Tell uv not to sync dev harder

Fixes #1444

.docker/Dockerfile

@@ -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:24.04 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 \
@@ -29,15 +25,11 @@ 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 \
@@ -48,21 +40,23 @@ COPY . /app
 
 WORKDIR /app
 
-RUN pip3 install --no-cache-dir .[test,webservice,watcher]
+# Copy uv from ghcr
+COPY --from=ghcr.io/astral-sh/uv:0.5.5 /uv /uvx /bin/
+
+ENV UV_COMPILE_BYTECODE=1 UV_LINK_MODE=copy
+
+RUN uv sync --extra test --extra webservice --extra watcher --no-dev
 
 FROM base
 
-# For Tesseract 5
-RUN apt-get update && apt-get install -y --no-install-recommends \
-  software-properties-common gpg-agent
-RUN add-apt-repository -y ppa:alex-p/tesseract-ocr-devel
+RUN apt-get update && apt-get install -y software-properties-common
+
+RUN add-apt-repository -y ppa:alex-p/tesseract-ocr5
 
 RUN apt-get update && apt-get install -y --no-install-recommends \
   ghostscript \
   fonts-droid-fallback \
   jbig2dec \
-  img2pdf \
-  libsm6 libxext6 libxrender-dev \
   pngquant \
   tesseract-ocr \
   tesseract-ocr-chi-sim \
@@ -79,11 +73,13 @@ 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
+
+ENV PATH="/app/.venv/bin:${PATH}"
+
+ENTRYPOINT ["/app/.venv/bin/ocrmypdf"]
 
-ENTRYPOINT ["/usr/local/bin/ocrmypdf"]

.docker/Dockerfile.alpine

@@ -1,7 +1,14 @@
 # SPDX-FileCopyrightText: 2023 James R. Barlow
 # SPDX-License-Identifier: MPL-2.0
 
-FROM alpine:3.18 as base
+# Note: Alpine 3.20 builds tesseract with --enable-opencl, which is not
+# supported by anyone. OCRmyPDF is not compatible with Alpine 3.20.0
+# through 3.20.3. The Alpine issue should be fixed in 3.21.0. It is
+# not clear if 3.20.4+ will have the fix.
+# Details
+#  https://gitlab.alpinelinux.org/alpine/aports/-/issues/16143
+#  https://github.com/ocrmypdf/OCRmyPDF/issues/1395
+FROM alpine:3.19 AS base
 
 ENV LANG=C.UTF-8
 ENV TZ=UTC
@@ -10,40 +17,24 @@ RUN apk add --no-cache \
     python3 \
     zlib
 
-FROM base as builder
+FROM base AS builder
 
 RUN apk add --no-cache \
     ca-certificates \
     git \
     python3-dev \
-    py3-pip
-
-# On arm64, we need to build cffi from source.
-ARG TARGETPLATFORM
-
-RUN if [ "${TARGETPLATFORM}" == "linux/arm64" ]; then \
-    apk add --no-cache \
-    build-base \
-    autoconf \
-    automake \
-    libtool \
-    zlib-dev \
-    libffi-dev \
-    cairo-dev \
-    pkgconfig \
-    ;  \
-    fi
+    curl
 
 COPY . /app
 
 WORKDIR /app
 
-RUN python3 -m venv .venv
+COPY --from=ghcr.io/astral-sh/uv:0.5.5 /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
+
+# Instead of restarting the shell, use uv directly from its installed location.
+RUN uv sync --extra test --extra webservice --extra watcher --no-dev
 
 FROM base
 
@@ -66,17 +57,11 @@ RUN apk add --no-cache \
 
 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/
-
-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
+RUN rm -rf /app/.git && \
+    ln -s /app/misc/webservice.py /app/webservice.py && \
+    ln -s /app/misc/watcher.py /app/watcher.py
 
 ENV PATH="/app/.venv/bin:${PATH}"
 

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

@@ -1,7 +1,7 @@
-name: General issues
+name: Installation, packaging, dependencies
 description: Installation, packages, dependencies, "nothing works", test suite failures...
 title: "[Bug]: "
-labels: ["bug", "triage"]
+labels: ["triage"]
 assignees:
   - jbarlow83
 body:
@@ -9,6 +9,10 @@ body:
     attributes:
       value: |
         Thanks for taking the time to fill out this bug report!
+
+        If your issue involves using OCRmyPDF on specific file(s) and not getting
+        good results, this is the *wrong* issue template. Please use the recommended
+        template to ensure we have enough information to help.
   - type: textarea
     id: what-happened
     attributes:
@@ -20,7 +24,7 @@ body:
   - type: dropdown
     id: packaging-system
     attributes:
-      label: Where are you installing from?
+      label: Where are you installing/running from?
       multiple: true
       options:
         - PyPI (pip, poetry, pipx, etc.)
@@ -33,6 +37,11 @@ body:
         - source build
     validations:
       required: true
+  - type: input
+    id: version
+    attributes:
+      label: OCRmyPDF version
+      description: Paste "ocrmypdf --version" here
   - type: dropdown
     id: operating-system
     attributes:
@@ -43,6 +52,18 @@ body:
         - Windows
         - macOS
         - BSD
+  - type: input
+    id: os_version
+    attributes:
+      label: Operating system details and version
+  - type: checkboxes
+    attributes:
+      label: Simple sanity checks
+      description: Select all that apply
+      options:
+        - label: Operating system is currently supported by its vendor (not end of life)
+        - label: Python version is compatible with OCRmyPDF
+        - label: This issue is not about a specific input file
   - type: textarea
     id: logs
     attributes:

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

@@ -1,7 +1,7 @@
 name: Problem with specific file
 description: Something went wrong while trying to OCR a specific file
 title: "[Bug]: "
-labels: ["bug", "triage"]
+labels: ["triage"]
 assignees:
   - jbarlow83
 body:
@@ -21,7 +21,7 @@ body:
     id: reproduce
     attributes:
       label: Steps to reproduce
-      description: Please include steps to reproduce
+      description: Please include steps to reproduce.
       value: |
         1. Run ocrmypdf -v1 ...arguments... input.pdf output.pdf
         2. Open output.pdf
@@ -31,8 +31,21 @@ body:
     id: files
     attributes:
       label: Files
-      description: Please attach the input and output files, or any screenshots that may be helpful.
-      placeholder: Drag and drop files here
+      description: |
+        Please attach the input and output files, or any screenshots that may be helpful.
+
+        If you cannot provide a test file, we probably won't be able to help with the issue.
+        PDF is a complex file format, and there may be technical details in the PDF that are
+        causing the issue. There's really no substitute for a test file.
+
+        We understand files may contain personal or sensitive information. Here are some options:
+        - Try reproducing the issue with a file from the OCRmyPDF test suite. (See tests/resources)
+        - Try to create another file in the same way as your private file.
+        - Encrypt the file to OCRmyPDF's private GPG key, and then zip the GPG file.
+        - Use ``qpdf --json yourfile.pdf`` to produce a JSON representation of your file that
+          omits personal information.
+      placeholder: |
+        Drag and drop files here.
   - type: dropdown
     id: packaging-system
     attributes:

.github/ISSUE_TEMPLATE/3-app.yml

@@ -0,0 +1,83 @@
+name: Problem with third party app that uses OCRmyPDF
+description: |
+  For PDF generation issues with third party software such as Paperless-ngx that
+  uses OCRmyPDF to perform OCR or generate PDFs.
+title: "[3rdparty]: "
+labels: ["triage"]
+assignees:
+  - jbarlow83
+body:
+  - type: markdown
+    attributes:
+      value: |
+        Thanks for taking the time to describe this issue with a particular file
+        and third party app.
+
+        If you are comfortable using OCRmyPDF, please trying to install OCRmyPDF,
+        run it on your file, and see if it works. It's easier for everyone
+        if you can confirm that the issue occurs with OCRmyPDF and not with
+        the third party app.
+  - type: checkboxes
+    attributes:
+      label: Simple sanity checks
+      description: Select all that apply
+      options:
+        - label: This is an issue with an app that uses OCRmyPDF for OCR
+        - label: I am using a recent version of the third party app
+        - label: I will include a file that reproduces the issuse
+  - type: input
+    id: thirdparty-app-name-version
+    attributes:
+      label: Third party app name and version
+      description: e.g. Paperless-ngx 2.9.0
+  - type: textarea
+    id: what-happened
+    attributes:
+      label: Describe the bug
+      description: A clear and concise description of what the bug is.
+      placeholder: Tell us what you see!
+    validations:
+      required: true
+  - type: textarea
+    id: reproduce
+    attributes:
+      label: Steps to reproduce
+      description: Please include steps to reproduce.
+      value: |
+        1. Import attached file into Paperless-ngx
+        2. Trigger OCR
+        3. Check log file
+        4. ...
+      render: plain text
+  - type: textarea
+    id: files
+    attributes:
+      label: Files
+      description: |
+        Please attach the input and output files, or any screenshots that may be helpful.
+
+        If you cannot provide a test file, we probably won't be able to help with the issue.
+        PDF is a complex file format, and there may be technical details in the PDF that are
+        causing the issue. There's really no substitute for a test file.
+
+        We understand files may contain personal or sensitive information. Here are some options:
+        - Try reproducing the issue with a file from the test suite. (See tests/resources)
+        - Try to create another file in the same way as your private file.
+        - Encrypt the file to OCRmyPDF's private GPG key, and then zip the GPG file.
+        - Use ``qpdf --json yourfile.pdf`` to produce a JSON representation of your file that
+          omits personal information.
+      placeholder: |
+        Drag and drop files here.
+  - type: input
+    id: version
+    attributes:
+      label: OCRmyPDF version
+      description: Paste "ocrmypdf --version" here
+      placeholder: ocrmypdf --version
+  - type: textarea
+    id: logs
+    attributes:
+      label: Relevant log output
+      description: Please copy and paste any relevant log output. This will be automatically formatted into code, so no need for backticks.
+      placeholder: Run OCRmyPDF with verbosity `-v1` to get more detailed logging output.
+      render: plain text

.github/workflows/build.yml

@@ -21,19 +21,14 @@ jobs:
     runs-on: ${{ matrix.os }}
     strategy:
       matrix:
+        os: [ubuntu-22.04, ubuntu-24.04]
+        python: ["3.10", "3.11", "3.12", "3.13"]
         include:
           - os: ubuntu-22.04
+            tesseract_ppa: "ppa"
             python: "3.10"
-          - os: ubuntu-22.04
-            python: "3.11"
-          - os: ubuntu-22.04
-            python: "3.10"
-            tesseract5: true
-          - os: ubuntu-latest
-            python: "3.12"
-            tesseract5: true
-          # - os: ubuntu-latest
-          #   python: "pypy3.10"
+          - os: ubuntu-24.04
+            python: "pypy3.10"
 
     env:
       OS: ${{ matrix.os }}
@@ -44,16 +39,20 @@ jobs:
         with:
           fetch-depth: "0" # 0=all, needed for setuptools-scm to resolve version tags
 
-      - uses: actions/setup-python@v5
-        name: Setup Python
+      - name: Install uv
+        uses: astral-sh/setup-uv@v4
+        with:
+          version: "0.5.x"
+
+      - name: "Set up Python"
+        uses: actions/setup-python@v5
         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-ocr5.3
 
       - name: Install common packages
         run: |
@@ -61,6 +60,7 @@ jobs:
           sudo apt-get install -y --no-install-recommends \
             curl \
             ghostscript \
+            jbig2dec \
             img2pdf \
             libexempi8 \
             libffi-dev \
@@ -84,8 +84,7 @@ jobs:
 
       - name: Install Python packages
         run: |
-          python -m pip install --upgrade pip wheel
-          python -m pip install --prefer-binary .[test]
+          uv sync --extra test --no-dev
 
       - name: Report versions
         run: |
@@ -93,14 +92,16 @@ 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@v3
+        uses: codecov/codecov-action@v5
+        env:
+          CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}
         with:
           files: ./coverage.xml
           env_vars: OS,PYTHON
@@ -110,8 +111,8 @@ jobs:
     runs-on: ${{ matrix.os }}
     strategy:
       matrix:
-        os: [macos-latest]
-        python: ["3.10", "3.11", "3.12"]
+        os: [macos-latest, macos-13]  # macos-latest is arm64, macos-13 is x86_64
+        python: ["3.10", "3.11", "3.12", "3.13"]
 
     env:
       OS: ${{ matrix.os }}
@@ -131,34 +132,38 @@ jobs:
             ghostscript \
             jbig2enc \
             openjpeg \
-            openssl \
             pngquant \
             tesseract
 
-      - uses: actions/setup-python@v5
-        name: Setup Python
+      - name: Install uv
+        uses: astral-sh/setup-uv@v4
+        with:
+          version: "0.5.x"
+
+      - name: "Set up Python"
+        uses: actions/setup-python@v5
         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 --extra test --no-dev
 
       - 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@v3
+        uses: codecov/codecov-action@v5
+        env:
+          CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}
         with:
           files: ./coverage.xml
           env_vars: OS,PYTHON
@@ -169,7 +174,7 @@ jobs:
     strategy:
       matrix:
         os: [windows-latest]
-        python: ["3.10", "3.11", "3.12"]
+        python: ["3.10", "3.11", "3.12", "3.13"]
 
     env:
       OS: ${{ matrix.os }}
@@ -180,28 +185,33 @@ jobs:
         with:
           fetch-depth: "0" # 0=all, needed for setuptools-scm to resolve version tags
 
-      - uses: actions/setup-python@v5
-        name: Setup Python
+      - name: Install uv
+        uses: astral-sh/setup-uv@v4
+        with:
+          version: "0.5.x"
+
+      - name: "Set up Python"
+        uses: actions/setup-python@v5
         with:
           python-version: ${{ matrix.python }}
-          cache: "pip"
 
       - name: Install system packages
         run: |
           choco install --yes --no-progress --pre tesseract
-          choco install --yes --no-progress --ignore-checksums ghostscript
+          choco install --yes --no-progress --ignore-checksums ghostscript --version 9.56.1
 
       - name: Install Python packages
         run: |
-          python -m pip install --upgrade pip wheel
-          python -m pip install --prefer-binary .[test]
+          uv sync --extra test --no-dev
 
       - 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@v3
+        uses: codecov/codecov-action@v5
+        env:
+          CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}
         with:
           files: ./coverage.xml
           env_vars: OS,PYTHON
@@ -214,16 +224,14 @@ jobs:
         with:
           fetch-depth: "0" # 0=all, needed for setuptools-scm to resolve version tags
 
-      - uses: actions/setup-python@v5
-        name: Setup Python
+      - name: Install uv
+        uses: astral-sh/setup-uv@v4
         with:
-          python-version: "3.10"
-          cache: "pip"
+          version: "0.5.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
         with:
@@ -243,6 +251,7 @@ jobs:
     steps:
       - uses: actions/download-artifact@v4
         with:
+          name: artifact
           path: dist
 
       - name: Publish to PyPI
@@ -250,28 +259,45 @@ jobs:
 
   create_release:
     name: Create GitHub release
-    needs: [wheel_sdist_linux, test_linux, test_macos, test_windows]
+    needs: [upload_pypi]
     runs-on: ubuntu-latest
     if: github.event_name == 'push' && startsWith(github.event.ref, 'refs/tags/v')
     permissions:
       # Required to create a release
       contents: write
+      id-token: write
     steps:
       - uses: actions/download-artifact@v4
         with:
+          name: artifact
           path: dist
 
-      - name: Create Release
-        id: create-release
-        uses: shogo82148/actions-create-release@v1
-
-      - name: Upload Assets
-        uses: shogo82148/actions-upload-release-asset@v1
+      - name: Sign the dists with Sigstore
+        uses: sigstore/gh-action-sigstore-python@v3.0.0
         with:
-          upload_url: ${{ steps.create-release.outputs.upload_url }}
-          asset_path: |
-            ./dist/*.whl
+          inputs: >-
             ./dist/*.tar.gz
+            ./dist/*.whl
+
+      - name: Create GitHub Release
+        env:
+          GITHUB_TOKEN: ${{ github.token }}
+        run: >-
+          gh release create
+          '${{ github.ref_name }}'
+          --repo '${{ github.repository }}'
+          --notes ""
+
+      - name: Upload artifact signatures to GitHub Release
+        env:
+          GITHUB_TOKEN: ${{ github.token }}
+        # Upload to GitHub Release using the `gh` CLI.
+        # `dist/` contains the built packages, and the
+        # sigstore-produced signatures and certificates.
+        run: >-
+          gh release upload
+          '${{ github.ref_name }}' dist/**
+          --repo '${{ github.repository }}'
 
   docker_ubuntu:
     name: Build Ubuntu-based Docker image
@@ -350,9 +376,6 @@ jobs:
           username: jbarlow83
           password: ${{ secrets.DOCKERHUB_TOKEN }}
 
-      - name: Set up QEMU
-        uses: docker/setup-qemu-action@v3
-
       - name: Set up Docker Buildx
         id: buildx
         uses: docker/setup-buildx-action@v3
@@ -364,6 +387,6 @@ jobs:
         run: |
           docker buildx build \
             --push \
-            --platform linux/amd64  \
+            --platform linux/amd64,linux/arm64  \
             --tag "${DOCKER_REPOSITORY}/${DOCKER_IMAGE_NAME}:${DOCKER_IMAGE_TAG}" \
             --file .docker/Dockerfile.alpine .

.gitignore

@@ -44,3 +44,4 @@ docs/_build/
 docs/_static/
 docs/_templates/
 docs/Makefile
+src/ocrmypdf/_version.py

README.md

@@ -70,10 +70,10 @@ Linux, Windows, macOS and FreeBSD are supported. Docker images are also availabl
 | Windows Subsystem for Linux   | ``apt install ocrmypdf``      |
 | Fedora                        | ``dnf install ocrmypdf``      |
 | macOS (Homebrew)              | ``brew install ocrmypdf``     |
+| macOS (MacPorts)              | ``port install ocrmypdf``     |
 | macOS (nix)                   | ``nix-env -i ocrmypdf``       |
 | LinuxBrew                     | ``brew install ocrmypdf``     |
 | FreeBSD                       | ``pkg install py-ocrmypdf``   |
-| Conda                         | ``conda install ocrmypdf``    |
 | Ubuntu Snap                   | ``snap install ocrmypdf``     |
 
 For everyone else, [see our documentation](https://ocrmypdf.readthedocs.io/en/latest/installation.html) for installation steps.
@@ -112,9 +112,33 @@ 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 convert to PDF/A
+ocrmypdf 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.
 
