Update docker document and v15.2.0 release notes

Don't build docker alpine aarch64 for now and add alias tag for Ubuntu
Attempt at alpine on arm64 - not working
2023-10-10 01:25:26 -07:00 · 2023-10-09 17:36:08 -07:00 · 2023-10-09 17:34:28 -07:00 · 2023-10-09 15:08:38 -07:00 · 2023-10-09 14:59:56 -07:00 · 2023-10-09 14:57:55 -07:00
258 changed files with 7013 additions and 5126 deletions
@@ -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 \
@@ -57,6 +59,7 @@ 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 \
@@ -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"]
@@ -0,0 +1,51 @@
+name: General issues
+description: Installation, packages, dependencies, "nothing works", test suite failures...
+title: "[Bug]: "
+labels: ["bug", "triage"]
+assignees:
+  - jbarlow83
+body:
+  - type: markdown
+    attributes:
+      value: |
+        Thanks for taking the time to fill out this bug report!
+  - type: textarea
+    id: what-happened
+    attributes:
+      label: What were you trying to do?
+      description: Also tell us, what did you expect to happen?
+      placeholder: Tell us what you see!
+    validations:
+      required: true
+  - type: dropdown
+    id: packaging-system
+    attributes:
+      label: Where are you installing from?
+      multiple: true
+      options:
+        - PyPI (pip, poetry, pipx, etc.)
+        - Linux package manager (apt, dnf, etc.)
+        - Wndows package manager (chocolatey, etc.)
+        - Homebrew
+        - Docker container
+        - Ubuntu snap
+        - Conda
+        - source build
+    validations:
+      required: true
+  - type: dropdown
+    id: operating-system
+    attributes:
+      label: What operating system are you working on?
+      multiple: true
+      options:
+        - Linux
+        - Windows
+        - macOS
+        - BSD
+  - type: textarea
+    id: logs
+    attributes:
+      label: Relevant log output
+      description: Please copy and paste any relevant log output. This will be automatically formatted into code, so no need for backticks.
+      render: plain text
@@ -0,0 +1,62 @@
+name: Problem with specific file
+description: Something went wrong while trying to OCR a specific file
+title: "[Bug]: "
+labels: ["bug", "triage"]
+assignees:
+  - jbarlow83
+body:
+  - type: markdown
+    attributes:
+      value: |
+        Thanks for taking the time to describe this issue with a particular file.
+  - type: textarea
+    id: what-happened
+    attributes:
+      label: Describe the bug
+      description: A clear and concise description of what the bug is.
+      placeholder: Tell us what you see!
+    validations:
+      required: true
+  - type: textarea
+    id: reproduce
+    attributes:
+      label: Steps to reproduce
+      description: Please include steps to reproduce
+      value: |
+        1. Run ocrmypdf -v1 ...arguments... input.pdf output.pdf
+        2. Open output.pdf
+        3. ...
+      render: plain text
+  - type: textarea
+    id: files
+    attributes:
+      label: Files
+      description: Please attach the input and output files, or any screenshots that may be helpful.
+      placeholder: Drag and drop files here
+  - type: dropdown
+    id: packaging-system
+    attributes:
+      label: How did you download and install the software?
+      multiple: true
+      options:
+        - PyPI (pip, poetry, pipx, etc.)
+        - Linux package manager (apt, dnf, etc.)
+        - Windows package manager (chocolatey, etc.)
+        - Homebrew
+        - Docker container
+        - Ubuntu snap
+        - Conda
+        - source build
+  - type: input
+    id: version
+    attributes:
+      label: OCRmyPDF version
+      description: Paste "ocrmypdf --version" here
+      placeholder: ocrmypdf --version
+  - type: textarea
+    id: logs
+    attributes:
+      label: Relevant log output
+      description: Please copy and paste any relevant log output. This will be automatically formatted into code, so no need for backticks.
+      placeholder: Run OCRmyPDF with verbosity `-v1` to get more detailed logging output.
+      render: plain text
@@ -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.
@@ -1,23 +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. You could also look in ``tests/resources`` and see if any of those files demonstrates your issue.
-
-**Additional context**
-Add any other context or screenshots about the feature request here.
@@ -1,33 +0,0 @@
---
-name: General issues
-about: Installation, packages, dependencies, "nothing works", test suite failures...
-title: "[BUG]"
-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:
- - Platform: x64 or ARM
-
-**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.
@@ -1,40 +0,0 @@
---
-name: Problem with specific file
-about: Something went wrong while trying to OCR a specific file
-title: "[BUG]"
-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?
@@ -5,7 +5,7 @@ name: Test and deploy
 on:
  push:
    branches:
-      - master
+      - main
      - ci
      - release/*
      - feature/*
@@ -22,39 +22,35 @@ jobs:
    strategy:
      matrix:
        include:
-          - os: ubuntu-20.04
-            python: "3.8"
-          - os: ubuntu-20.04
+          - os: ubuntu-22.04
            python: "3.9"
-          - os: ubuntu-20.04
+          - os: ubuntu-22.04
            python: "3.10"
-          - os: ubuntu-latest
-            python: "3.9"
-          - os: ubuntu-latest
-            python: "3.10"
-          - os: ubuntu-latest
+          - os: ubuntu-22.04
            python: "3.11"
-          # - os: ubuntu-latest
-          #   python: "pypy3.8"
-          #- os: ubuntu-latest
-          #  python: "pypy3.9"
-          - os: ubuntu-latest
+          - os: ubuntu-22.04
            python: "3.9"
            tesseract5: true
+          - os: ubuntu-latest
+            python: "3.12-dev"
+            tesseract5: true
+            #- os: ubuntu-latest
+            #  python: "pypy3.9"

    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
+        name: Setup Python
        with:
          python-version: ${{ matrix.python }}
+          cache: "pip"

      - name: Install Tesseract 5
        if: matrix.tesseract5
@@ -68,6 +64,7 @@ jobs:
            curl \
            ghostscript \
            img2pdf \
+            libexempi8 \
            libffi-dev \
            libsm6 libxext6 libxrender-dev \
            pngquant \
@@ -79,12 +76,6 @@ jobs:
            unpaper \
            zlib1g

-      - 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: |
@@ -122,14 +113,14 @@ jobs:
    strategy:
      matrix:
        os: [macos-latest]
-        python: ["3.10", "3.11"]
+        python: ["3.10", "3.11", "3.12-dev"]

    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

@@ -146,9 +137,10 @@ jobs:
            tesseract

      - uses: actions/setup-python@v4
-        name: Install Python
+        name: Setup Python
        with:
          python-version: ${{ matrix.python }}
+          cache: "pip"

      - name: Install Python packages
        run: |
@@ -178,21 +170,22 @@ jobs:
    strategy:
      matrix:
        os: [windows-latest]
-        python: ["3.10", "3.11"]
+        python: ["3.10", "3.11", "3.12-dev"]

    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
+        name: Setup Python
        with:
          python-version: ${{ matrix.python }}
+          cache: "pip"

      - name: Install system packages
        run: |
@@ -218,14 +211,15 @@ 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
-        name: Install Python
+        name: Setup Python
        with:
-          python-version: "3.7"
+          python-version: "3.9"
+          cache: "pip"

      - name: Make wheels and sdist
        run: |
@@ -242,6 +236,9 @@ 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
@@ -249,14 +246,37 @@ jobs:
          name: artifact
          path: dist

-      - uses: pypa/gh-action-pypi-publish@master
-        with:
-          user: __token__
-          password: ${{ secrets.TOKEN_PYPI }}
-          # repository_url: https://test.pypi.org/legacy/
+      - name: Publish to PyPI
+        uses: pypa/gh-action-pypi-publish@release/v1

-  docker:
-    name: Build Docker images
+  create_release:
+    name: Create GitHub release
+    needs: [wheel_sdist_linux, test_linux, test_macos, test_windows]
+    runs-on: ubuntu-latest
+    if: github.event_name == 'push' && startsWith(github.event.ref, 'refs/tags/v')
+    permissions:
+      # Required to create a release
+      contents: write
+    steps:
+      - uses: actions/download-artifact@v3
+        with:
+          name: artifact
+          path: dist
+
+      - name: Create Release
+        id: create-release
+        uses: shogo82148/actions-create-release@v1
+
+      - name: Upload Assets
+        uses: shogo82148/actions-upload-release-asset@v1
+        with:
+          upload_url: ${{ steps.create-release.outputs.upload_url }}
+          asset_path: |
+            ./dist/*.whl
+            ./dist/*.tar.gz
+
+  docker_ubuntu:
+    name: Build Ubuntu-based Docker image
    needs: [wheel_sdist_linux, test_linux, test_macos, test_windows]
    runs-on: ubuntu-latest
    if: github.event_name != 'pull_request'
@@ -264,9 +284,9 @@ jobs:
      - name: Set image tag to release or branch
        run: echo "DOCKER_IMAGE_TAG=${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 .
@@ -6,6 +6,7 @@
 .venv*/
 .tox/
 .vscode/
+.hypothesis/
 .ipynb_checkpoints/
 .mypy_cache/
 .pytest_cache/
@@ -26,6 +27,7 @@ venv*/
 *.traineddata
 /private
 /coverage.xml
+/issuepdf

 # Package building
 *.egg-info/
@@ -3,34 +3,26 @@

 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
-    rev: 5.10.1
+  - repo: https://github.com/charliermarsh/ruff-pre-commit
+    rev: "v0.0.261"
    hooks:
-      - id: isort
-        args: ["--profile", "black", "-a", "from __future__ import annotations"]
+      - id: ruff
+        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: ["--py38-plus"]
  - repo: https://github.com/pre-commit/mirrors-mypy
-    rev: v0.971
+    rev: v1.2.0
    hooks:
      - id: mypy
        additional_dependencies:
@@ -16,8 +16,12 @@ formats:
  - pdf

 # Optionally set the version of Python and requirements required to build your docs
+build:
+  os: ubuntu-22.04
+  tools:
+    python: "3.9"
+
 python:
-  version: "3.8"
  install:
    - method: pip
      path: .
@@ -41,6 +41,7 @@ Files:
 tests/resources/trivial.pdf
 tests/resources/truetype_font_nomapping.pdf
 tests/resources/type3_font_nomapping.pdf
+ misc/screencast/*
 Copyright: (C) 2022 James R. Barlow
 License: CC-BY-SA-4.0

@@ -39,8 +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
- Battle-tested on millions of PDFs
+- Scales properly to handle files with thousands of pages.
+- Battle-tested on millions of PDFs.
+
+<img src="misc/screencast/demo.svg" alt="Demo of OCRmyPDF in a terminal session">

 For details: please consult the [documentation](https://ocrmypdf.readthedocs.io/en/latest/).

@@ -68,9 +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 py-ocrmypdf`` |
+| FreeBSD                       | ``pkg install py-ocrmypdf``   |
 | Conda                         | ``conda install ocrmypdf``    |
 | Ubuntu Snap                   | ``snap install ocrmypdf``     |

@@ -112,7 +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

@@ -123,6 +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

@@ -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
-   result in errors.
+   file and produce one file; errors will result if this assumption is not
+   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
-text. This is useful for redoing OCR, for fixing OCR text with a damaged
-character map (text is selectable but not searchable), and destroying
-redacted information. Any forms and vector graphics will be rasterized
-as well.
+images, discarding any hidden OCR text, rasterizing any printable
+text, and flattening form fields or interactive objects into their visual
+representation. This is useful for redoing OCR, for fixing OCR text
+with a damaged character map (text is selectable but not searchable),
+and destroying redacted information.

 Time and image size limits
 --------------------------
@@ -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
 ----------------------------

@@ -154,12 +192,13 @@ 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://tesseract-ocr.github.io/tessdoc/tess3/ControlParams.html>`__
 with a configuration file.

@@ -234,13 +273,44 @@ Unlike ``sandwich`` this renderer is implemented within OCRmyPDF; anyone
 looking to customize how OCR is presented should look here. A major
 disadvantage of this renderer is it not capable of correctly handling
 text outside the Latin alphabet (specifically, it supports the ISO 8859-1
-character). Pull requests to improve the situation are welcome.
+character set). Pull requests to improve the situation are welcome.

 Currently, this renderer has the best compatibility with Mozilla's
 PDF.js viewer.

 This works in all versions of Tesseract.

+Rendering and rasterizing options
+=================================
+
+.. versionadded:: 14.3.0
+
+The ``--continue-on-soft-render-error`` option allows OCRmyPDF to
+proceed if a page cannot be rasterized/rendered. This is useful if you are
+trying to get the best possible OCR from a PDF that is not well-formed,
+and you are willing to accept some pages that may not visually match the
+input, and that may not OCR well.
+
+Color conversion strategy
+=========================
+
+.. versionadded:: 15.0.0
+
+OCRmyPDF uses Ghostscript to convert PDF to PDF/A. In some cases, this
+conversion requires color conversion. The default strategy is to convert
+using the ``LeaveColorUnchanged`` strategy, which preserves the original
+color space wherever possible (some rare color spaces might still be
+converted).
+
+Usually document scanners produce PDFs in the sRGB color space, and do
+not need to be converted, so the default strategy is appropriate.
+
+Suppose that you have a document that was prepared for professional
+printing in a Separation or CMYK color space, and text was converted to
+curves. In this case, you may want to use a different color conversion
+strategy. The ``--color-conversion-strategy`` option allows you to select a
+different strategy, such as ``RGB``.
+
 Return code policy
 ==================

@@ -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
-the temporary folder and print the location, whether it succeeded or
-failed (provided the Python interpreter did not crash). An example
-message is:
+If the ``--keep-temporary-files`` (``-k```) argument is issued on the
+command line, OCRmyPDF will keep the temporary folder and print the location,
+whether it succeeded or failed. An example message is:

 .. code-block:: none

@@ -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 (on Linux, forking itself; on Windows and macOS, by
-  spawning)
+- create worker processes or threads
 - 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
@@ -89,12 +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
 ----------

@@ -104,9 +123,6 @@ 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
@@ -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
-products use ARM or Power processors and do not support Docker. Further
-adjustments might be needed to deal with the Synology's relatively
+At the time this script was written, it only worked for x86-based Synology
+products. It is not known if it will work on ARM-based Synology products.
+Further adjustments might be needed to deal with the Synology's relatively
 limited CPU and RAM.

 .. literalinclude:: ../misc/synology.py
@@ -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}'``."
@@ -151,14 +150,14 @@ The watcher service is included in the OCRmyPDF Docker image. To run it:
 .. code-block:: bash

    docker run \
-        -v <path to files to convert>:/input \
-        -v <path to store results>:/output \
-        -v <path to store processed originals>:/archive \
-        -e OCR_OUTPUT_DIRECTORY_YEAR_MONTH=1 \
-        -e OCR_ON_SUCCESS_ARCHIVE=1 \
-        -e OCR_DESKEW=1 \
-        -e PYTHONUNBUFFERED=1 \
-        -it --entrypoint python3 \
+        --volume <path to files to convert>:/input \
+        --volume <path to store results>:/output \
+        --volume <path to store processed originals>:/archive \
+        --env OCR_OUTPUT_DIRECTORY_YEAR_MONTH=1 \
+        --env OCR_ON_SUCCESS_ARCHIVE=1 \
+        --env OCR_DESKEW=1 \
+        --env PYTHONUNBUFFERED=1 \
+        --interactive --tty --entrypoint python3 \
        jbarlow83/ocrmypdf \
        watcher.py

@@ -170,13 +169,13 @@ original to ``/archive``. The parameters to this image are:
    :header: "Parameter", "Description"
    :widths: 50, 50

-    "``-v <path to files to convert>:/input``", "Files placed in this location will be OCRed"
-    "``-v <path to store results>:/output``", "This is where OCRed files will be stored"
-    "``-v <path to store processed originals>:/archive``", "Archive processed originals here"
-    "``-e OCR_OUTPUT_DIRECTORY_YEAR_MONTH=1``", "Define environment variable ``OCR_OUTPUT_DIRECTORY_YEAR_MONTH=1`` to place files in the output in ``{output}/{year}/{month}/{filename}``"
-    "``-e OCR_ON_SUCCESS_ARCHIVE=1``", "Define environment variable ``OCR_ON_SUCCESS_ARCHIVE`` to move processed originals"
-    "``-e OCR_DESKEW=1``", "Define environment variable ``OCR_DESKEW``  to apply deskew to crooked input PDFs"
-    "``-e PYTHONBUFFERED=1``", "This will force ``STDOUT`` to be unbuffered and allow you to see messages in docker logs"
+    "``--volume <path to files to convert>:/input``", "Files placed in this location will be OCRed"
+    "``--volume <path to store results>:/output``", "This is where OCRed files will be stored"
+    "``--volume <path to store processed originals>:/archive``", "Archive processed originals here"
+    "``--env OCR_OUTPUT_DIRECTORY_YEAR_MONTH=1``", "Define environment variable ``OCR_OUTPUT_DIRECTORY_YEAR_MONTH=1`` to place files in the output in ``{output}/{year}/{month}/{filename}``"
+    "``--env OCR_ON_SUCCESS_ARCHIVE=1``", "Define environment variable ``OCR_ON_SUCCESS_ARCHIVE`` to move processed originals"
+    "``--env OCR_DESKEW=1``", "Define environment variable ``OCR_DESKEW``  to apply deskew to crooked input PDFs"
+    "``--env PYTHONBUFFERED=1``", "This will force ``STDOUT`` to be unbuffered and allow you to see messages in docker logs"

 This service relies on polling to check for changes to the filesystem. It
 may not be suitable for some environments, such as filesystems shared on a
@@ -0,0 +1,87 @@
+.. _ocr-service:
+
+==================
+Online deployments
+==================
+
+OCRmyPDF is designed to be used as a command line tool, but it can be
+used in a web service. This document describes some considerations for
+doing so.
+
+A basic web service implementation is provided in the source code
+repository, as ``misc/webservice.py``. It is only demonstration quality
+and is not intended for production use.
+
+OCRmyPDF is not designed for use as a public web service where a
+malicious user could upload a chosen PDF. In particular, it is not
+necessarily secure against PDF malware or PDFs that cause denial of
+service. For further discussino of security, see :ref:`security`.
+
+OCRmyPDF relies on Ghostscript, and therefore, if deployed
+online one should be prepared to comply with Ghostscript's Affero GPL
+license, and any other licenses.
+
+Setting aside these concerns, a side effect of OCRmyPDF is that it may
+incidentally sanitize PDFs containing certain types of malware. It
+repairs the PDF with pikepdf/libqpdf, which could correct malformed PDF
+structures that are part of an attack. When PDF/A output is selected
+(the default), the input PDF is partially reconstructed by Ghostscript.
+When ``--force-ocr`` is used, all pages are rasterized and reconverted
+to PDF, which could remove malware in embedded images.
+
+Limiting CPU usage
+------------------
+
+OCRmyPDF will attempt to use all available CPUs and storage, so
+executing ``nice ocrmypdf`` or limiting the number of jobs with the
+``--jobs`` argument may ensure the server remains responsive. Another option
+would be to run OCRmyPDF jobs inside a Docker container, a virtual machine,
+or a cloud instance, which can impose its own limits on CPU usage and be
+terminated "from orbit" if it fails to complete.
+
+Temporary storage requirements
+------------------------------
+
+OCRmyPDF will use a large amount of temporary storage for its work,
+proportional to the total number of pixels needed to rasterize the PDF.
+The raster image of a 8.5×11" color page at 300 DPI takes 25 MB
+uncompressed; OCRmyPDF saves its intermediates as PNG, but that still
+means it requires about 9 MB per intermediate based on average
+compression ratios. Multiple intermediates per page are also required,
+depending on the command line given. A rule of thumb would be to allow
+100 MB of temporary storage per page in a file – meaning that a small
+cloud servers or small VM partitions should be provisioned with plenty
+of extra space, if say, a 500 page file might be sent.
+
+To change the temporary directory, see :ref:`tmpdir`.
+
+On Amazon Web Services or other cloud vendors, consider setting your
+temporary directory to `empheral
+storage <https://docs.aws.amazon.com/AWSEC2/latest/UserGuide/InstanceStorage.html>`__.
+
+Timeouts
+--------
+
+To prevent excessively long OCR jobs consider setting
+``--tesseract-timeout`` and/or ``--skip-big`` arguments. ``--skip-big``
+is particularly helpful if your PDFs include documents such as reports
+on standard page sizes with large images attached - often large images
+are not worth OCR'ing anyway.
+
+Document management systems
+---------------------------
+
+If you are looking for a full document management system, consider
+`paperless-ngx <https://github.com/paperless-ngx/paperless-ngx>`__,
+which is a web application that uses OCRmyPDF to automatically OCR and
+archive documents.
+
+Commercial OCR alternatives
+---------------------------
+
+The author also provides professional services that include OCR and
+building databases around PDFs, and is happy to provide consultation.
+
+Abbyy Cloud OCR is viable commercial alternative with a web services
+API. Amazon Textract, Google Cloud Vision, and Microsoft Azure
+Computer Vision provide advanced OCR but have less PDF rendering capability.
@@ -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'

@@ -78,7 +78,6 @@ author = 'James R. Barlow'
 import os
 from importlib.metadata import version as package_version

-
 on_rtd = os.environ.get('READTHEDOCS') == 'True'

 if on_rtd:
@@ -18,7 +18,7 @@ work you're contemplating is already half-done in a development branch.
 Code style
 ==========

-We use PEP8, ``black`` for code formatting and ``isort`` for import sorting. The
+We use PEP8, ``black`` for code formatting and ``ruff`` for everything else. The
 settings for these programs are in ``pyproject.toml`` and ``setup.cfg``. Pull
 requests should follow the style guide. One difference we use from "black" style
 is that strings shown to the user are always in double quotes (``"``) and strings
@@ -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
-contribute or license to us.
+MIT, with a few minor exceptions. Please contribute only content that you own
+or have the right to contribute under these licenses.
@@ -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 or PDF/A conversion.
+processing without performing OCR (by causing OCR to time out). This works
+if all you want to is to apply image processing or PDF/A conversion.

 .. code-block:: bash

    ocrmypdf --tesseract-timeout=0 --remove-background input.pdf output.pdf

+.. versionchanged:: v14.1.0
+
+    Prior to this version, ``--tesseract-timeout 0`` would prevent other
+    uses of Tesseract, such as deskewing, from working. This is no longer
+    the case. Use ``--tesseract-non-ocr-timeout`` to control the timeout
+    for non-OCR operations, if needed.
+
 Optimize images without performing OCR
 --------------------------------------

@@ -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
@@ -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.
@@ -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.
+
@@ -8,14 +8,13 @@
 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
-installation and may require Docker engine configuration.
-
-OCRmyPDF needs a generous amount of RAM, CPU cores, temporary storage
+installation and may require Docker engine configuration. OCRmyPDF
+needs a generous amount of RAM, CPU cores, temporary storage
 space, whether running in a Docker container or on its own. It may be
 necessary to ensure the container is provisioned with additional
 resources.
@@ -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
-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
+OCRmyPDF will use all available CPU cores. See the Docker documentation for
 `adjusting memory and CPU on other platforms <https://docs.docker.com/config/containers/resource_constraints/>`__.

