v15.0.2 release notes

Maintainers of ARM 32-bit in particular don't necessarily need to drop support....

.docker/Dockerfile

@@ -25,7 +25,9 @@ RUN apt-get update && apt-get install -y --no-install-recommends \
   libffi-dev \
   ca-certificates \
   curl \
-  git
+  git \
+  libcairo2-dev \
+  pkg-config
 
 # Get the latest pip (Ubuntu version doesn't support manylinux2010)
 RUN \
@@ -57,6 +59,7 @@ RUN add-apt-repository -y ppa:alex-p/tesseract-ocr-devel
 
 RUN apt-get update && apt-get install -y --no-install-recommends \
   ghostscript \
+  fonts-droid-fallback \
   jbig2dec \
   img2pdf \
   libsm6 libxext6 libxrender-dev \

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

@@ -0,0 +1,51 @@
+name: General issues
+description: Installation, packages, dependencies, "nothing works", test suite failures...
+title: "[Bug]: "
+labels: ["bug", "triage"]
+assignees:
+  - jbarlow83
+body:
+  - type: markdown
+    attributes:
+      value: |
+        Thanks for taking the time to fill out this bug report!
+  - type: textarea
+    id: what-happened
+    attributes:
+      label: What were you trying to do?
+      description: Also tell us, what did you expect to happen?
+      placeholder: Tell us what you see!
+    validations:
+      required: true
+  - type: dropdown
+    id: packaging-system
+    attributes:
+      label: Where are you installing from?
+      multiple: true
+      options:
+        - PyPI (pip, poetry, pipx, etc.)
+        - Linux package manager (apt, dnf, etc.)
+        - Wndows package manager (chocolatey, etc.)
+        - Homebrew
+        - Docker container
+        - Ubuntu snap
+        - Conda
+        - source build
+    validations:
+      required: true
+  - type: dropdown
+    id: operating-system
+    attributes:
+      label: What operating system are you working on?
+      multiple: true
+      options:
+        - Linux
+        - Windows
+        - macOS
+        - BSD
+  - type: textarea
+    id: logs
+    attributes:
+      label: Relevant log output
+      description: Please copy and paste any relevant log output. This will be automatically formatted into code, so no need for backticks.
+      render: plain text

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

@@ -0,0 +1,62 @@
+name: Problem with specific file
+description: Something went wrong while trying to OCR a specific file
+title: "[Bug]: "
+labels: ["bug", "triage"]
+assignees:
+  - jbarlow83
+body:
+  - type: markdown
+    attributes:
+      value: |
+        Thanks for taking the time to describe this issue with a particular file.
+  - type: textarea
+    id: what-happened
+    attributes:
+      label: Describe the bug
+      description: A clear and concise description of what the bug is.
+      placeholder: Tell us what you see!
+    validations:
+      required: true
+  - type: textarea
+    id: reproduce
+    attributes:
+      label: Steps to reproduce
+      description: Please include steps to reproduce
+      value: |
+        1. Run ocrmypdf -v1 ...arguments... input.pdf output.pdf
+        2. Open output.pdf
+        3. ...
+      render: plain text
+  - type: textarea
+    id: files
+    attributes:
+      label: Files
+      description: Please attach the input and output files, or any screenshots that may be helpful.
+      placeholder: Drag and drop files here
+  - type: dropdown
+    id: packaging-system
+    attributes:
+      label: How did you download and install the software?
+      multiple: true
+      options:
+        - PyPI (pip, poetry, pipx, etc.)
+        - Linux package manager (apt, dnf, etc.)
+        - Windows package manager (chocolatey, etc.)
+        - Homebrew
+        - Docker container
+        - Ubuntu snap
+        - Conda
+        - source build
+  - type: input
+    id: version
+    attributes:
+      label: OCRmyPDF version
+      description: Paste "ocrmypdf --version" here
+      placeholder: ocrmypdf --version
+  - type: textarea
+    id: logs
+    attributes:
+      label: Relevant log output
+      description: Please copy and paste any relevant log output. This will be automatically formatted into code, so no need for backticks.
+      placeholder: Run OCRmyPDF with verbosity `-v1` to get more detailed logging output.
+      render: plain text

.github/ISSUE_TEMPLATE/3-feature-request.yml

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

.github/ISSUE_TEMPLATE/feature_request.md

@@ -1,23 +0,0 @@
----
-name: Feature request
-about: Suggest an idea for this project
-title: ''
-labels: ''
-assignees: ''
-
----
-
-**Is your feature request related to a problem? Please describe.**
-A clear and concise description of what the problem is. Ex. I'm always frustrated when [...]
-
-**Describe the solution you'd like**
-A clear and concise description of what you want to happen.
-
-**Describe alternatives you've considered**
-A clear and concise description of any alternative solutions or features you've considered. Please include the versions of OCRmyPDF and other supporting programs (Tesseract OCR, Ghostscript) - maybe an alternative already exists in a newer version.
-
-**Example file**
-If your issue concerns how OCRmyPDF processes certain files, and please provide an example file that helps illustrate how OCRmyPDF's output could be improve. You could also look in ``tests/resources`` and see if any of those files demonstrates your issue.
-
-**Additional context**
-Add any other context or screenshots about the feature request here.

.github/ISSUE_TEMPLATE/general-issues.md

@@ -1,33 +0,0 @@
----
-name: General issues
-about: Installation, packages, dependencies, "nothing works", test suite failures...
-title: "[BUG]"
-labels: ''
-assignees: ''
-
----
-
-**Describe the bug**
-What's the problem?
-
-**To Reproduce**
-Steps to reproduce the behavior.
-
-**Expected behavior**
-What did you expected to happen?
-
-**Screenshots**
-If applicable, add screenshots to help explain your problem.
-
-**System (please complete the following information):**
- - OS:
- - Python version:
- - OCRmyPDF version:
- - Platform: x64 or ARM
-
-**Installation**
-How did you install OCRmyPDF? Did you install it from your operating system's
-package manager, or using pip?
-
-**Additional context**
-Add any other context about the problem here.

.github/ISSUE_TEMPLATE/problem-with-specific-file.md

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

.github/workflows/build.yml

@@ -5,7 +5,7 @@ name: Test and deploy
 on:
   push:
     branches:
-      - master
+      - main
       - ci
       - release/*
       - feature/*
@@ -22,39 +22,35 @@ jobs:
     strategy:
       matrix:
         include:
-          - os: ubuntu-20.04
+          - os: ubuntu-22.04
-            python: "3.8"
-          - os: ubuntu-20.04
             python: "3.9"
-          - os: ubuntu-20.04
+          - os: ubuntu-22.04
             python: "3.10"
-          - os: ubuntu-latest
+          - os: ubuntu-22.04
-            python: "3.9"
-          - os: ubuntu-latest
-            python: "3.10"
-          - os: ubuntu-latest
             python: "3.11"
-          # - os: ubuntu-latest
+          - os: ubuntu-22.04
-          #   python: "pypy3.8"
-          #- os: ubuntu-latest
-          #  python: "pypy3.9"
-          - os: ubuntu-latest
             python: "3.9"
             tesseract5: true
+          - os: ubuntu-latest
+            python: "3.12-dev"
+            tesseract5: true
+            #- os: ubuntu-latest
+            #  python: "pypy3.9"
 
     env:
       OS: ${{ matrix.os }}
       PYTHON: ${{ matrix.python }}
 
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
         with:
           fetch-depth: "0" # 0=all, needed for setuptools-scm to resolve version tags
 
       - uses: actions/setup-python@v4
-        name: Install Python
+        name: Setup Python
         with:
           python-version: ${{ matrix.python }}
+          cache: "pip"
 
       - name: Install Tesseract 5
         if: matrix.tesseract5
@@ -68,6 +64,7 @@ jobs:
             curl \
             ghostscript \
             img2pdf \
+            libexempi8 \
             libffi-dev \
             libsm6 libxext6 libxrender-dev \
             pngquant \
@@ -79,12 +76,6 @@ jobs:
             unpaper \
             zlib1g
 
-      - name: Install Ubuntu 20.04 packages
-        if: matrix.os == 'ubuntu-20.04' || matrix.os == 'ubuntu-latest'
-        run: |
-          sudo apt-get install -y --no-install-recommends \
-            libexempi8
-
       - name: Install Ubuntu packages for PyPy
         if: startsWith(matrix.python, 'pypy')
         run: |
@@ -122,14 +113,14 @@ jobs:
     strategy:
       matrix:
         os: [macos-latest]
-        python: ["3.10", "3.11"]
+        python: ["3.10", "3.11", "3.12-dev"]
 
     env:
       OS: ${{ matrix.os }}
       PYTHON: ${{ matrix.python }}
 
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
         with:
           fetch-depth: "0" # 0=all, needed for setuptools-scm to resolve version tags
 
@@ -146,9 +137,10 @@ jobs:
             tesseract
 
       - uses: actions/setup-python@v4
-        name: Install Python
+        name: Setup Python
         with:
           python-version: ${{ matrix.python }}
+          cache: "pip"
 
       - name: Install Python packages
         run: |
@@ -178,21 +170,22 @@ jobs:
     strategy:
       matrix:
         os: [windows-latest]
-        python: ["3.10", "3.11"]
+        python: ["3.10", "3.11", "3.12-dev"]
 
     env:
       OS: ${{ matrix.os }}
       PYTHON: ${{ matrix.python }}
 
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
         with:
           fetch-depth: "0" # 0=all, needed for setuptools-scm to resolve version tags
 
       - uses: actions/setup-python@v4
-        name: Install Python
+        name: Setup Python
         with:
           python-version: ${{ matrix.python }}
+          cache: "pip"
 
       - name: Install system packages
         run: |
@@ -218,14 +211,15 @@ jobs:
     name: Build sdist and wheels
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
         with:
           fetch-depth: "0" # 0=all, needed for setuptools-scm to resolve version tags
 
       - uses: actions/setup-python@v4
-        name: Install Python
+        name: Setup Python
         with:
-          python-version: "3.7"
+          python-version: "3.9"
+          cache: "pip"
 
       - name: Make wheels and sdist
         run: |
@@ -242,6 +236,9 @@ jobs:
     name: Deploy artifacts to PyPI
     needs: [wheel_sdist_linux, test_linux, test_macos, test_windows]
     runs-on: ubuntu-latest
+    environment: release
+    permissions:
+      id-token: write  # mandatory for PyPI publishing
     if: github.event_name == 'push' && startsWith(github.event.ref, 'refs/tags/v')
     steps:
       - uses: actions/download-artifact@v3
@@ -249,11 +246,34 @@ jobs:
           name: artifact
           path: dist
 
-      - uses: pypa/gh-action-pypi-publish@master
+      - name: Publish to PyPI
+        uses: pypa/gh-action-pypi-publish@release/v1
+
+  create_release:
+    name: Create GitHub release
+    needs: [wheel_sdist_linux, test_linux, test_macos, test_windows]
+    runs-on: ubuntu-latest
+    if: github.event_name == 'push' && startsWith(github.event.ref, 'refs/tags/v')
+    permissions:
+      # Required to create a release
+      contents: write
+    steps:
+      - uses: actions/download-artifact@v3
         with:
-          user: __token__
+          name: artifact
-          password: ${{ secrets.TOKEN_PYPI }}
+          path: dist
-          # repository_url: https://test.pypi.org/legacy/
+
+      - name: Create Release
+        id: create-release
+        uses: shogo82148/actions-create-release@v1
+
+      - name: Upload Assets
+        uses: shogo82148/actions-upload-release-asset@v1
+        with:
+          upload_url: ${{ steps.create-release.outputs.upload_url }}
+          asset_path: |
+            ./dist/*.whl
+            ./dist/*.tar.gz
 
   docker:
     name: Build Docker images
@@ -264,9 +284,9 @@ jobs:
       - name: Set image tag to release or branch
         run: echo "DOCKER_IMAGE_TAG=${GITHUB_REF##*/}" >> $GITHUB_ENV
 
-      - name: If master, set to latest
+      - name: If main, set to latest
         run: echo 'DOCKER_IMAGE_TAG=latest' >> $GITHUB_ENV
-        if: env.DOCKER_IMAGE_TAG == 'master'
+        if: env.DOCKER_IMAGE_TAG == 'main'
 
       - name: Set Docker Hub repository to username
         run: echo "DOCKER_REPOSITORY=jbarlow83" >> $GITHUB_ENV
@@ -274,22 +294,22 @@ jobs:
       - name: Set image name
         run: echo "DOCKER_IMAGE_NAME=ocrmypdf" >> $GITHUB_ENV
 
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
         with:
           fetch-depth: "0" # 0=all, needed for setuptools-scm to resolve version tags
 
       - name: Login to Docker Hub
-        uses: docker/login-action@v2
+        uses: docker/login-action@v3
         with:
           username: jbarlow83
           password: ${{ secrets.DOCKERHUB_TOKEN }}
 
       - name: Set up QEMU
-        uses: docker/setup-qemu-action@v2
+        uses: docker/setup-qemu-action@v3
 
       - name: Set up Docker Buildx
         id: buildx
-        uses: docker/setup-buildx-action@v2
+        uses: docker/setup-buildx-action@v3
 
       - name: Print image tag
         run: echo "Building image ${DOCKER_REPOSITORY}/${DOCKER_IMAGE_NAME}:${DOCKER_IMAGE_TAG}"

.gitignore

@@ -6,6 +6,7 @@
 .venv*/
 .tox/
 .vscode/
+.hypothesis/
 .ipynb_checkpoints/
 .mypy_cache/
 .pytest_cache/
@@ -26,6 +27,7 @@ venv*/
 *.traineddata
 /private
 /coverage.xml
+/issuepdf
 
 # Package building
 *.egg-info/

.readthedocs.yaml

@@ -16,8 +16,12 @@ formats:
   - pdf
 
 # Optionally set the version of Python and requirements required to build your docs
+build:
+  os: ubuntu-22.04
+  tools:
+    python: "3.9"
+
 python:
-  version: "3.8"
   install:
     - method: pip
       path: .

.reuse/dep5

@@ -41,6 +41,7 @@ Files:
  tests/resources/trivial.pdf
  tests/resources/truetype_font_nomapping.pdf
  tests/resources/type3_font_nomapping.pdf
+ misc/screencast/*
 Copyright: (C) 2022 James R. Barlow
 License: CC-BY-SA-4.0
 

README.md

@@ -42,6 +42,8 @@ ocrmypdf                      # it's a scriptable command line program
 - 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/).
 
 ## Motivation
@@ -68,7 +70,7 @@ Linux, Windows, macOS and FreeBSD are supported. Docker images are also availabl
 | Windows Subsystem for Linux   | ``apt install ocrmypdf``      |
 | Fedora                        | ``dnf install ocrmypdf``      |
 | macOS (Homebrew)              | ``brew install ocrmypdf``     |
-| macOS (nix)                   | ``nix-env -i  ocrmypdf``      |
+| macOS (nix)                   | ``nix-env -i ocrmypdf``       |
 | LinuxBrew                     | ``brew install ocrmypdf``     |
 | FreeBSD                       | ``pkg install py-ocrmypdf``   |
 | Conda                         | ``conda install ocrmypdf``    |

docs/advanced.rst

@@ -10,7 +10,7 @@ Control of unpaper
 
 OCRmyPDF uses ``unpaper`` to provide the implementation of the
 ``--clean`` and ``--clean-final`` arguments.
-`unpaper <https://github.com/Flameeyes/unpaper/blob/master/doc/basic-concepts.md>`__
+`unpaper <https://github.com/Flameeyes/unpaper/blob/main/doc/basic-concepts.md>`__
 provides a variety of image processing filters to improve images.
 
 By default, OCRmyPDF uses only ``unpaper`` arguments that were found to
@@ -47,8 +47,8 @@ and clean up the margins of both.
 
    Some ``unpaper`` features cause multiple input or output files to be
    consumed or produced. OCRmyPDF requires ``unpaper`` to consume one
-   file and produce one file. An deviation from that condition will
+   file and produce one file; errors will result if this assumption is not
-   result in errors.
+   met.
 
 .. note::
 
@@ -82,14 +82,17 @@ is stripped out. Then an image of each page is created with visible text
 masked out. The page image is sent for OCR, and any additional text is
 inserted as OCR. If a file contains a mix of text and bitmap images that
 contain text, OCRmyPDF will locate the additional text in images without
-disrupting the existing text.
+disrupting the existing text. Some PDF OCR solutions render text as
+technically printable or visible in some way, perhaps by drawing it and
+then painting over it. OCRmyPDF cannot distinguish this type of OCR
+text from real text, so it will not be "redone".
 
 If ``--force-ocr`` is issued, then all pages will be rasterized to
-images, discarding any hidden OCR text, and rasterizing any printable
+images, discarding any hidden OCR text, rasterizing any printable
-text. This is useful for redoing OCR, for fixing OCR text with a damaged
+text, and flattening form fields or interactive objects into their visual
-character map (text is selectable but not searchable), and destroying
+representation. This is useful for redoing OCR, for fixing OCR text
-redacted information. Any forms and vector graphics will be rasterized
+with a damaged character map (text is selectable but not searchable),
-as well.
+and destroying redacted information.
 
 Time and image size limits
 --------------------------
@@ -104,13 +107,48 @@ was requested, the preprocessed image layer will be inserted.
 If you want to adjust the amount of time spent on OCR, change
 ``--tesseract-timeout``. You can also automatically skip images that
 exceed a certain number of megapixels with ``--skip-big``. (A 300 DPI,
-8.5×11" page is 8.4 megapixels.)
+8.5×11" page image is 8.4 megapixels.)
 
 .. code-block:: bash
 
     # Allow 300 seconds for OCR; skip any page larger than 50 megapixels
     ocrmypdf --tesseract-timeout 300 --skip-big 50 bigfile.pdf output.pdf
 
+OCR for huge images
+-------------------
+
+Tesseract has internal limits on the size
+of images it will process. If you issue
+``--tesseract-downsample-large-images``, OCRmyPDF will downsample images
+to fit Tesseract limits. (The limits are usually entered only for scanned
+images of oversized media, such as large maps or blueprints exceeding
+110 cm or 43 inches in either dimension, and at high DPI.)
+
+``--tesseract-downsample-above Npixels`` adjusts the threshold at which images
+will be downsampled. By default, only images that exceed any of Tesseract's
+internal limits are downsampled.
+
+You will also need to set ``--tesseract-timeout`` high enough to allow
+for processing.
+
+Only the image sent for OCR is downsampled. The original image is
+preserved.
+
+.. code-block:: bash
+
+    # Allow 600 seconds for OCR on huge images
+    ocrmypdf --tesseract-timeout 600 \
+        --tesseract-downsample-large-images \
+        bigfile.pdf output.pdf
+
+    # Downsample images above 5000 pixels on the longest dimension to
+    # 5000 pixels
+    ocrmypdf --tesseract-timeout 120 \
+        --tesseract-downsample-large-images \
+        --tesseract-downsample-above 5000 \
+        bigfile.pdf output_downsampled_ocr.pdf
+
+
 Overriding default tesseract
 ----------------------------
 
@@ -154,12 +192,13 @@ In addition to tesseract, OCRmyPDF uses the following external binaries:
 -  ``jbig2``
 
 In each case OCRmyPDF will search the ``PATH`` environment variable to
-locate the binaries.
+locate the binaries. By modifying the ``PATH`` environment variable, you
+can override the binaries that OCRmyPDF uses.
 
-Changing tesseract configuration variables
+Changing Tesseract configuration variables
 ------------------------------------------
 
-You can override tesseract's default `control
+You can override Tesseract's default `control
 parameters <https://tesseract-ocr.github.io/tessdoc/tess3/ControlParams.html>`__
 with a configuration file.
 
@@ -234,13 +273,44 @@ Unlike ``sandwich`` this renderer is implemented within OCRmyPDF; anyone
 looking to customize how OCR is presented should look here. A major
 disadvantage of this renderer is it not capable of correctly handling
 text outside the Latin alphabet (specifically, it supports the ISO 8859-1
-character). Pull requests to improve the situation are welcome.
+character set). Pull requests to improve the situation are welcome.
 
 Currently, this renderer has the best compatibility with Mozilla's
 PDF.js viewer.
 
 This works in all versions of Tesseract.
 