 ## Press & Media
 

docs/advanced.rst

@@ -118,15 +118,16 @@ OCR for huge images
 -------------------
 
 Tesseract has internal limits on the size
-of images it will process. If you issue
-``--tesseract-downsample-large-images``, OCRmyPDF will downsample images
-to fit Tesseract limits. (The limits are usually entered only for scanned
-images of oversized media, such as large maps or blueprints exceeding
-110 cm or 43 inches in either dimension, and at high DPI.)
+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.
+internal limits are downsampled (32767 pixels on either dimension).
 
 You will also need to set ``--tesseract-timeout`` high enough to allow
 for processing.
@@ -227,6 +228,59 @@ then run ocrmypdf as follows (along with any other desired arguments):
    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
 =========================
 
@@ -391,7 +445,7 @@ 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
+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:
 
@@ -400,6 +454,10 @@ whether it succeeded or failed. An example message is:
     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
@@ -411,9 +469,9 @@ suffix indicates the file type. Some important files include:
    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
+-  ``_ocr_hocr.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,
+-  ``_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

docs/api.rst

@@ -112,7 +112,9 @@ 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.
+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
 ----------

docs/batch.rst

@@ -44,7 +44,7 @@ place, and printing each filename in between runs:
 
 .. code-block:: bash
 
-   find . -printf '%p\n' -name '*.pdf' -exec ocrmypdf '{}' '{}' \;
+   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
@@ -135,7 +135,7 @@ Users may need to customize the script to meet their requirements.
     "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_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 to report"
 

docs/conf.py

@@ -42,7 +42,7 @@ extensions = [
 ]
 
 # 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"
 

docs/cookbook.rst

@@ -187,7 +187,7 @@ might remove desirable content, especially from poor quality scans.
    background from grayscale or color images. Monochrome images are
    ignored. This should not be used on documents that contain color
    photos as it may remove them.
--  ``--deskew`` will correct pages were scanned at a skewed angle by
+-  ``--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
@@ -245,6 +245,20 @@ if all you want to is to apply image processing or PDF/A conversion.
     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
 --------------------------------------
 
@@ -385,7 +399,7 @@ Some users may consider enabling lossy JBIG2. See: :ref:`jbig2-lossy`.
 Digitally signed PDFs
 =====================
 
-OCRmyPDF cannot preserve digital signatures in PDFs and also add to OCR to them.
+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.
@@ -393,4 +407,4 @@ 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.
+without warning.

docs/docker.rst

@@ -42,7 +42,7 @@ execute the image:
      - Architecture
      - Description
    * - ``jbarlow83/ocrmypdf-alpine``
-     - x86_64 only
+     - x86_64 and arm64
      - Recommended image, based on Alpine Linux.
    * - ``jbarlow83/ocrmypdf-ubuntu``
      - x86_64 and arm64
@@ -65,7 +65,13 @@ 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/>`__.
+`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
 ==========================================
@@ -81,7 +87,7 @@ To start a Docker container (instance of the image):
 
 .. code-block:: bash
 
-   docker tag jbarlow83/ocrmypdf ocrmypdf
+   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

docs/installation.rst

@@ -23,14 +23,14 @@ These platforms have one-liner installs:
 +-------------------------------+-----------------------------------------+
 | Fedora                        | ``dnf install ocrmypdf tesseract-osd``  |
 +-------------------------------+-----------------------------------------+
-| macOS                         | ``brew install ocrmypdf``               |
+| 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``               |
 +-------------------------------+-----------------------------------------+
 
@@ -99,12 +99,12 @@ For full details on version availability for your platform, check the
 Fedora
 ------
 
-.. |fedora-37| image:: https://repology.org/badge/version-for-repo/fedora_37/ocrmypdf.svg
-    :alt: Fedora 37
-
 .. |fedora-38| image:: https://repology.org/badge/version-for-repo/fedora_38/ocrmypdf.svg
     :alt: Fedora 38
 
+.. |fedora-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
 
@@ -113,7 +113,7 @@ Fedora
 +-----------------------------------------------+
 | |latest|                                      |
 +-----------------------------------------------+
-| |fedora-37| |fedora-38| |fedora-rawhide|      |
+| |fedora-38| |fedora-39| |fedora-rawhide|      |
 +-----------------------------------------------+
 
 Users of Fedora may simply
@@ -123,7 +123,7 @@ Users of Fedora may simply
     dnf install ocrmypdf tesseract-osd
 
 For full details on version availability, check the `Fedora Package
-Tracker <https://apps.fedoraproject.org/packages/ocrmypdf>`__.
+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
@@ -135,10 +135,36 @@ from sources <#installing-head-revision-from-sources>`__.
    issues. OCRmyPDF works fine without it but will produce larger output
    files. If you build jbig2enc from source, ocrmypdf 7.0.0 and later
    will automatically detect it on the ``PATH``. To add JBIG2 encoding,
-   see `Installing the JBIG2 encoder <jbig2>`__.
+   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
 -------------------------------------------------
 
@@ -162,37 +188,13 @@ To add JBIG2 encoding, see :ref:`jbig2`.
 Ubuntu 20.04 LTS
 ----------------
 
-Ubuntu 20.04 includes ocrmypdf 9.6.0 - you can install that with ``apt``. To
-install a more recent version, uninstall the system-provided version of
-ocrmypdf, and install the following dependencies:
+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
 
-    sudo apt-get -y remove ocrmypdf  # remove system ocrmypdf, if installed
-    sudo apt-get -y update
-    sudo apt-get -y install \
-        ghostscript \
-        icc-profiles-free \
-        libxml2 \
-        pngquant \
-        python3-pip \
-        tesseract-ocr \
-        zlib1g
-
-To install ocrmypdf for the system:
-
-.. code-block:: bash
-
-    pip3 install ocrmypdf
-
-To install for the current user only:
-
-.. code-block:: bash
-
-    export PATH=$HOME/.local/bin:$PATH
-    pip3 install --user ocrmypdf
-
-To add JBIG2 encoding, see :ref:`jbig2`.
+    brew install ocrmypdf
 
 Arch Linux (AUR)
 ----------------
@@ -215,12 +217,12 @@ you are using a VM image, such as `the official Vagrant image
 be completed for you.
 
 Next you should install the `base-devel package group
-<https://www.archlinux.org/groups/x86_64/base-devel/>`__. This includes the
+<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 base-devel
+   sudo pacman -S --needed base-devel
 
 Now you are ready to install the OCRmyPDF package.
 
@@ -258,7 +260,7 @@ page.
     <https://aur.archlinux.org/packages/jbig2enc-git/>`__ and may be installed
     using the same series of steps as for the installation OCRmyPDF AUR
     package. Alternatively, it may be built manually from source following the
-    instructions in `Installing the JBIG2 encoder <jbig2>`__.  If JBIG2 is
+    instructions in :ref:`Installing the JBIG2 encoder <jbig2>`.  If JBIG2 is
     installed, OCRmyPDF 7.0.0 and later will automatically detect it.
 
 Alpine Linux
@@ -323,6 +325,22 @@ languages you can optionally install them all:
 
     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
 ----------------------------
 
@@ -404,7 +422,7 @@ the following when running in an Administrator command prompt):
 * ``choco install --pre tesseract``
 * ``choco install pngquant`` (optional)
 
-Either set of commands will install the required software. At the mmoment there is no
+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
@@ -540,9 +558,25 @@ try:
 
     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
 -------------------------------------
 
@@ -553,7 +587,7 @@ manager. ``pip`` cannot provide them.
 The following versions are required:
 
 -  Python 3.10 or newer
--  Ghostscript 9.55 or newer
+-  Ghostscript 9.54 or newer
 -  Tesseract 4.1.1 or newer
 -  jbig2enc 0.29 or newer
 -  pngquant 2.5 or newer
@@ -604,8 +638,7 @@ environment:
 
     pip install git+https://github.com/ocrmypdf/OCRmyPDF.git
 
-Or, to install in `development
-mode <https://pythonhosted.org/setuptools/setuptools.html#development-mode>`__,
+Or, to install in editable mode
 allowing customization of OCRmyPDF, use the ``-e`` flag:
 
 .. code-block:: bash
@@ -645,7 +678,7 @@ 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
+    python -m venv .venv
     source .venv/bin/activate
     cd OCRmyPDF
     pip install -e .[test]
@@ -671,7 +704,7 @@ To manually install the ``fish`` completion, copy
 Note on 32-bit support
 ======================
 
-Many Python libraries no longer 32-bit binary wheels for Linux. This
+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.
@@ -681,4 +714,4 @@ 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.
+ARM NAS or Raspberry Pi processing small documents, it should work.

docs/jbig2.rst

@@ -41,7 +41,15 @@ For all other platforms, you would need to build the JBIG2 encoder from source:
 
 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.
+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
 ================

docs/languages.rst

@@ -18,16 +18,26 @@ Tesseract's documentation also lists the three-letter code for your language.
 Some are anglicized, e.g. Spanish is ``spa`` rather than ``esp``, while others
 are not, e.g. German is ``deu`` and French is ``fra``.
 
+Language packs (strictly speaking, Tesseract "traineddata" files) generally correspond
+to the language in question, but different language packs are used in certain
+situations. For German, the "Fraktur" language pack can assist with reading older
+materials in the Fraktur typeface family (``deu_frak``). Some communities have changed
+their script from Cyrillic to Latin; the Cyrillic version of Uzbek is available
+as ``uzb_cyrl`` and the Latin version is ``uzb``.
+
 After you have installed a language pack, you can use it with ``ocrmypdf -l <language>``,
 for example ``ocrmypdf -l spa``. For multilingual documents, you can specify
 all languages to be expected, e.g. ``ocrmypdf -l eng+fra`` for English and French.
 English is assumed by default unless other language(s) are specified.
 
 For Linux users, you can often find packages that provide language
-packs:
+packs.
 
-Debian and Ubuntu users
-=======================
+Platform install steps
+======================
+
+Debian and Ubuntu (apt)
+-----------------------
 
 .. code-block:: bash
 
@@ -42,8 +52,8 @@ to what languages it should search for. Multiple languages can be
 requested using either ``-l eng+fra`` (English and French) or
 ``-l eng -l fra``.
 
-Fedora users
-============
+Fedora
+------
 
 .. code-block:: bash
 
@@ -58,8 +68,24 @@ to what languages it should search for. Multiple languages can be
 requested using either ``-l eng+fra`` (English and French) or
 ``-l eng -l fra``.
 
-Gentoo users
-============
+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``.
@@ -85,23 +111,31 @@ to what languages it should search for. Multiple languages can be
 requested using either ``-l eng+fra`` (English and French) or
 ``-l eng -l fra``.
 
-macOS users
-===========
+macOS
+-----
 
 You can install additional language packs by
 :ref:`installing Tesseract using Homebrew with all language packs <macos-all-languages>`.
 
-Docker users
-============
+Docker
+------
 
 Users of the OCRmyPDF Docker image should install language packs into a
 derived Docker image as
 :ref:`described in that section <docker-lang-packs>`.
 
-Windows users
-=============
+Windows
+-------
 
 The Tesseract installer provided by Chocolatey currently includes only English language.
 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.

docs/maintainers.rst

@@ -38,12 +38,13 @@ 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
+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.
+necessary, or set the environment variable ``SETUPTOOLS_SCM_PRETEND_VERSION``
+to the required version, if you need to override versioning for some reason.
 
 jbig2enc
 --------
@@ -64,4 +65,13 @@ installation documentation.
 
 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.
+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.

docs/plugins.rst

@@ -29,6 +29,9 @@ 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
 ==============
 
@@ -70,14 +73,15 @@ similar to ``pytest`` packages such as ``pytest-cov`` (the package) and
     module), just like pytest plugins. At the same time, please make it clear
     that your package is not official.
 
-Setuptools plugins
-==================
+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.
+installed in the same virtual environment, using a project entrypoint.
+OCRmyPDF uses the entrypoint namespace "ocrmypdf".
 
-Your package's ``pyproject.toml`` would need to contain the following, for a plugin
-named ``ocrmypdf-exampleplugin``:
+For example, ``pyproject.toml`` would need to contain the following, for a plugin named
+``ocrmypdf-exampleplugin``:
 
 .. code-block:: toml
 
@@ -87,13 +91,6 @@ named ``ocrmypdf-exampleplugin``:
     [project.entry-points."ocrmypdf"]
     exampleplugin = "exampleplugin.pluginmodule"
 
-.. code-block:: ini
-
-    # equivalent setup.cfg
-    [options.entry_points]
-    ocrmypdf =
-        exampleplugin = exampleplugin.pluginmodule
-
 Plugin requirements
 ===================
 

docs/release_notes.rst

@@ -30,6 +30,189 @@ OCRmyPDF typically supports the three most recent Python versions.
 
 .. |OCRmyPDF PyPI| image:: https://img.shields.io/pypi/v/ocrmypdf.svg
 
+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
 =======
 

misc/batch.py

@@ -1,5 +1,6 @@
 #!/usr/bin/env python3
 # SPDX-FileCopyrightText: 2016 findingorder <https://github.com/findingorder>
+# SPDX-FileCopyrightText: 2024 nilsro <https://github.com/nilsro>
 # SPDX-License-Identifier: MIT
 
 """Example of using ocrmypdf as a library in a script.
@@ -13,7 +14,11 @@ You should edit this script to meet your needs.
 
 from __future__ import annotations
 
+import filecmp
 import logging
+import os
+import posixpath
+import shutil
 import sys
 from pathlib import Path
 
@@ -22,32 +27,65 @@ import ocrmypdf
 # pylint: disable=logging-format-interpolation
 # pylint: disable=logging-not-lazy
 
+
+def filecompare(a, b):
+    try:
+        return filecmp.cmp(a, b, shallow=True)
+    except FileNotFoundError:
+        return False
+
+
 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(".")
 
 if len(sys.argv) > 2:
     log_file = Path(sys.argv[2])
 else:
-    log_file = script_dir.with_name('ocr-tree.log')
+    log_file = script_dir.with_name("ocr-tree.log")
 
 logging.basicConfig(
     level=logging.INFO,
-    format='%(asctime)s %(message)s',
+    format="%(asctime)s %(message)s",
     filename=log_file,
-    filemode='a',
+    filemode="a",
 )
 
+logging.info(f"Start directory {start_dir}")
+
 ocrmypdf.configure_logging(ocrmypdf.Verbosity.default)
 
-for filename in start_dir.glob("**/*.py"):
+for filename in start_dir.glob("**/*.pdf"):
     logging.info(f"Processing {filename}")
-    result = ocrmypdf.ocr(filename, filename, deskew=True)
-    if result == ocrmypdf.ExitCode.already_done_ocr:
-        logging.error("Skipped document because it already contained text")
-    elif result == ocrmypdf.ExitCode.ok:
+    if ocrmypdf.pdfa.file_claims_pdfa(filename)["pass"]:
+        logging.info("Skipped document because it already contained text")
+    else:
+        archive_filename = archive_dir + str(filename)
+        if len(archive_dir) > 0 and not filecompare(filename, archive_filename):
+            logging.info(f"Archiving document to {archive_filename}")
+            try:
+                shutil.copy2(filename, posixpath.dirname(archive_filename))
+            except OSError:
+                os.makedirs(posixpath.dirname(archive_filename))
+                shutil.copy2(filename, posixpath.dirname(archive_filename))
+        try:
+            result = ocrmypdf.ocr(filename, filename, deskew=True)
+            logging.info(result)
+        except ocrmypdf.exceptions.EncryptedPdfError:
+            logging.info("Skipped document because it is encrypted")
+        except ocrmypdf.exceptions.PriorOcrFoundError:
+            logging.info("Skipped document because it already contained text")
+        except ocrmypdf.exceptions.DigitalSignatureError:
+            logging.info("Skipped document because it has a digital signature")
+        except ocrmypdf.exceptions.TaggedPDFError:
+            logging.info(
+                "Skipped document because it does not need ocr as it is tagged"
+            )
+        except Exception:
+            logging.error("Unhandled error occured")
         logging.info("OCR complete")
-    logging.info(result)

misc/bisect_pdf.py

@@ -0,0 +1,42 @@
+#!/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."""
+
+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")

misc/synology.py

@@ -53,9 +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)
-        with open(filename, 'rb') as input_file, open(
-            full_path_ocr, 'wb'
-        ) as output_file:
+        with (
+            open(filename, 'rb') as input_file,
+            open(full_path_ocr, 'wb') as output_file,
+        ):
             proc = subprocess.run(
                 cmd,
                 stdin=input_file,

misc/watcher.py

@@ -7,7 +7,6 @@
 
 # Do not enable annotations!
 # https://github.com/tiangolo/typer/discussions/598
-# from __future__ import annotations
 
 import json
 import logging
@@ -47,15 +46,18 @@ class LoggingLevelEnum(str, Enum):
     CRITICAL = "CRITICAL"
 
 
-def get_output_dir(root: Path, basename: str, output_dir_year_month: bool) -> Path:
+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()
         output_directory_year_month = root / str(today.year) / f'{today.month:02d}'
         if not output_directory_year_month.exists():
             output_directory_year_month.mkdir(parents=True, exist_ok=True)
-        output_path = Path(output_directory_year_month) / basename
+        output_path = Path(output_directory_year_month) / Path(basename).with_suffix(
+            '.pdf'
+        )
     else:
-        output_path = root / basename
+        output_path = root / Path(basename).with_suffix('.pdf')
     return output_path
 
 
@@ -99,7 +101,7 @@ def execute_ocrmypdf(
     retries_loading_file: int,
     output_dir_year_month: bool,
 ):
-    output_path = get_output_dir(output_dir, file_path.name, output_dir_year_month)
+    output_path = get_output_path(output_dir, file_path.name, output_dir_year_month)
 
     log.info("-" * 20)
     log.info(f'New file: {file_path}. Waiting until fully written...')
@@ -131,7 +133,7 @@ def execute_ocrmypdf(
 
 
 class HandleObserverEvent(PatternMatchingEventHandler):
-    def __init__(
+    def __init__(  # noqa: D107
         self,
         patterns=None,
         ignore_patterns=None,
@@ -191,7 +193,7 @@ def main(
         bool,
         typer.Option(
             envvar='OCR_OUTPUT_DIRECTORY_YEAR_MONTH',
-            help='Create a subdirectory in the output directory for each year and month',
+            help='Create a subdirectory in the output directory for each year/month',
         ),
     ] = False,
     on_success_delete: Annotated[

pyproject.toml

@@ -1,8 +1,8 @@
 # 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", "hatch-vcs"]
+build-backend = "hatchling.build"
 
