v16.10.0 release notes

I prefer to write the name in full aka `jbarlow83/ocrmypdf-alpine` and I'd also suggest to document this because:
* if you use `docker tag` this AFAIK only tags the currently downloaded (=pulled) version of that image
* in case a new update comes out, the new one will not be pulled automatically and one would have to pull and tag the image locally, again
* This `docker tag`  command is easily overlooked, if users just run `docker run ocrmypdf` this may or may not work, depending on how it is resolved.
   Also, AFAIK if one could get Docker to register https://hub.docker.com/ocrmypdf then this would suddenly be used instead of your image (currently `podman pull docker.io/ocrmypdf` returns a 404 for me, though)
* It is more common to write at least the user namespace there and the project, to prevent such errors.

Also, default [Docker has many shortcuts for this and e.g. assumes Docker-Hub is always being used](https://stackoverflow.com/questions/37861791/how-are-docker-image-names-parsed). Podman usually does not, that's why I personally prefer to use the very full and clear `docker.io/jbarlow83/ocrmypdf-alpine:latest` e.g. for alpine. This makes it not only clear which version is used, but also where it is pulled from (should one have configured different Docker registries).

.docker/Dockerfile

@@ -1,7 +1,7 @@
-# OCRmyPDF
-#
+# 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
@@ -9,51 +9,65 @@ 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 \
-  git
-
-# Get the latest pip (Ubuntu version doesn't support manylinux2010)
-RUN \
-  curl https://bootstrap.pypa.io/get-pip.py | python3
+  git \
+  libcairo2-dev \
+  pkg-config
 
 # Compile and install jbig2
 # Needs libleptonica-dev, zlib1g-dev
 RUN \
   mkdir jbig2 \
-  && curl -L https://github.com/agl/jbig2enc/archive/ea6a40a.tar.gz | \
+  && curl -L https://github.com/agl/jbig2enc/archive/c0141bf.tar.gz | \
   tar xz -C jbig2 --strip-components=1 \
   && cd jbig2 \
   && ./autogen.sh && ./configure && make && make install \
   && cd .. \
   && rm -rf jbig2
 
-COPY . /app
 
 WORKDIR /app
 
-RUN pip3 install --no-cache-dir .[test,webservice,watcher]
+# Copy uv from ghcr
+COPY --from=ghcr.io/astral-sh/uv:0.5.5 /uv /uvx /bin/
+
+ENV UV_COMPILE_BYTECODE=1 UV_LINK_MODE=copy
+
+# Install the project's dependencies using the lockfile and settings
+RUN --mount=type=cache,target=/root/.cache/uv \
+    --mount=type=bind,source=uv.lock,target=uv.lock \
+    --mount=type=bind,source=pyproject.toml,target=pyproject.toml \
+    uv sync --frozen --no-install-project --no-dev
+
+# Then, add the rest of the project source code and install it
+# Installing separately from its dependencies allows optimal layer caching
+COPY . /app
+RUN --mount=type=cache,target=/root/.cache/uv \
+    uv sync --frozen \
+        --extra test --extra webservice --extra watcher --no-dev \
+        --no-install-package pyarrow
 
 FROM base
 
+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 \
-  img2pdf \
-  libsm6 libxext6 libxrender-dev \
+  fonts-droid-fallback \
+  jbig2dec \
   pngquant \
   tesseract-ocr \
   tesseract-ocr-chi-sim \
@@ -70,11 +84,13 @@ 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/setup.cfg /app/setup.py /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

@@ -0,0 +1,80 @@
+# SPDX-FileCopyrightText: 2023 James R. Barlow
+# SPDX-License-Identifier: MPL-2.0
+
+# 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 issue is fixed in 3.21.
+# Details
+#  https://gitlab.alpinelinux.org/alpine/aports/-/issues/16143
+#  https://github.com/ocrmypdf/OCRmyPDF/issues/1395
+FROM alpine:3.21 AS base
+
+ENV LANG=C.UTF-8
+ENV TZ=UTC
+
+RUN apk add --no-cache \
+    python3 \
+    zlib
+
+FROM base AS builder
+
+# Yes it really is python3-dev, and py3-package
+RUN apk add --no-cache \
+    ca-certificates \
+    git \
+    python3-dev \
+    py3-pyarrow \
+    curl
+
+WORKDIR /app
+
+COPY --from=ghcr.io/astral-sh/uv:0.5.5 /uv /uvx /bin/
+
+ENV UV_COMPILE_BYTECODE=1 UV_LINK_MODE=copy
+
+RUN uv venv --system-site-packages .venv
+
+# Install the project's dependencies using the lockfile and settings
+RUN --mount=type=cache,target=/root/.cache/uv \
+    --mount=type=bind,source=uv.lock,target=uv.lock \
+    --mount=type=bind,source=pyproject.toml,target=pyproject.toml \
+    uv sync --frozen --no-install-project --no-dev
+
+# Then, add the rest of the project source code and install it
+# Installing separately from its dependencies allows optimal layer caching
+COPY . /app
+RUN --mount=type=cache,target=/root/.cache/uv \
+    uv sync --frozen \
+        --extra test --extra webservice --extra watcher --no-dev \
+        --no-install-package pyarrow
+
+FROM base
+
+RUN apk add --no-cache \
+    ghostscript \
+    jbig2dec \
+    jbig2enc \
+    pngquant \
+    tesseract-ocr \
+    tesseract-ocr-data-chi_sim \
+    tesseract-ocr-data-deu \
+    tesseract-ocr-data-eng \
+    tesseract-ocr-data-fra \
+    tesseract-ocr-data-osd \
+    tesseract-ocr-data-por \
+    tesseract-ocr-data-spa \
+    ttf-droid \
+    unpaper \
+    && rm -rf /var/cache/apk/*
+
+WORKDIR /app
+
+COPY --from=builder --chown=app:app /app /app
+
+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"]

.dockerignore

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

.gitattributes

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

.github/FUNDING.yml

@@ -1,3 +1,6 @@
+# SPDX-FileCopyrightText: 2022 James R. Barlow
+# SPDX-License-Identifier: MPL-2.0
+
 # These are supported funding model platforms
 
 github: # Replace with up to 4 GitHub Sponsors-enabled usernames e.g., [user1, user2]

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

@@ -0,0 +1,72 @@
+name: Installation, packaging, dependencies
+description: Installation, packages, dependencies, "nothing works", test suite failures...
+title: "[Bug]: "
+labels: ["triage"]
+assignees:
+  - jbarlow83
+body:
+  - type: markdown
+    attributes:
+      value: |
+        Thanks for taking the time to fill out this bug report!
+
+        If your issue involves using OCRmyPDF on specific file(s) and not getting
+        good results, this is the *wrong* issue template. Please use the recommended
+        template to ensure we have enough information to help.
+  - type: textarea
+    id: what-happened
+    attributes:
+      label: What were you trying to do?
+      description: Also tell us, what did you expect to happen?
+      placeholder: Tell us what you see!
+    validations:
+      required: true
+  - type: dropdown
+    id: packaging-system
+    attributes:
+      label: Where are you installing/running from?
+      multiple: true
+      options:
+        - PyPI (pip, poetry, pipx, etc.)
+        - Linux package manager (apt, dnf, etc.)
+        - Wndows package manager (chocolatey, etc.)
+        - Homebrew
+        - Docker container
+        - Ubuntu snap
+        - Conda
+        - source build
+    validations:
+      required: true
+  - type: input
+    id: version
+    attributes:
+      label: OCRmyPDF version
+      description: Paste "ocrmypdf --version" here
+  - type: dropdown
+    id: operating-system
+    attributes:
+      label: What operating system are you working on?
+      multiple: true
+      options:
+        - Linux
+        - 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:
+      label: Relevant log output
+      description: Please copy and paste any relevant log output. This will be automatically formatted into code, so no need for backticks.
+      render: plain text

.github/ISSUE_TEMPLATE/1-general-issues.md

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

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

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

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

@@ -0,0 +1,75 @@
+name: Problem with specific file
+description: Something went wrong while trying to OCR a specific file
+title: "[Bug]: "
+labels: ["triage"]
+assignees:
+  - jbarlow83
+body:
+  - type: markdown
+    attributes:
+      value: |
+        Thanks for taking the time to describe this issue with a particular file.
+  - type: textarea
+    id: what-happened
+    attributes:
+      label: Describe the bug
+      description: A clear and concise description of what the bug is.
+      placeholder: Tell us what you see!
+    validations:
+      required: true
+  - type: textarea
+    id: reproduce
+    attributes:
+      label: Steps to reproduce
+      description: Please include steps to reproduce.
+      value: |
+        1. Run ocrmypdf -v1 ...arguments... input.pdf output.pdf
+        2. Open output.pdf
+        3. ...
+      render: plain text
+  - type: textarea
+    id: files
+    attributes:
+      label: Files
+      description: |
+        Please attach the input and output files, or any screenshots that may be helpful.
+
+        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:
+      label: How did you download and install the software?
+      multiple: true
+      options:
+        - PyPI (pip, poetry, pipx, etc.)
+        - Linux package manager (apt, dnf, etc.)
+        - Windows package manager (chocolatey, etc.)
+        - Homebrew
+        - Docker container
+        - Ubuntu snap
+        - Conda
+        - source build
+  - type: input
+    id: version
+    attributes:
+      label: OCRmyPDF version
+      description: Paste "ocrmypdf --version" here
+      placeholder: ocrmypdf --version
+  - type: textarea
+    id: logs
+    attributes:
+      label: Relevant log output
+      description: Please copy and paste any relevant log output. This will be automatically formatted into code, so no need for backticks.
+      placeholder: Run OCRmyPDF with verbosity `-v1` to get more detailed logging output.
+      render: plain text

.github/ISSUE_TEMPLATE/3-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/ISSUE_TEMPLATE/3-feature_request.md

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

.github/ISSUE_TEMPLATE/4-feature-request.yml

@@ -0,0 +1,12 @@
+name: Feature request
+description: Suggest an idea for this project
+title: "[Feature]: "
+labels: ["enhancement", "triage"]
+assignees:
+  - jbarlow83
+body:
+  - type: textarea
+    id: feature
+    attributes:
+      label: Describe the proposed feature
+      description: A clear and concise description of what the desired is.

.github/dependabot.yml

@@ -1,3 +1,6 @@
+# SPDX-FileCopyrightText: 2022 James R. Barlow
+# SPDX-License-Identifier: MPL-2.0
+
 # To get started with Dependabot version updates, you'll need to specify which
 # package ecosystems to update and where the package manifests are located.
 # Please see the documentation for all configuration options:

.github/workflows/build.yml

@@ -1,9 +1,11 @@
+# SPDX-FileCopyrightText: 2022 James R. Barlow
+# SPDX-License-Identifier: MPL-2.0
 name: Test and deploy
 
 on:
   push:
     branches:
-      - master
+      - main
       - ci
       - release/*
       - feature/*
@@ -19,41 +21,38 @@ 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-18.04
-            python: "3.7"
-          - os: ubuntu-20.04
-            python: "3.8"
-          - os: ubuntu-20.04
-            python: "3.9"
-          - os: ubuntu-20.04
+          - os: ubuntu-22.04
+            tesseract_ppa: "ppa"
             python: "3.10"
-          - os: ubuntu-latest
-            python: "3.9"
-          - os: ubuntu-latest
-            python: "pypy-3.8"
-          - os: ubuntu-latest
-            python: "3.9"
-            tesseract5: true
+          - os: ubuntu-24.04
+            python: "pypy3.10"
 
     env:
       OS: ${{ matrix.os }}
       PYTHON: ${{ matrix.python }}
 
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
         with:
           fetch-depth: "0" # 0=all, needed for setuptools-scm to resolve version tags
 
-      - uses: actions/setup-python@v4
-        name: Install Python
+      - name: Install uv
+        uses: astral-sh/setup-uv@v5
+        with:
+          version: "0.5.x"
+
+      - name: "Set up Python"
+        uses: actions/setup-python@v5
         with:
           python-version: ${{ matrix.python }}
 
-      - name: Install Tesseract 5
-        if: matrix.tesseract5
+      - name: Install Tesseract from PPA
+        if: matrix.tesseract_ppa == 'ppa'
         run: |
-          sudo add-apt-repository ppa:alex-p/tesseract-ocr-devel
+          sudo add-apt-repository -y ppa:alex-p/tesseract-ocr5.3
 
       - name: Install common packages
         run: |
@@ -61,7 +60,9 @@ jobs:
           sudo apt-get install -y --no-install-recommends \
             curl \
             ghostscript \
+            jbig2dec \
             img2pdf \
+            libexempi8 \
             libffi-dev \
             libsm6 libxext6 libxrender-dev \
             pngquant \
@@ -73,18 +74,6 @@ jobs:
             unpaper \
             zlib1g
 
-      - name: Install Ubuntu 18.04 packages
-        if: matrix.os == 'ubuntu-18.04'
-        run: |
-          sudo apt-get install -y --no-install-recommends \
-            libexempi3
-
-      - name: Install Ubuntu 20.04 packages
-        if: matrix.os == 'ubuntu-20.04' || matrix.os == 'ubuntu-latest'
-        run: |
-          sudo apt-get install -y --no-install-recommends \
-            libexempi8
-
       - name: Install Ubuntu packages for PyPy
         if: startsWith(matrix.python, 'pypy')
         run: |
@@ -95,8 +84,7 @@ jobs:
 
       - name: Install Python packages
         run: |
-          python -m pip install --upgrade pip wheel
-          python -m pip install .[test]
+          uv sync --extra test --no-dev
 
       - name: Report versions
         run: |
@@ -104,14 +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
@@ -121,24 +111,20 @@ jobs:
     runs-on: ${{ matrix.os }}
     strategy:
       matrix:
-        os: [macos-latest]
-        python: ["3.9", "3.10"]
+        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 }}
       PYTHON: ${{ matrix.python }}
 
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
         with:
           fetch-depth: "0" # 0=all, needed for setuptools-scm to resolve version tags
 
-      - uses: actions/setup-python@v4
-        name: Install Python
-        with:
-          python-version: ${{ matrix.python }}
-
       - name: Install Homebrew deps
+        continue-on-error: true
         run: |
           brew update
           brew install \
@@ -149,24 +135,35 @@ jobs:
             pngquant \
             tesseract
 
+      - name: Install uv
+        uses: astral-sh/setup-uv@v5
+        with:
+          version: "0.5.x"
+
+      - name: "Set up Python"
+        uses: actions/setup-python@v5
+        with:
+          python-version: ${{ matrix.python }}
+
       - name: Install Python packages
         run: |
-          python -m pip install --upgrade pip wheel
-          python -m pip install .[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
@@ -177,38 +174,44 @@ jobs:
     strategy:
       matrix:
         os: [windows-latest]
-        python: ["3.9", "3.10"]
+        python: ["3.10", "3.11", "3.12", "3.13"]
 
     env:
       OS: ${{ matrix.os }}
       PYTHON: ${{ matrix.python }}
 
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
         with:
           fetch-depth: "0" # 0=all, needed for setuptools-scm to resolve version tags
 
-      - uses: actions/setup-python@v4
-        name: Install Python
+      - name: Install uv
+        uses: astral-sh/setup-uv@v5
+        with:
+          version: "0.5.x"
+
+      - name: "Set up Python"
+        uses: actions/setup-python@v5
         with:
           python-version: ${{ matrix.python }}
 
       - 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 .[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
@@ -217,23 +220,22 @@ jobs:
     name: Build sdist and wheels
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
         with:
           fetch-depth: "0" # 0=all, needed for setuptools-scm to resolve version tags
 
-      - uses: actions/setup-python@v4
-        name: Install Python
+      - name: Install uv
+        uses: astral-sh/setup-uv@v5
         with:
-          python-version: "3.7"
+          version: "0.5.x"
 
       - name: Make wheels and sdist
         run: |
-          python -m pip install --upgrade pip wheel
-          python setup.py sdist
-          python setup.py bdist_wheel
+          uv build --sdist --wheel
 
-      - uses: actions/upload-artifact@v3
+      - uses: actions/upload-artifact@v4
         with:
+          name: artifact
           path: |
             ./dist/*.whl
             ./dist/*.tar.gz
@@ -242,21 +244,63 @@ jobs:
     name: Deploy artifacts to PyPI
     needs: [wheel_sdist_linux, test_linux, test_macos, test_windows]
     runs-on: ubuntu-latest
+    environment: release
+    permissions:
+      id-token: write  # mandatory for PyPI publishing
     if: github.event_name == 'push' && startsWith(github.event.ref, 'refs/tags/v')
     steps:
-      - uses: actions/download-artifact@v3
+      - uses: actions/download-artifact@v4
         with:
           name: artifact
           path: dist
 
-      - uses: pypa/gh-action-pypi-publish@master
-        with:
-          user: __token__
-          password: ${{ secrets.TOKEN_PYPI }}
-          # repository_url: https://test.pypi.org/legacy/
+      - name: Publish to PyPI
+        uses: pypa/gh-action-pypi-publish@release/v1
 
-  docker:
-    name: Build Docker images
+  create_release:
+    name: Create GitHub release
+    needs: [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: Sign the dists with Sigstore
+        uses: sigstore/gh-action-sigstore-python@v3.0.0
+        with:
+          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 "$GITHUB_REPOSITORY"
+
+  docker_ubuntu:
+    name: Build Ubuntu-based Docker image
     needs: [wheel_sdist_linux, test_linux, test_macos, test_windows]
     runs-on: ubuntu-latest
     if: github.event_name != 'pull_request'
@@ -264,9 +308,9 @@ jobs:
       - name: Set image tag to release or branch
         run: echo "DOCKER_IMAGE_TAG=${GITHUB_REF##*/}" >> $GITHUB_ENV
 
-      - name: If master, set to latest
+      - name: If main, set to latest
         run: echo 'DOCKER_IMAGE_TAG=latest' >> $GITHUB_ENV
-        if: env.DOCKER_IMAGE_TAG == 'master'
+        if: env.DOCKER_IMAGE_TAG == 'main'
 
       - name: Set Docker Hub repository to username
         run: echo "DOCKER_REPOSITORY=jbarlow83" >> $GITHUB_ENV
@@ -274,22 +318,22 @@ jobs:
       - name: Set image name
         run: echo "DOCKER_IMAGE_NAME=ocrmypdf" >> $GITHUB_ENV
 
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
         with:
           fetch-depth: "0" # 0=all, needed for setuptools-scm to resolve version tags
 
       - name: Login to Docker Hub
-        uses: docker/login-action@v2
+        uses: docker/login-action@v3
         with:
           username: jbarlow83
           password: ${{ secrets.DOCKERHUB_TOKEN }}
 
       - name: Set up QEMU
-        uses: docker/setup-qemu-action@v2
+        uses: docker/setup-qemu-action@v3
 
       - name: Set up Docker Buildx
         id: buildx
-        uses: docker/setup-buildx-action@v2
+        uses: docker/setup-buildx-action@v3
 
       - name: Print image tag
         run: echo "Building image ${DOCKER_REPOSITORY}/${DOCKER_IMAGE_NAME}:${DOCKER_IMAGE_TAG}"
@@ -300,4 +344,49 @@ jobs:
             --push \
             --platform linux/arm64/v8,linux/amd64  \
             --tag "${DOCKER_REPOSITORY}/${DOCKER_IMAGE_NAME}:${DOCKER_IMAGE_TAG}" \
+            --tag "${DOCKER_REPOSITORY}/${DOCKER_IMAGE_NAME}-ubuntu:${DOCKER_IMAGE_TAG}" \
             --file .docker/Dockerfile .
+
+  docker_alpine:
+    name: Build Alpine-based Docker images
+    needs: [wheel_sdist_linux, test_linux, test_macos, test_windows]
+    runs-on: ubuntu-latest
+    if: github.event_name != 'pull_request'
+    steps:
+      - name: Set image tag to release or branch
+        run: echo "DOCKER_IMAGE_TAG=${GITHUB_REF##*/}" >> $GITHUB_ENV
+
+      - name: If main, set to latest
+        run: echo 'DOCKER_IMAGE_TAG=latest' >> $GITHUB_ENV
+        if: env.DOCKER_IMAGE_TAG == 'main'
+
+      - name: Set Docker Hub repository to username
+        run: echo "DOCKER_REPOSITORY=jbarlow83" >> $GITHUB_ENV
+
+      - name: Set image name
+        run: echo "DOCKER_IMAGE_NAME=ocrmypdf-alpine" >> $GITHUB_ENV
+
+      - uses: actions/checkout@v4
+        with:
+          fetch-depth: "0" # 0=all, needed for setuptools-scm to resolve version tags
+
+      - name: Login to Docker Hub
+        uses: docker/login-action@v3
+        with:
+          username: jbarlow83
+          password: ${{ secrets.DOCKERHUB_TOKEN }}
+
+      - name: Set up Docker Buildx
+        id: buildx
+        uses: docker/setup-buildx-action@v3
+
+      - name: Print image tag
+        run: echo "Building image ${DOCKER_REPOSITORY}/${DOCKER_IMAGE_NAME}:${DOCKER_IMAGE_TAG}"
+
+      - name: Build
+        run: |
+          docker buildx build \
+            --push \
+            --platform linux/amd64,linux/arm64  \
+            --tag "${DOCKER_REPOSITORY}/${DOCKER_IMAGE_NAME}:${DOCKER_IMAGE_TAG}" \
+            --file .docker/Dockerfile.alpine .

.github/workflows/triage.yml

@@ -0,0 +1,32 @@
+# SPDX-FileCopyrightText: 2024 James R. Barlow
+# SPDX-License-Identifier: MPL-2.0
+
+name: Remove Triage Label on Reply
+
+on:
+  issue_comment:
+    types:
+      - created
+
+jobs:
+  remove-triage-label:
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Check if comment is by the repository owner
+        id: check_comment
+        run: |
+          echo "::set-output name=is_owner::$(
+            if [[ '${{ github.event.comment.user.login }}' == 'jbarlow83' ]]; then
+              echo 'true';
+            else
+              echo 'false';
+            fi
+          )"
+
+      - name: Remove 'triage' label
+        if: ${{ steps.check_comment.outputs.is_owner == 'true' }}
+        uses: actions-ecosystem/action-remove-labels@v1
+        with:
+          github_token: ${{ secrets.GITHUB_TOKEN }}
+          labels: triage

.gitignore

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

.pre-commit-config.yaml

@@ -1,33 +1,28 @@
+# SPDX-FileCopyrightText: 2022 James R. Barlow
+# SPDX-License-Identifier: MPL-2.0
+
 repos:
   - repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v4.3.0
+    rev: v4.4.0
     hooks:
       - id: check-case-conflict
       - id: check-merge-conflict
       - id: check-toml
       - id: check-yaml
       - id: debug-statements
-  - repo: https://github.com/pycqa/isort
-    rev: 5.10.1
+  - repo: https://github.com/charliermarsh/ruff-pre-commit
+    rev: "v0.0.261"
     hooks:
-      - id: isort
-        args: ["--profile", "black", "-a", "from __future__ import annotations"]
+      - id: ruff
+        files: "src/.*\\.pyi?$"
+        args: [--fix, --exit-non-zero-on-fix]
   - repo: https://github.com/psf/black
-    rev: 22.6.0
+    rev: 23.3.0
     hooks:
       - id: black
         language_version: python
-  - repo: https://github.com/asottile/setup-cfg-fmt
-    rev: v1.20.2
-    hooks:
-      - id: setup-cfg-fmt
-  - repo: https://github.com/asottile/pyupgrade
-    rev: v2.37.2
-    hooks:
-      - id: pyupgrade
-        args: ["--py37-plus"]
   - repo: https://github.com/pre-commit/mirrors-mypy
-    rev: v0.971
+    rev: v1.2.0
     hooks:
       - id: mypy
         additional_dependencies:

.readthedocs.yaml

@@ -1,3 +1,6 @@
+# SPDX-FileCopyrightText: 2022 James R. Barlow
+# SPDX-License-Identifier: MPL-2.0
+
 # Read the Docs configuration file
 # See https://docs.readthedocs.io/en/stable/config-file/v2.html for details
 
@@ -8,13 +11,13 @@ version: 2
 sphinx:
   configuration: docs/conf.py
 
-# Optionally build your docs in additional formats such as PDF
-formats:
-  - pdf
-
 # Optionally set the version of Python and requirements required to build your docs
+build:
+  os: ubuntu-22.04
+  tools:
+    python: "3.10"
+
 python:
-  version: "3.7"
   install:
     - method: pip
       path: .

.reuse/dep5

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

README.md

@@ -1,3 +1,7 @@
+<!-- SPDX-FileCopyrightText: 2014 Julien Pfefferkorn -->
+<!-- SPDX-FileCopyrightText: 2015 James R. Barlow -->
+<!-- SPDX-License-Identifier: CC-BY-SA-4.0 -->
+
 <img src="docs/images/logo.svg" width="240" alt="OCRmyPDF">
 
 [![Build Status](https://github.com/ocrmypdf/OCRmyPDF/actions/workflows/build.yml/badge.svg)](https://github.com/ocrmypdf/OCRmyPDF/actions/workflows/build.yml) [![PyPI version][pypi]](https://pypi.org/project/ocrmypdf/) ![Homebrew version][homebrew] ![ReadTheDocs][docs] ![Python versions][pyversions]
@@ -35,8 +39,10 @@ ocrmypdf                      # it's a scriptable command line program
 - Distributes work across all available CPU cores
 - Uses [Tesseract OCR](https://github.com/tesseract-ocr/tesseract) engine to recognize more than [100 languages](https://github.com/tesseract-ocr/tessdata)
 - Keeps your private data private.
-- Scales properly to handle files with thousands of pages
-- Battle-tested on millions of PDFs
+- Scales properly to handle files with thousands of pages.
+- Battle-tested on millions of PDFs.
+
+<img src="misc/screencast/demo.svg" alt="Demo of OCRmyPDF in a terminal session">
 
 For details: please consult the [documentation](https://ocrmypdf.readthedocs.io/en/latest/).
 
@@ -64,10 +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 (nix)                   | ``nix-env -i  ocrmypdf``      |
+| macOS (MacPorts)              | ``port install ocrmypdf``     |
+| macOS (nix)                   | ``nix-env -i ocrmypdf``       |
 | LinuxBrew                     | ``brew install ocrmypdf``     |
-| FreeBSD                       | ``pkg install py37-ocrmypdf`` |
-| Conda                         | ``conda install ocrmypdf``    |
+| FreeBSD                       | ``pkg install py-ocrmypdf``   |
 | Ubuntu Snap                   | ``snap install ocrmypdf``     |
 
 For everyone else, [see our documentation](https://ocrmypdf.readthedocs.io/en/latest/installation.html) for installation steps.
@@ -92,10 +98,7 @@ brew install tesseract-lang
 
 You can then pass the `-l LANG` argument to OCRmyPDF to give a hint as to what languages it should search for. Multiple languages can be requested.
 
-OCRmyPDF supports Tesseract 4.0 and the beta versions of Tesseract 5.0. It will
-automatically use whichever version it finds first on the `PATH` environment
-variable. On Windows, if `PATH` does not provide a Tesseract binary, we use
-the highest version number that is installed according to the Windows Registry.
+OCRmyPDF supports Tesseract 4.1.1+. It will automatically use whichever version it finds first on the `PATH` environment variable. On Windows, if `PATH` does not provide a Tesseract binary, we use the highest version number that is installed according to the Windows Registry.
 
 ## Documentation and support
 
@@ -109,9 +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 (3.7+), OCRmyPDF requires external program installations of Ghostscript and Tesseract OCR. OCRmyPDF is pure Python, and runs on pretty much everything: Linux, macOS, Windows and FreeBSD.
+In addition to the required Python version, OCRmyPDF requires external program installations of Ghostscript and Tesseract OCR. OCRmyPDF is pure Python, and runs on pretty much everything: Linux, macOS, Windows and FreeBSD.
 
 ## Press & Media
 
@@ -122,6 +149,7 @@ In addition to the required Python version (3.7+), OCRmyPDF requires external pr
 - [heise Durchsuchbare PDF-Dokumente mit OCRmyPDF erstellen](https://www.heise.de/ratgeber/Durchsuchbare-PDF-Dokumente-mit-OCRmyPDF-erstellen-4607592.html)
 - [Excellent Utilities: OCRmyPDF](https://www.linuxlinks.com/excellent-utilities-ocrmypdf-add-ocr-text-layer-scanned-pdfs/)
 - [LinuxUser Texterkennung mit OCRmyPDF und Scanbd automatisieren](https://www.linux-community.de/ausgaben/linuxuser/2021/06/texterkennung-mit-ocrmypdf-und-scanbd-automatisieren/)
+- [Y Combinator discussion](https://news.ycombinator.com/item?id=32028752)
 
 ## Business enquiries
 

docs/advanced.rst

@@ -10,7 +10,7 @@ Control of unpaper
 
 OCRmyPDF uses ``unpaper`` to provide the implementation of the
 ``--clean`` and ``--clean-final`` arguments.
-`unpaper <https://github.com/Flameeyes/unpaper/blob/master/doc/basic-concepts.md>`__
+`unpaper <https://github.com/Flameeyes/unpaper/blob/main/doc/basic-concepts.md>`__
 provides a variety of image processing filters to improve images.
 
 By default, OCRmyPDF uses only ``unpaper`` arguments that were found to
@@ -47,8 +47,8 @@ and clean up the margins of both.
 
    Some ``unpaper`` features cause multiple input or output files to be
    consumed or produced. OCRmyPDF requires ``unpaper`` to consume one
-   file and produce one file. An deviation from that condition will
-   result in errors.
+   file and produce one file; errors will result if this assumption is not
+   met.
 
 .. note::
 
@@ -82,14 +82,17 @@ is stripped out. Then an image of each page is created with visible text
 masked out. The page image is sent for OCR, and any additional text is
 inserted as OCR. If a file contains a mix of text and bitmap images that
 contain text, OCRmyPDF will locate the additional text in images without
-disrupting the existing text.
+disrupting the existing text. Some PDF OCR solutions render text as
+technically printable or visible in some way, perhaps by drawing it and
+then painting over it. OCRmyPDF cannot distinguish this type of OCR
+text from real text, so it will not be "redone".
 
 If ``--force-ocr`` is issued, then all pages will be rasterized to
-images, discarding any hidden OCR text, and rasterizing any printable
-text. This is useful for redoing OCR, for fixing OCR text with a damaged
-character map (text is selectable but not searchable), and destroying
-redacted information. Any forms and vector graphics will be rasterized
-as well.
+images, discarding any hidden OCR text, rasterizing any printable
+text, and flattening form fields or interactive objects into their visual
+representation. This is useful for redoing OCR, for fixing OCR text
+with a damaged character map (text is selectable but not searchable),
+and destroying redacted information.
 
 Time and image size limits
 --------------------------
@@ -104,13 +107,49 @@ was requested, the preprocessed image layer will be inserted.
 If you want to adjust the amount of time spent on OCR, change
 ``--tesseract-timeout``. You can also automatically skip images that
 exceed a certain number of megapixels with ``--skip-big``. (A 300 DPI,
-8.5×11" page is 8.4 megapixels.)
+8.5×11" page image is 8.4 megapixels.)
 
 .. code-block:: bash
 
     # Allow 300 seconds for OCR; skip any page larger than 50 megapixels
     ocrmypdf --tesseract-timeout 300 --skip-big 50 bigfile.pdf output.pdf
 
+OCR for huge images
+-------------------
+
+Tesseract has internal limits on the size
+of images it will process. By default,
+``--tesseract-downsample-large-images`` is enabled, and OCRmyPDF will
+downsample images to fit Tesseract limits. (The limits are usually encountered
+only for scanned images of oversized media, such as large maps or blueprints exceeding
+110 cm or 43 inches in either dimension, and at high DPI.) This feature can disabled
+using ``--no-tesseract-downsample-large-images``.
+
+``--tesseract-downsample-above Npixels`` adjusts the threshold at which images
+will be downsampled. By default, only images that exceed any of Tesseract's
+internal limits are downsampled (32767 pixels on either dimension).
+
+You will also need to set ``--tesseract-timeout`` high enough to allow
+for processing.
+
+Only the image sent for OCR is downsampled. The original image is
+preserved.
+
+.. code-block:: bash
+
+    # Allow 600 seconds for OCR on huge images
+    ocrmypdf --tesseract-timeout 600 \
+        --tesseract-downsample-large-images \
+        bigfile.pdf output.pdf
+
+    # Downsample images above 5000 pixels on the longest dimension to
+    # 5000 pixels
+    ocrmypdf --tesseract-timeout 120 \
+        --tesseract-downsample-large-images \
+        --tesseract-downsample-above 5000 \
+        bigfile.pdf output_downsampled_ocr.pdf
+
+
 Overriding default tesseract
 ----------------------------
 
@@ -154,13 +193,14 @@ In addition to tesseract, OCRmyPDF uses the following external binaries:
 -  ``jbig2``
 
 In each case OCRmyPDF will search the ``PATH`` environment variable to
-locate the binaries.
+locate the binaries. By modifying the ``PATH`` environment variable, you
+can override the binaries that OCRmyPDF uses.
 
-Changing tesseract configuration variables
+Changing Tesseract configuration variables
 ------------------------------------------
 
-You can override tesseract's default `control
-parameters <https://github.com/tesseract-ocr/tesseract/wiki/ControlParams>`__
+You can override Tesseract's default `control
+parameters <https://tesseract-ocr.github.io/tessdoc/tess3/ControlParams.html>`__
 with a configuration file.
 
 As an example, this configuration will disable Tesseract's dictionary
@@ -188,6 +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
 =========================
 
@@ -200,46 +293,77 @@ rendering
 OCRmyPDF has these PDF renderers: ``sandwich`` and ``hocr``. The
 renderer may be selected using ``--pdf-renderer``. The default is
 ``auto`` which lets OCRmyPDF select the renderer to use. Currently,
-``auto`` always selects ``sandwich``.
+``auto`` always selects ``hocr``.
+
+The ``hocr`` renderer
+---------------------
+
+.. versionchanged:: 16.0.0
+
+In both renderers, a text-only layer is rendered and sandwiched (overlaid)
+on to either the original PDF page, or newly rasterized version of the
+original PDF page (when ``--force-ocr`` is used). In this way, loss
+of PDF information is generally avoided. (You may need to disable PDF/A
+conversion and optimization to eliminate all lossy transformations.)
+
+The current approach used by the new hOCR renderer is a re-implementation
+of Tesseract's PDF renderer, using the same Glyphless font and general
+ideas, but fixing many technical issues that impeded it. The new hocr
+provides better text placement accuracy, avoids issues with word
+segmentation, and provides better positioning of skewed text.
+
+Using the experimental API, it is also possible to edit the OCR output
+from Tesseract, using any tool that is capable of editing hOCR files.
+
+Older versions of this renderer did not support non-Latin languages, but
+it is now universal.
 
 The ``sandwich`` renderer
 -------------------------
 
-The ``sandwich`` renderer uses Tesseract's new text-only PDF feature,
-which produces a PDF page that lays out the OCR in invisible text. This
-page is then "sandwiched" onto the original PDF page, allowing lossless
-application of OCR even to PDF pages that contain other vector objects.
+The ``sandwich`` renderer uses Tesseract's text-only PDF feature,
+which produces a PDF page that lays out the OCR in invisible text.
 
-Currently this is the best renderer for most uses, however it is
-implemented in Tesseract so OCRmyPDF cannot influence it. Currently some
-problematic PDF viewers like Mozilla PDF.js and macOS Preview have
-problems with segmenting its text output, and
-mightrunseveralwordstogether.
+Currently some problematic PDF viewers like Mozilla PDF.js and macOS
+Preview have problems with segmenting its text output, and
+mightrunseveralwordstogether. It also does not implement right to left
+fonts (Arabic, Hebrew, Persian). The output of this renderer cannot
+be edited. The sandwich renderer is retained for testing.
 
 When image preprocessing features like ``--deskew`` are used, the
 original PDF will be rendered as a full page and the OCR layer will be
 placed on top.
 
-The ``hocr`` renderer
----------------------
+Rendering and rasterizing options
+=================================
 
-The ``hocr`` renderer works with older versions of Tesseract. The image
-layer is copied from the original PDF page if possible, avoiding
-potentially lossy transcoding or loss of other PDF information. If
-preprocessing is specified, then the image layer is a new PDF. (You may
-need to disable PDF/A conversion nad optimization to eliminate all
-lossy transformations.)
+.. versionadded:: 14.3.0
 
-Unlike ``sandwich`` this renderer is implemented within OCRmyPDF; anyone
-looking to customize how OCR is presented should look here. A major
-disadvantage of this renderer is it not capable of correctly handling
-text outside the Latin alphabet (specifically, it supports the ISO 8859-1
-character). Pull requests to improve the situation are welcome.
+The ``--continue-on-soft-render-error`` option allows OCRmyPDF to
+proceed if a page cannot be rasterized/rendered. This is useful if you are
+trying to get the best possible OCR from a PDF that is not well-formed,
+and you are willing to accept some pages that may not visually match the
+input, and that may not OCR well.
 
-Currently, this renderer has the best compatibility with Mozilla's
-PDF.js viewer.
+Color conversion strategy
+=========================
 
-This works in all versions of Tesseract.
+.. versionadded:: 15.0.0
+
+OCRmyPDF uses Ghostscript to convert PDF to PDF/A. In some cases, this
+conversion requires color conversion. The default strategy is to convert
+using the ``LeaveColorUnchanged`` strategy, which preserves the original
+color space wherever possible (some rare color spaces might still be
+converted).
+
+Usually document scanners produce PDFs in the sRGB color space, and do
+not need to be converted, so the default strategy is appropriate.
+
+Suppose that you have a document that was prepared for professional
+printing in a Separation or CMYK color space, and text was converted to
+curves. In this case, you may want to use a different color conversion
+strategy. The ``--color-conversion-strategy`` option allows you to select a
+different strategy, such as ``RGB``.
 
 Return code policy
 ==================
@@ -299,22 +423,41 @@ stable user interface. They may be imported from
         - The program was interrupted by pressing Ctrl+C.
 
 
+.. _tmpdir:
+
+Changing temporary storage location
+===================================
+
+OCRmyPDF generates many temporary files during processing.
+
+To change where temporary files are stored, change the ``TMPDIR``
+environment variable for ocrmypdf's environment. (Python's
+``tempfile.gettempdir()`` returns the root directory in which temporary
+files will be stored.) For example, one could redirect ``TMPDIR`` to a
+large RAM disk to avoid wear on HDD/SSD and potentially improve
+performance.
+
+On Windows, the ``TEMP`` environment variable is used instead.
+
 Debugging the intermediate files
 ================================
 
 OCRmyPDF normally saves its intermediate results to a temporary folder
 and deletes this folder when it exits, whether it succeeded or failed.
 
-If the ``-k`` argument is issued on the command line, OCRmyPDF will keep
-the temporary folder and print the location, whether it succeeded or
-failed (provided the Python interpreter did not crash). An example
-message is:
+If the ``--keep-temporary-files`` (``-k``) argument is issued on the
+command line, OCRmyPDF will keep the temporary folder and print the location,
+whether it succeeded or failed. An example message is:
 
 .. code-block:: none
 
     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
@@ -326,9 +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

@@ -39,9 +39,7 @@ Parent process requirements
 The :func:`ocrmypdf.ocr` function runs OCRmyPDF similar to command line
 execution. To do this, it will:
 
-- create a monitoring thread
-- create worker processes (on Linux, forking itself; on Windows and macOS, by
-  spawning)
+- create worker processes or threads
 - manage the signal flags of its worker processes
 - execute other subprocesses (forking and executing other programs)
 
@@ -54,7 +52,19 @@ processes.
 
 Creating a child process to call :func:`ocrmypdf.ocr()` is suggested. That
 way your application will survive and remain interactive even if
-OCRmyPDF fails for any reason.
+OCRmyPDF fails for any reason. For example:
+
+.. code-block:: python
+
+    from multiprocessing import Process
+
+    def ocrmypdf_process():
+        ocrmypdf.ocr('input.pdf', 'output.pdf')
+
+    def call_ocrmypdf_from_my_app():
+        p = Process(target=ocrmypdf_process)
+        p.start()
+        p.join()
 
 Programs that call :func:`ocrmypdf.ocr()` should also install a SIGBUS signal
 handler (except on Windows), to raise an exception if access to a memory
@@ -72,14 +82,6 @@ OCRmyPDF, use processes.
     not take at least one of these steps, process semantics will prevent
     OCRmyPDF from working correctly.
 
-.. warning::
-
-    On macOS with Python 3.7, you must call
-    :func:`multiprocessing.set_start_method("spawn")`. Without this, multiprocessing
-    will be unstable. From the command line, OCRmyPDF does this automatically,
-    but as an API user you must do this. See Python bpo-33725 for details.
-    Python 3.8+ also resolve this automatically.
-
 Logging
 -------
 
@@ -97,12 +99,23 @@ your use case.
 Progress monitoring
 -------------------
 
-OCRmyPDF uses the ``tqdm`` package to implement its progress bars.
+OCRmyPDF uses the ``rich`` package to implement its progress bars.
 :func:`ocrmypdf.configure_logging` will set up logging output to
 ``sys.stderr`` in a way that is compatible with the display of the
 progress bar. Use ``ocrmypdf.ocr(...progress_bar=False)`` to disable
 the progress bar.
 
+Standard output
+---------------
+
+OCRmyPDF is strict about not writing to standard output so that
+users can safely use it in a pipeline and produce a valid output
+file. A caller application will have to ensure it does not write to
+standard output either, if it wants to be compatible with this
+behavior and support piping to a file. 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
 ----------
 
@@ -112,18 +125,4 @@ exceptions, some exceptions related to multiprocessing, and
 handler. OCRmyPDF will clean up its temporary files and worker processes
 automatically when an exception occurs.
 
-Programs that call OCRmyPDF should consider trapping KeyboardInterrupt
-so that they allow OCR to terminate with the whole program terminating.
-
 When OCRmyPDF succeeds conditionally, it returns an integer exit code.
-
-Reference
----------
-
-.. autofunction:: ocrmypdf.ocr
-
-.. autoclass:: ocrmypdf.Verbosity
-    :members:
-    :undoc-members:
-
-.. autofunction:: ocrmypdf.configure_logging

docs/apiref.rst

@@ -3,19 +3,16 @@
 .. SPDX-License-Identifier: CC-BY-SA-4.0
 
 =============
-API Reference
+API reference
 =============
 
 This page summarizes the rest of the public API. Generally speaking this
-should mainly of interest to plugin developers.
+should be mainly of interest to plugin developers.
 
-ocrmypdf
-========
+ocrmypdf.api
+============
 
-.. autoclass:: ocrmypdf.PageContext
-    :members:
-
-.. autoclass:: ocrmypdf.PdfContext
+.. automodule:: ocrmypdf.api
     :members:
 
 ocrmypdf.exceptions

docs/batch.rst

@@ -21,8 +21,8 @@ processors. To maximize parallelism without overloading your system with
 processes, consider using ``parallel -j 2`` to limit parallel to running
 two jobs at once.
 
-This command will run all ocrmypdf all files named ``*.pdf`` in the
-current directory and write them to the previous created ``output/``
+This command will run ``ocrmypdf`` on all files named ``*.pdf`` in the
+current directory and write them to the previously created ``output/``
 folder. It will not search subdirectories.
 
 The ``--tag`` argument tells parallel to print the filename as a prefix
@@ -44,17 +44,7 @@ place, and printing each filename in between runs:
 
 .. code-block:: bash
 
-   find . -printf '%p\n' -name '*.pdf' -exec ocrmypdf '{}' '{}' \;
-
-Alternatively, with a Docker container and streaming the file through
-standard input and output:
-
-.. code-block:: bash
-
-   find . -name '*.pdf' -print0 | xargs -0 | while read pdf; do
-       pdfout=$(mktemp)
-       docker run --rm -i jbarlow83/ocrmypdf - - <$pdf >$pdfout && cp $pdfout $pdf
-   done
+   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
@@ -70,6 +60,15 @@ In a Windows batch file, use
 
    for /r %%f in (*.pdf) do ocrmypdf %%f %%f
 
+With a Docker container, you will need to stream through standard input and output:
+
+.. code-block:: bash
+
+   find . -name '*.pdf' -print0 | xargs -0 | while read pdf; do
+       pdfout=$(mktemp)
+       docker run --rm -i jbarlow83/ocrmypdf - - <$pdf >$pdfout && cp $pdfout $pdf
+   done
+
 Sample script
 -------------
 
@@ -88,9 +87,9 @@ package <https://www.synology.com/en-global/dsm/packages/Docker>`__ is
 installed. Attached is a script to address particular quirks of using
 OCRmyPDF on one of these devices.
 
-This is only possible for x86-based Synology products. Some Synology
-products use ARM or Power processors and do not support Docker. Further
-adjustments might be needed to deal with the Synology's relatively
+At the time this script was written, it only worked for x86-based Synology
+products. It is not known if it will work on ARM-based Synology products.
+Further adjustments might be needed to deal with the Synology's relatively
 limited CPU and RAM.
 