+Rendering and rasterizing options
+=================================
+
+.. versionadded:: 14.3.0
+
+The ``--continue-on-soft-render-error`` option allows OCRmyPDF to
+proceed if a page cannot be rasterized/rendered. This is useful if you are
+trying to get the best possible OCR from a PDF that is not well-formed,
+and you are willing to accept some pages that may not visually match the
+input, and that may not OCR well.
+
+Color conversion strategy
+=========================
+
+.. versionadded:: 15.0.0
+
+OCRmyPDF uses Ghostscript to convert PDF to PDF/A. In some cases, this
+conversion requires color conversion. The default strategy is to convert
+using the ``LeaveColorUnchanged`` strategy, which preserves the original
+color space wherever possible (some rare color spaces might still be
+converted).
+
+Usually document scanners produce PDFs in the sRGB color space, and do
+not need to be converted, so the default strategy is appropriate.
+
+Suppose that you have a document that was prepared for professional
+printing in a Separation or CMYK color space, and text was converted to
+curves. In this case, you may want to use a different color conversion
+strategy. The ``--color-conversion-strategy`` option allows you to select a
+different strategy, such as ``RGB``.
+
 Return code policy
 ==================
 
@@ -299,16 +369,31 @@ stable user interface. They may be imported from
         - The program was interrupted by pressing Ctrl+C.
 
 
+.. _tmpdir:
+
+Changing temporary storage location
+===================================
+
+OCRmyPDF generates many temporary files during processing.
+
+To change where temporary files are stored, change the ``TMPDIR``
+environment variable for ocrmypdf's environment. (Python's
+``tempfile.gettempdir()`` returns the root directory in which temporary
+files will be stored.) For example, one could redirect ``TMPDIR`` to a
+large RAM disk to avoid wear on HDD/SSD and potentially improve
+performance.
+
+On Windows, the ``TEMP`` environment variable is used instead.
+
 Debugging the intermediate files
 ================================
 
 OCRmyPDF normally saves its intermediate results to a temporary folder
 and deletes this folder when it exits, whether it succeeded or failed.
 
-If the ``-k`` argument is issued on the command line, OCRmyPDF will keep
+If the ``--keep-temporary-files`` (``-k```) argument is issued on the
-the temporary folder and print the location, whether it succeeded or
+command line, OCRmyPDF will keep the temporary folder and print the location,
-failed (provided the Python interpreter did not crash). An example
+whether it succeeded or failed. An example message is:
-message is:
 
 .. code-block:: none
 

docs/batch.rst

@@ -46,16 +46,6 @@ place, and printing each filename in between runs:
 
    find . -printf '%p\n' -name '*.pdf' -exec ocrmypdf '{}' '{}' \;
 
-Alternatively, with a Docker container and streaming the file through
-standard input and output:
-
-.. code-block:: bash
-
-   find . -name '*.pdf' -print0 | xargs -0 | while read pdf; do
-       pdfout=$(mktemp)
-       docker run --rm -i jbarlow83/ocrmypdf - - <$pdf >$pdfout && cp $pdfout $pdf
-   done
-
 This only runs one ``ocrmypdf`` process at a time. This variation uses
 ``find`` to create a directory list and ``parallel`` to parallelize runs
 of ``ocrmypdf``, again updating files in place.
@@ -70,6 +60,15 @@ In a Windows batch file, use
 
    for /r %%f in (*.pdf) do ocrmypdf %%f %%f
 
+With a Docker container, you will need to stream through standard input and output:
+
+.. code-block:: bash
+
+   find . -name '*.pdf' -print0 | xargs -0 | while read pdf; do
+       pdfout=$(mktemp)
+       docker run --rm -i jbarlow83/ocrmypdf - - <$pdf >$pdfout && cp $pdfout $pdf
+   done
+
 Sample script
 -------------
 
@@ -88,9 +87,9 @@ package <https://www.synology.com/en-global/dsm/packages/Docker>`__ is
 installed. Attached is a script to address particular quirks of using
 OCRmyPDF on one of these devices.
 
-This is only possible for x86-based Synology products. Some Synology
+At the time this script was written, it only worked for x86-based Synology
-products use ARM or Power processors and do not support Docker. Further
+products. It is not known if it will work on ARM-based Synology products.
-adjustments might be needed to deal with the Synology's relatively
+Further adjustments might be needed to deal with the Synology's relatively
 limited CPU and RAM.
 
 .. literalinclude:: ../misc/synology.py
@@ -151,14 +150,14 @@ The watcher service is included in the OCRmyPDF Docker image. To run it:
 .. code-block:: bash
 
     docker run \
-        -v <path to files to convert>:/input \
+        --volume <path to files to convert>:/input \
-        -v <path to store results>:/output \
+        --volume <path to store results>:/output \
-        -v <path to store processed originals>:/archive \
+        --volume <path to store processed originals>:/archive \
-        -e OCR_OUTPUT_DIRECTORY_YEAR_MONTH=1 \
+        --env OCR_OUTPUT_DIRECTORY_YEAR_MONTH=1 \
-        -e OCR_ON_SUCCESS_ARCHIVE=1 \
+        --env OCR_ON_SUCCESS_ARCHIVE=1 \
-        -e OCR_DESKEW=1 \
+        --env OCR_DESKEW=1 \
-        -e PYTHONUNBUFFERED=1 \
+        --env PYTHONUNBUFFERED=1 \
-        -it --entrypoint python3 \
+        --interactive --tty --entrypoint python3 \
         jbarlow83/ocrmypdf \
         watcher.py
 
@@ -170,13 +169,13 @@ original to ``/archive``. The parameters to this image are:
     :header: "Parameter", "Description"
     :widths: 50, 50
 
-    "``-v <path to files to convert>:/input``", "Files placed in this location will be OCRed"
+    "``--volume <path to files to convert>:/input``", "Files placed in this location will be OCRed"
-    "``-v <path to store results>:/output``", "This is where OCRed files will be stored"
+    "``--volume <path to store results>:/output``", "This is where OCRed files will be stored"
-    "``-v <path to store processed originals>:/archive``", "Archive processed originals here"
+    "``--volume <path to store processed originals>:/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}``"
+    "``--env OCR_OUTPUT_DIRECTORY_YEAR_MONTH=1``", "Define environment variable ``OCR_OUTPUT_DIRECTORY_YEAR_MONTH=1`` to place files in the output in ``{output}/{year}/{month}/{filename}``"
-    "``-e OCR_ON_SUCCESS_ARCHIVE=1``", "Define environment variable ``OCR_ON_SUCCESS_ARCHIVE`` to move processed originals"
+    "``--env OCR_ON_SUCCESS_ARCHIVE=1``", "Define environment variable ``OCR_ON_SUCCESS_ARCHIVE`` to move processed originals"
-    "``-e OCR_DESKEW=1``", "Define environment variable ``OCR_DESKEW``  to apply deskew to crooked input PDFs"
+    "``--env OCR_DESKEW=1``", "Define environment variable ``OCR_DESKEW``  to apply deskew to crooked input PDFs"
-    "``-e PYTHONBUFFERED=1``", "This will force ``STDOUT`` to be unbuffered and allow you to see messages in docker logs"
+    "``--env PYTHONBUFFERED=1``", "This will force ``STDOUT`` to be unbuffered and allow you to see messages in docker logs"
 
 This service relies on polling to check for changes to the filesystem. It
 may not be suitable for some environments, such as filesystems shared on a

docs/cloud.rst

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

docs/conf.py

@@ -65,7 +65,7 @@ master_doc = 'index'
 # General information about the project.
 project = 'ocrmypdf'
 copyright = (
-    '2022, James R. Barlow. Licensed under Creative Commons Attribution-ShareAlike 4.0.'
+    '2023, James R. Barlow. Licensed under Creative Commons Attribution-ShareAlike 4.0.'
 )
 author = 'James R. Barlow'
 

docs/contributing.rst

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

docs/cookbook.rst

@@ -231,13 +231,20 @@ Don't actually OCR my PDF
 =========================
 
 If you set ``--tesseract-timeout 0`` OCRmyPDF will apply its image
-processing without performing OCR, if all you want to is to apply image
+processing without performing OCR (by causing OCR to time out). This works
-processing or PDF/A conversion.
+if all you want to is to apply image processing or PDF/A conversion.
 
 .. code-block:: bash
 
     ocrmypdf --tesseract-timeout=0 --remove-background input.pdf output.pdf
 
+.. versionchanged:: v14.1.0
+
+    Prior to this version, ``--tesseract-timeout 0`` would prevent other
+    uses of Tesseract, such as deskewing, from working. This is no longer
+    the case. Use ``--tesseract-non-ocr-timeout`` to control the timeout
+    for non-OCR operations, if needed.
+
 Optimize images without performing OCR
 --------------------------------------
 
@@ -261,9 +268,10 @@ Hyphens denote a range of pages and commas separate page numbers. If you prefer
 to use spaces, quote all of the page numbers: ``--pages '2, 3, 5, 7'``.
 
 OCRmyPDF will warn if your list of page numbers contains duplicates or
-overlap pages. OCRmyPDF does not currently account for document page numbers,
+overlapping pages. OCRmyPDF does not currently account for document page numbers,
 such as an introduction section of a book that uses Roman numerals. It simply
-counts the number of virtual pieces of paper since the start.
+counts the number of virtual pieces of paper since the start. If your list of
+pages is out of numerical order, OCRmyPDF will sort it for you.
 
 Regardless of the argument to ``--pages``, OCRmyPDF will optimize all pages/images
 in the file and convert it to PDF/A, unless you disable those options. Both of these
@@ -372,3 +380,17 @@ Some users may consider enabling lossy JBIG2. See: :ref:`jbig2-lossy`.
 
     Image processing and PDF/A conversion can also introduce lossy transformations
     to your PDF images, even when ``--optimize 1`` is in use.
+
+
+Digitally signed PDFs
+=====================
+
+OCRmyPDF cannot preserve digital signatures in PDFs and also add to OCR to them.
+By default, it will refuse to modify a signed PDF regardless of other settings. You can
+override this behavior with ``--invalidate-digital-signatures``; as the name suggests,
+any digital signatures will be invalidated.
+
+OCRmyPDF cannot open documents that are encrypted with a digital certificate.
+
+Versions of OCRmyPDF prior to 14.4.0 would invalidate existing digital signatures
+without warning.

docs/design_notes.rst

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

docs/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

@@ -72,8 +72,7 @@ Debian and Ubuntu 20.04 or newer
 | |ubu-2004| |ubu-2204|                         |
 +-----------------------------------------------+
 
-Users of Debian 9 ("stretch") or later, or Ubuntu 18.04 or later, including users
+Users of Debian or Ubuntu may simply
-of Windows Subsystem for Linux, may simply
 
 .. code-block:: bash
 
@@ -100,11 +99,11 @@ For full details on version availability for your platform, check the
 Fedora
 ------
 
-.. |fedora-35| image:: https://repology.org/badge/version-for-repo/fedora_35/ocrmypdf.svg
+.. |fedora-37| image:: https://repology.org/badge/version-for-repo/fedora_37/ocrmypdf.svg
-    :alt: Fedora 35
+    :alt: Fedora 37
 
-.. |fedora-36| image:: https://repology.org/badge/version-for-repo/fedora_36/ocrmypdf.svg
+.. |fedora-38| image:: https://repology.org/badge/version-for-repo/fedora_38/ocrmypdf.svg
-    :alt: Fedora 36
+    :alt: Fedora 38
 
 .. |fedora-rawhide| image:: https://repology.org/badge/version-for-repo/fedora_rawhide/ocrmypdf.svg
     :alt: Fedore Rawhide
@@ -114,10 +113,10 @@ Fedora
 +-----------------------------------------------+
 | |latest|                                      |
 +-----------------------------------------------+
-| |fedora-35| |fedora-36| |fedora-rawhide|      |
+| |fedora-37| |fedora-38| |fedora-rawhide|      |
 +-----------------------------------------------+
 
-Users of Fedora 29 or later may simply
+Users of Fedora may simply
 
 .. code-block:: bash
 
@@ -156,7 +155,7 @@ user, follow these steps:
 
 If you get the message ``WARNING: The script ocrmypdf is installed in
 '/home/$USER/.local/bin' which is not on PATH.``, you may need to re-login
-or open a new shell, or manually add this to your user's PATH.
+or open a new shell, or manually adjust your PATH.
 
 To add JBIG2 encoding, see :ref:`jbig2`.
 
@@ -275,6 +274,21 @@ To install OCRmyPDF for Alpine Linux:
 
     apk add ocrmypdf
 
+Gentoo Linux
+------------
+
+.. image:: https://repology.org/badge/version-for-repo/gentoo_ovl_guru/ocrmypdf.svg
+    :alt: Gentoo Linux
+    :target: https://repology.org/metapackage/ocrmypdf
+
+To install OCRmyPDF on Gentoo Linux, use the following commands:
+
+.. code-block:: bash
+
+    eselect repository enable guru
+    emaint sync --repo guru
+    emerge --ask app-text/OCRmyPDF
+
 Other Linux packages
 --------------------
 
@@ -344,18 +358,12 @@ Update the homebrew pip:
 
     pip install --upgrade pip
 
-You can then install OCRmyPDF from PyPI, for the current user:
+You can then install OCRmyPDF from PyPI for the current user:
 
 .. code-block:: bash
 
     pip install --user ocrmypdf
 
-or system-wide:
-
-.. code-block:: bash
-
-    pip install ocrmypdf
-
 The command line program should now be available:
 
 .. code-block:: bash
@@ -374,29 +382,33 @@ Native Windows
 
 You must install the following for Windows:
 
-* Python 3.8 (64-bit) or later
+* Python 64-bit
-* Tesseract 4.1.1 (64-bit) or later
+* Tesseract 64-bit
-* Ghostscript 9.50 (64-bit) or later
+* Ghostscript 64-bit
 
-Using the `Chocolatey <https://chocolatey.org/>`_ package manager, install the
+Using the `winget <https://docs.microsoft.com/en-us/windows/package-manager/winget/>`_
-following when running in an Administrator command prompt:
+package manager:
+
+* ``winget install -e --id Python.Python.3.11``
+* ``winget install -e --id UB-Mannheim.TesseractOCR``
+* ``winget install -e --id ArtifexSoftware.GhostScript``
+
+
+(Or alternately, using the `Chocolatey <https://chocolatey.org/>`_ package manager, install
+the following when running in an Administrator command prompt):
 
 * ``choco install python3``
 * ``choco install --pre tesseract``
 * ``choco install ghostscript``
 * ``choco install pngquant`` (optional)
 
-The commands above will install Python 3.x (latest version), Tesseract, Ghostscript
+Either set of commands will install the required software. At the mmoment there is no
-and pngquant. Chocolatey may also need to install the Windows Visual C++ Runtime
+single command to install Windows.
-DLLs or other Windows patches, and may require a reboot.
 
 You may then use ``pip`` to install ocrmypdf. (This can performed by a user or
 Administrator.):
 
-* ``pip install ocrmypdf``
+* ``python3 -m pip install ocrmypdf``
-
-Chocolatey automatically selects appropriate versions of these applications. Please make sure
-you are installing the 64-bit versions.
 
 OCRmyPDF will check the Windows Registry and standard locations in your Program Files
 for third party software it needs (specifically, Tesseract and Ghostscript). To
@@ -408,12 +420,12 @@ to change the PATH.
 
     As of early 2021, users have reported problems with the Microsoft Store version of
     Python and OCRmyPDF. These issues affect many other third party Python packages.
-    Please download Python from Python.org or Chocolatey instead, and do not use the
+    Please download Python from Python.org or a package manager instead of the
     Microsoft Store version.
 
 .. warning::
 
-    32-bit Windows might work, but is not supported.
+    32-bit Windows is not supported.
 
 Windows Subsystem for Linux
 ---------------------------
@@ -440,7 +452,7 @@ Cygwin64
 
 First install the the following prerequisite Cygwin packages using ``setup-x86_64.exe``::
 
-    python38 (or later)
+    python39 (or later)
     python3?-devel
     python3?-pip
     python3?-lxml
@@ -449,7 +461,7 @@ First install the the following prerequisite Cygwin packages using ``setup-x86_6
        (where 3? means match the version of python3 you installed)
 
     gcc-g++
-    ghostscript (<=9.50 or >=9.52-2 see note below)
+    ghostscript
     libexempi3
     libexempi-devel
     libffi6
@@ -460,13 +472,6 @@ First install the the following prerequisite Cygwin packages using ``setup-x86_6
     tesseract-ocr
     tesseract-ocr-devel
 
-.. note::
-
-    The Cygwin package for Ghostscript in versions 9.52 and
-    9.52-1 contained a bug that caused an exception to occur when
-    ocrmypdf invoked gs.  Make sure you have either 9.50 (or earlier)
-    or 9.52-2 (or later).
-
 Then open a Cygwin terminal (i.e. ``mintty``), run the following commands. Note
 that if you are using the version of ``pip`` that was installed with the Cygwin
 Python package, the command name will be ``pip3``.  If you have since updated
@@ -518,21 +523,6 @@ the latest version. However, PyPI and ``pip`` cannot address the fact
 that ``ocrmypdf`` depends on certain non-Python system libraries and
 programs being installed.
 
-.. warning::
-
-    Debian and Ubuntu users: unfortunately, Debian and Ubuntu customize
-    Python in non-standard ways, and the nature of these customizations
-    varies from release to release. This can make for a frustrating
-    user experience. The instructions below work on almost all platforms that
-    have Python installed, except for Debian and Ubuntu, where you may need
-    to take additional steps. For best results on Debian and Ubuntu, use the
-    ``apt`` packages; or if these are too old, run
-    ``apt install python3-pip python3-venv``, create a virtual environment,
-    and install OCRmyPDF in that environment.
-
-    `See here for more information on Debian-Python issues
-    <https://gist.github.com/tiran/2dec9e03c6f901814f6d1e8dad09528e>`__.
-
 For best results, first install `your platform's
 version <https://repology.org/metapackage/ocrmypdf/versions>`__ of
 ``ocrmypdf``, using the instructions elsewhere in this document. Then
@@ -551,21 +541,6 @@ try:
 You should then be able to run ``ocrmypdf --version`` and see that the
 latest version was located.
 
-Since ``pip install --user`` does not work correctly on some platforms,
-notably Ubuntu 16.04 and older, and the Homebrew version of Python,
-instead use this for a system wide installation:
-
-.. code-block:: bash
-
-    pip install ocrmypdf
-
-.. note::
-
-    AArch64 (ARM64) users: this process will be difficult because most
-    Python packages are not available as binary wheels for your platform.
-    You're probably better off using a platform install on Debian, Ubuntu,
-    or Fedora.
-
 Requirements for pip and HEAD install
 -------------------------------------
 
@@ -575,13 +550,16 @@ manager. ``pip`` cannot provide them.
 
 The following versions are required:
 
--  Python 3.8 or newer
+-  Python 3.9 or newer
--  Ghostscript 9.50 or newer
+-  Ghostscript 9.55 or newer
 -  Tesseract 4.1.1 or newer
 -  jbig2enc 0.29 or newer
 -  pngquant 2.5 or newer
 -  unpaper 6.1
 
+We recommend 64-bit versions of all software. (32-bit versions are not
+supported, although on Linux, they may still work.)
+
 jbig2enc, pngquant, and unpaper are optional. If missing certain
 features are disabled. OCRmyPDF will discover them as soon as they are
 available.
@@ -608,7 +586,7 @@ unfortunately, the ``pip install`` command cannot satisfy all of them.
 Installing HEAD revision from sources
 =====================================
 
-If you have ``git`` and Python 3.8 or newer installed, you can install
+If you have ``git`` and Python 3.9 or newer installed, you can install
 from source. When the ``pip`` installer runs, it will alert you if
 dependencies are missing.
 
@@ -637,9 +615,9 @@ system-wide:
 
 .. code-block:: bash
 
-    git clone -b master https://github.com/ocrmypdf/OCRmyPDF.git
+    git clone -b main https://github.com/ocrmypdf/OCRmyPDF.git
-    python3 -m venv venv
+    python3 -m venv .venv
-    source venv/bin/activate
+    source .venv/bin/activate
     cd OCRmyPDF
     pip install .
 
@@ -664,9 +642,9 @@ To install all of the development and test requirements:
 
 .. code-block:: bash
 
-    git clone -b master https://github.com/ocrmypdf/OCRmyPDF.git
+    git clone -b main https://github.com/ocrmypdf/OCRmyPDF.git
-    python -m venv
+    python -m .venv
-    source venv/bin/activate
+    source .venv/bin/activate
     cd OCRmyPDF
     pip install -e .[test]
 
@@ -687,3 +665,18 @@ To manually install the ``bash`` completion, copy
 To manually install the ``fish`` completion, copy
 ``misc/completion/ocrmypdf.fish`` to
 ``~/.config/fish/completions/ocrmypdf.fish``.
+
+Note on 32-bit support
+======================
+
+Many Python libraries no longer 32-bit binary wheels for Linux. This
+includes many of the libraries that OCRmyPDF depends on, such as
+Pillow. The easiest way to express this to end users is to say we don't
+support 32-bit Linux.
+
+However, if your Linux distribution still supports 32-bit binaries, you
+can still install and use OCRmyPDF. A warning message will appear.
+In practice, OCRmyPDF may need more than 32-bit memory space to run when
+large documents are processed, so there are practical limitations to what
+users can accomplish with it. Still, for the common use case of an 32-bit
+ARM NAS or Raspberry Pi processing small documents, it should work.

docs/jbig2.rst

@@ -59,5 +59,9 @@ To turn on JBIG2 lossy mode, add the argument ``--jbig2-lossy``.
 also required. Also, a JBIG2 encoder must be installed as described in
 the previous section.
 