 [project]
 name = "ocrmypdf"
@@ -12,12 +12,13 @@ readme = "README.md"
 license = { text = "MPL-2.0" }
 requires-python = ">=3.10"
 dependencies = [
-  "Pillow>=10.0.1",
   "deprecation>=2.1.0",
   "img2pdf>=0.5",
   "packaging>=20",
   "pdfminer.six>=20220319",
+  "pi-heif",                # Heif image format - maintainers: if this is removed, it will NOT break
   "pikepdf>=8.10.1",
+  "Pillow>=10.0.1",
   "pluggy>=1",
   "rich>=13",
 ]
@@ -45,6 +46,7 @@ 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/docs/release_notes.rst"
 
 [project.optional-dependencies]
 docs = ["sphinx", "sphinx-issues", "sphinx-rtd-theme"]
@@ -60,47 +62,21 @@ test = [
   "types-Pillow",
   "types-humanfriendly",
 ]
-watcher = ["watchdog>=1.0.2", "typer[all]", "python-dotenv"]
+watcher = ["watchdog>=1.0.2", "typer-slim[standard]", "python-dotenv"]
 webservice = ["Flask>=2.0.1"]
 
 [project.scripts]
 ocrmypdf = "ocrmypdf.__main__:run"
 
-[tool.setuptools.package-data]
-ocrmypdf = ["data/sRGB.icc", "py.typed"]
+[tool.hatch.version]
+source = "vcs"
 
-[tool.setuptools.packages.find]
-where = ["src"]
-namespaces = false
-
-[tool.setuptools_scm]
+[tool.hatch.build.hooks.vcs]
+version-file = "src/ocrmypdf/_version.py"
 
 [tool.distutils.bdist_wheel]
 python-tag = "py310"
 
-[tool.black]
-line-length = 88
-target-version = ["py310", "py311", "py312"]
-skip-string-normalization = true
-include = '\.pyi?$'
-exclude = '''
-/(
-    \.eggs
-  | \.git
-  | \.hg
-  | \.mypy_cache
-  | \.tox
-  | \.venv
-  | _build
-  | buck-out
-  | build
-  | dist
-  | docs
-  | misc
-  | \.egg-info
-)/
-'''
-
 [tool.coverage.run]
 branch = true
 parallel = true
@@ -131,15 +107,17 @@ norecursedirs = ["lib", ".pc", ".git", "venv", "output", "cache", "resources"]
 testpaths = ["tests"]
 addopts = "-n auto"
 markers = ["slow"]
-filterwarnings = ["ignore:.*XMLParser.*:DeprecationWarning"]
+filterwarnings = [
+  "ignore:.*XMLParser.*:DeprecationWarning",
+  "ignore:.*ast.NameConstant.*:DeprecationWarning:reportlab",
+  "ignore:.*distutils.*:DeprecationWarning:libxmp",
+]
 
 [tool.mypy]
 
 [[tool.mypy.overrides]]
 module = [
   'pluggy',
-  'tqdm',
-  'coloredlogs',
   'img2pdf',
   'pdfminer.*',
   'reportlab.*',
@@ -149,7 +127,10 @@ module = [
 ignore_missing_imports = true
 
 [tool.ruff]
-select = [
+target-version = "py310"
+
+[tool.ruff.lint]
+"select" = [
   "D",    # pydocstyle
   "E",    # pycodestyle
   "W",    # pycodestyle
@@ -157,17 +138,26 @@ select = [
   "I001", # isort
   "UP",   # pyupgrade
 ]
-target-version = "py310"
 
-[tool.ruff.isort]
+[tool.ruff.lint.isort]
 known-first-party = ["ocrmypdf"]
-required-imports = ["from __future__ import annotations"]
 
-[tool.ruff.pydocstyle]
+[tool.ruff.lint.pydocstyle]
 convention = "google"
 
-[tool.ruff.per-file-ignores]
+[tool.ruff.lint.per-file-ignores]
 "docs/conf.py" = ["D100", "D101", "D105"]
 "tests/*.py" = ["D100", "D101", "D102", "D103", "D105"]
 "misc/*.py" = ["D103", "D101", "D102"]
 "src/ocrmypdf/builtin_plugins/*.py" = ["D103", "D102", "D105"]
+
+[tool.ruff.format]
+quote-style = "preserve"
+
+[dependency-groups]
+dev = [
+  "mypy>=1.13.0",
+  "pymupdf>=1.24.14",
+  "streamlit-pdf-viewer>=0.0.19",
+  "streamlit>=1.40.2",
+]

snapcraft.yaml

@@ -18,8 +18,8 @@ architectures: [amd64]
 
 environment:
   TESSDATA_PREFIX: $SNAP/usr/share/tesseract-ocr/4.00/tessdata
-  GS_LIB: $SNAP/usr/share/ghostscript/9.55/Resource/Init
-  GS_FONTPATH: $SNAP/usr/share/ghostscript/9.55/Resource/Font
+  GS_LIB: $SNAP/usr/share/ghostscript/9.55.0/Resource/Init
+  GS_FONTPATH: $SNAP/usr/share/ghostscript/9.55.0/Resource/Font
   LD_LIBRARY_PATH: $SNAP/usr/lib/x86_64-linux-gnu
 
 apps:

src/ocrmypdf/__init__.py

@@ -9,11 +9,12 @@ 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._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,
@@ -37,7 +38,6 @@ from ocrmypdf.pluginspec import OcrEngine, OrientationConfidence
 
 hookimpl = _HookimplMarker('ocrmypdf')
 
-
 __all__ = [
     '__version__',
     'BadArgsError',

src/ocrmypdf/_annots.py

@@ -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

src/ocrmypdf/_concurrent.py

@@ -7,8 +7,8 @@ from __future__ import annotations
 
 import threading
 from abc import ABC, abstractmethod
-from collections.abc import Iterable
-from typing import Any, Callable, TypeVar
+from collections.abc import Callable, Iterable
+from typing import Any, TypeVar
 
 from ocrmypdf._progressbar import NullProgressBar, ProgressBar
 

src/ocrmypdf/_defaults.py

@@ -0,0 +1,10 @@
+# SPDX-FileCopyrightText: 2024 James R. Barlow
+# SPDX-License-Identifier: MPL-2.0
+
+# Enforce English hegemony
+DEFAULT_LANGUAGE = 'eng'
+
+# Default rotation threshold
+DEFAULT_ROTATE_PAGES_THRESHOLD = 14.0
+
+PROGRAM_NAME = 'OCRmyPDF'

src/ocrmypdf/_exec/ghostscript.py

@@ -125,7 +125,7 @@ def rasterize_pdf(
         + (['-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 +137,15 @@ 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)
 
     try:
-        with Image.open(BytesIO(p.stdout)) as im:
+        with Image.open(output_file) as im:
             if rotation is not None:
                 log.debug("Rotating output by %i", rotation)
                 # rotation is a clockwise angle and Image.ROTATE_* is
@@ -157,13 +158,19 @@ 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:
@@ -177,6 +184,17 @@ class GhostscriptFollower:
         self.progressbar_class = progressbar_class
         self.progressbar = None
 
+    def __enter__(self):
+        # We can't actually set up the progressbar here, because we don't know
+        # how many pages there are until the first __call__() happens. So we
+        # do it in __call__().
+        return self
+
+    def __exit__(self, exc_type, exc_value, traceback):
+        if self.progressbar:
+            return self.progressbar.__exit__(exc_type, exc_value, traceback)
+        return False
+
     def __call__(self, line):
         if not self.progressbar_class:
             return
@@ -187,7 +205,8 @@ class GhostscriptFollower:
                 self.progressbar = self.progressbar_class(
                     total=self.count, desc="PDF/A conversion", unit='page'
                 )
-                return
+                # Now that we know the count, we can set up the progressbar.
+                self.progressbar.__enter__()
         else:
             if self.re_page.match(line.strip()):
                 self.progressbar.update()
@@ -259,22 +278,21 @@ def generate_pdfa(
             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:
+        with GhostscriptFollower(progressbar_class) as pbar:
             p = run_polling_stderr(
                 args_gs,
-                stdout=output,
                 stderr=PIPE,
                 check=True,
                 text=True,
                 encoding='utf-8',
                 errors='replace',
-                callback=GhostscriptFollower(progressbar_class),
+                callback=pbar,
             )
     except CalledProcessError as e:
         # Ghostscript does not change return code when it fails to create

src/ocrmypdf/_exec/jbig2enc.py

@@ -5,7 +5,7 @@
 
 from __future__ import annotations
 
-from subprocess import PIPE
+from subprocess import PIPE, CalledProcessError
 
 from packaging.version import Version
 
@@ -14,7 +14,13 @@ from ocrmypdf.subprocess import get_version, run
 
 
 def version() -> Version:
-    return Version(get_version('jbig2', regex=r'jbig2enc (\d+(\.\d+)*).*'))
+    try:
+        version = get_version('jbig2', regex=r'jbig2enc (\d+(\.\d+)*).*')
+    except CalledProcessError as e:
+        # TeX Live for Windows provides an incompatible jbig2.EXE which may
+        # be on the PATH.
+        raise MissingDependencyError('jbig2enc') from e
+    return Version(version)
 
 
 def available():

src/ocrmypdf/_exec/tesseract.py

@@ -220,7 +220,8 @@ def get_deskew(
 
 def tesseract_log_output(stream: bytes) -> None:
     tlog = TesseractLoggerAdapter(
-        log, extra=log.extra if hasattr(log, 'extra') else None  # type: ignore
+        log,
+        extra=log.extra if hasattr(log, 'extra') else None,  # type: ignore
     )
 
     if not stream:

src/ocrmypdf/_exec/unpaper.py

@@ -8,19 +8,17 @@ from __future__ import annotations
 import logging
 import os
 import shlex
-import sys
 from collections.abc import Iterator
 from contextlib import contextmanager
 from decimal import Decimal
 from pathlib import Path
 from subprocess import PIPE, STDOUT
 from tempfile import TemporaryDirectory
-from typing import Union
 
 from packaging.version import Version
 from PIL import Image
 
-from ocrmypdf.exceptions import MissingDependencyError, SubprocessOutputError
+from ocrmypdf.exceptions import SubprocessOutputError
 from ocrmypdf.subprocess import get_version, run
 
 # unpaper documentation:
@@ -29,7 +27,7 @@ from ocrmypdf.subprocess import get_version, run
 
 UNPAPER_IMAGE_PIXEL_LIMIT = 256 * 1024 * 1024
 
-DecFloat = Union[Decimal, float]
+DecFloat = Decimal | float
 
 log = logging.getLogger(__name__)
 
@@ -50,7 +48,7 @@ class UnpaperImageTooLargeError(Exception):
 
 
 def version() -> Version:
-    return Version(get_version('unpaper'))
+    return Version(get_version('unpaper', regex=r'(?m).*?(\d+(\.\d+)(\.\d+)?)'))
 
 
 @contextmanager

src/ocrmypdf/_graft.py

@@ -289,9 +289,9 @@ class OcrGrafter:
 
             # Translate the text so it is centered at (0, 0), rotate it there, adjust
             # for a size different between initial and text PDF, then untranslate, and
-            # finally move the lower left corner to match the mediabox. All transforms
-            # must be premultiplied so they are applied in reverse order here.
-            ctm = corner @ untranslate @ scale @ rotate @ translate
+            # finally move the lower left corner to match the mediabox.
+            ctm = translate @ rotate @ scale @ untranslate @ corner
+            log.debug("Grafting with ctm %r", ctm)
 
             base_resources = _ensure_dictionary(base_page.obj, Name.Resources)
             base_xobjs = _ensure_dictionary(base_resources, Name.XObject)
@@ -311,9 +311,16 @@ class OcrGrafter:
 
             if strip_old_text:
                 strip_invisible_text(self.pdf_base, base_page)
-
+            base_page.contents_coalesce()
+            if self.render_mode == RenderMode.ON_TOP:
+                # Add q/Q to ensure content we append is drawn correctly
+                # Strictly speaking this needs to trace the whole q/Q stack in case
+                # stack is not balanced.
+                original = base_page.Contents.read_bytes()
+                base_page.Contents.write(b'q\n' + original + b'\nQ\n')
             base_page.contents_add(
-                new_text_layer, prepend=self.render_mode == RenderMode.ON_TOP
+                new_text_layer, prepend=self.render_mode == RenderMode.UNDERNEATH
             )
+            base_page.contents_coalesce()
 
             _update_resources(obj=base_page.obj, font=font, font_key=font_key)

src/ocrmypdf/_jobcontext.py

@@ -93,8 +93,8 @@ class PageContext:
         state = self.__dict__.copy()
 
         state['options'] = copy(self.options)
-        if not isinstance(state['options'].input_file, (str, bytes, os.PathLike)):
+        if not isinstance(state['options'].input_file, str | bytes | os.PathLike):
             state['options'].input_file = 'stream'
-        if not isinstance(state['options'].output_file, (str, bytes, os.PathLike)):
+        if not isinstance(state['options'].output_file, str | bytes | os.PathLike):
             state['options'].output_file = 'stream'
         return state

src/ocrmypdf/_logging.py

@@ -26,5 +26,5 @@ class PageNumberFilter(logging.Filter):
 class RichLoggingHandler(RichHandler):
     def __init__(self, console: Console, **kwargs):
         super().__init__(
-            console=console, show_level=False, show_time=False, markup=True, **kwargs
+            console=console, show_level=False, show_time=False, markup=False, **kwargs
         )

src/ocrmypdf/_metadata.py

@@ -15,8 +15,9 @@ from pikepdf import Dictionary, Name, Pdf
 from pikepdf import __version__ as PIKEPDF_VERSION
 from pikepdf.models.metadata import PdfMetadata, encode_pdf_date
 
+from ocrmypdf._annots import remove_broken_goto_annotations
+from ocrmypdf._defaults import PROGRAM_NAME
 from ocrmypdf._jobcontext import PdfContext
-from ocrmypdf._version import PROGRAM_NAME
 from ocrmypdf._version import __version__ as OCRMYPF_VERSION
 from ocrmypdf.languages import iso_639_2_from_3
 
@@ -153,22 +154,52 @@ def _set_language(pdf: Pdf, languages: list[str]):
     pdf.Root.Lang = iso639_2
 
 
+class MetadataProgress:
+    def __init__(self, progressbar_class, enable: bool = True):
+        self.progressbar_class = progressbar_class
+        self.progressbar = self.progressbar_class(
+            total=100, desc="Linearizing", unit='%', disable=not enable
+        )
+
+    def __enter__(self):
+        self.progressbar.__enter__()
+        return self
+
+    def __exit__(self, exc_type, exc_value, traceback):
+        return self.progressbar.__exit__(exc_type, exc_value, traceback)
+
+    def __call__(self, percent: int):
+        if not self.progressbar_class:
+            return
+        self.progressbar.update(completed=percent)
+
+
 def metadata_fixup(
     working_file: Path, context: PdfContext, pdf_save_settings: dict[str, Any]
 ) -> Path:
-    """Fix certain metadata fields after Ghostscript PDF/A conversion.
+    """Fix certain metadata fields whether PDF or PDF/A.
+
+    Override some of Ghostscript's metadata choices.
 
     Also report on metadata in the input file that was not retained during
-    PDF/A conversion.
+    conversion.
     """
     output_file = context.get_path('metafix.pdf')
     options = context.options
 
-    with Pdf.open(context.origin) as original, Pdf.open(working_file) as pdf:
+    pbar_class = context.plugin_manager.hook.get_progressbar_class()
+    with (
+        Pdf.open(context.origin) as original,
+        Pdf.open(working_file) as pdf,
+        MetadataProgress(pbar_class, options.progress_bar) as pbar,
+    ):
         docinfo = get_docinfo(original, context)
-        with original.open_metadata(
-            set_pikepdf_as_editor=False, update_docinfo=False, strict=False
-        ) as meta_original, pdf.open_metadata() as meta_pdf:
+        with (
+            original.open_metadata(
+                set_pikepdf_as_editor=False, update_docinfo=False, strict=False
+            ) as meta_original,
+            pdf.open_metadata() as meta_pdf,
+        ):
             meta_pdf.load_from_docinfo(
                 docinfo, delete_missing=False, raise_failure=False
             )
@@ -179,6 +210,6 @@ def metadata_fixup(
             report_on_metadata(options, meta_missing)
 
         _set_language(pdf, options.languages)
-        pdf.save(output_file, **pdf_save_settings)
+        pdf.save(output_file, progress=pbar, **pdf_save_settings)
 
     return output_file

src/ocrmypdf/_pipeline.py

@@ -12,8 +12,9 @@ import re
 import sys
 from collections.abc import Iterable, Iterator, Sequence
 from contextlib import suppress
+from io import BytesIO
 from pathlib import Path
-from shutil import copyfileobj, copystat
+from shutil import copyfileobj
 from typing import Any, BinaryIO, TypeVar, cast
 
 import img2pdf
@@ -34,17 +35,29 @@ from ocrmypdf.exceptions import (
     UnsupportedImageFormatError,
 )
 from ocrmypdf.helpers import IMG2PDF_KWARGS, Resolution, safe_symlink
-from ocrmypdf.hocrtransform import HocrTransform
+from ocrmypdf.hocrtransform import DebugRenderOptions, HocrTransform
+from ocrmypdf.hocrtransform._font import Courier
 from ocrmypdf.pdfa import generate_pdfa_ps
 from ocrmypdf.pdfinfo import Colorspace, Encoding, PageInfo, PdfInfo
 from ocrmypdf.pluginspec import OrientationConfidence
 
+try:
+    from pi_heif import register_heif_opener
+except ImportError:
+
+    def register_heif_opener():
+        pass
+
+
 T = TypeVar("T")
 log = logging.getLogger(__name__)
 
 VECTOR_PAGE_DPI = 400
 
 
+register_heif_opener()
+
+
 def triage_image_file(input_file: Path, output_file: Path, options) -> None:
     """Triage the input image file.
 