 Using the Docker image on the command line
@@ -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
@@ -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

@@ -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``               |
 +-------------------------------+-----------------------------------------+
@@ -72,8 +72,7 @@ Debian and Ubuntu 20.04 or newer
 | |ubu-2004| |ubu-2204|                         |
 +-----------------------------------------------+

-Users of Debian 9 ("stretch") or later, or Ubuntu 18.04 or later, including users
-of Windows Subsystem for Linux, may simply
+Users of Debian or Ubuntu may simply

 .. code-block:: bash

@@ -100,11 +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
-    :alt: Fedora 35
+.. |fedora-37| image:: https://repology.org/badge/version-for-repo/fedora_37/ocrmypdf.svg
+    :alt: Fedora 37

-.. |fedora-36| image:: https://repology.org/badge/version-for-repo/fedora_36/ocrmypdf.svg
-    :alt: Fedora 36
+.. |fedora-38| image:: https://repology.org/badge/version-for-repo/fedora_38/ocrmypdf.svg
+    :alt: Fedora 38

 .. |fedora-rawhide| image:: https://repology.org/badge/version-for-repo/fedora_rawhide/ocrmypdf.svg
    :alt: Fedore Rawhide
@@ -114,14 +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>`__.
@@ -156,7 +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`.

@@ -275,6 +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
 --------------------

@@ -293,7 +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:
@@ -344,18 +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
@@ -374,29 +382,33 @@ Native Windows

 You must install the following for Windows:

-* Python 3.8 (64-bit) or later
-* Tesseract 4.1.1 (64-bit) or later
-* Ghostscript 9.50 (64-bit) or later
+* Python 64-bit
+* Tesseract 64-bit
+* Ghostscript 64-bit

-Using the `Chocolatey <https://chocolatey.org/>`_ package manager, install the
-following when running in an Administrator command prompt:
+Using the `winget <https://docs.microsoft.com/en-us/windows/package-manager/winget/>`_
+package manager:
+
+* ``winget install -e --id Python.Python.3.11``
+* ``winget install -e --id UB-Mannheim.TesseractOCR``
+* ``winget install -e --id ArtifexSoftware.GhostScript``
+
+
+(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
-and pngquant. Chocolatey may also need to install the Windows Visual C++ Runtime
-DLLs or other Windows patches, and may require a reboot.
+Either set of commands will install the required software. At the mmoment there is no
+single command to install Windows.

 You may then use ``pip`` to install ocrmypdf. (This can performed by a user or
 Administrator.):

-* ``pip install ocrmypdf``
-
-Chocolatey automatically selects appropriate versions of these applications. Please make sure
-you are installing the 64-bit versions.
+* ``python3 -m pip install ocrmypdf``

 OCRmyPDF will check the Windows Registry and standard locations in your Program Files
 for third party software it needs (specifically, Tesseract and Ghostscript). To
@@ -408,12 +420,12 @@ 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 might work, but is not supported.
+    32-bit Windows is not supported.

 Windows Subsystem for Linux
 ---------------------------
@@ -440,7 +452,7 @@ Cygwin64

 First install the the following prerequisite Cygwin packages using ``setup-x86_64.exe``::

-    python38 (or later)
+    python39 (or later)
    python3?-devel
    python3?-pip
    python3?-lxml
@@ -449,7 +461,7 @@ 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
@@ -460,13 +472,6 @@ 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
@@ -518,21 +523,6 @@ 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
@@ -551,21 +541,6 @@ 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
 -------------------------------------

@@ -575,13 +550,16 @@ manager. ``pip`` cannot provide them.

 The following versions are required:

-  Python 3.8 or newer
-  Ghostscript 9.50 or newer
+-  Python 3.9 or newer
+-  Ghostscript 9.55 or newer
 -  Tesseract 4.1.1 or newer
 -  jbig2enc 0.29 or newer
 -  pngquant 2.5 or newer
 -  unpaper 6.1

+We recommend 64-bit versions of all software. (32-bit versions are not
+supported, although on Linux, they may still work.)
+
 jbig2enc, pngquant, and unpaper are optional. If missing certain
 features are disabled. OCRmyPDF will discover them as soon as they are
 available.
@@ -608,7 +586,7 @@ unfortunately, the ``pip install`` command cannot satisfy all of them.
 Installing HEAD revision from sources
 =====================================

-If you have ``git`` and Python 3.8 or newer installed, you can install
+If you have ``git`` and Python 3.9 or newer installed, you can install
 from source. When the ``pip`` installer runs, it will alert you if
 dependencies are missing.

@@ -637,9 +615,9 @@ system-wide:

 .. code-block:: bash

-    git clone -b master https://github.com/ocrmypdf/OCRmyPDF.git
-    python3 -m venv venv
-    source venv/bin/activate
+    git clone -b main https://github.com/ocrmypdf/OCRmyPDF.git
+    python3 -m venv .venv
+    source .venv/bin/activate
    cd OCRmyPDF
    pip install .

@@ -664,9 +642,9 @@ To install all of the development and test requirements:

 .. code-block:: bash

-    git clone -b master https://github.com/ocrmypdf/OCRmyPDF.git
-    python -m venv
-    source venv/bin/activate
+    git clone -b main https://github.com/ocrmypdf/OCRmyPDF.git
+    python -m .venv
+    source .venv/bin/activate
    cd OCRmyPDF
    pip install -e .[test]

@@ -687,3 +665,18 @@ 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.
@@ -193,7 +193,7 @@ Ghostscript also imposes some limitations:
   (Modern Ghostscript can copy JPEG images without transcoding them.)
 -  Ghostscript's PDF/A conversion removes any XMP metadata that is not
   one of the standard XMP metadata namespaces for PDFs. In particular,
-   PRISM Metdata is removed.
+   PRISM Metadata is removed.
 -  Ghostscript's PDF/A conversion seems to remove or deactivate
   hyperlinks and other active content.

@@ -59,5 +59,9 @@ To turn on JBIG2 lossy mode, add the argument ``--jbig2-lossy``.
 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.*
@@ -12,7 +12,7 @@ OCRmyPDF uses Tesseract for OCR, and relies on its language packs for all langua
 On most platforms, English is installed with Tesseract by default, but not always.

 Tesseract supports `most
-languages <https://github.com/tesseract-ocr/tesseract/blob/master/doc/tesseract.1.asc#languages>`__.
+languages <https://github.com/tesseract-ocr/tesseract/blob/main/doc/tesseract.1.asc#languages>`__.
 Languages are identified by standardized three-letter codes (called ISO 639-2 Alpha-3).
 Tesseract's documentation also lists the three-letter code for your language.
 Some are anglicized, e.g. Spanish is ``spa`` rather than ``esp``, while others
@@ -70,13 +70,13 @@ 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

@@ -101,7 +101,7 @@ derived Docker image as
 Windows users
 =============

-The Tesseract installer provided by Chocolatey currently includes only English language. 
-To install other languages, download the respective language pack (``.traineddata`` file) 
-from https://github.com/tesseract-ocr/tessdata/ and place it in 
+The Tesseract installer provided by Chocolatey currently includes only English language.
+To install other languages, download the respective language pack (``.traineddata`` file)
+from https://github.com/tesseract-ocr/tessdata/ and place it in
 ``C:\\Program Files\\Tesseract-OCR\\tessdata`` (or wherever Tesseract OCR is installed).
@@ -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.
@@ -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
-optimization and ``3`` implements all options. ``1``, the default, performs only
-safe and lossless optimizations. (This is similar to GCC's optimization
-parameter.) The exact type of optimizations performed will vary over time.
+.. list-table:: Title
+   :widths: 33 6 60
+   :header-rows: 1

-PDF optimization requires third-party, optional tools for certain optimizations.
-If these are not installed or cannot be found by OCRmyPDF, optimization will not
-be as good.
+    * - Optimization level
+      - Shorthand
+      - Description
+    * - ``--optimize 0``
+      - ``-O0``
+      - Disable most optimizations.
+    * - ``--optimize 1`` (default)
+      - ``-O1``
+      - Safe and lossless optimizations.
+    * - ``--optimize 2``
+      - ``-O2``
+      - Safe and lossy optimizations.
+    * - ``--optimize 3``
+      - ``-O3``
+      - Aggressive lossy optimizations.
+
+The exact type of optimizations performed will vary over time, and depend on
+the availability of third-party tools.
+
+Despite optimizations, OCRmyPDF might still increase the overall file size,
+since it must embed information about the recognized text, and depending on the
+settings chosen, may not be able to represent the output file as compactly as
+the input file.

 Optimizations that always occurs
 ================================

 OCRmyPDF will automatically replace obsolete or inferior compression schemes
-such as RLE or LZW with superior schemes such as Deflate and converting
-monochrome images to CCITT G4. Since this is harmless it always occurs and there
+such as RLE or LZW with superior schemes such as Deflate, and convert
+monochrome images to CCITT G4. Since this is lossless, it always occurs and there
 is no way to disable it. Other non-image compressed objects are compressed as
 well.

@@ -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
-actually slightly increases the file size.
+reduces the latency of viewing a PDF both online and from local storage, in
+exchange for a slight increase in file size.

 To disable this optimization and all others, use ``ocrmypdf --optimize 0 ...``
 or the shorthand ``-O0``.

+Adobe Acrobat might not report the file as being "fast web view".
+
 Lossless optimizations
 ======================

@@ -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
-`article <https://theinvisiblethings.blogspot.ca/2013/02/converting-untrusted-pdfs-into-trusted.html>`__
-describes a high-paranoia method which allows potentially hostile PDFs
-to be viewed and rasterized safely in a disposable virtual machine. A
-trusted PDF created in this manner is converted to images and loses all
-information making it searchable and losing all compression. OCRmyPDF
-could be used to restore searchability.
+If you do not trust a PDF or its source, do not open it or use OCRmyPDF
+on it. Consider using a Docker container or virtual machine to isolate
+an untrusted PDF from your system.

 How OCRmyPDF processes PDFs
 ===========================
@@ -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
-OCRmyPDF will succeed, but offers no security guarantees. qpdf is also
+scanners, are not well-formed files. QPDF makes it more likely that
+OCRmyPDF will succeed, but offers no security guarantees. QPDF is also
 used to split the PDF into single page PDFs.

 Finally, OCRmyPDF rasterizes each page of the PDF using
@@ -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:
-
-Using OCRmyPDF online or as a service
-=====================================
-
-OCRmyPDF is not designed for use as a public web service where a
-malicious user could upload a chosen PDF. In particular, it is not
-necessarily secure against PDF malware or PDFs that cause denial of
-service. OCRmyPDF relies on Ghostscript, and therefore, if deployed
-online one should be prepared to comply with Ghostscript's Affero GPL
-license, and any other licenses.
-
-Setting aside these concerns, a side effect of OCRmyPDF is that it may
-incidentally sanitize PDFs containing certain types of malware. It
-repairs the PDF with pikepdf/libqpdf, which could correct malformed PDF
-structures that are part of an attack. When PDF/A output is selected
-(the default), the input PDF is partially reconstructed by Ghostscript.
-When ``--force-ocr`` is used, all pages are rasterized and reconverted
-to PDF, which could remove malware in embedded images.
-
-OCRmyPDF should be relatively safe to use in a trusted intranet, with
-some considerations:
-
-Limiting CPU usage
------------------
-
-OCRmyPDF will attempt to use all available CPUs and storage, so
-executing ``nice ocrmypdf`` or limiting the number of jobs with the
-``-j`` argument may ensure the server remains available. Another option
-would be to run OCRmyPDF jobs inside a Docker container, a virtual machine,
-or a cloud instance, which can impose its own limits on CPU usage and be
-terminated "from orbit" if it fails to complete.
-
-Temporary storage requirements
------------------------------
-
-OCRmyPDF will use a large amount of temporary storage for its work,
-proportional to the total number of pixels needed to rasterize the PDF.
-The raster image of a 8.5×11" color page at 300 DPI takes 25 MB
-uncompressed; OCRmyPDF saves its intermediates as PNG, but that still
-means it requires about 9 MB per intermediate based on average
-compression ratios. Multiple intermediates per page are also required,
-depending on the command line given. A rule of thumb would be to allow
-100 MB of temporary storage per page in a file – meaning that a small
-cloud servers or small VM partitions should be provisioned with plenty
-of extra space, if say, a 500 page file might be sent.
-
-To check temporary storage usage on actual files, run
-``ocrmypdf -k ...`` which will preserve and print the path to temporary
-storage when the job is done.
-
-To change where temporary files are stored, change the ``TMPDIR``
-environment variable for ocrmypdf's environment. (Python's
-``tempfile.gettempdir()`` returns the root directory in which temporary
-files will be stored.) For example, one could redirect ``TMPDIR`` to a
-large RAM disk to avoid wear on HDD/SSD and potentially improve
-performance. On Amazon Web Services, ``TMPDIR`` can be set to `empheral
-storage <https://docs.aws.amazon.com/AWSEC2/latest/UserGuide/InstanceStorage.html>`__.
-
-Timeouts
--------
-
-To prevent excessively long OCR jobs consider setting
-``--tesseract-timeout`` and/or ``--skip-big`` arguments. ``--skip-big``
-is particularly helpful if your PDFs include documents such as reports
-on standard page sizes with large images attached - often large images
-are not worth OCR'ing anyway.
-
-Commercial alternatives
-----------------------
-
-The author also provides professional services that include OCR and
-building databases around PDFs, and is happy to provide consultation.
-
-Abbyy Cloud OCR is viable commercial alternative with a web services
-API. Amazon Textract, Google Cloud Vision, and Microsoft Azure 
-Computer Vision provide advanced OCR but have less PDF rendering capability.
-
-Password protection, digital signatures and certification
-=========================================================
+Password protected PDFs
+=======================

 Password protected PDFs usually have two passwords, and owner and user
 password. When the user password is set to empty, PDF readers will open
-the file automatically and marked it as "(SECURED)". While not as
-reliable as a digital signature, this indicates that whoever set the
-password approved of the file at that time. When the user password is
-set, the document cannot be viewed without the password.
+the file automatically and mark it as "(SECURED)". Password security can
+also request certain restrictions on the PDF, but anyone can remove these
+restrictions if they have either the owner *or* user password. Passwords
+mainly present a barrier for casual users.

-Either way, OCRmyPDF does not remove passwords from PDFs and exits with
-an error on encountering them.
+OCRmyPDF cannot remove passwords from PDFs. If you want to remove a
+password from a PDF, you must use other software, such as ``qpdf``.

-``qpdf`` can remove passwords. If the owner and user password are set, a
+If the owner and user password are set, a
 password is required for ``qpdf``. If only the owner password is set, then the
-password can be stripped, even if one does not have the owner password.
+password can be stripped, even if one does not have the owner password. To
+remove the password from a using QPDF, use:

-After OCR is applied, password protection is not permitted on PDF/A
-documents but the file can be converted to regular PDF.
+.. code-block:: bash
+
+   qpdf --decrypt --password='abc123' input.pdf no_password.pdf
+
+Then you can run OCRmyPDF on the file.
+
+In its default mode, OCRmyPDF generates PDF/A. Passwords may not be set on PDF/A
+documents. If you want to set a password on the output PDF, you must
+specify ``--output-type pdf``.
+
+Signature images
+================

 Many programs exist which are capable of inserting an image of someone's
 signature. On its own, this offers no security guarantees. It is trivial
 to remove the signature image and apply it to other files. This practice
 offers no real security.

+Digital signatures
+==================
+
 Important documents can be digitally signed and certified to attest to
-their authorship. OCRmyPDF cannot do this. Open source tools such as
-pdfbox (Java) have this capability as does Adobe Acrobat.
+their authorship, approval or execution of a legal agreement. OCRmyPDF
+will detect signed PDFs and will not modify them, unless the
+``--invalidate-digital-signatures`` option is used, which will
+invalidate any signatures. (The signature may still be present in the PDF
+if opened, but PDF readers will not validate it.)
+
+A digital signature adds a cryptographic hash of the document to the
+document, so tamper protection is provided. That also precludes OCRmyPDF
+from modifying the document and preserving the signature.
+
+Digital signatures are not the same as a signature image. A digital
+signature is a cryptographic hash of the document that is encrypted with
+the author's private key. The signature is decrypted with the author's
+public key. The public key is usually distributed by a certificate
+authority. The signature is then verified by the PDF reader. If the
+document is modified, the signature will be invalidated.
+
+Certificate-encrypted PDFs
+==========================
+
+PDFs can be encrypted with a certificate. This is a more secure form of
+encryption than a password. The certificate is usually issued by a
+certificate authority. A certificate is used to encrypt the document using
+the public key for the benefit of a specific recipient who possesses
+the private key.
+
+OCRmyPDF cannot open certificate-encrypted PDFs. If you have the
+certificate, you can use other PDF software, such as Acrobat, to
+decrypt the PDF.
@@ -28,6 +28,144 @@ tagged yet.

 .. |OCRmyPDF PyPI| image:: https://img.shields.io/pypi/v/ocrmypdf.svg

+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
 =======

@@ -711,7 +849,7 @@ 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
@@ -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

@@ -6,52 +6,56 @@ set -o errexit

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

    COMPREPLY=( $( compgen -W "$arguments" -- "$cur") )
@@ -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
@@ -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"
@@ -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
@@ -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
+```
@@ -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"]
@@ -2,7 +2,7 @@
 # SPDX-FileCopyrightText: 2017 Enantiomerie
 # SPDX-License-Identifier: MIT

-"""Example OCRmyPDF for Synology NAS"""
+"""Example OCRmyPDF for Synology NAS."""

 from __future__ import annotations

@@ -3,6 +3,8 @@
 # SPDX-FileCopyrightText: 2020 James R Barlow <https://github.com/jbarlow83>
 # SPDX-License-Identifier: MIT

+"""Watch a directory for new PDFs and OCR them."""
+
 from __future__ import annotations

 import json
@@ -38,6 +40,7 @@ DESKEW = getenv_bool('OCR_DESKEW')
 OCR_JSON_SETTINGS = json.loads(os.getenv('OCR_JSON_SETTINGS', '{}'))
 POLL_NEW_FILE_SECONDS = int(os.getenv('OCR_POLL_NEW_FILE_SECONDS', '1'))
 USE_POLLING = getenv_bool('OCR_USE_POLLING')
+RETRIES_LOADING_FILE = int(os.getenv('OCR_RETRIES_LOADING_FILE', '5'))
 LOGLEVEL = os.getenv('OCR_LOGLEVEL', 'INFO')
 PATTERNS = ['*.pdf', '*.PDF']

@@ -64,7 +67,7 @@ def wait_for_file_ready(file_path):
    # watchdog event before the file is actually fully on disk, causing
    # pikepdf to fail.

-    retries = 5
+    retries = RETRIES_LOADING_FILE
    while retries:
        try:
            pdf = pikepdf.open(file_path)
@@ -142,6 +145,7 @@ def main():
        f"DESKEW: {DESKEW}\n"
        f"ARGS: {OCR_JSON_SETTINGS}\n"
        f"POLL_NEW_FILE_SECONDS: {POLL_NEW_FILE_SECONDS}\n"
+        f"RETRIES_LOADING_FILE: {RETRIES_LOADING_FILE}\n"
        f"USE_POLLING: {USE_POLLING}\n"
        f"LOGLEVEL: {LOGLEVEL}"
    )
@@ -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')
@@ -1,11 +1,7 @@
 # SPDX-FileCopyrightText: 2022 James R. Barlow
 # SPDX-License-Identifier: MPL-2.0
 [build-system]
-requires = [
-  "setuptools >= 61",
-  "setuptools_scm[toml] >= 7.0.5",
-  "wheel"
-]
+requires = ["setuptools >= 61", "setuptools_scm[toml] >= 7.0.5", "wheel"]
 build-backend = "setuptools.build_meta"

 [project]
@@ -13,23 +9,21 @@ 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 = ">=3.8"
+license = { text = "MPL-2.0" }
+requires-python = ">=3.9"
 dependencies = [
-  "Pillow>=8.2.0",
-  "coloredlogs>=14.0",
+  "Pillow>=10.0.1",
  "deprecation>=2.1.0",
-  "img2pdf>=0.3.0", # pure Python
+  "img2pdf>=0.4.4",
  "packaging>=20",
-  "pdfminer.six>=20201018",
-  "pikepdf>=5.0.1",
+  "pdfminer.six>=20220319",
+  "pikepdf>=8",
  "pluggy>=0.13.0",
-  "reportlab>=3.5.66",
-  "tqdm>=4",
-  "importlib-resources>=5;python_version<'3.9'",  # until Python 3.9
+  "reportlab>=3.6.8",
+  "rich>=13",
  "typing-extensions>=4;python_version<'3.10'",
 ]
-authors = [{name = "James R. Barlow", email="james@purplerock.ca"}]
+authors = [{ name = "James R. Barlow", email = "james@purplerock.ca" }]
 classifiers = [
  "Development Status :: 5 - Production/Stable",
  "Environment :: Console",
@@ -37,27 +31,17 @@ classifiers = [
  "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 :: MacOS",
+  "Operating System :: Microsoft :: Windows",
  "Operating System :: POSIX",
  "Operating System :: POSIX :: BSD",
  "Operating System :: POSIX :: Linux",
  "Programming Language :: Python :: 3",
-  "Programming Language :: Python :: 3 :: Only",
-  "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",
-]
+keywords = ["PDF", "OCR", "optical character recognition", "PDF/A", "scanning"]

 [project.urls]
 Documentation = "https://ocrmypdf.readthedocs.io/"
@@ -68,16 +52,17 @@ Tracker = "https://github.com/ocrmypdf/OCRmyPDF/issues"
 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
+  "coverage[toml]>=6.2",
+  "hypothesis>=6.36.0",
+  "pytest>=6.2.5",
+  "pytest-cov>=3.0.0",
+  "pytest-xdist>=2.5.0",
+  "python-xmp-toolkit==2.0.1", # also requires apt-get install libexempi3
  "types-Pillow",
  "types-humanfriendly",
 ]
 watcher = ["watchdog>=1.0.2"]
-webservice = ["Flask>=1"]
+webservice = ["Flask>=2.0.1"]

 [project.scripts]
 ocrmypdf = "ocrmypdf.__main__:run"
@@ -92,11 +77,11 @@ namespaces = false
 [tool.setuptools_scm]

 [tool.distutils.bdist_wheel]
-python-tag = "py38"
+python-tag = "py39"