+You can adjust the threshold for JBIG2 compression with the
+``--jbig2-threshold``. The default is 0.85, meaning that if two symbols
+are 85% similar, they will be compressed together.
+
 *Due to an oversight, ocrmypdf v7.0 and v7.1 used lossy mode by
 default.*

docs/languages.rst

@@ -12,7 +12,7 @@ OCRmyPDF uses Tesseract for OCR, and relies on its language packs for all langua
 On most platforms, English is installed with Tesseract by default, but not always.
 
 Tesseract supports `most
-languages <https://github.com/tesseract-ocr/tesseract/blob/master/doc/tesseract.1.asc#languages>`__.
+languages <https://github.com/tesseract-ocr/tesseract/blob/main/doc/tesseract.1.asc#languages>`__.
 Languages are identified by standardized three-letter codes (called ISO 639-2 Alpha-3).
 Tesseract's documentation also lists the three-letter code for your language.
 Some are anglicized, e.g. Spanish is ``spa`` rather than ``esp``, while others

docs/maintainers.rst

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

docs/optimizer.rst

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

docs/pdfsecurity.rst

@@ -29,13 +29,9 @@ attack vectors.
 In short, PDFs `may contain
 viruses <https://security.stackexchange.com/questions/64052/can-a-pdf-file-contain-a-virus>`__.
 
-This
+If you do not trust a PDF or its source, do not open it or use OCRmyPDF
-`article <https://theinvisiblethings.blogspot.ca/2013/02/converting-untrusted-pdfs-into-trusted.html>`__
+on it. Consider using a Docker container or virtual machine to isolate
-describes a high-paranoia method which allows potentially hostile PDFs
+an untrusted PDF from your system.
-to be viewed and rasterized safely in a disposable virtual machine. A
-trusted PDF created in this manner is converted to images and loses all
-information making it searchable and losing all compression. OCRmyPDF
-could be used to restore searchability.
 
 How OCRmyPDF processes PDFs
 ===========================
@@ -43,11 +39,11 @@ How OCRmyPDF processes PDFs
 OCRmyPDF must open and interpret your PDF in order to insert an OCR
 layer. First, it runs all PDFs through
 `pikepdf <https://github.com/pikepdf/pikepdf>`__, a library based on
-`qpdf <https://github.com/qpdf/qpdf>`__, a program that repairs PDFs
+`QPDF <https://github.com/qpdf/qpdf>`__, a program that repairs PDFs
 with syntax errors. This is done because, in the author's experience, a
 significant number of PDFs in the wild, especially those created by
-scanners, are not well-formed files. qpdf makes it more likely that
+scanners, are not well-formed files. QPDF makes it more likely that
-OCRmyPDF will succeed, but offers no security guarantees. qpdf is also
+OCRmyPDF will succeed, but offers no security guarantees. QPDF is also
 used to split the PDF into single page PDFs.
 
 Finally, OCRmyPDF rasterizes each page of the PDF using
@@ -58,109 +54,72 @@ into the existing PDF or it may essentially reconstruct ("re-fry") a
 visually identical PDF that may be quite different at the binary level.
 That said, OCRmyPDF is not a tool designed for sanitizing PDFs.
 
-.. _ocr-service:
+Password protected PDFs
-
+=======================
-Using OCRmyPDF online or as a service
-=====================================
-
-OCRmyPDF is not designed for use as a public web service where a
-malicious user could upload a chosen PDF. In particular, it is not
-necessarily secure against PDF malware or PDFs that cause denial of
-service. OCRmyPDF relies on Ghostscript, and therefore, if deployed
-online one should be prepared to comply with Ghostscript's Affero GPL
-license, and any other licenses.
-
-Setting aside these concerns, a side effect of OCRmyPDF is that it may
-incidentally sanitize PDFs containing certain types of malware. It
-repairs the PDF with pikepdf/libqpdf, which could correct malformed PDF
-structures that are part of an attack. When PDF/A output is selected
-(the default), the input PDF is partially reconstructed by Ghostscript.
-When ``--force-ocr`` is used, all pages are rasterized and reconverted
-to PDF, which could remove malware in embedded images.
-
-OCRmyPDF should be relatively safe to use in a trusted intranet, with
-some considerations:
-
-Limiting CPU usage
-------------------
-
-OCRmyPDF will attempt to use all available CPUs and storage, so
-executing ``nice ocrmypdf`` or limiting the number of jobs with the
-``-j`` argument may ensure the server remains available. Another option
-would be to run OCRmyPDF jobs inside a Docker container, a virtual machine,
-or a cloud instance, which can impose its own limits on CPU usage and be
-terminated "from orbit" if it fails to complete.
-
-Temporary storage requirements
-------------------------------
-
-OCRmyPDF will use a large amount of temporary storage for its work,
-proportional to the total number of pixels needed to rasterize the PDF.
-The raster image of a 8.5×11" color page at 300 DPI takes 25 MB
-uncompressed; OCRmyPDF saves its intermediates as PNG, but that still
-means it requires about 9 MB per intermediate based on average
-compression ratios. Multiple intermediates per page are also required,
-depending on the command line given. A rule of thumb would be to allow
-100 MB of temporary storage per page in a file – meaning that a small
-cloud servers or small VM partitions should be provisioned with plenty
-of extra space, if say, a 500 page file might be sent.
-
-To check temporary storage usage on actual files, run
-``ocrmypdf -k ...`` which will preserve and print the path to temporary
-storage when the job is done.
-
-To change where temporary files are stored, change the ``TMPDIR``
-environment variable for ocrmypdf's environment. (Python's
-``tempfile.gettempdir()`` returns the root directory in which temporary
-files will be stored.) For example, one could redirect ``TMPDIR`` to a
-large RAM disk to avoid wear on HDD/SSD and potentially improve
-performance. On Amazon Web Services, ``TMPDIR`` can be set to `empheral
-storage <https://docs.aws.amazon.com/AWSEC2/latest/UserGuide/InstanceStorage.html>`__.
-
-Timeouts
---------
-
-To prevent excessively long OCR jobs consider setting
-``--tesseract-timeout`` and/or ``--skip-big`` arguments. ``--skip-big``
-is particularly helpful if your PDFs include documents such as reports
-on standard page sizes with large images attached - often large images
-are not worth OCR'ing anyway.
-
-Commercial alternatives
------------------------
-
-The author also provides professional services that include OCR and
-building databases around PDFs, and is happy to provide consultation.
-
-Abbyy Cloud OCR is viable commercial alternative with a web services
-API. Amazon Textract, Google Cloud Vision, and Microsoft Azure 
-Computer Vision provide advanced OCR but have less PDF rendering capability.
-
-Password protection, digital signatures and certification
-=========================================================
 
 Password protected PDFs usually have two passwords, and owner and user
 password. When the user password is set to empty, PDF readers will open
-the file automatically and marked it as "(SECURED)". While not as
+the file automatically and mark it as "(SECURED)". Password security can
-reliable as a digital signature, this indicates that whoever set the
+also request certain restrictions on the PDF, but anyone can remove these
-password approved of the file at that time. When the user password is
+restrictions if they have either the owner *or* user password. Passwords
-set, the document cannot be viewed without the password.
+mainly present a barrier for casual users.
 
-Either way, OCRmyPDF does not remove passwords from PDFs and exits with
+OCRmyPDF cannot remove passwords from PDFs. If you want to remove a
-an error on encountering them.
+password from a PDF, you must use other software, such as ``qpdf``.
 
-``qpdf`` can remove passwords. If the owner and user password are set, a
+If the owner and user password are set, a
 password is required for ``qpdf``. If only the owner password is set, then the
-password can be stripped, even if one does not have the owner password.
+password can be stripped, even if one does not have the owner password. To
+remove the password from a using QPDF, use:
 
-After OCR is applied, password protection is not permitted on PDF/A
+.. code-block:: bash
-documents but the file can be converted to regular PDF.
+
+   qpdf --decrypt --password='abc123' input.pdf no_password.pdf
+
+Then you can run OCRmyPDF on the file.
+
+In its default mode, OCRmyPDF generates PDF/A. Passwords may not be set on PDF/A
+documents. If you want to set a password on the output PDF, you must
+specify ``--output-type pdf``.
+
+Signature images
+================
 
 Many programs exist which are capable of inserting an image of someone's
 signature. On its own, this offers no security guarantees. It is trivial
 to remove the signature image and apply it to other files. This practice
 offers no real security.
 
+Digital signatures
+==================
+
 Important documents can be digitally signed and certified to attest to
-their authorship. OCRmyPDF cannot do this. Open source tools such as
+their authorship, approval or execution of a legal agreement. OCRmyPDF
-pdfbox (Java) have this capability as does Adobe Acrobat.
+will detect signed PDFs and will not modify them, unless the
+``--invalidate-digital-signatures`` option is used, which will
+invalidate any signatures. (The signature may still be present in the PDF
+if opened, but PDF readers will not validate it.)
+
+A digital signature adds a cryptographic hash of the document to the
+document, so tamper protection is provided. That also precludes OCRmyPDF
+from modifying the document and preserving the signature.
+
+Digital signatures are not the same as a signature image. A digital
+signature is a cryptographic hash of the document that is encrypted with
+the author's private key. The signature is decrypted with the author's
+public key. The public key is usually distributed by a certificate
+authority. The signature is then verified by the PDF reader. If the
+document is modified, the signature will be invalidated.
+
+Certificate-encrypted PDFs
+==========================
+
+PDFs can be encrypted with a certificate. This is a more secure form of
+encryption than a password. The certificate is usually issued by a
+certificate authority. A certificate is used to encrypt the document using
+the public key for the benefit of a specific recipient who possesses
+the private key.
+
+OCRmyPDF cannot open certificate-encrypted PDFs. If you have the
+certificate, you can use other PDF software, such as Acrobat, to
+decrypt the PDF.

docs/release_notes.rst

@@ -28,6 +28,99 @@ tagged yet.
 
 .. |OCRmyPDF PyPI| image:: https://img.shields.io/pypi/v/ocrmypdf.svg
 
+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 many older dependencies - see ``pyproject.toml`` for details.
+   Generally speaking, Ubuntu 22.04 is our baseline system.
+-  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 an issue
+   with pikepdf has been 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 situations where a small portion of an image on a page reports a
+   high DPI (resolution). Previously, the entire page would be rasterized at the
+   highest resolution, 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
 =======
 

misc/completion/ocrmypdf.bash

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

misc/completion/ocrmypdf.fish

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

misc/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"]

pyproject.toml

@@ -1,11 +1,7 @@
 # SPDX-FileCopyrightText: 2022 James R. Barlow
 # SPDX-License-Identifier: MPL-2.0
 [build-system]
-requires = [
+requires = ["setuptools >= 61", "setuptools_scm[toml] >= 7.0.5", "wheel"]
-  "setuptools >= 61",
-  "setuptools_scm[toml] >= 7.0.5",
-  "wheel"
-]
 build-backend = "setuptools.build_meta"
 
 [project]
@@ -13,23 +9,21 @@ name = "ocrmypdf"
 dynamic = ["version"]
 description = "OCRmyPDF adds an OCR text layer to scanned PDF files, allowing them to be searched"
 readme = "README.md"
-license = {text = "MPL-2.0"}
+license = { text = "MPL-2.0" }
-requires-python = ">=3.8"
+requires-python = ">=3.9"
 dependencies = [
-  "Pillow>=8.2.0",
+  "Pillow>=9.0.1",
-  "coloredlogs>=14.0",
   "deprecation>=2.1.0",
-  "img2pdf>=0.3.0", # pure Python
+  "img2pdf>=0.4.4",
   "packaging>=20",
-  "pdfminer.six>=20201018",
+  "pdfminer.six>=20220319",
-  "pikepdf>=5.0.1",
+  "pikepdf>=8",
   "pluggy>=0.13.0",
-  "reportlab>=3.5.66",
+  "reportlab>=3.6.8",
-  "tqdm>=4",
+  "rich>=13",
-  "importlib-resources>=5;python_version<'3.9'",  # until Python 3.9
   "typing-extensions>=4;python_version<'3.10'",
 ]
-authors = [{name = "James R. Barlow", email="james@purplerock.ca"}]
+authors = [{ name = "James R. Barlow", email = "james@purplerock.ca" }]
 classifiers = [
   "Development Status :: 5 - Production/Stable",
   "Environment :: Console",
@@ -37,27 +31,17 @@ classifiers = [
   "Intended Audience :: Science/Research",
   "Intended Audience :: System Administrators",
   "License :: OSI Approved :: Mozilla Public License 2.0 (MPL 2.0)",
-  "Operating System :: MacOS :: MacOS X",
+  "Operating System :: MacOS",
-  "Operating System :: Microsoft :: Windows :: Windows 10",
+  "Operating System :: Microsoft :: Windows",
   "Operating System :: POSIX",
   "Operating System :: POSIX :: BSD",
   "Operating System :: POSIX :: Linux",
   "Programming Language :: Python :: 3",
-  "Programming Language :: Python :: 3 :: Only",
-  "Programming Language :: Python :: 3.8",
-  "Programming Language :: Python :: 3.9",
-  "Programming Language :: Python :: 3.10",
   "Topic :: Scientific/Engineering :: Image Recognition",
   "Topic :: Text Processing :: Indexing",
   "Topic :: Text Processing :: Linguistic",
 ]
-keywords = [
+keywords = ["PDF", "OCR", "optical character recognition", "PDF/A", "scanning"]
-  "PDF",
-  "OCR",
-  "optical character recognition",
-  "PDF/A",
-  "scanning",
-]
 
 [project.urls]
 Documentation = "https://ocrmypdf.readthedocs.io/"
@@ -68,16 +52,17 @@ Tracker = "https://github.com/ocrmypdf/OCRmyPDF/issues"
 docs = ["sphinx", "sphinx-issues", "sphinx-rtd-theme"]
 extended_test = ["PyMuPDF==1.19.1"]
 test = [
-  "coverage[toml]>=5",
+  "coverage[toml]>=6.2",
-  "pytest>=6.0.0",
+  "hypothesis>=6.36.0",
-  "pytest-cov>=2.11.1",
+  "pytest>=6.2.5",
-  "pytest-xdist>=2.2.0",
+  "pytest-cov>=3.0.0",
-  "python-xmp-toolkit==2.0.1",  # also requires apt-get install libexempi3
+  "pytest-xdist>=2.5.0",
+  "python-xmp-toolkit==2.0.1", # also requires apt-get install libexempi3
   "types-Pillow",
   "types-humanfriendly",
 ]
 watcher = ["watchdog>=1.0.2"]
-webservice = ["Flask>=1"]
+webservice = ["Flask>=2.0.1"]
 
 [project.scripts]
 ocrmypdf = "ocrmypdf.__main__:run"
@@ -92,11 +77,11 @@ namespaces = false
 [tool.setuptools_scm]
 
 [tool.distutils.bdist_wheel]
-python-tag = "py38"
+python-tag = "py39"
 
 [tool.black]
 line-length = 88
-target-version = ["py38", "py39", "py310", "py311"]
+target-version = ["py39", "py310", "py311"]
 skip-string-normalization = true
 include = '\.pyi?$'
 exclude = '''
@@ -137,28 +122,7 @@ exclude_lines = [
   "if 0:",
   "if False:",
   "if __name__ == .__main__.:",
-  "if TYPE_CHECKING:"
+  "if TYPE_CHECKING:",
-]
-
-[tool.isort]
-profile = "black"
-known_first_party = "ocrmypdf"
-known_third_party = [
-  "PIL",
-  "flask",
-  "img2pdf",
-  "ocrmypdf",
-  "pdfminer",
-  "pikepdf",
-  "pkg_resources",
-  "pluggy",
-  "pytest",
-  "reportlab",
-  "setuptools",
-  "sphinx_rtd_theme",
-  "tqdm",
-  "watchdog",
-  "werkzeug"
 ]
 
 [tool.pytest.ini_options]
@@ -180,20 +144,20 @@ module = [
   'pdfminer.*',
   'reportlab.*',
   'fitz',
-  'libxmp.utils'
+  'libxmp.utils',
 ]
 ignore_missing_imports = true
 
 [tool.ruff]
 select = [
-  "D", # pydocstyle
+  "D",    # pydocstyle
-  "E", # pycodestyle
+  "E",    # pycodestyle
-  "W", # pycodestyle
+  "W",    # pycodestyle
-  "F", # pyflakes
+  "F",    # pyflakes
   "I001", # isort
-  "UP", # pyupgrade
+  "UP",   # pyupgrade
 ]
-target-version = "py38"
+target-version = "py39"
 
 [tool.ruff.isort]
 known-first-party = ["ocrmypdf"]

snapcraft.yaml

@@ -5,9 +5,9 @@
 
 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
@@ -18,8 +18,8 @@ architectures: [amd64]
 
 environment:
   TESSDATA_PREFIX: $SNAP/usr/share/tesseract-ocr/4.00/tessdata
-  GS_LIB: $SNAP/usr/share/ghostscript/9.50/Resource/Init
+  GS_LIB: $SNAP/usr/share/ghostscript/9.55/Resource/Init
-  GS_FONTPATH: $SNAP/usr/share/ghostscript/9.50/Resource/Font
+  GS_FONTPATH: $SNAP/usr/share/ghostscript/9.55/Resource/Font
   LD_LIBRARY_PATH: $SNAP/usr/lib/x86_64-linux-gnu
 
 apps:
@@ -49,7 +49,7 @@ parts:
   jbig2enc:
     plugin: autotools
     source: https://github.com/agl/jbig2enc.git
-    source-tag: '0.29'
+    source-tag: "0.29"
     build-packages:
       - libleptonica-dev
 

src/ocrmypdf/_exec/ghostscript.py

@@ -28,24 +28,50 @@ except AttributeError:
     # Pillow 9 shim
     Transpose = Image  # type: ignore
 
+
+COLOR_CONVERSION_STRATEGIES = frozenset(
+    [
+        'CMYK',
+        'Gray',
+        'LeaveColorUnchanged',
+        'RGB',
+        'UseDeviceIndependentColor',
+    ]
+)
+
 log = logging.getLogger(__name__)
 
-# Most reliable what to get the bitness of Python interpreter, according to Python docs
-_IS_64BIT = sys.maxsize > 2**32
 
-_GSWIN = None
+class DuplicateFilter(logging.Filter):
-if os.name == 'nt':
+    """Filter out duplicate log messages."""
-    if _IS_64BIT:
-        _GSWIN = 'gswin64c'
-    else:
-        _GSWIN = 'gswin32c'
 
-GS = _GSWIN if _GSWIN else 'gs'
+    def __init__(self, logger: logging.Logger):
-del _GSWIN
+        self.last: logging.LogRecord | None = None
+        self.count = 0
+        self.logger = logger
+
+    def filter(self, record):
+        if self.last and record.msg == self.last.msg:
+            self.count += 1
+            return False
+        else:
+            if self.count >= 1:
+                rep_msg = f"(previous message repeated {self.count} times)"
+                self.count = 0  # Avoid infinite recursion
+                self.logger.log(self.last.levelno, rep_msg)
+            self.last = record
+            return True
 
 
-def version():
+log.addFilter(DuplicateFilter(log))
-    return get_version(GS)
+
+
+# Ghostscript executable - gswin32c is not supported
+GS = 'gswin64c' if os.name == 'nt' else 'gs'
+
+
+def version() -> Version:
+    return Version(get_version(GS))
 
 
 def _gs_error_reported(stream) -> bool:
@@ -63,6 +89,7 @@ def rasterize_pdf(
     page_dpi: Resolution | None = None,
     rotation: int | None = None,
     filter_vector: bool = False,
+    stop_on_error: bool = False,
 ):
     """Rasterize one page of a PDF at resolution raster_dpi in canvas units."""
     raster_dpi = raster_dpi.round(6)
@@ -83,6 +110,7 @@ def rasterize_pdf(
             f'-r{raster_dpi.x:f}x{raster_dpi.y:f}',
         ]
         + (['-dFILTERVECTOR'] if filter_vector else [])
+        + (['-dPDFSTOPONERROR'] if stop_on_error else [])
         + [
             '-o',
             '-',
@@ -158,9 +186,11 @@ def generate_pdfa(
     output_file: os.PathLike,
     *,
     compression: str,
+    color_conversion_strategy: str,
     pdf_version: str = '1.5',
     pdfa_part: str = '2',
     progressbar_class=None,
+    stop_on_error: bool = False,
 ):
     # Ghostscript's compression is all or nothing. We can either force all images
     # to JPEG, force all to Flate/PNG, or let it decide how to encode the images.
@@ -186,13 +216,16 @@ def generate_pdfa(
             "-dAutoFilterGrayImages=true",
         ]
 