@@ -129,7 +142,7 @@ def _pdf_guess_version(input_file: Path, search_window=1024) -> str:
     """
     with open(input_file, 'rb') as f:
         signature = f.read(search_window)
-    m = re.search(br'%PDF-(\d\.\d)', signature)
+    m = re.search(rb'%PDF-(\d\.\d)', signature)
     if m:
         return m.group(1).decode('ascii')
     return ''
@@ -146,8 +159,13 @@ def triage(
                     "Argument --image-dpi is being ignored because the "
                     "input file is a PDF, not an image."
                 )
-            # Origin file is a pdf create a symlink with pdf extension
-            safe_symlink(input_file, output_file)
+            try:
+                with pikepdf.open(input_file) as pdf:
+                    pdf.save(output_file)
+            except pikepdf.PdfError as e:
+                raise InputFileError() from e
+            except pikepdf.PasswordError as e:
+                raise EncryptedPdfError() from e
             return output_file
     except OSError as e:
         log.debug(f"Temporary file was at: {input_file}")
@@ -462,7 +480,7 @@ def calculate_raster_dpi(page_context: PageContext):
     page_dpi = get_page_square_dpi(page_context, image_dpi)
     if dpi_profile and dpi_profile.average_to_max_dpi_ratio < 0.8:
         log.warning(
-            "Weight average image DPI is %0.1f, max DPI is %0.1f. "
+            "Weighted average image DPI is %0.1f, max DPI is %0.1f. "
             "The discrepancy may indicate a high detail region on this page, "
             "but could also indicate a problem with the input PDF file. "
             "Page image will be rendered at %0.1f DPI.",
@@ -712,19 +730,29 @@ def create_pdf_page_from_image(
     pageinfo = page_context.pageinfo
     pagesize = 72.0 * float(pageinfo.width_inches), 72.0 * float(pageinfo.height_inches)
     effective_rotation = (pageinfo.rotation - orientation_correction) % 360
-    if effective_rotation % 180 == 90:
+    swap_axis = effective_rotation % 180 == 90
+    if swap_axis:
         pagesize = pagesize[1], pagesize[0]
 
-    # This create a single page PDF
-    with open(image, 'rb') as imfile, open(output_file, 'wb') as pdf:
+    # Create a new single page PDF to hold
+    bio = BytesIO()
+    with open(image, 'rb') as imfile:
         log.debug('convert')
 
         layout_fun = img2pdf.get_layout_fun(pagesize)
         img2pdf.convert(
-            imfile, layout_fun=layout_fun, outputstream=pdf, **IMG2PDF_KWARGS
+            imfile,
+            layout_fun=layout_fun,
+            outputstream=bio,
+            engine=img2pdf.Engine.pikepdf,
+            rotation=img2pdf.Rotation.ifvalid,
         )
         log.debug('convert done')
 
+    # img2pdf does not generate boxes correctly, so we fix them
+    bio.seek(0)
+    fix_pagepdf_boxes(bio, output_file, page_context, swap_axis=swap_axis)
+
     output_file = page_context.plugin_manager.hook.filter_pdf_page(
         page=page_context, image_filename=image, output_pdf=output_file
     )
@@ -741,15 +769,27 @@ def render_hocr_page(hocr: Path, page_context: PageContext) -> Path:
         return output_file
 
     dpi = get_page_square_dpi(page_context, calculate_image_dpi(page_context))
-    debug_mode = options.pdf_renderer == 'hocrdebug'
-
+    debug_kwargs = {}
+    if options.pdf_renderer == 'hocrdebug':
+        debug_kwargs = dict(
+            debug_render_options=DebugRenderOptions(
+                render_baseline=True,
+                render_triangle=True,
+                render_line_bbox=False,
+                render_word_bbox=True,
+                render_paragraph_bbox=False,
+                render_space_bbox=False,
+            ),
+            font=Courier(),
+        )
     HocrTransform(
         hocr_filename=hocr,
-        dpi=dpi.to_scalar(),  # square
-        debug=debug_mode,
+        dpi=dpi.to_scalar(),
+        **debug_kwargs,  # square
     ).to_pdf(
         out_filename=output_file,
         image_filename=None,
+        invisible_text=True if not debug_kwargs else False,
     )
     return output_file
 
@@ -769,7 +809,57 @@ def ocr_engine_textonly_pdf(
         output_text=output_text,
         options=options,
     )
-    return (output_pdf, output_text)
+    return output_pdf, output_text
+
+
+def _offset_rect(rect: tuple[float, float, float, float], offset: tuple[float, float]):
+    """Offset a rectangle by a given amount."""
+    return (
+        rect[0] + offset[0],
+        rect[1] + offset[1],
+        rect[2] + offset[0],
+        rect[3] + offset[1],
+    )
+
+
+def fix_pagepdf_boxes(
+    infile: Path | BinaryIO,
+    out_file: Path,
+    page_context: PageContext,
+    swap_axis: bool = False,
+) -> Path:
+    """Fix the bounding boxes in a single page PDF.
+
+    The single page PDF is created with a normal MediaBox with its lower left corner
+    at (0, 0). infile is the single page PDF. page_context.mediabox has the original
+    file's mediabox, which may have a different origin. We needto adjust the other
+    boxes in the single page PDF to match the effect they had on the original page.
+
+    When correcting page rotation, we create a single page PDF that is correctly
+    rotated instead of an incorrectly rotated and then setting page.Rotate on it.
+    If rotation is either 90 or 270 degrees, then this function can be called
+    with swap_axis to swap the X and Y coordinates of all the boxes.
+
+    We are not concerned with solving degenerate cases where the boxes overlap or
+    or express invalid rectangles. We merely pass the boxes, producing a
+    transformation equivalent to the change made by constructing a new page image.
+    """
+    with pikepdf.open(infile) as pdf:
+        for page in pdf.pages:
+            # page.BleedBox = page_context.pageinfo.bleedbox
+            # page.ArtBox = page_context.pageinfo.artbox
+            mediabox = page_context.pageinfo.mediabox
+            offset = mediabox[0], mediabox[1]
+            cropbox = _offset_rect(page_context.pageinfo.cropbox, offset)
+            trimbox = _offset_rect(page_context.pageinfo.trimbox, offset)
+
+            if swap_axis:
+                cropbox = cropbox[1], cropbox[0], cropbox[3], cropbox[2]
+                trimbox = trimbox[1], trimbox[0], trimbox[3], trimbox[2]
+            page.CropBox = cropbox
+            page.TrimBox = trimbox
+        pdf.save(out_file)
+    return out_file
 
 
 def generate_postscript_stub(context: PdfContext) -> Path:

src/ocrmypdf/_pipelines/_common.py

@@ -11,16 +11,18 @@ import os
 import shutil
 import sys
 import threading
-from collections.abc import Sequence
+from collections.abc import Callable, Sequence
 from concurrent.futures.process import BrokenProcessPool
 from concurrent.futures.thread import BrokenThreadPool
 from contextlib import contextmanager
 from dataclasses import dataclass
 from pathlib import Path
-from typing import Callable, NamedTuple, cast
+from typing import NamedTuple, cast
 
 import PIL
+from pikepdf import Pdf
 
+from ocrmypdf._annots import remove_broken_goto_annotations
 from ocrmypdf._concurrent import Executor, setup_executor
 from ocrmypdf._jobcontext import PageContext, PdfContext
 from ocrmypdf._logging import PageNumberFilter
@@ -33,6 +35,7 @@ from ocrmypdf._pipeline import (
     generate_postscript_stub,
     get_orientation_correction,
     get_pdf_save_settings,
+    get_pdfinfo,
     optimize_pdf,
     preprocess_clean,
     preprocess_deskew,
@@ -51,9 +54,12 @@ from ocrmypdf.helpers import (
     available_cpu_count,
     check_pdf,
     pikepdf_enable_mmap,
+    running_in_docker,
+    running_in_snap,
     samefile,
 )
 from ocrmypdf.pdfa import file_claims_pdfa
+from ocrmypdf.pdfinfo import PdfInfo
 
 log = logging.getLogger(__name__)
 tls = threading.local()
@@ -100,6 +106,23 @@ class PageResult(NamedTuple):
     """Orientation correction in degrees."""
 
 
+class HOCRResultEncoder(json.JSONEncoder):
+    def default(self, obj):
+        if isinstance(obj, Path):
+            return {'Path': str(obj)}
+        return super().default(obj)
+
+
+class HOCRResultDecoder(json.JSONDecoder):
+    def __init__(self, *args, **kwargs):
+        super().__init__(object_hook=self.dict_to_object, *args, **kwargs)
+
+    def dict_to_object(self, d):
+        if 'Path' in d:
+            return Path(d['Path'])
+        return d
+
+
 @dataclass
 class HOCRResult:
     """Result when hOCR is finished processing."""
@@ -119,38 +142,14 @@ class HOCRResult:
     orientation_correction: int = 0
     """Orientation correction in degrees."""
 
-    def __getstate__(self):
-        """Return state values to be pickled."""
-        return {
-            k: (
-                ('Path://' + str(v))
-                if k in ('pdf_page_from_image', 'hocr', 'textpdf') and v is not None
-                else v
-            )
-            for k, v in self.__dict__.items()
-        }
-
-    def __setstate__(self, state):
-        """Restore state from the unpickled state values."""
-        self.__dict__.update(
-            {
-                k: (
-                    Path(v.removeprefix('Path://'))
-                    if k in ('pdf_page_from_image', 'hocr', 'textpdf') and v is not None
-                    else v
-                )
-                for k, v in state.items()
-            }
-        )
-
     @classmethod
     def from_json(cls, json_str: str) -> HOCRResult:
         """Create an instance from a dict."""
-        return cls(**json.loads(json_str))
+        return cls(**json.loads(json_str, cls=HOCRResultDecoder))
 
     def to_json(self) -> str:
         """Serialize to a JSON string."""
-        return json.dumps(self.__getstate__())
+        return json.dumps(self.__dict__, cls=HOCRResultEncoder)
 
 
 def configure_debug_logging(
@@ -183,7 +182,7 @@ def configure_debug_logging(
     return log_file_handler, remover
 
 
-def worker_init(max_pixels: int) -> None:
+def worker_init(max_pixels: int | None) -> None:
     """Initialize a worker thread or process."""
     # In Windows, child process will not inherit our change to this value in
     # the parent process, so ensure workers get it set. Not needed when running
@@ -215,6 +214,22 @@ def manage_debug_log_handler(
             remover()
 
 
+def _print_temp_folder_location(work_folder: Path):
+    """Print the location of the temporary work folder."""
+    msgs = [f"Temporary working files retained at:\n{work_folder}"]
+    if running_in_docker():  # pragma: no cover
+        msgs.append(
+            "OCRmyPDF is running in a Docker container, "
+            "so the files will be inside the container."
+        )
+    elif running_in_snap():  # pragma: no cover
+        msgs.append(
+            "OCRmyPDF is running in a Snap container, "
+            "so the files will be inside the container."
+        )
+    print('\n'.join(msgs), file=sys.stderr)
+
+
 @contextmanager
 def manage_work_folder(*, work_folder: Path, retain: bool, print_location: bool):
     try:
@@ -222,10 +237,7 @@ def manage_work_folder(*, work_folder: Path, retain: bool, print_location: bool)
     finally:
         if retain:
             if print_location:
-                print(
-                    f"Temporary working files retained at:\n{work_folder}",
-                    file=sys.stderr,
-                )
+                _print_temp_folder_location(work_folder)
         else:
             shutil.rmtree(work_folder, ignore_errors=True)
 
@@ -300,6 +312,20 @@ def setup_pipeline(
     return executor
 
 
+def do_get_pdfinfo(
+    pdf_path: Path, executor: Executor, options: argparse.Namespace
+) -> PdfInfo:
+    return get_pdfinfo(
+        pdf_path,
+        executor=executor,
+        detailed_analysis=options.redo_ocr,
+        progbar=options.progress_bar,
+        max_workers=options.jobs,
+        use_threads=options.use_threads,
+        check_pages=options.pages,
+    )
+
+
 def preprocess(
     page_context: PageContext,
     image: Path,
@@ -414,7 +440,14 @@ def postprocess(
     pdf_file: Path, context: PdfContext, executor: Executor
 ) -> tuple[Path, Sequence[str]]:
     """Postprocess the PDF file."""
-    pdf_out = pdf_file
+    # pdf_out = pdf_file
+    with Pdf.open(pdf_file) as pdf:
+        fix_annots = context.get_path('fix_annots.pdf')
+        if remove_broken_goto_annotations(pdf):
+            pdf.save(fix_annots)
+            pdf_out = fix_annots
+        else:
+            pdf_out = pdf_file
     if context.options.output_type.startswith('pdfa'):
         ps_stub_out = generate_postscript_stub(context)
         pdf_out = convert_to_pdfa(pdf_out, ps_stub_out, context)
@@ -441,7 +474,8 @@ def report_output_pdf(options, start_input_file, optimize_messages) -> ExitCode:
                 log.info("Output file is a %s (as expected)", pdfa_info['conformance'])
             else:
                 log.warning(
-                    "Output file is okay but is not PDF/A (seems to be %s)",
+                    "Output file is a valid PDF, but conversion to PDF/A did not "
+                    "succeed (issue: %s)",
                     pdfa_info['conformance'],
                 )
                 return ExitCode.pdfa_conversion_failed

src/ocrmypdf/_pipelines/hocr_to_ocr_pdf.py

@@ -4,7 +4,6 @@
 
 """Implements the concurrent and page synchronous parts of the pipeline."""
 
-
 from __future__ import annotations
 
 import argparse
@@ -20,11 +19,11 @@ from ocrmypdf._graft import OcrGrafter
 from ocrmypdf._jobcontext import PageContext, PdfContext
 from ocrmypdf._pipeline import (
     copy_final,
-    get_pdfinfo,
     render_hocr_page,
 )
 from ocrmypdf._pipelines._common import (
     HOCRResult,
+    do_get_pdfinfo,
     manage_work_folder,
     postprocess,
     report_output_pdf,
@@ -118,15 +117,7 @@ def run_hocr_to_ocr_pdf_pipeline(
         origin_pdf = work_folder / 'origin.pdf'
 
         # Gather pdfinfo and create context
-        pdfinfo = get_pdfinfo(
-            origin_pdf,
-            executor=executor,
-            detailed_analysis=options.redo_ocr,
-            progbar=options.progress_bar,
-            max_workers=options.jobs,
-            use_threads=options.use_threads,
-            check_pages=options.pages,
-        )
+        pdfinfo = do_get_pdfinfo(origin_pdf, executor, options)
         context = PdfContext(options, work_folder, origin_pdf, pdfinfo, plugin_manager)
         plugin_manager.hook.check_options(options=options)
         optimize_messages = exec_hocr_to_ocr_pdf(context, executor)

src/ocrmypdf/_pipelines/ocr.py

@@ -4,7 +4,6 @@
 
 """Implements the concurrent and page synchronous parts of the pipeline."""
 
-
 from __future__ import annotations
 
 import argparse
@@ -22,7 +21,6 @@ from ocrmypdf._graft import OcrGrafter
 from ocrmypdf._jobcontext import PageContext, PdfContext
 from ocrmypdf._pipeline import (
     copy_final,
-    get_pdfinfo,
     is_ocr_required,
     merge_sidecars,
     ocr_engine_hocr,
@@ -34,6 +32,7 @@ from ocrmypdf._pipeline import (
 from ocrmypdf._pipelines._common import (
     PageResult,
     cli_exception_handler,
+    do_get_pdfinfo,
     manage_debug_log_handler,
     manage_work_folder,
     postprocess,
@@ -80,7 +79,6 @@ def _exec_page_sync(page_context: PageContext) -> PageResult:
         page_context
     )
     ocr_out, text_out = _image_to_ocr_text(page_context, ocr_image_out)
-
     return PageResult(
         pageno=page_context.pageno,
         pdf_page_from_image=pdf_page_from_image_out,
@@ -105,14 +103,14 @@ def exec_concurrent(context: PdfContext, executor: Executor) -> Sequence[str]:
         try:
             set_thread_pageno(result.pageno + 1)
             sidecars[result.pageno] = result.text
-            pbar.update()
+            pbar.update(0.5)
             ocrgraft.graft_page(
                 pageno=result.pageno,
                 image=result.pdf_page_from_image,
                 textpdf=result.ocr,
                 autorotate_correction=result.orientation_correction,
             )
-            pbar.update()
+            pbar.update(0.5)
         finally:
             set_thread_pageno(None)
 
@@ -120,10 +118,9 @@ def exec_concurrent(context: PdfContext, executor: Executor) -> Sequence[str]:
         use_threads=options.use_threads,
         max_workers=max_workers,
         progress_kwargs=dict(
-            total=(2 * len(context.pdfinfo)),
+            total=len(context.pdfinfo),
             desc='OCR' if options.tesseract_timeout > 0 else 'Image processing',
             unit='page',
-            unit_scale=0.5,
             disable=not options.progress_bar,
         ),
         worker_initializer=partial(worker_init, PIL.Image.MAX_IMAGE_PIXELS),
@@ -156,12 +153,13 @@ def _run_pipeline(
     options: argparse.Namespace,
     plugin_manager: OcrmypdfPluginManager,
 ) -> ExitCode:
-    with manage_work_folder(
-        work_folder=Path(mkdtemp(prefix="ocrmypdf.io.")),
-        retain=options.keep_temporary_files,
-        print_location=options.keep_temporary_files,
-    ) as work_folder, manage_debug_log_handler(
-        options=options, work_folder=work_folder
+    with (
+        manage_work_folder(
+            work_folder=Path(mkdtemp(prefix="ocrmypdf.io.")),
+            retain=options.keep_temporary_files,
+            print_location=options.keep_temporary_files,
+        ) as work_folder,
+        manage_debug_log_handler(options=options, work_folder=work_folder),
     ):
         executor = setup_pipeline(options, plugin_manager)
         check_requested_output_file(options)
@@ -173,16 +171,7 @@ def _run_pipeline(
         )
 
         # Gather pdfinfo and create context
-        pdfinfo = get_pdfinfo(
-            origin_pdf,
-            executor=executor,
-            detailed_analysis=options.redo_ocr,
-            progbar=options.progress_bar,
-            max_workers=options.jobs,
-            use_threads=options.use_threads,
-            check_pages=options.pages,
-        )
-
+        pdfinfo = do_get_pdfinfo(origin_pdf, executor, options)
         context = PdfContext(options, work_folder, origin_pdf, pdfinfo, plugin_manager)
 
         # Validate options are okay for this pdf

src/ocrmypdf/_pipelines/pdf_to_hocr.py

@@ -4,7 +4,6 @@
 
 """Implements the concurrent and page synchronous parts of the pipeline."""
 