 [tool.black]
 line-length = 88
-target-version = ["py38", "py39", "py310", "py311"]
+target-version = ["py39", "py310", "py311"]
 skip-string-normalization = true
 include = '\.pyi?$'
 exclude = '''
@@ -137,28 +122,7 @@ exclude_lines = [
  "if 0:",
  "if False:",
  "if __name__ == .__main__.:",
-  "if TYPE_CHECKING:"
-]
-
-[tool.isort]
-profile = "black"
-known_first_party = "ocrmypdf"
-known_third_party = [
-  "PIL",
-  "flask",
-  "img2pdf",
-  "ocrmypdf",
-  "pdfminer",
-  "pikepdf",
-  "pkg_resources",
-  "pluggy",
-  "pytest",
-  "reportlab",
-  "setuptools",
-  "sphinx_rtd_theme",
-  "tqdm",
-  "watchdog",
-  "werkzeug"
+  "if TYPE_CHECKING:",
 ]

 [tool.pytest.ini_options]
@@ -180,11 +144,30 @@ module = [
  'pdfminer.*',
  'reportlab.*',
  'fitz',
-  'libxmp.utils'
+  'libxmp.utils',
 ]
 ignore_missing_imports = true

-[tool.pylint.basic]
-good-names = ["i", "j", "k", "ex", "Run", "_", "e", "p", "im", "w", "h", "m", "x", "y", "a", "b", "fp", "n", "f", "s", "v", "q", "dx", "dy"]
-logging-format-style = "old"
-disable = ["raw-checker-failed", "bad-inline-option", "locally-disabled", "file-ignored", "suppressed-message", "useless-suppression", "deprecated-pragma", "use-symbolic-message-instead", "logging-fstring-interpolation", "missing-function-docstring", "too-few-public-methods"]
+[tool.ruff]
+select = [
+  "D",    # pydocstyle
+  "E",    # pycodestyle
+  "W",    # pycodestyle
+  "F",    # pyflakes
+  "I001", # isort
+  "UP",   # pyupgrade
+]
+target-version = "py39"
+
+[tool.ruff.isort]
+known-first-party = ["ocrmypdf"]
+required-imports = ["from __future__ import annotations"]
+
+[tool.ruff.pydocstyle]
+convention = "google"
+
+[tool.ruff.per-file-ignores]
+"docs/conf.py" = ["D100", "D101", "D105"]
+"tests/*.py" = ["D100", "D101", "D102", "D103", "D105"]
+"misc/*.py" = ["D103", "D101", "D102"]
+"src/ocrmypdf/builtin_plugins/*.py" = ["D103", "D102", "D105"]
@@ -1,12 +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
@@ -17,8 +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_FONTPATH: $SNAP/usr/share/ghostscript/9.50/Resource/Font
+  GS_LIB: $SNAP/usr/share/ghostscript/9.55/Resource/Init
+  GS_FONTPATH: $SNAP/usr/share/ghostscript/9.55/Resource/Font
  LD_LIBRARY_PATH: $SNAP/usr/lib/x86_64-linux-gnu

 apps:
@@ -48,13 +49,16 @@ parts:
  jbig2enc:
    plugin: autotools
    source: https://github.com/agl/jbig2enc.git
-    source-tag: '0.29'
+    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
@@ -77,7 +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
@@ -29,3 +29,33 @@ from ocrmypdf.exceptions import (
 from ocrmypdf.pluginspec import OcrEngine, OrientationConfidence

 hookimpl = _HookimplMarker('ocrmypdf')
+
+__all__ = [
+    '__version__',
+    'BadArgsError',
+    'configure_logging',
+    'DpiError',
+    'EncryptedPdfError',
+    'Executor',
+    'ExitCode',
+    'ExitCodeException',
+    'helpers',
+    'hocrtransform',
+    'hookimpl',
+    'InputFileError',
+    'MissingDependencyError',
+    'ocr',
+    'OcrEngine',
+    'OrientationConfidence',
+    'OutputFileAccessError',
+    'PageContext',
+    'pdfa',
+    'PdfContext',
+    'pdfinfo',
+    'PriorOcrFoundError',
+    'PROGRAM_NAME',
+    'SubprocessOutputError',
+    'TesseractConfigError',
+    'UnsupportedImageFormatError',
+    'Verbosity',
+]
@@ -11,7 +11,6 @@ import os
 import signal
 import sys
 from contextlib import suppress
-from multiprocessing import set_start_method

 from ocrmypdf import __version__
 from ocrmypdf._plugin_manager import get_parser_options_plugins
@@ -29,10 +28,16 @@ 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):
@@ -7,7 +7,8 @@ from __future__ import annotations

 import threading
 from abc import ABC, abstractmethod
-from typing import Callable, Iterable
+from collections.abc import Iterable
+from typing import Callable


 def _task_noop(*_args, **_kwargs):
@@ -51,8 +52,7 @@ class Executor(ABC):
        task_arguments: Iterable | None = None,
        task_finished: Callable | None = None,
    ) -> None:
-        """
-        Set up parallel execution and progress reporting.
+        """Set up parallel execution and progress reporting.

        Args:
            use_threads: If ``False``, the workload is the sort that will benefit from
@@ -60,7 +60,7 @@ class Executor(ABC):
                heavily, and parallelizing it with threads is not expected to be
                performant).
            max_workers: The maximum number of workers that should be run.
-            tdqm_kwargs: Arguments to set up the progress bar.
+            tqdm_kwargs: Arguments to set up the progress bar.
            worker_initializer: Called when a worker is initialized, in the worker's
                execution context. If the child workers are processes, it must be
                possible to marshall/pickle the worker initializer.
@@ -73,7 +73,6 @@ class Executor(ABC):
                task. This runs in the parent's context, but the parameters must be
                marshallable to the worker.
        """
-
        if not task_arguments:
            return  # Nothing to do!
        if not worker_initializer:
@@ -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
@@ -1,14 +1,13 @@
 # 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 io import BytesIO
 from os import fspath
 from pathlib import Path
@@ -21,31 +20,49 @@ from ocrmypdf.exceptions import SubprocessOutputError
 from ocrmypdf.helpers import Resolution
 from ocrmypdf.subprocess import get_version, run, run_polling_stderr

-# Remove this workaround when we require Pillow >= 10
-try:
-    Transpose = Image.Transpose  # type: ignore
-except AttributeError:
-    # Pillow 9 shim
-    Transpose = Image  # type: ignore
+COLOR_CONVERSION_STRATEGIES = frozenset(
+    [
+        'CMYK',
+        'Gray',
+        'LeaveColorUnchanged',
+        'RGB',
+        'UseDeviceIndependentColor',
+    ]
+)

 log = logging.getLogger(__name__)

-# Most reliable what to get the bitness of Python interpreter, according to Python docs
-_IS_64BIT = sys.maxsize > 2**32

-_GSWIN = None
-if os.name == 'nt':
-    if _IS_64BIT:
-        _GSWIN = 'gswin64c'
-    else:
-        _GSWIN = 'gswin32c'
+class DuplicateFilter(logging.Filter):
+    """Filter out duplicate log messages."""

-GS = _GSWIN if _GSWIN else 'gs'
-del _GSWIN
+    def __init__(self, logger: logging.Logger):
+        self.last: logging.LogRecord | None = None
+        self.count = 0
+        self.logger = logger
+
+    def filter(self, record):
+        if self.last and record.msg == self.last.msg:
+            self.count += 1
+            return False
+        else:
+            if self.count >= 1:
+                rep_msg = f"(previous message repeated {self.count} times)"
+                self.count = 0  # Avoid infinite recursion
+                self.logger.log(self.last.levelno, rep_msg)
+            self.last = record
+            return True


-def version():
-    return get_version(GS)
+log.addFilter(DuplicateFilter(log))
+
+
+# Ghostscript executable - gswin32c is not supported
+GS = 'gswin64c' if os.name == 'nt' else 'gs'
+
+
+def version() -> Version:
+    return Version(get_version(GS))


 def _gs_error_reported(stream) -> bool:
@@ -63,6 +80,7 @@ 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)
@@ -83,6 +101,7 @@ 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',
            '-',
@@ -110,11 +129,11 @@ 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)
@@ -158,9 +177,11 @@ 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.
@@ -186,13 +207,16 @@ def generate_pdfa(
            "-dAutoFilterGrayImages=true",
        ]

-    strategy = 'LeaveColorUnchanged'
-    gs_version = Version(version())
+    gs_version = version()
    if gs_version == Version('9.56.0'):
        # 9.56.0 breaks our OCR, should be fixed in 9.56.1
        # https://bugs.ghostscript.com/show_bug.cgi?id=705187
        compression_args.append('-dNEWPDF=false')

+    if os.name == 'nt':
+        # Windows has lots of fatal "permission denied" errors
+        stop_on_error = False
+
    # nb no need to specify ProcessColorModel when ColorConversionStrategy
    # is set; see:
    # https://bugs.ghostscript.com/show_bug.cgi?id=699392
@@ -202,15 +226,16 @@ 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",
            "-",
@@ -241,14 +266,9 @@ def generate_pdfa(
        # If there is an error we log the whole stderr, except for filtering
        # duplicates.
        if _gs_error_reported(stderr):
-            last_part = None
-            repcount = 0
+            # Ghostscript outputs the pattern **** Error: ....  frequently.
+            # Occasionally the error message is spammed many times. We filter
+            # out duplicates of this message using the filter above. We use
+            # the **** pattern to split the stderr into parts.
            for part in stderr.split('****'):
-                if part != last_part:
-                    if repcount > 1:
-                        log.error(f"(previous error message repeated {repcount} times)")
-                        repcount = 0
-                    log.error(part)
-                else:
-                    repcount += 1
-                last_part = part
+                log.error(part)
@@ -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():
-    return get_version('jbig2', regex=r'jbig2enc (\d+(\.\d+)*).*')
+def version() -> Version:
+    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)
@@ -40,11 +44,13 @@ def convert_group(*, cwd, infiles, out_prefix):


 def convert_group_mp(args):
-    return convert_group(cwd=args[0], infiles=args[1], out_prefix=args[2])
+    return convert_group(
+        cwd=args[0], infiles=args[1], out_prefix=args[2], threshold=args[3]
+    )


-def convert_single(*, cwd, infile, outfile):
-    args = ['jbig2', '-p', infile]
+def convert_single(*, cwd, infile, outfile, threshold):
+    args = ['jbig2', '--pdf', '-t', str(threshold), infile]
    with open(outfile, 'wb') as fstdout:
        proc = run(args, cwd=cwd, stdout=fstdout, stderr=PIPE)
    proc.check_returncode()
@@ -52,4 +58,6 @@ def convert_single(*, cwd, infile, outfile):


 def convert_single_mp(args):
-    return convert_single(cwd=args[0], infile=args[1], outfile=args[2])
+    return convert_single(
+        cwd=args[0], infile=args[1], outfile=args[2], threshold=args[3]
+    )
@@ -1,7 +1,7 @@
 # SPDX-FileCopyrightText: 2022 James R. Barlow
 # SPDX-License-Identifier: MPL-2.0

-"""Interface to pngquant executable"""
+"""Interface to pngquant executable."""

 from __future__ import annotations

@@ -10,14 +10,15 @@ from io import BytesIO
 from pathlib import Path
 from subprocess import PIPE

+from packaging.version import Version
 from PIL import Image

 from ocrmypdf.exceptions import MissingDependencyError
 from ocrmypdf.subprocess import get_version, run


-def version():
-    return get_version('pngquant', regex=r'(\d+(\.\d+)*).*')
+def version() -> Version:
+    return Version(get_version('pngquant', regex=r'(\d+(\.\d+)*).*'))


 def available():
@@ -1,7 +1,7 @@
 # SPDX-FileCopyrightText: 2022 James R. Barlow
 # SPDX-License-Identifier: MPL-2.0

-"""Interface to Tesseract executable"""
+"""Interface to Tesseract executable."""

 from __future__ import annotations

@@ -34,10 +34,12 @@ HOCR_TEMPLATE = """<?xml version="1.0" encoding="UTF-8"?>
  <title></title>
 <meta http-equiv="Content-Type" content="text/html;charset=utf-8" />
  <meta name='ocr-system' content='tesseract 4.1.1' />
-  <meta name='ocr-capabilities' content='ocr_page ocr_carea ocr_par ocr_line ocrx_word ocrp_wconf'/>
+  <meta name='ocr-capabilities'
+    content='ocr_page ocr_carea ocr_par ocr_line ocrx_word ocrp_wconf'/>
 </head>
 <body>
-  <div class='ocr_page' id='page_1' title='image "_blank.png"; bbox 0 0 {0} {1}; ppageno 0'>
+  <div class='ocr_page' id='page_1'
+    title='image "_blank.png"; bbox 0 0 {0} {1}; ppageno 0'>
  </div>
 </body>
 </html>
@@ -52,7 +54,7 @@ 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
@@ -104,19 +106,20 @@ 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:
-    return get_version('tesseract', regex=r'tesseract\s(.+)')
+def version() -> Version:
+    return TesseractVersion(get_version('tesseract', regex=r'tesseract\s(.+)'))


 def has_thresholding() -> bool:
    """Does Tesseract have -c thresholding method capability?"""
-    return version() >= '5.0'
+    return version() >= Version('5.0')


 def get_languages() -> set[str]:
@@ -230,6 +233,7 @@ 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


@@ -280,8 +284,10 @@ 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
-    the same size as the input image."""
+    """Produce a .hocr file that reports no text detected.
+
+    Ensures page is the same size as the input image.
+    """
    with Image.open(image) as im:
        w, h = im.size

@@ -1,7 +1,7 @@
 # SPDX-FileCopyrightText: 2022 James R. Barlow
 # SPDX-License-Identifier: MPL-2.0

-"""Interface to unpaper executable"""
+"""Interface to unpaper executable."""

 from __future__ import annotations

@@ -9,19 +9,21 @@ 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 typing import Union

+from packaging.version import Version
 from PIL import Image

 from ocrmypdf.exceptions import MissingDependencyError, SubprocessOutputError
 from ocrmypdf.subprocess import get_version, run

 # unpaper documentation:
-# https://github.com/Flameeyes/unpaper/blob/master/doc/basic-concepts.md
+# https://github.com/Flameeyes/unpaper/blob/main/doc/basic-concepts.md


 if sys.version_info >= (3, 10):
@@ -67,8 +69,8 @@ class UnpaperImageTooLargeError(Exception):
        super().__init__(self.message)


-def version() -> str:
-    return get_version('unpaper')
+def version() -> Version:
+    return Version(get_version('unpaper'))


 SUPPORTED_MODES = {'1', 'L', 'RGB'}
@@ -37,7 +37,6 @@ def _update_resources(*, obj, font, font_key, procset):

    obj can be a page or Form XObject.
    """
-
    resources = _ensure_dictionary(obj, Name.Resources)
    fonts = _ensure_dictionary(resources, Name.Font)
    if font_key is not None and font_key not in fonts:
@@ -131,7 +130,8 @@ class OcrGrafter:
        text_misaligned = (text_rotation - content_rotation) % 360
        log.debug(
            f"Text rotation: (text, autorotate, content) -> text misalignment = "
-            f"({text_rotation}, {autorotate_correction}, {content_rotation}) -> {text_misaligned}"
+            f"({text_rotation}, {autorotate_correction}, {content_rotation}) -> "
+            f"{text_misaligned}"
        )

        if textpdf and self.font:
@@ -166,7 +166,6 @@ class OcrGrafter:
        the font to page 1 even if page 1 doesn't use it, so we have a way to get it
        back.
        """
-
        page0 = self.pdf_base.pages[0]
        _update_resources(
            obj=page0, font=self.font, font_key=self.font_key, procset=self.procset
@@ -199,8 +198,7 @@ class OcrGrafter:
        return self.output_file

    def _find_font(self, text):
-        """Copy a font from the filename text into pdf_base"""
-
+        """Copy a font from the filename text into pdf_base."""
        font, font_key = None, None
        possible_font_names = ('/f-0-0', '/F1')
        try:
@@ -233,8 +231,7 @@ class OcrGrafter:
        text_rotation: int,
        strip_old_text: bool,
    ):
-        """Insert the text layer from text page 0 on to pdf_base at page_num"""
-
+        """Insert the text layer from text page 0 on to pdf_base at page_num."""
        # pylint: disable=invalid-name

        log.debug("Grafting")
@@ -9,9 +9,9 @@ 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

@@ -59,7 +59,7 @@ class PdfContext:
 class PageContext:
    """Holds our context for a page.

-    Must be pickable, so stores only intrinsic/simple data elements or those
+    Must be pickle-able, so stores only intrinsic/simple data elements or those
    capable of their serializing themselves via ``__getstate__``.
    """

@@ -6,9 +6,18 @@
 from __future__ import annotations

 import logging
-from contextlib import suppress

-from tqdm import tqdm
+from rich.console import Console
+from rich.logging import RichHandler
+from rich.progress import (
+    BarColumn,
+    MofNCompleteColumn,
+    Progress,
+    TaskProgressColumn,
+    TextColumn,
+    TimeRemainingColumn,
+)
+from rich.table import Column


 class PageNumberFilter(logging.Filter):
@@ -23,21 +32,61 @@ class PageNumberFilter(logging.Filter):
        return True


-class TqdmConsole:
-    """Wrapper to log messages in a way that is compatible with tqdm progress bar
+class RichLoggingHandler(RichHandler):
+    def __init__(self, console: Console, **kwargs):
+        super().__init__(
+            console=console, show_level=False, show_time=False, markup=True, **kwargs
+        )

-    This routes log messages through tqdm so that it can print them above the
-    progress bar, and then refresh the progress bar, rather than overwriting
-    it which looks messy.
-    """

-    def __init__(self, file):
-        self.file = file
+class RichTqdmProgressAdapter:
+    """Adapt tqdm API to rich progress bar."""

-    def write(self, msg):
-        # When no progress bar is active, tqdm.write() routes to print()
-        tqdm.write(msg.rstrip(), end='\n', file=self.file)
+    def __init__(
+        self,
+        *,
+        console: Console,
+        desc: str,
+        total: float | None = None,
+        unit: str | None = None,
+        unit_scale: float | None = 1.0,
+        disable: bool = False,
+        **kwargs,
+    ):
+        self.progress = Progress(
+            TextColumn(
+                "[progress.description]{task.description}",
+                table_column=Column(min_width=20),
+            ),
+            BarColumn(),
+            TaskProgressColumn(),
+            MofNCompleteColumn(),
+            TimeRemainingColumn(),
+            console=console,
+            auto_refresh=True,
+            redirect_stderr=True,
+            redirect_stdout=False,
+            disable=disable,
+            **kwargs,
+        )
+        self.unit_scale = unit_scale
+        self.progress_bar = self.progress.add_task(
+            desc,
+            total=total * self.unit_scale
+            if total is not None and self.unit_scale is not None
+            else None,
+            unit=unit,
+        )

-    def flush(self):
-        with suppress(AttributeError):
-            self.file.flush()
+    def __enter__(self):
+        self.progress.start()
+        return self
+
+    def __exit__(self, exc_type, exc_value, traceback):
+        self.progress.refresh()
+        self.progress.stop()
+        return False
+
+    def update(self, value=None):
+        advance = self.unit_scale if value is None else value
+        self.progress.update(self.progress_bar, advance=advance)
@@ -10,11 +10,12 @@ 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 typing import Any, Iterable, Sequence
+from typing import Any, BinaryIO, TypeVar, cast

 import img2pdf
 import pikepdf
@@ -27,6 +28,7 @@ from ocrmypdf._jobcontext import PageContext, PdfContext
 from ocrmypdf._version import PROGRAM_NAME
 from ocrmypdf._version import __version__ as VERSION
 from ocrmypdf.exceptions import (
+    DigitalSignatureError,
    DpiError,
    EncryptedPdfError,
    InputFileError,
@@ -37,20 +39,29 @@ from ocrmypdf.helpers import IMG2PDF_KWARGS, Resolution, safe_symlink
 from ocrmypdf.hocrtransform import HocrTransform
 from ocrmypdf.pdfa import generate_pdfa_ps
 from ocrmypdf.pdfinfo import Colorspace, Encoding, PageInfo, PdfInfo
+from ocrmypdf.pluginspec import OrientationConfidence

-# 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: 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)
@@ -65,34 +76,32 @@ def triage_image_file(input_file: Path, output_file: Path, options) -> None:
            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...")
@@ -110,7 +119,6 @@ def triage_image_file(input_file: Path, output_file: Path, options) -> None:
            )
        log.info("Successfully converted to PDF, processing...")
    except img2pdf.ImageOpenError as e:
-        log.error(e)
        raise UnsupportedImageFormatError() from e


@@ -121,7 +129,6 @@ def _pdf_guess_version(input_file: Path, search_window=1024) -> str:

    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)
@@ -133,6 +140,7 @@ def _pdf_guess_version(input_file: Path, search_window=1024) -> str:
 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:
@@ -161,6 +169,7 @@ def get_pdfinfo(
    max_workers: int | None = None,
    check_pages=None,
 ) -> PdfInfo:
+    """Get the PDF info."""
    try:
        return PdfInfo(
            input_file,
@@ -177,31 +186,26 @@ def get_pdfinfo(


 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_userunit and options.output_type.startswith('pdfa'):
-        log.error(
-            "This input file uses a PDF feature that is not supported "
-            "by Ghostscript, so you cannot use --output-type=pdfa for this "
-            "file. (Specifically, it uses the PDF-1.6 /UserUnit feature to "
-            "support very large or small page sizes, and Ghostscript cannot "
-            "output these files.)  Use --output-type=pdf instead."
-        )
-        raise InputFileError()
+    if pdfinfo.has_signature:
+        if options.invalidate_digital_signatures:
+            log.warning("All digital signatures will be invalidated")
+        else:
+            raise DigitalSignatureError()
    if pdfinfo.has_acroform:
        if options.redo_ocr:
-            log.error(
+            raise InputFileError(
                "This PDF has a user fillable form. --redo-ocr is not "
                "currently possible on such files."
            )
-            raise InputFileError()
        else:
            log.warning(
                "This PDF has a fillable form. "
@@ -218,28 +222,23 @@ def validate_pdfinfo_options(context: PdfContext) -> None:


 def _vector_page_dpi(pageinfo: PageInfo) -> int:
+    """Get a DPI to use for vector pages, if the page has vector content."""
    return VECTOR_PAGE_DPI if pageinfo.has_vector or pageinfo.has_text else 0


-def get_page_dpi(pageinfo: PageInfo, options) -> Resolution:
-    "Get the DPI when nonsquare DPI is tolerable"
-    xres = max(
-        pageinfo.dpi.x or VECTOR_PAGE_DPI,
-        options.oversample or 0.0,
-        _vector_page_dpi(pageinfo),
-    )
-    yres = max(
-        pageinfo.dpi.y or VECTOR_PAGE_DPI,
-        options.oversample or 0,
-        _vector_page_dpi(pageinfo),
-    )
-    return Resolution(float(xres), float(yres))
+def get_page_square_dpi(
+    page_context: PageContext, image_dpi: Resolution | None = None
+) -> Resolution:
+    """Get the DPI when we require xres == yres, scaled to physical units.

