Bump version: v17.9.0

bump_version.py: format after edit
Add v17.9.0 release notes for #1723 , #1713 , and CI release-draft fix
2026-07-31 01:14:13 -07:00 · 2026-07-31 01:14:00 -07:00 · 2026-07-31 00:45:59 -07:00 · 2026-07-31 00:26:12 -07:00 · 2026-07-28 11:30:52 -07:00 · 2026-07-28 01:10:04 -07:00
358 changed files with 41653 additions and 19498 deletions
@@ -1,7 +1,7 @@
-# SPDX-FileCopyrightText: 2022 James R. Barlow
+# SPDX-FileCopyrightText: 2024 James R. Barlow
 # SPDX-License-Identifier: MPL-2.0

-FROM ubuntu:22.04 as base
+FROM ubuntu:26.04 AS base

 ENV LANG=C.UTF-8
 ENV TZ=UTC
@@ -9,19 +9,15 @@ RUN echo 'debconf debconf/frontend select Noninteractive' | debconf-set-selectio

 RUN apt-get update && apt-get install -y --no-install-recommends \
  python3 \
-  libqpdf-dev \
-  zlib1g \
-  liblept5
+  python-is-python3

-FROM base as builder
+FROM base AS builder

 # Note we need leptonica here to build jbig2
 RUN apt-get update && apt-get install -y --no-install-recommends \
  build-essential autoconf automake libtool \
  libleptonica-dev \
  zlib1g-dev \
-  python3-dev \
-  python3-distutils \
  libffi-dev \
  ca-certificates \
  curl \
@@ -29,42 +25,50 @@ RUN apt-get update && apt-get install -y --no-install-recommends \
  libcairo2-dev \
  pkg-config

-# Get the latest pip (Ubuntu version doesn't support manylinux2010)
-RUN \
-  curl https://bootstrap.pypa.io/get-pip.py | python3
-
 # Compile and install jbig2
 # Needs libleptonica-dev, zlib1g-dev
 RUN \
  mkdir jbig2 \
-  && curl -L https://github.com/agl/jbig2enc/archive/ea6a40a.tar.gz | \
+  && curl -L https://github.com/agl/jbig2enc/archive/c0141bf.tar.gz | \
  tar xz -C jbig2 --strip-components=1 \
  && cd jbig2 \
  && ./autogen.sh && ./configure && make && make install \
  && cd .. \
  && rm -rf jbig2

-COPY . /app

 WORKDIR /app

-RUN pip3 install --no-cache-dir .[test,webservice,watcher]
+# Copy uv from ghcr
+COPY --from=ghcr.io/astral-sh/uv:0.11.21 /uv /uvx /bin/
+
+ENV UV_COMPILE_BYTECODE=1 UV_LINK_MODE=copy
+
+# Install the project's dependencies using the lockfile and settings
+RUN --mount=type=cache,target=/root/.cache/uv \
+    --mount=type=bind,source=uv.lock,target=uv.lock \
+    --mount=type=bind,source=pyproject.toml,target=pyproject.toml \
+    uv sync --frozen --no-install-project --no-dev
+
+# Then, add the rest of the project source code and install it
+# Installing separately from its dependencies allows optimal layer caching
+COPY . /app
+RUN --mount=type=cache,target=/root/.cache/uv \
+    uv sync --frozen \
+        --extra webservice --extra watcher --no-dev \
+        --no-install-package pyarrow

 FROM base

-# For Tesseract 5
-RUN apt-get update && apt-get install -y --no-install-recommends \
-  software-properties-common gpg-agent
-RUN add-apt-repository -y ppa:alex-p/tesseract-ocr-devel
-
+# Tesseract 5 ships in the Ubuntu archive as of 24.04, so no third-party PPA is
+# needed. (Previously this used ppa:alex-p/tesseract-ocr5.)
 RUN apt-get update && apt-get install -y --no-install-recommends \
  ghostscript \
  fonts-droid-fallback \
+  fonts-noto-core \
+  fonts-noto-cjk \
  jbig2dec \
-  img2pdf \
-  libsm6 libxext6 libxrender-dev \
  pngquant \
-  python-is-python3 \
  tesseract-ocr \
  tesseract-ocr-chi-sim \
  tesseract-ocr-deu \
@@ -75,16 +79,42 @@ RUN apt-get update && apt-get install -y --no-install-recommends \
  unpaper \
  && rm -rf /var/lib/apt/lists/*

+# Create a non-root user to run the application (defense in depth). The build
+# stages above need root to install packages, but the entrypoint should not.
+# A fixed uid/gid of 1000 keeps `--user`/`--userns keep-id` mappings predictable
+# and matches the --chown below. See docs/docker.md for the volume/permissions
+# implications under rootless vs rootful Docker.
+# The Ubuntu base ships a default "ubuntu" user at uid/gid 1000; remove it so
+# "app" can claim that uid for parity with the Alpine image.
+RUN userdel -r ubuntu 2>/dev/null; groupdel ubuntu 2>/dev/null; \
+  groupadd -g 1000 app \
+  && useradd -u 1000 -g app -m -d /home/app app
+ENV HOME=/home/app
+
 WORKDIR /app

 COPY --from=builder /usr/local/lib/ /usr/local/lib/
 COPY --from=builder /usr/local/bin/ /usr/local/bin/

-COPY --from=builder /app/misc/webservice.py /app/
-COPY --from=builder /app/misc/watcher.py /app/
+COPY --from=builder --chown=app:app /app /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
+RUN rm -rf /app/.git && \
+ln -s /app/misc/webservice.py /app/webservice.py && \
+ln -s /app/misc/watcher.py /app/watcher.py && \
+chown app:app /app
+
+# Default working directory for bind-mounted data, so relative input/output
+# paths work without passing --workdir (e.g. `-v "$PWD:/data" in.pdf out.pdf`).
+# The webservice/watcher are run by absolute path (/app/*.py), unaffected by this.
+RUN mkdir -p /data && chown app:app /data
+WORKDIR /data
+
+ENV PATH="/app/.venv/bin:${PATH}"
+
+# Drop privileges: run the entrypoint (ocrmypdf, or the webservice/watcher when
+# overridden) as the unprivileged app user. Override with `--user root` if you
+# need root inside a running container (e.g. to apt install extra packages).
+USER app
+
+ENTRYPOINT ["/app/.venv/bin/ocrmypdf"]

-ENTRYPOINT ["/usr/local/bin/ocrmypdf"]
@@ -1,7 +1,7 @@
 # SPDX-FileCopyrightText: 2023 James R. Barlow
 # SPDX-License-Identifier: MPL-2.0

-FROM alpine:3.19.1 as base
+FROM alpine:3.24 AS base

 ENV LANG=C.UTF-8
 ENV TZ=UTC
@@ -10,40 +10,37 @@ RUN apk add --no-cache \
    python3 \
    zlib

-FROM base as builder
+FROM base AS builder

+# Yes it really is python3-dev, and py3-package
 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
+    py3-pyarrow \
+    curl

 WORKDIR /app

-RUN python3 -m venv .venv
+COPY --from=ghcr.io/astral-sh/uv:0.11.21 /uv /uvx /bin/

-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]
+ENV UV_COMPILE_BYTECODE=1 UV_LINK_MODE=copy
+
+RUN uv venv --system-site-packages .venv
+
+# Install the project's dependencies using the lockfile and settings
+RUN --mount=type=cache,target=/root/.cache/uv \
+    --mount=type=bind,source=uv.lock,target=uv.lock \
+    --mount=type=bind,source=pyproject.toml,target=pyproject.toml \
+    uv sync --frozen --no-install-project --no-dev
+
+# Then, add the rest of the project source code and install it
+# Installing separately from its dependencies allows optimal layer caching
+COPY . /app
+RUN --mount=type=cache,target=/root/.cache/uv \
+    uv sync --frozen \
+        --extra webservice --extra watcher --no-dev \
+        --no-install-package pyarrow

 FROM base

@@ -60,24 +57,40 @@ RUN apk add --no-cache \
    tesseract-ocr-data-osd \
    tesseract-ocr-data-por \
    tesseract-ocr-data-spa \
+    font-noto \
    ttf-droid \
    unpaper \
    && rm -rf /var/cache/apk/*

+# Create a non-root user to run the application (defense in depth). The build
+# stages above need root to install packages, but the entrypoint should not.
+# A fixed uid/gid of 1000 keeps `--user`/`--userns keep-id` mappings predictable
+# and matches the --chown below. See docs/docker.md for the volume/permissions
+# implications under rootless vs rootful Docker.
+RUN addgroup -g 1000 app \
+    && adduser -u 1000 -G app -D -h /home/app app
+ENV HOME=/home/app
+
 WORKDIR /app

-COPY --from=builder /usr/local/lib/ /usr/local/lib/
-COPY --from=builder /usr/local/bin/ /usr/local/bin/
+COPY --from=builder --chown=app:app /app /app

-COPY --from=builder /app/.venv/ /app/.venv/
+RUN rm -rf /app/.git && \
+    ln -s /app/misc/webservice.py /app/webservice.py && \
+    ln -s /app/misc/watcher.py /app/watcher.py && \
+    chown app:app /app

-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
+# Default working directory for bind-mounted data, so relative input/output
+# paths work without passing --workdir (e.g. `-v "$PWD:/data" in.pdf out.pdf`).
+# The webservice/watcher are run by absolute path (/app/*.py), unaffected by this.
+RUN mkdir -p /data && chown app:app /data
+WORKDIR /data

 ENV PATH="/app/.venv/bin:${PATH}"

+# Drop privileges: run the entrypoint (ocrmypdf, or the webservice/watcher when
+# overridden) as the unprivileged app user. Override with `--user root` if you
+# need root inside a running container (e.g. to apk add extra packages).
+USER app
+
 ENTRYPOINT ["/app/.venv/bin/ocrmypdf"]
@@ -13,5 +13,6 @@
 *.jpg	binary
 *.bin   binary
 *.afdesign  binary
+*.ttf   binary

 .git_archival.txt  export-subst
@@ -9,57 +9,73 @@ on:
      - ci
      - release/*
      - feature/*
-    tags:
-      - v*
    paths-ignore:
      - README*
  pull_request:

 jobs:
+  lint:
+    name: Lint (prek)
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v7
+
+      - name: Install uv
+        uses: astral-sh/setup-uv@v7
+        with:
+          version: "0.9.x"
+
+      - name: "Set up Python"
+        uses: actions/setup-python@v7
+        with:
+          python-version: "3.11"
+
+      - name: Run prek
+        run: |
+          uv run prek run --all-files
+
  test_linux:
    name: Test ${{ matrix.os }} with Python ${{ matrix.python }}
+    needs: lint
    runs-on: ${{ matrix.os }}
    strategy:
      matrix:
+        os: [ubuntu-22.04, ubuntu-24.04]
+        python: ["3.11", "3.12", "3.13", "3.14"]
        include:
          - os: ubuntu-22.04
-            python: "3.10"
-          - os: ubuntu-22.04
+            tesseract_ppa: "ppa"
            python: "3.11"
-          - os: ubuntu-22.04
-            python: "3.10"
-            tesseract5: true
-          - os: ubuntu-latest
-            python: "3.12"
-            tesseract5: true
-          - os: ubuntu-latest
-            python: "pypy3.10"

    env:
      OS: ${{ matrix.os }}
      PYTHON: ${{ matrix.python }}

    steps:
-      - uses: actions/checkout@v4
-        with:
-          fetch-depth: "0" # 0=all, needed for setuptools-scm to resolve version tags
+      - uses: actions/checkout@v7

-      - uses: actions/setup-python@v5
-        name: Setup Python
+      - name: Install uv
+        uses: astral-sh/setup-uv@v7
+        with:
+          version: "0.9.x"
+
+      - name: "Set up Python"
+        uses: actions/setup-python@v7
        with:
          python-version: ${{ matrix.python }}
-          cache: "pip"

-      - name: Install Tesseract 5
-        if: matrix.tesseract5
+      - name: Install Tesseract from PPA
+        if: matrix.tesseract_ppa == 'ppa'
        run: |
-          sudo add-apt-repository -y ppa:alex-p/tesseract-ocr-devel
+          sudo add-apt-repository -y ppa:alex-p/tesseract-ocr5

      - name: Install common packages
        run: |
          sudo apt-get update
          sudo apt-get install -y --no-install-recommends \
            curl \
+            fonts-noto-core \
+            fonts-noto-cjk \
            ghostscript \
            jbig2dec \
            img2pdf \
@@ -75,18 +91,9 @@ jobs:
            unpaper \
            zlib1g

-      - name: Install Ubuntu packages for PyPy
-        if: startsWith(matrix.python, 'pypy')
-        run: |
-          sudo apt-get install -y --no-install-recommends \
-            libxml2-dev \
-            libxslt1-dev \
-            pypy3-dev
-
      - name: Install Python packages
        run: |
-          python -m pip install --upgrade pip wheel
-          python -m pip install --prefer-binary .[test]
+          uv sync --group test

      - name: Report versions
        run: |
@@ -94,37 +101,35 @@ jobs:
          gs --version
          pngquant --version
          unpaper --version
-          img2pdf --version
+          uv run --no-dev img2pdf --version

      - name: Test
        run: |
-          python -m pytest --cov-report xml --cov=ocrmypdf --cov=tests/ -n0 tests/
+          uv run --no-dev pytest --cov-report xml --cov=ocrmypdf --cov=tests/ -n0 tests/

      - name: Upload coverage to Codecov
-        uses: codecov/codecov-action@v4
+        uses: codecov/codecov-action@v7
        env:
          CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}
        with:
          files: ./coverage.xml
          env_vars: OS,PYTHON

-
  test_macos:
    name: Test macOS
+    needs: lint
    runs-on: ${{ matrix.os }}
    strategy:
      matrix:
-        os: [macos-latest, macos-13]  # macos-latest is arm64, macos-13 is x86_64
-        python: ["3.10", "3.11", "3.12"]
+        os: [macos-latest]
+        python: ["3.11", "3.12", "3.13", "3.14"]

    env:
      OS: ${{ matrix.os }}
      PYTHON: ${{ matrix.python }}

    steps:
-      - uses: actions/checkout@v4
-        with:
-          fetch-depth: "0" # 0=all, needed for setuptools-scm to resolve version tags
+      - uses: actions/checkout@v7

      - name: Install Homebrew deps
        continue-on-error: true
@@ -136,32 +141,37 @@ jobs:
            jbig2enc \
            openjpeg \
            pngquant \
-            tesseract
+            poppler \
+            tesseract \
+            verapdf

-      - uses: actions/setup-python@v5
-        name: Setup Python
+      - name: Install uv
+        uses: astral-sh/setup-uv@v7
+        with:
+          version: "0.9.x"
+
+      - name: "Set up Python"
+        uses: actions/setup-python@v7
        with:
          python-version: ${{ matrix.python }}
-          cache: "pip"

      - name: Install Python packages
        run: |
-          python -m pip install --upgrade pip wheel
-          python -m pip install --prefer-binary .[test]
+          uv sync --group test

      - name: Report versions
        run: |
          tesseract --version
          gs --version
          pngquant --version
-          img2pdf --version
+          uv run --no-dev img2pdf --version

      - name: Test
        run: |
-          python -m pytest --cov-report xml --cov=ocrmypdf --cov=tests/ -n0 tests/
+          uv run --no-dev pytest --cov-report xml --cov=ocrmypdf --cov=tests/ -n0 tests/

      - name: Upload coverage to Codecov
-        uses: codecov/codecov-action@v4
+        uses: codecov/codecov-action@v7
        env:
          CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}
        with:
@@ -170,43 +180,46 @@ jobs:

  test_windows:
    name: Test Windows
+    needs: lint
    runs-on: ${{ matrix.os }}
    strategy:
      matrix:
        os: [windows-latest]
-        python: ["3.10", "3.11", "3.12"]
+        python: ["3.11", "3.12", "3.13", "3.14"]

    env:
      OS: ${{ matrix.os }}
      PYTHON: ${{ matrix.python }}

    steps:
-      - uses: actions/checkout@v4
-        with:
-          fetch-depth: "0" # 0=all, needed for setuptools-scm to resolve version tags
+      - uses: actions/checkout@v7

-      - uses: actions/setup-python@v5
-        name: Setup Python
+      - name: Install uv
+        uses: astral-sh/setup-uv@v7
+        with:
+          version: "0.9.x"
+
+      - name: "Set up Python"
+        uses: actions/setup-python@v7
        with:
          python-version: ${{ matrix.python }}
-          cache: "pip"

      - name: Install system packages
        run: |
-          choco install --yes --no-progress --pre tesseract
+          choco install --yes --no-progress tesseract
          choco install --yes --no-progress --ignore-checksums ghostscript --version 9.56.1
+          choco install --yes --no-progress poppler --version=25.11.0

      - name: Install Python packages
        run: |
-          python -m pip install --upgrade pip wheel
-          python -m pip install --prefer-binary .[test]
+          uv sync --group test

      - name: Test
        run: |
-          python -m pytest --cov-report xml --cov=ocrmypdf --cov=tests/ -n0 tests/
+          uv run --no-dev pytest --cov-report xml --cov=ocrmypdf --cov=tests/ -n0 tests/

      - name: Upload coverage to Codecov
-        uses: codecov/codecov-action@v4
+        uses: codecov/codecov-action@v7
        env:
          CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}
        with:
@@ -217,70 +230,68 @@ jobs:
    name: Build sdist and wheels
    runs-on: ubuntu-latest
    steps:
-      - uses: actions/checkout@v4
-        with:
-          fetch-depth: "0" # 0=all, needed for setuptools-scm to resolve version tags
+      - uses: actions/checkout@v7

-      - uses: actions/setup-python@v5
-        name: Setup Python
+      - name: Install uv
+        uses: astral-sh/setup-uv@v7
        with:
-          python-version: "3.10"
-          cache: "pip"
+          version: "0.9.x"

      - name: Make wheels and sdist
        run: |
-          python -m pip install --upgrade pip wheel build
-          python -m build --sdist --wheel
+          uv build --sdist --wheel

-      - uses: actions/upload-artifact@v4
+      - uses: actions/upload-artifact@v7
        with:
          name: artifact
          path: |
            ./dist/*.whl
            ./dist/*.tar.gz

-  upload_pypi:
-    name: Deploy artifacts to PyPI
+  stage_release:
+    name: Stage release artifacts
    needs: [wheel_sdist_linux, test_linux, test_macos, test_windows]
    runs-on: ubuntu-latest
-    environment: release
+    if: github.ref == 'refs/heads/main'
    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@v4
-        with:
-          name: artifact
-          path: dist
-
-      - name: Publish to PyPI
-        uses: pypa/gh-action-pypi-publish@release/v1
-
-  create_release:
-    name: Create GitHub release
-    needs: [wheel_sdist_linux, test_linux, test_macos, test_windows]
-    runs-on: ubuntu-latest
-    if: github.event_name == 'push' && startsWith(github.event.ref, 'refs/tags/v')
-    permissions:
-      # Required to create a release
      contents: write
    steps:
-      - uses: actions/download-artifact@v4
+      - uses: actions/checkout@v7
+
+      - uses: actions/download-artifact@v8
        with:
          name: artifact
          path: dist

-      - name: Create Release
-        id: create-release
-        uses: shogo82148/actions-create-release@v1
+      - name: Read version from source
+        id: version
+        run: |
+          VERSION=$(python3 -c "exec(open('src/ocrmypdf/_version.py').read()); print(__version__)")
+          echo "version=$VERSION" >> $GITHUB_OUTPUT

-      - 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
+      - name: Create or update draft release
+        env:
+          GITHUB_TOKEN: ${{ github.token }}
+        run: |
+          TAG="v${{ steps.version.outputs.version }}"
+
+          # If release.yml already published this version, _version.py may
+          # still reflect it until the next version bump commit. Don't
+          # re-draft an already-published release on later pushes to main.
+          if [[ "$(gh release view "$TAG" --json isDraft --jq .isDraft 2>/dev/null)" == "false" ]]; then
+            echo "Release $TAG is already published; skipping."
+            exit 0
+          fi
+
+          # Delete existing draft release if it exists (ignore errors)
+          gh release delete "$TAG" --yes 2>/dev/null || true
+
+          # Create new draft release with all artifacts
+          gh release create "$TAG" \
+            --draft \
+            --title "$TAG" \
+            --notes "Draft release - will be updated when tag is pushed" \
+            dist/*

  docker_ubuntu:
    name: Build Ubuntu-based Docker image
@@ -301,22 +312,20 @@ jobs:
      - name: Set image name
        run: echo "DOCKER_IMAGE_NAME=ocrmypdf" >> $GITHUB_ENV

-      - uses: actions/checkout@v4
-        with:
-          fetch-depth: "0" # 0=all, needed for setuptools-scm to resolve version tags
+      - uses: actions/checkout@v7

      - name: Login to Docker Hub
-        uses: docker/login-action@v3
+        uses: docker/login-action@v4
        with:
          username: jbarlow83
          password: ${{ secrets.DOCKERHUB_TOKEN }}

      - name: Set up QEMU
-        uses: docker/setup-qemu-action@v3
+        uses: docker/setup-qemu-action@v4

      - name: Set up Docker Buildx
        id: buildx
-        uses: docker/setup-buildx-action@v3
+        uses: docker/setup-buildx-action@v4

      - name: Print image tag
        run: echo "Building image ${DOCKER_REPOSITORY}/${DOCKER_IMAGE_NAME}:${DOCKER_IMAGE_TAG}"
@@ -349,19 +358,17 @@ jobs:
      - 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
+      - uses: actions/checkout@v7

      - name: Login to Docker Hub
-        uses: docker/login-action@v3
+        uses: docker/login-action@v4
        with:
          username: jbarlow83
          password: ${{ secrets.DOCKERHUB_TOKEN }}

      - name: Set up Docker Buildx
        id: buildx
-        uses: docker/setup-buildx-action@v3
+        uses: docker/setup-buildx-action@v4

      - name: Print image tag
        run: echo "Building image ${DOCKER_REPOSITORY}/${DOCKER_IMAGE_NAME}:${DOCKER_IMAGE_TAG}"
@@ -0,0 +1,114 @@
+# SPDX-FileCopyrightText: 2022 James R. Barlow
+# SPDX-License-Identifier: MPL-2.0
+
+name: Publish Release
+
+on:
+  push:
+    tags:
+      - "v*"
+
+jobs:
+  publish:
+    name: Publish release
+    runs-on: ubuntu-latest
+    environment:
+      name: release
+      url: https://pypi.org/p/ocrmypdf
+    permissions:
+      contents: write
+      id-token: write
+    steps:
+      - uses: actions/checkout@v7
+
+      - name: Download artifacts from draft release
+        env:
+          GITHUB_TOKEN: ${{ github.token }}
+        run: |
+          mkdir -p dist
+          gh release download "$GITHUB_REF_NAME" --dir dist --pattern '*.whl'
+          gh release download "$GITHUB_REF_NAME" --dir dist --pattern '*.tar.gz'
+
+      - name: Publish to PyPI
+        uses: pypa/gh-action-pypi-publish@release/v1
+
+      # PyPI doesn't support sigstore publishing, so generate after publishing to PyPI
+      - name: Sign the dists with Sigstore
+        uses: sigstore/gh-action-sigstore-python@v3.4.0
+        with:
+          inputs: |
+            ./dist/*.tar.gz
+            ./dist/*.whl
+
+      - name: Extract release notes
+        run: |
+          VERSION="${GITHUB_REF_NAME#v}"
+          MAJOR="${VERSION%%.*}"
+          MAJOR_PADDED=$(printf "%02d" "$MAJOR")
+          RELEASE_FILE="docs/releasenotes/version${MAJOR_PADDED}.md"
+
+          python3 << EOF
+          import re
+
+          version = "${VERSION}"
+          release_file = "${RELEASE_FILE}"
+
+          try:
+              with open(release_file) as f:
+                  content = f.read()
+
+              # Find the section for this version
+              # Match from "## vX.Y.Z" until the next "## v" or end of file
+              pattern = rf"## v{re.escape(version)}\n(.*?)(?=\n## v|\Z)"
+              match = re.search(pattern, content, re.DOTALL)
+              notes = match.group(1).strip() if match else ""
+          except FileNotFoundError:
+              notes = ""
+
+          with open("release_notes.md", "w") as f:
+              f.write(notes)
+          EOF
+
+      - name: Publish release (convert draft to published)
+        env:
+          GITHUB_TOKEN: ${{ github.token }}
+        run: |
+          # Update release: remove draft status, add release notes
+          gh release edit "$GITHUB_REF_NAME" \
+            --draft=false \
+            --notes-file release_notes.md
+
+          # Upload signatures to the release
+          gh release upload "$GITHUB_REF_NAME" dist/*.sigstore.json --clobber
+
+  docker_tag:
+    name: Tag Docker images with release version
+    needs: [publish]
+    runs-on: ubuntu-latest
+    steps:
+      - name: Login to Docker Hub
+        uses: docker/login-action@v4
+        with:
+          username: jbarlow83
+          password: ${{ secrets.DOCKERHUB_TOKEN }}
+
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v4
+
+      - name: Tag ocrmypdf (Ubuntu) image
+        run: |
+          docker buildx imagetools create \
+            --tag "jbarlow83/ocrmypdf:$GITHUB_REF_NAME" \
+            "jbarlow83/ocrmypdf:latest"
+
+      - name: Tag ocrmypdf-ubuntu image
+        run: |
+          docker buildx imagetools create \
+            --tag "jbarlow83/ocrmypdf-ubuntu:$GITHUB_REF_NAME" \
+            "jbarlow83/ocrmypdf-ubuntu:latest"
+
+      - name: Tag ocrmypdf-alpine image
+        run: |
+          docker buildx imagetools create \
+            --tag "jbarlow83/ocrmypdf-alpine:$GITHUB_REF_NAME" \
+            "jbarlow83/ocrmypdf-alpine:latest"
@@ -0,0 +1,32 @@
+# SPDX-FileCopyrightText: 2024 James R. Barlow
+# SPDX-License-Identifier: MPL-2.0
+
+name: Remove Triage Label on Reply
+
+on:
+  issue_comment:
+    types:
+      - created
+
+jobs:
+  remove-triage-label:
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Check if comment is by the repository owner
+        id: check_comment
+        run: |
+          echo "::set-output name=is_owner::$(
+            if [[ '${{ github.event.comment.user.login }}' == 'jbarlow83' ]]; then
+              echo 'true';
+            else
+              echo 'false';
+            fi
+          )"
+
+      - name: Remove 'triage' label
+        if: ${{ steps.check_comment.outputs.is_owner == 'true' }}
+        uses: actions-ecosystem/action-remove-labels@v1
+        with:
+          github_token: ${{ secrets.GITHUB_TOKEN }}
+          labels: triage
@@ -44,3 +44,8 @@ docs/_build/
 docs/_static/
 docs/_templates/
 docs/Makefile
+
+.idea/
+.aider*
+CLAUDE.md
+.claude/
@@ -1,32 +0,0 @@
-# SPDX-FileCopyrightText: 2022 James R. Barlow
-# SPDX-License-Identifier: MPL-2.0
-
-repos:
-  - repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v4.4.0
-    hooks:
-      - id: check-case-conflict
-      - id: check-merge-conflict
-      - id: check-toml
-      - id: check-yaml
-      - id: debug-statements
-  - repo: https://github.com/charliermarsh/ruff-pre-commit
-    rev: "v0.0.261"
-    hooks:
-      - id: ruff
-        files: "src/.*\\.pyi?$"
-        args: [--fix, --exit-non-zero-on-fix]
-  - repo: https://github.com/psf/black
-    rev: 23.3.0
-    hooks:
-      - id: black
-        language_version: python
-  - repo: https://github.com/pre-commit/mirrors-mypy
-    rev: v1.2.0
-    hooks:
-      - id: mypy
-        additional_dependencies:
-          - types-toml
-          - types-setuptools
-          - types-requests
-          - types-Pillow
@@ -11,19 +11,17 @@ version: 2
 sphinx:
  configuration: docs/conf.py

-# Optionally build your docs in additional formats such as PDF
-formats:
-  - pdf
-
 # Optionally set the version of Python and requirements required to build your docs
 build:
  os: ubuntu-22.04
  tools:
-    python: "3.10"
-
-python:
-  install:
-    - method: pip
-      path: .
-      extra_requirements:
-        - docs
+    python: "3.13"
+  jobs:
+    pre_create_environment:
+      - asdf plugin add uv
+      - asdf install uv latest
+      - asdf global uv latest
+    create_environment:
+      - uv venv "${READTHEDOCS_VIRTUALENV_PATH}"
+    install:
+      - UV_PROJECT_ENVIRONMENT="${READTHEDOCS_VIRTUALENV_PATH}" uv sync --frozen --group docs
@@ -1,140 +0,0 @@
-Format: https://www.debian.org/doc/packaging-manuals/copyright-format/1.0/
-Upstream-Name: OCRmyPDF
-Upstream-Contact: James R. Barlow <james@purplerock.ca>
-Source: https://github.com/ocrmypdf/OCRmyPDF
-
-Files:
- .git_archival.txt
- docs/images/logo-social.png
- docs/images/logo-square-256.svg
- docs/images/logo-square.png
- docs/images/logo-square.svg
- docs/images/logo.svg
-Copyright: (C) 2022 James R. Barlow
-License: MPL-2.0
-
-Files:
- .github/ISSUE_TEMPLATE/*.yml
- docs/images/macos-workflow.png
-Copyright: (C) 2023 James R. Barlow
-License: CC-BY-SA-4.0
-
-Files:
- tests/resources/acroform.pdf
- tests/resources/aspect.pdf
- tests/resources/blank.pdf
- tests/resources/cmyk.pdf
- tests/resources/crom.png
- tests/resources/enormous.pdf
- tests/resources/formxobject.pdf
- tests/resources/francais.pdf
- tests/resources/hugemono.pdf
- tests/resources/invalid.pdf
- tests/resources/kcs.pdf
- tests/resources/livecycle.pdf
- tests/resources/meta.pdf
- tests/resources/missing_docinfo.pdf
- tests/resources/negzero.pdf
- tests/resources/no_contents.pdf
- tests/resources/tagged*
- tests/resources/toc.pdf
- tests/resources/trivial.pdf
- tests/resources/truetype_font_nomapping.pdf
- tests/resources/type3_font_nomapping.pdf
-Copyright: (C) 2023 James R. Barlow
-License: CC-BY-SA-4.0
-
-Files:
- tests/resources/graph.pdf
- tests/resources/graph_ocred.pdf
-Copyright: (C) 2012 SmokeyJoe
-License: GFDL-1.2-or-later or CC-BY-SA-3.0
-
-Files: tests/resources/c02-22.pdf
- tests/resources/multipage.pdf
-Copyright: Public domain
-License: public-domain
- Copyright on these files has expired.
-
-Files: docs/images/bitmap_vs_svg.svg
-Copyright: (C) 2006 Yug
-License: CC-BY-SA-2.5
-
-Files: tests/cache/*
-Copyright: (C) 2022 James R. Barlow
-License: CC-BY-SA-4.0
-
-Files: tests/resources/linn.png
- tests/resources/linn.pdf
- tests/resources/linn.txt
- tests/resources/ccitt.pdf
- tests/resources/cardinal.pdf
- tests/resources/jbig2.pdf
- tests/resources/jbig2_baddevicen.pdf
- tests/resources/skew.pdf
- tests/resources/rotated_skew.pdf
- tests/resources/poster.pdf
-Copyright: (C) 1985 Forat Electronics
-License: GFDL-1.2-or-later or CC-BY-SA-3.0
-
-Files: tests/resources/lichtenstein.pdf
-Copyright: (C) 2001 Andreas Tille
- (C) 2007 Alessio Damato
-License: GFDL-1.2-or-later or CC-BY-SA-3.0
-
-Files: tests/resources/masks.pdf
-Copyright: held by the contributors to the German Wikipedia article "Linux"
- see: https://de.wikipedia.org/w/index.php?title=Linux&action=history
- (masks.pdf generated from Wikipedia article as of 2016-08-24)
-License: CC-BY-SA-3.0
-
-Files: tests/resources/epson.pdf
-Copyright: held by the contributors to the Wikipedia article "Optical character recognition"
- see: https://en.wikipedia.org/w/index.php?title=Optical_character_recognition&action=history
- (epson.pdf generated from Wikipedia article as of 2016-09-14)
-License: CC-BY-SA-3.0
-
-Files: tests/resources/typewriter.png tests/resources/2400dpi.pdf
-Copyright: (C) 2005 Ellywa
-License: GFDL-1.2-or-later or CC-BY-SA-1.0 or CC-BY-SA-2.0 or CC-BY-SA-2.5 or CC-BY-SA-3.0
-Comment:
- Obtained from: https://commons.wikimedia.org/wiki/File:Triumph.typewriter_text_Linzensoep.gif
-
-Files: tests/resources/overlay.pdf
-Copyright: (C) 2017 Max Anderson
-License: MIT
-
-Files:
- tests/resources/baiona*.png
- tests/resources/baiona*.jpg
- tests/resources/link.pdf
- tests/resources/palette.pdf
-Copyright: (C) 2014 Euskaldunaa
-License: CC-BY-SA-4.0
-
-Files: tests/resources/vector.pdf
-Copyright: (C) 2018 Catscratch
-License: MIT
-
-Files: src/ocrmypdf/data/sRGB.icc
-Copyright:  Kai-Uwe Behrmann <www.behrmann.name>
-            Marti Maria <www.littlecms.com>
-            Photogamut <www.photogamut.org>
-            Graeme Gill <www.argyllcms.com>
-            ColorSolutions <www.basICColor.com>
-License: Zlib
-
-Files: src/ocrmypdf/data/pdf.ttf
-Copyright: (C) 2014 Ray Smith
- (C) 2015 Ken Sharp
- (C) 2016 James R. Barlow
- (C) 2016 Jeff Breidenbach
- (C) 2017 Zdenko Podobný
-License: Apache-2.0
-
-Files: tests/resources/3small.pdf
-Copyright: (C) 2014 Euskaldunaa
- (C) 2017 James R. Barlow
- (C) 2005 Ellywa
-License: CC-BY-SA-4.0 and (GFDL-1.2-or-later or CC-BY-SA-1.0 or CC-BY-SA-2.0 or CC-BY-SA-2.5 or CC-BY-SA-3.0)
-Comment: concatenation of baiona_gray.png, crom.png and typewriter.png/2400dpi.pdf
@@ -0,0 +1,73 @@
+Apache License
+Version 2.0, January 2004
+http://www.apache.org/licenses/
+
+TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+1. Definitions.
+
+"License" shall mean the terms and conditions for use, reproduction, and distribution as defined by Sections 1 through 9 of this document.
+
+"Licensor" shall mean the copyright owner or entity authorized by the copyright owner that is granting the License.
+
+"Legal Entity" shall mean the union of the acting entity and all other entities that control, are controlled by, or are under common control with that entity. For the purposes of this definition, "control" means (i) the power, direct or indirect, to cause the direction or management of such entity, whether by contract or otherwise, or (ii) ownership of fifty percent (50%) or more of the outstanding shares, or (iii) beneficial ownership of such entity.
+
+"You" (or "Your") shall mean an individual or Legal Entity exercising permissions granted by this License.
+
+"Source" form shall mean the preferred form for making modifications, including but not limited to software source code, documentation source, and configuration files.
+
+"Object" form shall mean any form resulting from mechanical transformation or translation of a Source form, including but not limited to compiled object code, generated documentation, and conversions to other media types.
+
+"Work" shall mean the work of authorship, whether in Source or Object form, made available under the License, as indicated by a copyright notice that is included in or attached to the work (an example is provided in the Appendix below).
+
+"Derivative Works" shall mean any work, whether in Source or Object form, that is based on (or derived from) the Work and for which the editorial revisions, annotations, elaborations, or other modifications represent, as a whole, an original work of authorship. For the purposes of this License, Derivative Works shall not include works that remain separable from, or merely link (or bind by name) to the interfaces of, the Work and Derivative Works thereof.
+
+"Contribution" shall mean any work of authorship, including the original version of the Work and any modifications or additions to that Work or Derivative Works thereof, that is intentionally submitted to Licensor for inclusion in the Work by the copyright owner or by an individual or Legal Entity authorized to submit on behalf of the copyright owner. For the purposes of this definition, "submitted" means any form of electronic, verbal, or written communication sent to the Licensor or its representatives, including but not limited to communication on electronic mailing lists, source code control systems, and issue tracking systems that are managed by, or on behalf of, the Licensor for the purpose of discussing and improving the Work, but excluding communication that is conspicuously marked or otherwise designated in writing by the copyright owner as "Not a Contribution."
+
+"Contributor" shall mean Licensor and any individual or Legal Entity on behalf of whom a Contribution has been received by Licensor and subsequently incorporated within the Work.
+
+2. Grant of Copyright License. Subject to the terms and conditions of this License, each Contributor hereby grants to You a perpetual, worldwide, non-exclusive, no-charge, royalty-free, irrevocable copyright license to reproduce, prepare Derivative Works of, publicly display, publicly perform, sublicense, and distribute the Work and such Derivative Works in Source or Object form.
+
+3. Grant of Patent License. Subject to the terms and conditions of this License, each Contributor hereby grants to You a perpetual, worldwide, non-exclusive, no-charge, royalty-free, irrevocable (except as stated in this section) patent license to make, have made, use, offer to sell, sell, import, and otherwise transfer the Work, where such license applies only to those patent claims licensable by such Contributor that are necessarily infringed by their Contribution(s) alone or by combination of their Contribution(s) with the Work to which such Contribution(s) was submitted. If You institute patent litigation against any entity (including a cross-claim or counterclaim in a lawsuit) alleging that the Work or a Contribution incorporated within the Work constitutes direct or contributory patent infringement, then any patent licenses granted to You under this License for that Work shall terminate as of the date such litigation is filed.
+
+4. Redistribution. You may reproduce and distribute copies of the Work or Derivative Works thereof in any medium, with or without modifications, and in Source or Object form, provided that You meet the following conditions:
+
+     (a) You must give any other recipients of the Work or Derivative Works a copy of this License; and
+
+     (b) You must cause any modified files to carry prominent notices stating that You changed the files; and
+
+     (c) You must retain, in the Source form of any Derivative Works that You distribute, all copyright, patent, trademark, and attribution notices from the Source form of the Work, excluding those notices that do not pertain to any part of the Derivative Works; and
+
+     (d) If the Work includes a "NOTICE" text file as part of its distribution, then any Derivative Works that You distribute must include a readable copy of the attribution notices contained within such NOTICE file, excluding those notices that do not pertain to any part of the Derivative Works, in at least one of the following places: within a NOTICE text file distributed as part of the Derivative Works; within the Source form or documentation, if provided along with the Derivative Works; or, within a display generated by the Derivative Works, if and wherever such third-party notices normally appear. The contents of the NOTICE file are for informational purposes only and do not modify the License. You may add Your own attribution notices within Derivative Works that You distribute, alongside or as an addendum to the NOTICE text from the Work, provided that such additional attribution notices cannot be construed as modifying the License.
+
+     You may add Your own copyright statement to Your modifications and may provide additional or different license terms and conditions for use, reproduction, or distribution of Your modifications, or for any such Derivative Works as a whole, provided Your use, reproduction, and distribution of the Work otherwise complies with the conditions stated in this License.
+
+5. Submission of Contributions. Unless You explicitly state otherwise, any Contribution intentionally submitted for inclusion in the Work by You to the Licensor shall be under the terms and conditions of this License, without any additional terms or conditions. Notwithstanding the above, nothing herein shall supersede or modify the terms of any separate license agreement you may have executed with Licensor regarding such Contributions.
+
+6. Trademarks. This License does not grant permission to use the trade names, trademarks, service marks, or product names of the Licensor, except as required for reasonable and customary use in describing the origin of the Work and reproducing the content of the NOTICE file.
+
+7. Disclaimer of Warranty. Unless required by applicable law or agreed to in writing, Licensor provides the Work (and each Contributor provides its Contributions) on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied, including, without limitation, any warranties or conditions of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A PARTICULAR PURPOSE. You are solely responsible for determining the appropriateness of using or redistributing the Work and assume any risks associated with Your exercise of permissions under this License.
+
+8. Limitation of Liability. In no event and under no legal theory, whether in tort (including negligence), contract, or otherwise, unless required by applicable law (such as deliberate and grossly negligent acts) or agreed to in writing, shall any Contributor be liable to You for damages, including any direct, indirect, special, incidental, or consequential damages of any character arising as a result of this License or out of the use or inability to use the Work (including but not limited to damages for loss of goodwill, work stoppage, computer failure or malfunction, or any and all other commercial damages or losses), even if such Contributor has been advised of the possibility of such damages.
+
+9. Accepting Warranty or Additional Liability. While redistributing the Work or Derivative Works thereof, You may choose to offer, and charge a fee for, acceptance of support, warranty, indemnity, or other liability obligations and/or rights consistent with this License. However, in accepting such obligations, You may act only on Your own behalf and on Your sole responsibility, not on behalf of any other Contributor, and only if You agree to indemnify, defend, and hold each Contributor harmless for any liability incurred by, or claims asserted against, such Contributor by reason of your accepting any such warranty or additional liability.
+
+END OF TERMS AND CONDITIONS
+
+APPENDIX: How to apply the Apache License to your work.
+
+To apply the Apache License to your work, attach the following boilerplate notice, with the fields enclosed by brackets "[]" replaced with your own identifying information. (Don't include the brackets!)  The text should be enclosed in the appropriate comment syntax for the file format. We also recommend that a file or class name and description of purpose be included on the same "printed page" as the copyright notice for easier identification within third-party archives.
+
+Copyright [yyyy] [name of copyright owner]
+
+Licensed under the Apache License, Version 2.0 (the "License");
+you may not use this file except in compliance with the License.
+You may obtain a copy of the License at
+
+http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software
+distributed under the License is distributed on an "AS IS" BASIS,
+WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+See the License for the specific language governing permissions and
+limitations under the License.
@@ -74,7 +74,7 @@ Linux, Windows, macOS and FreeBSD are supported. Docker images are also availabl
 | macOS (nix)                   | ``nix-env -i ocrmypdf``       |
 | LinuxBrew                     | ``brew install ocrmypdf``     |
 | FreeBSD                       | ``pkg install py-ocrmypdf``   |
-| Conda                         | ``conda install ocrmypdf``    |
+| OpenBSD                       | ``pkg_add ocrmypdf``          |
 | Ubuntu Snap                   | ``snap install ocrmypdf``     |

 For everyone else, [see our documentation](https://ocrmypdf.readthedocs.io/en/latest/installation.html) for installation steps.
@@ -84,17 +84,27 @@ For everyone else, [see our documentation](https://ocrmypdf.readthedocs.io/en/la
 OCRmyPDF uses Tesseract for OCR, and relies on its language packs. For Linux users, you can often find packages that provide language packs:

 ```bash
-# Display a list of all Tesseract language packs
-apt-cache search tesseract-ocr

 # Debian/Ubuntu users
+apt-cache search tesseract-ocr # Display a list of all Tesseract language packs
 apt-get install tesseract-ocr-chi-sim  # Example: Install Chinese Simplified language pack

+
 # Arch Linux users
 pacman -S tesseract-data-eng tesseract-data-deu # Example: Install the English and German language packs

+# OpenBSD users
+pkg_info -aQ tesseract  # Display a list of all Tesseract language packs
+pkg_add tesseract-cym  # Example: Install the Welsh language pack
+
 # brew macOS users
 brew install tesseract-lang
+
+# Fedora users
+dnf search tesseract-langpack # Display a list of all Tesseract language packs 
+dnf install tesseract-langpack-ita # Example: Install the Italian language pack
+
+
 ```

 You can then pass the `-l LANG` argument to OCRmyPDF to give a hint as to what languages it should search for. Multiple languages can be requested.
@@ -113,9 +123,43 @@ Our [documentation is served on Read the Docs](https://ocrmypdf.readthedocs.io/e

 Please report issues on our [GitHub issues](https://github.com/ocrmypdf/OCRmyPDF/issues) page, and follow the issue template for quick response.

+## Feature demo
+
+```bash
+# Add an OCR layer and require PDF/A
+ocrmypdf --output-type pdfa input.pdf output.pdf
+
+# Convert an image to single page PDF
+ocrmypdf input.jpg output.pdf
+
+# Add OCR to a file in place (only modifies file on success)
+ocrmypdf myfile.pdf myfile.pdf
+
+# OCR with non-English languages (look up your language's ISO 639-3 code)
+ocrmypdf -l fra LeParisien.pdf LeParisien.pdf
+
+# OCR multilingual documents
+ocrmypdf -l eng+fra Bilingual-English-French.pdf Bilingual-English-French.pdf
+
+# Deskew (straighten crooked pages)
+ocrmypdf --deskew input.pdf output.pdf
+```
+
+For more features, see the [documentation](https://ocrmypdf.readthedocs.io/en/latest/index.html).
+
 ## Requirements

-In addition to the required Python version (3.8+), OCRmyPDF requires external program installations of Ghostscript and Tesseract OCR. OCRmyPDF is pure Python, and runs on pretty much everything: Linux, macOS, Windows and FreeBSD.
+In addition to the required Python version, 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.
+
+## Plugins
+
+OCRmyPDF provides a plugin interface allowing its capabilities to be extended or replaced. Here are some plugins we are aware of:
+
+- [OCRmyPDF-AppleOCR](https://github.com/mkyt/ocrmypdf-AppleOCR): replaces the standard Tesseract OCR engine with Apple Vision Framework. Requires macOS.
+- [OCRmyPDF-EasyOCR](https://github.com/ocrmypdf/OCRmyPDF-EasyOCR): replaces the standard Tesseract OCR engine with EasyOCR, a newer OCR engine based on PyTorch. GPU strongly recommended.
+- [OCRmyPDF-PaddleOCR](https://github.com/clefru/ocrmypdf-paddleocr): replaces the standard Tesseract OCR engine with PaddleOCR, a powerful GPU accelerated OCR engine.
+
+[paperless-ngx](https://docs.paperless-ngx.com/) provides integration of OCRmyPDF into a searchable document management system.