-    strategy = 'LeaveColorUnchanged'
+    gs_version = version()
-    gs_version = Version(version())
     if gs_version == Version('9.56.0'):
         # 9.56.0 breaks our OCR, should be fixed in 9.56.1
         # https://bugs.ghostscript.com/show_bug.cgi?id=705187
         compression_args.append('-dNEWPDF=false')
 
+    if os.name == 'nt':
+        # Windows has lots of fatal "permission denied" errors
+        stop_on_error = False
+
     # nb no need to specify ProcessColorModel when ColorConversionStrategy
     # is set; see:
     # https://bugs.ghostscript.com/show_bug.cgi?id=699392
@@ -202,15 +235,16 @@ def generate_pdfa(
             "-dBATCH",
             "-dNOPAUSE",
             "-dSAFER",
-            "-dCompatibilityLevel=" + str(pdf_version),
+            f"-dCompatibilityLevel={str(pdf_version)}",
             "-sDEVICE=pdfwrite",
             "-dAutoRotatePages=/None",
-            "-sColorConversionStrategy=" + strategy,
+            f"-sColorConversionStrategy={color_conversion_strategy}",
         ]
+        + (['-dPDFSTOPONERROR'] if stop_on_error else [])
         + compression_args
         + [
             "-dJPEGQ=95",
-            "-dPDFA=" + pdfa_part,
+            f"-dPDFA={pdfa_part}",
             "-dPDFACompatibilityPolicy=1",
             "-o",
             "-",
@@ -241,14 +275,9 @@ def generate_pdfa(
         # If there is an error we log the whole stderr, except for filtering
         # duplicates.
         if _gs_error_reported(stderr):
-            last_part = None
+            # Ghostscript outputs the pattern **** Error: ....  frequently.
-            repcount = 0
+            # Occasionally the error message is spammed many times. We filter
+            # out duplicates of this message using the filter above. We use
+            # the **** pattern to split the stderr into parts.
             for part in stderr.split('****'):
-                if part != last_part:
+                log.error(part)
-                    if repcount > 1:
-                        log.error(f"(previous error message repeated {repcount} times)")
-                        repcount = 0
-                    log.error(part)
-                else:
-                    repcount += 1
-                last_part = part

src/ocrmypdf/_exec/jbig2enc.py

@@ -7,12 +7,14 @@ from __future__ import annotations
 
 from subprocess import PIPE
 
+from packaging.version import Version
+
 from ocrmypdf.exceptions import MissingDependencyError
 from ocrmypdf.subprocess import get_version, run
 
 
-def version():
+def version() -> Version:
-    return get_version('jbig2', regex=r'jbig2enc (\d+(\.\d+)*).*')
+    return Version(get_version('jbig2', regex=r'jbig2enc (\d+(\.\d+)*).*'))
 
 
 def available():
@@ -23,15 +25,17 @@ def available():
     return True
 
 
-def convert_group(*, cwd, infiles, out_prefix):
+def convert_group(*, cwd, infiles, out_prefix, threshold):
     args = [
         'jbig2',
         '-b',
         out_prefix,
-        '-s',  # symbol mode (lossy)
+        '--symbol-mode',  # symbol mode (lossy)
+        '-t',
+        str(threshold),  # threshold
         # '-r', # refinement mode (lossless symbol mode, currently disabled in
         # jbig2)
-        '-p',
+        '--pdf',
     ]
     args.extend(infiles)
     proc = run(args, cwd=cwd, stdout=PIPE, stderr=PIPE)
@@ -40,11 +44,13 @@ def convert_group(*, cwd, infiles, out_prefix):
 
 
 def convert_group_mp(args):
-    return convert_group(cwd=args[0], infiles=args[1], out_prefix=args[2])
+    return convert_group(
+        cwd=args[0], infiles=args[1], out_prefix=args[2], threshold=args[3]
+    )
 
 
-def convert_single(*, cwd, infile, outfile):
+def convert_single(*, cwd, infile, outfile, threshold):
-    args = ['jbig2', '-p', infile]
+    args = ['jbig2', '--pdf', '-t', str(threshold), infile]
     with open(outfile, 'wb') as fstdout:
         proc = run(args, cwd=cwd, stdout=fstdout, stderr=PIPE)
     proc.check_returncode()
@@ -52,4 +58,6 @@ def convert_single(*, cwd, infile, outfile):
 
 
 def convert_single_mp(args):
-    return convert_single(cwd=args[0], infile=args[1], outfile=args[2])
+    return convert_single(
+        cwd=args[0], infile=args[1], outfile=args[2], threshold=args[3]
+    )

src/ocrmypdf/_exec/pngquant.py

@@ -10,14 +10,15 @@ from io import BytesIO
 from pathlib import Path
 from subprocess import PIPE
 
+from packaging.version import Version
 from PIL import Image
 
 from ocrmypdf.exceptions import MissingDependencyError
 from ocrmypdf.subprocess import get_version, run
 
 
-def version():
+def version() -> Version:
-    return get_version('pngquant', regex=r'(\d+(\.\d+)*).*')
+    return Version(get_version('pngquant', regex=r'(\d+(\.\d+)*).*'))
 
 
 def available():

src/ocrmypdf/_exec/tesseract.py

@@ -113,13 +113,13 @@ class TesseractVersion(Version):
     )
 
 
-def version() -> str:
+def version() -> Version:
-    return get_version('tesseract', regex=r'tesseract\s(.+)')
+    return TesseractVersion(get_version('tesseract', regex=r'tesseract\s(.+)'))
 
 
 def has_thresholding() -> bool:
     """Does Tesseract have -c thresholding method capability?"""
-    return version() >= '5.0'
+    return version() >= Version('5.0')
 
 
 def get_languages() -> set[str]:
@@ -233,6 +233,7 @@ def get_deskew(
     parsed = _parse_tesseract_output(p.stdout)
     deskew_radians = float(parsed.get('Deskew angle', 0))
     deskew_degrees = 180 / pi * deskew_radians
+    log.debug(f"Deskew angle: {deskew_degrees:.3f}")
     return deskew_degrees
 
 

src/ocrmypdf/_exec/unpaper.py

@@ -15,13 +15,14 @@ from pathlib import Path
 from subprocess import PIPE, STDOUT
 from typing import Iterator, Union
 
+from packaging.version import Version
 from PIL import Image
 
 from ocrmypdf.exceptions import MissingDependencyError, SubprocessOutputError
 from ocrmypdf.subprocess import get_version, run
 
 # unpaper documentation:
-# https://github.com/Flameeyes/unpaper/blob/master/doc/basic-concepts.md
+# https://github.com/Flameeyes/unpaper/blob/main/doc/basic-concepts.md
 
 
 if sys.version_info >= (3, 10):
@@ -67,8 +68,8 @@ class UnpaperImageTooLargeError(Exception):
         super().__init__(self.message)
 
 
-def version() -> str:
+def version() -> Version:
-    return get_version('unpaper')
+    return Version(get_version('unpaper'))
 
 
 SUPPORTED_MODES = {'1', 'L', 'RGB'}

src/ocrmypdf/_logging.py

@@ -6,9 +6,18 @@
 from __future__ import annotations
 
 import logging
-from contextlib import suppress
 
-from tqdm import tqdm
+from rich.console import Console
+from rich.logging import RichHandler
+from rich.progress import (
+    BarColumn,
+    MofNCompleteColumn,
+    Progress,
+    TaskProgressColumn,
+    TextColumn,
+    TimeRemainingColumn,
+)
+from rich.table import Column
 
 
 class PageNumberFilter(logging.Filter):
@@ -23,21 +32,61 @@ class PageNumberFilter(logging.Filter):
         return True
 
 
-class TqdmConsole:
+class RichLoggingHandler(RichHandler):
-    """Wrapper to log messages in a way that is compatible with tqdm progress bar.
+    def __init__(self, console: Console, **kwargs):
+        super().__init__(
+            console=console, show_level=False, show_time=False, markup=True, **kwargs
+        )
 
-    This routes log messages through tqdm so that it can print them above the
-    progress bar, and then refresh the progress bar, rather than overwriting
-    it which looks messy.
-    """
 
-    def __init__(self, file):
+class RichTqdmProgressAdapter:
-        self.file = file
+    """Adapt tqdm API to rich progress bar."""
 
-    def write(self, msg):
+    def __init__(
-        # When no progress bar is active, tqdm.write() routes to print()
+        self,
-        tqdm.write(msg.rstrip(), end='\n', file=self.file)
+        *,
+        console: Console,
+        desc: str,
+        total: float | None = None,
+        unit: str | None = None,
+        unit_scale: float | None = 1.0,
+        disable: bool = False,
+        **kwargs,
+    ):
+        self.progress = Progress(
+            TextColumn(
+                "[progress.description]{task.description}",
+                table_column=Column(min_width=20),
+            ),
+            BarColumn(),
+            TaskProgressColumn(),
+            MofNCompleteColumn(),
+            TimeRemainingColumn(),
+            console=console,
+            auto_refresh=True,
+            redirect_stderr=True,
+            redirect_stdout=False,
+            disable=disable,
+            **kwargs,
+        )
+        self.unit_scale = unit_scale
+        self.progress_bar = self.progress.add_task(
+            desc,
+            total=total * self.unit_scale
+            if total is not None and self.unit_scale is not None
+            else None,
+            unit=unit,
+        )
 
-    def flush(self):
+    def __enter__(self):
-        with suppress(AttributeError):
+        self.progress.start()
-            self.file.flush()
+        return self
+
+    def __exit__(self, exc_type, exc_value, traceback):
+        self.progress.refresh()
+        self.progress.stop()
+        return False
+
+    def update(self, value=None):
+        advance = self.unit_scale if value is None else value
+        self.progress.update(self.progress_bar, advance=advance)

src/ocrmypdf/_pipeline.py

@@ -14,7 +14,7 @@ from contextlib import suppress
 from datetime import datetime, timezone
 from pathlib import Path
 from shutil import copyfileobj
-from typing import Any, BinaryIO, Iterable, Sequence, cast
+from typing import Any, BinaryIO, Iterable, Iterator, Sequence, cast
 
 import img2pdf
 import pikepdf
@@ -27,6 +27,7 @@ from ocrmypdf._jobcontext import PageContext, PdfContext
 from ocrmypdf._version import PROGRAM_NAME
 from ocrmypdf._version import __version__ as VERSION
 from ocrmypdf.exceptions import (
+    DigitalSignatureError,
     DpiError,
     EncryptedPdfError,
     InputFileError,
@@ -37,6 +38,7 @@ from ocrmypdf.helpers import IMG2PDF_KWARGS, Resolution, safe_symlink
 from ocrmypdf.hocrtransform import HocrTransform
 from ocrmypdf.pdfa import generate_pdfa_ps
 from ocrmypdf.pdfinfo import Colorspace, Encoding, PageInfo, PdfInfo
+from ocrmypdf.pluginspec import OrientationConfidence
 
 # Remove this workaround when we require Pillow >= 10
 try:
@@ -51,6 +53,20 @@ VECTOR_PAGE_DPI = 400
 
 
 def triage_image_file(input_file: Path, output_file: Path, options) -> None:
+    """Triage the input image file.
+
+    If the input file is an image, check its resolution and convert it to PDF.
+
+    Args:
+        input_file: The path to the input file.
+        output_file: The path to the output file.
+        options: An object containing the options passed to the OCRmyPDF command.
+
+    Raises:
+        UnsupportedImageFormatError: If the input file is not a supported image format.
+        DpiError: If the input image has no resolution (DPI) in its metadata or if the
+            resolution is not credible.
+    """
     log.info("Input file is not a PDF, checking if it is an image...")
     try:
         im = Image.open(input_file)
@@ -65,34 +81,32 @@ def triage_image_file(input_file: Path, output_file: Path, options) -> None:
             if im.info['dpi'] <= (96, 96) and not options.image_dpi:
                 log.info("Image size: (%d, %d)", *im.size)
                 log.info("Image resolution: (%d, %d)", *im.info['dpi'])
-                log.error(
+                raise DpiError(
                     "Input file is an image, but the resolution (DPI) is "
                     "not credible.  Estimate the resolution at which the "
                     "image was scanned and specify it using --image-dpi."
                 )
-                raise DpiError()
         elif not options.image_dpi:
             log.info("Image size: (%d, %d)", *im.size)
-            log.error(
+            raise DpiError(
                 "Input file is an image, but has no resolution (DPI) "
                 "in its metadata.  Estimate the resolution at which "
                 "image was scanned and specify it using --image-dpi."
             )
-            raise DpiError()
 
         if im.mode in ('RGBA', 'LA'):
-            log.error(
+            raise UnsupportedImageFormatError(
                 "The input image has an alpha channel. Remove the alpha "
                 "channel first."
             )
-            raise UnsupportedImageFormatError()
 
         if 'iccprofile' not in im.info:
             if im.mode == 'RGB':
                 log.info("Input image has no ICC profile, assuming sRGB")
             elif im.mode == 'CMYK':
-                log.error("Input CMYK image has no ICC profile, not usable")
+                raise UnsupportedImageFormatError(
-                raise UnsupportedImageFormatError()
+                    "Input CMYK image has no ICC profile, not usable"
+                )
 
     try:
         log.info("Image seems valid. Try converting to PDF...")
@@ -110,7 +124,6 @@ def triage_image_file(input_file: Path, output_file: Path, options) -> None:
             )
         log.info("Successfully converted to PDF, processing...")
     except img2pdf.ImageOpenError as e:
-        log.error(e)
         raise UnsupportedImageFormatError() from e
 
 
@@ -180,27 +193,21 @@ def validate_pdfinfo_options(context: PdfContext) -> None:
     options = context.options
 
     if pdfinfo.needs_rendering:
-        log.error(
+        raise InputFileError(
             "This PDF contains dynamic XFA forms created by Adobe LiveCycle "
             "Designer and can only be read by Adobe Acrobat or Adobe Reader."
         )
-        raise InputFileError()
+    if pdfinfo.has_signature:
-    if pdfinfo.has_userunit and options.output_type.startswith('pdfa'):
+        if options.invalidate_digital_signatures:
-        log.error(
+            log.warning("All digital signatures will be invalidated")
-            "This input file uses a PDF feature that is not supported "
+        else:
-            "by Ghostscript, so you cannot use --output-type=pdfa for this "
+            raise DigitalSignatureError()
-            "file. (Specifically, it uses the PDF-1.6 /UserUnit feature to "
-            "support very large or small page sizes, and Ghostscript cannot "
-            "output these files.)  Use --output-type=pdf instead."
-        )
-        raise InputFileError()
     if pdfinfo.has_acroform:
         if options.redo_ocr:
-            log.error(
+            raise InputFileError(
                 "This PDF has a user fillable form. --redo-ocr is not "
                 "currently possible on such files."
             )
-            raise InputFileError()
         else:
             log.warning(
                 "This PDF has a fillable form. "
@@ -217,28 +224,23 @@ def validate_pdfinfo_options(context: PdfContext) -> None:
 
 
 def _vector_page_dpi(pageinfo: PageInfo) -> int:
+    """Get a DPI to use for vector pages, if the page has vector content."""
     return VECTOR_PAGE_DPI if pageinfo.has_vector or pageinfo.has_text else 0
 
 
-def get_page_dpi(pageinfo: PageInfo, options) -> Resolution:
+def get_page_square_dpi(
-    """Get the DPI when nonsquare DPI is tolerable."""
+    page_context: PageContext, image_dpi: Resolution | None = None
-    xres = max(
+) -> Resolution:
-        pageinfo.dpi.x or VECTOR_PAGE_DPI,
+    """Get the DPI when we require xres == yres, scaled to physical units.
-        options.oversample or 0.0,
-        _vector_page_dpi(pageinfo),
-    )
-    yres = max(
-        pageinfo.dpi.y or VECTOR_PAGE_DPI,
-        options.oversample or 0,
-        _vector_page_dpi(pageinfo),
-    )
-    return Resolution(float(xres), float(yres))
 
-
+    Page DPI includes UserUnit scaling.
-def get_page_square_dpi(pageinfo: PageInfo, options) -> Resolution:
+    """
-    """Get the DPI when we require xres == yres, scaled to physical units."""
+    pageinfo = page_context.pageinfo
-    xres = pageinfo.dpi.x or 0.0
+    options = page_context.options
-    yres = pageinfo.dpi.y or 0.0
+    if not image_dpi:
+        image_dpi = pageinfo.dpi
+    xres = image_dpi.x or 0.0
+    yres = image_dpi.y or 0.0
     userunit = float(pageinfo.userunit) or 1.0
     units = float(
         max(
@@ -251,12 +253,23 @@ def get_page_square_dpi(pageinfo: PageInfo, options) -> Resolution:
     return Resolution(units, units)
 
 
-def get_canvas_square_dpi(pageinfo: PageInfo, options) -> Resolution:
+def get_canvas_square_dpi(
-    """Get the DPI when we require xres == yres, in Postscript units."""
+    page_context: PageContext, image_dpi: Resolution | None = None
+) -> Resolution:
+    """Get the DPI when we require xres == yres, in Postscript units.
+
+    Canvas DPI is independent of PDF UserUnit scaling, which is
+    used to describe situations where the PDF user space is not 1:1 with
+    the physical units of the page.
+    """
+    pageinfo = page_context.pageinfo
+    options = page_context.options
+    if not image_dpi:
+        image_dpi = pageinfo.dpi
     units = float(
         max(
-            (pageinfo.dpi.x) or VECTOR_PAGE_DPI,
+            image_dpi.x or VECTOR_PAGE_DPI,
-            (pageinfo.dpi.y) or VECTOR_PAGE_DPI,
+            image_dpi.y or VECTOR_PAGE_DPI,
             _vector_page_dpi(pageinfo),
             options.oversample or 0.0,
         )
@@ -265,6 +278,7 @@ def get_canvas_square_dpi(pageinfo: PageInfo, options) -> Resolution:
 
 
 def is_ocr_required(page_context: PageContext) -> bool:
+    """Check if the page needs to be OCR'd."""
     pageinfo = page_context.pageinfo
     options = page_context.options
 
@@ -340,9 +354,12 @@ def is_ocr_required(page_context: PageContext) -> bool:
 
 
 def rasterize_preview(input_file: Path, page_context: PageContext) -> Path:
+    """Generate a lower quality preview image."""
     output_file = page_context.get_path('rasterize_preview.jpg')
-    canvas_dpi = get_canvas_square_dpi(page_context.pageinfo, page_context.options)
+    canvas_dpi = Resolution(300.0, 300.0).take_min(
-    page_dpi = get_page_square_dpi(page_context.pageinfo, page_context.options)
+        [get_canvas_square_dpi(page_context)]
+    )
+    page_dpi = Resolution(300.0, 300.0).take_min([get_page_square_dpi(page_context)])
     page_context.plugin_manager.hook.rasterize_pdf_page(
         input_file=input_file,
         output_file=output_file,
@@ -352,12 +369,15 @@ def rasterize_preview(input_file: Path, page_context: PageContext) -> Path:
         page_dpi=page_dpi,
         rotation=0,
         filter_vector=False,
+        stop_on_soft_error=not page_context.options.continue_on_soft_render_error,
     )
     return output_file
 
 
-def describe_rotation(page_context: PageContext, orient_conf, correction: int) -> str:
+def describe_rotation(
-    """Describe the page rotation we are going to perform."""
+    page_context: PageContext, orient_conf: OrientationConfidence, correction: int
+) -> str:
+    """Describe the page rotation we are going to perform (or not perform)."""
     direction = {0: '⇧', 90: '⇨', 180: '⇩', 270: '⇦'}
     turns = {0: ' ', 90: '⬏', 180: '↻', 270: '⬑'}
 
@@ -384,7 +404,7 @@ def describe_rotation(page_context: PageContext, orient_conf, correction: int) -
 
 
 def get_orientation_correction(preview: Path, page_context: PageContext) -> int:
-    """Work out orientation correct for each page.
+    """Work out orientation correction for each page.
 