-
-def get_page_square_dpi(pageinfo: PageInfo, options) -> Resolution:
-    "Get the DPI when we require xres == yres, scaled to physical units"
-    xres = pageinfo.dpi.x or 0.0
-    yres = pageinfo.dpi.y or 0.0
+    Page DPI includes UserUnit scaling.
+    """
+    pageinfo = page_context.pageinfo
+    options = page_context.options
+    if not image_dpi:
+        image_dpi = pageinfo.dpi
+    xres = image_dpi.x or 0.0
+    yres = image_dpi.y or 0.0
    userunit = float(pageinfo.userunit) or 1.0
    units = float(
        max(
@@ -252,12 +251,23 @@ def get_page_square_dpi(pageinfo: PageInfo, options) -> Resolution:
    return Resolution(units, units)


-def get_canvas_square_dpi(pageinfo: PageInfo, options) -> Resolution:
-    """Get the DPI when we require xres == yres, in Postscript units"""
+def get_canvas_square_dpi(
+    page_context: PageContext, image_dpi: Resolution | None = None
+) -> Resolution:
+    """Get the DPI when we require xres == yres, in Postscript units.
+
+    Canvas DPI is independent of PDF UserUnit scaling, which is
+    used to describe situations where the PDF user space is not 1:1 with
+    the physical units of the page.
+    """
+    pageinfo = page_context.pageinfo
+    options = page_context.options
+    if not image_dpi:
+        image_dpi = pageinfo.dpi
    units = float(
        max(
-            (pageinfo.dpi.x) or VECTOR_PAGE_DPI,
-            (pageinfo.dpi.y) or VECTOR_PAGE_DPI,
+            image_dpi.x or VECTOR_PAGE_DPI,
+            image_dpi.y or VECTOR_PAGE_DPI,
            _vector_page_dpi(pageinfo),
            options.oversample or 0.0,
        )
@@ -266,6 +276,7 @@ def get_canvas_square_dpi(pageinfo: PageInfo, options) -> Resolution:


 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

@@ -315,8 +326,8 @@ def is_ocr_required(page_context: PageContext) -> bool:
            log.warning(
                "page has no images - "
                "all vector content will be "
-                f"rasterized at {VECTOR_PAGE_DPI} DPI, losing some resolution and likely "
-                "increasing file size. Use --oversample to adjust the "
+                f"rasterized at {VECTOR_PAGE_DPI} DPI, losing some resolution and "
+                "likely increasing file size. Use --oversample to adjust the "
                "DPI."
            )
        else:
@@ -341,9 +352,12 @@ def is_ocr_required(page_context: PageContext) -> bool:


 def rasterize_preview(input_file: Path, page_context: PageContext) -> Path:
+    """Generate a lower quality preview image."""
    output_file = page_context.get_path('rasterize_preview.jpg')
-    canvas_dpi = get_canvas_square_dpi(page_context.pageinfo, page_context.options)
-    page_dpi = get_page_square_dpi(page_context.pageinfo, page_context.options)
+    canvas_dpi = Resolution(300.0, 300.0).take_min(
+        [get_canvas_square_dpi(page_context)]
+    )
+    page_dpi = Resolution(300.0, 300.0).take_min([get_page_square_dpi(page_context)])
    page_context.plugin_manager.hook.rasterize_pdf_page(
        input_file=input_file,
        output_file=output_file,
@@ -353,14 +367,15 @@ def rasterize_preview(input_file: Path, page_context: PageContext) -> Path:
        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) -> str:
-    """
-    Describe the page rotation we are going to perform.
-    """
+def describe_rotation(
+    page_context: PageContext, orient_conf: OrientationConfidence, correction: int
+) -> str:
+    """Describe the page rotation we are going to perform (or not perform)."""
    direction = {0: '⇧', 90: '⇨', 180: '⇩', 270: '⇦'}
    turns = {0: ' ', 90: '⬏', 180: '↻', 270: '⬑'}

@@ -387,7 +402,7 @@ def describe_rotation(page_context: PageContext, orient_conf, correction: int) -


 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
@@ -401,7 +416,6 @@ def get_orientation_correction(preview: Path, page_context: PageContext) -> int:
    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
    )
@@ -417,13 +431,59 @@ def get_orientation_correction(preview: Path, page_context: PageContext) -> int:
    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

@@ -454,10 +514,7 @@ def rasterize(

    log.debug(f"Rasterize with {device}, rotation {correction}")

-    # Produce the page image with square resolution or else deskew and OCR
-    # will not work properly.
-    canvas_dpi = get_canvas_square_dpi(pageinfo, page_context.options)
-    page_dpi = get_page_square_dpi(pageinfo, page_context.options)
+    canvas_dpi, page_dpi = calculate_raster_dpi(page_context)

    page_context.plugin_manager.hook.rasterize_pdf_page(
        input_file=input_file,
@@ -468,11 +525,13 @@ 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) -> 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')
@@ -483,8 +542,17 @@ def preprocess_remove_background(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)
@@ -494,7 +562,7 @@ def preprocess_deskew(input_file: Path, page_context: PageContext) -> Path:
        # 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)
@@ -503,21 +571,23 @@ def preprocess_deskew(input_file: Path, page_context: PageContext) -> Path:


 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) -> Path:
-    """Create the image we send for OCR. May not be the same as the display
-    image depending on preprocessing. This image will never be shown to the
-    user."""
+    """Create the image we send for OCR.

+    Might not be the same as the display image depending on preprocessing.
+    This image will never be shown to the user.
+    """
    output_file = page_context.get_path('ocr.png')
    options = page_context.options
    with Image.open(image) as im:
@@ -562,6 +632,7 @@ def create_ocr_image(image: Path, page_context: PageContext) -> Path:


 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
@@ -577,11 +648,26 @@ def ocr_engine_hocr(input_file: Path, page_context: PageContext) -> tuple[Path,


 def should_visible_page_image_use_jpg(pageinfo: PageInfo) -> bool:
-    # If all images were JPEGs originally, produce a JPEG as output
-    return pageinfo.images and all(im.enc == Encoding.jpeg for im in pageinfo.images)
+    """Determines whether the visible page image should be saved as a JPEG.
+
+    If all images were JPEGs originally, permit a JPEG as output.
+
+    Args:
+        pageinfo: The PageInfo object containing information about the page.
+
+    Returns:
+        A boolean indicating whether the visible page image should be saved as a JPEG.
+    """
+    return bool(pageinfo.images) and all(
+        im.enc == Encoding.jpeg for im in pageinfo.images
+    )


 def create_visible_page_jpg(image: Path, page_context: PageContext) -> Path:
+    """Create a visible page image in JPEG format.
+
+    This is intended to be used when all images on the page were originally JPEGs.
+    """
    output_file = page_context.get_path('visible.jpg')
    with Image.open(image) as im:
        # At this point the image should be a .png, but deskew, unpaper
@@ -593,7 +679,7 @@ 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())
@@ -603,6 +689,7 @@ def create_visible_page_jpg(image: Path, page_context: PageContext) -> Path:
 def create_pdf_page_from_image(
    image: Path, page_context: PageContext, orientation_correction: int
 ) -> Path:
+    """Create a PDF page from a page image."""
    # We rasterize a square DPI version of each page because most image
    # processing tools don't support rectangular DPI. Use the square DPI as it
    # accurately describes the image. It would be possible to resample the image
@@ -634,9 +721,10 @@ def create_pdf_page_from_image(


 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)
+    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
@@ -653,6 +741,7 @@ def render_hocr_page(hocr: Path, page_context: PageContext) -> Path:
 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
@@ -668,6 +757,7 @@ def ocr_engine_textonly_pdf(


 def get_docinfo(base_pdf: pikepdf.Pdf, context: PdfContext) -> dict[str, str]:
+    """Read the document info and store it in a dictionary."""
    options = context.options

    def from_document_info(key):
@@ -699,12 +789,28 @@ def get_docinfo(base_pdf: pikepdf.Pdf, context: PdfContext) -> dict[str, str]:


 def generate_postscript_stub(context: PdfContext) -> Path:
+    """Generates a PostScript file stub for the given PDF context.
+
+    Args:
+        context: The PDF context to generate the PostScript file stub for.
+
+    Returns:
+        Path: The path to the generated PostScript file stub.
+    """
    output_file = context.get_path('pdfa.ps')
    generate_pdfa_ps(output_file)
    return output_file


 def convert_to_pdfa(input_pdf: Path, input_ps_stub: Path, context: PdfContext) -> Path:
+    """Converts the given PDF to PDF/A.
+
+    Args:
+        input_pdf: The input PDF file path (presumably not PDF/A).
+        input_ps_stub: The input PostScript file path, containing instructions
+            for the PDF/A generator to use.
+        context: The PDF context.
+    """
    options = context.options
    input_pdfinfo = context.pdfinfo
    fix_docinfo_file = context.get_path('fix_docinfo.pdf')
@@ -715,21 +821,8 @@ def convert_to_pdfa(input_pdf: Path, input_ps_stub: Path, context: PdfContext) -
    # NULs in DocumentInfo seem to be common since older Acrobats included them.
    # pikepdf can deal with this, but we make the world a better place by
    # stamping them out as soon as possible.
-    modified = False
    with pikepdf.open(input_pdf) as pdf_file:
-        try:
-            len(pdf_file.docinfo)
-        except TypeError:
-            log.error(
-                "File contains a malformed DocumentInfo block - continuing anyway"
-            )
-        else:
-            if pdf_file.docinfo:
-                for k, v in pdf_file.docinfo.items():
-                    if b'\x00' in bytes(v):
-                        pdf_file.docinfo[k] = bytes(v).replace(b'\x00', b'')
-                        modified = True
-        if modified:
+        if _repair_docinfo_nuls(pdf_file):
            pdf_file.save(fix_docinfo_file)
        else:
            safe_symlink(input_pdf, fix_docinfo_file)
@@ -739,19 +832,43 @@ 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 _repair_docinfo_nuls(pdf):
+    """If the DocumentInfo block contains NUL characters, remove them.
+
+    If the DocumentInfo block is malformed, log an error and continue.
+    """
+    modified = False
+    try:
+        if not isinstance(pdf.docinfo, pikepdf.Dictionary):
+            raise TypeError("DocumentInfo is not a dictionary")
+        for k, v in pdf.docinfo.items():
+            if isinstance(v, str) and b'\x00' in bytes(v):
+                pdf.docinfo[k] = bytes(v).replace(b'\x00', b'')
+                modified = True
+    except TypeError:
+        # TypeError can also be raised if dictionary items are unexpected types
+        log.error("File contains a malformed DocumentInfo block - continuing anyway.")
+    return modified
+
+
 def should_linearize(working_file: Path, context: PdfContext) -> bool:
+    """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
@@ -759,6 +876,11 @@ def should_linearize(working_file: Path, context: PdfContext) -> bool:


 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.
@@ -777,6 +899,11 @@ def get_pdf_save_settings(output_type: str) -> dict[str, Any]:


 def metadata_fixup(working_file: Path, context: PdfContext) -> 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

@@ -799,24 +926,43 @@ def metadata_fixup(working_file: Path, context: PdfContext) -> Path:

    with pikepdf.open(context.origin) as original, pikepdf.open(working_file) as pdf:
        docinfo = get_docinfo(original, context)
-        with pdf.open_metadata() as meta:
-            meta.load_from_docinfo(docinfo, delete_missing=False, raise_failure=False)
+        with 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
+            )
            # If xmp:CreateDate is missing, set it to the modify date to
-            # match Ghostscript, for consistency
-            if 'xmp:CreateDate' not in meta:
-                meta['xmp:CreateDate'] = meta.get('xmp:ModifyDate', '')
-
-            with original.open_metadata(
-                set_pikepdf_as_editor=False, update_docinfo=False, strict=False
-            ) as meta_original:
-                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)
+            # 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']
+            # If the user explicitly specified an empty string for any of the
+            # following, they should be unset and not reported as missing in
+            # the output pdf. Note that some metadata fields use differing names
+            # between PDF-A and PDF.
+            for meta in [meta_pdf, meta_original]:
+                if options.title == '' and 'dc:title' in meta:
+                    del meta['dc:title']  # PDF-A and PDF
+                if options.author == '':
+                    if 'dc:creator' in meta:
+                        del meta['dc:creator']  # PDF-A (Not xmp:CreatorTool)
+                    if 'pdf:Author' in meta:
+                        del meta['pdf:Author']  # PDF
+                if options.subject == '':
+                    if 'dc:description' in meta:
+                        del meta['dc:description']  # PDF-A
+                    if 'dc:subject' in meta:
+                        del meta['dc:subject']  # PDF
+                if options.keywords == '' and 'pdf:Keywords' in meta:
+                    del meta['pdf:Keywords']  # PDF-A and PDF
+            meta_missing = set(meta_original.keys()) - set(meta_pdf.keys())
+            report_on_metadata(meta_missing)

        optimizing = context.plugin_manager.hook.is_optimization_enabled(
            context=context
@@ -832,9 +978,33 @@ def metadata_fixup(working_file: Path, context: PdfContext) -> Path:
    return output_file


+def _file_size_ratio(
+    input_file: Path, output_file: Path
+) -> tuple[float | None, float | None]:
+    """Calculate ratio of input to output file sizes and percentage savings.
+
+    Args:
+        input_file (Path): The path to the input file.
+        output_file (Path): The path to the output file.
+
+    Returns:
+        tuple[float | None, float | None]: A tuple containing the file size
+        ratio and the percentage savings achieved by the output file size
+        compared to the input file size.
+    """
+    input_size = input_file.stat().st_size
+    output_size = output_file.stat().st_size
+    if output_size == 0:
+        return None, None
+    ratio = input_size / output_size
+    savings = 1 - output_size / input_size
+    return ratio, savings
+
+
 def optimize_pdf(
    input_file: Path, context: PdfContext, executor: Executor
 ) -> tuple[Path, Sequence[str]]:
+    """Optimize the given PDF file."""
    output_file = context.get_path('optimize.pdf')
    output_pdf, messages = context.plugin_manager.hook.optimize_pdf(
        input_pdf=input_file,
@@ -844,17 +1014,29 @@ def optimize_pdf(
        linearize=should_linearize(input_file, context),
    )

-    input_size = input_file.stat().st_size
-    output_size = output_file.stat().st_size
-    if output_size > 0:
-        ratio = input_size / output_size
-        savings = 1 - output_size / input_size
-        log.info(f"Optimize ratio: {ratio:.2f} savings: {(savings):.1%}")
-
+    ratio, savings = _file_size_ratio(input_file, output_file)
+    if ratio:
+        log.info(f"Image optimization ratio: {ratio:.2f} savings: {(savings):.1%}")
+    ratio, savings = _file_size_ratio(context.origin, output_file)
+    if ratio:
+        log.info(f"Total file size ratio: {ratio:.2f} savings: {(savings):.1%}")
    return output_pdf, messages


-def enumerate_compress_ranges(iterable):
+def enumerate_compress_ranges(
+    iterable: Iterable[T],
+) -> Iterator[tuple[tuple[int, int], T]]:
+    """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
@@ -871,21 +1053,22 @@ def enumerate_compress_ranges(iterable):


 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 = in_.read()
-                    # Some OCR engines (e.g. Tesseract v4 alpha) add form feeds
-                    # between pages, and some do not. For consistency, we ignore
-                    # any added by the OCR engine and them on our own.
-                    if txt.endswith('\f'):
-                        stream.write(txt[:-1])
-                    else:
-                        stream.write(txt)
+                txt = txt_file.read_text(encoding="utf-8")
+                # Some versions of Tesseract add a form feed at the end and
+                # others don't. Remove it if it exists, since we add one manually.
+                stream.write(txt.removesuffix('\f'))
            else:
                if from_ != to_:
                    pages = f'{from_}-{to_}'
@@ -895,15 +1078,27 @@ def merge_sidecars(txt_files: Iterable[Path | None], context: PdfContext) -> Pat
    return output_file


-def copy_final(input_file, output_file, _context: PdfContext) -> None:
+def copy_final(
+    input_file: Path, output_file: str | Path | BinaryIO, _context: PdfContext
+) -> None:
+    """Copy the final temporary file to the output destination.
+
+    Args:
+        input_file (Path): The input file to copy.
+        output_file (str | Path | BinaryIO): The output file to copy to.
+        _context (PdfContext): The PDF context.
+
+    Returns:
+        None
+    """
    log.debug('%s -> %s', input_file, output_file)
-    with open(input_file, 'rb') as input_stream:
+    with input_file.open('rb') as input_stream:
        if output_file == '-':
-            copyfileobj(input_stream, sys.stdout.buffer)
+            copyfileobj(input_stream, sys.stdout.buffer)  # type: ignore[misc]
            sys.stdout.flush()
        elif hasattr(output_file, 'writable'):
-            output_stream = output_file
-            copyfileobj(input_stream, output_stream)
+            output_stream = cast(BinaryIO, output_file)
+            copyfileobj(input_stream, output_stream)  # type: ignore[misc]
            with suppress(AttributeError):
                output_stream.flush()
        else:
@@ -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

@@ -100,7 +100,9 @@ class OcrmypdfPluginManager(pluggy.PluginManager):
            self.register(module)


-def get_plugin_manager(plugins: list[str | Path], builtins=True):
+def get_plugin_manager(
+    plugins: list[str | Path], builtins=True
+) -> OcrmypdfPluginManager:
    return OcrmypdfPluginManager(
        project_name='ocrmypdf',
        plugins=plugins,
@@ -13,12 +13,13 @@ import logging.handlers
 import os
 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 pathlib import Path
 from tempfile import mkdtemp
-from typing import NamedTuple, Sequence, cast
+from typing import NamedTuple, cast

 import PIL

@@ -104,6 +105,7 @@ def preprocess(
    deskew: bool,
    clean: bool,
 ) -> Path:
+    """Preprocess an image."""
    if remove_background:
        image = preprocess_remove_background(image, page_context)
    if deskew:
@@ -116,6 +118,7 @@ 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
@@ -173,6 +176,7 @@ def make_intermediate_images(


 def exec_page_sync(page_context: PageContext) -> PageResult:
+    """Execute a pipeline for a single page synchronously."""
    options = page_context.options
    tls.pageno = page_context.pageno + 1

@@ -233,6 +237,7 @@ def exec_page_sync(page_context: PageContext) -> PageResult:
 def post_process(
    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)
@@ -243,6 +248,7 @@ def post_process(


 def worker_init(max_pixels: int) -> None:
+    """Initialize a worker thread or process."""
    # In Windows, child process will not inherit our change to this value in
    # the parent process, so ensure workers get it set. Not needed when running
    # threaded, but harmless to set again.
@@ -251,9 +257,8 @@ def worker_init(max_pixels: int) -> None:


 def exec_concurrent(context: PdfContext, executor: Executor) -> Sequence[str]:
-    """Execute the pipeline concurrently"""
-
-    # Run exec_page_sync on every page context
+    """Execute the OCR pipeline concurrently."""
+    # Run exec_page_sync on every page
    options = context.options
    max_workers = min(len(context.pdfinfo), options.jobs)
    if max_workers > 1:
@@ -263,6 +268,7 @@ def exec_concurrent(context: PdfContext, executor: Executor) -> Sequence[str]:
    ocrgraft = OcrGrafter(context)

    def update_page(result: PageResult, pbar):
+        """After OCR is complete for a page, update the PDF."""
        try:
            tls.pageno = result.pageno + 1
            sidecars[result.pageno] = result.text
@@ -316,10 +322,9 @@ def exec_concurrent(context: PdfContext, executor: Executor) -> Sequence[str]:
 def configure_debug_logging(
    log_filename: Path, prefix: str = ''
 ) -> logging.FileHandler:
-    """
-    Create a debug log file at a specified location.
+    """Create a debug log file at a specified location.

-    Arguments:
+    Args:
        log_filename: Where to the put the log file.
        prefix: The logging domain prefix that should be sent to the log.
    """
@@ -340,6 +345,17 @@ def run_pipeline(
    plugin_manager: OcrmypdfPluginManager | None,
    api: bool = False,
 ) -> ExitCode:
+    """Run the OCR pipeline.
+
+    Args:
+        options: The parsed command line options.
+        plugin_manager: The plugin manager to use. If not provided, one will be
+            created.
+        api: If ``True``, the pipeline is being run from the API. This is used
+            to manage exceptions in a way appropriate for API or CLI usage.
+            For CLI (``api=False``), exceptions are printed and described;
+            for API use, they are propagated to the caller.
+    """
    # 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.)
@@ -420,13 +436,13 @@ def run_pipeline(
                options, start_input_file, options.output_file, optimize_messages
            )

-    except (KeyboardInterrupt if not api else NeverRaise):
+    except KeyboardInterrupt if not api else NeverRaise:
        if options.verbose >= 1:
            log.exception("KeyboardInterrupt")
        else:
            log.error("KeyboardInterrupt")
        return ExitCode.ctrl_c
-    except (ExitCodeException if not api else NeverRaise) as e:
+    except ExitCodeException if not api else NeverRaise as e:
        e = cast(ExitCodeException, e)
        if options.verbose >= 1:
            log.exception("ExitCodeException")
@@ -435,7 +451,7 @@ def run_pipeline(
        else:
            log.error(type(e).__name__)
        return e.exit_code
-    except (PIL.Image.DecompressionBombError if not api else NeverRaise):
+    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 "
@@ -453,7 +469,7 @@ def run_pipeline(
            "argument."
        )
        return ExitCode.child_process_error
-    except (Exception if not api else NeverRaise):  # pylint: disable=broad-except
+    except Exception if not api else NeverRaise:  # pylint: disable=broad-except
        log.exception("An exception occurred while executing the pipeline")
        return ExitCode.other_error
    finally:
@@ -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
@@ -43,35 +43,47 @@ log = logging.getLogger(__name__)


 def check_platform() -> None:
-    if os.name == 'nt' and sys.maxsize <= 2**32:  # pragma: no cover
-        # 32-bit interpreter on Windows
-        log.error(
-            "You are running OCRmyPDF in a 32-bit (x86) Python interpreter."
+    if sys.maxsize <= 2**32:  # pragma: no cover
+        log.warning(
+            "You are running OCRmyPDF in a 32-bit (x86) Python interpreter. "
+            "This is not supported. 32-bit does not have enough address space "
+            "to process large files. "
            "Please use a 64-bit (x86-64) version of Python."
        )


-def check_options_languages(options: Namespace, ocr_engine_languages: 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)
+    is_latin = set(options.languages).issubset(HOCR_OK_LANGS)

    if options.pdf_renderer.startswith('hocr') and not is_latin:
        log.warning(
@@ -109,12 +121,10 @@ def check_options_output(options: Namespace) -> None:
 def check_options_sidecar(options: Namespace) -> None:
    if options.sidecar == '\0':
        if options.output_file == '-':
-            raise BadArgsError(
-                "--sidecar filename must be specified when output file is stdout."
-            )
+            raise BadArgsError("--sidecar filename needed when output file is stdout.")
        elif options.output_file == os.devnull:
            raise BadArgsError(
-                "--sidecar filename must be specified when output file is /dev/null or NUL."
+                "--sidecar filename needed when output file is /dev/null or NUL."
            )
        options.sidecar = options.output_file + '.txt'
    if options.sidecar == options.input_file or options.sidecar == options.output_file:
@@ -195,16 +205,6 @@ 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):
@@ -231,7 +231,6 @@ def _check_plugin_invariant_options(options: Namespace) -> None:
    check_options_sidecar(options)
    check_options_preprocessing(options)
    check_options_ocr_behavior(options)
-    check_options_advanced(options)
    check_options_pillow(options)


@@ -276,7 +275,8 @@ def create_input_file(options: Namespace, work_folder: Path) -> tuple[Path, str]
                    "permissions correctly.\n"
                    "You may find it easier to use stdin/stdout:"
                    "\n"
-                    "\tdocker run -i --rm jbarlow83/ocrmypdf - - <input.pdf >output.pdf\n"
+                    "\tdocker run -i --rm jbarlow83/ocrmypdf - - <input.pdf >output.pdf"
+                    "\n"
                )
            raise InputFileError(msg) from e

@@ -333,7 +333,7 @@ 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)
@@ -9,16 +9,17 @@ import logging
 import os
 import sys
 import threading
+from argparse import Namespace
+from collections.abc import Iterable
 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

-import coloredlogs
-from humanfriendly.terminal import enable_ansi_support
+import pluggy

-from ocrmypdf._logging import PageNumberFilter, TqdmConsole
+from ocrmypdf._logging import PageNumberFilter
 from ocrmypdf._plugin_manager import get_plugin_manager
 from ocrmypdf._sync import run_pipeline
 from ocrmypdf._validation import check_options
@@ -46,7 +47,7 @@ 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.