 ## Press & Media

@@ -0,0 +1,187 @@
+<!-- SPDX-FileCopyrightText: 2014 Julien Pfefferkorn -->
+<!-- SPDX-FileCopyrightText: 2015 James R. Barlow -->
+<!-- SPDX-License-Identifier: CC-BY-SA-4.0 -->
+
+<img src="docs/images/logo.svg" width="240" alt="OCRmyPDF">
+
+[![构建状态](https://github.com/ocrmypdf/OCRmyPDF/actions/workflows/build.yml/badge.svg)](https://github.com/ocrmypdf/OCRmyPDF/actions/workflows/build.yml) [![PyPI 版本][pypi]](https://pypi.org/project/ocrmypdf/) ![Homebrew 版本][homebrew] ![ReadTheDocs][docs] ![Python 版本][pyversions]
+
+[pypi]: https://img.shields.io/pypi/v/ocrmypdf.svg "PyPI 版本"
+[homebrew]: https://img.shields.io/homebrew/v/ocrmypdf.svg "Homebrew 版本"
+[docs]: https://readthedocs.org/projects/ocrmypdf/badge/?version=latest "RTD"
+[pyversions]: https://img.shields.io/pypi/pyversions/ocrmypdf "支持的 Python 版本"
+
+OCRmyPDF 会为扫描版 PDF 文件添加 OCR 文本层，使其可以搜索或复制粘贴。
+
+```bash
+ocrmypdf                      # 它是一个可脚本化的命令行程序
+   -l eng+fra                 # 它支持多种语言
+   --rotate-pages             # 它可以修正旋转方向错误的页面
+   --deskew                   # 它可以校正歪斜的 PDF！
+   --title "My PDF"           # 它可以更改输出元数据
+   --jobs 4                   # 它默认使用多个 CPU 核心
+   --output-type pdfa         # 它默认生成 PDF/A
+   input_scanned.pdf          # 接受 PDF 输入（或图像）
+   output_searchable.pdf      # 生成经过验证的 PDF 输出
+```
+
+[查看发布说明，了解最新变更详情](https://ocrmypdf.readthedocs.io/en/latest/release_notes.html)。
+
+## 主要功能
+
+- 从普通 PDF 生成可搜索的 [PDF/A](https://en.wikipedia.org/?title=PDF/A) 文件
+- 将 OCR 文本准确放置在图像下方，便于复制/粘贴
+- 保持原始嵌入图像的精确分辨率
+- 在可能时，以“无损”操作插入 OCR 信息，不干扰任何其他内容
+- 优化 PDF 图像，通常生成比输入文件更小的文件
+- 按需在执行 OCR 前校正和/或清理图像
+- 验证输入和输出文件
+- 在所有可用 CPU 核心间分配工作
+- 使用 [Tesseract OCR](https://github.com/tesseract-ocr/tesseract) 引擎识别超过 [100 种语言](https://github.com/tesseract-ocr/tessdata)
+- 保护你的私有数据。
+- 可以妥善扩展，处理包含数千页的文件。
+- 已在数百万份 PDF 上经过实战检验。
+
+<img src="misc/screencast/demo.svg" alt="OCRmyPDF 在终端会话中的演示">
+
+详情请参阅[文档](https://ocrmypdf.readthedocs.io/en/latest/)。
+
+## 动机
+
+我曾在网上寻找一款免费的命令行工具来对 PDF 文件执行 OCR：我找到了很多，但没有一个真正令人满意：
+
+- 要么生成的 PDF 文件中文本位于图像下方的错误位置（导致无法复制/粘贴）
+- 要么无法处理重音字符和多语言字符
+- 要么会改变嵌入图像的分辨率
+- 要么生成的 PDF 文件大得离谱
+- 要么在尝试 OCR 时崩溃
+- 要么无法生成有效的 PDF 文件
+- 除此之外，它们都不能生成 PDF/A 文件（专为长期存储设计的格式）
+
+……所以我决定开发自己的工具。
+
+## 安装
+
+支持 Linux、Windows、macOS 和 FreeBSD。也提供 Docker 镜像，同时支持 x64 和 ARM。
+
+| 操作系统                      | 安装命令                       |
+| ----------------------------- | ------------------------------ |
+| Debian, Ubuntu                | ``apt install ocrmypdf``       |
+| Windows Subsystem for Linux   | ``apt install ocrmypdf``       |
+| Fedora                        | ``dnf install ocrmypdf``       |
+| macOS (Homebrew)              | ``brew install ocrmypdf``      |
+| macOS (MacPorts)              | ``port install ocrmypdf``      |
+| macOS (nix)                   | ``nix-env -i ocrmypdf``        |
+| LinuxBrew                     | ``brew install ocrmypdf``      |
+| FreeBSD                       | ``pkg install py-ocrmypdf``    |
+| OpenBSD                       | ``pkg_add ocrmypdf``           |
+| Ubuntu Snap                   | ``snap install ocrmypdf``      |
+
+其他用户请[参阅我们的文档](https://ocrmypdf.readthedocs.io/en/latest/installation.html)了解安装步骤。
+
+## 语言
+
+OCRmyPDF 使用 Tesseract 执行 OCR，并依赖其语言包。对于 Linux 用户，通常可以找到提供语言包的软件包：
+
+```bash
+
+# Debian/Ubuntu 用户
+apt-cache search tesseract-ocr # 显示所有 Tesseract 语言包列表
+apt-get install tesseract-ocr-chi-sim  # 示例：安装简体中文语言包
+
+
+# Arch Linux 用户
+pacman -S tesseract-data-eng tesseract-data-deu # 示例：安装英语和德语语言包
+
+# OpenBSD 用户
+pkg_info -aQ tesseract  # 显示所有 Tesseract 语言包列表
+pkg_add tesseract-cym  # 示例：安装威尔士语语言包
+
+# brew macOS 用户
+brew install tesseract-lang
+
+# Fedora 用户
+dnf search tesseract-langpack # 显示所有 Tesseract 语言包列表
+dnf install tesseract-langpack-ita # 示例：安装意大利语语言包
+
+
+```
+
+随后可以向 OCRmyPDF 传递 `-l LANG` 参数，提示它应搜索哪些语言。可以同时请求多种语言。
+
+OCRmyPDF 支持 Tesseract 4.1.1+。它会自动使用 `PATH` 环境变量中首先找到的版本。在 Windows 上，如果 `PATH` 中没有 Tesseract 二进制文件，我们会根据 Windows 注册表使用已安装的最高版本号。
+
+## 文档和支持
+
+安装 OCRmyPDF 后，可以通过以下命令访问内置帮助，了解命令语法和选项：
+
+```bash
+ocrmypdf --help
+```
+
+我们的[文档托管在 Read the Docs 上](https://ocrmypdf.readthedocs.io/en/latest/index.html)。
+
+请在我们的 [GitHub issues](https://github.com/ocrmypdf/OCRmyPDF/issues) 页面报告问题，并遵循 issue 模板以便快速获得响应。
+
+## 功能演示
+
+```bash
+# 添加 OCR 层并要求输出 PDF/A
+ocrmypdf --output-type pdfa input.pdf output.pdf
+
+# 将图像转换为单页 PDF
+ocrmypdf input.jpg output.pdf
+
+# 就地为文件添加 OCR（仅在成功时修改文件）
+ocrmypdf myfile.pdf myfile.pdf
+
+# 使用非英语语言执行 OCR（请查找对应语言的 ISO 639-3 代码）
+ocrmypdf -l fra LeParisien.pdf LeParisien.pdf
+
+# OCR 多语言文档
+ocrmypdf -l eng+fra Bilingual-English-French.pdf Bilingual-English-French.pdf
+
+# 校正歪斜页面
+ocrmypdf --deskew input.pdf output.pdf
+```
+
+更多功能请参阅[文档](https://ocrmypdf.readthedocs.io/en/latest/index.html)。
+
+## 要求
+
+除所需的 Python 版本外，OCRmyPDF 还需要安装 Ghostscript 和 Tesseract OCR 这两个外部程序。OCRmyPDF 是纯 Python 项目，几乎可以在所有平台上运行：Linux、macOS、Windows 和 FreeBSD。
+
+## 插件
+
+OCRmyPDF 提供插件接口，允许扩展或替换其能力。以下是我们知道的一些插件：
+
+- [OCRmyPDF-AppleOCR](https://github.com/mkyt/ocrmypdf-AppleOCR)：用 Apple Vision Framework 替换标准 Tesseract OCR 引擎。需要 macOS。
+- [OCRmyPDF-EasyOCR](https://github.com/ocrmypdf/OCRmyPDF-EasyOCR)：用 EasyOCR 替换标准 Tesseract OCR 引擎；EasyOCR 是基于 PyTorch 的较新 OCR 引擎。强烈建议使用 GPU。
+- [OCRmyPDF-PaddleOCR](https://github.com/clefru/ocrmypdf-paddleocr)：用 PaddleOCR 替换标准 Tesseract OCR 引擎；PaddleOCR 是功能强大的 GPU 加速 OCR 引擎。
+
+[paperless-ngx](https://docs.paperless-ngx.com/) 将 OCRmyPDF 集成到可搜索的文档管理系统中。
+
+## 新闻与媒体
+
+- [Going paperless with OCRmyPDF](https://medium.com/@ikirichenko/going-paperless-with-ocrmypdf-e2f36143f46a)
+- [Converting a scanned document into a compressed searchable PDF with redactions](https://medium.com/@treyharris/converting-a-scanned-document-into-a-compressed-searchable-pdf-with-redactions-63f61c34fe4c)
+- [c't 1-2014，第 59 页](https://heise.de/-2279695)：德国领先 IT 杂志 c't 对 OCRmyPDF v1.0 的详细介绍
+- [heise Open Source, 09/2014: Texterkennung mit OCRmyPDF](https://heise.de/-2356670)
+- [heise Durchsuchbare PDF-Dokumente mit OCRmyPDF erstellen](https://www.heise.de/ratgeber/Durchsuchbare-PDF-Dokumente-mit-OCRmyPDF-erstellen-4607592.html)
+- [Excellent Utilities: OCRmyPDF](https://www.linuxlinks.com/excellent-utilities-ocrmypdf-add-ocr-text-layer-scanned-pdfs/)
+- [LinuxUser Texterkennung mit OCRmyPDF und Scanbd automatisieren](https://www.linux-community.de/ausgaben/linuxuser/2021/06/texterkennung-mit-ocrmypdf-und-scanbd-automatisieren/)
+- [Y Combinator discussion](https://news.ycombinator.com/item?id=32028752)
+
+## 商务咨询
+
+如果没有公司和用户选择支持功能开发与咨询服务，OCRmyPDF 不会成为今天的软件。无论是扩展现有功能集，还是将 OCRmyPDF 集成到更大的系统中，我们都很乐意讨论各类咨询需求。
+
+## 许可证
+
+OCRmyPDF 软件采用 Mozilla Public License 2.0 (MPL-2.0) 授权。该许可证允许将 OCRmyPDF 与其他代码集成，包括商业代码和闭源代码，但要求你发布对 OCRmyPDF 所做的源代码级修改。
+
+OCRmyPDF 的某些组件采用其他许可证，具体由标准 SPDX 许可证标识符或 DEP5 版权与许可信息文件标明。一般来说，非核心代码采用 MIT 许可证，文档和测试文件采用 Creative Commons ShareAlike 4.0 (CC-BY-SA 4.0) 许可证。
+
+## 免责声明
+
+本软件按“原样”分发，不提供任何明示或暗示的保证或条件。
@@ -0,0 +1,184 @@
+version = 1
+SPDX-PackageName = "OCRmyPDF"
+SPDX-PackageSupplier = "James R. Barlow <james@purplerock.ca>"
+SPDX-PackageDownloadLocation = "https://github.com/ocrmypdf/OCRmyPDF"
+
+[[annotations]]
+path = ["docs/**", 'misc/screencast/**']
+precedence = "aggregate"
+SPDX-FileCopyrightText = "(C) 2025 James R. Barlow"
+SPDX-License-Identifier = "CC-BY-SA-4.0"
+
+[[annotations]]
+path = [
+    "uv.lock",
+    ".git_archival.txt",
+    "docs/images/logo-social.png",
+    "docs/images/logo-square-256.svg",
+    "docs/images/logo-square.png",
+    "docs/images/logo-square.svg",
+    "docs/images/logo.svg",
+]
+precedence = "aggregate"
+SPDX-FileCopyrightText = "(C) 2025 James R. Barlow"
+SPDX-License-Identifier = "MPL-2.0"
+
+[[annotations]]
+path = [".github/ISSUE_TEMPLATE/**.yml"]
+precedence = "aggregate"
+SPDX-FileCopyrightText = "(C) 2025 James R. Barlow"
+SPDX-License-Identifier = "CC-BY-SA-4.0"
+
+[[annotations]]
+path = [
+    "tests/resources/acroform.pdf",
+    "tests/resources/aspect.pdf",
+    "tests/resources/blank.pdf",
+    "tests/resources/cmyk.pdf",
+    "tests/resources/crom.png",
+    "tests/resources/enormous.pdf",
+    "tests/resources/formxobject.pdf",
+    "tests/resources/francais.pdf",
+    "tests/resources/hugemono.pdf",
+    "tests/resources/invalid.pdf",
+    "tests/resources/kcs.pdf",
+    "tests/resources/livecycle.pdf",
+    "tests/resources/meta.pdf",
+    "tests/resources/missing_docinfo.pdf",
+    "tests/resources/negzero.pdf",
+    "tests/resources/no_contents.pdf",
+    "tests/resources/tagged**",
+    "tests/resources/toc.pdf",
+    "tests/resources/trivial.pdf",
+    "tests/resources/truetype_font_nomapping.pdf",
+    "tests/resources/type3_font_nomapping.pdf",
+]
+precedence = "aggregate"
+SPDX-FileCopyrightText = "(C) 2025 James R. Barlow"
+SPDX-License-Identifier = "CC-BY-SA-4.0"
+
+[[annotations]]
+path = ["tests/resources/graph.pdf", "tests/resources/graph_ocred.pdf"]
+precedence = "aggregate"
+SPDX-FileCopyrightText = "(C) 2012 SmokeyJoe"
+SPDX-License-Identifier = "GFDL-1.2-or-later or CC-BY-SA-3.0"
+
+[[annotations]]
+path = ["tests/resources/c02-22.pdf", "tests/resources/multipage.pdf"]
+precedence = "aggregate"
+SPDX-FileCopyrightText = "Public domain"
+SPDX-License-Identifier = "public-domain"
+
+[[annotations]]
+path = "docs/images/bitmap_vs_svg.svg"
+precedence = "aggregate"
+SPDX-FileCopyrightText = "(C) 2006 Yug"
+SPDX-License-Identifier = "CC-BY-SA-2.5"
+
+[[annotations]]
+path = "tests/cache/**"
+precedence = "aggregate"
+SPDX-FileCopyrightText = "(C) 2025 James R. Barlow"
+SPDX-License-Identifier = "CC-BY-SA-4.0"
+
+[[annotations]]
+path = [
+    "tests/resources/linn.png",
+    "tests/resources/linn.pdf",
+    "tests/resources/linn.txt",
+    "tests/resources/ccitt.pdf",
+    "tests/resources/cardinal.pdf",
+    "tests/resources/jbig2.pdf",
+    "tests/resources/jbig2_baddevicen.pdf",
+    "tests/resources/skew.pdf",
+    "tests/resources/rotated_skew.pdf",
+    "tests/resources/poster.pdf",
+]
+precedence = "aggregate"
+SPDX-FileCopyrightText = "(C) 1985 Forat Electronics"
+SPDX-License-Identifier = "GFDL-1.2-or-later or CC-BY-SA-3.0"
+
+[[annotations]]
+path = "tests/resources/lichtenstein.pdf"
+precedence = "aggregate"
+SPDX-FileCopyrightText = ["(C) 2001 Andreas Tille", "(C) 2007 Alessio Damato"]
+SPDX-License-Identifier = "GFDL-1.2-or-later or CC-BY-SA-3.0"
+
+[[annotations]]
+path = "tests/resources/masks.pdf"
+precedence = "aggregate"
+SPDX-FileCopyrightText = [
+    "held by the contributors to the German Wikipedia article \"Linux\"",
+    "see: https://de.wikipedia.org/w/index.php?title=Linux&action=history",
+    "(masks.pdf generated from Wikipedia article as of 2016-08-24)",
+]
+SPDX-License-Identifier = "CC-BY-SA-3.0"
+
+[[annotations]]
+path = "tests/resources/epson.pdf"
+precedence = "aggregate"
+SPDX-FileCopyrightText = [
+    "held by the contributors to the Wikipedia article \"Optical character recognition\"",
+    "see: https://en.wikipedia.org/w/index.php?title=Optical_character_recognition&action=history",
+    "(epson.pdf generated from Wikipedia article as of 2016-09-14)",
+]
+SPDX-License-Identifier = "CC-BY-SA-3.0"
+
+[[annotations]]
+path = ["tests/resources/typewriter.png", "tests/resources/2400dpi.pdf"]
+precedence = "aggregate"
+SPDX-FileCopyrightText = "(C) 2005 Ellywa"
+SPDX-License-Identifier = "GFDL-1.2-or-later or CC-BY-SA-1.0 or CC-BY-SA-2.0 or CC-BY-SA-2.5 or CC-BY-SA-3.0"
+SPDX-FileComment = "\n Obtained from: https://commons.wikimedia.org/wiki/File:Triumph.typewriter_text_Linzensoep.gif"
+
+[[annotations]]
+path = "tests/resources/overlay.pdf"
+precedence = "aggregate"
+SPDX-FileCopyrightText = "(C) 2017 Max Anderson"
+SPDX-License-Identifier = "MIT"
+
+[[annotations]]
+path = [
+    "tests/resources/baiona**.png",
+    "tests/resources/baiona**.jpg",
+    "tests/resources/link.pdf",
+    "tests/resources/palette.pdf",
+]
+precedence = "aggregate"
+SPDX-FileCopyrightText = "(C) 2014 Euskaldunaa"
+SPDX-License-Identifier = "CC-BY-SA-4.0"
+
+[[annotations]]
+path = "tests/resources/vector.pdf"
+precedence = "aggregate"
+SPDX-FileCopyrightText = "(C) 2018 Catscratch"
+SPDX-License-Identifier = "MIT"
+
+[[annotations]]
+path = "src/ocrmypdf/data/sRGB.icc"
+precedence = "aggregate"
+SPDX-FileCopyrightText = [
+    "Kai-Uwe Behrmann <www.behrmann.name>",
+    "Marti Maria <www.littlecms.com>",
+    "Photogamut <www.photogamut.org>",
+    "Graeme Gill <www.argyllcms.com>",
+    "ColorSolutions <www.basICColor.com>",
+]
+SPDX-License-Identifier = "Zlib"
+
+[[annotations]]
+path = "src/ocrmypdf/data/Occulta.ttf"
+precedence = "aggregate"
+SPDX-FileCopyrightText = ["(C) 2026 James R. Barlow"]
+SPDX-License-Identifier = "Apache-2.0"
+
+[[annotations]]
+path = "tests/resources/3small.pdf"
+precedence = "aggregate"
+SPDX-FileCopyrightText = [
+    "(C) 2014 Euskaldunaa",
+    "(C) 2017 James R. Barlow",
+    "(C) 2005 Ellywa",
+]
+SPDX-License-Identifier = "CC-BY-SA-4.0 and (GFDL-1.2-or-later or CC-BY-SA-1.0 or CC-BY-SA-2.0 or CC-BY-SA-2.5 or CC-BY-SA-3.0)"
+SPDX-FileComment = "concatenation of baiona_gray.png, crom.png and typewriter.png/2400dpi.pdf"
@@ -0,0 +1,408 @@
+#!/usr/bin/env python3
+# SPDX-FileCopyrightText: 2017-2019 Joe Rickerby and contributors
+# SPDX-License-Identifier: BSD-2-Clause
+
+"""Bump the version number in all the right places."""
+
+from __future__ import annotations
+
+import os
+import subprocess
+import sys
+import time
+import urllib.parse
+from pathlib import Path
+
+import cyclopts
+from packaging.version import InvalidVersion, Version
+
+try:
+    from github import Auth, Github, GithubException
+except ImportError:
+    Auth = None  # type: ignore
+    Github = None  # type: ignore
+    GithubException = Exception  # type: ignore
+
+import ocrmypdf
+
+config = [
+    # file path, version find/replace format
+    ("src/ocrmypdf/_version.py", '__version__ = "{}"'),
+    ("pyproject.toml", 'version = "{}"'),
+]
+
+RED = "\u001b[31m"
+GREEN = "\u001b[32m"
+YELLOW = "\u001b[33m"
+OFF = "\u001b[0m"
+
+REPO_NAME = "ocrmypdf/OCRmyPDF"
+
+
+def validate_release_notes(new_version: str) -> bool:
+    """Check that the version appears in the release notes.
+
+    Returns True if the version is found, False otherwise.
+    """
+    version_obj = Version(new_version)
+    major = version_obj.major
+    release_notes_path = Path(f"docs/releasenotes/version{major:02d}.md")
+
+    if not release_notes_path.exists():
+        print(f"{RED}error:{OFF} Release notes file not found: {release_notes_path}")
+        return False
+
+    content = release_notes_path.read_text(encoding="utf8")
+    version_header = f"## v{new_version}"
+
+    if version_header not in content:
+        print(
+            f"{RED}error:{OFF} Version v{new_version} not found in {release_notes_path}"
+        )
+        print(f"       Expected to find: {version_header}")
+        return False
+
+    print(f"{GREEN}Found v{new_version} in {release_notes_path}{OFF}")
+    return True
+
+
+def get_github_client():
+    """Get an authenticated GitHub client."""
+    if Github is None or Auth is None:
+        print(f"{RED}error:{OFF} PyGithub is not installed")
+        print("       Install with: pip install PyGithub")
+        return None
+
+    # Try GITHUB_TOKEN env var first
+    token = os.environ.get("GITHUB_TOKEN")
+
+    # Fall back to gh CLI
+    if not token:
+        try:
+            result = subprocess.run(
+                ["gh", "auth", "token"],
+                capture_output=True,
+                encoding="utf8",
+                check=True,
+            )
+            token = result.stdout.strip()
+        except (FileNotFoundError, subprocess.CalledProcessError):
+            print(f"{RED}error:{OFF} No GitHub authentication found")
+            print("       Set GITHUB_TOKEN env var or run: gh auth login")
+            return None
+
+    try:
+        return Github(auth=Auth.Token(token))
+    except GithubException as e:
+        print(f"{RED}error:{OFF} Failed to authenticate with GitHub: {e}")
+        return None
+
+
+def wait_for_ci_completion(commit_sha: str, timeout_minutes: int = 30) -> bool:
+    """Wait for CI to complete on the given commit.
+
+    Returns True if CI passed, False otherwise.
+    """
+    gh = get_github_client()
+    if gh is None:
+        return False
+
+    try:
+        repo = gh.get_repo(REPO_NAME)
+    except GithubException as e:
+        print(f"{RED}error:{OFF} Failed to access repository: {e}")
+        return False
+
+    workflow_name = "Test and deploy"
+    start_time = time.time()
+    timeout_seconds = timeout_minutes * 60
+    poll_interval = 30  # seconds
+
+    print(f"Waiting for CI workflow '{workflow_name}' on commit {commit_sha[:8]}...")
+
+    # First, wait for the workflow run to appear
+    run = None
+    while time.time() - start_time < timeout_seconds:
+        try:
+            runs = repo.get_workflow_runs(head_sha=commit_sha)
+            for r in runs:
+                if r.name == workflow_name:
+                    run = r
+                    break
+            if run:
+                break
+        except GithubException as e:
+            print(f"{YELLOW}Warning:{OFF} Error checking workflow runs: {e}")
+
+        elapsed = int(time.time() - start_time)
+        print(f"  Waiting for workflow to start... ({elapsed}s)")
+        time.sleep(poll_interval)
+
+    if not run:
+        print(
+            f"{RED}error:{OFF} Workflow run not found within {timeout_minutes} minutes"
+        )
+        return False
+
+    print(f"  Found workflow run #{run.run_number} (ID: {run.id})")
+
+    # Now wait for the workflow to complete
+    while time.time() - start_time < timeout_seconds:
+        try:
+            run = repo.get_workflow_run(run.id)  # Refresh the run
+        except GithubException as e:
+            print(f"{YELLOW}Warning:{OFF} Error refreshing workflow run: {e}")
+            time.sleep(poll_interval)
+            continue
+
+        status = run.status
+        conclusion = run.conclusion
+
+        elapsed = int(time.time() - start_time)
+        if status == "completed":
+            if conclusion == "success":
+                print(f"{GREEN}CI passed!{OFF} (took {elapsed}s)")
+                return True
+            else:
+                print(f"{RED}CI failed!{OFF} Conclusion: {conclusion}")
+                print(f"  View details: {run.html_url}")
+                return False
+        else:
+            print(f"  Status: {status} ({elapsed}s elapsed)")
+            time.sleep(poll_interval)
+
+    print(f"{RED}error:{OFF} CI did not complete within {timeout_minutes} minutes")
+    return False
+
+
+def push_and_wait_for_ci(branch: str) -> bool:
+    """Push to remote and wait for CI tests to pass."""
+    print("Pushing to GitHub...")
+
+    push_result = subprocess.run(
+        ["git", "push", "origin", branch],
+        capture_output=True,
+        encoding="utf8",
+    )
+
+    if push_result.returncode != 0:
+        print(f"{RED}error:{OFF} Failed to push: {push_result.stderr}")
+        return False
+
+    # Get the commit SHA we just pushed
+    sha_result = subprocess.run(
+        ["git", "rev-parse", "HEAD"],
+        capture_output=True,
+        encoding="utf8",
+        check=True,
+    )
+    commit_sha = sha_result.stdout.strip()
+
+    print(f"Pushed commit {commit_sha[:8]}")
+
+    return wait_for_ci_completion(commit_sha)
+
+
+def push_tag(tag: str) -> bool:
+    """Push the tag to trigger release workflow."""
+    print(f"Pushing tag {tag} to trigger release...")
+
+    result = subprocess.run(
+        ["git", "push", "origin", tag],
+        capture_output=True,
+        encoding="utf8",
+    )
+
+    if result.returncode != 0:
+        print(f"{RED}error:{OFF} Failed to push tag: {result.stderr}")
+        return False
+
+    print(f"{GREEN}Tag {tag} pushed successfully!{OFF}")
+    return True
+
+
+def bump_version() -> None:
+    """Bump the version number in all the right places."""
+    current_version = ocrmypdf.__version__  # type: ignore
+    try:
+        commit_date_str = subprocess.run(
+            [
+                "git",
+                "show",
+                "--no-patch",
+                "--pretty=format:%ci",
+                f"v{current_version}^{{commit}}",
+            ],
+            check=True,
+            capture_output=True,
+            encoding="utf8",
+        ).stdout
+        cd_date, cd_time, cd_tz = commit_date_str.split(" ")
+
+        url_opts = urllib.parse.urlencode(
+            {"q": f"is:pr merged:>{cd_date}T{cd_time}{cd_tz}"}
+        )
+        url = f"https://github.com/{REPO_NAME}/pulls?{url_opts}"
+
+        print(f"PRs merged since last release:\n  {url}")
+        print()
+    except subprocess.CalledProcessError as e:
+        print(e)
+        print("Failed to get previous version tag information.")
+        print("Is the virtual environment active?")
+        sys.exit(1)
+
+    git_changes_result = subprocess.run(["git diff-index --quiet HEAD --"], shell=True)
+    repo_has_uncommitted_changes = git_changes_result.returncode != 0
+
+    if repo_has_uncommitted_changes:
+        print("error: Uncommitted changes detected.")
+        sys.exit(1)
+
+    # fmt: off
+    print(              'Current version:', current_version)
+    new_version = input('    New version: ').strip()
+    # fmt: on
+
+    try:
+        Version(new_version)
+    except InvalidVersion:
+        print("error: This version doesn't conform to PEP440")
+        print("       https://www.python.org/dev/peps/pep-0440/")
+        sys.exit(1)
+
+    # Validate release notes contain this version
+    if not validate_release_notes(new_version):
+        print()
+        print("Please add release notes for this version before proceeding.")
+        print(f"Edit: docs/releasenotes/version{Version(new_version).major:02d}.md")
+        sys.exit(1)
+
+    actions = []
+
+    for path_pattern, version_pattern in config:
+        paths = list(Path().glob(path_pattern))
+
+        if not paths:
+            print(f"error: Pattern {path_pattern} didn't match any files")
+            sys.exit(1)
+
+        find_pattern = version_pattern.format(current_version)
+        replace_pattern = version_pattern.format(new_version)
+        found_at_least_one_file_needing_update = False
+
+        for path in paths:
+            contents = path.read_text(encoding="utf8")
+            if find_pattern in contents:
+                found_at_least_one_file_needing_update = True
+                actions.append(
+                    (
+                        path,
+                        find_pattern,
+                        replace_pattern,
+                    )
+                )
+
+        if not found_at_least_one_file_needing_update:
+            print(
+                f'''error: Didn't find any occurrences of "{find_pattern}" '''
+                f'''in "{path_pattern}"'''
+            )
+            sys.exit(1)
+
+    print()
+    print("Here's the plan:")
+    print()
+
+    for action in actions:
+        path, find, replace = action
+        print(f"{path}  {RED}{find}{OFF} → {GREEN}{replace}{OFF}")
+
+    print(f"Then commit, and tag as v{new_version}")
+
+    answer = input("Proceed? [y/N] ").strip()
+
+    if answer != "y":
+        print("Aborted")
+        sys.exit(1)
+
+    for path, find, replace in actions:
+        contents = path.read_text(encoding="utf8")
+        contents = contents.replace(find, replace)
+        path.write_text(contents, encoding="utf8")
+
+    # Format only after every file (including pyproject.toml) reflects the new
+    # version. Running `uv run` while pyproject.toml still had the old version
+    # would leave its post-bump environment/lockfile resync to happen for the
+    # first time during the commit's pre-commit hooks instead of here, which
+    # then aborts the commit with a spurious "files were modified by this
+    # hook" error.
+    for path, _find, _replace in actions:
+        if path.suffix == ".py":
+            subprocess.run(["uv", "run", "ruff", "format", str(path)], check=True)
+
+    print("Files updated.")
+    print()
+
+    while input('Type "done" to continue: ').strip().lower() != "done":
+        pass
+
+    subprocess.run(
+        [
+            "git",
+            "commit",
+            "--all",
+            f"--message=Bump version: v{new_version}",
+        ],
+        check=True,
+    )
+
+    subprocess.run(
+        [
+            "git",
+            "tag",
+            "--annotate",
+            f"--message=v{new_version}",
+            f"v{new_version}",
+        ],
+        check=True,
+    )
+
+    print("Commit and tag created locally.")
+    print()
+
+    # Get current branch
+    branch_result = subprocess.run(
+        ["git", "rev-parse", "--abbrev-ref", "HEAD"],
+        capture_output=True,
+        encoding="utf8",
+        check=True,
+    )
+    branch = branch_result.stdout.strip()
+
+    # Push commit and wait for CI
+    if not push_and_wait_for_ci(branch):
+        print()
+        print(f"{RED}CI failed. The tag was NOT pushed.{OFF}")
+        print("Fix the issues, then manually push the tag:")
+        print(f"    git push origin v{new_version}")
+        sys.exit(1)
+
+    # Push tag to trigger release
+    if not push_tag(f"v{new_version}"):
+        print(f"{RED}Failed to push tag.{OFF} Push manually:")
+        print(f"    git push origin v{new_version}")
+        sys.exit(1)
+
+    print()
+    print(f"{GREEN}Done! Release workflow has been triggered.{OFF}")
+    print()
+
+    release_url = f"https://github.com/{REPO_NAME}/releases/tag/v{new_version}"
+    print("Monitor the release at:")
+    print(f"    {release_url}")
+
+
+if __name__ == "__main__":
+    os.chdir(Path(__file__).parent.parent.resolve())
+    cyclopts.run(bump_version)
@@ -0,0 +1,741 @@
+% SPDX-FileCopyrightText: 2022 James R. Barlow
+% SPDX-License-Identifier: CC-BY-SA-4.0
+
+# Advanced features
+
+## Control of unpaper
+
+OCRmyPDF uses `unpaper` to provide the implementation of the
+`--clean` and `--clean-final` arguments.
+[unpaper](https://github.com/Flameeyes/unpaper/blob/main/doc/basic-concepts.md)
+provides a variety of image processing filters to improve images.
+
+By default, OCRmyPDF uses only `unpaper` arguments that were found to
+be safe to use on almost all files without having to inspect every page
+of the file afterwards. This is particularly true when only `--clean`
+is used, since that instructs OCRmyPDF to only clean the image before
+OCR and not the final image.
+
+However, if you wish to use the more aggressive options in `unpaper`,
+you may use `--unpaper-args '...'` to override the OCRmyPDF's defaults
+and forward other arguments to unpaper. This option will forward
+arguments to `unpaper` without any knowledge of what that program
+considers to be valid arguments. The string of arguments must be quoted
+as shown in the examples below. No filename arguments may be included.
+OCRmyPDF will assume it can append input and output filename of
+intermediate images to the `--unpaper-args` string.
+
+In this example, we tell `unpaper` to expect two pages of text on a
+sheet (image), such as occurs when two facing pages of a book are
+scanned. `unpaper` uses this information to deskew each independently
+and clean up the margins of both.
+
+```bash
+ocrmypdf --clean --clean-final --unpaper-args '--layout double' input.pdf output.pdf
+ocrmypdf --clean --clean-final --unpaper-args '--layout double --no-noisefilter' input.pdf output.pdf
+```
+
+:::{warning}
+Some `unpaper` features will reposition text within the image.
+`--clean-final` is recommended to avoid this issue.
+:::
+
+:::{warning}
+Some `unpaper` features cause multiple input or output files to be
+consumed or produced. OCRmyPDF requires `unpaper` to consume one
+file and produce one file; errors will result if this assumption is not
+met.
+:::
+
+:::{note}
+`unpaper` uses uncompressed PBM/PGM/PPM files for its intermediate
+files. For large images or documents, it can take a lot of temporary
+disk space.
+:::
+
+## Control of OCR options
+
+OCRmyPDF provides many features to control the behavior of the OCR
+engine, Tesseract.
+
+### OCR processing mode
+
+:::{versionadded} 17.0.0
+The `--mode` (`-m`) argument consolidates OCR processing options.
+:::
+
+OCRmyPDF provides a unified `--mode` argument to control how pages with
+existing text are handled:
+
+| Mode | Behavior | Legacy equivalent |
+|------|----------|-------------------|
+| `default` | Error if text is found | (no flag) |
+| `force` | Rasterize all content and run OCR | `--force-ocr` |
+| `skip` | Skip pages with existing text | `--skip-text` |
+| `redo` | Re-OCR pages, stripping old OCR layer | `--redo-ocr` |
+
+```bash
+# Skip pages that already have text
+ocrmypdf --mode skip input.pdf output.pdf
+# or equivalently:
+ocrmypdf -m skip input.pdf output.pdf
+
+# Force OCR on all pages (rasterizes everything)
+ocrmypdf --mode force input.pdf output.pdf
+
+# Re-do OCR, replacing old invisible text
+ocrmypdf --mode redo input.pdf output.pdf
+```
+
+The legacy flags (`--force-ocr`, `--skip-text`, `--redo-ocr`) remain as
+silent aliases for backward compatibility.
+
+### When OCR is skipped
+
+If a page in a PDF seems to have text, by default OCRmyPDF will exit
+without modifying the PDF. This is to ensure that PDFs that were
+previously OCRed or were "born digital" rather than scanned are not
+processed.
+
+If `--mode skip` (or `--skip-text`) is issued, then no image processing or OCR will be
+performed on pages that already have text. The page will be copied to
+the output. This may be useful for documents that contain both "born
+digital" and scanned content, or to use OCRmyPDF to normalize and
+convert to PDF/A regardless of their contents.
+
+If `--mode redo` (or `--redo-ocr`) is issued, then a detailed text analysis is performed.
+Text is categorized as either visible or invisible. Invisible text (OCR)
+is stripped out. Then an image of each page is created with visible text
+masked out. The page image is sent for OCR, and any additional text is
+inserted as OCR. If a file contains a mix of text and bitmap images that
+contain text, OCRmyPDF will locate the additional text in images without
+disrupting the existing text. Some PDF OCR solutions render text as
+technically printable or visible in some way, perhaps by drawing it and
+then painting over it. OCRmyPDF cannot distinguish this type of OCR
+text from real text, so it will not be "redone".
+
+If `--mode force` (or `--force-ocr`) is issued, then all pages will be rasterized to
+images, discarding any hidden OCR text, rasterizing any printable
+text, and flattening form fields or interactive objects into their visual
+representation. This is useful for redoing OCR, for fixing OCR text
+with a damaged character map (text is selectable but not searchable),
+and destroying redacted information.
+
+### Tagged PDFs and structural markup
+
+Some PDFs carry a logical structure tree (`/StructTreeRoot`), the markup that
+makes a "Tagged PDF" — typically the result of layout analysis or a born-digital
+export. By default OCRmyPDF treats this as a signal that the document may not need
+OCR and exits, in the same way it stops on PDFs that already contain text. Use
+`--tagged-pdf-mode ignore`, or one of `--mode skip`/`redo`/`force`, to process
+such a file anyway.
+
+OCRmyPDF cannot rebuild a structure tree to match newly recognized text. When
+`--force-ocr` rasterizes pages, or `--redo-ocr` strips and rewrites the text layer,
+the structure tree no longer corresponds to the page content, so it is discarded.
+`--mode skip` leaves text pages untouched, so their structural markup is preserved.
+
+:::{note}
+Preservation under `--mode skip` only holds when the output is not converted to
+PDF/A. PDF/A conversion is performed by Ghostscript, and Ghostscript 10.x discards
+the structure tree during conversion (Ghostscript 9.x preserved it). Because the
+default `--output-type auto` may fall back to Ghostscript, use
+`--output-type pdf` if you need to guarantee that a Tagged PDF's structural markup
+survives. For best results, install veraPDF so that speculative PDF/A
+conversion can sidestep this issue entirely in most real cases.
+:::
+
+### Time and image size limits
+
+By default, OCRmyPDF permits tesseract to run for three minutes (180
+seconds) per page. This is usually more than enough time to find all
+text on a reasonably sized page with modern hardware.
+
+If a page is skipped, it will be inserted without OCR. If preprocessing
+was requested, the preprocessed image layer will be inserted.
+
+If you want to adjust the amount of time spent on OCR, change
+`--tesseract-timeout`. You can also automatically skip images that
+exceed a certain number of megapixels with `--skip-big`. (A 300 DPI,
+8.5×11" page image is 8.4 megapixels.)
+
+```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. By default,
+`--tesseract-downsample-large-images` is enabled, and OCRmyPDF will
+downsample images to fit Tesseract limits. (The limits are usually encountered
+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.) This feature can disabled
+using `--no-tesseract-downsample-large-images`.
+
+`--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 (32767 pixels on either dimension).
+
+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.
+
+```bash
+# Allow 600 seconds for OCR on huge images
+ocrmypdf --tesseract-timeout 600 \
+    --tesseract-downsample-large-images \
+    bigfile.pdf output.pdf
+
+# Downsample images above 5000 pixels on the longest dimension to
+# 5000 pixels
+ocrmypdf --tesseract-timeout 120 \
+    --tesseract-downsample-large-images \
+    --tesseract-downsample-above 5000 \
+    bigfile.pdf output_downsampled_ocr.pdf
+```
+
+### Overriding default tesseract
+
+OCRmyPDF checks the system `PATH` for the `tesseract` binary.
+
+Some relevant environment variables that influence Tesseract's behavior
+include:
+
+```{eval-rst}
+.. envvar:: TESSDATA_PREFIX
+
+   Overrides the path to Tesseract's data files. This can allow
+   simultaneous installation of the "best" and "fast" training data
+   sets. OCRmyPDF does not manage this environment variable.
+
+   If you point ``TESSDATA_PREFIX`` at a hand-assembled ``tessdata``
+   folder (for example, individual ``.traineddata`` files downloaded
+   from tessdata_best), make sure it also contains the ``configs/``
+   subdirectory with the ``hocr`` and ``txt`` files. OCRmyPDF requires
+   these; without them Tesseract produces no output. See
+   :ref:`Tesseract cannot open its config file <tesseract-config-missing>`.
+```
+
+```{eval-rst}
+.. envvar:: OMP_THREAD_LIMIT
+
+   Controls the number of threads Tesseract will use. OCRmyPDF will
+   manage this environment variable if it is not already set.
+```
+
+For example, if you have a development build of Tesseract don't wish to
+use the system installation, you can launch OCRmyPDF as follows:
+
+```bash
+env \
+    PATH=/home/user/src/tesseract/api:$PATH \
+    TESSDATA_PREFIX=/home/user/src/tesseract \
+    ocrmypdf input.pdf output.pdf
+```
+
+In this example `TESSDATA_PREFIX` is required to redirect Tesseract to
+an alternate folder for its "tessdata" files.
+
+### Overriding other support programs
+
+In addition to tesseract, OCRmyPDF uses the following external binaries:
+
+- `gs` (Ghostscript)
+- `unpaper`
+- `pngquant`
+- `jbig2`
+
+In each case OCRmyPDF will search the `PATH` environment variable to
+locate the binaries. By modifying the `PATH` environment variable, you
+can override the binaries that OCRmyPDF uses.
+
+### Changing Tesseract configuration variables
+
+You can override Tesseract's default [control
+parameters](https://tesseract-ocr.github.io/tessdoc/tess3/ControlParams.html)
+with a configuration file.
+
+As an example, this configuration will disable Tesseract's dictionary
+for current language. Normally the dictionary is helpful for
+interpolating words that are unclear, but it may interfere with OCR if
+the document does not contain many words (for example, a list of part
+numbers).
+
+Create a file named "no-dict.cfg" with these contents:
+
+```
+load_system_dawg 0
+language_model_penalty_non_dict_word 0
+language_model_penalty_non_freq_dict_word 0
+```
+
+then run ocrmypdf as follows (along with any other desired arguments):
+
+```bash
+ocrmypdf --tesseract-config no-dict.cfg input.pdf output.pdf
+```
+
+:::{warning}
+Some combinations of control parameters will break Tesseract or break
+assumptions that OCRmyPDF makes about Tesseract's output.
+:::
+
+### Changing page segmentation mode
+
+The directive `--tesseract-pagesegmode Nmode` forwards the desired page segmentation
+mode to Tesseract OCR. The default is 3.
+
+Page segmentation can improve OCR results when you know that a PDF ought to be
+analyzed a particular way, such as PDFs whose pages contain only a single line of
+text. For the vast majority of users, changing the page segmentation mode will only
+make things worse.
+
+As of June 2024, the Tesseract page segmentation modes are:
+
+| ID  | Description                                                                                   |
+| --- | --------------------------------------------------------------------------------------------- |
+| 0   | Orientation and script detection (OSD) only.                                                  |
+| 1   | Automatic page segmentation with OSD.                                                         |
+| 2   | Automatic page segmentation, but no OSD, or OCR. (not implemented)                            |
+| 3   | Fully automatic page segmentation, but no OSD. (Default)                                      |
+| 4   | Assume a single column of text of variable sizes.                                             |
+| 5   | Assume a single uniform block of vertically aligned text.                                     |
+| 6   | Assume a single uniform block of text.                                                        |
+| 7   | Treat the image as a single text line.                                                        |
+| 8   | Treat the image as a single word.                                                             |
+| 9   | Treat the image as a single word in a circle.                                                 |
+| 10  | Treat the image as a single character.                                                        |
+| 11  | Sparse text. Find as much text as possible in no particular order.                            |
+| 12  | Sparse text with OSD.                                                                         |
+| 13  | Raw line. Treat the image as a single text line, bypassing hacks that are Tesseract-specific. |
+
+Modes 0, 1, 2, and 12 (all of those that enable orientation and script detection)
+are not compatible with OCRmyPDF, which performs OSD in a separate step from OCR.
+Their use may interfere with `--rotate-pages` and other features.
+
+It is currently not possible to use advanced Tesseract OCR features, such as creating
+OCR information, when using Tesseract through OCRmyPDF.
+
+## Choosing a PDF rasterizer
+
+:::{versionadded} 17.0.0
+:::
+
+rasterizing
+
+: Converting a PDF page to an image for OCR processing.
+
+OCRmyPDF supports two PDF rasterizers:
+
+| Rasterizer | Package | Advantages | Disadvantages |
+|------------|---------|------------|---------------|
+| pypdfium2 | Python package | Faster, fewer version issues | Requires pypdfium2 package |
+| Ghostscript | System binary | More widely packaged | Version consistency issues, restrictive AGPLv3 |
+
+The `--rasterizer` argument controls which rasterizer is used:
+
+```bash
+# Automatic selection (default) - prefers pypdfium when available
+ocrmypdf --rasterizer auto input.pdf output.pdf
+
+# Force pypdfium2
+ocrmypdf --rasterizer pypdfium input.pdf output.pdf
+
+# Force Ghostscript
+ocrmypdf --rasterizer ghostscript input.pdf output.pdf
+```
+
+pypdfium2 is a Python binding for pdfium, the PDF rendering library used
+by Google Chrome and Chromium. It generally produces output identical to
+Ghostscript but with better performance.
+
+:::{note}
+If pypdfium2 is not installed and `--rasterizer pypdfium` is requested,
+OCRmyPDF will exit with an error. Install it with: `pip install pypdfium2`
+:::
+
+## Changing the PDF renderer
+
+rendering
+
+: Creating a new PDF from other data (such as an existing PDF).
+
+:::{versionchanged} 17.0.0
+The fpdf2 renderer is now the default, replacing the legacy hOCR renderer.
+:::
+
+OCRmyPDF uses PDF renderers to create the invisible text layer. The
+renderer may be selected using `--pdf-renderer`. The default is
+`auto` which selects `fpdf2`.
+
+### The `fpdf2` renderer (default)
+
+:::{versionadded} 17.0.0
+:::
+
+The fpdf2 renderer creates text layers using the fpdf2 library. It provides:
+
+- Full multilingual support including RTL languages (Arabic, Hebrew, Persian)
+- Accurate text positioning aligned with OCR bounding boxes
+- Improved "Occulta" glyphless font handling:
+  - Zero-width markers are properly handled
+  - Double-width CJK characters are properly sized
+- Direct OcrElement tree input (no hOCR intermediate format required)
+
+The fpdf2 renderer is the recommended choice for all installations.
+
+:::{note}
+The fpdf2 renderer may be slightly slower than the legacy hocrtransform
+renderer for some workloads. This is an area of ongoing optimization.
+:::
+
+In both renderers, a text-only layer is rendered and sandwiched (overlaid)
+on to either the original PDF page, or newly rasterized version of the
+original PDF page (when `--mode force` is used). In this way, loss
+of PDF information is generally avoided. (You may need to disable PDF/A
+conversion and optimization to eliminate all lossy transformations.)
+
+### The `sandwich` renderer
+
+The `sandwich` renderer uses Tesseract's text-only PDF feature,
+which produces a PDF page that lays out the OCR in invisible text.
+
+Currently some problematic PDF viewers like Mozilla PDF.js and macOS
+Preview have problems with segmenting its text output, and
+mightrunseveralwordstogether. It also does not implement right to left
+fonts (Arabic, Hebrew, Persian). The output of this renderer cannot
+be edited. The sandwich renderer is retained for testing.
+
+When image preprocessing features like `--deskew` are used, the
+original PDF will be rendered as a full page and the OCR layer will be
+placed on top.
+
+### Legacy renderer options
+
+The `hocr` and `hocrdebug` renderer options are deprecated and
+automatically redirect to `fpdf2`. They will be removed in a future version.
+
+## 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`.
+
+## Advanced Ghostscript tuning
+
+:::{versionadded} 17.5.0
+:::
+
+OCRmyPDF intentionally hides most Ghostscript controls because Ghostscript
+is a legacy code path. The preferred PDF/A pipeline in v17+ uses pypdfium2
+as the rasterizer and verapdf to validate speculative PDF/A output, with
+Ghostscript reserved as a fallback for PDFs that cannot be made compliant
+without it. OCRmyPDF's separate optimizer (controlled by `--optimize`,
+`--jpeg-quality`, `--png-quality`, etc.) is the supported way to shrink
+output PDFs: it gives consistent results across input files, and isolates
+Ghostscript so it can focus on producing a PDF/A with as few image
+transformations as possible.
+
+The two options below are exposed for advanced users who want to tune
+Ghostscript's intermediate PDF/A output directly. Most users will get
+more predictable results from the optimizer.
+
+### `--ghostscript-jpeg-quality Q`
+
+Sets Ghostscript's `-dJPEGQ` switch for images that Ghostscript chooses
+to recompress to JPEG while building a PDF/A. `Q=0` requests maximum
+compression and `Q=100` requests best quality; if the flag is omitted,
+OCRmyPDF passes `95` (the historical default). This only affects images
+Ghostscript transcodes — existing JPEGs pass through unchanged on modern
+Ghostscript releases. For end-to-end JPEG quality tuning, prefer
+`--jpeg-quality`, which is implemented by the OCRmyPDF optimizer and is
+applied independently of whatever Ghostscript decides to do.
+
+Note: setting both `--ghostscript-jpeg-quality` and `--jpeg-quality` can
+result in double JPEG recompression, since the optimizer may re-encode
+images that Ghostscript already recompressed. This can degrade quality
+in subtle ways.
+
+### `--ghostscript-jpeg-maxdpi DPI`
+
+Enables Ghostscript's image downsampling and caps color, grayscale, and
+monochrome image resolution to `DPI`. The downsample threshold is set to
+`1.0`, so any image whose effective DPI exceeds the cap will be
+downsampled.
+
+Reducing JPEG quality is almost always a better trade than downsampling
+at the same compression budget: a 400 DPI JPEG at modest quality usually
+looks much better than a 200 DPI JPEG, because the JPEG codec can spend
+bits where they count. Downsampling is also dangerous for PDFs that
+combine a low-resolution color image with a high-resolution monochrome
+mask — capping the mask resolution can produce visible quality loss.
+For these reasons, prefer `--jpeg-quality` over `--ghostscript-jpeg-maxdpi`
+unless you specifically want to force a hard DPI cap.
+
+Example:
+
+```bash
+ocrmypdf --output-type pdfa \
+    --ghostscript-jpeg-quality 80 \
+    --ghostscript-jpeg-maxdpi 150 \
+    in.pdf out.pdf
+```
+
+These options only take effect when Ghostscript is invoked for PDF/A
+conversion (`--output-type pdfa`, `pdfa-1`, `pdfa-2`, or `pdfa-3`, or
+when `--output-type auto` falls back to Ghostscript).
+
+## PDF/A output modes
+
+:::{versionchanged} 17.0.0
+The default `--output-type` is now `auto` instead of `pdfa`.
+:::
+
+OCRmyPDF can produce PDF/A compliant output for long-term archival. The
+`--output-type` argument controls PDF/A conversion:
+
+| Output type | Behavior |
+|-------------|----------|
+| `auto` | Best-effort PDF/A without requiring Ghostscript (default) |
+| `pdfa` | PDF/A-2b via Ghostscript |
+| `pdfa-1` | PDF/A-1b via Ghostscript |
+| `pdfa-2` | PDF/A-2b via Ghostscript (same as `pdfa`) |
+| `pdfa-3` | PDF/A-3b via Ghostscript |
+| `pdf` | Standard PDF, no PDF/A conversion |
+| `none` | No output file (useful with `--sidecar`) |
+
+### Non-embedded fonts and PDF/A
+
+:::{versionadded} 17.8.0
+OCRmyPDF now refuses to corrupt non-embedded CID text layers during PDF/A
+conversion.
+:::
+
+PDF/A requires every font to be embedded. If your input already has a text
+layer that uses *non-embedded* CID fonts — most commonly a CJK
+(Chinese-Japanese-Korean) OCR layer
+produced by Adobe Acrobat, which relies on the reader's system fonts —
+Ghostscript would have to substitute and re-embed a replacement font to make
+the file PDF/A. For CID-keyed (CJK) fonts this routinely corrupts the
+character-to-Unicode mapping, so the text silently becomes garbage or stops
+being searchable even though the page still *looks* correct.
+
+Rather than emit corrupted output, OCRmyPDF detects this situation and:
+
+- with `--output-type auto` (the default), produces a regular PDF instead of
+  PDF/A, preserving the existing text layer exactly;
+- with an explicit `--output-type pdfa` (or `pdfa-1`/`pdfa-2`/`pdfa-3`), stops
+  with an error.
+
+This is a Ghostscript limitation that OCRmyPDF cannot repair, because a
+non-embedded font cannot be made PDF/A-compliant without re-embedding it. To
+keep the existing text layer, use `--output-type pdf`. To produce PDF/A anyway,
+re-run OCR with `--force-ocr`, which discards the original text layer and
+rebuilds it with embedded fonts. Text layers whose fonts are *already embedded*
+are converted to PDF/A normally.
+
+### Speculative PDF/A conversion
+
+:::{versionadded} 17.0.0
+:::
+
+When `--output-type auto` is used (the default), OCRmyPDF attempts a
+fast "speculative" PDF/A conversion that avoids Ghostscript when possible:
+
+1. OCRmyPDF adds an sRGB ICC profile and PDF/A XMP metadata using pikepdf
+2. If verapdf is available, it validates the result
+3. If validation passes, Ghostscript is skipped entirely
+4. If validation fails or verapdf is unavailable, falls back to Ghostscript
+
+This fast path avoids some Ghostscript limitations (such as image
+transcoding) and is used whenever it can produce valid PDF/A. When it
+cannot — for example when veraPDF is not installed, or the input needs real
+conversion — `auto` falls back to Ghostscript so that it still produces
+PDF/A by default, matching OCRmyPDF 16 and earlier. If even Ghostscript
+cannot safely produce PDF/A, `auto` outputs a regular PDF instead of failing.
+
+### PDF/A conversion flow
+
+The following diagram illustrates the PDF/A conversion decision tree:
+
+```{mermaid}
+flowchart TD
+    A[Start] --> B{--output-type?}
+    B -->|pdf| C[Output standard PDF]
+    B -->|pdfa/pdfa-N| D[Use Ghostscript]
+    B -->|auto| E[Attempt speculative conversion]
+
+    E --> F["Add sRGB ICC + XMP metadata (pikepdf)"]
+    F --> G{verapdf available?}
+
+    G -->|No| H{Ghostscript available?}
+    G -->|Yes| I[Validate with verapdf]
+
+    I --> J{Validation passed?}
+    J -->|Yes| K[Output PDF/A - Ghostscript skipped]
+    J -->|No| H
+
+    H -->|Yes| D
+    H -->|No| L[Output standard PDF + WARNING]
+
+    D --> M[Ghostscript PDF/A conversion]
+    M --> N[Output PDF/A]
+
+    style K fill:#90EE90
+    style N fill:#90EE90
+    style L fill:#FFB6C1
+```
+
+:::{warning}
+**Breaking change:** If neither Ghostscript nor verapdf is installed,
+`--output-type auto` will produce a standard PDF instead of PDF/A.
+This is a change from previous versions where Ghostscript was required
+and PDF/A was always produced.
+:::
+
+## Return code policy
+
+OCRmyPDF writes all messages to `stderr`. `stdout` is reserved for
+piping output files. `stdin` is reserved for piping input files.
+
+The return codes generated by the OCRmyPDF are considered part of the
+stable user interface. They may be imported from
+`ocrmypdf.exceptions`.
+
+```{eval-rst}
+.. list-table:: Return codes
+    :widths: 5 35 60
+    :header-rows: 1
+
+    *   - Code
+        - Name
+        - Interpretation
+    *   - 0
+        - ``ExitCode.ok``
+        - Everything worked as expected.
+    *   - 1
+        - ``ExitCode.bad_args``
+        - Invalid arguments, exited with an error.
+    *   - 2
+        - ``ExitCode.input_file``
+        - The input file does not seem to be a valid PDF.
+    *   - 3
+        - ``ExitCode.missing_dependency``
+        - An external program required by OCRmyPDF is missing.
+    *   - 4
+        - ``ExitCode.invalid_output_pdf``
+        - An output file was created, but it does not seem to be a valid PDF. The file will be available.
+    *   - 5
+        - ``ExitCode.file_access_error``
+        - The user running OCRmyPDF does not have sufficient permissions to read the input file and write the output file.
+    *   - 6
+        - ``ExitCode.already_done_ocr``
+        - The file already appears to contain text so it may not need OCR. See output message.
+    *   - 7
+        - ``ExitCode.child_process_error``
+        - An error occurred in an external program (child process) and OCRmyPDF cannot continue.
+    *   - 8
+        - ``ExitCode.encrypted_pdf``
+        - The input PDF is encrypted. OCRmyPDF does not read encrypted PDFs. Use another program such as ``qpdf`` to remove encryption.
+    *   - 9
+        - ``ExitCode.invalid_config``
+        - A custom configuration file was forwarded to Tesseract using ``--tesseract-config``, and Tesseract rejected this file.
+    *   - 10
+        - ``ExitCode.pdfa_conversion_failed``
+        - A valid PDF was created, PDF/A conversion failed. The file will be available.
+    *   - 15
+        - ``ExitCode.other_error``
+        - Some other error occurred.
+    *   - 130
+        - ``ExitCode.ctrl_c``
+        - The program was interrupted by pressing Ctrl+C.
+
+```
+
+(tmpdir)=
+## Changing temporary storage location
+
+OCRmyPDF generates many temporary files during processing.
+
+To change where temporary files are stored, change the `TMPDIR`
+environment variable for ocrmypdf's environment. (Python's
+`tempfile.gettempdir()` returns the root directory in which temporary
+files will be stored.) For example, one could redirect `TMPDIR` to a
+large RAM disk to avoid wear on HDD/SSD and potentially improve
+performance.
+
+On Windows, the `TEMP` environment variable is used instead.
+
+## Debugging the intermediate files
+
+OCRmyPDF normally saves its intermediate results to a temporary folder
+and deletes this folder when it exits, whether it succeeded or failed.
+
+If the `--keep-temporary-files` (`-k`) argument is issued on the
+command line, OCRmyPDF will keep the temporary folder and print the location,
+whether it succeeded or failed. An example message is:
+
+```none
+Temporary working files retained at:
+/tmp/ocrmypdf.io.u20wpz07
+```
+
+When OCRmyPDF is launched as a snap, this corresponds to the snap filesystem, for instance:
+
+> /tmp/snap-private-tmp/snap.ocrmypdf/tmp/ocrmypdf.io.u20wpz07
+
+The organization of this folder is an implementation detail and subject
+to change between releases. However the general organization is that
+working files on a per page basis have the page number as a prefix
+(starting with page 1), an infix indicates the processing stage, and a
+suffix indicates the file type. Some important files include:
+
+- `_rasterize.png` - what the input page looks like
+- `_ocr.png` - the file that is sent to Tesseract for OCR; depending
+  on arguments this may differ from the presentation image
+- `_pp_deskew.png` - the image, after deskewing
+- `_pp_clean.png` - the image, after cleaning with unpaper
+- `_ocr_hocr.pdf` - the OCR file; appears as a blank page with invisible
+  text embedded
+- `_ocr_hocr.txt` - the OCR text (not necessarily all text on the page,
+  if the page is mixed format)
+- `fix_docinfo.pdf` - a temporary file created to fix the PDF DocumentInfo
+  data structure
+- `graft_layers.pdf` - the rendered PDF with OCR layers grafted on
+- `pdfa.pdf` - `graft_layers.pdf` after conversion to PDF/A
+- `pdfa.ps` - a PostScript file used by Ghostscript for PDF/A conversion
+- `optimize.pdf` - the PDF generated before optimization
+- `optimize.out.pdf` - the PDF generated by optimization
+- `origin` - the input file
+- `origin.pdf` - the input file or the input image converted to PDF
+- `images/*` - images extracted during the optimization process; here
+  the prefix indicates a PDF object ID not a page number
@@ -1,482 +0,0 @@
-.. SPDX-FileCopyrightText: 2022 James R. Barlow
-.. SPDX-License-Identifier: CC-BY-SA-4.0
-
-=================
-Advanced features
-=================
-
-Control of unpaper
-==================
-
-OCRmyPDF uses ``unpaper`` to provide the implementation of the
-``--clean`` and ``--clean-final`` arguments.
-`unpaper <https://github.com/Flameeyes/unpaper/blob/main/doc/basic-concepts.md>`__
-provides a variety of image processing filters to improve images.
-
-By default, OCRmyPDF uses only ``unpaper`` arguments that were found to
-be safe to use on almost all files without having to inspect every page
-of the file afterwards. This is particularly true when only ``--clean``
-is used, since that instructs OCRmyPDF to only clean the image before
-OCR and not the final image.
-
-However, if you wish to use the more aggressive options in ``unpaper``,
-you may use ``--unpaper-args '...'`` to override the OCRmyPDF's defaults
-and forward other arguments to unpaper. This option will forward
-arguments to ``unpaper`` without any knowledge of what that program
-considers to be valid arguments. The string of arguments must be quoted
-as shown in the examples below. No filename arguments may be included.
-OCRmyPDF will assume it can append input and output filename of
-intermediate images to the ``--unpaper-args`` string.
-
-In this example, we tell ``unpaper`` to expect two pages of text on a
-sheet (image), such as occurs when two facing pages of a book are
-scanned. ``unpaper`` uses this information to deskew each independently
-and clean up the margins of both.
-
-.. code-block:: bash
-
-    ocrmypdf --clean --clean-final --unpaper-args '--layout double' input.pdf output.pdf
-    ocrmypdf --clean --clean-final --unpaper-args '--layout double --no-noisefilter' input.pdf output.pdf
-
-.. warning::
-
-   Some ``unpaper`` features will reposition text within the image.
-   ``--clean-final`` is recommended to avoid this issue.
-
-.. warning::
-
-   Some ``unpaper`` features cause multiple input or output files to be
-   consumed or produced. OCRmyPDF requires ``unpaper`` to consume one
-   file and produce one file; errors will result if this assumption is not
-   met.
-
-.. note::
-
-   ``unpaper`` uses uncompressed PBM/PGM/PPM files for its intermediate
-   files. For large images or documents, it can take a lot of temporary
-   disk space.
-
-Control of OCR options
-======================
-
-OCRmyPDF provides many features to control the behavior of the OCR
-engine, Tesseract.
-
-When OCR is skipped
-------------------
-
-If a page in a PDF seems to have text, by default OCRmyPDF will exit
-without modifying the PDF. This is to ensure that PDFs that were
-previously OCRed or were "born digital" rather than scanned are not
-processed.
-
-If ``--skip-text`` is issued, then no image processing or OCR will be
-performed on pages that already have text. The page will be copied to
-the output. This may be useful for documents that contain both "born
-digital" and scanned content, or to use OCRmyPDF to normalize and
-convert to PDF/A regardless of their contents.
-
-If ``--redo-ocr`` is issued, then a detailed text analysis is performed.
-Text is categorized as either visible or invisible. Invisible text (OCR)
-is stripped out. Then an image of each page is created with visible text
-masked out. The page image is sent for OCR, and any additional text is
-inserted as OCR. If a file contains a mix of text and bitmap images that
-contain text, OCRmyPDF will locate the additional text in images without
-disrupting the existing text. Some PDF OCR solutions render text as
-technically printable or visible in some way, perhaps by drawing it and
-then painting over it. OCRmyPDF cannot distinguish this type of OCR
-text from real text, so it will not be "redone".
-
-If ``--force-ocr`` is issued, then all pages will be rasterized to
-images, discarding any hidden OCR text, rasterizing any printable
-text, and flattening form fields or interactive objects into their visual
-representation. This is useful for redoing OCR, for fixing OCR text
-with a damaged character map (text is selectable but not searchable),
-and destroying redacted information.
-
-Time and image size limits
--------------------------
-
-By default, OCRmyPDF permits tesseract to run for three minutes (180
-seconds) per page. This is usually more than enough time to find all
-text on a reasonably sized page with modern hardware.
-
-If a page is skipped, it will be inserted without OCR. If preprocessing
-was requested, the preprocessed image layer will be inserted.
-
-If you want to adjust the amount of time spent on OCR, change
-``--tesseract-timeout``. You can also automatically skip images that
-exceed a certain number of megapixels with ``--skip-big``. (A 300 DPI,
-8.5×11" page image is 8.4 megapixels.)
-
-.. code-block:: bash
-
-    # Allow 300 seconds for OCR; skip any page larger than 50 megapixels
-    ocrmypdf --tesseract-timeout 300 --skip-big 50 bigfile.pdf output.pdf
-
-OCR for huge images
-------------------
-
-Tesseract has internal limits on the size
-of images it will process. By default,
-``--tesseract-downsample-large-images`` is enabled, and OCRmyPDF will
-downsample images to fit Tesseract limits. (The limits are usually encountered
-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.) This feature can disabled
-using ``--no-tesseract-downsample-large-images``.
-
-``--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 (32767 pixels on either dimension).
-
-You will also need to set ``--tesseract-timeout`` high enough to allow
-for processing.
-
-Only the image sent for OCR is downsampled. The original image is
-preserved.
-
-.. code-block:: bash
-
-    # Allow 600 seconds for OCR on huge images
-    ocrmypdf --tesseract-timeout 600 \
-        --tesseract-downsample-large-images \
-        bigfile.pdf output.pdf
-
-    # Downsample images above 5000 pixels on the longest dimension to
-    # 5000 pixels
-    ocrmypdf --tesseract-timeout 120 \
-        --tesseract-downsample-large-images \
-        --tesseract-downsample-above 5000 \
-        bigfile.pdf output_downsampled_ocr.pdf
-
-
-Overriding default tesseract
----------------------------
-
-OCRmyPDF checks the system ``PATH`` for the ``tesseract`` binary.
-
-Some relevant environment variables that influence Tesseract's behavior
-include:
-
-.. envvar:: TESSDATA_PREFIX
-
-   Overrides the path to Tesseract's data files. This can allow
-   simultaneous installation of the "best" and "fast" training data
-   sets. OCRmyPDF does not manage this environment variable.
-
-.. envvar:: OMP_THREAD_LIMIT
-
-   Controls the number of threads Tesseract will use. OCRmyPDF will
-   manage this environment variable if it is not already set.
-
-For example, if you have a development build of Tesseract don't wish to
-use the system installation, you can launch OCRmyPDF as follows:
-
-.. code-block:: bash
-
-    env \
-        PATH=/home/user/src/tesseract/api:$PATH \
-        TESSDATA_PREFIX=/home/user/src/tesseract \
-        ocrmypdf input.pdf output.pdf
-
-In this example ``TESSDATA_PREFIX`` is required to redirect Tesseract to
-an alternate folder for its "tessdata" files.
-
-Overriding other support programs
---------------------------------
-
-In addition to tesseract, OCRmyPDF uses the following external binaries:
-
-  ``gs`` (Ghostscript)
-  ``unpaper``
-  ``pngquant``
-  ``jbig2``
-
-In each case OCRmyPDF will search the ``PATH`` environment variable to
-locate the binaries. By modifying the ``PATH`` environment variable, you
-can override the binaries that OCRmyPDF uses.
-
-Changing Tesseract configuration variables
------------------------------------------
-
-You can override Tesseract's default `control
-parameters <https://tesseract-ocr.github.io/tessdoc/tess3/ControlParams.html>`__
-with a configuration file.
-
-As an example, this configuration will disable Tesseract's dictionary
-for current language. Normally the dictionary is helpful for
-interpolating words that are unclear, but it may interfere with OCR if
-the document does not contain many words (for example, a list of part
-numbers).
-
-Create a file named "no-dict.cfg" with these contents:
-
-::
-
-    load_system_dawg 0
-    language_model_penalty_non_dict_word 0
-    language_model_penalty_non_freq_dict_word 0
-
-then run ocrmypdf as follows (along with any other desired arguments):
-
-.. code-block:: bash
-
-    ocrmypdf --tesseract-config no-dict.cfg input.pdf output.pdf
-
-.. warning::
-
-   Some combinations of control parameters will break Tesseract or break
-   assumptions that OCRmyPDF makes about Tesseract's output.
-
-Changing page segmentation mode
-------------------------------
-
-The directive ``--tesseract-pagesegmode Nmode`` forwards the desired page segmentation
-mode to Tesseract OCR. The default is 3.
-
-Page segmentation can improve OCR results when you know that a PDF ought to be
-analyzed a particular way, such as PDFs whose pages contain only a single line of 
-text. For the vast majority of users, changing the page segmentation mode will only
-make things worse.
-
-As of June 2024, the Tesseract page segmentation modes are:
-
-+-----+----------------------------------------------------------------------------------+
-| ID  | Description                                                                      |
-+=====+==================================================================================+
-|  0  | Orientation and script detection (OSD) only.                                      |
-+-----+----------------------------------------------------------------------------------+
-|  1  | Automatic page segmentation with OSD.                                             |
-+-----+----------------------------------------------------------------------------------+
-|  2  | Automatic page segmentation, but no OSD, or OCR. (not implemented)               |
-+-----+----------------------------------------------------------------------------------+
-|  3  | Fully automatic page segmentation, but no OSD. (Default)                         |
-+-----+----------------------------------------------------------------------------------+
-|  4  | Assume a single column of text of variable sizes.                                 |
-+-----+----------------------------------------------------------------------------------+
-|  5  | Assume a single uniform block of vertically aligned text.                         |
-+-----+----------------------------------------------------------------------------------+
-|  6  | Assume a single uniform block of text.                                            |
-+-----+----------------------------------------------------------------------------------+
-|  7  | Treat the image as a single text line.                                            |
-+-----+----------------------------------------------------------------------------------+
-|  8  | Treat the image as a single word.                                                 |
-+-----+----------------------------------------------------------------------------------+
-|  9  | Treat the image as a single word in a circle.                                     |
-+-----+----------------------------------------------------------------------------------+
-| 10  | Treat the image as a single character.                                            |
-+-----+----------------------------------------------------------------------------------+
-| 11  | Sparse text. Find as much text as possible in no particular order.                |
-+-----+----------------------------------------------------------------------------------+
-| 12  | Sparse text with OSD.                                                            |
-+-----+----------------------------------------------------------------------------------+
-| 13  | Raw line. Treat the image as a single text line, bypassing hacks that are        |
-|     | Tesseract-specific.                                                               |
-+-----+----------------------------------------------------------------------------------+
-
-Modes 0, 1, 2, and 12 (all of those that enable orientation and script detection) 
-are not compatible with OCRmyPDF, which performs OSD in a separate step from OCR.
-Their use may interfere with ``--rotate-pages`` and other features.
-
-It is currently not possible to use advanced Tesseract OCR features, such as creating
-OCR information, when using Tesseract through OCRmyPDF.
-
-Changing the PDF renderer
-=========================
-
-rasterizing
-  Converting a PDF to an image for display.
-
-rendering
-  Creating a new PDF from other data (such as an existing PDF).
-
-OCRmyPDF has these PDF renderers: ``sandwich`` and ``hocr``. The
-renderer may be selected using ``--pdf-renderer``. The default is
-``auto`` which lets OCRmyPDF select the renderer to use. Currently,
-``auto`` always selects ``hocr``.
-
-The ``hocr`` renderer
---------------------
-
-.. versionchanged:: 16.0.0
-
-In both renderers, a text-only layer is rendered and sandwiched (overlaid)
-on to either the original PDF page, or newly rasterized version of the
-original PDF page (when ``--force-ocr`` is used). In this way, loss
-of PDF information is generally avoided. (You may need to disable PDF/A
-conversion and optimization to eliminate all lossy transformations.)
-
-The current approach used by the new hOCR renderer is a re-implementation
-of Tesseract's PDF renderer, using the same Glyphless font and general
-ideas, but fixing many technical issues that impeded it. The new hocr
-provides better text placement accuracy, avoids issues with word
-segmentation, and provides better positioning of skewed text.
-
-Using the experimental API, it is also possible to edit the OCR output
-from Tesseract, using any tool that is capable of editing hOCR files.
-
-Older versions of this renderer did not support non-Latin languages, but
-it is now universal.
-
-The ``sandwich`` renderer
-------------------------
-
-The ``sandwich`` renderer uses Tesseract's text-only PDF feature,
-which produces a PDF page that lays out the OCR in invisible text.
-
-Currently some problematic PDF viewers like Mozilla PDF.js and macOS
-Preview have problems with segmenting its text output, and
-mightrunseveralwordstogether. It also does not implement right to left
-fonts (Arabic, Hebrew, Persian). The output of this renderer cannot
-be edited. The sandwich renderer is retained for testing.
-
-When image preprocessing features like ``--deskew`` are used, the
-original PDF will be rendered as a full page and the OCR layer will be
-placed on top.
-
-Rendering and rasterizing options
-=================================
-
-.. versionadded:: 14.3.0
-
-The ``--continue-on-soft-render-error`` option allows OCRmyPDF to
-proceed if a page cannot be rasterized/rendered. This is useful if you are
-trying to get the best possible OCR from a PDF that is not well-formed,
-and you are willing to accept some pages that may not visually match the
-input, and that may not OCR well.
-
-Color conversion strategy
-=========================
-
-.. versionadded:: 15.0.0
-
-OCRmyPDF uses Ghostscript to convert PDF to PDF/A. In some cases, this
-conversion requires color conversion. The default strategy is to convert
-using the ``LeaveColorUnchanged`` strategy, which preserves the original
-color space wherever possible (some rare color spaces might still be
-converted).
-
-Usually document scanners produce PDFs in the sRGB color space, and do
-not need to be converted, so the default strategy is appropriate.
-
-Suppose that you have a document that was prepared for professional
-printing in a Separation or CMYK color space, and text was converted to
-curves. In this case, you may want to use a different color conversion
-strategy. The ``--color-conversion-strategy`` option allows you to select a
-different strategy, such as ``RGB``.
-
-Return code policy
-==================
-
-OCRmyPDF writes all messages to ``stderr``. ``stdout`` is reserved for
-piping output files. ``stdin`` is reserved for piping input files.
-
-The return codes generated by the OCRmyPDF are considered part of the
-stable user interface. They may be imported from
-``ocrmypdf.exceptions``.
-
-.. list-table:: Return codes
-    :widths: 5 35 60
-    :header-rows: 1
-
-    *	- Code
-        - Name
-        - Interpretation
-    *	- 0
-        - ``ExitCode.ok``
-        - Everything worked as expected.
-    *	- 1
-        - ``ExitCode.bad_args``
-        - Invalid arguments, exited with an error.
-    *	- 2
-        - ``ExitCode.input_file``
-        - The input file does not seem to be a valid PDF.
-    *	- 3
-        - ``ExitCode.missing_dependency``
-        - An external program required by OCRmyPDF is missing.
-    *	- 4
-        - ``ExitCode.invalid_output_pdf``
-        - An output file was created, but it does not seem to be a valid PDF. The file will be available.
-    *	- 5
-        - ``ExitCode.file_access_error``
-        - The user running OCRmyPDF does not have sufficient permissions to read the input file and write the output file.
-    *	- 6
-        - ``ExitCode.already_done_ocr``
-        - The file already appears to contain text so it may not need OCR. See output message.
-    *	- 7
-        - ``ExitCode.child_process_error``
-        - An error occurred in an external program (child process) and OCRmyPDF cannot continue.
-    *	- 8
-        - ``ExitCode.encrypted_pdf``
-        - The input PDF is encrypted. OCRmyPDF does not read encrypted PDFs. Use another program such as ``qpdf`` to remove encryption.
-    *	- 9
-        - ``ExitCode.invalid_config``
-        - A custom configuration file was forwarded to Tesseract using ``--tesseract-config``, and Tesseract rejected this file.
-    *   - 10
-        - ``ExitCode.pdfa_conversion_failed``
-        - A valid PDF was created, PDF/A conversion failed. The file will be available.
-    *	- 15
-        - ``ExitCode.other_error``
-        - Some other error occurred.
-    *	- 130
-        - ``ExitCode.ctrl_c``
-        - The program was interrupted by pressing Ctrl+C.
-
-
-.. _tmpdir:
-
-Changing temporary storage location
-===================================
-
-OCRmyPDF generates many temporary files during processing.
-
-To change where temporary files are stored, change the ``TMPDIR``
-environment variable for ocrmypdf's environment. (Python's
-``tempfile.gettempdir()`` returns the root directory in which temporary
-files will be stored.) For example, one could redirect ``TMPDIR`` to a
-large RAM disk to avoid wear on HDD/SSD and potentially improve
-performance.
-
-On Windows, the ``TEMP`` environment variable is used instead.
-
-Debugging the intermediate files
-================================
-
-OCRmyPDF normally saves its intermediate results to a temporary folder
-and deletes this folder when it exits, whether it succeeded or failed.
-
-If the ``--keep-temporary-files`` (``-k```) argument is issued on the
-command line, OCRmyPDF will keep the temporary folder and print the location,
-whether it succeeded or failed. An example message is:
-
-.. code-block:: none
-
-    Temporary working files retained at:
-    /tmp/ocrmypdf.io.u20wpz07
-
-The organization of this folder is an implementation detail and subject
-to change between releases. However the general organization is that
-working files on a per page basis have the page number as a prefix
-(starting with page 1), an infix indicates the processing stage, and a
-suffix indicates the file type. Some important files include:
-
-  ``_rasterize.png`` - what the input page looks like
-  ``_ocr.png`` - the file that is sent to Tesseract for OCR; depending
-   on arguments this may differ from the presentation image
-  ``_pp_deskew.png`` - the image, after deskewing
-  ``_pp_clean.png`` - the image, after cleaning with unpaper
-  ``_ocr_tess.pdf`` - the OCR file; appears as a blank page with invisible
-   text embedded
-  ``_ocr_tess.txt`` - the OCR text (not necessarily all text on the page,
-   if the page is mixed format)
-  ``fix_docinfo.pdf`` - a temporary file created to fix the PDF DocumentInfo
-   data structure
-  ``graft_layers.pdf`` - the rendered PDF with OCR layers grafted on
-  ``pdfa.pdf`` - ``graft_layers.pdf`` after conversion to PDF/A
-  ``pdfa.ps`` - a PostScript file used by Ghostscript for PDF/A conversion
-  ``optimize.pdf`` - the PDF generated before optimization
-  ``optimize.out.pdf`` - the PDF generated by optimization
-  ``origin`` - the input file
-  ``origin.pdf`` - the input file or the input image converted to PDF
-  ``images/*`` - images extracted during the optimization process; here
-   the prefix indicates a PDF object ID not a page number
@@ -0,0 +1,179 @@
+% SPDX-FileCopyrightText: 2022 James R. Barlow
+% SPDX-License-Identifier: CC-BY-SA-4.0
+
+# Using the OCRmyPDF API
+
+OCRmyPDF originated as a command line program and continues to have this
+legacy, but parts of it can be imported and used in other Python
+applications.
+
+Some applications may want to consider running ocrmypdf from a
+subprocess call anyway, as this provides isolation of its activities.
+
+## Example
+
+OCRmyPDF provides one high-level function to run its main engine from an
+application.
+
+```{versionchanged} 17.0
+The {func}`ocrmypdf.ocr` function now accepts an {class}`~ocrmypdf.OcrOptions`
+object as its first argument, providing a cleaner API with full type hints
+and validation. The previous positional argument style remains supported.
+```
+
+### Modern API (recommended)
+
+The recommended way to call {func}`ocrmypdf.ocr` is to construct an
+{class}`~ocrmypdf.OcrOptions` object with all settings, then pass it
+as the sole argument:
+
+```python
+import ocrmypdf
+from ocrmypdf import OcrOptions
+
+if __name__ == '__main__':  # To ensure correct behavior on Windows and macOS
+    options = OcrOptions(
+        input_file='input.pdf',
+        output_file='output.pdf',
+        deskew=True,
+        languages=['eng'],
+    )
+    ocrmypdf.ocr(options)
+```
+
+{class}`~ocrmypdf.OcrOptions` is a Pydantic model that provides:
+
+- Full type hints and IDE autocompletion
+- Validation of option values at construction time
+- Clear documentation of all available options
+
+```{versionadded} 17.0
+The {class}`~ocrmypdf.OcrOptions` class is now exported from the top-level
+`ocrmypdf` module.
+```
+
+### Legacy API
+
+For compatibility with OCRmyPDF < v17, the traditional calling style
+with positional arguments is still fully supported:
+
+```python
+import ocrmypdf
+
+if __name__ == '__main__':  # To ensure correct behavior on Windows and macOS
+    ocrmypdf.ocr('input.pdf', 'output.pdf', deskew=True)
+```
+
+With this style, all of the command line arguments are available
+and may be passed as equivalent keywords.
+
+A few differences are that `verbose` and `quiet` are not available.
+Instead, output should be managed by configuring logging.
+
+### Parent process requirements
+
+The {func}`ocrmypdf.ocr` function runs OCRmyPDF similar to command line
+execution. To do this, it will:
+
+- create worker processes or threads
+- manage the signal flags of its worker processes
+- execute other subprocesses (forking and executing other programs)
+
+The Python process that calls {func}`ocrmypdf.ocr()` must be sufficiently
+privileged to perform these actions.
+
+There currently is no option to manage how jobs are scheduled other
+than the argument `jobs=` which will limit the number of worker
+processes.
+
+Creating a child process to call {func}`ocrmypdf.ocr()` is suggested. That
+way your application will survive and remain interactive even if
+OCRmyPDF fails for any reason. For example:
+
+```python
+from multiprocessing import Process
+import ocrmypdf
+from ocrmypdf import OcrOptions
+
+
+def ocrmypdf_process():
+    options = OcrOptions(input_file='input.pdf', output_file='output.pdf')
+    ocrmypdf.ocr(options)
+
+
+def call_ocrmypdf_from_my_app():
+    p = Process(target=ocrmypdf_process)
+    p.start()
+    p.join()
+```
+
+Programs that call {func}`ocrmypdf.ocr()` should also install a SIGBUS signal
+handler (except on Windows), to raise an exception if access to a memory
+mapped file fails. OCRmyPDF may use memory mapping.
+
+{func}`ocrmypdf.ocr()` will take a threading lock to prevent multiple runs of itself
+in the same Python interpreter process. This is not thread-safe, because of how
+OCRmyPDF's plugins and Python's library import system work. If you need to parallelize
+OCRmyPDF, use processes.
+
+:::{warning}
+On Windows and macOS, the script that calls {func}`ocrmypdf.ocr()` must be
+protected by an "ifmain" guard (`if __name__ == '__main__'`). If you do
+not take at least one of these steps, process semantics will prevent
+OCRmyPDF from working correctly.
+:::
+
+### Logging
+
+OCRmyPDF will log under loggers named `ocrmypdf`. In addition, it
+imports `pdfminer` and `PIL`, both of which post log messages under
+those logging namespaces.
+
+You can configure the logging as desired for your application or call
+{func}`ocrmypdf.configure_logging` to configure logging the same way
+OCRmyPDF itself does. The command line parameters such as `--quiet`
+and `--verbose` have no equivalents in the API; you must use the
+provided configuration function or do configuration in a way that suits
+your use case.
+
+### Progress monitoring
+
+OCRmyPDF uses the `rich` package to implement its progress bars.
+{func}`ocrmypdf.configure_logging` will set up logging output to
+`sys.stderr` in a way that is compatible with the display of the
+progress bar. Use `ocrmypdf.ocr(...progress_bar=False)` to disable
+the progress bar.
+
+### Standard output
+
+OCRmyPDF is strict about not writing to standard output so that
+users can safely use it in a pipeline and produce a valid output
+file. A caller application will have to ensure it does not write to
+standard output either, if it wants to be compatible with this
+behavior and support piping to a file. Another benefit of running
+OCRmyPDF in a child process, as recommended above, is that it will
+not interfere with the parent process's standard output.
+
+### Exceptions
+
+OCRmyPDF may throw standard Python exceptions, `ocrmypdf.exceptions.*`
+exceptions, some exceptions related to multiprocessing, and
+{exc}`KeyboardInterrupt`. The parent process should provide an exception
+handler. OCRmyPDF will clean up its temporary files and worker processes
+automatically when an exception occurs.
+
+When OCRmyPDF succeeds conditionally, it returns an integer exit code.
+
+### Plugin Development Changes
+
+```{versionchanged} 16.13
+Plugin hooks now receive {class}`~ocrmypdf.OcrOptions` objects instead of
+`argparse.Namespace`.
+```
+
+- {class}`~ocrmypdf.OcrOptions` provides the same attribute access as `Namespace` (duck-typing compatible)
+- Plugin developers should update type hints: `from ocrmypdf import OcrOptions`
+- Built-in plugins no longer modify options in-place for better immutability
+
+Most existing plugins will continue working without modification due to the
+duck-typing compatibility between {class}`~ocrmypdf.OcrOptions` and `Namespace`.
@@ -1,128 +0,0 @@
-.. SPDX-FileCopyrightText: 2022 James R. Barlow
-..
-.. SPDX-License-Identifier: CC-BY-SA-4.0
-
-======================
-Using the OCRmyPDF API
-======================
-
-OCRmyPDF originated as a command line program and continues to have this
-legacy, but parts of it can be imported and used in other Python
-applications.
-
-Some applications may want to consider running ocrmypdf from a
-subprocess call anyway, as this provides isolation of its activities.
-
-Example
-=======
-
-OCRmyPDF provides one high-level function to run its main engine from an
-application. The parameters are symmetric to the command line arguments
-and largely have the same functions.
-
-.. code-block:: python
-
-    import ocrmypdf
-
-    if __name__ == '__main__':  # To ensure correct behavior on Windows and macOS
-        ocrmypdf.ocr('input.pdf', 'output.pdf', deskew=True)
-
-With some exceptions, all of the command line arguments are available
-and may be passed as equivalent keywords.
-
-A few differences are that ``verbose`` and ``quiet`` are not available.
-Instead, output should be managed by configuring logging.
-
-Parent process requirements
---------------------------
-
-The :func:`ocrmypdf.ocr` function runs OCRmyPDF similar to command line
-execution. To do this, it will:
-
- create worker processes or threads
- manage the signal flags of its worker processes
- execute other subprocesses (forking and executing other programs)
-
-The Python process that calls :func:`ocrmypdf.ocr()` must be sufficiently
-privileged to perform these actions.
-
-There currently is no option to manage how jobs are scheduled other
-than the argument ``jobs=`` which will limit the number of worker
-processes.
-
-Creating a child process to call :func:`ocrmypdf.ocr()` is suggested. That
-way your application will survive and remain interactive even if
-OCRmyPDF fails for any reason. For example:
-
-.. code-block:: python
-
-    from multiprocessing import Process
-
-    def ocrmypdf_process():
-        ocrmypdf.ocr('input.pdf', 'output.pdf')
-
-    def call_ocrmypdf_from_my_app():
-        p = Process(target=ocrmypdf_process)
-        p.start()
-        p.join()
-
-Programs that call :func:`ocrmypdf.ocr()` should also install a SIGBUS signal
-handler (except on Windows), to raise an exception if access to a memory
-mapped file fails. OCRmyPDF may use memory mapping.
-
-:func:`ocrmypdf.ocr()` will take a threading lock to prevent multiple runs of itself
-in the same Python interpreter process. This is not thread-safe, because of how
-OCRmyPDF's plugins and Python's library import system work. If you need to parallelize
-OCRmyPDF, use processes.
-
-.. warning::
-
-    On Windows and macOS, the script that calls :func:`ocrmypdf.ocr()` must be
-    protected by an "ifmain" guard (``if __name__ == '__main__'``). If you do
-    not take at least one of these steps, process semantics will prevent
-    OCRmyPDF from working correctly.
-
-Logging
-------
-
-OCRmyPDF will log under loggers named ``ocrmypdf``. In addition, it
-imports ``pdfminer`` and ``PIL``, both of which post log messages under
-those logging namespaces.
-
-You can configure the logging as desired for your application or call
-:func:`ocrmypdf.configure_logging` to configure logging the same way
-OCRmyPDF itself does. The command line parameters such as ``--quiet``
-and ``--verbose`` have no equivalents in the API; you must use the
-provided configuration function or do configuration in a way that suits
-your use case.
-
-Progress monitoring
-------------------
-
-OCRmyPDF uses the ``rich`` package to implement its progress bars.
-:func:`ocrmypdf.configure_logging` will set up logging output to
-``sys.stderr`` in a way that is compatible with the display of the
-progress bar. Use ``ocrmypdf.ocr(...progress_bar=False)`` to disable
-the progress bar.
-
-Standard output
---------------
-
-OCRmyPDF is strict about not writing to standard output so that
-users can safely use it in a pipeline and produce a valid output
-file. A caller application will have to ensure it does not write to
-standard output either, if it wants to be compatible with this
-behavior and support piping to a file. Another benefit of running
-OCRmyPDF in a child process, as recommended above, is that it will
-not interfere with the parent process's standard output.
-
-Exceptions
----------
-
-OCRmyPDF may throw standard Python exceptions, ``ocrmypdf.exceptions.*``
-exceptions, some exceptions related to multiprocessing, and
-:exc:`KeyboardInterrupt`. The parent process should provide an exception
-handler. OCRmyPDF will clean up its temporary files and worker processes
-automatically when an exception occurs.
-
-When OCRmyPDF succeeds conditionally, it returns an integer exit code.
@@ -0,0 +1,64 @@
+% SPDX-FileCopyrightText: 2022 James R. Barlow
+% SPDX-License-Identifier: CC-BY-SA-4.0
+
+# API reference
+
+This page summarizes the rest of the public API. Generally speaking this
+should be mainly of interest to plugin developers.
+
+## ocrmypdf.api
+
+```{eval-rst}
+.. automodule:: ocrmypdf.api
+    :members:
+```
+
+## ocrmypdf._options
+
+```{eval-rst}
+.. automodule:: ocrmypdf._options
+    :members: OcrOptions
+```
+
+## ocrmypdf.exceptions
+
+```{eval-rst}
+.. automodule:: ocrmypdf.exceptions
+    :members:
+    :undoc-members:
+```
+
+## ocrmypdf.helpers
+
+```{eval-rst}
+.. automodule:: ocrmypdf.helpers
+    :members:
+```
+
+## ocrmypdf.hocrtransform
+
+```{eval-rst}
+.. automodule:: ocrmypdf.hocrtransform
+    :members:
+```
+
+## ocrmypdf.pdfa
+
+```{eval-rst}
+.. automodule:: ocrmypdf.pdfa
+    :members:
+```
+
+## ocrmypdf.quality
+
+```{eval-rst}
+.. automodule:: ocrmypdf.quality
+    :members:
+```
+
+## ocrmypdf.subprocess
+
+```{eval-rst}
+.. automodule:: ocrmypdf.subprocess
+    :members:
+```
@@ -1,71 +0,0 @@
-.. SPDX-FileCopyrightText: 2022 James R. Barlow
-..
-.. SPDX-License-Identifier: CC-BY-SA-4.0
-
-=============
-API reference
-=============
-
-This page summarizes the rest of the public API. Generally speaking this
-should be mainly of interest to plugin developers.
-
-ocrmypdf
-========
-
-.. autoclass:: ocrmypdf.PageContext
-    :members:
-
-.. autoclass:: ocrmypdf.PdfContext
-    :members:
-
-.. autoclass:: ocrmypdf.Verbosity
-    :members:
-    :undoc-members:
-
-.. autofunction:: ocrmypdf.configure_logging
-
-.. autofunction:: ocrmypdf.ocr
-
-.. autofunction:: ocrmypdf.pdf_to_hocr
-
-.. autofunction:: ocrmypdf.hocr_to_ocr_pdf
-
-ocrmypdf.exceptions
-===================
-
-.. automodule:: ocrmypdf.exceptions
-    :members:
-    :undoc-members:
-
-ocrmypdf.helpers
-================
-
-.. automodule:: ocrmypdf.helpers
-    :members:
-    :noindex: deprecated
-
-    .. autodecorator:: deprecated
-
-ocrmypdf.hocrtransform
-======================
-
-.. automodule:: ocrmypdf.hocrtransform
-    :members:
-
-ocrmypdf.pdfa
-=============
-
-.. automodule:: ocrmypdf.pdfa
-    :members:
-
-ocrmypdf.quality
-================
-
-.. automodule:: ocrmypdf.quality
-    :members:
-
-ocrmypdf.subprocess
-===================
-
-.. automodule:: ocrmypdf.subprocess
-    :members:
@@ -0,0 +1,264 @@
+% SPDX-FileCopyrightText: 2022 James R. Barlow
+% SPDX-License-Identifier: CC-BY-SA-4.0
+
+Batch processing
+================
+
+This article provides information about running OCRmyPDF on multiple
+files or configuring it as a service triggered by file system events.
+
+Batch jobs
+----------
+
+Consider using the excellent [GNU
+Parallel](https://www.gnu.org/software/parallel/) to apply OCRmyPDF to
+multiple files at once.
+
+Both `parallel` and `ocrmypdf` will try to use all available processors.
+To maximize parallelism without overloading your system with processes,
+consider using `parallel -j 2` to limit parallel to running two jobs at
+once.
+
+This command will run `ocrmypdf` on all files named `*.pdf` in the
+current directory and write them to the previously created `output/`
+folder. It will not search subdirectories.
+
+The `--tag` argument tells parallel to print the filename as a prefix
+whenever a message is printed, so that one can trace any errors to the
+file that produced them.
+
+:::{code} bash
+parallel --tag -j 2 ocrmypdf '{}' 'output/{}' ::: *.pdf
+:::
+
+OCRmyPDF automatically repairs PDFs before parsing and gathering
+information from them.
+
+Directory trees
+---------------
+
+This will walk through a directory tree and run OCR on all files in
+place, and printing each filename in between runs:
+
+:::{code} bash
+find . -name '*.pdf' -printf '%p\n' -exec ocrmypdf '{}' '{}' \;
+:::
+
+This only runs one `ocrmypdf` process at a time. This variation uses
+`find` to create a directory list and `parallel` to parallelize runs of
+`ocrmypdf`, again updating files in place.
+
+:::{code} bash
+find . -name '*.pdf' | parallel --tag -j 2 ocrmypdf '{}' '{}'
+:::
+
+In a Windows batch file, use
+
+:::{code} bat
+for /r %%f in (*.pdf) do ocrmypdf %%f %%f
+:::
+
+With a Docker container, you will need to stream through standard input
+and output:
+
+:::{code} bash
+find . -name '*.pdf' -print0 | xargs -0 | while read pdf; do
+    pdfout=$(mktemp)
+    docker run --rm -i jbarlow83/ocrmypdf - - <$pdf >$pdfout && cp $pdfout $pdf
+done
+:::
+
+### Sample script
+
+This user contributed script also provides an example of batch
+processing.
+
+:::{literalinclude} ../misc/batch.py
+---
+caption: misc/batch.py
+---
+:::
+
+### Synology DiskStations
+
+Synology DiskStations (Network Attached Storage devices) can run the
+Docker image of OCRmyPDF if the Synology [Docker
+package](https://www.synology.com/en-global/dsm/packages/Docker) is
+installed. Attached is a script to address particular quirks of using
+OCRmyPDF on one of these devices.
+
+At the time this script was written, it only worked for x86-based
+Synology products. It is not known if it will work on ARM-based Synology
+products. Further adjustments might be needed to deal with the
+Synology\'s relatively limited CPU and RAM.
+
+:::{literalinclude} ../misc/synology.py
+---
+caption: misc/synology.py - Sample script for Synology DiskStations
+---
+:::
+
+### Huge batch jobs
+
+If you have thousands of files to work with, contact the author.
+Consulting work related to OCRmyPDF helps fund this open source project
+and all inquiries are appreciated.
+
+Hot (watched) folders
+---------------------
+
+### Watched folders with watcher.py
+
+OCRmyPDF has a folder watcher called watcher.py, which is currently
+included in source distributions but not part of the main program. It
+may be used natively or may run in a Docker container. Native instances
+tend to give better performance. watcher.py works on all platforms.
+
+Users may need to customize the script to meet their requirements.
+
+:::{code} bash
+# Using uv (recommended)
+uv sync --extra watcher
+
+# Or using pip
+pip3 install ocrmypdf[watcher]
+
+env OCR_INPUT_DIRECTORY=/mnt/input-pdfs \
+    OCR_OUTPUT_DIRECTORY=/mnt/output-pdfs \
+    OCR_OUTPUT_DIRECTORY_YEAR_MONTH=1 \
+    python3 watcher.py
+:::
+
+:::{list-table} watcher.py environment variables
+---
+header-rows: 1
+---
+
+* - Environment variable
+  - Description
+* - OCR\_INPUT\_DIRECTORY
+  - Set input directory to monitor (recursive)
+* - OCR\_OUTPUT\_DIRECTORY
+  - Set output directory (should not be under input)
+* - OCR\_ARCHIVE\_DIRECTORY
+  - Set archive directory for processed originals (should not be under input, requires `OCR_ON_SUCCESS_ARCHIVE` to be set)
+* - OCR\_ON\_SUCCESS\_DELETE
+  - This will 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, "optimize": "3"}'`.
+* - OCR\_POLL\_NEW\_FILE\_SECONDS
+  - Polling interval
+* - OCR\_LOGLEVEL
+  - Level of log messages t
+:::
+
+One could configure a networked scanner or scanning computer to drop
+files in the watched folder.
+
+### Watched folders with Docker
+
+The watcher service is included in the OCRmyPDF Docker image. To run it:
+
+:::{code} bash
+docker run \
+    --volume <path to files to convert>:/input \
+    --volume <path to store results>:/output \
+    --volume <path to store processed originals>:/processed \
+    --env OCR_OUTPUT_DIRECTORY_YEAR_MONTH=1 \
+    --env OCR_ON_SUCCESS_ARCHIVE=1 \
+    --env OCR_DESKEW=1 \
+    --env PYTHONUNBUFFERED=1 \
+    --interactive --tty --entrypoint python3 \
+    jbarlow83/ocrmypdf \
+    /app/watcher.py
+:::
+
+:::{note}
+The image runs as the non-root `app` user (uid 1000) by default, so it
+may not be able to write to the `/output` and `/processed` volumes unless
+you add a `--user` argument. The correct value depends on whether you use
+rootful Docker, rootless Docker, or Podman -- see
+{ref}`Bind-mounted volumes <docker-volumes>` for details.
+:::
+
+This service will watch for a file that matches `/input/\*.pdf`, convert
+it to a OCRed PDF in `/output/`, and move the processed original to
+`/processed`. The parameters to this image are:
+
+:::{list-table} Watcher Docker Parameters
+:header-rows: 1
+
+* - Parameter
+  - Description
+* - `--volume <path to files to convert>:/input`
+  - Files placed in this location will be OCRed
+* - `--volume <path to store results>:/output`
+  - This is where OCRed files will be stored
+* - `--volume <path to store processed originals>:/processed`
+  - Archive processed originals here
+* - `--env OCR_OUTPUT_DIRECTORY_YEAR_MONTH=1`
+  - Define environment variable `OCR_OUTPUT_DIRECTORY_YEAR_MONTH=1` to place files in the output in `{output}/{year}/{month}/{filename}`
+* - `--env OCR_ON_SUCCESS_ARCHIVE=1`
+  - Define environment variable `OCR_ON_SUCCESS_ARCHIVE` to move processed originals
+* - `--env OCR_DESKEW=1`
+  - Define environment variable `OCR_DESKEW` to apply deskew to crooked input PDFs
+* - `--env PYTHONBUFFERED=1`
+  - This will force `STDOUT` to be unbuffered and allow you to see messages in docker logs
+* - `--env OCR_LOGLEVEL='DEBUG'`
+  - Level of log messages
+* - `--env OCR_JSON_SETTINGS={"language":"deu+eng", "rotate_pages": true}`
+  - A JSON string specifying any other arguments for `ocrmypdf.ocr`
+:::
+
+This service relies on polling to check for changes to the filesystem.
+It may not be suitable for some environments, such as filesystems shared
+on a slow network.
+
+A configuration manager such as Docker Compose could be used to ensure
+that the service is always available.
+
+:::{literalinclude} ../misc/docker-compose.example.yml
+---
+caption: misc/docker-compose.example.yml
+---
+:::
+
+### Caveats
+
+-   `watchmedo` may not work properly on a networked file system,
+    depending on the capabilities of the file system client and server.
+-   This simple recipe does not filter for the type of file system
+    event, so file copies, deletes and moves, and directory operations,
+    will all be sent to ocrmypdf, producing errors in several cases.
+    Disable your watched folder if you are doing anything other than
+    copying files to it.
+-   If the source and destination directory are the same, watchmedo may
+    create an infinite loop.
+-   On BSD, FreeBSD and older versions of macOS, you may need to
+    increase the number of file descriptors to monitor more files, using
+    `ulimit -n 1024` to watch a folder of up to 1024 files.
+
+### Alternatives
+
+-   On Linux, [systemd user
+    services](https://wiki.archlinux.org/index.php/Systemd/User) can be
+    configured to automatically perform OCR on a collection of files.
+-   [Watchman](https://facebook.github.io/watchman/) is a more powerful
+    alternative to `watchmedo`.
+
+macOS Automator
+---------------
+
+You can use the Automator app with macOS, to create a Workflow or Quick
+Action. Use a *Run Shell Script* action in your workflow. In the context
+of Automator, the `PATH` may be set differently your Terminal\'s `PATH`;
+you may need to explicitly set the PATH to include `ocrmypdf`. The
+following example may serve as a starting point:
+
+![](images/macos-workflow.png)
+
+You may customize the command sent to ocrmypdf.
@@ -1,228 +0,0 @@
-.. SPDX-FileCopyrightText: 2022 James R. Barlow
-..
-.. SPDX-License-Identifier: CC-BY-SA-4.0
-
-================
-Batch processing
-================
-
-This article provides information about running OCRmyPDF on multiple
-files or configuring it as a service triggered by file system events.
-
-Batch jobs
-==========
-
-Consider using the excellent `GNU
-Parallel <https://www.gnu.org/software/parallel/>`__ to apply OCRmyPDF
-to multiple files at once.
-
-Both ``parallel`` and ``ocrmypdf`` will try to use all available
-processors. To maximize parallelism without overloading your system with
-processes, consider using ``parallel -j 2`` to limit parallel to running
-two jobs at once.
-
-This command will run ``ocrmypdf`` on all files named ``*.pdf`` in the
-current directory and write them to the previously created ``output/``
-folder. It will not search subdirectories.
-
-The ``--tag`` argument tells parallel to print the filename as a prefix
-whenever a message is printed, so that one can trace any errors to the
-file that produced them.
-
-.. code-block:: bash
-
-   parallel --tag -j 2 ocrmypdf '{}' 'output/{}' ::: *.pdf
-
-OCRmyPDF automatically repairs PDFs before parsing and gathering
-information from them.
-
-Directory trees
-===============
-
-This will walk through a directory tree and run OCR on all files in
-place, and printing each filename in between runs:
-
-.. code-block:: bash
-
-   find . -printf '%p\n' -name '*.pdf' -exec ocrmypdf '{}' '{}' \;
-
-This only runs one ``ocrmypdf`` process at a time. This variation uses
-``find`` to create a directory list and ``parallel`` to parallelize runs
-of ``ocrmypdf``, again updating files in place.
-
-.. code-block:: bash
-
-   find . -name '*.pdf' | parallel --tag -j 2 ocrmypdf '{}' '{}'
-
-In a Windows batch file, use
-
-.. code-block:: bat
-
-   for /r %%f in (*.pdf) do ocrmypdf %%f %%f
-
-With a Docker container, you will need to stream through standard input and output:
-
-.. code-block:: bash
-
-   find . -name '*.pdf' -print0 | xargs -0 | while read pdf; do
-       pdfout=$(mktemp)
-       docker run --rm -i jbarlow83/ocrmypdf - - <$pdf >$pdfout && cp $pdfout $pdf
-   done
-
-Sample script
-------------
-
-This user contributed script also provides an example of batch
-processing.
-
-.. literalinclude:: ../misc/batch.py
-    :caption: misc/batch.py
-
-Synology DiskStations
---------------------
-
-Synology DiskStations (Network Attached Storage devices) can run the
-Docker image of OCRmyPDF if the Synology `Docker
-package <https://www.synology.com/en-global/dsm/packages/Docker>`__ is
-installed. Attached is a script to address particular quirks of using
-OCRmyPDF on one of these devices.
-
-At the time this script was written, it only worked for x86-based Synology
-products. It is not known if it will work on ARM-based Synology products.
-Further adjustments might be needed to deal with the Synology's relatively
-limited CPU and RAM.
-
-.. literalinclude:: ../misc/synology.py
-    :caption: misc/synology.py - Sample script for Synology DiskStations
-
-Huge batch jobs
---------------
-
-If you have thousands of files to work with, contact the author.
-Consulting work related to OCRmyPDF helps fund this open source project
-and all inquiries are appreciated.
-
-Hot (watched) folders
-=====================
-
-Watched folders with watcher.py
-------------------------------
-
-OCRmyPDF has a folder watcher called watcher.py, which is currently included in source
-distributions but not part of the main program. It may be used natively or may run
-in a Docker container. Native instances tend to give better performance. watcher.py
-works on all platforms.
-
-Users may need to customize the script to meet their requirements.
-
-.. code-block:: bash
-
-    pip3 install ocrmypdf[watcher]
-
-    env OCR_INPUT_DIRECTORY=/mnt/input-pdfs \
-        OCR_OUTPUT_DIRECTORY=/mnt/output-pdfs \
-        OCR_OUTPUT_DIRECTORY_YEAR_MONTH=1 \
-        python3 watcher.py
-
-.. csv-table:: watcher.py environment variables
-    :header: "Environment variable", "Description"
-    :widths: 50, 50
-
-    "OCR_INPUT_DIRECTORY", "Set input directory to monitor (recursive)"
-    "OCR_OUTPUT_DIRECTORY", "Set output directory (should not be under input)"
-    "OCR_ARCHIVE_DIRECTORY", "Set archive directory for processed originals (should not be under input, requires ``OCR_ON_SUCCESS_ARCHIVE`` to be set)"
-    "OCR_ON_SUCCESS_DELETE", "This will delete the input file if the exit code is 0 (OK)"
-    "OCR_ON_SUCCESS_ARCHIVE", "This will move the processed original file to ``OCR_ARCHIVE_DIRECTORY`` if the exit code is 0 (OK). Note that ``OCR_ON_SUCCESS_DELETE`` takes precedence over this option, i.e. if both options are set, the input file will be deleted."
-    "OCR_OUTPUT_DIRECTORY_YEAR_MONTH", "This will place files in the output in ``{output}/{year}/{month}/{filename}``"
-    "OCR_DESKEW", "Apply deskew to crooked input PDFs"
-    "OCR_JSON_SETTINGS", "A JSON string specifying any other arguments for ``ocrmypdf.ocr``, e.g. ``'OCR_JSON_SETTINGS={""rotate_pages"": true}'``."
-    "OCR_POLL_NEW_FILE_SECONDS", "Polling interval"
-    "OCR_LOGLEVEL", "Level of log messages to report"
-
-One could configure a networked scanner or scanning computer to drop files in the
-watched folder.
-
-Watched folders with Docker
---------------------------
-
-The watcher service is included in the OCRmyPDF Docker image. To run it:
-
-.. code-block:: bash
-
-    docker run \
-        --volume <path to files to convert>:/input \
-        --volume <path to store results>:/output \
-        --volume <path to store processed originals>:/processed \
-        --env OCR_OUTPUT_DIRECTORY_YEAR_MONTH=1 \
-        --env OCR_ON_SUCCESS_ARCHIVE=1 \
-        --env OCR_DESKEW=1 \
-        --env PYTHONUNBUFFERED=1 \
-        --interactive --tty --entrypoint python3 \
-        jbarlow83/ocrmypdf \
-        watcher.py
-
-This service will watch for a file that matches ``/input/\*.pdf``,
-convert it to a OCRed PDF in ``/output/``, and move the processed
-original to ``/processed``. The parameters to this image are:
-
-.. csv-table:: watcher.py parameters for Docker
-    :header: "Parameter", "Description"
-    :widths: 50, 50
-
-    "``--volume <path to files to convert>:/input``", "Files placed in this location will be OCRed"
-    "``--volume <path to store results>:/output``", "This is where OCRed files will be stored"
-    "``--volume <path to store processed originals>:/processed``", "Archive processed originals here"
-    "``--env OCR_OUTPUT_DIRECTORY_YEAR_MONTH=1``", "Define environment variable ``OCR_OUTPUT_DIRECTORY_YEAR_MONTH=1`` to place files in the output in ``{output}/{year}/{month}/{filename}``"
-    "``--env OCR_ON_SUCCESS_ARCHIVE=1``", "Define environment variable ``OCR_ON_SUCCESS_ARCHIVE`` to move processed originals"
-    "``--env OCR_DESKEW=1``", "Define environment variable ``OCR_DESKEW``  to apply deskew to crooked input PDFs"
-    "``--env PYTHONBUFFERED=1``", "This will force ``STDOUT`` to be unbuffered and allow you to see messages in docker logs"
-
-This service relies on polling to check for changes to the filesystem. It
-may not be suitable for some environments, such as filesystems shared on a
-slow network.
-
-A configuration manager such as Docker Compose could be used to ensure that the
-service is always available.
-
-.. literalinclude:: ../misc/docker-compose.example.yml
-    :language: yaml
-    :caption: misc/docker-compose.example.yml
-
-Caveats
-------
-
-  ``watchmedo`` may not work properly on a networked file system,
-   depending on the capabilities of the file system client and server.
-  This simple recipe does not filter for the type of file system event,
-   so file copies, deletes and moves, and directory operations, will all
-   be sent to ocrmypdf, producing errors in several cases. Disable your
-   watched folder if you are doing anything other than copying files to
-   it.
-  If the source and destination directory are the same, watchmedo may
-   create an infinite loop.
-  On BSD, FreeBSD and older versions of macOS, you may need to increase
-   the number of file descriptors to monitor more files, using
-   ``ulimit -n 1024`` to watch a folder of up to 1024 files.
-
-Alternatives
------------
-
-  On Linux, `systemd user services <https://wiki.archlinux.org/index.php/Systemd/User>`__
-   can be configured to automatically perform OCR on a collection of files.
-
-  `Watchman <https://facebook.github.io/watchman/>`__ is a more
-   powerful alternative to ``watchmedo``.
-
-macOS Automator
-===============
-
-You can use the Automator app with macOS, to create a Workflow or Quick
-Action. Use a *Run Shell Script* action in your workflow. In the context
-of Automator, the ``PATH`` may be set differently your Terminal's
-``PATH``; you may need to explicitly set the PATH to include
-``ocrmypdf``. The following example may serve as a starting point:
-
-.. figure:: images/macos-workflow.png
-    :alt: Example macOS Automator workflow
-
-You may customize the command sent to ocrmypdf.
@@ -0,0 +1,84 @@
+% SPDX-FileCopyrightText: 2025 James R. Barlow
+% SPDX-License-Identifier: CC-BY-SA-4.0
+
+(ocr-service)=
+
+# Online deployments
+
+OCRmyPDF is designed to be used as a command line tool, but it can be
+used in a web service. This document describes some considerations for
+doing so.
+
+A basic web service implementation is provided in the source code
+repository, as `misc/webservice.py`. It is only demonstration quality
+and is not intended for production use.
+
+OCRmyPDF is not designed for use as a public web service where a
+malicious user could upload a chosen PDF. In particular, it is not
+necessarily secure against PDF malware or PDFs that cause denial of
+service. For further discussino of security, see
+[security](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 [tmpdir](#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.
@@ -1,92 +0,0 @@
-.. SPDX-FileCopyrightText: 2023 James R. Barlow
-..
-.. SPDX-License-Identifier: CC-BY-SA-4.0
-
-
-.. _ocr-service:
-
-==================
-Online deployments
-==================
-
-OCRmyPDF is designed to be used as a command line tool, but it can be
-used in a web service. This document describes some considerations for
-doing so.
-
-A basic web service implementation is provided in the source code
-repository, as ``misc/webservice.py``. It is only demonstration quality
-and is not intended for production use.
-
-OCRmyPDF is not designed for use as a public web service where a
-malicious user could upload a chosen PDF. In particular, it is not
-necessarily secure against PDF malware or PDFs that cause denial of
-service. For further discussino of security, see :ref:`security`.
-
-OCRmyPDF relies on Ghostscript, and therefore, if deployed
-online one should be prepared to comply with Ghostscript's Affero GPL
-license, and any other licenses.
-
-Setting aside these concerns, a side effect of OCRmyPDF is that it may
-incidentally sanitize PDFs containing certain types of malware. It
-repairs the PDF with pikepdf/libqpdf, which could correct malformed PDF
-structures that are part of an attack. When PDF/A output is selected
-(the default), the input PDF is partially reconstructed by Ghostscript.
-When ``--force-ocr`` is used, all pages are rasterized and reconverted
-to PDF, which could remove malware in embedded images.
-
-Limiting CPU usage
------------------
-
-OCRmyPDF will attempt to use all available CPUs and storage, so
-executing ``nice ocrmypdf`` or limiting the number of jobs with the
-``--jobs`` argument may ensure the server remains responsive. Another option
-would be to run OCRmyPDF jobs inside a Docker container, a virtual machine,
-or a cloud instance, which can impose its own limits on CPU usage and be
-terminated "from orbit" if it fails to complete.
-
-Temporary storage requirements
------------------------------
-
-OCRmyPDF will use a large amount of temporary storage for its work,
-proportional to the total number of pixels needed to rasterize the PDF.
-The raster image of a 8.5×11" color page at 300 DPI takes 25 MB
-uncompressed; OCRmyPDF saves its intermediates as PNG, but that still
-means it requires about 9 MB per intermediate based on average
-compression ratios. Multiple intermediates per page are also required,
-depending on the command line given. A rule of thumb would be to allow
-100 MB of temporary storage per page in a file – meaning that a small
-cloud servers or small VM partitions should be provisioned with plenty
-of extra space, if say, a 500 page file might be sent.
-
-To change the temporary directory, see :ref:`tmpdir`.
-
-On Amazon Web Services or other cloud vendors, consider setting your
-temporary directory to `empheral
-storage <https://docs.aws.amazon.com/AWSEC2/latest/UserGuide/InstanceStorage.html>`__.
-
-Timeouts
--------
-
-To prevent excessively long OCR jobs consider setting
-``--tesseract-timeout`` and/or ``--skip-big`` arguments. ``--skip-big``
-is particularly helpful if your PDFs include documents such as reports
-on standard page sizes with large images attached - often large images
-are not worth OCR'ing anyway.
-
-Document management systems
---------------------------
-
-If you are looking for a full document management system, consider
-`paperless-ngx <https://github.com/paperless-ngx/paperless-ngx>`__,
-which is a web application that uses OCRmyPDF to automatically OCR and
-archive documents.
-
-Commercial OCR alternatives
---------------------------
-
-The author also provides professional services that include OCR and
-building databases around PDFs, and is happy to provide consultation.
-
-Abbyy Cloud OCR is viable commercial alternative with a web services
-API. Amazon Textract, Google Cloud Vision, and Microsoft Azure
-Computer Vision provide advanced OCR but have less PDF rendering capability.
@@ -25,47 +25,53 @@
 # sys.path.insert(0, os.path.abspath('.'))