     We ask Ghostscript to draw a preview page, which will rasterize with the
     current /Rotate applied, and then ask OCR which way the page is
@@ -413,13 +433,58 @@ def get_orientation_correction(preview: Path, page_context: PageContext) -> int:
     return 0
 
 
+def calculate_image_dpi(page_context: PageContext) -> Resolution:
+    pageinfo = page_context.pageinfo
+    dpi_profile = pageinfo.page_dpi_profile()
+    if dpi_profile and dpi_profile.average_to_max_dpi_ratio < 0.8:
+        image_dpi = Resolution(dpi_profile.weighted_dpi, dpi_profile.weighted_dpi)
+    else:
+        image_dpi = pageinfo.dpi
+    return image_dpi
+
+
+def calculate_raster_dpi(page_context: PageContext):
+    """Calculate the DPI for rasterization."""
+    # Produce the page image with square resolution or else deskew and OCR
+    # will not work properly.
+    image_dpi = calculate_image_dpi(page_context)
+    dpi_profile = page_context.pageinfo.page_dpi_profile()
+    canvas_dpi = get_canvas_square_dpi(page_context, image_dpi)
+    page_dpi = get_page_square_dpi(page_context, image_dpi)
+    if dpi_profile and dpi_profile.average_to_max_dpi_ratio < 0.8:
+        log.warning(
+            "Weight average image DPI is %0.1f, max DPI is %0.1f. "
+            "The discrepancy may indicate a high detail region on this page, "
+            "but could also indicate a problem with the input PDF file. "
+            "Page image will be rendered at %0.1f DPI.",
+            dpi_profile.weighted_dpi,
+            dpi_profile.max_dpi,
+            canvas_dpi.to_scalar(),
+        )
+    return canvas_dpi, page_dpi
+
+
 def rasterize(
     input_file: Path,
     page_context: PageContext,
     correction: int = 0,
     output_tag: str = '',
-    remove_vectors=None,
+    remove_vectors: bool | None = None,
-):
+) -> Path:
+    """Rasterize a PDF page to a PNG image.
+
+    Args:
+        input_file: The input PDF file path.
+        page_context: The page context object.
+        correction: The orientation correction angle. Defaults to 0.
+        output_tag: The output tag. Defaults to ''.
+        remove_vectors: Whether to remove vectors. Defaults to None, which means
+            the value from the page context options will be used. If the value
+            is True or False, it will override the page context options.
+
+    Returns:
+        Path: The output PNG file path.
+    """
     colorspaces = ['pngmono', 'pnggray', 'png256', 'png16m']
     device_idx = 0
 
@@ -450,10 +515,7 @@ def rasterize(
 
     log.debug(f"Rasterize with {device}, rotation {correction}")
 
-    # Produce the page image with square resolution or else deskew and OCR
+    canvas_dpi, page_dpi = calculate_raster_dpi(page_context)
-    # will not work properly.
-    canvas_dpi = get_canvas_square_dpi(pageinfo, page_context.options)
-    page_dpi = get_page_square_dpi(pageinfo, page_context.options)
 
     page_context.plugin_manager.hook.rasterize_pdf_page(
         input_file=input_file,
@@ -464,6 +526,7 @@ def rasterize(
         pageno=pageinfo.pageno + 1,
         rotation=correction,
         filter_vector=remove_vectors,
+        stop_on_soft_error=not page_context.options.continue_on_soft_render_error,
     )
     return output_file
 
@@ -479,8 +542,17 @@ def preprocess_remove_background(input_file: Path, page_context: PageContext) ->
 
 
 def preprocess_deskew(input_file: Path, page_context: PageContext) -> Path:
+    """Deskews the input image using the OCR engine and saves the output to a file.
+
+    Args:
+        input_file: The input image file to deskew.
+        page_context: The context of the page being processed.
+
+    Returns:
+        Path: The path to the deskewed image file.
+    """
     output_file = page_context.get_path('pp_deskew.png')
-    dpi = get_page_square_dpi(page_context.pageinfo, page_context.options)
+    dpi = get_page_square_dpi(page_context, calculate_image_dpi(page_context))
 
     ocr_engine = page_context.plugin_manager.hook.get_ocr_engine()
     deskew_angle_degrees = ocr_engine.get_deskew(input_file, page_context.options)
@@ -500,11 +572,11 @@ def preprocess_deskew(input_file: Path, page_context: PageContext) -> Path:
 
 def preprocess_clean(input_file: Path, page_context: PageContext) -> Path:
     output_file = page_context.get_path('pp_clean.png')
-    dpi = get_page_square_dpi(page_context.pageinfo, page_context.options)
+    dpi = get_page_square_dpi(page_context, calculate_image_dpi(page_context))
     return unpaper.clean(
         input_file,
         output_file,
-        dpi=dpi.x,
+        dpi=dpi.to_scalar(),
         unpaper_args=page_context.options.unpaper_args,
     )
 
@@ -574,7 +646,16 @@ def ocr_engine_hocr(input_file: Path, page_context: PageContext) -> tuple[Path,
 
 
 def should_visible_page_image_use_jpg(pageinfo: PageInfo) -> bool:
-    # If all images were JPEGs originally, produce a JPEG as output
+    """Determines whether the visible page image should be saved as a JPEG.
+
+    If all images were JPEGs originally, permit a JPEG as output.
+
+    Args:
+        pageinfo: The PageInfo object containing information about the page.
+
+    Returns:
+        A boolean indicating whether the visible page image should be saved as a JPEG.
+    """
     return bool(pageinfo.images) and all(
         im.enc == Encoding.jpeg for im in pageinfo.images
     )
@@ -592,7 +673,7 @@ def create_visible_page_jpg(image: Path, page_context: PageContext) -> Path:
             dpi = Resolution(*im.info['dpi'])
         else:
             # Fallback to page-implied DPI
-            dpi = get_page_square_dpi(page_context.pageinfo, page_context.options)
+            dpi = get_page_square_dpi(page_context, calculate_image_dpi(page_context))
 
         # Pillow requires integer DPI
         im.save(output_file, format='JPEG', dpi=dpi.to_int())
@@ -635,7 +716,7 @@ def create_pdf_page_from_image(
 def render_hocr_page(hocr: Path, page_context: PageContext) -> Path:
     options = page_context.options
     output_file = page_context.get_path('ocr_hocr.pdf')
-    dpi = get_page_square_dpi(page_context.pageinfo, options)
+    dpi = get_page_square_dpi(page_context, calculate_image_dpi(page_context))
     debug_mode = options.pdf_renderer == 'hocrdebug'
 
     hocrtransform = HocrTransform(hocr_filename=hocr, dpi=dpi.x)  # square
@@ -698,6 +779,14 @@ def get_docinfo(base_pdf: pikepdf.Pdf, context: PdfContext) -> dict[str, str]:
 
 
 def generate_postscript_stub(context: PdfContext) -> Path:
+    """Generates a PostScript file stub for the given PDF context.
+
+    Args:
+        context: The PDF context to generate the PostScript file stub for.
+
+    Returns:
+        Path: The path to the generated PostScript file stub.
+    """
     output_file = context.get_path('pdfa.ps')
     generate_pdfa_ps(output_file)
     return output_file
@@ -714,21 +803,8 @@ def convert_to_pdfa(input_pdf: Path, input_ps_stub: Path, context: PdfContext) -
     # NULs in DocumentInfo seem to be common since older Acrobats included them.
     # pikepdf can deal with this, but we make the world a better place by
     # stamping them out as soon as possible.
-    modified = False
     with pikepdf.open(input_pdf) as pdf_file:
-        try:
+        if _repair_docinfo_nuls(pdf_file):
-            len(pdf_file.docinfo)
-        except TypeError:
-            log.error(
-                "File contains a malformed DocumentInfo block - continuing anyway"
-            )
-        else:
-            if pdf_file.docinfo:
-                for k, v in pdf_file.docinfo.items():
-                    if b'\x00' in bytes(v):
-                        pdf_file.docinfo[k] = bytes(v).replace(b'\x00', b'')
-                        modified = True
-        if modified:
             pdf_file.save(fix_docinfo_file)
         else:
             safe_symlink(input_pdf, fix_docinfo_file)
@@ -738,18 +814,38 @@ def convert_to_pdfa(input_pdf: Path, input_ps_stub: Path, context: PdfContext) -
         pdf_pages=[fix_docinfo_file],
         pdfmark=input_ps_stub,
         output_file=output_file,
-        compression=options.pdfa_image_compression,
+        context=context,
         pdfa_part=options.output_type[-1],  # is pdfa-1, pdfa-2, or pdfa-3
         progressbar_class=(
             context.plugin_manager.hook.get_progressbar_class()
             if options.progress_bar
             else None
         ),
+        stop_on_soft_error=not options.continue_on_soft_render_error,
     )
 
     return output_file
 
 
+def _repair_docinfo_nuls(pdf):
+    """If the DocumentInfo block contains NUL characters, remove them.
+
+    If the DocumentInfo block is malformed, log an error and continue.
+    """
+    modified = False
+    try:
+        if not isinstance(pdf.docinfo, pikepdf.Dictionary):
+            raise TypeError("DocumentInfo is not a dictionary")
+        for k, v in pdf.docinfo.items():
+            if isinstance(v, str) and b'\x00' in bytes(v):
+                pdf.docinfo[k] = bytes(v).replace(b'\x00', b'')
+                modified = True
+    except TypeError:
+        # TypeError can also be raised if dictionary items are unexpected types
+        log.error("File contains a malformed DocumentInfo block - continuing anyway.")
+    return modified
+
+
 def should_linearize(working_file: Path, context: PdfContext) -> bool:
     filesize = os.stat(working_file).st_size
     if filesize > (context.options.fast_web_view * 1_000_000):
@@ -798,24 +894,45 @@ def metadata_fixup(working_file: Path, context: PdfContext) -> Path:
 
     with pikepdf.open(context.origin) as original, pikepdf.open(working_file) as pdf:
         docinfo = get_docinfo(original, context)
-        with pdf.open_metadata() as meta:
+        with pdf.open_metadata() as meta_pdf:
-            meta.load_from_docinfo(docinfo, delete_missing=False, raise_failure=False)
+            meta_pdf.load_from_docinfo(
+                docinfo, delete_missing=False, raise_failure=False
+            )
             # If xmp:CreateDate is missing, set it to the modify date to
-            # match Ghostscript, for consistency
+            # ensure consistency with Ghostscript.
-            if 'xmp:CreateDate' not in meta:
+            if 'xmp:CreateDate' not in meta_pdf:
-                meta['xmp:CreateDate'] = meta.get('xmp:ModifyDate', '')
+                meta_pdf['xmp:CreateDate'] = meta_pdf.get('xmp:ModifyDate', '')
 
             with original.open_metadata(
                 set_pikepdf_as_editor=False, update_docinfo=False, strict=False
             ) as meta_original:
-                if meta.get('dc:title') == 'Untitled':
+                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['dc:title']
+                        del meta_pdf['dc:title']
-                missing = set(meta_original.keys()) - set(meta.keys())
+                # If the user explicitly specified an empty string for any of the
-                report_on_metadata(missing)
+                # following, they should be unset and not reported as missing in
+                # the output pdf. Note that some metadata fields use differing names
+                # between PDF-A and PDF.
+                for meta in [meta_pdf, meta_original]:
+                    if options.title == '' and 'dc:title' in meta:
+                        del meta['dc:title']  # PDF-A and PDF
+                    if options.author == '':
+                        if 'dc:creator' in meta:
+                            del meta['dc:creator']  # PDF-A (Not xmp:CreatorTool)
+                        if 'pdf:Author' in meta:
+                            del meta['pdf:Author']  # PDF
+                    if options.subject == '':
+                        if 'dc:description' in meta:
+                            del meta['dc:description']  # PDF-A
+                        if 'dc:subject' in meta:
+                            del meta['dc:subject']  # PDF
+                    if options.keywords == '' and 'pdf:Keywords' in meta:
+                        del meta['pdf:Keywords']  # PDF-A and PDF
+                meta_missing = set(meta_original.keys()) - set(meta_pdf.keys())
+                report_on_metadata(meta_missing)
 
         optimizing = context.plugin_manager.hook.is_optimization_enabled(
             context=context
@@ -831,6 +948,29 @@ def metadata_fixup(working_file: Path, context: PdfContext) -> Path:
     return output_file
 
 
+def _file_size_ratio(
+    input_file: Path, output_file: Path
+) -> tuple[float | None, float | None]:
+    """Calculate ratio of input to output file sizes and percentage savings.
+
+    Args:
+        input_file (Path): The path to the input file.
+        output_file (Path): The path to the output file.
+
+    Returns:
+        tuple[float | None, float | None]: A tuple containing the file size
+        ratio and the percentage savings achieved by the output file size
+        compared to the input file size.
+    """
+    input_size = input_file.stat().st_size
+    output_size = output_file.stat().st_size
+    if output_size == 0:
+        return None, None
+    ratio = input_size / output_size
+    savings = 1 - output_size / input_size
+    return ratio, savings
+
+
 def optimize_pdf(
     input_file: Path, context: PdfContext, executor: Executor
 ) -> tuple[Path, Sequence[str]]:
@@ -843,17 +983,29 @@ def optimize_pdf(
         linearize=should_linearize(input_file, context),
     )
 
-    input_size = input_file.stat().st_size
+    ratio, savings = _file_size_ratio(input_file, output_file)
-    output_size = output_file.stat().st_size
+    if ratio:
-    if output_size > 0:
+        log.info(f"Image optimization ratio: {ratio:.2f} savings: {(savings):.1%}")
-        ratio = input_size / output_size
+    ratio, savings = _file_size_ratio(context.origin, output_file)
-        savings = 1 - output_size / input_size
+    if ratio:
-        log.info(f"Optimize ratio: {ratio:.2f} savings: {(savings):.1%}")
+        log.info(f"Total file size ratio: {ratio:.2f} savings: {(savings):.1%}")
-
     return output_pdf, messages
 
 
-def enumerate_compress_ranges(iterable):
+def enumerate_compress_ranges(
+    iterable: Iterable,
+) -> Iterator[tuple[tuple[int, int], Any]]:
+    """Enumerate the ranges of non-empty elements in an iterable.
+
+    Compresses consecutive ranges of length 1 into single elements.
+
+    Args:
+        iterable: An iterable of elements to enumerate.
+
+    Yields:
+        A tuple containing a range of indices and the corresponding element.
+        If the element is None, the range represents a skipped range of indices.
+    """
     skipped_from, index = None, None
     for index, txt_file in enumerate(iterable):
         index += 1
@@ -897,6 +1049,16 @@ def merge_sidecars(txt_files: Iterable[Path | None], context: PdfContext) -> Pat
 def copy_final(
     input_file: Path, output_file: str | Path | BinaryIO, _context: PdfContext
 ) -> None:
+    """Copy the final temporary file to the output destination.
+
+    Args:
+        input_file (Path): The input file to copy.
+        output_file (str | Path | BinaryIO): The output file to copy to.
+        _context (PdfContext): The PDF context.
+
+    Returns:
+        None
+    """
     log.debug('%s -> %s', input_file, output_file)
     with input_file.open('rb') as input_stream:
         if output_file == '-':

src/ocrmypdf/_plugin_manager.py

@@ -100,7 +100,9 @@ class OcrmypdfPluginManager(pluggy.PluginManager):
             self.register(module)
 
 
-def get_plugin_manager(plugins: list[str | Path], builtins=True):
+def get_plugin_manager(
+    plugins: list[str | Path], builtins=True
+) -> OcrmypdfPluginManager:
     return OcrmypdfPluginManager(
         project_name='ocrmypdf',
         plugins=plugins,

src/ocrmypdf/_validation.py

@@ -43,35 +43,47 @@ log = logging.getLogger(__name__)
 
 
 def check_platform() -> None:
-    if os.name == 'nt' and sys.maxsize <= 2**32:  # pragma: no cover
+    if sys.maxsize <= 2**32:  # pragma: no cover
-        # 32-bit interpreter on Windows
+        log.warning(
-        log.error(
+            "You are running OCRmyPDF in a 32-bit (x86) Python interpreter. "
-            "You are running OCRmyPDF in a 32-bit (x86) Python interpreter."
+            "This is not supported. 32-bit does not have enough address space "
+            "to process large files. "
             "Please use a 64-bit (x86-64) version of Python."
         )
 
 
-def check_options_languages(options: Namespace, ocr_engine_languages: set[str]) -> None:
+def check_options_languages(
+    options: Namespace, ocr_engine_languages: list[str]
+) -> None:
     if not options.languages:
-        options.languages = {DEFAULT_LANGUAGE}
+        options.languages = [DEFAULT_LANGUAGE]
         system_lang = locale.getlocale()[0]
         if system_lang and not system_lang.startswith('en'):
             log.debug("No language specified; assuming --language %s", DEFAULT_LANGUAGE)
     if not ocr_engine_languages:
         return
-    missing_languages = options.languages - ocr_engine_languages
+    missing_languages = set(options.languages) - set(ocr_engine_languages)
     if missing_languages:
+        lang_text = '\n'.join(lang for lang in missing_languages)
         msg = (
             "OCR engine does not have language data for the following "
             "requested languages: \n"
+            f"{lang_text}\n"
+            "Please install the appropriate language data for your OCR engine.\n"
+            "\n"
+            "See the online documentation for instructions:\n"
+            "    https://ocrmypdf.readthedocs.io/en/latest/languages.html\n"
+            "\n"
+            "Note: most languages are identified by a 3-letter ISO 639-2 Code.\n"
+            "For example, English is 'eng', German is 'deu', and Spanish is 'spa'.\n"
+            "Simplified Chinese is 'chi_sim' and Traditional Chinese is 'chi_tra'."
+            "\n"
         )
-        msg += '\n'.join(lang for lang in missing_languages)
-        msg += '\nNote: most languages are identified by a 3-digit ISO 639-2 Code'
         raise MissingDependencyError(msg)
 
 
 def check_options_output(options: Namespace) -> None:
-    is_latin = options.languages.issubset(HOCR_OK_LANGS)
+    is_latin = set(options.languages).issubset(HOCR_OK_LANGS)
 
     if options.pdf_renderer.startswith('hocr') and not is_latin:
         log.warning(
@@ -193,16 +205,6 @@ def check_options_ocr_behavior(options: Namespace) -> None:
         options.pages = _pages_from_ranges(options.pages)
 
 
-def check_options_advanced(options: Namespace) -> None:
-    if options.pdfa_image_compression != 'auto' and not options.output_type.startswith(
-        'pdfa'
-    ):
-        log.warning(
-            "--pdfa-image-compression argument only applies when "
-            "--output-type is one of 'pdfa', 'pdfa-1', or 'pdfa-2'"
-        )
-
-
 def check_options_metadata(options: Namespace) -> None:
     docinfo = [options.title, options.author, options.keywords, options.subject]
     for s in (m for m in docinfo if m):
@@ -229,7 +231,6 @@ def _check_plugin_invariant_options(options: Namespace) -> None:
     check_options_sidecar(options)
     check_options_preprocessing(options)
     check_options_ocr_behavior(options)
-    check_options_advanced(options)
     check_options_pillow(options)
 
 

src/ocrmypdf/api.py

@@ -9,16 +9,16 @@ import logging
 import os
 import sys
 import threading
+from argparse import Namespace
 from enum import IntEnum
 from io import IOBase
 from pathlib import Path
 from typing import AnyStr, BinaryIO, Iterable, Union
 from warnings import warn
 
-import coloredlogs
+import pluggy
-from humanfriendly.terminal import enable_ansi_support
 
-from ocrmypdf._logging import PageNumberFilter, TqdmConsole
+from ocrmypdf._logging import PageNumberFilter
 from ocrmypdf._plugin_manager import get_plugin_manager
 from ocrmypdf._sync import run_pipeline
 from ocrmypdf._validation import check_options
@@ -46,7 +46,7 @@ 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.
 
@@ -112,14 +112,7 @@ def configure_logging(
     else:
         fmt = '%(pageno)s%(message)s'
 
-    use_colors = progress_bar_friendly
     formatter = None
-    if use_colors:
-        use_colors = enable_ansi_support()
-        if use_colors:
-            use_colors = coloredlogs.terminal_supports_colors()
-        if use_colors:
-            formatter = coloredlogs.ColoredFormatter(fmt=fmt)
 
     if not formatter:
         formatter = logging.Formatter(fmt=fmt)
@@ -141,8 +134,21 @@ def configure_logging(
 
 def create_options(
     *, input_file: PathOrIO, output_file: PathOrIO, parser: ArgumentParser, **kwargs
-):
+) -> Namespace:
-    """Construct an options object from the input/output files and keyword arguments."""
+    """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 = []
 
@@ -248,6 +254,7 @@ def ocr(  # noqa: ruff: disable=D417
     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,
     plugins: Iterable[StrPath] | None = None,
     plugin_manager=None,
     keep_temporary_files: bool | None = None,
@@ -348,7 +355,6 @@ def ocr(  # noqa: ruff: disable=D417
 
 __all__ = [
     'PageNumberFilter',
-    'TqdmConsole',
     'Verbosity',
     'check_options',
     'configure_logging',

src/ocrmypdf/builtin_plugins/concurrency.py

@@ -16,10 +16,10 @@ from concurrent.futures import ProcessPoolExecutor, ThreadPoolExecutor, as_compl
 from contextlib import suppress
 from typing import Callable, Iterable, Type, Union
 
-from tqdm import tqdm
+from rich.console import Console as RichConsole
 
 from ocrmypdf import Executor, hookimpl
-from ocrmypdf._logging import TqdmConsole
+from ocrmypdf._logging import RichLoggingHandler, RichTqdmProgressAdapter
 from ocrmypdf.exceptions import InputFileError
 from ocrmypdf.helpers import remove_all_log_handlers
 
@@ -68,7 +68,7 @@ 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)
 
@@ -95,15 +95,6 @@ def thread_init(q: Queue, user_init: UserInit, loglevel) -> None:
 class StandardExecutor(Executor):
     """Standard OCRmyPDF concurrent task executor."""
 
