbose output
+        # See https://github.com/pytest-dev/pytest/issues/5502 for why we skip this
+        # when pytest is running
+        _debug_log_handler, remover = configure_debug_logging(
+            work_folder / "debug.log", prefix=""
+        )  # pragma: no cover
+    try:
+        yield
+    finally:
+        if remover:
+            remover()
+
+
+@contextmanager
+def manage_work_folder(*, work_folder: Path, retain: bool, print_location: bool):
+    try:
+        yield work_folder
+    finally:
+        if retain:
+            if print_location:
+                print(
+                    f"Temporary working files retained at:\n{work_folder}",
+                    file=sys.stderr,
+                )
+        else:
+            shutil.rmtree(work_folder, ignore_errors=True)
+
+
+def cli_exception_handler(
+    fn: Callable[[argparse.Namespace, OcrmypdfPluginManager], ExitCode],
+    options: argparse.Namespace,
+    plugin_manager: OcrmypdfPluginManager,
+) -> ExitCode:
+    """Convert exceptions into command line error messages and exit codes.
+
+    When known exceptions are raised, the exception message is printed to stderr
+    and the program exits with a non-zero exit code. When unknown exceptions are
+    raised, the exception traceback is printed to stderr and the program exits
+    with a non-zero exit code.
+    """
+    try:
+        # We cannot use a generator and yield here, as would be the usual pattern
+        # for exception handling context managers, because we need to return an exit
+        # code.
+        return fn(options, plugin_manager)
+    except KeyboardInterrupt:
+        if options.verbose >= 1:
+            log.exception("KeyboardInterrupt")
+        else:
+            log.error("KeyboardInterrupt")
+        return ExitCode.ctrl_c
+    except ExitCodeException as e:
+        e = cast(ExitCodeException, e)
+        if options.verbose >= 1:
+            log.exception("ExitCodeException")
+        elif str(e):
+            log.error("%s: %s", type(e).__name__, str(e))
+        else:
+            log.error(type(e).__name__)
+        return e.exit_code
+    except PIL.Image.DecompressionBombError:
+        log.exception(
+            "A decompression bomb error was encountered while executing the "
+            "pipeline. Use the argument --max-image-mpixels to raise the maximum "
+            "image pixel limit."
+        )
+        return ExitCode.other_error
+    except (
+        BrokenProcessPool,
+        BrokenThreadPool,
+    ):
+        log.exception(
+            "A worker process was terminated unexpectedly. This is known to occur if "
+            "processing your file takes all available swap space and RAM. It may "
+            "help to try again with a smaller number of jobs, using the --jobs "
+            "argument."
+        )
+        return ExitCode.child_process_error
+    except Exception:  # pylint: disable=broad-except
+        log.exception("An exception occurred while executing the pipeline")
+        return ExitCode.other_error
+
+
+def setup_pipeline(
+    options: argparse.Namespace,
+    plugin_manager: OcrmypdfPluginManager,
+) -> Executor:
+    # Any changes to options will not take effect for options that are already
+    # bound to function parameters in the pipeline. (For example
+    # options.input_file, options.pdf_renderer are already bound.)
+    if not options.jobs:
+        options.jobs = available_cpu_count()
+
+    pikepdf_enable_mmap()
+    executor = setup_executor(plugin_manager)
+    return executor
 
 
 def preprocess(
@@ -103,6 +307,7 @@ def preprocess(
     deskew: bool,
     clean: bool,
 ) -> Path:
+    """Preprocess an image."""
     if remove_background:
         image = preprocess_remove_background(image, page_context)
     if deskew:
@@ -115,6 +320,7 @@ def preprocess(
 def make_intermediate_images(
     page_context: PageContext, orientation_correction: int
 ) -> tuple[Path, Path | None]:
+    """Create intermediate and preprocessed images for OCR."""
     options = page_context.options
 
     ocr_image = preprocess_out = None
@@ -171,19 +377,9 @@ def make_intermediate_images(
     return ocr_image, preprocess_out
 
 
-def exec_page_sync(page_context: PageContext) -> PageResult:
+def process_page(page_context: PageContext) -> tuple[Path, Path | None, int]:
+    """Process page to create OCR image, visible page image and orientation."""
     options = page_context.options
-    tls.pageno = page_context.pageno + 1
-
-    if not is_ocr_required(page_context):
-        return PageResult(
-            pageno=page_context.pageno,
-            pdf_page_from_image=None,
-            ocr=None,
-            text=None,
-            orientation_correction=0,
-        )
-
     orientation_correction = 0
     if options.rotate_pages:
         # Rasterize
@@ -206,262 +402,53 @@ 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
         )
-
+    return ocr_image_out, pdf_page_from_image_out, orientation_correction
-    if options.pdf_renderer.startswith('hocr'):
-        (hocr_out, text_out) = ocr_engine_hocr(ocr_image_out, page_context)
-        ocr_out = render_hocr_page(hocr_out, page_context)
-    elif options.pdf_renderer == 'sandwich':
-        (ocr_out, text_out) = ocr_engine_textonly_pdf(ocr_image_out, page_context)
-    else:
-        raise NotImplementedError(f"pdf_renderer {options.pdf_renderer}")
-
-    return PageResult(
-        pageno=page_context.pageno,
-        pdf_page_from_image=pdf_page_from_image_out,
-        ocr=ocr_out,
-        text=text_out,
-        orientation_correction=orientation_correction,
-    )
 
 
-def post_process(
+def postprocess(
     pdf_file: Path, context: PdfContext, executor: Executor
 ) -> tuple[Path, Sequence[str]]:
+    """Postprocess the PDF file."""
     pdf_out = pdf_file
     if context.options.output_type.startswith('pdfa'):
         ps_stub_out = generate_postscript_stub(context)
         pdf_out = convert_to_pdfa(pdf_out, ps_stub_out, context)
 
-    pdf_out = metadata_fixup(pdf_out, context)
+    optimizing = context.plugin_manager.hook.is_optimization_enabled(context=context)
+    save_settings = get_pdf_save_settings(context.options.output_type)
+    save_settings['linearize'] = not optimizing and should_linearize(pdf_out, context)
+
+    pdf_out = metadata_fixup(pdf_out, context, pdf_save_settings=save_settings)
     return optimize_pdf(pdf_out, context, executor)
 
 
-def worker_init(max_pixels: int) -> None:
+def report_output_pdf(options, start_input_file, optimize_messages) -> ExitCode:
-    # In Windows, child process will not inherit our change to this value in
+    if options.output_file == '-':
-    # the parent process, so ensure workers get it set. Not needed when running
+        log.info("Output sent to stdout")
-    # threaded, but harmless to set again.
+    elif hasattr(options.output_file, 'writable') and options.output_file.writable():
-    PIL.Image.MAX_IMAGE_PIXELS = max_pixels
+        log.info("Output written to stream")
-    pikepdf_enable_mmap()
+    elif samefile(options.output_file, Path(os.devnull)):
-
+        pass  # Say nothing when sending to dev null
-
+    else:
-def exec_concurrent(context: PdfContext, executor: Executor) -> Sequence[str]:
+        if options.output_type.startswith('pdfa'):
-    """Execute the pipeline concurrently"""
+            pdfa_info = file_claims_pdfa(options.output_file)
-
+            if pdfa_info['pass']:
-    # Run exec_page_sync on every page context
+                log.info("Output file is a %s (as expected)", pdfa_info['conformance'])
-    options = context.options
+            else:
-    max_workers = min(len(context.pdfinfo), options.jobs)
+                log.warning(
-    if max_workers > 1:
+                    "Output file is okay but is not PDF/A (seems to be %s)",
-        log.info("Start processing %d pages concurrently", max_workers)
+                    pdfa_info['conformance'],
-
+                )
-    sidecars: list[Path | None] = [None] * len(context.pdfinfo)
+                return ExitCode.pdfa_conversion_failed
-    ocrgraft = OcrGrafter(context)
+        if not check_pdf(options.output_file):
-
+            log.warning('Output file: The generated PDF is INVALID')
-    def update_page(result: PageResult, pbar):
+            return ExitCode.invalid_output_pdf
-        try:
+        report_output_file_size(
-            tls.pageno = result.pageno + 1
+            options, start_input_file, options.output_file, optimize_messages
-            sidecars[result.pageno] = result.text
-            pbar.update()
-            ocrgraft.graft_page(
-                pageno=result.pageno,
-                image=result.pdf_page_from_image,
-                textpdf=result.ocr,
-                autorotate_correction=result.orientation_correction,
-            )
-            pbar.update()
-        finally:
-            tls.pageno = None
-
-    executor(
-        use_threads=options.use_threads,
-        max_workers=max_workers,
-        tqdm_kwargs=dict(
-            total=(2 * len(context.pdfinfo)),
-            desc='OCR' if options.tesseract_timeout > 0 else 'Image processing',
-            unit='page',
-            unit_scale=0.5,
-            disable=not options.progress_bar,
-        ),
-        worker_initializer=partial(worker_init, PIL.Image.MAX_IMAGE_PIXELS),
-        task=exec_page_sync,
-        task_arguments=context.get_page_contexts(),
-        task_finished=update_page,
-    )
-
-    # Output sidecar text
-    if options.sidecar:
-        text = merge_sidecars(sidecars, context)
-        # Copy text file to destination
-        copy_final(text, options.sidecar, context)
-
-    # Merge layers to one single pdf
-    pdf = ocrgraft.finalize()
-
-    messages: Sequence[str] = []
-    if options.output_type != 'none':
-        # PDF/A and metadata
-        log.info("Postprocessing...")
-        pdf, messages = 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.
-
-    Arguments:
-        log_filename: Where to the put the log file.
-        prefix: The logging domain prefix that should be sent to the log.
-    """
-    log_file_handler = logging.FileHandler(log_filename, delay=True)
-    log_file_handler.setLevel(logging.DEBUG)
-    formatter = logging.Formatter(
-        '[%(asctime)s] - %(name)s - %(levelname)7s -%(pageno)s %(message)s'
-    )
-    log_file_handler.setFormatter(formatter)
-    log_file_handler.addFilter(PageNumberFilter())
-    logging.getLogger(prefix).addHandler(log_file_handler)
-    return log_file_handler
-
-
-def run_pipeline(
-    options: argparse.Namespace,
-    *,
-    plugin_manager: OcrmypdfPluginManager | None,
-    api: bool = False,
-) -> ExitCode:
-    # Any changes to options will not take effect for options that are already
-    # bound to function parameters in the pipeline. (For example
-    # options.input_file, options.pdf_renderer are already bound.)
-    if not options.jobs:
-        options.jobs = available_cpu_count()
-    if not plugin_manager:
-        plugin_manager = get_plugin_manager(options.plugins)
-
-    work_folder = Path(mkdtemp(prefix="ocrmypdf.io."))
-    debug_log_handler = None
-    if (
-        (options.keep_temporary_files or options.verbose >= 1)
-        and not os.environ.get('PYTEST_CURRENT_TEST', '')
-        and not api
-    ):
-        # Debug log for command line interface only with verbose output
-        # See https://github.com/pytest-dev/pytest/issues/5502 for why we skip this
-        # when pytest is running
-        debug_log_handler = configure_debug_logging(
-            Path(work_folder) / "debug.log"
-        )  # pragma: no cover
-
-    pikepdf_enable_mmap()
-
-    executor = setup_executor(plugin_manager)
-    try:
-        check_requested_output_file(options)
-        start_input_file, original_filename = create_input_file(options, work_folder)
-
-        # Triage image or pdf
-        origin_pdf = triage(
-            original_filename, start_input_file, work_folder / 'origin.pdf', options
         )
-
-        # Gather pdfinfo and create context
-        pdfinfo = get_pdfinfo(
-            origin_pdf,
-            executor=executor,
-            detailed_analysis=options.redo_ocr,
-            progbar=options.progress_bar,
-            max_workers=options.jobs if not options.use_threads else 1,  # To help debug
-            check_pages=options.pages,
-        )
-
-        context = PdfContext(options, work_folder, origin_pdf, pdfinfo, plugin_manager)
-
-        # Validate options are okay for this pdf
-        validate_pdfinfo_options(context)
-
-        # Execute the pipeline
-        optimize_messages = exec_concurrent(context, executor)
-
-        if options.output_file == '-':
-            log.info("Output sent to stdout")
-        elif (
-            hasattr(options.output_file, 'writable') and options.output_file.writable()
-        ):
-            log.info("Output written to stream")
-        elif samefile(options.output_file, Path(os.devnull)):
-            pass  # Say nothing when sending to dev null
-        else:
-            if options.output_type.startswith('pdfa'):
-                pdfa_info = file_claims_pdfa(options.output_file)
-                if pdfa_info['pass']:
-                    log.info(
-                        "Output file is a %s (as expected)", pdfa_info['conformance']
-                    )
-                else:
-                    log.warning(
-                        "Output file is okay but is not PDF/A (seems to be %s)",
-                        pdfa_info['conformance'],
-                    )
-                    return ExitCode.pdfa_conversion_failed
-            if not check_pdf(options.output_file):
-                log.warning('Output file: The generated PDF is INVALID')
-                return ExitCode.invalid_output_pdf
-            report_output_file_size(
-                options, start_input_file, options.output_file, optimize_messages
-            )
-
-    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:
-        e = cast(ExitCodeException, e)
-        if options.verbose >= 1:
-            log.exception("ExitCodeException")
-        elif str(e):
-            log.error("%s: %s", type(e).__name__, str(e))
-        else:
-            log.error(type(e).__name__)
-        return e.exit_code
-    except (PIL.Image.DecompressionBombError 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 "
-            "image pixel limit."
-        )
-        return ExitCode.other_error
-    except (
-        BrokenProcessPool if not api else NeverRaise,
-        BrokenThreadPool if not api else NeverRaise,
-    ):
-        log.exception(
-            "A worker process was terminated unexpectedly. This is known to occur if "
-            "processing your file takes all available swap space and RAM. It may "
-            "help to try again with a smaller number of jobs, using the --jobs "
-            "argument."
-        )
-        return ExitCode.child_process_error
-    except (Exception if not api else NeverRaise):  # pylint: disable=broad-except
-        log.exception("An exception occurred while executing the pipeline")
-        return ExitCode.other_error
-    finally:
-        if debug_log_handler:
-            try:
-                debug_log_handler.close()
-                log.removeHandler(debug_log_handler)
-            except OSError as e:
-                print(e, file=sys.stderr)
-        cleanup_working_files(work_folder, options)
-
     return ExitCode.ok

src/ocrmypdf/_pipelines/hocr_to_ocr_pdf.py

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

src/ocrmypdf/_pipelines/ocr.py

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

src/ocrmypdf/_pipelines/pdf_to_hocr.py

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

src/ocrmypdf/_plugin_manager.py

@@ -10,8 +10,8 @@ import importlib
 import importlib.util
 import pkgutil
 import sys
+from collections.abc import Sequence
 from pathlib import Path
-from typing import Sequence
 
 import pluggy
 
@@ -33,7 +33,7 @@ class OcrmypdfPluginManager(pluggy.PluginManager):
     def __init__(
         self,
         *args,
-        plugins: list[str | Path],
+        plugins: Sequence[str | Path],
         builtins: bool = True,
         **kwargs,
     ):
@@ -100,10 +100,12 @@ class OcrmypdfPluginManager(pluggy.PluginManager):
             self.register(module)
 
 
-def get_plugin_manager(plugins: list[str | Path], builtins=True):
+def get_plugin_manager(
+    plugins: Sequence[str | Path] | None = None, builtins=True
+) -> OcrmypdfPluginManager:
     return OcrmypdfPluginManager(
         project_name='ocrmypdf',
-        plugins=plugins,
+        plugins=plugins if plugins is not None else [],
         builtins=builtins,
     )
 

src/ocrmypdf/_progressbar.py

@@ -0,0 +1,142 @@
+# SPDX-FileCopyrightText: 2023 James R. Barlow
+# SPDX-License-Identifier: MPL-2.0
+
+"""Defines progress bar API."""
+
+from __future__ import annotations
+
+from typing import Protocol
+
+from rich.console import Console
+from rich.progress import (
+    BarColumn,
+    MofNCompleteColumn,
+    Progress,
+    TaskProgressColumn,
+    TextColumn,
+    TimeRemainingColumn,
+)
+from rich.table import Column
+
+
+class ProgressBar(Protocol):
+    """The protocol that OCRmyPDF expects progress bar classes to be compatible with.
+
+    In practice this could be used for any time of monitoring, not just a progress bar.
+
+    Calling the class should return a new progress bar object, which is activated
+    with ``__enter__`` and terminated with ``__exit__``. An update method is called
+    whenever the progress bar is updated. Progress bar objects will not be reused;
+    a new one will be created for each group of tasks.
+
+    The progress bar is held in the main process/thread and not updated by child
+    process/threads. When a child notifies the parent of completed work, the
+    parent updates the progress bar.
+
+    Progress bars should never write to ``sys.stdout``, or they will corrupt the
+    output if OCRmyPDF writes a PDF to standard output.
+
+    The type of events that OCRmyPDF reports to a progress bar may change in
+    minor releases.
+    """
+
+    def __init__(
+        self,
+        *,
+        total: int | float | None,
+        desc: str | None,
+        unit: str | None,
+        disable: bool = False,
+        **kwargs,
+    ):
+        """Initialize a progress bar.
+
+        *total* indicates the total number of work units. If None, the total
+        number of work units is unknown. If *disable* is True, the progress bar
+        should be disabled. *unit* is a description of the work unit.
+        *desc* is a description of the overall task to be performed.
+
+        Unrecognized keyword arguments must be ignored, as the list of keyword
+        arguments may grow with time.
+        """
+
+    def __enter__(self):
+        """Enter a progress bar context."""
+
+    def __exit__(self, *args):
+        """Exit a progress bar context."""
+
+    def update(self, n=1):
+        """Update the progress bar by an increment.
+
+        For use within a progress bar context.
+        """
+
+
+class NullProgressBar:
+    """Progress bar API that takes no actions."""
+
+    def __init__(self, **kwargs):
+        pass
+
+    def __enter__(self):
+        return self
+
+    def __exit__(self, exc_type, exc_value, traceback):
+        return False
+
+    def update(self, _arg=None):
+        return
+
+
+class RichProgressBar:
+    """Display progress bar using rich."""
+
+    def __init__(
+        self,
+        *,
+        console: Console,
+        desc: str,
+        total: float | None = None,
+        unit: str | None = None,
+        unit_scale: float | None = 1.0,
+        disable: bool = False,
+        **kwargs,
+    ):
+        self.progress = Progress(
+            TextColumn(
+                "[progress.description]{task.description}",
+                table_column=Column(min_width=20),
+            ),
+            BarColumn(),
+            TaskProgressColumn(),
+            MofNCompleteColumn(),
+            TimeRemainingColumn(),
+            console=console,
+            auto_refresh=True,
+            redirect_stderr=True,
+            redirect_stdout=False,
+            disable=disable,
+            **kwargs,
+        )
+        self.unit_scale = unit_scale
+        self.progress_bar = self.progress.add_task(
+            desc,
+            total=total * self.unit_scale
+            if total is not None and self.unit_scale is not None
+            else None,
+            unit=unit,
+        )
+
+    def __enter__(self):
+        self.progress.start()
+        return self
+
+    def __exit__(self, exc_type, exc_value, traceback):
+        self.progress.refresh()
+        self.progress.stop()
+        return False
+
+    def update(self, value=None):
+        advance = self.unit_scale if value is None else value
+        self.progress.update(self.progress_bar, advance=advance)

src/ocrmypdf/_validation.py

@@ -12,9 +12,9 @@ import os
 import sys
 import unicodedata
 from argparse import Namespace
+from collections.abc import Sequence
 from pathlib import Path
 from shutil import copyfileobj
-from typing import Sequence
 
 import pikepdf
 import PIL
@@ -28,7 +28,6 @@ from ocrmypdf.exceptions import (
     OutputFileAccessError,
 )
 from ocrmypdf.helpers import is_file_writable, monotonic, safe_symlink
-from ocrmypdf.hocrtransform import HOCR_OK_LANGS
 from ocrmypdf.subprocess import check_external_program
 
 # -------------
@@ -43,43 +42,46 @@ log = logging.getLogger(__name__)
 
 
 def check_platform() -> None:
-    if os.name == 'nt' and sys.maxsize <= 2**32:  # pragma: no cover
+    if sys.maxsize <= 2**32:  # pragma: no cover
-        # 32-bit interpreter on Windows
+        log.warning(
-        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: Namespace, ocr_engine_languages: set[str]) -> None:
+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: Namespace) -> None:
-    is_latin = options.languages.issubset(HOCR_OK_LANGS)
-
-    if options.pdf_renderer.startswith('hocr') and not is_latin:
-        log.warning(
-            "The 'hocr' PDF renderer is known to cause problems with one "
-            "or more of the languages in your document.  Use "
-            "`--pdf-renderer auto` (the default) to avoid this issue."
-        )
-
     if options.output_type == 'none' and options.output_file not in (os.devnull, '-'):
         raise BadArgsError(
             "Since you specified `--output-type none`, the output file "
@@ -87,6 +89,8 @@ def check_options_output(options: Namespace) -> None:
             f"`-` to suppress this message."
         )
 