 # -- General configuration ------------------------------------------------
+from __future__ import annotations

-# If your documentation needs a minimal Sphinx version, state it here.
-#
-# needs_sphinx = '1.0'
+needs_sphinx = '8'
+
+import datetime as dt

 # Add any Sphinx extension module names here, as strings. They can be
 # extensions coming with Sphinx (named 'sphinx.ext.*') or your custom
 # ones.
 extensions = [
+    'myst_parser',
    'sphinx.ext.autodoc',
    'sphinx.ext.intersphinx',
    'sphinx.ext.autosummary',
    'sphinx.ext.napoleon',
+    'sphinx.ext.imgconverter',  # PDF docs needs this for SVG to PNG conversion
    'sphinx_issues',
+    'sphinx_reredirects',
+    'sphinxcontrib.mermaid',
 ]

+myst_enable_extensions = ['colon_fence', 'attrs_block', 'attrs_inline', 'substitution']
+
 # Extension settings
-intersphinx_mapping = {'https://docs.python.org/': None}
+intersphinx_mapping = {'python': ('https://docs.python.org/3', None)}
 napoleon_use_rtype = False
 issues_github_path = "ocrmypdf/OCRmyPDF"
+redirects = {
+    "release_notes": "releasenotes/index.html",
+}

 # Add any paths that contain templates here, relative to this directory.
 templates_path = ['_templates']

 # The suffix(es) of source filenames.
-# You can specify multiple suffix as a list of string:
-#
-# source_suffix = ['.rst', '.md']
-source_suffix = '.rst'
-
-# The encoding of source files.
-#
-# source_encoding = 'utf-8-sig'
+source_suffix = {'.rst': 'restructuredtext', '.md': 'markdown', '.txt': 'markdown'}

 # The master toctree document.
 master_doc = 'index'

 # General information about the project.
 project = 'ocrmypdf'
+
+year = str(dt.date.today().year)
 copyright = (
-    '2023, James R. Barlow. Licensed under Creative Commons Attribution-ShareAlike 4.0.'
+    f'{year}, James R. Barlow. '
+    + 'Licensed under Creative Commons Attribution-ShareAlike 4.0'
 )
 author = 'James R. Barlow'

@@ -92,6 +98,7 @@ if on_rtd:

    MOCK_MODULES = [
        'pikepdf',
+        'pikepdf.canvas',
        'pikepdf.models',
        'pikepdf.models.metadata',
    ]
@@ -108,7 +115,7 @@ version = '.'.join(release.split('.')[:2])
 #
 # This is also used if you do content translation via gettext catalogs.
 # Usually you set "language" from the command line for these cases.
-language = None
+language = 'en'

 # There are two options for replacing |today|: either, you set today to some
 # non-false value, then it is used:
@@ -158,19 +165,32 @@ todo_include_todos = False

 # -- Options for HTML output ----------------------------------------------

-import sphinx_rtd_theme
+import sphinx_rtd_theme  # noqa: F401

 # The theme to use for HTML and HTML Help pages.  See the documentation for
 # a list of builtin themes.
 #
 html_theme = 'sphinx_rtd_theme'
-html_theme_path = [sphinx_rtd_theme.get_html_theme_path()]

 # Theme options are theme-specific and customize the look and feel of a theme
 # further.  For a list of options available for each theme, see the
 # documentation.
 #
-html_theme_options = {'display_version': False}
+html_theme_options = {}
+
+# ReadTheDocs used to inject the "Edit on GitHub" context automatically, but
+# dropped it when it switched to Addons, so set it explicitly here. This makes
+# sphinx_rtd_theme add an "Edit on GitHub" link to each page that points at the
+# corresponding source file in the repository, replacing the static
+# "View page source" (_sources/*.txt) link. See
+# https://github.com/ocrmypdf/OCRmyPDF/issues/1490
+html_context = {
+    'display_github': True,
+    'github_user': 'ocrmypdf',
+    'github_repo': 'OCRmyPDF',
+    'github_version': 'main',
+    'conf_py_path': '/docs/',
+}

 # Add any paths that contain custom themes here, relative to this directory.
 # html_theme_path = []
@@ -198,7 +218,7 @@ html_theme_options = {'display_version': False}
 # Add any paths that contain custom static files (such as style sheets) here,
 # relative to this directory. They are copied after the builtin static files,
 # so a file named "default.css" will overwrite the builtin "default.css".
-html_static_path = ['_static']
+# html_static_path = ['_static']