 .. literalinclude:: ../misc/synology.py
@@ -133,10 +132,10 @@ Users may need to customize the script to meet their requirements.
     "OCR_OUTPUT_DIRECTORY", "Set output directory (should not be under input)"
     "OCR_ARCHIVE_DIRECTORY", "Set archive directory for processed originals (should not be under input, requires ``OCR_ON_SUCCESS_ARCHIVE`` to be set)"
     "OCR_ON_SUCCESS_DELETE", "This will delete the input file if the exit code is 0 (OK)"
-    "OCR_ON_SUCCESS_ARCHIVE", "This will move the processed orignal file to ``OCR_ARCHIVE_DIRECTORY`` if the exit code is 0 (OK). Note that ``OCR_ON_SUCCESS_DELETE`` takes precedence over this option, i.e. if both options are set, the input file will be deleted."
+    "OCR_ON_SUCCESS_ARCHIVE", "This will move the processed original file to ``OCR_ARCHIVE_DIRECTORY`` if the exit code is 0 (OK). Note that ``OCR_ON_SUCCESS_DELETE`` takes precedence over this option, i.e. if both options are set, the input file will be deleted."
     "OCR_OUTPUT_DIRECTORY_YEAR_MONTH", "This will place files in the output in ``{output}/{year}/{month}/{filename}``"
     "OCR_DESKEW", "Apply deskew to crooked input PDFs"
-    "OCR_JSON_SETTINGS", "A JSON string specifying any other arguments for ``ocrmypdf.ocr``, e.g. ``'OCR_JSON_SETTINGS={""rotate_pages"": true}'``."
+    "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"
 
@@ -151,32 +150,32 @@ The watcher service is included in the OCRmyPDF Docker image. To run it:
 .. code-block:: bash
 
     docker run \
-        -v <path to files to convert>:/input \
-        -v <path to store results>:/output \
-        -v <path to store processed originals>:/archive \
-        -e OCR_OUTPUT_DIRECTORY_YEAR_MONTH=1 \
-        -e OCR_ON_SUCCESS_ARCHIVE=1 \
-        -e OCR_DESKEW=1 \
-        -e PYTHONUNBUFFERED=1 \
-        -it --entrypoint python3 \
+        --volume <path to files to convert>:/input \
+        --volume <path to store results>:/output \
+        --volume <path to store processed originals>:/processed \
+        --env OCR_OUTPUT_DIRECTORY_YEAR_MONTH=1 \
+        --env OCR_ON_SUCCESS_ARCHIVE=1 \
+        --env OCR_DESKEW=1 \
+        --env PYTHONUNBUFFERED=1 \
+        --interactive --tty --entrypoint python3 \
         jbarlow83/ocrmypdf \
         watcher.py
 
 This service will watch for a file that matches ``/input/\*.pdf``,
 convert it to a OCRed PDF in ``/output/``, and move the processed
-original to ``/archive``. The parameters to this image are:
+original to ``/processed``. The parameters to this image are:
 
 .. csv-table:: watcher.py parameters for Docker
     :header: "Parameter", "Description"
     :widths: 50, 50
 
-    "``-v <path to files to convert>:/input``", "Files placed in this location will be OCRed"
-    "``-v <path to store results>:/output``", "This is where OCRed files will be stored"
-    "``-v <path to store processed originals>:/archive``", "Archive processed originals here"
-    "``-e OCR_OUTPUT_DIRECTORY_YEAR_MONTH=1``", "Define environment variable ``OCR_OUTPUT_DIRECTORY_YEAR_MONTH=1`` to place files in the output in ``{output}/{year}/{month}/{filename}``"
-    "``-e OCR_ON_SUCCESS_ARCHIVE=1``", "Define environment variable ``OCR_ON_SUCCESS_ARCHIVE`` to move processed originals"
-    "``-e OCR_DESKEW=1``", "Define environment variable ``OCR_DESKEW``  to apply deskew to crooked input PDFs"
-    "``-e PYTHONBUFFERED=1``", "This will force ``STDOUT`` to be unbuffered and allow you to see messages in docker logs"
+    "``--volume <path to files to convert>:/input``", "Files placed in this location will be OCRed"
+    "``--volume <path to store results>:/output``", "This is where OCRed files will be stored"
+    "``--volume <path to store processed originals>:/processed``", "Archive processed originals here"
+    "``--env OCR_OUTPUT_DIRECTORY_YEAR_MONTH=1``", "Define environment variable ``OCR_OUTPUT_DIRECTORY_YEAR_MONTH=1`` to place files in the output in ``{output}/{year}/{month}/{filename}``"
+    "``--env OCR_ON_SUCCESS_ARCHIVE=1``", "Define environment variable ``OCR_ON_SUCCESS_ARCHIVE`` to move processed originals"
+    "``--env OCR_DESKEW=1``", "Define environment variable ``OCR_DESKEW``  to apply deskew to crooked input PDFs"
+    "``--env PYTHONBUFFERED=1``", "This will force ``STDOUT`` to be unbuffered and allow you to see messages in docker logs"
 
 This service relies on polling to check for changes to the filesystem. It
 may not be suitable for some environments, such as filesystems shared on a

docs/cloud.rst

@@ -0,0 +1,92 @@
+.. SPDX-FileCopyrightText: 2023 James R. Barlow
+..
+.. SPDX-License-Identifier: CC-BY-SA-4.0
+
+
+.. _ocr-service:
+
+==================
+Online deployments
+==================
+
+OCRmyPDF is designed to be used as a command line tool, but it can be
+used in a web service. This document describes some considerations for
+doing so.
+
+A basic web service implementation is provided in the source code
+repository, as ``misc/webservice.py``. It is only demonstration quality
+and is not intended for production use.
+
+OCRmyPDF is not designed for use as a public web service where a
+malicious user could upload a chosen PDF. In particular, it is not
+necessarily secure against PDF malware or PDFs that cause denial of
+service. For further discussino of security, see :ref:`security`.
+
+OCRmyPDF relies on Ghostscript, and therefore, if deployed
+online one should be prepared to comply with Ghostscript's Affero GPL
+license, and any other licenses.
+
+Setting aside these concerns, a side effect of OCRmyPDF is that it may
+incidentally sanitize PDFs containing certain types of malware. It
+repairs the PDF with pikepdf/libqpdf, which could correct malformed PDF
+structures that are part of an attack. When PDF/A output is selected
+(the default), the input PDF is partially reconstructed by Ghostscript.
+When ``--force-ocr`` is used, all pages are rasterized and reconverted
+to PDF, which could remove malware in embedded images.
+
+Limiting CPU usage
+------------------
+
+OCRmyPDF will attempt to use all available CPUs and storage, so
+executing ``nice ocrmypdf`` or limiting the number of jobs with the
+``--jobs`` argument may ensure the server remains responsive. Another option
+would be to run OCRmyPDF jobs inside a Docker container, a virtual machine,
+or a cloud instance, which can impose its own limits on CPU usage and be
+terminated "from orbit" if it fails to complete.
+
+Temporary storage requirements
+------------------------------
+
+OCRmyPDF will use a large amount of temporary storage for its work,
+proportional to the total number of pixels needed to rasterize the PDF.
+The raster image of a 8.5×11" color page at 300 DPI takes 25 MB
+uncompressed; OCRmyPDF saves its intermediates as PNG, but that still
+means it requires about 9 MB per intermediate based on average
+compression ratios. Multiple intermediates per page are also required,
+depending on the command line given. A rule of thumb would be to allow
+100 MB of temporary storage per page in a file – meaning that a small
+cloud servers or small VM partitions should be provisioned with plenty
+of extra space, if say, a 500 page file might be sent.
+
+To change the temporary directory, see :ref:`tmpdir`.
+
+On Amazon Web Services or other cloud vendors, consider setting your
+temporary directory to `empheral
+storage <https://docs.aws.amazon.com/AWSEC2/latest/UserGuide/InstanceStorage.html>`__.
+
+Timeouts
+--------
+
+To prevent excessively long OCR jobs consider setting
+``--tesseract-timeout`` and/or ``--skip-big`` arguments. ``--skip-big``
+is particularly helpful if your PDFs include documents such as reports
+on standard page sizes with large images attached - often large images
+are not worth OCR'ing anyway.
+
+Document management systems
+---------------------------
+
+If you are looking for a full document management system, consider
+`paperless-ngx <https://github.com/paperless-ngx/paperless-ngx>`__,
+which is a web application that uses OCRmyPDF to automatically OCR and
+archive documents.
+
+Commercial OCR alternatives
+---------------------------
+
+The author also provides professional services that include OCR and
+building databases around PDFs, and is happy to provide consultation.
+
+Abbyy Cloud OCR is viable commercial alternative with a web services
+API. Amazon Textract, Google Cloud Vision, and Microsoft Azure
+Computer Vision provide advanced OCR but have less PDF rendering capability.

docs/conf.py

@@ -2,6 +2,8 @@
 # SPDX-FileCopyrightText: 2022 James R. Barlow
 # SPDX-License-Identifier: CC-BY-SA-4.0
 
+# ruff: noqa: E402
+
 # ocrmypdf documentation build configuration file, created by
 # sphinx-quickstart on Sun Sep  4 14:29:43 2016.
 #
@@ -22,14 +24,14 @@
 # import sys
 # sys.path.insert(0, os.path.abspath('.'))
 
-"""isort:skip_file"""
-
 # -- General configuration ------------------------------------------------
 
 # If your documentation needs a minimal Sphinx version, state it here.
 #
 # needs_sphinx = '1.0'
 
+import datetime
+
 # Add any Sphinx extension module names here, as strings. They can be
 # extensions coming with Sphinx (named 'sphinx.ext.*') or your custom
 # ones.
@@ -38,11 +40,12 @@ extensions = [
     'sphinx.ext.intersphinx',
     'sphinx.ext.autosummary',
     'sphinx.ext.napoleon',
+    'sphinx.ext.imgconverter',  # PDF docs needs this for SVG to PNG conversion
     'sphinx_issues',
 ]
 
 # 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"
 
@@ -50,10 +53,7 @@ issues_github_path = "ocrmypdf/OCRmyPDF"
 templates_path = ['_templates']
 
 # The suffix(es) of source filenames.
-# You can specify multiple suffix as a list of string:
-#
-# source_suffix = ['.rst', '.md']
-source_suffix = '.rst'
+source_suffix = {'.rst': 'restructuredtext', '.md': 'markdown'}
 
 # The encoding of source files.
 #
@@ -64,8 +64,11 @@ master_doc = 'index'
 
 # General information about the project.
 project = 'ocrmypdf'
+
+year = str(datetime.date.today().year)
 copyright = (
-    '2022, James R. Barlow. Licensed under Creative Commons Attribution-ShareAlike 4.0.'
+    f'{year}, James R. Barlow. ',
+    'Licensed under Creative Commons Attribution-ShareAlike 4.0.',
 )
 author = 'James R. Barlow'
 
@@ -76,6 +79,7 @@ author = 'James R. Barlow'
 # The short X.Y version.
 
 import os
+from importlib.metadata import version as package_version
 
 on_rtd = os.environ.get('READTHEDOCS') == 'True'
 
@@ -91,15 +95,12 @@ if on_rtd:
 
     MOCK_MODULES = [
         'pikepdf',
+        'pikepdf.canvas',
         'pikepdf.models',
         'pikepdf.models.metadata',
     ]
     sys.modules.update((mod_name, Mock()) for mod_name in MOCK_MODULES)
 
-try:
-    from importlib_metadata import version as package_version
-except ModuleNotFoundError:
-    from importlib.metadata import version as package_version
 
 # The full version, including alpha/beta/rc tags.
 release = package_version('ocrmypdf')
@@ -111,7 +112,7 @@ version = '.'.join(release.split('.')[:2])
 #
 # This is also used if you do content translation via gettext catalogs.
 # Usually you set "language" from the command line for these cases.
-language = None
+language = 'en'
 
 # There are two options for replacing |today|: either, you set today to some
 # non-false value, then it is used:
@@ -161,19 +162,18 @@ todo_include_todos = False
 
 # -- Options for HTML output ----------------------------------------------
 
-import sphinx_rtd_theme
+import sphinx_rtd_theme  # noqa: F401
 
 # The theme to use for HTML and HTML Help pages.  See the documentation for
 # a list of builtin themes.
 #
 html_theme = 'sphinx_rtd_theme'
-html_theme_path = [sphinx_rtd_theme.get_html_theme_path()]
 
 # Theme options are theme-specific and customize the look and feel of a theme
 # further.  For a list of options available for each theme, see the
 # documentation.
 #
-html_theme_options = {'display_version': False}
+html_theme_options = {}
 
 # Add any paths that contain custom themes here, relative to this directory.
 # html_theme_path = []
@@ -201,7 +201,7 @@ html_theme_options = {'display_version': False}
 # Add any paths that contain custom static files (such as style sheets) here,
 # relative to this directory. They are copied after the builtin static files,
 # so a file named "default.css" will overwrite the builtin "default.css".
-html_static_path = ['_static']
+# html_static_path = ['_static']
 
 # Add any extra paths that contain custom files (such as robots.txt or
 # .htaccess) here, relative to this directory. These files are copied

docs/contributing.rst

@@ -18,8 +18,8 @@ work you're contemplating is already half-done in a development branch.
 Code style
 ==========
 
-We use PEP8, ``black`` for code formatting and ``isort`` for import sorting. The
-settings for these programs are in ``pyproject.toml`` and ``setup.cfg``. Pull
+We use PEP8, ``black`` for code formatting and ``ruff`` for everything else. The
+settings for these programs are in ``pyproject.toml``. Pull
 requests should follow the style guide. One difference we use from "black" style
 is that strings shown to the user are always in double quotes (``"``) and strings
 for internal uses are in single quotes (``'``).
@@ -29,12 +29,17 @@ Tests
 
 New features should come with tests that confirm their correctness.
 
-New Python dependencies
-=======================
+New dependencies
+================
 
-If you are proposing a change that will require a new Python dependency, we
+If you are proposing a change that will require a new dependency, we
 prefer dependencies that are already packaged by Debian or Red Hat. This makes
-life much easier for our downstream package maintainers.
+life much easier for our downstream package maintainers. A package that is only
+available on PyPI or GitHub, and not more widely packaged, may not be accepted.
+
+We are unlikely to accept a dependency on CUDA or other GPU-based libraries,
+because these are still difficult to package and install on many systems.
+We recommend implementing these changes as plugins.
 
 Python dependencies must also be license-compatible. GPLv3 or AGPLv3 are likely
 incompatible with the project's license, but LGPLv3 is compatible.
@@ -43,7 +48,19 @@ New non-Python dependencies
 ===========================
 
 OCRmyPDF uses several external programs (Tesseract, Ghostscript and others) for
-its functionality. In general we prefer to avoid adding new external programs.
+its functionality. In general we prefer to avoid adding new external programs,
+and if we are to add external programs, we prefer those that are already
+packaged by Debian or Red Hat.
+
+Plugins
+=======
+
+Some new features may be a good fit for a plugin. Plugins are a way to add
+features to OCRmyPDF without adding them to the core program. Plugins are
+installed separately from OCRmyPDF. They are written in Python and can be
+installed from PyPI. See the `plugin documentation <https://ocrmypdf.readthedocs.io/en/latest/plugins.html>`_.
+
+We are happy to link users to your plugin from the documentation.
 
 Style guide: Is it OCRmyPDF or ocrmypdf?
 ========================================
@@ -53,8 +70,8 @@ The program/project is OCRmyPDF and the name of the executable or library is ocr
 Copyright and license
 =====================
 
-For contributions over 10 lines of code, please include your name to list of
+For contributions over 10 lines of code, please add your name to list of
 copyright holders for that file. The core program is licensed under MPL-2.0,
 test files and documentation under CC-BY-SA 4.0, and miscellaneous files under
-MIT. Please contribute code only that you wrote and you have the permission to
-contribute or license to us.
+MIT, with a few minor exceptions. Please contribute only content that you own
+or have the right to contribute under these licenses.

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
@@ -231,13 +231,34 @@ Don't actually OCR my PDF
 =========================
 
 If you set ``--tesseract-timeout 0`` OCRmyPDF will apply its image
-processing without performing OCR, if all you want to is to apply image
-processing or PDF/A conversion.
+processing without performing OCR (by causing OCR to time out). This works
+if all you want to is to apply image processing or PDF/A conversion.
 
 .. code-block:: bash
 
     ocrmypdf --tesseract-timeout=0 --remove-background input.pdf output.pdf
 
+.. versionchanged:: v14.1.0
+
+    Prior to this version, ``--tesseract-timeout 0`` would prevent other
+    uses of Tesseract, such as deskewing, from working. This is no longer
+    the case. Use ``--tesseract-non-ocr-timeout`` to control the timeout
+    for non-OCR operations, if needed.
+
+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
 --------------------------------------
 
@@ -261,9 +282,10 @@ Hyphens denote a range of pages and commas separate page numbers. If you prefer
 to use spaces, quote all of the page numbers: ``--pages '2, 3, 5, 7'``.
 
 OCRmyPDF will warn if your list of page numbers contains duplicates or
-overlap pages. OCRmyPDF does not currently account for document page numbers,
+overlapping pages. OCRmyPDF does not currently account for document page numbers,
 such as an introduction section of a book that uses Roman numerals. It simply
-counts the number of virtual pieces of paper since the start.
+counts the number of virtual pieces of paper since the start. If your list of
+pages is out of numerical order, OCRmyPDF will sort it for you.
 
 Regardless of the argument to ``--pages``, OCRmyPDF will optimize all pages/images
 in the file and convert it to PDF/A, unless you disable those options. Both of these
@@ -283,7 +305,7 @@ argument. (Normally, OCRmyPDF will exit with an error if asked to modify
 a file with OCR.)
 
 This may be helpful for users who want to take advantage of accuracy
-improvements in Tesseract 4.0 for files they previously OCRed with an
+improvements in Tesseract for files they previously OCRed with an
 earlier version of Tesseract and OCRmyPDF.
 
 .. code-block:: bash
@@ -360,7 +382,7 @@ The types of optimization available may expand over time. By default,
 OCRmyPDF compresses data streams inside PDFs, and will change
 inefficient compression modes to more modern versions. A program like
 ``qpdf`` can be used to change encodings, e.g. to inspect the internals
-fo a PDF.
+for a PDF.
 
 .. code-block:: bash
 
@@ -372,3 +394,17 @@ Some users may consider enabling lossy JBIG2. See: :ref:`jbig2-lossy`.
 
     Image processing and PDF/A conversion can also introduce lossy transformations
     to your PDF images, even when ``--optimize 1`` is in use.
+
+
+Digitally signed PDFs
+=====================
+
+OCRmyPDF cannot preserve digital signatures in PDFs and also add OCR to them.
+By default, it will refuse to modify a signed PDF regardless of other settings. You can
+override this behavior with ``--invalidate-digital-signatures``; as the name suggests,
+any digital signatures will be invalidated.
+
+OCRmyPDF cannot open documents that are encrypted with a digital certificate.
+
+Versions of OCRmyPDF prior to 14.4.0 would invalidate existing digital signatures
+without warning.

docs/design_notes.rst

@@ -0,0 +1,32 @@
+.. SPDX-FileCopyrightText: 2023 James R. Barlow
+.. SPDX-License-Identifier: CC-BY-SA-4.0
+
+============
+Design notes
+============
+
+Why doesn't OCRmyPDF use PyTesseract?
+=====================================
+
+PyTesseract is a Python wrapper around the Tesseract OCR engine. When OCRmyPDF was
+first written, PyTesseract used ABI bindings to call the Tesseract library. This
+was not a good fit for OCRmyPDF because ABI bindings can be fragile.
+
+PyTesseract has since evolved calling the Tesseract executable, abandoning the ABI
+approach and using the CLI instead, just like OCRmyPDF does. If it were written from
+scratch today, OCRmyPDF might use PyTesseract.
+
+PyTesseract has more features don't particularly need PDF output, but less features
+than OCRmyPDF's API for creating PDFs.
+
+What is ``executor()``?
+=======================
+
+OCRmyPDF uses a custom concurrent executor which can support either threads or
+processes with the same interface. This is useful because OCRmyPDF can use
+either threads or processes to parallelize work, whichever is more appropriate
+for the task at hand.
+
+The interface is currently private and subject to change. In particular, if
+experiments with asyncio and anyio are successful, the interface will change.
+

docs/docker.rst

@@ -8,17 +8,16 @@
 OCRmyPDF Docker image
 =====================
 
-OCRmyPDF is also available in a Docker image that packages recent
+OCRmyPDF is also available in Docker images that packages recent
 versions of all dependencies.
 
 For users who already have Docker installed this may be an easy and
-convenient option. However, it is less performant than a system
-installation and may require Docker engine configuration.
+convenient option.
 
-OCRmyPDF needs a generous amount of RAM, CPU cores, temporary storage
-space, whether running in a Docker container or on its own. It may be
-necessary to ensure the container is provisioned with additional
-resources.
+On platforms other than Linux, Docker runs in a virtual machine, and so may
+be less performant. You may also want to adjust the Docker virtual machine's
+memory and CPU allocation. On Linux, the Docker image runs natively and
+performance is comparable to a system installation.
 
 .. _docker-install:
 
@@ -35,29 +34,44 @@ execute the image:
 
    docker run hello-world
 
-The recommended OCRmyPDF Docker image is currently named ``ocrmypdf``:
+.. list-table:: Docker images
+   :widths: 30 20 50
+   :header-rows: 1
+
+   * - Image
+     - Architecture
+     - Description
+   * - ``jbarlow83/ocrmypdf-alpine``
+     - x86_64 and arm64
+     - Recommended image, based on Alpine Linux.
+   * - ``jbarlow83/ocrmypdf-ubuntu``
+     - x86_64 and arm64
+     - Alternate image, based on Ubuntu. When the Alpine image is considered
+       stable and available for arm64, this image will be deprecated.
+   * - ``jbarlow83/ocrmypdf``
+     - x86_64 and arm64
+     - Currently an alias for ocrmypdf-ubuntu. When the Alpine image is
+       considered stable and available for arm64, this name point to the
+       Alpine image. If you don't about the difference between Alpine and
+       Ubuntu, use this image.
+
+To install:
 
 .. code-block:: bash
 
-   docker pull jbarlow83/ocrmypdf
+   docker pull jbarlow83/ocrmypdf-alpine
 
+The ``ocrmypdf`` image is also available, but is deprecated and will be removed
+in the future.
 
-OCRmyPDF will use all available CPU cores. By default, the VirtualBox
-machine instance on Windows and macOS has only a single CPU core
-enabled. Use the VirtualBox Manager to determine the name of your Docker
-engine host, and then follow these optional steps to enable multiple
-CPUs:
+OCRmyPDF will use all available CPU cores. See the Docker documentation for
+`adjusting memory and CPU on other platforms <https://docs.docker.com/config/containers/resource_constraints/>`__
+if you are using Docker on macOS or Windows, where you may need to manually assign
+more resources. On Linux, all resources will be available automatically.
 
-.. code-block:: bash
-
-   # Optional step for Mac OS X users
-   docker-machine stop "yourVM"
-   VBoxManage modifyvm "yourVM" --cpus 2  # or whatever number of core is desired
-   docker-machine start "yourVM"
-   eval $(docker-machine env "yourVM")
-
-See the Docker documentation for
-`adjusting memory and CPU on other platforms <https://docs.docker.com/config/containers/resource_constraints/>`__.
+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
 ==========================================
@@ -66,13 +80,14 @@ Using the Docker image on the command line
 container is ephemeral – it runs for one OCR job and terminates, just like a
 command line program. We are using Docker to deliver an application (as opposed
 to the more conventional case, where a Docker container runs as a server).
+For that reason we usually use the ``--rm`` argument to delete the container
+when it exits.
 
 To start a Docker container (instance of the image):
 
 .. code-block:: bash
 
-   docker tag jbarlow83/ocrmypdf ocrmypdf
-   docker run --rm -i ocrmypdf (... all other arguments here...) - -
+   docker run --rm -i jbarlow83/ocrmypdf-alpine (... all other arguments here...) - -
 
 For convenience, create a shell alias to hide the Docker command. It is
 easier to send the input file as stdin and read the output from
@@ -80,7 +95,7 @@ stdout – **this avoids the messy permission issues with Docker entirely**.
 
 .. code-block:: bash
 
-   alias docker_ocrmypdf='docker run --rm -i ocrmypdf'
+   alias docker_ocrmypdf='docker run --rm -i jbarlow83/ocrmypdf-alpine'
    docker_ocrmypdf --version  # runs docker version
    docker_ocrmypdf - - <input.pdf >output.pdf
 
@@ -88,7 +103,7 @@ Or in the wonderful `fish shell <https://fishshell.com/>`__:
 
 .. code-block:: fish
 
-   alias docker_ocrmypdf 'docker run --rm ocrmypdf'
+   alias docker_ocrmypdf 'docker run --rm jbarlow83/ocrmypdf-alpine'
    funcsave docker_ocrmypdf
 
 Alternately, you could mount the local current working directory as a
@@ -96,9 +111,27 @@ Docker volume:
 
 .. code-block:: bash
 
-   alias docker_ocrmypdf='docker run --rm  -i --user "$(id -u):$(id -g)" --workdir /data -v "$PWD:/data" ocrmypdf'
+   alias docker_ocrmypdf='docker run --rm  -i --user "$(id -u):$(id -g)" --workdir /data -v "$PWD:/data" jbarlow83/ocrmypdf-alpine'
    docker_ocrmypdf /data/input.pdf /data/output.pdf
 
+Podman
+======
+
+Especially if you use `Podman <https://podman.io/>`__ (or have SELinux enabled on your
+system), you may need to add ``--userns keep-id`` there, otherwise you may get access
+errors, because the user is otherwise not mapped to the same UID as on the host:
+
+.. code-block:: bash
+
+   alias podman_ocrmypdf='podman run --rm  -i --user "$(id -u):$(id -g)" --userns keep-id --workdir /data -v "$PWD:/data" ocrmypdf'
+   podman_ocrmypdf /data/input.pdf /data/output.pdf
+
+If you use SELinux you may additionally need to add the ``:Z`` `suffix to the volume
+<https://docs.podman.io/en/stable/markdown/podman-run.1.html#volume-v-source-volume-host-dir-container-dir-options>`__
+or disable SELinux for the container using ``--security-opt label=disable``, which is
+suggested for system files as they should not be re-labelled. Please refer to the „Note”
+section at the end of the linked podman documentation for details.
+
 .. _docker-lang-packs:
 
 Adding languages to the Docker image
@@ -116,7 +149,7 @@ Dockerfile based on the public one.
    # Example: add Italian
    RUN apt install tesseract-ocr-ita
 
-To install language packs (training data) such as the 
+To install language packs (training data) such as the
 `tessdata_best <https://github.com/tesseract-ocr/tessdata_best>`_ suite or
 custom data, you first need to determine the version of Tesseract data files, which
 may differ from the Tesseract program version. Use this command to determine the data
@@ -132,17 +165,35 @@ You can then add new data with either a Dockerfile:
 
 .. code-block:: dockerfile
 
-   FROM jbarlow83/ocrmypdf
+   FROM jbarlow83/ocrmypdf:{TAG}
 
    # Example: add a tessdata_best file
    COPY chi_tra_vert.traineddata /usr/share/tesseract-ocr/<data version>/tessdata/
 
+When creating your own image, you should always pin a specific version of the
+OCRmyPDF Docker image. This ensures that your image will not break when a new
+version of OCRmyPDF is released.
+
 Alternately, you can copy training data into a Docker container as follows:
 
 .. code-block:: bash
 
    docker cp mycustomtraining.traineddata name_of_container:/usr/share/tesseract-ocr/<tesseract version>/tessdata/
 
+Extending the Docker image
+==========================
+
+You can extend the Docker image with your own customizations, similar to the way
+it is extended to add language packs.
+
+Note that the Docker image is subject to change at any time. For example, the base
+image may be updated to a newer version of Ubuntu or Debian. Such changes will be
+noted in the release notes but might occur at minor versions releases, unless the
+way a "casual" user of the Docker image is affected.
+
+If you extend the Docker image, you should pin a specific version of the OCRmyPDF
+Docker image.
+
 Executing the test suite
 ========================
 
@@ -150,16 +201,16 @@ The OCRmyPDF test suite is installed with image. To run it:
 
 .. code-block:: bash
 
-   docker run --entrypoint python3  jbarlow83/ocrmypdf -m pytest
+   docker run --rm --entrypoint python  jbarlow83/ocrmypdf -m pytest
 
 Accessing the shell
 ===================
 
-To use the bash shell in the Docker image:
+To use the shell in the Docker image:
 
 .. code-block:: bash
 
-   docker run -it --entrypoint bash  jbarlow83/ocrmypdf
+   docker run -it --entrypoint sh  jbarlow83/ocrmypdf
 
 Using the OCRmyPDF web service wrapper
 ======================================
@@ -169,7 +220,10 @@ service. The webservice may be launched as follows:
 
 .. code-block:: bash
 
-   docker run --entrypoint python3 -p 5000:5000  jbarlow83/ocrmypdf webservice.py
+   docker run --entrypoint python -p 5000:5000  jbarlow83/ocrmypdf webservice.py
+
+We omit the ``--rm`` parameter so that the container will not be
+automatically deleted when it exits.
 
 This will configure the machine to listen on port 5000. On Linux machines
 this is port 5000 of localhost. On macOS or Windows machines running

docs/index.rst

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

docs/installation.rst

@@ -21,16 +21,16 @@ These platforms have one-liner installs:
 +-------------------------------+-----------------------------------------+
 | Windows Subsystem for Linux   | ``apt install ocrmypdf``                |
 +-------------------------------+-----------------------------------------+
-| Fedora                        | ``dnf install ocrmypdf``                |
+| Fedora                        | ``dnf install ocrmypdf tesseract-osd``  |
 +-------------------------------+-----------------------------------------+
-| macOS                         | ``brew install ocrmypdf``               |
+| 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``               |
 +-------------------------------+-----------------------------------------+
 
@@ -44,7 +44,7 @@ install, or install a more recent version than your platform provides, read on.
 Installing on Linux
 ===================
 
-Debian and Ubuntu 18.04 or newer
+Debian and Ubuntu 20.04 or newer
 --------------------------------
 
 .. |deb-11| image:: https://repology.org/badge/version-for-repo/debian_11/ocrmypdf.svg
@@ -56,9 +56,6 @@ Debian and Ubuntu 18.04 or newer
 .. |deb-unstable| image:: https://repology.org/badge/version-for-repo/debian_unstable/ocrmypdf.svg
     :alt: Debian unstable
 
-.. |ubu-1804| image:: https://repology.org/badge/version-for-repo/ubuntu_18_04/ocrmypdf.svg
-    :alt: Ubuntu 18.04 LTS
-
 .. |ubu-2004| image:: https://repology.org/badge/version-for-repo/ubuntu_20_04/ocrmypdf.svg
     :alt: Ubuntu 20.04 LTS
 
@@ -72,15 +69,14 @@ Debian and Ubuntu 18.04 or newer
 +-----------------------------------------------+
 | |deb-11| |deb-12| |deb-unstable|              |
 +-----------------------------------------------+
-| |ubu-1804| |ubu-2004| |ubu-2204|              |
+| |ubu-2004| |ubu-2204|                         |
 +-----------------------------------------------+
 
-Users of Debian 9 ("stretch") or later, or Ubuntu 18.04 or later, including users
-of Windows Subsystem for Linux, may simply
+Users of Debian or Ubuntu may simply
 
 .. code-block:: bash
 
-    apt-get install ocrmypdf
+    apt install ocrmypdf
 
 As indicated in the table above, Debian and Ubuntu releases may lag
 behind the latest version. If the version available for your platform is
@@ -103,11 +99,11 @@ For full details on version availability for your platform, check the
 Fedora
 ------
 
-.. |fedora-35| image:: https://repology.org/badge/version-for-repo/fedora_35/ocrmypdf.svg
-    :alt: Fedora 35
+.. |fedora-38| image:: https://repology.org/badge/version-for-repo/fedora_38/ocrmypdf.svg
+    :alt: Fedora 38
 
-.. |fedora-36| image:: https://repology.org/badge/version-for-repo/fedora_36/ocrmypdf.svg
-    :alt: Fedora 36
+.. |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
@@ -117,17 +113,17 @@ Fedora
 +-----------------------------------------------+
 | |latest|                                      |
 +-----------------------------------------------+
-| |fedora-35| |fedora-36| |fedora-rawhide|      |
+| |fedora-38| |fedora-39| |fedora-rawhide|      |
 +-----------------------------------------------+
 
-Users of Fedora 29 or later may simply
+Users of Fedora may simply
 
 .. code-block:: bash
 
-    dnf install ocrmypdf
+    dnf install ocrmypdf tesseract-osd
 
 For full details on version availability, check the `Fedora Package
-Tracker <https://apps.fedoraproject.org/packages/ocrmypdf>`__.
+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
@@ -139,10 +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
 -------------------------------------------------
 
@@ -159,84 +181,20 @@ user, follow these steps:
 
 If you get the message ``WARNING: The script ocrmypdf is installed in
 '/home/$USER/.local/bin' which is not on PATH.``, you may need to re-login
-or open a new shell, or manually add this to your user's PATH.
+or open a new shell, or manually adjust your PATH.
 
 To add JBIG2 encoding, see :ref:`jbig2`.
 
 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`.
-
-Ubuntu 18.04 LTS
-----------------
-
-Ubuntu 18.04 includes ocrmypdf 6.1.2 - you can install that with ``apt``, but
-it is quite old now. To install a more recent version, uninstall the old version
-of ocrmypdf, and install the following dependencies:
-
-.. code-block:: bash
-
-    sudo apt-get -y remove ocrmypdf
-    sudo apt-get -y update
-    sudo apt-get -y install \
-        ghostscript \
-        icc-profiles-free \
-        libxml2 \
-        pngquant \
-        python3-distutils \
-        python3-pkg-resources \
-        python3-reportlab \
-        qpdf \
-        tesseract-ocr \
-        zlib1g \
-        unpaper
-
-We will need a newer version of ``pip`` then was available for Ubuntu 18.04:
-
-.. code-block:: bash
-
-    wget https://bootstrap.pypa.io/get-pip.py && python3 get-pip.py
-
-Then install the most recent ocrmypdf for the local user and set the
-user's ``PATH`` to check for the user's Python packages.
-
-.. code-block:: bash
-
-    export PATH=$HOME/.local/bin:$PATH
-    python3 -m pip install --user ocrmypdf
-
-To add JBIG2 encoding, see :ref:`jbig2`.
+    brew install ocrmypdf
 
 Arch Linux (AUR)
 ----------------
@@ -259,12 +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.
 
@@ -302,7 +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
@@ -318,6 +276,21 @@ To install OCRmyPDF for Alpine Linux:
 
     apk add ocrmypdf
 
+Gentoo Linux
+------------
+
+.. image:: https://repology.org/badge/version-for-repo/gentoo_ovl_guru/ocrmypdf.svg
+    :alt: Gentoo Linux
+    :target: https://repology.org/metapackage/ocrmypdf
+
+To install OCRmyPDF on Gentoo Linux, use the following commands:
+
+.. code-block:: bash
+
+    eselect repository enable guru
+    emaint sync --repo guru
+    emerge --ask app-text/OCRmyPDF
+
 Other Linux packages
 --------------------
 
@@ -336,7 +309,7 @@ Homebrew
 
 .. image:: https://img.shields.io/homebrew/v/ocrmypdf.svg
     :alt: homebrew
-    :target: http://brewformulas.org/Ocrmypdf
+    :target: https://formulae.brew.sh/formula/ocrmypdf
 
 OCRmyPDF is now a standard `Homebrew <https://brew.sh>`__ formula. To
 install on macOS:
@@ -352,6 +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
 ----------------------------
 
@@ -387,18 +376,12 @@ Update the homebrew pip:
 
     pip install --upgrade pip
 
-You can then install OCRmyPDF from PyPI, for the current user:
+You can then install OCRmyPDF from PyPI for the current user:
 
 .. code-block:: bash
 
     pip install --user ocrmypdf
 
-or system-wide:
-
-.. code-block:: bash
-
-    pip install ocrmypdf
-
 The command line program should now be available:
 
 .. code-block:: bash
@@ -411,37 +394,64 @@ Installing on Windows
 Native Windows
 --------------
 
+..
+  If you have a Windows that is not the Home edition, you can use Windows Sandbox to test on a blank Windows instance.
+  https://learn.microsoft.com/en-us/windows/security/application-security/application-isolation/windows-sandbox/
+
 .. note::
 
     Administrator privileges will be required for some of these steps.
 
 You must install the following for Windows:
 
-* Python 3.7 (64-bit) or later
-* Tesseract 4.0 or later
-* Ghostscript 9.50 or later
+* Python 64-bit
+* Tesseract 64-bit
+* Ghostscript 64-bit
 
-Using the `Chocolatey <https://chocolatey.org/>`_ package manager, install the
-following when running in an Administrator command prompt:
+Using the `winget <https://docs.microsoft.com/en-us/windows/package-manager/winget/>`_
+package manager:
+
+* ``winget install -e --id Python.Python.3.11``
+* ``winget install -e --id UB-Mannheim.TesseractOCR``
+
+You will need to install Ghostscript manually, `since it does not support automated
+installs anymore <https://artifex.com/news/ghostscript-10.01.0-disabling-silent-install-option>`_.
+
+* `Ghostscript download page <https://ghostscript.com/releases/gsdnld.html>`_.`
+
+(Or alternately, using the `Chocolatey <https://chocolatey.org/>`_ package manager, install
+the following when running in an Administrator command prompt):
 
 * ``choco install python3``
 * ``choco install --pre tesseract``
-* ``choco install ghostscript``
 * ``choco install pngquant`` (optional)
 
-The commands above will install Python 3.x (latest version), Tesseract, Ghostscript
-and pngquant. Chocolatey may also need to install the Windows Visual C++ Runtime
-DLLs or other Windows patches, and may require a reboot.
+Either set of commands will install the required software. At the moment there is no
+single command to install Windows.
 
 You may then use ``pip`` to install ocrmypdf. (This can performed by a user or
 Administrator.):
 
-* ``pip install ocrmypdf``
+* ``python3 -m pip install ocrmypdf``
 
-Chocolatey automatically selects appropriate versions of these applications. If you
-are installing them manually, please install 64-bit versions of all applications for
-64-bit Windows, or 32-bit versions of all applications for 32-bit Windows. Mixing
-the "bitness" of these programs will lead to errors.
+..
+  The Windows Python versions do not place any python or python3 executable in the path.
+  They add the py launcher to the path:
+  https://docs.python.org/3/using/windows.html#python-launcher-for-windows
+
+If you installed Python using WinGet, then use the following command instead:
+
+* ``py -m pip install ocrmypdf``
+
+and use:
+
+* ``py -m ocrmypdf``
+
+To start OCRmyPDF.
+
+If you intend to use more Python software on your Windows machine, consider the use of
+`pipx <https://pipx.pypa.io/stable/>`_ or a similar tool to create isolated Python
+environments for each Python software that you want to use.
 
 OCRmyPDF will check the Windows Registry and standard locations in your Program Files
 for third party software it needs (specifically, Tesseract and Ghostscript). To
@@ -453,9 +463,13 @@ to change the PATH.
 
     As of early 2021, users have reported problems with the Microsoft Store version of
     Python and OCRmyPDF. These issues affect many other third party Python packages.
-    Please download Python from Python.org or Chocolatey instead, and do not use the
+    Please download Python from Python.org or a package manager instead of the
     Microsoft Store version.
 
+.. warning::
+
+    32-bit Windows is not supported.
+
 Windows Subsystem for Linux
 ---------------------------
 
@@ -481,7 +495,7 @@ Cygwin64
 
 First install the the following prerequisite Cygwin packages using ``setup-x86_64.exe``::
 
-    python37 (or later)
+    python310 (or later)
     python3?-devel
     python3?-pip
     python3?-lxml
@@ -490,7 +504,7 @@ First install the the following prerequisite Cygwin packages using ``setup-x86_6
        (where 3? means match the version of python3 you installed)
 
     gcc-g++
-    ghostscript (<=9.50 or >=9.52-2 see note below)
+    ghostscript
     libexempi3
     libexempi-devel
     libffi6
@@ -501,13 +515,6 @@ First install the the following prerequisite Cygwin packages using ``setup-x86_6
     tesseract-ocr
     tesseract-ocr-devel
 
-.. note::
-
-    The Cygwin package for Ghostscript in versions 9.52 and
-    9.52-1 contained a bug that caused an exception to occur when
-    ocrmypdf invoked gs.  Make sure you have either 9.50 (or earlier)
-    or 9.52-2 (or later).
-
 Then open a Cygwin terminal (i.e. ``mintty``), run the following commands. Note
 that if you are using the version of ``pip`` that was installed with the Cygwin
 Python package, the command name will be ``pip3``.  If you have since updated
@@ -559,21 +566,6 @@ the latest version. However, PyPI and ``pip`` cannot address the fact
 that ``ocrmypdf`` depends on certain non-Python system libraries and
 programs being installed.
 
-.. warning::
-
-    Debian and Ubuntu users: unfortunately, Debian and Ubuntu customize
-    Python in non-standard ways, and the nature of these customizations
-    varies from release to release. This can make for a frustrating
-    user experience. The instructions below work on almost all platforms that
-    have Python installed, except for Debian and Ubuntu, where you may need
-    to take additional steps. For best results on Debian and Ubuntu, use the
-    ``apt`` packages; or if these are too old, run
-    ``apt install python3-pip python3-venv``, create a virtual environment,
-    and install OCRmyPDF in that environment.
-
-    `See here for more inforation on Debian-Python issues
-    <https://gist.github.com/tiran/2dec9e03c6f901814f6d1e8dad09528e>`__.
-
 For best results, first install `your platform's
 version <https://repology.org/metapackage/ocrmypdf/versions>`__ of
 ``ocrmypdf``, using the instructions elsewhere in this document. Then
@@ -589,23 +581,24 @@ 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.
 
-Since ``pip install --user`` does not work correctly on some platforms,
-notably Ubuntu 16.04 and older, and the Homebrew version of Python,
-instead use this for a system wide installation:
+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
 
-    pip install ocrmypdf
+    pipx run ocrmypdf
 
-.. note::
-
-    AArch64 (ARM64) users: this process will be difficult because most
-    Python packages are not available as binary wheels for your platform.
-    You're probably better off using a platform install on Debian, Ubuntu,
-    or Fedora.
+(If not installed, pipx will install first.)
 
 Requirements for pip and HEAD install
 -------------------------------------
@@ -616,13 +609,16 @@ manager. ``pip`` cannot provide them.
 
 The following versions are required:
 
--  Python 3.7 or newer
--  Ghostscript 9.23 or newer
--  Tesseract 4.0.0 or newer
+-  Python 3.10 or newer
+-  Ghostscript 9.54 or newer
+-  Tesseract 4.1.1 or newer
 -  jbig2enc 0.29 or newer
 -  pngquant 2.5 or newer
 -  unpaper 6.1
 
+We recommend 64-bit versions of all software. (32-bit versions are not
+supported, although on Linux, they may still work.)
+
 jbig2enc, pngquant, and unpaper are optional. If missing certain
 features are disabled. OCRmyPDF will discover them as soon as they are
 available.
@@ -649,7 +645,7 @@ unfortunately, the ``pip install`` command cannot satisfy all of them.
 Installing HEAD revision from sources
 =====================================
 
-If you have ``git`` and Python 3.7 or newer installed, you can install
+If you have ``git`` and Python 3.10 or newer installed, you can install
 from source. When the ``pip`` installer runs, it will alert you if
 dependencies are missing.
 
@@ -665,8 +661,7 @@ 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
@@ -678,9 +673,9 @@ system-wide:
 
 .. code-block:: bash
 
-    git clone -b master https://github.com/ocrmypdf/OCRmyPDF.git
-    python3 -m venv
-    source venv/bin/activate
+    git clone -b main https://github.com/ocrmypdf/OCRmyPDF.git
+    python3 -m venv .venv
+    source .venv/bin/activate
     cd OCRmyPDF
     pip install .
 
@@ -705,9 +700,9 @@ To install all of the development and test requirements:
 
 .. code-block:: bash
 
-    git clone -b master https://github.com/ocrmypdf/OCRmyPDF.git
-    python -m venv
-    source venv/bin/activate
+    git clone -b main https://github.com/ocrmypdf/OCRmyPDF.git
+    python -m venv .venv
+    source .venv/bin/activate
     cd OCRmyPDF
     pip install -e .[test]
 
@@ -728,3 +723,18 @@ To manually install the ``bash`` completion, copy
 To manually install the ``fish`` completion, copy
 ``misc/completion/ocrmypdf.fish`` to
 ``~/.config/fish/completions/ocrmypdf.fish``.
+
+Note on 32-bit support
+======================
+
+Many Python libraries no longer provide 32-bit binary wheels for Linux. This
+includes many of the libraries that OCRmyPDF depends on, such as
+Pillow. The easiest way to express this to end users is to say we don't
+support 32-bit Linux.
+
+However, if your Linux distribution still supports 32-bit binaries, you
+can still install and use OCRmyPDF. A warning message will appear.
+In practice, OCRmyPDF may need more than 32-bit memory space to run when
+large documents are processed, so there are practical limitations to what
+users can accomplish with it. Still, for the common use case of an 32-bit
+ARM NAS or Raspberry Pi processing small documents, it should work.

docs/introduction.rst

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

docs/jbig2.rst

@@ -14,17 +14,20 @@ expired as of 2017, but it is possible that unknown patents exist.
 