@@ -86,7 +87,6 @@ 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)
@@ -113,14 +113,7 @@ def configure_logging(
    else:
        fmt = '%(pageno)s%(message)s'

-    use_colors = progress_bar_friendly
    formatter = None
-    if 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)
@@ -142,7 +135,21 @@ def configure_logging(

 def create_options(
    *, input_file: PathOrIO, output_file: PathOrIO, parser: ArgumentParser, **kwargs
-):
+) -> Namespace:
+    """Construct an options object from the input/output files and keyword arguments.
+
+    Args:
+        input_file: Input file path or file object.
+        output_file: Output file path or file object.
+        parser: ArgumentParser object.
+        **kwargs: Keyword arguments.
+
+    Returns:
+        argparse.Namespace: A Namespace object containing the parsed arguments.
+
+    Raises:
+        TypeError: If the type of a keyword argument is not supported.
+    """
    cmdline = []
    deferred = []

@@ -203,59 +210,78 @@ 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,
-    image_dpi: int = None,
-    output_type=None,
+    language: Iterable[str] | None = None,
+    image_dpi: int | None = None,
+    output_type: str | None = None,
    sidecar: StrPath | None = None,
-    jobs: int = None,
-    use_threads: bool = None,
-    title: str = None,
-    author: str = None,
-    subject: str = None,
-    keywords: str = None,
-    rotate_pages: bool = None,
-    remove_background: bool = None,
-    deskew: bool = None,
-    clean: bool = None,
-    clean_final: bool = None,
-    unpaper_args: str = None,
-    oversample: int = None,
-    remove_vectors: bool = None,
-    force_ocr: bool = None,
-    skip_text: bool = None,
-    redo_ocr: bool = None,
-    skip_big: float = None,
-    optimize: int = None,
-    jpg_quality: int = None,
-    png_quality: int = None,
-    jbig2_lossy: bool = None,
-    jbig2_page_group_size: int = None,
-    pages: str = None,
-    max_image_mpixels: float = None,
-    tesseract_config: Iterable[str] = None,
-    tesseract_pagesegmode: int = None,
-    tesseract_oem: int = None,
-    tesseract_thresholding: int = None,
-    pdf_renderer=None,
-    tesseract_timeout: float = None,
-    rotate_pages_threshold: float = None,
-    pdfa_image_compression=None,
-    user_words: os.PathLike = None,
-    user_patterns: os.PathLike = None,
-    fast_web_view: float = None,
-    plugins: Iterable[StrPath] = None,
+    jobs: int | None = None,
+    use_threads: bool | None = None,
+    title: str | None = None,
+    author: str | None = None,
+    subject: str | None = None,
+    keywords: str | None = None,
+    rotate_pages: bool | None = None,
+    remove_background: bool | None = None,
+    deskew: bool | None = None,
+    clean: bool | None = None,
+    clean_final: bool | None = None,
+    unpaper_args: str | None = None,
+    oversample: int | None = None,
+    remove_vectors: bool | None = None,
+    force_ocr: bool | None = None,
+    skip_text: bool | None = None,
+    redo_ocr: bool | None = None,
+    skip_big: float | None = None,
+    optimize: int | None = None,
+    jpg_quality: int | None = None,
+    png_quality: int | None = None,
+    jbig2_lossy: bool | None = None,
+    jbig2_page_group_size: int | None = None,
+    jbig2_threshold: float | None = None,
+    pages: str | None = None,
+    max_image_mpixels: float | None = None,
+    tesseract_config: Iterable[str] | None = None,
+    tesseract_pagesegmode: int | None = None,
+    tesseract_oem: int | None = None,
+    tesseract_thresholding: int | None = None,
+    pdf_renderer: str | None = None,
+    tesseract_timeout: float | None = None,
+    tesseract_non_ocr_timeout: float | None = None,
+    tesseract_downsample_above: int | None = None,
+    tesseract_downsample_large_images: bool | None = None,
+    rotate_pages_threshold: float | None = None,
+    pdfa_image_compression: str | None = None,
+    color_conversion_strategy: str | None = None,
+    user_words: os.PathLike | None = None,
+    user_patterns: os.PathLike | None = None,
+    fast_web_view: float | None = None,
+    continue_on_soft_render_error: bool | None = None,
+    invalidate_digital_signatures: bool | None = None,
+    plugins: Iterable[StrPath] | None = None,
    plugin_manager=None,
-    keep_temporary_files: bool = None,
-    progress_bar: bool = None,
+    keep_temporary_files: bool | None = None,
+    progress_bar: bool | None = None,
    **kwargs,
 ):
    """Run OCRmyPDF on one PDF or image.

    For most arguments, see documentation for the equivalent command line parameter.
+
+    This API takes a threading lock, because OCRmyPDF uses global state in particular
+    for the plugin system. The jobs parameter will be used to create a pool of
+    worker threads or processes at different times, subject to change. A Python
+    process can only run one OCRmyPDF task at a time.
+
+    To run parallelize instances OCRmyPDF, use separate Python processes to scale
+    horizontally. Generally speaking you should set jobs=sqrt(cpu_count) and run
+    sqrt(cpu_count) processes as a starting point. If you have files with a high page
+    count, run fewer processes and more jobs per process. If you have a lot of short
+    files, run more processes and fewer jobs per process.
+
    A few specific arguments are discussed here:

    Args:
@@ -277,6 +303,7 @@ 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.MissingDependencyError: If a required dependency program is missing or
            was not found on PATH.
@@ -334,7 +361,6 @@ def ocr(  # pylint: disable=unused-argument

 __all__ = [
    'PageNumberFilter',
-    'TqdmConsole',
    'Verbosity',
    'check_options',
    'configure_logging',
@@ -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.
-# The plugin manager will not load it, so anything defined here may not be
-# processed as a module.
+from __future__ import annotations
@@ -12,25 +12,26 @@ 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, RichTqdmProgressAdapter
 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 +40,6 @@ 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 +55,12 @@ 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 +69,7 @@ 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 +82,7 @@ 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...
@@ -95,15 +96,6 @@ 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,
        *,
@@ -127,6 +119,11 @@ 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()

@@ -142,7 +139,7 @@ class StandardExecutor(Executor):
                    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 +148,7 @@ 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 +161,24 @@ class StandardExecutor(Executor):

@hookimpl
 def get_executor(progressbar_class):
+    """Return the default executor."""
    return StandardExecutor(pbar_class=progressbar_class)


+RICH_CONSOLE = RichConsole(stderr=True)
+
+
@hookimpl
 def get_progressbar_class():
-    return tqdm
+    """Return the default progress bar class."""
+
+    def partial_RichTqdmProgressAdapter(*args, **kwargs):
+        return RichTqdmProgressAdapter(*args, **kwargs, console=RICH_CONSOLE)
+
+    return partial_RichTqdmProgressAdapter


@hookimpl
 def get_logging_console():
-    return logging.StreamHandler(stream=TqdmConsole(sys.stderr))
+    """Return the default logging console handler."""
+    return RichLoggingHandler(console=RICH_CONSOLE)
@@ -8,23 +8,54 @@ import logging

 from ocrmypdf import hookimpl
 from ocrmypdf._exec import ghostscript
-from ocrmypdf._validation import HOCR_OK_LANGS
 from ocrmypdf.exceptions import MissingDependencyError
 from ocrmypdf.subprocess import check_external_program

 log = logging.getLogger(__name__)

+# Currently all blacklisted versions are lower than 9.55, so none need to
+# be added here. If a future version is blacklisted, add it here.
+BLACKLISTED_GS_VERSIONS: frozenset[str] = frozenset()
+
+
+@hookimpl
+def add_options(parser):
+    gs = parser.add_argument_group("Ghostscript", "Advanced control of Ghostscript")
+    gs.add_argument(
+        '--color-conversion-strategy',
+        action='store',
+        type=str,
+        metavar='STRATEGY',
+        choices=ghostscript.COLOR_CONVERSION_STRATEGIES,
+        default='LeaveColorUnchanged',
+        help="Set Ghostscript color conversion strategy",
+    )
+    gs.add_argument(
+        '--pdfa-image-compression',
+        choices=['auto', 'jpeg', 'lossless'],
+        default='auto',
+        help="Specify how to compress images in the output PDF/A. 'auto' lets "
+        "OCRmyPDF decide.  'jpeg' changes all grayscale and color images to "
+        "JPEG compression.  'lossless' uses PNG-style lossless compression "
+        "for all images.  Monochrome images are always compressed using a "
+        "lossless codec.  Compression settings "
+        "are applied to all pages, including those for which OCR was "
+        "skipped.  Not supported for --output-type=pdf ; that setting "
+        "preserves the original compression of all images.",
+    )
+

@hookimpl
 def check_options(options):
+    """Check that the options are valid for this plugin."""
    check_external_program(
        program='gs',
        package='ghostscript',
        version_checker=ghostscript.version,
-        need_version='9.50',  # Ubuntu 20.04's version
+        need_version='9.55',  # Ubuntu 22.04's version
    )
    gs_version = ghostscript.version()
-    if gs_version in ('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 "
@@ -33,6 +64,17 @@ def check_options(options):

    if options.output_type == 'pdfa':
        options.output_type = 'pdfa-2'
+    if options.color_conversion_strategy not in ghostscript.COLOR_CONVERSION_STRATEGIES:
+        raise ValueError(
+            f"Invalid color conversion strategy: {options.color_conversion_strategy}"
+        )
+    if options.pdfa_image_compression != 'auto' and not options.output_type.startswith(
+        'pdfa'
+    ):
+        log.warning(
+            "--pdfa-image-compression argument only applies when "
+            "--output-type is one of 'pdfa', 'pdfa-1', or 'pdfa-2'"
+        )


@hookimpl
@@ -45,7 +87,9 @@ def rasterize_pdf_page(
    page_dpi,
    rotation,
    filter_vector,
+    stop_on_soft_error,
 ):
+    """Rasterize a single page of a PDF file using Ghostscript."""
    ghostscript.rasterize_pdf(
        input_file,
        output_file,
@@ -55,6 +99,7 @@ def rasterize_pdf_page(
        page_dpi=page_dpi,
        rotation=rotation,
        filter_vector=filter_vector,
+        stop_on_error=stop_on_soft_error,
    )
    return output_file

@@ -64,17 +109,21 @@ def generate_pdfa(
    pdf_pages,
    pdfmark,
    output_file,
-    compression,
+    context,
    pdf_version,
    pdfa_part,
    progressbar_class,
+    stop_on_soft_error,
 ):
+    """Generate a PDF/A from the list of PDF pages and PDF/A metadata."""
    ghostscript.generate_pdfa(
        pdf_pages=[*pdf_pages, pdfmark],
        output_file=output_file,
-        compression=compression,
+        compression=context.options.pdfa_image_compression,
+        color_conversion_strategy=context.options.color_conversion_strategy,
        pdf_version=pdf_version,
        pdfa_part=pdfa_part,
        progressbar_class=progressbar_class,
+        stop_on_error=stop_on_soft_error,
    )
    return output_file
@@ -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}',
        )

@@ -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',
@@ -58,7 +62,7 @@ def add_options(parser):
        metavar='METHOD',
        help=(
            "Set Tesseract 5.0+ input image thresholding mode. This may improve OCR "
-            "results on low quality images or those that contain high constrast color. "
+            "results on low quality images or those that contain high contrast color. "
            "legacy-otsu is the Tesseract default; adaptive-otsu is an improved Otsu "
            "algorithm with improved sort for background color changes; sauvola is "
            "based on local standard deviation."
@@ -69,8 +73,51 @@ def add_options(parser):
        default=180.0,
        type=numeric(float, 0),
        metavar='SECONDS',
-        help='Give up on OCR after the timeout, but copy the preprocessed page '
-        'into the final output',
+        help=(
+            "Give up on OCR after the timeout, but copy the preprocessed page "
+            "into the final output. This timeout is only used when using Tesseract "
+            "for OCR. When Tesseract is used for other operations such as "
+            "deskewing and orientation, the timeout is controlled by "
+            "--tesseract-non-ocr-timeout."
+        ),
+    )
+    tess.add_argument(
+        '--tesseract-non-ocr-timeout',
+        default=180.0,
+        type=numeric(float, 0),
+        metavar='SECONDS',
+        help=(
+            "Give up on non-OCR operations such as deskewing and orientation "
+            "after timeout. This is a separate timeout from --tesseract-timeout "
+            "because these operations are not as expensive as OCR."
+        ),
+    )
+    tess.add_argument(
+        '--tesseract-downsample-large-images',
+        action='store_true',
+        help=(
+            "Downsample large images before OCR. Tesseract has an upper limit on the "
+            "size images it will support. If this argument is given, OCRmyPDF will "
+            "downsample large images to fit Tesseract. This may reduce OCR quality, "
+            "on large images the most desirable text is usually larger. If this "
+            "parameter is not supplied, Tesseract will error out and produce no OCR "
+            "on the page in question. This argument should be used with a high value "
+            "of --tesseract-timeout to ensure Tesseract has enough to time."
+        ),
+    )
+    tess.add_argument(
+        '--tesseract-downsample-above',
+        action='store',
+        type=numeric(int, 100, 32767),
+        default=32767,
+        help=(
+            "Downsample images larger than this size pixel size in either dimension "
+            "before OCR. --tesseract-downsample-large-images downsamples only when "
+            "an image exceeds Tesseract's internal limits. This argument causes "
+            "downsampling to occur when an image exceeds the given size. This may "
+            "reduce OCR quality, but on large images the most desirable text is "
+            "usually larger."
+        ),
    )
    tess.add_argument(
        '--user-words',
@@ -93,7 +140,7 @@ def check_options(options):
        program='tesseract',
        package={'linux': 'tesseract-ocr'},
        version_checker=tesseract.version,
-        need_version='4.1.1',  # Ubuntu 20.04 version
+        need_version='4.1.1',  # Ubuntu 22.04 version (also 20.04)
        version_parser=tesseract.TesseractVersion,
    )

@@ -131,13 +178,41 @@ def validate(pdfinfo, options):
        tess_threads = int(os.environ['OMP_THREAD_LIMIT'])
    log.debug("Using Tesseract OpenMP thread limit %d", tess_threads)

+    if (
+        options.tesseract_downsample_above != 32767
+        and not options.tesseract_downsample_large_images
+    ):
+        log.warning(
+            "The --tesseract-downsample-above argument will have no effect unless "
+            "--tesseract-downsample-large-images is also given."
+        )
+
+
+@hookimpl
+def filter_ocr_image(page: PageContext, image: Image.Image) -> Image.Image:
+    """Filter the image before OCR.
+
+    Tesseract cannot handle images with more than 32767 pixels in either axis,
+    or more than 2**31 bytes. This function resizes the image to fit within
+    those limits.
+    """
+    threshold = min(page.options.tesseract_downsample_above, 32767)
+
+    options = page.options
+    if options.tesseract_downsample_large_images:
+        size = calculate_downsample(
+            image, max_size=(threshold, threshold), max_bytes=(2**31) - 1
+        )
+        image = downsample_image(image, size)
+    return image
+

 class TesseractOcrEngine(OcrEngine):
    """Implements OCR with Tesseract."""

    @staticmethod
    def version():
-        return tesseract.version()
+        return str(tesseract.version())

    @staticmethod
    def creator_tag(options):
@@ -156,7 +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
@@ -165,7 +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
@@ -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',
@@ -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',
@@ -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)
@@ -94,7 +95,7 @@ class EncryptedPdfError(ExitCodeException):

    exit_code = ExitCode.encrypted_pdf
    message = dedent(
-        '''\
+        """\
        Input PDF is encrypted. The encryption must be removed to
        perform OCR.

@@ -103,7 +104,19 @@ class EncryptedPdfError(ExitCodeException):

        You can remove the encryption using
            qpdf --decrypt [--password=[password]] infilename
-        '''
+        """
+    )
+
+
+class DigitalSignatureError(ExitCodeException):
+    """PDF has a digital signature."""
+
+    exit_code = ExitCode.input_file
+    message = dedent(
+        """\
+        Input PDF has a digital signature. OCR would alter the document,
+        invalidating the signature.
+        """
    )


@@ -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 ...
+"""
@@ -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
@@ -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
@@ -10,30 +10,29 @@ import multiprocessing
 import os
 import shutil
 import warnings
-from collections.abc import Iterable
+from collections.abc import Iterable, Sequence
 from contextlib import suppress
+from decimal import Decimal
 from io import StringIO
 from math import isclose, isfinite
 from pathlib import Path
-from typing import Any, Generic, Sequence, SupportsFloat, SupportsRound, TypeVar
+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(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
-    )
+IMG2PDF_KWARGS = dict(engine=img2pdf.Engine.pikepdf, rotation=img2pdf.Rotation.ifvalid)


-T = TypeVar('T', bound=SupportsRound[Any])
+T = TypeVar('T', float, int, Decimal)


 class Resolution(Generic[T]):
@@ -49,6 +48,7 @@ class Resolution(Generic[T]):
    __slots__ = ('x', 'y')

    def __init__(self, x: T, y: T):
+        """Construct a Resolution object."""
        self.x = x
        self.y = y

@@ -57,9 +57,11 @@ class Resolution(Generic[T]):
    CONVERSION_ERROR = 0.002

    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) -> Resolution[int]:
+        """Round to nearest integer."""
        return Resolution(int(round(self.x)), int(round(self.y)))

    @classmethod
@@ -68,38 +70,65 @@ class Resolution(Generic[T]):

    @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:
-        if isinstance(self.x, SupportsFloat) and isinstance(self.y, SupportsFloat):
-            return isfinite(self.x) and isfinite(self.y)
-        return True
+        """True if both x and y are finite numbers."""
+        return isfinite(self.x) and isfinite(self.y)
+
+    def to_scalar(self) -> float:
+        """Return the harmonic mean of x and y as a 1D approximation.
+
+        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:
-        if yvals is not None:
-            return Resolution(max(self.x, *vals), max(self.y, *yvals))
-        max_x, max_y = self.x, self.y
-        for x, y in vals:
-            max_x = max(x, max_x)
-            max_y = max(y, max_y)
-        return Resolution(max_x, max_y)
+        """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):
@@ -108,10 +137,10 @@ class Resolution(Generic[T]):


 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.
@@ -126,7 +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
@@ -152,7 +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:
@@ -170,7 +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])


@@ -199,7 +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,
@@ -267,26 +300,29 @@ 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):
-    "Remove all log handlers, usually used in a child process."
+def remove_all_log_handlers(logger: logging.Logger) -> None:
+    """Remove all log handlers, usually used in a child process.
+
+    The child process inherits the log handlers from the parent process when
+    a fork occurs. Typically we want to remove all log handlers in the child
+    process so that the child process can set up a single queue handler to
+    forward log messages to the parent process.
+    """
    for handler in logger.handlers[:]:
        logger.removeHandler(handler)
        handler.close()  # To ensure handlers with opened resources are released


-def pikepdf_enable_mmap():
-    # try:
-    #     if pikepdf._qpdf.set_access_default_mmap(True):
-    #         log.debug("pikepdf mmap enabled")
-    # except AttributeError:
-    #     log.debug("pikepdf mmap not available")
-    # We found a race condition probably related to pybind issue #2252 that can
-    # cause a crash. For now, disable pikepdf mmap to be on the safe side.
-    # Fix is not in pybind11 2.6.0
-    # log.debug("pikepdf mmap disabled")
-    return
+def pikepdf_enable_mmap() -> None:
+    """Enable pikepdf mmap."""
+    try:
+        if pikepdf._core.set_access_default_mmap(True):
+            log.debug("pikepdf mmap enabled")
+    except AttributeError:
+        log.debug("pikepdf mmap not available")
+    log.debug("pikepdf mmap disabled")
@@ -19,6 +19,7 @@ from xml.etree import ElementTree

 with warnings.catch_warnings():
    # reportlab uses deprecated load_module
+    # shim can be removed when we require reportlab >= 3.7
    warnings.filterwarnings(
        'ignore', category=DeprecationWarning, message=r".*load_module.*"
    )
@@ -99,11 +100,10 @@ class HocrTransformError(Exception):


 class HocrTransform:
+    """A class for converting documents from the hOCR format.