-
 from __future__ import annotations
 
 import argparse
@@ -18,13 +17,13 @@ import PIL
 from ocrmypdf._concurrent import Executor
 from ocrmypdf._jobcontext import PageContext, PdfContext
 from ocrmypdf._pipeline import (
-    get_pdfinfo,
     is_ocr_required,
     ocr_engine_hocr,
     validate_pdfinfo_options,
 )
 from ocrmypdf._pipelines._common import (
     HOCRResult,
+    do_get_pdfinfo,
     manage_work_folder,
     process_page,
     set_thread_pageno,
@@ -95,18 +94,11 @@ def run_hocr_pipeline(
         work_folder=options.output_folder, retain=True, print_location=False
     ) as work_folder:
         executor = setup_pipeline(options, plugin_manager)
-        shutil.copy2(options.input_file, work_folder / 'origin.pdf')
+        origin_pdf = work_folder / 'origin.pdf'
+        shutil.copy2(options.input_file, origin_pdf)
 
         # Gather pdfinfo and create context
-        pdfinfo = get_pdfinfo(
-            options.input_file,
-            executor=executor,
-            detailed_analysis=options.redo_ocr,
-            progbar=options.progress_bar,
-            max_workers=options.jobs,
-            use_threads=options.use_threads,
-            check_pages=options.pages,
-        )
+        pdfinfo = do_get_pdfinfo(origin_pdf, executor, options)
         context = PdfContext(
             options, work_folder, options.input_file, pdfinfo, plugin_manager
         )

src/ocrmypdf/_progressbar.py

@@ -66,7 +66,7 @@ class ProgressBar(Protocol):
     def __exit__(self, *args):
         """Exit a progress bar context."""
 
-    def update(self, n=1):
+    def update(self, n=1, *, completed=None):
         """Update the progress bar by an increment.
 
         For use within a progress bar context.
@@ -85,7 +85,7 @@ class NullProgressBar:
     def __exit__(self, exc_type, exc_value, traceback):
         return False
 
-    def update(self, _arg=None):
+    def update(self, _arg=None, *, completed=None):
         return
 
 
@@ -103,6 +103,7 @@ class RichProgressBar:
         disable: bool = False,
         **kwargs,
     ):
+        self._entered = False
         self.progress = Progress(
             TextColumn(
                 "[progress.description]{task.description}",
@@ -130,6 +131,7 @@ class RichProgressBar:
 
     def __enter__(self):
         self.progress.start()
+        self._entered = True
         return self
 
     def __exit__(self, exc_type, exc_value, traceback):
@@ -137,6 +139,10 @@ class RichProgressBar:
         self.progress.stop()
         return False
 
-    def update(self, value=None):
-        advance = self.unit_scale if value is None else value
-        self.progress.update(self.progress_bar, advance=advance)
+    def update(self, n=1, *, completed=None):
+        assert self._entered, "Progress bar must be entered before updating"
+        if completed is None:
+            advance = self.unit_scale if n is None else n
+            self.progress.update(self.progress_bar, advance=advance)
+        else:
+            self.progress.update(self.progress_bar, completed=completed)

src/ocrmypdf/_validation.py

@@ -20,6 +20,7 @@ import pikepdf
 import PIL
 from pluggy import PluginManager
 
+from ocrmypdf._defaults import DEFAULT_LANGUAGE, DEFAULT_ROTATE_PAGES_THRESHOLD
 from ocrmypdf._exec import unpaper
 from ocrmypdf.exceptions import (
     BadArgsError,
@@ -27,20 +28,18 @@ from ocrmypdf.exceptions import (
     MissingDependencyError,
     OutputFileAccessError,
 )
-from ocrmypdf.helpers import is_file_writable, monotonic, safe_symlink
+from ocrmypdf.helpers import (
+    is_file_writable,
+    monotonic,
+    running_in_docker,
+    running_in_snap,
+    safe_symlink,
+)
 from ocrmypdf.subprocess import check_external_program
 
-# -------------
-# External dependencies
-
-DEFAULT_LANGUAGE = 'eng'  # Enforce English hegemony
-
 log = logging.getLogger(__name__)
 
 
-# --------
-
-
 def check_platform() -> None:
     if sys.maxsize <= 2**32:  # pragma: no cover
         log.warning(
@@ -61,6 +60,7 @@ def check_options_languages(
             log.debug("No language specified; assuming --language %s", DEFAULT_LANGUAGE)
     if not ocr_engine_languages:
         return
+
     missing_languages = set(options.languages) - set(ocr_engine_languages)
     if missing_languages:
         lang_text = '\n'.join(lang for lang in missing_languages)
@@ -130,6 +130,11 @@ def check_options_preprocessing(options: Namespace) -> None:
         options.clean = True
     if options.unpaper_args and not options.clean:
         raise BadArgsError("--clean is required for --unpaper-args")
+    if (
+        options.rotate_pages_threshold != DEFAULT_ROTATE_PAGES_THRESHOLD
+        and not options.rotate_pages
+    ):
+        raise BadArgsError("--rotate-pages is required for --rotate-pages-threshold")
     if options.clean:
         check_external_program(
             program='unpaper',
@@ -238,18 +243,6 @@ def check_options(options: Namespace, plugin_manager: PluginManager) -> None:
     _check_plugin_options(options, plugin_manager)
 
 
-def _in_docker():
-    return Path('/.dockerenv').exists()
-
-
-def _in_snap():
-    try:
-        cgroup_text = Path('/proc/self/cgroup').read_text()
-        return 'snap.ocrmypdf' in cgroup_text
-    except FileNotFoundError:
-        return False
-
-
 def create_input_file(options: Namespace, work_folder: Path) -> tuple[Path, str]:
     if options.input_file == '-':
         # stdin
@@ -273,7 +266,7 @@ def create_input_file(options: Namespace, work_folder: Path) -> tuple[Path, str]
             return target, os.fspath(options.input_file)
         except FileNotFoundError as e:
             msg = f"File not found - {options.input_file}"
-            if _in_docker():  # pragma: no cover
+            if running_in_docker():  # pragma: no cover
                 msg += (
                     "\nDocker cannot access your working directory unless you "
                     "explicitly share it with the Docker container and set up"
@@ -283,7 +276,7 @@ def create_input_file(options: Namespace, work_folder: Path) -> tuple[Path, str]
                     "\tdocker run -i --rm jbarlow83/ocrmypdf - - <input.pdf >output.pdf"
                     "\n"
                 )
-            elif _in_snap():  # pragma: no cover
+            elif running_in_snap():  # pragma: no cover
                 msg += (
                     "\nSnap applications cannot access files outside of "
                     "your home directory unless you explicitly allow it. "

src/ocrmypdf/_version.py

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

src/ocrmypdf/api.py

@@ -14,7 +14,7 @@ from collections.abc import Iterable, Sequence
 from enum import IntEnum
 from io import IOBase
 from pathlib import Path
-from typing import AnyStr, BinaryIO, Union
+from typing import BinaryIO
 from warnings import warn
 
 import pluggy
@@ -28,8 +28,8 @@ from ocrmypdf._validation import check_options
 from ocrmypdf.cli import ArgumentParser, get_parser
 from ocrmypdf.helpers import is_iterable_notstr
 
-StrPath = Union[Path, AnyStr]
-PathOrIO = Union[BinaryIO, StrPath]
+StrPath = Path | str | bytes
+PathOrIO = BinaryIO | StrPath
 
 # Installing plugins affects the global state of the Python interpreter,
 # so we need to use a lock to prevent multiple threads from installing
@@ -140,9 +140,9 @@ def configure_logging(
 
 def _kwargs_to_cmdline(
     *, defer_kwargs: set[str], **kwargs
-) -> tuple[list[str], dict[str, AnyStr]]:
+) -> tuple[list[str | bytes], dict[str, str | bytes]]:
     """Convert kwargs to command line arguments."""
-    cmdline = []
+    cmdline: list[str | bytes] = []
     deferred = {}
     for arg, val in kwargs.items():
         if val is None:
@@ -169,7 +169,7 @@ def _kwargs_to_cmdline(
 
         # We have a parameter
         cmdline.append(f"--{cmd_style_arg}")
-        if isinstance(val, (int, float)):
+        if isinstance(val, int | float):
             cmdline.append(str(val))
         elif isinstance(val, str):
             cmdline.append(val)
@@ -201,14 +201,17 @@ def create_options(
         defer_kwargs={'progress_bar', 'plugins', 'parser', 'input_file', 'output_file'},
         **kwargs,
     )
-    if isinstance(input_file, (BinaryIO, IOBase)):
+    if isinstance(input_file, BinaryIO | IOBase):
         cmdline.append('stream://input_file')
     else:
         cmdline.append(os.fspath(input_file))
-    if isinstance(output_file, (BinaryIO, IOBase)):
+    if isinstance(output_file, BinaryIO | IOBase):
         cmdline.append('stream://output_file')
     else:
         cmdline.append(os.fspath(output_file))
+    if 'sidecar' in kwargs and isinstance(kwargs['sidecar'], BinaryIO | IOBase):
+        cmdline.append('--sidecar')
+        cmdline.append('stream://sidecar')
 
     parser.enable_api_mode()
     options = parser.parse_args(cmdline)
@@ -219,6 +222,8 @@ def create_options(
         options.input_file = input_file
     if options.output_file == 'stream://output_file':
         options.output_file = output_file
+    if options.sidecar == 'stream://sidecar':
+        options.sidecar = kwargs['sidecar']
 
     return options
 
@@ -230,7 +235,7 @@ def ocr(  # noqa: D417
     language: Iterable[str] | None = None,
     image_dpi: int | None = None,
     output_type: str | None = None,
-    sidecar: StrPath | None = None,
+    sidecar: PathOrIO | None = None,
     jobs: int | None = None,
     use_threads: bool | None = None,
     title: str | None = None,
@@ -274,7 +279,7 @@ def ocr(  # noqa: D417
     fast_web_view: float | None = None,
     continue_on_soft_render_error: bool | None = None,
     invalidate_digital_signatures: bool | None = None,
-    plugins: Iterable[StrPath] | None = None,
+    plugins: Iterable[Path | str] | None = None,
     plugin_manager=None,
     keep_temporary_files: bool | None = None,
     progress_bar: bool | None = None,
@@ -343,7 +348,7 @@ def ocr(  # noqa: D417
 
     if not plugins:
         plugins = []
-    elif isinstance(plugins, (str, Path)):
+    elif isinstance(plugins, str | Path):
         plugins = [plugins]
     else:
         plugins = list(plugins)
@@ -415,7 +420,7 @@ def _pdf_to_hocr(  # noqa: D417
     continue_on_soft_render_error: bool | None = None,
     invalidate_digital_signatures: bool | None = None,
     plugin_manager=None,
-    plugins: Sequence[StrPath] | None = None,
+    plugins: Sequence[Path | str] | None = None,
     keep_temporary_files: bool | None = None,
     **kwargs,
 ):
@@ -486,7 +491,7 @@ def _hocr_to_ocr_pdf(  # noqa: D417
     color_conversion_strategy: str | None = None,
     fast_web_view: float | None = None,
     plugin_manager=None,
-    plugins: Sequence[StrPath] | None = None,
+    plugins: Sequence[Path | str] | None = None,
     **kwargs,
 ):
     """Run OCRmyPDF on a work folder and produce an output PDF.

src/ocrmypdf/builtin_plugins/concurrency.py

@@ -12,10 +12,10 @@ import queue
 import signal
 import sys
 import threading
-from collections.abc import Iterable
+from collections.abc import Callable, Iterable
 from concurrent.futures import ProcessPoolExecutor, ThreadPoolExecutor, as_completed
 from contextlib import suppress
-from typing import Callable, Union
+from typing import Union
 
 from rich.console import Console as RichConsole
 
@@ -25,8 +25,10 @@ from ocrmypdf._progressbar import RichProgressBar
 from ocrmypdf.exceptions import InputFileError
 from ocrmypdf.helpers import remove_all_log_handlers
 
-FuturesExecutorClass = Union[type[ThreadPoolExecutor], type[ProcessPoolExecutor]]
-Queue = Union[multiprocessing.Queue, queue.Queue]
+FuturesExecutorClass = Union[  # noqa: UP007
+    type[ThreadPoolExecutor], type[ProcessPoolExecutor]
+]
+Queue = Union[multiprocessing.Queue, queue.Queue]  # noqa: UP007
 UserInit = Callable[[], None]
 WorkerInit = Callable[[Queue, UserInit, int], None]
 
@@ -128,11 +130,14 @@ class StandardExecutor(Executor):
         listener = threading.Thread(target=log_listener, args=(log_queue,))
         listener.start()
 
-        with self.pbar_class(**progress_kwargs) as pbar, executor_class(
-            max_workers=max_workers,
-            initializer=initializer,
-            initargs=(log_queue, worker_initializer, logging.getLogger("").level),
-        ) as executor:
+        with (
+            self.pbar_class(**progress_kwargs) as pbar,
+            executor_class(
+                max_workers=max_workers,
+                initializer=initializer,
+                initargs=(log_queue, worker_initializer, logging.getLogger("").level),
+            ) as executor,
+        ):
             futures = [executor.submit(task, *args) for args in task_arguments]
             try:
                 for future in as_completed(futures):

src/ocrmypdf/builtin_plugins/default_filters.py

@@ -8,7 +8,5 @@ from ocrmypdf import hookimpl
 
 
 @hookimpl
-def filter_pdf_page(
-    page, image_filename, output_pdf
-):  # pylint: disable=unused-argument
+def filter_pdf_page(page, image_filename, output_pdf):  # pylint: disable=unused-argument
     return output_pdf

src/ocrmypdf/builtin_plugins/ghostscript.py

@@ -17,7 +17,7 @@ log = logging.getLogger(__name__)
 
 # Currently all blacklisted versions are lower than 9.55, so none need to
 # be added here. If a future version is blacklisted, add it here.
-BLACKLISTED_GS_VERSIONS: frozenset[str] = frozenset()
+BLACKLISTED_GS_VERSIONS: frozenset[Version] = frozenset()
 
 
 @hookimpl
@@ -54,7 +54,7 @@ def check_options(options):
         program='gs',
         package='ghostscript',
         version_checker=ghostscript.version,
-        need_version='9.55',  # Ubuntu 22.04's version
+        need_version='9.54',  # RHEL 9's version; Ubuntu 22.04 has 9.55
     )
     gs_version = ghostscript.version()
     if gs_version in BLACKLISTED_GS_VERSIONS:
@@ -62,13 +62,16 @@ def check_options(options):
             f"Ghostscript {gs_version} contains serious regressions and is not "
             "supported. Please upgrade to a newer version."
         )
-    if gs_version < Version('10.02.0'):
-        log.warning(
-            f"The installed version of Ghostscript {gs_version}, contains a remote "
-            "code execution security vulnerability. Please upgrade to a newer "
-            "version. For details see CVE-2023-43115. The issue is not known to "
-            "affect OCRmyPDF or processing PDFs with Ghostscript, but upgrading "
-            "Ghostscript is recommended."
+    if Version('10.0.0') <= gs_version < Version('10.02.1') and (
+        options.skip_text or options.redo_ocr
+    ):
+        raise MissingDependencyError(
+            f"Ghostscript 10.0.0 through 10.02.0 (your version: {gs_version}) "
+            "contain serious regressions that corrupt PDFs with existing text, "
+            "such as those processed using --skip-text or --redo-ocr. "
+            "Please upgrade to a "
+            "newer version, or use --output-type pdf to avoid Ghostscript, or "
+            "use --force-ocr to discard existing text."
         )
 
     if options.output_type == 'pdfa':
@@ -126,7 +129,7 @@ def generate_pdfa(
 ):
     """Generate a PDF/A from the list of PDF pages and PDF/A metadata."""
     ghostscript.generate_pdfa(
-        pdf_pages=[*pdf_pages, pdfmark],
+        pdf_pages=[pdfmark, *pdf_pages],
         output_file=output_file,
         compression=context.options.pdfa_image_compression,
         color_conversion_strategy=context.options.color_conversion_strategy,

src/ocrmypdf/builtin_plugins/tesseract_ocr.py

@@ -2,9 +2,9 @@
 # SPDX-License-Identifier: MPL-2.0
 """Built-in plugin to implement OCR using Tesseract."""
 