 JBIG2 encoding is recommended for OCRmyPDF and is used to losslessly
 create smaller PDFs. If JBIG2 encoding is not available, lower quality
-encodings will be used.
+CCITT encoding will be used for monochrome images.
 
 JBIG2 decoding is not patented and is performed automatically by most
 PDF viewers. It is widely supported and has been part of the PDF
 specification since 2001.
 
-On macOS, Homebrew packages jbig2enc and OCRmyPDF includes it by
-default. The Docker image for OCRmyPDF also builds its own JBIG2 encoder
-from source.
+JBIG encoding is automatically provided by these OCRmyPDF packages:
+- Docker image (both Ubuntu and Alpine)
+- Snap package
+- ArchLinux AUR package
+- Alpine Linux package
+- Homebrew on macOS
 
-For all other Linux, you must build a JBIG2 encoder from source:
+For all other platforms, you would need to build the JBIG2 encoder from source:
 
 .. code-block:: bash
 
@@ -34,29 +37,45 @@ For all other Linux, you must build a JBIG2 encoder from source:
    ./configure && make
    [sudo] make install
 
-.. _jbig2-lossy:
-
 Dependencies include libtoolize and libleptonica, which on Ubuntu systems
-are packaged as libtool and libleptonica-dev.
+are packaged as libtool and libleptonica-dev. On Fedora (35) they are packaged
+as libtool and leptonica-devel. 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
+
+.. _jbig2-lossy:
 
 Lossy mode JBIG2
 ================
 
-OCRmyPDF provides lossy mode JBIG2 as an advanced feature. Users should
+OCRmyPDF provides lossy mode JBIG2 as an advanced and potentially dangerous
+feature. Users should
 `review the technical concerns with JBIG2 in lossy
 mode <https://en.wikipedia.org/wiki/JBIG2#Disadvantages>`__
-and decide if this feature is acceptable for their use case.
+and decide if this feature is acceptable for their use case. In general,
+this mode should not be used for archival purposes, should not be used when
+the original document is not available or will be destroyed, and should
+not be used when numbers present in the document are important, because
+there is a risk of 6/8 and 8/6 substitution errors.
 
 JBIG2 lossy mode does achieve higher compression ratios than any other
 monochrome (bitonal) compression technology; for large text documents
 the savings are considerable. JBIG2 lossless still gives great
 compression ratios and is a major improvement over the older CCITT G4
-standard. As explained above, there is some risk of substitution errors.
+standard.
 
 To turn on JBIG2 lossy mode, add the argument ``--jbig2-lossy``.
 ``--optimize {1,2,3}`` are necessary for the argument to take effect
 also required. Also, a JBIG2 encoder must be installed as described in
 the previous section.
 
+You can adjust the threshold for JBIG2 compression with the
+``--jbig2-threshold``. The default is 0.85, meaning that if two symbols
+are 85% similar, they will be compressed together.
+
 *Due to an oversight, ocrmypdf v7.0 and v7.1 used lossy mode by
 default.*

docs/languages.rst

@@ -12,22 +12,32 @@ OCRmyPDF uses Tesseract for OCR, and relies on its language packs for all langua
 On most platforms, English is installed with Tesseract by default, but not always.
 
 Tesseract supports `most
-languages <https://github.com/tesseract-ocr/tesseract/blob/master/doc/tesseract.1.asc#languages>`__.
+languages <https://github.com/tesseract-ocr/tesseract/blob/main/doc/tesseract.1.asc#languages>`__.
 Languages are identified by standardized three-letter codes (called ISO 639-2 Alpha-3).
 Tesseract's documentation also lists the three-letter code for your language.
 Some are anglicized, e.g. Spanish is ``spa`` rather than ``esp``, while others
 are not, e.g. German is ``deu`` and French is ``fra``.
 
+Language packs (strictly speaking, Tesseract "traineddata" files) generally correspond
+to the language in question, but different language packs are used in certain
+situations. For German, the "Fraktur" language pack can assist with reading older
+materials in the Fraktur typeface family (``deu_frak``). Some communities have changed
+their script from Cyrillic to Latin; the Cyrillic version of Uzbek is available
+as ``uzb_cyrl`` and the Latin version is ``uzb``.
+
 After you have installed a language pack, you can use it with ``ocrmypdf -l <language>``,
 for example ``ocrmypdf -l spa``. For multilingual documents, you can specify
 all languages to be expected, e.g. ``ocrmypdf -l eng+fra`` for English and French.
 English is assumed by default unless other language(s) are specified.
 
 For Linux users, you can often find packages that provide language
-packs:
+packs.
 
-Debian and Ubuntu users
-=======================
+Platform install steps
+======================
+
+Debian and Ubuntu (apt)
+-----------------------
 
 .. code-block:: bash
 
@@ -42,8 +52,8 @@ to what languages it should search for. Multiple languages can be
 requested using either ``-l eng+fra`` (English and French) or
 ``-l eng -l fra``.
 
-Fedora users
-============
+Fedora
+------
 
 .. code-block:: bash
 
@@ -58,8 +68,24 @@ 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
-============
+Arch Linux
+----------
+
+.. 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``.
@@ -70,13 +96,13 @@ This enables these languages for all packages (e.g. including aspell).
 
    # Display a list of all Tesseract language packs
    equery uses app-text/tessdata_fast
-   
+
    # Add English and German language support for Tesseract only
    echo 'app-text/tessdata_fast l10n_de l10n_en' >> /etc/portage/package.use
-   
-   # Add global English and German language support (the `l10n_` from equery has to be omited)
+
+   # Add global English and German language support (the `l10n_` from equery has to be omitted)
    echo L10N="de en" >> /etc/portage/make.conf
-   
+
    # update system to reflect changed USE flags
    emerge --update --deep --newuse @world
 
@@ -85,23 +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 
+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

@@ -38,17 +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.
-
-OCRmyPDF uses setuptools-scm-git-archive to ensure that tarballs downloaded from
-GitHub contain version information. Unfortunately, these tarballs are not always
-deterministic. See this
-`issue <https://github.com/ocrmypdf/OCRmyPDF/issues/841#issuecomment-936562696>`_.
+necessary, or set the environment variable ``SETUPTOOLS_SCM_PRETEND_VERSION``
+to the required version, if you need to override versioning for some reason.
 
 jbig2enc
 --------
@@ -61,4 +57,21 @@ improve OCRmyPDF's compression.
 Command line completions
 ------------------------
 
-Please ensure that command line completions are installed.
+Please ensure that command line completions are installed, as described in the
+installation documentation.
+
+32-bit Linux support
+--------------------
+
+If you maintain a Linux distribution that supports 32-bit x86 or ARM, OCRmyPDF
+should continue to work as long as all of its dependencies continue to be
+available in 32-bit form. Please note we do not test on 32-bit platforms.
+
+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/optimizer.rst

@@ -13,21 +13,40 @@ tuned. Optimization occurs after OCR, and only if OCR succeeded.  It does not
 perform other possible optimizations such as deduplicating resources,
 consolidating fonts, simplifying vector drawings, or anything of that nature.
 
-Optimization ranges from ``-O0`` through ``-O3``, where ``0`` disables
-optimization and ``3`` implements all options. ``1``, the default, performs only
-safe and lossless optimizations. (This is similar to GCC's optimization
-parameter.) The exact type of optimizations performed will vary over time.
+.. list-table:: Title
+    :widths: 33 6 60
+    :header-rows: 1
 
-PDF optimization requires third-party, optional tools for certain optimizations.
-If these are not installed or cannot be found by OCRmyPDF, optimization will not
-be as good.
+    * - Optimization level
+      - Shorthand
+      - Description
+    * - ``--optimize 0``
+      - ``-O0``
+      - Disable most optimizations.
+    * - ``--optimize 1`` (default)
+      - ``-O1``
+      - Safe and lossless optimizations.
+    * - ``--optimize 2``
+      - ``-O2``
+      - Safe and lossy optimizations.
+    * - ``--optimize 3``
+      - ``-O3``
+      - Aggressive lossy optimizations.
+
+The exact type of optimizations performed will vary over time, and depend on
+the availability of third-party tools.
+
+Despite optimizations, OCRmyPDF might still increase the overall file size,
+since it must embed information about the recognized text, and depending on the
+settings chosen, may not be able to represent the output file as compactly as
+the input file.
 
 Optimizations that always occurs
 ================================
 
 OCRmyPDF will automatically replace obsolete or inferior compression schemes
-such as RLE or LZW with superior schemes such as Deflate and converting
-monochrome images to CCITT G4. Since this is harmless it always occurs and there
+such as RLE or LZW with superior schemes such as Deflate, and convert
+monochrome images to CCITT G4. Since this is lossless, it always occurs and there
 is no way to disable it. Other non-image compressed objects are compressed as
 well.
 
@@ -37,12 +56,14 @@ Fast web view
 OCRmyPDF automatically optimizes PDFs for "fast web view" in Adobe Acrobat's
 parlance, or equivalently, linearizes PDFs so that the resources they reference
 are presented in the order a viewer needs them for sequential display. This
-reduces the latency of viewing a PDF both online and from local storage. This
-actually slightly increases the file size.
+reduces the latency of viewing a PDF both online and from local storage, in
+exchange for a slight increase in file size.
 
 To disable this optimization and all others, use ``ocrmypdf --optimize 0 ...``
 or the shorthand ``-O0``.
 
+Adobe Acrobat might not report the file as being "fast web view".
+
 Lossless optimizations
 ======================
 

docs/pdfsecurity.rst

@@ -2,6 +2,8 @@
 ..
 .. SPDX-License-Identifier: CC-BY-SA-4.0
 
+.. _security:
+
 ===================
 PDF security issues
 ===================
@@ -29,13 +31,9 @@ attack vectors.
 In short, PDFs `may contain
 viruses <https://security.stackexchange.com/questions/64052/can-a-pdf-file-contain-a-virus>`__.
 
-This
-`article <https://theinvisiblethings.blogspot.ca/2013/02/converting-untrusted-pdfs-into-trusted.html>`__
-describes a high-paranoia method which allows potentially hostile PDFs
-to be viewed and rasterized safely in a disposable virtual machine. A
-trusted PDF created in this manner is converted to images and loses all
-information making it searchable and losing all compression. OCRmyPDF
-could be used to restore searchability.
+If you do not trust a PDF or its source, do not open it or use OCRmyPDF
+on it. Consider using a Docker container or virtual machine to isolate
+an untrusted PDF from your system.
 
 How OCRmyPDF processes PDFs
 ===========================
@@ -43,11 +41,11 @@ How OCRmyPDF processes PDFs
 OCRmyPDF must open and interpret your PDF in order to insert an OCR
 layer. First, it runs all PDFs through
 `pikepdf <https://github.com/pikepdf/pikepdf>`__, a library based on
-`qpdf <https://github.com/qpdf/qpdf>`__, a program that repairs PDFs
+`QPDF <https://github.com/qpdf/qpdf>`__, a program that repairs PDFs
 with syntax errors. This is done because, in the author's experience, a
 significant number of PDFs in the wild, especially those created by
-scanners, are not well-formed files. qpdf makes it more likely that
-OCRmyPDF will succeed, but offers no security guarantees. qpdf is also
+scanners, are not well-formed files. QPDF makes it more likely that
+OCRmyPDF will succeed, but offers no security guarantees. QPDF is also
 used to split the PDF into single page PDFs.
 
 Finally, OCRmyPDF rasterizes each page of the PDF using
@@ -58,109 +56,72 @@ into the existing PDF or it may essentially reconstruct ("re-fry") a
 visually identical PDF that may be quite different at the binary level.
 That said, OCRmyPDF is not a tool designed for sanitizing PDFs.
 
-.. _ocr-service:
-
-Using OCRmyPDF online or as a service
-=====================================
-
-OCRmyPDF is not designed for use as a public web service where a
-malicious user could upload a chosen PDF. In particular, it is not
-necessarily secure against PDF malware or PDFs that cause denial of
-service. OCRmyPDF relies on Ghostscript, and therefore, if deployed
-online one should be prepared to comply with Ghostscript's Affero GPL
-license, and any other licenses.
-
-Setting aside these concerns, a side effect of OCRmyPDF is that it may
-incidentally sanitize PDFs containing certain types of malware. It
-repairs the PDF with pikepdf/libqpdf, which could correct malformed PDF
-structures that are part of an attack. When PDF/A output is selected
-(the default), the input PDF is partially reconstructed by Ghostscript.
-When ``--force-ocr`` is used, all pages are rasterized and reconverted
-to PDF, which could remove malware in embedded images.
-
-OCRmyPDF should be relatively safe to use in a trusted intranet, with
-some considerations:
-
-Limiting CPU usage
-------------------
-
-OCRmyPDF will attempt to use all available CPUs and storage, so
-executing ``nice ocrmypdf`` or limiting the number of jobs with the
-``-j`` argument may ensure the server remains available. Another option
-would be to run OCRmyPDF jobs inside a Docker container, a virtual machine,
-or a cloud instance, which can impose its own limits on CPU usage and be
-terminated "from orbit" if it fails to complete.
-
-Temporary storage requirements
-------------------------------
-
-OCRmyPDF will use a large amount of temporary storage for its work,
-proportional to the total number of pixels needed to rasterize the PDF.
-The raster image of a 8.5×11" color page at 300 DPI takes 25 MB
-uncompressed; OCRmyPDF saves its intermediates as PNG, but that still
-means it requires about 9 MB per intermediate based on average
-compression ratios. Multiple intermediates per page are also required,
-depending on the command line given. A rule of thumb would be to allow
-100 MB of temporary storage per page in a file – meaning that a small
-cloud servers or small VM partitions should be provisioned with plenty
-of extra space, if say, a 500 page file might be sent.
-
-To check temporary storage usage on actual files, run
-``ocrmypdf -k ...`` which will preserve and print the path to temporary
-storage when the job is done.
-
-To change where temporary files are stored, change the ``TMPDIR``
-environment variable for ocrmypdf's environment. (Python's
-``tempfile.gettempdir()`` returns the root directory in which temporary
-files will be stored.) For example, one could redirect ``TMPDIR`` to a
-large RAM disk to avoid wear on HDD/SSD and potentially improve
-performance. On Amazon Web Services, ``TMPDIR`` can be set to `empheral
-storage <https://docs.aws.amazon.com/AWSEC2/latest/UserGuide/InstanceStorage.html>`__.
-
-Timeouts
---------
-
-To prevent excessively long OCR jobs consider setting
-``--tesseract-timeout`` and/or ``--skip-big`` arguments. ``--skip-big``
-is particularly helpful if your PDFs include documents such as reports
-on standard page sizes with large images attached - often large images
-are not worth OCR'ing anyway.
-
-Commercial alternatives
------------------------
-
-The author also provides professional services that include OCR and
-building databases around PDFs, and is happy to provide consultation.
-
-Abbyy Cloud OCR is viable commercial alternative with a web services
-API. Amazon Textract, Google Cloud Vision, and Microsoft Azure 
-Computer Vision provide advanced OCR but have less PDF rendering capability.
-
-Password protection, digital signatures and certification
-=========================================================
+Password protected PDFs
+=======================
 
 Password protected PDFs usually have two passwords, and owner and user
 password. When the user password is set to empty, PDF readers will open
-the file automatically and marked it as "(SECURED)". While not as
-reliable as a digital signature, this indicates that whoever set the
-password approved of the file at that time. When the user password is
-set, the document cannot be viewed without the password.
+the file automatically and mark it as "(SECURED)". Password security can
+also request certain restrictions on the PDF, but anyone can remove these
+restrictions if they have either the owner *or* user password. Passwords
+mainly present a barrier for casual users.
 
-Either way, OCRmyPDF does not remove passwords from PDFs and exits with
-an error on encountering them.
+OCRmyPDF cannot remove passwords from PDFs. If you want to remove a
+password from a PDF, you must use other software, such as ``qpdf``.
 
-``qpdf`` can remove passwords. If the owner and user password are set, a
+If the owner and user password are set, a
 password is required for ``qpdf``. If only the owner password is set, then the
-password can be stripped, even if one does not have the owner password.
+password can be stripped, even if one does not have the owner password. To
+remove the password from a using QPDF, use:
 
-After OCR is applied, password protection is not permitted on PDF/A
-documents but the file can be converted to regular PDF.
+.. code-block:: bash
+
+   qpdf --decrypt --password='abc123' input.pdf no_password.pdf
+
+Then you can run OCRmyPDF on the file.
+
+In its default mode, OCRmyPDF generates PDF/A. Passwords may not be set on PDF/A
+documents. If you want to set a password on the output PDF, you must
+specify ``--output-type pdf``.
+
+Signature images
+================
 
 Many programs exist which are capable of inserting an image of someone's
 signature. On its own, this offers no security guarantees. It is trivial
 to remove the signature image and apply it to other files. This practice
 offers no real security.
 
+Digital signatures
+==================
+
 Important documents can be digitally signed and certified to attest to
-their authorship. OCRmyPDF cannot do this. Open source tools such as
-pdfbox (Java) have this capability as does Adobe Acrobat.
+their authorship, approval or execution of a legal agreement. OCRmyPDF
+will detect signed PDFs and will not modify them, unless the
+``--invalidate-digital-signatures`` option is used, which will
+invalidate any signatures. (The signature may still be present in the PDF
+if opened, but PDF readers will not validate it.)
+
+A digital signature adds a cryptographic hash of the document to the
+document, so tamper protection is provided. That also precludes OCRmyPDF
+from modifying the document and preserving the signature.
+
+Digital signatures are not the same as a signature image. A digital
+signature is a cryptographic hash of the document that is encrypted with
+the author's private key. The signature is decrypted with the author's
+public key. The public key is usually distributed by a certificate
+authority. The signature is then verified by the PDF reader. If the
+document is modified, the signature will be invalidated.
+
+Certificate-encrypted PDFs
+==========================
+
+PDFs can be encrypted with a certificate. This is a more secure form of
+encryption than a password. The certificate is usually issued by a
+certificate authority. A certificate is used to encrypt the document using
+the public key for the benefit of a specific recipient who possesses
+the private key.
+
+OCRmyPDF cannot open certificate-encrypted PDFs. If you have the
+certificate, you can use other PDF software, such as Acrobat, to
+decrypt the PDF.

docs/performance.rst

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

docs/plugins.rst

@@ -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
 ==============
 
@@ -70,33 +73,23 @@ 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 ``setup.py`` 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:: python
+.. code-block:: toml
 
-    # sample ./setup.py file
-    from setuptools import setup
+    [project]
+    name = "ocrmypdf-exampleplugin"
 
-    setup(
-        name="ocrmypdf-exampleplugin",
-        packages=["exampleplugin"],
-        # the following makes a plugin available to pytest
-        entry_points={"ocrmypdf": ["exampleplugin = exampleplugin.pluginmodule"]},
-    )
-
-.. code-block:: ini
-
-    # equivalent setup.cfg
-    [options.entry_points]
-    ocrmypdf =
-        exampleplugin = exampleplugin.pluginmodule
+    [project.entry-points."ocrmypdf"]
+    exampleplugin = "exampleplugin.pluginmodule"
 
 Plugin requirements
 ===================
@@ -181,8 +174,13 @@ Custom command line arguments
 Execution and progress reporting
 --------------------------------
 
+.. autoclass:: ocrmypdf.pluginspec.ProgressBar
+    :members:
+    :special-members: __init__, __enter__, __exit__
+
 .. autoclass:: ocrmypdf.pluginspec.Executor
     :members:
+    :special-members: __call__
 
 .. autofunction:: ocrmypdf.pluginspec.get_logging_console
 

docs/release_notes.rst

@@ -20,6 +20,8 @@ The most recent release of OCRmyPDF is |OCRmyPDF PyPI|. Any newer versions
 referred to in these notes may exist the main branch but have not been
 tagged yet.
 
+OCRmyPDF typically supports the three most recent Python versions.
+
 .. note::
 
    Attention maintainers: these release notes may be updated with information
@@ -28,6 +30,496 @@ tagged yet.
 
 .. |OCRmyPDF PyPI| image:: https://img.shields.io/pypi/v/ocrmypdf.svg
 
+v16.10.0
+========
+
+-  Added hocr textangle processing, improving handling of text at angles.
+   Thanks @0dinD :issue:`1467`
+-  Docker documentation updates related to podman. Thanks @rugk. :issue:`1489,1488`
+-  Dropped webservice.py's fragile use of ttyd. Instead, messages from ocrmypdf are
+   printed to the console.
+-  Fixed broken test test_hocrtransform_matches_sandwich, which had become
+   an invalid test. Thanks @QuLogic for reporting.
+-  Improved install instructions for Windows. Thanks @alex.
+
+v16.9.0
+=======
+
+-  Added hocr caption processing. Thanks @0dinD :issue:`1466`
+-  ocrmypdf-alpine Docker image is now built with Alpine 3.21.
+-  Fixed error handling of PDFs that contain invalid images with both ImageMask
+   and ColorSpace defined. :issue:`1453`
+-  Fixed test suite regression when only older Ghostscripts are installed.
+-  Improved documetnation of _progressbar.py. Thanks @QuentinFuxa. :issue:`1456`
+-  Disabling building of documentation as PDF on ReadTheDocs, as this caused
+   complex build issues deemed not worth solving.
+
+v16.8.0
+=======
+
+-  Upgraded webservice.py demonstration using streamlit. It's now possible to
+   exercise most of OCRmyPDF's functionality in a simple web UI.
+-  Added cache to Dockerfiles to improve build speed.
+-  Fixed numerous formatting errors in the documentation that prevented some
+   parts of documentation from generating correctly.
+-  Improved OCR text rendering by suppressing negative-width spaces. Thanks
+   @pajowu. :issue:`1446`
+-  Improved detecting of invisible text when using `--redo-ocr`. Thanks
+   @pajowu. :issue:`1448``
+
+v16.7.0
+=======
+
+-  Fixed further issues with Docker build and updated some versions.
+-  Main Docker image returned to Ubuntu 24.04 since the fix in v16.6.2 resolved
+   that concern.
+-  Code that previously sent Ghostscript output to stdout has been changed to
+   output to temporary files, since Ghostscript was doing that anyway internally.
+   This is a modest efficiency improvement.
+-  Fixed an issue with debug log output being parsed as rich markup. :issue:`1444`
+
+v16.6.2
+=======
+
+-  Remove invalid hyperlink annotations to satisfy Ghostscript 10.x during PDF/A
+   conversion. :issue:`1425`
+
+v16.6.1
+=======
+
+-  Fixed some issues with Docker build, such as removing unnecessary content and using
+   a stable Tesseract version.
+-  Reverted Docker image to Ubuntu 22.04 to access older/more stable Ghostscript
+   for now.
+-  Clarified batch commands in documentation.
+-  Fixed an issue with JSON serialization and pickling of HOCRResult. :issue:`1427`
+
+v16.6.0
+=======
+
+-  Fixed an issue where damaged PDFs would fail with ``--redo-ocr``. :issue:`1403`
+-  Fixed an error that prevented JBIG2 optimization on Windows if the image
+   was optimized in an earlier step. :issue:`1396`
+-  Fixed an error detecting the version of unpaper 7.0.0. :issue:`1409`
+-  Fixed a performance regression when scanning pages. :issue:`1378`. Thanks @aliemjay.
+-  Fixed Alpine Docker image by enforcing Alpine 3.19. Alpine 3.20 includes a
+   defective version of Tesseract OCR and so is not usable.
+-  Upgraded Ubuntu Docker image to use Ubuntu 24.04.
+-  Build and test scripts/actions switched to uv.
+-  When running in a container, we now remind the user that temporary folders
+   are inside the container and may not be accessible.
+-  Fixed Linux test coverage matrix, which was missing some key versions.
+
+v16.5.0
+=======
+
+-  Fixed issue with interpreting PDFs that have images with array masks.
+   :issue:`1377`
+-  Enabled testing on Python 3.13.
+-  Fixed a test that did not work correctly but still passed. :issue:`1382`
+-  Improved "PDF/A conversion failed" warning message to better describe implications.
+-  Updated documentation to better explain OCR_JSON_SETTINGS in batch processing.
+-  Build backend changed from setuptools to hatchling.
+
+v16.4.3
+=======
+
+-  Work around pdfminer.six issue where a token on the buffer boundary is incorrectly
+   parsed as two tokens. :issue:`1361`
+-  New rules are applied to stencil masks and explicit masks when calculating the
+   optimal page DPI for rendering. :issue:`1362`
+-  Fixed attempts to use an incompatible jbig2.EXE provided by TeX Live. :issue:`1363`
+
+v16.4.2
+=======
+
+-  Fixed order of filenames passed to Ghostscript for PDF/A generation. :issue:`1359`
+-  Suppressed missing jbig2dec warning message. :issue:`1358`
+-  Fixed calculation of image size when soft mask dimensions don't match image
+   dimension. :issue:`1351`
+-  Several fixes to documentation. Thanks to users Iris and JoKalliauer
+   who contributed these changes.
+-  Fixed error on processing PDFs that are missing certain image metadata. :issue:`1315`
+
+v16.4.1
+=======
+
+-  Fixed calculation of image printed area (used in finding weighted DPI for OCR).
+   :issue:`1334`
+-  Fixed "NotImplementedError: not sure how to get colorspace" error
+   messages in logs which simply records a failure to optimize images with
+   print production colorspaces. :issue:`1315`
+
+v16.4.0
+=======
+
+-  Selecting the ``osd`` and ``equ`` pseudo-languages with ``-l/--language`` now
+   exits with an error when using Tesseract OCR, because these are not
+   regular Tesseract languages but implementation details implemented.
+   Using them can cause Tesseract to crash.
+-  The hOCR renderer is more tolerant of extra whitespace in input files.
+-  watcher.py now changes the output file extension to .pdf when the input is not
+   .pdf.
+-  Improved handling of PDFs that contain circularly referenced Form XObjects.
+   :issue:`1321`
+-  Fixed Alpine Docker image for ARM64, which was not building correctly.
+-  Docker images now use pikepdf 9.0.0.
+-  Prevent use of Tesseract OCR 5.4.0, a version with known regressions.
+-  Disabled progressbar for "Linearizing" when ``--no-progress-bar`` set.
+-  Fixed some tests that warn about missing JBIG2 decoding via pikepdf, by
+   installing the necessary libraries during tests.
+
+v16.3.1
+=======
+
+-  Fixed a test suite failure with Ghostscript 10.03.0+. :issue:`1316`
+-  Fixed an issue with the presentation of the "OCR" progress bar. :issue:`1313`
+
+v16.3.0
+=======
+
+-  Fixed progress bar not displaying for Ghostscript PDF/A conversion. :issue:`1313`
+-  Added progress bar for linearization. :issue:`1313`
+-  If `--rotate-pages-threshold` issued without `--rotate-pages` we now exit with
+   an error since the user likely intended to use `--rotate-pages`. :issue:`1309`
+-  If Tesseract hOCR gives an invalid line box, print an error message instead of
+   exiting with an error. :issue:`1312`
+
+v16.2.0
+=======
+
+-  Fixed issue 'NoneType' object has no attribute 'get' when optimizing certain PDFs.
+   :issue:`1293,1271`
+-  Switched formatting from black to ruff.
+-  Added support for sending sidecar output to io.BytesIO.
+-  Added support for converting HEIF/HEIC images (the native image of iPhones and
+   some other devices) to PDFs, when the appropriate pi-hief library is installed.
+   This library is marked as a dependency, but maintainers may opt out if needed.
+-  We now default to downsampling large images that would exceed Tesseract's internal
+   limits, but only if it cause processing to fail. Previously, this behavior only
+   occurred if specifically requested on command line. It can still be configured
+   and disabled. See the --tesseract command line options.
+-  Added Macports install instructions. Thanks @akierig.
+-  Improved logging output when an unexpected error occurs while trying to obtain
+   the version of a third party program.
+
+v16.1.2
+=======
+
+-  Fixed test suite failure when using Ghostscript 10.3.
+-  Other minor corrections.
+
+v16.1.1
+=======
+
+-  Fixed PyPy 3.10 support.
+
+v16.1.0
+=======
+
+-  Improved hOCR renderer is now default for left to right languages.
+-  Improved handling of rotated pages. Previously, OCR text might be missing for
+   pages that were rotated with a /Rotate tag on the page entry.
+-  Improved handling of cropped pages. Previously, in some cases a page with a
+   crop box would not have its OCR applied correctly and misalignment between
+   OCR text and visible text coudl occur.
+-  Documentation improvements, especially installation instructions for less
+   common platforms.
+
+v16.0.4
+=======
+
+-  Fixed some issues for left-to-right text with the new hOCR renderer. It is still
+   not default yet but will be made so soon. Right-to-left text is still in progress.
+-  Added an error to prevent use of several versions of Ghostscript that seem
+   corrupt existing text in input PDFs. Newly generated OCR is not affected.
+   For best results, use Ghostscript 10.02.1 or newer, which contains the fix
+   for the issue.
+
+v16.0.3
+=======
+
+-  Changed minimum required Ghostscript to 9.54, to support users of RHEL 9 and its
+   derivatives, since that is the latest version available there.
+-  Removed warning message about CVE-2023-43115, on the assumption that most
+   distributions have backported the patch by now.
+
+v16.0.2
+=======
+
+-  Temporarily changed PDF text renderer back to sandwich by default to address
+   regressions in macOS Preview.
+
+v16.0.1
+=======
+
+-  Fixed text rendering issue with new hOCR text renderer - extraneous byte order
+   marks.
+-  Tightened dependencies.
+
+v16.0.0
+=======
+
+-  Added OCR text renderer, combined the best ideas of Tesseract's PDF
+   generator and the older hOCR transformer renderer. The result is a hopefully
+   permanent fix for wordssmushedtogetherwithoutspaces issues in extracted text,
+   better registration/position of text on skewed baselines :issue:`1009`,
+   fixes to character output when the German Fraktur script is used :issue:`1191`,
+   proper rendering of right to left languages (Arabic, Hebrew, Persian) :issue:`1157`.
+   Asian languages may still have excessive word breaks compared to expectations.
+   The new renderer is the default; the old sandwich renderer is still available
+   using ``--pdf-renderer sandwich``; the old hOCR renderer is no more.
+-  The ``ocrmypdf.hocrtransform`` API has changed substantially.
+-  Support for Python 3.9 has been dropped. Python 3.10+ is now required.
+-  pikepdf >= 8.8.0 is now required.
+
+
+v15.4.4
+=======
+
+-  Fixed documentation for installing Ghostscript on Windows. :issue:`1198`
+-  Added warning message about security issue in older versions of Ghostscript.
+
+v15.4.3
+=======
+
+-  Fixed deprecation warning in pikepdf older than 8.7.1; pikepdf >= 8.7.1 is
+   now required.
+
+v15.4.2
+=======
+
+-  We now raise an exception on a certain class of PDFs that likely need an
+   explicit color conversion strategy selected to display correctly
+   for PDF/A conversion.
+-  Fixed an error that occurred while trying to write a log message after the
+   debug log handler was removed.
+
+v15.4.1
+=======
+
+-  Fixed misc/watcher.py regressions: accept ``--ocr-json-settings`` as either
+   filename or JSON string, as previously; and argument count mismatch.
+   :issue:`1183,1185`
+-  We no longer attempt to set /ProcSet in the PDF output, since this is an
+   obsolete PDF feature.
+-  Documentation improvements.
+
+v15.4.0
+=======
+
+-  Added new experimental APIs to support offline editing of the final text.
+   Specifically, one can now generate hOCR files with OCRmyPDF, edit them with
+   some other tool, and then finalize the PDF. They are experimental and
+   subject to change, including details of how the working folder is used.
+   There is no command line interface.
+-  Code reorganization: executors, progress bars, initialization and setup.
+-  Fixed test coverage in cases where the coverage tool did not properly trace
+   into threads or subprocesses. This code was still being tested but appeared
+   as not covered.
+-  In the test suite, reduced use of subprocesses and other techniques that
+   interfere with coverage measurement.
+-  Improved error check for when we appear to be running inside a snap container
+   and files are not available.
+-  Plugin specification now properly defines progress bars as a protocol rather
+   than defining them as "tqdm-like".
+-  We now default to using "forkserver" process creation on POSIX platforms
+   rather than fork, since this is method is more robust and avoids some
+   issues when threads are present.
+-  Fixed an instance where the user's request to ``--no-use-threads`` was ignored.
+-  If a PDF does not have language metadata on its top level object, we add
+   the OCR language.
+-  Replace some cryptic test error messages with more helpful ones.
+-  Debug messages for how OCRmyPDF picks the colorspace for a page are now
+   more descriptive.
+
+v15.3.1
+=======
+
+-  Fixed an issue with logging settings for misc/watcher.py introduced in the
+   previous release. :issue:`1180`
+-  We now attempt to preserve the input's extended attributes when creating
+   the output file.
+-  For some reason, the macOS build now needs OpenSSL explicitly installed.
+-  Updated documentation on Docker performance concerns.
+
+v15.3.0
+=======
+
+-  Update misc/watcher.py to improve command line interface using Typer, and
+   support ``.env`` specification of environment variables. Improved error
+   messages. Thanks to @mflagg2814 for the PR that prompted this improvement.
+-  Improved error message when a file cannot be read because we are running in
+   a snap container.
+
+v15.2.0
+=======
+
+-  Added a Docker image based on Alpine Linux. This image is smaller than the
+   Ubuntu-based image and may be useful in some situations. Currently hosted at
+   jbarlow83/ocrmypdf-alpine. Currently not available in ARM flavor.
+-  The Ubuntu Docker is now aliased to jbarlow83/ocrmypdf-ubuntu.
+-  Updated Docker documentation.
+
+v15.1.0
+=======
+
+-  We now require Pillow 10.0.1, due a serious security vulnerability in all earlier
+   versions of that dependency. The vulnerability concerns WebP images and could
+   be triggered in OCRmyPDF when creating a PDF from a malicious WebP image.
+-  Added some keyword arguments to ``ocrmypdf.ocr`` that were previously accepted
+   but undocumented.
+-  Documentation updates and typing improvements.
+
+v15.0.2
+=======
+
+-  Added Python 3.12 to test matrix.
+-  Updated documentation for notes on Python 3.12, 32-bit support and some new
+   features in v15.
+
+v15.0.1
+=======
+
+-  Wheels Python tag changed to py39.
+-  Marked as a expected fail a test that fails on recent Ghostscript versions.
+-  Clarified documentation and release notes around the extent of 32-bit support.
+-  Updated installation documentation to changes in v15.
+
+v15.0.0
+=======
+
+-  Dropped support for Python 3.8.
+-  Dropped support some older dependencies, specifically ``coloredlogs`` and
+   ``tqdm`` in favor of rich - see ``pyproject.toml`` for details.
+   Generally speaking, Ubuntu 22.04 is our new baseline system.
+-  Tightened version requirements for some dependencies.
+-  Dropped support for 32-bit Linux wheels. We strongly recommend a 64-bit operating
+   system, and 64-bit versions of Python, Tesseract and Ghostscript to use OCRmyPDF.
+   Many of our dependencies are dropping 32-bit builds (e.g. Pillow), and we are
+   following suit. (Maintainers may still build 32-bit versions from source.)
+-  Changed to trusted release for PyPI publishing.
+-  pikepdf memory mapping is enabled again for improved performance, now that an
+   issue with feature in pikepdf is fixed.
+-  ``ocrmypdf.helpers.calculate_downsample`` previously had two variants, one
+   that took a ``PIL.Image`` and one that took a ``tuple[int, int]``. The latter
+   was removed.
+-  The snap version of ocrmypdf is now based on Ubuntu core22.
+-  We now account for situations where a small portion of an image on a page is drawn
+   at high DPI (resolution). Previously, the entire page would be rasterized at the
+   highest resolution of any feature, which caused performance problems. Now,
+   the page is rasterized
+   at a resolution based on the average DPI of the page, weighted by the area that
+   each feature occupies. Typically, small areas of high resolution in PDFs are
+   errors or quirks from the repeated use of assets and high resolution is not
+   beneficial. :issue:`1010,1104,1004,1079,1010`
+-  Ghostscript color conversion strategy is now configurable using
+   ``--color-conversion-strategy``. :issue:`1143`
+-  JBIG2 threshold for optimization is now configurable using
+   ``--jbig2-threshold``. :issue:`1133`
+
+v14.4.0
+=======
+
+-  Digitally signed PDFs are now detected. If the PDF is signed, OCRmyPDF will
+   refuse to modify it. Previously, only encrypted PDFs were detected, not
+   those that were signed but not encrypted. :issue:`1040`
+-  In addition, ``--invalidate-digital-signatures`` can be used to override the
+   above behavior and modify the PDF anyway. :issue:`1040`
+-  tqdm progress bars replaced with "rich" progress bars. The rich library is
+   a new dependency. Certain APIs that used tqdm are now deprecated and will
+   be removed in the next major release.
+-  Improved integration with GitHub Releases. Thanks to @stumpylog.
+
+v14.3.0
+=======
+
+-  Renamed master branch to main.
+-  Improve PDF rasterization accuracy by using the ``-dPDFSTOPONERROR`` option
+   to Ghostscript. Use ``--continue-on-soft-render-error`` if you want to render
+   the PDF anyway. The plugin specification was adjusted to support this feature;
+   plugin authors may want to adapt PDF rasterizing and rendering
+   plugins. :issue:`1083`
+-  The calculated deskew angle is now recorded in the logged output. :issue:`1101`
+-  Metadata can now be unset by setting a metadata type such as ``--title`` to an
+   empty string. :issue:`1117,1059`
+-  Fixed random order of languages due to use of a set. This may have caused output
+   to vary when multiple languages were set for OCR. :issue:`1113`
+-  Clarified the optimization ratio reported in the log output.
+-  Documentation improvements.
+
+v14.2.1
+=======
+
+-  Fixed :issue:`977`, where images inside Form XObjects were always excluded
+   from image optimization.
+
+v14.2.0
+=======
+
+-  Added ``--tesseract-downsample-above`` to downsample larger images even when
+   they do not exceed Tesseract's internal limits. This can be used to speed
+   up OCR, possibly sacrificing accuracy.
+-  Fixed resampling AttributeError on older Pillow. :issue:`1096`
+-  Removed an error about using Ghostscript on PDFs with that have the /UserUnit
+   feature in use. Previously, Ghostscript would fail to process these PDFs,
+   but in all supported versions it is now supported, so the error is no longer
+   needed.
+-  Improved documentation around installing other language packs for Tesseract.
+
+v14.1.0
+=======
+
+-  Added ``--tesseract-non-ocr-timeout``. This allows using Tesseract's deskew
+   and other non-OCR features while disabling OCR using ``--tesseract-timeout 0``.
+-  Added ``--tesseract-downsample-large-images``. This downsamples larges images
+   that exceed the maximum image size Tesseract can handle. Large images may still
+   take a long time to process, but this allows them to be processed if that
+   is desired.
+-  Fixed :issue:`1082`, an issue with snap packaged building.
+-  Change linter to ruff, fix lint errors, update documentation.
+
+v14.0.4
+=======
+
+-  Fixed :issue:`1066, 1075`, an exception when processing certain malformed PDFs.
+
+v14.0.3
+=======
+
+-  Fixed :issue:`1068`, avoid deleting /dev/null when running as root.
+-  Other documentation fixes.
+
+v14.0.2
+=======
+
+-  Fixed :issue:`1052`, an exception on attempting to process certain nonconforming PDFs.
+-  Explicitly documented that Windows 32-bit is no longer supported.
+-  Fixed source installation instructions.
+-  Other documentation fixes.
+
+v14.0.1
+=======
+
+-  Fixed some version checks done with smart version comparison.
+-  Added missing jbig2dec to Docker image.
+
+v14.0.0
+=======
+
+-  Dropped support for Python 3.7.
+-  Dropped support generally speaking, all dependencies older than what Ubuntu 20.04
+   provides.
+-  Ghostscript 9.50 or newer is now required. Shims to support old versions were
+   removed.
+-  Tesseract 4.1.1 or newer is now required. Shims to support old versions were
+   removed.
+-  Docker image now uses Tesseract 5.
+-  Dropped setup.cfg configuration for pyproject.toml.
+-  Removed deprecation exception PdfMergeFailedError.
+-  A few more public domain test files were removed or replaced. We are aiming for
+   100% compliance with SPDX and generally towards simplifying copyright.
+
 v13.7.0
 =======
 
@@ -681,7 +1173,7 @@ v10.3.2
 v10.3.1
 =======
 
--  Fixed a number of test suite failures with pdfminer.six older than veresion 20200402.
+-  Fixed a number of test suite failures with pdfminer.six older than version 20200402.
 -  Enabled support for pdfminer.six 20200720.
 