 # Add any extra paths that contain custom files (such as robots.txt or
 # .htaccess) here, relative to this directory. These files are copied
@@ -0,0 +1,72 @@
+% SPDX-FileCopyrightText: 2025 James R. Barlow
+% SPDX-License-Identifier: CC-BY-SA-4.0
+
+# Contributing guidelines
+
+Contributions are welcome!
+
+## Big changes
+
+Please open a new issue to discuss or propose a major change. Not only
+is it fun to discuss big ideas, but we might save each other\'s time
+too. Perhaps some of the work you\'re contemplating is already half-done
+in a development branch.
+
+## Code style
+
+We use `ruff` for code formatting.
+The settings for these programs are in `pyproject.toml`. Pull requests
+should follow the style guide. One difference we use from \"black\"
+style is that strings shown to the user are always in double quotes
+(`"`) and strings for internal uses are in single quotes (`'`).
+
+## Tests
+
+New features should come with tests that confirm their correctness.
+
+## New dependencies
+
+If you are proposing a change that will require a new dependency, we
+prefer dependencies that are already packaged by Debian or Red Hat. This
+makes life much easier for our downstream package maintainers. A package
+that is only available on PyPI or GitHub, and not more widely packaged,
+may not be accepted.
+
+We are unlikely to accept a dependency on CUDA or other GPU-based
+libraries, because these are still difficult to package and install on
+many systems. We recommend implementing these changes as plugins.
+
+Python dependencies must also be license-compatible. GPLv3 or AGPLv3 are
+likely incompatible with the project\'s license, but LGPLv3 is
+compatible.
+
+## New non-Python dependencies
+
+OCRmyPDF uses several external programs (Tesseract, Ghostscript and
+others) for its functionality. In general we prefer to avoid adding new
+external programs, and if we are to add external programs, we prefer
+those that are already packaged by Debian or Red Hat.
+
+## Plugins
+
+Some new features may be a good fit for a plugin. Plugins are a way to
+add features to OCRmyPDF without adding them to the core program.
+Plugins are installed separately from OCRmyPDF. They are written in
+Python and can be installed from PyPI. See the [plugin
+documentation](https://ocrmypdf.readthedocs.io/en/latest/plugins.html).
+
+We are happy to link users to your plugin from the documentation.
+
+## Style guide: Is it OCRmyPDF or ocrmypdf?
+
+The program/project is OCRmyPDF and the name of the executable or
+library is ocrmypdf.
+
+## Copyright and license
+
+For contributions over 10 lines of code, please add your name to list of
+copyright holders for that file. The core program is licensed under
+MPL-2.0, test files and documentation under CC-BY-SA 4.0, and
+miscellaneous files under MIT, with a few minor exceptions. Please
+contribute only content that you own or have the right to contribute
+under these licenses.
@@ -1,77 +0,0 @@
-.. SPDX-FileCopyrightText: 2022 James R. Barlow
-..
-.. SPDX-License-Identifier: CC-BY-SA-4.0
-
-=======================
-Contributing guidelines
-=======================
-
-Contributions are welcome!
-
-Big changes
-===========
-
-Please open a new issue to discuss or propose a major change. Not only is it fun
-to discuss big ideas, but we might save each other's time too. Perhaps some of the
-work you're contemplating is already half-done in a development branch.
-
-Code style
-==========
-
-We use PEP8, ``black`` for code formatting and ``ruff`` for everything else. The
-settings for these programs are in ``pyproject.toml``. Pull
-requests should follow the style guide. One difference we use from "black" style
-is that strings shown to the user are always in double quotes (``"``) and strings
-for internal uses are in single quotes (``'``).
-
-Tests
-=====
-
-New features should come with tests that confirm their correctness.
-
-New dependencies
-================
-
-If you are proposing a change that will require a new dependency, we
-prefer dependencies that are already packaged by Debian or Red Hat. This makes
-life much easier for our downstream package maintainers. A package that is only
-available on PyPI or GitHub, and not more widely packaged, may not be accepted.
-
-We are unlikely to accept a dependency on CUDA or other GPU-based libraries,
-because these are still difficult to package and install on many systems.
-We recommend implementing these changes as plugins.
-
-Python dependencies must also be license-compatible. GPLv3 or AGPLv3 are likely
-incompatible with the project's license, but LGPLv3 is compatible.
-
-New non-Python dependencies
-===========================
-
-OCRmyPDF uses several external programs (Tesseract, Ghostscript and others) for
-its functionality. In general we prefer to avoid adding new external programs,
-and if we are to add external programs, we prefer those that are already
-packaged by Debian or Red Hat.
-
-Plugins
-=======
-
-Some new features may be a good fit for a plugin. Plugins are a way to add
-features to OCRmyPDF without adding them to the core program. Plugins are
-installed separately from OCRmyPDF. They are written in Python and can be
-installed from PyPI. See the `plugin documentation <https://ocrmypdf.readthedocs.io/en/latest/plugins.html>`_.
-
-We are happy to link users to your plugin from the documentation.
-
-Style guide: Is it OCRmyPDF or ocrmypdf?
-========================================
-
-The program/project is OCRmyPDF and the name of the executable or library is ocrmypdf.
-
-Copyright and license
-=====================
-
-For contributions over 10 lines of code, please add your name to list of
-copyright holders for that file. The core program is licensed under MPL-2.0,
-test files and documentation under CC-BY-SA 4.0, and miscellaneous files under
-MIT, with a few minor exceptions. Please contribute only content that you own
-or have the right to contribute under these licenses.
@@ -0,0 +1,471 @@
+% SPDX-FileCopyrightText: 2025 James R. Barlow
+% SPDX-License-Identifier: CC-BY-SA-4.0
+
+# Cookbook
+
+## Basic examples
+
+### Help!
+
+ocrmypdf has built-in help.
+
+```bash
+ocrmypdf --help
+```
+
+### Add an OCR layer and convert to PDF/A
+
+```bash
+ocrmypdf input.pdf output.pdf
+```
+
+### Add an OCR layer and output a standard PDF
+
+```bash
+ocrmypdf --output-type pdf input.pdf output.pdf
+```
+
+### Create a PDF/A with all color and grayscale images converted to JPEG
+
+```bash
+ocrmypdf --output-type pdfa --pdfa-image-compression jpeg input.pdf output.pdf
+```
+
+### Reduce JPEG quality with the optimizer
+
+This is the recommended way to shrink JPEG content in the output. The
+optimizer applies regardless of `--output-type`, so it works on both
+plain PDFs and Ghostscript-produced PDF/A files.
+
+```bash
+ocrmypdf --optimize 2 --jpeg-quality 60 input.pdf output.pdf
+```
+
+### Modify a file in place
+
+The file will only be overwritten if OCRmyPDF is successful.
+
+```bash
+ocrmypdf myfile.pdf myfile.pdf
+```
+
+### Correct page rotation
+
+OCR will attempt to automatic correct the rotation of each page. This
+can help fix a scanning job that contains a mix of landscape and
+portrait pages.
+
+```bash
+ocrmypdf --rotate-pages myfile.pdf myfile.pdf
+```
+
+You can increase (decrease) the parameter `--rotate-pages-threshold` to
+make page rotation more (less) aggressive. The threshold number is the
+ratio of how confidence the OCR engine is that the document image should
+be changed, compared to kept the same. The default value is quite
+conservative; on some files it may not attempt rotations at all unless
+it is very confident that the current rotation is wrong. A lower value
+of `2.0` will produce more rotations, and more false positives. Run with
+`-v1` to see the confidence level for each page to see if there may be a
+better value for your files.
+
+If the page is \"just a little off horizontal\", like a crooked picture,
+then you want `--deskew`. `--rotate-pages` is for when the cardinal
+angle is wrong.
+
+### OCR languages other than English
+
+OCRmyPDF assumes the document is in English unless told otherwise. OCR
+quality may be poor if the wrong language is used.
+
+```bash
+ocrmypdf -l fra LeParisien.pdf LeParisien.pdf
+ocrmypdf -l eng+fra Bilingual-English-French.pdf Bilingual-English-French.pdf
+```
+
+Language packs must be installed for all languages specified. See
+`Installing additional language packs <lang-packs>`{.interpreted-text
+role="ref"}.
+
+Unfortunately, the Tesseract OCR engine has no ability to detect the
+language when it is unknown.
+
+### Produce PDF and text file containing OCR text
+
+This produces a file named \"output.pdf\" and a companion text file
+named \"output.txt\".
+
+```bash
+ocrmypdf --sidecar output.txt input.pdf output.pdf
+```
+
+:::{note}
+The sidecar file contains the **OCR text** found by OCRmyPDF. If the
+document contains pages that already have text, that text will not
+appear in the sidecar. If the option `--pages` is used, only those pages
+on which OCR was performed will be included in the sidecar. If certain
+pages were skipped because of options like `--skip-big` or
+`--tesseract-timeout`, those pages will not be in the sidecar.
+
+If you don\'t want to generate the output PDF, use `--output-type=none`
+to avoid generating one. Set the output filename to `-` (i.e. redirect
+to stdout).
+
+To extract all text from a PDF, whether generated from OCR or otherwise,
+use a program like Poppler\'s `pdftotext` or `pdfgrep`.
+:::
+
+### OCR images, not PDFs
+
+#### Option: use Tesseract
+
+If you are starting with images, you can just use Tesseract directly to
+convert images to PDFs:
+
+```bash
+tesseract my-image.jpg output-prefix pdf
+```
+
+```bash
+# When there are multiple images
+tesseract text-file-containing-list-of-image-filenames.txt output-prefix pdf
+```
+
+Tesseract\'s PDF output is quite good -- OCRmyPDF uses it internally, in
+some cases. However, OCRmyPDF has many features not available in
+Tesseract like image processing, metadata control, and PDF/A generation.
+
+#### Option: use img2pdf
+
+You can also use a program like
+[img2pdf](https://gitlab.mister-muffin.de/josch/img2pdf) to convert your
+images to PDFs, and then pipe the results to run ocrmypdf. The `-` tells
+ocrmypdf to read standard input.
+
+```bash
+img2pdf my-images*.jpg | ocrmypdf - myfile.pdf
+```
+
+`img2pdf` is recommended because it does an excellent job at generating
+PDFs without transcoding images.
+
+#### Option: use OCRmyPDF (single images only)
+
+For convenience, OCRmyPDF can also convert single images to PDFs on its
+own. If the resolution (dots per inch, DPI) of an image is not set or is
+incorrect, it can be overridden with `--image-dpi`. (As 1 inch is 2.54
+cm, 1 dpi = 0.39 dpcm).
+
+```bash
+ocrmypdf --image-dpi 300 image.png myfile.pdf
+```
+
+If you have multiple images, you must use `img2pdf` to convert the
+images to PDF.
+
+#### Not recommended
+
+We caution against using ImageMagick or Ghostscript to convert images to
+PDF, since they may transcode images or produce downsampled images,
+sometimes without warning.
+
+(image-processing)=
+
+## Image processing
+
+OCRmyPDF perform some image processing on each page of a PDF, if
+desired. The same processing is applied to each page. It is suggested
+that the user review files after image processing as these commands
+might remove desirable content, especially from poor quality scans.
+
+-   `--rotate-pages` attempts to determine the correct orientation for
+    each page and rotates the page if necessary.
+-   `--remove-background` attempts to detect and remove a noisy
+    background from grayscale or color images. Monochrome images are
+    ignored. This should not be used on documents that contain color
+    photos as it may remove them.
+-   `--deskew` will correct pages that were scanned at a skewed angle by
+    rotating them back into place.
+-   `--clean` uses [unpaper](https://www.flameeyes.eu/projects/unpaper)
+    to clean up pages before OCR, but does not alter the final output.
+    This makes it less likely that OCR will try to find text in
+    background noise.
+-   `--clean-final` uses unpaper to clean up pages before OCR and
+    inserts the page into the final output. You will want to review each
+    page to ensure that unpaper did not remove something important.
+
+:::{note}
+In many cases image processing will rasterize PDF pages as images,
+potentially losing quality.
+:::
+
+:::{warning}
+`--clean-final` and `--remove-background` may leave undesirable visual
+artifacts in some images where their algorithms have shortcomings. Files
+should be visually reviewed after using these options.
+:::
+
+### Example: OCR and correct document skew (crooked scan)
+
+Deskew:
+
+```bash
+ocrmypdf --deskew input.pdf output.pdf
+```
+
+Image processing commands can be combined. The order in which options
+are given does not matter. OCRmyPDF always applies the steps of the
+image processing pipeline in the same order (rotate, remove background,
+deskew, clean).
+
+```bash
+ocrmypdf --deskew --clean --rotate-pages input.pdf output.pdf
+```
+
+Don\'t actually OCR my PDF
+--------------------------
+
+If you set `--ocr-engine none` OCRmyPDF will apply its image processing without
+performing OCR. This works if all you want to is to apply image processing or PDF/A
+conversion.
+
+```bash
+ocrmypdf --ocr-engine none --deskew --output-type pdfa input.pdf output.pdf
+```
+
+:::{versionchanged} v17.0.0
+
+Prior to this version, `--tesseract-timeout 0` was recommended as an idiom
+to turn off OCR. This is not longer recommended, as we move away from
+Tesseract OCR as the primary OCR engine.
+
+:::
+
+:::{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.
+:::
+
+### Remove the OCR text layer from my PDF
+
+To remove the invisible OCR text layer while keeping the original pages
+exactly as they are -- no rasterizing, no change to images or visible
+content, and a smaller output file -- use `--mode strip`:
+
+```bash
+ocrmypdf --mode strip input.pdf output.pdf
+```
+
+Why would you want to do this? Perhaps you have a PDF where OCR failed to
+produce useful results and you simply want to get rid of it.
+
+`--mode strip` removes only text drawn as *invisible* (PDF text render
+mode 3), which is how OCRmyPDF and most OCR tools add a searchable layer
+over a scanned page. Some OCR products -- and OCRmyPDF v2.2 and earlier --
+instead draw *visible* text and paint an opaque image on top of it. That
+text is part of the visible page, so `--mode strip` cannot remove it
+without altering the page's appearance.
+
+To strip *all* text, including such visible text, rasterize the whole page
+into a \"bag of images\" PDF instead (this rebuilds every page as an image,
+so the file usually grows and vector content is lost):
+
+```bash
+ocrmypdf --ocr-engine none --force-ocr input.pdf output.pdf
+```
+
+### Optimize images without performing OCR
+
+You can also optimize all images without performing any OCR:
+
+```bash
+ocrmypdf --ocr-engine none --optimize 3 --skip-text input.pdf output.pdf
+```
+
+## Using v17 features
+
+### Select a rasterizer
+
+:::{versionadded} 17.0.0
+:::
+
+OCRmyPDF can use pypdfium2 or Ghostscript to rasterize PDF pages. pypdfium2
+is generally faster and is preferred when available.
+
+```bash
+# Automatic selection (default) - prefers pypdfium when available
+ocrmypdf --rasterizer auto input.pdf output.pdf
+
+# Explicitly use pypdfium2 (requires pip install pypdfium2)
+ocrmypdf --rasterizer pypdfium input.pdf output.pdf
+
+# Explicitly use Ghostscript
+ocrmypdf --rasterizer ghostscript input.pdf output.pdf
+```
+
+### PDF/A without Ghostscript
+
+:::{versionadded} 17.0.0
+:::
+
+With verapdf installed, OCRmyPDF can produce PDF/A without using Ghostscript
+for conversion. This is faster and avoids some Ghostscript limitations.
+
+```bash
+# Uses speculative conversion with verapdf validation (default)
+ocrmypdf --output-type auto input.pdf output.pdf
+
+# Explicitly request Ghostscript-based PDF/A conversion
+ocrmypdf --output-type pdfa input.pdf output.pdf
+```
+
+### Using --mode instead of legacy flags
+
+:::{versionadded} 17.0.0
+:::
+
+The `--mode` (`-m`) flag consolidates OCR behavior options:
+
+```bash
+# Instead of --skip-text
+ocrmypdf --mode skip input.pdf output.pdf
+
+# Instead of --force-ocr
+ocrmypdf --mode force input.pdf output.pdf
+
+# Instead of --redo-ocr
+ocrmypdf --mode redo input.pdf output.pdf
+
+# Short form
+ocrmypdf -m skip input.pdf output.pdf
+```
+
+The legacy flags continue to work as aliases.
+
+### Process only certain pages
+
+You can ask OCRmyPDF to only apply [image processing](#image-processing)
+and OCR to certain pages.
+
+```bash
+ocrmypdf --pages 2,3,13-17 input.pdf output.pdf
+```
+
+Hyphens denote a range of pages and commas separate page numbers. If you
+prefer to use spaces, quote all of the page numbers:
+`--pages '2, 3, 5, 7'`.
+
+The token `end` (case-insensitive) is an alias for the last page in the
+document. For example, `--pages 3-end` OCRs from page 3 through the
+final page, and `--pages end` OCRs only the last page:
+
+```bash
+ocrmypdf --pages 3-end input.pdf output.pdf
+ocrmypdf --pages end input.pdf output.pdf
+```
+
+OCRmyPDF will warn if your list of page numbers contains duplicates or
+overlapping pages. (Repeated page numbers are de-duplicated automatically,
+since the underlying set of pages is what matters.) OCRmyPDF does not
+currently account for document page numbers, such as an introduction
+section of a book that uses Roman numerals. It simply counts the number
+of virtual pieces of paper since the start. If your list of pages is out
+of numerical order, OCRmyPDF will sort it for you.
+
+Regardless of the argument to `--pages`, OCRmyPDF will optimize all
+pages/images in the file and convert it to PDF/A, unless you disable
+those options. Both of these steps are \"whole file\" operations. In
+this example, we want to OCR only the title and otherwise change the PDF
+as little as possible:
+
+```bash
+ocrmypdf --pages 1 --output-type pdf --optimize 0 input.pdf output.pdf
+```
+
+## Redo existing OCR
+
+To redo OCR on a file OCRed with other OCR software or a previous
+version of OCRmyPDF and/or Tesseract, you may use the `--redo-ocr`
+argument. (Normally, OCRmyPDF will exit with an error if asked to modify
+a file with OCR.)
+
+This may be helpful for users who want to take advantage of accuracy
+improvements in Tesseract for files they previously OCRed with an
+earlier version of Tesseract and OCRmyPDF.
+
+```bash
+ocrmypdf --redo-ocr input.pdf output.pdf
+```
+
+This method will replace OCR without rasterizing, reducing quality or
+removing vector content. If a file contains a mix of pure digital text
+and OCR, digital text will be ignored and OCR will be replaced. As such
+this mode is incompatible with image processing options, since they
+alter the appearance of the file.
+
+In some cases, existing OCR cannot be detected or replaced. Files
+produced by OCRmyPDF v2.2 or earlier, for example, are internally
+represented as having visible text with an opaque image drawn on top.
+This situation cannot be detected.
+
+If `--redo-ocr` does not work, you can use `--force-ocr`, which will
+force rasterization of all pages, potentially reducing quality or losing
+vector content.
+
+Improving OCR quality
+---------------------
+
+The [Image processing](#image-processing) features can improve OCR
+quality.
+
+Rotating pages and deskewing helps to ensure that the page orientation
+is correct before OCR begins. Removing the background and/or cleaning
+the page can also improve results. The `--oversample DPI` argument can
+be specified to resample images to higher resolution before attempting
+OCR; this can improve results as well.
+
+OCR quality will suffer if the resolution of input images is not correct
+(since the range of pixel sizes that will be checked for possible fonts
+will also be incorrect).
+
+## PDF optimization
+
+By default OCRmyPDF will attempt to perform lossless optimizations on
+the images inside PDFs after OCR is complete. Optimization is performed
+even if no OCR text is found.
+
+The `--optimize N` (short form `-O`) argument controls optimization,
+where `N` ranges from 0 to 3 inclusive, analogous to the optimization
+levels in the GCC compiler. `-O1` is the default.
+
+For further details, see the section on [PDF optimization](optimizer).
+
+```bash
+ocrmypdf --optimize 3 in.pdf out.pdf  # Make it small
+```
+
+Some users may consider enabling lossy JBIG2. See:
+`jbig2-lossy`{.interpreted-text role="ref"}.
+
+:::{note}
+Image processing and PDF/A conversion can also introduce lossy
+transformations to your PDF images, even when `--optimize 1` is in use.
+:::
+
+Digitally signed PDFs
+---------------------
+
+OCRmyPDF cannot preserve digital signatures in PDFs and also add 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.
@@ -1,410 +0,0 @@
-.. SPDX-FileCopyrightText: 2022 James R. Barlow
-..
-.. SPDX-License-Identifier: CC-BY-SA-4.0
-
-========
-Cookbook
-========
-
-Basic examples
-==============
-
-Help!
-----
-
-ocrmypdf has built-in help.
-
-.. code-block:: bash
-
-    ocrmypdf --help
-
-Add an OCR layer and convert to PDF/A
-------------------------------------
-
-.. code-block:: bash
-
-    ocrmypdf input.pdf output.pdf
-
-Add an OCR layer and output a standard PDF
------------------------------------------
-
-.. code-block:: bash
-
-    ocrmypdf --output-type pdf input.pdf output.pdf
-
-Create a PDF/A with all color and grayscale images converted to JPEG
--------------------------------------------------------------------
-
-.. code-block:: bash
-
-    ocrmypdf --output-type pdfa --pdfa-image-compression jpeg input.pdf output.pdf
-
-Modify a file in place
----------------------
-
-The file will only be overwritten if OCRmyPDF is successful.
-
-.. code-block:: bash
-
-    ocrmypdf myfile.pdf myfile.pdf
-
-Correct page rotation
---------------------
-
-OCR will attempt to automatic correct the rotation of each page. This
-can help fix a scanning job that contains a mix of landscape and
-portrait pages.
-
-.. code-block:: bash
-
-    ocrmypdf --rotate-pages myfile.pdf myfile.pdf
-
-You can increase (decrease) the parameter ``--rotate-pages-threshold``
-to make page rotation more (less) aggressive. The threshold number is the ratio
-of how confidence the OCR engine is that the document image should be changed,
-compared to kept the same. The default value is quite conservative; on some files
-it may not attempt rotations at all unless it is very confident that the current
-rotation is wrong. A lower value of ``2.0`` will produce more rotations, and
-more false positives. Run with ``-v1`` to see the confidence level for each
-page to see if there may be a better value for your files.
-
-If the page is "just a little off horizontal", like a crooked picture,
-then you want ``--deskew``. ``--rotate-pages`` is for when the cardinal
-angle is wrong.
-
-OCR languages other than English
--------------------------------
-
-OCRmyPDF assumes the document is in English unless told otherwise. OCR
-quality may be poor if the wrong language is used.
-
-.. code-block:: bash
-
-    ocrmypdf -l fra LeParisien.pdf LeParisien.pdf
-    ocrmypdf -l eng+fra Bilingual-English-French.pdf Bilingual-English-French.pdf
-
-Language packs must be installed for all languages specified. See
-:ref:`Installing additional language packs <lang-packs>`.
-
-Unfortunately, the Tesseract OCR engine has no ability to detect the
-language when it is unknown.
-
-Produce PDF and text file containing OCR text
---------------------------------------------
-
-This produces a file named "output.pdf" and a companion text file named
-"output.txt".
-
-.. code-block:: bash
-
-    ocrmypdf --sidecar output.txt input.pdf output.pdf
-
-.. note::
-
-    The sidecar file contains the **OCR text** found by OCRmyPDF. If the document
-    contains pages that already have text, that text will not appear in the
-    sidecar. If the option ``--pages`` is used, only those pages on which OCR
-    was performed will be included in the sidecar. If certain pages were skipped
-    because of options like ``--skip-big`` or ``--tesseract-timeout``, those pages
-    will not be in the sidecar.
-
-    If you don't want to generate the output PDF, use ``--output-type=none`` to
-    avoid generating one. Set the output filename to ``-`` (i.e. redirect to stdout).
-
-    To extract all text from a PDF, whether generated from OCR or otherwise,
-    use a program like Poppler's ``pdftotext`` or ``pdfgrep``.
-
-OCR images, not PDFs
--------------------
-
-Option: use Tesseract
-~~~~~~~~~~~~~~~~~~~~~
-
-If you are starting with images, you can just use Tesseract directly to
-convert images to PDFs:
-
-.. code-block:: bash
-
-    tesseract my-image.jpg output-prefix pdf
-
-.. code-block:: bash
-
-    # When there are multiple images
-    tesseract text-file-containing-list-of-image-filenames.txt output-prefix pdf
-
-Tesseract's PDF output is quite good – OCRmyPDF uses it internally, in
-some cases. However, OCRmyPDF has many features not available in
-Tesseract like image processing, metadata control, and PDF/A generation.
-
-Option: use img2pdf
-~~~~~~~~~~~~~~~~~~~
-
-You can also use a program like
-`img2pdf <https://gitlab.mister-muffin.de/josch/img2pdf>`__ to convert
-your images to PDFs, and then pipe the results to run ocrmypdf. The
-``-`` tells ocrmypdf to read standard input.
-
-.. code-block:: bash
-
-    img2pdf my-images*.jpg | ocrmypdf - myfile.pdf
-
-``img2pdf`` is recommended because it does an excellent job at
-generating PDFs without transcoding images.
-
-Option: use OCRmyPDF (single images only)
-~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
-
-For convenience, OCRmyPDF can also convert single images to PDFs on its
-own. If the resolution (dots per inch, DPI) of an image is not set or is
-incorrect, it can be overridden with ``--image-dpi``. (As 1 inch is 2.54
-cm, 1 dpi = 0.39 dpcm).
-
-.. code-block:: bash
-
-    ocrmypdf --image-dpi 300 image.png myfile.pdf
-
-If you have multiple images, you must use ``img2pdf`` to convert the
-images to PDF.
-
-Not recommended
-~~~~~~~~~~~~~~~
-
-We caution against using ImageMagick or Ghostscript to convert images to
-PDF, since they may transcode images or produce downsampled images,
-sometimes without warning.
-
-Image processing
-================
-
-OCRmyPDF perform some image processing on each page of a PDF, if
-desired. The same processing is applied to each page. It is suggested
-that the user review files after image processing as these commands
-might remove desirable content, especially from poor quality scans.
-
-  ``--rotate-pages`` attempts to determine the correct orientation for
-   each page and rotates the page if necessary.
-  ``--remove-background`` attempts to detect and remove a noisy
-   background from grayscale or color images. Monochrome images are
-   ignored. This should not be used on documents that contain color
-   photos as it may remove them.
-  ``--deskew`` will correct pages that were scanned at a skewed angle by
-   rotating them back into place.
-  ``--clean`` uses
-   `unpaper <https://www.flameeyes.eu/projects/unpaper>`__ to clean up
-   pages before OCR, but does not alter the final output. This makes it
-   less likely that OCR will try to find text in background noise.
-  ``--clean-final`` uses unpaper to clean up pages before OCR and
-   inserts the page into the final output. You will want to review each
-   page to ensure that unpaper did not remove something important.
-
-.. note::
-
-   In many cases image processing will rasterize PDF pages as images,
-   potentially losing quality.
-
-.. warning::
-
-   ``--clean-final`` and ``--remove-background`` may leave undesirable
-   visual artifacts in some images where their algorithms have
-   shortcomings. Files should be visually reviewed after using these
-   options.
-
-Example: OCR and correct document skew (crooked scan)
-----------------------------------------------------
-
-Deskew:
-
-.. code-block:: bash
-
-    ocrmypdf --deskew input.pdf output.pdf
-
-Image processing commands can be combined. The order in which options
-are given does not matter. OCRmyPDF always applies the steps of the
-image processing pipeline in the same order (rotate, remove background,
-deskew, clean).
-
-.. code-block:: bash
-
-    ocrmypdf --deskew --clean --rotate-pages input.pdf output.pdf
-
-Don't actually OCR my PDF
-=========================
-
-If you set ``--tesseract-timeout 0`` OCRmyPDF will apply its image
-processing without performing OCR (by causing OCR to time out). This works
-if all you want to is to apply image processing or PDF/A conversion.
-
-.. code-block:: bash
-
-    ocrmypdf --tesseract-timeout=0 --remove-background input.pdf output.pdf
-
-.. versionchanged:: v14.1.0
-
-    Prior to this version, ``--tesseract-timeout 0`` would prevent other
-    uses of Tesseract, such as deskewing, from working. This is no longer
-    the case. Use ``--tesseract-non-ocr-timeout`` to control the timeout
-    for non-OCR operations, if needed.
-
-Remove all text or OCR from my PDF
----------------------------------
-
-This is getting ridiculous, but OCRmyPDF can complete strip all textual
-information from a PDF and reconstruct it as a "bag of images" PDF.
-
-.. code-block::
-
-    ocrmypdf --tesseract-timeout 0 --force-ocr input.pdf output.pdf
-
-Why would you want to do this? Perhaps you have a PDF where OCR
-fails to produce useful results, and just want to get rid of all OCR information.
-This command also removes OCR generated by third party tools.
-
-Optimize images without performing OCR
--------------------------------------
-
-You can also optimize all images without performing any OCR:
-
-.. code-block:: bash
-
-    ocrmypdf --tesseract-timeout=0 --optimize 3 --skip-text input.pdf output.pdf
-
-Process only certain pages
--------------------------
-
-You can ask OCRmyPDF to only apply `image processing <#image-processing>`__
-and OCR to certain pages.
-
-.. code-block:: bash
-
-    ocrmypdf --pages 2,3,13-17 input.pdf output.pdf
-
-Hyphens denote a range of pages and commas separate page numbers. If you prefer
-to use spaces, quote all of the page numbers: ``--pages '2, 3, 5, 7'``.
-
-OCRmyPDF will warn if your list of page numbers contains duplicates or
-overlapping pages. OCRmyPDF does not currently account for document page numbers,
-such as an introduction section of a book that uses Roman numerals. It simply
-counts the number of virtual pieces of paper since the start. If your list of
-pages is out of numerical order, OCRmyPDF will sort it for you.
-
-Regardless of the argument to ``--pages``, OCRmyPDF will optimize all pages/images
-in the file and convert it to PDF/A, unless you disable those options. Both of these
-steps are "whole file" operations. In this example, we want to OCR only the title
-and otherwise change the PDF as little as possible:
-
-.. code-block:: bash
-
-    ocrmypdf --pages 1 --output-type pdf --optimize 0 input.pdf output.pdf
-
-Redo existing OCR
-=================
-
-To redo OCR on a file OCRed with other OCR software or a previous
-version of OCRmyPDF and/or Tesseract, you may use the ``--redo-ocr``
-argument. (Normally, OCRmyPDF will exit with an error if asked to modify
-a file with OCR.)
-
-This may be helpful for users who want to take advantage of accuracy
-improvements in Tesseract for files they previously OCRed with an
-earlier version of Tesseract and OCRmyPDF.
-
-.. code-block:: bash
-
-    ocrmypdf --redo-ocr input.pdf output.pdf
-
-This method will replace OCR without rasterizing, reducing quality or
-removing vector content. If a file contains a mix of pure digital text
-and OCR, digital text will be ignored and OCR will be replaced. As such
-this mode is incompatible with image processing options, since they
-alter the appearance of the file.
-
-In some cases, existing OCR cannot be detected or replaced. Files
-produced by OCRmyPDF v2.2 or earlier, for example, are internally
-represented as having visible text with an opaque image drawn on top.
-This situation cannot be detected.
-
-If ``--redo-ocr`` does not work, you can use ``--force-ocr``, which will
-force rasterization of all pages, potentially reducing quality or losing
-vector content.
-
-Improving OCR quality
-=====================
-
-The `Image processing <#image-processing>`__ features can improve OCR
-quality.
-
-Rotating pages and deskewing helps to ensure that the page orientation
-is correct before OCR begins. Removing the background and/or cleaning
-the page can also improve results. The ``--oversample DPI`` argument can
-be specified to resample images to higher resolution before attempting
-OCR; this can improve results as well.
-
-OCR quality will suffer if the resolution of input images is not correct
-(since the range of pixel sizes that will be checked for possible fonts
-will also be incorrect).
-
-PDF optimization
-================
-
-By default OCRmyPDF will attempt to perform lossless optimizations on
-the images inside PDFs after OCR is complete. Optimization is performed
-even if no OCR text is found.
-
-The ``--optimize N`` (short form ``-O``) argument controls optimization,
-where ``N`` ranges from 0 to 3 inclusive, analogous to the optimization
-levels in the GCC compiler.
-
-.. list-table::
-    :widths: auto
-    :header-rows: 1
-
-    *   - Level
-        - Comments
-    *   - ``--optimize 0``
-        - Disables optimization.
-    *   - ``--optimize 1``
-        - Enables lossless optimizations, such as transcoding images to more
-          efficient formats. Also compress other uncompressed objects in the
-          PDF and enables the more efficient "object streams" within the PDF.
-          (If ``--jbig2-lossy`` is issued, then lossy JBIG2 optimization is used.
-          The decision to use lossy JBIG2 is separate from standard optimization
-          settings.)
-    *   - ``--optimize 2``
-        - All of the above, and enables lossy optimizations and color quantization.
-    *   - ``--optimize 3``
-        - All of the above, and enables more aggressive optimizations and targets lower image quality.
-
-Optimization is improved when a JBIG2 encoder is available and when
-``pngquant`` is installed. If either of these components are missing,
-then some types of images cannot be optimized.
-
-The types of optimization available may expand over time. By default,
-OCRmyPDF compresses data streams inside PDFs, and will change
-inefficient compression modes to more modern versions. A program like
-``qpdf`` can be used to change encodings, e.g. to inspect the internals
-for a PDF.
-
-.. code-block:: bash
-
-    ocrmypdf --optimize 3 in.pdf out.pdf  # Make it small
-
-Some users may consider enabling lossy JBIG2. See: :ref:`jbig2-lossy`.
-
-.. note::
-
-    Image processing and PDF/A conversion can also introduce lossy transformations
-    to your PDF images, even when ``--optimize 1`` is in use.
-
-
-Digitally signed PDFs
-=====================
-
-OCRmyPDF cannot preserve digital signatures in PDFs and also add to OCR to them.
-By default, it will refuse to modify a signed PDF regardless of other settings. You can
-override this behavior with ``--invalidate-digital-signatures``; as the name suggests,
-any digital signatures will be invalidated.
-
-OCRmyPDF cannot open documents that are encrypted with a digital certificate.
-
-Versions of OCRmyPDF prior to 14.4.0 would invalidate existing digital signatures
-without warning.
@@ -0,0 +1,30 @@
+% 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.
@@ -1,32 +0,0 @@
-.. SPDX-FileCopyrightText: 2023 James R. Barlow
-.. SPDX-License-Identifier: CC-BY-SA-4.0
-
-============
-Design notes
-============
-
-Why doesn't OCRmyPDF use PyTesseract?
-=====================================
-
-PyTesseract is a Python wrapper around the Tesseract OCR engine. When OCRmyPDF was
-first written, PyTesseract used ABI bindings to call the Tesseract library. This
-was not a good fit for OCRmyPDF because ABI bindings can be fragile.
-
-PyTesseract has since evolved calling the Tesseract executable, abandoning the ABI
-approach and using the CLI instead, just like OCRmyPDF does. If it were written from
-scratch today, OCRmyPDF might use PyTesseract.
-
-PyTesseract has more features don't particularly need PDF output, but less features
-than OCRmyPDF's API for creating PDFs.
-
-What is ``executor()``?
-=======================
-
-OCRmyPDF uses a custom concurrent executor which can support either threads or
-processes with the same interface. This is useful because OCRmyPDF can use
-either threads or processes to parallelize work, whichever is more appropriate
-for the task at hand.
-
-The interface is currently private and subject to change. In particular, if
-experiments with asyncio and anyio are successful, the interface will change.
-
@@ -0,0 +1,312 @@
+# OCRmyPDF Docker image {#docker}
+
+OCRmyPDF is also available in Docker images that packages recent
+versions of all dependencies.
+
+For users who already have Docker installed this may be an easy and
+convenient option.
+
+On platforms other than Linux, Docker runs in a virtual machine, and so
+may be less performant. You may also want to adjust the Docker virtual
+machine\'s memory and CPU allocation. On Linux, the Docker image runs
+natively and performance is comparable to a system installation.
+
+{#docker-install}
+## Installing the Docker image
+
+If you have [Docker](https://docs.docker.com/) installed on your system,
+you can install a Docker image of the latest release.
+
+If you can run this command successfully, your system is ready to
+download and execute the image:
+
+:::{code} bash
+docker run hello-world
+:::
+
+:::{list-table} Docker Images
+:header-rows: 1
+
+* - Image
+  - Architecture
+  - Description
+* - `jbarlow83/ocrmypdf-alpine`
+  - x86_64 and arm64
+  - 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 will point to the Alpine image. If you don\'t know about the difference between Alpine and Ubuntu, use this image.
+:::
+
+To install:
+
+:::{code} bash
+docker pull jbarlow83/ocrmypdf-alpine
+:::
+
+The `ocrmypdf` image is also available, but is deprecated and will be
+removed in the future.
+
+OCRmyPDF will use all available CPU cores. See the Docker documentation
+for [adjusting memory and CPU on other
+platforms](https://docs.docker.com/config/containers/resource_constraints/)
+if you are using Docker on macOS or Windows, where you may need to
+manually assign more resources. On Linux, all resources will be
+available automatically.
+
+The underlying operating system and other details in Docker images are
+considered implementation details and **subject to change at minor
+releases**. If you are modifying the image, you should pin the version
+you intend to use.
+
+## Using the Docker image on the command line
+
+**Unlike typical Docker containers**, in this section the OCRmyPDF
+Docker container is ephemeral -- it runs for one OCR job and terminates,
+just like a command line program. We are using Docker to deliver an
+application (as opposed to the more conventional case, where a Docker
+container runs as a server). For that reason we usually use the `--rm`
+argument to delete the container when it exits.
+
+:::{note}
+The image runs as a non-root user (`app`, uid/gid 1000) by default,
+rather than as root. This is a defense-in-depth measure: a flaw in
+OCRmyPDF or one of its dependencies cannot trivially act as root inside
+the container. The examples below assume **rootless Docker** or
+**Podman**; the differences for traditional *rootful* Docker are
+described separately under *Special case: rootful Docker* below.
+:::
+
+To start a Docker container (instance of the image):
+
+:::{code} bash
+docker run --rm -i jbarlow83/ocrmypdf-alpine (... all other arguments here...) - -
+:::
+
+### Recommended: pipe through stdin and stdout
+
+The easiest and most portable way to use the image is to send the input
+file on stdin and read the output from stdout. This **avoids file
+permission issues entirely** -- nothing is written to a mounted
+directory, so it does not matter which user the container runs as, nor
+whether you use rootless or rootful Docker. For convenience, create a
+shell alias to hide the Docker command:
+
+:::{code} bash
+alias docker_ocrmypdf='docker run --rm -i jbarlow83/ocrmypdf-alpine'
+docker_ocrmypdf --version  # runs docker version
+docker_ocrmypdf - - <input.pdf >output.pdf
+:::
+
+Or in the wonderful [fish shell](https://fishshell.com/):
+
+:::{code} fish
+alias docker_ocrmypdf 'docker run --rm -i jbarlow83/ocrmypdf-alpine'
+funcsave docker_ocrmypdf
+:::
+
+{#docker-volumes}
+### Bind-mounted volumes
+
+If you would rather mount a directory and pass file paths, you need to
+consider which user owns the files OCRmyPDF writes back into that
+directory. The image's default working directory is `/data`, so mounting
+your files there lets you pass plain relative paths without an explicit
+`--workdir`. Because the container runs as the non-root `app` user, the
+right invocation otherwise depends on your container runtime.
+
+**Rootless Docker (the assumed default).** Your own account runs the
+daemon, so the container's `root` maps back to *your* unprivileged host
+user, while every other container uid -- including the image's default
+`app`/1000 -- maps to a *subordinate* uid. A directory you own on the
+host therefore appears owned by `root` inside the container, so the
+default `app` user usually **cannot write to it at all**. Run the job as
+container-`root`, which under rootless Docker is still your ordinary host
+user, so the write succeeds and the output is owned by you:
+
+:::{code} bash
+alias docker_ocrmypdf='docker run --rm -i --user 0:0 -v "$PWD:/data" jbarlow83/ocrmypdf-alpine'
+docker_ocrmypdf input.pdf output.pdf
+:::
+
+**Podman.** Podman provides `--userns keep-id`, which maps your host uid
+straight through into the container. Combined with `--user`, you run as
+your own uid and own the output directly, otherwise you may get access
+errors because the user ID is not mapped to the same UID as on the host:
+
+:::{code} bash
+alias podman_ocrmypdf='podman run --rm -i --user "$(id -u):$(id -g)" --userns keep-id -v "$PWD:/data" jbarlow83/ocrmypdf-alpine'
+podman_ocrmypdf input.pdf output.pdf
+:::
+
+If you have SELinux enabled, you may additionally need to add the `:Z` [suffix to
+the
+volume](https://docs.podman.io/en/stable/markdown/podman-run.1.html#volume-v-source-volume-host-dir-container-dir-options)
+or disable SELinux for the container using
+`--security-opt label=disable`, which is suggested for system files as
+they should not be re-labelled. Please refer to the „Note" section at
+the end of the linked podman documentation for details. This results in
+the following full command:
+
+:::{code} bash
+alias podman_ocrmypdf='podman run --rm -i --user "$(id -u):$(id -g)" --userns keep-id -v "$PWD:/data" --security-opt label=disable jbarlow83/ocrmypdf-alpine'
+podman_ocrmypdf input.pdf output.pdf
+:::
+
+{#docker-rootful}
+### Special case: rootful Docker
+
+With a traditional root daemon, container uid *N* is the *same* uid *N*
+on the host. Running the container as root would therefore fill your
+mounted directory with root-owned files and -- more importantly -- a
+container escape would run as real host root. Drop to your own uid so the
+output is owned by you and the process stays unprivileged:
+
+:::{code} bash
+alias docker_ocrmypdf='docker run --rm -i --user "$(id -u):$(id -g)" -v "$PWD:/data" jbarlow83/ocrmypdf-alpine'
+docker_ocrmypdf input.pdf output.pdf
+:::
+
+The non-root default and the `--user` override both reduce the risk here,
+but rootless Docker or Podman remain the safer choice when available.
+
+{#docker-lang-packs}
+## Adding languages to the Docker image
+
+By default the Docker image includes English, German, Simplified
+Chinese, French, Portuguese and Spanish, the most popular languages for
+OCRmyPDF users based on feedback. You may add other languages by
+creating a new Dockerfile based on the public one.
+
+:::{code} dockerfile
+FROM jbarlow83/ocrmypdf
+
+# The image runs as the non-root "app" user, so switch back to root for
+# build steps that install packages, then drop back to "app".
+USER root
+# Example: add Italian
+RUN apt-get update && apt-get install -y tesseract-ocr-ita
+USER app
+:::
+
+To install language packs (training data) such as the
+[tessdata\_best](https://github.com/tesseract-ocr/tessdata_best) suite
+or custom data, you first need to determine the version of Tesseract
+data files, which may differ from the Tesseract program version. Use
+this command to determine the data file version:
+
+:::{code} bash
+docker run -i --rm --entrypoint /bin/ls jbarlow83/ocrmypdf /usr/share/tesseract-ocr
+:::
+
+As of 2021, the data file version is probably `4.00`.
+
+You can then add new data with either a Dockerfile:
+
+:::{code} dockerfile
+FROM jbarlow83/ocrmypdf:{TAG}
+
+# Example: add a tessdata_best file
+COPY chi_tra_vert.traineddata /usr/share/tesseract-ocr/<data version>/tessdata/
+:::
+
+When creating your own image, you should always pin a specific version
+of the OCRmyPDF Docker image. This ensures that your image will not
+break when a new version of OCRmyPDF is released.
+
+Alternately, you can copy training data into a Docker container as
+follows:
+
+:::{code} 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. Because the image runs as
+the non-root `app` user, switch to `USER root` for any build steps that
+require root (installing packages, writing to system directories) and
+back to `USER app` afterwards, as shown in the language pack example
+above.
+
+Note that the Docker image is subject to change at any time. For
+example, the base image may be updated to a newer version of Ubuntu or
+Debian. Such changes will be noted in the release notes but might occur
+at minor versions releases, unless the way a \"casual\" user of the
+Docker image is affected.
+
+If you extend the Docker image, you should pin a specific version of the
+OCRmyPDF Docker image.
+
+Executing the test suite
+------------------------
+
+The OCRmyPDF test suite is installed with image. To run it:
+
+:::{code} bash
+docker run --rm --workdir /app --entrypoint python jbarlow83/ocrmypdf -m pytest
+:::
+
+Accessing the shell
+-------------------
+
+To use the shell in the Docker image:
+
+:::{code} bash
+docker run -it --entrypoint sh jbarlow83/ocrmypdf-alpine
+:::
+
+This shell runs as the non-root `app` user. If you need root inside the
+container -- for example to install extra packages with `apk` or `apt` --
+add `--user root`:
+
+:::{code} bash
+docker run -it --user root --entrypoint sh jbarlow83/ocrmypdf-alpine
+:::
+
+Using the OCRmyPDF web service wrapper
+--------------------------------------
+
+The OCRmyPDF Docker image includes an example, barebones HTTP web
+service. The webservice may be launched as follows:
+
+:::{code} bash
+docker run --entrypoint python -p 5000:5000 jbarlow83/ocrmypdf /app/webservice.py
+:::
+
+We omit the `--rm` parameter so that the container will not be
+automatically deleted when it exits.
+
+This will configure the machine to listen on port 5000. On Linux
+machines this is port 5000 of localhost. On macOS or Windows machines
+running Docker, this is port 5000 of the virtual machine that runs your
+Docker images. You can find its IP address using the command
+`docker-machine ip`.
+
+Unlike command line usage this program will open a socket and wait for
+connections.
+
+:::{warning}
+The OCRmyPDF web service wrapper is intended for demonstration or
+development. It provides no security, no authentication, no protection
+against denial of service attacks, and no load balancing. The default
+Flask WSGI server is used, which is intended for development only. The
+server is single-threaded and so can respond to only one client at a
+time. While running OCR, it cannot respond to any other clients.
+:::
+
+Clients must keep their open connection while waiting for OCR to
+complete. This may entail setting a long timeout; this interface is more
+useful for internal HTTP API calls.
+
+Unlike the rest of OCRmyPDF, this web service is licensed under the
+Affero GPLv3 (AGPLv3) since Ghostscript is also licensed in this way.
+
+In addition to the above, please read our
+`general remarks on using OCRmyPDF as a service <ocr-service>`{.interpreted-text
+role="ref"}.
@@ -1,231 +0,0 @@
-.. SPDX-FileCopyrightText: 2022 James R. Barlow
-..
-.. SPDX-License-Identifier: CC-BY-SA-4.0
-
-.. _docker:
-
-=====================
-OCRmyPDF Docker image
-=====================
-
-OCRmyPDF is also available in Docker images that packages recent
-versions of all dependencies.
-
-For users who already have Docker installed this may be an easy and
-convenient option.
-
-On platforms other than Linux, Docker runs in a virtual machine, and so may
-be less performant. You may also want to adjust the Docker virtual machine's
-memory and CPU allocation. On Linux, the Docker image runs natively and
-performance is comparable to a system installation.
-
-.. _docker-install:
-
-Installing the Docker image
-===========================
-
-If you have `Docker <https://docs.docker.com/>`__ installed on your
-system, you can install a Docker image of the latest release.
-
-If you can run this command successfully, your system is ready to download and
-execute the image:
-
-.. code-block:: bash
-
-   docker run hello-world
-
-.. list-table:: Docker images
-   :width: 30 20 50
-   :header-rows: 1
-
-   * - Image
-     - Architecture
-     - Description
-   * - ``jbarlow83/ocrmypdf-alpine``
-     - x86_64 and arm64
-     - Recommended image, based on Alpine Linux.
-   * - ``jbarlow83/ocrmypdf-ubuntu``
-     - x86_64 and arm64
-     - Alternate image, based on Ubuntu. When the Alpine image is considered
-       stable and available for arm64, this image will be deprecated.
-   * - ``jbarlow83/ocrmypdf``
-     - x86_64 and arm64
-     - Currently an alias for ocrmypdf-ubuntu. When the Alpine image is
-       considered stable and available for arm64, this name point to the
-       Alpine image. If you don't about the difference between Alpine and
-       Ubuntu, use this image.
-
-To install:
-
-.. code-block:: bash
-
-   docker pull jbarlow83/ocrmypdf-alpine
-
-The ``ocrmypdf`` image is also available, but is deprecated and will be removed
-in the future.
-
-OCRmyPDF will use all available CPU cores. See the Docker documentation for
-`adjusting memory and CPU on other platforms <https://docs.docker.com/config/containers/resource_constraints/>`__.
-
-Using the Docker image on the command line
-==========================================
-
-**Unlike typical Docker containers**, in this section the OCRmyPDF Docker
-container is ephemeral – it runs for one OCR job and terminates, just like a
-command line program. We are using Docker to deliver an application (as opposed
-to the more conventional case, where a Docker container runs as a server).
-For that reason we usually use the ``--rm`` argument to delete the container
-when it exits.
-
-To start a Docker container (instance of the image):
-
-.. code-block:: bash
-
-   docker tag jbarlow83/ocrmypdf-alpine ocrmypdf
-   docker run --rm -i ocrmypdf (... all other arguments here...) - -
-
-For convenience, create a shell alias to hide the Docker command. It is
-easier to send the input file as stdin and read the output from
-stdout – **this avoids the messy permission issues with Docker entirely**.
-
-.. code-block:: bash
-
-   alias docker_ocrmypdf='docker run --rm -i ocrmypdf'
-   docker_ocrmypdf --version  # runs docker version
-   docker_ocrmypdf - - <input.pdf >output.pdf
-
-Or in the wonderful `fish shell <https://fishshell.com/>`__:
-
-.. code-block:: fish
-
-   alias docker_ocrmypdf 'docker run --rm ocrmypdf'
-   funcsave docker_ocrmypdf
-
-Alternately, you could mount the local current working directory as a
-Docker volume:
-
-.. code-block:: bash
-
-   alias docker_ocrmypdf='docker run --rm  -i --user "$(id -u):$(id -g)" --workdir /data -v "$PWD:/data" ocrmypdf'
-   docker_ocrmypdf /data/input.pdf /data/output.pdf
-
-.. _docker-lang-packs:
-
-Adding languages to the Docker image
-====================================
-
-By default the Docker image includes English, German, Simplified Chinese,
-French, Portuguese and Spanish, the most popular languages for OCRmyPDF
-users based on feedback. You may add other languages by creating a new
-Dockerfile based on the public one.
-
-.. code-block:: dockerfile
-
-   FROM jbarlow83/ocrmypdf
-
-   # Example: add Italian
-   RUN apt install tesseract-ocr-ita
-
-To install language packs (training data) such as the
-`tessdata_best <https://github.com/tesseract-ocr/tessdata_best>`_ suite or
-custom data, you first need to determine the version of Tesseract data files, which
-may differ from the Tesseract program version. Use this command to determine the data
-file version:
-
-.. code-block:: bash
-
-   docker run -i --rm --entrypoint /bin/ls jbarlow83/ocrmypdf /usr/share/tesseract-ocr
-
-As of 2021, the data file version is probably ``4.00``.
-
-You can then add new data with either a Dockerfile:
-
-.. code-block:: dockerfile
-
-   FROM jbarlow83/ocrmypdf:{TAG}
-
-   # Example: add a tessdata_best file
-   COPY chi_tra_vert.traineddata /usr/share/tesseract-ocr/<data version>/tessdata/
-
-When creating your own image, you should always pin a specific version of the
-OCRmyPDF Docker image. This ensures that your image will not break when a new
-version of OCRmyPDF is released.
-
-Alternately, you can copy training data into a Docker container as follows:
-
-.. code-block:: bash
-
-   docker cp mycustomtraining.traineddata name_of_container:/usr/share/tesseract-ocr/<tesseract version>/tessdata/
-
-Extending the Docker image
-==========================
-
-You can extend the Docker image with your own customizations, similar to the way
-it is extended to add language packs.
-
-Note that the Docker image is subject to change at any time. For example, the base
-image may be updated to a newer version of Ubuntu or Debian. Such changes will be
-noted in the release notes but might occur at minor versions releases, unless the
-way a "casual" user of the Docker image is affected.
-
-If you extend the Docker image, you should pin a specific version of the OCRmyPDF
-Docker image.
-
-Executing the test suite
-========================
-
-The OCRmyPDF test suite is installed with image. To run it:
-
-.. code-block:: bash
-
-   docker run --rm --entrypoint python  jbarlow83/ocrmypdf -m pytest
-
-Accessing the shell
-===================
-
-To use the shell in the Docker image:
-
-.. code-block:: bash
-
-   docker run -it --entrypoint sh  jbarlow83/ocrmypdf
-
-Using the OCRmyPDF web service wrapper
-======================================
-
-The OCRmyPDF Docker image includes an example, barebones HTTP web
-service. The webservice may be launched as follows:
-
-.. code-block:: bash
-
-   docker run --entrypoint python -p 5000:5000  jbarlow83/ocrmypdf webservice.py
-
-We omit the ``--rm`` parameter so that the container will not be
-automatically deleted when it exits.
-
-This will configure the machine to listen on port 5000. On Linux machines
-this is port 5000 of localhost. On macOS or Windows machines running
-Docker, this is port 5000 of the virtual machine that runs your Docker
-images. You can find its IP address using the command ``docker-machine ip``.
-
-Unlike command line usage this program will open a socket and wait for
-connections.
-
-.. warning::
-
-   The OCRmyPDF web service wrapper is intended for demonstration or
-   development. It provides no security, no authentication, no
-   protection against denial of service attacks, and no load balancing.
-   The default Flask WSGI server is used, which is intended for
-   development only. The server is single-threaded and so can respond to
-   only one client at a time. While running OCR, it cannot respond to
-   any other clients.
-
-Clients must keep their open connection while waiting for OCR to
-complete. This may entail setting a long timeout; this interface is more
-useful for internal HTTP API calls.
-
-Unlike the rest of OCRmyPDF, this web service is licensed under the
-Affero GPLv3 (AGPLv3) since Ghostscript is also licensed in this way.
-
-In addition to the above, please read our
-:ref:`general remarks on using OCRmyPDF as a service <ocr-service>`.
@@ -0,0 +1,79 @@
+% SPDX-FileCopyrightText: 2022 James R. Barlow
+% SPDX-License-Identifier: CC-BY-SA-4.0
+
+# Common error messages
+
+## Page already has text
+
+:::{code}
+ERROR -    1: page already has text! – aborting (use --force-ocr to force OCR)
+:::
+
+You ran ocrmypdf on a file that already contains printable text or a
+hidden OCR text layer (it can\'t quite tell the difference). You
+probably don\'t want to do this, because the file is already searchable.
+
+As the error message suggests, your options are:
+
+-   `ocrmypdf --force-ocr` to
+    `rasterize <raster-vector>`{.interpreted-text role="ref"} all vector
+    content and run OCR on the images. This is useful if a previous OCR
+    program failed, or if the document contains a text watermark.
+-   `ocrmypdf --skip-text` to skip OCR and other processing on any pages
+    that contain text. Text pages will be copied into the output PDF
+    without modification.
+-   `ocrmypdf --redo-ocr` to scan the file for any existing OCR
+    (non-printing text), remove it, and do OCR again. This is one way to
+    take advantage of improvements in OCR accuracy. Printable vector
+    text is excluded from OCR, so this can be used on files that contain
+    a mix of digital and scanned files.
+
+## Input file \'filename\' is not a valid PDF
+
+OCRmyPDF checks files with pikepdf, a library that in turn uses libqpdf
+to fixes errors in PDFs, before it tries to work on them. In most cases
+this happens because the PDF is corrupt and truncated (incomplete file
+copying) and not much can be done.
+
+You can try rewriting the file with Ghostscript:
+
+:::{code} bash
+gs -o output.pdf -dSAFER -sDEVICE=pdfwrite input.pdf
+:::
+
+`pdftk` can also rewrite PDFs:
+
+:::{code} bash
+pdftk input.pdf cat output output.pdf
+:::
+
+Sometimes Acrobat can repair PDFs with its [Preflight
+tool](https://helpx.adobe.com/acrobat/using/correcting-problem-areas-preflight-tool.html).
+
+(tesseract-config-missing)=
+
+## Tesseract cannot open its config file \'hocr\' or \'txt\'
+
+:::{code}
+ERROR - Tesseract cannot open its config file 'hocr'.
+:::
+
+OCRmyPDF asks Tesseract to produce `hocr` and `txt` output. Tesseract
+reads the instructions for these output formats from configuration files
+named `hocr` and `txt` that live in the `configs/` subdirectory of its
+`tessdata` folder. If those files are missing, Tesseract prints
+`read_params_file: Can't open hocr`, exits without error, and produces no
+output.
+
+This usually happens when a `tessdata` directory was assembled by hand --
+for example, by downloading individual `.traineddata` files from
+[tessdata_best](https://github.com/tesseract-ocr/tessdata_best) and
+pointing `TESSDATA_PREFIX` at them -- because those repositories do not
+include the `configs/` directory. A complete Tesseract installation from
+your operating system\'s package manager includes it.
+
+To fix this, ensure the `configs/hocr` and `configs/txt` files exist in
+the `tessdata` directory that Tesseract is using. Copying the `configs/`
+directory from a full Tesseract installation is sufficient. See
+{envvar}`TESSDATA_PREFIX` for more on selecting an alternate `tessdata`
+folder.
@@ -1,57 +0,0 @@
-.. SPDX-FileCopyrightText: 2022 James R. Barlow
-..
-.. SPDX-License-Identifier: CC-BY-SA-4.0
-
-=====================
-Common error messages
-=====================
-
-Page already has text
-=====================
-
-.. code-block::
-
-   ERROR -    1: page already has text! – aborting (use --force-ocr to force OCR)
-
-You ran ocrmypdf on a file that already contains printable text or a
-hidden OCR text layer (it can't quite tell the difference). You probably
-don't want to do this, because the file is already searchable.
-
-As the error message suggests, your options are:
-
-  ``ocrmypdf --force-ocr`` to :ref:`rasterize <raster-vector>` all
-   vector content and run OCR on the images. This is useful if a
-   previous OCR program failed, or if the document contains a text
-   watermark.
-  ``ocrmypdf --skip-text`` to skip OCR and other processing on any
-   pages that contain text. Text pages will be copied into the output
-   PDF without modification.
-  ``ocrmypdf --redo-ocr`` to scan the file for any existing OCR
-   (non-printing text), remove it, and do OCR again. This is one way
-   to take advantage of improvements in OCR accuracy. Printable vector
-   text is excluded from OCR, so this can be used on files that contain
-   a mix of digital and scanned files.
-
-
-Input file 'filename' is not a valid PDF
-========================================
-
-OCRmyPDF checks files with pikepdf, a library that in turn uses libqpdf to fixes
-errors in PDFs, before it tries to work on them. In most cases this happens
-because the PDF is corrupt and truncated (incomplete file copying) and not much
-can be done.
-
-You can try rewriting the file with Ghostscript:
-
-.. code-block:: bash
-
-    gs -o output.pdf -dSAFER -sDEVICE=pdfwrite input.pdf
-
-``pdftk`` can also rewrite PDFs:
-
-.. code-block:: bash
-
-    pdftk input.pdf cat output output.pdf
-
-Sometimes Acrobat can repair PDFs with its `Preflight
-tool <https://helpx.adobe.com/acrobat/using/correcting-problem-areas-preflight-tool.html>`__.
@@ -0,0 +1,57 @@
+% SPDX-FileCopyrightText: 2022 James R. Barlow
+% SPDX-License-Identifier: CC-BY-SA-4.0
+
+# OCRmyPDF documentation
+
+:::{figure} images/logo.svg
+:::
+
+OCRmyPDF adds an optical character recognition (OCR) text layer to scanned PDF
+files, allowing them to be searched.
+
+PDF is the best format for storing and exchanging scanned documents.
+Unfortunately, PDFs can be difficult to modify. OCRmyPDF makes it easy to apply
+image processing and OCR (recognized, searchable text) to existing PDFs.
+
+```{toctree}
+:maxdepth: 1
+
+introduction
+releasenotes/index
+installation
+languages
+jbig2
+```
+
+```{toctree}
+:caption: Usage
+:maxdepth: 2
+
+cookbook
+optimizer
+docker
+advanced
+batch
+cloud
+performance
+pdfsecurity
+errors
+```
+
+```{toctree}
+:caption: Developers
+:maxdepth: 2
+
+api
+plugins
+apiref
+design_notes
+contributing
+maintainers
+```
+
+# Indices and tables
+
+- {ref}`genindex`
+- {ref}`modindex`
+- {ref}`search`
@@ -1,56 +0,0 @@
-.. SPDX-FileCopyrightText: 2022 James R. Barlow
-..
-.. SPDX-License-Identifier: CC-BY-SA-4.0
-
-OCRmyPDF documentation
-======================
-
-.. figure:: images/logo.svg
-
-OCRmyPDF adds an optical character recognition (OCR) text layer to scanned PDF
-files, allowing them to be searched.
-
-PDF is the best format for storing and exchanging scanned documents.
-Unfortunately, PDFs can be difficult to modify. OCRmyPDF makes it easy to apply
-image processing and OCR (recognized, searchable text) to existing PDFs.
-
-.. toctree::
-   :maxdepth: 1
-
-   introduction
-   release_notes
-   installation
-   languages
-   jbig2
-
-.. toctree::
-   :caption: Usage
-   :maxdepth: 2
-
-   cookbook
-   optimizer
-   docker
-   advanced
-   batch
-   cloud
-   performance
-   pdfsecurity
-   errors
-
-.. toctree::
-   :caption: Developers
-   :maxdepth: 2
-
-   api
-   plugins
-   apiref
-   design_notes
-   contributing
-   maintainers
-
-Indices and tables
-==================
-
-* :ref:`genindex`
-* :ref:`modindex`
-* :ref:`search`
@@ -0,0 +1,852 @@
+---
+myst:
+  substitutions:
+    deb_12: |-
+      :::{image} https://repology.org/badge/version-for-repo/debian_12/ocrmypdf.svg
+      :alt: Debian 12
+      :::
+    deb_13: |-
+      :::{image} https://repology.org/badge/version-for-repo/debian_13/ocrmypdf.svg
+      :alt: Debian 13
+      :::
+    deb_unstable: |-
+      :::{image} https://repology.org/badge/version-for-repo/debian_unstable/ocrmypdf.svg
+      :alt: Debian unstable
+      :::
+    fedora_40: |-
+      :::{image} https://repology.org/badge/version-for-repo/fedora_40/ocrmypdf.svg
+      :alt: Fedora 40
+      :::
+    fedora_41: |-
+      :::{image} https://repology.org/badge/version-for-repo/fedora_41/ocrmypdf.svg
+      :alt: Fedora 41
+      :::
+    fedora_rawhide: |-
+      :::{image} https://repology.org/badge/version-for-repo/fedora_rawhide/ocrmypdf.svg
+      :alt: Fedora Rawhide
+      :::
+    latest: |-
+      :::{image} https://img.shields.io/pypi/v/ocrmypdf.svg
+      :alt: OCRmyPDF latest released version on PyPI
+      :::
+    ubu_2204: |-
+      :::{image} https://repology.org/badge/version-for-repo/ubuntu_22_04/ocrmypdf.svg
+      :alt: Ubuntu 22.04 LTS
+      :::
+    ubu_2404: |-
+      :::{image} https://repology.org/badge/version-for-repo/ubuntu_24_04/ocrmypdf.svg
+      :alt: Ubuntu 24.04 LTS
+      :::
+---
+
+% SPDX-FileCopyrightText: 2022 James R. Barlow
+% SPDX-License-Identifier: CC-BY-SA-4.0
+
+# Installing OCRmyPDF
+
+(latest)=
+
+The easiest way to install OCRmyPDF is to follow the steps for your operating
+system/platform. This version may be out of date, however.
+
+These platforms have one-liner installs:
+
+:::{list-table}
+:header-rows: 0
+
+* - Homebrew (macOS and Linux)
+  - ``brew install ocrmypdf``
+* - Debian, Ubuntu
+  - ``apt install ocrmypdf``
+* - Windows Subsystem for Linux
+  - ``apt install ocrmypdf``
+* - Fedora
+  - ``dnf install ocrmypdf tesseract-osd``
+* - macOS (MacPorts)
+  - ``port install ocrmypdf``
+* - FreeBSD
+  - ``pkg install textproc/py-ocrmypdf``
+* - Snap (snapcraft packaging)
+  - ``snap install ocrmypdf``
+:::
+
+More detailed procedures are outlined below. If you want to do a manual
+install, or install a more recent version than your platform provides, read on.
+
+:::{contents} Platform-specific steps
+:depth: 2
+:local: true
+:::
+
+## Installing on Linux
+
+### Debian and Ubuntu 22.04 or newer
+
+:::{list-table}
+:header-rows: 1
+
+* - OCRmyPDF versions in Debian & Ubuntu
+* - {{ latest }}
+* - {{ deb_12 }} {{ deb_13 }} {{ deb_unstable }}
+* - {{ ubu_2204 }} {{ ubu_2404 }}
+:::
+
+Users of Debian or Ubuntu may simply
+
+```bash
+apt install ocrmypdf
+```
+
+As indicated in the table above, Debian and Ubuntu releases may lag
+behind the latest version. If the version available for your platform is
+out of date, you could opt to install the latest version from source.
+See [Installing HEAD revision from
+sources](#installing-head-revision-from-sources).
+
+For full details on version availability for your platform, check the
+[Debian Package Tracker](https://tracker.debian.org/pkg/ocrmypdf) or
+[Ubuntu launchpad.net](https://launchpad.net/ocrmypdf).
+
+:::{note}
+OCRmyPDF for Debian and Ubuntu currently omit the JBIG2 encoder.
+OCRmyPDF works fine without it but will produce larger output files.
+All JBIG2 patents expired in 2017, so if you build jbig2enc from source,
+OCRmyPDF will automatically detect it on the `PATH`.
+To add JBIG2 encoding, see {ref}`jbig2`.
+:::
+
+### Fedora
+
+:::{list-table}
+:header-rows: 1
+
+* - OCRmyPDF version
+* - {{latest}}
+* - {{fedora_40}} {{fedora_41}} {{fedora_rawhide}}
+:::
+
+Users of Fedora may simply
+
+```bash
+dnf install ocrmypdf tesseract-osd
+```
+
+For full details on version availability, check the [Fedora Package
+Tracker](https://packages.fedoraproject.org/pkgs/ocrmypdf/ocrmypdf/).
+
+If the version available for your platform is out of date, you could opt
+to install the latest version from source. See [Installing HEAD revision
+from sources](#installing-head-revision-from-sources).
+
+:::{note}
+OCRmyPDF for Fedora currently omits the JBIG2 encoder. All JBIG2 patents
+expired in 2017. OCRmyPDF works fine without it but will produce larger
+output files. If you build jbig2enc from source, OCRmyPDF will automatically
+detect it on the `PATH`. To add JBIG2 encoding, see {ref}`jbig2`.
+:::
+
+(ubuntu-lts-latest)=
+
+### RHEL 9
+
+Prepare the environment by getting Python 3.12:
+
+```bash
+dnf install python3.12 python3.12-pip
+```
+
+Then, follow [Requirements for pip and HEAD install](#requirements-for-pip-and-head-install) to install dependencies:
+
+```bash
+dnf install ghostscript tesseract
+```
+
+and build ocrmypdf in virtual environment:
+
+```bash
+python3.12 -m venv .venv
+```
+
+To add JBIG2 encoding, see {ref}`Installing the JBIG2 encoder <jbig2>`.
+
+Note Fedora packages for language data haven't been branched for RHEL/EPEL, but you can get traineddata files directly from [tesseract](https://github.com/tesseract-ocr/tessdata/) and place them in `/usr/share/tesseract/tessdata`.
+
+### Installing the latest version on Ubuntu 22.04/24.04 LTS
+
+Ubuntu includes an older version of OCRmyPDF - you can install that with
+`apt install ocrmypdf`. To install the latest version, we recommend using uv:
+
+```bash
+# Install system dependencies first
+sudo apt-get update
+sudo apt-get -y install ocrmypdf
+
+# Install uv and upgrade to the latest OCRmyPDF
+pip install uv
+uv pip install --user --upgrade ocrmypdf
+```
+
+Alternatively, use Homebrew on Linux for a full-featured installation (see below).
+
+To add JBIG2 encoding, see {ref}`jbig2`.
+
+### Ubuntu 20.04 LTS (and other older distributions)
+
+:::{note}
+Ubuntu 20.04 is approaching end of life. Consider upgrading to Ubuntu 22.04 or 24.04 LTS.
+:::
+
+For older distributions, the most convenient way to install a recent version of
+OCRmyPDF is to use Homebrew on Linux:
+
+```bash
+brew install ocrmypdf
+```
+
+See {ref}`homebrew-linux` for more information on using Homebrew on Linux.
+
+### Arch Linux (AUR)
+
+:::{image} https://repology.org/badge/version-for-repo/aur/ocrmypdf.svg
+:alt: ArchLinux
+:target: https://repology.org/metapackage/ocrmypdf
+:::
+
+There is an [Arch User Repository (AUR) package for OCRmyPDF](https://aur.archlinux.org/packages/ocrmypdf/).
+
+Installing AUR packages as root is not allowed, so you must first [setup a
+non-root user](https://wiki.archlinux.org/index.php/Users_and_groups#User_management) and
+[configure sudo](https://wiki.archlinux.org/index.php/Sudo#Configuration).
+The standard Docker image, `archlinux/base:latest`, does **not** have a
+non-root user configured, so users of that image must follow these guides. If
+you are using a VM image, such as [the official Vagrant image](https://app.vagrantup.com/archlinux/boxes/archlinux), this work may already
+be completed for you.
+
+Next you should install the [base-devel package group](https://archlinux.org/packages/core/any/base-devel/). This includes the
+standard tooling needed to build packages, such as a compiler and binary tools.
+
+```bash
+sudo pacman -S --needed base-devel
+```
+
+Now you are ready to install the OCRmyPDF package.
+
+```bash
+curl -O https://aur.archlinux.org/cgit/aur.git/snapshot/ocrmypdf.tar.gz
+tar xvzf ocrmypdf.tar.gz
+cd ocrmypdf
+makepkg -sri
+```
+
+At this point you will have a working install of OCRmyPDF, but the Tesseract
+install won’t include any OCR language data. You can install [the
+tesseract-data package group](https://www.archlinux.org/groups/any/tesseract-data/) to add all supported
+languages, or use that package listing to identify the appropriate package for
+your desired language.
+
+```bash
+sudo pacman -S tesseract-data-eng
+```
+
+As an alternative to this manual procedure, consider using an [AUR helper](https://wiki.archlinux.org/index.php/AUR_helpers). Such a tool will
+automatically fetch, build and install the AUR package, resolve dependencies
+(including dependencies on AUR packages), and ease the upgrade procedure.
+
+If you have any difficulties with installation, check the repository package
+page.
+
+:::{note}
+The OCRmyPDF AUR package currently omits the JBIG2 encoder. OCRmyPDF works
+fine without it but will produce larger output files. The encoder is
+available from [the jbig2enc-git AUR package](https://aur.archlinux.org/packages/jbig2enc-git/) and may be installed
+using the same series of steps as for the installation OCRmyPDF AUR
+package. Alternatively, it may be built manually from source following the
+instructions in {ref}`Installing the JBIG2 encoder <jbig2>`. If JBIG2 is
+installed, OCRmyPDF 7.0.0 and later will automatically detect it.
+:::
+
+### Alpine Linux
+
+:::{image} https://repology.org/badge/version-for-repo/alpine_edge/ocrmypdf.svg
+:alt: Alpine Linux
+:target: https://repology.org/metapackage/ocrmypdf
+:::
+
+To install OCRmyPDF for Alpine Linux:
+
+```bash
+apk add ocrmypdf
+```
+
+### Gentoo Linux
+
+:::{image} https://repology.org/badge/version-for-repo/gentoo_ovl_guru/ocrmypdf.svg
+:alt: Gentoo Linux
+:target: https://repology.org/metapackage/ocrmypdf
+:::
+
+To install OCRmyPDF on Gentoo Linux, use the following commands:
+
+```bash
+eselect repository enable guru
+emaint sync --repo guru
+emerge --ask app-text/OCRmyPDF
+```
+
+### Other Linux packages
+
+See the
+[Repology](https://repology.org/metapackage/ocrmypdf/versions) page.
+
+In general, first install the OCRmyPDF package for your system, then
+optionally use the procedure [Installing with Python
+pip](#installing-with-python-pip) to install a more recent version.
+
+(homebrew-linux)=
+
+## Installing with Homebrew (macOS and Linux)
+
+:::{image} https://img.shields.io/homebrew/v/ocrmypdf.svg
+:alt: homebrew
+:target: https://formulae.brew.sh/formula/ocrmypdf
+:::
+
+[Homebrew](https://brew.sh) provides a full-featured OCRmyPDF installation
+on both macOS and Linux with all recommended dependencies. This is often
+the easiest way to get a complete, up-to-date installation.
+
+```bash
+brew install ocrmypdf
+```
+
+This includes Tesseract, Ghostscript, and all required dependencies. English
+language support is included by default. For other languages:
+
+```bash
+brew install tesseract-lang  # Optional: Install all language packs
+```
+
+:::{tip}
+**For Linux users:** Homebrew on Linux is an excellent choice when your
+distribution's package is outdated or missing optional dependencies like
+jbig2enc, pngquant, or unpaper. Homebrew provides a consistent, full-featured
+installation that works across many Linux distributions.
+
+Install Homebrew on Linux: https://brew.sh
+:::
+
+## Installing on macOS
+
+### Homebrew
+
+See {ref}`homebrew-linux` above - the installation is identical on macOS.
+
+### MacPorts
+
+:::{image} https://img.shields.io/badge/dynamic/json?url=https%3A%2F%2Fports.macports.org%2Fapi%2Fv1%2Fports%2Focrmypdf%2F%3Fformat%3Djson&query=version&label=MacPorts
+:alt: Macports Version Information
+:target: https://ports.macports.org/port/ocrmypdf
+:::
+
+OCRmyPDF is included in MacPorts:
+
+```bash
+sudo port install ocrmypdf
+```
+
+Note that while this will install tesseract you will need to install
+the appropriate tesseract [language ports](https://ports.macports.org/search/?selected_facets=categories_exact%3Atextproc&installed_file=&q=tesseract&name=on).
+
+### Manual installation on macOS
+
+These instructions are for installing a more current version of OCRmyPDF than
+is available from Homebrew. Note that Homebrew versions usually track
+releases fairly closely.
+
+If it's not already present, [install Homebrew](http://brew.sh/).
+
+Update Homebrew and install dependencies:
+
+```bash
+brew update
+```
+
+Install or upgrade the required Homebrew packages, if any are missing.
+To do this, use `brew edit ocrmypdf` to obtain a recent list of Homebrew
+dependencies. You could also check the `.workflows/build.yml`.
+
+This will include the English, French, German and Spanish language
+packs. If you need other languages you can optionally install them all:
+
+(macos-all-languages)=
+
+> ```bash
+> brew install tesseract-lang  # Option 2: for all language packs
+> ```
+
+Install uv and OCRmyPDF:
+
+```bash
+pip install uv
+uv pip install --user ocrmypdf
+```
+
+The command line program should now be available:
+
+```bash
+ocrmypdf --help
+```
+
+## Installing on Windows
+
+### Native Windows
+
+% If you have a Windows that is not the Home edition, you can use Windows Sandbox to test on a blank Windows instance.
+% https://learn.microsoft.com/en-us/windows/security/application-security/application-isolation/windows-sandbox/
+
+:::{note}
+Administrator privileges will be required for some of these steps.
+:::
+
+You must install the following for Windows:
+
+- Python 64-bit
+- Tesseract 64-bit
+- Ghostscript 64-bit
+
+Using the [winget](https://docs.microsoft.com/en-us/windows/package-manager/winget/)
+package manager:
+
+- `winget install -e --id Python.Python.3.12`
+- `winget install -e --id UB-Mannheim.TesseractOCR`
+
+You will need to install Ghostscript manually, [since it does not support automated
+installs anymore](https://artifex.com/news/ghostscript-10.01.0-disabling-silent-install-option).
+
+- [Ghostscript download page](https://ghostscript.com/releases/gsdnld.html).\`
+
+(Or alternately, using the [Chocolatey](https://chocolatey.org/) package manager, install
+the following when running in an Administrator command prompt):
+
+- `choco install python3`
+- `choco install --pre tesseract`
+- `choco install pngquant` (optional)
+
+Either set of commands will install the required software. At the moment there is no
+single command to install Windows.
+
+You may then use `pip` to install ocrmypdf. (This can performed by a user or
+Administrator.):
+
+- `python3 -m pip install ocrmypdf`
+
+% The Windows Python versions do not place any python or python3 executable in the path.
+% They add the py launcher to the path:
+% https://docs.python.org/3/using/windows.html#python-launcher-for-windows
+
+If you installed Python using WinGet, then use the following command instead:
+
+- `py -m pip install ocrmypdf`
+
+and use:
+
+- `py -m ocrmypdf`
+
+To start OCRmyPDF.
+
+If you intend to use more Python software on your Windows machine, consider the use of
+[pipx](https://pipx.pypa.io/stable/) or a similar tool to create isolated Python
+environments for each Python software that you want to use.
+
+OCRmyPDF will check the Windows Registry and standard locations in your Program Files
+for third party software it needs (specifically, Tesseract and Ghostscript). To
+override the versions OCRmyPDF selects, you can modify the `PATH` environment
+variable. [Follow these directions](https://www.computerhope.com/issues/ch000549.htm#dospath)
+to change the PATH.
+
+:::{warning}
+32-bit Windows is not supported.
+:::
+
+### Windows Subsystem for Linux
+
+1. Install Ubuntu 22.04 for Windows Subsystem for Linux, if not already installed.
+2. Follow the procedure to install {ref}`OCRmyPDF on Ubuntu 22.04 <ubuntu-lts-latest>`.
+3. Open the Windows command prompt and create a symlink:
+
+```powershell
+wsl sudo ln -s  /home/$USER/.local/bin/ocrmypdf /usr/local/bin/ocrmypdf
+```
+
+Then confirm that the expected version from PyPI ({{ latest }}) is installed:
+
+```powershell
+wsl ocrmypdf --version
+```
+
+You can then run OCRmyPDF in the Windows command prompt or Powershell, prefixing
+`wsl`, and call it from Windows programs or batch files.
+
+### Cygwin64
+
+First install the the following prerequisite Cygwin packages using `setup-x86_64.exe`:
+
+```
+python311 (or later)
+python3?-devel
+python3?-pip
+python3?-lxml
+python3?-imaging
+
+   (where 3? means match the version of python3 you installed)
+
+gcc-g++
+ghostscript
+libexempi3
+libexempi-devel
+libffi6
+libffi-devel
+pngquant
+qpdf
+libqpdf-devel
+tesseract-ocr
+tesseract-ocr-devel
+```
+
+Then open a Cygwin terminal (i.e. `mintty`), run the following commands. Note
+that if you are using the version of `pip` that was installed with the Cygwin
+Python package, the command name will be `pip3`. If you have since updated
+`pip` (with, for instance `pip3 install --upgrade pip`) the the command is
+likely just `pip` instead of `pip3`:
+
+```bash
+pip3 install wheel
+pip3 install ocrmypdf
+```
+
+The optional dependency "unpaper" that is currently not available under Cygwin.
+Without it, certain options such as `--clean` will produce an error message.
+However, the OCR-to-text-layer functionality is available.
+
+### Docker
+
+You can also [Install the Docker image](docker) on Windows. Ensure that
+your command prompt can run the docker "hello world" container.
+
+## Installing on FreeBSD
+
+:::{image} https://repology.org/badge/version-for-repo/freebsd/ocrmypdf.svg
+:alt: FreeBSD
+:target: https://repology.org/project/ocrmypdf/versions
+:::
+
+```bash
+pkg install textproc/py-ocrmypdf
+```
+
+To install a more recent version, you could attempt to first install the system
+version with `pkg`, then use `pip install --user ocrmypdf`.
+
+## Installing the Docker image
+
+For some users, installing the Docker image will be easier than
+installing all of OCRmyPDF's dependencies.
+
+See [Installing the Docker image](docker) for more information.
+
+(installing-with-python-pip)=
+
+## Installing with uv (recommended)
+
+We recommend using [uv](https://docs.astral.sh/uv/) for installing OCRmyPDF from PyPI.
+uv is a fast, modern Python package manager that provides better dependency resolution
+and consistent behavior across all platforms.
+
+For best results, first install [your platform's
+version](https://repology.org/metapackage/ocrmypdf/versions) of
+`ocrmypdf` using the instructions elsewhere in this document to satisfy system
+dependencies. Then use uv to get the latest OCRmyPDF version.
+
+```bash
+# Install uv if you don't have it
+pip install uv
+
+# Install ocrmypdf in a virtual environment (recommended)
+uv venv
+source .venv/bin/activate  # On Windows: .venv\Scripts\activate
+uv pip install ocrmypdf
+
+# Or install globally
+uv pip install --system ocrmypdf
+```
+
+Use `ocrmypdf --version` to confirm what version was installed.
+
+### Installing with pip
+
+If you prefer pip, you can still use it:
+
+```bash
+pip install --user ocrmypdf
+```
+
+(If the message appears `Requirement already satisfied: ocrmypdf in...`,
+you will need to use `pip install --user --upgrade ocrmypdf`.)
+
+### Installing with pipx
+
+Some users may prefer pipx for isolated command-line tool installations:
+
+```bash
+pipx install ocrmypdf
+```
+
+Or run without permanent installation:
+
+```bash
+pipx run ocrmypdf
+```
+
+(requirements-for-pip-and-head-install)=
+
+### Requirements for pip and HEAD install
+
+OCRmyPDF currently requires these external programs and libraries to be
+installed, and must be satisfied using the operating system package
+manager. `pip` cannot provide them.
+
+:::{versionchanged} 17.0.0
+Ghostscript is now optional. pypdfium2 can be used for PDF rasterization,
+and verapdf can validate speculative PDF/A conversion.
+:::
+
+The following versions are required:
+
+- Python 3.11 or newer (3.12+ recommended)
+- Tesseract 4.1.1 or newer
+- One of: Ghostscript 9.54+ **or** pypdfium2 (Python package)
+- One of: Ghostscript 9.54+ **or** verapdf (for PDF/A output)
+- fpdf2 2.8 or newer (Python package)
+- uharfbuzz (Python package)
+- fonts-noto or equivalent (system package, recommended)
+- jbig2enc 0.29 or newer (optional)
+- pngquant 2.5 or newer (optional)
+- unpaper 6.1 (optional)
+
+:::{note}
+For the best user experience, install both Ghostscript and pypdfium2. pypdfium2 is
+faster for rasterization, while Ghostscript provides is required for certain PDF/A
+conversions.
+:::
+
+**Dependency summary:**
+
+| Feature | Option 1 | Option 2 | Notes |
+|---------|----------|----------|-------|
+| PDF rasterization | pypdfium2 (Python) | Ghostscript (binary) | pypdfium2 preferred when available |
+| PDF/A conversion | verapdf + pikepdf | Ghostscript | verapdf validates speculative conversion |
+| Text rendering | fpdf2 + uharfbuzz | - | Required |
+| OCR | tesseract-ocr | `--ocr-engine none` | Can be skipped entirely |
+
+**Minimum viable installation:**
+tesseract-ocr + (pypdfium2 OR Ghostscript) + fpdf2 + uharfbuzz
+
+**Recommended installation:**
+tesseract-ocr + pypdfium2 + Ghostscript + verapdf + fpdf2 + uharfbuzz + fonts-noto + unpaper + pngquant + jbig2enc
+
+We recommend 64-bit versions of all software. (32-bit versions are not
+supported, although on Linux, they may still work.)
+
+**fpdf2** and **uharfbuzz** are required dependencies that provide the text
+layer rendering engine. fpdf2 generates the PDF text layer, while uharfbuzz
+provides text shaping for proper multilingual support. These replace the
+legacy hOCR-based renderer. Install with: `pip install fpdf2 uharfbuzz`
+
+**fonts-noto** (or an equivalent comprehensive font package) is recommended
+for proper text rendering, especially for non-Latin scripts. OCRmyPDF bundles
+a Latin font only, and discovers the rest from the fonts installed on your
+system.
+
+- Debian/Ubuntu: `apt install fonts-noto`
+- Fedora: `dnf install google-noto-fonts-all`
+- macOS with Homebrew: Homebrew has no single Noto package; each family is a
+  separate cask. Install at least
+  `brew install --cask font-noto-sans font-noto-serif`, plus a cask per
+  additional script you OCR, for example
+  `brew install --cask font-noto-sans-arabic font-noto-sans-cjk`. Run
+  `brew search font-noto` to list them all.
+
+If OCRmyPDF warns that no installed font has glyphs for some of the text, the
+message names the characters it could not render, for example
+`'Ꮳ' U+13E3 CHEROKEE LETTER TSA`. Install the Noto font for that script — here,
+`fonts-noto-core` on Debian or `font-noto-sans-cherokee` on Homebrew. The text
+layer remains searchable and copyable either way; only its appearance when
+highlighted in a PDF viewer is affected.
+
+**pypdfium2**, if present, provides fast PDF page rasterization using
+the pdfium library (the same library used by Google Chrome). It is
+preferred over Ghostscript when available due to better performance.
+Install with: `pip install pypdfium2`
+
+**verapdf**, if present, enables fast speculative PDF/A conversion.
+OCRmyPDF attempts to create PDF/A by adding metadata and ICC profiles
+using pikepdf, then validates with verapdf. If validation passes,
+Ghostscript is skipped entirely. See your distribution's package manager
+or visit [verapdf.org](https://verapdf.org/).
+
+**jbig2enc**, if present, will be used to optimize the encoding of
+monochrome images. This can significantly reduce the file size of the
+output file. It is not required.
+[jbig2enc](https://github.com/agl/jbig2enc) is not available in some
+distributions due to historical patent concerns, but all JBIG2 patents
+expired in 2017. It can easily be built from source. To add JBIG2 encoding,
+see {ref}`jbig2`.
+
+:::{warning}
+Lossy JBIG2 encoding (`--jbig2-lossy`) has been removed in v17.0.0 due to
+well-documented risks of character substitution errors. Only lossless
+JBIG2 compression is now supported.
+:::
+
+**pngquant**, if present, is optionally used to optimize the encoding of
+PNG-style images in PDFs (actually, any that are that losslessly
+encoded) by lossily quantizing to a smaller color palette. It is only
+activated then the `--optimize` argument is `2` or `3`.
+
+**unpaper**, if present, enables the `--clean` and `--clean-final`
+command line options.
+
+These are in addition to the Python packaging dependencies, meaning that
+unfortunately, the `pip install` command cannot satisfy all of them.
+
+(installing-head-revision-from-sources)=
+
+## Installing HEAD revision from sources
+
+If you have `git` and Python 3.12 or newer installed, you can install
+from source. (Python 3.11 is supported but 3.12+ is recommended.) When the `pip` installer runs, it will alert you if
+dependencies are missing.
+
+If you prefer to build every from source, you will need to [build
+pikepdf from
+source](https://pikepdf.readthedocs.io/en/latest/installation.html#building-from-source).
+First ensure you can build and install pikepdf.
+
+We recommend using uv to install from sources:
+
+```bash
+git clone -b main https://github.com/ocrmypdf/OCRmyPDF.git
+cd OCRmyPDF
+pip install uv  # If not already installed
+uv sync
+```
+
+This creates a virtual environment and installs all dependencies. Activate
+the environment to use ocrmypdf:
+
+```bash
+source .venv/bin/activate
+ocrmypdf --help
+```
+
+Alternatively, install directly from GitHub using pip:
+
+```bash
+pip install git+https://github.com/ocrmypdf/OCRmyPDF.git
+```
+
+Or, to install in editable mode allowing customization:
+
+```bash
+git clone -b main https://github.com/ocrmypdf/OCRmyPDF.git
+cd OCRmyPDF
+pip install -e .
+```
+
+Note: `ocrmypdf` will only be accessible when the virtual environment
+is activated.
+
+To run the program:
+
+```bash
+ocrmypdf --help
+```
+
+If not yet installed, the script will notify you about dependencies that
+need to be installed. The script requires specific versions of the
+dependencies. Older version than the ones mentioned in the release notes
+are likely not to be compatible to OCRmyPDF.
+
+## Optional Features
+
+OCRmyPDF provides optional features and development tools. We recommend using `uv` as your package manager.
+
+### Installing User Features
+
+User features are available as optional dependencies. Install them with `uv` (recommended) or `pip`:
+
+```bash
+# Using uv (recommended)
+uv sync --extra watcher        # File watching service
+uv sync --extra webservice     # Streamlit web UI
+uv sync --extra watcher --extra webservice  # Multiple features
+```
+
+### Development Tools
+
+Development tools use dependency groups:
+
+```bash
+# Testing infrastructure
+uv sync --group test
+
+# Documentation building
+uv sync --group docs
+
+# Enhanced Streamlit development
+uv sync --group streamlit-dev
+
+# All development groups
+uv sync
+```
+
+**Why use uv?**
+
+- Modern, fast Python package manager
+- Required for development (testing, docs)
+- Better dependency resolution
+- Consistent across all platforms
+
+Install uv: `curl -LsSf https://astral.sh/uv/install.sh | sh` or visit https://docs.astral.sh/uv/
+
+### For development
+
+To install all of the development and test requirements:
+
+```bash
+git clone -b main https://github.com/ocrmypdf/OCRmyPDF.git
+cd OCRmyPDF
+uv sync --all-groups
+```
+
+To add JBIG2 encoding, see {ref}`jbig2`.
+
+## Shell completions
+
+Completions for `bash` and `fish` are available in the project's
+`misc/completion` folder. The `bash` completions are likely `zsh`
+compatible but this has not been confirmed. Package maintainers, please
+install these at the appropriate locations for your system.
+
+To manually install the `bash` completion, copy
+`misc/completion/ocrmypdf.bash` to `/etc/bash_completion.d/ocrmypdf`
+(rename the file).
+
+To manually install the `fish` completion, copy
+`misc/completion/ocrmypdf.fish` to
+`~/.config/fish/completions/ocrmypdf.fish`.
+
+## Note on 32-bit support
+
+We don't support any 32-bit system, including 32-bit Python or 32-bit
+Ghostscript on Windows.
@@ -1,720 +0,0 @@
-.. SPDX-FileCopyrightText: 2022 James R. Barlow
-..
-.. SPDX-License-Identifier: CC-BY-SA-4.0
-
-===================
-Installing OCRmyPDF
-===================
-
-.. |latest| image:: https://img.shields.io/pypi/v/ocrmypdf.svg
-    :alt: OCRmyPDF latest released version on PyPI
-
-|latest|
-
-The easiest way to install OCRmyPDF is to follow the steps for your operating
-system/platform. This version may be out of date, however.
-
-These platforms have one-liner installs:
-
-+-------------------------------+-----------------------------------------+
-| Debian, Ubuntu                | ``apt install ocrmypdf``                |
-+-------------------------------+-----------------------------------------+
-| Windows Subsystem for Linux   | ``apt install ocrmypdf``                |
-+-------------------------------+-----------------------------------------+
-| Fedora                        | ``dnf install ocrmypdf tesseract-osd``  |
-+-------------------------------+-----------------------------------------+
-| macOS (Homebrew)              | ``brew install ocrmypdf``               |
-+-------------------------------+-----------------------------------------+
-| macOS (MacPorts)              | ``port install ocrmypdf``               |
-+-------------------------------+-----------------------------------------+
-| LinuxBrew                     | ``brew install ocrmypdf``               |
-+-------------------------------+-----------------------------------------+
-| FreeBSD                       | ``pkg install textproc/py-ocrmypdf``    |
-+-------------------------------+-----------------------------------------+
-| Conda (WSL, macOS, Linux)     | ``conda install ocrmypdf``              |
-+-------------------------------+-----------------------------------------+
-| Snap (snapcraft packaging)    | ``snap install ocrmypdf``               |
-+-------------------------------+-----------------------------------------+
-
-More detailed procedures are outlined below. If you want to do a manual
-install, or install a more recent version than your platform provides, read on.
-
-.. contents:: Platform-specific steps
-    :depth: 2
-    :local:
-
-Installing on Linux
-===================
-
-Debian and Ubuntu 20.04 or newer
--------------------------------
-
-.. |deb-11| image:: https://repology.org/badge/version-for-repo/debian_11/ocrmypdf.svg
-    :alt: Debian 11
-
-.. |deb-12| image:: https://repology.org/badge/version-for-repo/debian_12/ocrmypdf.svg
-    :alt: Debian 12
-
-.. |deb-unstable| image:: https://repology.org/badge/version-for-repo/debian_unstable/ocrmypdf.svg
-    :alt: Debian unstable
-
-.. |ubu-2004| image:: https://repology.org/badge/version-for-repo/ubuntu_20_04/ocrmypdf.svg
-    :alt: Ubuntu 20.04 LTS
-
-.. |ubu-2204| image:: https://repology.org/badge/version-for-repo/ubuntu_22_04/ocrmypdf.svg
-    :alt: Ubuntu 22.04 LTS
-
-+-----------------------------------------------+
-| **OCRmyPDF versions in Debian & Ubuntu**      |
-+-----------------------------------------------+
-| |latest|                                      |
-+-----------------------------------------------+
-| |deb-11| |deb-12| |deb-unstable|              |
-+-----------------------------------------------+
-| |ubu-2004| |ubu-2204|                         |
-+-----------------------------------------------+
-
-Users of Debian or Ubuntu may simply
-
-.. code-block:: bash
-
-    apt install ocrmypdf
-
-As indicated in the table above, Debian and Ubuntu releases may lag
-behind the latest version. If the version available for your platform is
-out of date, you could opt to install the latest version from source.
-See `Installing HEAD revision from
-sources <#installing-head-revision-from-sources>`__.
-
-For full details on version availability for your platform, check the
-`Debian Package Tracker <https://tracker.debian.org/pkg/ocrmypdf>`__ or
-`Ubuntu launchpad.net <https://launchpad.net/ocrmypdf>`__.
-
-.. note::
-
-   OCRmyPDF for Debian and Ubuntu currently omit the JBIG2 encoder.
-   OCRmyPDF works fine without it but will produce larger output files.
-   If you build jbig2enc from source, ocrmypdf will
-   automatically detect it (specifically the ``jbig2`` binary) on the
-   ``PATH``. To add JBIG2 encoding, see :ref:`jbig2`.
-
-Fedora
------
-
-.. |fedora-38| image:: https://repology.org/badge/version-for-repo/fedora_38/ocrmypdf.svg
-    :alt: Fedora 38
-
-.. |fedora-39| image:: https://repology.org/badge/version-for-repo/fedora_39/ocrmypdf.svg
-    :alt: Fedora 39
-
-.. |fedora-rawhide| image:: https://repology.org/badge/version-for-repo/fedora_rawhide/ocrmypdf.svg
-    :alt: Fedore Rawhide
-
-+-----------------------------------------------+
-| **OCRmyPDF version**                          |
-+-----------------------------------------------+
-| |latest|                                      |
-+-----------------------------------------------+
-| |fedora-38| |fedora-39| |fedora-rawhide|      |
-+-----------------------------------------------+
-
-Users of Fedora may simply
-
-.. code-block:: bash
-
-    dnf install ocrmypdf tesseract-osd
-
-For full details on version availability, check the `Fedora Package
-Tracker <https://packages.fedoraproject.org/pkgs/ocrmypdf/ocrmypdf/>`__.
-
-If the version available for your platform is out of date, you could opt
-to install the latest version from source. See `Installing HEAD revision
-from sources <#installing-head-revision-from-sources>`__.
-
-.. note::
-
-   OCRmyPDF for Fedora currently omits the JBIG2 encoder due to patent
-   issues. OCRmyPDF works fine without it but will produce larger output
-   files. If you build jbig2enc from source, ocrmypdf 7.0.0 and later
-   will automatically detect it on the ``PATH``. To add JBIG2 encoding,
-   see :ref:`Installing the JBIG2 encoder <jbig2>`.
-
-.. _ubuntu-lts-latest:
-
-RHEL 9
------
-
-Prepare the environment by getting Python 3.11:
-
-.. code-block:: bash
-
-    dnf install python3.11 python3.11-pip
-
-Then, follow `Requirements for pip and HEAD install <#requirements-for-pip-and-head-install>`__ to instal dependencies:
-
-.. code-block:: bash
-
-    dnf install ghostscript tesseract
-
-and build ocrmypdf in virtual environment:
-
-.. code-block:: bash
-
-    python3.11 -m venv .venv
-
-To add JBIG2 encoding, see :ref:`Installing the JBIG2 encoder <jbig2>`.
-
-Note Fedora packages for language data haven't been branched for RHEL/EPEL, but you can get traineddata files directly from `tesseract
-<https://github.com/tesseract-ocr/tessdata/>`__ and place them in ``/usr/share/tesseract/tessdata``.
-
-Installing the latest version on Ubuntu 22.04 LTS
-------------------------------------------------
-
-Ubuntu 22.04 includes ocrmypdf 13.4.0 - you can install that with
-``apt install ocrmypdf``. To install a more recent version for the current
-user, follow these steps:
-
-.. code-block:: bash
-
-    sudo apt-get update
-    sudo apt-get -y install ocrmypdf python3-pip
-
-    pip install --user --upgrade ocrmypdf
-
-If you get the message ``WARNING: The script ocrmypdf is installed in
-'/home/$USER/.local/bin' which is not on PATH.``, you may need to re-login
-or open a new shell, or manually adjust your PATH.
-
-To add JBIG2 encoding, see :ref:`jbig2`.
-
-Ubuntu 20.04 LTS
----------------
-
-Ubuntu 20.04 includes ocrmypdf 9.6.0 - you can install that with ``apt``. The
-most convenient way to install recent OCRmyPDF on older Ubuntu is to use
-Homebrew on Linux (Linuxbrew).
-
-.. code-block:: bash
-
-    brew install ocrmypdf
-
-Arch Linux (AUR)
----------------
-
-.. image:: https://repology.org/badge/version-for-repo/aur/ocrmypdf.svg
-    :alt: ArchLinux
-    :target: https://repology.org/metapackage/ocrmypdf
-
-There is an `Arch User Repository (AUR) package for OCRmyPDF
-<https://aur.archlinux.org/packages/ocrmypdf/>`__.
-
-Installing AUR packages as root is not allowed, so you must first `setup a
-non-root user
-<https://wiki.archlinux.org/index.php/Users_and_groups#User_management>`__ and
-`configure sudo <https://wiki.archlinux.org/index.php/Sudo#Configuration>`__.
-The standard Docker image, ``archlinux/base:latest``, does **not** have a
-non-root user configured, so users of that image must follow these guides. If
-you are using a VM image, such as `the official Vagrant image
-<https://app.vagrantup.com/archlinux/boxes/archlinux>`__, this work may already
-be completed for you.
-
-Next you should install the `base-devel package group
-<https://archlinux.org/packages/core/any/base-devel/>`__. This includes the
-standard tooling needed to build packages, such as a compiler and binary tools.
-
-.. code-block:: bash
-
-   sudo pacman -S --needed base-devel
-
-Now you are ready to install the OCRmyPDF package.
-
-.. code-block:: bash
-
-   curl -O https://aur.archlinux.org/cgit/aur.git/snapshot/ocrmypdf.tar.gz
-   tar xvzf ocrmypdf.tar.gz
-   cd ocrmypdf
-   makepkg -sri
-
-At this point you will have a working install of OCRmyPDF, but the Tesseract
-install won’t include any OCR language data. You can install `the
-tesseract-data package group
-<https://www.archlinux.org/groups/any/tesseract-data/>`__ to add all supported
-languages, or use that package listing to identify the appropriate package for
-your desired language.
-
-.. code-block:: bash
-
-   sudo pacman -S tesseract-data-eng
-
-As an alternative to this manual procedure, consider using an `AUR helper
-<https://wiki.archlinux.org/index.php/AUR_helpers>`__. Such a tool will
-automatically fetch, build and install the AUR package, resolve dependencies
-(including dependencies on AUR packages), and ease the upgrade procedure.
-
-If you have any difficulties with installation, check the repository package
-page.
-
-.. note::
-
-    The OCRmyPDF AUR package currently omits the JBIG2 encoder. OCRmyPDF works
-    fine without it but will produce larger output files. The encoder is
-    available from `the jbig2enc-git AUR package
-    <https://aur.archlinux.org/packages/jbig2enc-git/>`__ and may be installed
-    using the same series of steps as for the installation OCRmyPDF AUR
-    package. Alternatively, it may be built manually from source following the
-    instructions in :ref:`Installing the JBIG2 encoder <jbig2>`.  If JBIG2 is
-    installed, OCRmyPDF 7.0.0 and later will automatically detect it.
-
-Alpine Linux
------------
-
-.. image:: https://repology.org/badge/version-for-repo/alpine_edge/ocrmypdf.svg
-    :alt: Alpine Linux
-    :target: https://repology.org/metapackage/ocrmypdf
-
-To install OCRmyPDF for Alpine Linux:
-
-.. code-block:: bash
-
-    apk add ocrmypdf
-
-Gentoo Linux
------------
-
-.. image:: https://repology.org/badge/version-for-repo/gentoo_ovl_guru/ocrmypdf.svg
-    :alt: Gentoo Linux
-    :target: https://repology.org/metapackage/ocrmypdf
-
-To install OCRmyPDF on Gentoo Linux, use the following commands:
-
-.. code-block:: bash
-
-    eselect repository enable guru
-    emaint sync --repo guru
-    emerge --ask app-text/OCRmyPDF
-
-Other Linux packages
--------------------
-
-See the
-`Repology <https://repology.org/metapackage/ocrmypdf/versions>`__ page.
-
-In general, first install the OCRmyPDF package for your system, then
-optionally use the procedure `Installing with Python
-pip <#installing-with-python-pip>`__ to install a more recent version.
-
-Installing on macOS
-===================
-
-Homebrew
--------
-
-.. image:: https://img.shields.io/homebrew/v/ocrmypdf.svg
-    :alt: homebrew
-    :target: https://formulae.brew.sh/formula/ocrmypdf
-
-OCRmyPDF is now a standard `Homebrew <https://brew.sh>`__ formula. To
-install on macOS:
-
-.. code-block:: bash
-
-    brew install ocrmypdf
-
-This will include only the English language pack. If you need other
-languages you can optionally install them all:
-
-.. code-block:: bash
-
-    brew install tesseract-lang  # Optional: Install all language packs
-
-MacPorts
--------
-
-.. image:: https://img.shields.io/badge/dynamic/json?url=https%3A%2F%2Fports.macports.org%2Fapi%2Fv1%2Fports%2Focrmypdf%2F%3Fformat%3Djson&query=version&label=MacPorts
-   :alt: Macports Version Information
-   :target: https://ports.macports.org/port/ocrmypdf
-
-OCRmyPDF is includes in MacPorts:
-
-.. code-block:: bash
-
-    sudo port install ocrmypdf
-
-Note that while this will install tesseract you will need to install
-the appropriate tesseract `language ports <https://ports.macports.org/search/?selected_facets=categories_exact%3Atextproc&installed_file=&q=tesseract&name=on>`__. 
-
-Manual installation on macOS
----------------------------
-
-These instructions probably work on all macOS supported by Homebrew, and are
-for installing a more current version of OCRmyPDF than is available from
-Homebrew. Note that the Homebrew versions usually track the release versions
-fairly closely.
-
-If it's not already present, `install Homebrew <http://brew.sh/>`__.
-
-Update Homebrew:
-
-.. code-block:: bash
-
-    brew update
-
-Install or upgrade the required Homebrew packages, if any are missing.
-To do this, use ``brew edit ocrmypdf`` to obtain a recent list of Homebrew
-dependencies. You could also check the ``.workflows/build.yml``.
-
-This will include the English, French, German and Spanish language
-packs. If you need other languages you can optionally install them all:
-
-.. _macos-all-languages:
-
-   .. code-block:: bash
-
-    brew install tesseract-lang  # Option 2: for all language packs
-
-Update the homebrew pip:
-
-.. code-block:: bash
-
-    pip install --upgrade pip
-
-You can then install OCRmyPDF from PyPI for the current user:
-
-.. code-block:: bash
-
-    pip install --user ocrmypdf
-
-The command line program should now be available:
-
-.. code-block:: bash
-
-    ocrmypdf --help
-
-Installing on Windows
-=====================
-
-Native Windows
--------------
-
-.. note::
-
-    Administrator privileges will be required for some of these steps.
-
-You must install the following for Windows:
-
-* Python 64-bit
-* Tesseract 64-bit
-* Ghostscript 64-bit
-
-Using the `winget <https://docs.microsoft.com/en-us/windows/package-manager/winget/>`_
-package manager:
-
-* ``winget install -e --id Python.Python.3.11``
-* ``winget install -e --id UB-Mannheim.TesseractOCR``
-
-You will need to install Ghostscript manually, `since it does not support automated
-installs anymore <https://artifex.com/news/ghostscript-10.01.0-disabling-silent-install-option>`_.
-
-* `Ghostscript download page <https://ghostscript.com/releases/gsdnld.html>`_.`
-
-(Or alternately, using the `Chocolatey <https://chocolatey.org/>`_ package manager, install
-the following when running in an Administrator command prompt):
-
-* ``choco install python3``
-* ``choco install --pre tesseract``
-* ``choco install pngquant`` (optional)
-
-Either set of commands will install the required software. At the moment there is no
-single command to install Windows.
-
-You may then use ``pip`` to install ocrmypdf. (This can performed by a user or
-Administrator.):
-
-* ``python3 -m pip install ocrmypdf``
-
-OCRmyPDF will check the Windows Registry and standard locations in your Program Files
-for third party software it needs (specifically, Tesseract and Ghostscript). To
-override the versions OCRmyPDF selects, you can modify the ``PATH`` environment
-variable. `Follow these directions <https://www.computerhope.com/issues/ch000549.htm#dospath>`_
-to change the PATH.
-
-.. warning::
-
-    As of early 2021, users have reported problems with the Microsoft Store version of
-    Python and OCRmyPDF. These issues affect many other third party Python packages.
-    Please download Python from Python.org or a package manager instead of the
-    Microsoft Store version.
-
-.. warning::
-
-    32-bit Windows is not supported.
-
-Windows Subsystem for Linux
---------------------------
-
-#. Install Ubuntu 22.04 for Windows Subsystem for Linux, if not already installed.
-#. Follow the procedure to install :ref:`OCRmyPDF on Ubuntu 22.04 <ubuntu-lts-latest>`.
-#. Open the Windows command prompt and create a symlink:
-
-.. code-block:: powershell
-
-    wsl sudo ln -s  /home/$USER/.local/bin/ocrmypdf /usr/local/bin/ocrmypdf
-
-Then confirm that the expected version from PyPI (|latest|) is installed:
-
-.. code-block:: powershell
-
-    wsl ocrmypdf --version
-
-You can then run OCRmyPDF in the Windows command prompt or Powershell, prefixing
-``wsl``, and call it from Windows programs or batch files.
-
-Cygwin64
--------
-
-First install the the following prerequisite Cygwin packages using ``setup-x86_64.exe``::
-
-    python310 (or later)
-    python3?-devel
-    python3?-pip
-    python3?-lxml
-    python3?-imaging
-
-       (where 3? means match the version of python3 you installed)
-
-    gcc-g++
-    ghostscript
-    libexempi3
-    libexempi-devel
-    libffi6
-    libffi-devel
-    pngquant
-    qpdf
-    libqpdf-devel
-    tesseract-ocr
-    tesseract-ocr-devel
-
-Then open a Cygwin terminal (i.e. ``mintty``), run the following commands. Note
-that if you are using the version of ``pip`` that was installed with the Cygwin
-Python package, the command name will be ``pip3``.  If you have since updated
-``pip`` (with, for instance ``pip3 install --upgrade pip``) the the command is
-likely just ``pip`` instead of ``pip3``:
-
-.. code-block:: bash
-
-    pip3 install wheel
-    pip3 install ocrmypdf
-
-The optional dependency "unpaper" that is currently not available under Cygwin.
-Without it, certain options such as ``--clean`` will produce an error message.
-However, the OCR-to-text-layer functionality is available.
-
-Docker
------
-
-You can also :ref:`Install the Docker <docker>` container on Windows. Ensure that
-your command prompt can run the docker "hello world" container.
-
-Installing on FreeBSD
-=====================
-
-.. image:: https://repology.org/badge/version-for-repo/freebsd/ocrmypdf.svg
-    :alt: FreeBSD
-    :target: https://repology.org/project/ocrmypdf/versions
-
-.. code-block:: bash
-
-    pkg install textproc/py-ocrmypdf
-
-To install a more recent version, you could attempt to first install the system
-version with ``pkg``, then use ``pip install --user ocrmypdf``.
-
-Installing the Docker image
-===========================
-
-For some users, installing the Docker image will be easier than
-installing all of OCRmyPDF's dependencies.
-
-See :ref:`docker` for more information.
-
-Installing with Python pip
-==========================
-
-OCRmyPDF is delivered by PyPI because it is a convenient way to install
-the latest version. However, PyPI and ``pip`` cannot address the fact
-that ``ocrmypdf`` depends on certain non-Python system libraries and
-programs being installed.
-
-For best results, first install `your platform's
-version <https://repology.org/metapackage/ocrmypdf/versions>`__ of
-``ocrmypdf``, using the instructions elsewhere in this document. Then
-you can use ``pip`` to get the latest version if your platform version
-is out of date. Chances are that this will satisfy most dependencies.
-
-Use ``ocrmypdf --version`` to confirm what version was installed.
-
-Then you can install the latest OCRmyPDF from the Python wheels. First
-try:
-
-.. code-block:: bash
-
-    pip install --user ocrmypdf
-
-(If the message appears ``Requirement already satisfied: ocrmypdf in...``,
-you will need to use ``pip install --user --upgrade ocrmypdf``.)
-
-You should then be able to run ``ocrmypdf --version`` and see that the
-latest version was located.
-
-Installing with pipx
-====================
-
-Some users may prefer pipx. As with the method above, you will need to
-satisfy all non-Python dependencies. Then if pipx is installed, you
-can use
-
-.. code-block:: bash
-
-    pipx run ocrmypdf
-
-(If not installed, pipx will install first.)
-
-Requirements for pip and HEAD install
-------------------------------------
-
-OCRmyPDF currently requires these external programs and libraries to be
-installed, and must be satisfied using the operating system package
-manager. ``pip`` cannot provide them.
-
-The following versions are required:
-
-  Python 3.10 or newer
-  Ghostscript 9.54 or newer
-  Tesseract 4.1.1 or newer
-  jbig2enc 0.29 or newer
-  pngquant 2.5 or newer
-  unpaper 6.1
-
-We recommend 64-bit versions of all software. (32-bit versions are not
-supported, although on Linux, they may still work.)
-
-jbig2enc, pngquant, and unpaper are optional. If missing certain
-features are disabled. OCRmyPDF will discover them as soon as they are
-available.
-
-**jbig2enc**, if present, will be used to optimize the encoding of
-monochrome images. This can significantly reduce the file size of the
-output file. It is not required.
-`jbig2enc <https://github.com/agl/jbig2enc>`__ is not generally
-available for Ubuntu or Debian due to lingering concerns about patent
-issues, but can easily be built from source. To add JBIG2 encoding, see
-:ref:`jbig2`.
-
-**pngquant**, if present, is optionally used to optimize the encoding of
-PNG-style images in PDFs (actually, any that are that losslessly
-encoded) by lossily quantizing to a smaller color palette. It is only
-activated then the ``--optimize`` argument is ``2`` or ``3``.
-
-**unpaper**, if present, enables the ``--clean`` and ``--clean-final``
-command line options.
-
-These are in addition to the Python packaging dependencies, meaning that
-unfortunately, the ``pip install`` command cannot satisfy all of them.
-
-Installing HEAD revision from sources
-=====================================
-
-If you have ``git`` and Python 3.10 or newer installed, you can install
-from source. When the ``pip`` installer runs, it will alert you if
-dependencies are missing.
-
-If you prefer to build every from source, you will need to `build
-pikepdf from
-source <https://pikepdf.readthedocs.io/en/latest/installation.html#building-from-source>`__.
-First ensure you can build and install pikepdf.
-
-To install the HEAD revision from sources in the current Python 3
-environment:
-
-.. code-block:: bash
-
-    pip install git+https://github.com/ocrmypdf/OCRmyPDF.git
-
-Or, to install in `development
-mode <https://packaging.python.org/en/latest/guides/distributing-packages-using-setuptools/#working-in-development-mode>`__,
-allowing customization of OCRmyPDF, use the ``-e`` flag:
-
-.. code-block:: bash
-
-    pip install -e git+https://github.com/ocrmypdf/OCRmyPDF.git
-
-You may find it easiest to install in a virtual environment, rather than
-system-wide:
-
-.. code-block:: bash
-
-    git clone -b main https://github.com/ocrmypdf/OCRmyPDF.git
-    python3 -m venv .venv
-    source .venv/bin/activate
-    cd OCRmyPDF
-    pip install .
-
-However, ``ocrmypdf`` will only be accessible on the system PATH when
-you activate the virtual environment.
-
-To run the program:
-
-.. code-block:: bash
-
-    ocrmypdf --help
-
-If not yet installed, the script will notify you about dependencies that
-need to be installed. The script requires specific versions of the
-dependencies. Older version than the ones mentioned in the release notes
-are likely not to be compatible to OCRmyPDF.
-
-For development
---------------
-
-To install all of the development and test requirements:
-
-.. code-block:: bash
-
-    git clone -b main https://github.com/ocrmypdf/OCRmyPDF.git
-    python -m venv .venv
-    source .venv/bin/activate
-    cd OCRmyPDF
-    pip install -e .[test]
-
-To add JBIG2 encoding, see :ref:`jbig2`.
-
-Shell completions
-=================
-
-Completions for ``bash`` and ``fish`` are available in the project's
-``misc/completion`` folder. The ``bash`` completions are likely ``zsh``
-compatible but this has not been confirmed. Package maintainers, please
-install these at the appropriate locations for your system.
-
-To manually install the ``bash`` completion, copy
-``misc/completion/ocrmypdf.bash`` to ``/etc/bash_completion.d/ocrmypdf``
-(rename the file).
-
-To manually install the ``fish`` completion, copy
-``misc/completion/ocrmypdf.fish`` to
-``~/.config/fish/completions/ocrmypdf.fish``.
-
-Note on 32-bit support
-======================
-
-Many Python libraries no longer provide 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.
@@ -1,10 +1,7 @@
-.. SPDX-FileCopyrightText: 2022 James R. Barlow
-..
-.. SPDX-License-Identifier: CC-BY-SA-4.0
+% SPDX-FileCopyrightText: 2022 James R. Barlow
+% SPDX-License-Identifier: CC-BY-SA-4.0

-============
-Introduction
-============
+# Introduction

 OCRmyPDF is a Python application and library that adds text "layers" to images in
 PDFs, making scanned image PDFs searchable. It uses OCR to guess the text
@@ -13,31 +10,30 @@ that enable customization of its processing steps, and it is highly tolerant
 of PDFs containing scanned images and "born digital" content that doesn't
 require text recognition.

-About OCR
-=========
+## About OCR

-`Optical character
-recognition <https://en.wikipedia.org/wiki/Optical_character_recognition>`__
+[Optical character
+recognition](https://en.wikipedia.org/wiki/Optical_character_recognition)
 is a technology that converts images of typed or handwritten text, such as
 in a scanned document, into computer text that can be selected, searched and copied.

 OCRmyPDF uses
-`Tesseract <https://github.com/tesseract-ocr/tesseract>`__, a widely
+[Tesseract](https://github.com/tesseract-ocr/tesseract), a widely
 available open source OCR engine, to perform OCR.

-.. _raster-vector:
+(raster-vector)=

-About PDFs
-==========
+## About PDFs

 PDFs are page description files that attempt to preserve a layout
-exactly. They contain `vector
-graphics <http://vector-conversions.com/vectorizing/raster_vs_vector.html>`__
+exactly. They contain [vector
+graphics](http://vector-conversions.com/vectorizing/raster_vs_vector.html)
 that can contain raster objects, such as scanned images. Because PDFs can
 contain multiple pages (unlike many image formats) and can contain fonts
 and text, they are a suitable format for exchanging scanned documents.

-|image|
+:::{image} images/bitmap_vs_svg.svg
+:::

 A PDF page may contain multiple images, even if it appears to have only
 one image. Some scanners or scanning software may segment pages into
@@ -48,10 +44,9 @@ Rasterizing a PDF is the process of generating corresponding raster images.
 OCR engines like Tesseract work with images, not scalable vector graphics
 or mixed raster-vector-text graphics such as PDF.

-About PDF/A
-===========
+## About PDF/A

-`PDF/A <https://en.wikipedia.org/wiki/PDF/A>`__ is an ISO-standardized
+[PDF/A](https://en.wikipedia.org/wiki/PDF/A) is an ISO-standardized
 subset of the full PDF specification that is designed for archiving (the
 'A' stands for Archive). PDF/A differs from PDF primarily by omitting
 features that could complicate future file readability,
@@ -63,8 +58,8 @@ of embedded content, it is likely more secure.
 There are various conformance levels and versions, such as "PDF/A-2b".

 In general, the preferred format for scanned documents is PDF/A. Some
-governments and jurisdictions, US Courts in particular, `mandate the use
-of PDF/A <https://pdfblog.com/2012/02/13/what-is-pdfa/>`__ for scanned
+governments and jurisdictions, US Courts in particular, [mandate the use
+of PDF/A](https://pdfblog.com/2012/02/13/what-is-pdfa/) for scanned
 documents.

 Since most individuals scanning documents aim for long-term readability,
@@ -78,15 +73,21 @@ files can be digitally signed but may not be encrypted to ensure future
 readability. Fortunately, converting from PDF/A to a regular PDF is
 straightforward, and any PDF viewer can handle PDF/A files.

-What OCRmyPDF does
-==================
+## What OCRmyPDF does

 OCRmyPDF analyzes each page of a PDF to determine the required colorspace
 and resolution (DPI) for capturing all the information on that page without
-losing content. It uses
-`Ghostscript <http://ghostscript.com/>`__ to rasterize each page and subsequently
-performs OCR on the rasterized image to generate an OCR "layer." This layer
-is then integrated back into the original PDF.
+losing content. It uses a PDF rasterizer (pypdfium2 or
+[Ghostscript](http://ghostscript.com/)) to convert each page to an image and
+subsequently performs OCR on the rasterized image to generate an OCR "layer."
+This layer is then integrated back into the original PDF.
+
+:::{versionchanged} 17.0.0
+OCRmyPDF now supports pypdfium2 as an alternative rasterizer to Ghostscript.
+pypdfium2 is a Python binding for pdfium, the PDF rendering library used by
+Google Chrome. The `--rasterizer auto` setting (default) prefers pypdfium2
+when available.
+:::

 While it is possible to use a program like Ghostscript or ImageMagick to
 obtain an image and then run that image through Tesseract OCR, this process
@@ -101,10 +102,9 @@ options are utilized, the OCR layer is integrated into the processed image.
 By default, OCRmyPDF generates archival PDFs in the PDF/A format, which is
 a more rigid subset of PDF features designed for long-term archives. If you
 prefer regular PDFs, you can disable this feature using the
-``--output-type pdf`` option.
+`--output-type pdf` option.

-Why you shouldn't do this manually
-==================================
+## Why you shouldn't do this manually

 A PDF is similar to an HTML file, in that it contains document structure
 along with images. While some PDFs may solely display a full-page image,
@@ -142,55 +142,78 @@ like pikepdf and QPDF, it can auto-repair damaged PDFs. You don't need to
 understand the intricacies of these issues; you should be able to use
 OCRmyPDF with any PDF file, and expect reasonable results.

-Limitations
-===========
+## Limitations

 OCRmyPDF is subject to limitations imposed by the Tesseract OCR engine.
 These limitations are inherent to any software relying on Tesseract:

-  The OCR accuracy may not match that of commercial OCR solutions.
-  It is incapable of recognizing handwriting.
-  It may detect gibberish and report it as OCR output.
-  Results may be subpar when a document contains languages not specified
-   in the ``-l LANG`` argument.
-  Tesseract may struggle to analyze the natural reading order of documents.
-   For instance, it might fail to recognize two columns in a document and
-   attempt to join text across columns.
-  Poor quality scans can result in subpar OCR quality. In other words, the
-   quality of the OCR output depends on the quality of the input.
-  Tesseract does not provide information about the font family to which text
-   belongs.
-  Tesseract does not divide text into paragraphs or headings. It only provides
-   the text and its bounding box. As such, the generated PDF does not
-   contain any information about the document's structure.
+- The OCR accuracy may not match that of commercial OCR solutions.
+- It is incapable of recognizing handwriting.
+- It may detect gibberish and report it as OCR output.
+- Results may be subpar when a document contains languages not specified
+  in the `-l LANG` argument.
+- Tesseract may struggle to analyze the natural reading order of documents.
+  For instance, it might fail to recognize two columns in a document and
+  attempt to join text across columns.
+- Poor quality scans can result in subpar OCR quality. In other words, the
+  quality of the OCR output depends on the quality of the input.
+- Tesseract does not provide information about the font family to which text
+  belongs.
+- Tesseract does not divide text into paragraphs or headings. It only provides
+  the text and its bounding box. As such, the generated PDF does not
+  contain any information about the document's structure.

-Ghostscript also imposes some limitations:
+### Ghostscript considerations

-  PDFs containing JPEG 2000-encoded content may be converted to JPEG
-   encoding, which may introduce compression artifacts, if Ghostscript
-   PDF/A is enabled.
-  Ghostscript may transcode grayscale and color images, potentially
-   lossily, based on an internal algorithm. This
-   behavior can be suppressed by setting ``--pdfa-image-compression`` to
-   ``jpeg`` or ``lossless`` to set all images to one type or the other.
-   Ghostscript lacks an option to maintain the input image's format.
-   (Modern Ghostscript can copy JPEG images without transcoding them.)
-  Ghostscript's PDF/A conversion removes any XMP metadata that is not
-   one of the standard XMP metadata namespaces for PDFs. In particular,
-   PRISM Metadata is removed.
-  Ghostscript's PDF/A conversion may remove or deactivate
-   hyperlinks and other active content.
+:::{versionchanged} 17.0.0
+Ghostscript is no longer strictly required. OCRmyPDF can use pypdfium2
+for rasterization and verapdf for PDF/A validation.
+:::

-You can use ``--output-type pdf`` to disable PDF/A conversion and produce
+While Ghostscript remains a capable and feature-rich tool with a long history,
+recent releases have introduced some compatibility challenges that OCRmyPDF
+v17 addresses through alternative codepaths. When Ghostscript is used:
+
+- PDFs containing JPEG 2000-encoded content may be converted to JPEG
+  encoding, which may introduce compression artifacts, if Ghostscript
+  PDF/A is enabled.
+- Ghostscript may transcode grayscale and color images, potentially
+  lossily, based on an internal algorithm. By default
+  (`--pdfa-image-compression=auto`) OCRmyPDF selects lossless image
+  compression at `-O0` so Ghostscript will not transcode lossless images
+  to JPEG. At `-O1` (the default optimization level) and above, `auto`
+  defers to Ghostscript's heuristic instead; `-O1` is a historical
+  exception, kept for backwards compatibility because coercing it to
+  lossless can substantially bloat output. You can override this by
+  setting `--pdfa-image-compression` to `jpeg` or `lossless` to force all
+  images to one type or the other. `lossless` passes existing JPEGs
+  through untouched (re-encoding them losslessly would only inflate them)
+  while encoding non-JPEG images losslessly.
+  (Modern Ghostscript can copy JPEG images without transcoding them.)
+  Advanced users can also tune Ghostscript's image recompression with
+  `--ghostscript-jpeg-quality` and `--ghostscript-jpeg-maxdpi`; see
+  [Advanced Ghostscript tuning](advanced.md#advanced-ghostscript-tuning).
+  Most users should prefer `--jpeg-quality` (applied by the OCRmyPDF
+  optimizer) over those Ghostscript-scoped controls.
+- Ghostscript's PDF/A conversion removes any XMP metadata that is not
+  one of the standard XMP metadata namespaces for PDFs. In particular,
+  PRISM Metadata is removed.
+- Ghostscript's PDF/A conversion may remove or deactivate
+  hyperlinks and other active content.
+
+When pypdfium2 and verapdf are available, many of these limitations can be
+avoided by using the speculative PDF/A conversion path (enabled by default
+with `--output-type auto`).
+
+You can use `--output-type pdf` to disable PDF/A conversion and produce
 a standard, non-archival PDF.

 Regarding OCRmyPDF itself:

-  PDFs using transparency are not currently represented in the test
-   suite
+- PDFs using transparency are not currently represented in the test
+  suite

-Similar programs
-================
+## Similar programs

 To the author's knowledge, OCRmyPDF is the most feature-rich and
 thoroughly tested command line OCR PDF conversion tool. If it does not
@@ -199,8 +222,7 @@ meet your needs, contributions and suggestions are welcome.
 Ghostscript recently added three "pdfocr" output devices. They work by
 rasterizing all content and converting all pages to a single colour space.

-Web front-ends
-==============
+## Web front-ends

 The Docker image of OCRmyPDF provides a web service front-end
 that allows files to submitted over HTTP, and the results can be downloaded.
@@ -210,16 +232,14 @@ public internet and does not provide any security measures.

 In addition, the following third-party integrations are available:

-  `Paperless-ngx <https://docs.paperless-ngx.com/>`__ is a free software
-   document management system that uses OCRmyPDF to perform OCR on
-   uploaded documents.
-  `Nextcloud OCR <https://github.com/janis91/ocr>`__ is a free software
-   plugin for the Nextcloud private cloud software.
+- [Paperless-ngx](https://docs.paperless-ngx.com/) is a free software
+  document management system that uses OCRmyPDF to perform OCR on
+  uploaded documents.
+- [Nextcloud OCR](https://github.com/janis91/ocr) is a free software
+  plugin for the Nextcloud private cloud software.