+
+def set_lossless_reconstruction(options: Namespace) -> None:
     lossless_reconstruction = False
     if not any(
         (
@@ -109,12 +113,10 @@ def check_options_output(options: Namespace) -> None:
 def check_options_sidecar(options: Namespace) -> None:
     if options.sidecar == '\0':
         if options.output_file == '-':
-            raise BadArgsError(
+            raise BadArgsError("--sidecar filename needed when output file is stdout.")
-                "--sidecar filename must be specified 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:
@@ -134,7 +136,7 @@ def check_options_preprocessing(options: Namespace) -> None:
             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:
@@ -195,16 +197,6 @@ def check_options_ocr_behavior(options: Namespace) -> None:
         options.pages = _pages_from_ranges(options.pages)
 
 
-def check_options_advanced(options: Namespace) -> None:
-    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: Namespace) -> None:
     docinfo = [options.title, options.author, options.keywords, options.subject]
     for s in (m for m in docinfo if m):
@@ -221,17 +213,17 @@ def check_options_metadata(options: Namespace) -> None:
 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_plugin_invariant_options(options: Namespace) -> None:
     check_platform()
     check_options_metadata(options)
     check_options_output(options)
+    set_lossless_reconstruction(options)
     check_options_sidecar(options)
     check_options_preprocessing(options)
     check_options_ocr_behavior(options)
-    check_options_advanced(options)
     check_options_pillow(options)
 
 
@@ -246,6 +238,18 @@ def check_options(options: Namespace, plugin_manager: PluginManager) -> None:
     _check_plugin_options(options, plugin_manager)
 
 
+def _in_docker():
+    return Path('/.dockerenv').exists()
+
+
+def _in_snap():
+    try:
+        cgroup_text = Path('/proc/self/cgroup').read_text()
+        return 'snap.ocrmypdf' in cgroup_text
+    except FileNotFoundError:
+        return False
+
+
 def create_input_file(options: Namespace, work_folder: Path) -> tuple[Path, str]:
     if options.input_file == '-':
         # stdin
@@ -269,14 +273,24 @@ def create_input_file(options: Namespace, work_folder: Path) -> tuple[Path, str]
             return target, os.fspath(options.input_file)
         except FileNotFoundError as e:
             msg = f"File not found - {options.input_file}"
-            if Path('/.dockerenv').exists():  # pragma: no cover
+            if _in_docker():  # pragma: no cover
                 msg += (
-                    "\nDocker cannot your working directory unless you "
+                    "\nDocker cannot access your working directory unless you "
                     "explicitly share it with the Docker container and set up"
                     "permissions correctly.\n"
                     "You may find it easier to use stdin/stdout:"
                     "\n"
-                    "\tdocker run -i --rm jbarlow83/ocrmypdf - - <input.pdf >output.pdf\n"
+                    "\tdocker run -i --rm jbarlow83/ocrmypdf - - <input.pdf >output.pdf"
+                    "\n"
+                )
+            elif _in_snap():  # pragma: no cover
+                msg += (
+                    "\nSnap applications cannot access files outside of "
+                    "your home directory unless you explicitly allow it. "
+                    "You may find it easier to use stdin/stdout:"
+                    "\n"
+                    "\tsnap run ocrmypdf - - <input.pdf >output.pdf"
+                    "\n"
                 )
             raise InputFileError(msg) from e
 
@@ -333,7 +347,7 @@ def report_output_file_size(
     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."
             )
 
     reasons.extend(optimize_messages)

src/ocrmypdf/_version.py

@@ -8,10 +8,7 @@ OCRmyPDF uses setuptools_scm to derive version from git tags.
 
 from __future__ import annotations
 
-try:
+from importlib.metadata import version as _package_version
-    from importlib.metadata import version as _package_version
-except ImportError:
-    from importlib_metadata import version as _package_version  # type: ignore
 
 PROGRAM_NAME = 'ocrmypdf'
 

src/ocrmypdf/api.py

@@ -9,31 +9,31 @@ import logging
 import os
 import sys
 import threading
+from argparse import Namespace
+from collections.abc import Iterable, Sequence
 from enum import IntEnum
 from io import IOBase
 from pathlib import Path
-from typing import AnyStr, BinaryIO, Iterable, Union
+from typing import AnyStr, BinaryIO, Union
 from warnings import warn
 
-from ocrmypdf._logging import PageNumberFilter, TqdmConsole
+import pluggy
+
+from ocrmypdf._logging import PageNumberFilter
+from ocrmypdf._pipelines.hocr_to_ocr_pdf import run_hocr_to_ocr_pdf_pipeline
+from ocrmypdf._pipelines.ocr import run_pipeline, run_pipeline_cli
+from ocrmypdf._pipelines.pdf_to_hocr import run_hocr_pipeline
 from ocrmypdf._plugin_manager import get_plugin_manager
-from ocrmypdf._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  # pylint: disable=invalid-name
-
-if coloredlogs:
-    from humanfriendly.terminal import enable_ansi_support
-
-
 StrPath = Union[Path, AnyStr]
 PathOrIO = Union[BinaryIO, StrPath]
 
+# Installing plugins affects the global state of the Python interpreter,
+# so we need to use a lock to prevent multiple threads from installing
+# plugins at the same time.
 _api_lock = threading.Lock()
 
 
@@ -52,7 +52,7 @@ 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.
 
@@ -92,7 +92,6 @@ 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)
@@ -119,14 +118,7 @@ def configure_logging(
     else:
         fmt = '%(pageno)s%(message)s'
 
-    use_colors = progress_bar_friendly
     formatter = None
-    if coloredlogs and use_colors:
-        use_colors = enable_ansi_support()
-        if use_colors:
-            use_colors = coloredlogs.terminal_supports_colors()
-        if use_colors:
-            formatter = coloredlogs.ColoredFormatter(fmt=fmt)
 
     if not formatter:
         formatter = logging.Formatter(fmt=fmt)
@@ -146,20 +138,19 @@ def configure_logging(
     return log
 
 
-def create_options(
+def _kwargs_to_cmdline(
-    *, input_file: PathOrIO, output_file: PathOrIO, parser: ArgumentParser, **kwargs
+    *, defer_kwargs: set[str], **kwargs
-):
+) -> tuple[list[str], dict[str, AnyStr]]:
+    """Convert kwargs to command line arguments."""
     cmdline = []
-    deferred = []
+    deferred = {}
-
     for arg, val in kwargs.items():
         if val is None:
             continue
 
-        # These arguments with special handling for which we bypass
+        # Skip arguments that are handled elsewhere
-        # argparse
+        if arg in defer_kwargs:
-        if arg in {'progress_bar', 'plugins'}:
+            deferred[arg] = val
-            deferred.append((arg, val))
             continue
 
         cmd_style_arg = arg.replace('_', '-')
@@ -186,7 +177,30 @@ def create_options(
             cmdline.append(str(val))
         else:
             raise TypeError(f"{arg}: {val} ({type(val)})")
+    return cmdline, deferred
 
+
+def create_options(
+    *, input_file: PathOrIO, output_file: PathOrIO, parser: ArgumentParser, **kwargs
+) -> Namespace:
+    """Construct an options object from the input/output files and keyword arguments.
+
+    Args:
+        input_file: Input file path or file object.
+        output_file: Output file path or file object.
+        parser: ArgumentParser object.
+        **kwargs: Keyword arguments.
+
+    Returns:
+        argparse.Namespace: A Namespace object containing the parsed arguments.
+
+    Raises:
+        TypeError: If the type of a keyword argument is not supported.
+    """
+    cmdline, deferred = _kwargs_to_cmdline(
+        defer_kwargs={'progress_bar', 'plugins', 'parser', 'input_file', 'output_file'},
+        **kwargs,
+    )
     if isinstance(input_file, (BinaryIO, IOBase)):
         cmdline.append('stream://input_file')
     else:
@@ -198,7 +212,7 @@ def create_options(
 
     parser.enable_api_mode()
     options = parser.parse_args(cmdline)
-    for keyword, val in deferred:
+    for keyword, val in deferred.items():
         setattr(options, keyword, val)
 
     if options.input_file == 'stream://input_file':
@@ -209,59 +223,78 @@ def create_options(
     return options
 
 
-def ocr(  # pylint: disable=unused-argument
+def ocr(  # noqa: D417
     input_file: PathOrIO,
     output_file: PathOrIO,
     *,
-    language: Iterable[str] = None,
+    language: Iterable[str] | None = None,
-    image_dpi: int = None,
+    image_dpi: int | None = None,
-    output_type=None,
+    output_type: str | None = None,
     sidecar: StrPath | None = None,
-    jobs: int = None,
+    jobs: int | None = None,
-    use_threads: bool = None,
+    use_threads: bool | None = None,
-    title: str = None,
+    title: str | None = None,
-    author: str = None,
+    author: str | None = None,
-    subject: str = None,
+    subject: str | None = None,
-    keywords: str = None,
+    keywords: str | None = None,
-    rotate_pages: bool = None,
+    rotate_pages: bool | None = None,
-    remove_background: bool = None,
+    remove_background: bool | None = None,
-    deskew: bool = None,
+    deskew: bool | None = None,
-    clean: bool = None,
+    clean: bool | None = None,
-    clean_final: bool = None,
+    clean_final: bool | None = None,
-    unpaper_args: str = None,
+    unpaper_args: str | None = None,
-    oversample: int = None,
+    oversample: int | None = None,
-    remove_vectors: bool = None,
+    remove_vectors: bool | None = None,
-    force_ocr: bool = None,
+    force_ocr: bool | None = None,
-    skip_text: bool = None,
+    skip_text: bool | None = None,
-    redo_ocr: bool = None,
+    redo_ocr: bool | None = None,
-    skip_big: float = None,
+    skip_big: float | None = None,
-    optimize: int = None,
+    optimize: int | None = None,
-    jpg_quality: int = None,
+    jpg_quality: int | None = None,
-    png_quality: int = None,
+    png_quality: int | None = None,
-    jbig2_lossy: bool = None,
+    jbig2_lossy: bool | None = None,
-    jbig2_page_group_size: int = None,
+    jbig2_page_group_size: int | None = None,
-    pages: str = None,
+    jbig2_threshold: float | None = None,
-    max_image_mpixels: float = None,
+    pages: str | None = None,
-    tesseract_config: Iterable[str] = None,
+    max_image_mpixels: float | None = None,
-    tesseract_pagesegmode: int = None,
+    tesseract_config: Iterable[str] | None = None,
-    tesseract_oem: int = None,
+    tesseract_pagesegmode: int | None = None,
-    tesseract_thresholding: int = None,
+    tesseract_oem: int | None = None,
-    pdf_renderer=None,
+    tesseract_thresholding: int | None = None,
-    tesseract_timeout: float = None,
+    pdf_renderer: str | None = None,
-    rotate_pages_threshold: float = None,
+    tesseract_timeout: float | None = None,
-    pdfa_image_compression=None,
+    tesseract_non_ocr_timeout: float | None = None,
-    user_words: os.PathLike = None,
+    tesseract_downsample_above: int | None = None,
-    user_patterns: os.PathLike = None,
+    tesseract_downsample_large_images: bool | None = None,
-    fast_web_view: float = None,
+    rotate_pages_threshold: float | None = None,
-    plugins: Iterable[StrPath] = None,
+    pdfa_image_compression: str | None = None,
+    color_conversion_strategy: str | None = None,
+    user_words: os.PathLike | None = None,
+    user_patterns: os.PathLike | None = None,
+    fast_web_view: float | None = None,
+    continue_on_soft_render_error: bool | None = None,
+    invalidate_digital_signatures: bool | None = None,
+    plugins: Iterable[StrPath] | None = None,
     plugin_manager=None,
-    keep_temporary_files: bool = None,
+    keep_temporary_files: bool | None = None,
-    progress_bar: bool = 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:
@@ -283,9 +316,8 @@ 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
@@ -317,17 +349,15 @@ def ocr(  # pylint: disable=unused-argument
         plugins = list(plugins)
 
     # No new variable names should be assigned until these two steps are run
-    create_options_kwargs = {k: v for k, v in locals().items() if k != 'kwargs'}
+    create_options_kwargs = {
+        k: v
+        for k, v in locals().items()
+        if k not in {'input_file', 'output_file', 'kwargs'}
+    }
     create_options_kwargs.update(kwargs)
 
     parser = get_parser()
-    create_options_kwargs['parser'] = parser
-
     with _api_lock:
-        # We can't allow multiple ocrmypdf.ocr() threads to run in parallel, because
-        # they might install different plugins, and generally speaking we have areas
-        # of code that use global state.
-
         if not plugin_manager:
             plugin_manager = get_plugin_manager(plugins)
         plugin_manager.hook.add_options(parser=parser)  # pylint: disable=no-member
@@ -335,14 +365,181 @@ def ocr(  # pylint: disable=unused-argument
         if 'verbose' in kwargs:
             warn("ocrmypdf.ocr(verbose=) is ignored. Use ocrmypdf.configure_logging().")
 
-        options = create_options(**create_options_kwargs)
+        options = create_options(
+            input_file=input_file,
+            output_file=output_file,
+            parser=parser,
+            **create_options_kwargs,
+        )
         check_options(options, plugin_manager)
-        return run_pipeline(options=options, plugin_manager=plugin_manager, api=True)
+        return run_pipeline(options=options, plugin_manager=plugin_manager)
+
+
+def _pdf_to_hocr(  # noqa: D417
+    input_pdf: Path,
+    output_folder: Path,
+    *,
+    language: Iterable[str] | None = None,
+    image_dpi: int | None = None,
+    jobs: int | None = None,
+    use_threads: bool | None = None,
+    title: str | None = None,
+    author: str | None = None,
+    subject: str | None = None,
+    keywords: str | None = None,
+    rotate_pages: bool | None = None,
+    remove_background: bool | None = None,
+    deskew: bool | None = None,
+    clean: bool | None = None,
+    clean_final: bool | None = None,
+    unpaper_args: str | None = None,
+    oversample: int | None = None,
+    remove_vectors: bool | None = None,
+    force_ocr: bool | None = None,
+    skip_text: bool | None = None,
+    redo_ocr: bool | None = None,
+    skip_big: float | None = None,
+    pages: str | None = None,
+    max_image_mpixels: float | None = None,
+    tesseract_config: Iterable[str] | None = None,
+    tesseract_pagesegmode: int | None = None,
+    tesseract_oem: int | None = None,
+    tesseract_thresholding: int | None = None,
+    tesseract_timeout: float | None = None,
+    tesseract_non_ocr_timeout: float | None = None,
+    tesseract_downsample_above: int | None = None,
+    tesseract_downsample_large_images: bool | None = None,
+    rotate_pages_threshold: float | None = None,
+    user_words: os.PathLike | None = None,
+    user_patterns: os.PathLike | None = None,
+    continue_on_soft_render_error: bool | None = None,
+    invalidate_digital_signatures: bool | None = None,
+    plugin_manager=None,
+    plugins: Sequence[StrPath] | None = None,
+    keep_temporary_files: bool | None = None,
+    **kwargs,
+):
+    """Partially run OCRmyPDF and produces an output folder containing hOCR files.
+
+    Given a PDF file, this function will run OCRmyPDF up to the point where
+    the PDF is rasterized to images, OCRed, and the hOCR files are produced,
+    all of which are saved to the output folder. This is useful for applications
+    that want to provide an interface for users to edit the text before
+    rendering the final PDF.
+
+    Use :func:`hocr_to_ocr_pdf` to produce the final PDF.
+
+    For arguments not explicitly documented here, see documentation for the
+    equivalent command line parameter.
+
+    This API is **experimental** and subject to change.
+
+    Args:
+        input_pdf: Input PDF file path.
+        output_folder: Output folder path.
+        **kwargs: Keyword arguments.
+    """
+    # No new variable names should be assigned until these two steps are run
+    create_options_kwargs = {
+        k: v
+        for k, v in locals().items()
+        if k not in {'input_pdf', 'output_folder', 'kwargs'}
+    }
+    create_options_kwargs.update(kwargs)
+
+    parser = get_parser()
+
+    with _api_lock:
+        if not plugin_manager:
+            plugin_manager = get_plugin_manager(plugins)
+        plugin_manager.hook.add_options(parser=parser)  # pylint: disable=no-member
+
+        cmdline, deferred = _kwargs_to_cmdline(
+            defer_kwargs={'input_pdf', 'output_folder', 'plugins'},
+            **create_options_kwargs,
+        )
+        cmdline.append(str(input_pdf))
+        cmdline.append(str(output_folder))
+        parser.enable_api_mode()
+        options = parser.parse_args(cmdline)
+        for keyword, val in deferred.items():
+            setattr(options, keyword, val)
+        delattr(options, 'output_file')
+        setattr(options, 'output_folder', output_folder)
+
+        return run_hocr_pipeline(options=options, plugin_manager=plugin_manager)
+
+
+def _hocr_to_ocr_pdf(  # noqa: D417
+    work_folder: Path,
+    output_file: Path,
+    *,
+    jobs: int | None = None,
+    use_threads: bool | None = None,
+    optimize: int | None = None,
+    jpg_quality: int | None = None,
+    png_quality: int | None = None,
+    jbig2_lossy: bool | None = None,
+    jbig2_page_group_size: int | None = None,
+    jbig2_threshold: float | None = None,
+    pdfa_image_compression: str | None = None,
+    color_conversion_strategy: str | None = None,
+    fast_web_view: float | None = None,
+    plugin_manager=None,
+    plugins: Sequence[StrPath] | None = None,
+    **kwargs,
+):
+    """Run OCRmyPDF on a work folder and produce an output PDF.
+
+    After running :func:`pdf_to_hocr`, this function will run OCRmyPDF on the work
+    folder to produce an output PDF. This function consolidates any changes made
+    to the hOCR files in the work folder and produces a final PDF.
+
+    For arguments not explicitly documented here, see documentation for the
+    equivalent command line parameter.
+
+    This API is **experimental** and subject to change.
+
+    Args:
+        work_folder: Work folder path, as generated by :func:`pdf_to_hocr`.
+        output_file: Output PDF file path.
+        **kwargs: Keyword arguments.
+    """
+    # No new variable names should be assigned until these two steps are run
+    create_options_kwargs = {
+        k: v
+        for k, v in locals().items()
+        if k not in {'work_folder', 'output_pdf', 'kwargs'}
+    }
+    create_options_kwargs.update(kwargs)
+
+    parser = get_parser()
+
+    with _api_lock:
+        if not plugin_manager:
+            plugin_manager = get_plugin_manager(plugins)
+        plugin_manager.hook.add_options(parser=parser)  # pylint: disable=no-member
+
+        cmdline, deferred = _kwargs_to_cmdline(
+            defer_kwargs={'work_folder', 'output_file', 'plugins'},
+            **create_options_kwargs,
+        )
+        cmdline.append(str(work_folder))
+        cmdline.append(str(output_file))
+        parser.enable_api_mode()
+        options = parser.parse_args(cmdline)
+        for keyword, val in deferred.items():
+            setattr(options, keyword, val)
+        delattr(options, 'input_file')
+        setattr(options, 'work_folder', work_folder)
+
+        return run_hocr_to_ocr_pdf_pipeline(
+            options=options, plugin_manager=plugin_manager
+        )
 
 
 __all__ = [
     'PageNumberFilter',
-    'TqdmConsole',
     'Verbosity',
     'check_options',
     'configure_logging',
@@ -351,4 +548,5 @@ __all__ = [
     'get_plugin_manager',
     'ocr',
     'run_pipeline',
+    'run_pipeline_cli',
 ]

src/ocrmypdf/builtin_plugins/__init__.py

@@ -1,8 +1,6 @@
 # SPDX-FileCopyrightText: 2022 James R. Barlow
 # SPDX-License-Identifier: MPL-2.0
 
-from __future__ import annotations
+"""Plugins in this package are automatically loaded by ocrmypdf."""
 
-# This file exists only mark builtin_plugins as a package.
+from __future__ import annotations
-# The plugin manager will not load it, so anything defined here may not be
-# processed as a module.

src/ocrmypdf/builtin_plugins/concurrency.py

@@ -1,9 +1,9 @@
 # SPDX-FileCopyrightText: 2022 James R. Barlow
 # SPDX-License-Identifier: MPL-2.0
-from __future__ import annotations
-
 """OCRmyPDF's multiprocessing/multithreading abstraction layer."""
 