 v10.3.0

misc/_webservice.py

@@ -0,0 +1,241 @@
+# SPDX-FileCopyrightText: 2025 James R. Barlow
+# SPDX-License-Identifier: AGPL-3.0-or-later
+
+"""This is a simple web service/HTTP wrapper for OCRmyPDF.
+
+This may be more convenient than the command line tool for some Docker users.
+Note that OCRmyPDF uses Ghostscript, which is licensed under AGPLv3+. While
+OCRmyPDF is under GPLv3, this file is distributed under the Affero GPLv3+ license,
+to emphasize that SaaS deployments should make sure they comply with
+Ghostscript's license as well as OCRmyPDF's.
+"""
+
+from __future__ import annotations
+
+import os
+import subprocess
+import sys
+import time
+from functools import partial
+from operator import getitem
+from pathlib import Path
+from shutil import which
+from tempfile import NamedTemporaryFile
+
+import pikepdf
+import streamlit as st
+from streamlit.components.v1 import iframe
+
+from ocrmypdf._defaults import DEFAULT_ROTATE_PAGES_THRESHOLD
+
+
+def get_host_url_with_port(port: int) -> str:
+    """Get the host URL for the web service. Hacky."""
+    host_url = st.context.headers["host"]
+    try:
+        host, _streamlit_port = host_url.split(":", maxsplit=1)
+    except ValueError:
+        host = host_url
+    return f"//{host}:{port}"  # Use the same protocol
+
+
+st.title("OCRmyPDF Web Service")
+
+uploaded = st.file_uploader("Upload input PDF or image", type=["pdf"], key="file")
+
+mode = st.selectbox("Mode", options=["normal", "skip-text", "force-ocr", "redo-ocr"])
+
+with st.expander("Input options"):
+    invalidate_digital_signatures = st.checkbox(
+        "Invalidate digital signatures", value=False
+    )
+    language = st.selectbox("Language", options=["eng", "deu", "fra", "spa"])
+
+    image_dpi = st.slider(
+        "Image DPI", value=300, key="image_dpi", min_value=1, max_value=5000, step=50
+    )
+with st.expander("Preprocessing"):
+    skip_big = st.checkbox("Skip OCR on big pages", value=False, key="skip_big")
+    oversample = st.slider("Oversample", min_value=0, max_value=5000, value=0, step=50)
+    rotate_pages = st.checkbox("Rotate pages", value=False, key="rotate")
+    deskew = st.checkbox("Deskew pages", value=False, key="deskew")
+    clean = st.checkbox("Clean pages before OCR", value=False, key="clean")
+    clean_final = st.checkbox("Clean final", value=False, key="clean_final")
+    remove_vectors = st.checkbox("Remove vectors", value=False, key="remove_vectors")
+
+
+with st.expander("Output options"):
+    output_type = st.selectbox(
+        "Output type", options=["pdfa", "pdfa", "pdfa-1", "pdfa-2", "pdfa-3", "none"]
+    )
+
+    pdf_renderer = st.selectbox(
+        "PDF rendereer", options=["auto", "hocr", "hocrdebug", "sandwich"]
+    )
+
+    optimize = st.selectbox("Optimize", options=["0", "1", "2", "3"])
+
+    st.selectbox("PDF/A compression", options=["auto", "jpeg", "lossless"])
+
+with st.expander("Metadata"):
+    title = author = keywords = subject = None
+    if uploaded:
+        with pikepdf.open(uploaded) as pdf, pdf.open_metadata() as meta:
+            st.code(str(meta), language="xml")
+            title = st.text_input("Title", value=meta.get('dc:title', ''))
+            author = st.text_input("Author", value=meta.get('dc:creator', ''))
+            keywords = st.text_input("Keywords", value=meta.get('dc:subject', ''))
+            subject = st.text_input("Subject", value=meta.get('dc:description', ''))
+
+
+with st.expander("Optimization after OCR"):
+    jpeg_quality = st.slider(
+        "JPEG quality", min_value=0, max_value=100, value=75, key="jpeg_quality"
+    )
+    png_quality = st.slider(
+        "PNG quality", min_value=0, max_value=100, value=75, key="png_quality"
+    )
+    jbig2_lossy = st.checkbox("JBIG2 lossy (dangerous)", value=False, key="jbig2_lossy")
+    jbig2_threshold = st.number_input("JBIG2 threshold", value=0, key="jbig2_threshold")
+
+with st.expander("Advanced options"):
+    jobs = st.slider(
+        "Threads",
+        min_value=1,
+        max_value=os.cpu_count(),
+        value=os.cpu_count(),
+        key="threads",
+    )
+    pages = st.text_input(
+        "Pages", value="", help="Comma-separated list of pages to process"
+    )
+    max_image_mpixels = st.number_input(
+        "Max image size",
+        value=250.0,
+        min_value=0.0,
+        help="Maximum image size in megapixels",
+    )
+    rotate_pages_threshold = st.number_input(
+        "Rotate pages threshold",
+        value=DEFAULT_ROTATE_PAGES_THRESHOLD,
+        min_value=0.0,
+        max_value=1000.0,
+        help="Threshold for automatic page rotation",
+    )
+    fast_web_view = st.number_input(
+        "Fast web view",
+        value=1.0,
+        min_value=0.0,
+        help="Linearize files above this size in MB",
+    )
+    continue_on_soft_render_error = st.checkbox(
+        "Continue on soft render error", value=True
+    )
+    verbose_labels = ["quiet", "default", "debug", "debug_all"]
+    verbose = st.selectbox(
+        "Verbosity level",
+        options=[-1, 0, 1, 2],
+        index=1,
+        format_func=partial(getitem, verbose_labels),
+    )
+
+if uploaded:
+    args = []
+    if mode and mode != 'normal':
+        args.append(f"--{mode}")
+    if language:
+        args.append(f"--language={language}")
+    if not uploaded.name.lower().endswith(".pdf") and image_dpi:
+        args.append(f"--image-dpi={image_dpi}")
+    if skip_big:
+        args.append("--skip-big")
+    if oversample:
+        args.append(f"--oversample={oversample}")
+    if rotate_pages:
+        args.append("--rotate-pages")
+    if deskew:
+        args.append("--deskew")
+    if clean:
+        args.append("--clean")
+    if clean_final:
+        args.append("--clean-final")
+    if remove_vectors:
+        args.append("--remove-vectors")
+    if output_type:
+        args.append(f"--output-type={output_type}")
+    if pdf_renderer:
+        args.append(f"--pdf-renderer={pdf_renderer}")
+    if optimize:
+        args.append(f"--optimize={optimize}")
+    if title:
+        args.append(f"--title={title}")
+    if author:
+        args.append(f"--author={author}")
+    if keywords:
+        args.append(f"--keywords={keywords}")
+    if subject:
+        args.append(f"--subject={subject}")
+    if pages:
+        args.append(f"--pages={pages}")
+    if max_image_mpixels:
+        args.append(f"--max-image-mpixels={max_image_mpixels}")
+    if rotate_pages_threshold:
+        args.append(f"--rotate-pages-threshold={rotate_pages_threshold}")
+    if fast_web_view:
+        args.append(f"--fast-web-view={fast_web_view}")
+    if continue_on_soft_render_error:
+        args.append("--continue-on-soft-render-error")
+    if verbose:
+        args.append(f"--verbose={verbose}")
+    if optimize > '0' and jpeg_quality:
+        args.append(f"--jpeg-quality={jpeg_quality}")
+    if optimize > '0' and png_quality:
+        args.append(f"--png-quality={png_quality}")
+    if jbig2_lossy:
+        args.append("--jbig2-lossy")
+    if jbig2_threshold:
+        args.append(f"--jbig2-threshold={jbig2_threshold}")
+    if jobs:
+        args.append(f"--jobs={jobs}")
+    input_file = NamedTemporaryFile(delete=True, suffix=f"_{uploaded.name}")
+    input_file.write(uploaded.getvalue())
+    input_file.flush()
+    input_file.seek(0)
+    args.append(str(input_file.name))
+    output_file = NamedTemporaryFile(delete=True, suffix=".pdf")
+    args.append(str(output_file.name))
+
+    st.session_state['running'] = (
+        'run_button' in st.session_state and st.session_state.run_button
+    )
+    if st.button(
+        "Run OCRmyPDF",
+        disabled=st.session_state.get("running", False),
+        key='run_button',
+    ):
+        st.session_state['running'] = True
+        args = [sys.executable, '-u', '-m', "ocrmypdf"] + args
+
+        proc = subprocess.Popen(args, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
+        with st.container(border=True):
+            while proc.poll() is None:
+                line = proc.stderr.readline()
+                if line:
+                    st.html("<code>" + line.decode().strip() + "</code>")
+
+        if proc.returncode != 0:
+            st.error(f"ocrmypdf failed with exit code {proc.returncode}")
+            st.session_state['running'] = False
+            st.stop()
+
+        if Path(output_file.name).stat().st_size == 0:
+            st.error("No output PDF file was generated")
+            st.stop()
+
+        st.download_button(
+            label="Download output PDF",
+            data=input_file.read(),
+            file_name=uploaded.name,
+            mime="application/pdf",
+        )
+        st.session_state['running'] = False

misc/batch.py

@@ -1,12 +1,24 @@
 #!/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.
+
+This script will recursively search a directory for PDF files and run OCR on
+them. It will log the results. It runs OCR on every file, even if it already
+has text. OCRmyPDF will detect files that already have text.
+
+You should edit this script to meet your needs.
+"""
+
 from __future__ import annotations
 
-# This script must be edited to meet your needs.
+import filecmp
 import logging
 import os
+import posixpath
+import shutil
 import sys
 from pathlib import Path
 
@@ -15,32 +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/completion/ocrmypdf.bash

@@ -6,52 +6,56 @@ set -o errexit
 
 __ocrmypdf_arguments()
 {
-    local arguments="--help                   (show help message)
---language               (language(s) of the file to be OCRed)
---image-dpi              (assume this DPI if input image DPI is unknown)
---output-type            (select PDF output options)
---sidecar                (write OCR to text file)
---version                (print program version and exit)
---jobs                   (how many worker processes to use)
---quiet                  (suppress INFO messages)
---verbose                (set verbosity level)
---title                  (set metadata)
---author                 (set metadata)
---subject                (set metadata)
---keywords               (set metadata)
---rotate-pages           (rotate pages to correct orientation)
---remove-background      (attempt to remove background from pages)
---deskew                 (fix small horizontal alignment skew)
---clean                  (clean document images before OCR)
---clean-final            (clean document images and keep result)
---unpaper-args           (a quoted string of arguments to pass to unpaper)
---oversample             (oversample images to this DPI)
---remove-vectors         (don\'t send vector objects to OCR)
---threshold              (threshold images before OCR)
---force-ocr              (OCR documents that already have printable text)
---skip-text              (skip OCR on any pages that already contain text)
---redo-ocr               (redo OCR on any pages that seem to have OCR already)
---skip-big               (skip OCR on pages larger than this many MPixels)
---optimize               (select optimization level)
---jpeg-quality           (JPEG quality [0..100])
---png-quality            (PNG quality [0..100])
---jbig2-lossy            (enable lossy JBIG2 (see docs))
---pages                  (apply OCR to only the specified pages)
---max-image-mpixels      (image decompression bomb threshold)
---pdf-renderer           (select PDF renderer options)
---rotate-pages-threshold (page rotation confidence)
---pdfa-image-compression (set PDF/A image compression options)
---fast-web-view          (if file size if above this amount in MB linearize PDF)
---plugin                 (name of plugin to import)
---keep-temporary-files   (keep temporary files (debug)
---tesseract-config       (set custom tesseract config file)
---tesseract-pagesegmode  (set tesseract --psm)
---tesseract-oem          (set tesseract --oem)
---tesseract-thresholding (set tesseract image thresholding)
---tesseract-timeout      (maximum number of seconds to wait for OCR)
---user-words             (specify location of user words file)
---user-patterns          (specify location of user patterns file)
---no-progress-bar        (disable the progress bar)
+    local arguments="\
+--help                          (show help message)
+--language                      (language(s) of the file to be OCRed)
+--image-dpi                     (assume this DPI if input image DPI is unknown)
+--output-type                   (select PDF output options)
+--sidecar                       (write OCR to text file)
+--version                       (print program version and exit)
+--jobs                          (how many worker processes to use)
+--quiet                         (suppress INFO messages)
+--verbose                       (set verbosity level)
+--title                         (set metadata)
+--author                        (set metadata)
+--subject                       (set metadata)
+--keywords                      (set metadata)
+--rotate-pages                  (rotate pages to correct orientation)
+--remove-background             (attempt to remove background from pages)
+--deskew                        (fix small horizontal alignment skew)
+--clean                         (clean document images before OCR)
+--clean-final                   (clean document images and keep result)
+--unpaper-args                  (a quoted string of arguments to pass to unpaper)
+--oversample                    (oversample images to this DPI)
+--remove-vectors                (don\'t send vector objects to OCR)
+--threshold                     (threshold images before OCR)
+--force-ocr                     (OCR documents that already have printable text)
+--skip-text                     (skip OCR on any pages that already contain text)
+--redo-ocr                      (redo OCR on any pages that seem to have OCR already)
+--invalidate-digital-signatures (remove digital signatures from PDF)
+--skip-big                      (skip OCR on pages larger than this many MPixels)
+--optimize                      (select optimization level)
+--jpeg-quality                  (JPEG quality [0..100])
+--png-quality                   (PNG quality [0..100])
+--jbig2-lossy                   (enable lossy JBIG2 (see docs))
+--jbig2-threshold               (set JBIG2 threshold (see docs))
+--pages                         (apply OCR to only the specified pages)
+--max-image-mpixels             (image decompression bomb threshold)
+--pdf-renderer                  (select PDF renderer options)
+--rotate-pages-threshold        (page rotation confidence)
+--pdfa-image-compression        (set PDF/A image compression options)
+--fast-web-view                 (if file size if above this amount in MB linearize PDF)
+--plugin                        (name of plugin to import)
+--keep-temporary-files          (keep temporary files (debug)
+--tesseract-config              (set custom tesseract config file)
+--tesseract-pagesegmode         (set tesseract --psm)
+--tesseract-oem                 (set tesseract --oem)
+--tesseract-thresholding        (set tesseract image thresholding)
+--tesseract-timeout             (maximum number of seconds to wait for OCR)
+--user-words                    (specify location of user words file)
+--user-patterns                 (specify location of user patterns file)
+--no-progress-bar               (disable the progress bar)
+--color-conversion-strategy     (select color conversion strategy)
 "
 
     COMPREPLY=( $( compgen -W "$arguments" -- "$cur") )
@@ -191,6 +195,20 @@ sauvola       (use Sauvola thresholding)"
     fi
 }
 
+__ocrmypdf_color-conversion-strategy()
+{
+    local choices="LeaveColorUnchanged (default)
+CMYK (convert to CMYK)
+Gray (convert to grayscale)
+RGB (convert to RGB)
+UseDeviceIndependentColor (convert with device independent color)"
+
+    COMPREPLY=( $( compgen -W "$choices" -- "$cur") )
+    # Remove description if only one completion exists
+    if [[ ${#COMPREPLY[*]} -eq 1 ]]; then
+        COMPREPLY=( ${COMPREPLY[0]%% *} )
+    fi
+}
 
 __ocrmypdf_check_previous()
 {
@@ -250,6 +268,10 @@ __ocrmypdf_check_previous()
             _filedir
             return 0
             ;;
+        --color-conversion-strategy)
+            __ocrmypdf_color-conversion-strategy
+            return 0
+            ;;
     esac
 
     return 1

misc/completion/ocrmypdf.fish

@@ -14,8 +14,9 @@ complete -c ocrmypdf -s i -l clean-final -d "clean document images and keep resu
 complete -c ocrmypdf -l remove-vectors -d "don't send vector objects to OCR"
 
 complete -c ocrmypdf -s f -l force-ocr -d "OCR documents that already have printable text"
-complete -c ocrmypdf -s s -l skip-ocr -d "skip OCR on pages that text, otherwise try OCR"
+complete -c ocrmypdf -s s -l skip-text -d "skip OCR on any pages that already contain text"
 complete -c ocrmypdf -l redo-ocr -d "redo OCR on any pages that seem to have OCR already"
+complete -c ocrmypdf -l invalidate-digital-signatures -d "invalidate digital signatures and allow OCR to proceed"
 
 complete -c ocrmypdf -s k -l keep-temporary-files -d "keep temporary files (debug)"
 
@@ -83,6 +84,7 @@ complete -c ocrmypdf -x -l skip-big -d "skip OCR on pages larger than this many
 complete -c ocrmypdf -x -l jpeg-quality -d "JPEG quality [0..100]"
 complete -c ocrmypdf -x -l png-quality -d "PNG quality [0..100]"
 complete -c ocrmypdf -x -l jbig2-lossy -d "enable lossy JBIG2 (see docs)"
+complete -c ocrmypdf -x -l jbig2-threshold -d "JBIG2 compression threshold (see docs)"
 complete -c ocrmypdf -x -l max-image-mpixels -d "image decompression bomb threshold"
 complete -c ocrmypdf -x -l pages -d "apply OCR to only the specified pages"
 complete -c ocrmypdf -x -l tesseract-config -d "set custom tesseract config file"
@@ -128,4 +130,27 @@ complete -c ocrmypdf -r -l user-words -d "specify location of user words file"
 complete -c ocrmypdf -r -l user-patterns -d "specify location of user patterns file"
 complete -c ocrmypdf -x -l fast-web-view -d "if file size if above this amount in MB, linearize PDF"
 
-complete -c ocrmypdf -x -a "(__fish_complete_suffix .pdf; __fish_complete_suffix .PDF; __fish_complete_suffix .jpg; __fish_complete_suffix .png)"
+function __fish_ocrmypdf_color_conversion_strategy
+    echo -e "LeaveColorUnchanged\t"(_ "do not convert color spaces (default)")
+    echo -e "CMYK\t"(_ "convert all color spaces to CMYK")
+    echo -e "Gray\t"(_ "convert all color spaces to grayscale")
+    echo -e "RGB\t"(_ "convert all color spaces to RGB")
+    echo -e "UseDeviceIndependentColor\t"(_ "convert all color spaces to ICC-based color spaces")
+end
+
+complete -c ocrmypdf -x -l color-conversion-strategy -a '(__fish_ocrmypdf_color_conversion_strategy)' -d "set color conversion strategy"
+
+function __fish_ocrmypdf_input_file_given
+    set -l tokens (commandline -opc)
+    for token in $tokens
+        if string match -q -r '^-' -- $token
+            continue
+        end
+        if test -f "$token"
+            return 0
+        end
+    end
+    return 1
+end
+
+complete -c ocrmypdf -x -n 'not __fish_ocrmypdf_input_file_given' -a "(__fish_complete_suffix .pdf)" -d "input file"

misc/docker-compose.example.yml

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

misc/example_plugin.py

@@ -1,8 +1,7 @@
 # SPDX-FileCopyrightText: 2022 James R Barlow: https://github.com/jbarlow83
 # SPDX-License-Identifier: MIT
 
-"""
-An example of an OCRmyPDF plugin.
+"""An example of an OCRmyPDF plugin.
 
 This plugin adds two new command line arguments
     --grayscale-ocr: converts the image to grayscale before performing OCR on it

misc/ocrmypdf_compare.py

@@ -0,0 +1,123 @@
+# SPDX-FileCopyrightText: 2025 James R. Barlow
+# SPDX-License-Identifier: MIT
+
+"""Run OCRmyPDF on the same PDF with different options."""
+
+from __future__ import annotations
+
+import os
+import shlex
+from io import BytesIO
+from pathlib import Path
+from subprocess import check_output, run
+from tempfile import TemporaryDirectory
+
+import pikepdf
+import pymupdf
+import streamlit as st
+from lxml import etree
+from streamlit_pdf_viewer import pdf_viewer
+
+
+def main():
+    st.set_page_config(layout="wide")
+
+    st.title("OCRmyPDF Compare")
+    st.write("Run OCRmyPDF on the same PDF with different options.")
+
+    uploaded_pdf = st.file_uploader("Upload a PDF", type=["pdf"])
+    if uploaded_pdf is None:
+        return
+
+    pdf_bytes = uploaded_pdf.read()
+
+    with pikepdf.open(BytesIO(pdf_bytes)) as p, TemporaryDirectory() as d:
+        with st.expander("PDF Metadata"):
+            with p.open_metadata() as meta:
+                xml_txt = str(meta)
+                parser = etree.XMLParser(remove_blank_text=True)
+                tree = etree.fromstring(xml_txt, parser=parser)
+                st.code(
+                    etree.tostring(tree, pretty_print=True).decode("utf-8"),
+                    language="xml",
+                )
+            st.write(p.docinfo)
+            st.write("Number of pages:", len(p.pages))
+
+        col1, col2 = st.columns(2)
+        with col1:
+            cli1 = st.text_area(
+                "Command line arguments for A",
+                key="args1",
+                value="ocrmypdf {in_} {out}",
+            )
+            env1 = st.text_area("Environment variables for A", key="env1")
+            args1 = shlex.split(
+                cli1.format(
+                    in_=os.path.join(d, "input.pdf"),
+                    out=os.path.join(d, "output1.pdf"),
+                )
+            )
+            st.code(shlex.join(args1))
+        with col2:
+            cli2 = st.text_area(
+                "Command line arguments for B",
+                key="args2",
+                value="ocrmypdf {in_} {out}",
+            )
+            env2 = st.text_area("Environment variables for B", key="env2")
+            args2 = shlex.split(
+                cli2.format(
+                    in_=os.path.join(d, "input.pdf"),
+                    out=os.path.join(d, "output2.pdf"),
+                )
+            )
+            st.code(shlex.join(args2))
+
+        if not st.button("Execute and Compare"):
+            return
+        with st.spinner("Executing..."):
+            Path(d, "input.pdf").write_bytes(pdf_bytes)
+            run(args1, env=dict(os.environ, **eval(env1 or "{}")))
+            run(args2, env=dict(os.environ, **eval(env2 or "{}")))
+
+            col1, col2 = st.columns(2)
+            with col1:
+                st.text(
+                    "Ghostscript version A: "
+                    + check_output(
+                        ["gs", "--version"],
+                        env=dict(os.environ, **eval(env1 or "{}")),
+                        text=True,
+                    )
+                )
+            with col2:
+                st.text(
+                    "Ghostscript version B: "
+                    + check_output(
+                        ["gs", "--version"],
+                        env=dict(os.environ, **eval(env2 or "{}")),
+                        text=True,
+                    )
+                )
+
+            doc1 = pymupdf.open(os.path.join(d, "output1.pdf"))
+            doc2 = pymupdf.open(os.path.join(d, "output2.pdf"))
+            for i, page1_2 in enumerate(zip(doc1, doc2)):
+                st.write(f"Page {i+1}")
+                page1, page2 = page1_2
+                col1, col2 = st.columns(2)
+                with col1, st.container(border=True):
+                    st.write(page1.get_text())
+                with col2, st.container(border=True):
+                    st.write(page2.get_text())
+
+            col1, col2 = st.columns(2)
+            with col1, st.expander("PDF Viewer"):
+                pdf_viewer(Path(d, "output1.pdf"))
+            with col2, st.expander("PDF Viewer"):
+                pdf_viewer(Path(d, "output2.pdf"))
+
+
+if __name__ == "__main__":
+    main()

misc/pdf_compare.py

@@ -0,0 +1,83 @@
+# SPDX-FileCopyrightText: 2025 James R. Barlow
+# SPDX-License-Identifier: MIT
+
+"""Compare two PDFs."""
+
+from __future__ import annotations
+
+import os
+from io import BytesIO
+from pathlib import Path
+from tempfile import TemporaryDirectory
+
+import pikepdf
+import pymupdf
+import streamlit as st
+from lxml import etree
+from streamlit_pdf_viewer import pdf_viewer
+
+
+def do_metadata(pdf):
+    with pikepdf.open(pdf) as pdf:
+        with pdf.open_metadata() as meta:
+            xml_txt = str(meta)
+            parser = etree.XMLParser(remove_blank_text=True)
+            tree = etree.fromstring(xml_txt, parser=parser)
+            st.code(
+                etree.tostring(tree, pretty_print=True).decode("utf-8"),
+                language="xml",
+            )
+        st.write(pdf.docinfo)
+        st.write("Number of pages:", len(pdf.pages))
+
+
+def main():
+    st.set_page_config(layout="wide")
+
+    st.title("PDF Compare")
+    st.write("Compare two PDFs.")
+
+    col1, col2 = st.columns(2)
+    with col1:
+        uploaded_pdf1 = st.file_uploader("Upload a PDF", type=["pdf"], key='pdf1')
+    with col2:
+        uploaded_pdf2 = st.file_uploader("Upload a PDF", type=["pdf"], key='pdf2')
+    if uploaded_pdf1 is None or uploaded_pdf2 is None:
+        return
+
+    pdf_bytes1 = uploaded_pdf1.getvalue()
+    pdf_bytes2 = uploaded_pdf2.getvalue()
+
+    with st.expander("PDF Metadata"):
+        col1, col2 = st.columns(2)
+        with col1:
+            do_metadata(BytesIO(pdf_bytes1))
+        with col2:
+            do_metadata(BytesIO(pdf_bytes2))
+
+    with TemporaryDirectory() as d:
+        Path(d, "1.pdf").write_bytes(pdf_bytes1)
+        Path(d, "2.pdf").write_bytes(pdf_bytes2)
+
+        with st.expander("Text"):
+            doc1 = pymupdf.open(os.path.join(d, "1.pdf"))
+            doc2 = pymupdf.open(os.path.join(d, "2.pdf"))
+            for i, page1_2 in enumerate(zip(doc1, doc2)):
+                st.write(f"Page {i+1}")
+                page1, page2 = page1_2
+                col1, col2 = st.columns(2)
+                with col1, st.container(border=True):
+                    st.write(page1.get_text())
+                with col2, st.container(border=True):
+                    st.write(page2.get_text())
+
+        with st.expander("PDF Viewer"):
+            col1, col2 = st.columns(2)
+            with col1:
+                pdf_viewer(Path(d, "1.pdf"), key='pdf_viewer1', render_text=True)
+            with col2:
+                pdf_viewer(Path(d, "2.pdf"), key='pdf_viewer2', render_text=True)
+
+
+if __name__ == "__main__":
+    main()

misc/pdf_text_diff.py

@@ -0,0 +1,46 @@
+# SPDX-FileCopyrightText: 2025 James R. Barlow
+# SPDX-License-Identifier: MPL-2.0
+
+"""Compare text in PDFs."""
+
+from __future__ import annotations
+
+from subprocess import run
+from tempfile import NamedTemporaryFile
+from typing import Annotated
+
+import typer
+
+
+def main(
+    pdf1: Annotated[typer.FileBinaryRead, typer.Argument()],
+    pdf2: Annotated[typer.FileBinaryRead, typer.Argument()],
+    engine: Annotated[str, typer.Option()] = 'pdftotext',
+):
+    """Compare text in PDFs."""
+
+    text1 = run(
+        ['pdftotext', '-layout', '-', '-'], stdin=pdf1, capture_output=True, check=True
+    )
+    text2 = run(
+        ['pdftotext', '-layout', '-', '-'], stdin=pdf2, capture_output=True, check=True
+    )
+
+    with NamedTemporaryFile() as f1, NamedTemporaryFile() as f2:
+        f1.write(text1.stdout)
+        f1.flush()
+        f2.write(text2.stdout)
+        f2.flush()
+        diff = run(
+            ['diff', '--color=always', '--side-by-side', f1.name, f2.name],
+            capture_output=True,
+        )
+        run(['less', '-R'], input=diff.stdout, check=True)
+        if text1.stdout.strip() != text2.stdout.strip():
+            return 1
+
+    return 0
+
+
+if __name__ == '__main__':
+    typer.run(main)

misc/screencast/README.md

@@ -0,0 +1,31 @@
+<!-- SPDX-License-Identifier: CC-BY-SA-4.0 -->
+
+To regenerate
+=============
+
+Using asciinema and svg-term (`npm install -g svg-term-cli`).
+
+Create `~/.config/asciinema/config` to disable prompt.
+
+```
+[record]
+
+command = fish --init-command 'alias fish_prompt="echo \>\ "'
+```
+
+Run asciinema
+
+```
+asciinema rec new_input.cast
+```
+
+Re-record faster version with fewer pauses
+
+```
+asciinema rec demo.cast -c "asciinema play new_input.cast --speed 2 --idle-time-limit 0.5"
+```
+
+Convert to SVG
+```
+svg-term --in=misc/screencast/demo.cast --out=misc/screencast/demo.svg --window
+```

misc/screencast/demo.cast

@@ -0,0 +1,65 @@
+{"version": 2, "width": 131, "height": 24, "timestamp": 1687247006, "env": {"SHELL": "/usr/bin/fish", "TERM": "xterm-256color"}}
+[0.103649, "o", "\u001b[?2004h\u001b]7; \u0007"]
+[0.104223, "o", "\u001b]0;fish  \u0007\u001b[30m\u001b(B\u001b[m\r> \u001b[K\r\u001b[C\u001b[C"]
+[0.604542, "o", "o\r\u001b[3C\b\u001b[38;2;255;0;0mo\r\u001b[3C\u001b[30m\u001b(B\u001b[m\u001b[38;2;85;85;85mcrmypdf multipage.pdf multipage_with_ocr.pdf\r\u001b[3C\u001b[30m\u001b(B\u001b[m"]
+[0.679571, "o", "\u001b[38;2;255;0;0mc\u001b[38;2;85;85;85mrmypdf multipage.pdf multipage_with_ocr.pdf\r\u001b[4C\u001b[30m\u001b(B\u001b[m"]
+[0.767271, "o", "\u001b[38;2;255;0;0mr\u001b[38;2;85;85;85mmypdf multipage.pdf multipage_with_ocr.pdf\r\u001b[5C\u001b[30m\u001b(B\u001b[m"]
+[0.814505, "o", "\u001b[38;2;255;0;0mm\u001b[38;2;85;85;85mypdf multipage.pdf multipage_with_ocr.pdf\r\u001b[6C\u001b[30m\u001b(B\u001b[m"]
+[0.938919, "o", "\u001b[38;2;255;0;0my\u001b[38;2;85;85;85mpdf multipage.pdf multipage_with_ocr.pdf\r\u001b[7C\u001b[30m\u001b(B\u001b[m"]
+[0.967347, "o", "\u001b[38;2;255;0;0mp\u001b[38;2;85;85;85mdf multipage.pdf multipage_with_ocr.pdf\r\u001b[8C\u001b[30m\u001b(B\u001b[m"]
+[1.009954, "o", "\u001b[38;2;255;0;0md\u001b[38;2;85;85;85mf multipage.pdf multipage_with_ocr.pdf\r\u001b[9C\u001b[30m\u001b(B\u001b[m"]
+[1.034488, "o", "\u001b[38;2;255;0;0mf\u001b[38;2;85;85;85m multipage.pdf multipage_with_ocr.pdf\r\u001b[10C\u001b[30m\u001b(B\u001b[m\b\b\b\b\b\b\b\b\u001b[38;2;0;95;215mocrmypdf\u001b[38;2;85;85;85m multipage.pdf multipage_with_ocr.pdf\r\u001b[10C\u001b[30m\u001b(B\u001b[m"]
+[1.069226, "o", "\u001b[38;2;0;95;215m \u001b[38;2;85;85;85mmultipage.pdf multipage_with_ocr.pdf\r\u001b[11C\u001b[30m\u001b(B\u001b[m\b \u001b[38;2;85;85;85mmultipage.pdf multipage_with_ocr.pdf\r\u001b[11C\u001b[30m\u001b(B\u001b[m"]
+[1.569682, "o", "-\u001b[K\r\u001b[12C\u001b[38;2;85;85;85m-version\r\u001b[12C\u001b[30m\u001b(B\u001b[m\b\u001b[38;2;0;175;255m-\u001b[38;2;85;85;85m-version\r\u001b[12C\u001b[30m\u001b(B\u001b[m"]
+[1.642096, "o", "\u001b[38;2;0;175;255m-\u001b[38;2;85;85;85mversion\r\u001b[13C\u001b[30m\u001b(B\u001b[m"]
+[1.71793, "o", "\u001b[38;2;0;175;255ms\u001b[30m\u001b(B\u001b[m\u001b[K\r\u001b[14C"]
+[1.771483, "o", "\u001b[38;2;0;175;255mk\r\u001b[15C\u001b[30m\u001b(B\u001b[m"]
+[1.864664, "o", "\u001b[38;2;0;175;255mi\r\u001b[16C\u001b[30m\u001b(B\u001b[m"]
+[1.876085, "o", "\u001b[38;2;0;175;255mp\r\u001b[17C\u001b[30m\u001b(B\u001b[m"]
+[2.092979, "o", "\u001b[38;2;0;175;255m-\r\u001b[18C\u001b[30m\u001b(B\u001b[m"]
+[2.138821, "o", "\u001b[38;2;0;175;255mt\r\u001b[19C\u001b[30m\u001b(B\u001b[m"]
+[2.18017, "o", "\u001b[38;2;0;175;255me\r\u001b[20C\u001b[30m\u001b(B\u001b[m"]
+[2.268222, "o", "\u001b[38;2;0;175;255mx\r\u001b[21C\u001b[30m\u001b(B\u001b[m"]
+[2.277031, "o", "\u001b[38;2;0;175;255mt\r\u001b[22C\u001b[30m\u001b(B\u001b[m"]
+[2.322469, "o", "\u001b[38;2;0;175;255m \r\u001b[23C\u001b[30m\u001b(B\u001b[m\b \r\u001b[23C"]
+[2.824696, "o", "m\r\u001b[24C\b\u001b[38;2;0;175;255m\u001b[4mm\r\u001b[24C\u001b[30m\u001b(B\u001b[m\u001b[38;2;85;85;85masks.pdf \r\u001b[24C\u001b[30m\u001b(B\u001b[m"]
+[2.923234, "o", "\u001b[38;2;0;175;255m\u001b[4mu\u001b[30m\u001b(B\u001b[m\u001b[K\r\u001b[25C\u001b[38;2;85;85;85mltipage.pdf \r\u001b[25C\u001b[30m\u001b(B\u001b[m"]
+[2.960685, "o", "\u001b[38;2;0;175;255m\u001b[4ml\u001b[38;2;85;85;85m\u001b[24mtipage.pdf \r\u001b[26C\u001b[30m\u001b(B\u001b[m"]
+[3.03365, "o", "\u001b[38;2;0;175;255m\u001b[4mt\u001b[38;2;85;85;85m\u001b[24mipage.pdf \r\u001b[27C\u001b[30m\u001b(B\u001b[m"]
+[3.479338, "o", "\u001b[38;2;0;175;255m\u001b[4mipage.pdf \r\u001b[37C\u001b[30m\u001b(B\u001b[m\b \r\u001b[37C"]
+[3.754818, "o", "m\r\u001b[38C\b\u001b[38;2;0;175;255m\u001b[4mm\r\u001b[38C\u001b[30m\u001b(B\u001b[m\u001b[38;2;85;85;85masks.pdf \r\u001b[38C\u001b[30m\u001b(B\u001b[m"]
+[3.873318, "o", "\u001b[38;2;0;175;255m\u001b[4mu\u001b[30m\u001b(B\u001b[m\u001b[K\r\u001b[39C\u001b[38;2;85;85;85mltipage.pdf \r\u001b[39C\u001b[30m\u001b(B\u001b[m"]
+[3.926829, "o", "\u001b[38;2;0;175;255m\u001b[4ml\u001b[38;2;85;85;85m\u001b[24mtipage.pdf \r\u001b[40C\u001b[30m\u001b(B\u001b[m"]
+[4.272251, "o", "\u001b[38;2;0;175;255m\u001b[4mtipage.pdf \r\u001b[51C\u001b[30m\u001b(B\u001b[m\b \r\u001b[51C"]
+[4.343464, "o", "\r\u001b[50C"]
+[4.416286, "o", "\r\u001b[49C"]
+[4.490574, "o", "\r\u001b[48C"]
+[4.564115, "o", "\r\u001b[47C"]
+[4.630398, "o", "\r\u001b[46C"]
+[4.76825, "o", "\u001b[38;2;0;175;255m\u001b[4m_.pd\u001b[30m\u001b(B\u001b[mf \r\u001b[47C\u001b[10D\u001b[38;2;0;175;255mmultipage_.pdf\u001b[30m\u001b(B\u001b[m \r\u001b[47C"]
+[5.012506, "o", "\u001b[38;2;0;175;255mo.pd\u001b[30m\u001b(B\u001b[mf \r\u001b[48C\u001b[3C\u001b[38;2;0;175;255mf\u001b[30m\u001b(B\u001b[m \r\u001b[48C"]
+[5.053615, "o", "\u001b[38;2;0;175;255mc.pd\u001b[30m\u001b(B\u001b[mf \r\u001b[49C\u001b[3C\u001b[38;2;0;175;255mf\u001b[30m\u001b(B\u001b[m \r\u001b[49C"]
+[5.103957, "o", "\u001b[38;2;0;175;255mr.pd\u001b[30m\u001b(B\u001b[mf \r\u001b[50C\u001b[3C\u001b[38;2;0;175;255mf\u001b[30m\u001b(B\u001b[m \r\u001b[50C"]
+[5.226183, "o", "\r\u001b[55C"]
+[5.728321, "o", "\r\n\u001b[30m\u001b(B\u001b[m\u001b[?2004l\u001b]0;ocrmypdf --skip-text multipage.pdf multipage_ocr.pdf  /home/jb/src/ocrmypdf/tests/resources\u0007\u001b[30m\u001b(B\u001b[m\r"]
+[5.801032, "o", "\rScanning contents:   0%|                                                                                   | 0/6 [00:00<?, ?page/s]"]
+[5.802664, "o", "\rScanning contents: 100%|█████████████████████████████████████████████████████████████████████████| 6/6 [00:00<00:00, 1270.68page/s]\r\n"]
+[5.802747, "o", "Start processing 6 pages concurrently\r\n"]
+[5.803488, "o", "\rOCR:   0%|                                                                                             | 0.0/6.0 [00:00<?, ?page/s]"]
+[5.804896, "o", "\r                                                                                                                                   \r    4 skipping all processing on this page\r\n\rOCR:   0%|                                                                                             | 0.0/6.0 [00:00<?, ?page/s]"]
+[5.896969, "o", "\rOCR:  25%|█████████████████████▎                                                               | 1.5/6.0 [00:00<00:00,  8.12page/s]"]
+[6.170021, "o", "\rOCR:  42%|███████████████████████████████████▍                                                 | 2.5/6.0 [00:00<00:01,  3.05page/s]"]
+[6.292338, "o", "\rOCR:  58%|█████████████████████████████████████████████████▌                                   | 3.5/6.0 [00:00<00:00,  3.39page/s]"]
+[6.586017, "o", "\rOCR:  75%|███████████████████████████████████████████████████████████████▊                     | 4.5/6.0 [00:01<00:00,  2.49page/s]"]
+[7.087058, "o", "\rOCR:  92%|█████████████████████████████████████████████████████████████████████████████▉       | 5.5/6.0 [00:06<00:00,  1.98s/page]\rOCR: 100%|█████████████████████████████████████████████████████████████████████████████████████| 6.0/6.0 [00:06<00:00,  1.09s/page]\r\nPostprocessing...\r\n"]
+[7.104927, "o", "\rPDF/A conversion:   0%|                                                                                    | 0/6 [00:00<?, ?page/s]"]
+[7.607392, "o", "\rPDF/A conversion:  50%|██████████████████████████████████████                                      | 3/6 [00:01<00:01,  1.61page/s]"]
+[7.653781, "o", "\rPDF/A conversion:  83%|███████████████████████████████████████████████████████████████▎            | 5/6 [00:01<00:00,  2.90page/s]"]
+[7.774532, "o", "\rPDF/A conversion: 100%|████████████████████████████████████████████████████████████████████████████| 6/6 [00:02<00:00,  2.71page/s]\r\n"]
+[7.778252, "o", "\u001b[33mSome input metadata could not be copied because it is not permitted in PDF/A. You may wish to examine the output PDF's XMP metadata.\u001b[0m\r\n"]
+[8.280789, "o", "\rRecompressing JPEGs: 0image [00:00, ?image/s]\rRecompressing JPEGs: 0image [00:00, ?image/s]\r\n\rDeflating JPEGs:   0%|                                                                                    | 0/4 [00:00<?, ?image/s]\rDeflating JPEGs: 100%|███████████████████████████████████████████████████████████████████████████| 4/4 [00:00<00:00, 238.28image/s]\r\n"]
+[8.28149, "o", "\rJBIG2: 0item [00:00, ?item/s]\rJBIG2: 0item [00:00, ?item/s]\r\n"]
+[8.289998, "o", "Image optimization ratio: 1.01 savings: 1.3%\r\nTotal file size ratio: 1.02 savings: 1.6%\r\n"]
+[8.291209, "o", "Output file is a PDF/A-2B (as expected)\r\n"]
+[8.361316, "o", "\u001b[2m⏎\u001b(B\u001b[m                                                                                                                                  \r⏎ \r\u001b[K\u001b[?2004h\u001b]0;fish /home/jb/src/ocrmypdf/tests/resources\u0007\u001b[30m\u001b(B\u001b[m> \u001b[K\r\u001b[C\u001b[C"]
+[8.862206, "o", "\r\n\u001b[30m\u001b(B\u001b[m\u001b[30m\u001b(B\u001b[m\u001b[?2004l"]

misc/synology.py

@@ -2,6 +2,8 @@
 # SPDX-FileCopyrightText: 2017 Enantiomerie
 # SPDX-License-Identifier: MIT
 
+"""Example OCRmyPDF for Synology NAS."""
+
 from __future__ import annotations
 
 # This script must be edited to meet your needs.
@@ -25,10 +27,7 @@ logging.basicConfig(
     filemode='w',
 )
 
-if len(sys.argv) > 1:
-    start_dir = sys.argv[1]
-else:
-    start_dir = '.'
+start_dir = sys.argv[1] if len(sys.argv) > 1 else '.'
 
 for dir_name, _subdirs, file_list in os.walk(start_dir):
     logging.info(dir_name)
@@ -54,9 +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

@@ -3,165 +3,334 @@
 # SPDX-FileCopyrightText: 2020 James R Barlow <https://github.com/jbarlow83>
 # SPDX-License-Identifier: MIT
 
-from __future__ import annotations
+"""Watch a directory for new PDFs and OCR them."""
+
+# Do not enable annotations!
+# https://github.com/tiangolo/typer/discussions/598
 
 import json
 import logging
-import os
 import shutil
 import sys
 import time
 from datetime import datetime
+from enum import Enum
 from pathlib import Path
+from typing import Annotated, Any
 
 import pikepdf
+import typer
+from dotenv import load_dotenv
 from watchdog.events import PatternMatchingEventHandler
 from watchdog.observers import Observer
 from watchdog.observers.polling import PollingObserver
 
 import ocrmypdf
 
+load_dotenv()
+
+
 # pylint: disable=logging-format-interpolation
-
-
-def getenv_bool(name: str, default: str = 'False'):
-    return os.getenv(name, default).lower() in ('true', 'yes', 'y', '1')
-
-
-INPUT_DIRECTORY = os.getenv('OCR_INPUT_DIRECTORY', '/input')
-OUTPUT_DIRECTORY = os.getenv('OCR_OUTPUT_DIRECTORY', '/output')
-ARCHIVE_DIRECTORY = os.getenv('OCR_ARCHIVE_DIRECTORY', '/processed')
-OUTPUT_DIRECTORY_YEAR_MONTH = getenv_bool('OCR_OUTPUT_DIRECTORY_YEAR_MONTH')
-ON_SUCCESS_DELETE = getenv_bool('OCR_ON_SUCCESS_DELETE')
-ON_SUCCESS_ARCHIVE = getenv_bool('OCR_ON_SUCCESS_ARCHIVE')
-DESKEW = getenv_bool('OCR_DESKEW')
-OCR_JSON_SETTINGS = json.loads(os.getenv('OCR_JSON_SETTINGS', '{}'))
-POLL_NEW_FILE_SECONDS = int(os.getenv('OCR_POLL_NEW_FILE_SECONDS', '1'))
-USE_POLLING = getenv_bool('OCR_USE_POLLING')
-LOGLEVEL = os.getenv('OCR_LOGLEVEL', 'INFO')
-PATTERNS = ['*.pdf', '*.PDF']
+app = typer.Typer(name="ocrmypdf-watcher")
 
 log = logging.getLogger('ocrmypdf-watcher')
 
 
-def get_output_dir(root, basename):
-    if OUTPUT_DIRECTORY_YEAR_MONTH:
+class LoggingLevelEnum(str, Enum):
+    """Enum for logging levels."""
+
+    DEBUG = "DEBUG"
+    INFO = "INFO"
+    WARNING = "WARNING"
+    ERROR = "ERROR"
+    CRITICAL = "CRITICAL"
+
+
+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 = (
-            Path(root) / str(today.year) / f'{today.month:02d}'
-        )
+        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 = Path(OUTPUT_DIRECTORY) / basename
+        output_path = root / Path(basename).with_suffix('.pdf')
     return output_path
 
 
-def wait_for_file_ready(file_path):
+def wait_for_file_ready(
+    file_path: Path, poll_new_file_seconds: int, retries_loading_file: int
+):
     # This loop waits to make sure that the file is completely loaded on
     # disk before attempting to read. Docker sometimes will publish the
     # watchdog event before the file is actually fully on disk, causing
     # pikepdf to fail.
 