 OCRmyPDF is not designed to be secure against malware-bearing PDFs (see
-`Using OCRmyPDF online <ocr-service>`__). Users should ensure they
+[Using OCRmyPDF online](ocr-service)). Users should ensure they
 comply with OCRmyPDF's licenses and the licenses of all dependencies. In
 particular, OCRmyPDF requires Ghostscript, which is licensed under
 AGPLv3.
-
-.. |image| image:: images/bitmap_vs_svg.svg
@@ -0,0 +1,63 @@
+% SPDX-FileCopyrightText: 2022 James R. Barlow
+% SPDX-License-Identifier: CC-BY-SA-4.0
+
+{#jbig2}
+
+# Installing the JBIG2 encoder
+
+Most Linux distributions do not include a JBIG2 encoder since JBIG2
+encoding was patented for a long time. All known JBIG2 US patents have
+expired as of 2017, but it is possible that unknown patents exist.
+
+JBIG2 encoding is recommended for OCRmyPDF and is used to losslessly
+create smaller PDFs. If JBIG2 encoding is not available, lower quality
+CCITT encoding will be used for monochrome images.
+
+JBIG2 decoding is not patented and is performed automatically by most
+PDF viewers. It is widely supported and has been part of the PDF
+specification since 2001.
+
+JBIG encoding is automatically provided by these OCRmyPDF packages: -
+Docker image (both Ubuntu and Alpine) - Snap package - ArchLinux AUR
+package - Alpine Linux package - Homebrew on macOS
+
+For all other platforms, you would need to build the JBIG2 encoder from
+source:
+
+:::{code} bash
+git clone https://github.com/agl/jbig2enc
+cd jbig2enc
+./autogen.sh
+./configure && make
+[sudo] make install
+:::
+
+Dependencies include libtoolize and libleptonica, which on Ubuntu
+systems are packaged as libtool and libleptonica-dev. On Fedora (35)
+they are packaged as libtool and leptonica-devel. For this to work,
+please make sure to install `autotools`, `automake`, `libtool`, `pkg-config`
+and `leptonica` first if not already installed. Other dependencies might
+be required depending on your system.
+
+:::{code} bash
+[sudo] apt install autotools-dev automake libtool libleptonica-dev pkg-config
+:::
+
+## JBIG2 Compression
+
+OCRmyPDF uses JBIG2 lossless compression for bitonal (black and white)
+images. This provides excellent compression ratios compared to the older
+CCITT G4 standard, while preserving the exact pixel content of the
+original image.
+
+You can adjust the threshold for JBIG2 compression with
+`--jbig2-threshold`. The default is 0.85.
+
+:::{note}
+Previous versions of OCRmyPDF supported a lossy JBIG2 mode
+(`--jbig2-lossy`). This feature has been removed due to the well-known
+risk of character substitution errors (e.g., 6/8 confusion). See
+[JBIG2 disadvantages](https://en.wikipedia.org/wiki/JBIG2#Disadvantages)
+for more information on why lossy JBIG2 is problematic. The `--jbig2-lossy`
+and `--jbig2-page-group-size` arguments are now ignored with a warning.
+:::
@@ -1,83 +0,0 @@
-.. SPDX-FileCopyrightText: 2022 James R. Barlow
-..
-.. SPDX-License-Identifier: CC-BY-SA-4.0
-
-.. _jbig2:
-
-============================
-Installing the JBIG2 encoder
-============================
-
-Most Linux distributions do not include a JBIG2 encoder since JBIG2
-encoding was patented for a long time. All known JBIG2 US patents have
-expired as of 2017, but it is possible that unknown patents exist.
-
-JBIG2 encoding is recommended for OCRmyPDF and is used to losslessly
-create smaller PDFs. If JBIG2 encoding is not available, lower quality
-CCITT encoding will be used for monochrome images.
-
-JBIG2 decoding is not patented and is performed automatically by most
-PDF viewers. It is widely supported and has been part of the PDF
-specification since 2001.
-
-JBIG encoding is automatically provided by these OCRmyPDF packages:
- Docker image (both Ubuntu and Alpine)
- Snap package
- ArchLinux AUR package
- Alpine Linux package
- Homebrew on macOS
-
-For all other platforms, you would need to build the JBIG2 encoder from source:
-
-.. code-block:: bash
-
-   git clone https://github.com/agl/jbig2enc
-   cd jbig2enc
-   ./autogen.sh
-   ./configure && make
-   [sudo] make install
-
-.. _jbig2-lossy:
-
-Dependencies include libtoolize and libleptonica, which on Ubuntu systems
-are packaged as libtool and libleptonica-dev. On Fedora (35) they are packaged
-as libtool and leptonica-devel. For this to work, please make sure to install
-``autotools``, ``automake``, ``libtool`` and ``leptonica`` first if not already
-installed.
-
-.. code-block:: bash
-
-    [sudo] apt install autotools-dev automake libtool libleptonica-dev
-..
-
-
-Lossy mode JBIG2
-================
-
-OCRmyPDF provides lossy mode JBIG2 as an advanced and potentially dangerous
-feature. Users should
-`review the technical concerns with JBIG2 in lossy
-mode <https://en.wikipedia.org/wiki/JBIG2#Disadvantages>`__
-and decide if this feature is acceptable for their use case. In general,
-this mode should not be used for archival purposes, should not be used when
-the original document is not available or will be destroyed, and should
-not be used when numbers present in the document are important, because
-there is a risk of 6/8 and 8/6 substitution errors.
-
-JBIG2 lossy mode does achieve higher compression ratios than any other
-monochrome (bitonal) compression technology; for large text documents
-the savings are considerable. JBIG2 lossless still gives great
-compression ratios and is a major improvement over the older CCITT G4
-standard.
-
-To turn on JBIG2 lossy mode, add the argument ``--jbig2-lossy``.
-``--optimize {1,2,3}`` are necessary for the argument to take effect
-also required. Also, a JBIG2 encoder must be installed as described in
-the previous section.
-
-You can adjust the threshold for JBIG2 compression with the
-``--jbig2-threshold``. The default is 0.85, meaning that if two symbols
-are 85% similar, they will be compressed together.
-
-*Due to an oversight, ocrmypdf v7.0 and v7.1 used lossy mode by
-default.*
@@ -0,0 +1,129 @@
+% SPDX-FileCopyrightText: 2022 James R. Barlow
+% SPDX-License-Identifier: CC-BY-SA-4.0
+
+(lang-packs)=
+
+# Installing additional language packs
+
+OCRmyPDF uses Tesseract for OCR, and relies on its language packs for all languages.
+On most platforms, English is installed with Tesseract by default, but not always.
+
+Tesseract supports [most
+languages](https://github.com/tesseract-ocr/tesseract/blob/main/doc/tesseract.1.asc#languages).
+Languages are identified by standardized three-letter codes (called ISO 639-2 Alpha-3).
+Tesseract's documentation also lists the three-letter code for your language.
+Some are anglicized, e.g. Spanish is `spa` rather than `esp`, while others
+are not, e.g. German is `deu` and French is `fra`.
+
+Language packs (strictly speaking, Tesseract "traineddata" files) generally correspond
+to the language in question, but different language packs are used in certain
+situations. For German, the "Fraktur" language pack can assist with reading older
+materials in the Fraktur typeface family (`deu_frak`). Some communities have changed
+their script from Cyrillic to Latin; the Cyrillic version of Uzbek is available
+as `uzb_cyrl` and the Latin version is `uzb`.
+
+After you have installed a language pack, you can use it with `ocrmypdf -l <language>`,
+for example `ocrmypdf -l spa`. For multilingual documents, you can specify
+all languages to be expected, e.g. `ocrmypdf -l eng+fra` for English and French.
+English is assumed by default unless other language(s) are specified.
+
+For Linux users, you can often find packages that provide language
+packs.
+
+## Platform install steps
+
+### Debian and Ubuntu (apt)
+
+```bash
+# Display a list of all Tesseract language packs
+apt-cache search tesseract-ocr
+
+# Install Chinese Simplified language pack
+apt-get install tesseract-ocr-chi-sim
+```
+
+You can then pass the `-l LANG` argument to OCRmyPDF to give a hint as
+to what languages it should search for. Multiple languages can be
+requested using either `-l eng+fra` (English and French) or
+`-l eng -l fra`.
+
+### Fedora
+
+```bash
+# Display a list of all Tesseract language packs
+dnf search tesseract
+
+# Install Chinese Simplified language pack
+dnf install tesseract-langpack-chi_sim
+```
+
+You can then pass the `-l LANG` argument to OCRmyPDF to give a hint as
+to what languages it should search for. Multiple languages can be
+requested using either `-l eng+fra` (English and French) or
+`-l eng -l fra`.
+
+### Arch Linux
+
+```bash
+# Display a list of all Tesseract language packs
+pacman -Ss tesseract-data
+
+# Install German language pack
+pacman -S tesseract-data-deu
+```
+
+You can then pass the `-l LANG` argument to OCRmyPDF to give a hint as
+to what languages it should search for. Multiple languages can be
+requested using either `-l eng+fra` (English and French) or
+`-l eng -l fra`.
+
+### Gentoo
+
+On Gentoo the package `app-text/tessdata_fast`, which `app-text/tesseract` depends on, handles Tesseract languages.
+It accepts USE flags to select what languages should be installed, these can be set in `/etc/portage/package.use`.
+Alternatively one can globally set the [L10N use extension](https://wiki.gentoo.org/wiki/Localization/Guide#L10N) in `/etc/portage/make.conf`.
+This enables these languages for all packages (e.g. including aspell).
+
+```bash
+# Display a list of all Tesseract language packs
+equery uses app-text/tessdata_fast
+
+# Add English and German language support for Tesseract only
+echo 'app-text/tessdata_fast l10n_de l10n_en' >> /etc/portage/package.use
+
+# Add global English and German language support (the `l10n_` from equery has to be omitted)
+echo L10N="de en" >> /etc/portage/make.conf
+
+# update system to reflect changed USE flags
+emerge --update --deep --newuse @world
+```
+
+You can then pass the `-l LANG` argument to OCRmyPDF to give a hint as
+to what languages it should search for. Multiple languages can be
+requested using either `-l eng+fra` (English and French) or
+`-l eng -l fra`.
+
+### macOS
+
+You can install additional language packs by
+{ref}`installing Tesseract using Homebrew with all language packs <macos-all-languages>`.
+
+### Docker
+
+Users of the OCRmyPDF Docker image should install language packs into a
+derived Docker image as
+{ref}`described in that section <docker-lang-packs>`.
+
+### Windows
+
+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).
+
+## Custom language packs
+
+If you have fine-tuned or trained Tesseract and generated custom trained data, you can
+copy your `customlang.traineddata` file into your Tesseract "tessdata" folder, and
+then use the `-l customlang` argument to tell OCRmyPDF to pass that language on to
+Tesseract.
@@ -1,141 +0,0 @@
-.. SPDX-FileCopyrightText: 2022 James R. Barlow
-..
-.. SPDX-License-Identifier: CC-BY-SA-4.0
-
-.. _lang-packs:
-
-====================================
-Installing additional language packs
-====================================
-
-OCRmyPDF uses Tesseract for OCR, and relies on its language packs for all languages.
-On most platforms, English is installed with Tesseract by default, but not always.
-
-Tesseract supports `most
-languages <https://github.com/tesseract-ocr/tesseract/blob/main/doc/tesseract.1.asc#languages>`__.
-Languages are identified by standardized three-letter codes (called ISO 639-2 Alpha-3).
-Tesseract's documentation also lists the three-letter code for your language.
-Some are anglicized, e.g. Spanish is ``spa`` rather than ``esp``, while others
-are not, e.g. German is ``deu`` and French is ``fra``.
-
-Language packs (strictly speaking, Tesseract "traineddata" files) generally correspond
-to the language in question, but different language packs are used in certain
-situations. For German, the "Fraktur" language pack can assist with reading older
-materials in the Fraktur typeface family (``deu_frak``). Some communities have changed
-their script from Cyrillic to Latin; the Cyrillic version of Uzbek is available
-as ``uzb_cyrl`` and the Latin version is ``uzb``.
-
-After you have installed a language pack, you can use it with ``ocrmypdf -l <language>``,
-for example ``ocrmypdf -l spa``. For multilingual documents, you can specify
-all languages to be expected, e.g. ``ocrmypdf -l eng+fra`` for English and French.
-English is assumed by default unless other language(s) are specified.
-
-For Linux users, you can often find packages that provide language
-packs.
-
-Platform install steps
-======================
-
-Debian and Ubuntu (apt)
-----------------------
-
-.. code-block:: bash
-
-   # Display a list of all Tesseract language packs
-   apt-cache search tesseract-ocr
-
-   # Install Chinese Simplified language pack
-   apt-get install tesseract-ocr-chi-sim
-
-You can then pass the ``-l LANG`` argument to OCRmyPDF to give a hint as
-to what languages it should search for. Multiple languages can be
-requested using either ``-l eng+fra`` (English and French) or
-``-l eng -l fra``.
-
-Fedora
------
-
-.. code-block:: bash
-
-   # Display a list of all Tesseract language packs
-   dnf search tesseract
-
-   # Install Chinese Simplified language pack
-   dnf install tesseract-langpack-chi_sim
-
-You can then pass the ``-l LANG`` argument to OCRmyPDF to give a hint as
-to what languages it should search for. Multiple languages can be
-requested using either ``-l eng+fra`` (English and French) or
-``-l eng -l fra``.
-
-Archlinux
------
-
-.. code-block:: bash
-
-   # Display a list of all Tesseract language packs
-   pacman -Ss tesseract-data
-
-   # Install German language pack
-   pacman -S tesseract-data-deu
-
-You can then pass the ``-l LANG`` argument to OCRmyPDF to give a hint as
-to what languages it should search for. Multiple languages can be
-requested using either ``-l eng+fra`` (English and French) or
-``-l eng -l fra``.
-
-Gentoo
------
-
-On Gentoo the package ``app-text/tessdata_fast``, which ``app-text/tesseract`` depends on, handles Tesseract languages.
-It accepts USE flags to select what languages should be installed, these can be set in ``/etc/portage/package.use``.
-Alternatively one can globally set the `L10N use extension <https://wiki.gentoo.org/wiki/Localization/Guide#L10N>`__ in ``/etc/portage/make.conf``.
-This enables these languages for all packages (e.g. including aspell).
-
-.. code-block:: bash
-
-   # Display a list of all Tesseract language packs
-   equery uses app-text/tessdata_fast
-
-   # Add English and German language support for Tesseract only
-   echo 'app-text/tessdata_fast l10n_de l10n_en' >> /etc/portage/package.use
-
-   # Add global English and German language support (the `l10n_` from equery has to be omitted)
-   echo L10N="de en" >> /etc/portage/make.conf
-
-   # update system to reflect changed USE flags
-   emerge --update --deep --newuse @world
-
-You can then pass the ``-l LANG`` argument to OCRmyPDF to give a hint as
-to what languages it should search for. Multiple languages can be
-requested using either ``-l eng+fra`` (English and French) or
-``-l eng -l fra``.
-
-macOS
-----
-
-You can install additional language packs by
-:ref:`installing Tesseract using Homebrew with all language packs <macos-all-languages>`.
-
-Docker
------
-
-Users of the OCRmyPDF Docker image should install language packs into a
-derived Docker image as
-:ref:`described in that section <docker-lang-packs>`.
-
-Windows
-------
-
-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).
-
-Custom language packs
-=====================
-
-If you have fine-tuned or trained Tesseract and generated custom trained data, you can
-copy your ``customlang.traineddata`` file into your Tesseract "tessdata" folder, and
-then use the ``-l customlang`` argument to tell OCRmyPDF to pass that language on to
-Tesseract.
@@ -0,0 +1,181 @@
+% SPDX-FileCopyrightText: 2022 James R. Barlow
+% SPDX-License-Identifier: CC-BY-SA-4.0
+
+# Maintainer notes
+
+This is for those who package OCRmyPDF for downstream use. (Thank you
+for your hard work.)
+
+## Known ports/packagers
+
+OCRmyPDF has been ported to many platforms already. If you are
+interesting in porting to a new platform, check with
+[Repology](https://repology.org/projects/?search=ocrmypdf) to see the
+status of that platform.
+
+### Make sure you can package pikepdf
+
+pikepdf, created by the same author, is a mixed Python and C++14 package
+with much stiffer build requirements. If you want to use OCRmyPDF on
+some novel platform or distribution, first make sure you can package
+pikepdf.
+
+### Core dependencies
+
+:::{versionchanged} 17.0.0
+Ghostscript is no longer strictly required. OCRmyPDF now supports alternative
+codepaths for both PDF rasterization and PDF/A conversion.
+:::
+
+OCRmyPDF has the following runtime dependencies:
+
+**For PDF rasterization** (converting PDF pages to images for OCR):
+
+- `pypdfium2` (Python package) - OR -
+- `ghostscript` (system binary)
+- Recommendation: Install both for best compatibility
+
+**For PDF/A conversion**:
+
+- `verapdf` (system binary) with pikepdf's speculative conversion - OR -
+- `ghostscript` (system binary)
+- Recommendation: Install both for best compatibility
+
+**For OCR**:
+- `tesseract-ocr` (system binary) - Required for MVP
+
+**For text rendering** (expressing OCR results in PDF):
+- `fpdf2` (Python package) - Required for text layer rendering
+- `uharfbuzz` (Python package) - Required for text layer rendering
+- Noto fonts (system package) - Recommended for text layer rendering.
+  `fonts-noto` on Debian/Ubuntu, `google-noto-fonts-all` on Fedora; Homebrew
+  has no single Noto package, only per-family casks such as `font-noto-sans`.
+
+**Other dependencies**:
+- `unpaper` (system binary) - Optional, enables `--clean` and `--clean-final`
+- `pngquant` (system binary) - Optional, enables `--optimize 2` and `--optimize 3`
+- `jbig2enc` (system binary) - Optional, improves compression of monochrome images
+
+While Ghostscript remains a capable and feature-rich tool with a long history,
+recent releases have introduced some compatibility challenges that OCRmyPDF v17
+addresses through alternative codepaths. For the best user experience, packagers
+should install both Ghostscript and the alternative tools (pypdfium2, verapdf)
+when available.
+
+On Windows, OCRmyPDF will also check the registry for Tesseract and Ghostscript
+locations.
+
+Tesseract OCR relies on SIMD for performance and only has proper support
+for this on ARM and x86\_64. Performance may be poor on other processor
+architectures.
+
+### Versioning scheme
+
+OCRmyPDF uses hatch-vcs for versioning, which derives the version from
+Git as a single source of truth. This may be unsuitable for some
+distributions, e.g. to indicate that your distribution modifies OCRmyPDF
+in some way.
+
+You can patch the `__version__` variable in `src/ocrmypdf/_version.py`
+if necessary, or set the environment variable
+`SETUPTOOLS_SCM_PRETEND_VERSION` to the required version, if you need to
+override versioning for some reason.
+
+### jbig2enc
+
+OCRmyPDF will use jbig2enc, a JBIG2 encoder, if one can be found. Some
+distributions have shied away from packaging JBIG2 because it contains
+patented algorithms, but all patents have expired since 2017. If
+possible, consider packaging it too to improve OCRmyPDF's compression.
+
+:::{note}
+Lossy JBIG2 encoding has been removed in v17.0.0 due to well-documented
+risks of character substitution errors. Previously we provided this feature
+on a "caveat emptor" basis but in the interest of focusing and eliminating
+risks, we decided to remove this option. Now, only lossless JBIG2 compression
+is supported.
+:::
+
+### Dependency matrix for packagers
+
+:::{versionadded} 17.0.0
+:::
+
+The following table summarizes the dependency options introduced in v17.0.0:
+
+| Feature | Option 1 | Option 2 | Notes |
+|---------|----------|----------|-------|
+| PDF rasterization | pypdfium2 (Python) | ghostscript (binary) | pypdfium2 preferred when available |
+| PDF/A conversion | verapdf + pikepdf | ghostscript | verapdf validates speculative conversion |
+| Text rendering | fpdf2 (Python) | - | Required, replaces legacy hOCR renderer |
+| OCR | tesseract-ocr | `--ocr-engine none` | Can be skipped entirely |
+
+**Minimum viable installation:**
+
+- tesseract-ocr + (pypdfium2 OR ghostscript) + fpdf2
+
+**Recommended installation:**
+
+- tesseract-ocr + pypdfium2 + ghostscript + verapdf + fpdf2 + unpaper + pngquant + jbig2enc
+
+:::{warning}
+If Ghostscript is not installed and verapdf is not available, PDF/A output
+cannot be produced. The output will be a standard PDF instead. This is a
+breaking change for rare configurations that previously relied on PDF/A
+output without Ghostscript alternatives.
+:::
+
+**Sample debian/control dependency specification**
+
+```
+Depends:
+ fonts-noto,
+ fpdf2 (>= 2.8),
+ ghostscript (>= 9.55),  # Not strictly required, but best user experience
+ icc-profiles-free,
+ img2pdf,
+ python3-coloredlogs,
+ python3-deprecation,
+ python3-pdfminer (>= 20181108+dfsg-3),
+ python3-pikepdf (>= 8.14.0),
+ python3-pil,
+ python3-pluggy,
+ python3-reportlab,
+ python3-rich,
+ python3-uharfbuzz,  # Not currently in Debian
+ tesseract-ocr (>= 5.0.0),
+ zlib1g,
+ ${misc:Depends},
+ ${python3:Depends},
+Recommends:
+ cyclopts,   # Not currently in Debian
+ jbig2
+ paddleocr,  # Not currently in Debian
+ pngquant,
+ pypdfium2,  # Not currently in Debian
+ unpaper,
+ verapdf,    # Not currently in Debian
+Suggests:
+ ocrmypdf-doc,
+ python-watchdog,
+```
+
+### Command line completions
+
+Please ensure that command line completions are installed, as described
+in the installation documentation.
+
+### 32-bit Linux support
+
+If you maintain a Linux distribution that supports 32-bit x86 or ARM,
+OCRmyPDF should continue to work as long as all of its dependencies
+continue to be available in 32-bit form. Please note we do not test on
+32-bit platforms.
+
+### HEIF/HEIC
+
+OCRmyPDF defaults to installing the pi-heif PyPI package, which supports
+converting HEIF (High Efficiency Image File Format) images to PDF from
+the command line. If your distribution does not have this library
+available, you can exclude it and OCRmyPDF will gracefully degrade
+automatically, losing only support for this feature.
@@ -1,76 +0,0 @@
-.. SPDX-FileCopyrightText: 2022 James R. Barlow
-..
-.. SPDX-License-Identifier: CC-BY-SA-4.0
-
-================
-Maintainer notes
-================
-
-This is for those who package OCRmyPDF for downstream use.  (Thank you
-for your hard work.)
-
-Known ports/packagers
-=====================
-
-OCRmyPDF has been ported to many platforms already. If you are interesting in
-porting to a new platform, check with
-`Repology <https://repology.org/projects/?search=ocrmypdf>`__ to see the status
-of that platform.
-
-Make sure you can package pikepdf
---------------------------------
-
-pikepdf, created by the same author, is a mixed Python and C++14 package with
-much stiffer build requirements. If you want to use OCRmyPDF on some novel platform
-or distribution, first make sure you can package pikepdf.
-
-Non-Python dependencies
-----------------------
-
-Note that we have non-Python dependencies. In particular, OCRmyPDF requires
-Ghostscript and Tesseract OCR to be installed and needs to be able to locate their
-binaries on the system PATH. On Windows, OCRmyPDF will also check the registry
-for their locations.
-
-Tesseract OCR relies on SIMD for performance and only has proper support for this
-on ARM and x86_64. Performance may be poor on other processor architectures.
-
-Versioning scheme
-----------------
-
-OCRmyPDF uses setuptools-scm for versioning, which derives the version from
-Git as a single source of truth. This may be unsuitable for some distributions, e.g.
-to indicate that your distribution modifies OCRmyPDF in some way.
-
-You can patch the ``__version__`` variable in ``src/ocrmypdf/_version.py`` if
-necessary.
-
-jbig2enc
--------
-
-OCRmyPDF will use jbig2enc, a JBIG2 encoder, if one can be found. Some distributions
-have shied away from packaging JBIG2 because it contains patented algorithms, but
-all patents have expired since 2017. If possible, consider packaging it too to
-improve OCRmyPDF's compression.
-
-Command line completions
------------------------
-
-Please ensure that command line completions are installed, as described in the
-installation documentation.
-
-32-bit Linux support
--------------------
-
-If you maintain a Linux distribution that supports 32-bit x86 or ARM, OCRmyPDF
-should continue to work as long as all of its dependencies continue to be
-available in 32-bit form. Please note we do not test on 32-bit platforms.
-
-HEIF/HEIC
---------
-
-OCRmyPDF defaults to installing the pi-heif PyPI package, which supports converting
-HEIF (High Efficiency Image File Format) images to PDF from the command line.
-If your distribution does not have this library available, you can exclude it and
-OCRmyPDF will gracefully degrade automatically, losing only support for this
-feature.
@@ -0,0 +1,113 @@
+% SPDX-FileCopyrightText: 2022 James R. Barlow
+% SPDX-License-Identifier: CC-BY-SA-4.0
+
+# PDF optimization
+
+OCRmyPDF includes an image-oriented PDF optimizer. By default, the
+optimizer runs with safe settings with the goal of improving compression
+at no loss of quality. At higher optimization levels, lossy
+optimizations may be applied and tuned. Optimization occurs after OCR,
+and only if OCR succeeded. It does not perform other possible
+optimizations such as deduplicating resources, consolidating fonts,
+simplifying vector drawings, or anything of that nature.
+
+:::{list-table} OCRmyPDF optimization settings
+---
+widths: 33 6 60
+header-rows: 1
+---
+
+* - Optimization level
+  - Shorthand
+  - Description
+* - ``--optimize 0``
+  - ``-O0``
+  - Disable most optimizations.
+* - ``--optimize 1`` (default)
+  - ``-O1``
+  - Enables lossless optimizations, such as transcoding images to more
+      efficient formats. Also compress other uncompressed objects in the
+      PDF and enables the more efficient "object streams" within the PDF.
+* - ``--optimize 2``
+  - ``-O2``
+  - All of the above, and enables lossy optimizations and color quantization.
+* - ``--optimize 3``
+  - ``-O3``
+  - All of the above, and enables more aggressive optimizations and targets lower
+      image quality.
+:::
+
+The exact type of optimizations performed will vary over time, and
+depend on what third party tools are installed.
+
+Despite optimizations, OCRmyPDF might still increase the overall file
+size, since it must embed information about the recognized text, and
+depending on the settings chosen, may not be able to represent the
+output file as compactly as the input file.
+
+## Optimizations that always occurs
+
+OCRmyPDF will automatically replace obsolete or inferior compression
+schemes such as RLE or LZW with superior schemes such as Deflate, and
+convert monochrome images to CCITT G4. Since this is lossless, it always
+occurs and there is no way to disable it. Other non-image compressed
+objects are compressed as well.
+
+## Fast web view
+
+OCRmyPDF automatically optimizes PDFs for \"fast web view\" in Adobe
+Acrobat\'s parlance, or equivalently, linearizes PDFs so that the
+resources they reference are presented in the order a viewer needs them
+for sequential display. This reduces the latency of viewing a PDF both
+online and from local storage, in exchange for a slight increase in file
+size.
+
+To disable this optimization and all others, use
+`ocrmypdf --optimize 0 ...` or the shorthand `-O0`.
+
+Adobe Acrobat might not report the file as being \"fast web view\".
+
+## Lossless optimizations
+
+At optimization level `-O1` (the default), OCRmyPDF will also attempt
+lossless image optimization.
+
+If a JBIG2 encoder is available, then monochrome images will be
+converted to JBIG2, with the potential for huge savings on large black
+and white images, since JBIG2 is far more efficient than any other
+monochrome (bi-level) compression. (All known US patents related to
+JBIG2 have probably expired, but it remains the responsibility of the
+user to supply a JBIG2 encoder such as
+[jbig2enc](https://github.com/agl/jbig2enc). OCRmyPDF does not implement
+JBIG2 encoding on its own.)
+
+OCRmyPDF currently does not attempt to recompress losslessly compressed
+objects more aggressively.
+
+## Lossy optimizations
+
+At optimization level `-O1`, `-O2` and `-O3`, OCRmyPDF will some attempt
+loss image optimization.
+
+If Ghostscript is used to create a PDF/A (the default), Ghostscript will
+optimize some images by converting them to JPEG, which are lossy. If
+`--output-type pdf` is used, there are no lossy optimizations. Ghostscript's
+JPEG conversion is quite safe.
+
+If `pngquant` is installed, OCRmyPDF will use it to perform quantize
+paletted images to reduce their size.
+
+The quality of JPEGs may be lowered, on the assumption that a lower
+quality image may be suitable for storage after OCR. Use `--jpeg-quality`
+to control the optimizer's JPEG quality target. The optimizer is the
+recommended way to reduce JPEG image sizes: it applies consistently
+regardless of whether Ghostscript was used to produce a PDF/A.
+
+If you specifically need to tune Ghostscript's own PDF/A image handling
+(for example, to force a hard DPI cap), see
+[Advanced Ghostscript tuning](advanced.md#advanced-ghostscript-tuning)
+for the separate `--ghostscript-jpeg-quality` and
+`--ghostscript-jpeg-maxdpi` options.
+
+It is not possible to optimize all image types. Uncommon image types may
+be skipped by the optimizer.
@@ -1,100 +0,0 @@
-.. SPDX-FileCopyrightText: 2022 James R. Barlow
-..
-.. SPDX-License-Identifier: CC-BY-SA-4.0
-
-================
-PDF optimization
-================
-
-OCRmyPDF includes an image-oriented PDF optimizer. By default, the optimizer
-runs with safe settings with the goal of improving compression at no loss of
-quality. At higher optimization levels, lossy optimizations may be applied and
-tuned. Optimization occurs after OCR, and only if OCR succeeded.  It does not
-perform other possible optimizations such as deduplicating resources,
-consolidating fonts, simplifying vector drawings, or anything of that nature.
-
-.. list-table:: Title
-   :widths: 33 6 60
-   :header-rows: 1
-
-    * - Optimization level
-      - Shorthand
-      - Description
-    * - ``--optimize 0``
-      - ``-O0``
-      - Disable most optimizations.
-    * - ``--optimize 1`` (default)
-      - ``-O1``
-      - Safe and lossless optimizations.
-    * - ``--optimize 2``
-      - ``-O2``
-      - Safe and lossy optimizations.
-    * - ``--optimize 3``
-      - ``-O3``
-      - Aggressive lossy optimizations.
-
-The exact type of optimizations performed will vary over time, and depend on
-the availability of third-party tools.
-
-Despite optimizations, OCRmyPDF might still increase the overall file size,
-since it must embed information about the recognized text, and depending on the
-settings chosen, may not be able to represent the output file as compactly as
-the input file.
-
-Optimizations that always occurs
-================================
-
-OCRmyPDF will automatically replace obsolete or inferior compression schemes
-such as RLE or LZW with superior schemes such as Deflate, and convert
-monochrome images to CCITT G4. Since this is lossless, it always occurs and there
-is no way to disable it. Other non-image compressed objects are compressed as
-well.
-
-Fast web view
-=============
-
-OCRmyPDF automatically optimizes PDFs for "fast web view" in Adobe Acrobat's
-parlance, or equivalently, linearizes PDFs so that the resources they reference
-are presented in the order a viewer needs them for sequential display. This
-reduces the latency of viewing a PDF both online and from local storage, in
-exchange for a slight increase in file size.
-
-To disable this optimization and all others, use ``ocrmypdf --optimize 0 ...``
-or the shorthand ``-O0``.
-
-Adobe Acrobat might not report the file as being "fast web view".
-
-Lossless optimizations
-======================
-
-At optimization level ``-O1`` (the default), OCRmyPDF will also attempt lossless
-image optimization.
-
-If a JBIG2 encoder is available, then monochrome images will be converted to
-JBIG2, with the potential for huge savings on large black and white images,
-since JBIG2 is far more efficient than any other monochrome (bi-level)
-compression. (All known US patents related to JBIG2 have probably expired, but
-it remains the responsibility of the user to supply a JBIG2 encoder such as
-`jbig2enc <https://github.com/agl/jbig2enc>`__. OCRmyPDF does not implement
-JBIG2 encoding on its own.)
-
-OCRmyPDF currently does not attempt to recompress losslessly compressed objects
-more aggressively.
-
-Lossy optimizations
-===================
-
-At optimization level ``-O2`` and ``-O3``, OCRmyPDF will some attempt lossy
-image optimization.
-
-If ``pngquant`` is installed, OCRmyPDF will use it to perform quantize paletted
-images to reduce their size.
-
-The quality of JPEGs may be lowered, on the assumption that a lower quality
-image may be suitable for storage after OCR.
-
-It is not possible to optimize all image types. Uncommon image types may be
-skipped by the optimizer.
-
-OCRmyPDF provides :ref:`lossy mode JBIG2 <jbig2-lossy>` as an advanced feature
-that additional requires the argument ``--jbig2-lossy``.
@@ -1,13 +1,9 @@
-.. SPDX-FileCopyrightText: 2022 James R. Barlow
-..
-.. SPDX-License-Identifier: CC-BY-SA-4.0
+(security)=

-===================
-PDF security issues
-===================
+# PDF security issues

-   OCRmyPDF should only be used on PDFs you trust. It is not designed to
-   protect you against malware.
+> OCRmyPDF should only be used on PDFs you trust. It is not designed to
+> protect you against malware.

 Recognizing that many users have an interest in handling PDFs and
 applying OCR to PDFs they did not generate themselves, this article
@@ -16,89 +12,84 @@ themselves.

 The disclaimer applies: this software has no warranties of any kind.

-PDFs may contain malware
-========================
+## PDFs may contain malware

 PDF is a rich, complex file format. The official PDF 1.7 specification,
 ISO 32000:2008, is hundreds of pages long and references several annexes
 each of which are similar in length. PDFs can contain video, audio, XML,
 JavaScript and other programming, and forms. In some cases, they can
-open internet connections to pre-selected URLs. All of these are possible
-attack vectors.
+open internet connections to pre-selected URLs. All of these are
+possible attack vectors.

-In short, PDFs `may contain
-viruses <https://security.stackexchange.com/questions/64052/can-a-pdf-file-contain-a-virus>`__.
+In short, PDFs [may contain
+viruses](https://security.stackexchange.com/questions/64052/can-a-pdf-file-contain-a-virus).

 If you do not trust a PDF or its source, do not open it or use OCRmyPDF
 on it. Consider using a Docker container or virtual machine to isolate
 an untrusted PDF from your system.

-How OCRmyPDF processes PDFs
-===========================
+## How OCRmyPDF processes PDFs

 OCRmyPDF must open and interpret your PDF in order to insert an OCR
 layer. First, it runs all PDFs through
-`pikepdf <https://github.com/pikepdf/pikepdf>`__, a library based on
-`QPDF <https://github.com/qpdf/qpdf>`__, a program that repairs PDFs
-with syntax errors. This is done because, in the author's experience, a
+[pikepdf](https://github.com/pikepdf/pikepdf), a library based on
+[QPDF](https://github.com/qpdf/qpdf), a program that repairs PDFs with
+syntax errors. This is done because, in the author\'s experience, a
 significant number of PDFs in the wild, especially those created by
 scanners, are not well-formed files. QPDF makes it more likely that
 OCRmyPDF will succeed, but offers no security guarantees. QPDF is also
 used to split the PDF into single page PDFs.

 Finally, OCRmyPDF rasterizes each page of the PDF using
-`Ghostscript <http://ghostscript.com/>`__ in ``-dSAFER`` mode.
+[Ghostscript](http://ghostscript.com/) in `-dSAFER` mode.

 Depending on the options specified, OCRmyPDF may graft the OCR layer
-into the existing PDF or it may essentially reconstruct ("re-fry") a
+into the existing PDF or it may essentially reconstruct (\"re-fry\") a
 visually identical PDF that may be quite different at the binary level.
 That said, OCRmyPDF is not a tool designed for sanitizing PDFs.

-Password protected PDFs
-=======================
+## Password protected PDFs

 Password protected PDFs usually have two passwords, and owner and user
 password. When the user password is set to empty, PDF readers will open
-the file automatically and mark it as "(SECURED)". Password security can
-also request certain restrictions on the PDF, but anyone can remove these
-restrictions if they have either the owner *or* user password. Passwords
-mainly present a barrier for casual users.
+the file automatically and mark it as \"(SECURED)\". Password security
+can also request certain restrictions on the PDF, but anyone can remove
+these restrictions if they have either the owner *or* user password.
+Passwords mainly present a barrier for casual users.

 OCRmyPDF cannot remove passwords from PDFs. If you want to remove a
-password from a PDF, you must use other software, such as ``qpdf``.
+password from a PDF, you must use other software, such as `qpdf`.

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

-.. code-block:: bash
-
-   qpdf --decrypt --password='abc123' input.pdf no_password.pdf
+:::{code} 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``.
+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
-================
+## 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.
+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
-==================
+## Digital signatures