-
 from __future__ import annotations
 
+import argparse
 import logging
 import os
 
@@ -14,6 +14,7 @@ from ocrmypdf import hookimpl
 from ocrmypdf._exec import tesseract
 from ocrmypdf._jobcontext import PageContext
 from ocrmypdf.cli import numeric, str_to_int
+from ocrmypdf.exceptions import BadArgsError, MissingDependencyError
 from ocrmypdf.helpers import clamp
 from ocrmypdf.imageops import calculate_downsample, downsample_image
 from ocrmypdf.pluginspec import OcrEngine
@@ -94,7 +95,8 @@ def add_options(parser):
     )
     tess.add_argument(
         '--tesseract-downsample-large-images',
-        action='store_true',
+        action=argparse.BooleanOptionalAction,
+        default=True,
         help=(
             "Downsample large images before OCR. Tesseract has an upper limit on the "
             "size images it will support. If this argument is given, OCRmyPDF will "
@@ -143,10 +145,20 @@ def check_options(options):
         need_version='4.1.1',  # Ubuntu 22.04 version (also 20.04)
         version_parser=tesseract.TesseractVersion,
     )
+    tess_version = tesseract.version()
+    if tess_version == tesseract.TesseractVersion('5.4.0'):
+        raise MissingDependencyError(
+            "Tesseract 5.4.0 is not supported due to regressions in this version. "
+            "Please upgrade to a newer or supported older version."
+        )
 
     # Decide on what renderer to use
     if options.pdf_renderer == 'auto':
-        options.pdf_renderer = 'hocr'
+        if {'ara', 'heb', 'fas', 'per'} & set(options.languages):
+            log.info("Using sandwich renderer since there is an RTL language")
+            options.pdf_renderer = 'sandwich'
+        else:
+            options.pdf_renderer = 'hocr'
 
     if not tesseract.has_thresholding() and options.tesseract_thresholding != 0:
         log.warning(
@@ -159,6 +171,14 @@ def check_options(options):
             "The --tesseract-pagesegmode argument you select will disable OCR. "
             "This may cause processing to fail."
         )
+    DENIED_LANGUAGES = {'equ', 'osd'}
+    if DENIED_LANGUAGES & set(options.languages):
+        raise BadArgsError(
+            "The following languages for Tesseract's internal use and should not "
+            "be issued explicitly: "
+            f"{', '.join(DENIED_LANGUAGES & set(options.languages))}\n"
+            "Remove them from the -l/--language argument."
+        )
 
 
 @hookimpl
@@ -216,7 +236,7 @@ class TesseractOcrEngine(OcrEngine):
 
     @staticmethod
     def creator_tag(options):
-        tag = '-PDF' if options.pdf_renderer == 'sandwich' else 'hOCR'
+        tag = '-PDF' if options.pdf_renderer == 'sandwich' else '-hOCR'
         return f"Tesseract OCR{tag} {TesseractOcrEngine.version()}"
 
     def __str__(self):

src/ocrmypdf/cli.py

@@ -6,10 +6,11 @@
 from __future__ import annotations
 
 import argparse
-from collections.abc import Mapping
-from typing import Any, Callable, TypeVar
+from collections.abc import Callable, Mapping
+from typing import Any, TypeVar
 
-from ocrmypdf._version import PROGRAM_NAME as _PROGRAM_NAME
+from ocrmypdf._defaults import DEFAULT_ROTATE_PAGES_THRESHOLD
+from ocrmypdf._defaults import PROGRAM_NAME as _PROGRAM_NAME
 from ocrmypdf._version import __version__ as _VERSION
 
 T = TypeVar('T', int, float)
@@ -390,7 +391,7 @@ Online documentation is located at:
         action='store',
         type=numeric(float, 0),
         metavar='MPixels',
-        help="Set maximum number of pixels to unpack before treating an image as a "
+        help="Set maximum number of megapixels to unpack before treating an image as a "
         "decompression bomb",
         default=250.0,
     )
@@ -403,7 +404,7 @@ Online documentation is located at:
     )
     advanced.add_argument(
         '--rotate-pages-threshold',
-        default=14.0,
+        default=DEFAULT_ROTATE_PAGES_THRESHOLD,
         type=numeric(float, 0, 1000),
         metavar='CONFIDENCE',
         help="Only rotate pages when confidence is above this value (arbitrary "

src/ocrmypdf/extra_plugins/semfree.py

@@ -20,13 +20,12 @@ from __future__ import annotations
 import logging
 import logging.handlers
 import signal
-from collections.abc import Iterable, Iterator
+from collections.abc import Callable, Iterable, Iterator
 from contextlib import suppress
 from enum import Enum, auto
 from itertools import islice, repeat, takewhile, zip_longest
 from multiprocessing import Pipe, Process
 from multiprocessing.connection import Connection, wait
-from typing import Callable
 
 from ocrmypdf import Executor, hookimpl
 from ocrmypdf._concurrent import NullProgressBar

src/ocrmypdf/helpers.py

@@ -10,7 +10,7 @@ import multiprocessing
 import os
 import shutil
 import warnings
-from collections.abc import Iterable, Sequence
+from collections.abc import Callable, Iterable, Sequence
 from contextlib import suppress
 from decimal import Decimal
 from io import StringIO
@@ -19,13 +19,13 @@ from pathlib import Path
 from statistics import harmonic_mean
 from typing import (
     Any,
-    Callable,
     Generic,
     TypeVar,
 )
 
 import img2pdf
 import pikepdf
+from deprecation import deprecated
 
 log = logging.getLogger(__name__)
 
@@ -136,6 +136,7 @@ class Resolution(Generic[T]):
         return self._isclose(self.x, other.x) and self._isclose(self.y, other.y)
 
 
+@deprecated(deprecated_in='15.4.0')
 class NeverRaise(Exception):
     """An exception that is never raised."""
 
@@ -267,7 +268,9 @@ def check_pdf(input_file: Path) -> bool:
         return False
     else:
         with pdf:
-            messages = pdf.check()
+            with warnings.catch_warnings():
+                warnings.filterwarnings('ignore', message=r'pikepdf.*JBIG2.*')
+                messages = pdf.check()
             success = True
             for msg in messages:
                 if 'error' in msg.lower():
@@ -332,3 +335,17 @@ def pikepdf_enable_mmap() -> None:
         )
     except AttributeError:
         log.debug("pikepdf mmap not available")
+
+
+def running_in_docker() -> bool:
+    """Returns True if we seem to be running in a Docker container."""
+    return Path('/.dockerenv').exists()
+
+
+def running_in_snap() -> bool:
+    """Returns True if we seem to be running in a Snap container."""
+    try:
+        cgroup_text = Path('/proc/self/cgroup').read_text()
+        return 'snap.ocrmypdf' in cgroup_text
+    except FileNotFoundError:
+        return False

src/ocrmypdf/hocrtransform/_font.py

@@ -18,7 +18,12 @@ from pikepdf.canvas import Font
 log = logging.getLogger(__name__)
 
 
-class GlyphlessFont(Font):
+class EncodableFont(Font):
+    def text_encode(self, text: str) -> bytes:
+        raise NotImplementedError()
+
+
+class GlyphlessFont(EncodableFont):
     CID_TO_GID_DATA = zlib.compress(b"\x00\x01" * 65536)
     GLYPHLESS_FONT_NAME = 'pdf.ttf'
     GLYPHLESS_FONT = (package_files('ocrmypdf.data') / GLYPHLESS_FONT_NAME).read_bytes()
@@ -27,11 +32,14 @@ class GlyphlessFont(Font):
     def __init__(self):
         pass
 
-    def text_width(self, text: str, fontsize: float) -> int:
+    def text_width(self, text: str, fontsize: float) -> float:
         """Estimate the width of a text string when rendered with the given font."""
         # NFKC: split ligatures, combine diacritics
         return len(unicodedata.normalize("NFKC", text)) * (fontsize / self.CHAR_ASPECT)
 
+    def text_encode(self, text: str) -> bytes:
+        return text.encode('utf-16be')
+
     def register(self, pdf: Pdf):
         """Register the glyphless font.
 
@@ -110,3 +118,24 @@ class GlyphlessFont(Font):
         font_descriptor.FontFile2 = pdf.make_stream(self.GLYPHLESS_FONT)
         cid_font_type2.FontDescriptor = font_descriptor
         return basefont
+
+
+class Courier(EncodableFont):
+    """Courier font."""
+
+    def text_width(self, text: str, fontsize: float) -> float:
+        """Estimate the width of a text string when rendered with the given font."""
+        return len(text) * fontsize
+
+    def text_encode(self, text: str) -> bytes:
+        return text.encode('pdfdoc', errors='ignore')
+
+    def register(self, pdf: Pdf) -> Dictionary:
+        """Register the font."""
+        return pdf.make_indirect(
+            Dictionary(
+                BaseFont=Name.Courier,
+                Type=Name.Font,
+                Subtype=Name.Type1,
+            )
+        )

src/ocrmypdf/hocrtransform/_hocr.py

@@ -27,11 +27,11 @@ from pikepdf.canvas import (
     MAGENTA,
     RED,
     Canvas,
-    Font,
     Text,
     TextDirection,
 )
 
+from ocrmypdf.hocrtransform._font import EncodableFont as Font
 from ocrmypdf.hocrtransform._font import GlyphlessFont
 
 log = logging.getLogger(__name__)
@@ -45,12 +45,12 @@ Element = ElementTree.Element
 class DebugRenderOptions:
     """A class for managing rendering options."""
 
-    render_paragraph_bbox: bool
-    render_baseline: bool
-    render_triangle: bool
-    render_line_bbox: bool
-    render_word_bbox: bool
-    render_space_bbox: bool
+    render_paragraph_bbox: bool = False
+    render_baseline: bool = False
+    render_triangle: bool = False
+    render_line_bbox: bool = False
+    render_word_bbox: bool = False
+    render_space_bbox: bool = False
 
 
 class HocrTransformError(Exception):
@@ -61,15 +61,25 @@ class HocrTransform:
     """A class for converting documents from the hOCR format.
 
     For details of the hOCR format, see:
-    http://kba.cloud/hocr-spec/.
+    http://kba.github.io/hocr-spec/1.2/.
     """
 
-    box_pattern = re.compile(r'bbox (\d+) (\d+) (\d+) (\d+)')
+    box_pattern = re.compile(
+        r'''
+        bbox \s+
+        (\d+) \s+   # left: uint
+        (\d+) \s+   # top: uint
+        (\d+) \s+   # right: uint
+        (\d+)       # bottom: uint
+        ''',
+        re.VERBOSE,
+    )
     baseline_pattern = re.compile(
         r'''
         baseline \s+
         ([\-\+]?\d*\.?\d*) \s+  # +/- decimal float
-        ([\-\+]?\d+)            # +/- int''',
+        ([\-\+]?\d+)            # +/- int
+        ''',
         re.VERBOSE,
     )
 
@@ -81,8 +91,21 @@ class HocrTransform:
         debug: bool = False,
         fontname: Name = Name("/f-0-0"),
         font: Font = GlyphlessFont(),
+        debug_render_options: DebugRenderOptions | None = None,
     ):
         """Initialize the HocrTransform object."""
+        if debug:
+            log.warning("Use debug_render_options instead", DeprecationWarning)
+            self.render_options = DebugRenderOptions(
+                render_baseline=debug,
+                render_triangle=debug,
+                render_line_bbox=False,
+                render_word_bbox=debug,
+                render_paragraph_bbox=False,
+                render_space_bbox=False,
+            )
+        else:
+            self.render_options = debug_render_options or DebugRenderOptions()
         self.dpi = dpi
         self.hocr = ElementTree.parse(os.fspath(hocr_filename))
         self._fontname = fontname
@@ -103,24 +126,13 @@ class HocrTransform:
             self.height = (coords.ury - coords.lly) / (self.dpi / INCH)
             # Stop after first div that has page coordinates
             break
-        self.render_options = DebugRenderOptions(
-            render_baseline=debug,
-            render_triangle=debug,
-            render_line_bbox=False,
-            render_word_bbox=debug,
-            render_paragraph_bbox=False,
-            render_space_bbox=False,
-        )
 
-    def _get_element_text(self, element: Element):
+    def _get_element_text(self, element: Element) -> str:
         """Return the textual content of the element and its children."""
-        text = ''
-        if element.text is not None:
-            text += element.text
+        text = element.text if element.text is not None else ''
         for child in element:
             text += self._get_element_text(child)
-        if element.tail is not None:
-            text += element.tail
+        text += element.tail if element.tail is not None else ''
         return text
 
     @classmethod
@@ -215,12 +227,13 @@ class HocrTransform:
             if not found_lines:
                 # Tesseract did not report any lines (just words)
                 root = self.hocr.find(self._child_xpath('div', 'ocr_page'))
+                direction = self._get_text_direction(root)
                 self._do_line(
                     canvas,
                     root,
                     "ocrx_word",
                     invisible_text,
-                    TextDirection.LTR,
+                    direction,
                     True,
                 )
         # put the image on the page, scaled to fill the page
@@ -280,7 +293,13 @@ class HocrTransform:
         line_box = self.element_coordinates(line)
         if not line_box:
             return
-        assert line_box.ury > line_box.lly  # lly is top, ury is bottom
+        if line_box.ury <= line_box.lly:
+            log.error(
+                "line box is invalid so we cannot render it: box=%s text=%s",
+                line_box,
+                self._get_element_text(line),
+            )
+            return
 
         self._debug_draw_line_bbox(canvas, line_box)
 
@@ -311,8 +330,7 @@ class HocrTransform:
             line_box_height = abs(line_box.height) / cos(angle)
             fontsize = line_box_height + intercept
             text.font(self._fontname, fontsize)
-            if invisible_text or True:
-                text.render_mode(3)  # Invisible (indicates OCR text)
+            text.render_mode(3 if invisible_text else 0)
 
             self._debug_draw_baseline(
                 canvas, line_matrix.inverse().transform(line_box), 0
@@ -339,7 +357,7 @@ class HocrTransform:
         line_matrix: Matrix,
         text: Text,
         fontsize: float,
-        elem: Element,
+        elem: Element | None,
         next_elem: Element | None,
         text_direction: TextDirection,
         inject_word_breaks: bool,
@@ -362,10 +380,15 @@ class HocrTransform:
         self._debug_draw_word_bbox(canvas, box)
 
         # If this word is 0 units wide, our best bet seems to be to suppress this text
+        if text_direction == TextDirection.RTL:
+            log.info("RTL: %s", elemtxt)
         if font_width > 0:
-            text.text_transform(Matrix(1, 0, 0, 1, box.llx, 0))
+            if text_direction == TextDirection.LTR:
+                text.text_transform(Matrix(1, 0, 0, -1, box.llx, 0))
+            elif text_direction == TextDirection.RTL:
+                text.text_transform(Matrix(-1, 0, 0, -1, box.llx + box.width, 0))
             text.horiz_scale(100 * box.width / font_width)
-            text.show(elemtxt.encode('utf-16be'))
+            text.show(self._font.text_encode(elemtxt))
 
         # Get coordinates of the next word (if there is one)
         hocr_next_box = (
@@ -385,11 +408,16 @@ class HocrTransform:
         elif text_direction == TextDirection.RTL:
             space_box = Rectangle(next_box.urx, box.lly, box.llx, next_box.ury)
         self._debug_draw_space_bbox(canvas, space_box)
-        text.text_transform(Matrix(1, 0, 0, 1, space_box.llx, 0))
         space_width = self._font.text_width(' ', fontsize)
         if space_width > 0:
+            if text_direction == TextDirection.LTR:
+                text.text_transform(Matrix(1, 0, 0, -1, space_box.llx, 0))
+            elif text_direction == TextDirection.RTL:
+                text.text_transform(
+                    Matrix(-1, 0, 0, -1, space_box.llx + space_box.width, 0)
+                )
             text.horiz_scale(100 * space_box.width / space_width)
-            text.show(' '.encode('utf-16be'))
+            text.show(self._font.text_encode(' '))
 
     def _debug_draw_paragraph_boxes(self, canvas: Canvas, color=CYAN):
         """Draw boxes around paragraphs in the document."""
@@ -406,7 +434,7 @@ class HocrTransform:
                 if ocr_par is None:
                     continue
                 canvas.do.rect(
-                    ocr_par.llx, ocr_par.lly, ocr_par.width, ocr_par.height, fill=0
+                    ocr_par.llx, ocr_par.lly, ocr_par.width, ocr_par.height, fill=False
                 )
 
     def _debug_draw_line_bbox(self, canvas: Canvas, line_box: Rectangle, color=BLUE):
@@ -415,7 +443,7 @@ class HocrTransform:
             return
         with canvas.do.save_state():
             canvas.do.stroke_color(color).line_width(0.15).rect(
-                line_box.llx, line_box.lly, line_box.width, line_box.height, fill=0
+                line_box.llx, line_box.lly, line_box.width, line_box.height, fill=False
             )
 
     def _debug_draw_word_triangle(
@@ -439,7 +467,7 @@ class HocrTransform:
             return
         with canvas.do.save_state():
             canvas.do.stroke_color(color).line_width(line_width).rect(
-                box.llx, box.lly, box.width, box.height, fill=0
+                box.llx, box.lly, box.width, box.height, fill=False
             )
 
     def _debug_draw_space_bbox(
@@ -450,7 +478,7 @@ class HocrTransform:
             return
         with canvas.do.save_state():
             canvas.do.fill_color(color).line_width(line_width).rect(
-                box.llx, box.lly, box.width, box.height, fill=1
+                box.llx, box.lly, box.width, box.height, fill=True
             )
 
     def _debug_draw_baseline(

src/ocrmypdf/languages.py

@@ -7,12 +7,12 @@ Derived from
 https://www.loc.gov/standards/iso639-2/ascii_8bits.html
 """
 
-
 from typing import NamedTuple
 
 
 class ISOCodeData(NamedTuple):
     """Data for a single ISO 639 code."""
+
     alt: str
     alpha_2: str
     english: str
@@ -168,8 +168,10 @@ ISO_639_3 = {
     'chu': ISOCodeData(
         '',
         'cu',
-        ('Church Slavic; Old Slavonic; Church Slavonic;'
-         ' Old Bulgarian; Old Church Slavonic'),
+        (
+            'Church Slavic; Old Slavonic; Church Slavonic;'
+            ' Old Bulgarian; Old Church Slavonic'
+        ),
         "slavon d'église; vieux slave; slavon liturgique; vieux bulgare",
     ),
     'chv': ISOCodeData('', 'cv', 'Chuvash', 'tchouvache'),

src/ocrmypdf/optimize.py

@@ -3,7 +3,6 @@
 
 """Post-processing image optimization of OCR PDFs."""
 