-    """
-    A class for converting documents from the hOCR format.
    For details of the hOCR format, see:
-    http://kba.cloud/hocr-spec/
+    http://kba.cloud/hocr-spec/.
    """

    box_pattern = re.compile(r'bbox((\s+\d+){4})')
@@ -119,6 +119,7 @@ class HocrTransform:
    )

    def __init__(self, *, hocr_filename: str | Path, dpi: float):
+        """Initialize the HocrTransform object."""
        self.dpi = dpi
        self.hocr = ElementTree.parse(os.fspath(hocr_filename))

@@ -143,9 +144,7 @@ class HocrTransform:
            raise HocrTransformError("hocr file is missing page dimensions")

    def __str__(self):  # pragma: no cover
-        """
-        Return the textual content of the HTML body
-        """
+        """Return the textual content of the HTML body."""
        if self.hocr is None:
            return ''
        body = self.hocr.find(self._child_xpath('body'))
@@ -155,9 +154,7 @@ class HocrTransform:
            return ''

    def _get_element_text(self, element: Element):
-        """
-        Return the textual content of the element and its children
-        """
+        """Return the textual content of the element and its children."""
        text = ''
        if element.text is not None:
            text += element.text
@@ -169,10 +166,7 @@ class HocrTransform:

    @classmethod
    def element_coordinates(cls, element: Element) -> Rect:
-        """
-        Returns a tuple containing the coordinates of the bounding box around
-        an element
-        """
+        """Get coordinates of the bounding box around an element."""
        out = Rect._make(0 for _ in range(4))
        if 'title' in element.attrib:
            matches = cls.box_pattern.search(element.attrib['title'])
@@ -183,9 +177,7 @@ class HocrTransform:

    @classmethod
    def baseline(cls, element: Element) -> tuple[float, float]:
-        """
-        Returns a tuple containing the baseline slope and intercept.
-        """
+        """Get baseline's slope and intercept."""
        if 'title' in element.attrib:
            matches = cls.baseline_pattern.search(element.attrib['title'])
            if matches:
@@ -193,9 +185,7 @@ class HocrTransform:
        return (0.0, 0.0)

    def pt_from_pixel(self, pxl) -> Rect:
-        """
-        Returns the quantity in PDF units (pt) given quantity in pixels
-        """
+        """Returns the quantity in PDF units (pt) given quantity in pixels."""
        return Rect._make((c / self.dpi * inch) for c in pxl)

    def _child_xpath(self, html_tag: str, html_class: str | None = None) -> str:
@@ -206,21 +196,9 @@ class HocrTransform:

    @classmethod
    def replace_unsupported_chars(cls, s: str) -> str:
-        """
-        Given an input string, returns the corresponding string that:
-        * is available in the Helvetica facetype
-        * does not contain any ligature (to allow easy search in the PDF file)
-        """
+        """Replaces characters with those available in the Helvetica typeface."""
        return s.translate(cls.ligatures)

-    def topdown_position(self, element):
-        pxl_line_coords = self.element_coordinates(element)
-        line_box = self.pt_from_pixel(pxl_line_coords)
-        # Coordinates here are still in the hocr coordinate system, so 0 on the y axis
-        # is the top of the page and increasing values of y will move towards the
-        # bottom of the page.
-        return line_box.y2
-
    def to_pdf(
        self,
        *,
@@ -231,8 +209,8 @@ class HocrTransform:
        invisible_text: bool = False,
        interword_spaces: bool = False,
    ) -> None:
-        """
-        Creates a PDF file with an image superimposed on top of the text.
+        """Creates a PDF file with an image superimposed on top of the text.
+
        Text is positioned according to the bounding box of the lines in
        the hOCR file.
        The image need not be identical to the image used to create the hOCR
@@ -323,6 +301,7 @@ class HocrTransform:

    @classmethod
    def polyval(cls, poly, x):  # pragma: no cover
+        """Calculate the value of a polynomial at a point."""
        return x * poly[0] + poly[1]

    def _do_line(
@@ -0,0 +1,160 @@
+# SPDX-FileCopyrightText: 2023 James R. Barlow
+# SPDX-License-Identifier: MPL-2.0
+
+"""OCR-related image manipulation."""
+
+from __future__ import annotations
+
+import logging
+from math import floor, sqrt
+from typing import Optional
+
+from PIL import Image
+
+# While from __future__ import annotations, we use singledispatch here, which
+# does not support annotations. Disable check about using old-style typing
+# until Python 3.10, OR when drop singledispatch in ocrmypdf 15.
+# ruff: noqa: UP006
+# ruff: noqa: UP007
+
+
+log = logging.getLogger(__name__)
+
+
+def bytes_per_pixel(mode: str) -> int:
+    """Return the number of padded bytes per pixel for a given PIL image mode.
+
+    In RGB mode we assume 4 bytes per pixel, which is the case for most
+    consumers.
+    """
+    if mode in ('1', 'L', 'P'):
+        return 1
+    if mode in ('LA', 'PA', 'La') or mode.startswith('I;16'):
+        return 2
+    return 4
+
+
+def _calculate_downsample(
+    image_size: tuple[int, int],
+    bytes_per_pixel: int,
+    *,
+    max_size: Optional[tuple[int, int]] = None,
+    max_pixels: Optional[int] = None,
+    max_bytes: Optional[int] = None,
+) -> tuple[int, int]:
+    """Calculate image size required to downsample an image to fit limits.
+
+    If no limit is exceeded, the input image's size is returned.
+
+    Args:
+        image_size: Dimensions of image.
+        bytes_per_pixel: Number of bytes per pixel.
+        max_size: The maximum width and height of the image.
+        max_pixels: The maximum number of pixels in the image. Some image consumers
+            limit the total number of pixels as some value other than width*height.
+        max_bytes: The maximum number of bytes in the image. RGB is counted as 4
+            bytes; all other modes are counted as 1 byte.
+    """
+    size = image_size
+
+    if max_size is not None:
+        overage = max_size[0] / size[0], max_size[1] / size[1]
+        size_factor = min(overage)
+        if size_factor < 1.0:
+            log.debug("Resizing image to fit image dimensions limit")
+            size = floor(size[0] * size_factor), floor(size[1] * size_factor)
+            if size[0] == 0:
+                size = 1, min(size[1], max_size[1])
+            elif size[1] == 0:
+                size = min(size[0], max_size[0]), 1
+
+    if max_pixels is not None:
+        if size[0] * size[1] > max_pixels:
+            log.debug("Resizing image to fit image pixel limit")
+            pixels_factor = sqrt(max_pixels / (size[0] * size[1]))
+            size = floor(size[0] * pixels_factor), floor(size[1] * pixels_factor)
+
+    if max_bytes is not None:
+        bpp = bytes_per_pixel
+        # stride = bytes per line
+        stride = size[0] * bpp
+        height = size[1]
+        if stride * height > max_bytes:
+            log.debug("Resizing image to fit image byte size limit")
+            bytes_factor = sqrt(max_bytes / (stride * height))
+            scaled_stride = floor(stride * bytes_factor)
+            scaled_height = floor(height * bytes_factor)
+            if scaled_stride == 0:
+                scaled_stride = bpp
+                scaled_height = min(max_bytes // bpp, scaled_height)
+            if scaled_height == 0:
+                scaled_height = 1
+                scaled_stride = min(max_bytes // scaled_height, scaled_stride)
+            size = floor(scaled_stride / bpp), scaled_height
+
+    return size
+
+
+def calculate_downsample(
+    image: Image.Image,
+    *,
+    max_size: Optional[tuple[int, int]] = None,
+    max_pixels: Optional[int] = None,
+    max_bytes: Optional[int] = None,
+) -> tuple[int, int]:
+    """Calculate image size required to downsample an image to fit limits.
+
+    If no limit is exceeded, the input image's size is returned.
+
+    Args:
+        image: The image to downsample.
+        max_size: The maximum width and height of the image.
+        max_pixels: The maximum number of pixels in the image. Some image consumers
+            limit the total number of pixels as some value other than width*height.
+        max_bytes: The maximum number of bytes in the image. RGB is counted as 4
+            bytes; all other modes are counted as 1 byte.
+    """
+    return _calculate_downsample(
+        image.size,
+        bytes_per_pixel(image.mode),
+        max_size=max_size,
+        max_pixels=max_pixels,
+        max_bytes=max_bytes,
+    )
+
+
+def downsample_image(
+    image: Image.Image,
+    new_size: tuple[int, int],
+    *,
+    resample_mode: Image.Resampling = 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
@@ -11,9 +11,10 @@ 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 Callable, NamedTuple, NewType
 from zlib import compress

 import img2pdf
@@ -53,21 +54,25 @@ 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
+    pdf: Pdf, root: Path, image: Stream, xref: Xref
 ) -> tuple[PdfImage, tuple[Name, Object]] | None:
-    del pike  # unused args
+    """Determine if an image is extractable."""
+    del pdf  # unused args
    del root

    if image.Subtype != Name.Image:
@@ -122,11 +127,12 @@ 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(pdf, root, image, xref)
    if result is None:
        return None
    pim, filtdp = result
@@ -163,9 +169,10 @@ 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(pdf, root, image, xref)
    if result is None:
        return None
    pim, filtdp = result
@@ -224,13 +231,72 @@ 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, 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 +310,13 @@ 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):
-        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
+    working_xrefs, pageno_for_xref = _find_image_xrefs(pdf)
    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 +330,12 @@ 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 +345,10 @@ def extract_images_generic(
    return jpegs, pngs


-def extract_images_jbig2(pike: Pdf, root: Path, options) -> dict[int, list[XrefExt]]:
-    """Extract any bitonal image that we think we can improve as JBIG2"""
-
+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."""
    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 +359,7 @@ 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():
@@ -327,6 +368,7 @@ 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]]):
@@ -339,6 +381,7 @@ 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:
@@ -363,7 +406,7 @@ def _produce_jbig2_images(


 def convert_to_jbig2(
-    pike: Pdf,
+    pdf: Pdf,
    jbig2_groups: dict[int, list[XrefExt]],
    root: Path,
    options,
@@ -390,7 +433,7 @@ 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
@@ -401,7 +444,7 @@ 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
            )
@@ -421,8 +464,10 @@ 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)
@@ -433,7 +478,7 @@ def transcode_jpegs(
        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()

@@ -453,9 +498,9 @@ 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(pdf, root, image, xref)
    if result is None:
        return None
    _pim, filtdp = result
@@ -467,9 +512,9 @@ def _find_deflatable_jpeg(


 def _deflate_jpeg(args: tuple[Pdf, threading.Lock, Xref, int]) -> tuple[Xref, bytes]:
-    pike, lock, xref, complevel = args
+    pdf, lock, xref, complevel = args
    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)
@@ -494,13 +545,13 @@ 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):
        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()

@@ -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,
 ) -> None:
+    """Apply lossy transcoding to PNGs."""
    modified: MutableSet[Xref] = set()
    if options.optimize >= 2:
        png_quality = (
@@ -601,7 +653,7 @@ def transcode_pngs(

    for xref in modified:
        filename = png_name(root, xref)
-        _transcode_png(pike, filename, xref)
+        _transcode_png(pdf, filename, xref)


 DEFAULT_EXECUTOR = SerialExecutor()
@@ -614,6 +666,7 @@ def optimize(
    save_settings,
    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)
-        transcode_jpegs(pike, jpegs, root, options, executor)
-        deflate_jpegs(pike, root, options, executor)
+        jpegs, pngs = extract_images_generic(pdf, root, options)
+        transcode_jpegs(pdf, jpegs, 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(pike, pngs, png_name, root, options, executor)
+        #    transcode_pngs(pdf, jpegs, jpg_name, root, options)
+        transcode_pngs(pdf, pngs, png_name, root, options, executor)

-        jbig2_groups = extract_images_jbig2(pike, root, options)
-        convert_to_jbig2(pike, jbig2_groups, root, options, executor)
+        jbig2_groups = extract_images_jbig2(pdf, root, options)
+        convert_to_jbig2(pdf, jbig2_groups, root, options, executor)

        target_file = output_file.with_suffix('.opt.pdf')
-        pike.remove_unreferenced_resources()
-        pike.save(target_file, **save_settings)
+        pdf.remove_unreferenced_resources()
+        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:
-            pike.remove_unreferenced_resources()
-            pike.save(output_file, **save_settings)
+        with Pdf.open(input_file) as pdf:
+            pdf.remove_unreferenced_resources()
+            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

@@ -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_data: bytes = None,
+    stream_name: str | None = 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:
@@ -7,3 +7,5 @@
 from __future__ import annotations

 from ocrmypdf.pdfinfo.info import Colorspace, Encoding, PageInfo, PdfInfo
+
+__all__ = ["Colorspace", "Encoding", "PageInfo", "PdfInfo"]
@@ -9,7 +9,10 @@ from __future__ import annotations
 import atexit
 import logging
 import re
+import statistics
+import sys
 from collections import defaultdict
+from collections.abc import Container, Iterable, Iterator, Mapping, Sequence
 from contextlib import ExitStack
 from decimal import Decimal
 from enum import Enum, auto
@@ -17,11 +20,14 @@ from functools import partial
 from math import hypot, inf, isclose
 from os import PathLike
 from pathlib import Path
-from typing import Container, Iterable, Iterator, Mapping, NamedTuple, Sequence, Tuple
+from typing import Callable, NamedTuple
 from warnings import warn

+from pdfminer.layout import LTPage, LTTextBox
 from pikepdf import (
+    Name,
    Object,
+    Page,
    Pdf,
    PdfImage,
    PdfInlineImage,
@@ -33,7 +39,7 @@ from pikepdf import (
 from ocrmypdf._concurrent import Executor, SerialExecutor
 from ocrmypdf.exceptions import EncryptedPdfError, InputFileError
 from ocrmypdf.helpers import Resolution, available_cpu_count, pikepdf_enable_mmap
-from ocrmypdf.pdfinfo.layout import get_page_analysis, get_text_boxes
+from ocrmypdf.pdfinfo.layout import LTStateAwareChar, get_page_analysis, get_text_boxes

 logger = logging.getLogger()

@@ -69,7 +75,7 @@ class Encoding(Enum):
    runlength = auto()


-FloatRect = Tuple[float, float, float, float]
+FloatRect = tuple[float, float, float, float]

 FRIENDLY_COLORSPACE: dict[str, Colorspace] = {
    '/DeviceGray': Colorspace.gray,
@@ -164,7 +170,7 @@ class TextMarker:


 def _normalize_stack(graphobjs):
-    """Convert runs of qQ's in the stack into single graphobjs"""
+    """Convert runs of qQ's in the stack into single graphobjs."""
    for operands, operator in graphobjs:
        operator = str(operator)
        if re.match(r'Q*q+$', operator):  # Zero or more Q, one or more q
@@ -200,7 +206,6 @@ def _interpret_contents(contentstream: Object, initial_shorthand=UNIT_SQUARE):
    undefined in the spec, but we just pretend nothing happened and leave the
    CTM unchanged.
    """
-
    stack = []
    ctm = PdfMatrix(initial_shorthand)
    xobject_settings: list[XobjectSettings] = []
@@ -307,7 +312,6 @@ def _get_dpi(ctm_shorthand, image_size) -> Resolution:
    /MediaBox.

    """
-
    a, b, c, d, _, _ = ctm_shorthand  # pylint: disable=invalid-name

    # Calculate the width and height of the image in PDF units
@@ -324,7 +328,12 @@ def _get_dpi(ctm_shorthand, image_size) -> Resolution:


 class ImageInfo:
-    """Information about an image found in a PDF."""
+    """Information about an image found in a PDF.
+
+    This gathers information from pikepdf and pdfminer.six, and is pickle-able
+    so that it can be passed to a worker process, unlike objects from those
+    libraries.
+    """

    DPI_PREC = Decimal('1.000')

@@ -339,6 +348,7 @@ class ImageInfo:
        inline: PdfInlineImage | None = None,
        shorthand=None,
    ):
+        """Initialize an ImageInfo."""
        self._name = str(name)
        self._shorthand = shorthand

@@ -405,54 +415,77 @@ class ImageInfo:

    @property
    def name(self):
+        """Name of the image as it appears in the PDF."""
        return self._name

    @property
    def type_(self):
+        """Type of image, either 'image' or 'stencil'."""
        return self._type

    @property
-    def width(self):
+    def width(self) -> int:
+        """Width of the image in pixels."""
        return self._width

    @property
-    def height(self):
+    def height(self) -> int:
+        """Height of the image in pixels."""
        return self._height

    @property
    def bpc(self):
+        """Bits per component."""
        return self._bpc

    @property
    def color(self):
+        """Colorspace of the image."""
        return self._color if self._color is not None else '?'

    @property
    def comp(self):
+        """Number of components/channels in the image."""
        return self._comp if self._comp is not None else '?'

    @property
    def enc(self):
+        """Encoding of the image."""
        return self._enc if self._enc is not None else 'image'

    @property
-    def renderable(self):
+    def renderable(self) -> bool:
+        """Whether the image is renderable.
+
+        Some PDFs in the wild have invalid images that are not renderable.
+        """
        return self.dpi.is_finite and self.width >= 0 and self.height >= 0

    @property
-    def dpi(self):
+    def dpi(self) -> Resolution:
+        """Dots per inch of the image.
+
+        Calculated based on where and how the image is drawn in the PDF.
+        """
        return _get_dpi(self._shorthand, (self._width, self._height))

+    @property
+    def printed_area(self) -> float:
+        """Physical area of the image in square inches."""
+        if not self.renderable:
+            return 0.0
+        return float(self.width * self.dpi.x * self.height * self.dpi.y)
+
    def __repr__(self):
+        """Return a string representation of the image."""
        return (
-            f"<ImageInfo '{self.name}' {self.type_} {self.width}x{self.height} "
+            f"<ImageInfo '{self.name}' {self.type_} {self.width}×{self.height} "
            f"{self.color} {self.comp} {self.bpc} {self.enc} {self.dpi}>"
        )


 def _find_inline_images(contentsinfo: ContentsInfo) -> Iterator[ImageInfo]:
-    "Find inline images in the contentstream"
-
+    """Find inline images in the contentstream."""
    for n, inline in enumerate(contentsinfo.inline_images):
        yield ImageInfo(
            name=f'inline-{n:02d}', shorthand=inline.shorthand, inline=inline.iimage
@@ -460,7 +493,7 @@ def _find_inline_images(contentsinfo: ContentsInfo) -> Iterator[ImageInfo]:


 def _image_xobjects(container) -> Iterator[tuple[Object, str]]:
-    """Search for all XObject-based images in the container
+    """Search for all XObject-based images in the container.

    Usually the container is a page, but it could also be a Form XObject
    that contains images. Filter out the Form XObjects which are dealt with
@@ -471,16 +504,15 @@ def _image_xobjects(container) -> Iterator[tuple[Object, str]]:
    since the object does not know its own name.

    """
-
-    if '/Resources' not in container:
+    if Name.Resources not in container:
        return
-    resources = container['/Resources']
-    if '/XObject' not in resources:
+    resources = container[Name.Resources]
+    if Name.XObject not in resources:
        return
-    for key, candidate in resources['/XObject'].items():
-        if candidate is None or '/Subtype' not in candidate:
+    for key, candidate in resources[Name.XObject].items():
+        if candidate is None or Name.Subtype not in candidate:
            continue
-        if candidate['/Subtype'] == '/Image':
+        if candidate[Name.Subtype] == Name.Image:
            pdfimage = candidate
            yield (pdfimage, key)

@@ -488,14 +520,13 @@ def _image_xobjects(container) -> Iterator[tuple[Object, str]]:
 def _find_regular_images(
    container: Object, contentsinfo: ContentsInfo
 ) -> Iterator[ImageInfo]:
-    """Find images stored in the container's /Resources /XObject
+    """Find images stored in the container's /Resources /XObject.

    Usually the container is a page, but it could also be a Form XObject
    that contains images.

    Generates images with their DPI at time of drawing.
    """
-
    for pdfimage, xobj in _image_xobjects(container):
        if xobj not in contentsinfo.name_index:
            continue
@@ -512,20 +543,20 @@ def _find_regular_images(


 def _find_form_xobject_images(pdf: Pdf, container: Object, contentsinfo: ContentsInfo):
-    """Find any images that are in Form XObjects in the container
+    """Find any images that are in Form XObjects in the container.

    The container may be a page, or a parent Form XObject.

    """
-    if '/Resources' not in container:
+    if Name.Resources not in container:
        return
-    resources = container['/Resources']
-    if '/XObject' not in resources:
+    resources = container[Name.Resources]
+    if Name.XObject not in resources:
        return
-    xobjs = resources['/XObject'].as_dict()
+    xobjs = resources[Name.XObject].as_dict()
    for xobj in xobjs:
        candidate = xobjs[xobj]
-        if candidate['/Subtype'] != '/Form':
+        if candidate is None or candidate[Name.Subtype] != Name.Form:
            continue

        form_xobject = candidate
@@ -546,7 +577,7 @@ def _find_form_xobject_images(pdf: Pdf, container: Object, contentsinfo: Content
 def _process_content_streams(
    *, pdf: Pdf, container: Object, shorthand=None
 ) -> Iterator[VectorMarker | TextMarker | ImageInfo]:
-    """Find all individual instances of images drawn in the container
+    """Find all individual instances of images drawn in the container.

    Usually the container is a page, but it may also be a Form XObject.

@@ -563,17 +594,19 @@ def _process_content_streams(
    downsampling.

    """
-
-    if container.get('/Type') == '/Page' and '/Contents' in container:
+    if container.get(Name.Type) == Name.Page and Name.Contents in container:
        initial_shorthand = shorthand or UNIT_SQUARE
-    elif container.get('/Type') == '/XObject' and container['/Subtype'] == '/Form':
+    elif (
+        container.get(Name.Type) == Name.XObject
+        and container[Name.Subtype] == Name.Form
+    ):
        # Set the CTM to the state it was when the "Do" operator was
        # encountered that is drawing this instance of the Form XObject
        ctm = PdfMatrix(shorthand) if shorthand else PdfMatrix.identity()

        # A Form XObject may provide its own matrix to map form space into
        # user space. Get this if one exists
-        form_shorthand = container.get('/Matrix', PdfMatrix.identity())
+        form_shorthand = container.get(Name.Matrix, PdfMatrix.identity())
        form_matrix = PdfMatrix(form_shorthand)

        # Concatenate form matrix with CTM to ensure CTM is correct for
@@ -595,8 +628,7 @@ def _process_content_streams(


 def _page_has_text(text_blocks: Iterable[FloatRect], page_width, page_height) -> bool:
-    """Smarter text detection that ignores text in margins"""
-
+    """Smarter text detection that ignores text in margins."""
    pw, ph = float(page_width), float(page_height)  # pylint: disable=invalid-name

    margin_ratio = 0.125
@@ -608,10 +640,11 @@ def _page_has_text(text_blocks: Iterable[FloatRect], page_width, page_height) ->
    )

    def rects_intersect(a: FloatRect, b: FloatRect) -> bool:
-        """
+        """Check if two 4-tuple rects intersect.
+
        Where (a,b) are 4-tuple rects (left-0, top-1, right-2, bottom-3)
        https://stackoverflow.com/questions/306316/determine-if-two-rectangles-overlap-each-other
-        Formula assumes all boxes are in first quadrant
+        Formula assumes all boxes are in first quadrant.
        """
        return a[0] < b[2] and a[2] > b[0] and a[1] > b[3] and a[3] < b[1]

@@ -623,15 +656,18 @@ def _page_has_text(text_blocks: Iterable[FloatRect], page_width, page_height) ->
    return has_text


-def simplify_textboxes(miner, textbox_getter) -> Iterator[TextboxInfo]:
-    """Extract only limited content from text boxes
+def simplify_textboxes(
+    miner: LTPage, textbox_getter: Callable[[LTPage], Iterator[LTTextBox]]
+) -> Iterator[TextboxInfo]:
+    """Extract only limited content from text boxes.