+from __future__ import annotations
+
 import logging
 import logging.handlers
 import multiprocessing
@@ -12,25 +12,27 @@ import queue
 import signal
 import sys
 import threading
+from collections.abc import Iterable
 from concurrent.futures import ProcessPoolExecutor, ThreadPoolExecutor, as_completed
 from contextlib import suppress
-from typing import Callable, Iterable, Type, Union
+from typing import Callable, 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
+from ocrmypdf._progressbar import RichProgressBar
 from ocrmypdf.exceptions import InputFileError
 from ocrmypdf.helpers import remove_all_log_handlers
 
-FuturesExecutorClass = Union[Type[ThreadPoolExecutor], Type[ProcessPoolExecutor]]
+FuturesExecutorClass = Union[type[ThreadPoolExecutor], type[ProcessPoolExecutor]]
 Queue = Union[multiprocessing.Queue, queue.Queue]
 UserInit = Callable[[], None]
 WorkerInit = Callable[[Queue, UserInit, int], None]
 
 
 def log_listener(q: Queue):
-    """Listen to the worker processes and forward the messages to logging
+    """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
@@ -39,7 +41,6 @@ def log_listener(q: Queue):
     See:
     https://docs.python.org/3/howto/logging-cookbook.html#logging-to-a-single-file-from-multiple-processes
     """
-
     while True:
         try:
             record = q.get()
@@ -55,12 +56,12 @@ 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)
 
@@ -69,7 +70,7 @@ 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)
 
@@ -82,6 +83,7 @@ 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...
@@ -95,21 +97,12 @@ def thread_init(q: Queue, user_init: UserInit, loglevel) -> None:
 class StandardExecutor(Executor):
     """Standard OCRmyPDF concurrent task executor."""
 
-    def _cancel_futures_kwargs(self):
-        """Shim older Pythons that do not have Executor.shutdown(...cancel_futures=).
-
-        Remove this code when support for Python 3.8 is dropped.
-        """
-        if sys.version_info[:2] < (3, 9):
-            return {}
-        return dict(cancel_futures=True)
-
     def _execute(
         self,
         *,
         use_threads: bool,
         max_workers: int,
-        tqdm_kwargs: dict,
+        progress_kwargs: dict,
         worker_initializer: Callable,
         task: Callable,
         task_arguments: Iterable,
@@ -127,22 +120,27 @@ class StandardExecutor(Executor):
         # Regardless of whether we use_threads for worker processes, the log_listener
         # must be a thread. Make sure we create the listener after the worker pool,
         # so that it does not get forked into the workers.
+        # If use_threads is False, we are currently guilty of creating a thread before
+        # forking on Linux, which is not recommended. However, we take a big
+        # performance hit in pdfinfo if we can't fork. Long term solution is to
+        # replace most of this with an asyncio implementation, and probably to
+        # migrate some of pdfinfo into C++ or Rust.
         listener = threading.Thread(target=log_listener, args=(log_queue,))
         listener.start()
 
-        with self.pbar_class(**tqdm_kwargs) as pbar, executor_class(
+        with self.pbar_class(**progress_kwargs) as pbar, executor_class(
             max_workers=max_workers,
             initializer=initializer,
             initargs=(log_queue, worker_initializer, logging.getLogger("").level),
         ) as executor:
-            futures = [executor.submit(task, args) for args in task_arguments]
+            futures = [executor.submit(task, *args) for args in task_arguments]
             try:
                 for future in as_completed(futures):
                     result = future.result()
                     task_finished(result, pbar)
             except KeyboardInterrupt:
                 # Terminate pool so we exit instantly
-                executor.shutdown(wait=False, **self._cancel_futures_kwargs())
+                executor.shutdown(wait=False, cancel_futures=True)
                 raise
             except Exception:
                 if not os.environ.get("PYTEST_CURRENT_TEST", ""):
@@ -151,7 +149,7 @@ class StandardExecutor(Executor):
                     # results will be discard. But if the condition above is True,
                     # then we are running in pytest, and we want everything to exit
                     # as cleanly as possible so that we get good error messages.
-                    executor.shutdown(wait=False, **self._cancel_futures_kwargs())
+                    executor.shutdown(wait=False, cancel_futures=True)
                 raise
             finally:
                 # Terminate log listener
@@ -164,14 +162,24 @@ 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_RichProgressBar(*args, **kwargs):
+        return RichProgressBar(*args, **kwargs, console=RICH_CONSOLE)
+
+    return partial_RichProgressBar
 
 
 @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/ghostscript.py

@@ -6,50 +6,75 @@ from __future__ import annotations
 
 import logging
 
+from packaging.version import Version
+
 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='9.54',  # RHEL 9's version; Ubuntu 22.04 has 9.55
     )
     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 "
+            "supported. Please upgrade to a newer version."
-            "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.color_conversion_strategy not in ghostscript.COLOR_CONVERSION_STRATEGIES:
-    if options.output_type == 'pdfa-3' and ghostscript.version() < '9.19':
+        raise ValueError(
-        raise MissingDependencyError(
+            f"Invalid color conversion strategy: {options.color_conversion_strategy}"
-            "--output-type pdfa-3 requires Ghostscript 9.19 or later"
+        )
+    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'"
         )
 
 
@@ -63,7 +88,9 @@ 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,
@@ -73,6 +100,7 @@ def rasterize_pdf_page(
         page_dpi=page_dpi,
         rotation=rotation,
         filter_vector=filter_vector,
+        stop_on_error=stop_on_soft_error,
     )
     return output_file
 
@@ -82,17 +110,21 @@ 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

@@ -6,8 +6,8 @@ from __future__ import annotations
 
 import argparse
 import logging
+from collections.abc import Sequence
 from pathlib import Path
-from typing import Sequence
 
 from ocrmypdf import Executor, PdfContext, hookimpl
 from ocrmypdf._exec import jbig2enc, pngquant
@@ -86,6 +86,16 @@ def add_options(parser):
         # 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
@@ -95,7 +105,7 @@ def check_options(options):
             program='pngquant',
             package='pngquant',
             version_checker=pngquant.version,
-            need_version='2.0.1',
+            need_version='2.12.2',
             required_for='--optimize {2,3}',
         )
 

src/ocrmypdf/builtin_plugins/tesseract_ocr.py

@@ -8,10 +8,14 @@ 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 '
+        help=(
-        'into the final output',
+            "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 "
@@ -136,17 +178,45 @@ 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):
-        tag = '-PDF' if options.pdf_renderer == 'sandwich' else ''
+        tag = '-PDF' if options.pdf_renderer == 'sandwich' else 'hOCR'
         return f"Tesseract OCR{tag} {TesseractOcrEngine.version()}"
 
     def __str__(self):
@@ -161,7 +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
@@ -170,7 +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

@@ -6,7 +6,8 @@
 from __future__ import annotations
 
 import argparse
-from typing import Any, Callable, Mapping, TypeVar
+from collections.abc import Mapping
+from typing import Any, Callable, TypeVar
 
 from ocrmypdf._version import PROGRAM_NAME as _PROGRAM_NAME
 from ocrmypdf._version import __version__ as _VERSION
@@ -15,7 +16,11 @@ T = TypeVar('T', int, float)
 
 
 def numeric(basetype: Callable[[Any], T], min_: T | None = None, max_: T | None = None):
-    """Validator for numeric params"""
+    """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
 
@@ -46,7 +51,7 @@ def str_to_int(mapping: Mapping[str, 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
 
@@ -57,13 +62,21 @@ class ArgumentParser(argparse.ArgumentParser):
     """
 
     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
@@ -74,19 +87,22 @@ 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,
@@ -166,7 +182,9 @@ 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',
@@ -175,8 +193,8 @@ Online documentation is located at:
         help="Choose output type. 'pdfa' creates a PDF/A-2b compliant file for "
         "long term archiving (default, recommended) but may not suitable "
         "for users who want their file altered as little as possible. 'pdfa' "
-        "also has problems with full Unicode text. 'pdf' attempts to "
+        "also has problems with full Unicode text. 'pdf' minimizes changes "
-        "preserve file contents as much as possible. 'pdf-a1' creates a "
+        "to the input file. 'pdf-a1' creates a "
         "PDF/A1-b file. 'pdf-a2' is equivalent to 'pdfa'. 'pdf-a3' creates a "
         "PDF/A3-b file. 'none' will produce no output, which may be helpful if "
         "only the --sidecar is desired.",
@@ -348,6 +366,13 @@ Online documentation is located at:
         help="Skip OCR on pages larger than the specified amount of megapixels, "
         "but include skipped pages in final output",
     )
+    ocrsettings.add_argument(
+        '--invalidate-digital-signatures',
+        action='store_true',
+        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(
         "Advanced", "Advanced options to control OCRmyPDF"
@@ -384,19 +409,6 @@ 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),
@@ -409,6 +421,14 @@ 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/exceptions.py

@@ -35,6 +35,7 @@ class ExitCodeException(Exception):
     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)
@@ -47,26 +48,6 @@ class BadArgsError(ExitCodeException):
     exit_code = ExitCode.bad_args
 
 
-class PdfMergeFailedError(ExitCodeException):  # deprecated
-    """An intermediate PDF can't be merged.
-
-    No longer in use.
-    """
-
-    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 correct the problem on its own.
-
-        Try using
-            ocrmypdf --pdf-renderer sandwich  [..other args..]
-        '''
-    )
-
-
 class MissingDependencyError(ExitCodeException):
     """A third-party dependency is missing."""
 
@@ -114,7 +95,7 @@ class EncryptedPdfError(ExitCodeException):
 
     exit_code = ExitCode.encrypted_pdf
     message = dedent(
-        '''\
+        """\
         Input PDF is encrypted. The encryption must be removed to
         perform OCR.
 
@@ -123,7 +104,7 @@ class EncryptedPdfError(ExitCodeException):
 
         You can remove the encryption using
             qpdf --decrypt [--password=[password]] infilename
-        '''
+        """
     )
 
 
@@ -132,3 +113,40 @@ class TesseractConfigError(ExitCodeException):
 
     exit_code = ExitCode.invalid_config
     message = "Error occurred while parsing a Tesseract configuration file"
+
+
+class DigitalSignatureError(InputFileError):
+    """PDF has a digital signature."""
+
+    message = dedent(
+        """\
+        Input PDF has a digital signature. OCR would alter the document,
+        invalidating the signature.
+        """
+    )
+
+
+class TaggedPDFError(InputFileError):
+    """PDF is tagged."""
+
+    message = dedent(
+        """\
+        This PDF is marked as a Tagged PDF. This often indicates
+        that the PDF was generated from an office document and does
+        not need OCR. Use --force-ocr, --skip-text or --redo-ocr to
+        override this error.
+        """
+    )
+
+
+class ColorConversionNeededError(BadArgsError):
+    """PDF needs color conversion."""
+
+    message = dedent(
+        """\
+        The input PDF has an unusual color space. Use
+        --color-conversion-strategy to convert to a common color space
+        such as RGB, or use --output-type pdf to skip PDF/A conversion
+        and retain the original color space.
+        """
+    )

src/ocrmypdf/extra_plugins/__init__.py

@@ -1,3 +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

@@ -12,7 +12,7 @@ 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
@@ -20,12 +20,13 @@ from __future__ import annotations
 import logging
 import logging.handlers
 import signal
+from collections.abc import Iterable, Iterator
 from contextlib import suppress
 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
+from typing import Callable
 
 from ocrmypdf import Executor, hookimpl
 from ocrmypdf._concurrent import NullProgressBar
@@ -54,6 +55,7 @@ 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")
 
 
@@ -61,20 +63,21 @@ 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)
+            result = task(*args)
         except Exception as e:  # pylint: disable=broad-except
             conn.send((MessageType.exception, e))
             break
@@ -111,16 +114,16 @@ class LambdaExecutor(Executor):
         *,
         use_threads: bool,
         max_workers: int,
-        tqdm_kwargs: dict,
+        progress_kwargs: dict,
         worker_initializer: Callable,
         task: Callable,
         task_arguments: Iterable,
         task_finished: Callable,
     ):
         if use_threads and max_workers == 1:
-            with self.pbar_class(**tqdm_kwargs) as pbar:
+            with self.pbar_class(**progress_kwargs) as pbar:
                 for args in task_arguments:
-                    result = task(args)
+                    result = task(*args)
                     task_finished(result, pbar)
             return
 
@@ -154,7 +157,7 @@ class LambdaExecutor(Executor):
         for process in processes:
             process.start()
 
-        with self.pbar_class(**tqdm_kwargs) as pbar:
+        with self.pbar_class(**progress_kwargs) as pbar:
             while connections:
                 for result in wait(connections):
                     if not isinstance(result, Connection):
@@ -166,8 +169,7 @@ class LambdaExecutor(Executor):
                         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)
@@ -185,14 +187,20 @@ 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

@@ -10,48 +10,58 @@ import multiprocessing
 import os
 import shutil
 import warnings
-from collections import namedtuple
+from collections.abc import Iterable, Sequence
-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,
+    TypeVar,
+)
 
 import img2pdf
 import pikepdf
-from packaging.version import Version
 
 log = logging.getLogger(__name__)
 
-if Version(img2pdf.__version__) < Version('0.4.0'):
+IMG2PDF_KWARGS = dict(engine=img2pdf.Engine.pikepdf, rotation=img2pdf.Rotation.ifvalid)
-    IMG2PDF_KWARGS = dict(without_pdfw=True)
-elif Version(img2pdf.__version__) < Version('0.4.3'):
-    IMG2PDF_KWARGS = dict(engine=img2pdf.Engine.pikepdf)
-else:
-    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
@@ -60,31 +70,65 @@ 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):
+    def to_scalar(self) -> float:
-        if yvals is not None:
+        """Return the harmonic mean of x and y as a 1D approximation.
-            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 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):
@@ -93,10 +137,10 @@ 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.
@@ -111,7 +155,7 @@ 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
@@ -137,7 +181,11 @@ def safe_symlink(input_file: os.PathLike, soft_link_name: os.PathLike):
     os.symlink(os.path.abspath(input_file), soft_link_name)
 
 
-def samefile(file1: os.PathLike, file2: 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 file1 == file2
     else:
@@ -155,7 +203,7 @@ def monotonic(seq: Sequence) -> bool:
 
 
 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])
 
 
@@ -184,7 +232,7 @@ 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,
@@ -252,43 +300,35 @@ def check_pdf(input_file: Path) -> bool:
             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):
+def remove_all_log_handlers(logger: logging.Logger) -> None:
-    "Remove all log handlers, usually used in a child process."
+    """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():
+def pikepdf_enable_mmap() -> None:
-    # try:
+    """Enable pikepdf memory mapping."""
-    #     if pikepdf._qpdf.set_access_default_mmap(True):
+    try:
-    #         log.debug("pikepdf mmap enabled")
+        pikepdf._core.set_access_default_mmap(True)
-    # except AttributeError:
+        log.debug(
-    #     log.debug("pikepdf mmap not available")
+            "pikepdf mmap "
-    # 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.
+                'enabled'
-    # Fix is not in pybind11 2.6.0
+                if pikepdf._core.get_access_default_mmap()  # type: ignore[attr-defined]
-    # log.debug("pikepdf mmap disabled")
+                else '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
+    except AttributeError:
-        return func(*args, **kwargs)
+        log.debug("pikepdf mmap not available")
-
-    return new_func