-    def _cancel_futures_kwargs(self):
-        """Shim older Pythons that do not have Executor.shutdown(...cancel_futures=).
-
-        Remove this code when support for Python 3.8 is dropped.
-        """
-        if sys.version_info[:2] < (3, 9):
-            return {}
-        return dict(cancel_futures=True)
-
     def _execute(
         self,
         *,
@@ -142,7 +133,7 @@ class StandardExecutor(Executor):
                     task_finished(result, pbar)
             except KeyboardInterrupt:
                 # Terminate pool so we exit instantly
-                executor.shutdown(wait=False, **self._cancel_futures_kwargs())
+                executor.shutdown(wait=False, cancel_futures=True)
                 raise
             except Exception:
                 if not os.environ.get("PYTEST_CURRENT_TEST", ""):
@@ -151,7 +142,7 @@ 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
@@ -168,13 +159,20 @@ def get_executor(progressbar_class):
     return StandardExecutor(pbar_class=progressbar_class)
 
 
+RICH_CONSOLE = RichConsole(stderr=True)
+
+
 @hookimpl
 def get_progressbar_class():
     """Return the default progress bar class."""
-    return tqdm
+
+    def partial_RichTqdmProgressAdapter(*args, **kwargs):
+        return RichTqdmProgressAdapter(*args, **kwargs, console=RICH_CONSOLE)
+
+    return partial_RichTqdmProgressAdapter
 
 
 @hookimpl
 def get_logging_console():
     """Return the default logging console handler."""
-    return logging.StreamHandler(stream=TqdmConsole(sys.stderr))
+    return RichLoggingHandler(console=RICH_CONSOLE)

src/ocrmypdf/builtin_plugins/ghostscript.py

@@ -13,6 +13,37 @@ from ocrmypdf.subprocess import check_external_program
 
 log = logging.getLogger(__name__)
 
+# Currently all blacklisted versions are lower than 9.55, so none need to
+# be added here. If a future version is blacklisted, add it here.
+BLACKLISTED_GS_VERSIONS: frozenset[str] = frozenset()
+
+
+@hookimpl
+def add_options(parser):
+    gs = parser.add_argument_group("Ghostscript", "Advanced control of Ghostscript")
+    gs.add_argument(
+        '--color-conversion-strategy',
+        action='store',
+        type=str,
+        metavar='STRATEGY',
+        choices=ghostscript.COLOR_CONVERSION_STRATEGIES,
+        default='LeaveColorUnchanged',
+        help="Set Ghostscript color conversion strategy",
+    )
+    gs.add_argument(
+        '--pdfa-image-compression',
+        choices=['auto', 'jpeg', 'lossless'],
+        default='auto',
+        help="Specify how to compress images in the output PDF/A. 'auto' lets "
+        "OCRmyPDF decide.  'jpeg' changes all grayscale and color images to "
+        "JPEG compression.  'lossless' uses PNG-style lossless compression "
+        "for all images.  Monochrome images are always compressed using a "
+        "lossless codec.  Compression settings "
+        "are applied to all pages, including those for which OCR was "
+        "skipped.  Not supported for --output-type=pdf ; that setting "
+        "preserves the original compression of all images.",
+    )
+
 
 @hookimpl
 def check_options(options):
@@ -21,10 +52,10 @@ def check_options(options):
         program='gs',
         package='ghostscript',
         version_checker=ghostscript.version,
-        need_version='9.50',  # Ubuntu 20.04's version
+        need_version='9.55',  # Ubuntu 22.04's version
     )
     gs_version = ghostscript.version()
-    if gs_version in ('9.51',):
+    if gs_version in BLACKLISTED_GS_VERSIONS:
         raise MissingDependencyError(
             f"Ghostscript {gs_version} contains serious regressions and is not "
             "supported. Please upgrade to a newer version, or downgrade to the "
@@ -33,6 +64,17 @@ def check_options(options):
 
     if options.output_type == 'pdfa':
         options.output_type = 'pdfa-2'
+    if options.color_conversion_strategy not in ghostscript.COLOR_CONVERSION_STRATEGIES:
+        raise ValueError(
+            f"Invalid color conversion strategy: {options.color_conversion_strategy}"
+        )
+    if options.pdfa_image_compression != 'auto' and not options.output_type.startswith(
+        'pdfa'
+    ):
+        log.warning(
+            "--pdfa-image-compression argument only applies when "
+            "--output-type is one of 'pdfa', 'pdfa-1', or 'pdfa-2'"
+        )
 
 
 @hookimpl
@@ -45,6 +87,7 @@ 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(
@@ -56,6 +99,7 @@ def rasterize_pdf_page(
         page_dpi=page_dpi,
         rotation=rotation,
         filter_vector=filter_vector,
+        stop_on_error=stop_on_soft_error,
     )
     return output_file
 
@@ -65,18 +109,21 @@ def generate_pdfa(
     pdf_pages,
     pdfmark,
     output_file,
-    compression,
+    context,
     pdf_version,
     pdfa_part,
     progressbar_class,
+    stop_on_soft_error,
 ):
     """Generate a PDF/A from the list of PDF pages and PDF/A metadata."""
     ghostscript.generate_pdfa(
         pdf_pages=[*pdf_pages, pdfmark],
         output_file=output_file,
-        compression=compression,
+        compression=context.options.pdfa_image_compression,
+        color_conversion_strategy=context.options.color_conversion_strategy,
         pdf_version=pdf_version,
         pdfa_part=pdfa_part,
         progressbar_class=progressbar_class,
+        stop_on_error=stop_on_soft_error,
     )
     return output_file

src/ocrmypdf/builtin_plugins/optimize.py

@@ -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

@@ -30,7 +30,7 @@ def add_options(parser):
         action='append',
         metavar='CFG',
         default=[],
-        help="Additional Tesseract configuration files -- see documentation",
+        help="Additional Tesseract configuration files -- see documentation.",
     )
     tess.add_argument(
         '--tesseract-pagesegmode',
@@ -38,7 +38,7 @@ def add_options(parser):
         type=int,
         metavar='PSM',
         choices=range(0, 14),
-        help="Set Tesseract page segmentation mode (see tesseract --help)",
+        help="Set Tesseract page segmentation mode (see tesseract --help).",
     )
     tess.add_argument(
         '--tesseract-oem',
@@ -75,7 +75,10 @@ def add_options(parser):
         metavar='SECONDS',
         help=(
             "Give up on OCR after the timeout, but copy the preprocessed page "
-            "into the final output."
+            "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(
@@ -102,6 +105,20 @@ def add_options(parser):
             "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',
         metavar='FILE',
@@ -123,7 +140,7 @@ def check_options(options):
         program='tesseract',
         package={'linux': 'tesseract-ocr'},
         version_checker=tesseract.version,
-        need_version='4.1.1',  # Ubuntu 20.04 version
+        need_version='4.1.1',  # Ubuntu 22.04 version (also 20.04)
         version_parser=tesseract.TesseractVersion,
     )
 
@@ -161,6 +178,15 @@ 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:
@@ -170,10 +196,12 @@ def filter_ocr_image(page: PageContext, image: Image.Image) -> Image.Image:
     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=(32767, 32767), max_bytes=(2**31) - 1
+            image, max_size=(threshold, threshold), max_bytes=(2**31) - 1
         )
         image = downsample_image(image, size)
     return image
@@ -184,7 +212,7 @@ class TesseractOcrEngine(OcrEngine):
 
     @staticmethod
     def version():
-        return tesseract.version()
+        return str(tesseract.version())
 
     @staticmethod
     def creator_tag(options):

src/ocrmypdf/cli.py

@@ -15,7 +15,11 @@ T = TypeVar('T', int, float)
 
 
 def numeric(basetype: Callable[[Any], T], min_: T | None = None, max_: T | None = None):
-    """Validator for numeric params."""
+    """Validator for numeric command line parameters.
+
+    Stipulates that the value must be of type basetype (typically int or float), and
+    optionally, within the range [min_, max_].
+    """
     min_ = basetype(min_) if min_ is not None else None
     max_ = basetype(max_) if max_ is not None else None
 
@@ -84,16 +88,16 @@ class LanguageSetAction(argparse.Action):
     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():
@@ -177,7 +181,9 @@ 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',
@@ -359,6 +365,13 @@ 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"
@@ -395,19 +408,6 @@ Online documentation is located at:
         help="Only rotate pages when confidence is above this value (arbitrary "
         "units reported by tesseract)",
     )
-    advanced.add_argument(
-        '--pdfa-image-compression',
-        choices=['auto', 'jpeg', 'lossless'],
-        default='auto',
-        help="Specify how to compress images in the output PDF/A. 'auto' lets "
-        "OCRmyPDF decide.  'jpeg' changes all grayscale and color images to "
-        "JPEG compression.  'lossless' uses PNG-style lossless compression "
-        "for all images.  Monochrome images are always compressed using a "
-        "lossless codec.  Compression settings "
-        "are applied to all pages, including those for which OCR was "
-        "skipped.  Not supported for --output-type=pdf ; that setting "
-        "preserves the original compression of all images.",
-    )
     advanced.add_argument(
         '--fast-web-view',
         type=numeric(float, 0),
@@ -420,6 +420,14 @@ 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

@@ -108,6 +108,18 @@ class EncryptedPdfError(ExitCodeException):
     )
 
 
+class DigitalSignatureError(ExitCodeException):
+    """PDF has a digital signature."""
+
+    exit_code = ExitCode.input_file
+    message = dedent(
+        """\
+        Input PDF has a digital signature. OCR would alter the document,
+        invalidating the signature.
+        """
+    )
+
+
 class TesseractConfigError(ExitCodeException):
     """Tesseract config can't be parsed."""
 

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

src/ocrmypdf/helpers.py

@@ -12,28 +12,30 @@ import shutil
 import warnings
 from collections.abc import Iterable
 from contextlib import suppress
+from decimal import Decimal
 from io import StringIO
 from math import isclose, isfinite
 from pathlib import Path
-from typing import Any, Generic, Sequence, SupportsFloat, SupportsRound, TypeVar
+from statistics import harmonic_mean
+from typing import (
+    Any,
+    Callable,
+    Generic,
+    Sequence,
+    SupportsFloat,
+    SupportsRound,
+    TypeVar,
+)
 
 import img2pdf
 import pikepdf
-from packaging.version import Version
 
 log = logging.getLogger(__name__)
 
-if Version(img2pdf.__version__) < Version('0.4.0'):
+IMG2PDF_KWARGS = dict(engine=img2pdf.Engine.pikepdf, rotation=img2pdf.Rotation.ifvalid)
-    IMG2PDF_KWARGS = dict(without_pdfw=True)
-elif Version(img2pdf.__version__) < Version('0.4.3'):
-    IMG2PDF_KWARGS = dict(engine=img2pdf.Engine.pikepdf)
-else:
-    IMG2PDF_KWARGS = dict(
-        engine=img2pdf.Engine.pikepdf, rotation=img2pdf.Rotation.ifvalid
-    )
 
 
-T = TypeVar('T', bound=SupportsRound[Any])
+T = TypeVar('T', float, int, Decimal)
 
 
 class Resolution(Generic[T]):
@@ -77,21 +79,40 @@ class Resolution(Generic[T]):
     @property
     def is_finite(self) -> bool:
         """True if both x and y are finite numbers."""
-        if isinstance(self.x, SupportsFloat) and isinstance(self.y, SupportsFloat):
+        return isfinite(self.x) and isfinite(self.y)
-            return isfinite(self.x) and isfinite(self.y)
+
-        return True
+    def to_scalar(self) -> float:
+        """Return the harmonic mean of x and y as a 1D approximation.
+
+        In most cases, Resolution is 2D, but typically it is "square" (x == y) and
+        can be approximated as a single number. When not square, the harmonic mean
+        is used to approximate the 2D resolution as a single number.
+        """
+        return harmonic_mean([float(self.x), float(self.y)])
+
+    def _take_minmax(
+        self, vals: Iterable[Any], yvals: Iterable[Any] | None, cmp: Callable
+    ) -> Resolution:
+        """Return a new Resolution object with the maximum resolution of inputs."""
+        if yvals is not None:
+            return Resolution(cmp(self.x, *vals), cmp(self.y, *yvals))
+        cmp_x, cmp_y = self.x, self.y
+        for x, y in vals:
+            cmp_x = cmp(x, cmp_x)
+            cmp_y = cmp(y, cmp_y)
+        return Resolution(cmp_x, cmp_y)
 
     def take_max(
         self, vals: Iterable[Any], yvals: Iterable[Any] | None = None
     ) -> Resolution:
         """Return a new Resolution object with the maximum resolution of inputs."""
-        if yvals is not None:
+        return self._take_minmax(vals, yvals, max)
-            return Resolution(max(self.x, *vals), max(self.y, *yvals))
+
-        max_x, max_y = self.x, self.y
+    def take_min(
-        for x, y in vals:
+        self, vals: Iterable[Any], yvals: Iterable[Any] | None = None
-            max_x = max(x, max_x)
+    ) -> Resolution:
-            max_y = max(y, max_y)
+        """Return a new Resolution object with the minimum resolution of inputs."""
-        return Resolution(max_x, max_y)
+        return self._take_minmax(vals, yvals, min)
 
     def flip_axis(self) -> Resolution[T]:
         """Return a new Resolution object with x and y swapped."""
@@ -103,11 +124,11 @@ class Resolution(Generic[T]):
 
     def __str__(self):
         """Return a string representation of the resolution."""
-        return f"{self.x:f}x{self.y:f}"
+        return f"{self.x:f}×{self.y:f}"
 
     def __repr__(self):  # pragma: no cover
         """Return a repr() of the resolution."""
-        return f"Resolution({self.x}x{self.y} dpi)"
+        return f"Resolution({self.x!r}, {self.y!r})"
 
     def __eq__(self, other):
         """Return True if the resolution is equal to another resolution."""
@@ -122,7 +143,7 @@ class NeverRaise(Exception):
     """An exception that is never raised."""
 
 
-def safe_symlink(input_file: os.PathLike, soft_link_name: os.PathLike):
+def safe_symlink(input_file: os.PathLike, soft_link_name: os.PathLike) -> None:
     """Create a symbolic link at ``soft_link_name``, which references ``input_file``.
 
     Think of this as copying ``input_file`` to ``soft_link_name`` with less overhead.
@@ -137,7 +158,7 @@ def safe_symlink(input_file: os.PathLike, soft_link_name: os.PathLike):
     # Guard against soft linking to oneself
     if input_file == soft_link_name:
         log.warning(
-            "No symbolic link created. You are using  the original data directory "
+            "No symbolic link created. You are using the original data directory "
             "as the working directory."
         )
         return
@@ -163,7 +184,7 @@ def safe_symlink(input_file: os.PathLike, soft_link_name: os.PathLike):
     os.symlink(os.path.abspath(input_file), soft_link_name)
 
 
-def samefile(file1: os.PathLike, file2: os.PathLike):
+def samefile(file1: os.PathLike, file2: os.PathLike) -> bool:
     """Return True if two files are the same file.
 
     Attempts to account for different relative paths to the same file.
@@ -282,12 +303,12 @@ def check_pdf(input_file: Path) -> bool:
             return False
 
 
-def clamp(n, smallest, largest):  # mypy doesn't understand types for this
+def clamp(n: T, smallest: T, largest: T) -> T:
     """Clamps the value of ``n`` to between ``smallest`` and ``largest``."""
     return max(smallest, min(n, largest))
 
 
-def remove_all_log_handlers(logger):
+def remove_all_log_handlers(logger: logging.Logger) -> None:
     """Remove all log handlers, usually used in a child process.
 
     The child process inherits the log handlers from the parent process when
@@ -300,15 +321,11 @@ def remove_all_log_handlers(logger):
         handler.close()  # To ensure handlers with opened resources are released
 
 
-def pikepdf_enable_mmap():
+def pikepdf_enable_mmap() -> None:
     """Enable pikepdf mmap."""
-    # try:
+    try:
-    #     if pikepdf._qpdf.set_access_default_mmap(True):
+        if pikepdf._core.set_access_default_mmap(True):
-    #         log.debug("pikepdf mmap enabled")
+            log.debug("pikepdf mmap enabled")
-    # except AttributeError:
+    except AttributeError:
-    #     log.debug("pikepdf mmap not available")
+        log.debug("pikepdf mmap not available")
-    # We found a race condition probably related to pybind issue #2252 that can
+    log.debug("pikepdf mmap disabled")
-    # cause a crash. For now, disable pikepdf mmap to be on the safe side.
-    # Fix is not in pybind11 2.6.0
-    # log.debug("pikepdf mmap disabled")
-    return

src/ocrmypdf/hocrtransform.py

@@ -19,6 +19,7 @@ from xml.etree import ElementTree
 
 with warnings.catch_warnings():
     # reportlab uses deprecated load_module
+    # shim can be removed when we require reportlab >= 3.7
     warnings.filterwarnings(
         'ignore', category=DeprecationWarning, message=r".*load_module.*"
     )

src/ocrmypdf/imageops.py

@@ -6,10 +6,26 @@
 from __future__ import annotations
 
 import logging
-from math import ceil, floor, sqrt
+from math import floor, sqrt
+from typing import Optional, Tuple
 
 from PIL import Image
 
+# Remove this workaround when we require Pillow >= 9.1.0
+try:
+    Resampling = Image.Resampling  # type: ignore
+except AttributeError:
+    # Pillow 9 shim
+    Resampling = Image  # type: ignore
+
+
+# While from __future__ import annotations, we use singledispatch here, which
+# does not support annotations. Disable check about using old-style typing
+# until Python 3.10, OR when drop singledispatch in ocrmypdf 15.
+# ruff: noqa: UP006
+# ruff: noqa: UP007
+
+
 log = logging.getLogger(__name__)
 
 
@@ -26,14 +42,75 @@ def bytes_per_pixel(mode: str) -> int:
     return 4
 
 
+def _calculate_downsample(
+    image_size: Tuple[int, int],
+    bytes_per_pixel: int,
+    *,
+    max_size: Optional[Tuple[int, int]] = None,
+    max_pixels: Optional[int] = None,
+    max_bytes: Optional[int] = None,
+) -> Tuple[int, int]:
+    """Calculate image size required to downsample an image to fit limits.
+
+    If no limit is exceeded, the input image's size is returned.
+
+    Args:
+        image_size: Dimensions of image.
+        bytes_per_pixel: Number of bytes per pixel.
+        max_size: The maximum width and height of the image.
+        max_pixels: The maximum number of pixels in the image. Some image consumers
+            limit the total number of pixels as some value other than width*height.
+        max_bytes: The maximum number of bytes in the image. RGB is counted as 4
+            bytes; all other modes are counted as 1 byte.
+    """
+    size = image_size
+
+    if max_size is not None:
+        overage = max_size[0] / size[0], max_size[1] / size[1]
+        size_factor = min(overage)
+        if size_factor < 1.0:
+            log.debug("Resizing image to fit image dimensions limit")
+            size = floor(size[0] * size_factor), floor(size[1] * size_factor)
+            if size[0] == 0:
+                size = 1, min(size[1], max_size[1])
+            elif size[1] == 0:
+                size = min(size[0], max_size[0]), 1
+
+    if max_pixels is not None:
+        if size[0] * size[1] > max_pixels:
+            log.debug("Resizing image to fit image pixel limit")
+            pixels_factor = sqrt(max_pixels / (size[0] * size[1]))
+            size = floor(size[0] * pixels_factor), floor(size[1] * pixels_factor)
+
+    if max_bytes is not None:
+        bpp = bytes_per_pixel
+        # stride = bytes per line
+        stride = size[0] * bpp
+        height = size[1]
+        if stride * height > max_bytes:
+            log.debug("Resizing image to fit image byte size limit")
+            bytes_factor = sqrt(max_bytes / (stride * height))
+            scaled_stride = floor(stride * bytes_factor)
+            scaled_height = floor(height * bytes_factor)
+            if scaled_stride == 0:
+                scaled_stride = bpp
+                scaled_height = min(max_bytes // bpp, scaled_height)
+            if scaled_height == 0:
+                scaled_height = 1
+                scaled_stride = min(max_bytes // scaled_height, scaled_stride)
+            size = floor(scaled_stride / bpp), scaled_height
+
+    return size
+
+
 def calculate_downsample(
     image: Image.Image,
     *,
-    max_size: tuple[int, int] | None = None,
+    max_size: Optional[Tuple[int, int]] = None,
-    max_pixels: int | None = None,
+    max_pixels: Optional[int] = None,
-    max_bytes: int | None = None,
+    max_bytes: Optional[int] = None,
-) -> tuple[int, int]:
+) -> Tuple[int, int]:
-    """Calculate image size required to downsample an image to fit lmiits.
+    """Calculate image size required to downsample an image to fit limits.
 