    We do this to save memory and ensure that our objects are pickleable.
    """
    for box in textbox_getter(miner):
        first_line = box._objs[0]  # pylint: disable=protected-access
        first_char = first_line._objs[0]  # pylint: disable=protected-access
-
+        if not isinstance(first_char, LTStateAwareChar):
+            continue
        visible = first_char.rendermode != 3
        corrupt = first_char.get_text() == '\ufffd'
        yield TextboxInfo(box.bbox, visible, corrupt)
@@ -725,12 +761,38 @@ def _pdf_pageinfo_concurrent(
    return pages


+class PageResolutionProfile(NamedTuple):
+    """Information about the resolutions of a page."""
+
+    weighted_dpi: float
+    """The weighted average DPI of the page, weighted by the area of each image."""
+
+    max_dpi: float
+    """The maximum DPI of an image on the page."""
+
+    average_to_max_dpi_ratio: float
+    """The average DPI of the page divided by the maximum DPI of the page.
+
+    This indicates the intensity of the resolution variation on the page.
+
+    If the average is 1.0 or close to 1.0, has all of its content at a uniform
+    resolution. If the average is much lower than 1.0, some content is at a
+    higher resolution than the rest of the page.
+    """
+
+    area_ratio: float
+    """The maximum-DPI area of the page divided by the total drawn area.
+
+    This indicates the prevalence of high-resolution content on the page.
+    """
+
+
 class PageInfo:
    """Information about type of contents on each page in a PDF."""

    _has_text: bool | None
    _has_vector: bool | None
-    _images: list[ImageInfo]
+    _images: list[ImageInfo] = []

    def __init__(
        self,
@@ -740,6 +802,7 @@ class PageInfo:
        check_pages: Container[int],
        detailed_analysis: bool = False,
    ):
+        """Initialize a PageInfo object."""
        self._pageno = pageno
        self._infile = infile
        self._detailed_analysis = detailed_analysis
@@ -753,7 +816,7 @@ class PageInfo:
        check_pages: Container[int],
        detailed_analysis: bool,
    ):
-        page = pdf.pages[pageno]
+        page: Page = pdf.pages[pageno]
        mediabox = [Decimal(d) for d in page.MediaBox.as_list()]
        width_pt = mediabox[2] - mediabox[0]
        height_pt = mediabox[3] - mediabox[1]
@@ -761,9 +824,12 @@ class PageInfo:
        check_this_page = pageno in check_pages

        if check_this_page and detailed_analysis:
-            pscript5_mode = str(pdf.docinfo.get('/Creator')).startswith('PScript5')
+            pscript5_mode = str(pdf.docinfo.get(Name.Creator)).startswith('PScript5')
            miner = get_page_analysis(infile, pageno, pscript5_mode)
-            self._textboxes = list(simplify_textboxes(miner, get_text_boxes))
+            if miner is not None:
+                self._textboxes = list(simplify_textboxes(miner, get_text_boxes))
+            else:
+                self._textboxes = []
            bboxes = (box.bbox for box in self._textboxes)

            self._has_text = _page_has_text(bboxes, width_pt, height_pt)
@@ -771,17 +837,13 @@ class PageInfo:
            self._textboxes = []
            self._has_text = None  # i.e. "no information"

-        userunit = page.get('/UserUnit', Decimal(1.0))
+        userunit = page.get(Name.UserUnit, Decimal(1.0))
        if not isinstance(userunit, Decimal):
            userunit = Decimal(userunit)
        self._userunit = userunit
        self._width_inches = width_pt * userunit / Decimal(72.0)
        self._height_inches = height_pt * userunit / Decimal(72.0)
-
-        try:
-            self._rotate = int(page['/Rotate'])
-        except KeyError:
-            self._rotate = 0
+        self._rotate = int(getattr(page.obj, 'Rotate', 0))

        userunit_shorthand = (userunit, 0, 0, userunit, 0, 0)

@@ -816,40 +878,56 @@ class PageInfo:

    @property
    def pageno(self) -> int:
+        """Return page number (0-based)."""
        return self._pageno

    @property
    def has_text(self) -> bool:
+        """Return True if page has text, False if not or unknown."""
        return bool(self._has_text)

    @property
    def has_corrupt_text(self) -> bool:
+        """Return True if page has corrupt text, False if not or unknown."""
        if not self._detailed_analysis:
            raise NotImplementedError('Did not do detailed analysis')
        return any(tbox.is_corrupt for tbox in self._textboxes)

    @property
    def has_vector(self) -> bool:
+        """Return True if page has vector graphics, False if not or unknown.
+
+        Vector graphics are sometimes used to draw fonts, so it may not be
+        obvious on visual inspection whether a page has text or not.
+        """
        return bool(self._has_vector)

    @property
    def width_inches(self) -> Decimal:
+        """Return width of page in inches."""
        return self._width_inches

    @property
    def height_inches(self) -> Decimal:
+        """Return height of page in inches."""
        return self._height_inches

    @property
    def width_pixels(self) -> int:
+        """Return width of page in pixels."""
        return int(round(float(self.width_inches) * self.dpi.x))

    @property
    def height_pixels(self) -> int:
+        """Return height of page in pixels."""
        return int(round(float(self.height_inches) * self.dpi.y))

    @property
    def rotation(self) -> int:
+        """Return rotation of page in degrees.
+
+        Will only be a multiple of 90.
+        """
        return self._rotate

    @rotation.setter
@@ -860,11 +938,16 @@ class PageInfo:
            raise ValueError("rotation must be a cardinal angle")

    @property
-    def images(self):
+    def images(self) -> list[ImageInfo]:
+        """Return images."""
        return self._images

    def get_textareas(self, visible: bool | None = None, corrupt: bool | None = None):
-        def predicate(obj, want_visible, want_corrupt):
+        """Return textareas bounding boxes in PDF coordinates on the page."""
+
+        def predicate(
+            obj: TextboxInfo, want_visible: bool | None, want_corrupt: bool | None
+        ) -> bool:
            result = True
            if want_visible is not None:
                if obj.is_visible != want_visible:
@@ -883,22 +966,67 @@ class PageInfo:

    @property
    def dpi(self) -> Resolution:
+        """Return DPI needed to render all images on the page."""
        if self._dpi is None:
            return Resolution(0.0, 0.0)
        return self._dpi

    @property
    def userunit(self) -> Decimal:
+        """Return user unit of page."""
        return self._userunit

    @property
    def min_version(self) -> str:
+        """Return minimum PDF version needed to render this page."""
        if self.userunit is not None:
            return '1.6'
        else:
            return '1.5'

+    def page_dpi_profile(self) -> PageResolutionProfile | None:
+        """Return information about the DPIs of the page.
+
+        This is useful to detect pages with a small proportion of high-resolution
+        content that is forcing us to use a high DPI for the whole page. The ratio
+        is weighted by the area of each image. If images overlap, the overlapped
+        area counts.
+
+        Vector graphics and text are ignored.
+
+        Returns None if there is no meaningful DPI for the page.
+        """
+        image_dpis = [
+            image.dpi.to_scalar() for image in self._images if image.renderable
+        ]
+        image_areas = [image.printed_area for image in self._images if image.renderable]
+        total_drawn_area = sum(image_areas)
+        if total_drawn_area == 0:
+            return None
+
+        weights = [area / total_drawn_area for area in image_areas]
+        # Calculate harmonic mean of DPIs weighted by area
+        if sys.version_info >= (3, 10):
+            weighted_dpi = statistics.harmonic_mean(image_dpis, weights)
+        else:
+            weighted_dpi = sum(weights) / sum(
+                weight / dpi for weight, dpi in zip(weights, image_dpis)
+            )
+        max_dpi = max(image_dpis)
+        dpi_average_max_ratio = weighted_dpi / max_dpi
+
+        arg_max_dpi = image_dpis.index(max_dpi)
+        max_area_ratio = image_areas[arg_max_dpi] / total_drawn_area
+
+        return PageResolutionProfile(
+            weighted_dpi,
+            max_dpi,
+            dpi_average_max_ratio,
+            max_area_ratio,
+        )
+
    def __repr__(self):
+        """Return string representation."""
        return (
            f'<PageInfo '
            f'pageno={self.pageno} {self.width_inches}"x{self.height_inches}" '
@@ -910,7 +1038,11 @@ DEFAULT_EXECUTOR = SerialExecutor()


 class PdfInfo:
-    """Get summary information about a PDF"""
+    """Get summary information about a PDF."""
+
+    _has_acroform: bool = False
+    _has_signature: bool = False
+    _needs_rendering: bool = False

    def __init__(
        self,
@@ -918,10 +1050,11 @@ class PdfInfo:
        *,
        detailed_analysis: bool = False,
        progbar: bool = False,
-        max_workers: int = None,
+        max_workers: int | None = None,
        check_pages=None,
        executor: Executor = DEFAULT_EXECUTOR,
    ):
+        """Initialize."""
        self._infile = infile
        if check_pages is None:
            check_pages = range(0, 1_000_000_000)
@@ -938,52 +1071,71 @@ class PdfInfo:
                check_pages=check_pages,
                detailed_analysis=detailed_analysis,
            )
-            self._needs_rendering = pdf.Root.get('/NeedsRendering', False)
-            self._has_acroform = False
-            if '/AcroForm' in pdf.Root:
-                if len(pdf.Root.AcroForm.get('/Fields', [])) > 0:
+            self._needs_rendering = pdf.Root.get(Name.NeedsRendering, False)
+            if Name.AcroForm in pdf.Root:
+                if len(pdf.Root.AcroForm.get(Name.Fields, [])) > 0:
                    self._has_acroform = True
-                elif '/XFA' in pdf.Root.AcroForm:
+                elif Name.XFA in pdf.Root.AcroForm:
                    self._has_acroform = True
+                self._has_signature = bool(pdf.Root.AcroForm.get(Name.SigFlags, 0) & 1)

    @property
    def pages(self) -> Sequence[PageInfo | None]:
+        """Return list of PageInfo objects, one per page in the PDF."""
        return self._pages

    @property
    def min_version(self) -> str:
+        """Return minimum PDF version needed to render this PDF."""
        # The minimum PDF is the maximum version that any particular page needs
        return max(page.min_version for page in self.pages if page)

    @property
    def has_userunit(self) -> bool:
+        """Return True if any page has a user unit."""
        return any(page.userunit != 1.0 for page in self.pages if page)

    @property
    def has_acroform(self) -> bool:
+        """Return True if the document catalog has an AcroForm."""
        return self._has_acroform

+    @property
+    def has_signature(self) -> bool:
+        """Return True if the document annotations has a digital signature."""
+        return self._has_signature
+
    @property
    def filename(self) -> str | Path:
+        """Return filename of PDF."""
        if not isinstance(self._infile, (str, Path)):
            raise NotImplementedError("can't get filename from stream")
        return self._infile

    @property
    def needs_rendering(self) -> bool:
+        """Return True if PDF contains XFA forms.
+
+        XFA forms are not supported by most standard PDF renderers, so we
+        need to detect and suppress them.
+        """
        return self._needs_rendering

    def __getitem__(self, item) -> PageInfo:
+        """Return PageInfo object for page number `item`."""
        return self._pages[item]

    def __len__(self):
+        """Return number of pages in PDF."""
        return len(self._pages)

    def __repr__(self):
+        """Return string representation."""
        return f"<PdfInfo('...'), page count={len(self)}>"


 def main():
+    """Run as a script."""
    import argparse  # pylint: disable=import-outside-toplevel
    from pprint import pprint  # pylint: disable=import-outside-toplevel

@@ -5,8 +5,12 @@
 from __future__ import annotations

 import re
+from collections.abc import Mapping
+from contextlib import contextmanager
 from math import copysign
+from os import PathLike
 from pathlib import Path
+from typing import Any, Iterator
 from unittest.mock import patch

 import pdfminer
@@ -15,10 +19,13 @@ import pdfminer.pdfdevice
 import pdfminer.pdfinterp
 from pdfminer.converter import PDFLayoutAnalyzer
 from pdfminer.layout import LAParams, LTChar, LTPage, LTTextBox
+from pdfminer.pdfcolor import PDFColorSpace
+from pdfminer.pdfdevice import PDFTextSeq
 from pdfminer.pdfdocument import PDFTextExtractionNotAllowed
-from pdfminer.pdffont import PDFSimpleFont, PDFUnicodeNotDefined
+from pdfminer.pdffont import FontWidthDict, PDFFont, PDFSimpleFont, PDFUnicodeNotDefined
+from pdfminer.pdfinterp import PDFGraphicState, PDFResourceManager, PDFTextState
 from pdfminer.pdfpage import PDFPage
-from pdfminer.utils import bbox2str, matrix2str
+from pdfminer.utils import Matrix, bbox2str, matrix2str

 from ocrmypdf.exceptions import EncryptedPdfError, InputFileError

@@ -28,19 +35,28 @@ STRIP_NAME = re.compile(r'[0-9]+')
 original_pdfsimplefont_init = PDFSimpleFont.__init__


-def pdfsimplefont__init__(self, descriptor, widths, spec):
+def pdfsimplefont__init__(
+    self,
+    descriptor: Mapping[str, Any],
+    widths: FontWidthDict,
+    spec: Mapping[str, Any],
+) -> None:
+    """Monkeypatch pdfminer.six PDFSimpleFont.__init__.
+
+    If there is no ToUnicode and no Encoding, pdfminer.six assumes that Unicode
+    conversion is possible. This is incorrect, according to PDF Reference Manual
+    9.10.2. This patch fixes that.
+    """
    # Font encoding is specified either by a name of
    # built-in encoding or a dictionary that describes
    # the differences.
    original_pdfsimplefont_init(self, descriptor, widths, spec)
-    # pdfminer is incorrect. If there is no ToUnicode and no Encoding, do not
-    # assume Unicode conversion is possible. RM 9.10.2
    if not self.unicode_map and 'Encoding' not in spec:
        self.cid2unicode = {}
    return


-PDFSimpleFont.__init__ = pdfsimplefont__init__
+setattr(PDFSimpleFont, '__init__', pdfsimplefont__init__)

 #
 # pdfminer patches when creator is PScript5.dll
@@ -48,6 +64,13 @@ PDFSimpleFont.__init__ = pdfsimplefont__init__


 def pdftype3font__pscript5_get_height(self):
+    """Monkeypatch for PScript5.dll PDFs.
+
+    The height of Type3 fonts is known to be incorrect in PScript5.dll
+    generated PDFs. This patch attempts to correct the height by
+    using the bbox height if it is available, otherwise using the
+    ascent and descent.
+    """
    h = self.bbox[3] - self.bbox[1]
    if h == 0:
        h = self.ascent - self.descent
@@ -55,15 +78,32 @@ def pdftype3font__pscript5_get_height(self):


 def pdftype3font__pscript5_get_descent(self):
+    """Monkeypatch for PScript5.dll PDFs.
+
+    The descent of Type3 fonts is known to be incorrect in PScript5.dll
+    generated PDFs. This patch attempts to correct the descent by
+    using the vscale.
+    """
    return self.descent * copysign(1.0, self.vscale)


 def pdftype3font__pscript5_get_ascent(self):
+    """Monkeypatch for PScript5.dll PDFs.
+
+    The ascent of Type3 fonts is known to be incorrect in PScript5.dll
+    generated PDFs. This patch attempts to correct the ascent by
+    using the vscale.
+    """
    return self.ascent * copysign(1.0, self.vscale)


+def _is_undefined_char(s: str) -> bool:
+    """Check if a string is an undefined character."""
+    return s.startswith('(cid:') and s.endswith(')')
+
+
 class LTStateAwareChar(LTChar):
-    """A subclass of LTChar that tracks text render mode at time of drawing"""
+    """A subclass of LTChar that tracks text render mode at time of drawing."""

    __slots__ = (
        'rendermode',
@@ -84,18 +124,19 @@ class LTStateAwareChar(LTChar):

    def __init__(
        self,
-        matrix,
-        font,
-        fontsize,
-        scaling,
-        rise,
-        text,
-        textwidth,
-        textdisp,
-        ncs,
-        graphicstate,
-        textstate,
-    ):
+        matrix: Matrix,
+        font: PDFFont,
+        fontsize: float,
+        scaling: float,
+        rise: float,
+        text: str,
+        textwidth: float,
+        textdisp: float | tuple[float | None, float],
+        ncs: PDFColorSpace,
+        graphicstate: PDFGraphicState,
+        textstate: PDFTextState,
+    ) -> None:
+        """Initialize."""
        super().__init__(
            matrix,
            font,
@@ -110,30 +151,31 @@ class LTStateAwareChar(LTChar):
        )
        self.rendermode = textstate.render

-    def is_compatible(self, obj):
-        """Check if characters can be combined into a textline
+    def is_compatible(self, obj: object) -> bool:
+        """Check if characters can be combined into a textline.

        We consider characters compatible if:
            - the Unicode mapping is known, and both have the same render mode
            - the Unicode mapping is unknown but both are part of the same font
        """
        # pylint: disable=protected-access
-        both_unicode_mapped = isinstance(self._text, str) and isinstance(obj._text, str)
-        try:
-            if both_unicode_mapped:
-                return self.rendermode == obj.rendermode
-            font0, _ = self._text
-            font1, _ = obj._text
-            return font0 == font1 and self.rendermode == obj.rendermode
-        except (ValueError, AttributeError):
+        if not isinstance(obj, LTStateAwareChar):
            return False
+        both_unicode_mapped = not _is_undefined_char(
+            self._text
+        ) and not _is_undefined_char(obj._text)
+        if both_unicode_mapped:
+            return self.rendermode == obj.rendermode
+        return self.fontname == obj.fontname and self.rendermode == obj.rendermode

-    def get_text(self):
-        if isinstance(self._text, tuple):
+    def get_text(self) -> str:
+        """Get text from this character."""
+        if _is_undefined_char(self._text):
            return '\ufffd'  # standard 'Unknown symbol'
        return self._text

-    def __repr__(self):
+    def __repr__(self) -> str:
+        """Return a string representation of this object."""
        return (
            f"<{self.__class__.__name__} "
            f"{bbox2str(self.bbox)} "
@@ -146,19 +188,27 @@ class LTStateAwareChar(LTChar):


 class TextPositionTracker(PDFLayoutAnalyzer):
-    """A page layout analyzer that pays attention to text visibility"""
+    """A page layout analyzer that pays attention to text visibility."""

-    def __init__(self, rsrcmgr, pageno=1, laparams=None):
+    textstate: PDFTextState
+
+    def __init__(
+        self,
+        rsrcmgr: PDFResourceManager,
+        pageno: int = 1,
+        laparams: LAParams | None = None,
+    ):
+        """Initialize the layout analyzer."""
        super().__init__(rsrcmgr, pageno, laparams)
-        self.textstate = None
-        self.result = None
-        self.cur_item = None  # not defined in pdfminer code as it should be
+        self.result: LTPage | None = None

-    def begin_page(self, page, ctm):
+    def begin_page(self, page: PDFPage, ctm: Matrix) -> None:
+        """Begin processing of a page."""
        super().begin_page(page, ctm)
        self.cur_item = LTPage(self.pageno, page.mediabox)

-    def end_page(self, page):
+    def end_page(self, page: PDFPage) -> None:
+        """End processing of a page."""
        assert not self._stack, str(len(self._stack))
        assert isinstance(self.cur_item, LTPage), str(type(self.cur_item))
        if self.laparams is not None:
@@ -166,13 +216,29 @@ class TextPositionTracker(PDFLayoutAnalyzer):
        self.pageno += 1
        self.receive_layout(self.cur_item)

-    def render_string(self, textstate, seq, ncs, graphicstate):
+    def render_string(
+        self,
+        textstate: PDFTextState,
+        seq: PDFTextSeq,
+        ncs: PDFColorSpace,
+        graphicstate: PDFGraphicState,
+    ) -> None:
+        """Respond to render string event by updating text state."""
        self.textstate = textstate.copy()
        super().render_string(self.textstate, seq, ncs, graphicstate)

    def render_char(
-        self, matrix, font, fontsize, scaling, rise, cid, ncs, graphicstate
-    ):
+        self,
+        matrix: Matrix,
+        font: PDFFont,
+        fontsize: float,
+        scaling: float,
+        rise: float,
+        cid: int,
+        ncs: PDFColorSpace,
+        graphicstate: PDFGraphicState,
+    ) -> float:
+        """Respond to render char event by updating text state."""
        try:
            text = font.to_unichr(cid)
            assert isinstance(text, str), str(type(text))
@@ -196,18 +262,35 @@ class TextPositionTracker(PDFLayoutAnalyzer):
        self.cur_item.add(item)
        return item.adv

-    def handle_undefined_char(self, font, cid):
-        # log.info('undefined: %r, %r', font, cid)
-        return (font.fontname, cid)
-
-    def receive_layout(self, ltpage):
+    def receive_layout(self, ltpage: LTPage) -> None:
+        """Receive layout handler."""
        self.result = ltpage

-    def get_result(self):
+    def get_result(self) -> LTPage | None:
+        """Get the result of the analysis."""
        return self.result


-def get_page_analysis(infile, pageno, pscript5_mode):
+@contextmanager
+def patch_pdfminer(pscript5_mode: bool):
+    """Patch pdfminer.six to work around bugs in PDFs created by PScript5."""
+    if pscript5_mode:
+        with patch.multiple(
+            'pdfminer.pdffont.PDFType3Font',
+            spec=True,
+            get_ascent=pdftype3font__pscript5_get_ascent,
+            get_descent=pdftype3font__pscript5_get_descent,
+            get_height=pdftype3font__pscript5_get_height,
+        ):
+            yield
+    else:
+        yield
+
+
+def get_page_analysis(
+    infile: PathLike, pageno: int, pscript5_mode: bool
+) -> LTPage | None:
+    """Get the page analysis for a given page."""
    rman = pdfminer.pdfinterp.PDFResourceManager(caching=True)
    disable_boxes_flow = None
    dev = TextPositionTracker(
@@ -218,36 +301,24 @@ def get_page_analysis(infile, pageno, pscript5_mode):
    )
    interp = pdfminer.pdfinterp.PDFPageInterpreter(rman, dev)

-    patcher = None
-    if pscript5_mode:
-        patcher = patch.multiple(
-            'pdfminer.pdffont.PDFType3Font',
-            spec=True,
-            get_ascent=pdftype3font__pscript5_get_ascent,
-            get_descent=pdftype3font__pscript5_get_descent,
-            get_height=pdftype3font__pscript5_get_height,
-        )
-        patcher.start()
-
-    try:
-        with Path(infile).open('rb') as f:
-            page_iter = PDFPage.get_pages(f, pagenos=[pageno], maxpages=0)
-            page = next(page_iter, None)
-            if page is None:
-                raise InputFileError(
-                    f"pdfminer could not process page {pageno} (counting from 0)."
-                )
-            interp.process_page(page)
-    except PDFTextExtractionNotAllowed as e:
-        raise EncryptedPdfError() from e
-    finally:
-        if patcher is not None:
-            patcher.stop()
+    with patch_pdfminer(pscript5_mode):
+        try:
+            with Path(infile).open('rb') as f:
+                page_iter = PDFPage.get_pages(f, pagenos=[pageno], maxpages=0)
+                page = next(page_iter, None)
+                if page is None:
+                    raise InputFileError(
+                        f"pdfminer could not process page {pageno} (counting from 0)."
+                    )
+                interp.process_page(page)
+        except PDFTextExtractionNotAllowed as e:
+            raise EncryptedPdfError() from e

    return dev.get_result()


-def get_text_boxes(obj):
+def get_text_boxes(obj) -> Iterator[LTTextBox]:
+    """Get the text boxes attached to the current node."""
    for child in obj:
        if isinstance(child, (LTTextBox)):
            yield child
@@ -7,9 +7,10 @@ from __future__ import annotations

 from abc import ABC, abstractmethod
 from argparse import ArgumentParser, Namespace
+from collections.abc import Sequence, Set
 from logging import Handler
 from pathlib import Path
-from typing import TYPE_CHECKING, AbstractSet, NamedTuple, Sequence
+from typing import TYPE_CHECKING, NamedTuple

 import pluggy

@@ -28,6 +29,7 @@ if TYPE_CHECKING:
 hookspec = pluggy.HookspecMarker('ocrmypdf')

 # pylint: disable=unused-argument
+# mypy: disable-error-code=empty-body


@hookspec(firstresult=True)
@@ -43,7 +45,7 @@ def get_logging_console() -> Handler:


@hookspec
-def initialize(plugin_manager: pluggy.PluginManager):
+def initialize(plugin_manager: pluggy.PluginManager) -> None:
    """Called when this plugin is first loaded into OCRmyPDF.