 Important documents can be digitally signed and certified to attest to
 their authorship, approval or execution of a legal agreement. OCRmyPDF
 will detect signed PDFs and will not modify them, unless the
-``--invalidate-digital-signatures`` option is used, which will
-invalidate any signatures. (The signature may still be present in the PDF
-if opened, but PDF readers will not validate it.)
+`--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
@@ -106,20 +97,19 @@ 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
+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
-==========================
+## 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.
+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.
+certificate, you can use other PDF software, such as Acrobat, to decrypt
+the PDF.
@@ -0,0 +1,24 @@
+% SPDX-FileCopyrightText: 2022 James R. Barlow
+% SPDX-License-Identifier: CC-BY-SA-4.0
+
+# Performance
+
+Some users have noticed that current versions of OCRmyPDF do not run as
+quickly as some older versions (specifically 6.x and older). This is
+because OCRmyPDF added image optimization as a postprocessing step, and
+it is enabled by default.
+
+## Speed
+
+If running OCRmyPDF quickly is your main goal, you can use settings such
+as:
+
+-   `--optimize 0` to disable file size optimization
+-   `--output-type pdf` to disable PDF/A generation
+-   `--fast-web-view 999999` to disable fast web view optimization
+-   `--skip-big` to skip large images, if some pages have large images
+
+You can also avoid:
+
+-   `--force-ocr`
+-   Image preprocessing
@@ -1,26 +0,0 @@
-.. SPDX-FileCopyrightText: 2022 James R. Barlow
-..
-.. SPDX-License-Identifier: CC-BY-SA-4.0
-
-===========
-Performance
-===========
-
-Some users have noticed that current versions of OCRmyPDF do not run as quickly
-as some older versions (specifically 6.x and older). This is because OCRmyPDF
-added image optimization as a postprocessing step, and it is enabled by default.
-
-Speed
-=====
-
-If running OCRmyPDF quickly is your main goal, you can use settings such as:
-
-* ``--optimize 0`` to disable file size optimization
-* ``--output-type pdf`` to disable PDF/A generation
-* ``--fast-web-view 999999`` to disable fast web view optimization
-* ``--skip-big`` to skip large images, if some pages have large images
-
-You can also avoid:
-
-* ``--force-ocr``
-* Image preprocessing
@@ -0,0 +1,416 @@
+% SPDX-FileCopyrightText: 2022 James R. Barlow
+% SPDX-License-Identifier: CC-BY-SA-4.0
+
+# Plugins
+
+> The key words "MUST", "MUST NOT", "REQUIRED", "SHALL", "SHALL
+> NOT", "SHOULD", "SHOULD NOT", "RECOMMENDED", "MAY", and
+> "OPTIONAL" in this document are to be interpreted as described in
+> RFC 2119.
+
+You can use plugins to customize the behavior of OCRmyPDF at certain points of
+interest.
+
+Currently, it is possible to:
+
+- add new command line arguments
+- override the decision for whether or not to perform OCR on a particular file
+- modify the image is about to be sent for OCR
+- modify the page image before it is converted to PDF
+- replace the Tesseract OCR with another OCR engine that has similar behavior
+- replace Ghostscript with another PDF to image converter (rasterizer) or
+  PDF/A generator
+
+OCRmyPDF plugins are based on the Python `pluggy` package and conform to its
+conventions. Note that: plugins installed with as setuptools entrypoints are
+not checked currently, because OCRmyPDF assumes you may not want to enable
+plugins for all files.
+
+See \[OCRmyPDF-EasyOCR\](<https://github.com/ocrmypdf/OCRmyPDF-EasyOCR>) for an
+example of a straightforward, fully working plugin.
+
+## Script plugins
+
+Script plugins may be called from the command line, by specifying the name of a file.
+Script plugins may be convenient for informal or "one-off" plugins, when a certain
+batch of files needs a special processing step for example.
+
+```bash
+ocrmypdf --plugin ocrmypdf_example_plugin.py input.pdf output.pdf
+```
+
+Multiple plugins may be installed by issuing the `--plugin` argument multiple times.
+
+## Packaged plugins
+
+Installed plugins may be installed into the same virtual environment as OCRmyPDF
+is installed into. They may be invoked using Python standard module naming.
+If you are intending to distribute a plugin, please package it.
+
+```bash
+ocrmypdf --plugin ocrmypdf_fancypants.pockets.contents input.pdf output.pdf
+```
+
+OCRmyPDF does not automatically import plugins, because the assumption is that
+plugins affect different files differently and you may not want them activated
+all the time. The command line or `ocrmypdf.ocr(plugin='...')` must call
+for them.
+
+Third parties that wish to distribute packages for ocrmypdf should package them
+as packaged plugins, and these modules should begin with the name `ocrmypdf_`
+similar to `pytest` packages such as `pytest-cov` (the package) and
+`pytest_cov` (the module).
+
+:::{note}
+We recommend plugin authors name their plugins with the prefix
+`ocrmypdf-` (for the package name on PyPI) and `ocrmypdf_` (for the
+module), just like pytest plugins. At the same time, please make it clear
+that your package is not official.
+:::
+
+## Plugins
+
+You can also create a plugin that OCRmyPDF will always automatically load if both are
+installed in the same virtual environment, using a project entrypoint.
+OCRmyPDF uses the entrypoint namespace "ocrmypdf".
+
+For example, `pyproject.toml` would need to contain the following, for a plugin named
+`ocrmypdf-exampleplugin`:
+
+```toml
+[project]
+name = "ocrmypdf-exampleplugin"
+
+[project.entry-points."ocrmypdf"]
+exampleplugin = "exampleplugin.pluginmodule"
+```
+
+## Plugin requirements
+
+OCRmyPDF generally uses multiple worker processes. When a new worker is started,
+Python will import all plugins again, including all plugins that were imported earlier.
+This means that the global state of a plugin in one worker will not be shared with
+other workers. As such, plugin hook implementations should be stateless, relying
+only on their inputs. Hook implementations may use their input parameters to
+to obtain a reference to shared state prepared by another hook implementation.
+Plugins must expect that other instances of the plugin will be running
+simultaneously.
+
+The `context` object that is passed to many hooks can be used to share information
+about a file being worked on. Plugins must write private, plugin-specific data to
+a subfolder named `{options.work_folder}/ocrmypdf-plugin-name`. Plugins MAY
+read and write files in `options.work_folder`, but should be aware that their
+semantics are subject to change.
+
+OCRmyPDF will delete `options.work_folder` when it has finished OCRing
+a file, unless invoked with `--keep-temporary-files`.
+
+The documentation for some plugin hooks contain a detailed description of the
+execution context in which they will be called.
+
+Plugins should be prepared to work whether executed in worker threads or worker
+processes. Generally, OCRmyPDF uses processes, but has a semi-hidden threaded
+argument that simplifies debugging.
+
+## Plugin hooks
+
+A plugin may provide the following hooks. Hooks must be decorated with
+`ocrmypdf.hookimpl`, for example:
+
+```python
+from ocrmypdf import hookimpl
+
+
+@hookimpl
+def add_options(parser):
+    pass
+```
+
+The following is a complete list of hooks that are available, and when
+they are called.
+
+(firstresult)=
+
+**Note on firstresult hooks**
+
+If multiple plugins install implementations for this hook, they will be called in
+the reverse of the order in which they are installed (i.e., last plugin wins).
+When each hook implementation is called in order, the first implementation that
+returns a value other than `None` will "win" and prevent execution of all other
+hooks. As such, you cannot "chain" a series of plugin filters together in this
+way. Instead, a single hook implementation should be responsible for any such
+chaining operations.
+
+## Examples
+
+- OCRmyPDF's test suite contains several plugins that are used to simulate certain
+  test conditions.
+- [ocrmypdf-papermerge](https://github.com/papermerge/OCRmyPDF_papermerge) is
+  a production plugin that integrates OCRmyPDF and the Papermerge document
+  management system.
+
+### Suppressing or overriding other plugins
+
+```{eval-rst}
+.. autofunction:: ocrmypdf.pluginspec.initialize
+```
+
+### Custom command line arguments
+
+```{eval-rst}
+.. autofunction:: ocrmypdf.pluginspec.add_options
+```
+
+```{eval-rst}
+.. autofunction:: ocrmypdf.pluginspec.check_options
+```
+
+### Plugin option models
+
+Plugins can define their own option models using Pydantic. This allows plugins to:
+
+- Define type-safe option structures with validation
+- Add CLI arguments that map to their option model fields
+- Access options via nested namespaces (e.g., `options.tesseract.timeout`)
+
+```{eval-rst}
+.. autofunction:: ocrmypdf.pluginspec.register_options
+```
+
+Plugin options can be accessed in two ways:
+
+1. **Flat access** (backward compatible): `options.tesseract_timeout`
+2. **Nested access**: `options.tesseract.timeout`
+
+Both access patterns are equivalent and return the same values.
+
+:::{note}
+**Plugin Interface Change**: Starting in OCRmyPDF v17.0.0, plugin hooks receive
+`OcrOptions` objects instead of `argparse.Namespace` objects. Most plugins will
+continue working due to duck-typing compatibility, but plugin developers should
+update their type hints accordingly.
+:::
+
+### Migration guide for plugin developers
+
+:::{versionadded} 17.0.0
+:::
+
+**Update imports:**
+
+```python
+from ocrmypdf._options import OcrOptions
+```
+
+**Update type hints:**
+
+```python
+# Before (v16 and earlier)
+def check_options(options: argparse.Namespace) -> None: ...
+
+
+# After (v17+)
+def check_options(options: OcrOptions) -> None: ...
+```
+
+**Attribute access unchanged:**
+
+```python
+# These work exactly as before
+options.languages
+options.output_type
+options.tesseract_timeout
+```
+
+**Remove in-place modifications:**
+
+```python
+# Before (v16 pattern - no longer recommended)
+def check_options(options):
+    options.some_computed_value = compute_value(options)
+
+
+# After (v17 pattern - compute at point of use)
+def some_function(options):
+    computed = compute_value(options)
+    use_computed(computed)
+```
+
+### Execution and progress reporting
+
+```{eval-rst}
+.. autoclass:: ocrmypdf.pluginspec.ProgressBar
+    :members:
+    :special-members: __init__, __enter__, __exit__
+```
+
+```{eval-rst}
+.. autoclass:: ocrmypdf.pluginspec.Executor
+    :members:
+    :special-members: __call__
+```
+
+```{eval-rst}
+.. autofunction:: ocrmypdf.pluginspec.get_logging_console
+```
+
+```{eval-rst}
+.. autofunction:: ocrmypdf.pluginspec.get_executor
+```
+
+```{eval-rst}
+.. autofunction:: ocrmypdf.pluginspec.get_progressbar_class
+```
+
+### Applying special behavior before processing
+
+```{eval-rst}
+.. autofunction:: ocrmypdf.pluginspec.validate
+```
+
+### PDF page to image
+
+```{eval-rst}
+.. autofunction:: ocrmypdf.pluginspec.rasterize_pdf_page
+```
+
+### Modifying intermediate images
+
+```{eval-rst}
+.. autofunction:: ocrmypdf.pluginspec.filter_ocr_image
+```
+
+```{eval-rst}
+.. autofunction:: ocrmypdf.pluginspec.filter_page_image
+```
+
+```{eval-rst}
+.. autofunction:: ocrmypdf.pluginspec.filter_pdf_page
+```
+
+### OCR engine
+
+```{eval-rst}
+.. autofunction:: ocrmypdf.pluginspec.get_ocr_engine
+```
+
+```{eval-rst}
+.. autoclass:: ocrmypdf.pluginspec.OcrEngine
+    :members:
+
+    .. automethod:: __str__
+```
+
+```{eval-rst}
+.. autoclass:: ocrmypdf.pluginspec.OrientationConfidence
+```
+
+### PDF/A production
+
+```{eval-rst}
+.. autofunction:: ocrmypdf.pluginspec.generate_pdfa
+```
+
+### PDF optimization
+
+```{eval-rst}
+.. autofunction:: ocrmypdf.pluginspec.optimize_pdf
+```
+
+```{eval-rst}
+.. autofunction:: ocrmypdf.pluginspec.is_optimization_enabled
+```
+
+### Working with OcrElement trees
+
+:::{versionadded} 17.0.0
+:::
+
+OCRmyPDF v17 introduces the `OcrElement` dataclass for representing OCR
+output in an engine-agnostic format. This enables plugins to work with
+OCR results without parsing hOCR XML.
+
+**Key classes:**
+
+```python
+from ocrmypdf import OcrElement, OcrClass, BoundingBox
+
+# OcrElement - represents any OCR structural unit
+page = OcrElement(
+    ocr_class=OcrClass.PAGE, bbox=BoundingBox(0, 0, 612, 792), children=[...]
+)
+
+# BoundingBox - axis-aligned bounding box (left, top, right, bottom)
+bbox = BoundingBox(left=100, top=50, right=300, bottom=80)
+
+# OcrClass - constants for element types
+OcrClass.PAGE  # "ocr_page"
+OcrClass.LINE  # "ocr_line"
+OcrClass.WORD  # "ocrx_word"
+OcrClass.PARAGRAPH  # "ocr_par"
+```
+
+**Navigating the tree:**
+
+```python
+# Get all words in a page
+words = page.words  # Returns list[OcrElement]
+
+# Get all lines
+lines = page.lines
+
+# Get combined text
+text = page.get_text_recursive()
+
+# Iterate by class
+for para in page.paragraphs:
+    print(para.get_text_recursive())
+```
+
+**OCR engine plugins:**
+
+Plugins implementing custom OCR engines can now output `OcrElement` trees
+directly via the `generate_ocr()` method, bypassing hOCR entirely:
+
+```python
+from pathlib import Path
+from ocrmypdf.pluginspec import OcrEngine
+from ocrmypdf import OcrElement, OcrClass, BoundingBox
+
+
+class MyOcrEngine(OcrEngine):
+    def generate_ocr(
+        self,
+        input_file: Path,
+        options,
+        context,
+    ) -> OcrElement:
+        # Perform OCR and return OcrElement tree directly
+        # No need to generate hOCR XML
+        return OcrElement(
+            ocr_class=OcrClass.PAGE,
+            bbox=BoundingBox(0, 0, width, height),
+            dpi=300,
+            children=[
+                OcrElement(
+                    ocr_class=OcrClass.LINE,
+                    bbox=BoundingBox(100, 50, 500, 80),
+                    children=[
+                        OcrElement(
+                            ocr_class=OcrClass.WORD,
+                            bbox=BoundingBox(100, 50, 200, 80),
+                            text="Hello",
+                        ),
+                        # ... more words
+                    ],
+                ),
+                # ... more lines
+            ],
+        )
+
+    def supports_generate_ocr(self) -> bool:
+        return True  # Indicate this engine uses generate_ocr()
+```
+
+This approach is simpler than generating hOCR and allows modern OCR
+engines to integrate more naturally with OCRmyPDF.
@@ -1,235 +0,0 @@
-.. SPDX-FileCopyrightText: 2022 James R. Barlow
-..
-.. SPDX-License-Identifier: CC-BY-SA-4.0
-
-=======
-Plugins
-=======
-
-    The key words "MUST", "MUST NOT", "REQUIRED", "SHALL", "SHALL
-    NOT", "SHOULD", "SHOULD NOT", "RECOMMENDED",  "MAY", and
-    "OPTIONAL" in this document are to be interpreted as described in
-    RFC 2119.
-
-You can use plugins to customize the behavior of OCRmyPDF at certain points of
-interest.
-
-Currently, it is possible to:
-
- add new command line arguments
- override the decision for whether or not to perform OCR on a particular file
- modify the image is about to be sent for OCR
- modify the page image before it is converted to PDF
- replace the Tesseract OCR with another OCR engine that has similar behavior
- replace Ghostscript with another PDF to image converter (rasterizer) or
-  PDF/A generator
-
-OCRmyPDF plugins are based on the Python ``pluggy`` package and conform to its
-conventions. Note that: plugins installed with as setuptools entrypoints are
-not checked currently, because OCRmyPDF assumes you may not want to enable
-plugins for all files.
-
-Script plugins
-==============
-
-Script plugins may be called from the command line, by specifying the name of a file.
-Script plugins may be convenient for informal or "one-off" plugins, when a certain
-batch of files needs a special processing step for example.
-
-.. code-block:: bash
-
-    ocrmypdf --plugin ocrmypdf_example_plugin.py input.pdf output.pdf
-
-Multiple plugins may be installed by issuing the ``--plugin`` argument multiple times.
-
-Packaged plugins
-================
-
-Installed plugins may be installed into the same virtual environment as OCRmyPDF
-is installed into. They may be invoked using Python standard module naming.
-If you are intending to distribute a plugin, please package it.
-
-.. code-block:: bash
-
-    ocrmypdf --plugin ocrmypdf_fancypants.pockets.contents input.pdf output.pdf
-
-OCRmyPDF does not automatically import plugins, because the assumption is that
-plugins affect different files differently and you may not want them activated
-all the time. The command line or ``ocrmypdf.ocr(plugin='...')`` must call
-for them.
-
-Third parties that wish to distribute packages for ocrmypdf should package them
-as packaged plugins, and these modules should begin with the name ``ocrmypdf_``
-similar to ``pytest`` packages such as ``pytest-cov`` (the package) and
-``pytest_cov`` (the module).
-
-.. note::
-
-    We recommend plugin authors name their plugins with the prefix
-    ``ocrmypdf-`` (for the package name on PyPI) and ``ocrmypdf_`` (for the
-    module), just like pytest plugins. At the same time, please make it clear
-    that your package is not official.
-
-Setuptools plugins
-==================
-
-You can also create a plugin that OCRmyPDF will always automatically load if both are
-installed in the same virtual environment, using a setuptools entrypoint.
-
-Your package's ``pyproject.toml`` would need to contain the following, for a plugin
-named ``ocrmypdf-exampleplugin``:
-
-.. code-block:: toml
-
-    [project]
-    name = "ocrmypdf-exampleplugin"
-
-    [project.entry-points."ocrmypdf"]
-    exampleplugin = "exampleplugin.pluginmodule"
-
-.. code-block:: ini
-
-    # equivalent setup.cfg
-    [options.entry_points]
-    ocrmypdf =
-        exampleplugin = exampleplugin.pluginmodule
-
-Plugin requirements
-===================
-
-OCRmyPDF generally uses multiple worker processes. When a new worker is started,
-Python will import all plugins again, including all plugins that were imported earlier.
-This means that the global state of a plugin in one worker will not be shared with
-other workers. As such, plugin hook implementations should be stateless, relying
-only on their inputs. Hook implementations may use their input parameters to
-to obtain a reference to shared state prepared by another hook implementation.
-Plugins must expect that other instances of the plugin will be running
-simultaneously.
-
-The ``context`` object that is passed to many hooks can be used to share information
-about a file being worked on. Plugins must write private, plugin-specific data to
-a subfolder named ``{options.work_folder}/ocrmypdf-plugin-name``. Plugins MAY
-read and write files in ``options.work_folder``, but should be aware that their
-semantics are subject to change.
-
-OCRmyPDF will delete ``options.work_folder`` when it has finished OCRing
-a file, unless invoked with ``--keep-temporary-files``.
-
-The documentation for some plugin hooks contain a detailed description of the
-execution context in which they will be called.
-
-Plugins should be prepared to work whether executed in worker threads or worker
-processes. Generally, OCRmyPDF uses processes, but has a semi-hidden threaded
-argument that simplifies debugging.
-
-
-Plugin hooks
-============
-
-A plugin may provide the following hooks. Hooks must be decorated with
-``ocrmypdf.hookimpl``, for example:
-
-.. code-block:: python
-
-    from ocrmpydf import hookimpl
-
-    @hookimpl
-    def add_options(parser):
-        pass
-
-The following is a complete list of hooks that are available, and when
-they are called.
-
-.. _firstresult:
-
-**Note on firstresult hooks**
-
-If multiple plugins install implementations for this hook, they will be called in
-the reverse of the order in which they are installed (i.e., last plugin wins).
-When each hook implementation is called in order, the first implementation that
-returns a value other than ``None`` will "win" and prevent execution of all other
-hooks. As such, you cannot "chain" a series of plugin filters together in this
-way. Instead, a single hook implementation should be responsible for any such
-chaining operations.
-
-Examples
-========
-
-* OCRmyPDF's test suite contains several plugins that are used to simulate certain
-  test conditions.
-* `ocrmypdf-papermerge <https://github.com/papermerge/OCRmyPDF_papermerge>`_ is
-  a production plugin that integrates OCRmyPDF and the Papermerge document
-  management system.
-
-
-Suppressing or overriding other plugins
---------------------------------------
-
-.. autofunction:: ocrmypdf.pluginspec.initialize
-
-Custom command line arguments
-----------------------------
-
-.. autofunction:: ocrmypdf.pluginspec.add_options
-
-.. autofunction:: ocrmypdf.pluginspec.check_options
-
-Execution and progress reporting
--------------------------------
-
-.. autoclass:: ocrmypdf.pluginspec.ProgressBar
-    :members:
-    :special-members: __init__, __enter__, __exit__
-
-.. autoclass:: ocrmypdf.pluginspec.Executor
-    :members:
-    :special-members: __call__
-
-.. autofunction:: ocrmypdf.pluginspec.get_logging_console
-
-.. autofunction:: ocrmypdf.pluginspec.get_executor
-
-.. autofunction:: ocrmypdf.pluginspec.get_progressbar_class
-
-Applying special behavior before processing
-------------------------------------------
-
-.. autofunction:: ocrmypdf.pluginspec.validate
-
-PDF page to image
-----------------
-
-.. autofunction:: ocrmypdf.pluginspec.rasterize_pdf_page
-
-Modifying intermediate images
-----------------------------
-
-.. autofunction:: ocrmypdf.pluginspec.filter_ocr_image
-
-.. autofunction:: ocrmypdf.pluginspec.filter_page_image
-
-.. autofunction:: ocrmypdf.pluginspec.filter_pdf_page
-
-OCR engine
----------
-
-.. autofunction:: ocrmypdf.pluginspec.get_ocr_engine
-
-.. autoclass:: ocrmypdf.pluginspec.OcrEngine
-    :members:
-
-    .. automethod:: __str__
-
-.. autoclass:: ocrmypdf.pluginspec.OrientationConfidence
-
-PDF/A production
----------------
-
-.. autofunction:: ocrmypdf.pluginspec.generate_pdfa
-
-PDF optimization
----------------
-
-.. autofunction:: ocrmypdf.pluginspec.optimize_pdf
-
-.. autofunction:: ocrmypdf.pluginspec.is_optimization_enabled
@@ -0,0 +1,34 @@
+% SPDX-FileCopyrightText: 2022 James R. Barlow
+% SPDX-License-Identifier: CC-BY-SA-4.0
+
+# Release notes
+
+OCRmyPDF uses [semantic versioning](http://semver.org/) for its
+command line interface and its public API.
+
+OCRmyPDF's output messages are not considered part of the stable interface -
+that is, output messages may be improved at any release level, so parsing them
+may be unreliable. Use the API to depend on precise behavior.
+
+The public API may be useful in scripts that launch OCRmyPDF processes or that
+wish to use some of its features for working with PDFs.
+
+The most recent release of OCRmyPDF is ![version](https://img.shields.io/pypi/v/ocrmypdf.svg). Any newer versions
+referred to in these notes may exist the main branch but have not been
+tagged yet.
+
+OCRmyPDF typically supports the three most recent Python versions.
+
+:::{note}
+Attention maintainers: these release notes may be updated with information
+about a forthcoming release that has not been tagged yet. A release is only
+official when it's tagged and posted to PyPI.
+:::
+
+```{toctree}
+:glob: true
+:maxdepth: 1
+:reversed: true
+
+version*
+```
@@ -0,0 +1,14 @@
+% SPDX-FileCopyrightText: 2022 James R. Barlow
+% SPDX-License-Identifier: CC-BY-SA-4.0
+
+# v2
+
+## v2.2-stable (2014-09-29)
+
+OCRmyPDF versions 1 and 2 were implemented as shell scripts. OCRmyPDF
+3.0+ is a fork that gradually replaced all shell scripts with Python
+while maintaining the existing command line arguments. No one is
+maintaining old versions.
+
+For details on older versions, see the [final version of its release
+notes](https://github.com/fritz-hh/OCRmyPDF/blob/7fd3dbdf42ca53a619412ce8add7532c5e81a9d1/RELEASE_NOTES.md).
@@ -0,0 +1,219 @@
+% SPDX-FileCopyrightText: 2022 James R. Barlow
+% SPDX-License-Identifier: CC-BY-SA-4.0
+
+# v3
+
+## v3.2.1
+
+Changes
+
+- Fixed {issue}`47`
+  "convert() got and unexpected keyword argument 'dpi'" by upgrading to
+  img2pdf 0.2
+- Tweaked the Dockerfiles
+
+## v3.2
+
+New features
+
+- Lossless reconstruction: when possible, OCRmyPDF will inject text
+  layers without otherwise manipulating the content and layout of a PDF
+  page. For example, a PDF containing a mix of vector and raster
+  content would see the vector content preserved. Images may still be
+  transcoded during PDF/A conversion. (`--deskew` and
+  `--clean-final` disable this mode, necessarily.)
+- New argument `--tesseract-pagesegmode` allows you to pass page
+  segmentation arguments to Tesseract OCR. This helps for two column
+  text and other situations that confuse Tesseract.
+- Added a new "polyglot" version of the Docker image, that generates
+  Tesseract with all languages packs installed, for the polyglots among
+  us. It is much larger.
+
+Changes
+
+- JPEG transcoding quality is now 95 instead of the default 75. Bigger
+  file sizes for less degradation.
+
+## v3.1.1
+
+Changes
+
+- Fixed bug that caused incorrect page size and DPI calculations on
+  documents with mixed page sizes
+
+## v3.1
+
+Changes
+
+- Default output format is now PDF/A-2b instead of PDF/A-1b
+- Python 3.5 and macOS El Capitan are now supported platforms - no
+  changes were needed to implement support
+- Improved some error messages related to missing input files
+- Fixed {issue}`20`: uppercase .PDF extension not accepted
+- Fixed an issue where OCRmyPDF failed to text that certain pages
+  contained previously OCR'ed text, such as OCR text produced by
+  Tesseract 3.04
+- Inserts /Creator tag into PDFs so that errors can be traced back to
+  this project
+- Added new option `--pdf-renderer=auto`, to let OCRmyPDF pick the
+  best PDF renderer. Currently it always chooses the 'hocrtransform'
+  renderer but that behavior may change.
+- Set up Travis CI automatic integration testing
+
+## v3.0
+
+New features
+
+- Easier installation with a Docker container or Python's `pip`
+  package manager
+- Eliminated many external dependencies, so it's easier to setup
+- Now installs `ocrmypdf` to `/usr/local/bin` or equivalent for
+  system-wide access and easier typing
+- Improved command line syntax and usage help (`--help`)
+- Tesseract 3.03+ PDF page rendering can be used instead for better
+  positioning of recognized text (`--pdf-renderer tesseract`)
+- PDF metadata (title, author, keywords) are now transferred to the
+  output PDF
+- PDF metadata can also be set from the command line (`--title`,
+  etc.)
+- Automatic repairs malformed input PDFs if possible
+- Added test cases to confirm everything is working
+- Added option to skip extremely large pages that take too long to OCR
+  and are often not OCRable (e.g. large scanned maps or diagrams);
+  other pages are still processed (`--skip-big`)
+- Added option to kill Tesseract OCR process if it seems to be taking
+  too long on a page, while still processing other pages
+  (`--tesseract-timeout`)
+- Less common colorspaces (CMYK, palette) are now supported by
+  conversion to RGB
+- Multiple images on the same PDF page are now supported
+
+Changes
+
+- New, robust rewrite in Python 3.4+ with
+  [ruffus](http://www.ruffus.org.uk/index.html) pipelines
+
+- Now uses Ghostscript 9.14's improved color conversion model to
+  preserve PDF colors
+
+- OCR text is now rendered in the PDF as invisible text. Previous
+  versions of OCRmyPDF incorrectly rendered visible text with an image
+  on top.
+
+- All "tasks" in the pipeline can be executed in parallel on any
+  available CPUs, increasing performance
+
+- The `-o DPI` argument has been phased out, in favor of
+  `--oversample DPI`, in case we need `-o OUTPUTFILE` in the future
+
+- Removed several dependencies, so it's easier to install. We no longer
+  use:
+
+  - GNU [parallel](https://www.gnu.org/software/parallel/)
+  - [ImageMagick](http://www.imagemagick.org/script/index.php)
+  - Python 2.7
+  - Poppler
+  - [MuPDF](http://mupdf.com/docs/) tools
+  - shell scripts
+  - Java and [JHOVE](http://jhove.sourceforge.net/)
+  - libxml2
+
+- Some new external dependencies are required or optional, compared to
+  v2.x:
+
+  - Ghostscript 9.14+
+  - [qpdf](http://qpdf.sourceforge.net/) 5.0.0+
+  - [Unpaper](https://github.com/Flameeyes/unpaper) 6.1 (optional)
+  - some automatically managed Python packages
+
+Release candidates^
+
+- rc9:
+
+  - Fix
+    {issue}`118`:
+    report error if ghostscript iccprofiles are missing
+  - fixed another issue related to
+    {issue}`111`: PDF
+    rasterized to palette file
+  - add support image files with a palette
+  - don't try to validate PDF file after an exception occurs
+
+- rc8:
+
+  - Fix
+    {issue}`111`:
+    exception thrown if PDF is missing DocumentInfo dictionary
+
+- rc7:
+
+  - fix error when installing direct from pip, "no such file
+    'requirements.txt'"
+
+- rc6:
+
+  - dropped libxml2 (Python lxml) since Python 3's internal XML parser
+    is sufficient
+  - set up Docker container
+  - fix Unicode errors if recognized text contains Unicode characters
+    and system locale is not UTF-8
+
+- rc5:
+
+  - dropped Java and JHOVE in favour of qpdf
+  - improved command line error output
+  - additional tests and bug fixes
+  - tested on Ubuntu 14.04 LTS
+
+- rc4:
+
+  - dropped MuPDF in favour of qpdf
+  - fixed some installer issues and errors in installation
+    instructions
+  - improve performance: run Ghostscript with multithreaded rendering
+  - improve performance: use multiple cores by default
+  - bug fix: checking for wrong exception on process timeout
+
+- rc3: skipping version number intentionally to avoid confusion with
+  Tesseract
+
+- rc2: first release for public testing to test-PyPI, Github
+
+- rc1: testing release process
+
+## Compatibility notes
+
+- `./OCRmyPDF.sh` script is still available for now
+- Stacking the verbosity option like `-vvv` is no longer supported
+- The configuration file `config.sh` has been removed. Instead, you
+  can feed a file to the arguments for common settings:
+
+```
+ocrmypdf input.pdf output.pdf @settings.txt
+```
+
+where `settings.txt` contains *one argument per line*, for example:
+
+```
+-l
+deu
+--author
+A. Merkel
+--pdf-renderer
+tesseract
+```
+
+Fixes
+
+- Handling of filenames containing spaces: fixed
+
+Notes and known issues
+
+- Some dependencies may work with lower versions than tested, so try
+  overriding dependencies if they are "in the way" to see if they work.
+- `--pdf-renderer tesseract` will output files with an incorrect page
+  size in Tesseract 3.03, due to a bug in Tesseract.
+- PDF files containing "inline images" are not supported and won't be
+  for the 3.0 release. Scanned images almost never contain inline
+  images.
+
@@ -0,0 +1,408 @@
+% SPDX-FileCopyrightText: 2022 James R. Barlow
+% SPDX-License-Identifier: CC-BY-SA-4.0
+
+# v4
+
+## v4.5.6
+
+- Fixed {issue}`156`,
+  'NoneType' object has no attribute 'getObject' on pages with no
+  optional /Contents record. This should resolve all issues related to
+  pages with no /Contents record.
+- Fixed {issue}`158`, ocrmypdf
+  now stops and terminates if Ghostscript fails on an intermediate
+  step, as it is not possible to proceed.
+- Fixed {issue}`160`,
+  exception thrown on certain invalid arguments instead of error
+  message
+
+## v4.5.5
+
+- Automated update of macOS homebrew tap
+- Fixed {issue}`154`, KeyError
+  '/Contents' when searching for text on blank pages that have no
+  /Contents record. Note: incomplete fix for this issue.
+
+## v4.5.4
+
+- Fixed `--skip-big` raising an exception if a page contains no images
+  ({issue}`152`) (thanks
+  to @TomRaz)
+- Fixed an issue where pages with no images might trigger "cannot write
+  mode P as JPEG"
+  ({issue}`151`)
+
+## v4.5.3
+
+- Added a workaround for Ghostscript 9.21 and probably earlier versions
+  would fail with the error message "VMerror -25", due to a Ghostscript
+  bug in XMP metadata handling
+- High Unicode characters (U+10000 and up) are no longer accepted for
+  setting metadata on the command line, as Ghostscript may not handle
+  them correctly.
+- Fixed an issue where the `tess4` renderer would duplicate content
+  onto output pages if tesseract failed or timed out
+- Fixed `tess4` renderer not recognized when lossless reconstruction
+  is possible
+
+## v4.5.2
+
+- Fixed {issue}`147`,
+  `--pdf-renderer tess4 --clean` will produce an oversized page
+  containing the original image in the bottom left corner, due to loss
+  DPI information.
+- Make "using Tesseract 4.0" warning less ominous
+- Set up machinery for homebrew OCRmyPDF tap
+
+## v4.5.1
+
+- Fixed {issue}`137`,
+  proportions of images with a non-square pixel aspect ratio would be
+  distorted in output for `--force-ocr` and some other combinations
+  of flags
+
+## v4.5
+
+- PDFs containing "Form XObjects" are now supported (issue
+  {issue}`134`; PDF
+  reference manual 8.10), and images they contain are taken into
+  account when determining the resolution for rasterizing
+- The Tesseract 4 Docker image no longer includes all languages,
+  because it took so long to build something would tend to fail
+- OCRmyPDF now warns about using `--pdf-renderer tesseract` with
+  Tesseract 3.04 or lower due to issues with Ghostscript corrupting the
+  OCR text in these cases
+
+## v4.4.2
+
+- The Docker images (ocrmypdf, ocrmypdf-polyglot, ocrmypdf-tess4) are
+  now based on Ubuntu 16.10 instead of Debian stretch
+
+  - This makes supporting the Tesseract 4 image easier
+  - This could be a disruptive change for any Docker users who built
+    customized these images with their own changes, and made those
+    changes in a way that depends on Debian and not Ubuntu
+
+- OCRmyPDF now prevents running the Tesseract 4 renderer with Tesseract
+  3.04, which was permitted in v4.4 and v4.4.1 but will not work
+
+## v4.4.1
+
+- To prevent a [TIFF output
+  error](https://github.com/python-pillow/Pillow/issues/2206) caused
+  by img2pdf >= 0.2.1 and Pillow \<= 3.4.2, dependencies have been
+  tightened
+- The Tesseract 4.00 simultaneous process limit was increased from 1 to
+  2, since it was observed that 1 lowers performance
+- Documentation improvements to describe the `--tesseract-config`
+  feature
+- Added test cases and fixed error handling for `--tesseract-config`
+- Tweaks to setup.py to deal with issues in the v4.4 release
+
+## v4.4
+
+- Tesseract 4.00 is now supported on an experimental basis.
+
+  - A new rendering option `--pdf-renderer tess4` exploits Tesseract
+    4's new text-only output PDF mode. See the documentation on PDF
+    Renderers for details.
+  - The `--tesseract-oem` argument allows control over the Tesseract
+    4 OCR engine mode (tesseract's `--oem`). Use
+    `--tesseract-oem 2` to enforce the new LSTM mode.
+  - Fixed poor performance with Tesseract 4.00 on Linux
+
+- Fixed an issue that caused corruption of output to stdout in some
+  cases
+
+- Removed test for Pillow JPEG and PNG support, as the minimum
+  supported version of Pillow now enforces this
+
+- OCRmyPDF now tests that the intended destination file is writable
+  before proceeding
+
+- The test suite now requires `pytest-helpers-namespace` to run (but
+  not install)
+
+- Significant code reorganization to make OCRmyPDF re-entrant and
+  improve performance. All changes should be backward compatible for
+  the v4.x series.
+
+  - However, OCRmyPDF's dependency "ruffus" is not re-entrant, so no
+    Python API is available. Scripts should continue to use the
+    command line interface.
+
+## v4.3.5
+
+- Update documentation to confirm Python 3.6.0 compatibility. No code
+  changes were needed, so many earlier versions are likely supported.
+
+## v4.3.4
+
+- Fixed "decimal.InvalidOperation: quantize result has too many digits"
+  for high DPI images
+
+## v4.3.3
+
+- Fixed PDF/A creation with Ghostscript 9.20 properly
+- Fixed an exception on inline stencil masks with a missing optional
+  parameter
+
+## v4.3.2
+
+- Fixed a PDF/A creation issue with Ghostscript 9.20 (note: this fix
+  did not actually work)
+
+## v4.3.1
+
+- Fixed an issue where pages produced by the "hocr" renderer after a
+  Tesseract timeout would be rotated incorrectly if the input page was
+  rotated with a /Rotate marker
+- Fixed a file handle leak in LeptonicaErrorTrap that would cause a
+  "too many open files" error for files around hundred pages of pages
+  long when `--deskew` or `--remove-background` or other Leptonica
+  based image processing features were in use, depending on the system
+  value of `ulimit -n`
+- Ability to specify multiple languages for multilingual documents is
+  now advertised in documentation
+- Reduced the file sizes of some test resources
+- Cleaned up debug output
+- Tesseract caching in test cases is now more cautious about false
+  cache hits and reproducing exact output, not that any problems were
+  observed
+
+## v4.3
+
+- New feature `--remove-background` to detect and erase the
+  background of color and grayscale images
+
+- Better documentation
+
+- Fixed an issue with PDFs that draw images when the raster stack depth
+  is zero
+
+- ocrmypdf can now redirect its output to stdout for use in a shell
+  pipeline
+
+  - This does not improve performance since temporary files are still
+    used for buffering
+  - Some output validation is disabled in this mode
+
+## v4.2.5
+
+- Fixed an issue
+  ({issue}`100`) with
+  PDFs that omit the optional /BitsPerComponent parameter on images
+- Removed non-free file milk.pdf
+
+## v4.2.4
+
+- Fixed an error
+  ({issue}`90`) caused by
+  PDFs that use stencil masks properly
+- Fixed handling of PDFs that try to draw images or stencil masks
+  without properly setting up the graphics state (such images are now
+  ignored for the purposes of calculating DPI)
+
+## v4.2.3
+
+- Fixed an issue with PDFs that store page rotation (/Rotate) in an
+  indirect object
+
+- Integrated a few fixes to simplify downstream packaging (Debian)
+
+  - The test suite no longer assumes it is installed
+  - If running Linux, skip a test that passes Unicode on the command
+    line
+
+- Added a test case to check explicit masks and stencil masks
+
+- Added a test case for indirect objects and linearized PDFs
+
+- Deprecated the OCRmyPDF.sh shell script
+
+## v4.2.2
+
+- Improvements to documentation
+
+## v4.2.1
+
+- Fixed an issue where PDF pages that contained stencil masks would
+  report an incorrect DPI and cause Ghostscript to abort
+- Implemented stdin streaming
+
+## v4.2
+
+- ocrmypdf will now try to convert single image files to PDFs if they
+  are provided as input
+  ({issue}`15`)
+
+  - This is a basic convenience feature. It only supports a single
+    image and always makes the image fill the whole page.
+  - For better control over image to PDF conversion, use `img2pdf`
+    (one of ocrmypdf's dependencies)
+
+- New argument `--output-type {pdf|pdfa}` allows disabling
+  Ghostscript PDF/A generation
+
+  - `pdfa` is the default, consistent with past behavior
+  - `pdf` provides a workaround for users concerned about the
+    increase in file size from Ghostscript forcing JBIG2 images to
+    CCITT and transcoding JPEGs
+  - `pdf` preserves as much as it can about the original file,
+    including problems that PDF/A conversion fixes
+
+- PDFs containing images with "non-square" pixel aspect ratios, such as
+  200x100 DPI, are now handled and converted properly (fixing a bug
+  that caused to be cropped)
+
+- `--force-ocr` rasterizes pages even if they contain no images
+
+  - supports users who want to use OCRmyPDF to reconstruct text
+    information in PDFs with damaged Unicode maps (copy and paste text
+    does not match displayed text)
+  - supports reinterpreting PDFs where text was rendered as curves for
+    printing, and text needs to be recovered
+  - fixes issue
+    {issue}`82`
+
+- Fixes an issue where, with certain settings, monochrome images in
+  PDFs would be converted to 8-bit grayscale, increasing file size
+  ({issue}`79`)
+
+- Support for Ubuntu 12.04 LTS "precise" has been dropped in favor of
+  (roughly) Ubuntu 14.04 LTS "trusty"
+
+  - Some Ubuntu "PPAs" (backports) are needed to make it work
+
+- Support for some older dependencies dropped
+
+  - Ghostscript 9.15 or later is now required (available in Ubuntu
+    trusty with backports)
+  - Tesseract 3.03 or later is now required (available in Ubuntu
+    trusty)
+
+- Ghostscript now runs in "safer" mode where possible
+
+## v4.1.4
+
+- Bug fix: monochrome images with an ICC profile attached were
+  incorrectly converted to full color images if lossless reconstruction
+  was not possible due to other settings; consequence was increased
+  file size for these images
+
+## v4.1.3
+
+- More helpful error message for PDFs with version 4 security handler
+- Update usage instructions for Windows/Docker users
+- Fixed order of operations for matrix multiplication (no effect on most
+  users)
+- Add a few leptonica wrapper functions (no effect on most users)
+
+## v4.1.2
+
+- Replace IEC sRGB ICC profile with Debian's sRGB (from
+  icc-profiles-free) which is more compatible with the MIT license
+- More helpful error message for an error related to certain types of
+  malformed PDFs
+
+## v4.1
+
+- `--rotate-pages` now only rotates pages when reasonably confidence
+  in the orientation. This behavior can be adjusted with the new
+  argument `--rotate-pages-threshold`
+- Fixed problems in error checking if `unpaper` is uninstalled or
+  missing at run-time
+- Fixed problems with "RethrownJobError" errors during error handling
+  that suppressed the useful error messages
+
+## v4.0.7
+
+- Minor correction to Ghostscript output settings
+
+## v4.0.6
+
+- Update install instructions
+- Provide a sRGB profile instead of using Ghostscript's
+
+## v4.0.5
+
+- Remove some verbose debug messages from v4.0.4
+- Fixed temporary that wasn't being deleted
+- DPI is now calculated correctly for cropped images, along with other
+  image transformations
+- Inline images are now checked during DPI calculation instead of
+  rejecting the image
+
+## v4.0.4
+
+Released with verbose debug message turned on. Do not use. Skip to
+v4.0.5.
+
+## v4.0.3
+
+New features
+
+- Page orientations detected are now reported in a summary comment
+
+Fixes
+
+- Show stack trace if unexpected errors occur
+- Treat "too few characters" error message from Tesseract as a reason
+  to skip that page rather than abort the file
+- Docker: fix blank JPEG2000 issue by insisting on Ghostscript versions
+  that have this fixed
+
+## v4.0.2
+
+Fixes
+
+- Fixed compatibility with Tesseract 3.04.01 release, particularly its
+  different way of outputting orientation information
+- Improved handling of Tesseract errors and crashes
+- Fixed use of chmod on Docker that broke most test cases
+
+## v4.0.1
+
+Fixes
+
+- Fixed a KeyError if tesseract fails to find page orientation
+  information
+
+## v4.0
+
+New features
+
+- Automatic page rotation (`-r`) is now available. It uses ignores
+  any prior rotation information on PDFs and sets rotation based on the
+  dominant orientation of detectable text. This feature is fairly
+  reliable but some false positives occur especially if there is not
+  much text to work with.
+  ({issue}`4`)
+- Deskewing is now performed using Leptonica instead of unpaper.
+  Leptonica is faster and more reliable at image deskewing than
+  unpaper.
+
+Fixes
+
+- Fixed an issue where lossless reconstruction could cause some pages
+  to be appear incorrectly if the page was rotated by the user in
+  Acrobat after being scanned (specifically if it a /Rotate tag)
+- Fixed an issue where lossless reconstruction could misalign the
+  graphics layer with respect to text layer if the page had been
+  cropped such that its origin is not (0, 0)
+  ({issue}`49`)
+
+Changes
+
+- Logging output is now much easier to read
+- `--deskew` is now performed by Leptonica instead of unpaper
+  ({issue}`25`)
+- libffi is now required
+- Some changes were made to the Docker and Travis build environments to
+  support libffi
+- `--pdf-renderer=tesseract` now displays a warning if the Tesseract
+  version is less than 3.04.01, the planned release that will include
+  fixes to an important OCR text rendering bug in Tesseract 3.04.00.
+  You can also manually install ./share/sharp2.ttf on top of pdf.ttf in
+  your Tesseract tessdata folder to correct the problem.
+
@@ -0,0 +1,210 @@
+% SPDX-FileCopyrightText: 2022 James R. Barlow
+% SPDX-License-Identifier: CC-BY-SA-4.0
+
+# v5
+
+## v5.7.0
+
+- Fixed an issue that caused poor CPU utilization on machines with more
+  than 4 cores when running Tesseract 4. (Related to {issue}`217`.)
+
+- The 'hocr' renderer has been improved. The 'sandwich' and 'tesseract'
+  renderers are still better for most use cases, but 'hocr' may be
+  useful for people who work with the PDF.js renderer in English/ASCII
+  languages. ({issue}`225`)
+
+  - It now formats text in a matter that is easier for certain PDF
+    viewers to select and extract copy and paste text. This should
+    help macOS Preview and PDF.js in particular.
+  - The appearance of selected text and behavior of selecting text is
+    improved.
+  - The PDF content stream now uses relative moves, making it more
+    compact and easier for viewers to determine when two words on the
+    same line.
+  - It can now deal with text on a skewed baseline.
+  - Thanks to @cforcey for the pull request, @jbreiden for many
+    helpful suggestions, @ctbarbour for another round of improvements,
+    and @acaloiaro for an independent review.
+
+## v5.6.3
+
+- Suppress two debug messages that were too verbose
+
+## v5.6.2
+
+- Development branch accidentally tagged as release. Do not use.
+
+## v5.6.1
+
+- Fixed {issue}`219`: change
+  how the final output file is created to avoid triggering permission
+  errors when the output is a special file such as `/dev/null`
+- Fixed test suite failures due to a qpdf 8.0.0 regression and Python
+  3.5's handling of symlink
+- The "encrypted PDF" error message was different depending on the type
+  of PDF encryption. Now a single clear message appears for all types
+  of PDF encryption.
+- ocrmypdf is now in Homebrew. Homebrew users are advised to the
+  version of ocrmypdf in the official homebrew-core formulas rather
+  than the private tap.
+- Some linting
+
+## v5.6.0
+
+- Fixed {issue}`216`: preserve
+  "text as curves" PDFs without rasterizing file
+- Related to the above, messages about rasterizing are more consistent
+- For consistency versions minor releases will now get the trailing .0
+  they always should have had.
+
+## v5.5
+
+- Add new argument `--max-image-mpixels`. Pillow 5.0 now raises an
+  exception when images may be decompression bombs. This argument can
+  be used to override the limit Pillow sets.
+- Fixed output page cropped when using the sandwich renderer and OCR is
+  skipped on a rotated and image-processed page
+- A warning is now issued when old versions of Ghostscript are used in
+  cases known to cause issues with non-Latin characters
+- Fixed a few parameter validation checks for `-output-type pdfa-1` and
+  `pdfa-2`
+
+## v5.4.4
+
+- Fixed {issue}`181`: fix
+  final merge failure for PDFs with more pages than the system file
+  handle limit (`ulimit -n`)
+- Fixed {issue}`200`: an
+  uncommon syntax for formatting decimal numbers in a PDF would cause
+  qpdf to issue a warning, which ocrmypdf treated as an error. Now this
+  the warning is relayed.
+- Fixed an issue where intermediate PDFs would be created at version 1.3
+  instead of the version of the original file. It's possible but
+  unlikely this had side effects.
+- A warning is now issued when older versions of qpdf are used since
+  issues like
+  {issue}`200` cause
+  qpdf to infinite-loop
+- Address issue
+  {issue}`140`: if
+  Tesseract outputs invalid UTF-8, escape it and print its message
+  instead of aborting with a Unicode error
+- Adding previously unlisted setup requirement, pytest-runner
+- Update documentation: fix an error in the example script for Synology
+  with Docker images, improved security guidance, advised
+  `pip install --user`
+
+## v5.4.3
+
+- If a subprocess fails to report its version when queried, exit
+  cleanly with an error instead of throwing an exception
+- Added test to confirm that the system locale is Unicode-aware and
+  fail early if it's not
+- Clarified some copyright information
+- Updated pinned requirements.txt so the homebrew formula captures more
+  recent versions
+
+## v5.4.2
+
+- Fixed a regression from v5.4.1 that caused sidecar files to be
+  created as empty files
+
+## v5.4.1
+
+- Add workaround for Tesseract v4.00alpha crash when trying to obtain
+  orientation and the latest language packs are installed
+
+## v5.4
+
+- Change wording of a deprecation warning to improve clarity
+- Added option to generate PDF/A-1b output if desired
+  (`--output-type pdfa-1`); default remains PDF/A-2b generation
+- Update documentation
+
+## v5.3.3
+
+- Fixed missing error message that should occur when trying to force
+  `--pdf-renderer sandwich` on old versions of Tesseract
+- Update copyright information in test files
+- Set system `LANG` to UTF-8 in Dockerfiles to avoid UTF-8 encoding
+  errors
+
+## v5.3.2
+
+- Fixed a broken test case related to language packs
+
+## v5.3.1
+
+- Fixed wrong return code given for missing Tesseract language packs
+- Fixed "brew audit" crashing on Travis when trying to auto-brew
+
+## v5.3
+
+- Added `--user-words` and `--user-patterns` arguments which are
+  forwarded to Tesseract OCR as words and regular expressions
+  respective to use to guide OCR. Supplying a list of subject-domain
+  words should assist Tesseract with resolving words.
+  ({issue}`165`)
+- Using a non Latin-1 language with the "hocr" renderer now warns about
+  possible OCR quality and recommends workarounds
+  ({issue}`176`)
+- Output file path added to error message when that location is not
+  writable
+  ({issue}`175`)
+- Otherwise valid PDFs with leading whitespace at the beginning of the
+  file are now accepted
+
+## v5.2
+
+- When using Tesseract 3.05.01 or newer, OCRmyPDF will select the
+  "sandwich" PDF renderer by default, unless another PDF renderer is
+  specified with the `--pdf-renderer` argument. The previous behavior
+  was to select `--pdf-renderer=hocr`.
+- The "tesseract" PDF renderer is now deprecated, since it can cause
+  problems with Ghostscript on Tesseract 3.05.00
+- The "tess4" PDF renderer has been renamed to "sandwich". "tess4" is
+  now a deprecated alias for "sandwich".
+
+## v5.1
+
+- Files with pages larger than 200" (5080 mm) in either dimension are
+  now supported with `--output-type=pdf` with the page size preserved
+  (in the PDF specification this feature is called UserUnit scaling).
+  Due to Ghostscript limitations this is not available in conjunction
+  with PDF/A output.
+
+## v5.0.1
+
+- Fixed {issue}`169`,
+  exception due to failure to create sidecar text files on some
+  versions of Tesseract 3.04, including the jbarlow83/ocrmypdf Docker
+  image
+
+## v5.0
+
+- Backward incompatible changes
+
+  > - Support for Python 3.4 dropped. Python 3.5 is now required.
+  > - Support for Tesseract 3.02 and 3.03 dropped. Tesseract 3.04 or
+  >   newer is required. Tesseract 4.00 (alpha) is supported.
+  > - The OCRmyPDF.sh script was removed.
+
+- Add a new feature, `--sidecar`, which allows creating "sidecar"
+  text files which contain the OCR results in plain text. These OCR
+  text is more reliable than extracting text from PDFs. Closes
+  {issue}`126`.
+
+- New feature: `--pdfa-image-compression`, which allows overriding
+  Ghostscript's lossy-or-lossless image encoding heuristic and making
+  all images JPEG encoded or lossless encoded as desired. Fixes
+  {issue}`163`.
+
+- Fixed {issue}`143`, added
+  `--quiet` to suppress "INFO" messages
+
+- Fixed {issue}`164`, a typo
+
+- Removed the command line parameters `-n` and `--just-print` since
+  they have not worked for some time (reported as Ubuntu bug
+  [#1687308](https://bugs.launchpad.net/ubuntu/+source/ocrmypdf/+bug/1687308))
+
@@ -0,0 +1,173 @@
+% SPDX-FileCopyrightText: 2022 James R. Barlow
+% SPDX-License-Identifier: CC-BY-SA-4.0
+
+# v6
+
+## v6.2.5
+
+- Disable a failing test due to Tesseract 4.0rc1 behavior change.
+  Previously, Tesseract would exit with an error message if its
+  configuration was invalid, and OCRmyPDF would intercept this message.
+  Now Tesseract issues a warning, which OCRmyPDF v6.2.5 may relay or
+  ignore. (In v7.x, OCRmyPDF will respond to the warning.)
+- This release branch no longer supports using the optional PyMuPDF
+  installation, since it was removed in v7.x.
+- This release branch no longer supports macOS. macOS users should
+  upgrade to v7.x.
+
+## v6.2.4
+
+- Backport Ghostscript 9.25 compatibility fixes, which removes support
+  for setting Unicode metadata
+- Backport blacklisting Ghostscript 9.24
+- Older versions of Ghostscript are still supported
+
+## v6.2.3
+
+- Fixed compatibility with img2pdf >= 0.3.0 by rejecting input images
+  that have an alpha channel
+- This version will be included in Ubuntu 18.10
+
+## v6.2.2
+
+- Backport compatibility fixes for Python 3.7 and ruffus 2.7.0 from
+  v7.0.0
+- Backport fix to ignore masks when deciding what colors are on a page
+- Backport some minor improvements from v7.0.0: better argument
+  validation and warnings about the Tesseract 4.0.0 `--user-words`
+  regression
+
+## v6.2.1
+
+- Fixed recent versions of Tesseract (after 4.0.0-beta1) not being
+  detected as supporting the `sandwich` renderer ({issue}`271`).
+
+## v6.2.0
+
+- **Docker**: The Docker image `ocrmypdf-tess4` has been removed. The
+  main Docker images, `ocrmypdf` and `ocrmypdf-polyglot` now use
+  Ubuntu 18.04 as a base image, and as such Tesseract 4.0.0-beta1 is
+  now the Tesseract version they use. There is no Docker image based on
+  Tesseract 3.05 anymore.
+- Creation of PDF/A-3 is now supported. However, there is no ability to
+  attach files to PDF/A-3.
+- Lists more reasons why the file size might grow.
+- Fixed {issue}`262`,
+  `--remove-background` error on PDFs contained colormapped
+  (paletted) images.
+- Fixed another XMP metadata validation issue, in cases where the input
+  file's creation date has no timezone and the creation date is not
+  overridden.
+
+## v6.1.5
+
+- Fixed {issue}`253`, a
+  possible division by zero when using the `hocr` renderer.
+- Fixed incorrectly formatted `<xmp:ModifyDate>` field inside XMP
+  metadata for PDF/As. veraPDF flags this as a PDF/A validation
+  failure. The error is caused the timezone and final digit of the
+  seconds of modified time to be omitted, so at worst the modification
+  time stamp is rounded to the nearest 10 seconds.
+
+## v6.1.4
+
+- Fixed {issue}`248`
+  `--clean` argument may remove OCR from left column of text on
+  certain documents. We now set `--layout none` to suppress this.
+- The test cache was updated to reflect the change above.
+- Change test suite to accommodate Ghostscript 9.23's new ability to
+  insert JPEGs into PDFs without transcoding.
+- XMP metadata in PDFs is now examined using `defusedxml` for safety.
+- If an external process exits with a signal when asked to report its
+  version, we now print the system error message instead of suppressing
+  it. This occurred when the required executable was found but was
+  missing a shared library.
+- qpdf 7.0.0 or newer is now required as the test suite can no longer
+  pass without it.
+
+### Notes
+
+- An apparent [regression in Ghostscript
+  9.23](https://bugs.ghostscript.com/show_bug.cgi?id=699216) will
+  cause some ocrmypdf output files to become invalid in rare cases; the
+  workaround for the moment is to set `--force-ocr`.
+
+## v6.1.3
+
+- Fixed {issue}`247`,
+  `/CreationDate` metadata not copied from input to output.
+- A warning is now issued when Python 3.5 is used on files with a large
+  page count, as this case is known to regress to single core
+  performance. The cause of this problem is unknown.
+
+## v6.1.2
+
+- Upgrade to PyMuPDF v1.12.5 which includes a more complete fix to
+  {issue}`239`.
+- Add `defusedxml` dependency.
+
+## v6.1.1
+
+- Fixed text being reported as found on all pages if PyMuPDF is not
+  installed.
+
+## v6.1.0
+
+- PyMuPDF is now an optional but recommended dependency, to alleviate
+  installation difficulties on platforms that have less access to
+  PyMuPDF than the author anticipated. (For version 6.x only) install
+  OCRmyPDF with `pip install ocrmypdf[fitz]` to use it to its full
+  potential.
+- Fixed `FileExistsError` that could occur if OCR timed out while it
+  was generating the output file.
+  ({issue}`218`)
+- Fixed table of contents/bookmarks all being redirected to page 1 when
+  generating a PDF/A (with PyMuPDF). (Without PyMuPDF the table of
+  contents is removed in PDF/A mode.)
+- Fixed "RuntimeError: invalid key in dict" when table of
+  contents/bookmarks titles contained the character `)`.
+  ({issue}`239`)
+- Added a new argument `--skip-repair` to skip the initial PDF repair
+  step if the PDF is already well-formed (because another program
+  repaired it).
+
+## v6.0.0
+
+- The software license has been changed to GPLv3 [it has since changed again].
+  Test resource files and some individual sources may have other licenses.
+
+- OCRmyPDF now depends on
+  [PyMuPDF](https://pymupdf.readthedocs.io/en/latest/installation/).
+  Including PyMuPDF is the primary reason for the change to GPLv3.
+
+- Other backward incompatible changes
+
+  - The `OCRMYPDF_TESSERACT`, `OCRMYPDF_QPDF`, `OCRMYPDF_GS` and
+    `OCRMYPDF_UNPAPER` environment variables are no longer used.
+    Change `PATH` if you need to override the external programs
+    OCRmyPDF uses.
+  - The `ocrmypdf` package has been moved to `src/ocrmypdf` to
+    avoid issues with accidental import.
+  - The function `ocrmypdf.exec.get_program` was removed.
+  - The deprecated module `ocrmypdf.pageinfo` was removed.
+  - The `--pdf-renderer tess4` alias for `sandwich` was removed.
+
+- Fixed an issue where OCRmyPDF failed to detect existing text on
+  pages, depending on how the text and fonts were encoded within the
+  PDF. ({issue}`233,232`)
+
+- Fixed an issue that caused dramatic inflation of file sizes when
+  `--skip-text --output-type pdf` was used. OCRmyPDF now removes
+  duplicate resources such as fonts, images and other objects that it
+  generates. ({issue}`237`)
+
+- Improved performance of the initial page splitting step. Originally
+  this step was not believed to be expensive and ran in a process.
+  Large file testing revealed it to be a bottleneck, so it is now
+  parallelized. On a 700 page file with quad core machine, this change
+  saves about 2 minutes. ({issue}`234`)
+
+- The test suite now includes a cache that can be used to speed up test
+  runs across platforms. This also does not require computing
+  checksums, so it's faster. ({issue}`217`)
+
@@ -0,0 +1,288 @@
+% SPDX-FileCopyrightText: 2022 James R. Barlow
+% SPDX-License-Identifier: CC-BY-SA-4.0
+
+# v7
+
+## v7.4.0
+
+- `--force-ocr` may now be used with the new `--threshold` and
+  `--mask-barcodes` features
+- pikepdf >= 0.9.1 is now required.
+- Changed metadata handling to pikepdf 0.9.1. As a result, metadata
+  handling of non-ASCII characters in Ghostscript 9.25 or later is
+  fixed.
+- chardet >= 3.0.4 is temporarily listed as required. pdfminer.six
+  depends on it, but the most recent release does not specify this
+  requirement.
+  ({issue}`326`)
+- python-xmp-toolkit and libexempi are no longer required.
+- A new Docker image is now being provided for users who wish to access
+  OCRmyPDF over a simple HTTP interface, instead of the command line.
+- Increase tolerance of PDFs that overflow or underflow the PDF
+  graphics stack.
+  ({issue}`325`)
+
+## v7.3.1
+
+- Fixed performance regression from v7.3.0; fast page analysis was not
+  selected when it should be.
+- Fixed a few exceptions related to the new `--mask-barcodes` feature
+  and improved argument checking
+- Added missing detection of TrueType fonts that lack a Unicode mapping
+
+## v7.3.0
+
+- Added a new feature `--redo-ocr` to detect existing OCR in a file,
+  remove it, and redo the OCR. This may be particularly helpful for
+  anyone who wants to take advantage of OCR quality improvements in
+  Tesseract 4.0. Note that OCR added by OCRmyPDF before version 3.0
+  cannot be detected since it was not properly marked as invisible text
+  in the earliest versions. OCR that constructs a font from visible
+  text, such as Adobe Acrobat's ClearScan.
+
+- OCRmyPDF's content detection is generally more sophisticated. It
+  learns more about the contents of each PDF and makes better
+  recommendations:
+
+  - OCRmyPDF can now detect when a PDF contains text that cannot be
+    mapped to Unicode (meaning it is readable to human eyes but
+    copy-pastes as gibberish). In these cases it recommends
+    `--force-ocr` to make the text searchable.
+  - PDFs containing vector objects are now rendered at more
+    appropriate resolution for OCR.
+  - We now exit with an error for PDFs that contain Adobe LiveCycle
+    Designer's dynamic XFA forms. Currently the open source community
+    does not have tools to work with these files.
+  - OCRmyPDF now warns when a PDF that contains Adobe AcroForms, since
+    such files probably do not need OCR. It can work with these files.
+
+- Added three new **experimental** features to improve OCR quality in
+  certain conditions. The name, syntax and behavior of these arguments
+  is subject to change. They may also be incompatible with some other
+  features.
+
+  - `--remove-vectors` which strips out vector graphics. This can
+    improve OCR quality since OCR will not search artwork for readable
+    text; however, it currently removes "text as curves" as well.
+  - `--mask-barcodes` to detect and suppress barcodes in files. We
+    have observed that barcodes can interfere with OCR because they
+    are "text-like" but not actually textual.
+  - `--threshold` which uses a more sophisticated thresholding
+    algorithm than is currently in use in Tesseract OCR. This works
+    around a [known issue in Tesseract
+    4.0](https://github.com/tesseract-ocr/tesseract/issues/1990)
+    with dark text on bright backgrounds.
+
+- Fixed an issue where an error message was not reported when the
+  installed Ghostscript was very old.
+
+- The PDF optimizer now saves files with object streams enabled when
+  the optimization level is `--optimize 1` or higher (the default).
+  This makes files a little bit smaller, but requires PDF 1.5. PDF 1.5
+  was first released in 2003 and is broadly supported by PDF viewers,
+  but some rudimentary PDF parsers such as PyPDF2 do not understand
+  object streams. You can use the command line tool
+  `qpdf --object-streams=disable` or
+  [pikepdf](https://github.com/pikepdf/pikepdf) library to remove
+  them.
+
+- New dependency: pdfminer.six 20181108. Note this is a fork of the
+  Python 2-only pdfminer.
+
+- Deprecation notice: At the end of 2018, we will be ending support for
+  Python 3.5 and Tesseract 3.x. OCRmyPDF v7 will continue to work with
+  older versions.
+
+## v7.2.1
+
+- Fixed compatibility with an API change in pikepdf 0.3.5.
+- A kludge to support Leptonica versions older than 1.72 in the test
+  suite was dropped. Older versions of Leptonica are likely still
+  compatible. The only impact is that a portion of the test suite will
+  be skipped.
+
+## v7.2.0
+
+**Lossy JBIG2 behavior change**
+
+A user reported that ocrmypdf was in fact using JBIG2 in **lossy**
+compression mode. This was not the intended behavior. Users should
+[review the technical concerns with JBIG2 in lossy
+mode](https://abbyy.technology/en:kb:tip:jbig2_compression_and_ocr)
+and decide if this is a concern for their use case.
+
+JBIG2 lossy mode does achieve higher compression ratios than any other
+monochrome compression technology; for large text documents the savings
+are considerable. JBIG2 lossless still gives great compression ratios
+and is a major improvement over the older CCITT G4 standard.
+
+Only users who have reviewed the concerns with JBIG2 in lossy mode
+should opt-in. As such, lossy mode JBIG2 is only turned on when the new
+argument `--jbig2-lossy` is issued. This is independent of the setting
+for `--optimize`.
+
+Users who did not install an optional JBIG2 encoder are unaffected.
+
+(Thanks to user 'bsdice' for reporting this issue.)
+
+**Other issues**
+
+- When the image optimizer quantizes an image to 1 bit per pixel, it
+  will now attempt to further optimize that image as CCITT or JBIG2,
+  instead of keeping it in the "flate" encoding which is not efficient
+  for 1 bpp images.
+  ({issue}`297`)
+- Images in PDFs that are used as soft masks (i.e. transparency masks
+  or alpha channels) are now excluded from optimization.
+- Fixed handling of Tesseract 4.0-rc1 which now accepts invalid
+  Tesseract configuration files, which broke the test suite.
+
+## v7.1.0
+
+- Improve the performance of initial text extraction, which is done to
+  determine if a file contains existing text of some kind or not. On
+  large files, this initial processing is now about 20x times faster.
+  ({issue}`299`)
+- pikepdf 0.3.3 is now required.
+- Fixed {issue}`231`, a
+  problem with JPEG2000 images where image metadata was only available
+  inside the JPEG2000 file.
+- Fixed some additional Ghostscript 9.25 compatibility issues.
+- Improved handling of KeyboardInterrupt error messages.
+  ({issue}`301`)
+- README.md is now served in GitHub markdown instead of
+  reStructuredText.
+
+## v7.0.6
+
+- Blacklist Ghostscript 9.24, now that 9.25 is available and fixes many
+  regressions in 9.24.
+
+## v7.0.5
+
+- Improve capability with Ghostscript 9.24, and enable the JPEG
+  passthrough feature when this version in installed.
+- Ghostscript 9.24 lost the ability to set PDF title, author, subject
+  and keyword metadata to Unicode strings. OCRmyPDF will set ASCII
+  strings and warn when Unicode is suppressed. Other software may be
+  used to update metadata. This is a short term work around.
+- PDFs generated by Kodak Capture Desktop, or generally PDFs that
+  contain indirect references to null objects in their table of
+  contents, would have an invalid table of contents after processing by
+  OCRmyPDF that might interfere with other viewers. This has been
+  fixed.
+- Detect PDFs generated by Adobe LiveCycle, which can only be displayed
+  in Adobe Acrobat and Reader currently. When these are encountered,
+  exit with an error instead of performing OCR on the "Please wait"
+  error message page.
+
+## v7.0.4
+
+- Fixed exception thrown when trying to optimize a certain type of PNG
+  embedded in a PDF with the `-O2`
+- Update to pikepdf 0.3.2, to gain support for optimizing some
+  additional image types that were previously excluded from
+  optimization (CMYK and grayscale). Fixes
+  {issue}`285`.
+
+## v7.0.3
+
+- Fixed {issue}`284`, an error
+  when parsing inline images that have are also image masks, by
+  upgrading pikepdf to 0.3.1
+
+## v7.0.2
+
+- Fixed a regression with `--rotate-pages` on pages that already had
+  rotations applied.
+  ({issue}`279`)
+- Improve quality of page rotation in some cases by rasterizing a
+  higher quality preview image.
+  ({issue}`281`)
+
+## v7.0.1
+
+- Fixed compatibility with img2pdf >= 0.3.0 by rejecting input images
+  that have an alpha channel
+- Add forward compatibility for pikepdf 0.3.0 (unrelated to img2pdf)
+- Various documentation updates for v7.0.0 changes
+
+## v7.0.0
+
+- The core algorithm for combining OCR layers with existing PDF pages
+  has been rewritten and improved considerably. PDFs are no longer
+  split into single page PDFs for processing; instead, images are
+  rendered and the OCR results are grafted onto the input PDF. The new
+  algorithm uses less temporary disk space and is much more performant
+  especially for large files.
+
+- New dependency: [pikepdf](https://github.com/pikepdf/pikepdf).
+  pikepdf is a powerful new Python PDF library driving the latest
+  OCRmyPDF features, built on the QPDF C++ library (libqpdf).
+
+- New feature: PDF optimization with `-O` or `--optimize`. After
+  OCR, OCRmyPDF will perform image optimizations relevant to OCR PDFs.
+
+  - If a JBIG2 encoder is available, then monochrome images will be
+    converted, with the potential for huge savings on large black and
+    white images, since JBIG2 is far more efficient than any other
+    monochrome (bi-level) compression. (All known US patents related
+    to JBIG2 have probably expired, but it remains the responsibility
+    of the user to supply a JBIG2 encoder such as
+    [jbig2enc](https://github.com/agl/jbig2enc). OCRmyPDF does not
+    implement JBIG2 encoding.)
+  - If `pngquant` is installed, OCRmyPDF will optionally use it to
+    perform lossy quantization and compression of PNG images.
+  - The quality of JPEGs can also be lowered, on the assumption that a
+    lower quality image may be suitable for storage after OCR.
+  - This image optimization component will eventually be offered as an
+    independent command line utility.
+  - 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.
+
+- Small amounts of text in the margins of a page, such as watermarks,
+  page numbers, or digital stamps, will no longer prevent the rest of a
+  page from being OCRed when `--skip-text` is issued. This behavior
+  is based on a heuristic.
+
+- Removed features
+
+  - The deprecated `--pdf-renderer tesseract` PDF renderer was
+    removed.
+  - `-g`, the option to generate debug text pages, was removed
+    because it was a maintenance burden and only worked in isolated
+    cases. HOCR pages can still be previewed by running the
+    hocrtransform.py with appropriate settings.
+
+- Removed dependencies
+
+  - `PyPDF2`
+  - `defusedxml`
+  - `PyMuPDF`
+
+- The `sandwich` PDF renderer can be used with all supported versions
+  of Tesseract, including that those prior to v3.05 which don't support
+  `-c textonly`. (Tesseract v4.0.0 is recommended and more
+  efficient.)
+
+- `--pdf-renderer auto` option and the diagnostics used to select a
+  PDF renderer now work better with old versions, but may make
+  different decisions than past versions.
+
+- If everything succeeds but PDF/A conversion fails, a distinct return
+  code is now returned (`ExitCode.pdfa_conversion_failed (10)`) where
+  this situation previously returned
+  `ExitCode.invalid_output_pdf (4)`. The latter is now returned only
+  if there is some indication that the output file is invalid.
+
+- Notes for downstream packagers
+
+  - There is also a new dependency on `python-xmp-toolkit` which in
+    turn depends on `libexempi3`.
+  - It may be necessary to separately `pip install pycparser` to
+    avoid [another Python 3.7
+    issue](https://github.com/eliben/pycparser/pull/135).
+
@@ -0,0 +1,153 @@
+% SPDX-FileCopyrightText: 2022 James R. Barlow
+% SPDX-License-Identifier: CC-BY-SA-4.0
+
+# v8
+
+## v8.3.2
+
+- Dropped workaround for macOS that allowed it work without pdfminer.six,
+  now a proper sdist release of pdfminer.six is available.
+- pikepdf 1.5.0 is now required.
+
+## v8.3.1
+
+- Fixed an issue where PDFs with malformed metadata would be rendered as
+  blank pages. {issue}`398`.
+
+## v8.3.0
+
+- Improved the strategy for updating pages when a new image of the page
+  was produced. We now attempt to preserve more content from the
+  original file, for annotations in particular.
+- For PDFs with more than 100 pages and a sequence where one PDF page
+  was replaced and one or more subsequent ones were skipped, an
+  intermediate file would be corrupted while grafting OCR text, causing
+  processing to fail. This is a regression, likely introduced in
+  v8.2.4.
+- Previously, we resized the images produced by Ghostscript by a small
+  number of pixels to ensure the output image size was an exactly what
+  we wanted. Having discovered a way to get Ghostscript to produce the
+  exact image sizes we require, we eliminated the resizing step.
+- Command line completions for `bash` are now available, in addition
+  to `fish`, both in `misc/completion`. Package maintainers, please
+  install these so users can take advantage.
+- Updated requirements.
+- pikepdf 1.3.0 is now required.
+
+## v8.2.4
+
+- Fixed a false positive while checking for a certain type of PDF that
+  only Acrobat can read. We now more accurately detect Acrobat-only
+  PDFs.
+- OCRmyPDF holds fewer open file handles and is more prompt about
+  releasing those it no longer needs.
+- Minor optimization: we no longer traverse the table of contents to
+  ensure all references in it are resolved, as changes to libqpdf have
+  made this unnecessary.
+- pikepdf 1.2.0 is now required.
+
+## v8.2.3
+
+- Fixed that `--mask-barcodes` would occasionally leave a unwanted
+  temporary file named `junkpixt` in the current working folder.
+- Fixed (hopefully) handling of Leptonica errors in an environment
+  where a non-standard `sys.stderr` is present.
+- Improved help text for `--verbose`.
+
+## v8.2.2
+
+- Fixed a regression from v8.2.0, an exception that occurred while
+  attempting to report that `unpaper` or another optional dependency
+  was unavailable.
+- In some cases, `ocrmypdf [-c|--clean]` failed to exit with an error
+  when `unpaper` is not installed.
+
+## v8.2.1
+
+- This release was canceled.
+
+## v8.2.0
+
+- A major improvement to our Docker image is now available thanks to
+  hard work contributed by @mawi12345. The new Docker image,
+  ocrmypdf-alpine, is based on Alpine Linux, and includes most of the
+  functionality of three existed images in a smaller package. This
+  image will replace the main Docker image eventually but for now all
+  are being built. [See documentation for
+  details](https://ocrmypdf.readthedocs.io/en/latest/docker.html).
+- Documentation reorganized especially around the use of Docker images.
+- Fixed a problem with PDF image optimization, where the optimizer
+  would unnecessarily decompress and recompress PNG images, in some
+  cases losing the benefits of the quantization it just had just
+  performed. The optimizer is now capable of embedding PNG images into
+  PDFs without transcoding them.
+- Fixed a minor regression with lossy JBIG2 image optimization. All
+  JBIG2 candidates images were incorrectly placed into a single
+  optimization group for the whole file, instead of grouping pages
+  together. This usually makes a larger JBIG2Globals dictionary and
+  results in inferior compression, so it worked less well than
+  designed. However, quality would not be impacted. Lossless JBIG2 was
+  entirely unaffected.
+- Updated dependencies, including pikepdf to 1.1.0. This fixes
+  {issue}`358`.
+- The install-time version checks for certain external programs have
+  been removed from setup.py. These tests are now performed at
+  run-time.
+- The non-standard option to override install-time checks
+  (`setup.py install --force`) is now deprecated and prints a
+  warning. It will be removed in a future release.
+
+## v8.1.0
+
+- Added a feature, `--unpaper-args`, which allows passing arbitrary
+  arguments to `unpaper` when using `--clean` or `--clean-final`.
+  The default, very conservative unpaper settings are suppressed.
+- The argument `--clean-final` now implies `--clean`. It was
+  possible to issue `--clean-final` on its before this, but it would
+  have no useful effect.
+- Fixed an exception on traversing corrupt table of contents entries
+  (specifically, those with invalid destination objects)
+- Fixed an issue when using `--tesseract-timeout` and image
+  processing features on a file with more than 100 pages.
+  {issue}`347`
+- OCRmyPDF now always calls `os.nice(5)` to signal to operating
+  systems that it is a background process.
+
+## v8.0.1
+
+- Fixed an exception when parsing PDFs that are missing a required
+  field. {issue}`325`
+- pikepdf 1.0.5 is now required, to address some other PDF parsing
+  issues.
+
+## v8.0.0
+
+No major features. The intent of this release is to sever support for
+older versions of certain dependencies.
+
+**Breaking changes**
+
+- Dropped support for Tesseract 3.x. Tesseract 4.0 or newer is now
+  required.
+- Dropped support for Python 3.5.
+- Some `ocrmypdf.pdfa` APIs that were deprecated in v7.x were
+  removed. This functionality has been moved to pikepdf.
+
+**Other changes**
+
+- Fixed an unhandled exception when attempting to mask barcodes.
+  {issue}`322`
+- It is now possible to use ocrmypdf without pdfminer.six, to support
+  distributions that do not have it or cannot currently use it (e.g.
+  Homebrew). Downstream maintainers should include pdfminer.six if
+  possible.
+- A warning is now issue when PDF/A conversion removes some XMP
+  metadata from the input PDF. (Only a "whitelist" of certain XMP
+  metadata types are allowed in PDF/A.)
+- Fixed several issues that caused PDF/As to be produced with
+  nonconforming XMP metadata (would fail validation with veraPDF).
+- Fixed some instances where invalid DocumentInfo from a PDF cause XMP
+  metadata creation to fail.
+- Fixed a few documentation problems.
+- pikepdf 1.0.2 is now required.
+
@@ -0,0 +1,252 @@
+% SPDX-FileCopyrightText: 2022 James R. Barlow
+% SPDX-License-Identifier: CC-BY-SA-4.0
+
+# v9
+
+## v9.8.2
+
+- Fixed an issue where OCRmyPDF would ignore text inside Form XObject when
+  making certain decisions about whether a document already had text.
+- Fixed file size increase warning to take overhead of small files into account.
+- Added instructions for installing on Cygwin.
+
+## v9.8.1
+
+- Fixed an issue where unexpected files in the `%PROGRAMFILES%\gs` directory
+  (Windows) caused an exception.
+- Mark pdfminer.six 20200517 as supported.
+- If jbig2enc is missing and optimization is requested, a warning is issued
+  instead of an error, which was the intended behavior.
+- Documentation updates.
+
+## v9.8.0
+
+- Fixed issue where only the first PNG (FlateDecode) image in a file would be
+  considered for optimization. File sizes should be improved from here on.
+- Fixed a startup crash when the chosen language was Japanese ({issue}`543`).
+- Added options to configure polling and log level to watcher.py.
+
+## v9.7.2
+
+- Fixed an issue with `ocrmypdf.ocr(...language=)` not accepting a list of
+  languages as documented.
+- Updated setup.py to confirm that pdfminer.six version 20200402 is supported.
+
+## v9.7.1
+
+- Fixed version check failing when used with qpdf 10.0.0.
+- Added some missing type annotations.
+- Updated documentation to warn about need for "ifmain" guard and Windows.
+
+## v9.7.0
+
+- Fixed an error in watcher.py if `OCR_JSON_SETTINGS` was not defined.
+- Ghostscript 9.51 is now blacklisted, due to numerous problems with this version.
+- Added a workaround for a problem with "txtwrite" in Ghostscript 9.52.
+- Fixed an issue where the incorrect number of threads used was shown when
+  `OMP_THREAD_LIMIT` was manipulated.
+- Removed a possible performance bottlenecks for files that use hundreds to
+  thousands of images on the same page.
+- Documentation improvements.
+- Optimization will now be applied to some monochrome images that have a color
+  profile defined instead of only black and white.
+- ICC profiles are consulted when determining the simplified colorspace of an
+  image.
+
+## v9.6.1
+
+- Documentation improvements - thanks to many users for their contributions!
+
+  > - Fixed installation instructions for ArchLinux (@pigmonkey)
+  > - Updated installation instructions for FreeBSD and other OSes (@knobix)
+  > - Added instructions for using Docker Compose with watchdog (@ianalexander,
+  >   @deisi)
+  > - Other miscellany (@mb720, @toy, @caiofacchinato)
+  > - Some scripts provided in the documentation have been migrated out so that
+  >   they can be copied out as whole files, and to ensure syntax checking
+  >   is maintained.
+
+- Fixed an error that caused bash completions to fail on macOS. ({issue}`502,504`;
+  @AlexanderWillner)
+
+- Fixed a rare case where OCRmyPDF threw an exception while processing a PDF
+  with the wrong object type in its `/Trailer /Info`. The error is now logged
+  and incorrect object is ignored. ({issue}`497`)
+
+- Removed potentially non-free file `enron1.pdf` and simplified the test that
+  used it.
+
+- Removed potentially non-free file `misc/media/logo.afdesign`.
+
+## v9.6.0
+
+- Fixed a regression with transferring metadata from the input PDF to the output
+  PDF in certain situations.
+- pdfminer.six is now supported up to version 2020-01-24.
+- Messages are explaining page rotation decisions are now shown at the standard
+  verbosity level again when `--rotate-pages`. In some previous version they
+  were set to debug level messages that only appeared with the parameter `-v1`.
+- Improvements to `misc/watcher.py`. Thanks to @ianalexander and @svenihoney.
+- Documentation improvements.
+
+## v9.5.0
+
+- Added API functions to measure OCR quality.
+- Modest improvements to handling PDFs with difficult/non compliant metadata.
+
+## v9.4.0
+
+- Updated recommended dependency versions.
+- Improvements to test coverage and changes to facilitate better measurement of
+  test coverage, such as when tests run in subprocesses.
+- Improvements to error messages when Leptonica is not installed correctly.
+- Fixed use of pytest "session scope" that may have caused some intermittent
+  CI failures.
+- When the argument `--keep-temporary-files` or verbosity is set to `-v1`,
+  a debug log file is generated in the working temporary folder.
+
+## v9.3.0
+
+- Improved native Windows support: we now check in the obvious places in
+  the "Program Files" folders installations of Tesseract and Ghostscript,
+  rather than relying on the user to edit `PATH` to specify their location.
+  The `PATH` environment variable can still be used to differentiate when
+  multiple installations are present or the programs are installed to non-
+  standard locations.
+- Fixed an exception on parsing Ghostscript error messages.
+- Added an improved example demonstrating how to set up a watched folder
+  for automated OCR processing (thanks to @ianalexander for the contribution).
+
+## v9.2.0
+
+- Native Windows is now supported.
+- Continuous integration moved to Azure Pipelines.
+- Improved test coverage and speed of tests.
+- Fixed an issue where a page that was originally a JPEG would be saved as a
+  PNG, increasing file size. This occurred only when a preprocessing option
+  was selected along with `--output-type=pdf` and all images on the original
+  page were JPEGs. Regression since v7.0.0.
+- OCRmyPDF no longer depends on the QPDF executable `qpdf` or `libqpdf`.
+  It uses pikepdf (which in turn depends on `libqpdf`). Package maintainers
+  should adjust dependencies so that OCRmyPDF no longer calls for libqpdf on
+  its own. For users of Python binary wheels, this change means a separate
+  installation of QPDF is no longer necessary. This change is mainly to
+  simplify installation on Windows.
+- Fixed a rare case where log messages from Tesseract would be discarded.
+- Fixed incorrect function signature for pixFindPageForeground, causing
+  exceptions on certain platforms/Leptonica versions.
+
+## v9.1.1
+
+- Expand the range of pdfminer.six versions that are supported.
+- Fixed Docker build when using pikepdf 1.7.0.
+- Fixed documentation to recommend using pip from get-pip.py.
+
+## v9.1.0
+
+- Improved diagnostics when file size increases at output. Now warns if JBIG2
+  or pngquant were not available.
+- pikepdf 1.7.0 is now required, to pick up changes that remove the need for
+  a source install on Linux systems running Python 3.8.
+
+## v9.0.5
+
+- The Alpine Docker image (jbarlow83/ocrmypdf-alpine) has been dropped due to
+  the difficulties of supporting Alpine Linux.
+- The primary Docker image (jbarlow83/ocrmypdf) has been improved to take on
+  the extra features that used to be exclusive to the Alpine image.
+- No changes to application code.
+- pdfminer.six version 20191020 is now supported.
+
+## v9.0.4
+
+- Fixed compatibility with Python 3.8 (but requires source install for the moment).
+- Fixed Tesseract settings for `--user-words` and `--user-patterns`.
+- Changed to pikepdf 1.6.5 (for Python 3.8).
+- Changed to Pillow 6.2.0 (to mitigate a security vulnerability in earlier Pillow).
+- A debug message now mentions when English is automatically selected if the locale
+  is not English.
+
+## v9.0.3
+
+- Embed an encoded version of the sRGB ICC profile in the intermediate
+  Postscript file (used for PDF/A conversion). Previously we included the
+  filename, which required Postscript to run with file access enabled. For
+  security, Ghostscript 9.28 enables `-dSAFER` and as such, no longer
+  permits access to any file by default. This fix is necessary for
+  compatibility with Ghostscript 9.28.
+- Exclude a test that sometimes times out and fails in continuous integration
+  from the standard test suite.
+
+## v9.0.2
+
+- The image optimizer now skips optimizing flate (PNG) encoded images in some
+  situations where the optimization effort was likely wasted.
+- The image optimizer now ignores images that specify arbitrary decode arrays,
+  since these are rare.
+- Fixed an issue that caused inversion of black and white in monochrome images.
+  We are not certain but the problem seems to be linked to Leptonica 1.76.0 and
+  older.
+- Fixed some cases where the test suite failed if
+  English or German Tesseract language packs were not installed.
+- Fixed a runtime error if the Tesseract English language is not installed.
+- Improved explicit closing of Pillow images after use.
+- Actually fixed of Alpine Docker image build.
+- Changed to pikepdf 1.6.3.
+
+## v9.0.1
+
+- Fixed test suite failing when either of optional dependencies unpaper and
+  pngquant were missing.
+- Attempted fix of Alpine Docker image build.
+- Documented that FreeBSD ports are now available.
+- Changed to pikepdf 1.6.1.
+
+## v9.0.0
+
+**Breaking changes**
+
+- The `--mask-barcodes` experimental feature has been dropped due to poor
+  reliability and occasional crashes, both due to the underlying library that
+  implements this feature (Leptonica).
+- The `-v` (verbosity level) parameter now accepts only `0`, `1`, and
+  `2`.
+- Dropped support for Tesseract 4.00.00-alpha releases. Tesseract 4.0 beta and
+  later remain supported.
+- Dropped the `ocrmypdf-polyglot` and `ocrmypdf-webservice` images.
+
+**New features**
+
+- Added a high level API for applications that want to integrate OCRmyPDF.
+  Special thanks to Martin Wind (@mawi1988) whose made significant contributions
+  to this effort.
+- Added progress bars for long-running steps. ■■■■■■■□□
+- We now create linearized ("fast web view") PDFs by default. The new parameter
+  `--fast-web-view` provides control over when this feature is applied.
+- Added a new `--pages` feature to limit OCR to only a specific page range.
+  The list may contain commas or single pages, such as `1, 3, 5-11`.
+- When the number of pages is small compared to the number of allowed jobs, we
+  run Tesseract in multithreaded (OpenMP) mode when available. This should
+  improve performance on files with low page counts.
+- Removed dependency on `ruffus`, and with that, the non-reentrancy
+  restrictions that previous made an API impossible.
+- Output and logging messages overhauled so that ocrmypdf may be integrated
+  into applications that use the logging module.
+- pikepdf 1.6.0 is required.
+- Added a logo. 😊
+
+**Bug fixes**
+
+- Pages with vector artwork are treated as full color. Previously, vectors
+  were ignored when considering the colorspace needed to cover a page, which
+  could cause loss of color under certain settings.
+- Test suite now spawns processes less frequently, allowing more accurate
+  measurement of code coverage.
+- Improved test coverage.
+- Fixed a rare division by zero (if optimization produced an invalid file).
+- Updated Docker images to use newer versions.
+- Fixed images encoded as JBIG2 with a colorspace other than `/DeviceGray`
+  were not interpreted correctly.
+- Fixed a OCR text-image registration (i.e. alignment) problem when the page
+  when MediaBox had a nonzero corner.
+
@@ -0,0 +1,121 @@
+% SPDX-FileCopyrightText: 2022 James R. Barlow
+% SPDX-License-Identifier: CC-BY-SA-4.0
+
+# v10
+
+## v10.3.3
+
+- Fixed a "KeyError: 'dpi'" error message when using `--threshold` on an image.
+  ({issue}`607`)
+
+## v10.3.2
+
+- Fixed a case where we reported "no reason" for a file size increase, when we
+  could determine the reason.
+- Enabled support for pdfminer.six 20200726.
+
+## v10.3.1
+
+- Fixed a number of test suite failures with pdfminer.six older than version 20200402.
+- Enabled support for pdfminer.six 20200720.
+
+## v10.3.0
+
+- Fixed an issue where we would consider images that were already JBIG2-encoded
+  for optimization, potentially producing a less optimized image than the original.
+  We do not believe this issue would ever cause an image to loss fidelity.
+- Where available, pikepdf memory mapping is now used. This improves performance.
+- When Leptonica 1.79+ is installed, use its new error handling API to avoid
+  a "messy" redirection of stderr which was necessary to capture its error
+  messages.
+- For older versions of Leptonica, added a new thread level lock. This fixes a
+  possible race condition in handling error conditions in Leptonica (although
+  there is no evidence it ever caused issues in practice).
+- Documentation improvements and more type hinting.
+
+## v10.2.1
+
+- Disabled calculation of text box order with pdfminer. We never needed this result
+  and it is expensive to calculate on files with complex pre-existing text.
+- Fixed plugin manager to accept `Path(plugin)` as a path to a plugin.
+- Fixed some typing errors.
+- Documentation improvements.
+
+## v10.2.0
+
+- Update Docker image to use Ubuntu 20.04.
+- Fixed issue PDF/A acquires title "Untitled" after conversion. ({issue}`582`)
+- Fixed a problem where, when using `--pdf-renderer hocr`, some text would
+  be missing from the output when using a more recent version of Tesseract.
+  Tesseract began adding more detailed markup about the semantics of text
+  that our HOCR transform did not recognize, so it ignored them. This option is
+  not the default. If necessary `--redo-ocr` also redoing OCR to fix such issues.
+- Fixed an error in Python 3.9 beta, due to removal of deprecated
+  `Element.getchildren()`. ({issue}`584`)
+- Implemented support using the API with `BytesIO` and other file stream objects.
+  ({issue}`545`)
+
+## v10.1.1
+
+- Fixed `OMP_THREAD_LIMIT` set to invalid value error messages on some input
+  files. (The error was harmless, apart from less than optimal performance in
+  some cases.)
+
+## v10.1.0
+
+- Previously, we `--clean-final` would cause an unpaper-cleaned page image to
+  be produced twice, which was necessary in some cases but not in general. We
+  now take this optimization opportunity and reuse the image if possible.
+- We now provide PNG files as input to unpaper, since it accepts them, instead
+  of generating PPM files which can be very large. This can improve performance
+  and temporary disk usage.
+- Documentation updated for plugins.
+
+## v10.0.1
+
+- Fixed regression when `-l lang1+lang2` is used from command line.
+
+## v10.0.0
+
+**Breaking changes**
+
+- Support for pdfminer.six version 20181108 has been dropped, along with a
+  monkeypatch that made this version work.
+- Output messages are now displayed in color (when supported by the terminal)
+  and prefixes describing the severity of the message are removed. As such
+  programs that parse OCRmyPDF's log message will need to be revised. (Please
+  consider using OCRmyPDF as a library instead.)
+- The minimum version for certain dependencies has increased.
+- Many API changes; see developer changes.
+- The Python libraries pluggy and coloredlogs are now required.
+
+**New features and improvements**
+
+- PDF page scanning is now parallelized across CPUs, speeding up this phase
+  dramatically for files with a high page counts.
+- PDF page scanning is optimized, addressing some performance regressions.
+- PDF page scanning is no longer run on pages that are not selected when the
+  `--pages` argument is used.
+- PDF page scanning is now independent of Ghostscript, ending our past reliance
+  on this occasionally unstable feature in Ghostscript.
+- A plugin architecture has been added, currently allowing one to more easily
+  use a different OCR engine or PDF renderer from Tesseract and Ghostscript,
+  respectively. A plugin can also override some decisions, such changing
+  the OCR settings after initial scanning.
+- Colored log messages.
+
+**Developer changes**
+
+- The test spoofing mechanism, used to test correct handling of failures in
+  Tesseract and Ghostscript, has been removed in favor of using plugins for
+  testing. The spoofing mechanism was fairly complex and required many special
+  hacks for Windows.
+- Code describing the resolution in DPI of images was refactored into a
+  `ocrmypdf.helpers.Resolution` class.
+- The module `ocrmypdf._exec` is now private to OCRmyPDF.
+- The `ocrmypdf.hocrtransform` module has been updated to follow PEP8 naming
+  conventions.
+- Ghostscript is no longer used for finding the location of text in PDFs, and
+  APIs related to this feature have been removed.
+- Lots of internal reorganization to support plugins.
+
@@ -0,0 +1,235 @@
+% SPDX-FileCopyrightText: 2022 James R. Barlow
+% SPDX-License-Identifier: CC-BY-SA-4.0
+
+# v11
+
+## v11.7.3
+
+- Exclude CCITT Group 3 images from being optimized. Some libraries
+  OCRmyPDF uses do not seem to handle this obscure compression format properly.
+  You may get errors or possible corrupted output images without this fix.
+
+## v11.7.2
+
+- Updated pinned versions in main.txt, primarily to upgrade Pillow to 8.1.2, due
+  to recently disclosed security vulnerabilities in that software.
+- The `--sidecar` parameter now causes an exception if set to the same file as
+  the input or output PDF.
+
+## v11.7.1
+
+- Some exceptions while attempting image optimization were only logged at the debug
+  level, causing them to be suppressed. These errors are now logged appropriately.
+- Improved the error message related to `--unpaper-args`.
+- Updated documentation to mention the new conda distribution.
+
+## v11.7.0
+
+- We now support using `--sidecar` in conjunction with `--pages`; these arguments
+  used to be mutually exclusive. ({issue}`735`)
+- Fixed a possible issue with PDF/A-1b generation. Acrobat complained that our PDFs use
+  object streams. More robust PDF/A validators like veraPDF don't consider this a
+  problem, but we'll honor Acrobat's objection from here on. This may increase file
+  size of PDF/A-1b files. PDF/A-2b files will not be affected.
+
+## v11.6.2
+
+- Fixed a regression where the wrong page orientation would be produced when using
+  arguments such as `--deskew --rotate-pages` ({issue}`730`).
+
+## v11.6.1
+
+- Fixed an issue with attempting optimize unusually narrow-width images by excluding
+  these images from optimization ({issue}`732`).
+- Remove an obsolete compatibility shim for a version of pikepdf that is no longer
+  supported.
+
+## v11.6.0
+
+- OCRmyPDF will now automatically register plugins from the same virtual environment
+  with an appropriate setuptools entrypoint.
+- Refactor the plugin manager to remove unnecessary complications and make plugin
+  registration more automatic.
+- `PageContext` and `PdfContext` are now formally part of the API, as they
+  should have been, since they were part of `ocrmypdf.pluginspec`.
+
+## v11.5.0
+
+- Fixed an issue where the output page size might differ by a fractional amount
+  due to rounding, when `--force-ocr` was used and the page contained objects
+  with multiple resolutions.
+- When determining the resolution at which to rasterize a page, we now consider
+  printed text on the page as requiring a higher resolution. This fixes issues
+  with certain pages being rendered with unacceptably low resolution text, but
+  may increase output file sizes in some workflows where low resolution text
+  is acceptable.
+- Added a workaround to fix an exception that occurs when trying to
+  `import ocrmypdf.leptonica` on Apple ARM silicon (or potentially, other
+  platforms that do not permit write+executable memory).
+
+## v11.4.5
+
+- Fixed an issue where files may not be closed when the API is used.
+- Improved `setup.cfg` with better settings for test coverage.
+
+## v11.4.4
+
+- Fixed `AttributeError: 'NoneType' object has no attribute 'userunit'` ({issue}`700`),
+  related to OCRmyPDF not properly forwarded an error message from pdfminer.six.
+- Adjusted typing of some arguments.
+- `ocrmypdf.ocr` now takes a `threading.Lock` for reasons outlined in the
+  documentation.
+
+## v11.4.3
+
+- Removed a redundant debug message.
+- Test suite now asserts that most patched functions are called when they should be.
+- Test suite now skips a test that fails on two particular versions of piekpdf.
+
+## v11.4.2
+
+- Fixed support for Cygwin, hopefully.
+- watcher.py: Fixed an issue with the OCR_LOGLEVEL not being interpreted.
+
+## v11.4.1
+
+- Fixed an issue where invalid pages ranges passed using the `pages` argument,
+  such as "1-0" would cause unhandled exceptions.
+- Accepted a user-contributed to the Synology demo script in misc/synology.py.
+- Clarified documentation about change of temporary file location `ocrmypdf.io`.
+- Fixed Python wheel tag which was incorrectly set to py35 even though we long
+  since dropped support for Python 3.5.
+
+## v11.4.0
+
+- When looking for Tesseract and Ghostscript, we now check the Windows Registry to
+  see if their installers registered the location of their executables. This should
+  help Windows users who have installed these programs to non-standard
+  locations.
+- We now report on the progress of PDF/A conversion, since this operation is
+  sometimes slow.
+- Improved command line completions.
+- The prefix of the temporary folder OCRmyPDF creates has been changed from
+  `com.github.ocrmypdf` to `ocrmypdf.io`. Scripts that chose to depend on this
+  prefix may need to be adjusted. (This has always been an implementation detail so is
+  not considered part of the semantic versioning "contract".)
+- Fixed {issue}`692`, where a particular file with malformed fonts would flood an
+  internal message cue by generating so many debug messages.
+- Fixed an exception on processing hOCR files with no page record. Tesseract
+  is not known to generate such files.
+
+## v11.3.4
+
+- Fixed an error message 'called readLinearizationData for file that is not
+  linearized' that may occur when pikepdf 2.1.0 is used. (Upgrading to pikepdf
+  2.1.1 also fixes the issue.)
+- File watcher now automatically includes `.PDF` in addition to `.pdf` to
+  better support case sensitive file systems.
+- Some documentation and comment improvements.
+
+## v11.3.3
+
+- If unpaper outputs non-UTF-8 data, quietly fix this rather than choke on the
+  conversion. (Possibly addresses {issue}`671`.)
+
+## v11.3.2
+
+- Explicitly require pikepdf 2.0.0 or newer when running on Python 3.9. (There are
+  concerns about the stability of pybind11 2.5.x with Python 3.9, which is used in
+  pikepdf 1.x.)
+- Fixed another issue related to page rotation.
+- Fixed an issue where image marked as image masks were not properly considered
+  as optimization candidates.
+- On some systems, unpaper seems to be unable to process the PNGs we offer it
+  as input. We now convert the input to PNM format, which unpaper always accepts.
+  Fixes {issue}`665` and {issue}`667`.
+- DPI sent to unpaper is now rounded to a more reasonable number of decimal digits.
+- Debug and error messages from unpaper were being suppressed.
+- Some documentation tweaks.
+
+## v11.3.1
+
+- Declare support for new versions: pdfminer.six 20201018 and pikepdf 2.x
+- Fixed warning related to `--pdfa-image-compression` that appears at the wrong
+  time.
+
+## v11.3.0
+
+- The "OCR" step is describing as "Image processing" in the output messages when
+  OCR is disabled, to better explain the application's behavior.
+- Debug logs are now only created when run as a command line, and not when OCR
+  is performed for an API call. It is the calling application's responsibility
+  to set up logging.
+- For PDFs with a low number of pages, we gathered information about the input PDF
+  in a thread rather than process (when there are more pages). When run as a
+  thread, we did not close the file handle to the working PDF, leaking one file
+  handle per call of `ocrmypdf.ocr`.
+- Fixed an issue where debug messages send by child worker processes did not match
+  the log settings of parent process, causing messages to be dropped. This affected
+  macOS and Windows only where the parent process is not forked.
+- Fixed the hookspec of rasterize_pdf_page to remove default parameters that
+  were not handled in an expected way by pluggy.
+- Fixed another issue with automatic page rotation ({issue}`658`) due to the issue above.
+
+## v11.2.1
+
+- Fixed an issue where optimization of a 1-bit image with a color palette or
+  associated ICC that was optimized to JBIG2 could have its colors inverted.
+
+## v11.2.0
+
+- Fixed an issue with optimizing PNG-type images that had soft masks or image masks.
+  This is a regression introduced in (or about) v11.1.0.
+- Improved type checking of the `plugins` parameter for the `ocrmypdf.ocr`
+  API call.
+
+## v11.1.2
+
+- Fixed hOCR renderer writing the text in roughly reverse order. This should not
+  affect reasonably smart PDF readers that properly locate the position of all
+  text, but may confuse those that rely on the order of objects in the content
+  stream. ({issue}`642`)
+
+## v11.1.1
+
+- We now avoid using named temporary files when using pngquant allowing containerized
+  pngquant installs to be used.
+- Clarified an error message.
+- Highest number of 1's in a release ever!
+
+## v11.1.0
+
+- Fixed page rotation issues: {issue}`634,589`.
+- Fixed some cases where optimization created an invalid image such as a
+  1-bit "RGB" image: {issue}`629,620`.
+- Page numbers are now displayed in debug logs when pages are being grafted.
+- ocrmypdf.optimize.rewrite_png and ocrmypdf.optimize.rewrite_png_as_g4 were
+  marked deprecated. Strictly speaking these should have been internal APIs,
+  but they were never hidden.
+- As a precaution, pikepdf mmap-based file access has been disabled due to a
+  rare race condition that causes a crash when certain objects are deallocated.
+  The problem is likely in pikepdf's dependency pybind11.
+- Extended the example plugin to demonstrate conversion to mono.
+
+## v11.0.2
+
+- Fixed {issue}`612`, TypeError exception. Fixed by eliminating unnecessary repair of
+  input PDF metadata in memory.
+
+## v11.0.1
+
+- Blacklist pdfminer.six 20200720, which has a regression fixed in 20200726.
+- Approve img2pdf 0.4 as it passes tests.
+- Clarify that the GPL-3 portion of pdfa.py was removed with the changes in v11.0.0;
+  the debian/copyright file did not properly annotate this change.
+
+## v11.0.0
+
+- Project license changed to Mozilla Public License 2.0. Some miscellaneous
+  code is now under MIT license and non-code content/media remains under
+  CC-BY-SA 4.0. License changed with approval of all people who were found
+  to have contributed to GPLv3 licensed sections of the project. ({issue}`600`)
+- Because the license changed, this is being treated as a major version number
+  change; however, there are no known breaking changes in functional behavior
+  or API compared to v10.x.
+
@@ -0,0 +1,181 @@
+% SPDX-FileCopyrightText: 2022 James R. Barlow
+% SPDX-License-Identifier: CC-BY-SA-4.0
+
+# v12
+
+## v12.7.2
+
+- Fixed "invalid version number" error for Tesseract packaging with nonstandard
+  version "5.0.0-rc1.20211030".
+- Fixed use of deprecated `importlib.resources.read_binary`.
+- Replace some uses of string paths with `pathlib.Path`.
+- Fixed a leaked file handle when using `--output-type none`.
+- Removed shims to support versions of pikepdf that are no longer supported.
+
+## v12.7.1
+
+- Declare support for pdfminer.six v20211012.
+
+## v12.7.0
+
+- Fixed test suite failure when using pikepdf 3.2.0 that was compiled with pybind11
+  2.8.0. {issue}`843`
+- Improve advice to user about using `--max-image-mpixels` if OCR fails for this
+  reason.
+- Minor documentation fixes. (Thanks to @mara004.)
+- Don't require importlib-metadata and importlib-resources backports on versions of
+  Python where the standard library implementation is sufficient.
+  (Thanks to Marco Genasci.)
+
+## v12.6.0
+
+- Implemented `--output-type=none` to skip producing PDFs for applications that
+  only want sidecar files ({issue}`787`).
+- Fixed ambiguities in descriptions of behavior of `--jbig2-lossy`.
+- Various improvements to documentation.
+
+## v12.5.0
+
+- Fixed build failure for the combination of PyPy 3.6 and pikepdf 3.0. This
+  combination can work in a source build but does not work with wheels.
+- Accepted bot that wanted to upgrade our deprecated requirements.txt.
+- Documentation updates.
+- Replace pkg_resources and install dependency on setuptools with
+  importlib-metadata and importlib-resources.
+- Fixed regression in hocrtransform causing text to be omitted when this
+  renderer was used.
+- Fixed some typing errors.
+
+## v12.4.0
+
+- When grafting text layers, use pikepdf's `unparse_content_stream` if available.
+- Confirmed support for pluggy 1.0. (Thanks @QuLogic.)
+- Fixed some typing issues, improved pre-commit settings, and fixed issues
+  flagged by linters.
+- PyPy 7.3.3 (=Python 3.6) is now supported. Note that PyPy does not necessarily
+  run faster, because the vast majority of OCRmyPDF's execution time is spent
+  running OCR or generally executing native code. However, PyPy may bring speed
+  improvements in some areas.
+
+## v12.3.3
+
+- watcher.py: fixed interpretation of boolean env vars ({issue}`821`).
+- Adjust CI scripts to test Tesseract 5 betas.
+- Document our support for the Tesseract 5 betas.
+
+## v12.3.2
+
+- Indicate support for flask 2.x, watcher 2.x ({issue}`815, 816`).
+
+## v12.3.1
+
+- Fixed issue with selection of text when using the hOCR renderer ({issue}`813`).
+- Fixed build errors with the Docker image by upgrading to a newer Ubuntu.
+  Also set the timezone of this image to UTC.
+
+## v12.3.0
+
+- Fixed a regression introduced in Pillow 8.3.0. Pillow no longer rounds DPI
+  for image resolutions. We now account for this ({issue}`802`).
+- We no longer use some API calls that are deprecated in the latest versions of
+  pikepdf.
+- Improved error message when a language is requested that doesn't look like a
+  typical ISO 639-2 code.
+- Fixed some tests that attempted to symlink on Windows, breaking tests on a
+  Windows desktop but not usually on CI.
+- Documentation fixes (thanks to @mara004)
+
+## v12.2.0
+
+- Fixed invalid Tesseract version number on Windows ({issue}`795`).
+- Documentation tweaks. Documentation build now depends on sphinx-issues package.
+
+## v12.1.0
+
+- For security reasons we now require Pillow >= 8.2.x. (Older versions will continue
+  to work if upgrading is not an option.)
+- The build system was reorganized to rely on `setup.cfg` instead of `setup.py`.
+  All changes should work with previously supported versions of setuptools.
+- The files in `requirements/*` are now considered deprecated but will be retained for v12.
+  Instead use `pip install ocrmypdf[test]` instead of `requirements/test.txt`, etc.
+  These files will be removed in v13.
+
+## v12.0.3
+
+- Expand the list of languages supported by the hocr PDF renderer.
+  Several languages were previously considered not supported, particularly those
+  non-European languages that use the Latin alphabet.
+- Fixed a case where the exception stack trace was suppressed in verbose mode.
+- Improved documentation around commercial OCR.
+
+## v12.0.2
+
+- Fixed exception thrown when using `--remove-background` on files containing small
+  images ({issue}`769`).
+- Improve documentation for description of adding language packs to the Docker image
+  and corrected name of French language pack.
+
+## v12.0.1
+
+- Fixed "invalid version number" for untagged tesseract versions ({issue}`770`).
+
+## v12.0.0
+
+**Breaking changes**
+
+- Due to recent security issues in pikepdf, Pillow and reportlab, we now require
+  newer versions of these libraries and some of their dependencies. (If necessary,
+  package maintainers may override these versions at their discretion; lower
+  versions will often work.)
+- We now use the "LeaveColorUnchanged" color conversion strategy when directing
+  Ghostscript to create a PDF/A. Generally this is faster than performing a
+  color conversion, which is not always necessary.
+- OCR text is now packaged in a Form XObject. This makes it easier to isolate
+  OCR from other document content. However, some poorly implemented PDF text
+  extraction algorithms may fail to detect the text.
+- Many API functions have stricter parameter checking or expect keyword arguments
+  were they previously did not.
+- Some deprecated functions in `ocrmypdf.optimize` were removed.
+- The `ocrmypdf.leptonica` module is now deprecated, due to difficulties with
+  the current strategy of ABI binding on newer platforms like Apple Silicon.
+  It will be removed and replaced, either by repackaging Leptonica as an
+  independent library using or using a different image processing library.
+- Continuous integration moved to GitHub Actions.
+- We no longer depend on `pytest_helpers_namespace` for testing.
+
+**New features**
+
+- New plugin hook: `get_progressbar_class`, for progress reporting,
+  allowing developers to replace the standard console progress bar with some
+  other mechanism, such as updating a GUI progress bar.
+- New plugin hook: `get_executor`, for replacing the concurrency model.
+  This is primarily to support execution on AWS Lambda, which does not support
+  standard Python `multiprocessing` due to its lack of shared memory.
+- New plugin hook: `get_logging_console`, for replacing the standard
+  way OCRmyPDF outputs its messages.
+- New plugin hook: `filter_pdf_page`, for modifying individual PDF
+  pages produced by OCRmyPDF.
+- OCRmyPDF now runs on nonstandard execution environments that do not have
+  interprocess semaphores, such as AWS Lambda and Android Termux. If the environment
+  does not have semaphores, OCRmyPDF will automatically select an alternate
+  process executor that does not use semaphores.
+- Continuous integration moved to GitHub Actions.
+- We now generate an ARM64-compatible Docker image alongside the x64 image.
+  Thanks to @andkrause for doing most of the work in a pull request several months
+  ago, which we were finally able to integrate now. Also thanks to @0x326 for
+  review comments.
+
+**Fixes**
+
+- Fixed a possible deadlock on attempting to flush `sys.stderr` when older
+  versions of Leptonica are in use.
+- Some worker processes inherited resources from their parents such as log
+  handlers that may have also lead to deadlocks. These resources are now released.
+- Improvements to test coverage.
+- Removed vestiges of support for Tesseract versions older than 4.0.0-beta1 (
+  which ships with Ubuntu 18.04).
+- OCRmyPDF can now parse all of Tesseract version numbers, since several
+  schemes have been in use.
+- Fixed an issue with parsing PDFs that contain images drawn at a scale of 0. ({issue}`761`)
+- Removed a frequently repeated message about disabling mmap.
+
@@ -0,0 +1,175 @@
+% SPDX-FileCopyrightText: 2022 James R. Barlow
+% SPDX-License-Identifier: CC-BY-SA-4.0
+
+# v13
+
+## v13.7.0
+
+- Fixed an exception when attempting to run and Tesseract is not installed.
+- Changed to SPDX license tracking and information files.
+
+## v13.6.2
+
+- Added a shim to prevent an "error during error handling" for Python 3.7 and 3.8.
+- Modernized some type annotations.
+- Improved annotations on our \_windows module to help IDEs and mypy figure out what
+  we're doing.
+
+## v13.6.1
+
+- Require setuptools-scm 7.0.5 to avoid possible issues with source distributions in
+  earlier versions of setuptools-scm.
+- Suppress a spurious warning, improve tests, improve typing and other miscellany.
+
+## v13.6.0
+
+- Added a new `initialize` plugin hook, making it possible to suppress built-in
+  plugins more easily, among other possibilities.
+- Fixed an issue where unpaper would exit with a "wrong stream" error, probably
+  related to images with an odd integer width. {issue}`887, 665`
+
+## v13.5.0
+
+- Added a new `optimize_pdf` plugin hook, making it possible to create plugins that
+  replace or enhance OCRmyPDF's PDF optimizer.
+- Removed all max version restrictions. Our new policy is to blacklist known-bad releases
+  and only block known-bad versions of dependencies.
+- The naming schema for object that holds all OCR text that OCRmyPDF inserts has
+  changed. This has always been an implementation detail (and remains so), but possibly,
+  someone was relying on it and would appreciate the heads-up.
+- Cleanup.
+
+## v13.4.7
+
+- Fixed PermissionError when cleaning up temporary files in rare cases. {issue}`974`
+- Fixed PermissionError when calling `os.nice` on platforms that lack it. {issue}`973`
+- Suppressed some warnings from libxmp during tests.
+
+## v13.4.6
+
+- Convert error on corrupt ICC profiles into a warning. Thanks to @oscherler.
+
+## v13.4.5
+
+- Remove upper bound on pdfminer.six version.
+- Documentation.
+
+## v13.4.4
+
+- Updated pdfminer.six version.
+- Docker image changed to Ubuntu 22.04 now that it is released and provides the
+  dependencies we need. This seems more consistent than our recent change to
+  Debian.
+
+## v13.4.3
+
+- Fix error on pytest.skip() with older versions of pytest.
+- Documentation updates.
+
+## v13.4.2
+
+- Worked around a
+  [major regression in Ghostscript 9.56.0](https://bugs.ghostscript.com/show_bug.cgi?id=705187)
+  where **all OCR text is stripped out of the PDF**. It simply removes all text,
+  even generated by software other than OCRmyPDF. Fortunately, we can ask
+  Ghostscript 9.56.0 to use its old behavior that worked correctly for our purposes.
+  Users must avoid the combination (Ghostscript 9.56.0, ocrmypdf \<13.4.2) since
+  older versions of OCRmyPDF have no way of detecting that this particular
+  version of Ghostscript removes all OCR text.
+- Marked pdfminer 20220319 as supported.
+- Fixed some deprecation warnings from recent versions of Pillow and pytest.
+- Test suite now covers Python 3.10 (Python 3.10 worked fine before, but was not
+  being tested).
+- Docker image now uses debian:bookworm-slim as the base image to fix the Docker
+  image build.
+
+## v13.4.1
+
+- Temporarily make threads rather than processes the default executor worker, due
+  to a persistent deadlock issue when processes are used. Add a new command line
+  argument `--no-use-threads` to disable this.
+
+## v13.4.0
+
+- Fixed test failures when using pikepdf 5.0.0.
+- Various improvements to the optimizer. In particular, we now recognize PDF images
+  that are encoded with both deflate (PNG) and DCT (JPEG), and also produce PDF
+  with images compressed with deflate and DCT, since this often yields file size
+  improvements compared to plain DCT.
+
+## v13.3.0
+
+- Made a harmless but "scary" exception after failing to optimize an image less scary.
+- Added a warning if a page image is too large for unpaper to clean. The image is
+  passed through without cleaning. This is due to a hard-coded limitation in a
+  C library used by unpaper so it cannot be rectified easily.
+- We now use better default settings when calling img2pdf.
+- We no longer try to optimize images that we failed to save in certain situations.
+- We now account for some differences in text output from Tesseract 5 compared to
+  Tesseract 4.
+- Better handling of Ghostscript producing empty images when attempting to rasterize
+  page images.
+
+## v13.2.0
+
+- Removed all runtime uses of distutils since it is deprecated in standard library. We
+  previous used `distutils.version` to examine version numbers of dependencies
+  at run time, and now use `packaging.version` for this. This is a new
+  dependency.
+- Fixed an error message advising the user that Ghostscript was not installed being
+  suppressed when this condition actually happens.
+- Fixed an issue with incorrect page number and totals being displayed in the progress
+  bar. This was purely a display/presentation issue. {issue}`876`.
+
+## v13.1.1
+
+- Fixed issue with attempting to deskew a blank page on Tesseract 5. {issue}`868`.
+
+## v13.1.0
+
+- Changed to using Python concurrent.futures-based parallel execution instead of
+  pools, since futures have now exceed pools in features.
+- If a child worker is terminated (perhaps by the operating system or the user
+  killing it in a task manager), the parallel task will fail an error message.
+  Previously, the main ocrmypdf process would "hang" indefinitely, waiting for the
+  child to report.
+- Added new argument `--tesseract-thresholding` to provide control over Tesseract 5's
+  threshold parameter.
+- Documentation updates and changes. Better documentation for `--output-type none`,
+  added a few releases ago. Removed some obsolete documentation.
+- Improved bash completions - thanks to @FPille.
+
+## v13.0.0
+
+**Breaking changes**
+
+- The deprecated module `ocrmypdf.leptonica` has been removed.
+- We no longer depend on Leptonica (`liblept`) or CFFI (`libffi`,
+  `python3-cffi`). (Note that Tesseract still requires Leptonica; OCRmyPDF no longer
+  directly uses this library.)
+- The argument `--remove-background` is temporarily disabled while we search for an
+  alternative to the Leptonica implementation of this feature.
+- The `--threshold` argument has been removed, since this also depended on Leptonica.
+  Tesseract 5.x has implemented improvements to thresholding, so this feature will be
+  redundant anyway.
+- `--deskew` was previous calculated by a Leptonica algorithm. We now use a feature
+  of Tesseract to find the appropriate the angle to deskew a page. The deskew angle
+  according to Tesseract may differ from Leptonica's algorithm. At least in theory,
+  Tesseract's deskew angle is informed by a more complex analysis than Leptonica,
+  so this should improve results in general. We also use Pillow to perform the
+  deskewing, which may affect the appearance of the image compared to Leptonica.
+- Support for Python 3.6 was dropped, since this release is approaching end of life.
+- We now require pikepdf 4.0 or newer. This, in turn, means that OCRmyPDF requires
+  a system compatible with the manylinux2014 specification. This change was "forced"
+  by Pillow not releasing manylinux2010 wheels anymore.
+- We no longer provide requirements.txt-style files. Use `pip install ocrmypdf[...]`
+  instead.
+- Bumped required versions of several libraries.
+
+**Fixes**
+
+- Fixed an issue where OCRmyPDF failed to find Ghostscript on Windows even when
+  installed, and would exit with an error.
+- By removing Leptonica, we fixed all issues related to Leptonica on Apple
+  Silicon or Leptonica failing to import on Windows.
+
@@ -0,0 +1,97 @@
+% SPDX-FileCopyrightText: 2022 James R. Barlow
+% SPDX-License-Identifier: CC-BY-SA-4.0
+
+# v14
+
+## v14.4.0
+
+- Digitally signed PDFs are now detected. If the PDF is signed, OCRmyPDF will
+  refuse to modify it. Previously, only encrypted PDFs were detected, not
+  those that were signed but not encrypted. {issue}`1040`
+- In addition, `--invalidate-digital-signatures` can be used to override the
+  above behavior and modify the PDF anyway. {issue}`1040`
+- tqdm progress bars replaced with "rich" progress bars. The rich library is
+  a new dependency. Certain APIs that used tqdm are now deprecated and will
+  be removed in the next major release.
+- Improved integration with GitHub Releases. Thanks to @stumpylog.
+
+## v14.3.0
+
+- Renamed master branch to main.
+- Improve PDF rasterization accuracy by using the `-dPDFSTOPONERROR` option
+  to Ghostscript. Use `--continue-on-soft-render-error` if you want to render
+  the PDF anyway. The plugin specification was adjusted to support this feature;
+  plugin authors may want to adapt PDF rasterizing and rendering
+  plugins. {issue}`1083`
+- The calculated deskew angle is now recorded in the logged output. {issue}`1101`
+- Metadata can now be unset by setting a metadata type such as `--title` to an
+  empty string. {issue}`1117,1059`
+- Fixed random order of languages due to use of a set. This may have caused output
+  to vary when multiple languages were set for OCR. {issue}`1113`
+- Clarified the optimization ratio reported in the log output.
+- Documentation improvements.
+
+## v14.2.1
+
+- Fixed {issue}`977`, where images inside Form XObjects were always excluded
+  from image optimization.
+
+## v14.2.0
+
+- Added `--tesseract-downsample-above` to downsample larger images even when
+  they do not exceed Tesseract's internal limits. This can be used to speed
+  up OCR, possibly sacrificing accuracy.
+- Fixed resampling AttributeError on older Pillow. {issue}`1096`
+- Removed an error about using Ghostscript on PDFs with that have the /UserUnit
+  feature in use. Previously, Ghostscript would fail to process these PDFs,
+  but in all supported versions it is now supported, so the error is no longer
+  needed.
+- Improved documentation around installing other language packs for Tesseract.
+
+## v14.1.0
+
+- Added `--tesseract-non-ocr-timeout`. This allows using Tesseract's deskew
+  and other non-OCR features while disabling OCR using `--tesseract-timeout 0`.
+- Added `--tesseract-downsample-large-images`. This downsamples larges images
+  that exceed the maximum image size Tesseract can handle. Large images may still
+  take a long time to process, but this allows them to be processed if that
+  is desired.
+- Fixed {issue}`1082`, an issue with snap packaged building.
+- Change linter to ruff, fix lint errors, update documentation.
+
+## v14.0.4
+
+- Fixed {issue}`1066, 1075`, an exception when processing certain malformed PDFs.
+
+## v14.0.3
+
+- Fixed {issue}`1068`, avoid deleting /dev/null when running as root.
+- Other documentation fixes.
+
+## v14.0.2
+
+- Fixed {issue}`1052`, an exception on attempting to process certain nonconforming PDFs.
+- Explicitly documented that Windows 32-bit is no longer supported.
+- Fixed source installation instructions.
+- Other documentation fixes.
+
+## v14.0.1
+
+- Fixed some version checks done with smart version comparison.
+- Added missing jbig2dec to Docker image.
+
+## v14.0.0
+
+- Dropped support for Python 3.7.
+- Dropped support generally speaking, all dependencies older than what Ubuntu 20.04
+  provides.
+- Ghostscript 9.50 or newer is now required. Shims to support old versions were
+  removed.
+- Tesseract 4.1.1 or newer is now required. Shims to support old versions were
+  removed.
+- Docker image now uses Tesseract 5.
+- Dropped setup.cfg configuration for pyproject.toml.
+- Removed deprecation exception PdfMergeFailedError.
+- A few more public domain test files were removed or replaced. We are aiming for
+  100% compliance with SPDX and generally towards simplifying copyright.
+
@@ -0,0 +1,137 @@
+% SPDX-FileCopyrightText: 2022 James R. Barlow
+% SPDX-License-Identifier: CC-BY-SA-4.0
+
+# v15
+
+## v15.4.4
+
+- Fixed documentation for installing Ghostscript on Windows. {issue}`1198`
+- Added warning message about security issue in older versions of Ghostscript.
+
+## v15.4.3
+
+- Fixed deprecation warning in pikepdf older than 8.7.1; pikepdf >= 8.7.1 is
+  now required.
+
+## v15.4.2
+
+- We now raise an exception on a certain class of PDFs that likely need an
+  explicit color conversion strategy selected to display correctly
+  for PDF/A conversion.
+- Fixed an error that occurred while trying to write a log message after the
+  debug log handler was removed.
+
+## v15.4.1
+
+- Fixed misc/watcher.py regressions: accept `--ocr-json-settings` as either
+  filename or JSON string, as previously; and argument count mismatch.
+  {issue}`1183,1185`
+- We no longer attempt to set /ProcSet in the PDF output, since this is an
+  obsolete PDF feature.
+- Documentation improvements.
+
+## v15.4.0
+
+- Added new experimental APIs to support offline editing of the final text.
+  Specifically, one can now generate hOCR files with OCRmyPDF, edit them with
+  some other tool, and then finalize the PDF. They are experimental and
+  subject to change, including details of how the working folder is used.
+  There is no command line interface.
+- Code reorganization: executors, progress bars, initialization and setup.
+- Fixed test coverage in cases where the coverage tool did not properly trace
+  into threads or subprocesses. This code was still being tested but appeared
+  as not covered.
+- In the test suite, reduced use of subprocesses and other techniques that
+  interfere with coverage measurement.
+- Improved error check for when we appear to be running inside a snap container
+  and files are not available.
+- Plugin specification now properly defines progress bars as a protocol rather
+  than defining them as "tqdm-like".
+- We now default to using "forkserver" process creation on POSIX platforms
+  rather than fork, since this is method is more robust and avoids some
+  issues when threads are present.
+- Fixed an instance where the user's request to `--no-use-threads` was ignored.
+- If a PDF does not have language metadata on its top level object, we add
+  the OCR language.
+- Replace some cryptic test error messages with more helpful ones.
+- Debug messages for how OCRmyPDF picks the colorspace for a page are now
+  more descriptive.
+
+## v15.3.1
+
+- Fixed an issue with logging settings for misc/watcher.py introduced in the
+  previous release. {issue}`1180`
+- We now attempt to preserve the input's extended attributes when creating
+  the output file.
+- For some reason, the macOS build now needs OpenSSL explicitly installed.
+- Updated documentation on Docker performance concerns.
+
+## v15.3.0
+
+- Update misc/watcher.py to improve command line interface using Typer, and
+  support `.env` specification of environment variables. Improved error
+  messages. Thanks to @mflagg2814 for the PR that prompted this improvement.
+- Improved error message when a file cannot be read because we are running in
+  a snap container.
+
+## v15.2.0
+
+- Added a Docker image based on Alpine Linux. This image is smaller than the
+  Ubuntu-based image and may be useful in some situations. Currently hosted at
+  jbarlow83/ocrmypdf-alpine. Currently not available in ARM flavor.
+- The Ubuntu Docker is now aliased to jbarlow83/ocrmypdf-ubuntu.
+- Updated Docker documentation.
+
+## v15.1.0
+
+- We now require Pillow 10.0.1, due a serious security vulnerability in all earlier
+  versions of that dependency. The vulnerability concerns WebP images and could
+  be triggered in OCRmyPDF when creating a PDF from a malicious WebP image.
+- Added some keyword arguments to `ocrmypdf.ocr` that were previously accepted
+  but undocumented.
+- Documentation updates and typing improvements.
+
+## v15.0.2
+
+- Added Python 3.12 to test matrix.
+- Updated documentation for notes on Python 3.12, 32-bit support and some new
+  features in v15.
+
+## v15.0.1
+
+- Wheels Python tag changed to py39.
+- Marked as a expected fail a test that fails on recent Ghostscript versions.
+- Clarified documentation and release notes around the extent of 32-bit support.
+- Updated installation documentation to changes in v15.
+
+## v15.0.0
+
+- Dropped support for Python 3.8.
+- Dropped support some older dependencies, specifically `coloredlogs` and
+  `tqdm` in favor of rich - see `pyproject.toml` for details.
+  Generally speaking, Ubuntu 22.04 is our new baseline system.
+- Tightened version requirements for some dependencies.
+- Dropped support for 32-bit Linux wheels. We strongly recommend a 64-bit operating
+  system, and 64-bit versions of Python, Tesseract and Ghostscript to use OCRmyPDF.
+  Many of our dependencies are dropping 32-bit builds (e.g. Pillow), and we are
+  following suit. (Maintainers may still build 32-bit versions from source.)
+- Changed to trusted release for PyPI publishing.
+- pikepdf memory mapping is enabled again for improved performance, now that an
+  issue with feature in pikepdf is fixed.
+- `ocrmypdf.helpers.calculate_downsample` previously had two variants, one
+  that took a `PIL.Image` and one that took a `tuple[int, int]`. The latter
+  was removed.
+- The snap version of ocrmypdf is now based on Ubuntu core22.
+- We now account for situations where a small portion of an image on a page is drawn
+  at high DPI (resolution). Previously, the entire page would be rasterized at the
+  highest resolution of any feature, which caused performance problems. Now,
+  the page is rasterized
+  at a resolution based on the average DPI of the page, weighted by the area that
+  each feature occupies. Typically, small areas of high resolution in PDFs are
+  errors or quirks from the repeated use of assets and high resolution is not
+  beneficial. {issue}`1010,1104,1004,1079,1010`
+- Ghostscript color conversion strategy is now configurable using
+  `--color-conversion-strategy`. {issue}`1143`
+- JBIG2 threshold for optimization is now configurable using
+  `--jbig2-threshold`. {issue}`1133`
+
@@ -0,0 +1,291 @@
+% SPDX-FileCopyrightText: 2022 James R. Barlow
+% SPDX-License-Identifier: CC-BY-SA-4.0
+
+# v16
+
+## v16.13.0
+
+- Added detection and repair for Ghostscript 10.6 JPEG corruption. When GS 10.6
+  truncates JPEG data by 1-15 bytes, OCRmyPDF now restores the original image
+  bytes from the input PDF. A warning is issued when GS 10.6+ is detected.
+  {issue}`1603`
+- We continue to force re-optimization of JPEGs, since this catches some issues with corruption for situations where Ghostscript modifies an image. It is likely there are still cases where we cannot mitigate all corruption issues. {issue}`1585`
+- Fixed handling of PDF page boxes (ArtBox, BleedBox) which were not being
+  processed correctly in some cases. {issue}`1181,1360`
+- Documentation: clarified podman usage instructions.
+
+## v16.12.0
+
+- Disable Ghostscript's subset fonts feature, which was found to corrupt text in certain
+  PDFs. Thanks @mnaegler for identifying this issue. {issue}`1592`
+- Users of Ghostscript 10.6.0+ reported that Ghostscript seems to generate corrupted
+  JPEGs. We force re-optimization of these JPEGs to mitigate the corruption until
+  Ghostscript fixes the issue. {issue}`1585`
+- OCRmyPDF now avoids applying flate compression to large JPEG images, unless maximum
+  optimization is requested, since flate+DCT compression reduces performances in PDF
+  viewers with large images.
+- Updated Dockerfiles to use more recent base operating systems.
+- Updated build and test matrix to include Python 3.14.
+- Minor documentation improvements.
+- pikepdf >= 10.0.0 is now required.
+
+## v16.11.1
+
+- Fixed issue with Tesseract changing an error message related to skew. {issue}`1576`
+- Dropped macOS 13 from build-test matrix since it is no longer supported by Apple.
+
+## v16.11.0
+
+- Deprecated "semfree" plugin in favor of falling back to threads if the platform
+  does not support semaphores. Fixes an issue with Python 3.14.
+- Fixed references to PDF/A compliances levels to be consistent with ISO nomenclature.
+  Thanks @5HT2. {issue}`1557`
+- Fixed an issue around using plugin_manager as an argument. {issue}`1555`
+- Added OpenBSD install steps to README. {issue}`1554`
+- Removed PyPy from test matrix due to declining support in third party libraries.
+- Documentation improvements.
+
+## v16.10.4
+
+- Corrected build errors in Python 3.13.3 and 3.13.4.
+
+## v16.10.3 (not released)
+
+- Blocked optimization of images with pre-blended soft masks. {issue}`1536`
+- Fixed warning from hypothesis on running tests.
+- Release incomplete due to new test failures in Python 3.13.3 and 3.13.4.
+
+## v16.10.2
+
+- Blacklist pikepdf 9.8.0 due to an incompatible change.
+
+## v16.10.1
+
+- No changes affecting OCRmyPDF functionality for command line end users.
+- webservice: made page specification easier to find in UI.
+- webservice: fix download button downloads wrong file.
+- Converted project documentation from rST to Markdown.
+- Added README translation to Simplified Chinese. Thanks @HuaPai.
+- Modernized license specification in pyproject.toml.
+- Modernized SPDX license to REUSE.toml.
+
+## v16.10.0
+
+- Added hocr textangle processing, improving handling of text at angles.
+  Thanks @0dinD {issue}`1467`
+- Docker documentation updates related to podman. Thanks @rugk. {issue}`1489,1488`
+- Dropped webservice.py's fragile use of ttyd. Instead, messages from ocrmypdf are
+  printed to the console.
+- Fixed broken test test_hocrtransform_matches_sandwich, which had become
+  an invalid test. Thanks @QuLogic for reporting.
+- Improved install instructions for Windows. Thanks @alex.
+
+## v16.9.0
+
+- Added hocr caption processing. Thanks @0dinD {issue}`1466`
+- ocrmypdf-alpine Docker image is now built with Alpine 3.21.
+- Fixed error handling of PDFs that contain invalid images with both ImageMask
+  and ColorSpace defined. {issue}`1453`
+- Fixed test suite regression when only older Ghostscripts are installed.
+- Improved documetnation of \_progressbar.py. Thanks @QuentinFuxa. {issue}`1456`
+- Disabling building of documentation as PDF on ReadTheDocs, as this caused
+  complex build issues deemed not worth solving.
+
+## v16.8.0
+
+- Upgraded webservice.py demonstration using streamlit. It's now possible to
+  exercise most of OCRmyPDF's functionality in a simple web UI.
+- Added cache to Dockerfiles to improve build speed.
+- Fixed numerous formatting errors in the documentation that prevented some
+  parts of documentation from generating correctly.
+- Improved OCR text rendering by suppressing negative-width spaces. Thanks
+  @pajowu. {issue}`1446`
+- Improved detecting of invisible text when using `--redo-ocr`. Thanks
+  @pajowu. {issue}`1448``
+
+## v16.7.0
+
+- Fixed further issues with Docker build and updated some versions.
+- Main Docker image returned to Ubuntu 24.04 since the fix in v16.6.2 resolved
+  that concern.
+- Code that previously sent Ghostscript output to stdout has been changed to
+  output to temporary files, since Ghostscript was doing that anyway internally.
+  This is a modest efficiency improvement.
+- Fixed an issue with debug log output being parsed as rich markup. {issue}`1444`
+
+## v16.6.2
+
+- Remove invalid hyperlink annotations to satisfy Ghostscript 10.x during PDF/A
+  conversion. {issue}`1425`
+
+## v16.6.1
+
+- Fixed some issues with Docker build, such as removing unnecessary content and using
+  a stable Tesseract version.
+- Reverted Docker image to Ubuntu 22.04 to access older/more stable Ghostscript
+  for now.
+- Clarified batch commands in documentation.
+- Fixed an issue with JSON serialization and pickling of HOCRResult. {issue}`1427`
+
+## v16.6.0
+
+- Fixed an issue where damaged PDFs would fail with `--redo-ocr`. {issue}`1403`
+- Fixed an error that prevented JBIG2 optimization on Windows if the image
+  was optimized in an earlier step. {issue}`1396`
+- Fixed an error detecting the version of unpaper 7.0.0. {issue}`1409`
+- Fixed a performance regression when scanning pages. {issue}`1378`. Thanks @aliemjay.
+- Fixed Alpine Docker image by enforcing Alpine 3.19. Alpine 3.20 includes a
+  defective version of Tesseract OCR and so is not usable.
+- Upgraded Ubuntu Docker image to use Ubuntu 24.04.
+- Build and test scripts/actions switched to uv.
+- When running in a container, we now remind the user that temporary folders
+  are inside the container and may not be accessible.
+- Fixed Linux test coverage matrix, which was missing some key versions.
+
+## v16.5.0
+
+- Fixed issue with interpreting PDFs that have images with array masks.
+  {issue}`1377`
+- Enabled testing on Python 3.13.
+- Fixed a test that did not work correctly but still passed. {issue}`1382`
+- Improved "PDF/A conversion failed" warning message to better describe implications.
+- Updated documentation to better explain OCR_JSON_SETTINGS in batch processing.
+- Build backend changed from setuptools to hatchling.
+
+## v16.4.3
+
+- Work around pdfminer.six issue where a token on the buffer boundary is incorrectly
+  parsed as two tokens. {issue}`1361`
+- New rules are applied to stencil masks and explicit masks when calculating the
+  optimal page DPI for rendering. {issue}`1362`
+- Fixed attempts to use an incompatible jbig2.EXE provided by TeX Live. {issue}`1363`
+
+## v16.4.2
+
+- Fixed order of filenames passed to Ghostscript for PDF/A generation. {issue}`1359`
+- Suppressed missing jbig2dec warning message. {issue}`1358`
+- Fixed calculation of image size when soft mask dimensions don't match image
+  dimension. {issue}`1351`
+- Several fixes to documentation. Thanks to users Iris and JoKalliauer
+  who contributed these changes.
+- Fixed error on processing PDFs that are missing certain image metadata. {issue}`1315`
+
+## v16.4.1
+
+- Fixed calculation of image printed area (used in finding weighted DPI for OCR).
+  {issue}`1334`
+- Fixed "NotImplementedError: not sure how to get colorspace" error
+  messages in logs which simply records a failure to optimize images with
+  print production colorspaces. {issue}`1315`
+
+## v16.4.0
+
+- Selecting the `osd` and `equ` pseudo-languages with `-l/--language` now
+  exits with an error when using Tesseract OCR, because these are not
+  regular Tesseract languages but implementation details implemented.
+  Using them can cause Tesseract to crash.
+- The hOCR renderer is more tolerant of extra whitespace in input files.
+- watcher.py now changes the output file extension to .pdf when the input is not
+  .pdf.
+- Improved handling of PDFs that contain circularly referenced Form XObjects.
+  {issue}`1321`
+- Fixed Alpine Docker image for ARM64, which was not building correctly.
+- Docker images now use pikepdf 9.0.0.
+- Prevent use of Tesseract OCR 5.4.0, a version with known regressions.
+- Disabled progressbar for "Linearizing" when `--no-progress-bar` set.
+- Fixed some tests that warn about missing JBIG2 decoding via pikepdf, by
+  installing the necessary libraries during tests.
+
+## v16.3.1
+
+- Fixed a test suite failure with Ghostscript 10.03.0+. {issue}`1316`
+- Fixed an issue with the presentation of the "OCR" progress bar. {issue}`1313`
+
+## v16.3.0
+
+- Fixed progress bar not displaying for Ghostscript PDF/A conversion. {issue}`1313`
+- Added progress bar for linearization. {issue}`1313`
+- If `--rotate-pages-threshold` issued without `--rotate-pages` we now exit with
+  an error since the user likely intended to use `--rotate-pages`. {issue}`1309`
+- If Tesseract hOCR gives an invalid line box, print an error message instead of
+  exiting with an error. {issue}`1312`
+
+## v16.2.0
+
+- Fixed issue 'NoneType' object has no attribute 'get' when optimizing certain PDFs.
+  {issue}`1293,1271`
+- Switched formatting from black to ruff.
+- Added support for sending sidecar output to io.BytesIO.
+- Added support for converting HEIF/HEIC images (the native image of iPhones and
+  some other devices) to PDFs, when the appropriate pi-hief library is installed.
+  This library is marked as a dependency, but maintainers may opt out if needed.
+- We now default to downsampling large images that would exceed Tesseract's internal
+  limits, but only if it cause processing to fail. Previously, this behavior only
+  occurred if specifically requested on command line. It can still be configured
+  and disabled. See the --tesseract command line options.
+- Added Macports install instructions. Thanks @akierig.
+- Improved logging output when an unexpected error occurs while trying to obtain
+  the version of a third party program.
+
+## v16.1.2
+
+- Fixed test suite failure when using Ghostscript 10.3.
+- Other minor corrections.
+
+## v16.1.1
+
+- Fixed PyPy 3.10 support.
+
+## v16.1.0
+
+- Improved hOCR renderer is now default for left to right languages.
+- Improved handling of rotated pages. Previously, OCR text might be missing for
+  pages that were rotated with a /Rotate tag on the page entry.
+- Improved handling of cropped pages. Previously, in some cases a page with a
+  crop box would not have its OCR applied correctly and misalignment between
+  OCR text and visible text coudl occur.
+- Documentation improvements, especially installation instructions for less
+  common platforms.
+
+## v16.0.4
+
+- Fixed some issues for left-to-right text with the new hOCR renderer. It is still
+  not default yet but will be made so soon. Right-to-left text is still in progress.
+- Added an error to prevent use of several versions of Ghostscript that seem
+  corrupt existing text in input PDFs. Newly generated OCR is not affected.
+  For best results, use Ghostscript 10.02.1 or newer, which contains the fix
+  for the issue.
+
+## v16.0.3
+
+- Changed minimum required Ghostscript to 9.54, to support users of RHEL 9 and its
+  derivatives, since that is the latest version available there.
+- Removed warning message about CVE-2023-43115, on the assumption that most
+  distributions have backported the patch by now.
+
+## v16.0.2
+
+- Temporarily changed PDF text renderer back to sandwich by default to address
+  regressions in macOS Preview.
+
+## v16.0.1
+
+- Fixed text rendering issue with new hOCR text renderer - extraneous byte order
+  marks.
+- Tightened dependencies.
+
+## v16.0.0
+
+- Added OCR text renderer, combined the best ideas of Tesseract's PDF
+  generator and the older hOCR transformer renderer. The result is a hopefully
+  permanent fix for wordssmushedtogetherwithoutspaces issues in extracted text,
+  better registration/position of text on skewed baselines {issue}`1009`,
+  fixes to character output when the German Fraktur script is used {issue}`1191`,
+  proper rendering of right to left languages (Arabic, Hebrew, Persian) {issue}`1157`.
+  Asian languages may still have excessive word breaks compared to expectations.
+  The new renderer is the default; the old sandwich renderer is still available
+  using `--pdf-renderer sandwich`; the old hOCR renderer is no more.
+- The `ocrmypdf.hocrtransform` API has changed substantially.
+- Support for Python 3.9 has been dropped. Python 3.10+ is now required.
+- pikepdf >= 8.8.0 is now required.
+
@@ -0,0 +1,433 @@
+% SPDX-FileCopyrightText: 2022 James R. Barlow
+% SPDX-License-Identifier: CC-BY-SA-4.0
+
+# v17
+
+## v17.9.0
+
+- OCRmyPDF now uses any Noto font installed on the system, not just the two
+  dozen script families it knows by name ({issue}`1722`). Previously a document
+  in, say, Cherokee or Vai was rendered with the glyphless fallback font even
+  though the matching font was installed — a common situation on macOS, which
+  ships around a hundred script-specific Noto faces. When the named fonts
+  cannot cover a word, OCRmyPDF now searches the installed fonts for one that
+  can.
+- The "no installed font has glyphs" warning now names the characters it could
+  not render, with their codepoints and Unicode names, so it is clear which
+  font to install. Text that mixes scripts no single font covers is now
+  reported as such, instead of advising the user to install fonts they may
+  already have.
+- Fixed the macOS font installation instructions, which recommended a Homebrew
+  package (`font-noto`) that does not exist ({issue}`1722`). Homebrew has no
+  single Noto package; each family is a separate cask. The Fedora package name
+  was also corrected to `google-noto-fonts-all`.
+- Font providers may now implement the optional `GlyphSearchingFontProvider`
+  protocol to participate in coverage-based font search.
+- Fixed `--jpeg-quality`/`--jpg-quality` having no effect on the CLI: the
+  value was silently dropped before reaching the optimizer, which then
+  always used its own built-in default JPEG quality regardless of what was
+  requested ({issue}`1723`). The same bug affected the Python API's
+  `jpg_quality` parameter. `ocrmypdf.ocr()` now accepts `jpeg_quality`
+  (matching the CLI flag name) as the canonical parameter; `jpg_quality`
+  still works but is deprecated.
+- Hardened PDF parsing against malformed (non-dictionary) `/Resources`,
+  `/XObject`, and `/FontDescriptor` entries, which previously crashed
+  `ocrmypdf.ocr()` with `AttributeError`/`TypeError`/`ValueError` on
+  otherwise-processable files, both during PDF/A font scanning and general
+  image scanning ({issue}`1713`). Thanks @mvanhorn for the initial fix.
+- Release process improvements: fixed a CI bug where every push to main
+  after a release was tagged would incorrectly revert the just-published
+  GitHub release back to draft status.
+
+## v17.8.1
+
+- Improved the `--tesseract-pagesegmode` help text to point to
+  `tesseract --help-extra`, since Tesseract 5.5.2 moved the page segmentation
+  mode documentation there from `tesseract --help`. Thanks @sokai.
+- Internal refactoring: completed a project-wide mypy type-checking pass
+  (`--check-untyped-defs` is now enabled, and the mypy pre-commit hook is now
+  blocking rather than advisory), fixing several latent edge-case bugs
+  surfaced along the way.
+- Release process improvements: migrated from pre-commit to prek for local
+  git hooks, and added a dedicated lint job to CI.
+- Improved typing strictness for `Path`.
+
+## v17.8.0
+
+- `--output-type auto` (the default) again produces PDF/A whenever it can,
+  matching OCRmyPDF 16's "PDF/A by default" behavior. It first tries the fast
+  Ghostscript-free conversion (validated by veraPDF when available) and now
+  falls back to Ghostscript when that cannot produce PDF/A, only emitting a
+  regular PDF when even Ghostscript cannot safely convert (for example, an
+  input with non-embedded CID/CJK fonts, per {issue}`1561`). A consequence is
+  that the default path may once again invoke Ghostscript, which is slower and
+  may transcode images; use `--output-type pdf` to skip PDF/A conversion
+  entirely.
+- Fixed detection of veraPDF 1.30.0 and newer: recent builds print JVM
+  warnings before their version string, which caused OCRmyPDF to report
+  veraPDF as unavailable and skip the fast PDF/A path.
+- OCRmyPDF no longer silently corrupts a non-embedded CID (CJK) text layer when
+  producing PDF/A ({issue}`1561`). PDF/A requires all fonts to be embedded, so
+  Ghostscript substitutes and re-embeds non-embedded CID fonts — such as the OCR
+  text layer Adobe Acrobat adds to scanned CJK documents — which mangles the
+  text and destroys searchability. OCRmyPDF now detects non-embedded CID fonts
+  before conversion: with `--output-type auto` (the default) it produces a
+  regular PDF and preserves the existing text layer, and with an explicit
+  `--output-type pdfa*` it stops with an error rather than emit corrupted
+  output. Use `--output-type pdf` to keep the text layer, or `--force-ocr` to
+  rebuild it with embedded fonts.
+- Writing the output PDF to standard output (`ocrmypdf input.pdf -`) is now
+  protected against corruption at the operating system level. Previously
+  OCRmyPDF relied on no in-process code — third-party libraries, plugins, or
+  stray `print()` calls — ever writing to stdout; a single accidental write
+  would silently corrupt the PDF. The command line program now saves the real
+  stdout at startup, before plugins are loaded or any worker process/thread is
+  started, and redirects file descriptor 1 to stderr, so that only OCRmyPDF's
+  final PDF output can reach stdout. A consequence is that a plugin which
+  intentionally prints to stdout will have that output redirected to stderr.
+- Added the public API function {func}`ocrmypdf.configure_stdout_protection`,
+  which installs this same protection. Like {func}`ocrmypdf.configure_logging`,
+  it is optional and intended for callers that want command-line-like behavior;
+  applications that manage their own standard output should not call it.
+- Fixed an uncaught `UnicodeDecodeError` when processing a PDF whose
+  `/DocumentInfo` dictionary contains a `/Name` key encoded in Latin-1 (or
+  another non-UTF-8 encoding), such as `/Saks#e5r`. `repair_docinfo_nuls` now
+  treats such a block as malformed, logs a message, and continues instead of
+  crashing the pipeline ({issue}`1540`). Current pikepdf releases tolerate these
+  keys by surrogate-escaping them, but older versions raised while iterating the
+  dictionary.
+
+## v17.7.1
+
+- Fixed a severe, Windows-specific performance regression in the "Scanning
+  contents" phase, most visible with `--redo-ocr` ({issue}`1662`). Since
+  v16.4.3, OCRmyPDF forced pdfminer's read buffer to 256 MiB to work around a
+  pdfminer bug that mishandled tokens split across the buffer boundary
+  ({issue}`1361`). On Windows, CPython's `BufferedReader.read()` eagerly
+  allocates a buffer of the requested size on every read, so the oversized
+  buffer made each of pdfminer's thousands of reads cost tens of milliseconds
+  (this allocation is lazy, and effectively free, on Linux). The underlying
+  pdfminer bug was fixed upstream in pdfminer.six 20250327
+  ([#1030](https://github.com/pdfminer/pdfminer.six/pull/1030)), with a
+  follow-up for tokens split across streams in 20260107
+  ([#1158](https://github.com/pdfminer/pdfminer.six/pull/1158)), so the
+  workaround has been removed and the minimum pdfminer.six version raised to
+  20260107.
+- The font discovery used to build the OCR text layer now finds variable fonts
+  such as `NotoSansArabic[wdth,wght].ttf`, the form shipped by Homebrew casks
+  and current Google Fonts releases. Previously only static `-Regular.ttf`/`.otf`
+  files were matched, so users who had installed the correct Noto font still got
+  the glyphless fallback and a "No font found" warning ({issue}`1652`).
+- Font discovery is now language-aware for CJK: each Chinese, Japanese, and
+  Korean language maps to its own per-language Noto family (NotoSansSC, TC, HK,
+  JP, KR), with the pan-CJK super font kept as a shared fallback, since the
+  per-language fonts are region subsets that may lack glyphs from other scripts.
+- The warning shown when no installed font has glyphs for some text was reworded
+  to explain the consequence — the text is still added as a searchable, copyable
+  layer but appears blank when highlighted in a viewer — and to name the specific
+  font family to install.
+
+## v17.7.0
+
+- The Docker images now run as a non-root user (`app`, uid/gid 1000) by default
+  rather than as root, as a defense-in-depth measure. If you bind-mount a
+  directory for input and output, you may now need to add a `--user` argument so
+  the container can write to it; the correct value differs for rootless Docker,
+  Podman, and rootful Docker, and is described in the Docker documentation.
+  Piping the input and output through stdin/stdout still works with no
+  permission setup.
+- The Docker images now default their working directory to `/data`, so files in
+  a directory mounted there can be given as relative paths without an explicit
+  `--workdir`.
+- The Ubuntu Docker image now installs Tesseract 5 from the Ubuntu archive
+  instead of the third-party `alex-p/tesseract-ocr5` PPA, and the base images
+  were updated to Ubuntu 26.04 and Alpine 3.24.
+- Fixed a missing space in the error message shown when OCRmyPDF cannot access
+  its working directory inside a Docker container.
+- Updated packaged dependencies, including the optional web service stack
+  (starlette, tornado, python-multipart) and cryptography.
+
+## v17.6.0
+
+- When the optimizer encounters an image it cannot process (for example, an
+  exotic colorspace that cannot be transcoded), it now logs a concise warning
+  that the image was left unchanged rather than printing an alarming
+  traceback. The output file was already valid in these cases; only the
+  reporting was misleading. The full traceback is still available at debug
+  verbosity (`-v 1`) ({issue}`846`).
+- `--pdfa-image-compression=auto` (the default) now selects lossless image
+  compression at `-O0` so Ghostscript no longer transcodes lossless images to
+  JPEG during PDF/A generation. At `-O1` and above, `auto` continues to defer
+  to Ghostscript's heuristic, which may recompress images lossily. `-O1` (the
+  default level) is kept as a historical exception because coercing it to
+  lossless can substantially bloat output; users who want guaranteed lossless
+  image handling should pass `--pdfa-image-compression=lossless` or use `-O0`
+  ({issue}`1124`).
+- `--pdfa-image-compression=lossless` now passes existing JPEG images through
+  unchanged rather than re-encoding them with a lossless codec. Re-encoding an
+  already-lossy JPEG losslessly cannot recover quality and only inflates the
+  file, so JPEGs are preserved while non-JPEG images are encoded losslessly.
+- OCRmyPDF now validates and repairs malformed page-boundary boxes
+  (``/MediaBox``, ``/CropBox``, ``/TrimBox``, ``/ArtBox``, ``/BleedBox``) in its
+  input, following the PDF 2.0 specification. Coordinates written in invalid
+  exponential notation are reinterpreted ({issue}`1398`); rectangles whose
+  corners are given in reversed order are normalized, which previously crashed
+  with ``NegativeDimensionError`` ({issue}`1526`); and a crop/trim/art/bleed box
+  that falls outside the MediaBox is clamped to their intersection, or discarded
+  when that intersection is empty, which previously produced an output with a
+  zero-height effective page that some viewers refused to open ({issue}`1400`).
+  When a box is discarded, clamped, or reinterpreted, OCRmyPDF logs a warning
+  recommending visual inspection of the output. Thanks @ajdlinux for the initial
+  fix in PR #1691.
+- OCRmyPDF now discards an embedded Adobe full-text search index
+  (``/Root/PieceInfo/SearchIndex``) from its output. This proprietary index,
+  produced by Acrobat's "Embed Index" feature, is read only by Adobe Acrobat;
+  other viewers ignore it and search the text on the fly. Because any change to
+  a PDF invalidates the index, retaining it after OCRmyPDF rewrites the document
+  would leave a stale index that returns incorrect search results in Acrobat.
+  Modern viewers rebuild a search index on demand, so there is no loss of
+  search capability.
+- OCRmyPDF now discards embedded per-page thumbnail images (the optional
+  ``/Thumb`` image XObject on a page) from its output. OCRmyPDF alters page
+  appearance (deskew, clean, rasterize, re-render) and plugins may edit pages
+  arbitrarily, so a retained thumbnail would be stale and no longer match its
+  page. Embedded thumbnails are a navigation aid that modern viewers generate
+  on demand, so there is no loss of functionality.
+- Fixed a regression in OCR quality for PDFs that paint a 1-bit image mask
+  (stencil) with a gray or colored fill color. Previously such pages were
+  rasterized as 1-bit black-and-white before OCR, so Ghostscript dithered
+  mid-tone text into an unreadable stipple and Tesseract failed to recognize
+  it. The rasterizer now inspects the fill color used to paint a mask and
+  promotes the page to grayscale or full color as needed, so the distinction
+  is preserved for the OCR engine. This applies to both the Ghostscript and
+  pypdfium rasterizers. {issue}`1688`
+- The default 1-bit raster device for Ghostscript is now ``pngmonod``
+  (error-diffusion) instead of ``pngmono`` (ordered dithering). It produces
+  better input for OCR on faint or anti-aliased scans at negligible cost and
+  no change to output file size, since the rasterized image is an
+  intermediate that is discarded after OCR.
+- When rasterizing pages with Ghostscript, OCRmyPDF now enables text and
+  graphics anti-aliasing (``-dTextAlphaBits=4 -dGraphicsAlphaBits=4``) for the
+  grayscale and color raster devices. Ghostscript 10.x renders aliased glyphs
+  that OCR frequently misreads as extra word breaks or substituted characters;
+  anti-aliasing materially improves OCR accuracy on the Ghostscript
+  rasterization path, especially for small fonts at moderate resolution. The
+  1-bit monochrome devices are unaffected, since they perform their own
+  anti-aliased downscaling and older Ghostscript versions reject alpha-bit
+  options on them. Note that the default rasterizer (``--rasterizer auto``)
+  prefers pypdfium2, which already anti-aliases; this change benefits users who
+  select ``--rasterizer ghostscript`` or do not have pypdfium2 installed.
+  OCRmyPDF now also logs which rasterizer rendered each page at debug verbosity
+  (``-v 1``), and the ``--rasterizer`` help text explains the OCR-quality
+  trade-off, to make such reports easier to diagnose. {issue}`1439`
+- When Tesseract reports a page with many diacritics, OCRmyPDF still logs its
+  interpreted "lots of diacritics - possibly poor OCR" hint, but now also emits
+  Tesseract's raw message at debug verbosity (``-v 1``) so the original wording
+  is available for diagnosis. {issue}`1566`
+- Added ``--mode strip``, which removes the invisible OCR text layer from a PDF
+  in place. Unlike ``--ocr-engine none --force-ocr``, it does not rasterize the
+  page, so images and visible content are preserved unchanged and the output is
+  smaller rather than larger. Only text drawn as invisible (PDF text render mode
+  3) is removed; some OCR engines -- and OCRmyPDF v2.2 and earlier -- express
+  text as visible glyphs covered by an opaque image, and that text cannot be
+  removed this way. {issue}`1435`
+
+## v17.5.0
+
+- Added support for the ``end`` alias in ``--pages``, denoting the last page
+  of the document. For example, ``--pages 3-end`` OCRs from page 3 through
+  the final page. {issue}`1615`
+- Added ``--ghostscript-jpeg-quality`` and ``--ghostscript-jpeg-maxdpi``
+  advanced options for tuning Ghostscript's PDF/A output. The optimizer's
+  ``--jpeg-quality`` remains the recommended file-size control.
+- Fixed pypdfium2 rasterizer clipping content when the CropBox was smaller
+  than the MediaBox (e.g. JSTOR or cropped PDFs). {issue}`1685`
+- Fixed Form XObject cycle detection in the optimizer's image xref scan.
+  Self-referential or DAG-shaped Form graphs (notably from PowerPoint
+  exports) previously produced floods of recursion warnings and could hang
+  for minutes. {issue}`1321`
+- Tesseract config errors are now surfaced as ``TesseractConfigError`` with
+  actionable guidance, instead of crashing later with a confusing
+  ``FileNotFoundError`` on the missing hOCR output. {issue}`1687`
+- Refreshed the Chinese README translation. Thanks @cislunarspace.
+- Internal refactoring of the ``_exec`` and ``subprocess`` modules to
+  separate probing from execution.
+- CI dependency updates.
+
+## v17.4.2
+
+- Fixed Python API unconditionally overriding ``PIL.Image.MAX_IMAGE_PIXELS``
+  when the caller did not explicitly set ``max_image_mpixels``. Host
+  applications (e.g. Paperless-NGX) that configure the PIL limit before
+  invoking ``ocrmypdf.ocr()`` now have their setting respected. The CLI
+  default of 250 megapixels is unchanged. {issue}`1665`
+- Updated uv.lock to avoid pinning a vulnerable version of Pillow. {issue}`1666`
+
+## v17.4.1
+
+- Fixed RTL text extraction order in the fpdf2 renderer. Arabic lam-alef
+  ligatures and other multi-character CMap entries were garbled by the bidi
+  algorithm during text extraction. {issue}`1655`
+- Fixed ``work_folder`` not being set in ``PdfContext`` options when using
+  the Python API. Thanks @bluebox-steven. {issue}`1613`
+- Updated Ghostscript JPEG corruption warning to include the detected version
+  number, confirming the bug persists in Ghostscript 10.7.0.
+- Internal refactoring.
+- CI dependency updates.
+
+## v17.4.0
+
+- Added ``--no-overwrite`` / ``-n`` option to prevent overwriting output files.
+  If the destination file already exists, OCRmyPDF exits with code 5
+  (``OutputFileAccessError``). {issue}`1642`
+- Fixed text layer stretching in the fpdf2 renderer for widely-spaced words.
+  The horizontal scaling (Tz) was incorrectly stretched to fill inter-word gaps
+  instead of relying on Td positioning, causing text selection to highlight far
+  beyond the actual word boundaries. {issue}`1635`
+- Fixed ``optimize=2`` or ``optimize=3`` crash when using the Python API without
+  explicitly setting ``jpg_quality`` or ``png_quality``. {issue}`1641`
+- Fixed ``verapdf`` availability check crashing with ``NotADirectoryError`` on
+  some platforms. {issue}`1638`
+
+## v17.3.0
+
+- Fixed Python API ignoring the ``language`` parameter, always defaulting to
+  ``eng``. The API now correctly maps ``language`` to OcrOptions ``languages``
+  and splits ``+``-separated codes (e.g. ``eng+deu``) to match CLI behavior.
+  {issue}`1640`
+- Fixed Python API producing empty OCR output because ``tesseract_timeout``
+  defaulted to 0, causing Tesseract to time out immediately. The default is
+  now ``None``, falling back to the plugin's 180-second timeout. {issue}`1636`
+- Fixed OCR text layer displacement on PDFs with non-zero MediaBox origins
+  (e.g. JSTOR or cropped PDFs). The coordinate transformation matrix is now
+  always computed, not skipped when rotation is zero. {issue}`1630`
+- Restored image overlay support (``--image``) for the hocrtransform tool,
+  enabling sandwich PDF output with the fpdf2 renderer. {issue}`1634`
+- Docker: updated Alpine base image to 3.23.
+- Documentation restructured into per-major-version release notes files.
+- Release process improvements.
+
+## v17.2.0
+
+- Fixed incorrect word spacing in poppler-based PDF viewers and tools (Evince,
+  pdftotext, and others) where words on the same line appeared separated by
+  double newlines. This works around a poppler bug where Tz (horizontal scaling)
+  is not carried across BT/ET boundaries. {issue}`1632`
+- Fixed OCR text layer being visible instead of invisible due to incorrect fpdf2
+  text rendering mode attribute. This caused OCR text to appear when images were
+  removed from the PDF. {issue}`1631`
+- Fixed OCR text layer misalignment with non-zero mediabox origins, which
+  affected cropped PDFs and JSTOR PDFs generated by iText. The ``--redo-ocr``
+  mode would shift text vertically on these files. {issue}`1630`
+- Fixed Ghostscript rasterization failure with very low DPI values (below 10).
+  OCRmyPDF now renders at a minimum of 10 DPI and resizes the output to match
+  the originally requested dimensions. {issue}`1612`
+
+## v17.1.0
+
+- Added `--tagged-pdf-mode` to allow skipping the TaggedPDF error message, if desired.
+- Fixed an issue where deflated JPEGs (FlateDecode + DCTDecode) were counted as
+  lossless images for the purpose of determining whether to compress to JPEG,
+  causing file size inflation with some workflows (`--mode force` in particular).
+
+## v17.0.1
+
+- Fixed output file size inflation when using pypdfium as rasterizer and force-ocr
+  mode.
+
+## v17.0.0
+
+**Breaking changes**
+
+- **Plugin interface migration**: Plugin hooks now receive `OcrOptions` objects instead of
+  `argparse.Namespace` objects. Most plugins will continue working due to duck-typing
+  compatibility, but plugin developers should update their type hints from `Namespace`
+  to `OcrOptions`.
+- Built-in plugins no longer modify options in-place, improving immutability and
+  code clarity.
+- **Lossy JBIG2 removed**: The `--jbig2-lossy` and `--jbig2-page-group-size` options have been
+  removed due to well-documented risks of character substitution errors. These options are now
+  deprecated and will emit warnings if used. Only lossless JBIG2 compression is supported.
+- **PDF/A output behavior change**: If neither Ghostscript nor verapdf is installed,
+  `--output-type auto` (the new default) will produce a standard PDF instead of PDF/A. This is
+  a change from previous versions where Ghostscript was required and PDF/A was always produced.
+  This configuration is rare but users should be aware of the change.
+
+**New features**
+
+- **pypdfium2 rasterizer**: Added optional pypdfium2-based PDF rasterization plugin as an
+  alternative to Ghostscript for page rendering. Use `--rasterizer pypdfium` to enable
+  (requires `pip install pypdfium2`). The default `--rasterizer auto` prefers pypdfium when
+  available and falls back to Ghostscript.
+- **Pluggable OCR engines**: New `--ocr-engine` option allows selecting OCR engines:
+  - `auto` (default): Uses Tesseract
+  - `tesseract`: Explicit Tesseract selection
+  - `none`: Skip OCR entirely for PDF processing-only workflows
+
+  This prepares the foundation for future third-party OCR engine plugins.
+- **Smart PDF/A conversion**: New `--output-type auto` (now the default) produces best-effort
+  PDF/A output without requiring Ghostscript when the verapdf validator is available. Falls back
+  to traditional Ghostscript conversion when needed.
+- **verapdf integration**: Added optional verapdf validation for fast PDF/A conversion. When
+  available, OCRmyPDF attempts speculative PDF/A conversion using pikepdf, validates with verapdf,
+  and skips Ghostscript if validation passes.
+- **Optional Ghostscript**: As a consequence of the changes above, Ghostscript is no longer a required dependency. It is optional.
+- **fpdf2 text renderer**: Replaced legacy hOCR text renderer with new fpdf2-based implementation,
+  providing better multilingual support and more accurate text positioning.
+- **Improved Occulta glyphless font**: The new Occulta font provides better handling of
+  zero-width markers and double-width CJK characters for accurate text layer positioning.
+- **Expanded multilingual font support**: Added FontProvider infrastructure with language-aware
+  font selection for Devanagari (Hindi, Sanskrit, Marathi, Nepali), CJK (Chinese, Japanese,
+  Korean), Arabic script, and many other scripts. System font discovery reduces package size.
+- **Simplified mode selection**: New `--mode` (`-m`) argument consolidates processing options:
+  - `default`: Error if text is found (standard behavior)
+  - `force`: Rasterize all content and run OCR (replaces `--force-ocr`)
+  - `skip`: Skip pages with existing text (replaces `--skip-text`)
+  - `redo`: Re-OCR pages, stripping old text layer (replaces `--redo-ocr`)
+
+  Legacy flags remain as silent aliases for backward compatibility.
+
+**API improvements**
+
+- Centralized validation logic in the `OcrOptions` Pydantic model
+- Removed scattered option mutation throughout the codebase
+- Better type safety for plugin development
+- Simplified plugin option handling
+- New `OcrElement`, `OcrClass`, and `BoundingBox` exports for OCR engine plugin developers
+- Extended `OcrEngine` ABC with `generate_ocr()` method for direct OCR tree output, eliding the need to translate a modern engine's output to hOCR or directly write to PDF.
+
+**Bug fixes**
+
+- Fixed double-compression of already-deflated JPEGs.
+- Fixed tesseract_cache plugin to properly handle cache misses.
+- Fixed handling of PDF page boxes (ArtBox, BleedBox) which were not being processed correctly.
+- Added thread safety lock to pypdfium plugin for concurrent operations.
+- Improved pdfminer.six compatibility with explicit word spacing.
+
+**Documentation**
+
+- Updated cookbook to replace deprecated `--tesseract-timeout 0` with `--ocr-engine none`.
+- Added comprehensive plugin documentation for new OCR engine framework.
+
+**Dependency changes**
+
+- Requires: one of `pypdfium2` or `ghostscript` for PDF rasterization (PDF to image)
+  - Preferred: both
+- Requires: one of `verapdf` or `ghostscript` for PDF/A generation
+  - Preferred: both
+- Recommended: `pypdfium2` for PDF rasterization (new dependency)
+- Recommended: `ghostscript` (used to be Required)
+- Recommended: Noto fonts for improved OCR text positioning
+- Optional: `verapdf` for fast PDF/A validation (new dependency)
+- Requires: `fpdf2` for text layer rendering (new dependency)
+- Recommended: replace `typer` with `cyclopts` in misc scripts (new dependency)
+- See docs/maintainers.md for details.
+
+**Migration guide for plugin developers**
+
+- Update imports: `from ocrmypdf._options import OcrOptions`
+- Update type hints: `def check_options(options: OcrOptions)` instead of `options: Namespace`
+- Attribute access remains unchanged: `options.languages`, `options.output_type`, etc.
+- Remove any in-place option modifications - compute values at point of use instead
+- Most existing plugins will continue working without changes due to duck-typing
+
@@ -0,0 +1,240 @@
+# SPDX-FileCopyrightText: 2025 James R. Barlow
+# SPDX-License-Identifier: AGPL-3.0-or-later
+
+"""This is a simple web service/HTTP wrapper for OCRmyPDF.
+
+This may be more convenient than the command line tool for some Docker users.
+Note that OCRmyPDF uses Ghostscript, which is licensed under AGPLv3+. While
+OCRmyPDF is under GPLv3, this file is distributed under the Affero GPLv3+ license,
+to emphasize that SaaS deployments should make sure they comply with
+Ghostscript's license as well as OCRmyPDF's.
+"""
+
+from __future__ import annotations
+
+import os
+import subprocess
+import sys
+from functools import partial
+from operator import getitem
+from pathlib import Path
+from tempfile import NamedTemporaryFile
+
+import pikepdf
+import streamlit as st
+
+from ocrmypdf._defaults import DEFAULT_ROTATE_PAGES_THRESHOLD
+
+
+def get_host_url_with_port(port: int) -> str:
+    """Get the host URL for the web service. Hacky."""
+    host_url = st.context.headers["host"]
+    try:
+        host, _streamlit_port = host_url.split(":", maxsplit=1)
+    except ValueError:
+        host = host_url
+    return f"//{host}:{port}"  # Use the same protocol
+
+
+st.title("OCRmyPDF Web Service")
+
+uploaded = st.file_uploader("Upload input PDF or image", type=["pdf"], key="file")
+
+mode = st.selectbox("Mode", options=["normal", "skip-text", "force-ocr", "redo-ocr"])
+
+pages = st.text_input(
+    "Pages", value="", help="Comma-separated list of pages to process"
+)
+
+with st.expander("Input options"):
+    invalidate_digital_signatures = st.checkbox(
+        "Invalidate digital signatures", value=False
+    )
+    language = st.selectbox("Language", options=["eng", "deu", "fra", "spa"])
+
+    image_dpi = st.slider(
+        "Image DPI", value=300, key="image_dpi", min_value=1, max_value=5000, step=50
+    )
+with st.expander("Preprocessing"):
+    skip_big = st.checkbox("Skip OCR on big pages", value=False, key="skip_big")
+    oversample = st.slider("Oversample", min_value=0, max_value=5000, value=0, step=50)
+    rotate_pages = st.checkbox("Rotate pages", value=False, key="rotate")
+    deskew = st.checkbox("Deskew pages", value=False, key="deskew")
+    clean = st.checkbox("Clean pages before OCR", value=False, key="clean")
+    clean_final = st.checkbox("Clean final", value=False, key="clean_final")
+    remove_vectors = st.checkbox("Remove vectors", value=False, key="remove_vectors")
+
+
+with st.expander("Output options"):
+    output_type = st.selectbox(
+        "Output type", options=["pdfa", "pdf", "pdfa-1", "pdfa-2", "pdfa-3", "none"]
+    )
+
+    pdf_renderer = st.selectbox(
+        "PDF renderer", options=["auto", "hocr", "hocrdebug", "sandwich"]
+    )
+
+    optimize = st.selectbox("Optimize", options=["0", "1", "2", "3"])
+
+    st.selectbox("PDF/A compression", options=["auto", "jpeg", "lossless"])
+
+with st.expander("Metadata"):
+    title = author = keywords = subject = None
+    if uploaded:
+        with pikepdf.open(uploaded) as pdf, pdf.open_metadata() as meta:
+            st.code(str(meta), language="xml")
+            title = st.text_input("Title", value=meta.get('dc:title', ''))
+            author = st.text_input("Author", value=meta.get('dc:creator', ''))
+            keywords = st.text_input("Keywords", value=meta.get('dc:subject', ''))
+            subject = st.text_input("Subject", value=meta.get('dc:description', ''))
+
+
+with st.expander("Optimization after OCR"):
+    jpeg_quality = st.slider(
+        "JPEG quality", min_value=0, max_value=100, value=75, key="jpeg_quality"
+    )
+    png_quality = st.slider(
+        "PNG quality", min_value=0, max_value=100, value=75, key="png_quality"
+    )
+    jbig2_threshold = st.number_input(
+        "JBIG2 threshold", value=0.85, key="jbig2_threshold"
+    )
+
+with st.expander("Advanced options"):
+    jobs = st.slider(
+        "Threads",
+        min_value=1,
+        max_value=os.cpu_count(),
+        value=os.cpu_count(),
+        key="threads",
+    )
+    max_image_mpixels = st.number_input(
+        "Max image size",
+        value=250.0,
+        min_value=0.0,
+        help="Maximum image size in megapixels",
+    )
+    rotate_pages_threshold = st.number_input(
+        "Rotate pages threshold",
+        value=DEFAULT_ROTATE_PAGES_THRESHOLD,
+        min_value=0.0,
+        max_value=1000.0,
+        help="Threshold for automatic page rotation",
+    )
+    fast_web_view = st.number_input(
+        "Fast web view",
+        value=1.0,
+        min_value=0.0,
+        help="Linearize files above this size in MB",
+    )
+    continue_on_soft_render_error = st.checkbox(
+        "Continue on soft render error", value=True
+    )
+    verbose_labels = ["quiet", "default", "debug", "debug_all"]
+    verbose = st.selectbox(
+        "Verbosity level",
+        options=[-1, 0, 1, 2],
+        index=1,
+        format_func=partial(getitem, verbose_labels),
+    )
+
+if uploaded:
+    args = []
+    if mode and mode != 'normal':
+        args.append(f"--{mode}")
+    if language:
+        args.append(f"--language={language}")
+    if not uploaded.name.lower().endswith(".pdf") and image_dpi:
+        args.append(f"--image-dpi={image_dpi}")
+    if skip_big:
+        args.append("--skip-big")
+    if oversample:
+        args.append(f"--oversample={oversample}")
+    if rotate_pages:
+        args.append("--rotate-pages")
+    if deskew:
+        args.append("--deskew")
+    if clean:
+        args.append("--clean")
+    if clean_final:
+        args.append("--clean-final")
+    if remove_vectors:
+        args.append("--remove-vectors")
+    if output_type:
+        args.append(f"--output-type={output_type}")
+    if pdf_renderer:
+        args.append(f"--pdf-renderer={pdf_renderer}")
+    if optimize:
+        args.append(f"--optimize={optimize}")
+    if title:
+        args.append(f"--title={title}")
+    if author:
+        args.append(f"--author={author}")
+    if keywords:
+        args.append(f"--keywords={keywords}")
+    if subject:
+        args.append(f"--subject={subject}")
+    if pages:
+        args.append(f"--pages={pages}")
+    if max_image_mpixels:
+        args.append(f"--max-image-mpixels={max_image_mpixels}")
+    if rotate_pages_threshold:
+        args.append(f"--rotate-pages-threshold={rotate_pages_threshold}")
+    if fast_web_view:
+        args.append(f"--fast-web-view={fast_web_view}")
+    if continue_on_soft_render_error:
+        args.append("--continue-on-soft-render-error")
+    if verbose:
+        args.append(f"--verbose={verbose}")
+    if optimize > '0' and jpeg_quality:
+        args.append(f"--jpeg-quality={jpeg_quality}")
+    if optimize > '0' and png_quality:
+        args.append(f"--png-quality={png_quality}")
+    if jbig2_threshold:
+        args.append(f"--jbig2-threshold={jbig2_threshold}")
+    if jobs:
+        args.append(f"--jobs={jobs}")
+    with NamedTemporaryFile(delete=True, suffix=f"_{uploaded.name}") as input_file:
+        input_file.write(uploaded.getvalue())
+        input_file.flush()
+        input_file.seek(0)
+        args.append(str(input_file.name))
+        with NamedTemporaryFile(delete=True, suffix=".pdf") as output_file:
+            args.append(str(output_file.name))
+
+            st.session_state['running'] = (
+                'run_button' in st.session_state and st.session_state.run_button
+            )
+            if st.button(
+                "Run OCRmyPDF",
+                disabled=st.session_state.get("running", False),
+                key='run_button',
+            ):
+                st.session_state['running'] = True
+                args = [sys.executable, '-u', '-m', "ocrmypdf"] + args
+
+                proc = subprocess.Popen(
+                    args, stdout=subprocess.PIPE, stderr=subprocess.PIPE
+                )
+                with st.container(border=True):
+                    while proc.poll() is None:
+                        line = proc.stderr.readline()
+                        if line:
+                            st.html("<code>" + line.decode().strip() + "</code>")
+
+                if proc.returncode != 0:
+                    st.error(f"ocrmypdf failed with exit code {proc.returncode}")
+                    st.session_state['running'] = False
+                    st.stop()
+
+                if Path(output_file.name).stat().st_size == 0:
+                    st.error("No output PDF file was generated")
+                    st.stop()
+
+                st.download_button(
+                    label="Download output PDF",
+                    data=output_file.read(),
+                    file_name=uploaded.name,
+                    mime="application/pdf",
+                )
+                st.session_state['running'] = False
@@ -16,7 +16,6 @@ from __future__ import annotations