-    retries = 5
-    while retries:
+    tries = retries_loading_file + 1
+    while tries:
         try:
-            pdf = pikepdf.open(file_path)
-        except (FileNotFoundError, pikepdf.PdfError) as e:
+            with pikepdf.Pdf.open(file_path) as pdf:
+                log.debug(f"{file_path} ready with {pdf.pages} pages")
+                return True
+        except (FileNotFoundError, OSError) as e:
             log.info(f"File {file_path} is not ready yet")
             log.debug("Exception was", exc_info=e)
-            time.sleep(POLL_NEW_FILE_SECONDS)
-            retries -= 1
-        else:
-            pdf.close()
-            return True
+            time.sleep(poll_new_file_seconds)
+            tries -= 1
+        except pikepdf.PdfError as e:
+            log.info(f"File {file_path} is not full written yet")
+            log.debug("Exception was", exc_info=e)
+            time.sleep(poll_new_file_seconds)
+            tries -= 1
 
     return False
 
 
-def execute_ocrmypdf(file_path):
-    file_path = Path(file_path)
-    output_path = get_output_dir(OUTPUT_DIRECTORY, file_path.name)
+def execute_ocrmypdf(
+    *,
+    file_path: Path,
+    archive_dir: Path,
+    output_dir: Path,
+    ocrmypdf_kwargs: dict[str, Any],
+    on_success_delete: bool,
+    on_success_archive: bool,
+    poll_new_file_seconds: int,
+    retries_loading_file: int,
+    output_dir_year_month: bool,
+):
+    output_path = get_output_path(output_dir, file_path.name, output_dir_year_month)
 
     log.info("-" * 20)
-    log.info(f'New file: {file_path}. Waiting until fully loaded...')
-    if not wait_for_file_ready(file_path):
+    log.info(f'New file: {file_path}. Waiting until fully written...')
+    if not wait_for_file_ready(file_path, poll_new_file_seconds, retries_loading_file):
         log.info(f"Gave up waiting for {file_path} to become ready")
         return
     log.info(f'Attempting to OCRmyPDF to: {output_path}')
+
+    log.debug(
+        f'OCRmyPDF input_file={file_path} output_file={output_path} '
+        f'kwargs: {ocrmypdf_kwargs}'
+    )
     exit_code = ocrmypdf.ocr(
         input_file=file_path,
         output_file=output_path,
-        deskew=DESKEW,
-        **OCR_JSON_SETTINGS,
+        **ocrmypdf_kwargs,
     )
     if exit_code == 0:
-        if ON_SUCCESS_DELETE:
+        if on_success_delete:
             log.info(f'OCR is done. Deleting: {file_path}')
             file_path.unlink()
-        elif ON_SUCCESS_ARCHIVE:
-            log.info(f'OCR is done. Archiving {file_path.name} to {ARCHIVE_DIRECTORY}')
-            shutil.move(file_path, f'{ARCHIVE_DIRECTORY}/{file_path.name}')
+        elif on_success_archive:
+            log.info(f'OCR is done. Archiving {file_path.name} to {archive_dir}')
+            shutil.move(file_path, f'{archive_dir}/{file_path.name}')
+        else:
+            log.info('OCR is done')
     else:
         log.info('OCR is done')
 
 
 class HandleObserverEvent(PatternMatchingEventHandler):
+    def __init__(  # noqa: D107
+        self,
+        patterns=None,
+        ignore_patterns=None,
+        ignore_directories=False,
+        case_sensitive=False,
+        settings={},
+    ):
+        super().__init__(
+            patterns=patterns,
+            ignore_patterns=ignore_patterns,
+            ignore_directories=ignore_directories,
+            case_sensitive=case_sensitive,
+        )
+        self._settings = settings
+
     def on_any_event(self, event):
         if event.event_type in ['created']:
-            execute_ocrmypdf(event.src_path)
+            execute_ocrmypdf(file_path=Path(event.src_path), **self._settings)
 
 
-def main():
+@app.command()
+def main(
+    input_dir: Annotated[
+        Path,
+        typer.Argument(
+            envvar='OCR_INPUT_DIRECTORY',
+            exists=True,
+            file_okay=False,
+            dir_okay=True,
+            readable=True,
+            resolve_path=True,
+        ),
+    ] = '/input',
+    output_dir: Annotated[
+        Path,
+        typer.Argument(
+            envvar='OCR_OUTPUT_DIRECTORY',
+            exists=True,
+            file_okay=False,
+            dir_okay=True,
+            writable=True,
+            resolve_path=True,
+        ),
+    ] = '/output',
+    archive_dir: Annotated[
+        Path,
+        typer.Argument(
+            envvar='OCR_ARCHIVE_DIRECTORY',
+            exists=True,
+            file_okay=False,
+            dir_okay=True,
+            writable=True,
+            resolve_path=True,
+        ),
+    ] = '/processed',
+    output_dir_year_month: Annotated[
+        bool,
+        typer.Option(
+            envvar='OCR_OUTPUT_DIRECTORY_YEAR_MONTH',
+            help='Create a subdirectory in the output directory for each year/month',
+        ),
+    ] = False,
+    on_success_delete: Annotated[
+        bool,
+        typer.Option(
+            envvar='OCR_ON_SUCCESS_DELETE',
+            help='Delete the input file after successful OCR',
+        ),
+    ] = False,
+    on_success_archive: Annotated[
+        bool,
+        typer.Option(
+            envvar='OCR_ON_SUCCESS_ARCHIVE',
+            help='Archive the input file after successful OCR',
+        ),
+    ] = False,
+    deskew: Annotated[
+        bool,
+        typer.Option(
+            envvar='OCR_DESKEW',
+            help='Deskew the input file before OCR',
+        ),
+    ] = False,
+    ocr_json_settings: Annotated[
+        str,
+        typer.Option(
+            envvar='OCR_JSON_SETTINGS',
+            help='JSON settings to pass to OCRmyPDF (JSON string or file path)',
+        ),
+    ] = None,
+    poll_new_file_seconds: Annotated[
+        int,
+        typer.Option(
+            envvar='OCR_POLL_NEW_FILE_SECONDS',
+            help='Seconds to wait before polling a new file',
+            min=0,
+        ),
+    ] = 1,
+    use_polling: Annotated[
+        bool,
+        typer.Option(
+            envvar='OCR_USE_POLLING',
+            help='Use polling instead of filesystem events',
+        ),
+    ] = False,
+    retries_loading_file: Annotated[
+        int,
+        typer.Option(
+            envvar='OCR_RETRIES_LOADING_FILE',
+            help='Number of times to retry loading a file before giving up',
+            min=0,
+        ),
+    ] = 5,
+    loglevel: Annotated[
+        LoggingLevelEnum,
+        typer.Option(
+            envvar='OCR_LOGLEVEL',
+            help='Logging level',
+        ),
+    ] = LoggingLevelEnum.INFO,
+    patterns: Annotated[
+        str,
+        typer.Option(
+            envvar='OCR_PATTERNS',
+            help='File patterns to watch',
+        ),
+    ] = '*.pdf,*.PDF',
+):
     ocrmypdf.configure_logging(
         verbosity=(
             ocrmypdf.Verbosity.default
-            if LOGLEVEL != 'DEBUG'
+            if loglevel != LoggingLevelEnum.DEBUG
             else ocrmypdf.Verbosity.debug
         ),
         manage_root_logger=True,
     )
-    log.setLevel(LOGLEVEL)
+    log.setLevel(loglevel.value)
     log.info(
         f"Starting OCRmyPDF watcher with config:\n"
-        f"Input Directory: {INPUT_DIRECTORY}\n"
-        f"Output Directory: {OUTPUT_DIRECTORY}\n"
-        f"Output Directory Year & Month: {OUTPUT_DIRECTORY_YEAR_MONTH}\n"
-        f"Archive Directory: {ARCHIVE_DIRECTORY}"
+        f"Input Directory: {input_dir}\n"
+        f"Output Directory: {output_dir}\n"
+        f"Output Directory Year & Month: {output_dir_year_month}\n"
+        f"Archive Directory: {archive_dir}"
     )
     log.debug(
-        f"INPUT_DIRECTORY: {INPUT_DIRECTORY}\n"
-        f"OUTPUT_DIRECTORY: {OUTPUT_DIRECTORY}\n"
-        f"OUTPUT_DIRECTORY_YEAR_MONTH: {OUTPUT_DIRECTORY_YEAR_MONTH}\n"
-        f"ARCHIVE_DIRECTORY: {ARCHIVE_DIRECTORY}\n"
-        f"ON_SUCCESS_DELETE: {ON_SUCCESS_DELETE}\n"
-        f"ON_SUCCESS_ARCHIVE: {ON_SUCCESS_ARCHIVE}\n"
-        f"DESKEW: {DESKEW}\n"
-        f"ARGS: {OCR_JSON_SETTINGS}\n"
-        f"POLL_NEW_FILE_SECONDS: {POLL_NEW_FILE_SECONDS}\n"
-        f"USE_POLLING: {USE_POLLING}\n"
-        f"LOGLEVEL: {LOGLEVEL}"
+        f"INPUT_DIRECTORY: {input_dir}\n"
+        f"OUTPUT_DIRECTORY: {output_dir}\n"
+        f"OUTPUT_DIRECTORY_YEAR_MONTH: {output_dir_year_month}\n"
+        f"ARCHIVE_DIRECTORY: {archive_dir}\n"
+        f"ON_SUCCESS_DELETE: {on_success_delete}\n"
+        f"ON_SUCCESS_ARCHIVE: {on_success_archive}\n"
+        f"DESKEW: {deskew}\n"
+        f"ARGS: {ocr_json_settings}\n"
+        f"POLL_NEW_FILE_SECONDS: {poll_new_file_seconds}\n"
+        f"RETRIES_LOADING_FILE: {retries_loading_file}\n"
+        f"USE_POLLING: {use_polling}\n"
+        f"LOGLEVEL: {loglevel.value}"
     )
 
-    if 'input_file' in OCR_JSON_SETTINGS or 'output_file' in OCR_JSON_SETTINGS:
-        log.error('OCR_JSON_SETTINGS should not specify input file or output file')
+    if ocr_json_settings and Path(ocr_json_settings).exists():
+        json_settings = json.loads(Path(ocr_json_settings).read_text())
+    else:
+        json_settings = json.loads(ocr_json_settings or '{}')
+
+    if 'input_file' in json_settings or 'output_file' in json_settings:
+        log.error(
+            'OCR_JSON_SETTINGS (--ocr-json-settings) may not specify input/output file'
+        )
         sys.exit(1)
 
-    handler = HandleObserverEvent(patterns=PATTERNS)
-    if USE_POLLING:
+    handler = HandleObserverEvent(
+        patterns=patterns.split(','),
+        settings={
+            'archive_dir': archive_dir,
+            'output_dir': output_dir,
+            'ocrmypdf_kwargs': json_settings | {'deskew': deskew},
+            'on_success_delete': on_success_delete,
+            'on_success_archive': on_success_archive,
+            'poll_new_file_seconds': poll_new_file_seconds,
+            'retries_loading_file': retries_loading_file,
+            'output_dir_year_month': output_dir_year_month,
+        },
+    )
+    if use_polling:
         observer = PollingObserver()
     else:
         observer = Observer()
-    observer.schedule(handler, INPUT_DIRECTORY, recursive=True)
+    observer.schedule(handler, input_dir, recursive=True)
     observer.start()
+    typer.echo(f"Watching {input_dir} for new PDFs. Press Ctrl+C to exit.")
     try:
         while True:
-            time.sleep(1)
+            time.sleep(30)
     except KeyboardInterrupt:
         observer.stop()
     observer.join()
 
 
 if __name__ == "__main__":
-    main()
+    app()

misc/webservice.py

@@ -1,107 +1,29 @@
-#!/usr/bin/env python3
-# SPDX-FileCopyrightText: 2019 James R. Barlow
+#!/usr/bin/env python
+# SPDX-FileCopyrightText: 2025 James R. Barlow
 # SPDX-License-Identifier: AGPL-3.0-or-later
 
-"""This is a simple web service/HTTP wrapper for OCRmyPDF
-
-This may be more convenient than the command line tool for some Docker users.
-Note that OCRmyPDF uses Ghostscript, which is licensed under AGPLv3+. While
-OCRmyPDF is under GPLv3, this file is distributed under the Affero GPLv3+ license,
-to emphasize that SaaS deployments should make sure they comply with
-Ghostscript's license as well as OCRmyPDF's.
-"""
-
-from __future__ import annotations
+"""Run the OCRmyPDF web service."""
 
 import os
-import shlex
-from subprocess import PIPE, run
-from tempfile import TemporaryDirectory
+import sys
 
-from flask import Flask, Response, request, send_from_directory
-from werkzeug.utils import secure_filename
+try:
+    import streamlit  # noqa: F401
+except ImportError:
+    raise ImportError(
+        'You need to install streamlit in the Python environment '
+        'to run the web service.\n'
+    )
 
-app = Flask(__name__)
-app.secret_key = "secret"
-app.config['MAX_CONTENT_LENGTH'] = 50_000_000
-app.config.from_envvar("OCRMYPDF_WEBSERVICE_SETTINGS", silent=True)
-
-ALLOWED_EXTENSIONS = {"pdf"}
-
-
-def allowed_file(filename):
-    return "." in filename and filename.rsplit(".", 1)[1].lower() in ALLOWED_EXTENSIONS
-
-
-def do_ocrmypdf(file):
-    uploaddir = TemporaryDirectory(prefix="ocrmypdf-upload")
-    downloaddir = TemporaryDirectory(prefix="ocrmypdf-download")
-
-    filename = secure_filename(file.filename)
-    up_file = os.path.join(uploaddir.name, filename)
-    file.save(up_file)
-
-    down_file = os.path.join(downloaddir.name, filename)
-
-    cmd_args = [arg for arg in shlex.split(request.form["params"])]
-    if "--sidecar" in cmd_args:
-        return Response("--sidecar not supported", 501, mimetype='text/plain')
-
-    ocrmypdf_args = ["ocrmypdf", *cmd_args, up_file, down_file]
-    proc = run(ocrmypdf_args, capture_output=True, encoding="utf-8")
-    if proc.returncode != 0:
-        stderr = proc.stderr
-        return Response(stderr, 400, mimetype='text/plain')
-
-    return send_from_directory(downloaddir.name, filename)
-
-
-@app.route("/", methods=["GET", "POST"])
-def upload_file():
-    if request.method == "POST":
-        if "file" not in request.files:
-            return Response("No file in POST", 400, mimetype='text/plain')
-        file = request.files["file"]
-        if file.filename == "":
-            return Response("Empty filename", 400, mimetype='text/plain')
-        if not allowed_file(file.filename):
-            return Response("Invalid filename", 400, mimetype='text/plain')
-        if file and allowed_file(file.filename):
-            return do_ocrmypdf(file)
-        return Response("Some other problem", 400, mimetype='text/plain')
-
-    return """
-    <!doctype html>
-    <title>OCRmyPDF webservice</title>
-    <h1>Upload a PDF (debug UI)</h1>
-    <form method=post enctype=multipart/form-data>
-      <label for="args">Command line parameters</label>
-      <input type=textbox name=params>
-      <label for="file">File to upload</label>
-      <input type=file name=file>
-      <input type=submit value=Upload>
-    </form>
-    <h4>Notice</h2>
-    <div style="font-size: 70%; max-width: 34em;">
-    <p>This is a webservice wrapper for OCRmyPDF.</p>
-    <p>Copyright 2019 James R. Barlow</p>
-    <p>This program is free software: you can redistribute it and/or modify
-    it under the terms of the GNU Affero General Public License as published by
-    the Free Software Foundation, either version 3 of the License, or
-    (at your option) any later version.
-    </p>
-    <p>This program is distributed in the hope that it will be useful,
-    but WITHOUT ANY WARRANTY; without even the implied warranty of
-    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-    GNU General Public License for more details.
-    </p>
-    <p>
-    You should have received a copy of the GNU Affero General Public License
-    along with this program.  If not, see &lt;http://www.gnu.org/licenses/&gt;.
-    </p>
-    </div>
-    """
-
-
-if __name__ == "__main__":
-    app.run(host='0.0.0.0', port=5000)
+if __name__ == '__main__':
+    os.execvp(
+        sys.executable,
+        [
+            sys.executable,
+            '-m',
+            'streamlit',
+            'run',
+            'misc/_webservice.py',
+            *sys.argv[1:],
+        ],
+    )

pyproject.toml

@@ -1,40 +1,87 @@
+# SPDX-FileCopyrightText: 2022 James R. Barlow
+# SPDX-License-Identifier: MPL-2.0
 [build-system]
-requires = [
-  "setuptools >= 52",
-  "setuptools_scm[toml] >= 7.0.5",
-  "wheel"
+requires = ["hatchling", "hatch-vcs"]
+build-backend = "hatchling.build"
+
+[project]
+name = "ocrmypdf"
+dynamic = ["version"]
+description = "OCRmyPDF adds an OCR text layer to scanned PDF files, allowing them to be searched"
+readme = "README.md"
+license = { text = "MPL-2.0" }
+requires-python = ">=3.10"
+dependencies = [
+  "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",
 ]
-build-backend = "setuptools.build_meta"
+authors = [{ name = "James R. Barlow", email = "james@purplerock.ca" }]
+classifiers = [
+  "Development Status :: 5 - Production/Stable",
+  "Environment :: Console",
+  "Intended Audience :: End Users/Desktop",
+  "Intended Audience :: Science/Research",
+  "Intended Audience :: System Administrators",
+  "License :: OSI Approved :: Mozilla Public License 2.0 (MPL 2.0)",
+  "Operating System :: MacOS",
+  "Operating System :: Microsoft :: Windows",
+  "Operating System :: POSIX",
+  "Operating System :: POSIX :: BSD",
+  "Operating System :: POSIX :: Linux",
+  "Programming Language :: Python :: 3",
+  "Topic :: Scientific/Engineering :: Image Recognition",
+  "Topic :: Text Processing :: Indexing",
+  "Topic :: Text Processing :: Linguistic",
+]
+keywords = ["PDF", "OCR", "optical character recognition", "PDF/A", "scanning"]
 
-[tool.setuptools_scm]
+[project.urls]
+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"
 
-[tool.black]
-line-length = 88
-target-version = ["py37", "py38"]
-skip-string-normalization = true
-include = '\.pyi?$'
-exclude = '''
-/(
-    \.eggs
-  | \.git
-  | \.hg
-  | \.mypy_cache
-  | \.tox
-  | \.venv
-  | _build
-  | buck-out
-  | build
-  | dist
-  | docs
-  | misc
-  | \.egg-info
-)/
-'''
+[project.optional-dependencies]
+docs = ["sphinx", "sphinx-issues", "sphinx-rtd-theme"]
+extended_test = ["PyMuPDF>=1.19.1"]
+test = [
+  "coverage[toml]>=6.2",
+  "hypothesis>=6.36.0",
+  "pytest>=6.2.5",
+  "pytest-cov>=3.0.0",
+  "pytest-xdist>=2.5.0",
+  "python-xmp-toolkit==2.0.1", # also requires apt-get install libexempi3
+  "reportlab>=3.6.8",
+  "types-Pillow",
+  "types-humanfriendly",
+]
+watcher = ["watchdog>=1.0.2", "typer-slim[standard]", "python-dotenv"]
+webservice = ["streamlit>=1.41.0"]
+
+[project.scripts]
+ocrmypdf = "ocrmypdf.__main__:run"
+
+[tool.hatch.version]
+source = "vcs"
+
+[tool.hatch.build.hooks.vcs]
+version-file = "src/ocrmypdf/_version.py"
+
+[tool.distutils.bdist_wheel]
+python-tag = "py310"
 
 [tool.coverage.run]
 branch = true
 parallel = true
-concurrency = ["multiprocessing"]
+concurrency = ["multiprocessing", "thread"]
+sigterm = true
 
 [tool.coverage.paths]
 source = ["src/ocrmypdf"]
@@ -51,28 +98,7 @@ exclude_lines = [
   "if 0:",
   "if False:",
   "if __name__ == .__main__.:",
-  "if TYPE_CHECKING:"
-]
-
-[tool.isort]
-profile = "black"
-known_first_party = "ocrmypdf"
-known_third_party = [
-  "PIL",
-  "flask",
-  "img2pdf",
-  "ocrmypdf",
-  "pdfminer",
-  "pikepdf",
-  "pkg_resources",
-  "pluggy",
-  "pytest",
-  "reportlab",
-  "setuptools",
-  "sphinx_rtd_theme",
-  "tqdm",
-  "watchdog",
-  "werkzeug"
+  "if TYPE_CHECKING:",
 ]
 
 [tool.pytest.ini_options]
@@ -81,25 +107,58 @@ 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.*',
   'fitz',
   'libxmp.utils',
-  'importlib_metadata'
 ]
 ignore_missing_imports = true
 
-[tool.pylint.basic]
-good-names = ["i", "j", "k", "ex", "Run", "_", "e", "p", "im", "w", "h", "m", "x", "y", "a", "b", "fp", "n", "f", "s", "v", "q", "dx", "dy"]
-logging-format-style = "old"
-disable = ["raw-checker-failed", "bad-inline-option", "locally-disabled", "file-ignored", "suppressed-message", "useless-suppression", "deprecated-pragma", "use-symbolic-message-instead", "logging-fstring-interpolation", "missing-function-docstring", "too-few-public-methods"]
+[tool.ruff]
+target-version = "py310"
+
+[tool.ruff.lint]
+"select" = [
+  "D",    # pydocstyle
+  "E",    # pycodestyle
+  "W",    # pycodestyle
+  "F",    # pyflakes
+  "I001", # isort
+  "UP",   # pyupgrade
+]
+
+[tool.ruff.lint.isort]
+known-first-party = ["ocrmypdf"]
+
+[tool.ruff.lint.pydocstyle]
+convention = "google"
+
+[tool.ruff.lint.per-file-ignores]
+"docs/conf.py" = ["D100", "D101", "D105"]
+"tests/*.py" = ["D100", "D101", "D102", "D103", "D105"]
+"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",
+  "ipykernel>=6.29.5",
+]

setup.cfg

@@ -1,116 +0,0 @@
-[metadata]
-name = ocrmypdf
-description = OCRmyPDF adds an OCR text layer to scanned PDF files, allowing them to be searched
-long_description = file: README.md
-long_description_content_type = text/markdown
-url = https://github.com/ocrmypdf/OCRmyPDF
-author = James R. Barlow
-author_email = james@purplerock.ca
-license = MPL-2.0
-license_file = LICENSE
-license_files =
-    LICENSE
-classifiers =
-    Development Status :: 5 - Production/Stable
-    Environment :: Console
-    Intended Audience :: End Users/Desktop
-    Intended Audience :: Science/Research
-    Intended Audience :: System Administrators
-    License :: OSI Approved :: Mozilla Public License 2.0 (MPL 2.0)
-    Operating System :: MacOS :: MacOS X
-    Operating System :: Microsoft :: Windows :: Windows 10
-    Operating System :: POSIX
-    Operating System :: POSIX :: BSD
-    Operating System :: POSIX :: Linux
-    Programming Language :: Python :: 3
-    Programming Language :: Python :: 3 :: Only
-    Programming Language :: Python :: 3.7
-    Programming Language :: Python :: 3.8
-    Programming Language :: Python :: 3.9
-    Programming Language :: Python :: 3.10
-    Topic :: Scientific/Engineering :: Image Recognition
-    Topic :: Text Processing :: Indexing
-    Topic :: Text Processing :: Linguistic
-keywords =
-    PDF
-    OCR
-    optical character recognition
-    PDF/A
-    scanning
-project_urls =
-    Documentation = https://ocrmypdf.readthedocs.io/
-    Source = https://github.com/ocrmypdf/OCRmyPDF
-    Tracker = https://github.com/ocrmypdf/OCRmyPDF/issues
-
-[options]
-packages = find:
-install_requires =
-    Pillow>=8.2.0
-    coloredlogs>=14.0  # strictly optional
-    img2pdf>=0.3.0  # pure Python
-    packaging>=20
-    pdfminer.six!=20200720,>=20191110
-    pikepdf!=5.0.0,>=4.0.0
-    pluggy>=0.13.0
-    reportlab>=3.5.66
-    tqdm>=4
-    importlib-metadata>=4;python_version<'3.8'  # until Python 3.8
-    importlib-resources>=5;python_version<'3.9'  # until Python 3.9
-    typing-extensions>=4;python_version<'3.10'
-python_requires = >=3.7
-include_package_data = True
-package_dir =
-    =src
-platforms = any
-setup_requires =
-    setuptools-scm
-    setuptools-scm-git-archive
-zip_safe = False
-
-[options.packages.find]
-where = src
-
-[options.entry_points]
-console_scripts =
-    ocrmypdf = ocrmypdf.__main__:run
-
-[options.extras_require]
-docs =
-    sphinx
-    sphinx-issues
-    sphinx-rtd-theme
-extended_test =
-    PyMuPDF==1.19.1
-test =
-    coverage[toml]>=5
-    pytest>=6.0.0
-    pytest-cov>=2.11.1
-    pytest-xdist>=2.2.0
-    python-xmp-toolkit==2.0.1  # also requires apt-get install libexempi3
-    types-Pillow
-    types-humanfriendly
-watcher =
-    watchdog>=1.0.2
-webservice =
-    Flask>=1
-
-[options.package_data]
-ocrmypdf =
-    data/sRGB.icc
-    py.typed
-
-[bdist_wheel]
-python-tag = py37
-
-[aliases]
-test = pytest
-
-[check-manifest]
-ignore =
-    .github
-
-[flake8]
-ignore = D203,F401,W503,E501,E203,F841
-exclude = .git,__pycache__,docs/conf.py,build,dist,.venv,.venvpp,.eggs,tmp,src/ocrmypdf/lib/
-max-complexity = 10
-max-line-length = 100

setup.py

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

snapcraft.yaml

@@ -1,8 +1,13 @@
+# SPDX-FileCopyrightText: 2022 Alexander Langanke
+# SPDX-FileCopyrightText: 2022 James R. Barlow
+# SPDX-FileCopyrightText: 2023 林博仁(Buo-ren, Lin) <Buo.Ren.Lin@gmail.com>
+# SPDX-License-Identifier: MPL-2.0
+
 name: ocrmypdf
 title: OCRmyPDF
-base: core20
+base: core22
 version: git
-summary: OCRmyPDF adds optical character recognition (OCR) to PDFs
+summary: OCRmyPDF adds a searchable text layer to scanned PDF files
 description: OCRmyPDF packaged for snap
 grade: stable
 confinement: strict
@@ -13,8 +18,8 @@ architectures: [amd64]
 
 environment:
   TESSDATA_PREFIX: $SNAP/usr/share/tesseract-ocr/4.00/tessdata
-  GS_LIB: $SNAP/usr/share/ghostscript/9.50/Resource/Init
-  GS_FONTPATH: $SNAP/usr/share/ghostscript/9.50/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:
@@ -41,9 +46,19 @@ parts:
     stage-packages:
       - lib32stdc++6
 
+  jbig2enc:
+    plugin: autotools
+    source: https://github.com/agl/jbig2enc.git
+    source-tag: "0.29"
+    build-packages:
+      - libleptonica-dev
+
   ocrmypdf:
     plugin: python
-    source: https://github.com/ocrmypdf/OCRmyPDF.git
+    source: .
+
+    build-packages:
+      - python3-pip
 
     stage-packages:
       - ghostscript
@@ -66,7 +81,14 @@ parts:
       - setuptools
       - tqdm
       - pipe
+      - wheel
 
     override-build: |
+      pip3 install --user dephell[full]
+      $HOME/.local/bin/dephell deps convert \
+          --from-path pyproject.toml \
+          --from-format pyproject \
+          --to-path setup.py \
+          --to-format setuppy
       snapcraftctl build
       ln -sf ../usr/lib/libsnapcraft-preload.so $SNAPCRAFT_PART_INSTALL/lib/libsnapcraft-preload.so

src/ocrmypdf/RELEASE.md

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

src/ocrmypdf/__init__.py

@@ -9,9 +9,17 @@ from pluggy import HookimplMarker as _HookimplMarker
 
 from ocrmypdf import helpers, hocrtransform, pdfa, pdfinfo
 from ocrmypdf._concurrent import Executor
+from ocrmypdf._defaults import PROGRAM_NAME
 from ocrmypdf._jobcontext import PageContext, PdfContext
-from ocrmypdf._version import PROGRAM_NAME, __version__
-from ocrmypdf.api import Verbosity, configure_logging, ocr
+from ocrmypdf._pipelines._common import (
+    configure_debug_logging,
+)
+from ocrmypdf._version import __version__
+from ocrmypdf.api import (
+    Verbosity,
+    configure_logging,
+    ocr,
+)
 from ocrmypdf.exceptions import (
     BadArgsError,
     DpiError,
@@ -21,7 +29,6 @@ from ocrmypdf.exceptions import (
     InputFileError,
     MissingDependencyError,
     OutputFileAccessError,
-    PdfMergeFailedError,
     PriorOcrFoundError,
     SubprocessOutputError,
     TesseractConfigError,
@@ -30,3 +37,34 @@ from ocrmypdf.exceptions import (
 from ocrmypdf.pluginspec import OcrEngine, OrientationConfidence
 
 hookimpl = _HookimplMarker('ocrmypdf')
+
+__all__ = [
+    '__version__',
+    'BadArgsError',
+    'configure_debug_logging',
+    'configure_logging',
+    'DpiError',
+    'EncryptedPdfError',
+    'Executor',
+    'ExitCode',
+    'ExitCodeException',
+    'helpers',
+    'hocrtransform',
+    'hookimpl',
+    'InputFileError',
+    'MissingDependencyError',
+    'ocr',
+    'OcrEngine',
+    'OrientationConfidence',
+    'OutputFileAccessError',
+    'PageContext',
+    'pdfa',
+    'PdfContext',
+    'pdfinfo',
+    'PriorOcrFoundError',
+    'PROGRAM_NAME',
+    'SubprocessOutputError',
+    'TesseractConfigError',
+    'UnsupportedImageFormatError',
+    'Verbosity',
+]

src/ocrmypdf/__main__.py

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

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

@@ -7,27 +7,20 @@ from __future__ import annotations
 
 import threading
 from abc import ABC, abstractmethod
-from typing import Callable, Iterable
+from collections.abc import Callable, Iterable
+from typing import Any, TypeVar
+
+from ocrmypdf._progressbar import NullProgressBar, ProgressBar
+
+T = TypeVar('T')
 
 
 def _task_noop(*_args, **_kwargs):
     return
 
 
-class NullProgressBar:
-    """Progress bar API that takes no actions."""
-
-    def __init__(self, **kwargs):
-        pass
-
-    def __enter__(self):
-        return self
-
-    def __exit__(self, exc_type, exc_value, traceback):
-        return False
-
-    def update(self, _arg=None):
-        return
+def _task_finished_noop(_result: Any, pbar: ProgressBar):
+    pbar.update()
 
 
 class Executor(ABC):
@@ -45,14 +38,13 @@ class Executor(ABC):
         *,
         use_threads: bool,
         max_workers: int,
-        tqdm_kwargs: dict,
+        progress_kwargs: dict,
         worker_initializer: Callable | None = None,
-        task: Callable | None = None,
+        task: Callable[..., T] | None = None,
         task_arguments: Iterable | None = None,
-        task_finished: Callable | None = None,
+        task_finished: Callable[[T, ProgressBar], None] | None = None,
     ) -> None:
-        """
-        Set up parallel execution and progress reporting.
+        """Set up parallel execution and progress reporting.
 
         Args:
             use_threads: If ``False``, the workload is the sort that will benefit from
@@ -60,7 +52,7 @@ class Executor(ABC):
                 heavily, and parallelizing it with threads is not expected to be
                 performant).
             max_workers: The maximum number of workers that should be run.
-            tdqm_kwargs: Arguments to set up the progress bar.
+            progress_kwargs: Arguments to set up the progress bar.
             worker_initializer: Called when a worker is initialized, in the worker's
                 execution context. If the child workers are processes, it must be
                 possible to marshall/pickle the worker initializer.
@@ -73,13 +65,12 @@ class Executor(ABC):
                 task. This runs in the parent's context, but the parameters must be
                 marshallable to the worker.
         """
-
         if not task_arguments:
             return  # Nothing to do!
         if not worker_initializer:
             worker_initializer = _task_noop
         if not task_finished:
-            task_finished = _task_noop
+            task_finished = _task_finished_noop
         if not task:
             task = _task_noop
 
@@ -87,7 +78,7 @@ class Executor(ABC):
             self._execute(
                 use_threads=use_threads,
                 max_workers=max_workers,
-                tqdm_kwargs=tqdm_kwargs,
+                progress_kwargs=progress_kwargs,
                 worker_initializer=worker_initializer,
                 task=task,
                 task_arguments=task_arguments,
@@ -100,7 +91,7 @@ class Executor(ABC):
         *,
         use_threads: bool,
         max_workers: int,
-        tqdm_kwargs: dict,
+        progress_kwargs: dict,
         worker_initializer: Callable,
         task: Callable,
         task_arguments: Iterable,
@@ -126,13 +117,13 @@ class SerialExecutor(Executor):
         *,
         use_threads: bool,
         max_workers: int,
-        tqdm_kwargs: dict,
+        progress_kwargs: dict,
         worker_initializer: Callable,
         task: Callable,
         task_arguments: Iterable,
         task_finished: Callable,
     ):  # pylint: disable=unused-argument
-        with self.pbar_class(**tqdm_kwargs) as pbar:
+        with self.pbar_class(**progress_kwargs) as pbar:
             for args in task_arguments:
-                result = task(args)
+                result = task(*args)
                 task_finished(result, pbar)

src/ocrmypdf/_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/__init__.py

@@ -1,6 +1,6 @@
 # SPDX-FileCopyrightText: 2022 James R. Barlow
 # SPDX-License-Identifier: MPL-2.0
 
-"""Manage third party executables"""
+"""Manage third party executables."""
 
 from __future__ import annotations

src/ocrmypdf/_exec/ghostscript.py

@@ -1,65 +1,79 @@
 # SPDX-FileCopyrightText: 2022 James R. Barlow
 # SPDX-License-Identifier: MPL-2.0
 
-"""Interface to Ghostscript executable"""
+"""Interface to Ghostscript executable."""
 
 from __future__ import annotations
 
 import logging
 import os
 import re
-import sys
+from collections import deque
 from io import BytesIO
 from os import fspath
 from pathlib import Path
 from subprocess import PIPE, CalledProcessError
 
+from packaging.version import Version
 from PIL import Image, UnidentifiedImageError
 
-from ocrmypdf.exceptions import SubprocessOutputError
+from ocrmypdf.exceptions import (
+    ColorConversionNeededError,
+    InputFileError,
+    SubprocessOutputError,
+)
 from ocrmypdf.helpers import Resolution
 from ocrmypdf.subprocess import get_version, run, run_polling_stderr
 
-# Remove this workaround when we require Pillow >= 10
-try:
-    Transpose = Image.Transpose  # type: ignore
-except AttributeError:
-    # Pillow 9 shim
-    Transpose = Image  # type: ignore
+COLOR_CONVERSION_STRATEGIES = frozenset(
+    [
+        'CMYK',
+        'Gray',
+        'LeaveColorUnchanged',
+        'RGB',
+        'UseDeviceIndependentColor',
+    ]
+)
+# Ghostscript executable - gswin32c is not supported
+GS = 'gswin64c' if os.name == 'nt' else 'gs'
+
 
 log = logging.getLogger(__name__)
 
-# Most reliable what to get the bitness of Python interpreter, according to Python docs
-_IS_64BIT = sys.maxsize > 2**32
 
-_GSWIN = None
-if os.name == 'nt':
-    if _IS_64BIT:
-        _GSWIN = 'gswin64c'
-    else:
-        _GSWIN = 'gswin32c'
+class DuplicateFilter(logging.Filter):
+    """Filter out duplicate log messages.
 
-GS = _GSWIN if _GSWIN else 'gs'
-del _GSWIN
-
-
-def version():
-    return get_version(GS)
-
-
-def jpeg_passthrough_available() -> bool:
-    """Returns True if the installed version of Ghostscript supports JPEG passthru
-
-    Prior to 9.23, Ghostscript decoded and re-encoded JPEGs internally. In 9.23
-    it gained the ability to keep JPEGs unmodified. However, the 9.23
-    implementation was buggy and would deletes the last two bytes of images in
-    some cases, as reported here.
-    https://bugs.ghostscript.com/show_bug.cgi?id=699216
-
-    The issue was fixed for 9.24, hence that is the first version we consider
-    the feature available. (Ghostscript 9.24 has its own problems is blacklisted.)
+    A context window of default 5 messages is used to determine if a message is a
+    duplicate. This is because some Ghostscript messages are word wrapped.
     """
-    return version() >= '9.24'
+
+    def __init__(self, logger: logging.Logger, context_window=5):
+        self.window: deque[str] = deque([], maxlen=context_window)
+        self.logger = logger
+        self.levelno = logging.DEBUG
+        self.count = 0
+
+    def filter(self, record):
+        if record.msg in self.window:
+            self.count += 1
+            self.levelno = record.levelno
+            return False
+        else:
+            if self.count >= 1:
+                rep_msg = f"(suppressed {self.count} repeated lines)"
+                self.count = 0  # Avoid infinite recursion
+                self.logger.log(self.levelno, rep_msg)
+                self.window.clear()
+            self.window.append(record.msg)
+            return True
+
+
+log.addFilter(DuplicateFilter(log))
+
+
+def version() -> Version:
+    return Version(get_version(GS))
 
 
 def _gs_error_reported(stream) -> bool:
@@ -67,6 +81,20 @@ def _gs_error_reported(stream) -> bool:
     return bool(match)
 
 
+def _gs_devicen_reported(stream) -> bool:
+    """Did Ghostscript warn about a DeviceN with inappropriate alternate?
+
+    If so, we need the user to select a color conversion, or the resulting PDF will
+    not present correctly in some PDF viewers.
+    """
+    match = re.search(
+        r'DeviceN.*inappropriate alternate',
+        stream,
+        flags=re.IGNORECASE | re.MULTILINE,
+    )
+    return bool(match)
+
+
 def rasterize_pdf(
     input_file: os.PathLike,
     output_file: os.PathLike,
@@ -77,6 +105,7 @@ def rasterize_pdf(
     page_dpi: Resolution | None = None,
     rotation: int | None = None,
     filter_vector: bool = False,
+    stop_on_error: bool = False,
 ):
     """Rasterize one page of a PDF at resolution raster_dpi in canvas units."""
     raster_dpi = raster_dpi.round(6)
@@ -86,7 +115,6 @@ def rasterize_pdf(
     args_gs = (
         [
             GS,
-            '-dQUIET',
             '-dSAFER',
             '-dBATCH',
             '-dNOPAUSE',
@@ -97,9 +125,10 @@ def rasterize_pdf(
             f'-r{raster_dpi.x:f}x{raster_dpi.y:f}',
         ]
         + (['-dFILTERVECTOR'] if filter_vector else [])
+        + (['-dPDFSTOPONERROR'] if stop_on_error else [])
         + [
             '-o',
-            '-',
+            fspath(output_file),
             '-sstdout=%stderr',  # Literal %s, not string interpolation
             '-dAutoRotatePages=/None',  # Probably has no effect on raster
             '-f',
@@ -111,33 +140,48 @@ def rasterize_pdf(
         p = run(args_gs, stdout=PIPE, stderr=PIPE, check=True)
     except CalledProcessError as e:
         log.error(e.stderr.decode(errors='replace'))
-        raise SubprocessOutputError('Ghostscript rasterizing failed') from e
-    else:
-        stderr = p.stderr.decode(errors='replace')
-        if _gs_error_reported(stderr):
-            log.error(stderr)
+        Path(output_file).unlink(missing_ok=True)
+        raise SubprocessOutputError("Ghostscript rasterizing failed") from e
+
+    stderr = p.stderr.decode(errors='replace')
+    if _gs_error_reported(stderr):
+        log.error(stderr)
+        if stop_on_error and "recoverable image error" in stderr:
+            Path(output_file).unlink(missing_ok=True)
+            raise InputFileError(
+                "Ghostscript rasterizing failed. The input file contains errors that "
+                "cause PDF viewers to interpret it differently and incorrectly. "
+                "Try using --continue-on-soft-render-error and manually inspect the "
+                "input and output files to check for visual differences or errors."
+            )
 
     try:
-        with Image.open(BytesIO(p.stdout)) as im:
+        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
                 # counterclockwise so this cancels out the rotation
                 if rotation == 90:
-                    im = im.transpose(Transpose.ROTATE_90)
+                    im = im.transpose(Image.Transpose.ROTATE_90)
                 elif rotation == 180:
-                    im = im.transpose(Transpose.ROTATE_180)
+                    im = im.transpose(Image.Transpose.ROTATE_180)
                 elif rotation == 270:
-                    im = im.transpose(Transpose.ROTATE_270)
+                    im = im.transpose(Image.Transpose.ROTATE_270)
                 if rotation % 180 == 90:
                     page_dpi = page_dpi.flip_axis()
-            im.save(fspath(output_file), dpi=page_dpi)
+            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:
@@ -151,6 +195,17 @@ 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
@@ -161,7 +216,8 @@ 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()
@@ -172,9 +228,11 @@ def generate_pdfa(
     output_file: os.PathLike,
     *,
     compression: str,
+    color_conversion_strategy: str,
     pdf_version: str = '1.5',
     pdfa_part: str = '2',
     progressbar_class=None,
+    stop_on_error: bool = False,
 ):
     # Ghostscript's compression is all or nothing. We can either force all images
     # to JPEG, force all to Flate/PNG, or let it decide how to encode the images.
@@ -200,23 +258,16 @@ def generate_pdfa(
             "-dAutoFilterGrayImages=true",
         ]
 
-    strategy = 'LeaveColorUnchanged'
-    # Older versions of Ghostscript expect a leading slash in
-    # sColorConversionStrategy, newer ones should not have it. See Ghostscript
-    # git commit fe1c025d.
     gs_version = version()
-    strategy = ('/' + strategy) if gs_version < '9.19' else strategy
-
-    if gs_version == '9.23':
-        # 9.23: added JPEG passthrough as a new feature, but with a bug that
-        # incorrectly formats some images. Fixed as of 9.24. So we disable this
-        # feature for 9.23.
-        # https://bugs.ghostscript.com/show_bug.cgi?id=699216
-        compression_args.append('-dPassThroughJPEGImages=false')
-    elif gs_version == '9.56.0':
-        # 9.56.0 breaks our OCR...?
+    if gs_version == Version('9.56.0'):
+        # 9.56.0 breaks our OCR, should be fixed in 9.56.1
+        # https://bugs.ghostscript.com/show_bug.cgi?id=705187
         compression_args.append('-dNEWPDF=false')
 
+    if os.name == 'nt':
+        # Windows has lots of fatal "permission denied" errors
+        stop_on_error = False
+
     # nb no need to specify ProcessColorModel when ColorConversionStrategy
     # is set; see:
     # https://bugs.ghostscript.com/show_bug.cgi?id=699392
@@ -226,34 +277,33 @@ def generate_pdfa(
             "-dBATCH",
             "-dNOPAUSE",
             "-dSAFER",
-            "-dCompatibilityLevel=" + str(pdf_version),
+            f"-dCompatibilityLevel={str(pdf_version)}",
             "-sDEVICE=pdfwrite",
             "-dAutoRotatePages=/None",
-            "-sColorConversionStrategy=" + strategy,
+            f"-sColorConversionStrategy={color_conversion_strategy}",
         ]
+        + (['-dPDFSTOPONERROR'] if stop_on_error else [])
         + compression_args
         + [
             "-dJPEGQ=95",
-            "-dPDFA=" + pdfa_part,
+            f"-dPDFA={pdfa_part}",
             "-dPDFACompatibilityPolicy=1",
             "-o",
-            "-",
+            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
@@ -265,14 +315,11 @@ def generate_pdfa(
         # If there is an error we log the whole stderr, except for filtering
         # duplicates.
         if _gs_error_reported(stderr):
-            last_part = None
-            repcount = 0
+            # Ghostscript outputs the pattern **** Error: ....  frequently.
+            # Occasionally the error message is spammed many times. We filter
+            # out duplicates of this message using the filter above. We use
+            # the **** pattern to split the stderr into parts.
             for part in stderr.split('****'):
-                if part != last_part:
-                    if repcount > 1:
-                        log.error(f"(previous error message repeated {repcount} times)")
-                        repcount = 0
-                    log.error(part)
-                else:
-                    repcount += 1
-                last_part = part
+                log.error(part)
+        if _gs_devicen_reported(stderr):
+            raise ColorConversionNeededError()

src/ocrmypdf/_exec/jbig2enc.py

@@ -1,18 +1,26 @@
 # SPDX-FileCopyrightText: 2022 James R. Barlow
 # SPDX-License-Identifier: MPL-2.0
 
-"""Interface to jbig2 executable"""
+"""Interface to jbig2 executable."""
 
 from __future__ import annotations
 
-from subprocess import PIPE
+from subprocess import PIPE, CalledProcessError
+
+from packaging.version import Version
 
 from ocrmypdf.exceptions import MissingDependencyError
 from ocrmypdf.subprocess import get_version, run
 
 
-def version():
-    return get_version('jbig2', regex=r'jbig2enc (\d+(\.\d+)*).*')
+def version() -> Version:
+    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():
@@ -23,15 +31,17 @@ def available():
     return True
 
 
-def convert_group(*, cwd, infiles, out_prefix):
+def convert_group(cwd, infiles, out_prefix, threshold):
     args = [
         'jbig2',
         '-b',
         out_prefix,
-        '-s',  # symbol mode (lossy)
+        '--symbol-mode',  # symbol mode (lossy)
+        '-t',
+        str(threshold),  # threshold
         # '-r', # refinement mode (lossless symbol mode, currently disabled in
         # jbig2)
-        '-p',
+        '--pdf',
     ]
     args.extend(infiles)
     proc = run(args, cwd=cwd, stdout=PIPE, stderr=PIPE)
@@ -39,17 +49,9 @@ def convert_group(*, cwd, infiles, out_prefix):
     return proc
 
 
-def convert_group_mp(args):
-    return convert_group(cwd=args[0], infiles=args[1], out_prefix=args[2])
-
-
-def convert_single(*, cwd, infile, outfile):
-    args = ['jbig2', '-p', infile]
+def convert_single(cwd, infile, outfile, threshold):
+    args = ['jbig2', '--pdf', '-t', str(threshold), infile]
     with open(outfile, 'wb') as fstdout:
         proc = run(args, cwd=cwd, stdout=fstdout, stderr=PIPE)
     proc.check_returncode()
     return proc
-
-
-def convert_single_mp(args):
-    return convert_single(cwd=args[0], infile=args[1], outfile=args[2])

src/ocrmypdf/_exec/pngquant.py

@@ -1,23 +1,21 @@
 # SPDX-FileCopyrightText: 2022 James R. Barlow
 # SPDX-License-Identifier: MPL-2.0
 
-"""Interface to pngquant executable"""
+"""Interface to pngquant executable."""
 
 from __future__ import annotations
 
-from contextlib import contextmanager
-from io import BytesIO
 from pathlib import Path
 from subprocess import PIPE
 
-from PIL import Image
+from packaging.version import Version
 
 from ocrmypdf.exceptions import MissingDependencyError
 from ocrmypdf.subprocess import get_version, run
 
 
-def version():
-    return get_version('pngquant', regex=r'(\d+(\.\d+)*).*')
+def version() -> Version:
+    return Version(get_version('pngquant', regex=r'(\d+(\.\d+)*).*'))
 
 
 def available():
@@ -28,21 +26,16 @@ def available():
     return True
 
 
-@contextmanager
-def input_as_png(input_file: Path):
-    if not input_file.name.endswith('.png'):
-        with Image.open(input_file) as im:
-            bio = BytesIO()
-            im.save(bio, format='png')
-            bio.seek(0)
-            yield bio
-    else:
-        with open(input_file, 'rb') as f:
-            yield f
-
-
 def quantize(input_file: Path, output_file: Path, quality_min: int, quality_max: int):
-    with input_as_png(input_file) as input_stream:
+    """Quantize a PNG image using pngquant.
+
+    Args:
+        input_file: Input PNG image
+        output_file: Output PNG image
+        quality_min: Minimum quality to use
+        quality_max: Maximum quality to use
+    """
+    with open(input_file, 'rb') as input_stream:
         args = [
             'pngquant',
             '--force',
@@ -57,7 +50,3 @@ def quantize(input_file: Path, output_file: Path, quality_min: int, quality_max:
     if result.returncode == 0:
         # input_file could be the same as output_file, so we defer the write
         output_file.write_bytes(result.stdout)
-
-
-def quantize_mp(args):
-    return quantize(*args)

src/ocrmypdf/_exec/tesseract.py

@@ -1,19 +1,19 @@
 # SPDX-FileCopyrightText: 2022 James R. Barlow
 # SPDX-License-Identifier: MPL-2.0
 
-"""Interface to Tesseract executable"""
+"""Interface to Tesseract executable."""
 
 from __future__ import annotations
 
 import logging
 import re
+from contextlib import suppress
 from math import pi
 from os import fspath
 from pathlib import Path
 from subprocess import PIPE, STDOUT, CalledProcessError, TimeoutExpired
 
 from packaging.version import Version
-from PIL import Image
 
 from ocrmypdf.exceptions import (
     MissingDependencyError,
@@ -26,23 +26,6 @@ from ocrmypdf.subprocess import get_version, run
 log = logging.getLogger(__name__)
 
 
-HOCR_TEMPLATE = """<?xml version="1.0" encoding="UTF-8"?>
-<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN"
-    "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
-<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
- <head>
-  <title></title>
-<meta http-equiv="Content-Type" content="text/html;charset=utf-8" />
-  <meta name='ocr-system' content='tesseract 4.0.0' />
-  <meta name='ocr-capabilities' content='ocr_page ocr_carea ocr_par ocr_line ocrx_word ocrp_wconf'/>
-</head>
-<body>
-  <div class='ocr_page' id='page_1' title='image "_blank.png"; bbox 0 0 {0} {1}; ppageno 0'>
-  </div>
- </body>
-</html>
-"""
-
 TESSERACT_THRESHOLDING_METHODS: dict[str, int] = {
     'auto': 0,
     'otsu': 0,
@@ -52,7 +35,7 @@ TESSERACT_THRESHOLDING_METHODS: dict[str, int] = {
 
 
 class TesseractLoggerAdapter(logging.LoggerAdapter):
-    "Prepend [tesseract] to messages emitted from tesseract"
+    """Prepend [tesseract] to messages emitted from tesseract."""
 
     def process(self, msg, kwargs):
         kwargs['extra'] = self.extra
@@ -104,28 +87,20 @@ TESSERACT_VERSION_PATTERN = r"""
 
 
 class TesseractVersion(Version):
-    "Modify standard packaging.Version regex to support Tesseract idiosyncracies."
+    """Modify standard packaging.Version regex to support Tesseract idiosyncrasies."""
+
     _regex = re.compile(
         r"^\s*" + TESSERACT_VERSION_PATTERN + r"\s*$", re.VERBOSE | re.IGNORECASE
     )
 
 
-def version() -> str:
-    return get_version('tesseract', regex=r'tesseract\s(.+)')
-
-
-def has_user_words() -> bool:
-    """Does Tesseract have --user-words capability?
-
-    Not available in 4.0, but available in 4.1. Also available in 3.x, but
-    we no longer support 3.x.
-    """
-    return version() >= '4.1'
+def version() -> Version:
+    return TesseractVersion(get_version('tesseract', regex=r'tesseract\s(.+)'))
 
 
 def has_thresholding() -> bool:
     """Does Tesseract have -c thresholding method capability?"""
-    return version() >= '5.0'
+    return version() >= Version('5.0')
 
 
 def get_languages() -> set[str]:
@@ -239,12 +214,14 @@ def get_deskew(
     parsed = _parse_tesseract_output(p.stdout)
     deskew_radians = float(parsed.get('Deskew angle', 0))
     deskew_degrees = 180 / pi * deskew_radians
+    log.debug(f"Deskew angle: {deskew_degrees:.3f}")
     return deskew_degrees
 
 
 def tesseract_log_output(stream: bytes) -> None:
     tlog = TesseractLoggerAdapter(
-        log, extra=log.extra if hasattr(log, 'extra') else None
+        log,
+        extra=log.extra if hasattr(log, 'extra') else None,  # type: ignore
     )
 
     if not stream:
@@ -289,12 +266,11 @@ def page_timedout(timeout: float) -> None:
 
 
 def _generate_null_hocr(output_hocr: Path, output_text: Path, image: Path) -> None:
-    """Produce a .hocr file that reports no text detected on a page that is
-    the same size as the input image."""
-    with Image.open(image) as im:
-        w, h = im.size
+    """Produce an empty .hocr file.
 