-
 from __future__ import annotations
 
 import logging
@@ -11,11 +10,10 @@ import sys
 import tempfile
 import threading
 from collections import defaultdict
-from collections.abc import Iterator, MutableSet, Sequence
+from collections.abc import Callable, Iterator, MutableSet, Sequence
 from os import fspath
 from pathlib import Path
-from typing import Any, Callable, NamedTuple, NewType
-from warnings import warn
+from typing import Any, NamedTuple, NewType
 from zlib import compress
 
 import img2pdf
@@ -30,6 +28,7 @@ from pikepdf import (
     Stream,
     UnsupportedImageTypeError,
 )
+from pikepdf.models.image import HifiPrintImageNotTranscodableError
 from PIL import Image
 
 from ocrmypdf._concurrent import Executor, SerialExecutor
@@ -76,10 +75,15 @@ def extract_image_filter(
     """Determine if an image is extractable."""
     if image.Subtype != Name.Image:
         return None
-    if image.Length < 100:
+    if not isinstance(image.Length, int) or image.Length < 100:
         log.debug(f"xref {xref}: skipping image with small stream size")
         return None
-    if image.Width < 8 or image.Height < 8:  # Issue 732
+    if (
+        not isinstance(image.Width, int)
+        or not isinstance(image.Height, int)
+        or image.Width < 8
+        or image.Height < 8
+    ):  # Issue 732
         log.debug(f"xref {xref}: skipping image with unusually small dimensions")
         return None
 
@@ -91,6 +95,7 @@ def extract_image_filter(
         if (
             len(pim.filter_decodeparms) == 2
             and first_filtdp[0] == Name.FlateDecode
+            and first_filtdp[1] is not None
             and first_filtdp[1].get(Name.Predictor, 1) == 1
             and second_filtdp[0] == Name.DCTDecode
             and not second_filtdp[1]
@@ -154,7 +159,17 @@ def extract_image_jbig2(
                 imgname = root / f'{xref:08d}'
                 with imgname.open('wb') as f:
                     ext = pim.extract_to(stream=f)
-                imgname.rename(imgname.with_suffix(ext))
+                # Rename the file so it has .prejbig2.ext extension
+                # Making it unique avoids problems with Windows if the
+                # same image is extracted multiple times
+                imgname.rename(imgname.with_suffix(".prejbig2" + ext))
+            except NotImplementedError as e:
+                if '/Decode' in str(e):
+                    log.debug(
+                        f"xref {xref}: skipping image with unsupported Decode table"
+                    )
+                    return None
+                raise
             except UnsupportedImageTypeError:
                 return None
             finally:
@@ -163,7 +178,7 @@ def extract_image_jbig2(
                     pim.obj.ColorSpace = colorspace
                 else:
                     del pim.obj.ColorSpace
-            return XrefExt(xref, ext)
+            return XrefExt(xref, ".prejbig2" + ext)
     return None
 
 
@@ -194,7 +209,7 @@ def extract_image_generic(
             with imgname.open('wb') as f:
                 ext = pim.extract_to(stream=f)
             imgname.rename(imgname.with_suffix(ext))
-        except UnsupportedImageTypeError:
+        except (UnsupportedImageTypeError, HifiPrintImageNotTranscodableError):
             return None
         return XrefExt(xref, ext)
     elif (
@@ -250,6 +265,9 @@ def _find_image_xrefs_container(
     for _imname, image in dict(xobjs).items():
         if image.objgen[1] != 0:
             continue  # Ignore images in an incremental PDF
+        xref = Xref(image.objgen[0])
+        if xref in include_xrefs or xref in exclude_xrefs:
+            continue  # Already processed
         if Name.Subtype in image and image.Subtype == Name.Form:
             # Recurse into Form XObjects
             log.debug(f"Recursing into Form XObject {_imname} in page {pageno}")
@@ -263,7 +281,6 @@ def _find_image_xrefs_container(
                 depth + 1,
             )
             continue
-        xref = Xref(image.objgen[0])
         if Name.SMask in image:
             # Ignore soft masks
             smask_xref = Xref(image.SMask.objgen[0])

src/ocrmypdf/pdfa.py

@@ -90,7 +90,7 @@ def generate_pdfa_ps(target_filename: Path, icc: str = 'sRGB'):
         icc: ICC identifier such as 'sRGB'
     References:
         Adobe PDFMARK Reference:
-        https://www.adobe.com/content/dam/acom/en/devnet/acrobat/pdfs/pdfmark_reference.pdf
+        https://opensource.adobe.com/dc-acrobat-sdk-docs/library/pdfmark/
     """
     if icc != 'sRGB':
         raise NotImplementedError("Only supporting sRGB")

src/ocrmypdf/pdfinfo/info.py

@@ -10,21 +10,21 @@ import atexit
 import logging
 import re
 import statistics
-import sys
 from collections import defaultdict
-from collections.abc import Container, Iterable, Iterator, Mapping, Sequence
-from contextlib import contextmanager
+from collections.abc import Callable, Container, Iterable, Iterator, Mapping, Sequence
+from contextlib import contextmanager, nullcontext
 from decimal import Decimal
 from enum import Enum, auto
 from functools import partial
 from math import hypot, inf, isclose
 from os import PathLike
 from pathlib import Path
-from typing import Callable, NamedTuple
+from typing import NamedTuple
 from warnings import warn
 
 from pdfminer.layout import LTPage, LTTextBox
 from pikepdf import (
+    Dictionary,
     Matrix,
     Name,
     Object,
@@ -41,7 +41,12 @@ from ocrmypdf._concurrent import Executor, SerialExecutor
 from ocrmypdf._progressbar import ProgressBar
 from ocrmypdf.exceptions import EncryptedPdfError, InputFileError
 from ocrmypdf.helpers import Resolution, available_cpu_count, pikepdf_enable_mmap
-from ocrmypdf.pdfinfo.layout import LTStateAwareChar, get_page_analysis, get_text_boxes
+from ocrmypdf.pdfinfo.layout import (
+    LTStateAwareChar,
+    PdfMinerState,
+    get_page_analysis,
+    get_text_boxes,
+)
 
 logger = logging.getLogger()
 
@@ -240,7 +245,13 @@ def _interpret_contents(contentstream: Object, initial_shorthand=UNIT_SQUARE):
                 # to do. Just pretend nothing happened, keep calm and carry on.
                 warn("PDF graphics stack underflowed - PDF may be malformed")
         elif operator == 'cm':
-            ctm = Matrix(operands) @ ctm
+            try:
+                ctm = Matrix(operands) @ ctm
+            except ValueError:
+                raise InputFileError(
+                    "PDF content stream is corrupt - this PDF is malformed. "
+                    "Use a PDF editor that is capable of visually inspecting the PDF."
+                )
         elif operator == 'Do':
             image_name = operands[0]
             settings = XobjectSettings(
@@ -364,8 +375,26 @@ class ImageInfo:
             pim = PdfImage(pdfimage)
         else:
             raise ValueError("Either pdfimage or inline must be set")
+
         self._width = pim.width
         self._height = pim.height
+        if (smask := pim.obj.get(Name.SMask, None)) is not None:
+            # SMask is pretty much an alpha channel, but in PDF it's possible
+            # for channel to have different dimensions than the image
+            # itself. Some PDF writers use this to create a grayscale stencil
+            # mask. For our purposes, the effective size is the size of the
+            # larger component (image or smask).
+            if isinstance(smask, Stream | Dictionary):
+                self._width = max(smask.get(Name.Width, 0), self._width)
+                self._height = max(smask.get(Name.Height, 0), self._height)
+        if (mask := pim.obj.get(Name.Mask, None)) is not None:
+            # If the image has a /Mask entry, it has an explicit mask.
+            # /Mask can be a Stream or an Array. If it's a Stream,
+            # use its /Width and /Height if they are larger than the main
+            # image's.
+            if isinstance(mask, Stream | Dictionary):
+                self._width = max(mask.get(Name.Width, 0), self._width)
+                self._height = max(mask.get(Name.Height, 0), self._height)
 
         # If /ImageMask is true, then this image is a stencil mask
         # (Images that draw with this stencil mask will have a reference to
@@ -469,9 +498,18 @@ class ImageInfo:
     def renderable(self) -> bool:
         """Whether the image is renderable.
 
-        Some PDFs in the wild have invalid images that are not renderable.
+        Some PDFs in the wild have invalid images that are not renderable,
+        due to unusual dimensions.
+
+        Stencil masks are not also not renderable, since they are not
+        drawn, but rather they control how rendering happens.
         """
-        return self.dpi.is_finite and self.width >= 0 and self.height >= 0
+        return (
+            self.dpi.is_finite
+            and self.width >= 0
+            and self.height >= 0
+            and self.type_ != 'stencil'
+        )
 
     @property
     def dpi(self) -> Resolution:
@@ -486,7 +524,7 @@ class ImageInfo:
         """Physical area of the image in square inches."""
         if not self.renderable:
             return 0.0
-        return float(self.width * self.dpi.x * self.height * self.dpi.y)
+        return float((self.width / self.dpi.x) * (self.height / self.dpi.y))
 
     def __repr__(self):
         """Return a string representation of the image."""
@@ -568,7 +606,7 @@ def _find_form_xobject_images(pdf: Pdf, container: Object, contentsinfo: Content
     xobjs = resources[Name.XObject].as_dict()
     for xobj in xobjs:
         candidate = xobjs[xobj]
-        if candidate is None or candidate[Name.Subtype] != Name.Form:
+        if candidate is None or candidate.get(Name.Subtype) != Name.Form:
             continue
 
         form_xobject = candidate
@@ -669,13 +707,13 @@ def _page_has_text(text_blocks: Iterable[FloatRect], page_width, page_height) ->
 
 
 def simplify_textboxes(
-    miner: LTPage, textbox_getter: Callable[[LTPage], Iterator[LTTextBox]]
+    miner_page: LTPage, textbox_getter: Callable[[LTPage], Iterator[LTTextBox]]
 ) -> Iterator[TextboxInfo]:
     """Extract only limited content from text boxes.
 
     We do this to save memory and ensure that our objects are pickleable.
     """
-    for box in textbox_getter(miner):
+    for box in textbox_getter(miner_page):
         first_line = box._objs[0]  # pylint: disable=protected-access
         first_char = first_line._objs[0]  # pylint: disable=protected-access
         if not isinstance(first_char, LTStateAwareChar):
@@ -722,9 +760,12 @@ def _pdf_pageinfo_sync(
     infile: Path,
     check_pages: Container[int],
     detailed_analysis: bool,
+    miner_state: PdfMinerState | None,
 ) -> PageInfo:
     with _pdf_pageinfo_sync_pdf(thread_pdf, infile) as pdf:
-        return PageInfo(pdf, pageno, infile, check_pages, detailed_analysis)
+        return PageInfo(
+            pdf, pageno, infile, check_pages, detailed_analysis, miner_state
+        )
 
 
 def _pdf_pageinfo_concurrent(
@@ -736,6 +777,7 @@ def _pdf_pageinfo_concurrent(
     progbar,
     check_pages,
     detailed_analysis: bool = False,
+    miner_state: PdfMinerState | None = None,
 ) -> Sequence[PageInfo | None]:
     pages: list[PageInfo | None] = [None] * len(pdf.pages)
 
@@ -767,7 +809,8 @@ def _pdf_pageinfo_concurrent(
     initial_pdf = pdf if use_threads else None
 
     contexts = (
-        (n, initial_pdf, infile, check_pages, detailed_analysis) for n in range(total)
+        (n, initial_pdf, infile, check_pages, detailed_analysis, miner_state)
+        for n in range(total)
     )
     assert n_workers == 1 if use_threads else n_workers >= 1, "Not multithreadable"
     logger.debug(
@@ -834,12 +877,15 @@ class PageInfo:
         infile: PathLike,
         check_pages: Container[int],
         detailed_analysis: bool = False,
+        miner_state: PdfMinerState | None = None,
     ):
         """Initialize a PageInfo object."""
         self._pageno = pageno
         self._infile = infile
         self._detailed_analysis = detailed_analysis
-        self._gather_pageinfo(pdf, pageno, infile, check_pages, detailed_analysis)
+        self._gather_pageinfo(
+            pdf, pageno, infile, check_pages, detailed_analysis, miner_state
+        )
 
     def _gather_pageinfo(
         self,
@@ -848,19 +894,27 @@ class PageInfo:
         infile: PathLike,
         check_pages: Container[int],
         detailed_analysis: bool,
+        miner_state: PdfMinerState | None,
     ):
         page: Page = pdf.pages[pageno]
         mediabox = [Decimal(d) for d in page.mediabox.as_list()]
         width_pt = mediabox[2] - mediabox[0]
         height_pt = mediabox[3] - mediabox[1]
 
+        # self._artbox = [float(d) for d in page.artbox.as_list()]
+        # self._bleedbox = [float(d) for d in page.bleedbox.as_list()]
+        self._cropbox = [float(d) for d in page.cropbox.as_list()]
+        self._mediabox = [float(d) for d in page.mediabox.as_list()]
+        self._trimbox = [float(d) for d in page.trimbox.as_list()]
+
         check_this_page = pageno in check_pages
 
         if check_this_page and detailed_analysis:
-            pscript5_mode = str(pdf.docinfo.get(Name.Creator)).startswith('PScript5')
-            miner = get_page_analysis(infile, pageno, pscript5_mode)
-            if miner is not None:
-                self._textboxes = list(simplify_textboxes(miner, get_text_boxes))
+            page_analysis = miner_state.get_page_analysis(pageno)
+            if page_analysis is not None:
+                self._textboxes = list(
+                    simplify_textboxes(page_analysis, get_text_boxes)
+                )
             else:
                 self._textboxes = []
             bboxes = (box.bbox for box in self._textboxes)
@@ -970,6 +1024,21 @@ class PageInfo:
         else:
             raise ValueError("rotation must be a cardinal angle")
 
+    @property
+    def cropbox(self) -> FloatRect:
+        """Return cropbox of page in PDF coordinates."""
+        return self._cropbox
+
+    @property
+    def mediabox(self) -> FloatRect:
+        """Return mediabox of page in PDF coordinates."""
+        return self._mediabox
+
+    @property
+    def trimbox(self) -> FloatRect:
+        """Return trimbox of page in PDF coordinates."""
+        return self._trimbox
+
     @property
     def images(self) -> list[ImageInfo]:
         """Return images."""
@@ -1029,28 +1098,26 @@ class PageInfo:
 
         Returns None if there is no meaningful DPI for the page.
         """
-        image_dpis = [
-            image.dpi.to_scalar() for image in self._images if image.renderable
-        ]
-        image_areas = [image.printed_area for image in self._images if image.renderable]
+        image_dpis = []
+        image_areas = []
+        for image in self._images:
+            if not image.renderable:
+                continue
+            image_dpis.append(image.dpi.to_scalar())
+            image_areas.append(image.printed_area)
+
         total_drawn_area = sum(image_areas)
         if total_drawn_area == 0:
             return None
 
         weights = [area / total_drawn_area for area in image_areas]
         # Calculate harmonic mean of DPIs weighted by area
-        if sys.version_info >= (3, 10):
-            weighted_dpi = statistics.harmonic_mean(image_dpis, weights)
-        else:
-            weighted_dpi = sum(weights) / sum(
-                weight / dpi for weight, dpi in zip(weights, image_dpis)
-            )
+        weighted_dpi = statistics.harmonic_mean(image_dpis, weights)
         max_dpi = max(image_dpis)
         dpi_average_max_ratio = weighted_dpi / max_dpi
 
         arg_max_dpi = image_dpis.index(max_dpi)
         max_area_ratio = image_areas[arg_max_dpi] / total_drawn_area
-
         return PageResolutionProfile(
             weighted_dpi,
             max_dpi,
@@ -1100,16 +1167,26 @@ class PdfInfo:
         with Pdf.open(infile) as pdf:
             if pdf.is_encrypted:
                 raise EncryptedPdfError()  # Triggered by encryption with empty passwd
-            self._pages = _pdf_pageinfo_concurrent(
-                pdf,
-                executor,
-                max_workers,
-                use_threads,
-                infile,
-                progbar,
-                check_pages=check_pages,
-                detailed_analysis=detailed_analysis,
+            pscript5_mode = str(pdf.docinfo.get(Name.Creator, "")).startswith(
+                'PScript5'
             )
+            self._miner_state = (
+                PdfMinerState(infile, pscript5_mode)
+                if detailed_analysis
+                else nullcontext()
+            )
+            with self._miner_state as miner_state:
+                self._pages = _pdf_pageinfo_concurrent(
+                    pdf,
+                    executor,
+                    max_workers,
+                    use_threads,
+                    infile,
+                    progbar,
+                    check_pages=check_pages,
+                    detailed_analysis=detailed_analysis,
+                    miner_state=miner_state,
+                )
             self._needs_rendering = pdf.Root.get(Name.NeedsRendering, False)
             if Name.AcroForm in pdf.Root:
                 if len(pdf.Root.AcroForm.get(Name.Fields, [])) > 0:
@@ -1155,7 +1232,7 @@ class PdfInfo:
     @property
     def filename(self) -> str | Path:
         """Return filename of PDF."""
-        if not isinstance(self._infile, (str, Path)):
+        if not isinstance(self._infile, str | Path):
             raise NotImplementedError("can't get filename from stream")
         return self._infile
 

src/ocrmypdf/pdfinfo/layout.py

@@ -5,18 +5,20 @@
 from __future__ import annotations
 
 import re
-from collections.abc import Mapping
+from collections.abc import Iterator, Mapping
 from contextlib import contextmanager
 from math import copysign
 from os import PathLike
 from pathlib import Path
-from typing import Any, Iterator
+from typing import Any
 from unittest.mock import patch
 
 import pdfminer
 import pdfminer.encodingdb
 import pdfminer.pdfdevice
 import pdfminer.pdfinterp
+import pdfminer.psparser
+from deprecation import deprecated
 from pdfminer.converter import PDFLayoutAnalyzer
 from pdfminer.layout import LAParams, LTChar, LTPage, LTTextBox
 from pdfminer.pdfcolor import PDFColorSpace
@@ -58,9 +60,10 @@ def pdfsimplefont__init__(
 
 setattr(PDFSimpleFont, '__init__', pdfsimplefont__init__)
 
-#
-# pdfminer patches when creator is PScript5.dll
-#
+# Patch pdfminer.six buffer size
+# The parser doesn't properly handle keyword tokens are split across the end of the
+# buffer, so increase the buffer size something far larger than will ever be seen.
+pdfminer.psparser.PSBaseParser.BUFSIZ = 256 * 1024 * 1024
 
 
 def pdftype3font__pscript5_get_height(self):
@@ -287,6 +290,7 @@ def patch_pdfminer(pscript5_mode: bool):
         yield
 
 
+@deprecated(deprecated_in='16.6.0', details='Use PdfMinerState instead.')
 def get_page_analysis(
     infile: PathLike, pageno: int, pscript5_mode: bool
 ) -> LTPage | None:
@@ -317,6 +321,73 @@ def get_page_analysis(
     return dev.get_result()
 
 
+class PdfMinerState:
+    """Provide a context manager for using pdfminer.six.
+
+    This ensures that the file is closed. It also provides a cache of pages
+    from the PDF so that they can be reused if needed, to improve performance.
+    """
+
+    def __init__(self, infile: Path, pscript5_mode: bool) -> None:
+        """Initialize the context manager.
+
+        Args:
+            infile: The path to the PDF file to be analyzed.
+            pscript5_mode: Whether the PDF was generated by PScript5.dll.
+        """
+        self.infile = infile
+        self.rman = pdfminer.pdfinterp.PDFResourceManager(caching=True)
+        self.disable_boxes_flow = None
+        self.page_cache: list[PDFPage] = []
+        self.pscript5_mode = pscript5_mode
+        self.file = None
+
+    def __enter__(self):
+        """Enter the context manager."""
+        self.file = Path(self.infile).open('rb')
+        return self
+
+    def __exit__(self, exc_type, exc_value, traceback):
+        """Exit the context manager."""
+        if self.file:
+            self.file.close()
+        return True
+
+    def _load_page_cache(self):
+        """Load the page cache."""
+        try:
+            self.page_cache = list(PDFPage.get_pages(self.file))
+            if not self.page_cache:
+                raise InputFileError(
+                    "pdfminer did not find any pages in the input file."
+                )
+            for n, page in enumerate(self.page_cache):
+                if page is None:
+                    raise InputFileError(
+                        f"pdfminer could not process page {n} (counting from 0)."
+                    )
+        except PDFTextExtractionNotAllowed as e:
+            raise EncryptedPdfError() from e
+
+    def get_page_analysis(self, pageno: int):
+        """Get the page analysis for a given page."""
+        if not self.page_cache:
+            self._load_page_cache()
+        page = self.page_cache[pageno]
+        dev = TextPositionTracker(
+            self.rman,
+            laparams=LAParams(
+                all_texts=True, detect_vertical=True, boxes_flow=self.disable_boxes_flow
+            ),
+        )
+        interp = pdfminer.pdfinterp.PDFPageInterpreter(self.rman, dev)
+
+        with patch_pdfminer(self.pscript5_mode):
+            interp.process_page(page)
+
+        return dev.get_result()
+
+
 def get_text_boxes(obj) -> Iterator[LTTextBox]:
     """Get the text boxes attached to the current node."""
     for child in obj:

src/ocrmypdf/quality.py

@@ -3,7 +3,6 @@
 
 """Utilities to measure OCR quality."""
 