 import filecmp
 import logging
-import os
 import posixpath
 import shutil
 import sys
@@ -39,10 +38,7 @@ script_dir = Path(__file__).parent
 # set archive_dir to a path for backup original documents. Leave empty if not required.
 archive_dir = "/pdfbak"

-if len(sys.argv) > 1:
-    start_dir = Path(sys.argv[1])
-else:
-    start_dir = Path(".")
+start_dir = Path(sys.argv[1]) if len(sys.argv) > 1 else Path()

 if len(sys.argv) > 2:
    log_file = Path(sys.argv[2])
@@ -71,7 +67,7 @@ for filename in start_dir.glob("**/*.pdf"):
            try:
                shutil.copy2(filename, posixpath.dirname(archive_filename))
            except OSError:
-                os.makedirs(posixpath.dirname(archive_filename))
+                Path(posixpath.dirname(archive_filename)).mkdir(parents=True)
                shutil.copy2(filename, posixpath.dirname(archive_filename))
        try:
            result = ocrmypdf.ocr(filename, filename, deskew=True)
@@ -0,0 +1,44 @@
+#!/usr/bin/env python3
+# SPDX-FileCopyrightText: 2024 James R. Barlow
+# SPDX-License-Identifier: MIT
+
+"""Helper script for bisecting PDFs to find a page with an issue."""
+
+from __future__ import annotations
+
+import sys
+
+import pikepdf
+
+if len(sys.argv) != 2:
+    print(f"Usage: {sys.argv[0]} <input.pdf>")
+    sys.exit(1)
+
+with pikepdf.open(sys.argv[1]) as pdf:
+    num_pages = len(pdf.pages)
+    low = 0
+    high = num_pages - 1
+    while low <= high:
+        mid = (low + high) // 2
+        with pikepdf.new() as new_pdf:
+            new_pdf.pages.extend(pdf.pages[low : mid + 1])
+            new_pdf.save(f"bisect-issue-{low + 1}-{mid + 1}.pdf")
+        print(f"Is bisect-issue-{low + 1}-{mid + 1}.pdf good or bad?", end=" ")
+        while True:
+            response = input().lower()
+            if response == "good":
+                low = mid + 1
+                break
+            elif response == "bad":
+                high = mid - 1
+                break
+            else:
+                print("Please respond with 'good' or 'bad'.")
+    print(f"The issue is on page {low + 1} of the original PDF.")
+    with pikepdf.new() as new_pdf:
+        new_pdf.pages.extend(pdf.pages[low])
+        new_pdf.save(f"bisect-issue-bad-{low + 1}.pdf")
+    with pikepdf.new() as new_pdf:
+        new_pdf.pages.extend(pdf.pages[:low])
+        new_pdf.pages.extend(pdf.pages[low + 1 :])
+        new_pdf.save(f"bisect-issue-good-{low + 1}.pdf")
@@ -21,18 +21,18 @@ __ocrmypdf_arguments()
 --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)
+--mode                          (processing mode for pages with existing text)
 --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)
+--tagged-pdf-mode               (control behavior for Tagged PDFs)
 --skip-big                      (skip OCR on pages larger than this many MPixels)
 --optimize                      (select optimization level)
 --jpeg-quality                  (JPEG quality [0..100])
@@ -42,9 +42,14 @@ __ocrmypdf_arguments()
 --pages                         (apply OCR to only the specified pages)
 --max-image-mpixels             (image decompression bomb threshold)
 --pdf-renderer                  (select PDF renderer options)
+--ocr-engine                    (OCR engine to use)
+--rasterizer                    (PDF page rasterizer)
 --rotate-pages-threshold        (page rotation confidence)
 --pdfa-image-compression        (set PDF/A image compression options)
+--ghostscript-jpeg-quality      (Ghostscript JPEG quality during PDF/A [0..100])
+--ghostscript-jpeg-maxdpi       (cap Ghostscript image DPI during PDF/A)
 --fast-web-view                 (if file size if above this amount in MB linearize PDF)
+--continue-on-soft-render-error (continue after recoverable render errors)
 --plugin                        (name of plugin to import)
 --keep-temporary-files          (keep temporary files (debug)
 --tesseract-config              (set custom tesseract config file)
@@ -52,6 +57,10 @@ __ocrmypdf_arguments()
 --tesseract-oem                 (set tesseract --oem)
 --tesseract-thresholding        (set tesseract image thresholding)
 --tesseract-timeout             (maximum number of seconds to wait for OCR)
+--tesseract-non-ocr-timeout     (maximum seconds for non-OCR operations)
+--tesseract-downsample-large-images    (downsample large images before OCR)
+--no-tesseract-downsample-large-images (do not downsample large images)
+--tesseract-downsample-above    (downsample images larger than this pixel size)
 --user-words                    (specify location of user words file)
 --user-patterns                 (specify location of user patterns file)
 --no-progress-bar               (disable the progress bar)
@@ -68,7 +77,8 @@ __ocrmypdf_arguments()

 __ocrmypdf_output-type()
 {
-    local choices="pdfa   (output a PDF/A (default))
+    local choices="auto   (best-effort PDF/A without Ghostscript (default))
+pdfa   (output a PDF/A-2b)
 pdf    (output a standard PDF)
 pdfa-1 (output a PDF/A-1b)
 pdfa-2 (output a PDF/A-2b)
@@ -114,10 +124,11 @@ __ocrmypdf_optimize()

 __ocrmypdf_pdf-renderer()
 {
-    local choices="auto      (auto select PDF renderer)
-hocr      (use hOCR renderer)
-hocrdebug (uses hOCR renderer in debug mode, showing recognized text)
-sandwich  (use sandwich renderer)"
+    local choices="auto      (auto select PDF renderer, uses fpdf2)
+fpdf2     (use fpdf2 renderer with full language support)
+sandwich  (use sandwich renderer)
+hocr      (use hOCR renderer - deprecated)
+hocrdebug (uses hOCR renderer in debug mode - deprecated)"

    COMPREPLY=( $( compgen -W "$choices" -- "$cur") )

@@ -210,6 +221,58 @@ UseDeviceIndependentColor (convert with device independent color)"
    fi
 }

+__ocrmypdf_mode()
+{
+    local choices="default (error if text is found)
+force   (rasterize all content and run OCR)
+skip    (skip pages with existing text)
+redo    (re-OCR pages, replacing old invisible text)"
+
+    COMPREPLY=( $( compgen -W "$choices" -- "$cur") )
+    # Remove description if only one completion exists
+    if [[ ${#COMPREPLY[*]} -eq 1 ]]; then
+        COMPREPLY=( ${COMPREPLY[0]%% *} )
+    fi
+}
+
+__ocrmypdf_tagged-pdf-mode()
+{
+    local choices="default (error if --mode is default, otherwise warn)
+ignore  (always warn but continue processing)"
+
+    COMPREPLY=( $( compgen -W "$choices" -- "$cur") )
+    # Remove description if only one completion exists
+    if [[ ${#COMPREPLY[*]} -eq 1 ]]; then
+        COMPREPLY=( ${COMPREPLY[0]%% *} )
+    fi
+}
+
+__ocrmypdf_ocr-engine()
+{
+    local choices="auto      (select best available engine)
+tesseract (use Tesseract OCR)
+none      (skip OCR entirely)"
+
+    COMPREPLY=( $( compgen -W "$choices" -- "$cur") )
+    # Remove description if only one completion exists
+    if [[ ${#COMPREPLY[*]} -eq 1 ]]; then
+        COMPREPLY=( ${COMPREPLY[0]%% *} )
+    fi
+}
+
+__ocrmypdf_rasterizer()
+{
+    local choices="auto        (prefer pypdfium, fall back to Ghostscript)
+ghostscript (use Ghostscript rasterizer)
+pypdfium    (use pypdfium rasterizer - faster)"
+
+    COMPREPLY=( $( compgen -W "$choices" -- "$cur") )
+    # Remove description if only one completion exists
+    if [[ ${#COMPREPLY[*]} -eq 1 ]]; then
+        COMPREPLY=( ${COMPREPLY[0]%% *} )
+    fi
+}
+
 __ocrmypdf_check_previous()
 {
    case $prev in
@@ -241,6 +304,22 @@ __ocrmypdf_check_previous()
            __ocrmypdf_pdf-renderer
            return 0
            ;;
+        -m|--mode)
+            __ocrmypdf_mode
+            return 0
+            ;;
+        --tagged-pdf-mode)
+            __ocrmypdf_tagged-pdf-mode
+            return 0
+            ;;
+        --ocr-engine)
+            __ocrmypdf_ocr-engine
+            return 0
+            ;;
+        --rasterizer)
+            __ocrmypdf_rasterizer
+            return 0
+            ;;
        --pdfa-image-compression)
            __ocrmypdf_pdfa-image-compression
            return 0
@@ -260,7 +339,9 @@ __ocrmypdf_check_previous()

        --title|--author|--subject|--keywords|--unpaper-args|--pages|--plugin|\
        --jpeg-quality|--png-quality|--image-dpi|--oversample|--skip-big|--max-image-mpixels|\
-        --tesseract-timeout|--rotate-pages-threshold|--fast-web-view)
+        --ghostscript-jpeg-quality|--ghostscript-jpeg-maxdpi|\
+        --tesseract-timeout|--tesseract-non-ocr-timeout|--tesseract-downsample-above|\
+        --rotate-pages-threshold|--fast-web-view)
            # argument required but no completions available
            return 0
            ;;
@@ -11,13 +11,27 @@ complete -c ocrmypdf -s r -l rotate-pages -d "rotate pages to correct orientatio
 complete -c ocrmypdf -s d -l deskew -d "fix small horizontal alignment skew"
 complete -c ocrmypdf -s c -l clean -d "clean document images before OCR"
 complete -c ocrmypdf -s i -l clean-final -d "clean document images and keep result"
+complete -c ocrmypdf -x -l unpaper-args -d "quoted string of arguments to pass to unpaper"
 complete -c ocrmypdf -l remove-vectors -d "don't send vector objects to OCR"

+function __fish_ocrmypdf_mode
+    echo -e "default\t"(_ "error if text is found")
+    echo -e "force\t"(_ "rasterize all content and run OCR")
+    echo -e "skip\t"(_ "skip pages with existing text")
+    echo -e "redo\t"(_ "re-OCR pages, replacing old invisible text")
+end
+complete -c ocrmypdf -x -s m -l mode -a '(__fish_ocrmypdf_mode)' -d "processing mode for pages with existing text"
 complete -c ocrmypdf -s f -l force-ocr -d "OCR documents that already have printable text"
 complete -c ocrmypdf -s s -l skip-text -d "skip OCR on any pages that already contain text"
 complete -c ocrmypdf -l redo-ocr -d "redo OCR on any pages that seem to have OCR already"
 complete -c ocrmypdf -l invalidate-digital-signatures -d "invalidate digital signatures and allow OCR to proceed"

+function __fish_ocrmypdf_tagged_pdf_mode
+    echo -e "default\t"(_ "error if --mode is default, otherwise warn")
+    echo -e "ignore\t"(_ "always warn but continue processing")
+end
+complete -c ocrmypdf -x -l tagged-pdf-mode -a '(__fish_ocrmypdf_tagged_pdf_mode)' -d "control behavior for Tagged PDFs"
+
 complete -c ocrmypdf -s k -l keep-temporary-files -d "keep temporary files (debug)"

 function __fish_ocrmypdf_languages
@@ -32,7 +46,8 @@ complete -c ocrmypdf -x -s l -l language -a '(__fish_ocrmypdf_languages)' -d lan
 complete -c ocrmypdf -x -l image-dpi -d "assume this DPI if input image DPI is unknown"

 function __fish_ocrmypdf_output_type
-    echo -e "pdfa\t"(_ "output a PDF/A (default)")
+    echo -e "auto\t"(_ "best-effort PDF/A without requiring Ghostscript (default)")
+    echo -e "pdfa\t"(_ "output a PDF/A-2b")
    echo -e "pdf\t"(_ "output a standard PDF")
    echo -e "pdfa-1\t"(_ "output a PDF/A-1b")
    echo -e "pdfa-2\t"(_ "output a PDF/A-2b")
@@ -42,13 +57,28 @@ end
 complete -c ocrmypdf -x -l output-type -a '(__fish_ocrmypdf_output_type)' -d "select PDF output options"

 function __fish_ocrmypdf_pdf_renderer
-    echo -e "auto\t"(_ "auto select PDF renderer")
-    echo -e "hocr\t"(_ "use hOCR renderer")
-    echo -e "hocrdebug\t"(_ "uses hOCR renderer in debug mode, showing recognized text")
+    echo -e "auto\t"(_ "auto select PDF renderer (default, uses fpdf2)")
+    echo -e "fpdf2\t"(_ "use fpdf2 renderer with full language support")
    echo -e "sandwich\t"(_ "use sandwich renderer")
+    echo -e "hocr\t"(_ "use hOCR renderer (deprecated)")
+    echo -e "hocrdebug\t"(_ "uses hOCR renderer in debug mode (deprecated)")
 end
 complete -c ocrmypdf -x -l pdf-renderer -a '(__fish_ocrmypdf_pdf_renderer)' -d "select PDF renderer options"