-    output_hocr.write_text(HOCR_TEMPLATE.format(w, h), encoding='utf-8')
+    Ensures page is the same size as the input image.
+    """
+    output_hocr.write_text('', encoding='utf-8')
     output_text.write_text('[skipped page]', encoding='utf-8')
 
 
@@ -353,7 +329,7 @@ def generate_hocr(
         tesseract_log_output(stdout)
         # The sidecar text file will get the suffix .txt; rename it to
         # whatever caller wants it named
-        if prefix.with_suffix('.txt').exists():
+        with suppress(FileNotFoundError):
             prefix.with_suffix('.txt').replace(output_text)
 
 
@@ -409,7 +385,7 @@ def generate_pdf(
     try:
         p = run(args_tesseract, stdout=PIPE, stderr=STDOUT, timeout=timeout, check=True)
         stdout = p.stdout
-        if prefix.with_suffix('.txt').exists():
+        with suppress(FileNotFoundError):
             prefix.with_suffix('.txt').replace(output_text)
     except TimeoutExpired:
         page_timedout(timeout)

src/ocrmypdf/_exec/unpaper.py

@@ -1,51 +1,33 @@
 # SPDX-FileCopyrightText: 2022 James R. Barlow
 # SPDX-License-Identifier: MPL-2.0
 
-from __future__ import annotations
+"""Interface to unpaper executable."""
 
-# unpaper documentation:
-# https://github.com/Flameeyes/unpaper/blob/master/doc/basic-concepts.md
-"""Interface to unpaper executable"""
+from __future__ import annotations
 
 import logging
 import os
 import shlex
-import sys
+from collections.abc import Iterator
 from contextlib import contextmanager
 from decimal import Decimal
 from pathlib import Path
 from subprocess import PIPE, STDOUT
-from typing import Iterator, Union
+from tempfile import TemporaryDirectory
 
+from 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
 
-if sys.version_info >= (3, 10):
-    from tempfile import TemporaryDirectory
-else:
-    from tempfile import TemporaryDirectory as _TemporaryDirectory
-
-    class TemporaryDirectory(_TemporaryDirectory):
-        """Shim to consume ignore_cleanup_errors kwarg on Python 3.9 and older.
-
-        The argument is consumed without action. If users are getting errors related
-        to temporary file cleanup, they should upgrade to Python 3.10 which properly
-        cleans up temporary directories on Windows.
-
-        See: https://github.com/python/cpython/pull/24793
-        """
-
-        def __init__(self, ignore_cleanup_errors=False, **kwargs):
-            super().__init__(**kwargs)
-
-    del _TemporaryDirectory
+# unpaper documentation:
+# https://github.com/Flameeyes/unpaper/blob/main/doc/basic-concepts.md
 
 
 UNPAPER_IMAGE_PIXEL_LIMIT = 256 * 1024 * 1024
 
-DecFloat = Union[Decimal, float]
+DecFloat = Decimal | float
 
 log = logging.getLogger(__name__)
 
@@ -65,34 +47,8 @@ class UnpaperImageTooLargeError(Exception):
         super().__init__(self.message)
 
 
-def version() -> str:
-    return get_version('unpaper')
-
-
-SUPPORTED_MODES = {'1', 'L', 'RGB'}
-
-
-def _convert_image(im: Image.Image) -> tuple[Image.Image, bool]:
-    im_modified = False
-
-    if im.mode not in SUPPORTED_MODES:
-        log.info("Converting image to other colorspace")
-        try:
-            if im.mode == 'P' and len(im.getcolors()) == 2:
-                im = im.convert(mode='1')
-            else:
-                im = im.convert(mode='RGB')
-        except OSError as e:
-            raise MissingDependencyError(
-                "Could not convert image with type " + im.mode
-            ) from e
-        else:
-            im_modified = True
-        if im.mode not in SUPPORTED_MODES:
-            raise MissingDependencyError(
-                "Failed to convert image to a supported format."
-            ) from None
-    return im, im_modified
+def version() -> Version:
+    return Version(get_version('unpaper', regex=r'(?m).*?(\d+(\.\d+)(\.\d+)?)'))
 
 
 @contextmanager
@@ -100,21 +56,15 @@ def _setup_unpaper_io(input_file: Path) -> Iterator[tuple[Path, Path, Path]]:
     with Image.open(input_file) as im:
         if im.width * im.height >= UNPAPER_IMAGE_PIXEL_LIMIT:
             raise UnpaperImageTooLargeError(w=im.width, h=im.height)
-        im, im_modified = _convert_image(im)
 
-        with TemporaryDirectory(ignore_cleanup_errors=True) as tmpdir:
-            tmppath = Path(tmpdir)
-            if im_modified or input_file.suffix != '.png':
-                input_png = tmppath / 'input.png'
-                im.save(input_png, format='PNG')
-            else:
-                # No changes, PNG input, just use the file we already have
-                input_png = input_file
-
-            # unpaper can write .png too, but it seems to write them slowly
-            # adds a few seconds to test suite - so just use pnm
-            output_pnm = tmppath / 'output.pnm'
-            yield input_png, output_pnm, tmppath
+    with TemporaryDirectory(ignore_cleanup_errors=True) as tmpdir:
+        tmppath = Path(tmpdir)
+        # No changes, PNG input, just use the file we already have
+        input_png = input_file
+        # unpaper can write .png too, but it seems to write them slowly
+        # adds a few seconds to test suite - so just use pnm
+        output_pnm = tmppath / 'output.pnm'
+        yield input_png, output_pnm, tmppath
 
 
 def run_unpaper(

src/ocrmypdf/_graft.py

@@ -7,65 +7,85 @@ from __future__ import annotations
 
 import logging
 from contextlib import suppress
+from enum import Enum
 from pathlib import Path
 
 from pikepdf import (
     Dictionary,
+    Matrix,
     Name,
-    Object,
     Operator,
+    Page,
     Pdf,
     PdfError,
-    PdfMatrix,
     Stream,
     parse_content_stream,
     unparse_content_stream,
 )
 
+from ocrmypdf._jobcontext import PdfContext
+
+
+class RenderMode(Enum):
+    ON_TOP = 0
+    UNDERNEATH = 1
+
+
 log = logging.getLogger(__name__)
 MAX_REPLACE_PAGES = 100
 
 
-def _ensure_dictionary(obj, name):
+def _ensure_dictionary(obj: Dictionary | Stream, name: Name):
     if name not in obj:
         obj[name] = Dictionary({})
     return obj[name]
 
 
-def _update_resources(*, obj, font, font_key, procset):
+def _update_resources(
+    *,
+    obj: Dictionary | Stream,
+    font: Dictionary | None,
+    font_key: Name | None,
+):
     """Update this obj's fonts with a reference to the Glyphless font.
 
     obj can be a page or Form XObject.
     """
-
     resources = _ensure_dictionary(obj, Name.Resources)
     fonts = _ensure_dictionary(resources, Name.Font)
     if font_key is not None and font_key not in fonts:
         fonts[font_key] = font
 
-    # Reassign /ProcSet to one that just lists everything - ProcSet is
-    # obsolete and doesn't matter but recommended for old viewer support
-    if procset:
-        resources['/ProcSet'] = procset
 
-
-def strip_invisible_text(pdf, page):
+def strip_invisible_text(pdf: Pdf, page: Page):
     stream = []
     in_text_obj = False
     render_mode = 0
+    render_mode_stack = []
     text_objects = []
 
     for operands, operator in parse_content_stream(page, ''):
+        if operator == Operator('Tr'):
+            render_mode = operands[0]
+
+        if operator == Operator('q'):
+            render_mode_stack.append(render_mode)
+
+        if operator == Operator('Q'):
+            try:
+                render_mode = render_mode_stack.pop()
+            except IndexError:
+                # Stack underflow: content stream is malformed
+                # but try to carry on
+                pass
+
         if not in_text_obj:
             if operator == Operator('BT'):
                 in_text_obj = True
-                render_mode = 0
                 text_objects.append((operands, operator))
             else:
                 stream.append((operands, operator))
         else:
-            if operator == Operator('Tr'):
-                render_mode = operands[0]
             text_objects.append((operands, operator))
             if operator == Operator('ET'):
                 in_text_obj = False
@@ -80,22 +100,20 @@ def strip_invisible_text(pdf, page):
 class OcrGrafter:
     """Manages grafting text-only PDFs onto regular PDFs."""
 
-    def __init__(self, context):
+    def __init__(self, context: PdfContext):
         self.context = context
         self.path_base = context.origin
 
         self.pdf_base = Pdf.open(self.path_base)
-        self.font, self.font_key = None, None
+        self.font: Dictionary | None = None
+        self.font_key: Name | None = None
 
         self.pdfinfo = context.pdfinfo
         self.output_file = context.get_path('graft_layers.pdf')
 
-        self.procset = self.pdf_base.make_indirect(
-            Object.parse(b'[ /PDF /Text /ImageB /ImageC /ImageI ]')
-        )
-
         self.emplacements = 1
         self.interim_count = 0
+        self.render_mode = RenderMode.UNDERNEATH
 
     def graft_page(
         self,
@@ -120,7 +138,9 @@ class OcrGrafter:
                 foreign_image_page = pdf_image.pages[0]
                 self.pdf_base.pages.append(foreign_image_page)
                 local_image_page = self.pdf_base.pages[-1]
-                self.pdf_base.pages[pageno].emplace(local_image_page)
+                self.pdf_base.pages[pageno].emplace(
+                    local_image_page, retain=(Name.Parent,)
+                )
                 del self.pdf_base.pages[-1]
             emplaced_page = True
 
@@ -131,10 +151,13 @@ class OcrGrafter:
         text_misaligned = (text_rotation - content_rotation) % 360
         log.debug(
             f"Text rotation: (text, autorotate, content) -> text misalignment = "
-            f"({text_rotation}, {autorotate_correction}, {content_rotation}) -> {text_misaligned}"
+            f"({text_rotation}, {autorotate_correction}, {content_rotation}) -> "
+            f"{text_misaligned}"
         )
 
         if textpdf and self.font:
+            if self.font_key is None:
+                raise ValueError("Font key is not set")
             # Graft the text layer onto this page, whether new or old, possibly
             # rotating the text layer by the amount is misaligned.
             strip_old = self.context.options.redo_ocr
@@ -144,7 +167,6 @@ class OcrGrafter:
                 font=self.font,
                 font_key=self.font_key,
                 text_rotation=text_misaligned,
-                procset=self.procset,
                 strip_old_text=strip_old,
             )
 
@@ -159,18 +181,15 @@ class OcrGrafter:
         if self.emplacements % MAX_REPLACE_PAGES == 0:
             self.save_and_reload()
 
-    def save_and_reload(self):
+    def save_and_reload(self) -> None:
         """Save and reload the Pdf.
 
         This will keep a lid on our memory usage for very large files. Attach
         the font to page 1 even if page 1 doesn't use it, so we have a way to get it
         back.
         """
-
         page0 = self.pdf_base.pages[0]
-        _update_resources(
-            obj=page0, font=self.font, font_key=self.font_key, procset=self.procset
-        )
+        _update_resources(obj=page0.obj, font=self.font, font_key=self.font_key)
 
         # We cannot read and write the same file, that will corrupt it
         # but we don't to keep more copies than we need to. Delete intermediates.
@@ -189,7 +208,6 @@ class OcrGrafter:
         self.pdf_base.close()
 
         self.pdf_base = Pdf.open(next_file)
-        self.procset = self.pdf_base.pages[0].Resources.ProcSet
         self.font, self.font_key = None, None  # Ensure we reacquire this information
         self.interim_count += 1
 
@@ -198,25 +216,32 @@ class OcrGrafter:
         self.pdf_base.close()
         return self.output_file
 
-    def _find_font(self, text):
-        """Copy a font from the filename text into pdf_base"""
-
+    def _find_font(self, text: Path) -> tuple[Dictionary | None, Name | None]:
+        """Copy a font from the filename text into pdf_base."""
         font, font_key = None, None
         possible_font_names = ('/f-0-0', '/F1')
         try:
             with Pdf.open(text) as pdf_text:
                 try:
-                    pdf_text_fonts = pdf_text.pages[0].Resources.get('/Font', {})
+                    pdf_text_fonts = pdf_text.pages[0].Resources.get(
+                        Name.Font, Dictionary()
+                    )
                 except (AttributeError, IndexError, KeyError):
                     return None, None
+                if not isinstance(pdf_text_fonts, Dictionary):
+                    log.warning("Page fonts are not stored in a dictionary")
+                    return None, None
                 pdf_text_font = None
                 for f in possible_font_names:
                     pdf_text_font = pdf_text_fonts.get(f, None)
                     if pdf_text_font is not None:
-                        font_key = f
+                        font_key = Name(f)
                         break
                 if pdf_text_font:
                     font = self.pdf_base.copy_foreign(pdf_text_font)
+                if not isinstance(font, Dictionary):
+                    log.warning("Font is not a dictionary")
+                    font, font_key = None, None
                 return font, font_key
         except (FileNotFoundError, PdfError):
             # PdfError occurs if a 0-length file is written e.g. due to OCR timeout
@@ -227,14 +252,12 @@ class OcrGrafter:
         *,
         page_num: int,
         textpdf: Path,
-        font: Object,
-        font_key: Object,
-        procset: Object,
+        font: Dictionary,
+        font_key: Name,
         text_rotation: int,
         strip_old_text: bool,
     ):
-        """Insert the text layer from text page 0 on to pdf_base at page_num"""
-
+        """Insert the text layer from text page 0 on to pdf_base at page_num."""
         # pylint: disable=invalid-name
 
         log.debug("Grafting")
@@ -251,19 +274,19 @@ class OcrGrafter:
             # content may have a rotation applied. Wrap the text stream with a rotation
             # so it will be oriented the same way as the rest of the page content.
             # (Previous versions OCRmyPDF rotated the content layer to match the text.)
-            mediabox = [float(pdf_text.pages[0].MediaBox[v]) for v in range(4)]
+            mediabox = pdf_text.pages[0].mediabox
             wt, ht = mediabox[2] - mediabox[0], mediabox[3] - mediabox[1]
 
-            mediabox = [float(base_page.MediaBox[v]) for v in range(4)]
+            mediabox = base_page.mediabox
             wp, hp = mediabox[2] - mediabox[0], mediabox[3] - mediabox[1]
 
-            translate = PdfMatrix().translated(-wt / 2, -ht / 2)
-            untranslate = PdfMatrix().translated(wp / 2, hp / 2)
-            corner = PdfMatrix().translated(mediabox[0], mediabox[1])
+            translate = Matrix().translated(-wt / 2, -ht / 2)
+            untranslate = Matrix().translated(wp / 2, hp / 2)
+            corner = Matrix().translated(mediabox[0], mediabox[1])
             # -rotation because the input is a clockwise angle and this formula
             # uses CCW
             text_rotation = -text_rotation % 360
-            rotate = PdfMatrix().rotated(text_rotation)
+            rotate = Matrix().rotated(text_rotation)
 
             # Because of rounding of DPI, we might get a text layer that is not
             # identically sized to the target page. Scale to adjust. Normally this
@@ -274,14 +297,15 @@ class OcrGrafter:
             scale_y = hp / ht
 
             # log.debug('%r', scale_x, scale_y)
-            scale = PdfMatrix().scaled(scale_x, scale_y)
+            scale = Matrix().scaled(scale_x, scale_y)
 
             # Translate the text so it is centered at (0, 0), rotate it there, adjust
             # for a size different between initial and text PDF, then untranslate, and
-            # finally move the lower left corner to match the mediabox
+            # finally move the lower left corner to match the mediabox.
             ctm = translate @ rotate @ scale @ untranslate @ corner
+            log.debug("Grafting with ctm %r", ctm)
 
-            base_resources = _ensure_dictionary(base_page, Name.Resources)
+            base_resources = _ensure_dictionary(base_page.obj, Name.Resources)
             base_xobjs = _ensure_dictionary(base_resources, Name.XObject)
             text_xobj_name = Name.random(prefix="OCR-")
             xobj = self.pdf_base.make_stream(pdf_text_contents)
@@ -290,9 +314,7 @@ class OcrGrafter:
             xobj.Subtype = Name.Form
             xobj.FormType = 1
             xobj.BBox = mediabox
-            _update_resources(
-                obj=xobj, font=font, font_key=font_key, procset=[Name.PDF]
-            )
+            _update_resources(obj=xobj, font=font, font_key=font_key)
 
             pdf_draw_xobj = (
                 (b'q %s cm\n' % ctm.encode()) + (b'%s Do\n' % text_xobj_name) + b'\nQ\n'
@@ -301,9 +323,16 @@ class OcrGrafter:
 
             if strip_old_text:
                 strip_invisible_text(self.pdf_base, base_page)
-
-            base_page.contents_add(new_text_layer, prepend=True)
-
-            _update_resources(
-                obj=base_page, font=font, font_key=font_key, procset=procset
+            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.UNDERNEATH
             )
+            base_page.contents_coalesce()
+
+            _update_resources(obj=base_page.obj, font=font, font_key=font_key)

src/ocrmypdf/_jobcontext.py

@@ -6,12 +6,10 @@
 from __future__ import annotations
 
 import os
-import shutil
-import sys
 from argparse import Namespace
+from collections.abc import Iterator
 from copy import copy
 from pathlib import Path
-from typing import Iterator
 
 from pluggy import PluginManager
 
@@ -55,11 +53,17 @@ class PdfContext:
         for n in range(npages):
             yield PageContext(self, n)
 
+    def get_page_context_args(self) -> Iterator[tuple[PageContext]]:
+        """Get all ``PageContext`` for this PDF packaged in tuple for args-splatting."""
+        npages = len(self.pdfinfo)
+        for n in range(npages):
+            yield (PageContext(self, n),)
+
 
 class PageContext:
     """Holds our context for a page.
 
-    Must be pickable, so stores only intrinsic/simple data elements or those
+    Must be pickle-able, so stores only intrinsic/simple data elements or those
     capable of their serializing themselves via ``__getstate__``.
     """
 
@@ -89,15 +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
-
-
-def cleanup_working_files(work_folder: Path, options: Namespace):
-    if options.keep_temporary_files:
-        print(f"Temporary working files retained at:\n{work_folder}", file=sys.stderr)
-    else:
-        shutil.rmtree(work_folder, ignore_errors=True)

src/ocrmypdf/_logging.py

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

src/ocrmypdf/_metadata.py

@@ -0,0 +1,215 @@
+# SPDX-FileCopyrightText: 2023 James R. Barlow
+# SPDX-License-Identifier: MPL-2.0
+
+"""OCRmyPDF page processing pipeline functions."""
+
+from __future__ import annotations
+
+import logging
+import os
+from datetime import datetime, timezone
+from pathlib import Path
+from typing import Any
+
+from pikepdf import Dictionary, Name, Pdf
+from pikepdf import __version__ as PIKEPDF_VERSION
+from pikepdf.models.metadata import PdfMetadata, encode_pdf_date
+
+from ocrmypdf._annots import remove_broken_goto_annotations
+from ocrmypdf._defaults import PROGRAM_NAME
+from ocrmypdf._jobcontext import PdfContext
+from ocrmypdf._version import __version__ as OCRMYPF_VERSION
+from ocrmypdf.languages import iso_639_2_from_3
+
+log = logging.getLogger(__name__)
+
+
+def get_docinfo(base_pdf: Pdf, context: PdfContext) -> dict[str, str]:
+    """Read the document info and store it in a dictionary."""
+    options = context.options
+
+    def from_document_info(key):
+        try:
+            s = base_pdf.docinfo[key]
+            return str(s)
+        except (KeyError, TypeError):
+            return ''
+
+    pdfmark = {
+        k: from_document_info(k)
+        for k in ('/Title', '/Author', '/Keywords', '/Subject', '/CreationDate')
+    }
+    if options.title:
+        pdfmark['/Title'] = options.title
+    if options.author:
+        pdfmark['/Author'] = options.author
+    if options.keywords:
+        pdfmark['/Keywords'] = options.keywords
+    if options.subject:
+        pdfmark['/Subject'] = options.subject
+
+    creator_tag = context.plugin_manager.hook.get_ocr_engine().creator_tag(options)
+
+    pdfmark['/Creator'] = f'{PROGRAM_NAME} {OCRMYPF_VERSION} / {creator_tag}'
+    pdfmark['/Producer'] = f'pikepdf {PIKEPDF_VERSION}'
+    pdfmark['/ModDate'] = encode_pdf_date(datetime.now(timezone.utc))
+    return pdfmark
+
+
+def report_on_metadata(options, missing):
+    if not missing:
+        return
+    if options.output_type.startswith('pdfa'):
+        log.warning(
+            "Some input metadata could not be copied because it is not "
+            "permitted in PDF/A. You may wish to examine the output "
+            "PDF's XMP metadata."
+        )
+        log.debug("The following metadata fields were not copied: %r", missing)
+    else:
+        log.error(
+            "Some input metadata could not be copied."
+            "You may wish to examine the output PDF's XMP metadata."
+        )
+        log.info("The following metadata fields were not copied: %r", missing)
+
+
+def repair_docinfo_nuls(pdf):
+    """If the DocumentInfo block contains NUL characters, remove them.
+
+    If the DocumentInfo block is malformed, log an error and continue.
+    """
+    modified = False
+    try:
+        if not isinstance(pdf.docinfo, Dictionary):
+            raise TypeError("DocumentInfo is not a dictionary")
+        for k, v in pdf.docinfo.items():
+            if isinstance(v, str) and b'\x00' in bytes(v):
+                pdf.docinfo[k] = bytes(v).replace(b'\x00', b'')
+                modified = True
+    except TypeError:
+        # TypeError can also be raised if dictionary items are unexpected types
+        log.error("File contains a malformed DocumentInfo block - continuing anyway.")
+    return modified
+
+
+def should_linearize(working_file: Path, context: PdfContext) -> bool:
+    """Determine whether the PDF should be linearized.
+
+    For smaller files, linearization is not worth the effort.
+    """
+    filesize = os.stat(working_file).st_size
+    if filesize > (context.options.fast_web_view * 1_000_000):
+        return True
+    return False
+
+
+def _fix_metadata(meta_original: PdfMetadata, meta_pdf: PdfMetadata):
+    # If xmp:CreateDate is missing, set it to the modify date to
+    # ensure consistency with Ghostscript.
+    if 'xmp:CreateDate' not in meta_pdf:
+        meta_pdf['xmp:CreateDate'] = meta_pdf.get('xmp:ModifyDate', '')
+    if meta_pdf.get('dc:title') == 'Untitled':
+        # Ghostscript likes to set title to Untitled if omitted from input.
+        # Reverse this, because PDF/A TechNote 0003:Metadata in PDF/A-1
+        # and the XMP Spec do not make this recommendation.
+        if 'dc:title' not in meta_original:
+            del meta_pdf['dc:title']
+
+
+def _unset_empty_metadata(meta: PdfMetadata, options):
+    """Unset metadata fields that were explicitly set to empty strings.
+
+    If the user explicitly specified an empty string for any of the
+    following, they should be unset and not reported as missing in
+    the output pdf. Note that some metadata fields use differing names
+    between PDF/A and PDF.
+    """
+    if options.title == '' and 'dc:title' in meta:
+        del meta['dc:title']  # PDF/A and PDF
+    if options.author == '':
+        if 'dc:creator' in meta:
+            del meta['dc:creator']  # PDF/A (Not xmp:CreatorTool)
+        if 'pdf:Author' in meta:
+            del meta['pdf:Author']  # PDF
+    if options.subject == '':
+        if 'dc:description' in meta:
+            del meta['dc:description']  # PDF/A
+        if 'dc:subject' in meta:
+            del meta['dc:subject']  # PDF
+    if options.keywords == '' and 'pdf:Keywords' in meta:
+        del meta['pdf:Keywords']  # PDF/A and PDF
+
+
+def _set_language(pdf: Pdf, languages: list[str]):
+    """Set the language of the PDF."""
+    if Name.Lang in pdf.Root or not languages:
+        return  # Already set or can't change
+    primary_language_iso639_3 = languages[0]
+    if not primary_language_iso639_3:
+        return
+    iso639_2 = iso_639_2_from_3(primary_language_iso639_3)
+    if not iso639_2:
+        return
+    pdf.Root.Lang = iso639_2
+
+
+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 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
+    conversion.
+    """
+    output_file = context.get_path('metafix.pdf')
+    options = context.options
+
+    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,
+        ):
+            meta_pdf.load_from_docinfo(
+                docinfo, delete_missing=False, raise_failure=False
+            )
+            _fix_metadata(meta_original, meta_pdf)
+            _unset_empty_metadata(meta_original, options)
+            _unset_empty_metadata(meta_pdf, options)
+            meta_missing = set(meta_original.keys()) - set(meta_pdf.keys())
+            report_on_metadata(options, meta_missing)
+
+        _set_language(pdf, options.languages)
+        pdf.save(output_file, progress=pbar, **pdf_save_settings)
+
+    return output_file

src/ocrmypdf/_pipelines/__init__.py

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

src/ocrmypdf/_pipelines/_common.py

@@ -0,0 +1,488 @@
+# SPDX-FileCopyrightText: 2023 James R. Barlow
+# SPDX-License-Identifier: MPL-2.0
+
+from __future__ import annotations
+
+import argparse
+import json
+import logging
+import logging.handlers
+import os
+import shutil
+import sys
+import threading
+from collections.abc import 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 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
+from ocrmypdf._metadata import metadata_fixup
+from ocrmypdf._pipeline import (
+    convert_to_pdfa,
+    create_ocr_image,
+    create_pdf_page_from_image,
+    create_visible_page_jpg,
+    generate_postscript_stub,
+    get_orientation_correction,
+    get_pdf_save_settings,
+    get_pdfinfo,
+    optimize_pdf,
+    preprocess_clean,
+    preprocess_deskew,
+    preprocess_remove_background,
+    rasterize,
+    rasterize_preview,
+    should_linearize,
+    should_visible_page_image_use_jpg,
+)
+from ocrmypdf._plugin_manager import OcrmypdfPluginManager
+from ocrmypdf._validation import (
+    report_output_file_size,
+)
+from ocrmypdf.exceptions import ExitCode, ExitCodeException
+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()
+tls.pageno = None
+
+
+def _set_logging_tls(tls):
+    """Inject current page number (when available) into log records."""
+    old_factory = logging.getLogRecordFactory()
+
+    def wrapper(*args, **kwargs):
+        record = old_factory(*args, **kwargs)
+        if hasattr(tls, 'pageno'):
+            record.pageno = tls.pageno
+        return record
+
+    logging.setLogRecordFactory(wrapper)
+
+
+_set_logging_tls(tls)
+
+
+def set_thread_pageno(pageno: int | None):
+    """Set page number (1-based) that the current thread is processing."""
+    tls.pageno = pageno
+
+
+class PageResult(NamedTuple):
+    """Result when a page is finished processing."""
+
+    pageno: int
+    """Page number, 0-based."""
+
+    pdf_page_from_image: Path | None = None
+    """Single page PDF from image."""
+
+    ocr: Path | None = None
+    """Single page OCR PDF."""
+
+    text: Path | None = None
+    """Single page text file."""
+
+    orientation_correction: int = 0
+    """Orientation correction in degrees."""
+
+
+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."""
+
+    pageno: int
+    """Page number, 0-based."""
+
+    pdf_page_from_image: Path | None = None
+    """Single page PDF from image."""
+
+    hocr: Path | None = None
+    """Single page hOCR file."""
+
+    textpdf: Path | None = None
+    """hOCR file after conversion to PDF."""
+
+    orientation_correction: int = 0
+    """Orientation correction in degrees."""
+
+    @classmethod
+    def from_json(cls, json_str: str) -> HOCRResult:
+        """Create an instance from a dict."""
+        return cls(**json.loads(json_str, cls=HOCRResultDecoder))
+
+    def to_json(self) -> str:
+        """Serialize to a JSON string."""
+        return json.dumps(self.__dict__, cls=HOCRResultEncoder)
+
+
+def configure_debug_logging(
+    log_filename: Path, prefix: str = ''
+) -> tuple[logging.FileHandler, Callable[[], None]]:
+    """Create a debug log file at a specified location.
+
+    Returns the log handler, and a function to remove the handler.
+
+    Args:
+        log_filename: Where to the put the log file.
+        prefix: The logging domain prefix that should be sent to the log.
+    """
+    log_file_handler = logging.FileHandler(log_filename, delay=True)
+    log_file_handler.setLevel(logging.DEBUG)
+    formatter = logging.Formatter(
+        '[%(asctime)s] - %(name)s - %(levelname)7s -%(pageno)s %(message)s'
+    )
+    log_file_handler.setFormatter(formatter)
+    log_file_handler.addFilter(PageNumberFilter())
+    logging.getLogger(prefix).addHandler(log_file_handler)
+
+    def remover():
+        try:
+            logging.getLogger(prefix).removeHandler(log_file_handler)
+            log_file_handler.close()
+        except OSError as e:
+            print(e, file=sys.stderr)
+
+    return log_file_handler, remover
+
+
+def 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
+    # threaded, but harmless to set again.
+    PIL.Image.MAX_IMAGE_PIXELS = max_pixels
+    pikepdf_enable_mmap()
+
+
+@contextmanager
+def manage_debug_log_handler(
+    *,
+    options: argparse.Namespace,
+    work_folder: Path,
+):
+    remover = None
+    if (options.keep_temporary_files or options.verbose >= 1) and not os.environ.get(
+        'PYTEST_CURRENT_TEST', ''
+    ):
+        # Debug log for command line interface only with verbose output
+        # See https://github.com/pytest-dev/pytest/issues/5502 for why we skip this
+        # when pytest is running
+        _debug_log_handler, remover = configure_debug_logging(
+            work_folder / "debug.log", prefix=""
+        )  # pragma: no cover
+    try:
+        yield
+    finally:
+        if remover:
+            remover()
+
+
+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:
+        yield work_folder
+    finally:
+        if retain:
+            if print_location:
+                _print_temp_folder_location(work_folder)
+        else:
+            shutil.rmtree(work_folder, ignore_errors=True)
+
+
+def cli_exception_handler(
+    fn: Callable[[argparse.Namespace, OcrmypdfPluginManager], ExitCode],
+    options: argparse.Namespace,
+    plugin_manager: OcrmypdfPluginManager,
+) -> ExitCode:
+    """Convert exceptions into command line error messages and exit codes.
+
+    When known exceptions are raised, the exception message is printed to stderr
+    and the program exits with a non-zero exit code. When unknown exceptions are
+    raised, the exception traceback is printed to stderr and the program exits
+    with a non-zero exit code.
+    """
+    try:
+        # We cannot use a generator and yield here, as would be the usual pattern
+        # for exception handling context managers, because we need to return an exit
+        # code.
+        return fn(options, plugin_manager)
+    except KeyboardInterrupt:
+        if options.verbose >= 1:
+            log.exception("KeyboardInterrupt")
+        else:
+            log.error("KeyboardInterrupt")
+        return ExitCode.ctrl_c
+    except ExitCodeException as e:
+        e = cast(ExitCodeException, e)
+        if options.verbose >= 1:
+            log.exception("ExitCodeException")
+        elif str(e):
+            log.error("%s: %s", type(e).__name__, str(e))
+        else:
+            log.error(type(e).__name__)
+        return e.exit_code
+    except PIL.Image.DecompressionBombError:
+        log.exception(
+            "A decompression bomb error was encountered while executing the "
+            "pipeline. Use the argument --max-image-mpixels to raise the maximum "
+            "image pixel limit."
+        )
+        return ExitCode.other_error
+    except (
+        BrokenProcessPool,
+        BrokenThreadPool,
+    ):
+        log.exception(
+            "A worker process was terminated unexpectedly. This is known to occur if "
+            "processing your file takes all available swap space and RAM. It may "
+            "help to try again with a smaller number of jobs, using the --jobs "
+            "argument."
+        )
+        return ExitCode.child_process_error
+    except Exception:  # pylint: disable=broad-except
+        log.exception("An exception occurred while executing the pipeline")
+        return ExitCode.other_error
+
+
+def setup_pipeline(
+    options: argparse.Namespace,
+    plugin_manager: OcrmypdfPluginManager,
+) -> Executor:
+    # Any changes to options will not take effect for options that are already
+    # bound to function parameters in the pipeline. (For example
+    # options.input_file, options.pdf_renderer are already bound.)
+    if not options.jobs:
+        options.jobs = available_cpu_count()
+
+    pikepdf_enable_mmap()
+    executor = setup_executor(plugin_manager)
+    return executor
+
+
+def 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,
+    remove_background: bool,
+    deskew: bool,
+    clean: bool,
+) -> Path:
+    """Preprocess an image."""
+    if remove_background:
+        image = preprocess_remove_background(image, page_context)
+    if deskew:
+        image = preprocess_deskew(image, page_context)
+    if clean:
+        image = preprocess_clean(image, page_context)
+    return image
+
+
+def make_intermediate_images(
+    page_context: PageContext, orientation_correction: int
+) -> tuple[Path, Path | None]:
+    """Create intermediate and preprocessed images for OCR."""
+    options = page_context.options
+
+    ocr_image = preprocess_out = None
+    rasterize_out = rasterize(
+        page_context.origin,
+        page_context,
+        correction=orientation_correction,
+        remove_vectors=False,
+    )
+
+    if not any([options.clean, options.clean_final, options.remove_vectors]):
+        ocr_image = preprocess_out = preprocess(
+            page_context,
+            rasterize_out,
+            options.remove_background,
+            options.deskew,
+            clean=False,
+        )
+    else:
+        if not options.lossless_reconstruction:
+            preprocess_out = preprocess(
+                page_context,
+                rasterize_out,
+                options.remove_background,
+                options.deskew,
+                clean=options.clean_final,
+            )
+        if options.remove_vectors:
+            rasterize_ocr_out = rasterize(
+                page_context.origin,
+                page_context,
+                correction=orientation_correction,
+                remove_vectors=True,
+                output_tag='_ocr',
+            )
+        else:
+            rasterize_ocr_out = rasterize_out
+
+        if (
+            preprocess_out
+            and rasterize_ocr_out == rasterize_out
+            and options.clean == options.clean_final
+        ):
+            # Optimization: image for OCR is identical to presentation image
+            ocr_image = preprocess_out
+        else:
+            ocr_image = preprocess(
+                page_context,
+                rasterize_ocr_out,
+                options.remove_background,
+                options.deskew,
+                clean=options.clean,
+            )
+    return ocr_image, preprocess_out
+
+
+def process_page(page_context: PageContext) -> tuple[Path, Path | None, int]:
+    """Process page to create OCR image, visible page image and orientation."""
+    options = page_context.options
+    orientation_correction = 0
+    if options.rotate_pages:
+        # Rasterize
+        rasterize_preview_out = rasterize_preview(page_context.origin, page_context)
+        orientation_correction = get_orientation_correction(
+            rasterize_preview_out, page_context
+        )
+
+    ocr_image, preprocess_out = make_intermediate_images(
+        page_context, orientation_correction
+    )
+    ocr_image_out = create_ocr_image(ocr_image, page_context)
+
+    pdf_page_from_image_out = None
+    if not options.lossless_reconstruction:
+        assert preprocess_out
+        visible_image_out = preprocess_out
+        if should_visible_page_image_use_jpg(page_context.pageinfo):
+            visible_image_out = create_visible_page_jpg(visible_image_out, page_context)
+        filtered_image = page_context.plugin_manager.hook.filter_page_image(
+            page=page_context, image_filename=visible_image_out
+        )
+        if filtered_image is not None:  # None if no hook is present
+            visible_image_out = filtered_image
+        pdf_page_from_image_out = create_pdf_page_from_image(
+            visible_image_out, page_context, orientation_correction
+        )
+    return ocr_image_out, pdf_page_from_image_out, orientation_correction
+
+
+def postprocess(
+    pdf_file: Path, context: PdfContext, executor: Executor
+) -> tuple[Path, Sequence[str]]:
+    """Postprocess the 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)
+
+    optimizing = context.plugin_manager.hook.is_optimization_enabled(context=context)
+    save_settings = get_pdf_save_settings(context.options.output_type)
+    save_settings['linearize'] = not optimizing and should_linearize(pdf_out, context)
+
+    pdf_out = metadata_fixup(pdf_out, context, pdf_save_settings=save_settings)
+    return optimize_pdf(pdf_out, context, executor)
+
+
+def report_output_pdf(options, start_input_file, optimize_messages) -> ExitCode:
+    if options.output_file == '-':
+        log.info("Output sent to stdout")
+    elif hasattr(options.output_file, 'writable') and options.output_file.writable():
+        log.info("Output written to stream")
+    elif samefile(options.output_file, Path(os.devnull)):
+        pass  # Say nothing when sending to dev null
+    else:
+        if options.output_type.startswith('pdfa'):
+            pdfa_info = file_claims_pdfa(options.output_file)
+            if pdfa_info['pass']:
+                log.info("Output file is a %s (as expected)", pdfa_info['conformance'])
+            else:
+                log.warning(
+                    "Output file is a valid PDF, but conversion to PDF/A did not "
+                    "succeed (issue: %s)",
+                    pdfa_info['conformance'],
+                )
+                return ExitCode.pdfa_conversion_failed
+        if not check_pdf(options.output_file):
+            log.warning('Output file: The generated PDF is INVALID')
+            return ExitCode.invalid_output_pdf
+        report_output_file_size(
+            options, start_input_file, options.output_file, optimize_messages
+        )
+    return ExitCode.ok

src/ocrmypdf/_pipelines/hocr_to_ocr_pdf.py

@@ -0,0 +1,125 @@
+# SPDX-FileCopyrightText: 2019-2023 James R. Barlow
+# SPDX-FileCopyrightText: 2019 Martin Wind
+# SPDX-License-Identifier: MPL-2.0
+
+"""Implements the concurrent and page synchronous parts of the pipeline."""
+
+from __future__ import annotations
+
+import argparse
+import logging
+import logging.handlers
+from collections.abc import Sequence
+from functools import partial
+
+import PIL
+
+from ocrmypdf._concurrent import Executor
+from ocrmypdf._graft import OcrGrafter
+from ocrmypdf._jobcontext import PageContext, PdfContext
+from ocrmypdf._pipeline import (
+    copy_final,
+    render_hocr_page,
+)
+from ocrmypdf._pipelines._common import (
+    HOCRResult,
+    do_get_pdfinfo,
+    manage_work_folder,
+    postprocess,
+    report_output_pdf,
+    set_thread_pageno,
+    setup_pipeline,
+    worker_init,
+)
+from ocrmypdf._plugin_manager import OcrmypdfPluginManager
+from ocrmypdf._progressbar import ProgressBar
+from ocrmypdf.exceptions import ExitCode
+
+log = logging.getLogger(__name__)
+
+
+def _exec_hocrtransform_sync(page_context: PageContext) -> HOCRResult:
+    """Process each page."""
+    hocr_json = page_context.get_path('hocr.json')
+    if not hocr_json.exists():
+        # No hOCR file, so no OCR was performed on this page.
+        return HOCRResult(pageno=page_context.pageno)
+    hocr_result = HOCRResult.from_json(hocr_json.read_text())
+    hocr_result.textpdf = render_hocr_page(
+        page_context.get_path('ocr_hocr.hocr'), page_context
+    )
+    return hocr_result
+
+
+def exec_hocr_to_ocr_pdf(context: PdfContext, executor: Executor) -> Sequence[str]:
+    """Convert hOCR files to OCR PDF."""
+    # Run exec_page_sync on every page
+    options = context.options
+    max_workers = min(len(context.pdfinfo), options.jobs)
+    if max_workers > 1:
+        log.info("Continue processing %d pages concurrently", max_workers)
+
+    ocrgraft = OcrGrafter(context)
+
+    def graft_page(result: HOCRResult, pbar: ProgressBar):
+        """Graft text only PDF on to main PDF's page."""
+        try:
+            set_thread_pageno(result.pageno + 1)
+            pbar.update()
+            ocrgraft.graft_page(
+                pageno=result.pageno,
+                image=result.pdf_page_from_image,
+                textpdf=result.textpdf,
+                autorotate_correction=result.orientation_correction,
+            )
+            pbar.update()
+        finally:
+            set_thread_pageno(None)
+
+    executor(
+        use_threads=options.use_threads,
+        max_workers=max_workers,
+        progress_kwargs=dict(
+            total=(2 * len(context.pdfinfo)),
+            desc='Grafting hOCR to PDF',
+            unit='page',
+            unit_scale=0.5,
+            disable=not options.progress_bar,
+        ),
+        worker_initializer=partial(worker_init, PIL.Image.MAX_IMAGE_PIXELS),
+        task=_exec_hocrtransform_sync,
+        task_arguments=context.get_page_context_args(),
+        task_finished=graft_page,
+    )
+
+    pdf = ocrgraft.finalize()
+    messages: Sequence[str] = []
+    if options.output_type != 'none':
+        # PDF/A and metadata
+        log.info("Postprocessing...")
+        pdf, messages = postprocess(pdf, context, executor)
+
+        # Copy PDF file to destination (we don't know the input PDF file name)
+        copy_final(pdf, options.output_file, None)
+    return messages
+
+
+def run_hocr_to_ocr_pdf_pipeline(
+    options: argparse.Namespace,
+    *,
+    plugin_manager: OcrmypdfPluginManager,
+) -> ExitCode:
+    """Run pipeline to convert hOCR to final output PDF."""
+    with manage_work_folder(
+        work_folder=options.work_folder, retain=True, print_location=False
+    ) as work_folder:
+        executor = setup_pipeline(options, plugin_manager)
+        origin_pdf = work_folder / 'origin.pdf'
+
+        # Gather pdfinfo and create context
+        pdfinfo = 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)
+
+        return report_output_pdf(options, origin_pdf, optimize_messages)