    The primary intended use of this is for plugins to check compatibility with other
@@ -99,6 +101,8 @@ def check_options(options: Namespace) -> None:
        ocrmypdf.exceptions.ExitCodeException: If options are not acceptable
            and the application should terminate gracefully with an informative
            message and error code.
+
+
    Note:
        This hook will be called from the main process, and may modify global state
        before child worker processes are forked.
@@ -127,6 +131,8 @@ def get_executor(progressbar_class) -> Executor:
    Note:
        This hook will be called from the main process, and may modify global state
        before child worker processes are forked.
+
+
    Note:
        This is a :ref:`firstresult hook<firstresult>`.
    """
@@ -159,7 +165,6 @@ def get_progressbar_class():
    Here is how OCRmyPDF will use the progress bar:

    Example:
-
        pbar_class = pm.hook.get_progressbar_class()
        with pbar_class(**tqdm_kwargs) as pbar:
            ...
@@ -181,6 +186,8 @@ def validate(pdfinfo: PdfInfo, options: Namespace) -> None:
        ocrmypdf.exceptions.ExitCodeException: If options or pdfinfo are not acceptable
            and the application should terminate gracefully with an informative
            message and error code.
+
+
    Note:
        This hook will be called from the main process, and may modify global state
        before child worker processes are forked.
@@ -197,6 +204,7 @@ def rasterize_pdf_page(
    page_dpi: Resolution | None,
    rotation: int | None,
    filter_vector: bool,
+    stop_on_soft_error: bool,
 ) -> Path:
    """Rasterize one page of a PDF at resolution raster_dpi in canvas units.

@@ -207,17 +215,26 @@ def rasterize_pdf_page(
    Args:
        input_file: The PDF to rasterize.
        output_file: The desired name of the rasterized image.
-        raster_device: Type of image to produce at output_file
-        raster_dpi: Resolution at which to rasterize page
-        pageno: Page number to rasterize (beginning at page 1)
-        page_dpi: Resolution, overriding output image DPI
-        rotation: Cardinal angle, clockwise, to rotate page
-        filter_vector: If True, remove vector graphics objects
+        raster_device: Type of image to produce at output_file.
+        raster_dpi: Resolution in dots per inch at which to rasterize page.
+        pageno: Page number to rasterize (beginning at page 1).
+        page_dpi: Resolution, overriding output image DPI.
+        rotation: Cardinal angle, clockwise, to rotate page.
+        filter_vector: If True, remove vector graphics objects.
+        stop_on_soft_error: If there is an "soft error" such that PDF page image
+            generation can proceed, but may visually differ from the original,
+            the implementer of this hook should raise a detailed exception. If
+            ``False``, continue processing and report by logging it. If the hook
+            cannot proceed, it should always raise an exception, regardless of
+            this setting. One "soft error" would be a missing font that is
+            required to properly rasterize the PDF.
+
    Returns:
        Path: output_file if successful
    Note:
        This hook will be called from child processes. Modifying global state
        will not affect the main process or other child processes.
+
    Note:
        This is a :ref:`firstresult hook<firstresult>`.
    """
@@ -228,23 +245,32 @@ def filter_ocr_image(page: PageContext, image: Image.Image) -> Image.Image:
    """Called to filter the image before it is sent to OCR.

    This is the image that OCR sees, not what the user sees when they view the
-    PDF. If ``redo_ocr`` is enabled, portions of the image will be masked so
-    they are not shown to OCR. The main use of this hook is expected to be hiding
-    content from OCR.
+    PDF. In certain modes such as ``--redo-ocr``, portions of the image may be
+    masked out to hide them from OCR.
+
+    The main uses of this hook are expected to be hiding content from OCR,
+    conditioning images to OCR better with filters, and adjusting images to
+    match any constraints imposed by the OCR engine.

    The input image may be color, grayscale, or monochrome, and the
-    output image may differ. The pixel width and height of the
-    output image must be identical to the input image, or misalignment between
-    the OCR text layer and visual position of the text will occur. Likewise,
-    the output must be a faithful representation of the input, or alignment
-    errors may occurs.
+    output image may differ. For example, if you know that a custom OCR engine
+    does not care about the color of the text, you could convert the image to
+    it to grayscale or monochrome.

-    Tesseract OCR only deals with monochrome images, and internally converts
-    non-monochrome images to OCR.
+    Generally speaking, the output image should be a faithful representation of
+    of the input image. You *may* change the pixel width and height of the
+    the input image, but you must not change the aspect ratio, and you must
+    calculate the DPI of the output image based on the new pixel width and
+    height or the OCR text layer will be misaligned with the visual position.
+
+    The built-in Tesseract OCR engine uses this hook itself to downsample
+    very large images to fit its constraints.

    Note:
        This hook will be called from child processes. Modifying global state
        will not affect the main process or other child processes.
+
+
    Note:
        This is a :ref:`firstresult hook<firstresult>`.
    """
@@ -269,7 +295,7 @@ def filter_page_image(page: PageContext, image_filename: Path) -> Path:
    to enforce these constraints; it is up to the plugin to do sensible things.

    OCRmyPDF will create the PDF page based on the image format used (unless the
-    hook is overriden). If you convert the image to a JPEG, the output page will
+    hook is overridden). If you convert the image to a JPEG, the output page will
    be created as a JPEG, etc. If you change the colorspace, that change will be
    kept. Note that the OCRmyPDF image optimization stage, if enabled, may
    ultimately chose a different format.
@@ -281,6 +307,8 @@ def filter_page_image(page: PageContext, image_filename: Path) -> Path:
    Note:
        This hook will be called from child processes. Modifying global state
        will not affect the main process or other child processes.
+
+
    Note:
        This is a :ref:`firstresult hook<firstresult>`.
    """
@@ -323,6 +351,7 @@ def filter_pdf_page(page: PageContext, image_filename: Path, output_pdf: Path) -
    Note:
        This hook will be called from child processes. Modifying global state
        will not affect the main process or other child processes.
+
    Note:
        This is a :ref:`firstresult hook<firstresult>`.
    """
@@ -377,11 +406,12 @@ class OcrEngine(ABC):

    @staticmethod
    @abstractmethod
-    def languages(options: Namespace) -> AbstractSet[str]:
+    def languages(options: Namespace) -> Set[str]:
        """Returns the set of all languages that are supported by the engine.

        Languages are typically given in 3-letter ISO 3166-1 codes, but actually
-        can be any value understood by the OCR engine."""
+        can be any value understood by the OCR engine.
+        """

    @staticmethod
    @abstractmethod
@@ -413,6 +443,9 @@ class OcrEngine(ABC):
                a single page PDF with no visible content of any kind, sized
                to the dimensions implied by the input_file's width, height
                and DPI. The image will be grafted onto the input PDF page.
+            output_text: The expected name of a text file containing the
+                recognized text.
+            options: The command line options.
        """


@@ -433,10 +466,11 @@ def generate_pdfa(
    pdf_pages: list[Path],
    pdfmark: Path,
    output_file: Path,
-    compression: str,
+    context: PdfContext,
    pdf_version: str,
    pdfa_part: str,
    progressbar_class,
+    stop_on_soft_error: bool,
 ) -> Path:
    """Generate a PDF/A.

@@ -450,11 +484,7 @@ def generate_pdfa(
        pdfmark: A PostScript file intended for Ghostscript with details on
            how to perform the PDF/A conversion.
        output_file: The name of the desired output file.
-        compression: One of ``'jpeg'``, ``'lossless'``, ``''``. For ``'jpeg'``,
-            the PDF/A generator should convert all images to JPEG encoding where
-            possible. For lossless, all images should be converted to FlateEncode
-            (lossless PNG). If an empty string, the PDF generator should make its
-            own decisions about how to encode images.
+        context: The current context.
        pdf_version: The minimum PDF version that the output file should be.
            At its own discretion, the PDF/A generator may raise the version,
            but should not lower it.
@@ -467,6 +497,12 @@ def generate_pdfa(
            and the name of the work units ("page"). Then ``instance.update()``
            will be called when a work unit is completed. If ``None``, no
            progress information is reported.
+        stop_on_soft_error: If there is an "soft error" such that PDF/A generation
+            can proceed and produce a valid PDF/A, but output may be invalid or
+            may not visually resemble the original, the implementer of this hook
+            should raise a detailed exception. If ``False``, continue processing
+            and report by logging it. If the hook cannot proceed, it should always
+            raise an exception, regardless of this setting.

    Returns:
        Path: If successful, the hook should return ``output_file``.
@@ -474,7 +510,12 @@ def generate_pdfa(
    Note:
        This is a :ref:`firstresult hook<firstresult>`.

-    See also:
+    Note:
+        Before version 15.0.0, the ``context`` was not provided and ``compression``
+        was provided instead. Plugins should now read the context object to determine
+        if compression is requested.
+
+    See Also:
        https://github.com/tqdm/tqdm
    """

@@ -1,13 +1,13 @@
 # SPDX-FileCopyrightText: 2022 James R. Barlow
 # SPDX-License-Identifier: MPL-2.0

-"""Utilities to measure OCR quality"""
+"""Utilities to measure OCR quality."""


 from __future__ import annotations

 import re
-from typing import Iterable
+from collections.abc import Iterable


 class OcrQualityDictionary:
@@ -1,6 +1,6 @@
 # SPDX-FileCopyrightText: 2022 James R. Barlow
 # SPDX-License-Identifier: MPL-2.0
-"""Wrappers to manage subprocess calls"""
+"""Wrappers to manage subprocess calls."""

 from __future__ import annotations

@@ -8,11 +8,12 @@ import logging
 import os
 import re
 import sys
+from collections.abc import Mapping, Sequence
 from contextlib import suppress
 from pathlib import Path
 from subprocess import PIPE, STDOUT, CalledProcessError, CompletedProcess, Popen
 from subprocess import run as subprocess_run
-from typing import Callable, Mapping, Sequence, Union
+from typing import Callable, Union

 from packaging.version import Version

@@ -34,20 +35,25 @@ def run(
    check: bool = False,
    **kwargs,
 ) -> CompletedProcess:
-    """Wrapper around :py:func:`subprocess.run`
+    """Wrapper around :py:func:`subprocess.run`.

    The main purpose of this wrapper is to log subprocess output in an orderly
-    fashion that indentifies the responsible subprocess. An additional
+    fashion that identifies the responsible subprocess. An additional
    task is that this function goes to greater lengths to find possible Windows
    locations of our dependencies when they are not on the system PATH.

    Arguments should be identical to ``subprocess.run``, except for following:

-    Arguments:
+    Args:
+        args: Positional arguments to pass to ``subprocess.run``.
+        env: A set of environment variables. If None, the OS environment is used.
        logs_errors_to_stdout: If True, indicates that the process writes its error
            messages to stdout rather than stderr, so stdout should be logged
            if there is an error. If False, stderr is logged. Could be used with
            stderr=STDOUT, stdout=PIPE for example.
+        check: If True, raise an exception if the process exits with a non-zero
+            status code. If False, the return value will indicate success or failure.
+        kwargs: Additional arguments to pass to ``subprocess.run``.
    """
    args, env, process_log, _text = _fix_process_args(args, env, kwargs)

@@ -113,8 +119,6 @@ def run_polling_stderr(
 def _fix_process_args(
    args: Args, env: OsEnviron | None, kwargs
 ) -> tuple[Args, OsEnviron, logging.Logger, bool]:
-    assert 'universal_newlines' not in kwargs, "Use text= instead of universal_newlines"
-
    if not env:
        env = os.environ

@@ -141,7 +145,7 @@ def get_version(
    regex=r'(\d+(\.\d+)*)',
    env: OsEnviron | None = None,
 ) -> str:
-    """Get the version of the specified program
+    """Get the version of the specified program.

    Arguments:
        program: The program to version check.
@@ -289,21 +293,12 @@ def _error_old_version(
    _error_trailer(**locals())


-def _remove_leading_v(s: str) -> str:
-    if sys.version_info >= (3, 9):
-        return s.removeprefix('v')
-
-    if s.startswith('v'):
-        return s[1:]
-    return s
-
-
 def check_external_program(
    *,
    program: str,
    package: str,
-    version_checker: Callable[[], str],
-    need_version: str,
+    version_checker: Callable[[], Version],
+    need_version: str | Version,
    required_for: str | None = None,
    recommended: bool = False,
    version_parser: type[Version] = Version,
@@ -323,7 +318,8 @@ def check_external_program(
        version_parser: A class that should be used to parse and compare version
            numbers. Used when version numbers do not follow standard conventions.
    """
-
+    if not isinstance(need_version, Version):
+        need_version = version_parser(need_version)
    try:
        found_version = version_checker()
    except (CalledProcessError, FileNotFoundError) as e:
@@ -337,11 +333,10 @@ def check_external_program(
            raise
        return

-    found_version = _remove_leading_v(found_version)
-    need_version = _remove_leading_v(need_version)
-
-    if found_version and version_parser(found_version) < version_parser(need_version):
-        _error_old_version(program, package, need_version, found_version, required_for)
+    if found_version and found_version < need_version:
+        _error_old_version(
+            program, package, str(need_version), str(found_version), required_for
+        )
        if not recommended:
            raise MissingDependencyError(program)

@@ -9,9 +9,10 @@ import os
 import re
 import shutil
 import sys
+from collections.abc import Iterable, Iterator
 from itertools import chain
 from pathlib import Path
-from typing import Any, Callable, Iterable, Iterator, TypeVar
+from typing import Any, Callable, TypeVar

 from packaging.version import InvalidVersion, Version

@@ -32,7 +33,7 @@ else:
        spec=['HKEYType', 'EnumKey', 'EnumValue', 'HKEY_LOCAL_MACHINE', 'OpenKey']
    )
    # mypy does not understand winreg.HKeyType where winreg is a Mock (fair enough!)
-    HKEYType: TypeAlias = Any
+    HKEYType: TypeAlias = Any  # type: ignore


 log = logging.getLogger(__name__)
@@ -169,8 +170,7 @@ SHIMS = [


 def fix_windows_args(program: str, args, env):
-    """Adjust our desired program and command line arguments for use on Windows"""
-
+    """Adjust our desired program and command line arguments for use on Windows."""
    # If we are running a .py on Windows, ensure we call it with this Python
    # (to support test suite shims)
    if program.lower().endswith('.py'):
@@ -188,7 +188,7 @@ def fix_windows_args(program: str, args, env):


 def unique_everseen(iterable: Iterable[T], key: Callable[[T], Tkey]) -> Iterator[T]:
-    "List unique elements, preserving order."
+    """List unique elements, preserving order."""
    # unique_everseen('AAAABBBCCDAABBB') --> A B C D
    # unique_everseen('ABBCcAD', str.lower) --> A B C D
    seen: set[Tkey] = set()
@@ -1,4 +1,6 @@
 # SPDX-FileCopyrightText: 2022 James R. Barlow
 # SPDX-License-Identifier: MPL-2.0

+"""Tests."""
+
 from __future__ import annotations
@@ -1 +0,0 @@
-Tesseract Open Source OCR Engine v5.0.0-beta-20210916-12-g19cc9 with Leptonica
@@ -1,7 +1,5 @@
 i a la Waterman

- 
-
 4 ons linzen

 3 liter water
@@ -17,11 +15,10 @@ laurier, kruidnagel, kerrie, zout
 De linzgen wassen en in-l liter kokend wa-
 ter 1 dag laten weken, 2 liter water bij
 de linzen voegen, zonder het water waarin
-ze geweekt zijn af te gieten., De helft van
+ze geweekt zijn af te gieten, De helft van
 de uien bakken met laurier en Kruidnagel.
 Alle uien, kerrie en zgout bij de linzen
 voegen, Alles aan de kook brengen, Van de
 bloem met boter en melk een papje maken en
 verder afmaken met de soep, Als de linzen
 gfgaar Zijn is de soep klaar.
-
@@ -1 +0,0 @@
-Tesseract Open Source OCR Engine v5.0.0-beta-20210916-12-g19cc9 with Leptonica
@@ -1,25 +1,11 @@
 Tarnose

-  
-  
-
- 
-
 Bokale oa

- 
-
 Lehuntze

-   
-  
- 
-
 Mugerre

- 
-  
-
 Milafranga Komunikabideak

 BAIONA  zeiteninsiie —
@@ -27,4 +13,3 @@ BAIONA  zeiteninsiie —
 7 Trenbideak -----

 t\ Basusarri — spmeans:20141004 ae: . _ ~
-
@@ -1 +0,0 @@
-Tesseract Open Source OCR Engine v5.0.0-beta-20210916-12-g19cc9 with Leptonica
@@ -1,2 +1 @@
 Covfefe is a perfectly cromulent word.
-
@@ -1 +0,0 @@
-Tesseract Open Source OCR Engine v5.0.0-beta-20210916-12-g19cc9 with Leptonica
@@ -1,7 +1,5 @@
 Linzensoep a la Waterman

- 
-
 4 ons linzen

 3 liter water
@@ -17,11 +15,10 @@ laurier, kruidnagel, kerrie, zout
 De linzgen wassen en in-l liter kokend wa-
 ter 1 dag laten weken, 2 liter water bij
 de linzen voegen, zonder het water waarin
-ze geweekt zijn af te gieten., De helft van
+ze geweekt zijn af te gieten, De helft van
 de uien bakken met laurier en Kruidnagel.
 Alle uien, kerrie en zgout bij de linzen
 voegen, Alles aan de kook brengen, Van de
 bloem met boter en melk een papje maken en
 verder afmaken met de soep, Als de linzen
 gfgaar Zijn is de soep klaar.
-
@@ -5,27 +5,21 @@
 <head>
  <title></title>
  <meta http-equiv="Content-Type" content="text/html;charset=utf-8"/>
-  <meta name='ocr-system' content='tesseract 5.0.0-beta-20210916-12-g19cc9' />
+  <meta name='ocr-system' content='tesseract 5.3.2' />
  <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 "/tmp/ocrmypdf.io.gzrr1v_b/000001_ocr.png"; bbox 0 0 1000 800; ppageno 0'>
-   <div class='ocr_carea' id='block_1_1' title="bbox 296 96 704 504">
-    <p class='ocr_par' id='par_1_1' lang='eng' title="bbox 296 96 704 504">
-     <span class='ocr_line' id='line_1_1' title="bbox 296 96 704 504; baseline 0 296; x_size 169.33333; x_descenders 42.333332; x_ascenders 42.333336">
-      <span class='ocrx_word' id='word_1_1' title='bbox 296 96 704 504; x_wconf 95'> </span>
-     </span>
-    </p>
-   </div>
+  <div class='ocr_page' id='page_1' title='image "/tmp/ocrmypdf.io.9_hn68nz/000001_ocr.png"; bbox 0 0 1000 800; ppageno 0; scan_res 200 200'>
+   <div class='ocr_photo' id='block_1_1' title="bbox 296 96 704 504"></div>
   <div class='ocr_carea' id='block_1_2' title="bbox 150 592 841 622">
-    <p class='ocr_par' id='par_1_2' lang='eng' title="bbox 150 592 841 622">
-     <span class='ocr_line' id='line_1_2' title="bbox 150 592 841 622; baseline 0 -6; x_size 30; x_descenders 6; x_ascenders 8">
-      <span class='ocrx_word' id='word_1_2' title='bbox 150 592 230 616; x_wconf 95'>This</span>
-      <span class='ocrx_word' id='word_1_3' title='bbox 260 592 384 616; x_wconf 95'>should</span>
-      <span class='ocrx_word' id='word_1_4' title='bbox 413 592 449 616; x_wconf 95'>be</span>
-      <span class='ocrx_word' id='word_1_5' title='bbox 479 600 493 616; x_wconf 94'>a</span>
-      <span class='ocrx_word' id='word_1_6' title='bbox 523 592 668 622; x_wconf 94'>perfect</span>
-      <span class='ocrx_word' id='word_1_7' title='bbox 698 592 841 616; x_wconf 61'>circle:</span>
+    <p class='ocr_par' id='par_1_1' lang='eng' title="bbox 150 592 841 622">
+     <span class='ocr_line' id='line_1_1' title="bbox 150 592 841 622; baseline 0 -5; x_size 30; x_descenders 5; x_ascenders 7">
+      <span class='ocrx_word' id='word_1_1' title='bbox 150 592 230 617; x_wconf 96'>This</span>
+      <span class='ocrx_word' id='word_1_2' title='bbox 260 592 384 617; x_wconf 96'>should</span>
+      <span class='ocrx_word' id='word_1_3' title='bbox 413 592 449 617; x_wconf 95'>be</span>
+      <span class='ocrx_word' id='word_1_4' title='bbox 479 599 493 617; x_wconf 95'>a</span>
+      <span class='ocrx_word' id='word_1_5' title='bbox 523 592 668 622; x_wconf 95'>perfect</span>
+      <span class='ocrx_word' id='word_1_6' title='bbox 698 592 841 617; x_wconf 25'>circle.</span>
     </span>
    </p>
   </div>
@@ -1 +0,0 @@
-Tesseract Open Source OCR Engine v5.0.0-beta-20210916-12-g19cc9 with Leptonica
@@ -1,4 +1 @@
- 
-
-This should be a perfect circle:
-
+This should be a perfect circle.
@@ -1 +0,0 @@
-Tesseract Open Source OCR Engine v5.0.0-beta-20210916-12-g19cc9 with Leptonica
--- a/Show More
+++ b/Show More
				`@@ -1 +0,0 @@`
				`Tesseract Open Source OCR Engine v5.0.0-beta-20210916-12-g19cc9 with Leptonica`