src/ocrmypdf/hocrtransform.py

@@ -1,481 +0,0 @@
-#!/usr/bin/env python3
-# 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 xml.etree import ElementTree
-
-with warnings.catch_warnings():
-    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,
-# assuming Tesseract has the necessary languages installed. Note that there may
-# not be language packs for them.
-HOCR_OK_LANGS = frozenset(
-    [
-        # Languages fully covered by Latin-1:
-        'afr',  # Afrikaans
-        'alb',  # Albanian
-        'ast',  # Leonese
-        'baq',  # Basque
-        'bre',  # Breton
-        'cos',  # Corsican
-        'eng',  # English
-        'eus',  # Basque
-        'fao',  # Faoese
-        'gla',  # Scottish Gaelic
-        'glg',  # Galician
-        'glv',  # Manx
-        'ice',  # Icelandic
-        'ind',  # Indonesian
-        'isl',  # Icelandic
-        'ita',  # Italian
-        'ltz',  # Luxembourgish
-        'mal',  # Malay Rumi
-        'mga',  # Irish
-        'nor',  # Norwegian
-        'oci',  # Occitan
-        'por',  # Portugeuse
-        'roh',  # Romansh
-        'sco',  # Scots
-        'sma',  # Sami
-        'spa',  # Spanish
-        'sqi',  # Albanian
-        'swa',  # Swahili
-        'swe',  # Swedish
-        'tgl',  # Tagalog
-        'wln',  # Walloon
-        # Languages supported by Latin-1 except for a few rare characters that OCR
-        # is probably not trained to recognize anyway:
-        'cat',  # Catalan
-        'cym',  # Welsh
-        'dan',  # Danish
-        'deu',  # German
-        'dut',  # Dutch
-        'est',  # Estonian
-        'fin',  # Finnish
-        'fra',  # French
-        'hun',  # Hungarian
-        'kur',  # Kurdish
-        'nld',  # Dutch
-        'wel',  # Welsh
-    ]
-)
-
-
-Element = ElementTree.Element
-
-
-class Rect(NamedTuple):
-    """A rectangle for managing PDF coordinates."""
-
-    x1: Any
-    y1: Any
-    x2: Any
-    y2: Any
-
-
-class HocrTransformError(Exception):
-    """Error while applying hOCR transform."""
-
-
-class HocrTransform:
-
-    """
-    A class for converting documents from the hOCR format.
-    For details of the hOCR format, see:
-    http://kba.cloud/hocr-spec/
-    """
-
-    box_pattern = re.compile(r'bbox((\s+\d+){4})')
-    baseline_pattern = re.compile(
-        r'''
-        baseline \s+
-        ([\-\+]?\d*\.?\d*) \s+  # +/- decimal float
-        ([\-\+]?\d+)            # +/- int''',
-        re.VERBOSE,
-    )
-    ligatures = str.maketrans(
-        {'ff': 'ff', 'ffi': 'f‌f‌i', 'ffl': 'f‌f‌l', 'fi': 'fi', 'fl': 'fl'}
-    )
-
-    def __init__(self, *, hocr_filename: str | Path, dpi: float):
-        self.dpi = dpi
-        self.hocr = ElementTree.parse(os.fspath(hocr_filename))
-
-        # if the hOCR file has a namespace, ElementTree requires its use to
-        # find elements
-        matches = re.match(r'({.*})html', self.hocr.getroot().tag)
-        self.xmlns = ''
-        if matches:
-            self.xmlns = matches.group(1)
-
-        # get dimension in pt (not pixel!!!!) of the OCRed image
-        self.width, self.height = None, None
-        for div in self.hocr.findall(self._child_xpath('div', 'ocr_page')):
-            coords = self.element_coordinates(div)
-            pt_coords = self.pt_from_pixel(coords)
-            self.width = pt_coords.x2 - pt_coords.x1
-            self.height = pt_coords.y2 - pt_coords.y1
-            # there shouldn't be more than one, and if there is, we don't want
-            # it
-            break
-        if self.width is None or self.height is None:
-            raise HocrTransformError("hocr file is missing page dimensions")
-
-    def __str__(self):  # pragma: no cover
-        """
-        Return the textual content of the HTML body
-        """
-        if self.hocr is None:
-            return ''
-        body = self.hocr.find(self._child_xpath('body'))
-        if body:
-            return self._get_element_text(body)
-        else:
-            return ''
-
-    def _get_element_text(self, element: Element):
-        """
-        Return the textual content of the element and its children
-        """
-        text = ''
-        if element.text is not None:
-            text += element.text
-        for child in element:
-            text += self._get_element_text(child)
-        if element.tail is not None:
-            text += element.tail
-        return text
-
-    @classmethod
-    def element_coordinates(cls, element: Element) -> Rect:
-        """
-        Returns a tuple containing the 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'])
-            if matches:
-                coords = matches.group(1).split()
-                out = Rect._make(int(coords[n]) for n in range(4))
-        return out
-
-    @classmethod
-    def baseline(cls, element: Element) -> tuple[float, float]:
-        """
-        Returns a tuple containing the baseline slope and intercept.
-        """
-        if 'title' in element.attrib:
-            matches = cls.baseline_pattern.search(element.attrib['title'])
-            if matches:
-                return float(matches.group(1)), int(matches.group(2))
-        return (0.0, 0.0)
-
-    def pt_from_pixel(self, pxl) -> Rect:
-        """
-        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: str | None = None) -> str:
-        xpath = f".//{self.xmlns}{html_tag}"
-        if html_class:
-            xpath += f"[@class='{html_class}']"
-        return xpath
-
-    @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)
-        """
-        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: 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.
-        Text is positioned according to the bounding box of the lines in
-        the hOCR file.
-        The image need not be identical to the image used to create the hOCR
-        file.
-        It can have a lower resolution, different color mode, etc.
-
-        Arguments:
-            out_filename: Path of PDF to write.
-            image_filename: Image to use for this file. If omitted, the OCR text
-                is shown.
-            show_bounding_boxes: Show bounding boxes around various text regions,
-                for debugging.
-            fontname: Name of font to use.
-            invisible_text: If True, text is rendered invisible so that is
-                selectable but never drawn. If False, text is visible and may
-                be seen if the image is skipped or deleted in Acrobat.
-            interword_spaces: If True, insert spaces between words rather than
-                drawing each word without spaces. Generally this improves text
-                extraction.
-        """
-        # create the PDF file
-        # page size in points (1/72 in.)
-        pdf = Canvas(
-            os.fspath(out_filename),
-            pagesize=(self.width, self.height),
-            pageCompression=1,
-        )
-
-        # draw bounding box for each paragraph
-        # light blue for bounding box of paragraph
-        pdf.setStrokeColor(cyan)
-        # light blue for bounding box of paragraph
-        pdf.setFillColor(cyan)
-        pdf.setLineWidth(0)  # no line for bounding box
-        for elem in self.hocr.iterfind(self._child_xpath('p', 'ocr_par')):
-            elemtxt = self._get_element_text(elem).rstrip()
-            if len(elemtxt) == 0:
-                continue
-
-            pxl_coords = self.element_coordinates(elem)
-            pt = self.pt_from_pixel(pxl_coords)  # pylint: disable=invalid-name
-
-            # draw the bbox border
-            if show_bounding_boxes:  # pragma: no cover
-                pdf.rect(
-                    pt.x1, self.height - pt.y2, pt.x2 - pt.x1, pt.y2 - pt.y1, fill=1
-                )
-
-        found_lines = False
-        for line in (
-            element
-            for element in self.hocr.iterfind(self._child_xpath('span'))
-            if 'class' in element.attrib
-            and element.attrib['class'] in {'ocr_header', 'ocr_line', 'ocr_textfloat'}
-        ):
-            found_lines = True
-            self._do_line(
-                pdf,
-                line,
-                "ocrx_word",
-                fontname,
-                invisible_text,
-                interword_spaces,
-                show_bounding_boxes,
-            )
-
-        if not found_lines:
-            # Tesseract did not report any lines (just words)
-            root = self.hocr.find(self._child_xpath('div', 'ocr_page'))
-            self._do_line(
-                pdf,
-                root,
-                "ocrx_word",
-                fontname,
-                invisible_text,
-                interword_spaces,
-                show_bounding_boxes,
-            )
-        # put the image on the page, scaled to fill the page
-        if image_filename is not None:
-            pdf.drawImage(
-                os.fspath(image_filename), 0, 0, width=self.width, height=self.height
-            )
-
-        # finish up the page and save it
-        pdf.showPage()
-        pdf.save()
-
-    @classmethod
-    def polyval(cls, poly, x):  # pragma: no cover
-        return x * poly[0] + poly[1]
-
-    def _do_line(
-        self,
-        pdf: Canvas,
-        line: Element | None,
-        elemclass: str,
-        fontname: str,
-        invisible_text: bool,
-        interword_spaces: bool,
-        show_bounding_boxes: bool,
-    ):
-        if line is None:
-            return
-        pxl_line_coords = self.element_coordinates(line)
-        line_box = self.pt_from_pixel(pxl_line_coords)
-        line_height = line_box.y2 - line_box.y1
-
-        slope, pxl_intercept = self.baseline(line)
-        if abs(slope) < 0.005:
-            slope = 0.0
-        angle = atan(slope)
-        cos_a, sin_a = cos(angle), sin(angle)
-
-        text = pdf.beginText()
-        intercept = pxl_intercept / self.dpi * inch
-
-        # Don't allow the font to break out of the bounding box. Division by
-        # cos_a accounts for extra clearance between the glyph's vertical axis
-        # on a sloped baseline and the edge of the bounding box.
-        fontsize = (line_height - abs(intercept)) / cos_a
-        text.setFont(fontname, fontsize)
-        if invisible_text:
-            text.setTextRenderMode(3)  # Invisible (indicates OCR text)
-
-        # Intercept is normally negative, so this places it above the bottom
-        # of the line box
-        baseline_y2 = self.height - (line_box.y2 + intercept)
-
-        if show_bounding_boxes:  # pragma: no cover
-            # draw the baseline in magenta, dashed
-            pdf.setDash()
-            pdf.setStrokeColor(magenta)
-            pdf.setLineWidth(0.5)
-            # negate slope because it is defined as a rise/run in pixel
-            # coordinates and page coordinates have the y axis flipped
-            pdf.line(
-                line_box.x1,
-                baseline_y2,
-                line_box.x2,
-                self.polyval((-slope, baseline_y2), line_box.x2 - line_box.x1),
-            )
-            # light green for bounding box of word/line
-            pdf.setDash(6, 3)
-            pdf.setStrokeColor(red)
-
-        text.setTextTransform(cos_a, -sin_a, sin_a, cos_a, line_box.x1, baseline_y2)
-        pdf.setFillColor(black)  # text in black
-
-        elements = line.findall(self._child_xpath('span', elemclass))
-        for elem in elements:
-            elemtxt = self._get_element_text(elem).strip()
-            elemtxt = self.replace_unsupported_chars(elemtxt)
-            if elemtxt == '':
-                continue
-
-            pxl_coords = self.element_coordinates(elem)
-            box = self.pt_from_pixel(pxl_coords)
-            if interword_spaces:
-                # if  `--interword-spaces` is true, append a space
-                # to the end of each text element to allow simpler PDF viewers
-                # such as PDF.js to better recognize words in search and copy
-                # and paste. Do not remove space from last word in line, even
-                # though it would look better, because it will interfere with
-                # naive text extraction. \n does not work either.
-                elemtxt += ' '
-                box = Rect._make(
-                    (
-                        box.x1,
-                        line_box.y1,
-                        box.x2 + pdf.stringWidth(' ', fontname, line_height),
-                        line_box.y2,
-                    )
-                )
-            box_width = box.x2 - box.x1
-            font_width = pdf.stringWidth(elemtxt, fontname, fontsize)
-
-            # draw the bbox border
-            if show_bounding_boxes:  # pragma: no cover
-                pdf.rect(
-                    box.x1, self.height - line_box.y2, box_width, line_height, fill=0
-                )
-
-            # Adjust relative position of cursor
-            # This is equivalent to:
-            #   text.setTextOrigin(pt.x1, self.height - line_box.y2)
-            # but the former generates a full text reposition matrix (Tm) in the
-            # content stream while this issues a "offset" (Td) command.
-            # .moveCursor() is relative to start of the text line, where the
-            # "text line" means whatever reportlab defines it as. Do not use
-            # use .getCursor(), since moveCursor() rather unintuitively plans
-            # its moves relative to .getStartOfLine().
-            # For skewed lines, in the text transform we set up a rotated
-            # coordinate system, so we don't have to account for the
-            # incremental offset. Surprisingly most PDF viewers can handle this.
-            cursor = text.getStartOfLine()
-            dx = box.x1 - cursor[0]
-            dy = baseline_y2 - cursor[1]
-            text.moveCursor(dx, dy)
-
-            # If reportlab tells us this word is 0 units wide, our best seems
-            # to be to suppress this text
-            if font_width > 0:
-                text.setHorizScale(100 * box_width / font_width)
-                text.textOut(elemtxt)
-        pdf.drawText(text)
-
-
-if __name__ == "__main__":
-    parser = argparse.ArgumentParser(description='Convert hocr file to PDF')
-    parser.add_argument(
-        '-b',
-        '--boundingboxes',
-        action="store_true",
-        default=False,
-        help='Show bounding boxes borders',
-    )
-    parser.add_argument(
-        '-r',
-        '--resolution',
-        type=int,
-        default=300,
-        help='Resolution of the image that was OCRed',
-    )
-    parser.add_argument(
-        '-i',
-        '--image',
-        default=None,
-        help='Path to the image to be placed above the text',
-    )
-    parser.add_argument(
-        '--interword-spaces',
-        action='store_true',
-        default=False,
-        help='Add spaces between words',
-    )
-    parser.add_argument('hocrfile', help='Path to the hocr file to be parsed')
-    parser.add_argument('outputfile', help='Path to the PDF file to be generated')
-    args = parser.parse_args()
-
-    hocr = HocrTransform(hocr_filename=args.hocrfile, dpi=args.resolution)
-    hocr.to_pdf(
-        out_filename=args.outputfile,
-        image_filename=args.image,
-        show_bounding_boxes=args.boundingboxes,
-        interword_spaces=args.interword_spaces,
-    )

src/ocrmypdf/hocrtransform/__init__.py

@@ -0,0 +1,18 @@
+# SPDX-FileCopyrightText: 2023 James R. Barlow
+# SPDX-License-Identifier: MIT
+
+"""Transform .hocr and page image to text PDF."""
+
+from __future__ import annotations
+
+from ocrmypdf.hocrtransform._hocr import (
+    DebugRenderOptions,
+    HocrTransform,
+    HocrTransformError,
+)
+
+__all__ = (
+    'HocrTransform',
+    'HocrTransformError',
+    'DebugRenderOptions',
+)

src/ocrmypdf/hocrtransform/__main__.py

@@ -0,0 +1,40 @@
+# SPDX-FileCopyrightText: 2023 James R. Barlow
+# SPDX-License-Identifier: MIT
+
+"""Simple CLI for testing HOCR."""
+
+import argparse
+
+from ocrmypdf.hocrtransform import HocrTransform
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser(description='Convert hocr file to PDF')
+    parser.add_argument(
+        '-b',
+        '--boundingboxes',
+        action="store_true",
+        default=False,
+        help='Show bounding boxes borders',
+    )
+    parser.add_argument(
+        '-r',
+        '--resolution',
+        type=int,
+        default=300,
+        help='Resolution of the image that was OCRed',
+    )
+    parser.add_argument(
+        '-i',
+        '--image',
+        default=None,
+        help='Path to the image to be placed above the text',
+    )
+    parser.add_argument('hocrfile', help='Path to the hocr file to be parsed')
+    parser.add_argument('outputfile', help='Path to the PDF file to be generated')
+    args = parser.parse_args()
+
+    hocr = HocrTransform(hocr_filename=args.hocrfile, dpi=args.resolution)
+    hocr.to_pdf(
+        out_filename=args.outputfile,
+        image_filename=args.image,
+    )

src/ocrmypdf/hocrtransform/_font.py

@@ -0,0 +1,112 @@
+# SPDX-FileCopyrightText: 2023 James R. Barlow
+# SPDX-License-Identifier: MPL-2.0
+
+from __future__ import annotations
+
+import logging
+import unicodedata
+import zlib
+from importlib.resources import files as package_files
+
+from pikepdf import (
+    Dictionary,
+    Name,
+    Pdf,
+)
+from pikepdf.canvas import Font
+
+log = logging.getLogger(__name__)
+
+
+class GlyphlessFont(Font):
+    CID_TO_GID_DATA = zlib.compress(b"\x00\x01" * 65536)
+    GLYPHLESS_FONT_NAME = 'pdf.ttf'
+    GLYPHLESS_FONT = (package_files('ocrmypdf.data') / GLYPHLESS_FONT_NAME).read_bytes()
+    CHAR_ASPECT = 2
+
+    def __init__(self):
+        pass
+
+    def text_width(self, text: str, fontsize: float) -> int:
+        """Estimate the width of a text string when rendered with the given font."""
+        # NFKC: split ligatures, combine diacritics
+        return len(unicodedata.normalize("NFKC", text)) * (fontsize / self.CHAR_ASPECT)
+
+    def register(self, pdf: Pdf):
+        """Register the glyphless font.
+
+        Create several data structures in the Pdf to describe the font. While it create
+        the data, a reference should be set in at least one page's /Resources dictionary
+        to retain the font in the output PDF and ensure it is usable on that page.
+        """
+        PLACEHOLDER = Name.Placeholder
+
+        basefont = pdf.make_indirect(
+            Dictionary(
+                BaseFont=Name.GlyphLessFont,
+                DescendantFonts=[PLACEHOLDER],
+                Encoding=Name("/Identity-H"),
+                Subtype=Name.Type0,
+                ToUnicode=PLACEHOLDER,
+                Type=Name.Font,
+            )
+        )
+        cid_font_type2 = pdf.make_indirect(
+            Dictionary(
+                BaseFont=Name.GlyphLessFont,
+                CIDToGIDMap=PLACEHOLDER,
+                CIDSystemInfo=Dictionary(
+                    Ordering="Identity",
+                    Registry="Adobe",
+                    Supplement=0,
+                ),
+                FontDescriptor=PLACEHOLDER,
+                Subtype=Name.CIDFontType2,
+                Type=Name.Font,
+                DW=1000 // self.CHAR_ASPECT,
+            )
+        )
+        basefont.DescendantFonts = [cid_font_type2]
+        cid_font_type2.CIDToGIDMap = pdf.make_stream(
+            self.CID_TO_GID_DATA, Filter=Name.FlateDecode
+        )
+        basefont.ToUnicode = pdf.make_stream(
+            b"/CIDInit /ProcSet findresource begin\n"
+            b"12 dict begin\n"
+            b"begincmap\n"
+            b"/CIDSystemInfo\n"
+            b"<<\n"
+            b"  /Registry (Adobe)\n"
+            b"  /Ordering (UCS)\n"
+            b"  /Supplement 0\n"
+            b">> def\n"
+            b"/CMapName /Adobe-Identify-UCS def\n"
+            b"/CMapType 2 def\n"
+            b"1 begincodespacerange\n"
+            b"<0000> <FFFF>\n"
+            b"endcodespacerange\n"
+            b"1 beginbfrange\n"
+            b"<0000> <FFFF> <0000>\n"
+            b"endbfrange\n"
+            b"endcmap\n"
+            b"CMapName currentdict /CMap defineresource pop\n"
+            b"end\n"
+            b"end\n"
+        )
+        font_descriptor = pdf.make_indirect(
+            Dictionary(
+                Ascent=1000,
+                CapHeight=1000,
+                Descent=-1,
+                Flags=5,  # Fixed pitch and symbolic
+                FontBBox=[0, 0, 1000 // self.CHAR_ASPECT, 1000],
+                FontFile2=PLACEHOLDER,
+                FontName=Name.GlyphLessFont,
+                ItalicAngle=0,
+                StemV=80,
+                Type=Name.FontDescriptor,
+            )
+        )
+        font_descriptor.FontFile2 = pdf.make_stream(self.GLYPHLESS_FONT)
+        cid_font_type2.FontDescriptor = font_descriptor
+        return basefont