src/ocrmypdf/_pipelines/ocr.py

@@ -0,0 +1,214 @@
+# SPDX-FileCopyrightText: 2019-2023 James R. Barlow
+# SPDX-FileCopyrightText: 2019 Martin Wind
+# SPDX-License-Identifier: MPL-2.0
+
+"""Implements the concurrent and page synchronous parts of the pipeline."""
+
+from __future__ import annotations
+
+import argparse
+import logging
+import logging.handlers
+from collections.abc import Sequence
+from functools import partial
+from pathlib import Path
+from tempfile import mkdtemp
+
+import PIL
+
+from ocrmypdf._concurrent import Executor
+from ocrmypdf._graft import OcrGrafter
+from ocrmypdf._jobcontext import PageContext, PdfContext
+from ocrmypdf._pipeline import (
+    copy_final,
+    is_ocr_required,
+    merge_sidecars,
+    ocr_engine_hocr,
+    ocr_engine_textonly_pdf,
+    render_hocr_page,
+    triage,
+    validate_pdfinfo_options,
+)
+from ocrmypdf._pipelines._common import (
+    PageResult,
+    cli_exception_handler,
+    do_get_pdfinfo,
+    manage_debug_log_handler,
+    manage_work_folder,
+    postprocess,
+    process_page,
+    report_output_pdf,
+    set_thread_pageno,
+    setup_pipeline,
+    worker_init,
+)
+from ocrmypdf._plugin_manager import OcrmypdfPluginManager
+from ocrmypdf._progressbar import ProgressBar
+from ocrmypdf._validation import (
+    check_requested_output_file,
+    create_input_file,
+)
+from ocrmypdf.exceptions import ExitCode
+
+log = logging.getLogger(__name__)
+
+
+def _image_to_ocr_text(
+    page_context: PageContext, ocr_image_out: Path
+) -> tuple[Path, Path]:
+    """Run OCR engine on image to create OCR PDF and text file."""
+    options = page_context.options
+    if options.pdf_renderer.startswith('hocr'):
+        hocr_out, text_out = ocr_engine_hocr(ocr_image_out, page_context)
+        ocr_out = render_hocr_page(hocr_out, page_context)
+    elif options.pdf_renderer == 'sandwich':
+        ocr_out, text_out = ocr_engine_textonly_pdf(ocr_image_out, page_context)
+    else:
+        raise NotImplementedError(f"pdf_renderer {options.pdf_renderer}")
+    return ocr_out, text_out
+
+
+def _exec_page_sync(page_context: PageContext) -> PageResult:
+    """Execute a pipeline for a single page synchronously."""
+    set_thread_pageno(page_context.pageno + 1)
+
+    if not is_ocr_required(page_context):
+        return PageResult(pageno=page_context.pageno)
+
+    ocr_image_out, pdf_page_from_image_out, orientation_correction = process_page(
+        page_context
+    )
+    ocr_out, text_out = _image_to_ocr_text(page_context, ocr_image_out)
+    return PageResult(
+        pageno=page_context.pageno,
+        pdf_page_from_image=pdf_page_from_image_out,
+        ocr=ocr_out,
+        text=text_out,
+        orientation_correction=orientation_correction,
+    )
+
+
+def exec_concurrent(context: PdfContext, executor: Executor) -> Sequence[str]:
+    """Execute the OCR pipeline concurrently."""
+    options = context.options
+    max_workers = min(len(context.pdfinfo), options.jobs)
+    if max_workers > 1:
+        log.info("Start processing %d pages concurrently", max_workers)
+
+    sidecars: list[Path | None] = [None] * len(context.pdfinfo)
+    ocrgraft = OcrGrafter(context)
+
+    def update_page(result: PageResult, pbar: ProgressBar):
+        """After OCR is complete for a page, update the PDF."""
+        try:
+            set_thread_pageno(result.pageno + 1)
+            sidecars[result.pageno] = result.text
+            pbar.update(0.5)
+            ocrgraft.graft_page(
+                pageno=result.pageno,
+                image=result.pdf_page_from_image,
+                textpdf=result.ocr,
+                autorotate_correction=result.orientation_correction,
+            )
+            pbar.update(0.5)
+        finally:
+            set_thread_pageno(None)
+
+    executor(
+        use_threads=options.use_threads,
+        max_workers=max_workers,
+        progress_kwargs=dict(
+            total=len(context.pdfinfo),
+            desc='OCR' if options.tesseract_timeout > 0 else 'Image processing',
+            unit='page',
+            disable=not options.progress_bar,
+        ),
+        worker_initializer=partial(worker_init, PIL.Image.MAX_IMAGE_PIXELS),
+        task=_exec_page_sync,
+        task_arguments=context.get_page_context_args(),
+        task_finished=update_page,
+    )
+
+    # Output sidecar text
+    if options.sidecar:
+        text = merge_sidecars(sidecars, context)
+        # Copy text file to destination
+        copy_final(text, options.sidecar, options.input_file)
+
+    # Merge layers to one single pdf
+    pdf = ocrgraft.finalize()
+
+    messages: Sequence[str] = []
+    if options.output_type != 'none':
+        # PDF/A and metadata
+        log.info("Postprocessing...")
+        pdf, messages = postprocess(pdf, context, executor)
+
+        # Copy PDF file to destination
+        copy_final(pdf, options.output_file, options.input_file)
+    return messages
+
+
+def _run_pipeline(
+    options: argparse.Namespace,
+    plugin_manager: OcrmypdfPluginManager,
+) -> ExitCode:
+    with (
+        manage_work_folder(
+            work_folder=Path(mkdtemp(prefix="ocrmypdf.io.")),
+            retain=options.keep_temporary_files,
+            print_location=options.keep_temporary_files,
+        ) as work_folder,
+        manage_debug_log_handler(options=options, work_folder=work_folder),
+    ):
+        executor = setup_pipeline(options, plugin_manager)
+        check_requested_output_file(options)
+        start_input_file, original_filename = create_input_file(options, work_folder)
+
+        # Triage image or pdf
+        origin_pdf = triage(
+            original_filename, start_input_file, work_folder / 'origin.pdf', options
+        )
+
+        # Gather pdfinfo and create context
+        pdfinfo = do_get_pdfinfo(origin_pdf, executor, options)
+        context = PdfContext(options, work_folder, origin_pdf, pdfinfo, plugin_manager)
+
+        # Validate options are okay for this pdf
+        validate_pdfinfo_options(context)
+
+        # Execute the pipeline
+        optimize_messages = exec_concurrent(context, executor)
+
+        exitcode = report_output_pdf(options, start_input_file, optimize_messages)
+        return exitcode
+
+
+def run_pipeline_cli(
+    options: argparse.Namespace,
+    *,
+    plugin_manager: OcrmypdfPluginManager,
+) -> ExitCode:
+    """Run the OCR pipeline with command line exception handling.
+
+    Args:
+        options: The parsed command line options.
+        plugin_manager: The plugin manager to use. If not provided, one will be
+            created.
+    """
+    return cli_exception_handler(_run_pipeline, options, plugin_manager)
+
+
+def run_pipeline(
+    options: argparse.Namespace,
+    *,
+    plugin_manager: OcrmypdfPluginManager,
+) -> ExitCode:
+    """Run the OCR pipeline without command line exception handling.
+
+    Args:
+        options: The parsed command line options.
+        plugin_manager: The plugin manager to use. If not provided, one will be
+            created.
+    """
+    return _run_pipeline(options, plugin_manager)

src/ocrmypdf/_pipelines/pdf_to_hocr.py

@@ -0,0 +1,108 @@
+# SPDX-FileCopyrightText: 2019-2023 James R. Barlow
+# SPDX-FileCopyrightText: 2019 Martin Wind
+# SPDX-License-Identifier: MPL-2.0
+
+"""Implements the concurrent and page synchronous parts of the pipeline."""
+
+from __future__ import annotations
+
+import argparse
+import logging
+import logging.handlers
+import shutil
+from functools import partial
+
+import PIL
+
+from ocrmypdf._concurrent import Executor
+from ocrmypdf._jobcontext import PageContext, PdfContext
+from ocrmypdf._pipeline import (
+    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,
+    setup_pipeline,
+    worker_init,
+)
+from ocrmypdf._plugin_manager import OcrmypdfPluginManager
+from ocrmypdf._validation import (
+    set_lossless_reconstruction,
+)
+
+log = logging.getLogger(__name__)
+
+
+def _exec_page_hocr_sync(page_context: PageContext) -> HOCRResult:
+    """Execute a pipeline for a single page hOCR."""
+    set_thread_pageno(page_context.pageno + 1)
+
+    if not is_ocr_required(page_context):
+        return HOCRResult(pageno=page_context.pageno)
+
+    ocr_image_out, pdf_page_from_image_out, orientation_correction = process_page(
+        page_context
+    )
+    hocr_out, _ = ocr_engine_hocr(ocr_image_out, page_context)
+
+    result = HOCRResult(
+        pageno=page_context.pageno,
+        pdf_page_from_image=pdf_page_from_image_out,
+        hocr=hocr_out,
+        orientation_correction=orientation_correction,
+    )
+    page_context.get_path('hocr.json').write_text(result.to_json())
+    return result
+
+
+def exec_pdf_to_hocr(context: PdfContext, executor: Executor) -> None:
+    """Execute the OCR pipeline concurrently and output hOCR."""
+    # Run exec_page_sync on every page
+    options = context.options
+    max_workers = min(len(context.pdfinfo), options.jobs)
+    if max_workers > 1:
+        log.info("Start processing %d pages concurrently", max_workers)
+
+    executor(
+        use_threads=options.use_threads,
+        max_workers=max_workers,
+        progress_kwargs=dict(
+            total=(2 * len(context.pdfinfo)),
+            desc='hOCR',
+            unit='page',
+            unit_scale=0.5,
+            disable=not options.progress_bar,
+        ),
+        worker_initializer=partial(worker_init, PIL.Image.MAX_IMAGE_PIXELS),
+        task=_exec_page_hocr_sync,
+        task_arguments=context.get_page_context_args(),
+    )
+
+
+def run_hocr_pipeline(
+    options: argparse.Namespace,
+    *,
+    plugin_manager: OcrmypdfPluginManager,
+) -> None:
+    """Run pipeline to output hOCR."""
+    with manage_work_folder(
+        work_folder=options.output_folder, retain=True, print_location=False
+    ) as work_folder:
+        executor = setup_pipeline(options, plugin_manager)
+        origin_pdf = work_folder / 'origin.pdf'
+        shutil.copy2(options.input_file, origin_pdf)
+
+        # Gather pdfinfo and create context
+        pdfinfo = do_get_pdfinfo(origin_pdf, executor, options)
+        context = PdfContext(
+            options, work_folder, options.input_file, pdfinfo, plugin_manager
+        )
+        # Validate options are okay for this pdf
+        set_lossless_reconstruction(options)
+        validate_pdfinfo_options(context)
+        exec_pdf_to_hocr(context, executor)

src/ocrmypdf/_plugin_manager.py

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

src/ocrmypdf/_progressbar.py

@@ -0,0 +1,243 @@
+# SPDX-FileCopyrightText: 2023 James R. Barlow
+# SPDX-License-Identifier: MPL-2.0
+
+"""Defines progress bar API."""
+
+from __future__ import annotations
+
+from typing import Protocol
+
+from rich.console import Console
+from rich.progress import (
+    BarColumn,
+    MofNCompleteColumn,
+    Progress,
+    TaskProgressColumn,
+    TextColumn,
+    TimeRemainingColumn,
+)
+from rich.table import Column
+
+
+class ProgressBar(Protocol):
+    """The protocol that OCRmyPDF expects progress bar classes to be compatible with.
+
+    In practice this could be used for any time of monitoring, not just a progress bar.
+
+    Calling the class should return a new progress bar object, which is activated
+    with ``__enter__`` and terminated with ``__exit__``. An update method is called
+    whenever the progress bar is updated. Progress bar objects will not be reused;
+    a new one will be created for each group of tasks.
+
+    The progress bar is held in the main process/thread and not updated by child
+    process/threads. When a child notifies the parent of completed work, the
+    parent updates the progress bar.
+    Progress bars should never write to ``sys.stdout``, or they will corrupt the
+    output if OCRmyPDF writes a PDF to standard output.
+
+    Note:
+        The type of events that OCRmyPDF reports to a progress bar may change in
+    minor releases.
+
+    Args:
+        total (int | float | None):
+            The total number of work units expected. If ``None``, the total is unknown.
+            For example, if you are processing pages, this might be the number of pages,
+            or if you are measuring overall progress in percent, this might be 100.
+        desc (str | None):
+            A brief description of the current step (e.g. "Scanning contents",
+            "OCR", "PDF/A conversion"). OCRmyPDF updates this before each major step.
+        unit (str | None):
+            A short label for the type of work being tracked (e.g. "page", "%", "image").
+        disable (bool):
+            If ``True``, progress updates are suppressed (no output). Defaults to ``False``.
+        **kwargs:
+            Future or extra parameters that OCRmyPDF might pass. Implementations
+            should accept and ignore unrecognized keywords gracefully.
+
+    Example:
+        A simple plugin implementation could look like this:
+
+        .. code-block:: python
+
+            from ocrmypdf.pluginspec import ProgressBar
+            from ocrmypdf import hookimpl
+
+            class ConsoleProgressBar(ProgressBar):
+                def __init__(self, *, total=None, desc=None, unit=None, disable=False, **kwargs):
+                    self.total = total
+                    self.desc = desc
+                    self.unit = unit
+                    self.disable = disable
+                    self.current = 0
+
+                def __enter__(self):
+                    if not self.disable:
+                        print(f"Starting {self.desc or 'an OCR task'} (total={self.total} {self.unit})")
+                    return self
+
+                def __exit__(self, exc_type, exc_value, traceback):
+                    if not self.disable:
+                        if exc_type is None:
+                            print("Completed successfully.")
+                        else:
+                            print(f"Task ended with error: {exc_value}")
+                    return False  # Let OCRmyPDF raise any exceptions
+
+                def update(self, n=1, *, completed=None):
+                    if completed is not None:
+                        # If 'completed' is given, you could set self.current = completed
+                        # but let's just read it to show usage
+                        print(f"Absolute completion reported: {completed}")
+                    # Otherwise, we increment by 'n'
+                    self.current += n
+                    if not self.disable:
+                        if self.total:
+                            percent = (self.current / self.total) * 100
+                            print(f"{self.desc}: {self.current}/{self.total} ({percent:.1f}%)")
+                        else:
+                            print(f"{self.desc}: {self.current} units done")
+
+            @hookimpl
+            def get_progressbar_class():
+                return MyProgressBar
+
+    """
+
+    def __init__(
+        self,
+        *,
+        total: int | float | None,
+        desc: str | None,
+        unit: str | None,
+        disable: bool = False,
+        **kwargs,
+    ):
+        """Initialize a progress bar.
+
+        This is called once before any work is done. OCRmyPDF supplies the total
+        number of units (or None if unknown), a description of the work, and the
+        type of units. The ``disable`` parameter can be used to turn off progress
+        reporting. Unrecognized keyword arguments should be ignored.
+
+        Args:
+            total (int | float | None):
+                The total amount of work. If ``None``, the total is unknown.
+            desc (str | None):
+                A description of the current task. May change for different stages.
+            unit (str | None):
+                A short label for the unit of work.
+            disable (bool):
+                If ``True``, no output or logging should be displayed.
+            **kwargs:
+                Extra parameters that may be passed by OCRmyPDF in future versions.
+        """
+
+    def __enter__(self):
+        """Enter a progress bar context."""
+
+    def __exit__(self, *args):
+        """Exit a progress bar context."""
+
+    def update(self, n: float = 1, *, completed: float | None = None):
+        """Increment the progress bar by ``n`` units, or set an absolute completion.
+
+        OCRmyPDF calls this method repeatedly while processing pages or other tasks.
+        If your total is known and you track it, you might do something like:
+
+        .. code-block:: python
+
+            self.current += n
+            percent = (self.current / total) * 100
+
+        The ``completed`` argument can indicate an absolute position, which is
+        particularly helpful if you're tracking a percentage of work (e.g., 0 to 100)
+        and want precise updates. In contrast, the incremental parameter ``n`` is
+        often more useful for page-based increments.
+
+        Args:
+            n (float, optional):
+                The amount to increment the progress by. Defaults to 1. May be
+                fractional if OCRmyPDF performs partial steps. If you are tracking
+                pages, this is typically how many pages have been processed in the
+                most recent step.
+            completed (float | None, optional):
+                The absolute amount of work completed so far. This can override or
+                supplement the simple increment logic. It's particularly useful
+                for percentage-based tracking (e.g., when ``total`` is 100).
+        """
+
+
+class NullProgressBar:
+    """Progress bar API that takes no actions."""
+
+    def __init__(self, **kwargs):
+        pass
+
+    def __enter__(self):
+        return self
+
+    def __exit__(self, exc_type, exc_value, traceback):
+        return False
+
+    def update(self, _arg=None, *, completed=None):
+        return
+
+
+class RichProgressBar:
+    """Display progress bar using rich."""
+
+    def __init__(
+        self,
+        *,
+        console: Console,
+        desc: str,
+        total: float | None = None,
+        unit: str | None = None,
+        unit_scale: float | None = 1.0,
+        disable: bool = False,
+        **kwargs,
+    ):
+        self._entered = False
+        self.progress = Progress(
+            TextColumn(
+                "[progress.description]{task.description}",
+                table_column=Column(min_width=20),
+            ),
+            BarColumn(),
+            TaskProgressColumn(),
+            MofNCompleteColumn(),
+            TimeRemainingColumn(),
+            console=console,
+            auto_refresh=True,
+            redirect_stderr=True,
+            redirect_stdout=False,
+            disable=disable,
+            **kwargs,
+        )
+        self.unit_scale = unit_scale
+        self.progress_bar = self.progress.add_task(
+            desc,
+            total=total * self.unit_scale
+            if total is not None and self.unit_scale is not None
+            else None,
+            unit=unit,
+        )
+
+    def __enter__(self):
+        self.progress.start()
+        self._entered = True
+        return self
+
+    def __exit__(self, exc_type, exc_value, traceback):
+        self.progress.refresh()
+        self.progress.stop()
+        return False
+
+    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/_sync.py

@@ -1,467 +0,0 @@
-# SPDX-FileCopyrightText: 2022 James R. Barlow
-# SPDX-License-Identifier: MPL-2.0
-
-"""Implements the concurrent and page synchronous parts of the pipeline."""
-
-
-from __future__ import annotations
-
-import argparse
-import logging
-import logging.handlers
-import os
-import sys
-import threading
-from concurrent.futures.process import BrokenProcessPool
-from concurrent.futures.thread import BrokenThreadPool
-from functools import partial
-from pathlib import Path
-from tempfile import mkdtemp
-from typing import NamedTuple, Sequence, cast
-
-import PIL
-
-from ocrmypdf._concurrent import Executor, setup_executor
-from ocrmypdf._graft import OcrGrafter
-from ocrmypdf._jobcontext import PageContext, PdfContext, cleanup_working_files
-from ocrmypdf._logging import PageNumberFilter
-from ocrmypdf._pipeline import (
-    convert_to_pdfa,
-    copy_final,
-    create_ocr_image,
-    create_pdf_page_from_image,
-    create_visible_page_jpg,
-    generate_postscript_stub,
-    get_orientation_correction,
-    get_pdfinfo,
-    is_ocr_required,
-    merge_sidecars,
-    metadata_fixup,
-    ocr_engine_hocr,
-    ocr_engine_textonly_pdf,
-    optimize_pdf,
-    preprocess_clean,
-    preprocess_deskew,
-    preprocess_remove_background,
-    rasterize,
-    rasterize_preview,
-    render_hocr_page,
-    should_visible_page_image_use_jpg,
-    triage,
-    validate_pdfinfo_options,
-)
-from ocrmypdf._plugin_manager import OcrmypdfPluginManager, get_plugin_manager
-from ocrmypdf._validation import (
-    check_requested_output_file,
-    create_input_file,
-    report_output_file_size,
-)
-from ocrmypdf.exceptions import ExitCode, ExitCodeException
-from ocrmypdf.helpers import (
-    NeverRaise,
-    available_cpu_count,
-    check_pdf,
-    pikepdf_enable_mmap,
-    samefile,
-)
-from ocrmypdf.pdfa import file_claims_pdfa
-
-log = logging.getLogger(__name__)
-
-
-class PageResult(NamedTuple):
-    """Result when a page is finished processing."""
-
-    pageno: int
-    pdf_page_from_image: Path | None
-    ocr: Path | None
-    text: Path | None
-    orientation_correction: int
-
-
-tls = threading.local()
-tls.pageno = None
-
-
-old_factory = logging.getLogRecordFactory()
-
-
-def record_factory(*args, **kwargs):
-    record = old_factory(*args, **kwargs)
-    if hasattr(tls, 'pageno'):
-        record.pageno = tls.pageno
-    return record
-
-
-logging.setLogRecordFactory(record_factory)
-
-
-def preprocess(
-    page_context: PageContext,
-    image: Path,
-    remove_background: bool,
-    deskew: bool,
-    clean: bool,
-) -> Path:
-    if remove_background:
-        image = preprocess_remove_background(image, page_context)
-    if deskew:
-        image = preprocess_deskew(image, page_context)
-    if clean:
-        image = preprocess_clean(image, page_context)
-    return image
-
-
-def make_intermediate_images(
-    page_context: PageContext, orientation_correction: int
-) -> tuple[Path, Path | None]:
-    options = page_context.options
-
-    ocr_image = preprocess_out = None
-    rasterize_out = rasterize(
-        page_context.origin,
-        page_context,
-        correction=orientation_correction,
-        remove_vectors=False,
-    )
-
-    if not any([options.clean, options.clean_final, options.remove_vectors]):
-        ocr_image = preprocess_out = preprocess(
-            page_context,
-            rasterize_out,
-            options.remove_background,
-            options.deskew,
-            clean=False,
-        )
-    else:
-        if not options.lossless_reconstruction:
-            preprocess_out = preprocess(
-                page_context,
-                rasterize_out,
-                options.remove_background,
-                options.deskew,
-                clean=options.clean_final,
-            )
-        if options.remove_vectors:
-            rasterize_ocr_out = rasterize(
-                page_context.origin,
-                page_context,
-                correction=orientation_correction,
-                remove_vectors=True,
-                output_tag='_ocr',
-            )
-        else:
-            rasterize_ocr_out = rasterize_out
-
-        if (
-            preprocess_out
-            and rasterize_ocr_out == rasterize_out
-            and options.clean == options.clean_final
-        ):
-            # Optimization: image for OCR is identical to presentation image
-            ocr_image = preprocess_out
-        else:
-            ocr_image = preprocess(
-                page_context,
-                rasterize_ocr_out,
-                options.remove_background,
-                options.deskew,
-                clean=options.clean,
-            )
-    return ocr_image, preprocess_out
-
-
-def exec_page_sync(page_context: PageContext) -> PageResult:
-    options = page_context.options
-    tls.pageno = page_context.pageno + 1
-
-    if not is_ocr_required(page_context):
-        return PageResult(
-            pageno=page_context.pageno,
-            pdf_page_from_image=None,
-            ocr=None,
-            text=None,
-            orientation_correction=0,
-        )
-
-    orientation_correction = 0
-    if options.rotate_pages:
-        # Rasterize
-        rasterize_preview_out = rasterize_preview(page_context.origin, page_context)
-        orientation_correction = get_orientation_correction(
-            rasterize_preview_out, page_context
-        )
-
-    ocr_image, preprocess_out = make_intermediate_images(
-        page_context, orientation_correction
-    )
-    ocr_image_out = create_ocr_image(ocr_image, page_context)
-
-    pdf_page_from_image_out = None
-    if not options.lossless_reconstruction:
-        assert preprocess_out
-        visible_image_out = preprocess_out
-        if should_visible_page_image_use_jpg(page_context.pageinfo):
-            visible_image_out = create_visible_page_jpg(visible_image_out, page_context)
-        filtered_image = page_context.plugin_manager.hook.filter_page_image(
-            page=page_context, image_filename=visible_image_out
-        )
-        if filtered_image:
-            visible_image_out = filtered_image
-        pdf_page_from_image_out = create_pdf_page_from_image(
-            visible_image_out, page_context, orientation_correction
-        )
-
-    if options.pdf_renderer.startswith('hocr'):
-        (hocr_out, text_out) = ocr_engine_hocr(ocr_image_out, page_context)
-        ocr_out = render_hocr_page(hocr_out, page_context)
-    elif options.pdf_renderer == 'sandwich':
-        (ocr_out, text_out) = ocr_engine_textonly_pdf(ocr_image_out, page_context)
-    else:
-        raise NotImplementedError(f"pdf_renderer {options.pdf_renderer}")
-
-    return PageResult(
-        pageno=page_context.pageno,
-        pdf_page_from_image=pdf_page_from_image_out,
-        ocr=ocr_out,
-        text=text_out,
-        orientation_correction=orientation_correction,
-    )
-
-
-def post_process(
-    pdf_file: Path, context: PdfContext, executor: Executor
-) -> tuple[Path, Sequence[str]]:
-    pdf_out = pdf_file
-    if context.options.output_type.startswith('pdfa'):
-        ps_stub_out = generate_postscript_stub(context)
-        pdf_out = convert_to_pdfa(pdf_out, ps_stub_out, context)
-
-    pdf_out = metadata_fixup(pdf_out, context)
-    return optimize_pdf(pdf_out, context, executor)
-
-
-def worker_init(max_pixels: int) -> None:
-    # In Windows, child process will not inherit our change to this value in
-    # the parent process, so ensure workers get it set. Not needed when running
-    # threaded, but harmless to set again.
-    PIL.Image.MAX_IMAGE_PIXELS = max_pixels
-    pikepdf_enable_mmap()
-
-
-def exec_concurrent(context: PdfContext, executor: Executor) -> Sequence[str]:
-    """Execute the pipeline concurrently"""
-
-    # Run exec_page_sync on every page context
-    options = context.options
-    max_workers = min(len(context.pdfinfo), options.jobs)
-    if max_workers > 1:
-        log.info("Start processing %d pages concurrently", max_workers)
-
-    sidecars: list[Path | None] = [None] * len(context.pdfinfo)
-    ocrgraft = OcrGrafter(context)
-
-    def update_page(result: PageResult, pbar):
-        try:
-            tls.pageno = result.pageno + 1
-            sidecars[result.pageno] = result.text
-            pbar.update()
-            ocrgraft.graft_page(
-                pageno=result.pageno,
-                image=result.pdf_page_from_image,
-                textpdf=result.ocr,
-                autorotate_correction=result.orientation_correction,
-            )
-            pbar.update()
-        finally:
-            tls.pageno = None
-
-    executor(
-        use_threads=options.use_threads,
-        max_workers=max_workers,
-        tqdm_kwargs=dict(
-            total=(2 * len(context.pdfinfo)),
-            desc='OCR' if options.tesseract_timeout > 0 else 'Image processing',
-            unit='page',
-            unit_scale=0.5,
-            disable=not options.progress_bar,
-        ),
-        worker_initializer=partial(worker_init, PIL.Image.MAX_IMAGE_PIXELS),
-        task=exec_page_sync,
-        task_arguments=context.get_page_contexts(),
-        task_finished=update_page,
-    )
-
-    # Output sidecar text
-    if options.sidecar:
-        text = merge_sidecars(sidecars, context)
-        # Copy text file to destination
-        copy_final(text, options.sidecar, context)
-
-    # Merge layers to one single pdf
-    pdf = ocrgraft.finalize()
-
-    messages: Sequence[str] = []
-    if options.output_type != 'none':
-        # PDF/A and metadata
-        log.info("Postprocessing...")
-        pdf, messages = post_process(pdf, context, executor)
-
-        # Copy PDF file to destination
-        copy_final(pdf, options.output_file, context)
-    return messages
-
-
-def configure_debug_logging(
-    log_filename: Path, prefix: str = ''
-) -> logging.FileHandler:
-    """
-    Create a debug log file at a specified location.
-
-    Arguments:
-        log_filename: Where to the put the log file.
-        prefix: The logging domain prefix that should be sent to the log.
-    """
-    log_file_handler = logging.FileHandler(log_filename, delay=True)
-    log_file_handler.setLevel(logging.DEBUG)
-    formatter = logging.Formatter(
-        '[%(asctime)s] - %(name)s - %(levelname)7s -%(pageno)s %(message)s'
-    )
-    log_file_handler.setFormatter(formatter)
-    log_file_handler.addFilter(PageNumberFilter())
-    logging.getLogger(prefix).addHandler(log_file_handler)
-    return log_file_handler
-
-
-def run_pipeline(
-    options: argparse.Namespace,
-    *,
-    plugin_manager: OcrmypdfPluginManager | None,
-    api: bool = False,
-) -> ExitCode:
-    # Any changes to options will not take effect for options that are already
-    # bound to function parameters in the pipeline. (For example
-    # options.input_file, options.pdf_renderer are already bound.)
-    if not options.jobs:
-        options.jobs = available_cpu_count()
-    if not plugin_manager:
-        plugin_manager = get_plugin_manager(options.plugins)
-
-    work_folder = Path(mkdtemp(prefix="ocrmypdf.io."))
-    debug_log_handler = None
-    if (
-        (options.keep_temporary_files or options.verbose >= 1)
-        and not os.environ.get('PYTEST_CURRENT_TEST', '')
-        and not api
-    ):
-        # Debug log for command line interface only with verbose output
-        # See https://github.com/pytest-dev/pytest/issues/5502 for why we skip this
-        # when pytest is running
-        debug_log_handler = configure_debug_logging(
-            Path(work_folder) / "debug.log"
-        )  # pragma: no cover
-
-    pikepdf_enable_mmap()
-
-    executor = setup_executor(plugin_manager)
-    try:
-        check_requested_output_file(options)
-        start_input_file, original_filename = create_input_file(options, work_folder)
-
-        # Triage image or pdf
-        origin_pdf = triage(
-            original_filename, start_input_file, work_folder / 'origin.pdf', options
-        )
-
-        # Gather pdfinfo and create context
-        pdfinfo = get_pdfinfo(
-            origin_pdf,
-            executor=executor,
-            detailed_analysis=options.redo_ocr,
-            progbar=options.progress_bar,
-            max_workers=options.jobs if not options.use_threads else 1,  # To help debug
-            check_pages=options.pages,
-        )
-
-        context = PdfContext(options, work_folder, origin_pdf, pdfinfo, plugin_manager)
-
-        # Validate options are okay for this pdf
-        validate_pdfinfo_options(context)
-
-        # Execute the pipeline
-        optimize_messages = exec_concurrent(context, executor)
-
-        if options.output_file == '-':
-            log.info("Output sent to stdout")
-        elif (
-            hasattr(options.output_file, 'writable') and options.output_file.writable()
-        ):
-            log.info("Output written to stream")
-        elif samefile(options.output_file, Path(os.devnull)):
-            pass  # Say nothing when sending to dev null
-        else:
-            if options.output_type.startswith('pdfa'):
-                pdfa_info = file_claims_pdfa(options.output_file)
-                if pdfa_info['pass']:
-                    log.info(
-                        "Output file is a %s (as expected)", pdfa_info['conformance']
-                    )
-                else:
-                    log.warning(
-                        "Output file is okay but is not PDF/A (seems to be %s)",
-                        pdfa_info['conformance'],
-                    )
-                    return ExitCode.pdfa_conversion_failed
-            if not check_pdf(options.output_file):
-                log.warning('Output file: The generated PDF is INVALID')
-                return ExitCode.invalid_output_pdf
-            report_output_file_size(
-                options, start_input_file, options.output_file, optimize_messages
-            )
-
-    except (KeyboardInterrupt if not api else NeverRaise):
-        if options.verbose >= 1:
-            log.exception("KeyboardInterrupt")
-        else:
-            log.error("KeyboardInterrupt")
-        return ExitCode.ctrl_c
-    except (ExitCodeException if not api else NeverRaise) as e:
-        e = cast(ExitCodeException, e)
-        if options.verbose >= 1:
-            log.exception("ExitCodeException")
-        elif str(e):
-            log.error("%s: %s", type(e).__name__, str(e))
-        else:
-            log.error(type(e).__name__)
-        return e.exit_code
-    except (PIL.Image.DecompressionBombError if not api else NeverRaise):
-        log.exception(
-            "A decompression bomb error was encountered while executing the "
-            "pipeline. Use the argument --max-image-mpixels to raise the maximum "
-            "image pixel limit."
-        )
-        return ExitCode.other_error
-    except (
-        BrokenProcessPool if not api else NeverRaise,
-        BrokenThreadPool if not api else NeverRaise,
-    ):
-        log.exception(
-            "A worker process was terminated unexpectedly. This is known to occur if "
-            "processing your file takes all available swap space and RAM. It may "
-            "help to try again with a smaller number of jobs, using the --jobs "
-            "argument."
-        )
-        return ExitCode.child_process_error
-    except (Exception if not api else NeverRaise):  # pylint: disable=broad-except
-        log.exception("An exception occurred while executing the pipeline")
-        return ExitCode.other_error
-    finally:
-        if debug_log_handler:
-            try:
-                debug_log_handler.close()
-                log.removeHandler(debug_log_handler)
-            except OSError as e:
-                print(e, file=sys.stderr)
-        cleanup_working_files(work_folder, options)
-
-    return ExitCode.ok

src/ocrmypdf/_validation.py

@@ -12,14 +12,15 @@ import os
 import sys
 import unicodedata
 from argparse import Namespace
+from collections.abc import Sequence
 from pathlib import Path
 from shutil import copyfileobj
-from typing import Sequence
 
 import pikepdf
 import PIL
 from pluggy import PluginManager
 
+from ocrmypdf._defaults import DEFAULT_LANGUAGE, DEFAULT_ROTATE_PAGES_THRESHOLD
 from ocrmypdf._exec import unpaper
 from ocrmypdf.exceptions import (
     BadArgsError,
@@ -27,59 +28,60 @@ from ocrmypdf.exceptions import (
     MissingDependencyError,
     OutputFileAccessError,
 )
-from ocrmypdf.helpers import is_file_writable, monotonic, safe_symlink
-from ocrmypdf.hocrtransform import HOCR_OK_LANGS
+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 os.name == 'nt' and sys.maxsize <= 2**32:  # pragma: no cover
-        # 32-bit interpreter on Windows
-        log.error(
-            "You are running OCRmyPDF in a 32-bit (x86) Python interpreter."
+    if sys.maxsize <= 2**32:  # pragma: no cover
+        log.warning(
+            "You are running OCRmyPDF in a 32-bit (x86) Python interpreter. "
+            "This is not supported. 32-bit does not have enough address space "
+            "to process large files. "
             "Please use a 64-bit (x86-64) version of Python."
         )
 
 
-def check_options_languages(options: Namespace, ocr_engine_languages: set[str]) -> None:
+def check_options_languages(
+    options: Namespace, ocr_engine_languages: list[str]
+) -> None:
     if not options.languages:
-        options.languages = {DEFAULT_LANGUAGE}
+        options.languages = [DEFAULT_LANGUAGE]
         system_lang = locale.getlocale()[0]
         if system_lang and not system_lang.startswith('en'):
             log.debug("No language specified; assuming --language %s", DEFAULT_LANGUAGE)
     if not ocr_engine_languages:
         return
-    missing_languages = options.languages - ocr_engine_languages
+
+    missing_languages = set(options.languages) - set(ocr_engine_languages)
     if missing_languages:
+        lang_text = '\n'.join(lang for lang in missing_languages)
         msg = (
             "OCR engine does not have language data for the following "
             "requested languages: \n"
+            f"{lang_text}\n"
+            "Please install the appropriate language data for your OCR engine.\n"
+            "\n"
+            "See the online documentation for instructions:\n"
+            "    https://ocrmypdf.readthedocs.io/en/latest/languages.html\n"
+            "\n"
+            "Note: most languages are identified by a 3-letter ISO 639-2 Code.\n"
+            "For example, English is 'eng', German is 'deu', and Spanish is 'spa'.\n"
+            "Simplified Chinese is 'chi_sim' and Traditional Chinese is 'chi_tra'."
+            "\n"
         )
-        msg += '\n'.join(lang for lang in missing_languages)
-        msg += '\nNote: most languages are identified by a 3-digit ISO 639-2 Code'
         raise MissingDependencyError(msg)
 
 
 def check_options_output(options: Namespace) -> None:
-    is_latin = options.languages.issubset(HOCR_OK_LANGS)
-
-    if options.pdf_renderer.startswith('hocr') and not is_latin:
-        log.warning(
-            "The 'hocr' PDF renderer is known to cause problems with one "
-            "or more of the languages in your document.  Use "
-            "`--pdf-renderer auto` (the default) to avoid this issue."
-        )
-
     if options.output_type == 'none' and options.output_file not in (os.devnull, '-'):
         raise BadArgsError(
             "Since you specified `--output-type none`, the output file "
@@ -87,6 +89,8 @@ def check_options_output(options: Namespace) -> None:
             f"`-` to suppress this message."
         )
 
+
+def set_lossless_reconstruction(options: Namespace) -> None:
     lossless_reconstruction = False
     if not any(
         (
@@ -109,12 +113,10 @@ def check_options_output(options: Namespace) -> None:
 def check_options_sidecar(options: Namespace) -> None:
     if options.sidecar == '\0':
         if options.output_file == '-':
-            raise BadArgsError(
-                "--sidecar filename must be specified when output file is stdout."
-            )
+            raise BadArgsError("--sidecar filename needed when output file is stdout.")
         elif options.output_file == os.devnull:
             raise BadArgsError(
-                "--sidecar filename must be specified when output file is /dev/null or NUL."
+                "--sidecar filename needed when output file is /dev/null or NUL."
             )
         options.sidecar = options.output_file + '.txt'
     if options.sidecar == options.input_file or options.sidecar == options.output_file:
@@ -128,13 +130,18 @@ 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',
             package='unpaper',
             version_checker=unpaper.version,
             need_version='6.1',
-            required_for=['--clean, --clean-final'],
+            required_for="--clean, --clean-final",  # Problem arguments
         )
         try:
             if options.unpaper_args:
@@ -195,16 +202,6 @@ def check_options_ocr_behavior(options: Namespace) -> None:
         options.pages = _pages_from_ranges(options.pages)
 
 
-def check_options_advanced(options: Namespace) -> None:
-    if options.pdfa_image_compression != 'auto' and not options.output_type.startswith(
-        'pdfa'
-    ):
-        log.warning(
-            "--pdfa-image-compression argument only applies when "
-            "--output-type is one of 'pdfa', 'pdfa-1', or 'pdfa-2'"
-        )
-
-
 def check_options_metadata(options: Namespace) -> None:
     docinfo = [options.title, options.author, options.keywords, options.subject]
     for s in (m for m in docinfo if m):
@@ -221,17 +218,17 @@ def check_options_metadata(options: Namespace) -> None:
 def check_options_pillow(options: Namespace) -> None:
     PIL.Image.MAX_IMAGE_PIXELS = int(options.max_image_mpixels * 1_000_000)
     if PIL.Image.MAX_IMAGE_PIXELS == 0:
-        PIL.Image.MAX_IMAGE_PIXELS = None
+        PIL.Image.MAX_IMAGE_PIXELS = None  # type: ignore
 
 
 def _check_plugin_invariant_options(options: Namespace) -> None:
     check_platform()
     check_options_metadata(options)
     check_options_output(options)
+    set_lossless_reconstruction(options)
     check_options_sidecar(options)
     check_options_preprocessing(options)
     check_options_ocr_behavior(options)
-    check_options_advanced(options)
     check_options_pillow(options)
 
 
@@ -269,14 +266,24 @@ def create_input_file(options: Namespace, work_folder: Path) -> tuple[Path, str]
             return target, os.fspath(options.input_file)
         except FileNotFoundError as e:
             msg = f"File not found - {options.input_file}"
-            if Path('/.dockerenv').exists():  # pragma: no cover
+            if running_in_docker():  # pragma: no cover
                 msg += (
-                    "\nDocker cannot your working directory unless you "
+                    "\nDocker cannot access your working directory unless you "
                     "explicitly share it with the Docker container and set up"
                     "permissions correctly.\n"
                     "You may find it easier to use stdin/stdout:"
                     "\n"
-                    "\tdocker run -i --rm jbarlow83/ocrmypdf - - <input.pdf >output.pdf\n"
+                    "\tdocker run -i --rm jbarlow83/ocrmypdf - - <input.pdf >output.pdf"
+                    "\n"
+                )
+            elif running_in_snap():  # pragma: no cover
+                msg += (
+                    "\nSnap applications cannot access files outside of "
+                    "your home directory unless you explicitly allow it. "
+                    "You may find it easier to use stdin/stdout:"
+                    "\n"
+                    "\tsnap run ocrmypdf - - <input.pdf >output.pdf"
+                    "\n"
                 )
             raise InputFileError(msg) from e
 
@@ -333,7 +340,7 @@ def report_output_file_size(
     for arg in image_preproc:
         if getattr(options, arg, False):
             reasons.append(
-                f"The argument --{arg.replace('_', '-')} was issued, causing transcoding."
+                f"--{arg.replace('_', '-')} was issued, causing transcoding."
             )
 
     reasons.extend(optimize_messages)

src/ocrmypdf/_version.py

@@ -1,19 +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
-
-try:
-    from importlib.metadata import version as _package_version
-except ImportError:
-    from importlib_metadata import version as _package_version  # type: ignore
-
-PROGRAM_NAME = 'ocrmypdf'
-
-# Official PEP 396
-__version__ = _package_version('ocrmypdf')

src/ocrmypdf/api.py

@@ -9,31 +9,31 @@ import logging
 import os
 import sys
 import threading
+from argparse import Namespace
+from collections.abc import Iterable, Sequence
 from enum import IntEnum
 from io import IOBase
 from pathlib import Path
-from typing import AnyStr, BinaryIO, Iterable, Union
+from typing import BinaryIO
 from warnings import warn
 
-from ocrmypdf._logging import PageNumberFilter, TqdmConsole
+import pluggy
+
+from ocrmypdf._logging import PageNumberFilter
+from ocrmypdf._pipelines.hocr_to_ocr_pdf import run_hocr_to_ocr_pdf_pipeline
+from ocrmypdf._pipelines.ocr import run_pipeline, run_pipeline_cli
+from ocrmypdf._pipelines.pdf_to_hocr import run_hocr_pipeline
 from ocrmypdf._plugin_manager import get_plugin_manager
-from ocrmypdf._sync import run_pipeline
 from ocrmypdf._validation import check_options
 from ocrmypdf.cli import ArgumentParser, get_parser
 from ocrmypdf.helpers import is_iterable_notstr
 
-try:
-    import coloredlogs
-except ModuleNotFoundError:
-    coloredlogs = None  # pylint: disable=invalid-name
-
-if coloredlogs:
-    from humanfriendly.terminal import enable_ansi_support
-
-
-StrPath = Union[Path, AnyStr]
-PathOrIO = Union[BinaryIO, StrPath]
+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
+# plugins at the same time.
 _api_lock = threading.Lock()
 
 
@@ -52,7 +52,7 @@ def configure_logging(
     *,
     progress_bar_friendly: bool = True,
     manage_root_logger: bool = False,
-    plugin_manager=None,
+    plugin_manager: pluggy.PluginManager | None = None,
 ):
     """Set up logging.
 