-
 from __future__ import annotations
 
 import re

src/ocrmypdf/subprocess/__init__.py

@@ -8,12 +8,11 @@ import logging
 import os
 import re
 import sys
-from collections.abc import Mapping, Sequence
+from collections.abc import Callable, Mapping, Sequence
 from contextlib import suppress
 from pathlib import Path
 from subprocess import PIPE, STDOUT, CalledProcessError, CompletedProcess, Popen
 from subprocess import run as subprocess_run
-from typing import Callable, Union
 
 from packaging.version import Version
 
@@ -23,7 +22,7 @@ from ocrmypdf.exceptions import MissingDependencyError
 
 log = logging.getLogger(__name__)
 
-Args = Sequence[Union[Path, str]]
+Args = Sequence[Path | str]
 OsEnviron = os._Environ  # pylint: disable=protected-access
 
 
@@ -172,6 +171,7 @@ def get_version(
         ) from e
     except CalledProcessError as e:
         if e.returncode != 0:
+            log.exception(e)
             raise MissingDependencyError(
                 f"Ran program '{program}' but it exited with an error:\n{e.output}"
             ) from e
@@ -215,8 +215,10 @@ to have {found_version}.  Please update this program.
 
 OLD_VERSION_REQUIRED_FOR = '''
 OCRmyPDF requires '{program}' {need_version} or higher when run with the
-{required_for} arguments.  If you omit these arguments, OCRmyPDF may be able to
-proceed.  For best results, install the program.
+{required_for} arguments.  {program} {found_version} is installed.
+
+If you omit these arguments, OCRmyPDF may be able to
+proceed.  For best results, update the program.
 '''
 
 OSX_INSTALL_ADVICE = '''

src/ocrmypdf/subprocess/_windows.py

@@ -9,18 +9,13 @@ import os
 import re
 import shutil
 import sys
-from collections.abc import Iterable, Iterator
+from collections.abc import Callable, Iterable, Iterator
 from itertools import chain
 from pathlib import Path
-from typing import Any, Callable, TypeVar
+from typing import Any, TypeAlias, TypeVar
 
 from packaging.version import InvalidVersion, Version
 
-if sys.version_info >= (3, 10):
-    from typing import TypeAlias
-else:
-    from typing_extensions import TypeAlias  # pragma: no cover
-
 if sys.platform == 'win32':
     # mypy understands 'if sys.platform' better than try/except ModuleNotFoundError
     import winreg  # pylint: disable=import-error
@@ -84,7 +79,7 @@ def registry_path_ghostscript(env=None) -> Iterator[Path]:
                 registry_subkeys(k), key=ghostscript_version_key, default=(0, 0, 0)
             )
         with winreg.OpenKey(
-            winreg.HKEY_LOCAL_MACHINE, fr"SOFTWARE\Artifex\GPL Ghostscript\{latest_gs}"
+            winreg.HKEY_LOCAL_MACHINE, rf"SOFTWARE\Artifex\GPL Ghostscript\{latest_gs}"
         ) as k:
             for _, gs_path, _ in registry_values(k):
                 yield Path(gs_path) / 'bin'

tests/cache/2400dpi/__-l__eng__000001_ocr.png__000001_ocr_tess__pdf__txt/txt.bin

@@ -0,0 +1,24 @@
+i a la Waterman
+
+4 ons linzen
+
+3 liter water
+
+3 uien
+
+bloem, boter
+
+2 kopjes melk
+
+laurier, kruidnagel, kerrie, zout
+
+De linzgen wassen en in-l liter kokend wa-
+ter 1 dag laten weken, 2 liter water bij
+de linzen voegen, zonder het water waarin
+ze geweekt zijn af te gieten, De helft van
+de uien bakken met laurier en Kruidnagel.
+Alle uien, kerrie en zgout bij de linzen
+voegen, Alles aan de kook brengen, Van de
+bloem met boter en melk een papje maken en
+verder afmaken met de soep, Als de linzen
+gfgaar Zijn is de soep klaar.

tests/cache/3small/__-l__eng__000001_ocr.png__000001_ocr_tess__pdf__txt/txt.bin

@@ -0,0 +1,15 @@
+Tarnose
+
+Bokale oa
+
+Lehuntze
+
+Mugerre
+
+Milafranga Komunikabideak
+
+BAIONA  zeiteninsiie —
+
+7 Trenbideak -----
+
+t\ Basusarri — spmeans:20141004 ae: . _ ~

tests/cache/3small/__-l__eng__000002_ocr.png__000002_ocr_tess__pdf__txt/txt.bin

@@ -0,0 +1 @@
+Covfefe is a perfectly cromulent word.

tests/cache/3small/__-l__eng__000003_ocr.png__000003_ocr_tess__pdf__txt/txt.bin

@@ -0,0 +1,24 @@
+Linzensoep a la Waterman
+
+4 ons linzen
+
+3 liter water
+
+3 uien
+
+bloem, boter
+
+2 kopjes melk
+
+laurier, kruidnagel, kerrie, zout
+
+De linzgen wassen en in-l liter kokend wa-
+ter 1 dag laten weken, 2 liter water bij
+de linzen voegen, zonder het water waarin
+ze geweekt zijn af te gieten, De helft van
+de uien bakken met laurier en Kruidnagel.
+Alle uien, kerrie en zgout bij de linzen
+voegen, Alles aan de kook brengen, Van de
+bloem met boter en melk een papje maken en
+verder afmaken met de soep, Als de linzen
+gfgaar Zijn is de soep klaar.

tests/cache/francais/__-l__deu__000001_ocr.png__000001_ocr_tess__pdf__txt/txt.bin

@@ -0,0 +1,12 @@
+Portez ce vieux whisky au juge
+blond qui fume sur son Ile
+interieure, a cöte de l'alcöve
+ovoide, oU les büches se
+consument dans l'ätre, ce qui
+ui permet de penser & la
+caenogenese de |'etre dont il
+est question dans la cause
+ambigu& entendue a MoY, dans
+un capharnaüm qui, pense-t-il,
+diminue ca et la la qualit& de son
+ceuvre.

tests/cache/graph_ocred/__-l__eng__000001_ocr.png__000001_ocr_tess__pdf__txt/txt.bin

@@ -0,0 +1,22 @@
+600
+500 .
+400 _ EB fp ys
+300 —f— EN / ~/ Y
+Tg ANA a3
+100 - nee -eemiae
+0-+—-* a ee ee ee eee
+S @ s > oO © ve S ) @ + & & “A 5 oo
+Se ° Ps as ge eS € x ro NS Po e? & s AS
+a a © FF SF HY HK SK BM ee sO
+e < Na ‘ : > cy xs eS @ Ww a) Oo
+ee S&S FF SF HK S e © 4
+~ & e
+3 x
+
+—¢—Support
+
+—H— No vote[note 1]
+ir Oppose
+—=—Net[note 2]
+
+re Percentage [note 3]

tests/cache/manifest.jsonl

@@ -71,3 +71,15 @@
 {"tesseract_version": "5.3.2", "system": "Linux", "python": "3.11.6", "argv_slug": "__-l__eng__000001_ocr.png__000001_ocr_hocr__hocr__txt", "sourcefile": "resources/poster.pdf", "args": ["-l", "eng", "$TMPDIR/000001_ocr.png", "$TMPDIR/000001_ocr_hocr", "hocr", "txt"]}
 {"tesseract_version": "5.3.2", "system": "Linux", "python": "3.11.6", "argv_slug": "__-l__eng__000001_ocr.png__000001_ocr_tess__pdf__txt", "sourcefile": "resources/multipage.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000001_ocr.png", "$TMPDIR/000001_ocr_tess", "pdf", "txt"]}
 {"tesseract_version": "5.3.2", "system": "Linux", "python": "3.11.6", "argv_slug": "__-l__eng__000001_ocr.png__000001_ocr_hocr__hocr__txt", "sourcefile": "resources/poster.pdf", "args": ["-l", "eng", "$TMPDIR/000001_ocr.png", "$TMPDIR/000001_ocr_hocr", "hocr", "txt"]}
+{"tesseract_version": "5.3.2", "system": "Linux", "python": "3.11.7", "argv_slug": "__-l__deu__000001_ocr.png__000001_ocr_tess__pdf__txt", "sourcefile": "resources/francais.pdf", "args": ["-l", "deu", "-c", "textonly_pdf=1", "$TMPDIR/000001_ocr.png", "$TMPDIR/000001_ocr_tess", "pdf", "txt"]}
+{"tesseract_version": "5.3.2", "system": "Linux", "python": "3.11.7", "argv_slug": "__-l__eng__--oem__1__000001_ocr.png__000001_ocr_tess__pdf__txt", "sourcefile": "resources/trivial.pdf", "args": ["-l", "eng", "--oem", "1", "-c", "textonly_pdf=1", "$TMPDIR/000001_ocr.png", "$TMPDIR/000001_ocr_tess", "pdf", "txt"]}
+{"tesseract_version": "5.3.2", "system": "Linux", "python": "3.11.7", "argv_slug": "__-l__eng__000001_ocr.png__000001_ocr_tess__pdf__txt", "sourcefile": "resources/trivial.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000001_ocr.png", "$TMPDIR/000001_ocr_tess", "pdf", "txt"]}
+{"tesseract_version": "5.3.2", "system": "Linux", "python": "3.11.7", "argv_slug": "__-l__eng__000001_ocr.png__000001_ocr_tess__pdf__txt", "sourcefile": "resources/2400dpi.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000001_ocr.png", "$TMPDIR/000001_ocr_tess", "pdf", "txt"]}
+{"tesseract_version": "5.3.2", "system": "Linux", "python": "3.11.7", "argv_slug": "__-l__eng__thresholding_method=1__000001_ocr.png__000001_ocr_tess__pdf__txt", "sourcefile": "resources/trivial.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "-c", "thresholding_method=1", "$TMPDIR/000001_ocr.png", "$TMPDIR/000001_ocr_tess", "pdf", "txt"]}
+{"tesseract_version": "5.3.2", "system": "Linux", "python": "3.11.7", "argv_slug": "__-l__eng__thresholding_method=2__000001_ocr.png__000001_ocr_tess__pdf__txt", "sourcefile": "resources/trivial.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "-c", "thresholding_method=2", "$TMPDIR/000001_ocr.png", "$TMPDIR/000001_ocr_tess", "pdf", "txt"]}
+{"tesseract_version": "5.3.2", "system": "Linux", "python": "3.11.7", "argv_slug": "__-l__eng__000001_ocr.png__000001_ocr_tess__pdf__txt", "sourcefile": "resources/graph_ocred.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000001_ocr.png", "$TMPDIR/000001_ocr_tess", "pdf", "txt"]}
+{"tesseract_version": "5.3.2", "system": "Linux", "python": "3.11.7", "argv_slug": "__-l__eng__000002_ocr.png__000002_ocr_tess__pdf__txt", "sourcefile": "resources/3small.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000002_ocr.png", "$TMPDIR/000002_ocr_tess", "pdf", "txt"]}
+{"tesseract_version": "5.3.2", "system": "Linux", "python": "3.11.7", "argv_slug": "__-l__eng__000001_ocr.png__000001_ocr_tess__pdf__txt", "sourcefile": "resources/3small.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000001_ocr.png", "$TMPDIR/000001_ocr_tess", "pdf", "txt"]}
+{"tesseract_version": "5.3.2", "system": "Linux", "python": "3.11.7", "argv_slug": "__-l__eng__000003_ocr.png__000003_ocr_tess__pdf__txt", "sourcefile": "resources/3small.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000003_ocr.png", "$TMPDIR/000003_ocr_tess", "pdf", "txt"]}
+{"tesseract_version": "5.3.2", "system": "Linux", "python": "3.11.7", "argv_slug": "__-l__eng__000001_ocr.png__000001_ocr_tess__pdf__txt", "sourcefile": "resources/poster.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000001_ocr.png", "$TMPDIR/000001_ocr_tess", "pdf", "txt"]}
+{"tesseract_version": "5.3.2", "system": "Linux", "python": "3.11.7", "argv_slug": "__-l__eng__000001_ocr.png__000001_ocr_tess__pdf__txt", "sourcefile": "resources/poster.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000001_ocr.png", "$TMPDIR/000001_ocr_tess", "pdf", "txt"]}

tests/cache/poster/__-l__eng__000001_ocr.png__000001_ocr_tess__pdf__txt/txt.bin

@@ -0,0 +1,118 @@
+The LinnSequencer
+32 Track MIDI Sequence Recorder
+
+The LinnSequencer is a state-of-the-art composition and performance tool for the professional musician. It is
+extremely powerful, yet amazingly simple to learn and use. It’s many remarkable features include:
+
+© Operation is similar to multi-track tape recorder with PLAY, STOP, RECORD, FAST
+FORWARD, REWIND, and LOCATE controls.
+
+e Each of the 100 sequences contains 32 simultaneous, polyphonic tracks. Each track may
+be assigned to one of 16 MIDI channels. Simultaneously plays up to 16 polyphonic
+
+synthesizers!
+
+© Ultra-fast 3!” disk drive stores complex songs in seconds and holds over 110,000 notes
+
+per disk!
+
+¢ One or all tracks may be TRANSPOSED at the touch of a key.
+e Exclusive real-time ERASE function makes editing FAST.
+e Exclusive REPEAT function automatically repeats any held notes at a pre-selected
+
+rhythmic value.
+
+¢ TIMING CORRECTION works during playback and operates without ‘chopping’ notes.
+
+¢ Optional SMPTE time code synchronization.
+
+¢ Optional remote control.
+
+Recording a Sequence
+
+To record a sequence, simply press RECORD and PLAY,
+then play your MIDI keyboard in time to the Sequencer’s
+click track. When the sequence loops back around to bar 1,
+you’ ll hear what you played—only all timing errors will be
+corrected! (Timing correction may be adjusted or defeated).
+Any additional notes played will be added into the track
+—existing notes are not erased while recording!
+
+FAST FORWARD, REWIND, and LOCATE controls
+may be used at any time to quickly access any location in
+your sequence for spot-recording. To overdub a new part,
+select a different track and start recording—while you
+record, the first track will play in perfect sync (unless you
+MUTE it, or SOLO another track). In this way, up to 32
+tracks may be overdubbed! All MIDI effects are recorded
+including pitch bend, modulation, velocity, aftertouch,
+sustain pedal, and program changes!
+
+Editing
+
+To erase a wrong note, simply hold ERASE and press
+the note to be erased just before it plays in the sequence—
+when played back, it will be gone. Notes may also be
+added, erased, or changed using the SINGLE STEP func-
+tion. To overdub notes at specific points within a sequence,
+
+Additional Features
+
+simply use LOCATE, FAST FORWARD, or REWIND to
+find the desired bar number, then start recording.
+
+The INSERT/COPY function allows you to move bars
+from one location to another—in the same sequence or a
+different one. For example, you might insert a copy of the
+first verse between the second chorus and the bridge.
+DELETE BARS operates the same way to remove
+unwanted sections.
+
+Creating a Song
+
+One way to create a song is to record each track all the
+way through (up to 999 bars). Another way is to record
+each basic section (verse, chorus, etc.) in individual
+sequences, then use the CREATE SONG function to “chain”
+them together. CREATE SONG will then automatically
+copy all the parts into a new sequence. If desired, you can
+even set the last few bars to repeat infinitely, for a fadeout.
+
+Composition Without Compromise
+
+The technology you use should never be so complex that
+it interferes with the creative process. That’s precisely why
+the LinnSequencer is designed to let you compose, record
+and edit while devoting your undivided attention to your
+music. See your Linn dealer today for a demonstration!
+
+¢ Simple, easy to learn operation—the 32 character LCD display clearly guides you through all operations. If needed, the
+
+HELP button displays additional explanations.
+
+® Non-destructive recording—existing notes are not erased while recording.
+© Two FOOTSWITCH INPUTS may be assigned to remotely control many of the commonly used functions, including
+
+ERASE, REPEAT, PLAY/STOP, or LOCATE.
+
+¢ Two TRIGGER OUTPUTS may be programmed to output pulses at any selected note value.
+
+@ Will sync to standard LinnDrum or Linn 9000 sync tone.
+
+© Utilizes ultra high-speed, 8 MHz 80186 16 bit computer internally for FAST operation.
+¢ TEMPO may be specified in BEATS-PER-MINUTE or FRAMES-PER-BEAT at 24, 25, or 30 frames per second,
+
+(even drop frame!)
+
+¢ TEMPO may be entered numerically, adjustable in tenths of a Beat-Per-Minute increments, or by tapping quarter notes
+
+on the TAP TEMPO button.
+
+¢ TEMPO CHANGES may be programmed into a sequence, with smooth transitions if desired.
+e Any TIME SIGNATURE may be used, and may be changed within a song.
+
+linn
+Linn Electronics, Inc.
+
+18720 Oxnard Street, Tarzana, CA 91356
+(818) 708-8131 TELEX #298949 LINN UR