src/ocrmypdf/hocrtransform/_hocr.py

@@ -0,0 +1,473 @@
+# SPDX-FileCopyrightText: 2010 Jonathan Brinley
+# SPDX-FileCopyrightText: 2013-2014 Julien Pfefferkorn
+# SPDX-FileCopyrightText: 2023 James R. Barlow
+# SPDX-License-Identifier: MIT
+
+"""hOCR transform implementation."""
+
+from __future__ import annotations
+
+import logging
+import os
+import re
+import unicodedata
+from dataclasses import dataclass
+from itertools import pairwise
+from math import atan, cos, pi
+from pathlib import Path
+from xml.etree import ElementTree
+
+from pikepdf import Matrix, Name, Rectangle
+from pikepdf.canvas import (
+    BLACK,
+    BLUE,
+    CYAN,
+    DARKGREEN,
+    GREEN,
+    MAGENTA,
+    RED,
+    Canvas,
+    Font,
+    Text,
+    TextDirection,
+)
+
+from ocrmypdf.hocrtransform._font import GlyphlessFont
+
+log = logging.getLogger(__name__)
+
+INCH = 72.0
+
+Element = ElementTree.Element
+
+
+@dataclass
+class DebugRenderOptions:
+    """A class for managing rendering options."""
+
+    render_paragraph_bbox: bool
+    render_baseline: bool
+    render_triangle: bool
+    render_line_bbox: bool
+    render_word_bbox: bool
+    render_space_bbox: bool
+
+
+class HocrTransformError(Exception):
+    """Error while applying hOCR transform."""
+
+
+class HocrTransform:
+    """A class for converting documents from the hOCR format.
+
+    For details of the hOCR format, see:
+    http://kba.cloud/hocr-spec/.
+    """
+
+    box_pattern = re.compile(r'bbox (\d+) (\d+) (\d+) (\d+)')
+    baseline_pattern = re.compile(
+        r'''
+        baseline \s+
+        ([\-\+]?\d*\.?\d*) \s+  # +/- decimal float
+        ([\-\+]?\d+)            # +/- int''',
+        re.VERBOSE,
+    )
+
+    def __init__(
+        self,
+        *,
+        hocr_filename: str | Path,
+        dpi: float,
+        debug: bool = False,
+        fontname: Name = Name("/f-0-0"),
+        font: Font = GlyphlessFont(),
+    ):
+        """Initialize the HocrTransform object."""
+        self.dpi = dpi
+        self.hocr = ElementTree.parse(os.fspath(hocr_filename))
+        self._fontname = fontname
+        self._font = font
+
+        # if the hOCR file has a namespace, ElementTree requires its use to
+        # find elements
+        matches = re.match(r'({.*})html', self.hocr.getroot().tag)
+        self.xmlns = ''
+        if matches:
+            self.xmlns = matches.group(1)
+
+        for div in self.hocr.findall(self._child_xpath('div', 'ocr_page')):
+            coords = self.element_coordinates(div)
+            if not coords:
+                raise HocrTransformError("hocr file is missing page dimensions")
+            self.width = (coords.urx - coords.llx) / (self.dpi / INCH)
+            self.height = (coords.ury - coords.lly) / (self.dpi / INCH)
+            # Stop after first div that has page coordinates
+            break
+        self.render_options = DebugRenderOptions(
+            render_baseline=debug,
+            render_triangle=debug,
+            render_line_bbox=False,
+            render_word_bbox=debug,
+            render_paragraph_bbox=False,
+            render_space_bbox=False,
+        )
+
+    def _get_element_text(self, element: Element):
+        """Return the textual content of the element and its children."""
+        text = ''
+        if element.text is not None:
+            text += element.text
+        for child in element:
+            text += self._get_element_text(child)
+        if element.tail is not None:
+            text += element.tail
+        return text
+
+    @classmethod
+    def element_coordinates(cls, element: Element) -> Rectangle | None:
+        """Get coordinates of the bounding box around an element."""
+        matches = cls.box_pattern.search(element.attrib.get('title', ''))
+        if not matches:
+            return None
+        return Rectangle(
+            float(matches.group(1)),  # llx = left
+            float(matches.group(2)),  # lly = top
+            float(matches.group(3)),  # urx = right
+            float(matches.group(4)),  # ury = bottom
+        )
+
+    @classmethod
+    def baseline(cls, element: Element) -> tuple[float, float]:
+        """Get baseline's slope and intercept."""
+        matches = cls.baseline_pattern.search(element.attrib.get('title', ''))
+        if not matches:
+            return (0.0, 0.0)
+        return float(matches.group(1)), int(matches.group(2))
+
+    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}']"
+        return xpath
+
+    @classmethod
+    def normalize_text(cls, s: str) -> str:
+        """Normalize the given text using the NFKC normalization form."""
+        return unicodedata.normalize("NFKC", s)
+
+    def to_pdf(
+        self,
+        *,
+        out_filename: Path,
+        image_filename: Path | None = None,
+        invisible_text: bool = True,
+    ) -> None:
+        """Creates a PDF file with an image superimposed on top of the text.
+
+        Text is positioned according to the bounding box of the lines in
+        the hOCR file.
+        The image need not be identical to the image used to create the hOCR
+        file.
+        It can have a lower resolution, different color mode, etc.
+
+        Arguments:
+            out_filename: Path of PDF to write.
+            image_filename: Image to use for this file. If omitted, the OCR text
+                is shown.
+            invisible_text: If True, text is rendered invisible so that is
+                selectable but never drawn. If False, text is visible and may
+                be seen if the image is skipped or deleted in Acrobat.
+        """
+        # create the PDF file
+        # page size in points (1/72 in.)
+        canvas = Canvas(page_size=(self.width, self.height))
+        canvas.add_font(self._fontname, self._font)
+        page_matrix = (
+            Matrix()
+            .translated(0, self.height)
+            .scaled(1, -1)
+            .scaled(INCH / self.dpi, INCH / self.dpi)
+        )
+        log.debug(page_matrix)
+        with canvas.do.save_state(cm=page_matrix):
+            self._debug_draw_paragraph_boxes(canvas)
+            found_lines = False
+            for par in self.hocr.iterfind(self._child_xpath('p', 'ocr_par')):
+                for line in (
+                    element
+                    for element in par.iterfind(self._child_xpath('span'))
+                    if 'class' in element.attrib
+                    and element.attrib['class']
+                    in {'ocr_header', 'ocr_line', 'ocr_textfloat'}
+                ):
+                    found_lines = True
+                    direction = self._get_text_direction(par)
+                    inject_word_breaks = self._get_inject_word_breaks(par)
+                    self._do_line(
+                        canvas,
+                        line,
+                        "ocrx_word",
+                        invisible_text,
+                        direction,
+                        inject_word_breaks,
+                    )
+
+            if not found_lines:
+                # Tesseract did not report any lines (just words)
+                root = self.hocr.find(self._child_xpath('div', 'ocr_page'))
+                self._do_line(
+                    canvas,
+                    root,
+                    "ocrx_word",
+                    invisible_text,
+                    TextDirection.LTR,
+                    True,
+                )
+        # put the image on the page, scaled to fill the page
+        if image_filename is not None:
+            canvas.do.draw_image(
+                image_filename, 0, 0, width=self.width, height=self.height
+            )
+
+        # finish up the page and save it
+        canvas.to_pdf().save(out_filename)
+
+    def _get_text_direction(self, par):
+        """Get the text direction of the paragraph.
+
+        Arabic, Hebrew, Persian, are right-to-left languages.
+        """
+        return (
+            TextDirection.RTL
+            if par.attrib.get('dir', 'ltr') == 'rtl'
+            else TextDirection.LTR
+        )
+
+    def _get_inject_word_breaks(self, par):
+        """Determine whether word breaks should be injected.
+
+        In Chinese, Japanese, and Korean, word breaks are not injected, because
+        words are usually one or two characters and separators are usually explicit.
+        In all other languages, we inject word breaks to help word segmentation.
+        """
+        lang = par.attrib.get('lang', '')
+        log.debug(lang)
+        if lang in {'chi_sim', 'chi_tra', 'jpn', 'kor'}:
+            return False
+        return True
+
+    @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,
+        canvas: Canvas,
+        line: Element | None,
+        elemclass: str,
+        invisible_text: bool,
+        text_direction: TextDirection,
+        inject_word_breaks: bool,
+    ):
+        """Render the text for a given line.
+
+        The canvas's coordinate system must be configured so that hOCR pixel
+        coordinates are mapped to PDF coordinates.
+        """
+        if line is None:
+            return
+        line_box = self.element_coordinates(line)
+        if not line_box:
+            return
+        assert line_box.ury > line_box.lly  # lly is top, ury is bottom
+
+        self._debug_draw_line_bbox(canvas, line_box)
+
+        # Baseline is a polynomial (usually straight line) that describes the
+        # text baseline relative to the bottom left corner of the line bounding
+        # box.
+        bottom_left_corner = line_box.llx, line_box.ury
+        slope, intercept = self.baseline(line)
+        if abs(slope) < 0.005:
+            slope = 0.0
+        angle = atan(slope)
+
+        # Setup a new coordinate system on the line box's intercept and rotated by
+        # its slope.
+        line_matrix = (
+            Matrix()
+            .translated(*bottom_left_corner)
+            .translated(0, intercept)
+            .rotated(angle / pi * 180)
+        )
+        log.debug(line_matrix)
+        with canvas.do.save_state(cm=line_matrix):
+            text = Text(direction=text_direction)
+
+            # Don't allow the font to break out of the bounding box. Division by
+            # cos_a accounts for extra clearance between the glyph's vertical axis
+            # on a sloped baseline and the edge of the bounding box.
+            line_box_height = abs(line_box.height) / cos(angle)
+            fontsize = line_box_height + intercept
+            text.font(self._fontname, fontsize)
+            if invisible_text or True:
+                text.render_mode(3)  # Invisible (indicates OCR text)
+
+            self._debug_draw_baseline(
+                canvas, line_matrix.inverse().transform(line_box), 0
+            )
+
+            canvas.do.fill_color(BLACK)  # text in black
+            elements = line.findall(self._child_xpath('span', elemclass))
+            for elem, next_elem in pairwise(elements + [None]):
+                self._do_line_word(
+                    canvas,
+                    line_matrix,
+                    text,
+                    fontsize,
+                    elem,
+                    next_elem,
+                    text_direction,
+                    inject_word_breaks,
+                )
+            canvas.do.draw_text(text)
+
+    def _do_line_word(
+        self,
+        canvas: Canvas,
+        line_matrix: Matrix,
+        text: Text,
+        fontsize: float,
+        elem: Element,
+        next_elem: Element | None,
+        text_direction: TextDirection,
+        inject_word_breaks: bool,
+    ):
+        """Render the text for a single word."""
+        if elem is None:
+            return
+        elemtxt = self.normalize_text(self._get_element_text(elem).strip())
+        if elemtxt == '':
+            return
+
+        hocr_box = self.element_coordinates(elem)
+        if hocr_box is None:
+            return
+        box = line_matrix.inverse().transform(hocr_box)
+        font_width = self._font.text_width(elemtxt, fontsize)
+
+        # Debug sketches
+        self._debug_draw_word_triangle(canvas, box)
+        self._debug_draw_word_bbox(canvas, box)
+
+        # If this word is 0 units wide, our best bet seems to be to suppress this text
+        if font_width > 0:
+            text.text_transform(Matrix(1, 0, 0, 1, box.llx, 0))
+            text.horiz_scale(100 * box.width / font_width)
+            text.show(elemtxt.encode('utf-16be'))
+
+        # Get coordinates of the next word (if there is one)
+        hocr_next_box = (
+            self.element_coordinates(next_elem) if next_elem is not None else None
+        )
+        if hocr_next_box is None:
+            return
+        # Render a space this word and the next word. The explicit space helps
+        # PDF viewers identify the word break, and horizontally scaling it to
+        # occupy the space the between the words helps the PDF viewer
+        # avoid combiningthewordstogether.
+        if not inject_word_breaks:
+            return
+        next_box = line_matrix.inverse().transform(hocr_next_box)
+        if text_direction == TextDirection.LTR:
+            space_box = Rectangle(box.urx, box.lly, next_box.llx, next_box.ury)
+        elif text_direction == TextDirection.RTL:
+            space_box = Rectangle(next_box.urx, box.lly, box.llx, next_box.ury)
+        self._debug_draw_space_bbox(canvas, space_box)
+        text.text_transform(Matrix(1, 0, 0, 1, space_box.llx, 0))
+        space_width = self._font.text_width(' ', fontsize)
+        if space_width > 0:
+            text.horiz_scale(100 * space_box.width / space_width)
+            text.show(' '.encode('utf-16be'))
+
+    def _debug_draw_paragraph_boxes(self, canvas: Canvas, color=CYAN):
+        """Draw boxes around paragraphs in the document."""
+        if not self.render_options.render_paragraph_bbox:  # pragma: no cover
+            return
+        with canvas.do.save_state():
+            # draw box around paragraph
+            canvas.do.stroke_color(color).line_width(0.1)
+            for elem in self.hocr.iterfind(self._child_xpath('p', 'ocr_par')):
+                elemtxt = self._get_element_text(elem).strip()
+                if len(elemtxt) == 0:
+                    continue
+                ocr_par = self.element_coordinates(elem)
+                if ocr_par is None:
+                    continue
+                canvas.do.rect(
+                    ocr_par.llx, ocr_par.lly, ocr_par.width, ocr_par.height, fill=0
+                )
+
+    def _debug_draw_line_bbox(self, canvas: Canvas, line_box: Rectangle, color=BLUE):
+        """Render the bounding box of a text line."""
+        if not self.render_options.render_line_bbox:  # pragma: no cover
+            return
+        with canvas.do.save_state():
+            canvas.do.stroke_color(color).line_width(0.15).rect(
+                line_box.llx, line_box.lly, line_box.width, line_box.height, fill=0
+            )
+
+    def _debug_draw_word_triangle(
+        self, canvas: Canvas, box: Rectangle, color=RED, line_width=0.1
+    ):
+        """Render a triangle that conveys word height and drawing direction."""
+        if not self.render_options.render_triangle:  # pragma: no cover
+            return
+        with canvas.do.save_state():
+            canvas.do.stroke_color(color).line_width(line_width).line(
+                box.llx, box.lly, box.urx, box.lly
+            ).line(box.urx, box.lly, box.llx, box.ury).line(
+                box.llx, box.lly, box.llx, box.ury
+            )
+
+    def _debug_draw_word_bbox(
+        self, canvas: Canvas, box: Rectangle, color=GREEN, line_width=0.1
+    ):
+        """Render a box depicting the word."""
+        if not self.render_options.render_word_bbox:  # pragma: no cover
+            return
+        with canvas.do.save_state():
+            canvas.do.stroke_color(color).line_width(line_width).rect(
+                box.llx, box.lly, box.width, box.height, fill=0
+            )
+
+    def _debug_draw_space_bbox(
+        self, canvas: Canvas, box: Rectangle, color=DARKGREEN, line_width=0.1
+    ):
+        """Render a box depicting the space between two words."""
+        if not self.render_options.render_space_bbox:  # pragma: no cover
+            return
+        with canvas.do.save_state():
+            canvas.do.fill_color(color).line_width(line_width).rect(
+                box.llx, box.lly, box.width, box.height, fill=1
+            )
+
+    def _debug_draw_baseline(
+        self,
+        canvas: Canvas,
+        line_box: Rectangle,
+        baseline_lly,
+        color=MAGENTA,
+        line_width=0.25,
+    ):
+        """Render the text baseline."""
+        if not self.render_options.render_baseline:
+            return
+        with canvas.do.save_state():
+            canvas.do.stroke_color(color).line_width(line_width).line(
+                line_box.llx,
+                baseline_lly,
+                line_box.urx,
+                baseline_lly,
+            )

src/ocrmypdf/imageops.py

@@ -0,0 +1,152 @@
+# 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 PIL import Image
+
+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: tuple[int, int] | None = None,
+    max_pixels: int | None = None,
+    max_bytes: int | None = 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: tuple[int, int] | None = None,
+    max_pixels: int | None = None,
+    max_bytes: int | None = 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 = Image.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