@@ -92,7 +92,6 @@ def configure_logging(
     Returns:
         The toplevel logger for ocrmypdf (or the root logger, if we are managing it).
     """
-
     prefix = '' if manage_root_logger else 'ocrmypdf'
 
     log = logging.getLogger(prefix)
@@ -119,14 +118,7 @@ def configure_logging(
     else:
         fmt = '%(pageno)s%(message)s'
 
-    use_colors = progress_bar_friendly
     formatter = None
-    if coloredlogs and use_colors:
-        use_colors = enable_ansi_support()
-        if use_colors:
-            use_colors = coloredlogs.terminal_supports_colors()
-        if use_colors:
-            formatter = coloredlogs.ColoredFormatter(fmt=fmt)
 
     if not formatter:
         formatter = logging.Formatter(fmt=fmt)
@@ -146,20 +138,19 @@ def configure_logging(
     return log
 
 
-def create_options(
-    *, input_file: PathOrIO, output_file: PathOrIO, parser: ArgumentParser, **kwargs
-):
-    cmdline = []
-    deferred = []
-
+def _kwargs_to_cmdline(
+    *, defer_kwargs: set[str], **kwargs
+) -> tuple[list[str | bytes], dict[str, str | bytes]]:
+    """Convert kwargs to command line arguments."""
+    cmdline: list[str | bytes] = []
+    deferred = {}
     for arg, val in kwargs.items():
         if val is None:
             continue
 
-        # These arguments with special handling for which we bypass
-        # argparse
-        if arg in {'progress_bar', 'plugins'}:
-            deferred.append((arg, val))
+        # Skip arguments that are handled elsewhere
+        if arg in defer_kwargs:
+            deferred[arg] = val
             continue
 
         cmd_style_arg = arg.replace('_', '-')
@@ -178,7 +169,7 @@ def create_options(
 
         # 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)
@@ -186,82 +177,129 @@ def create_options(
             cmdline.append(str(val))
         else:
             raise TypeError(f"{arg}: {val} ({type(val)})")
+    return cmdline, deferred
 
-    if isinstance(input_file, (BinaryIO, IOBase)):
+
+def create_options(
+    *, input_file: PathOrIO, output_file: PathOrIO, parser: ArgumentParser, **kwargs
+) -> Namespace:
+    """Construct an options object from the input/output files and keyword arguments.
+
+    Args:
+        input_file: Input file path or file object.
+        output_file: Output file path or file object.
+        parser: ArgumentParser object.
+        **kwargs: Keyword arguments.
+
+    Returns:
+        argparse.Namespace: A Namespace object containing the parsed arguments.
+
+    Raises:
+        TypeError: If the type of a keyword argument is not supported.
+    """
+    cmdline, deferred = _kwargs_to_cmdline(
+        defer_kwargs={'progress_bar', 'plugins', 'parser', 'input_file', 'output_file'},
+        **kwargs,
+    )
+    if isinstance(input_file, BinaryIO | IOBase):
         cmdline.append('stream://input_file')
     else:
         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)
-    for keyword, val in deferred:
+    for keyword, val in deferred.items():
         setattr(options, keyword, val)
 
     if options.input_file == 'stream://input_file':
         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
 
 
-def ocr(  # pylint: disable=unused-argument
+def ocr(  # noqa: D417
     input_file: PathOrIO,
     output_file: PathOrIO,
     *,
-    language: Iterable[str] = None,
-    image_dpi: int = None,
-    output_type=None,
-    sidecar: StrPath | None = None,
-    jobs: int = None,
-    use_threads: bool = None,
-    title: str = None,
-    author: str = None,
-    subject: str = None,
-    keywords: str = None,
-    rotate_pages: bool = None,
-    remove_background: bool = None,
-    deskew: bool = None,
-    clean: bool = None,
-    clean_final: bool = None,
-    unpaper_args: str = None,
-    oversample: int = None,
-    remove_vectors: bool = None,
-    force_ocr: bool = None,
-    skip_text: bool = None,
-    redo_ocr: bool = None,
-    skip_big: float = None,
-    optimize: int = None,
-    jpg_quality: int = None,
-    png_quality: int = None,
-    jbig2_lossy: bool = None,
-    jbig2_page_group_size: int = None,
-    pages: str = None,
-    max_image_mpixels: float = None,
-    tesseract_config: Iterable[str] = None,
-    tesseract_pagesegmode: int = None,
-    tesseract_oem: int = None,
-    tesseract_thresholding: int = None,
-    pdf_renderer=None,
-    tesseract_timeout: float = None,
-    rotate_pages_threshold: float = None,
-    pdfa_image_compression=None,
-    user_words: os.PathLike = None,
-    user_patterns: os.PathLike = None,
-    fast_web_view: float = None,
-    plugins: Iterable[StrPath] = None,
+    language: Iterable[str] | None = None,
+    image_dpi: int | None = None,
+    output_type: str | None = None,
+    sidecar: PathOrIO | None = None,
+    jobs: int | None = None,
+    use_threads: bool | None = None,
+    title: str | None = None,
+    author: str | None = None,
+    subject: str | None = None,
+    keywords: str | None = None,
+    rotate_pages: bool | None = None,
+    remove_background: bool | None = None,
+    deskew: bool | None = None,
+    clean: bool | None = None,
+    clean_final: bool | None = None,
+    unpaper_args: str | None = None,
+    oversample: int | None = None,
+    remove_vectors: bool | None = None,
+    force_ocr: bool | None = None,
+    skip_text: bool | None = None,
+    redo_ocr: bool | None = None,
+    skip_big: float | None = None,
+    optimize: int | None = None,
+    jpg_quality: int | None = None,
+    png_quality: int | None = None,
+    jbig2_lossy: bool | None = None,
+    jbig2_page_group_size: int | None = None,
+    jbig2_threshold: float | None = None,
+    pages: str | None = None,
+    max_image_mpixels: float | None = None,
+    tesseract_config: Iterable[str] | None = None,
+    tesseract_pagesegmode: int | None = None,
+    tesseract_oem: int | None = None,
+    tesseract_thresholding: int | None = None,
+    pdf_renderer: str | None = None,
+    tesseract_timeout: float | None = None,
+    tesseract_non_ocr_timeout: float | None = None,
+    tesseract_downsample_above: int | None = None,
+    tesseract_downsample_large_images: bool | None = None,
+    rotate_pages_threshold: float | None = None,
+    pdfa_image_compression: str | None = None,
+    color_conversion_strategy: str | None = None,
+    user_words: os.PathLike | None = None,
+    user_patterns: os.PathLike | None = None,
+    fast_web_view: float | None = None,
+    continue_on_soft_render_error: bool | None = None,
+    invalidate_digital_signatures: bool | None = None,
+    plugins: Iterable[Path | str] | None = None,
     plugin_manager=None,
-    keep_temporary_files: bool = None,
-    progress_bar: bool = None,
+    keep_temporary_files: bool | None = None,
+    progress_bar: bool | None = None,
     **kwargs,
 ):
     """Run OCRmyPDF on one PDF or image.
 
     For most arguments, see documentation for the equivalent command line parameter.
+
+    This API takes a threading lock, because OCRmyPDF uses global state in particular
+    for the plugin system. The jobs parameter will be used to create a pool of
+    worker threads or processes at different times, subject to change. A Python
+    process can only run one OCRmyPDF task at a time.
+
+    To run parallelize instances OCRmyPDF, use separate Python processes to scale
+    horizontally. Generally speaking you should set jobs=sqrt(cpu_count) and run
+    sqrt(cpu_count) processes as a starting point. If you have files with a high page
+    count, run fewer processes and more jobs per process. If you have a lot of short
+    files, run more processes and fewer jobs per process.
+
     A few specific arguments are discussed here:
 
     Args:
@@ -283,9 +321,8 @@ def ocr(  # pylint: disable=unused-argument
             When a stream is used as output, whether via a writable object or
             ``"-"``, some final validation steps are not performed (we do not read
             back the stream after it is written).
+
     Raises:
-        ocrmypdf.PdfMergeFailedError: If the input PDF is malformed, preventing merging
-            with the OCR layer.
         ocrmypdf.MissingDependencyError: If a required dependency program is missing or
             was not found on PATH.
         ocrmypdf.UnsupportedImageFormatError: If the input file type was an image that
@@ -311,23 +348,21 @@ def ocr(  # pylint: disable=unused-argument
 
     if not plugins:
         plugins = []
-    elif isinstance(plugins, (str, Path)):
+    elif isinstance(plugins, str | Path):
         plugins = [plugins]
     else:
         plugins = list(plugins)
 
     # No new variable names should be assigned until these two steps are run
-    create_options_kwargs = {k: v for k, v in locals().items() if k != 'kwargs'}
+    create_options_kwargs = {
+        k: v
+        for k, v in locals().items()
+        if k not in {'input_file', 'output_file', 'kwargs'}
+    }
     create_options_kwargs.update(kwargs)
 
     parser = get_parser()
-    create_options_kwargs['parser'] = parser
-
     with _api_lock:
-        # We can't allow multiple ocrmypdf.ocr() threads to run in parallel, because
-        # they might install different plugins, and generally speaking we have areas
-        # of code that use global state.
-
         if not plugin_manager:
             plugin_manager = get_plugin_manager(plugins)
         plugin_manager.hook.add_options(parser=parser)  # pylint: disable=no-member
@@ -335,14 +370,181 @@ def ocr(  # pylint: disable=unused-argument
         if 'verbose' in kwargs:
             warn("ocrmypdf.ocr(verbose=) is ignored. Use ocrmypdf.configure_logging().")
 
-        options = create_options(**create_options_kwargs)
+        options = create_options(
+            input_file=input_file,
+            output_file=output_file,
+            parser=parser,
+            **create_options_kwargs,
+        )
         check_options(options, plugin_manager)
-        return run_pipeline(options=options, plugin_manager=plugin_manager, api=True)
+        return run_pipeline(options=options, plugin_manager=plugin_manager)
+
+
+def _pdf_to_hocr(  # noqa: D417
+    input_pdf: Path,
+    output_folder: Path,
+    *,
+    language: Iterable[str] | None = None,
+    image_dpi: int | None = None,
+    jobs: int | None = None,
+    use_threads: bool | None = None,
+    title: str | None = None,
+    author: str | None = None,
+    subject: str | None = None,
+    keywords: str | None = None,
+    rotate_pages: bool | None = None,
+    remove_background: bool | None = None,
+    deskew: bool | None = None,
+    clean: bool | None = None,
+    clean_final: bool | None = None,
+    unpaper_args: str | None = None,
+    oversample: int | None = None,
+    remove_vectors: bool | None = None,
+    force_ocr: bool | None = None,
+    skip_text: bool | None = None,
+    redo_ocr: bool | None = None,
+    skip_big: float | None = None,
+    pages: str | None = None,
+    max_image_mpixels: float | None = None,
+    tesseract_config: Iterable[str] | None = None,
+    tesseract_pagesegmode: int | None = None,
+    tesseract_oem: int | None = None,
+    tesseract_thresholding: int | None = None,
+    tesseract_timeout: float | None = None,
+    tesseract_non_ocr_timeout: float | None = None,
+    tesseract_downsample_above: int | None = None,
+    tesseract_downsample_large_images: bool | None = None,
+    rotate_pages_threshold: float | None = None,
+    user_words: os.PathLike | None = None,
+    user_patterns: os.PathLike | None = None,
+    continue_on_soft_render_error: bool | None = None,
+    invalidate_digital_signatures: bool | None = None,
+    plugin_manager=None,
+    plugins: Sequence[Path | str] | None = None,
+    keep_temporary_files: bool | None = None,
+    **kwargs,
+):
+    """Partially run OCRmyPDF and produces an output folder containing hOCR files.
+
+    Given a PDF file, this function will run OCRmyPDF up to the point where
+    the PDF is rasterized to images, OCRed, and the hOCR files are produced,
+    all of which are saved to the output folder. This is useful for applications
+    that want to provide an interface for users to edit the text before
+    rendering the final PDF.
+
+    Use :func:`hocr_to_ocr_pdf` to produce the final PDF.
+
+    For arguments not explicitly documented here, see documentation for the
+    equivalent command line parameter.
+
+    This API is **experimental** and subject to change.
+
+    Args:
+        input_pdf: Input PDF file path.
+        output_folder: Output folder path.
+        **kwargs: Keyword arguments.
+    """
+    # No new variable names should be assigned until these two steps are run
+    create_options_kwargs = {
+        k: v
+        for k, v in locals().items()
+        if k not in {'input_pdf', 'output_folder', 'kwargs'}
+    }
+    create_options_kwargs.update(kwargs)
+
+    parser = get_parser()
+
+    with _api_lock:
+        if not plugin_manager:
+            plugin_manager = get_plugin_manager(plugins)
+        plugin_manager.hook.add_options(parser=parser)  # pylint: disable=no-member
+
+        cmdline, deferred = _kwargs_to_cmdline(
+            defer_kwargs={'input_pdf', 'output_folder', 'plugins'},
+            **create_options_kwargs,
+        )
+        cmdline.append(str(input_pdf))
+        cmdline.append(str(output_folder))
+        parser.enable_api_mode()
+        options = parser.parse_args(cmdline)
+        for keyword, val in deferred.items():
+            setattr(options, keyword, val)
+        delattr(options, 'output_file')
+        setattr(options, 'output_folder', output_folder)
+
+        return run_hocr_pipeline(options=options, plugin_manager=plugin_manager)
+
+
+def _hocr_to_ocr_pdf(  # noqa: D417
+    work_folder: Path,
+    output_file: Path,
+    *,
+    jobs: int | None = None,
+    use_threads: bool | None = None,
+    optimize: int | None = None,
+    jpg_quality: int | None = None,
+    png_quality: int | None = None,
+    jbig2_lossy: bool | None = None,
+    jbig2_page_group_size: int | None = None,
+    jbig2_threshold: float | None = None,
+    pdfa_image_compression: str | None = None,
+    color_conversion_strategy: str | None = None,
+    fast_web_view: float | None = None,
+    plugin_manager=None,
+    plugins: Sequence[Path | str] | None = None,
+    **kwargs,
+):
+    """Run OCRmyPDF on a work folder and produce an output PDF.
+
+    After running :func:`pdf_to_hocr`, this function will run OCRmyPDF on the work
+    folder to produce an output PDF. This function consolidates any changes made
+    to the hOCR files in the work folder and produces a final PDF.
+
+    For arguments not explicitly documented here, see documentation for the
+    equivalent command line parameter.
+
+    This API is **experimental** and subject to change.
+
+    Args:
+        work_folder: Work folder path, as generated by :func:`pdf_to_hocr`.
+        output_file: Output PDF file path.
+        **kwargs: Keyword arguments.
+    """
+    # No new variable names should be assigned until these two steps are run
+    create_options_kwargs = {
+        k: v
+        for k, v in locals().items()
+        if k not in {'work_folder', 'output_pdf', 'kwargs'}
+    }
+    create_options_kwargs.update(kwargs)
+
+    parser = get_parser()
+
+    with _api_lock:
+        if not plugin_manager:
+            plugin_manager = get_plugin_manager(plugins)
+        plugin_manager.hook.add_options(parser=parser)  # pylint: disable=no-member
+
+        cmdline, deferred = _kwargs_to_cmdline(
+            defer_kwargs={'work_folder', 'output_file', 'plugins'},
+            **create_options_kwargs,
+        )
+        cmdline.append(str(work_folder))
+        cmdline.append(str(output_file))
+        parser.enable_api_mode()
+        options = parser.parse_args(cmdline)
+        for keyword, val in deferred.items():
+            setattr(options, keyword, val)
+        delattr(options, 'input_file')
+        setattr(options, 'work_folder', work_folder)
+
+        return run_hocr_to_ocr_pdf_pipeline(
+            options=options, plugin_manager=plugin_manager
+        )
 
 
 __all__ = [
     'PageNumberFilter',
-    'TqdmConsole',
     'Verbosity',
     'check_options',
     'configure_logging',
@@ -351,4 +553,5 @@ __all__ = [
     'get_plugin_manager',
     'ocr',
     'run_pipeline',
+    'run_pipeline_cli',
 ]

src/ocrmypdf/builtin_plugins/__init__.py

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

src/ocrmypdf/builtin_plugins/concurrency.py

@@ -1,9 +1,9 @@
 # SPDX-FileCopyrightText: 2022 James R. Barlow
 # SPDX-License-Identifier: MPL-2.0
-from __future__ import annotations
-
 """OCRmyPDF's multiprocessing/multithreading abstraction layer."""
 
+from __future__ import annotations
+
 import logging
 import logging.handlers
 import multiprocessing
@@ -12,25 +12,29 @@ import queue
 import signal
 import sys
 import threading
+from collections.abc import Callable, Iterable
 from concurrent.futures import ProcessPoolExecutor, ThreadPoolExecutor, as_completed
 from contextlib import suppress
-from typing import Callable, Iterable, Type, Union
+from typing import Union
 
-from tqdm import tqdm
+from rich.console import Console as RichConsole
 
 from ocrmypdf import Executor, hookimpl
-from ocrmypdf._logging import TqdmConsole
+from ocrmypdf._logging import RichLoggingHandler
+from ocrmypdf._progressbar import RichProgressBar
 from ocrmypdf.exceptions import InputFileError
 from ocrmypdf.helpers import remove_all_log_handlers
 
-FuturesExecutorClass = Union[Type[ThreadPoolExecutor], Type[ProcessPoolExecutor]]
-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]
 
 
 def log_listener(q: Queue):
-    """Listen to the worker processes and forward the messages to logging
+    """Listen to the worker processes and forward the messages to logging.
 
     For simplicity this is a thread rather than a process. Only one process
     should actually write to sys.stderr or whatever we're using, so if this is
@@ -39,7 +43,6 @@ def log_listener(q: Queue):
     See:
     https://docs.python.org/3/howto/logging-cookbook.html#logging-to-a-single-file-from-multiple-processes
     """
-
     while True:
         try:
             record = q.get()
@@ -55,12 +58,12 @@ def log_listener(q: Queue):
 
 
 def process_sigbus(*args):
+    """Handle SIGBUS signal at the worker level."""
     raise InputFileError("A worker process lost access to an input file")
 
 
 def process_init(q: Queue, user_init: UserInit, loglevel) -> None:
-    """Initialize a process pool worker"""
-
+    """Initialize a process pool worker."""
     # Ignore SIGINT (our parent process will kill us gracefully)
     signal.signal(signal.SIGINT, signal.SIG_IGN)
 
@@ -69,7 +72,7 @@ def process_init(q: Queue, user_init: UserInit, loglevel) -> None:
         # Windows and Cygwin do not have pthread_sigmask or SIGBUS
         signal.signal(signal.SIGBUS, process_sigbus)
 
-    # Remove any log handlers that belong to the parent process
+    # Remove any log handlers inherited from the parent process
     root = logging.getLogger()
     remove_all_log_handlers(root)
 
@@ -82,6 +85,7 @@ def process_init(q: Queue, user_init: UserInit, loglevel) -> None:
 
 
 def thread_init(q: Queue, user_init: UserInit, loglevel) -> None:
+    """Begin a thread pool worker."""
     del q  # unused but required argument
     del loglevel  # unused but required argument
     # As a thread, block SIGBUS so the main thread deals with it...
@@ -95,21 +99,12 @@ def thread_init(q: Queue, user_init: UserInit, loglevel) -> None:
 class StandardExecutor(Executor):
     """Standard OCRmyPDF concurrent task executor."""
 
-    def _cancel_futures_kwargs(self):
-        """Shim older Pythons that do not have Executor.shutdown(...cancel_futures=).
-
-        Remove this code when support for Python 3.8 is dropped.
-        """
-        if sys.version_info[:2] < (3, 9):
-            return {}
-        return dict(cancel_futures=True)
-
     def _execute(
         self,
         *,
         use_threads: bool,
         max_workers: int,
-        tqdm_kwargs: dict,
+        progress_kwargs: dict,
         worker_initializer: Callable,
         task: Callable,
         task_arguments: Iterable,
@@ -127,22 +122,30 @@ class StandardExecutor(Executor):
         # Regardless of whether we use_threads for worker processes, the log_listener
         # must be a thread. Make sure we create the listener after the worker pool,
         # so that it does not get forked into the workers.
+        # If use_threads is False, we are currently guilty of creating a thread before
+        # forking on Linux, which is not recommended. However, we take a big
+        # performance hit in pdfinfo if we can't fork. Long term solution is to
+        # replace most of this with an asyncio implementation, and probably to
+        # migrate some of pdfinfo into C++ or Rust.
         listener = threading.Thread(target=log_listener, args=(log_queue,))
         listener.start()
 
-        with self.pbar_class(**tqdm_kwargs) as pbar, executor_class(
-            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]
+        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):
                     result = future.result()
                     task_finished(result, pbar)
             except KeyboardInterrupt:
                 # Terminate pool so we exit instantly
-                executor.shutdown(wait=False, **self._cancel_futures_kwargs())
+                executor.shutdown(wait=False, cancel_futures=True)
                 raise
             except Exception:
                 if not os.environ.get("PYTEST_CURRENT_TEST", ""):
@@ -151,7 +154,7 @@ class StandardExecutor(Executor):
                     # results will be discard. But if the condition above is True,
                     # then we are running in pytest, and we want everything to exit
                     # as cleanly as possible so that we get good error messages.
-                    executor.shutdown(wait=False, **self._cancel_futures_kwargs())
+                    executor.shutdown(wait=False, cancel_futures=True)
                 raise
             finally:
                 # Terminate log listener
@@ -164,14 +167,24 @@ class StandardExecutor(Executor):
 
 @hookimpl
 def get_executor(progressbar_class):
+    """Return the default executor."""
     return StandardExecutor(pbar_class=progressbar_class)
 
 
+RICH_CONSOLE = RichConsole(stderr=True)
+
+
 @hookimpl
 def get_progressbar_class():
-    return tqdm
+    """Return the default progress bar class."""
+
+    def partial_RichProgressBar(*args, **kwargs):
+        return RichProgressBar(*args, **kwargs, console=RICH_CONSOLE)
+
+    return partial_RichProgressBar
 
 
 @hookimpl
 def get_logging_console():
-    return logging.StreamHandler(stream=TqdmConsole(sys.stderr))
+    """Return the default logging console handler."""
+    return RichLoggingHandler(console=RICH_CONSOLE)

src/ocrmypdf/builtin_plugins/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

@@ -6,50 +6,86 @@ from __future__ import annotations
 
 import logging
 
+from packaging.version import Version
+
 from ocrmypdf import hookimpl
 from ocrmypdf._exec import ghostscript
-from ocrmypdf._validation import HOCR_OK_LANGS
 from ocrmypdf.exceptions import MissingDependencyError
 from ocrmypdf.subprocess import check_external_program
 
 log = logging.getLogger(__name__)
 
+# Currently all blacklisted versions are lower than 9.55, so none need to
+# be added here. If a future version is blacklisted, add it here.
+BLACKLISTED_GS_VERSIONS: frozenset[Version] = frozenset()
+
+
+@hookimpl
+def add_options(parser):
+    gs = parser.add_argument_group("Ghostscript", "Advanced control of Ghostscript")
+    gs.add_argument(
+        '--color-conversion-strategy',
+        action='store',
+        type=str,
+        metavar='STRATEGY',
+        choices=ghostscript.COLOR_CONVERSION_STRATEGIES,
+        default='LeaveColorUnchanged',
+        help="Set Ghostscript color conversion strategy",
+    )
+    gs.add_argument(
+        '--pdfa-image-compression',
+        choices=['auto', 'jpeg', 'lossless'],
+        default='auto',
+        help="Specify how to compress images in the output PDF/A. 'auto' lets "
+        "OCRmyPDF decide.  'jpeg' changes all grayscale and color images to "
+        "JPEG compression.  'lossless' uses PNG-style lossless compression "
+        "for all images.  Monochrome images are always compressed using a "
+        "lossless codec.  Compression settings "
+        "are applied to all pages, including those for which OCR was "
+        "skipped.  Not supported for --output-type=pdf ; that setting "
+        "preserves the original compression of all images.",
+    )
+
 
 @hookimpl
 def check_options(options):
+    """Check that the options are valid for this plugin."""
     check_external_program(
         program='gs',
         package='ghostscript',
         version_checker=ghostscript.version,
-        need_version='9.15',  # limited by Travis CI / Ubuntu 14.04 backports
+        need_version='9.54',  # RHEL 9's version; Ubuntu 22.04 has 9.55
     )
     gs_version = ghostscript.version()
-    if gs_version in ('9.24', '9.51'):
+    if gs_version in BLACKLISTED_GS_VERSIONS:
         raise MissingDependencyError(
             f"Ghostscript {gs_version} contains serious regressions and is not "
-            "supported. Please upgrade to a newer version, or downgrade to the "
-            "previous version."
+            "supported. Please upgrade to a newer version."
         )
-
-    # We have these constraints to check for.
-    # 1. Ghostscript < 9.20 mangles multibyte Unicode
-    # 2. hocr doesn't work on non-Latin languages (so don't select it)
-    is_latin = options.languages.issubset(HOCR_OK_LANGS)
-    if gs_version < '9.20' and options.output_type != 'pdf' and not is_latin:
-        # https://bugs.ghostscript.com/show_bug.cgi?id=696874
-        # Ghostscript < 9.20 fails to encode multibyte characters properly
-        log.warning(
-            f"The installed version of Ghostscript ({gs_version}) does not work "
-            "correctly with the OCR languages you specified. Use --output-type pdf or "
-            "upgrade to Ghostscript 9.20 or later to avoid this issue."
+    if 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':
         options.output_type = 'pdfa-2'
-
-    if options.output_type == 'pdfa-3' and ghostscript.version() < '9.19':
-        raise MissingDependencyError(
-            "--output-type pdfa-3 requires Ghostscript 9.19 or later"
+    if options.color_conversion_strategy not in ghostscript.COLOR_CONVERSION_STRATEGIES:
+        raise ValueError(
+            f"Invalid color conversion strategy: {options.color_conversion_strategy}"
+        )
+    if options.pdfa_image_compression != 'auto' and not options.output_type.startswith(
+        'pdfa'
+    ):
+        log.warning(
+            "--pdfa-image-compression argument only applies when "
+            "--output-type is one of 'pdfa', 'pdfa-1', or 'pdfa-2'"
         )
 
 
@@ -63,7 +99,9 @@ def rasterize_pdf_page(
     page_dpi,
     rotation,
     filter_vector,
+    stop_on_soft_error,
 ):
+    """Rasterize a single page of a PDF file using Ghostscript."""
     ghostscript.rasterize_pdf(
         input_file,
         output_file,
@@ -73,6 +111,7 @@ def rasterize_pdf_page(
         page_dpi=page_dpi,
         rotation=rotation,
         filter_vector=filter_vector,
+        stop_on_error=stop_on_soft_error,
     )
     return output_file
 
@@ -82,17 +121,21 @@ def generate_pdfa(
     pdf_pages,
     pdfmark,
     output_file,
-    compression,
+    context,
     pdf_version,
     pdfa_part,
     progressbar_class,
+    stop_on_soft_error,
 ):
+    """Generate a PDF/A from the list of PDF pages and PDF/A metadata."""
     ghostscript.generate_pdfa(
-        pdf_pages=[*pdf_pages, pdfmark],
+        pdf_pages=[pdfmark, *pdf_pages],
         output_file=output_file,
-        compression=compression,
+        compression=context.options.pdfa_image_compression,
+        color_conversion_strategy=context.options.color_conversion_strategy,
         pdf_version=pdf_version,
         pdfa_part=pdfa_part,
         progressbar_class=progressbar_class,
+        stop_on_error=stop_on_soft_error,
     )
     return output_file

src/ocrmypdf/builtin_plugins/optimize.py

@@ -6,8 +6,8 @@ from __future__ import annotations
 
 import argparse
 import logging
+from collections.abc import Sequence
 from pathlib import Path
-from typing import Sequence
 
 from ocrmypdf import Executor, PdfContext, hookimpl
 from ocrmypdf._exec import jbig2enc, pngquant
@@ -86,6 +86,16 @@ def add_options(parser):
         # Adjust number of pages to consider at once for JBIG2 compression
         help=argparse.SUPPRESS,
     )
+    optimizing.add_argument(
+        '--jbig2-threshold',
+        type=numeric(float, 0.4, 0.9),
+        default=0.85,
+        metavar='T',
+        help=(
+            "Adjust JBIG2 symbol code classification threshold "
+            "(default 0.85), range 0.4 to 0.9."
+        ),
+    )
 
 
 @hookimpl
@@ -95,7 +105,7 @@ def check_options(options):
             program='pngquant',
             package='pngquant',
             version_checker=pngquant.version,
-            need_version='2.0.1',
+            need_version='2.12.2',
             required_for='--optimize {2,3}',
         )
 

src/ocrmypdf/builtin_plugins/tesseract_ocr.py

@@ -2,16 +2,21 @@
 # SPDX-License-Identifier: MPL-2.0
 """Built-in plugin to implement OCR using Tesseract."""
 
-
 from __future__ import annotations
 
+import argparse
 import logging
 import os
 
+from PIL import Image
+
 from ocrmypdf import hookimpl
 from ocrmypdf._exec import tesseract
+from ocrmypdf._jobcontext import PageContext
 from ocrmypdf.cli import numeric, str_to_int
+from ocrmypdf.exceptions import BadArgsError, MissingDependencyError
 from ocrmypdf.helpers import clamp
+from ocrmypdf.imageops import calculate_downsample, downsample_image
 from ocrmypdf.pluginspec import OcrEngine
 from ocrmypdf.subprocess import check_external_program
 
@@ -26,7 +31,7 @@ def add_options(parser):
         action='append',
         metavar='CFG',
         default=[],
-        help="Additional Tesseract configuration files -- see documentation",
+        help="Additional Tesseract configuration files -- see documentation.",
     )
     tess.add_argument(
         '--tesseract-pagesegmode',
@@ -34,7 +39,7 @@ def add_options(parser):
         type=int,
         metavar='PSM',
         choices=range(0, 14),
-        help="Set Tesseract page segmentation mode (see tesseract --help)",
+        help="Set Tesseract page segmentation mode (see tesseract --help).",
     )
     tess.add_argument(
         '--tesseract-oem',
@@ -43,7 +48,7 @@ def add_options(parser):
         metavar='MODE',
         choices=range(0, 4),
         help=(
-            "Set Tesseract 4.0+ OCR engine mode: "
+            "Set Tesseract 4+ OCR engine mode: "
             "0 - original Tesseract only; "
             "1 - neural nets LSTM only; "
             "2 - Tesseract + LSTM; "
@@ -58,7 +63,7 @@ def add_options(parser):
         metavar='METHOD',
         help=(
             "Set Tesseract 5.0+ input image thresholding mode. This may improve OCR "
-            "results on low quality images or those that contain high constrast color. "
+            "results on low quality images or those that contain high contrast color. "
             "legacy-otsu is the Tesseract default; adaptive-otsu is an improved Otsu "
             "algorithm with improved sort for background color changes; sauvola is "
             "based on local standard deviation."
@@ -69,8 +74,52 @@ def add_options(parser):
         default=180.0,
         type=numeric(float, 0),
         metavar='SECONDS',
-        help='Give up on OCR after the timeout, but copy the preprocessed page '
-        'into the final output',
+        help=(
+            "Give up on OCR after the timeout, but copy the preprocessed page "
+            "into the final output. This timeout is only used when using Tesseract "
+            "for OCR. When Tesseract is used for other operations such as "
+            "deskewing and orientation, the timeout is controlled by "
+            "--tesseract-non-ocr-timeout."
+        ),
+    )
+    tess.add_argument(
+        '--tesseract-non-ocr-timeout',
+        default=180.0,
+        type=numeric(float, 0),
+        metavar='SECONDS',
+        help=(
+            "Give up on non-OCR operations such as deskewing and orientation "
+            "after timeout. This is a separate timeout from --tesseract-timeout "
+            "because these operations are not as expensive as OCR."
+        ),
+    )
+    tess.add_argument(
+        '--tesseract-downsample-large-images',
+        action=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 "
+            "downsample large images to fit Tesseract. This may reduce OCR quality, "
+            "on large images the most desirable text is usually larger. If this "
+            "parameter is not supplied, Tesseract will error out and produce no OCR "
+            "on the page in question. This argument should be used with a high value "
+            "of --tesseract-timeout to ensure Tesseract has enough to time."
+        ),
+    )
+    tess.add_argument(
+        '--tesseract-downsample-above',
+        action='store',
+        type=numeric(int, 100, 32767),
+        default=32767,
+        help=(
+            "Downsample images larger than this size pixel size in either dimension "
+            "before OCR. --tesseract-downsample-large-images downsamples only when "
+            "an image exceeds Tesseract's internal limits. This argument causes "
+            "downsampling to occur when an image exceeds the given size. This may "
+            "reduce OCR quality, but on large images the most desirable text is "
+            "usually larger."
+        ),
     )
     tess.add_argument(
         '--user-words',
@@ -93,19 +142,24 @@ def check_options(options):
         program='tesseract',
         package={'linux': 'tesseract-ocr'},
         version_checker=tesseract.version,
-        need_version='4.0.0-beta.1',  # using backport for Travis CI
+        need_version='4.1.1',  # Ubuntu 22.04 version (also 20.04)
         version_parser=tesseract.TesseractVersion,
     )
+    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 = 'sandwich'
+        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_user_words() and (options.user_words or options.user_patterns):
-        log.warning(
-            "Tesseract 4.0 (which you have installed) ignores --user-words and "
-            "--user-patterns, so these arguments have no effect."
-        )
     if not tesseract.has_thresholding() and options.tesseract_thresholding != 0:
         log.warning(
             "The installed version of Tesseract does not support changes to its "
@@ -117,6 +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
@@ -136,17 +198,45 @@ def validate(pdfinfo, options):
         tess_threads = int(os.environ['OMP_THREAD_LIMIT'])
     log.debug("Using Tesseract OpenMP thread limit %d", tess_threads)
 
+    if (
+        options.tesseract_downsample_above != 32767
+        and not options.tesseract_downsample_large_images
+    ):
+        log.warning(
+            "The --tesseract-downsample-above argument will have no effect unless "
+            "--tesseract-downsample-large-images is also given."
+        )
+
+
+@hookimpl
+def filter_ocr_image(page: PageContext, image: Image.Image) -> Image.Image:
+    """Filter the image before OCR.
+
+    Tesseract cannot handle images with more than 32767 pixels in either axis,
+    or more than 2**31 bytes. This function resizes the image to fit within
+    those limits.
+    """
+    threshold = min(page.options.tesseract_downsample_above, 32767)
+
+    options = page.options
+    if options.tesseract_downsample_large_images:
+        size = calculate_downsample(
+            image, max_size=(threshold, threshold), max_bytes=(2**31) - 1
+        )
+        image = downsample_image(image, size)
+    return image
+
 
 class TesseractOcrEngine(OcrEngine):
     """Implements OCR with Tesseract."""
 
     @staticmethod
     def version():
-        return tesseract.version()
+        return str(tesseract.version())
 
     @staticmethod
     def creator_tag(options):
-        tag = '-PDF' if options.pdf_renderer == 'sandwich' else ''
+        tag = '-PDF' if options.pdf_renderer == 'sandwich' else '-hOCR'
         return f"Tesseract OCR{tag} {TesseractOcrEngine.version()}"
 
     def __str__(self):
@@ -161,7 +251,7 @@ class TesseractOcrEngine(OcrEngine):
         return tesseract.get_orientation(
             input_file,
             engine_mode=options.tesseract_oem,
-            timeout=options.tesseract_timeout,
+            timeout=options.tesseract_non_ocr_timeout,
         )
 
     @staticmethod
@@ -170,7 +260,7 @@ class TesseractOcrEngine(OcrEngine):
             input_file,
             languages=options.languages,
             engine_mode=options.tesseract_oem,
-            timeout=options.tesseract_timeout,
+            timeout=options.tesseract_non_ocr_timeout,
         )
 
     @staticmethod

src/ocrmypdf/cli.py

@@ -6,16 +6,22 @@
 from __future__ import annotations
 
 import argparse
-from typing import Any, Callable, Mapping, 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)
 
 
 def numeric(basetype: Callable[[Any], T], min_: T | None = None, max_: T | None = None):
-    """Validator for numeric params"""
+    """Validator for numeric command line parameters.
+
+    Stipulates that the value must be of type basetype (typically int or float), and
+    optionally, within the range [min_, max_].
+    """
     min_ = basetype(min_) if min_ is not None else None
     max_ = basetype(max_) if max_ is not None else None
 
@@ -46,7 +52,7 @@ def str_to_int(mapping: Mapping[str, int]):
 
 
 class ArgumentParser(argparse.ArgumentParser):
-    """Override parser's default behavior of calling sys.exit()
+    """Override parser's default behavior of calling sys.exit().
 
     https://stackoverflow.com/questions/5943249/python-argparse-and-controlling-overriding-the-exit-status-code
 
@@ -57,13 +63,21 @@ class ArgumentParser(argparse.ArgumentParser):
     """
 
     def __init__(self, *args, **kwargs):
+        """Initialize the parser."""
         super().__init__(*args, **kwargs)
         self._api_mode = False
 
     def enable_api_mode(self):
+        """Enable API mode.
+
+        When set, the parser will not call sys.exit() on error. OCRmyPDF was originally
+        a command line program, but now it has an API. The API works by synthesizing
+        command line arguments.
+        """
         self._api_mode = True
 
     def error(self, message):
+        """Override the default argparse error behavior."""
         if not self._api_mode:
             super().error(message)
             return
@@ -74,19 +88,22 @@ class LanguageSetAction(argparse.Action):
     """Manages a list of languages."""
 
     def __init__(self, option_strings, dest, default=None, **kwargs):
+        """Initialize the action."""
         if default is None:
-            default = set()
+            default = list()
         super().__init__(option_strings, dest, default=default, **kwargs)
 
     def __call__(self, parser, namespace, values, option_string=None):
+        """Add a language to the set."""
         dest = getattr(namespace, self.dest)
         if '+' in values:
-            dest.update(lang for lang in values.split('+'))
+            [dest.append(lang) for lang in values.split('+')]
         else:
-            dest.add(values)
+            dest.append(values)
 
 
 def get_parser():
+    """Get the main CLI parser."""
     parser = ArgumentParser(
         prog=_PROGRAM_NAME,
         allow_abbrev=True,
@@ -166,7 +183,9 @@ Online documentation is located at:
         '--image-dpi',
         metavar='DPI',
         type=int,
-        help="For input image instead of PDF, use this DPI instead of file's.",
+        help="When the input file is an image, not a PDF, use this DPI instead "
+        "of the DPI claimed by the input file. If the input does not claim a "
+        "sensible DPI, this option will be required.",
     )
     parser.add_argument(
         '--output-type',
@@ -175,8 +194,8 @@ Online documentation is located at:
         help="Choose output type. 'pdfa' creates a PDF/A-2b compliant file for "
         "long term archiving (default, recommended) but may not suitable "
         "for users who want their file altered as little as possible. 'pdfa' "
-        "also has problems with full Unicode text. 'pdf' attempts to "
-        "preserve file contents as much as possible. 'pdf-a1' creates a "
+        "also has problems with full Unicode text. 'pdf' minimizes changes "
+        "to the input file. 'pdf-a1' creates a "
         "PDF/A1-b file. 'pdf-a2' is equivalent to 'pdfa'. 'pdf-a3' creates a "
         "PDF/A3-b file. 'none' will produce no output, which may be helpful if "
         "only the --sidecar is desired.",
@@ -348,6 +367,13 @@ Online documentation is located at:
         help="Skip OCR on pages larger than the specified amount of megapixels, "
         "but include skipped pages in final output",
     )
+    ocrsettings.add_argument(
+        '--invalidate-digital-signatures',
+        action='store_true',
+        help="Normally, OCRmyPDF will refuse to OCR a PDF that has a digital "
+        "signature. This option allows OCR to proceed, but the digital signature "
+        "will be invalidated.",
+    )
 
     advanced = parser.add_argument_group(
         "Advanced", "Advanced options to control OCRmyPDF"
@@ -365,7 +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,
     )
@@ -378,25 +404,12 @@ 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 "
         "units reported by tesseract)",
     )
-    advanced.add_argument(
-        '--pdfa-image-compression',
-        choices=['auto', 'jpeg', 'lossless'],
-        default='auto',
-        help="Specify how to compress images in the output PDF/A. 'auto' lets "
-        "OCRmyPDF decide.  'jpeg' changes all grayscale and color images to "
-        "JPEG compression.  'lossless' uses PNG-style lossless compression "
-        "for all images.  Monochrome images are always compressed using a "
-        "lossless codec.  Compression settings "
-        "are applied to all pages, including those for which OCR was "
-        "skipped.  Not supported for --output-type=pdf ; that setting "
-        "preserves the original compression of all images.",
-    )
     advanced.add_argument(
         '--fast-web-view',
         type=numeric(float, 0),
@@ -409,6 +422,14 @@ Online documentation is located at:
         "which do not benefit. If the threshold is 0 it will be apply to all files. "
         "Set the threshold very high to disable.",
     )
+    advanced.add_argument(
+        '--continue-on-soft-render-error',
+        action='store_true',
+        help="Continue processing pages after a recoverable PDF rendering error. "
+        "A recoverable error is one that does not prevent the page from being "
+        "rendered, but may result in visual differences compared to the input "
+        "file. Missing fonts are a typical source of these errors.",
+    )
     advanced.add_argument(
         '--plugin',
         dest='plugins',

src/ocrmypdf/exceptions.py

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

src/ocrmypdf/extra_plugins/__init__.py

@@ -1,3 +1,9 @@
 # SPDX-FileCopyrightText: 2022 James R. Barlow
 #
 # SPDX-License-Identifier: MPL-2.0
+
+"""Extra plugins. These are not automatically inserted when ocrmypdf is run.
+
+You can use these plugins by specifying them on the command line, e.g.:
+ocrmypdf --plugin ocrmypdf.extra_plugins.semfree ...
+"""

src/ocrmypdf/extra_plugins/semfree.py

@@ -12,7 +12,7 @@ worker communicates only with the main process.
 
 This is not without drawbacks. If the tasks are not "even" in size, which cannot
 be guaranteed, some workers may end up with too much work while others are idle.
-It is less efficient than the standard implementation, so not th edefault.
+It is less efficient than the standard implementation, so not the default.
 """
 
 from __future__ import annotations
@@ -20,12 +20,12 @@ from __future__ import annotations
 import logging
 import logging.handlers
 import signal
+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, Iterable, Iterator
 
 from ocrmypdf import Executor, hookimpl
 from ocrmypdf._concurrent import NullProgressBar
@@ -54,6 +54,7 @@ def split_every(n: int, iterable: Iterable) -> Iterator:
 
 
 def process_sigbus(*args):
+    """Handle SIGBUS signal at the worker level."""
     raise InputFileError("A worker process lost access to an input file")
 
 
@@ -61,20 +62,21 @@ class ConnectionLogHandler(logging.handlers.QueueHandler):
     """Handler used by child processes to forward log messages to parent."""
 
     def __init__(self, conn: Connection) -> None:
+        """Initialize the handler."""
         # sets the parent's queue to None - parent only touches queue
         # in enqueue() which we override
         super().__init__(None)  # type: ignore
         self.conn = conn
 
     def enqueue(self, record):
+        """Enqueue a log message."""
         self.conn.send(('log', record))
 
 
 def process_loop(
     conn: Connection, user_init: Callable[[], None], loglevel, task, task_args
 ):
-    """Initialize a process pool worker"""
-
+    """Initialize a process pool worker."""
     # Install SIGBUS handler (so our parent process can abort somewhat gracefully)
     with suppress(AttributeError):  # Windows and Cygwin do not have SIGBUS
         # Windows and Cygwin do not have pthread_sigmask or SIGBUS
@@ -91,7 +93,7 @@ def process_loop(
 
     for args in task_args:
         try:
-            result = task(args)
+            result = task(*args)
         except Exception as e:  # pylint: disable=broad-except
             conn.send((MessageType.exception, e))
             break
@@ -111,16 +113,16 @@ class LambdaExecutor(Executor):
         *,
         use_threads: bool,
         max_workers: int,
-        tqdm_kwargs: dict,
+        progress_kwargs: dict,
         worker_initializer: Callable,
         task: Callable,
         task_arguments: Iterable,
         task_finished: Callable,
     ):
         if use_threads and max_workers == 1:
-            with self.pbar_class(**tqdm_kwargs) as pbar:
+            with self.pbar_class(**progress_kwargs) as pbar:
                 for args in task_arguments:
-                    result = task(args)
+                    result = task(*args)
                     task_finished(result, pbar)
             return
 
@@ -154,7 +156,7 @@ class LambdaExecutor(Executor):
         for process in processes:
             process.start()
 
-        with self.pbar_class(**tqdm_kwargs) as pbar:
+        with self.pbar_class(**progress_kwargs) as pbar:
             while connections:
                 for result in wait(connections):
                     if not isinstance(result, Connection):
@@ -166,8 +168,7 @@ class LambdaExecutor(Executor):
                         continue
 
                     if msg_type == MessageType.result:
-                        if task_finished:
-                            task_finished(msg, pbar)
+                        task_finished(msg, pbar)
                     elif msg_type == 'log':
                         record = msg
                         logger = logging.getLogger(record.name)
@@ -185,14 +186,20 @@ class LambdaExecutor(Executor):
 
 @hookimpl
 def get_executor(progressbar_class):
+    """Return a LambdaExecutor instance."""
     return LambdaExecutor(pbar_class=progressbar_class)
 
 
 @hookimpl
 def get_logging_console():
+    """Return a logging.StreamHandler instance."""
     return logging.StreamHandler()
 
 
 @hookimpl
 def get_progressbar_class():
+    """Return a NullProgressBar instance.
+
+    This executor cannot use a progress bar.
+    """
     return NullProgressBar