+function __fish_ocrmypdf_ocr_engine
+    echo -e "auto\t"(_ "select best available engine (default)")
+    echo -e "tesseract\t"(_ "use Tesseract OCR")
+    echo -e "none\t"(_ "skip OCR entirely")
+end
+complete -c ocrmypdf -x -l ocr-engine -a '(__fish_ocrmypdf_ocr_engine)' -d "OCR engine to use"
+
+function __fish_ocrmypdf_rasterizer
+    echo -e "auto\t"(_ "prefer pypdfium, fall back to Ghostscript (default)")
+    echo -e "ghostscript\t"(_ "use Ghostscript rasterizer")
+    echo -e "pypdfium\t"(_ "use pypdfium rasterizer (faster)")
+end
+complete -c ocrmypdf -x -l rasterizer -a '(__fish_ocrmypdf_rasterizer)' -d "PDF page rasterizer"
+
 function __fish_ocrmypdf_optimize
    echo -e "0\t"(_ "do not optimize")
    echo -e "1\t"(_ "do safe, lossless optimizations (default)")
@@ -72,6 +102,8 @@ function __fish_ocrmypdf_pdfa_compression
    echo -e "lossless\t"(_ "convert color and grayscale images to lossless (PNG)")
 end
 complete -c ocrmypdf -x -l pdfa-image-compression -a '(__fish_ocrmypdf_pdfa_compression)' -d "set PDF/A image compression options"
+complete -c ocrmypdf -x -l ghostscript-jpeg-quality -d "Ghostscript JPEG quality during PDF/A [0..100]"
+complete -c ocrmypdf -x -l ghostscript-jpeg-maxdpi -d "cap Ghostscript image DPI during PDF/A"

 complete -c ocrmypdf -x -s j -l jobs -d "how many worker processes to use"
 complete -c ocrmypdf -x -l title -d "set metadata"
@@ -124,11 +156,17 @@ end
 complete -c ocrmypdf -x -l tesseract-thresholding -a '(__fish_ocrmypdf_tesseract_thresholding)' -d "set tesseract thresholding method (needs Tesseract 5.x)"

 complete -c ocrmypdf -x -l tesseract-timeout -d "maximum number of seconds to wait for OCR"
+complete -c ocrmypdf -x -l tesseract-non-ocr-timeout -d "maximum seconds to wait for non-OCR operations"
+complete -c ocrmypdf -l tesseract-downsample-large-images -d "downsample large images before OCR"
+complete -c ocrmypdf -l no-tesseract-downsample-large-images -d "do not downsample large images"
+complete -c ocrmypdf -x -l tesseract-downsample-above -d "downsample images larger than this pixel size"
 complete -c ocrmypdf -x -l rotate-pages-threshold -d "page rotation confidence"

 complete -c ocrmypdf -r -l user-words -d "specify location of user words file"
 complete -c ocrmypdf -r -l user-patterns -d "specify location of user patterns file"
 complete -c ocrmypdf -x -l fast-web-view -d "if file size if above this amount in MB, linearize PDF"
+complete -c ocrmypdf -l continue-on-soft-render-error -d "continue processing after recoverable render errors"
+complete -c ocrmypdf -r -l plugin -d "name of plugin to import"

 function __fish_ocrmypdf_color_conversion_strategy
    echo -e "LeaveColorUnchanged\t"(_ "do not convert color spaces (default)")
@@ -6,12 +6,19 @@ services:
  ocrmypdf:
    restart: always
    container_name: ocrmypdf
-    image: jbarlow83/ocrmypdf
+    image: jbarlow83/ocrmypdf-alpine
    volumes:
      - "/media/scan:/input"
      - "/mnt/scan:/output"
    environment:
      - OCR_OUTPUT_DIRECTORY_YEAR_MONTH=0
+    # The image runs as the non-root "app" user (uid 1000) by default. The
+    # correct value here depends on your runtime, so that the watcher can write
+    # to the /output bind mount and the files end up owned by you:
+    #   rootful Docker  -> your host uid:gid
+    #   rootless Docker -> "0:0" (container root maps to your host user)
+    #   Podman          -> your host uid:gid, plus `userns_mode: "keep-id"`
+    # See docs/docker.md ("Bind-mounted volumes") for the reasoning.
    user: "<SET TO YOUR USER ID>:<SET TO YOUR GROUP ID>"
    entrypoint: python3
-    command: watcher.py
+    command: /app/watcher.py
@@ -0,0 +1,63 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<component type="console-application">
+  <id>io.ocrmypdf.ocrmypdf</id>
+
+  <name>OCRmyPDF</name>
+  <summary>Adds an OCR text layer to scanned PDF files, allowing them to be searched</summary>
+
+  <developer id="io.ocrmypdf">
+      <name>OCRmyPDF Developers</name>
+  </developer>
+
+  <url type="homepage">https://github.com/ocrmypdf/ocrmypdf</url>
+  <url type="bugtracker">https://github.com/ocrmypdf/OCRmyPDF/issues</url>
+
+  <content_rating type="oars-1.1" />
+
+  <metadata_license>CC0-1.0</metadata_license>
+  <project_license>MPL-2.0</project_license>
+
+  <description>
+    <ul>
+        <li>Generates a searchable PDF/A file from a regular PDF</li>
+        <li>Places OCR text accurately below the image to ease copy / paste</li>
+        <li>Keeps the exact resolution of the original embedded images</li>
+        <li>When possible, inserts OCR information as a lossless operation without disrupting any other content</li>
+        <li>Optimizes PDF images, often producing files smaller than the input file If requested, deskews and/or cleans the image before performing OCR</li>
+        <li>Validates input and output files</li>
+        <li>Distributes work across all available CPU cores</li>
+        <li>Uses Tesseract OCR engine to recognize more than 100 languages</li>
+        <li>Keeps your private data private</li>
+        <li>Scales properly to handle files with thousands of pages</li>
+        <li>Battle-tested on millions of PDFs</li>
+    </ul>
+  </description>
+
+  <provides>
+    <binary>ocrmypdf</binary>
+  </provides>
+
+  <icon type="stock">io.ocrmypdf.ocrmypdf</icon>
+
+  <screenshots>
+    <screenshot type="default">
+      <image>https://raw.githubusercontent.com/ocrmypdf/OCRmyPDF/f7ad5f16bd0340b0b1803dada0c02f9f40542bd8/misc/flatpak/sample_screenshot.png</image>
+      <caption>Sample usage of OCRmyPDF</caption>
+    </screenshot>
+  </screenshots>
+
+  <categories>
+    <category>Office</category>
+    <category>Utility</category>
+  </categories>
+
+  <keywords>
+    <keyword>ocr</keyword>
+    <keyword>pdf</keyword>
+    <keyword>tool</keyword>
+  </keywords>
+
+  <releases>
+    <release version="16.8.0" date="2025-01-05"/>
+  </releases>
+</component>
@@ -0,0 +1,128 @@
+# SPDX-FileCopyrightText: 2025 James R. Barlow
+# SPDX-License-Identifier: MIT
+
+"""Run OCRmyPDF on the same PDF with different options."""
+
+from __future__ import annotations
+
+import os
+import shlex
+from io import BytesIO
+from pathlib import Path
+from subprocess import check_output, run
+from tempfile import TemporaryDirectory
+
+import pikepdf
+import pymupdf
+import streamlit as st
+from lxml import etree
+from streamlit_pdf_viewer import pdf_viewer
+
+
+def do_column(label, suffix, d):
+    cli = st.text_area(
+        f"Command line arguments for {label}",
+        key=f"args{suffix}",
+        value="ocrmypdf {in_} {out}",
+    )
+    env_text = st.text_area(f"Environment variables for {label}", key=f"env{suffix}")
+    env = os.environ.copy()
+    for line in env_text.splitlines():
+        if line:
+            try:
+                k, v = line.split("=", 1)
+            except ValueError:
+                st.error(f"Invalid environment variable: {line}")
+                break
+            env[k] = v
+    args = shlex.split(
+        cli.format(
+            in_=Path(d) / "input.pdf",
+            out=Path(d) / f"output{suffix}.pdf",
+        )
+    )
+    with st.expander("Environment variables", expanded=bool(env_text.strip())):
+        st.code('\n'.join(f"{k}={v}" for k, v in env.items()))
+    st.code(shlex.join(args))
+    return env, args
+
+
+def main():
+    st.set_page_config(layout="wide")
+
+    st.title("OCRmyPDF Compare")
+    st.write("Run OCRmyPDF on the same PDF with different options.")
+    st.warning("This is a testing tool and is not intended for production use.")
+
+    uploaded_pdf = st.file_uploader("Upload a PDF", type=["pdf"])
+    if uploaded_pdf is None:
+        return
+
+    pdf_bytes = uploaded_pdf.read()
+
+    with pikepdf.open(BytesIO(pdf_bytes)) as p, TemporaryDirectory() as d:
+        with st.expander("PDF Metadata"):
+            with p.open_metadata() as meta:
+                xml_txt = str(meta)
+                parser = etree.XMLParser(remove_blank_text=True)
+                tree = etree.fromstring(xml_txt, parser=parser)
+                st.code(
+                    etree.tostring(tree, pretty_print=True).decode("utf-8"),
+                    language="xml",
+                )
+            st.write(p.docinfo)
+            st.write("Number of pages:", len(p.pages))
+
+        col1, col2 = st.columns(2)
+        with col1:
+            env1, args1 = do_column("A", "1", d)
+        with col2:
+            env2, args2 = do_column("B", "2", d)
+
+        if not st.button("Execute and Compare"):
+            return
+        with st.spinner("Executing..."):
+            Path(d, "input.pdf").write_bytes(pdf_bytes)
+            run(args1, env=env1)
+            run(args2, env=env2)
+
+            col1, col2 = st.columns(2)
+            with col1:
+                st.text(
+                    "Ghostscript version A: "
+                    + check_output(
+                        ["gs", "--version"],
+                        env=env1,
+                        text=True,
+                    )
+                )
+            with col2:
+                st.text(
+                    "Ghostscript version B: "
+                    + check_output(
+                        ["gs", "--version"],
+                        env=env2,
+                        text=True,
+                    )
+                )
+
+            doc1 = pymupdf.open(Path(d, "output1.pdf"))
+            doc2 = pymupdf.open(Path(d, "output2.pdf"))
+            for i, page1_2 in enumerate(zip(doc1, doc2, strict=False)):
+                st.write(f"Page {i + 1}")
+                page1, page2 = page1_2
+                col1, col2 = st.columns(2)
+                with col1, st.container(border=True):
+                    st.write(page1.get_text())
+                with col2, st.container(border=True):
+                    st.write(page2.get_text())
+
+            col1, col2 = st.columns(2)
+            with col1, st.expander("PDF Viewer"):
+                pdf_viewer(Path(d, "output1.pdf"))
+            with col2, st.expander("PDF Viewer"):
+                pdf_viewer(Path(d, "output2.pdf"))
+
+
+if __name__ == "__main__":
+    main()
@@ -0,0 +1,82 @@
+# SPDX-FileCopyrightText: 2025 James R. Barlow
+# SPDX-License-Identifier: MIT
+
+"""Compare two PDFs."""
+
+from __future__ import annotations
+
+from io import BytesIO
+from pathlib import Path
+from tempfile import TemporaryDirectory
+
+import pikepdf
+import pymupdf
+import streamlit as st
+from lxml import etree
+from streamlit_pdf_viewer import pdf_viewer
+
+
+def do_metadata(pdf):
+    with pikepdf.open(pdf) as pdf:
+        with pdf.open_metadata() as meta:
+            xml_txt = str(meta)
+            parser = etree.XMLParser(remove_blank_text=True)
+            tree = etree.fromstring(xml_txt, parser=parser)
+            st.code(
+                etree.tostring(tree, pretty_print=True).decode("utf-8"),
+                language="xml",
+            )
+        st.write(pdf.docinfo)
+        st.write("Number of pages:", len(pdf.pages))
+
+
+def main():
+    st.set_page_config(layout="wide")
+
+    st.title("PDF Compare")
+    st.write("Compare two PDFs.")
+
+    col1, col2 = st.columns(2)
+    with col1:
+        uploaded_pdf1 = st.file_uploader("Upload a PDF", type=["pdf"], key='pdf1')
+    with col2:
+        uploaded_pdf2 = st.file_uploader("Upload a PDF", type=["pdf"], key='pdf2')
+    if uploaded_pdf1 is None or uploaded_pdf2 is None:
+        return
+
+    pdf_bytes1 = uploaded_pdf1.getvalue()
+    pdf_bytes2 = uploaded_pdf2.getvalue()
+
+    with st.expander("PDF Metadata"):
+        col1, col2 = st.columns(2)
+        with col1:
+            do_metadata(BytesIO(pdf_bytes1))
+        with col2:
+            do_metadata(BytesIO(pdf_bytes2))
+
+    with TemporaryDirectory() as d:
+        Path(d, "1.pdf").write_bytes(pdf_bytes1)
+        Path(d, "2.pdf").write_bytes(pdf_bytes2)
+
+        with st.expander("Text"):
+            doc1 = pymupdf.open(Path(d, "1.pdf"))
+            doc2 = pymupdf.open(Path(d, "2.pdf"))
+            for i, page1_2 in enumerate(zip(doc1, doc2, strict=False)):
+                st.write(f"Page {i + 1}")
+                page1, page2 = page1_2
+                col1, col2 = st.columns(2)
+                with col1, st.container(border=True):
+                    st.write(page1.get_text())
+                with col2, st.container(border=True):
+                    st.write(page2.get_text())
+
+        with st.expander("PDF Viewer"):
+            col1, col2 = st.columns(2)
+            with col1:
+                pdf_viewer(Path(d, "1.pdf"), key='pdf_viewer1', render_text=True)
+            with col2:
+                pdf_viewer(Path(d, "2.pdf"), key='pdf_viewer2', render_text=True)
+
+
+if __name__ == "__main__":
+    main()
@@ -0,0 +1,57 @@
+# SPDX-FileCopyrightText: 2025 James R. Barlow
+# SPDX-License-Identifier: MPL-2.0
+
+"""Compare text in PDFs."""
+
+from __future__ import annotations
+
+from pathlib import Path
+from subprocess import run
+from tempfile import NamedTemporaryFile
+from typing import Annotated
+
+import cyclopts
+
+app = cyclopts.App()
+
+
+@app.default
+def main(
+    pdf1: Annotated[Path, cyclopts.Parameter()],
+    pdf2: Annotated[Path, cyclopts.Parameter()],
+    *,
+    engine: Annotated[str, cyclopts.Parameter()] = 'pdftotext',
+):
+    """Compare text in PDFs."""
+    with pdf1.open('rb') as f1, pdf2.open('rb') as f2:
+        text1 = run(
+            ['pdftotext', '-layout', '-', '-'],
+            stdin=f1,
+            capture_output=True,
+            check=True,
+        )
+        text2 = run(
+            ['pdftotext', '-layout', '-', '-'],
+            stdin=f2,
+            capture_output=True,
+            check=True,
+        )
+
+    with NamedTemporaryFile() as t1, NamedTemporaryFile() as t2:
+        t1.write(text1.stdout)
+        t1.flush()
+        t2.write(text2.stdout)
+        t2.flush()
+        diff = run(
+            ['diff', '--color=always', '--side-by-side', t1.name, t2.name],
+            capture_output=True,
+        )
+        run(['less', '-R'], input=diff.stdout, check=True)
+        if text1.stdout.strip() != text2.stdout.strip():
+            return 1
+
+    return 0
+
+
+if __name__ == '__main__':
+    app()
@@ -60,6 +60,6 @@
 [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"]
+[8.291209, "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"]
@@ -13,13 +13,14 @@ import shutil
 import subprocess
 import sys
 import time
+from pathlib import Path

 # pylint: disable=logging-format-interpolation
 # pylint: disable=logging-not-lazy

-script_dir = os.path.dirname(os.path.realpath(__file__))
+script_dir = Path(os.path.realpath(__file__)).parent
 timestamp = time.strftime("%Y-%m-%d-%H%M_")
-log_file = script_dir + '/' + timestamp + 'ocrmypdf.log'
+log_file = script_dir / (timestamp + 'ocrmypdf.log')
 logging.basicConfig(
    level=logging.INFO,
    format='%(asctime)s %(message)s',
@@ -33,10 +34,10 @@ for dir_name, _subdirs, file_list in os.walk(start_dir):
    logging.info(dir_name)
    os.chdir(dir_name)
    for filename in file_list:
-        file_stem, file_ext = os.path.splitext(filename)
+        file_stem, file_ext = Path(filename).stem, Path(filename).suffix
        if file_ext != '.pdf':
            continue
-        full_path = os.path.join(dir_name, filename)
+        full_path = Path(dir_name, filename)
        timestamp_ocr = time.strftime("%Y-%m-%d-%H%M_OCR_")
        filename_ocr = timestamp_ocr + file_stem + '.pdf'
        # create string for pdf processing
@@ -52,10 +53,10 @@ for dir_name, _subdirs, file_list in os.walk(start_dir):
            '-',
        ]
        logging.info(cmd)
-        full_path_ocr = os.path.join(dir_name, filename_ocr)
+        full_path_ocr = Path(dir_name, filename_ocr)
        with (
-            open(filename, 'rb') as input_file,
-            open(full_path_ocr, 'wb') as output_file,
+            Path(filename).open('rb') as input_file,
+            full_path_ocr.open('wb') as output_file,
        ):
            proc = subprocess.run(
                cmd,
@@ -67,8 +68,8 @@ for dir_name, _subdirs, file_list in os.walk(start_dir):
                errors='ignore',
            )
        logging.info(proc.stderr)
-        os.chmod(full_path_ocr, 0o664)
-        os.chmod(full_path, 0o664)
+        full_path_ocr.chmod(0o664)
+        full_path.chmod(0o664)
        full_path_ocr_archive = sys.argv[2]
        full_path_archive = sys.argv[2] + '/no_ocr'
        shutil.move(full_path_ocr, full_path_ocr_archive)
@@ -5,21 +5,20 @@

 """Watch a directory for new PDFs and OCR them."""

-# Do not enable annotations!
-# https://github.com/tiangolo/typer/discussions/598
+from __future__ import annotations

+import datetime as dt
 import json
 import logging
 import shutil
 import sys
 import time
-from datetime import datetime
-from enum import Enum
+from enum import StrEnum
 from pathlib import Path
 from typing import Annotated, Any

+import cyclopts
 import pikepdf
-import typer
 from dotenv import load_dotenv
 from watchdog.events import PatternMatchingEventHandler
 from watchdog.observers import Observer
@@ -31,12 +30,12 @@ load_dotenv()


 # pylint: disable=logging-format-interpolation
-app = typer.Typer(name="ocrmypdf-watcher")
+app = cyclopts.App(name="ocrmypdf-watcher")

 log = logging.getLogger('ocrmypdf-watcher')


-class LoggingLevelEnum(str, Enum):
+class LoggingLevelEnum(StrEnum):
    """Enum for logging levels."""

    DEBUG = "DEBUG"
@@ -49,7 +48,7 @@ class LoggingLevelEnum(str, Enum):
 def get_output_path(root: Path, basename: str, output_dir_year_month: bool) -> Path:
    assert '/' not in basename, "basename must not contain '/'"
    if output_dir_year_month:
-        today = datetime.today()
+        today = dt.datetime.today()
        output_directory_year_month = root / str(today.year) / f'{today.month:02d}'
        if not output_directory_year_month.exists():
            output_directory_year_month.mkdir(parents=True, exist_ok=True)
@@ -115,9 +114,11 @@ def execute_ocrmypdf(
        f'kwargs: {ocrmypdf_kwargs}'
    )
    exit_code = ocrmypdf.ocr(
-        input_file=file_path,
-        output_file=output_path,
-        **ocrmypdf_kwargs,
+        ocrmypdf.OcrOptions(
+            input_file=file_path,
+            output_file=output_path,
+            **ocrmypdf_kwargs,
+        )
    )
    if exit_code == 0:
        if on_success_delete:
@@ -139,7 +140,7 @@ class HandleObserverEvent(PatternMatchingEventHandler):
        ignore_patterns=None,
        ignore_directories=False,
        case_sensitive=False,
-        settings={},
+        settings=None,
    ):
        super().__init__(
            patterns=patterns,
@@ -147,117 +148,101 @@ class HandleObserverEvent(PatternMatchingEventHandler):
            ignore_directories=ignore_directories,
            case_sensitive=case_sensitive,
        )
-        self._settings = settings
+        self._settings = settings if settings else {}

    def on_any_event(self, event):
        if event.event_type in ['created']:
            execute_ocrmypdf(file_path=Path(event.src_path), **self._settings)


-@app.command()
+@app.default
 def main(
    input_dir: Annotated[
        Path,
-        typer.Argument(
-            envvar='OCR_INPUT_DIRECTORY',
-            exists=True,
-            file_okay=False,
-            dir_okay=True,
-            readable=True,
-            resolve_path=True,
+        cyclopts.Parameter(
+            env_var='OCR_INPUT_DIRECTORY',
        ),
-    ] = '/input',
+    ] = Path('/input'),
    output_dir: Annotated[
        Path,
-        typer.Argument(
-            envvar='OCR_OUTPUT_DIRECTORY',
-            exists=True,
-            file_okay=False,
-            dir_okay=True,
-            writable=True,
-            resolve_path=True,
+        cyclopts.Parameter(
+            env_var='OCR_OUTPUT_DIRECTORY',
        ),
-    ] = '/output',
+    ] = Path('/output'),
    archive_dir: Annotated[
        Path,
-        typer.Argument(
-            envvar='OCR_ARCHIVE_DIRECTORY',
-            exists=True,
-            file_okay=False,
-            dir_okay=True,
-            writable=True,
-            resolve_path=True,
+        cyclopts.Parameter(
+            env_var='OCR_ARCHIVE_DIRECTORY',
        ),
-    ] = '/processed',
+    ] = Path('/processed'),
+    *,
    output_dir_year_month: Annotated[
        bool,
-        typer.Option(
-            envvar='OCR_OUTPUT_DIRECTORY_YEAR_MONTH',
+        cyclopts.Parameter(
+            env_var='OCR_OUTPUT_DIRECTORY_YEAR_MONTH',
            help='Create a subdirectory in the output directory for each year/month',
        ),
    ] = False,
    on_success_delete: Annotated[
        bool,
-        typer.Option(
-            envvar='OCR_ON_SUCCESS_DELETE',
+        cyclopts.Parameter(
+            env_var='OCR_ON_SUCCESS_DELETE',
            help='Delete the input file after successful OCR',
        ),
    ] = False,
    on_success_archive: Annotated[
        bool,
-        typer.Option(
-            envvar='OCR_ON_SUCCESS_ARCHIVE',
+        cyclopts.Parameter(
+            env_var='OCR_ON_SUCCESS_ARCHIVE',
            help='Archive the input file after successful OCR',
        ),
    ] = False,
    deskew: Annotated[
        bool,
-        typer.Option(
-            envvar='OCR_DESKEW',
+        cyclopts.Parameter(
+            env_var='OCR_DESKEW',
            help='Deskew the input file before OCR',
        ),
    ] = False,
    ocr_json_settings: Annotated[
-        str,
-        typer.Option(
-            envvar='OCR_JSON_SETTINGS',
+        str | None,
+        cyclopts.Parameter(
+            env_var='OCR_JSON_SETTINGS',
            help='JSON settings to pass to OCRmyPDF (JSON string or file path)',
        ),
    ] = None,
    poll_new_file_seconds: Annotated[
        int,
-        typer.Option(
-            envvar='OCR_POLL_NEW_FILE_SECONDS',
+        cyclopts.Parameter(
+            env_var='OCR_POLL_NEW_FILE_SECONDS',
            help='Seconds to wait before polling a new file',
-            min=0,
        ),
    ] = 1,
    use_polling: Annotated[
        bool,
-        typer.Option(
-            envvar='OCR_USE_POLLING',
+        cyclopts.Parameter(
+            env_var='OCR_USE_POLLING',
            help='Use polling instead of filesystem events',
        ),
    ] = False,
    retries_loading_file: Annotated[
        int,
-        typer.Option(
-            envvar='OCR_RETRIES_LOADING_FILE',
+        cyclopts.Parameter(
+            env_var='OCR_RETRIES_LOADING_FILE',
            help='Number of times to retry loading a file before giving up',
-            min=0,
        ),
    ] = 5,
    loglevel: Annotated[
        LoggingLevelEnum,
-        typer.Option(
-            envvar='OCR_LOGLEVEL',
+        cyclopts.Parameter(
+            env_var='OCR_LOGLEVEL',
            help='Logging level',
        ),
    ] = LoggingLevelEnum.INFO,
    patterns: Annotated[
        str,
-        typer.Option(
-            envvar='OCR_PATTERNS',
+        cyclopts.Parameter(
+            env_var='OCR_PATTERNS',
            help='File patterns to watch',
        ),
    ] = '*.pdf,*.PDF',
@@ -278,11 +263,11 @@ def main(
        f"Output Directory Year & Month: {output_dir_year_month}\n"
        f"Archive Directory: {archive_dir}"
    )
-    log.debug(
+    log.info(
        f"INPUT_DIRECTORY: {input_dir}\n"
        f"OUTPUT_DIRECTORY: {output_dir}\n"
-        f"OUTPUT_DIRECTORY_YEAR_MONTH: {output_dir_year_month}\n"
        f"ARCHIVE_DIRECTORY: {archive_dir}\n"
+        f"OUTPUT_DIRECTORY_YEAR_MONTH: {output_dir_year_month}\n"
        f"ON_SUCCESS_DELETE: {on_success_delete}\n"
        f"ON_SUCCESS_ARCHIVE: {on_success_archive}\n"
        f"DESKEW: {deskew}\n"
@@ -317,13 +302,10 @@ def main(
            'output_dir_year_month': output_dir_year_month,
        },
    )
-    if use_polling:
-        observer = PollingObserver()
-    else:
-        observer = Observer()
+    observer = PollingObserver() if use_polling else Observer()
    observer.schedule(handler, input_dir, recursive=True)
    observer.start()
-    typer.echo(f"Watching {input_dir} for new PDFs. Press Ctrl+C to exit.")
+    print(f"Watching {input_dir} for new PDFs. Press Ctrl+C to exit.")
    try:
        while True:
            time.sleep(30)
@@ -1,107 +1,31 @@
-#!/usr/bin/env python3
-# SPDX-FileCopyrightText: 2019 James R. Barlow
+#!/usr/bin/env python
+# SPDX-FileCopyrightText: 2025 James R. Barlow
 # SPDX-License-Identifier: AGPL-3.0-or-later

-"""This is a simple web service/HTTP wrapper for OCRmyPDF.
-
-This may be more convenient than the command line tool for some Docker users.
-Note that OCRmyPDF uses Ghostscript, which is licensed under AGPLv3+. While
-OCRmyPDF is under GPLv3, this file is distributed under the Affero GPLv3+ license,
-to emphasize that SaaS deployments should make sure they comply with
-Ghostscript's license as well as OCRmyPDF's.
-"""
+"""Run the OCRmyPDF web service."""

 from __future__ import annotations

 import os
-import shlex
-from subprocess import run
-from tempfile import TemporaryDirectory
+import sys

-from flask import Flask, Response, request, send_from_directory
-from werkzeug.utils import secure_filename
+try:
+    import streamlit  # noqa: F401
+except ImportError:
+    raise ImportError(
+        'You need to install streamlit in the Python environment '
+        'to run the web service.\n'
+    ) from None

-app = Flask(__name__)
-app.secret_key = "secret"
-app.config['MAX_CONTENT_LENGTH'] = 50_000_000
-app.config.from_envvar("OCRMYPDF_WEBSERVICE_SETTINGS", silent=True)
-
-ALLOWED_EXTENSIONS = {"pdf"}
-
-
-def allowed_file(filename):
-    return "." in filename and filename.rsplit(".", 1)[1].lower() in ALLOWED_EXTENSIONS
-
-
-def do_ocrmypdf(file):
-    uploaddir = TemporaryDirectory(prefix="ocrmypdf-upload")
-    downloaddir = TemporaryDirectory(prefix="ocrmypdf-download")
-
-    filename = secure_filename(file.filename)
-    up_file = os.path.join(uploaddir.name, filename)
-    file.save(up_file)
-
-    down_file = os.path.join(downloaddir.name, filename)
-
-    cmd_args = [arg for arg in shlex.split(request.form["params"])]
-    if "--sidecar" in cmd_args:
-        return Response("--sidecar not supported", 501, mimetype='text/plain')
-
-    ocrmypdf_args = ["ocrmypdf", *cmd_args, up_file, down_file]
-    proc = run(ocrmypdf_args, capture_output=True, encoding="utf-8", check=False)
-    if proc.returncode != 0:
-        stderr = proc.stderr
-        return Response(stderr, 400, mimetype='text/plain')
-
-    return send_from_directory(downloaddir.name, filename)
-
-
-@app.route("/", methods=["GET", "POST"])
-def upload_file():
-    if request.method == "POST":
-        if "file" not in request.files:
-            return Response("No file in POST", 400, mimetype='text/plain')
-        file = request.files["file"]
-        if file.filename == "":
-            return Response("Empty filename", 400, mimetype='text/plain')
-        if not allowed_file(file.filename):
-            return Response("Invalid filename", 400, mimetype='text/plain')
-        if file and allowed_file(file.filename):
-            return do_ocrmypdf(file)
-        return Response("Some other problem", 400, mimetype='text/plain')
-
-    return """
-    <!doctype html>
-    <title>OCRmyPDF webservice</title>
-    <h1>Upload a PDF (debug UI)</h1>
-    <form method=post enctype=multipart/form-data>
-      <label for="args">Command line parameters</label>
-      <input type=textbox name=params>
-      <label for="file">File to upload</label>
-      <input type=file name=file>
-      <input type=submit value=Upload>
-    </form>
-    <h4>Notice</h2>
-    <div style="font-size: 70%; max-width: 34em;">
-    <p>This is a webservice wrapper for OCRmyPDF.</p>
-    <p>Copyright 2019 James R. Barlow</p>
-    <p>This program is free software: you can redistribute it and/or modify
-    it under the terms of the GNU Affero General Public License as published by
-    the Free Software Foundation, either version 3 of the License, or
-    (at your option) any later version.
-    </p>
-    <p>This program is distributed in the hope that it will be useful,
-    but WITHOUT ANY WARRANTY; without even the implied warranty of
-    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-    GNU General Public License for more details.
-    </p>
-    <p>
-    You should have received a copy of the GNU Affero General Public License
-    along with this program.  If not, see &lt;http://www.gnu.org/licenses/&gt;.
-    </p>
-    </div>
-    """
-
-
-if __name__ == "__main__":
-    app.run(host='0.0.0.0', port=5000)
+if __name__ == '__main__':
+    os.execvp(
+        sys.executable,
+        [
+            sys.executable,
+            '-m',
+            'streamlit',
+            'run',
+            'misc/_webservice.py',
+            *sys.argv[1:],
+        ],
+    )
@@ -0,0 +1,64 @@
+# prek pre-commit configuration — https://prek.j178.dev
+#
+# The local/system hooks below invoke the project's OWN pinned tools (ruff/mypy
+# from uv.lock) and mirror .github/workflows/build.yml's lint job exactly, so
+# they can never drift from CI's versions or rules. prek installs nothing of
+# its own for them — "system" language just execs whatever `uv run` resolves.
+#
+# The pre-commit/pre-commit-hooks repo hooks below are generic file checks with
+# no project-local tool equivalent, so they're kept as a normal (non-local) repo.
+#
+# Run all checks manually: `uv run prek run --all-files`
+# Install the git hooks:   `uv run prek install`
+
+default_install_hook_types = ["pre-commit", "pre-push"]
+default_stages = ["pre-commit"]
+
+[[repos]]
+repo = "https://github.com/pre-commit/pre-commit-hooks"
+rev = "v4.4.0"
+
+[[repos.hooks]]
+id = "check-case-conflict"
+
+[[repos.hooks]]
+id = "check-merge-conflict"
+
+[[repos.hooks]]
+id = "check-toml"
+
+[[repos.hooks]]
+id = "check-yaml"
+
+[[repos.hooks]]
+id = "debug-statements"
+
+[[repos]]
+repo = "local"
+
+[[repos.hooks]]
+id = "ruff-format"
+name = "ruff format (check)"
+language = "system"
+entry = "uv run ruff format --check ."
+types = ["python"]
+pass_filenames = false
+require_serial = true
+
+[[repos.hooks]]
+id = "ruff-check"
+name = "ruff check"
+language = "system"
+entry = "uv run ruff check ."
+types = ["python"]
+pass_filenames = false
+require_serial = true
+
+[[repos.hooks]]
+id = "mypy"
+name = "mypy"
+language = "system"
+entry = "uv run mypy src/ocrmypdf"
+types = ["python"]
+pass_filenames = false
+require_serial = true
@@ -1,26 +1,30 @@
 # SPDX-FileCopyrightText: 2022 James R. Barlow
 # SPDX-License-Identifier: MPL-2.0
 [build-system]
-requires = ["setuptools >= 61", "setuptools_scm[toml] >= 7.0.5", "wheel"]
-build-backend = "setuptools.build_meta"
+requires = ["hatchling"]
+build-backend = "hatchling.build"

 [project]
 name = "ocrmypdf"
-dynamic = ["version"]
+version = "17.9.0"
 description = "OCRmyPDF adds an OCR text layer to scanned PDF files, allowing them to be searched"
 readme = "README.md"
-license = { text = "MPL-2.0" }
-requires-python = ">=3.10"
+license = "MPL-2.0"
+requires-python = ">=3.11"
 dependencies = [
-  "deprecation>=2.1.0",
+  "fpdf2>=2.8.0",
  "img2pdf>=0.5",
  "packaging>=20",
-  "pdfminer.six>=20220319",
+  "pdfminer.six>=20260107",  # fixes parsing of tokens split across the read buffer/streams (gh #1361)
  "pi-heif",                # Heif image format - maintainers: if this is removed, it will NOT break
-  "pikepdf>=8.10.1",
+  "pikepdf>=10",
  "Pillow>=10.0.1",
  "pluggy>=1",
+  "pydantic>=2.12.5",
+  "pypdfium2>=5.0.0",
  "rich>=13",
+  "typing-extensions>=4.12; python_version < '3.13'",
+  "uharfbuzz>=0.53.2",
 ]
 authors = [{ name = "James R. Barlow", email = "james@purplerock.ca" }]
 classifiers = [
@@ -29,7 +33,6 @@ classifiers = [
  "Intended Audience :: End Users/Desktop",
  "Intended Audience :: Science/Research",
  "Intended Audience :: System Administrators",
-  "License :: OSI Approved :: Mozilla Public License 2.0 (MPL 2.0)",
  "Operating System :: MacOS",
  "Operating System :: Microsoft :: Windows",
  "Operating System :: POSIX",
@@ -46,38 +49,18 @@ keywords = ["PDF", "OCR", "optical character recognition", "PDF/A", "scanning"]
 Documentation = "https://ocrmypdf.readthedocs.io/"
 Source = "https://github.com/ocrmypdf/OCRmyPDF"
 Tracker = "https://github.com/ocrmypdf/OCRmyPDF/issues"
+Changelog = "https://github.com/ocrmypdf/OCRmyPDF/tree/main/docs/releasenotes"

 [project.optional-dependencies]
-docs = ["sphinx", "sphinx-issues", "sphinx-rtd-theme"]
-extended_test = ["PyMuPDF>=1.19.1"]
-test = [
-  "coverage[toml]>=6.2",
-  "hypothesis>=6.36.0",
-  "pytest>=6.2.5",
-  "pytest-cov>=3.0.0",
-  "pytest-xdist>=2.5.0",
-  "python-xmp-toolkit==2.0.1", # also requires apt-get install libexempi3
-  "reportlab>=3.6.8",
-  "types-Pillow",
-  "types-humanfriendly",
-]
-watcher = ["watchdog>=1.0.2", "typer-slim[standard]", "python-dotenv"]
-webservice = ["Flask>=2.0.1"]
+# User-installable features - use `uv sync --extra <name>` or `pip install ocrmypdf[name]`
+watcher = ["watchdog>=1.0.2", "cyclopts>=3", "python-dotenv"]
+webservice = ["streamlit>=1.41.0"]

 [project.scripts]
 ocrmypdf = "ocrmypdf.__main__:run"

-[tool.setuptools.package-data]
-ocrmypdf = ["data/sRGB.icc", "py.typed"]
-
-[tool.setuptools.packages.find]
-where = ["src"]
-namespaces = false
-
-[tool.setuptools_scm]
-
 [tool.distutils.bdist_wheel]
-python-tag = "py310"
+python-tag = "py311"

 [tool.coverage.run]
 branch = true
@@ -105,7 +88,6 @@ exclude_lines = [

 [tool.pytest.ini_options]
 minversion = "6.0"
-norecursedirs = ["lib", ".pc", ".git", "venv", "output", "cache", "resources"]
 testpaths = ["tests"]
 addopts = "-n auto"
 markers = ["slow"]
@@ -116,44 +98,105 @@ filterwarnings = [
 ]

 [tool.mypy]
+check_untyped_defs = true

 [[tool.mypy.overrides]]
 module = [
-  'pluggy',
-  'tqdm',
-  'coloredlogs',
  'img2pdf',
  'pdfminer.*',
  'reportlab.*',
  'fitz',
  'libxmp.utils',
+  'pypdfium2',
+  'uharfbuzz',
+  'pi_heif',
 ]
 ignore_missing_imports = true

+[[tool.mypy.overrides]]
+# Test functions are not required to annotate their return type (almost
+# always None); it's a low-value hint that would just be noise here.
+module = 'tests.*'
+disallow_untyped_defs = false
+disallow_incomplete_defs = false
+
 [tool.ruff]
-target-version = "py310"
+target-version = "py311"
+exclude = ["src/ocrmypdf/_version.py"] # Autogenerated

 [tool.ruff.lint]
 "select" = [
-  "D",    # pydocstyle
-  "E",    # pycodestyle
-  "W",    # pycodestyle
-  "F",    # pyflakes
-  "I001", # isort
-  "UP",   # pyupgrade
+  "D",   # pydocstyle
+  "E",   # pycodestyle
+  "W",   # pycodestyle
+  "F",   # pyflakes
+  "I",   # isort
+  "UP",  # pyupgrade
+  "SIM", # simplify
+  "B",   # flake8-bugbear
+  "ICN", # flake8-import-conventions
+  "PTH", # flake8-use-pathlib
+]
+ignore = [
+  "B028", # warning with no explicit stacklevel
+  # rule is key in dict instead of key in dict.keys(); but pikepdf semantics differ
+  "SIM118",
 ]

 [tool.ruff.lint.isort]
 known-first-party = ["ocrmypdf"]
+required-imports = ["from __future__ import annotations"]
+
+[tool.ruff.lint.flake8-import-conventions]
+# Prohibit explicit imports from the 'datetime' module
+banned-from = ["datetime"]
+# Optionally, suggest an alias for 'import datetime' (e.g., as dt)
+extend-aliases = { "datetime" = "dt" }

 [tool.ruff.lint.pydocstyle]
 convention = "google"

 [tool.ruff.lint.per-file-ignores]
 "docs/conf.py" = ["D100", "D101", "D105"]
-"tests/*.py" = ["D100", "D101", "D102", "D103", "D105"]
+"tests/*.py" = ["D100", "D101", "D102", "D103", "D105", "E501"]
 "misc/*.py" = ["D103", "D101", "D102"]
 "src/ocrmypdf/builtin_plugins/*.py" = ["D103", "D102", "D105"]

 [tool.ruff.format]
 quote-style = "preserve"
+
+[dependency-groups]
+# Developer-only tools - use `uv sync --group <name>`
+dev = [
+    "mypy>=1.13.0",
+    "ruff>=0.14.11",
+    "prek>=0.4.8",
+    "ipykernel>=6.29.5",
+    "reportlab>=4.4.4",
+    "cyclopts>=4.5.1",
+    "pygithub>=2.9.1",
+]
+test = [
+  # Core testing framework
+  "coverage[toml]>=6.2",
+  "hypothesis>=6.36.0",
+  "pytest>=6.2.5",
+  "pytest-cov>=3.0.0",
+  "pytest-xdist>=2.5.0",
+  # Test dependencies
+  "python-xmp-toolkit==2.0.1", # also requires apt-get install libexempi3
+  "reportlab>=3.6.8",
+  # Type stubs for testing
+  "types-humanfriendly",
+  # Extended test capabilities (merged from extended_test)
+  "pymupdf>=1.24.14",
+]
+docs = [
+  "myst-parser>=4.0.1",
+  "sphinx",
+  "sphinx-issues",
+  "sphinx-reredirects",
+  "sphinx-rtd-theme",
+  "sphinxcontrib-mermaid",
+]
+streamlit-dev = ["streamlit>=1.40.2", "streamlit-pdf-viewer>=0.0.19"]
@@ -0,0 +1,231 @@
+#!/usr/bin/env python3
+# SPDX-FileCopyrightText: 2024 James R. Barlow
+# SPDX-License-Identifier: MPL-2.0
+
+"""Generate the Occulta glyphless font for OCRmyPDF.
+
+Occulta (Latin for "hidden") is a glyphless font designed for invisible text layers
+in searchable PDFs. It has proper Unicode cmap coverage using format 13 (many-to-one)
+for efficient mapping of all BMP codepoints to a small set of width-specific glyphs.
+
+Features:
+- Full BMP coverage (U+0000 to U+FFFF)
+- Width-aware glyphs for proper text selection:
+  - Zero-width for combining marks and invisible characters
+  - Regular width (500 units) for Latin, Greek, Cyrillic, Arabic, Hebrew, etc.
+  - Double width (1000 units) for CJK and fullwidth characters
+- Uses cmap format 13 (many-to-one) for ~12KB size vs ~780KB with format 12
+- Compatible with fpdf2 and other modern PDF libraries
+
+Usage:
+    python scripts/generate_glyphless_font.py
+
+Output:
+    src/ocrmypdf/data/Occulta.ttf
+"""
+
+from __future__ import annotations
+
+import unicodedata
+from pathlib import Path
+
+from fontTools.fontBuilder import FontBuilder
+from fontTools.ttLib import TTFont
+from fontTools.ttLib.tables._c_m_a_p import CmapSubtable
+from fontTools.ttLib.tables._g_l_y_f import Glyph
+
+# Output path relative to this script
+OUTPUT_PATH = Path(__file__).parent.parent / "src" / "ocrmypdf" / "data" / "Occulta.ttf"
+
+# Font metrics (units per em = 1000)
+UNITS_PER_EM = 1000
+ASCENT = 800
+DESCENT = -200
+
+# Glyph definitions: (name, advance_width, left_side_bearing)
+GLYPHS = [
+    (".notdef", 500, 0),  # Required, used for unmapped characters
+    ("space", 500, 0),  # U+0020 SPACE
+    ("nbspace", 500, 0),  # U+00A0 NO-BREAK SPACE
+    ("blank0", 0, 0),  # Zero-width (combining marks, ZWNJ, ZWJ, BOM)
+    ("blank1", 500, 0),  # Regular width (most scripts)
+    ("blank2", 1000, 0),  # Double width (CJK, fullwidth)
+]
+
+# Explicit zero-width character codepoints
+ZERO_WIDTH_CHARS = frozenset(
+    [
+        0x200B,  # ZERO WIDTH SPACE
+        0x200C,  # ZERO WIDTH NON-JOINER
+        0x200D,  # ZERO WIDTH JOINER
+        0xFEFF,  # ZERO WIDTH NO-BREAK SPACE (BOM)
+        0x200E,  # LEFT-TO-RIGHT MARK
+        0x200F,  # RIGHT-TO-LEFT MARK
+        0x202A,  # LEFT-TO-RIGHT EMBEDDING
+        0x202B,  # RIGHT-TO-LEFT EMBEDDING
+        0x202C,  # POP DIRECTIONAL FORMATTING
+        0x202D,  # LEFT-TO-RIGHT OVERRIDE
+        0x202E,  # RIGHT-TO-LEFT OVERRIDE
+        0x2060,  # WORD JOINER
+        0x2061,  # FUNCTION APPLICATION
+        0x2062,  # INVISIBLE TIMES
+        0x2063,  # INVISIBLE SEPARATOR
+        0x2064,  # INVISIBLE PLUS
+    ]
+)
+
+
+def classify_codepoint(codepoint: int) -> str:
+    """Classify a Unicode codepoint into one of our glyph categories.
+
+    Args:
+        codepoint: Unicode codepoint (0x0000 to 0xFFFF)
+
+    Returns:
+        Glyph name to map this codepoint to
+    """
+    # Special cases first
+    if codepoint == 0x0020:
+        return "space"
+    if codepoint == 0x00A0:
+        return "nbspace"
+    if codepoint in ZERO_WIDTH_CHARS:
+        return "blank0"
+
+    # Use Unicode properties for the rest
+    char = chr(codepoint)
+    try:
+        category = unicodedata.category(char)
+        east_asian_width = unicodedata.east_asian_width(char)
+
+        # Combining marks are zero-width
+        if category.startswith("M"):
+            return "blank0"
+
+        # Wide and Fullwidth characters are double-width
+        if east_asian_width in ("W", "F"):
+            return "blank2"
+
+        # Everything else is regular width
+        return "blank1"
+
+    except (ValueError, TypeError):
+        # Fallback for any edge cases
+        return "blank1"
+
+
+def build_cmap() -> dict[int, str]:
+    """Build the Unicode to glyph name mapping for the entire BMP.
+
+    Returns:
+        Dictionary mapping codepoints to glyph names
+    """
+    return {cp: classify_codepoint(cp) for cp in range(0x10000)}
+
+
+def create_font() -> TTFont:
+    """Create the Occulta glyphless font.
+
+    Returns:
+        TTFont object ready to be saved
+    """
+    glyph_names = [g[0] for g in GLYPHS]
+
+    # Start building the font
+    fb = FontBuilder(UNITS_PER_EM, isTTF=True)
+    fb.setupGlyphOrder(glyph_names)
+
+    # Create empty (invisible) glyphs
+    glyphs = {}
+    for name, _, _ in GLYPHS:
+        glyph = Glyph()
+        glyph.numberOfContours = 0
+        glyphs[name] = glyph
+    fb.setupGlyf(glyphs)
+
+    # Set up horizontal metrics
+    metrics = {name: (width, lsb) for name, width, lsb in GLYPHS}
+    fb.setupHorizontalMetrics(metrics)
+
+    # Minimal cmap to satisfy FontBuilder (we'll replace it later)
+    fb.setupCharacterMap({0x0020: "space", 0x00A0: "nbspace"})
+
+    # Set up other required tables
+    fb.setupHorizontalHeader(ascent=ASCENT, descent=DESCENT)
+    fb.setupOS2(
+        sTypoAscender=ASCENT,
+        sTypoDescender=DESCENT,
+        sTypoLineGap=0,
+        usWinAscent=UNITS_PER_EM,
+        usWinDescent=abs(DESCENT),
+        sxHeight=500,
+        sCapHeight=700,
+    )
+    import time
+
+    # Use current time for font timestamps
+    now = int(time.time())
+    fb.setupHead(unitsPerEm=UNITS_PER_EM, created=now, modified=now)
+    fb.setupPost()
+    fb.setupNameTable(
+        {
+            "familyName": "Occulta",
+            "styleName": "Regular",
+            "uniqueFontIdentifier": "OCRmyPDF;Occulta-Regular;2026",
+            "fullName": "Occulta Regular",
+            "version": "Version 2.0",
+            "psName": "Occulta-Regular",
+        }
+    )
+
+    # Build the font
+    font = fb.font
+
+    # Now replace the cmap with format 13 for efficient many-to-one mapping
+    char_to_glyph = build_cmap()
+
+    cmap13 = CmapSubtable.newSubtable(13)
+    cmap13.platformID = 3  # Windows
+    cmap13.platEncID = 10  # Unicode full repertoire
+    cmap13.language = 0
+    cmap13.cmap = char_to_glyph
+
+    font["cmap"].tables = [cmap13]
+
+    return font
+
+
+def main() -> None:
+    """Generate the Occulta font and save it."""
+    print("Generating Occulta glyphless font...")
+
+    font = create_font()
+
+    # Create output directory if needed
+    OUTPUT_PATH.parent.mkdir(parents=True, exist_ok=True)
+
+    # Save the font
+    font.save(str(OUTPUT_PATH))
+    font.close()
+
+    # Report statistics
+    size = OUTPUT_PATH.stat().st_size
+    print(f"Saved to: {OUTPUT_PATH}")
+    print(f"Size: {size:,} bytes")
+
+    # Verify cmap
+    font = TTFont(str(OUTPUT_PATH))
+    for table in font["cmap"].tables:
+        print(
+            f"cmap: Platform {table.platformID}, "
+            f"Encoding {table.platEncID}, "
+            f"Format {table.format}, "
+            f"{len(table.cmap)} mappings"
+        )
+    font.close()
+
+    print("Done!")
+
+
+if __name__ == "__main__":
+    main()
@@ -5,7 +5,7 @@

 name: ocrmypdf
 title: OCRmyPDF
-base: core22
+base: core24
 version: git
 summary: OCRmyPDF adds a searchable text layer to scanned PDF files
 description: OCRmyPDF packaged for snap
@@ -14,12 +14,13 @@ confinement: strict
 icon: docs/images/logo-square-256.svg
 license: MPL-2.0

-architectures: [amd64]
+platforms:
+  amd64:

 environment:
-  TESSDATA_PREFIX: $SNAP/usr/share/tesseract-ocr/4.00/tessdata
-  GS_LIB: $SNAP/usr/share/ghostscript/9.55.0/Resource/Init
-  GS_FONTPATH: $SNAP/usr/share/ghostscript/9.55.0/Resource/Font
+  TESSDATA_PREFIX: $SNAP/usr/share/tesseract-ocr/5/tessdata
+  GS_LIB: $SNAP/usr/share/ghostscript/10.02.1/Resource/Init
+  GS_FONTPATH: $SNAP/usr/share/ghostscript/10.02.1/Resource/Font
  LD_LIBRARY_PATH: $SNAP/usr/lib/x86_64-linux-gnu

 apps:
@@ -84,11 +85,5 @@ parts:
      - 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
+      craftctl default
+      ln -sf ../usr/lib/libsnapcraft-preload.so $CRAFT_PART_INSTALL/lib/libsnapcraft-preload.so
@@ -9,14 +9,17 @@ from pluggy import HookimplMarker as _HookimplMarker

 from ocrmypdf import helpers, hocrtransform, pdfa, pdfinfo
 from ocrmypdf._concurrent import Executor
+from ocrmypdf._defaults import PROGRAM_NAME
 from ocrmypdf._jobcontext import PageContext, PdfContext
+from ocrmypdf._options import OcrOptions, TaggedPdfMode
 from ocrmypdf._pipelines._common import (
    configure_debug_logging,
 )
-from ocrmypdf._version import PROGRAM_NAME, __version__
+from ocrmypdf._version import __version__
 from ocrmypdf.api import (
    Verbosity,
    configure_logging,
+    configure_stdout_protection,
    ocr,
 )
 from ocrmypdf.exceptions import (
@@ -33,28 +36,41 @@ from ocrmypdf.exceptions import (
    TesseractConfigError,
    UnsupportedImageFormatError,
 )
+from ocrmypdf.models.ocr_element import (
+    Baseline,
+    BoundingBox,
+    FontInfo,
+    OcrClass,
+    OcrElement,
+)
 from ocrmypdf.pluginspec import OcrEngine, OrientationConfidence

 hookimpl = _HookimplMarker('ocrmypdf')

-
 __all__ = [
    '__version__',
    'BadArgsError',
+    'Baseline',
+    'BoundingBox',
    'configure_debug_logging',
    'configure_logging',
+    'configure_stdout_protection',
    'DpiError',
    'EncryptedPdfError',
    'Executor',
    'ExitCode',
    'ExitCodeException',
+    'FontInfo',
    'helpers',
    'hocrtransform',
    'hookimpl',
    'InputFileError',
    'MissingDependencyError',
    'ocr',
+    'OcrClass',
+    'OcrElement',
    'OcrEngine',
+    'OcrOptions',
    'OrientationConfidence',
    'OutputFileAccessError',
    'PageContext',
@@ -64,6 +80,7 @@ __all__ = [
    'PriorOcrFoundError',
    'PROGRAM_NAME',
    'SubprocessOutputError',
+    'TaggedPdfMode',
    'TesseractConfigError',
    'UnsupportedImageFormatError',
    'Verbosity',
@@ -15,9 +15,9 @@ from contextlib import suppress

 from ocrmypdf import __version__
 from ocrmypdf._pipelines.ocr import run_pipeline_cli
-from ocrmypdf._plugin_manager import get_parser_options_plugins
 from ocrmypdf._validation import check_options
-from ocrmypdf.api import Verbosity, configure_logging
+from ocrmypdf.api import Verbosity, configure_logging, configure_stdout_protection
+from ocrmypdf.cli import get_options_and_plugins
 from ocrmypdf.exceptions import (
    BadArgsError,
    ExitCode,
@@ -39,12 +39,17 @@ def sigbus(*args):

 def run(args=None):
    """Run the ocrmypdf command line interface."""
-    _parser, options, plugin_manager = get_parser_options_plugins(args=args)
+    # Protect the real stdout before loading plugins or starting any worker
+    # processes/threads, so that only our final PDF output can reach it and
+    # stray writes from plugins or libraries are diverted to stderr.
+    configure_stdout_protection()
+
+    options, plugin_manager = get_options_and_plugins(args=args)

    with suppress(AttributeError, PermissionError):
        os.nice(5)

-    verbosity = options.verbose
+    verbosity = Verbosity(options.verbose)
    if not os.isatty(sys.stderr.fileno()):
        options.progress_bar = False
    if options.quiet:
@@ -78,6 +83,7 @@ def run(args=None):

 if __name__ == '__main__':
    multiprocessing.freeze_support()
-    if os.name == 'posix':
-        multiprocessing.set_start_method('forkserver')
+    if sys.platform not in ('win32', 'darwin'):
+        with suppress(RuntimeError):
+            multiprocessing.set_start_method('forkserver')
    sys.exit(run())
@@ -0,0 +1,66 @@
+# SPDX-FileCopyrightText: 2024 James R. Barlow
+# SPDX-License-Identifier: MPL-2.0
+
+"""OCRmyPDF PDF annotation cleanup."""
+
+from __future__ import annotations
+
+import logging
+
+from pikepdf import Dictionary, Name, NameTree, Pdf
+
+log = logging.getLogger(__name__)
+
+
+def remove_broken_goto_annotations(pdf: Pdf) -> bool:
+    """Remove broken goto annotations from a PDF.
+
+    If a PDF contains a GoTo Action that points to a named destination that does not
+    exist, Ghostscript PDF/A conversion will fail. In any event, a named destination
+    that is not defined is not useful.
+
+    Args:
+        pdf: Opened PDF file.
+
+    Returns:
+        bool: True if the file was modified, False if not.
+    """
+    modified = False
+
+    # Check if there are any named destinations
+    if Name.Names not in pdf.Root:
+        return modified
+    if Name.Dests not in pdf.Root[Name.Names]:
+        return modified
+
+    dests = pdf.Root[Name.Names][Name.Dests]
+    if not isinstance(dests, Dictionary):
+        return modified
+    nametree = NameTree(dests)
+
+    # Create a set of all named destinations
+    names = set(k for k in nametree.keys())
+
+    for n, page in enumerate(pdf.pages):
+        if Name.Annots not in page:
+            continue
+        for annot in page[Name.Annots]:
+            if not isinstance(annot, Dictionary):
+                continue
+            if Name.A not in annot or Name.D not in annot[Name.A]:
+                continue
+            # We found an annotation that points to a named destination
+            named_destination = str(annot[Name.A][Name.D])
+            if named_destination not in names:
+                # If there is no corresponding named destination, remove the
+                # annotation. Having no destination set is still valid and just
+                # makes the link non-functional.
+                log.warning(
+                    f"Disabling a hyperlink annotation on page {n + 1} to a "
+                    "non-existent named destination "
+                    f"{named_destination}."
+                )
+                del annot[Name.A][Name.D]
+                modified = True
+
+    return modified
@@ -8,14 +8,14 @@ from __future__ import annotations
 import threading
 from abc import ABC, abstractmethod
 from collections.abc import Callable, Iterable
-from typing import Any, TypeVar
+from typing import Any, TypeVar, cast

 from ocrmypdf._progressbar import NullProgressBar, ProgressBar

 T = TypeVar('T')


-def _task_noop(*_args, **_kwargs):
+def _task_noop(*_args, **_kwargs) -> None:
    return


@@ -72,7 +72,10 @@ class Executor(ABC):
        if not task_finished:
            task_finished = _task_finished_noop
        if not task:
-            task = _task_noop
+            # _task_noop always returns None, but T is unbound here (it's
+            # only meaningful when a real task is supplied); task_finished's
+            # own no-op default accepts Any, so this is safe.
+            task = cast('Callable[..., T]', _task_noop)

        with self.pool_lock:
            self._execute(
@@ -101,8 +104,8 @@ class Executor(ABC):


 def setup_executor(plugin_manager) -> Executor:
-    pbar_class = plugin_manager.hook.get_progressbar_class()
-    return plugin_manager.hook.get_executor(progressbar_class=pbar_class)
+    pbar_class = plugin_manager.get_progressbar_class()
+    return plugin_manager.get_executor(progressbar_class=pbar_class)


 class SerialExecutor(Executor):
@@ -2,7 +2,11 @@
 # SPDX-License-Identifier: MPL-2.0

 # Enforce English hegemony
+from __future__ import annotations
+
 DEFAULT_LANGUAGE = 'eng'

 # Default rotation threshold
 DEFAULT_ROTATE_PAGES_THRESHOLD = 14.0
+
+PROGRAM_NAME = 'OCRmyPDF'
@@ -0,0 +1,72 @@
+# SPDX-FileCopyrightText: 2026 James R. Barlow
+# SPDX-License-Identifier: MPL-2.0
+"""Probe helper for external executables.
+
+Each ``ocrmypdf._exec.<tool>`` module describes its external program with a
+module-level :class:`ToolProbe` and delegates ``version()`` / ``available()``
+to it. This separates the "is the tool installed and suitable?" question
+(probing) from the "run the tool" question (execution). Work functions stay
+as pure module-level functions so they are trivially picklable for use in
+subprocess workers.
+"""
+
+from __future__ import annotations
+
+from collections.abc import Mapping
+from dataclasses import dataclass
+
+from packaging.version import Version
+
+from ocrmypdf.exceptions import MissingDependencyError
+from ocrmypdf.subprocess import get_version
+
+
+@dataclass(frozen=True)
+class ToolProbe:
+    """Describes how to detect an external executable and its version.
+
+    Attributes:
+        program: The program name as it appears on PATH (or a full path).
+        version_arg: The argument that elicits a version string.
+        version_regex: A regex with a capturing group that extracts the
+            version from the program's output.
+        version_cls: A :class:`packaging.version.Version` subclass, used for
+            tools with non-standard version strings (e.g. Tesseract).
+        env: Optional environment overrides applied when probing the version.
+        also_catch: Additional exception types that should be treated as
+            "not available" by :meth:`available`. :class:`OSError` is useful
+            for tools like verapdf whose launcher may fail with non-standard
+            errors when the JVM is missing.
+    """
+
+    program: str
+    version_arg: str = '--version'
+    version_regex: str = r'(\d+(\.\d+)*)'
+    version_cls: type[Version] = Version
+    env: Mapping[str, str] | None = None
+    also_catch: tuple[type[BaseException], ...] = ()
+
+    def version(self) -> Version:
+        """Return the installed version of the program.
+
+        Raises:
+            MissingDependencyError: if the program cannot be found or its
+                version string cannot be parsed.
+        """
+        raw = get_version(
+            self.program,
+            version_arg=self.version_arg,
+            regex=self.version_regex,
+            env=self.env,
+        )
+        return self.version_cls(raw)
+
+    def available(self) -> bool:
+        """Return whether a usable version of the program is installed."""
+        try:
+            self.version()
+        except MissingDependencyError:
+            return False
+        except self.also_catch:
+            return False
+        return True
@@ -9,7 +9,6 @@ import logging
 import os
 import re
 from collections import deque
-from io import BytesIO
 from os import fspath
 from pathlib import Path
 from subprocess import PIPE, CalledProcessError
@@ -17,9 +16,15 @@ from subprocess import PIPE, CalledProcessError
 from packaging.version import Version
 from PIL import Image, UnidentifiedImageError

-from ocrmypdf.exceptions import ColorConversionNeededError, SubprocessOutputError
+from ocrmypdf._exec._probe import ToolProbe
+from ocrmypdf.exceptions import (
+    ColorConversionNeededError,
+    InputFileError,
+    SubprocessOutputError,
+)
 from ocrmypdf.helpers import Resolution
-from ocrmypdf.subprocess import get_version, run, run_polling_stderr
+from ocrmypdf.pluginspec import GhostscriptRasterDevice
+from ocrmypdf.subprocess import run, run_polling_stderr

 COLOR_CONVERSION_STRATEGIES = frozenset(
    [
@@ -65,11 +70,19 @@ class DuplicateFilter(logging.Filter):
            return True


-log.addFilter(DuplicateFilter(log))
+PROBE = ToolProbe(program=GS)
+version = PROBE.version
+available = PROBE.available


-def version() -> Version:
-    return Version(get_version(GS))
+def _ensure_log_filter_installed() -> None:
+    """Idempotently attach the duplicate-suppressing filter to the GS logger.
+
+    Called at the top of each work function so the filter is present in the
+    main process *and* in any subprocess worker that calls Ghostscript.
+    """
+    if not any(isinstance(f, DuplicateFilter) for f in log.filters):
+        log.addFilter(DuplicateFilter(log))


 def _gs_error_reported(stream) -> bool:
@@ -92,26 +105,67 @@ def _gs_devicen_reported(stream) -> bool:


 def rasterize_pdf(
-    input_file: os.PathLike,
-    output_file: os.PathLike,
+    input_file: Path,
+    output_file: Path,
    *,
-    raster_device: str,
+    raster_device: GhostscriptRasterDevice,
    raster_dpi: Resolution,
    pageno: int = 1,
    page_dpi: Resolution | None = None,
    rotation: int | None = None,
    filter_vector: bool = False,
    stop_on_error: bool = False,
+    use_cropbox: bool = False,
 ):
-    """Rasterize one page of a PDF at resolution raster_dpi in canvas units."""
+    """Rasterize one page of a PDF at resolution raster_dpi in canvas units.
+
+    Args:
+        input_file: The PDF file to rasterize.
+        output_file: The file to write the rasterized PDF to.
+        raster_device: The Ghostscript raster device to use to rasterize the PDF.
+        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_error: If True, stop rasterizing on the first error.
+        use_cropbox: If True, rasterize the CropBox instead of MediaBox.
+            Default is False (use MediaBox).
+    """
+    _ensure_log_filter_installed()
    raster_dpi = raster_dpi.round(6)
    if not page_dpi:
        page_dpi = raster_dpi

+    # Ghostscript may fail with very low DPI values (below 10). If the requested
+    # DPI is too low, use a minimum of 10 DPI and resize the output afterward.
+    MIN_RASTER_DPI = 10
+    needs_low_dpi_resize = (
+        raster_dpi.x < MIN_RASTER_DPI or raster_dpi.y < MIN_RASTER_DPI
+    )
+    if needs_low_dpi_resize:
+        effective_dpi = Resolution(
+            max(raster_dpi.x, MIN_RASTER_DPI), max(raster_dpi.y, MIN_RASTER_DPI)
+        )
+    else:
+        effective_dpi = raster_dpi
+
+    # Anti-alias text and vector graphics when rendering to a contone device.
+    # Ghostscript 10.x renders aliased glyphs that OCR frequently misreads as
+    # extra word breaks; anti-aliasing empirically improves OCR accuracy on the
+    # Ghostscript path, especially for small fonts at moderate DPI (#1439).
+    # The 1-bit mono devices do not accept alpha bits (older Ghostscript
+    # rejects them) and pngmonod performs its own anti-aliased downscaling.
+    mono_devices = (GhostscriptRasterDevice.PNGMONO, GhostscriptRasterDevice.PNGMONOD)
+    antialias_args = (
+        []
+        if raster_device in mono_devices
+        else ['-dTextAlphaBits=4', '-dGraphicsAlphaBits=4']
+    )
+
    args_gs = (
        [
            GS,
-            '-dQUIET',
            '-dSAFER',
            '-dBATCH',
            '-dNOPAUSE',
@@ -119,13 +173,15 @@ def rasterize_pdf(
            f'-sDEVICE={raster_device}',
            f'-dFirstPage={pageno}',
            f'-dLastPage={pageno}',
-            f'-r{raster_dpi.x:f}x{raster_dpi.y:f}',
+            f'-r{effective_dpi.x:f}x{effective_dpi.y:f}',
        ]
+        + antialias_args
+        + (['-dUseCropBox'] if use_cropbox else [])
        + (['-dFILTERVECTOR'] if filter_vector else [])
        + (['-dPDFSTOPONERROR'] if stop_on_error else [])
        + [
            '-o',
-            '-',
+            fspath(output_file),
            '-sstdout=%stderr',  # Literal %s, not string interpolation
            '-dAutoRotatePages=/None',  # Probably has no effect on raster
            '-f',
@@ -137,14 +193,34 @@ def rasterize_pdf(
        p = run(args_gs, stdout=PIPE, stderr=PIPE, check=True)
    except CalledProcessError as e:
        log.error(e.stderr.decode(errors='replace'))
-        raise SubprocessOutputError('Ghostscript rasterizing failed') from e
-    else:
-        stderr = p.stderr.decode(errors='replace')
-        if _gs_error_reported(stderr):
-            log.error(stderr)
+        Path(output_file).unlink(missing_ok=True)
+        raise SubprocessOutputError("Ghostscript rasterizing failed") from e
+
+    stderr = p.stderr.decode(errors='replace')
+    if _gs_error_reported(stderr):
+        log.error(stderr)
+        if stop_on_error and "recoverable image error" in stderr:
+            Path(output_file).unlink(missing_ok=True)
+            raise InputFileError(
+                "Ghostscript rasterizing failed. The input file contains errors that "
+                "cause PDF viewers to interpret it differently and incorrectly. "
+                "Try using --continue-on-soft-render-error and manually inspect the "
+                "input and output files to check for visual differences or errors."
+            )

    try:
-        with Image.open(BytesIO(p.stdout)) as im:
+        im: Image.Image
+        with Image.open(output_file) as im:
+            if needs_low_dpi_resize:
+                # Resize to the dimensions that would have resulted from the
+                # original low DPI request
+                scale_x = raster_dpi.x / effective_dpi.x
+                scale_y = raster_dpi.y / effective_dpi.y
+                new_size = (
+                    max(1, int(round(im.width * scale_x))),
+                    max(1, int(round(im.height * scale_y))),
+                )
+                im = im.resize(new_size, Image.Resampling.LANCZOS)
            if rotation is not None:
                log.debug("Rotating output by %i", rotation)
                # rotation is a clockwise angle and Image.ROTATE_* is
@@ -157,13 +233,19 @@ def rasterize_pdf(
                    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)
+            im.save(output_file, dpi=page_dpi)
    except UnidentifiedImageError:
        log.error(
            f"Ghostscript (using {raster_device} at {raster_dpi} dpi) produced "
            "an invalid page image file."
        )
        raise
+    except OSError as e:
+        log.error(
+            f"Ghostscript (using {raster_device} at {raster_dpi} dpi) produced "
+            "an invalid page image file."
+        )
+        raise UnidentifiedImageError() from e


 class GhostscriptFollower:
@@ -207,15 +289,18 @@ class GhostscriptFollower:

 def generate_pdfa(
    pdf_pages,
-    output_file: os.PathLike,
+    output_file: Path,
    *,
    compression: str,
    color_conversion_strategy: str,
+    jpeg_quality: int | None = None,
+    jpeg_maxdpi: int | None = None,
    pdf_version: str = '1.5',
    pdfa_part: str = '2',
    progressbar_class=None,
    stop_on_error: bool = False,
 ):
+    _ensure_log_filter_installed()
    # Ghostscript's compression is all or nothing. We can either force all images
    # to JPEG, force all to Flate/PNG, or let it decide how to encode the images.
    # In most case it's best to let it decide.
@@ -229,6 +314,11 @@ def generate_pdfa(
        ]
    elif compression == 'lossless':
        compression_args = [
+            # Re-encoding an existing JPEG with a lossless codec only inflates
+            # its size: the lossy data is already baked in, so there is nothing
+            # to gain. Pass JPEGs through untouched and apply lossless (Flate)
+            # encoding only to images that are not already JPEG.
+            "-dPassThroughJPEGImages=true",
            "-dAutoFilterColorImages=false",
            "-dColorImageFilter=/FlateEncode",
            "-dAutoFilterGrayImages=false",
@@ -250,6 +340,35 @@ def generate_pdfa(
        # Windows has lots of fatal "permission denied" errors
        stop_on_error = False

+    # `-dJPEGQ=N` tells Ghostscript to use a JPEG quality of N, IF it decides
+    # to transcode an image to JPEG. When there are existing JPEG images,
+    # Ghostscript uses passthrough mode, so the quality level is not changed.
+    # OCRmyPDF's optimizer separately uses the `--jpeg-quality` command line
+    # option to potentially re-encode JPEG images, regardless of whether
+    # Ghostscript decided to transcode them to JPEG or not.
+    # `jpeg_quality=0` is meaningful to Ghostscript (maximum compression), so
+    # only fall back to the default when the value is None.
+    effective_jpeg_quality = jpeg_quality if jpeg_quality is not None else 95
+
+    # Downsampling images is a blunt-force way to reduce file size and almost
+    # always degrades quality more than lowering JPEG quality at the original
+    # resolution. We expose this for users with very specific needs (e.g.
+    # producing very small files for screen-only viewing); the optimizer is
+    # usually a better choice.
+    downsample_args: list[str] = []
+    if jpeg_maxdpi is not None:
+        downsample_args = [
+            "-dDownsampleColorImages=true",
+            "-dColorImageDownsampleThreshold=1.0",
+            "-dDownsampleGrayImages=true",
+            "-dGrayImageDownsampleThreshold=1.0",
+            "-dDownsampleMonoImages=true",
+            "-dMonoImageDownsampleThreshold=1.0",
+            f"-dColorImageResolution={jpeg_maxdpi}",
+            f"-dGrayImageResolution={jpeg_maxdpi}",
+            f"-dMonoImageResolution={jpeg_maxdpi}",
+        ]
+
    # nb no need to specify ProcessColorModel when ColorConversionStrategy
    # is set; see:
    # https://bugs.ghostscript.com/show_bug.cgi?id=699392
@@ -266,24 +385,22 @@ def generate_pdfa(
        ]
        + (['-dPDFSTOPONERROR'] if stop_on_error else [])
        + compression_args
+        + downsample_args
        + [
-            "-dJPEGQ=95",
+            f"-dJPEGQ={effective_jpeg_quality}",  # See note above on JPEG quality
+            "-dSubsetFonts=false",  # Prevents GS from messing up some encodings
            f"-dPDFA={pdfa_part}",
            "-dPDFACompatibilityPolicy=1",
            "-o",
-            "-",
+            fspath(output_file),
            "-sstdout=%stderr",  # Literal %s, not string interpolation
        ]
    )
    args_gs.extend(fspath(s) for s in pdf_pages)  # Stringify Path objs
    try:
-        with (
-            Path(output_file).open('wb') as output,
-            GhostscriptFollower(progressbar_class) as pbar,
-        ):
+        with GhostscriptFollower(progressbar_class) as pbar:
            p = run_polling_stderr(
                args_gs,
-                stdout=output,
                stderr=PIPE,
                check=True,
                text=True,
@@ -308,4 +425,8 @@ def generate_pdfa(
            for part in stderr.split('****'):
                log.error(part)
        if _gs_devicen_reported(stderr):
-            raise ColorConversionNeededError()
+            # Ghostscript could not normalize the DeviceN colorspace for PDF/A,
+            # even if the user requested a conversion strategy. The output is
+            # liable to render blank in some viewers, so raise regardless of the
+            # strategy and tailor the guidance to what was attempted.
+            raise ColorConversionNeededError(color_conversion_strategy)
@@ -5,19 +5,27 @@

 from __future__ import annotations

-from subprocess import PIPE
+from subprocess import PIPE, CalledProcessError

 from packaging.version import Version

+from ocrmypdf._exec._probe import ToolProbe
 from ocrmypdf.exceptions import MissingDependencyError
-from ocrmypdf.subprocess import get_version, run
+from ocrmypdf.subprocess import run
+
+_PROBE = ToolProbe(program='jbig2', version_regex=r'jbig2enc (\d+(\.\d+)*).*')


 def version() -> Version:
-    return Version(get_version('jbig2', regex=r'jbig2enc (\d+(\.\d+)*).*'))
+    try:
+        return _PROBE.version()
+    except CalledProcessError as e:
+        # TeX Live for Windows provides an incompatible jbig2.EXE which may
+        # be on the PATH.
+        raise MissingDependencyError('jbig2enc') from e


-def available():
+def available() -> bool:
    try:
        version()
    except MissingDependencyError:
@@ -25,27 +33,9 @@ def available():
    return True


-def convert_group(cwd, infiles, out_prefix, threshold):
-    args = [
-        'jbig2',
-        '-b',
-        out_prefix,
-        '--symbol-mode',  # symbol mode (lossy)
-        '-t',
-        str(threshold),  # threshold
-        # '-r', # refinement mode (lossless symbol mode, currently disabled in
-        # jbig2)
-        '--pdf',
-    ]
-    args.extend(infiles)
-    proc = run(args, cwd=cwd, stdout=PIPE, stderr=PIPE)
-    proc.check_returncode()
-    return proc
-
-
 def convert_single(cwd, infile, outfile, threshold):
    args = ['jbig2', '--pdf', '-t', str(threshold), infile]
-    with open(outfile, 'wb') as fstdout:
+    with outfile.open('wb') as fstdout:
        proc = run(args, cwd=cwd, stdout=fstdout, stderr=PIPE)
    proc.check_returncode()
    return proc
--- a/Show More
+++ b/Show More