src/ocrmypdf/languages.py

@@ -0,0 +1,849 @@
+# SPDX-FileCopyrightText: 2023 James R. Barlow
+# SPDX-License-Identifier: MPL-2.0
+
+"""Language codes and names from ISO 639.
+
+Derived from
+https://www.loc.gov/standards/iso639-2/ascii_8bits.html
+"""
+
+
+from typing import NamedTuple
+
+
+class ISOCodeData(NamedTuple):
+    """Data for a single ISO 639 code."""
+    alt: str
+    alpha_2: str
+    english: str
+    french: str
+
+
+ISO_639_3 = {
+    'aar': ISOCodeData('', 'aa', 'Afar', 'afar'),
+    'abk': ISOCodeData('', 'ab', 'Abkhazian', 'abkhaze'),
+    'ace': ISOCodeData('', '', 'Achinese', 'aceh'),
+    'ach': ISOCodeData('', '', 'Acoli', 'acoli'),
+    'ada': ISOCodeData('', '', 'Adangme', 'adangme'),
+    'ady': ISOCodeData('', '', 'Adyghe; Adygei', 'adyghé'),
+    'afa': ISOCodeData(
+        '',
+        '',
+        'Afro-Asiatic languages',
+        'afro-asiatiques, langues',
+    ),
+    'afh': ISOCodeData('', '', 'Afrihili', 'afrihili'),
+    'afr': ISOCodeData('', 'af', 'Afrikaans', 'afrikaans'),
+    'ain': ISOCodeData('', '', 'Ainu', 'aïnou'),
+    'aka': ISOCodeData('', 'ak', 'Akan', 'akan'),
+    'akk': ISOCodeData('', '', 'Akkadian', 'akkadien'),
+    'alb': ISOCodeData('sqi', 'sq', 'Albanian', 'albanais'),
+    'ale': ISOCodeData('', '', 'Aleut', 'aléoute'),
+    'alg': ISOCodeData(
+        '',
+        '',
+        'Algonquian languages',
+        'algonquines, langues',
+    ),
+    'alt': ISOCodeData('', '', 'Southern Altai', 'altai du Sud'),
+    'amh': ISOCodeData('', 'am', 'Amharic', 'amharique'),
+    'ang': ISOCodeData(
+        '',
+        '',
+        'English, Old (ca.450-1100)',
+        'anglo-saxon (ca.450-1100)',
+    ),
+    'anp': ISOCodeData('', '', 'Angika', 'angika'),
+    'apa': ISOCodeData('', '', 'Apache languages', 'apaches, langues'),
+    'ara': ISOCodeData('', 'ar', 'Arabic', 'arabe'),
+    'arc': ISOCodeData(
+        '',
+        '',
+        'Official Aramaic (700-300 BCE); Imperial Aramaic (700-300 BCE)',
+        "araméen d'empire (700-300 BCE)",
+    ),
+    'arg': ISOCodeData('', 'an', 'Aragonese', 'aragonais'),
+    'arm': ISOCodeData('hye', 'hy', 'Armenian', 'arménien'),
+    'arn': ISOCodeData(
+        '',
+        '',
+        'Mapudungun; Mapuche',
+        'mapudungun; mapuche; mapuce',
+    ),
+    'arp': ISOCodeData('', '', 'Arapaho', 'arapaho'),
+    'art': ISOCodeData(
+        '',
+        '',
+        'Artificial languages',
+        'artificielles, langues',
+    ),
+    'arw': ISOCodeData('', '', 'Arawak', 'arawak'),
+    'asm': ISOCodeData('', 'as', 'Assamese', 'assamais'),
+    'ast': ISOCodeData(
+        '',
+        '',
+        'Asturian; Bable; Leonese; Asturleonese',
+        'asturien; bable; léonais; asturoléonais',
+    ),
+    'ath': ISOCodeData(
+        '',
+        '',
+        'Athapascan languages',
+        'athapascanes, langues',
+    ),
+    'aus': ISOCodeData(
+        '',
+        '',
+        'Australian languages',
+        'australiennes, langues',
+    ),
+    'ava': ISOCodeData('', 'av', 'Avaric', 'avar'),
+    'ave': ISOCodeData('', 'ae', 'Avestan', 'avestique'),
+    'awa': ISOCodeData('', '', 'Awadhi', 'awadhi'),
+    'aym': ISOCodeData('', 'ay', 'Aymara', 'aymara'),
+    'aze': ISOCodeData('', 'az', 'Azerbaijani', 'azéri'),
+    'bad': ISOCodeData('', '', 'Banda languages', 'banda, langues'),
+    'bai': ISOCodeData('', '', 'Bamileke languages', 'bamiléké, langues'),
+    'bak': ISOCodeData('', 'ba', 'Bashkir', 'bachkir'),
+    'bal': ISOCodeData('', '', 'Baluchi', 'baloutchi'),
+    'bam': ISOCodeData('', 'bm', 'Bambara', 'bambara'),
+    'ban': ISOCodeData('', '', 'Balinese', 'balinais'),
+    'baq': ISOCodeData('eus', 'eu', 'Basque', 'basque'),
+    'bas': ISOCodeData('', '', 'Basa', 'basa'),
+    'bat': ISOCodeData('', '', 'Baltic languages', 'baltes, langues'),
+    'bej': ISOCodeData('', '', 'Beja; Bedawiyet', 'bedja'),
+    'bel': ISOCodeData('', 'be', 'Belarusian', 'biélorusse'),
+    'bem': ISOCodeData('', '', 'Bemba', 'bemba'),
+    'ben': ISOCodeData('', 'bn', 'Bengali', 'bengali'),
+    'ber': ISOCodeData('', '', 'Berber languages', 'berbères, langues'),
+    'bho': ISOCodeData('', '', 'Bhojpuri', 'bhojpuri'),
+    'bih': ISOCodeData('', 'bh', 'Bihari languages', 'langues biharis'),
+    'bik': ISOCodeData('', '', 'Bikol', 'bikol'),
+    'bin': ISOCodeData('', '', 'Bini; Edo', 'bini; edo'),
+    'bis': ISOCodeData('', 'bi', 'Bislama', 'bichlamar'),
+    'bla': ISOCodeData('', '', 'Siksika', 'blackfoot'),
+    'bnt': ISOCodeData('', '', 'Bantu languages', 'bantou, langues'),
+    'bos': ISOCodeData('', 'bs', 'Bosnian', 'bosniaque'),
+    'bra': ISOCodeData('', '', 'Braj', 'braj'),
+    'bre': ISOCodeData('', 'br', 'Breton', 'breton'),
+    'btk': ISOCodeData('', '', 'Batak languages', 'batak, langues'),
+    'bua': ISOCodeData('', '', 'Buriat', 'bouriate'),
+    'bug': ISOCodeData('', '', 'Buginese', 'bugi'),
+    'bul': ISOCodeData('', 'bg', 'Bulgarian', 'bulgare'),
+    'bur': ISOCodeData('mya', 'my', 'Burmese', 'birman'),
+    'byn': ISOCodeData('', '', 'Blin; Bilin', 'blin; bilen'),
+    'cad': ISOCodeData('', '', 'Caddo', 'caddo'),
+    'cai': ISOCodeData(
+        '',
+        '',
+        'Central American Indian languages',
+        "amérindiennes de L'Amérique centrale, langues",
+    ),
+    'car': ISOCodeData('', '', 'Galibi Carib', 'karib; galibi; carib'),
+    'cat': ISOCodeData('', 'ca', 'Catalan; Valencian', 'catalan; valencien'),
+    'cau': ISOCodeData(
+        '',
+        '',
+        'Caucasian languages',
+        'caucasiennes, langues',
+    ),
+    'ceb': ISOCodeData('', '', 'Cebuano', 'cebuano'),
+    'cel': ISOCodeData(
+        '',
+        '',
+        'Celtic languages',
+        'celtiques, langues; celtes, langues',
+    ),
+    'cha': ISOCodeData('', 'ch', 'Chamorro', 'chamorro'),
+    'chb': ISOCodeData('', '', 'Chibcha', 'chibcha'),
+    'che': ISOCodeData('', 'ce', 'Chechen', 'tchétchène'),
+    'chg': ISOCodeData('', '', 'Chagatai', 'djaghataï'),
+    'chi': ISOCodeData('zho', 'zh', 'Chinese', 'chinois'),
+    'chk': ISOCodeData('', '', 'Chuukese', 'chuuk'),
+    'chm': ISOCodeData('', '', 'Mari', 'mari'),
+    'chn': ISOCodeData('', '', 'Chinook jargon', 'chinook, jargon'),
+    'cho': ISOCodeData('', '', 'Choctaw', 'choctaw'),
+    'chp': ISOCodeData('', '', 'Chipewyan; Dene Suline', 'chipewyan'),
+    'chr': ISOCodeData('', '', 'Cherokee', 'cherokee'),
+    'chu': ISOCodeData(
+        '',
+        'cu',
+        ('Church Slavic; Old Slavonic; Church Slavonic;'
+         ' Old Bulgarian; Old Church Slavonic'),
+        "slavon d'église; vieux slave; slavon liturgique; vieux bulgare",
+    ),
+    'chv': ISOCodeData('', 'cv', 'Chuvash', 'tchouvache'),
+    'chy': ISOCodeData('', '', 'Cheyenne', 'cheyenne'),
+    'cmc': ISOCodeData('', '', 'Chamic languages', 'chames, langues'),
+    'cnr': ISOCodeData('', '', 'Montenegrin', 'monténégrin'),
+    'cop': ISOCodeData('', '', 'Coptic', 'copte'),
+    'cor': ISOCodeData('', 'kw', 'Cornish', 'cornique'),
+    'cos': ISOCodeData('', 'co', 'Corsican', 'corse'),
+    'cpe': ISOCodeData(
+        '',
+        '',
+        'Creoles and pidgins, English based',
+        "créoles et pidgins basés sur l'anglais",
+    ),
+    'cpf': ISOCodeData(
+        '',
+        '',
+        'Creoles and pidgins, French-based',
+        'créoles et pidgins basés sur le français',
+    ),
+    'cpp': ISOCodeData(
+        '',
+        '',
+        'Creoles and pidgins, Portuguese-based',
+        'créoles et pidgins basés sur le portugais',
+    ),
+    'cre': ISOCodeData('', 'cr', 'Cree', 'cree'),
+    'crh': ISOCodeData(
+        '',
+        '',
+        'Crimean Tatar; Crimean Turkish',
+        'tatar de Crimé',
+    ),
+    'crp': ISOCodeData('', '', 'Creoles and pidgins', 'créoles et pidgins'),
+    'csb': ISOCodeData('', '', 'Kashubian', 'kachoube'),
+    'cus': ISOCodeData('', '', 'Cushitic languages', 'couchitiques, langues'),
+    'cze': ISOCodeData('ces', 'cs', 'Czech', 'tchèque'),
+    'dak': ISOCodeData('', '', 'Dakota', 'dakota'),
+    'dan': ISOCodeData('', 'da', 'Danish', 'danois'),
+    'dar': ISOCodeData('', '', 'Dargwa', 'dargwa'),
+    'day': ISOCodeData('', '', 'Land Dayak languages', 'dayak, langues'),
+    'del': ISOCodeData('', '', 'Delaware', 'delaware'),
+    'den': ISOCodeData('', '', 'Slave (Athapascan)', 'esclave (athapascan)'),
+    'dgr': ISOCodeData('', '', 'Dogrib', 'dogrib'),
+    'din': ISOCodeData('', '', 'Dinka', 'dinka'),
+    'div': ISOCodeData('', 'dv', 'Divehi; Dhivehi; Maldivian', 'maldivien'),
+    'doi': ISOCodeData('', '', 'Dogri', 'dogri'),
+    'dra': ISOCodeData(
+        '',
+        '',
+        'Dravidian languages',
+        'dravidiennes, langues',
+    ),
+    'dsb': ISOCodeData('', '', 'Lower Sorbian', 'bas-sorabe'),
+    'dua': ISOCodeData('', '', 'Duala', 'douala'),
+    'dum': ISOCodeData(
+        '',
+        '',
+        'Dutch, Middle (ca.1050-1350)',
+        'néerlandais moyen (ca. 1050-1350)',
+    ),
+    'dut': ISOCodeData('nld', 'nl', 'Dutch; Flemish', 'néerlandais; flamand'),
+    'dyu': ISOCodeData('', '', 'Dyula', 'dioula'),
+    'dzo': ISOCodeData('', 'dz', 'Dzongkha', 'dzongkha'),
+    'efi': ISOCodeData('', '', 'Efik', 'efik'),
+    'egy': ISOCodeData('', '', 'Egyptian (Ancient)', 'égyptien'),
+    'eka': ISOCodeData('', '', 'Ekajuk', 'ekajuk'),
+    'elx': ISOCodeData('', '', 'Elamite', 'élamite'),
+    'eng': ISOCodeData('', 'en', 'English', 'anglais'),
+    'enm': ISOCodeData(
+        '',
+        '',
+        'English, Middle (1100-1500)',
+        'anglais moyen (1100-1500)',
+    ),
+    'epo': ISOCodeData('', 'eo', 'Esperanto', 'espéranto'),
+    'est': ISOCodeData('', 'et', 'Estonian', 'estonien'),
+    'ewe': ISOCodeData('', 'ee', 'Ewe', 'éwé'),
+    'ewo': ISOCodeData('', '', 'Ewondo', 'éwondo'),
+    'fan': ISOCodeData('', '', 'Fang', 'fang'),
+    'fao': ISOCodeData('', 'fo', 'Faroese', 'féroïen'),
+    'fat': ISOCodeData('', '', 'Fanti', 'fanti'),
+    'fij': ISOCodeData('', 'fj', 'Fijian', 'fidjien'),
+    'fil': ISOCodeData('', '', 'Filipino; Pilipino', 'filipino; pilipino'),
+    'fin': ISOCodeData('', 'fi', 'Finnish', 'finnois'),
+    'fiu': ISOCodeData(
+        '',
+        '',
+        'Finno-Ugrian languages',
+        'finno-ougriennes, langues',
+    ),
+    'fon': ISOCodeData('', '', 'Fon', 'fon'),
+    'fre': ISOCodeData('fra', 'fr', 'French', 'français'),
+    'frm': ISOCodeData(
+        '',
+        '',
+        'French, Middle (ca.1400-1600)',
+        'français moyen (1400-1600)',
+    ),
+    'fro': ISOCodeData(
+        '',
+        '',
+        'French, Old (842-ca.1400)',
+        'français ancien (842-ca.1400)',
+    ),
+    'frr': ISOCodeData('', '', 'Northern Frisian', 'frison septentrional'),
+    'frs': ISOCodeData('', '', 'Eastern Frisian', 'frison oriental'),
+    'fry': ISOCodeData('', 'fy', 'Western Frisian', 'frison occidental'),
+    'ful': ISOCodeData('', 'ff', 'Fulah', 'peul'),
+    'fur': ISOCodeData('', '', 'Friulian', 'frioulan'),
+    'gaa': ISOCodeData('', '', 'Ga', 'ga'),
+    'gay': ISOCodeData('', '', 'Gayo', 'gayo'),
+    'gba': ISOCodeData('', '', 'Gbaya', 'gbaya'),
+    'gem': ISOCodeData('', '', 'Germanic languages', 'germaniques, langues'),
+    'geo': ISOCodeData('kat', 'ka', 'Georgian', 'géorgien'),
+    'ger': ISOCodeData('deu', 'de', 'German', 'allemand'),
+    'gez': ISOCodeData('', '', 'Geez', 'guèze'),
+    'gil': ISOCodeData('', '', 'Gilbertese', 'kiribati'),
+    'gla': ISOCodeData(
+        '',
+        'gd',
+        'Gaelic; Scottish Gaelic',
+        'gaélique; gaélique écossais',
+    ),
+    'gle': ISOCodeData('', 'ga', 'Irish', 'irlandais'),
+    'glg': ISOCodeData('', 'gl', 'Galician', 'galicien'),
+    'glv': ISOCodeData('', 'gv', 'Manx', 'manx; mannois'),
+    'gmh': ISOCodeData(
+        '',
+        '',
+        'German, Middle High (ca.1050-1500)',
+        'allemand, moyen haut (ca. 1050-1500)',
+    ),
+    'goh': ISOCodeData(
+        '',
+        '',
+        'German, Old High (ca.750-1050)',
+        'allemand, vieux haut (ca. 750-1050)',
+    ),
+    'gon': ISOCodeData('', '', 'Gondi', 'gond'),
+    'gor': ISOCodeData('', '', 'Gorontalo', 'gorontalo'),
+    'got': ISOCodeData('', '', 'Gothic', 'gothique'),
+    'grb': ISOCodeData('', '', 'Grebo', 'grebo'),
+    'grc': ISOCodeData(
+        '',
+        '',
+        'Greek, Ancient (to 1453)',
+        "grec ancien (jusqu'à 1453)",
+    ),
+    'gre': ISOCodeData(
+        'ell',
+        'el',
+        'Greek, Modern (1453-)',
+        'grec moderne (après 1453)',
+    ),
+    'grn': ISOCodeData('', 'gn', 'Guarani', 'guarani'),
+    'gsw': ISOCodeData(
+        '',
+        '',
+        'Swiss German; Alemannic; Alsatian',
+        'suisse alémanique; alémanique; alsacien',
+    ),
+    'guj': ISOCodeData('', 'gu', 'Gujarati', 'goudjrati'),
+    'gwi': ISOCodeData('', '', "Gwich'in", "gwich'in"),
+    'hai': ISOCodeData('', '', 'Haida', 'haida'),
+    'hat': ISOCodeData(
+        '',
+        'ht',
+        'Haitian; Haitian Creole',
+        'haïtien; créole haïtien',
+    ),
+    'hau': ISOCodeData('', 'ha', 'Hausa', 'haoussa'),
+    'haw': ISOCodeData('', '', 'Hawaiian', 'hawaïen'),
+    'heb': ISOCodeData('', 'he', 'Hebrew', 'hébreu'),
+    'her': ISOCodeData('', 'hz', 'Herero', 'herero'),
+    'hil': ISOCodeData('', '', 'Hiligaynon', 'hiligaynon'),
+    'him': ISOCodeData(
+        '',
+        '',
+        'Himachali languages; Western Pahari languages',
+        'langues himachalis; langues paharis occidentales',
+    ),
+    'hin': ISOCodeData('', 'hi', 'Hindi', 'hindi'),
+    'hit': ISOCodeData('', '', 'Hittite', 'hittite'),
+    'hmn': ISOCodeData('', '', 'Hmong; Mong', 'hmong'),
+    'hmo': ISOCodeData('', 'ho', 'Hiri Motu', 'hiri motu'),
+    'hrv': ISOCodeData('', 'hr', 'Croatian', 'croate'),
+    'hsb': ISOCodeData('', '', 'Upper Sorbian', 'haut-sorabe'),
+    'hun': ISOCodeData('', 'hu', 'Hungarian', 'hongrois'),
+    'hup': ISOCodeData('', '', 'Hupa', 'hupa'),
+    'iba': ISOCodeData('', '', 'Iban', 'iban'),
+    'ibo': ISOCodeData('', 'ig', 'Igbo', 'igbo'),
+    'ice': ISOCodeData('isl', 'is', 'Icelandic', 'islandais'),
+    'ido': ISOCodeData('', 'io', 'Ido', 'ido'),
+    'iii': ISOCodeData('', 'ii', 'Sichuan Yi; Nuosu', 'yi de Sichuan'),
+    'ijo': ISOCodeData('', '', 'Ijo languages', 'ijo, langues'),
+    'iku': ISOCodeData('', 'iu', 'Inuktitut', 'inuktitut'),
+    'ile': ISOCodeData('', 'ie', 'Interlingue; Occidental', 'interlingue'),
+    'ilo': ISOCodeData('', '', 'Iloko', 'ilocano'),
+    'ina': ISOCodeData(
+        '',
+        'ia',
+        'Interlingua (International Auxiliary Language Association)',
+        'interlingua (langue auxiliaire internationale)',
+    ),
+    'inc': ISOCodeData('', '', 'Indic languages', 'indo-aryennes, langues'),
+    'ind': ISOCodeData('', 'id', 'Indonesian', 'indonésien'),
+    'ine': ISOCodeData(
+        '',
+        '',
+        'Indo-European languages',
+        'indo-européennes, langues',
+    ),
+    'inh': ISOCodeData('', '', 'Ingush', 'ingouche'),
+    'ipk': ISOCodeData('', 'ik', 'Inupiaq', 'inupiaq'),
+    'ira': ISOCodeData('', '', 'Iranian languages', 'iraniennes, langues'),
+    'iro': ISOCodeData('', '', 'Iroquoian languages', 'iroquoises, langues'),
+    'ita': ISOCodeData('', 'it', 'Italian', 'italien'),
+    'jav': ISOCodeData('', 'jv', 'Javanese', 'javanais'),
+    'jbo': ISOCodeData('', '', 'Lojban', 'lojban'),
+    'jpn': ISOCodeData('', 'ja', 'Japanese', 'japonais'),
+    'jpr': ISOCodeData('', '', 'Judeo-Persian', 'judéo-persan'),
+    'jrb': ISOCodeData('', '', 'Judeo-Arabic', 'judéo-arabe'),
+    'kaa': ISOCodeData('', '', 'Kara-Kalpak', 'karakalpak'),
+    'kab': ISOCodeData('', '', 'Kabyle', 'kabyle'),
+    'kac': ISOCodeData('', '', 'Kachin; Jingpho', 'kachin; jingpho'),
+    'kal': ISOCodeData('', 'kl', 'Kalaallisut; Greenlandic', 'groenlandais'),
+    'kam': ISOCodeData('', '', 'Kamba', 'kamba'),
+    'kan': ISOCodeData('', 'kn', 'Kannada', 'kannada'),
+    'kar': ISOCodeData('', '', 'Karen languages', 'karen, langues'),
+    'kas': ISOCodeData('', 'ks', 'Kashmiri', 'kashmiri'),
+    'kau': ISOCodeData('', 'kr', 'Kanuri', 'kanouri'),
+    'kaw': ISOCodeData('', '', 'Kawi', 'kawi'),
+    'kaz': ISOCodeData('', 'kk', 'Kazakh', 'kazakh'),
+    'kbd': ISOCodeData('', '', 'Kabardian', 'kabardien'),
+    'kha': ISOCodeData('', '', 'Khasi', 'khasi'),
+    'khi': ISOCodeData('', '', 'Khoisan languages', 'khoïsan, langues'),
+    'khm': ISOCodeData('', 'km', 'Central Khmer', 'khmer central'),
+    'kho': ISOCodeData('', '', 'Khotanese; Sakan', 'khotanais; sakan'),
+    'kik': ISOCodeData('', 'ki', 'Kikuyu; Gikuyu', 'kikuyu'),
+    'kin': ISOCodeData('', 'rw', 'Kinyarwanda', 'rwanda'),
+    'kir': ISOCodeData('', 'ky', 'Kirghiz; Kyrgyz', 'kirghiz'),
+    'kmb': ISOCodeData('', '', 'Kimbundu', 'kimbundu'),
+    'kok': ISOCodeData('', '', 'Konkani', 'konkani'),
+    'kom': ISOCodeData('', 'kv', 'Komi', 'kom'),
+    'kon': ISOCodeData('', 'kg', 'Kongo', 'kongo'),
+    'kor': ISOCodeData('', 'ko', 'Korean', 'coréen'),
+    'kos': ISOCodeData('', '', 'Kosraean', 'kosrae'),
+    'kpe': ISOCodeData('', '', 'Kpelle', 'kpellé'),
+    'krc': ISOCodeData('', '', 'Karachay-Balkar', 'karatchai balkar'),
+    'krl': ISOCodeData('', '', 'Karelian', 'carélien'),
+    'kro': ISOCodeData('', '', 'Kru languages', 'krou, langues'),
+    'kru': ISOCodeData('', '', 'Kurukh', 'kurukh'),
+    'kua': ISOCodeData('', 'kj', 'Kuanyama; Kwanyama', 'kuanyama; kwanyama'),
+    'kum': ISOCodeData('', '', 'Kumyk', 'koumyk'),
+    'kur': ISOCodeData('', 'ku', 'Kurdish', 'kurde'),
+    'kut': ISOCodeData('', '', 'Kutenai', 'kutenai'),
+    'lad': ISOCodeData('', '', 'Ladino', 'judéo-espagnol'),
+    'lah': ISOCodeData('', '', 'Lahnda', 'lahnda'),
+    'lam': ISOCodeData('', '', 'Lamba', 'lamba'),
+    'lao': ISOCodeData('', 'lo', 'Lao', 'lao'),
+    'lat': ISOCodeData('', 'la', 'Latin', 'latin'),
+    'lav': ISOCodeData('', 'lv', 'Latvian', 'letton'),
+    'lez': ISOCodeData('', '', 'Lezghian', 'lezghien'),
+    'lim': ISOCodeData(
+        '',
+        'li',
+        'Limburgan; Limburger; Limburgish',
+        'limbourgeois',
+    ),
+    'lin': ISOCodeData('', 'ln', 'Lingala', 'lingala'),
+    'lit': ISOCodeData('', 'lt', 'Lithuanian', 'lituanien'),
+    'lol': ISOCodeData('', '', 'Mongo', 'mongo'),
+    'loz': ISOCodeData('', '', 'Lozi', 'lozi'),
+    'ltz': ISOCodeData(
+        '',
+        'lb',
+        'Luxembourgish; Letzeburgesch',
+        'luxembourgeois',
+    ),
+    'lua': ISOCodeData('', '', 'Luba-Lulua', 'luba-lulua'),
+    'lub': ISOCodeData('', 'lu', 'Luba-Katanga', 'luba-katanga'),
+    'lug': ISOCodeData('', 'lg', 'Ganda', 'ganda'),
+    'lui': ISOCodeData('', '', 'Luiseno', 'luiseno'),
+    'lun': ISOCodeData('', '', 'Lunda', 'lunda'),
+    'luo': ISOCodeData(
+        '',
+        '',
+        'Luo (Kenya and Tanzania)',
+        'luo (Kenya et Tanzanie)',
+    ),
+    'lus': ISOCodeData('', '', 'Lushai', 'lushai'),
+    'mac': ISOCodeData('mkd', 'mk', 'Macedonian', 'macédonien'),
+    'mad': ISOCodeData('', '', 'Madurese', 'madourais'),
+    'mag': ISOCodeData('', '', 'Magahi', 'magahi'),
+    'mah': ISOCodeData('', 'mh', 'Marshallese', 'marshall'),
+    'mai': ISOCodeData('', '', 'Maithili', 'maithili'),
+    'mak': ISOCodeData('', '', 'Makasar', 'makassar'),
+    'mal': ISOCodeData('', 'ml', 'Malayalam', 'malayalam'),
+    'man': ISOCodeData('', '', 'Mandingo', 'mandingue'),
+    'mao': ISOCodeData('mri', 'mi', 'Maori', 'maori'),
+    'map': ISOCodeData(
+        '',
+        '',
+        'Austronesian languages',
+        'austronésiennes, langues',
+    ),
+    'mar': ISOCodeData('', 'mr', 'Marathi', 'marathe'),
+    'mas': ISOCodeData('', '', 'Masai', 'massaï'),
+    'may': ISOCodeData('msa', 'ms', 'Malay', 'malais'),
+    'mdf': ISOCodeData('', '', 'Moksha', 'moksa'),
+    'mdr': ISOCodeData('', '', 'Mandar', 'mandar'),
+    'men': ISOCodeData('', '', 'Mende', 'mendé'),
+    'mga': ISOCodeData(
+        '',
+        '',
+        'Irish, Middle (900-1200)',
+        'irlandais moyen (900-1200)',
+    ),
+    'mic': ISOCodeData('', '', "Mi'kmaq; Micmac", "mi'kmaq; micmac"),
+    'min': ISOCodeData('', '', 'Minangkabau', 'minangkabau'),
+    'mis': ISOCodeData('', '', 'Uncoded languages', 'langues non codées'),
+    'mkh': ISOCodeData('', '', 'Mon-Khmer languages', 'môn-khmer, langues'),
+    'mlg': ISOCodeData('', 'mg', 'Malagasy', 'malgache'),
+    'mlt': ISOCodeData('', 'mt', 'Maltese', 'maltais'),
+    'mnc': ISOCodeData('', '', 'Manchu', 'mandchou'),
+    'mni': ISOCodeData('', '', 'Manipuri', 'manipuri'),
+    'mno': ISOCodeData('', '', 'Manobo languages', 'manobo, langues'),
+    'moh': ISOCodeData('', '', 'Mohawk', 'mohawk'),
+    'mon': ISOCodeData('', 'mn', 'Mongolian', 'mongol'),
+    'mos': ISOCodeData('', '', 'Mossi', 'moré'),
+    'mul': ISOCodeData('', '', 'Multiple languages', 'multilingue'),
+    'mun': ISOCodeData('', '', 'Munda languages', 'mounda, langues'),
+    'mus': ISOCodeData('', '', 'Creek', 'muskogee'),
+    'mwl': ISOCodeData('', '', 'Mirandese', 'mirandais'),
+    'mwr': ISOCodeData('', '', 'Marwari', 'marvari'),
+    'myn': ISOCodeData('', '', 'Mayan languages', 'maya, langues'),
+    'myv': ISOCodeData('', '', 'Erzya', 'erza'),
+    'nah': ISOCodeData('', '', 'Nahuatl languages', 'nahuatl, langues'),
+    'nai': ISOCodeData(
+        '',
+        '',
+        'North American Indian languages',
+        'nord-amérindiennes, langues',
+    ),
+    'nap': ISOCodeData('', '', 'Neapolitan', 'napolitain'),
+    'nau': ISOCodeData('', 'na', 'Nauru', 'nauruan'),
+    'nav': ISOCodeData('', 'nv', 'Navajo; Navaho', 'navaho'),
+    'nbl': ISOCodeData(
+        '',
+        'nr',
+        'Ndebele, South; South Ndebele',
+        'ndébélé du Sud',
+    ),
+    'nde': ISOCodeData(
+        '',
+        'nd',
+        'Ndebele, North; North Ndebele',
+        'ndébélé du Nord',
+    ),
+    'ndo': ISOCodeData('', 'ng', 'Ndonga', 'ndonga'),
+    'nds': ISOCodeData(
+        '',
+        '',
+        'Low German; Low Saxon; German, Low; Saxon, Low',
+        'bas allemand; bas saxon; allemand, bas; saxon, bas',
+    ),
+    'nep': ISOCodeData('', 'ne', 'Nepali', 'népalais'),
+    'new': ISOCodeData('', '', 'Nepal Bhasa; Newari', 'nepal bhasa; newari'),
+    'nia': ISOCodeData('', '', 'Nias', 'nias'),
+    'nic': ISOCodeData(
+        '',
+        '',
+        'Niger-Kordofanian languages',
+        'nigéro-kordofaniennes, langues',
+    ),
+    'niu': ISOCodeData('', '', 'Niuean', 'niué'),
+    'nno': ISOCodeData(
+        '',
+        'nn',
+        'Norwegian Nynorsk; Nynorsk, Norwegian',
+        'norvégien nynorsk; nynorsk, norvégien',
+    ),
+    'nob': ISOCodeData(
+        '',
+        'nb',
+        'Bokmål, Norwegian; Norwegian Bokmål',
+        'norvégien bokmål',
+    ),
+    'nog': ISOCodeData('', '', 'Nogai', 'nogaï; nogay'),
+    'non': ISOCodeData('', '', 'Norse, Old', 'norrois, vieux'),
+    'nor': ISOCodeData('', 'no', 'Norwegian', 'norvégien'),
+    'nqo': ISOCodeData('', '', "N'Ko", "n'ko"),
+    'nso': ISOCodeData(
+        '',
+        '',
+        'Pedi; Sepedi; Northern Sotho',
+        'pedi; sepedi; sotho du Nord',
+    ),
+    'nub': ISOCodeData('', '', 'Nubian languages', 'nubiennes, langues'),
+    'nwc': ISOCodeData(
+        '',
+        '',
+        'Classical Newari; Old Newari; Classical Nepal Bhasa',
+        'newari classique',
+    ),
+    'nya': ISOCodeData(
+        '',
+        'ny',
+        'Chichewa; Chewa; Nyanja',
+        'chichewa; chewa; nyanja',
+    ),
+    'nym': ISOCodeData('', '', 'Nyamwezi', 'nyamwezi'),
+    'nyn': ISOCodeData('', '', 'Nyankole', 'nyankolé'),
+    'nyo': ISOCodeData('', '', 'Nyoro', 'nyoro'),
+    'nzi': ISOCodeData('', '', 'Nzima', 'nzema'),
+    'oci': ISOCodeData(
+        '',
+        'oc',
+        'Occitan (post 1500)',
+        'occitan (après 1500)',
+    ),
+    'oji': ISOCodeData('', 'oj', 'Ojibwa', 'ojibwa'),
+    'ori': ISOCodeData('', 'or', 'Oriya', 'oriya'),
+    'orm': ISOCodeData('', 'om', 'Oromo', 'galla'),
+    'osa': ISOCodeData('', '', 'Osage', 'osage'),
+    'oss': ISOCodeData('', 'os', 'Ossetian; Ossetic', 'ossète'),
+    'ota': ISOCodeData(
+        '',
+        '',
+        'Turkish, Ottoman (1500-1928)',
+        'turc ottoman (1500-1928)',
+    ),
+    'oto': ISOCodeData('', '', 'Otomian languages', 'otomi, langues'),
+    'paa': ISOCodeData('', '', 'Papuan languages', 'papoues, langues'),
+    'pag': ISOCodeData('', '', 'Pangasinan', 'pangasinan'),
+    'pal': ISOCodeData('', '', 'Pahlavi', 'pahlavi'),
+    'pam': ISOCodeData('', '', 'Pampanga; Kapampangan', 'pampangan'),
+    'pan': ISOCodeData('', 'pa', 'Panjabi; Punjabi', 'pendjabi'),
+    'pap': ISOCodeData('', '', 'Papiamento', 'papiamento'),
+    'pau': ISOCodeData('', '', 'Palauan', 'palau'),
+    'peo': ISOCodeData(
+        '',
+        '',
+        'Persian, Old (ca.600-400 B.C.)',
+        'perse, vieux (ca. 600-400 av. J.-C.)',
+    ),
+    'per': ISOCodeData('fas', 'fa', 'Persian', 'persan'),
+    'phi': ISOCodeData(
+        '',
+        '',
+        'Philippine languages',
+        'philippines, langues',
+    ),
+    'phn': ISOCodeData('', '', 'Phoenician', 'phénicien'),
+    'pli': ISOCodeData('', 'pi', 'Pali', 'pali'),
+    'pol': ISOCodeData('', 'pl', 'Polish', 'polonais'),
+    'pon': ISOCodeData('', '', 'Pohnpeian', 'pohnpei'),
+    'por': ISOCodeData('', 'pt', 'Portuguese', 'portugais'),
+    'pra': ISOCodeData('', '', 'Prakrit languages', 'prâkrit, langues'),
+    'pro': ISOCodeData(
+        '',
+        '',
+        'Provençal, Old (to 1500); Occitan, Old (to 1500)',
+        "provençal ancien (jusqu'à 1500); occitan ancien (jusqu'à 1500)",
+    ),
+    'pus': ISOCodeData('', 'ps', 'Pushto; Pashto', 'pachto'),
+    'qaa': ISOCodeData(
+        '',
+        '',
+        'Reserved for local use',
+        "réservée à l'usage local",
+    ),
+    'que': ISOCodeData('', 'qu', 'Quechua', 'quechua'),
+    'raj': ISOCodeData('', '', 'Rajasthani', 'rajasthani'),
+    'rap': ISOCodeData('', '', 'Rapanui', 'rapanui'),
+    'rar': ISOCodeData(
+        '',
+        '',
+        'Rarotongan; Cook Islands Maori',
+        'rarotonga; maori des îles Cook',
+    ),
+    'roa': ISOCodeData('', '', 'Romance languages', 'romanes, langues'),
+    'roh': ISOCodeData('', 'rm', 'Romansh', 'romanche'),
+    'rom': ISOCodeData('', '', 'Romany', 'tsigane'),
+    'rum': ISOCodeData(
+        'ron',
+        'ro',
+        'Romanian; Moldavian; Moldovan',
+        'roumain; moldave',
+    ),
+    'run': ISOCodeData('', 'rn', 'Rundi', 'rundi'),
+    'rup': ISOCodeData(
+        '',
+        '',
+        'Aromanian; Arumanian; Macedo-Romanian',
+        'aroumain; macédo-roumain',
+    ),
+    'rus': ISOCodeData('', 'ru', 'Russian', 'russe'),
+    'sad': ISOCodeData('', '', 'Sandawe', 'sandawe'),
+    'sag': ISOCodeData('', 'sg', 'Sango', 'sango'),
+    'sah': ISOCodeData('', '', 'Yakut', 'iakoute'),
+    'sai': ISOCodeData(
+        '',
+        '',
+        'South American Indian languages',
+        'sud-amérindiennes, langues',
+    ),
+    'sal': ISOCodeData('', '', 'Salishan languages', 'salishennes, langues'),
+    'sam': ISOCodeData('', '', 'Samaritan Aramaic', 'samaritain'),
+    'san': ISOCodeData('', 'sa', 'Sanskrit', 'sanskrit'),
+    'sas': ISOCodeData('', '', 'Sasak', 'sasak'),
+    'sat': ISOCodeData('', '', 'Santali', 'santal'),
+    'scn': ISOCodeData('', '', 'Sicilian', 'sicilien'),
+    'sco': ISOCodeData('', '', 'Scots', 'écossais'),
+    'sel': ISOCodeData('', '', 'Selkup', 'selkoupe'),
+    'sem': ISOCodeData('', '', 'Semitic languages', 'sémitiques, langues'),
+    'sga': ISOCodeData(
+        '',
+        '',
+        'Irish, Old (to 900)',
+        "irlandais ancien (jusqu'à 900)",
+    ),
+    'sgn': ISOCodeData('', '', 'Sign Languages', 'langues des signes'),
+    'shn': ISOCodeData('', '', 'Shan', 'chan'),
+    'sid': ISOCodeData('', '', 'Sidamo', 'sidamo'),
+    'sin': ISOCodeData('', 'si', 'Sinhala; Sinhalese', 'singhalais'),
+    'sio': ISOCodeData('', '', 'Siouan languages', 'sioux, langues'),
+    'sit': ISOCodeData(
+        '',
+        '',
+        'Sino-Tibetan languages',
+        'sino-tibétaines, langues',
+    ),
+    'sla': ISOCodeData('', '', 'Slavic languages', 'slaves, langues'),
+    'slo': ISOCodeData('slk', 'sk', 'Slovak', 'slovaque'),
+    'slv': ISOCodeData('', 'sl', 'Slovenian', 'slovène'),
+    'sma': ISOCodeData('', '', 'Southern Sami', 'sami du Sud'),
+    'sme': ISOCodeData('', 'se', 'Northern Sami', 'sami du Nord'),
+    'smi': ISOCodeData('', '', 'Sami languages', 'sames, langues'),
+    'smj': ISOCodeData('', '', 'Lule Sami', 'sami de Lule'),
+    'smn': ISOCodeData('', '', 'Inari Sami', "sami d'Inari"),
+    'smo': ISOCodeData('', 'sm', 'Samoan', 'samoan'),
+    'sms': ISOCodeData('', '', 'Skolt Sami', 'sami skolt'),
+    'sna': ISOCodeData('', 'sn', 'Shona', 'shona'),
+    'snd': ISOCodeData('', 'sd', 'Sindhi', 'sindhi'),
+    'snk': ISOCodeData('', '', 'Soninke', 'soninké'),
+    'sog': ISOCodeData('', '', 'Sogdian', 'sogdien'),
+    'som': ISOCodeData('', 'so', 'Somali', 'somali'),
+    'son': ISOCodeData('', '', 'Songhai languages', 'songhai, langues'),
+    'sot': ISOCodeData('', 'st', 'Sotho, Southern', 'sotho du Sud'),
+    'spa': ISOCodeData('', 'es', 'Spanish; Castilian', 'espagnol; castillan'),
+    'srd': ISOCodeData('', 'sc', 'Sardinian', 'sarde'),
+    'srn': ISOCodeData('', '', 'Sranan Tongo', 'sranan tongo'),
+    'srp': ISOCodeData('', 'sr', 'Serbian', 'serbe'),
+    'srr': ISOCodeData('', '', 'Serer', 'sérère'),
+    'ssa': ISOCodeData(
+        '',
+        '',
+        'Nilo-Saharan languages',
+        'nilo-sahariennes, langues',
+    ),
+    'ssw': ISOCodeData('', 'ss', 'Swati', 'swati'),
+    'suk': ISOCodeData('', '', 'Sukuma', 'sukuma'),
+    'sun': ISOCodeData('', 'su', 'Sundanese', 'soundanais'),
+    'sus': ISOCodeData('', '', 'Susu', 'soussou'),
+    'sux': ISOCodeData('', '', 'Sumerian', 'sumérien'),
+    'swa': ISOCodeData('', 'sw', 'Swahili', 'swahili'),
+    'swe': ISOCodeData('', 'sv', 'Swedish', 'suédois'),
+    'syc': ISOCodeData('', '', 'Classical Syriac', 'syriaque classique'),
+    'syr': ISOCodeData('', '', 'Syriac', 'syriaque'),
+    'tah': ISOCodeData('', 'ty', 'Tahitian', 'tahitien'),
+    'tai': ISOCodeData('', '', 'Tai languages', 'tai, langues'),
+    'tam': ISOCodeData('', 'ta', 'Tamil', 'tamoul'),
+    'tat': ISOCodeData('', 'tt', 'Tatar', 'tatar'),
+    'tel': ISOCodeData('', 'te', 'Telugu', 'télougou'),
+    'tem': ISOCodeData('', '', 'Timne', 'temne'),
+    'ter': ISOCodeData('', '', 'Tereno', 'tereno'),
+    'tet': ISOCodeData('', '', 'Tetum', 'tetum'),
+    'tgk': ISOCodeData('', 'tg', 'Tajik', 'tadjik'),
+    'tgl': ISOCodeData('', 'tl', 'Tagalog', 'tagalog'),
+    'tha': ISOCodeData('', 'th', 'Thai', 'thaï'),
+    'tib': ISOCodeData('bod', 'bo', 'Tibetan', 'tibétain'),
+    'tig': ISOCodeData('', '', 'Tigre', 'tigré'),
+    'tir': ISOCodeData('', 'ti', 'Tigrinya', 'tigrigna'),
+    'tiv': ISOCodeData('', '', 'Tiv', 'tiv'),
+    'tkl': ISOCodeData('', '', 'Tokelau', 'tokelau'),
+    'tlh': ISOCodeData('', '', 'Klingon; tlhIngan-Hol', 'klingon'),
+    'tli': ISOCodeData('', '', 'Tlingit', 'tlingit'),
+    'tmh': ISOCodeData('', '', 'Tamashek', 'tamacheq'),
+    'tog': ISOCodeData('', '', 'Tonga (Nyasa)', 'tonga (Nyasa)'),
+    'ton': ISOCodeData(
+        '',
+        'to',
+        'Tonga (Tonga Islands)',
+        'tongan (Îles Tonga)',
+    ),
+    'tpi': ISOCodeData('', '', 'Tok Pisin', 'tok pisin'),
+    'tsi': ISOCodeData('', '', 'Tsimshian', 'tsimshian'),
+    'tsn': ISOCodeData('', 'tn', 'Tswana', 'tswana'),
+    'tso': ISOCodeData('', 'ts', 'Tsonga', 'tsonga'),
+    'tuk': ISOCodeData('', 'tk', 'Turkmen', 'turkmène'),
+    'tum': ISOCodeData('', '', 'Tumbuka', 'tumbuka'),
+    'tup': ISOCodeData('', '', 'Tupi languages', 'tupi, langues'),
+    'tur': ISOCodeData('', 'tr', 'Turkish', 'turc'),
+    'tut': ISOCodeData('', '', 'Altaic languages', 'altaïques, langues'),
+    'tvl': ISOCodeData('', '', 'Tuvalu', 'tuvalu'),
+    'twi': ISOCodeData('', 'tw', 'Twi', 'twi'),
+    'tyv': ISOCodeData('', '', 'Tuvinian', 'touva'),
+    'udm': ISOCodeData('', '', 'Udmurt', 'oudmourte'),
+    'uga': ISOCodeData('', '', 'Ugaritic', 'ougaritique'),
+    'uig': ISOCodeData('', 'ug', 'Uighur; Uyghur', 'ouïgour'),
+    'ukr': ISOCodeData('', 'uk', 'Ukrainian', 'ukrainien'),
+    'umb': ISOCodeData('', '', 'Umbundu', 'umbundu'),
+    'und': ISOCodeData('', '', 'Undetermined', 'indéterminée'),
+    'urd': ISOCodeData('', 'ur', 'Urdu', 'ourdou'),
+    'uzb': ISOCodeData('', 'uz', 'Uzbek', 'ouszbek'),
+    'vai': ISOCodeData('', '', 'Vai', 'vaï'),
+    'ven': ISOCodeData('', 've', 'Venda', 'venda'),
+    'vie': ISOCodeData('', 'vi', 'Vietnamese', 'vietnamien'),
+    'vol': ISOCodeData('', 'vo', 'Volapük', 'volapük'),
+    'vot': ISOCodeData('', '', 'Votic', 'vote'),
+    'wak': ISOCodeData('', '', 'Wakashan languages', 'wakashanes, langues'),
+    'wal': ISOCodeData('', '', 'Wolaitta; Wolaytta', 'wolaitta; wolaytta'),
+    'war': ISOCodeData('', '', 'Waray', 'waray'),
+    'was': ISOCodeData('', '', 'Washo', 'washo'),
+    'wel': ISOCodeData('cym', 'cy', 'Welsh', 'gallois'),
+    'wen': ISOCodeData('', '', 'Sorbian languages', 'sorabes, langues'),
+    'wln': ISOCodeData('', 'wa', 'Walloon', 'wallon'),
+    'wol': ISOCodeData('', 'wo', 'Wolof', 'wolof'),
+    'xal': ISOCodeData('', '', 'Kalmyk; Oirat', 'kalmouk; oïrat'),
+    'xho': ISOCodeData('', 'xh', 'Xhosa', 'xhosa'),
+    'yao': ISOCodeData('', '', 'Yao', 'yao'),
+    'yap': ISOCodeData('', '', 'Yapese', 'yapois'),
+    'yid': ISOCodeData('', 'yi', 'Yiddish', 'yiddish'),
+    'yor': ISOCodeData('', 'yo', 'Yoruba', 'yoruba'),
+    'ypk': ISOCodeData('', '', 'Yupik languages', 'yupik, langues'),
+    'zap': ISOCodeData('', '', 'Zapotec', 'zapotèque'),
+    'zbl': ISOCodeData(
+        '',
+        '',
+        'Blissymbols; Blissymbolics; Bliss',
+        'symboles Bliss; Bliss',
+    ),
+    'zen': ISOCodeData('', '', 'Zenaga', 'zenaga'),
+    'zgh': ISOCodeData(
+        '',
+        '',
+        'Standard Moroccan Tamazight',
+        'amazighe standard marocain',
+    ),
+    'zha': ISOCodeData('', 'za', 'Zhuang; Chuang', 'zhuang; chuang'),
+    'znd': ISOCodeData('', '', 'Zande languages', 'zandé, langues'),
+    'zul': ISOCodeData('', 'zu', 'Zulu', 'zoulou'),
+    'zun': ISOCodeData('', '', 'Zuni', 'zuni'),
+    'zxx': ISOCodeData(
+        '',
+        '',
+        'No linguistic content; Not applicable',
+        'pas de contenu linguistique; non applicable',
+    ),
+    'zza': ISOCodeData(
+        '',
+        '',
+        'Zaza; Dimili; Dimli; Kirdki; Kirmanjki; Zazaki',
+        'zaza; dimili; dimli; kirdki; kirmanjki; zazaki',
+    ),
+}
+
+
+def iso_639_2_from_3(iso3: str) -> str:
+    """Convert ISO 639-3 code to ISO 639-2 code."""
+    if iso3 in ISO_639_3:
+        return ISO_639_3[iso3].alpha_2
+    else:
+        return ""