     If no limit is exceeded, the input image's size is returned.
 
@@ -45,42 +122,20 @@ def calculate_downsample(
         max_bytes: The maximum number of bytes in the image. RGB is counted as 4
             bytes; all other modes are counted as 1 byte.
     """
-    size = image.size
+    return _calculate_downsample(
-
+        image.size,
-    if max_size is not None:
+        bytes_per_pixel(image.mode),
-        major_axis = max(image.size)
+        max_size=max_size,
-        size_factor = max(max_size) / major_axis
+        max_pixels=max_pixels,
-        if size_factor < 1.0:
+        max_bytes=max_bytes,
-            log.debug("Resizing image to fit Tesseract image size limit")
+    )
-            size = floor(size[0] * size_factor), floor(size[1] * size_factor)
-
-    if max_pixels is not None:
-        if size[0] * size[1] > max_pixels:
-            log.debug("Resizing image to fit image pixel limit")
-            pixels_factor = sqrt(max_pixels / (image.size[0] * image.size[1]))
-            size = floor(size[0] * pixels_factor), floor(size[1] * pixels_factor)
-
-    if max_bytes is not None:
-        bpp = bytes_per_pixel(image.mode)
-        # stride = bytes per line
-        stride = size[0] * bpp
-        height = size[1]
-        if stride * height > max_bytes:
-            log.debug("Resizing image to fit image byte size limit")
-            bytes_factor = sqrt((max_bytes) / (stride * height))
-            scaled_stride = floor(stride * bytes_factor)
-            scaled_height = floor(height * bytes_factor)
-            size = ceil(scaled_stride / bpp), scaled_height
-            assert (size[0] * bpp * size[1]) <= max_bytes
-
-    return size
 
 
 def downsample_image(
     image: Image.Image,
     new_size: tuple[int, int],
     *,
-    resample_mode: Image.Resampling = Image.Resampling.BICUBIC,
+    resample_mode: Image.Resampling = Resampling.BICUBIC,
     reducing_gap: int = 3,
 ) -> Image.Image:
     """Downsample an image to fit within the given limits.

src/ocrmypdf/optimize.py

@@ -68,10 +68,10 @@ def jpg_name(root: Path, xref: Xref) -> Path:
 
 
 def extract_image_filter(
-    pike: Pdf, root: Path, image: Stream, xref: Xref
+    pdf: Pdf, root: Path, image: Stream, xref: Xref
 ) -> tuple[PdfImage, tuple[Name, Object]] | None:
     """Determine if an image is extractable."""
-    del pike  # unused args
+    del pdf  # unused args
     del root
 
     if image.Subtype != Name.Image:
@@ -126,12 +126,12 @@ def extract_image_filter(
 
 
 def extract_image_jbig2(
-    *, pike: Pdf, root: Path, image: Stream, xref: Xref, options
+    *, pdf: Pdf, root: Path, image: Stream, xref: Xref, options
 ) -> XrefExt | None:
     """Extract an image, saving it as a JBIG2 file."""
     del options  # unused arg
 
-    result = extract_image_filter(pike, root, image, xref)
+    result = extract_image_filter(pdf, root, image, xref)
     if result is None:
         return None
     pim, filtdp = result
@@ -168,10 +168,10 @@ def extract_image_jbig2(
 
 
 def extract_image_generic(
-    *, pike: Pdf, root: Path, image: Stream, xref: Xref, options
+    *, pdf: Pdf, root: Path, image: Stream, xref: Xref, options
 ) -> XrefExt | None:
     """Generic image extraction."""
-    result = extract_image_filter(pike, root, image, xref)
+    result = extract_image_filter(pdf, root, image, xref)
     if result is None:
         return None
     pim, filtdp = result
@@ -230,8 +230,67 @@ def extract_image_generic(
     return None
 
 
+def _find_image_xrefs_container(
+    pdf: Pdf,
+    container: Object,
+    pageno: int,
+    include_xrefs: MutableSet[Xref],
+    exclude_xrefs: MutableSet[Xref],
+    pageno_for_xref: dict[Xref, int],
+    depth: int = 0,
+):
+    """Find all image XRefs or Form XObject and add to the include/exclude sets."""
+    if depth > 10:
+        log.warning("Recursion depth exceeded in _find_image_xrefs_page")
+        return
+    try:
+        xobjs = container.Resources.XObject
+    except AttributeError:
+        return
+    for _imname, image in dict(xobjs).items():
+        if image.objgen[1] != 0:
+            continue  # Ignore images in an incremental PDF
+        if Name.Subtype in image and image.Subtype == Name.Form:
+            # Recurse into Form XObjects
+            log.debug(f"Recursing into Form XObject {_imname} in page {pageno}")
+            _find_image_xrefs_container(
+                pdf,
+                image,
+                pageno,
+                include_xrefs,
+                exclude_xrefs,
+                pageno_for_xref,
+                depth + 1,
+            )
+            continue
+        xref = Xref(image.objgen[0])
+        if Name.SMask in image:
+            # Ignore soft masks
+            smask_xref = Xref(image.SMask.objgen[0])
+            exclude_xrefs.add(smask_xref)
+            log.debug(f"xref {smask_xref}: skipping image because it is an SMask")
+        include_xrefs.add(xref)
+        log.debug(f"xref {xref}: treating as an optimization candidate")
+        if xref not in pageno_for_xref:
+            pageno_for_xref[xref] = pageno
+
+
+def _find_image_xrefs(pdf: Pdf):
+    include_xrefs: MutableSet[Xref] = set()
+    exclude_xrefs: MutableSet[Xref] = set()
+    pageno_for_xref: dict[Xref, int] = {}
+
+    for pageno, page in enumerate(pdf.pages):
+        _find_image_xrefs_container(
+            pdf, page, pageno, include_xrefs, exclude_xrefs, pageno_for_xref
+        )
+
+    working_xrefs = include_xrefs - exclude_xrefs
+    return working_xrefs, pageno_for_xref
+
+
 def extract_images(
-    pike: Pdf,
+    pdf: Pdf,
     root: Path,
     options,
     extract_fn: Callable[..., XrefExt | None],
@@ -250,35 +309,13 @@ def extract_images(
     it does a tuple should be returned: (xref, ext) where .ext is the file
     extension. extract_fn must also extract the file it finds interesting.
     """
-    include_xrefs: MutableSet[Xref] = set()
-    exclude_xrefs: MutableSet[Xref] = set()
-    pageno_for_xref = {}
     errors = 0
-    for pageno, page in enumerate(pike.pages):
+    working_xrefs, pageno_for_xref = _find_image_xrefs(pdf)
-        try:
-            xobjs = page.Resources.XObject
-        except AttributeError:
-            continue
-        for _imname, image in dict(xobjs).items():
-            if image.objgen[1] != 0:
-                continue  # Ignore images in an incremental PDF
-            xref = Xref(image.objgen[0])
-            if Name.SMask in image:
-                # Ignore soft masks
-                smask_xref = Xref(image.SMask.objgen[0])
-                exclude_xrefs.add(smask_xref)
-                log.debug(f"xref {smask_xref}: skipping image because it is an SMask")
-            include_xrefs.add(xref)
-            log.debug(f"xref {xref}: treating as an optimization candidate")
-            if xref not in pageno_for_xref:
-                pageno_for_xref[xref] = pageno
-
-    working_xrefs = include_xrefs - exclude_xrefs
     for xref in working_xrefs:
-        image = pike.get_object((xref, 0))
+        image = pdf.get_object((xref, 0))
         try:
             result = extract_fn(
-                pike=pike, root=root, image=image, xref=xref, options=options
+                pdf=pdf, root=root, image=image, xref=xref, options=options
             )
         except Exception:  # pylint: disable=broad-except
             log.exception(
@@ -292,12 +329,12 @@ def extract_images(
 
 
 def extract_images_generic(
-    pike: Pdf, root: Path, options
+    pdf: Pdf, root: Path, options
 ) -> tuple[list[Xref], list[Xref]]:
     """Extract any >=2bpp image we think we can improve."""
     jpegs = []
     pngs = []
-    for _, xref_ext in extract_images(pike, root, options, extract_image_generic):
+    for _, xref_ext in extract_images(pdf, root, options, extract_image_generic):
         log.debug('%s', xref_ext)
         if xref_ext.ext == '.png':
             pngs.append(xref_ext.xref)
@@ -307,10 +344,10 @@ def extract_images_generic(
     return jpegs, pngs
 
 
-def extract_images_jbig2(pike: Pdf, root: Path, options) -> dict[int, list[XrefExt]]:
+def extract_images_jbig2(pdf: Pdf, root: Path, options) -> dict[int, list[XrefExt]]:
     """Extract any bitonal image that we think we can improve as JBIG2."""
     jbig2_groups = defaultdict(list)
-    for pageno, xref_ext in extract_images(pike, root, options, extract_image_jbig2):
+    for pageno, xref_ext in extract_images(pdf, root, options, extract_image_jbig2):
         group = pageno // options.jbig2_page_group_size
         jbig2_groups[group].append(xref_ext)
 
@@ -330,6 +367,7 @@ def _produce_jbig2_images(
                 fspath(root),  # =cwd
                 (img_name(root, xref, ext) for xref, ext in xref_exts),  # =infiles
                 prefix,  # =out_prefix
+                options.jbig2_threshold,
             )
 
     def jbig2_single_args(root, groups: dict[int, list[XrefExt]]):
@@ -342,6 +380,7 @@ def _produce_jbig2_images(
                     fspath(root),
                     img_name(root, xref, ext),
                     root / f'{prefix}.{n:04d}',
+                    options.jbig2_threshold,
                 )
 
     if options.jbig2_page_group_size > 1:
@@ -366,7 +405,7 @@ def _produce_jbig2_images(
 
 
 def convert_to_jbig2(
-    pike: Pdf,
+    pdf: Pdf,
     jbig2_groups: dict[int, list[XrefExt]],
     root: Path,
     options,
@@ -393,7 +432,7 @@ def convert_to_jbig2(
         jbig2_symfile = root / (prefix + '.sym')
         if jbig2_symfile.exists():
             jbig2_globals_data = jbig2_symfile.read_bytes()
-            jbig2_globals = Stream(pike, jbig2_globals_data)
+            jbig2_globals = Stream(pdf, jbig2_globals_data)
             jbig2_globals_dict = Dictionary(JBIG2Globals=jbig2_globals)
         elif options.jbig2_page_group_size == 1:
             jbig2_globals_dict = None
@@ -404,7 +443,7 @@ def convert_to_jbig2(
             xref, _ = xref_ext
             jbig2_im_file = root / (prefix + f'.{n:04d}')
             jbig2_im_data = jbig2_im_file.read_bytes()
-            im_obj = pike.get_object(xref, 0)
+            im_obj = pdf.get_object(xref, 0)
             im_obj.write(
                 jbig2_im_data, filter=Name.JBIG2Decode, decode_parms=jbig2_globals_dict
             )
@@ -424,7 +463,7 @@ def _optimize_jpeg(args: tuple[Xref, Path, Path, int]) -> tuple[Xref, Path | Non
 
 
 def transcode_jpegs(
-    pike: Pdf, jpegs: Sequence[Xref], root: Path, options, executor: Executor
+    pdf: Pdf, jpegs: Sequence[Xref], root: Path, options, executor: Executor
 ) -> None:
     """Optimize JPEGs according to optimization settings."""
 
@@ -438,7 +477,7 @@ def transcode_jpegs(
         xref, opt_jpg = result
         if opt_jpg:
             compdata = opt_jpg.read_bytes()  # JPEG can inserted into PDF as is
-            im_obj = pike.get_object(xref, 0)
+            im_obj = pdf.get_object(xref, 0)
             im_obj.write(compdata, filter=Name.DCTDecode)
         pbar.update()
 
@@ -458,9 +497,9 @@ def transcode_jpegs(
 
 
 def _find_deflatable_jpeg(
-    *, pike: Pdf, root: Path, image: Stream, xref: Xref, options
+    *, pdf: Pdf, root: Path, image: Stream, xref: Xref, options
 ) -> XrefExt | None:
-    result = extract_image_filter(pike, root, image, xref)
+    result = extract_image_filter(pdf, root, image, xref)
     if result is None:
         return None
     _pim, filtdp = result
@@ -472,9 +511,9 @@ def _find_deflatable_jpeg(
 
 
 def _deflate_jpeg(args: tuple[Pdf, threading.Lock, Xref, int]) -> tuple[Xref, bytes]:
-    pike, lock, xref, complevel = args
+    pdf, lock, xref, complevel = args
     with lock:
-        xobj = pike.get_object(xref, 0)
+        xobj = pdf.get_object(xref, 0)
         try:
             data = xobj.read_raw_bytes()
         except PdfError:
@@ -485,7 +524,7 @@ def _deflate_jpeg(args: tuple[Pdf, threading.Lock, Xref, int]) -> tuple[Xref, by
     return xref, compdata
 
 
-def deflate_jpegs(pike: Pdf, root: Path, options, executor: Executor) -> None:
+def deflate_jpegs(pdf: Pdf, root: Path, options, executor: Executor) -> None:
     """Apply FlateDecode to JPEGs.
 
     This is a lossless compression method that is supported by all PDF viewers,
@@ -493,7 +532,7 @@ def deflate_jpegs(pike: Pdf, root: Path, options, executor: Executor) -> None:
     images.
     """
     jpegs = []
-    for _pageno, xref_ext in extract_images(pike, root, options, _find_deflatable_jpeg):
+    for _pageno, xref_ext in extract_images(pdf, root, options, _find_deflatable_jpeg):
         xref = xref_ext.xref
         log.debug(f'xref {xref}: marking this JPEG as deflatable')
         jpegs.append(xref)
@@ -505,13 +544,13 @@ def deflate_jpegs(pike: Pdf, root: Path, options, executor: Executor) -> None:
 
     def deflate_args() -> Iterator:
         for xref in jpegs:
-            yield pike, lock, xref, complevel
+            yield pdf, lock, xref, complevel
 
     def finish(result, pbar):
         xref, compdata = result
         if len(compdata) > 0:
             with lock:
-                xobj = pike.get_object(xref, 0)
+                xobj = pdf.get_object(xref, 0)
                 xobj.write(compdata, filter=[Name.FlateDecode, Name.DCTDecode])
         pbar.update()
 
@@ -530,16 +569,16 @@ def deflate_jpegs(pike: Pdf, root: Path, options, executor: Executor) -> None:
     )
 
 
-def _transcode_png(pike: Pdf, filename: Path, xref: Xref) -> bool:
+def _transcode_png(pdf: Pdf, filename: Path, xref: Xref) -> bool:
     output = filename.with_suffix('.png.pdf')
     with output.open('wb') as f:
         img2pdf.convert(fspath(filename), outputstream=f, **IMG2PDF_KWARGS)
 
     with Pdf.open(output) as pdf_image:
         foreign_image = next(iter(pdf_image.pages[0].images.values()))
-        local_image = pike.copy_foreign(foreign_image)
+        local_image = pdf.copy_foreign(foreign_image)
 
-        im_obj = pike.get_object(xref, 0)
+        im_obj = pdf.get_object(xref, 0)
         im_obj.write(
             local_image.read_raw_bytes(),
             filter=local_image.Filter,
@@ -572,7 +611,7 @@ def _transcode_png(pike: Pdf, filename: Path, xref: Xref) -> bool:
 
 
 def transcode_pngs(
-    pike: Pdf,
+    pdf: Pdf,
     images: Sequence[Xref],
     image_name_fn: Callable[[Path, Xref], Path],
     root: Path,
@@ -613,7 +652,7 @@ def transcode_pngs(
 
     for xref in modified:
         filename = png_name(root, xref)
-        _transcode_png(pike, filename, xref)
+        _transcode_png(pdf, filename, xref)
 
 
 DEFAULT_EXECUTOR = SerialExecutor()
@@ -639,24 +678,24 @@ def optimize(
     if options.jbig2_page_group_size == 0:
         options.jbig2_page_group_size = 10 if options.jbig2_lossy else 1
 
-    with Pdf.open(input_file) as pike:
+    with Pdf.open(input_file) as pdf:
         root = output_file.parent / 'images'
         root.mkdir(exist_ok=True)
 
-        jpegs, pngs = extract_images_generic(pike, root, options)
+        jpegs, pngs = extract_images_generic(pdf, root, options)
-        transcode_jpegs(pike, jpegs, root, options, executor)
+        transcode_jpegs(pdf, jpegs, root, options, executor)
-        deflate_jpegs(pike, root, options, executor)
+        deflate_jpegs(pdf, root, options, executor)
         # if options.optimize >= 2:
         # Try pngifying the jpegs
-        #    transcode_pngs(pike, jpegs, jpg_name, root, options)
+        #    transcode_pngs(pdf, jpegs, jpg_name, root, options)
-        transcode_pngs(pike, pngs, png_name, root, options, executor)
+        transcode_pngs(pdf, pngs, png_name, root, options, executor)
 
-        jbig2_groups = extract_images_jbig2(pike, root, options)
+        jbig2_groups = extract_images_jbig2(pdf, root, options)
-        convert_to_jbig2(pike, jbig2_groups, root, options, executor)
+        convert_to_jbig2(pdf, jbig2_groups, root, options, executor)
 
         target_file = output_file.with_suffix('.opt.pdf')
-        pike.remove_unreferenced_resources()
+        pdf.remove_unreferenced_resources()
-        pike.save(target_file, **save_settings)
+        pdf.save(target_file, **save_settings)
 
     input_size = input_file.stat().st_size
     output_size = target_file.stat().st_size
@@ -673,9 +712,9 @@ def optimize(
             "optimizations will not be used"
         )
         # We still need to save the file
-        with Pdf.open(input_file) as pike:
+        with Pdf.open(input_file) as pdf:
-            pike.remove_unreferenced_resources()
+            pdf.remove_unreferenced_resources()
-            pike.save(output_file, **save_settings)
+            pdf.save(output_file, **save_settings)
     else:
         safe_symlink(target_file, output_file)
 
@@ -700,6 +739,7 @@ def main(infile, outfile, level, jobs=1):
             self.png_quality = png_quality
             self.jbig2_page_group_size = 0
             self.jbig2_lossy = jb2lossy
+            self.jbig2_threshold = 0.85
             self.quiet = True
             self.progress_bar = False
 

src/ocrmypdf/pdfa.py

@@ -6,14 +6,10 @@
 from __future__ import annotations
 
 import base64
+from importlib.resources import files as package_files
 from pathlib import Path
 from typing import Iterator
 
-try:
-    from importlib.resources import files as package_files
-except ImportError:
-    from importlib_resources import files as package_files  # type: ignore
-
 import pikepdf
 
 SRGB_ICC_PROFILE_NAME = 'sRGB.icc'

src/ocrmypdf/pdfinfo/info.py

@@ -9,6 +9,8 @@ from __future__ import annotations
 import atexit
 import logging
 import re
+import statistics
+import sys
 from collections import defaultdict
 from contextlib import ExitStack
 from decimal import Decimal
@@ -21,7 +23,9 @@ from typing import Container, Iterable, Iterator, Mapping, NamedTuple, Sequence,
 from warnings import warn
 
 from pikepdf import (
+    Name,
     Object,
+    Page,
     Pdf,
     PdfImage,
     PdfInlineImage,
@@ -418,12 +422,12 @@ class ImageInfo:
         return self._type
 
     @property
-    def width(self):
+    def width(self) -> int:
         """Width of the image in pixels."""
         return self._width
 
     @property
-    def height(self):
+    def height(self) -> int:
         """Height of the image in pixels."""
         return self._height
 
@@ -456,17 +460,24 @@ class ImageInfo:
         return self.dpi.is_finite and self.width >= 0 and self.height >= 0
 
     @property
-    def dpi(self):
+    def dpi(self) -> Resolution:
         """Dots per inch of the image.
 