src/ocrmypdf/optimize.py

@@ -11,9 +11,11 @@ import sys
 import tempfile
 import threading
 from collections import defaultdict
+from collections.abc import Iterator, MutableSet, Sequence
 from os import fspath
 from pathlib import Path
-from typing import Callable, Iterator, MutableSet, NamedTuple, NewType, Sequence
+from typing import Any, Callable, NamedTuple, NewType
+from warnings import warn
 from zlib import compress
 
 import img2pdf
@@ -33,6 +35,7 @@ from PIL import Image
 from ocrmypdf._concurrent import Executor, SerialExecutor
 from ocrmypdf._exec import jbig2enc, pngquant
 from ocrmypdf._jobcontext import PdfContext
+from ocrmypdf._progressbar import ProgressBar
 from ocrmypdf.exceptions import OutputFileAccessError
 from ocrmypdf.helpers import IMG2PDF_KWARGS, safe_symlink
 
@@ -53,23 +56,24 @@ class XrefExt(NamedTuple):
 
 
 def img_name(root: Path, xref: Xref, ext: str) -> Path:
+    """Return the name of an image file for a given xref and extension."""
     return root / f'{xref:08d}{ext}'
 
 
 def png_name(root: Path, xref: Xref) -> Path:
+    """Return the name of a PNG file for a given xref."""
     return img_name(root, xref, '.png')
 
 
 def jpg_name(root: Path, xref: Xref) -> Path:
+    """Return the name of a JPEG file for a given xref."""
     return img_name(root, xref, '.jpg')
 
 
 def extract_image_filter(
-    pike: Pdf, root: Path, image: Stream, xref: Xref
+    image: Stream, xref: Xref
 ) -> tuple[PdfImage, tuple[Name, Object]] | None:
-    del pike  # unused args
+    """Determine if an image is extractable."""
-    del root
-
     if image.Subtype != Name.Image:
         return None
     if image.Length < 100:
@@ -122,11 +126,12 @@ def extract_image_filter(
 
 
 def extract_image_jbig2(
-    *, pike: Pdf, root: Path, image: Stream, xref: Xref, options
+    *, pdf: Pdf, root: Path, image: Stream, xref: Xref, options
 ) -> XrefExt | None:
+    """Extract an image, saving it as a JBIG2 file."""
     del options  # unused arg
 
-    result = extract_image_filter(pike, root, image, xref)
+    result = extract_image_filter(image, xref)
     if result is None:
         return None
     pim, filtdp = result
@@ -163,9 +168,10 @@ def extract_image_jbig2(
 
 
 def extract_image_generic(
-    *, pike: Pdf, root: Path, image: Stream, xref: Xref, options
+    *, pdf: Pdf, root: Path, image: Stream, xref: Xref, options
 ) -> XrefExt | None:
-    result = extract_image_filter(pike, root, image, xref)
+    """Generic image extraction."""
+    result = extract_image_filter(image, xref)
     if result is None:
         return None
     pim, filtdp = result
@@ -224,13 +230,72 @@ def extract_image_generic(
     return None
 
 
+def _find_image_xrefs_container(
+    pdf: Pdf,
+    container: Object,
+    pageno: int,
+    include_xrefs: MutableSet[Xref],
+    exclude_xrefs: MutableSet[Xref],
+    pageno_for_xref: dict[Xref, int],
+    depth: int = 0,
+):
+    """Find all image XRefs or Form XObject and add to the include/exclude sets."""
+    if depth > 10:
+        log.warning("Recursion depth exceeded in _find_image_xrefs_page")
+        return
+    try:
+        xobjs = container.Resources.XObject
+    except AttributeError:
+        return
+    for _imname, image in dict(xobjs).items():
+        if image.objgen[1] != 0:
+            continue  # Ignore images in an incremental PDF
+        if Name.Subtype in image and image.Subtype == Name.Form:
+            # Recurse into Form XObjects
+            log.debug(f"Recursing into Form XObject {_imname} in page {pageno}")
+            _find_image_xrefs_container(
+                pdf,
+                image,
+                pageno,
+                include_xrefs,
+                exclude_xrefs,
+                pageno_for_xref,
+                depth + 1,
+            )
+            continue
+        xref = Xref(image.objgen[0])
+        if Name.SMask in image:
+            # Ignore soft masks
+            smask_xref = Xref(image.SMask.objgen[0])
+            exclude_xrefs.add(smask_xref)
+            log.debug(f"xref {smask_xref}: skipping image because it is an SMask")
+        include_xrefs.add(xref)
+        log.debug(f"xref {xref}: treating as an optimization candidate")
+        if xref not in pageno_for_xref:
+            pageno_for_xref[xref] = pageno
+
+
+def _find_image_xrefs(pdf: Pdf):
+    include_xrefs: MutableSet[Xref] = set()
+    exclude_xrefs: MutableSet[Xref] = set()
+    pageno_for_xref: dict[Xref, int] = {}
+
+    for pageno, page in enumerate(pdf.pages):
+        _find_image_xrefs_container(
+            pdf, page.obj, pageno, include_xrefs, exclude_xrefs, pageno_for_xref
+        )
+
+    working_xrefs = include_xrefs - exclude_xrefs
+    return working_xrefs, pageno_for_xref
+
+
 def extract_images(
-    pike: Pdf,
+    pdf: Pdf,
     root: Path,
     options,
     extract_fn: Callable[..., XrefExt | None],
 ) -> Iterator[tuple[int, XrefExt]]:
-    """Extract image using extract_fn
+    """Extract image using extract_fn.
 
     Enumerate images on each page, lookup their xref/ID number in the PDF.
     Exclude images that are soft masks (i.e. alpha transparency related).
@@ -244,36 +309,13 @@ def extract_images(
     it does a tuple should be returned: (xref, ext) where .ext is the file
     extension. extract_fn must also extract the file it finds interesting.
     """
-
-    include_xrefs: MutableSet[Xref] = set()
-    exclude_xrefs: MutableSet[Xref] = set()
-    pageno_for_xref = {}
     errors = 0
-    for pageno, page in enumerate(pike.pages):
+    working_xrefs, pageno_for_xref = _find_image_xrefs(pdf)
-        try:
-            xobjs = page.Resources.XObject
-        except AttributeError:
-            continue
-        for _imname, image in dict(xobjs).items():
-            if image.objgen[1] != 0:
-                continue  # Ignore images in an incremental PDF
-            xref = Xref(image.objgen[0])
-            if Name.SMask in image:
-                # Ignore soft masks
-                smask_xref = Xref(image.SMask.objgen[0])
-                exclude_xrefs.add(smask_xref)
-                log.debug(f"xref {smask_xref}: skipping image because it is an SMask")
-            include_xrefs.add(xref)
-            log.debug(f"xref {xref}: treating as an optimization candidate")
-            if xref not in pageno_for_xref:
-                pageno_for_xref[xref] = pageno
-
-    working_xrefs = include_xrefs - exclude_xrefs
     for xref in working_xrefs:
-        image = pike.get_object((xref, 0))
+        image = pdf.get_object((xref, 0))
         try:
             result = extract_fn(
-                pike=pike, root=root, image=image, xref=xref, options=options
+                pdf=pdf, root=root, image=image, xref=xref, options=options
             )
         except Exception:  # pylint: disable=broad-except
             log.exception(
@@ -287,13 +329,12 @@ def extract_images(
 
 
 def extract_images_generic(
-    pike: Pdf, root: Path, options
+    pdf: Pdf, root: Path, options
 ) -> tuple[list[Xref], list[Xref]]:
-    """Extract any >=2bpp image we think we can improve"""
+    """Extract any >=2bpp image we think we can improve."""
-
     jpegs = []
     pngs = []
-    for _, xref_ext in extract_images(pike, root, options, extract_image_generic):
+    for _, xref_ext in extract_images(pdf, root, options, extract_image_generic):
         log.debug('%s', xref_ext)
         if xref_ext.ext == '.png':
             pngs.append(xref_ext.xref)
@@ -303,11 +344,10 @@ def extract_images_generic(
     return jpegs, pngs
 
 
-def extract_images_jbig2(pike: Pdf, root: Path, options) -> dict[int, list[XrefExt]]:
+def extract_images_jbig2(pdf: Pdf, root: Path, options) -> dict[int, list[XrefExt]]:
-    """Extract any bitonal image that we think we can improve as JBIG2"""
+    """Extract any bitonal image that we think we can improve as JBIG2."""
-
     jbig2_groups = defaultdict(list)
-    for pageno, xref_ext in extract_images(pike, root, options, extract_image_jbig2):
+    for pageno, xref_ext in extract_images(pdf, root, options, extract_image_jbig2):
         group = pageno // options.jbig2_page_group_size
         jbig2_groups[group].append(xref_ext)
 
@@ -318,7 +358,7 @@ def extract_images_jbig2(pike: Pdf, root: Path, options) -> dict[int, list[XrefE
 def _produce_jbig2_images(
     jbig2_groups: dict[int, list[XrefExt]], root: Path, options, executor: Executor
 ) -> None:
-    """Produce JBIG2 images from their groups"""
+    """Produce JBIG2 images from their groups."""
 
     def jbig2_group_args(root: Path, groups: dict[int, list[XrefExt]]):
         for group, xref_exts in groups.items():
@@ -327,9 +367,10 @@ def _produce_jbig2_images(
                 fspath(root),  # =cwd
                 (img_name(root, xref, ext) for xref, ext in xref_exts),  # =infiles
                 prefix,  # =out_prefix
+                options.jbig2_threshold,
             )
 
-    def jbig2_single_args(root, groups: dict[int, list[XrefExt]]):
+    def jbig2_single_args(root: Path, groups: dict[int, list[XrefExt]]):
         for group, xref_exts in groups.items():
             prefix = f'group{group:08d}'
             # Second loop is to ensure multiple images per page are unpacked
@@ -339,19 +380,20 @@ def _produce_jbig2_images(
                     fspath(root),
                     img_name(root, xref, ext),
                     root / f'{prefix}.{n:04d}',
+                    options.jbig2_threshold,
                 )
 
     if options.jbig2_page_group_size > 1:
         jbig2_args = jbig2_group_args
-        jbig2_convert = jbig2enc.convert_group_mp
+        jbig2_convert = jbig2enc.convert_group
     else:
         jbig2_args = jbig2_single_args
-        jbig2_convert = jbig2enc.convert_single_mp
+        jbig2_convert = jbig2enc.convert_single
 
     executor(
         use_threads=True,
         max_workers=options.jobs,
-        tqdm_kwargs=dict(
+        progress_kwargs=dict(
             total=len(jbig2_groups),
             desc="JBIG2",
             unit='item',
@@ -363,7 +405,7 @@ def _produce_jbig2_images(
 
 
 def convert_to_jbig2(
-    pike: Pdf,
+    pdf: Pdf,
     jbig2_groups: dict[int, list[XrefExt]],
     root: Path,
     options,
@@ -390,7 +432,7 @@ def convert_to_jbig2(
         jbig2_symfile = root / (prefix + '.sym')
         if jbig2_symfile.exists():
             jbig2_globals_data = jbig2_symfile.read_bytes()
-            jbig2_globals = Stream(pike, jbig2_globals_data)
+            jbig2_globals = Stream(pdf, jbig2_globals_data)
             jbig2_globals_dict = Dictionary(JBIG2Globals=jbig2_globals)
         elif options.jbig2_page_group_size == 1:
             jbig2_globals_dict = None
@@ -401,15 +443,15 @@ def convert_to_jbig2(
             xref, _ = xref_ext
             jbig2_im_file = root / (prefix + f'.{n:04d}')
             jbig2_im_data = jbig2_im_file.read_bytes()
-            im_obj = pike.get_object(xref, 0)
+            im_obj = pdf.get_object(xref, 0)
             im_obj.write(
                 jbig2_im_data, filter=Name.JBIG2Decode, decode_parms=jbig2_globals_dict
             )
 
 
-def _optimize_jpeg(args: tuple[Xref, Path, Path, int]) -> tuple[Xref, Path | None]:
+def _optimize_jpeg(
-    xref, in_jpg, opt_jpg, jpeg_quality = args
+    xref: Xref, in_jpg: Path, opt_jpg: Path, jpeg_quality: int
-
+) -> tuple[Xref, Path | None]:
     with Image.open(in_jpg) as im:
         im.save(opt_jpg, optimize=True, quality=jpeg_quality)
 
@@ -421,26 +463,28 @@ def _optimize_jpeg(args: tuple[Xref, Path, Path, int]) -> tuple[Xref, Path | Non
 
 
 def transcode_jpegs(
-    pike: Pdf, jpegs: Sequence[Xref], root: Path, options, executor: Executor
+    pdf: Pdf, jpegs: Sequence[Xref], root: Path, options, executor: Executor
 ) -> None:
+    """Optimize JPEGs according to optimization settings."""
+
     def jpeg_args() -> Iterator[tuple[Xref, Path, Path, int]]:
         for xref in jpegs:
             in_jpg = jpg_name(root, xref)
             opt_jpg = in_jpg.with_suffix('.opt.jpg')
             yield xref, in_jpg, opt_jpg, options.jpeg_quality
 
-    def finish_jpeg(result: tuple[Xref, Path | None], pbar):
+    def finish_jpeg(result: tuple[Xref, Path | None], pbar: ProgressBar):
         xref, opt_jpg = result
         if opt_jpg:
             compdata = opt_jpg.read_bytes()  # JPEG can inserted into PDF as is
-            im_obj = pike.get_object(xref, 0)
+            im_obj = pdf.get_object(xref, 0)
             im_obj.write(compdata, filter=Name.DCTDecode)
         pbar.update()
 
     executor(
         use_threads=True,  # Processes are significantly slower at this task
         max_workers=options.jobs,
-        tqdm_kwargs=dict(
+        progress_kwargs=dict(
             desc="Recompressing JPEGs",
             total=len(jpegs),
             unit='image',
@@ -453,9 +497,9 @@ def transcode_jpegs(
 
 
 def _find_deflatable_jpeg(
-    *, pike: Pdf, root: Path, image: Stream, xref: Xref, options
+    *, pdf: Pdf, root: Path, image: Stream, xref: Xref, options
 ) -> XrefExt | None:
-    result = extract_image_filter(pike, root, image, xref)
+    result = extract_image_filter(image, xref)
     if result is None:
         return None
     _pim, filtdp = result
@@ -466,10 +510,11 @@ def _find_deflatable_jpeg(
     return None
 
 
-def _deflate_jpeg(args: tuple[Pdf, threading.Lock, Xref, int]) -> tuple[Xref, bytes]:
+def _deflate_jpeg(
-    pike, lock, xref, complevel = args
+    pdf: Pdf, lock: threading.Lock, xref: Xref, complevel: int
+) -> tuple[Xref, bytes]:
     with lock:
-        xobj = pike.get_object(xref, 0)
+        xobj = pdf.get_object(xref, 0)
         try:
             data = xobj.read_raw_bytes()
         except PdfError:
@@ -480,9 +525,15 @@ def _deflate_jpeg(args: tuple[Pdf, threading.Lock, Xref, int]) -> tuple[Xref, by
     return xref, compdata
 
 
-def deflate_jpegs(pike: Pdf, root: Path, options, executor: Executor) -> None:
+def deflate_jpegs(pdf: Pdf, root: Path, options, executor: Executor) -> None:
+    """Apply FlateDecode to JPEGs.
+
+    This is a lossless compression method that is supported by all PDF viewers,
+    and generally results in a smaller file size compared to straight DCTDecode
+    images.
+    """
     jpegs = []
-    for _pageno, xref_ext in extract_images(pike, root, options, _find_deflatable_jpeg):
+    for _pageno, xref_ext in extract_images(pdf, root, options, _find_deflatable_jpeg):
         xref = xref_ext.xref
         log.debug(f'xref {xref}: marking this JPEG as deflatable')
         jpegs.append(xref)
@@ -494,20 +545,20 @@ def deflate_jpegs(pike: Pdf, root: Path, options, executor: Executor) -> None:
 
     def deflate_args() -> Iterator:
         for xref in jpegs:
-            yield pike, lock, xref, complevel
+            yield pdf, lock, xref, complevel
 
-    def finish(result, pbar):
+    def finish(result: tuple[Xref, bytes], pbar: ProgressBar):
         xref, compdata = result
         if len(compdata) > 0:
             with lock:
-                xobj = pike.get_object(xref, 0)
+                xobj = pdf.get_object(xref, 0)
                 xobj.write(compdata, filter=[Name.FlateDecode, Name.DCTDecode])
         pbar.update()
 
     executor(
         use_threads=True,  # We're sharing the pdf directly, must use threads
         max_workers=options.jobs,
-        tqdm_kwargs=dict(
+        progress_kwargs=dict(
             desc="Deflating JPEGs",
             total=len(jpegs),
             unit='image',
@@ -519,16 +570,16 @@ def deflate_jpegs(pike: Pdf, root: Path, options, executor: Executor) -> None:
     )
 
 
-def _transcode_png(pike: Pdf, filename: Path, xref: Xref) -> bool:
+def _transcode_png(pdf: Pdf, filename: Path, xref: Xref) -> bool:
     output = filename.with_suffix('.png.pdf')
     with output.open('wb') as f:
         img2pdf.convert(fspath(filename), outputstream=f, **IMG2PDF_KWARGS)
 
     with Pdf.open(output) as pdf_image:
         foreign_image = next(iter(pdf_image.pages[0].images.values()))
-        local_image = pike.copy_foreign(foreign_image)
+        local_image = pdf.copy_foreign(foreign_image)
 
-        im_obj = pike.get_object(xref, 0)
+        im_obj = pdf.get_object(xref, 0)
         im_obj.write(
             local_image.read_raw_bytes(),
             filter=local_image.Filter,
@@ -561,13 +612,14 @@ def _transcode_png(pike: Pdf, filename: Path, xref: Xref) -> bool:
 
 
 def transcode_pngs(
-    pike: Pdf,
+    pdf: Pdf,
     images: Sequence[Xref],
     image_name_fn: Callable[[Path, Xref], Path],
     root: Path,
     options,
-    executor,
+    executor: Executor,
 ) -> None:
+    """Apply lossy transcoding to PNGs."""
     modified: MutableSet[Xref] = set()
     if options.optimize >= 2:
         png_quality = (
@@ -589,19 +641,19 @@ def transcode_pngs(
         executor(
             use_threads=True,
             max_workers=options.jobs,
-            tqdm_kwargs=dict(
+            progress_kwargs=dict(
                 desc="PNGs",
                 total=len(images),
                 unit='image',
                 disable=not options.progress_bar,
             ),
-            task=pngquant.quantize_mp,
+            task=pngquant.quantize,
             task_arguments=pngquant_args(),
         )
 
     for xref in modified:
         filename = png_name(root, xref)
-        _transcode_png(pike, filename, xref)
+        _transcode_png(pdf, filename, xref)
 
 
 DEFAULT_EXECUTOR = SerialExecutor()
@@ -610,10 +662,11 @@ DEFAULT_EXECUTOR = SerialExecutor()
 def optimize(
     input_file: Path,
     output_file: Path,
-    context,
+    context: PdfContext,
-    save_settings,
+    save_settings: dict[str, Any],
     executor: Executor = DEFAULT_EXECUTOR,
 ) -> Path:
+    """Optimize images in a PDF file."""
     options = context.options
     if options.optimize == 0:
         safe_symlink(input_file, output_file)
@@ -626,24 +679,24 @@ def optimize(
     if options.jbig2_page_group_size == 0:
         options.jbig2_page_group_size = 10 if options.jbig2_lossy else 1
 
-    with Pdf.open(input_file) as pike:
+    with Pdf.open(input_file) as pdf:
         root = output_file.parent / 'images'
         root.mkdir(exist_ok=True)
 
-        jpegs, pngs = extract_images_generic(pike, root, options)
+        jpegs, pngs = extract_images_generic(pdf, root, options)
-        transcode_jpegs(pike, jpegs, root, options, executor)
+        transcode_jpegs(pdf, jpegs, root, options, executor)
-        deflate_jpegs(pike, root, options, executor)
+        deflate_jpegs(pdf, root, options, executor)
         # if options.optimize >= 2:
         # Try pngifying the jpegs
-        #    transcode_pngs(pike, jpegs, jpg_name, root, options)
+        #    transcode_pngs(pdf, jpegs, jpg_name, root, options)
-        transcode_pngs(pike, pngs, png_name, root, options, executor)
+        transcode_pngs(pdf, pngs, png_name, root, options, executor)
 
-        jbig2_groups = extract_images_jbig2(pike, root, options)
+        jbig2_groups = extract_images_jbig2(pdf, root, options)
-        convert_to_jbig2(pike, jbig2_groups, root, options, executor)
+        convert_to_jbig2(pdf, jbig2_groups, root, options, executor)
 
         target_file = output_file.with_suffix('.opt.pdf')
-        pike.remove_unreferenced_resources()
+        pdf.remove_unreferenced_resources()
-        pike.save(target_file, **save_settings)
+        pdf.save(target_file, **save_settings)
 
     input_size = input_file.stat().st_size
     output_size = target_file.stat().st_size
@@ -660,9 +713,9 @@ def optimize(
             "optimizations will not be used"
         )
         # We still need to save the file
-        with Pdf.open(input_file) as pike:
+        with Pdf.open(input_file) as pdf:
-            pike.remove_unreferenced_resources()
+            pdf.remove_unreferenced_resources()
-            pike.save(output_file, **save_settings)
+            pdf.save(output_file, **save_settings)
     else:
         safe_symlink(target_file, output_file)
 
@@ -670,11 +723,12 @@ def optimize(
 
 
 def main(infile, outfile, level, jobs=1):
+    """Entry point for direct optimization of a file."""
     from shutil import copy  # pylint: disable=import-outside-toplevel
     from tempfile import TemporaryDirectory  # pylint: disable=import-outside-toplevel
 
     class OptimizeOptions:
-        """Emulate ocrmypdf's options"""
+        """Emulate ocrmypdf's options."""
 
         def __init__(
             self, input_file, jobs, optimize_, jpeg_quality, png_quality, jb2lossy
@@ -686,6 +740,7 @@ def main(infile, outfile, level, jobs=1):
             self.png_quality = png_quality
             self.jbig2_page_group_size = 0
             self.jbig2_lossy = jb2lossy
+            self.jbig2_threshold = 0.85
             self.quiet = True
             self.progress_bar = False
 

src/ocrmypdf/pdfa.py

@@ -1,20 +1,14 @@
 # SPDX-FileCopyrightText: 2022 James R. Barlow
 # SPDX-License-Identifier: MPL-2.0
 
-"""
+"""Utilities for PDF/A production and confirmation with Ghostspcript."""
-Utilities for PDF/A production and confirmation with Ghostspcript.
-"""
 
 from __future__ import annotations
 
 import base64
+from collections.abc import Iterator
+from importlib.resources import files as package_files
 from pathlib import Path
-from typing import Iterator
-
-try:
-    from importlib.resources import files as package_files
-except ImportError:
-    from importlib_resources import files as package_files  # type: ignore
 
 import pikepdf
 
@@ -25,8 +19,8 @@ def _postscript_objdef(
     alias: str,
     dictionary: dict[str, str],
     *,
-    stream_name: str = None,
+    stream_name: str | None = None,
-    stream_data: bytes = None,
+    stream_data: bytes | None = None,
 ) -> Iterator[str]:
     assert (stream_name is None) == (stream_data is None)
 
@@ -75,7 +69,7 @@ def _make_postscript(icc_name: str, icc_data: bytes, colors: int) -> Iterator[st
 
 
 def generate_pdfa_ps(target_filename: Path, icc: str = 'sRGB'):
-    """Create a Postscript PDFMARK file for Ghostscript PDF/A conversion
+    """Create a Postscript PDFMARK file for Ghostscript PDF/A conversion.
 
     pdfmark is an extension to the Postscript language that describes some PDF
     features like bookmarks and annotations. It was originally specified Adobe
@@ -84,7 +78,7 @@ def generate_pdfa_ps(target_filename: Path, icc: str = 'sRGB'):
     Ghostscript uses pdfmark for PDF to PDF/A conversion as well. To use Ghostscript
     to create a PDF/A, we need to create a pdfmark file with the necessary metadata.
 
-    This function takes care of the many version-specific bugs and pecularities in
+    This function takes care of the many version-specific bugs and peculiarities in
     Ghostscript's handling of pdfmark.
 
     The only information we put in specifies that we want the file to be a
@@ -118,7 +112,6 @@ def file_claims_pdfa(filename: Path):
     This only checks if the XMP metadata contains a PDF/A marker. It does not
     do full PDF/A validation.
     """
-
     with pikepdf.open(filename) as pdf:
         pdfmeta = pdf.open_metadata()
         if not pdfmeta.pdfa_status:

src/ocrmypdf/pdfinfo/__init__.py

@@ -6,4 +6,6 @@
 
 from __future__ import annotations
 
-from ocrmypdf.pdfinfo.info import Colorspace, Encoding, PdfInfo
+from ocrmypdf.pdfinfo.info import Colorspace, Encoding, PageInfo, PdfInfo
+
+__all__ = ["Colorspace", "Encoding", "PageInfo", "PdfInfo"]