         Calculated based on where and how the image is drawn in the PDF.
         """
         return _get_dpi(self._shorthand, (self._width, self._height))
 
+    @property
+    def printed_area(self) -> float:
+        """Physical area of the image in square inches."""
+        if not self.renderable:
+            return 0.0
+        return float(self.width * self.dpi.x * self.height * self.dpi.y)
+
     def __repr__(self):
         """Return a string representation of the image."""
         return (
-            f"<ImageInfo '{self.name}' {self.type_} {self.width}x{self.height} "
+            f"<ImageInfo '{self.name}' {self.type_} {self.width}×{self.height} "
             f"{self.color} {self.comp} {self.bpc} {self.enc} {self.dpi}>"
         )
 
@@ -491,15 +502,15 @@ def _image_xobjects(container) -> Iterator[tuple[Object, str]]:
     since the object does not know its own name.
 
     """
-    if '/Resources' not in container:
+    if Name.Resources not in container:
         return
-    resources = container['/Resources']
+    resources = container[Name.Resources]
-    if '/XObject' not in resources:
+    if Name.XObject not in resources:
         return
-    for key, candidate in resources['/XObject'].items():
+    for key, candidate in resources[Name.XObject].items():
-        if candidate is None or '/Subtype' not in candidate:
+        if candidate is None or Name.Subtype not in candidate:
             continue
-        if candidate['/Subtype'] == '/Image':
+        if candidate[Name.Subtype] == Name.Image:
             pdfimage = candidate
             yield (pdfimage, key)
 
@@ -535,15 +546,15 @@ def _find_form_xobject_images(pdf: Pdf, container: Object, contentsinfo: Content
     The container may be a page, or a parent Form XObject.
 
     """
-    if '/Resources' not in container:
+    if Name.Resources not in container:
         return
-    resources = container['/Resources']
+    resources = container[Name.Resources]
-    if '/XObject' not in resources:
+    if Name.XObject not in resources:
         return
-    xobjs = resources['/XObject'].as_dict()
+    xobjs = resources[Name.XObject].as_dict()
     for xobj in xobjs:
         candidate = xobjs[xobj]
-        if candidate is None or candidate['/Subtype'] != '/Form':
+        if candidate is None or candidate[Name.Subtype] != Name.Form:
             continue
 
         form_xobject = candidate
@@ -581,16 +592,19 @@ def _process_content_streams(
     downsampling.
 
     """
-    if container.get('/Type') == '/Page' and '/Contents' in container:
+    if container.get(Name.Type) == Name.Page and Name.Contents in container:
         initial_shorthand = shorthand or UNIT_SQUARE
-    elif container.get('/Type') == '/XObject' and container['/Subtype'] == '/Form':
+    elif (
+        container.get(Name.Type) == Name.XObject
+        and container[Name.Subtype] == Name.Form
+    ):
         # Set the CTM to the state it was when the "Do" operator was
         # encountered that is drawing this instance of the Form XObject
         ctm = PdfMatrix(shorthand) if shorthand else PdfMatrix.identity()
 
         # A Form XObject may provide its own matrix to map form space into
         # user space. Get this if one exists
-        form_shorthand = container.get('/Matrix', PdfMatrix.identity())
+        form_shorthand = container.get(Name.Matrix, PdfMatrix.identity())
         form_matrix = PdfMatrix(form_shorthand)
 
         # Concatenate form matrix with CTM to ensure CTM is correct for
@@ -742,12 +756,38 @@ def _pdf_pageinfo_concurrent(
     return pages
 
 
+class PageResolutionProfile(NamedTuple):
+    """Information about the resolutions of a page."""
+
+    weighted_dpi: float
+    """The weighted average DPI of the page, weighted by the area of each image."""
+
+    max_dpi: float
+    """The maximum DPI of an image on the page."""
+
+    average_to_max_dpi_ratio: float
+    """The average DPI of the page divided by the maximum DPI of the page.
+
+    This indicates the intensity of the resolution variation on the page.
+
+    If the average is 1.0 or close to 1.0, has all of its content at a uniform
+    resolution. If the average is much lower than 1.0, some content is at a
+    higher resolution than the rest of the page.
+    """
+
+    area_ratio: float
+    """The maximum-DPI area of the page divided by the total drawn area.
+
+    This indicates the prevalence of high-resolution content on the page.
+    """
+
+
 class PageInfo:
     """Information about type of contents on each page in a PDF."""
 
     _has_text: bool | None
     _has_vector: bool | None
-    _images: list[ImageInfo]
+    _images: list[ImageInfo] = []
 
     def __init__(
         self,
@@ -771,7 +811,7 @@ class PageInfo:
         check_pages: Container[int],
         detailed_analysis: bool,
     ):
-        page = pdf.pages[pageno]
+        page: Page = pdf.pages[pageno]
         mediabox = [Decimal(d) for d in page.MediaBox.as_list()]
         width_pt = mediabox[2] - mediabox[0]
         height_pt = mediabox[3] - mediabox[1]
@@ -779,7 +819,7 @@ class PageInfo:
         check_this_page = pageno in check_pages
 
         if check_this_page and detailed_analysis:
-            pscript5_mode = str(pdf.docinfo.get('/Creator')).startswith('PScript5')
+            pscript5_mode = str(pdf.docinfo.get(Name.Creator)).startswith('PScript5')
             miner = get_page_analysis(infile, pageno, pscript5_mode)
             self._textboxes = list(simplify_textboxes(miner, get_text_boxes))
             bboxes = (box.bbox for box in self._textboxes)
@@ -789,17 +829,13 @@ class PageInfo:
             self._textboxes = []
             self._has_text = None  # i.e. "no information"
 
-        userunit = page.get('/UserUnit', Decimal(1.0))
+        userunit = page.get(Name.UserUnit, Decimal(1.0))
         if not isinstance(userunit, Decimal):
             userunit = Decimal(userunit)
         self._userunit = userunit
         self._width_inches = width_pt * userunit / Decimal(72.0)
         self._height_inches = height_pt * userunit / Decimal(72.0)
-
+        self._rotate = int(getattr(page.obj, 'Rotate', 0))
-        try:
-            self._rotate = int(page['/Rotate'])
-        except KeyError:
-            self._rotate = 0
 
         userunit_shorthand = (userunit, 0, 0, userunit, 0, 0)
 
@@ -938,6 +974,47 @@ class PageInfo:
         else:
             return '1.5'
 
+    def page_dpi_profile(self) -> PageResolutionProfile | None:
+        """Return information about the DPIs of the page.
+
+        This is useful to detect pages with a small proportion of high-resolution
+        content that is forcing us to use a high DPI for the whole page. The ratio
+        is weighted by the area of each image. If images overlap, the overlapped
+        area counts.
+
+        Vector graphics and text are ignored.
+
+        Returns None if there is no meaningful DPI for the page.
+        """
+        image_dpis = [
+            image.dpi.to_scalar() for image in self._images if image.renderable
+        ]
+        image_areas = [image.printed_area for image in self._images if image.renderable]
+        total_drawn_area = sum(image_areas)
+        if total_drawn_area == 0:
+            return None
+
+        weights = [area / total_drawn_area for area in image_areas]
+        # Calculate harmonic mean of DPIs weighted by area
+        if sys.version_info >= (3, 10):
+            weighted_dpi = statistics.harmonic_mean(image_dpis, weights)
+        else:
+            weighted_dpi = sum(weights) / sum(
+                weight / dpi for weight, dpi in zip(weights, image_dpis)
+            )
+        max_dpi = max(image_dpis)
+        dpi_average_max_ratio = weighted_dpi / max_dpi
+
+        arg_max_dpi = image_dpis.index(max_dpi)
+        max_area_ratio = image_areas[arg_max_dpi] / total_drawn_area
+
+        return PageResolutionProfile(
+            weighted_dpi,
+            max_dpi,
+            dpi_average_max_ratio,
+            max_area_ratio,
+        )
+
     def __repr__(self):
         """Return string representation."""
         return (
@@ -953,6 +1030,10 @@ DEFAULT_EXECUTOR = SerialExecutor()
 class PdfInfo:
     """Get summary information about a PDF."""
 
+    _has_acroform: bool = False
+    _has_signature: bool = False
+    _needs_rendering: bool = False
+
     def __init__(
         self,
         infile,
@@ -980,13 +1061,13 @@ class PdfInfo:
                 check_pages=check_pages,
                 detailed_analysis=detailed_analysis,
             )
-            self._needs_rendering = pdf.Root.get('/NeedsRendering', False)
+            self._needs_rendering = pdf.Root.get(Name.NeedsRendering, False)
-            self._has_acroform = False
+            if Name.AcroForm in pdf.Root:
-            if '/AcroForm' in pdf.Root:
+                if len(pdf.Root.AcroForm.get(Name.Fields, [])) > 0:
-                if len(pdf.Root.AcroForm.get('/Fields', [])) > 0:
                     self._has_acroform = True
-                elif '/XFA' in pdf.Root.AcroForm:
+                elif Name.XFA in pdf.Root.AcroForm:
                     self._has_acroform = True
+                self._has_signature = bool(pdf.Root.AcroForm.get(Name.SigFlags, 0) & 1)
 
     @property
     def pages(self) -> Sequence[PageInfo | None]:
@@ -1006,9 +1087,14 @@ class PdfInfo:
 
     @property
     def has_acroform(self) -> bool:
-        """Return True if any page has an AcroForm."""
+        """Return True if the document catalog has an AcroForm."""
         return self._has_acroform
 
+    @property
+    def has_signature(self) -> bool:
+        """Return True if the document annotations has a digital signature."""
+        return self._has_signature
+
     @property
     def filename(self) -> str | Path:
         """Return filename of PDF."""

src/ocrmypdf/pluginspec.py

@@ -203,6 +203,7 @@ def rasterize_pdf_page(
     page_dpi: Resolution | None,
     rotation: int | None,
     filter_vector: bool,
+    stop_on_soft_error: bool,
 ) -> Path:
     """Rasterize one page of a PDF at resolution raster_dpi in canvas units.
 
@@ -213,19 +214,26 @@ def rasterize_pdf_page(
     Args:
         input_file: The PDF to rasterize.
         output_file: The desired name of the rasterized image.
-        raster_device: Type of image to produce at output_file
+        raster_device: Type of image to produce at output_file.
-        raster_dpi: Resolution at which to rasterize page
+        raster_dpi: Resolution in dots per inch at which to rasterize page.
-        pageno: Page number to rasterize (beginning at page 1)
+        pageno: Page number to rasterize (beginning at page 1).
-        page_dpi: Resolution, overriding output image DPI
+        page_dpi: Resolution, overriding output image DPI.
-        rotation: Cardinal angle, clockwise, to rotate page
+        rotation: Cardinal angle, clockwise, to rotate page.
-        filter_vector: If True, remove vector graphics objects
+        filter_vector: If True, remove vector graphics objects.
+        stop_on_soft_error: If there is an "soft error" such that PDF page image
+            generation can proceed, but may visually differ from the original,
+            the implementer of this hook should raise a detailed exception. If
+            ``False``, continue processing and report by logging it. If the hook
+            cannot proceed, it should always raise an exception, regardless of
+            this setting. One "soft error" would be a missing font that is
+            required to properly rasterize the PDF.
+
     Returns:
         Path: output_file if successful
     Note:
         This hook will be called from child processes. Modifying global state
         will not affect the main process or other child processes.
 
-
     Note:
         This is a :ref:`firstresult hook<firstresult>`.
     """
@@ -343,7 +351,6 @@ def filter_pdf_page(page: PageContext, image_filename: Path, output_pdf: Path) -
         This hook will be called from child processes. Modifying global state
         will not affect the main process or other child processes.
 
-
     Note:
         This is a :ref:`firstresult hook<firstresult>`.
     """
@@ -458,10 +465,11 @@ def generate_pdfa(
     pdf_pages: list[Path],
     pdfmark: Path,
     output_file: Path,
-    compression: str,
+    context: PdfContext,
     pdf_version: str,
     pdfa_part: str,
     progressbar_class,
+    stop_on_soft_error: bool,
 ) -> Path:
     """Generate a PDF/A.
 
@@ -475,11 +483,7 @@ def generate_pdfa(
         pdfmark: A PostScript file intended for Ghostscript with details on
             how to perform the PDF/A conversion.
         output_file: The name of the desired output file.
-        compression: One of ``'jpeg'``, ``'lossless'``, ``''``. For ``'jpeg'``,
+        context: The current context.
-            the PDF/A generator should convert all images to JPEG encoding where
-            possible. For lossless, all images should be converted to FlateEncode
-            (lossless PNG). If an empty string, the PDF generator should make its
-            own decisions about how to encode images.
         pdf_version: The minimum PDF version that the output file should be.
             At its own discretion, the PDF/A generator may raise the version,
             but should not lower it.
@@ -492,6 +496,12 @@ def generate_pdfa(
             and the name of the work units ("page"). Then ``instance.update()``
             will be called when a work unit is completed. If ``None``, no
             progress information is reported.
+        stop_on_soft_error: If there is an "soft error" such that PDF/A generation
+            can proceed and produce a valid PDF/A, but output may be invalid or
+            may not visually resemble the original, the implementer of this hook
+            should raise a detailed exception. If ``False``, continue processing
+            and report by logging it. If the hook cannot proceed, it should always
+            raise an exception, regardless of this setting.
 
     Returns:
         Path: If successful, the hook should return ``output_file``.
@@ -499,6 +509,11 @@ def generate_pdfa(
     Note:
         This is a :ref:`firstresult hook<firstresult>`.
 
+    Note:
+        Before version 15.0.0, the ``context`` was not provided and ``compression``
+        was provided instead. Plugins should now read the context object to determine
+        if compression is requested.
+
     See Also:
         https://github.com/tqdm/tqdm
     """

src/ocrmypdf/subprocess/__init__.py

@@ -118,8 +118,6 @@ def run_polling_stderr(
 def _fix_process_args(
     args: Args, env: OsEnviron | None, kwargs
 ) -> tuple[Args, OsEnviron, logging.Logger, bool]:
-    assert 'universal_newlines' not in kwargs, "Use text= instead of universal_newlines"
-
     if not env:
         env = os.environ
 
@@ -294,21 +292,12 @@ def _error_old_version(
     _error_trailer(**locals())
 
 
-def _remove_leading_v(s: str) -> str:
-    if sys.version_info >= (3, 9):
-        return s.removeprefix('v')
-
-    if s.startswith('v'):
-        return s[1:]
-    return s
-
-
 def check_external_program(
     *,
     program: str,
     package: str,
-    version_checker: Callable[[], str],
+    version_checker: Callable[[], Version],
-    need_version: str,
+    need_version: str | Version,
     required_for: str | None = None,
     recommended: bool = False,
     version_parser: type[Version] = Version,
@@ -328,6 +317,8 @@ def check_external_program(
         version_parser: A class that should be used to parse and compare version
             numbers. Used when version numbers do not follow standard conventions.
     """
+    if not isinstance(need_version, Version):
+        need_version = version_parser(need_version)
     try:
         found_version = version_checker()
     except (CalledProcessError, FileNotFoundError) as e:
@@ -341,11 +332,10 @@ def check_external_program(
             raise
         return
 
-    found_version = _remove_leading_v(found_version)
+    if found_version and found_version < need_version:
-    need_version = _remove_leading_v(need_version)
+        _error_old_version(
-
+            program, package, str(need_version), str(found_version), required_for
-    if found_version and version_parser(found_version) < version_parser(need_version):
+        )
-        _error_old_version(program, package, need_version, found_version, required_for)
         if not recommended:
             raise MissingDependencyError(program)
 

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

@@ -1 +0,0 @@
-Tesseract Open Source OCR Engine v5.0.0-beta-20210916-12-g19cc9 with Leptonica

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

@@ -1,7 +1,5 @@
 i a la Waterman
 
- 
-
 4 ons linzen
 
 3 liter water
@@ -17,11 +15,10 @@ laurier, kruidnagel, kerrie, zout
 De linzgen wassen en in-l liter kokend wa-
 ter 1 dag laten weken, 2 liter water bij
 de linzen voegen, zonder het water waarin
-ze geweekt zijn af te gieten., De helft van
+ze geweekt zijn af te gieten, De helft van
 de uien bakken met laurier en Kruidnagel.
 Alle uien, kerrie en zgout bij de linzen
 voegen, Alles aan de kook brengen, Van de
 bloem met boter en melk een papje maken en
 verder afmaken met de soep, Als de linzen
 gfgaar Zijn is de soep klaar.
-

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

@@ -1 +0,0 @@
-Tesseract Open Source OCR Engine v5.0.0-beta-20210916-12-g19cc9 with Leptonica

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

@@ -1,25 +1,11 @@
 Tarnose
 
-  
-  
-
- 
-
 Bokale oa
 
- 
-
 Lehuntze
 
-   
-  
- 
-
 Mugerre
 
- 
-  
-
 Milafranga Komunikabideak
 
 BAIONA  zeiteninsiie —
@@ -27,4 +13,3 @@ BAIONA  zeiteninsiie —
 7 Trenbideak -----
 
 t\ Basusarri — spmeans:20141004 ae: . _ ~
-

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

@@ -1 +0,0 @@
-Tesseract Open Source OCR Engine v5.0.0-beta-20210916-12-g19cc9 with Leptonica

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

@@ -1,2 +1 @@
 Covfefe is a perfectly cromulent word.
-

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

@@ -1 +0,0 @@
-Tesseract Open Source OCR Engine v5.0.0-beta-20210916-12-g19cc9 with Leptonica

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

@@ -1,7 +1,5 @@
 Linzensoep a la Waterman
 
- 
-
 4 ons linzen
 
 3 liter water
@@ -17,11 +15,10 @@ laurier, kruidnagel, kerrie, zout
 De linzgen wassen en in-l liter kokend wa-
 ter 1 dag laten weken, 2 liter water bij
 de linzen voegen, zonder het water waarin
-ze geweekt zijn af te gieten., De helft van
+ze geweekt zijn af te gieten, De helft van
 de uien bakken met laurier en Kruidnagel.
 Alle uien, kerrie en zgout bij de linzen
 voegen, Alles aan de kook brengen, Van de
 bloem met boter en melk een papje maken en
 verder afmaken met de soep, Als de linzen
 gfgaar Zijn is de soep klaar.
-

tests/cache/aspect/__-l__eng__000001_ocr.png__000001_ocr_hocr__hocr__txt/hocr.bin

@@ -5,27 +5,21 @@
  <head>
   <title></title>
   <meta http-equiv="Content-Type" content="text/html;charset=utf-8"/>
-  <meta name='ocr-system' content='tesseract 5.0.0-beta-20210916-12-g19cc9' />
+  <meta name='ocr-system' content='tesseract 5.3.2' />
   <meta name='ocr-capabilities' content='ocr_page ocr_carea ocr_par ocr_line ocrx_word ocrp_wconf'/>
  </head>
  <body>
-  <div class='ocr_page' id='page_1' title='image "/tmp/ocrmypdf.io.gzrr1v_b/000001_ocr.png"; bbox 0 0 1000 800; ppageno 0'>
+  <div class='ocr_page' id='page_1' title='image "/tmp/ocrmypdf.io.9_hn68nz/000001_ocr.png"; bbox 0 0 1000 800; ppageno 0; scan_res 200 200'>
-   <div class='ocr_carea' id='block_1_1' title="bbox 296 96 704 504">
+   <div class='ocr_photo' id='block_1_1' title="bbox 296 96 704 504"></div>
-    <p class='ocr_par' id='par_1_1' lang='eng' title="bbox 296 96 704 504">
-     <span class='ocr_line' id='line_1_1' title="bbox 296 96 704 504; baseline 0 296; x_size 169.33333; x_descenders 42.333332; x_ascenders 42.333336">
-      <span class='ocrx_word' id='word_1_1' title='bbox 296 96 704 504; x_wconf 95'> </span>
-     </span>
-    </p>
-   </div>
    <div class='ocr_carea' id='block_1_2' title="bbox 150 592 841 622">
-    <p class='ocr_par' id='par_1_2' lang='eng' title="bbox 150 592 841 622">
+    <p class='ocr_par' id='par_1_1' lang='eng' title="bbox 150 592 841 622">
-     <span class='ocr_line' id='line_1_2' title="bbox 150 592 841 622; baseline 0 -6; x_size 30; x_descenders 6; x_ascenders 8">
+     <span class='ocr_line' id='line_1_1' title="bbox 150 592 841 622; baseline 0 -5; x_size 30; x_descenders 5; x_ascenders 7">
-      <span class='ocrx_word' id='word_1_2' title='bbox 150 592 230 616; x_wconf 95'>This</span>
+      <span class='ocrx_word' id='word_1_1' title='bbox 150 592 230 617; x_wconf 96'>This</span>
-      <span class='ocrx_word' id='word_1_3' title='bbox 260 592 384 616; x_wconf 95'>should</span>
+      <span class='ocrx_word' id='word_1_2' title='bbox 260 592 384 617; x_wconf 96'>should</span>
-      <span class='ocrx_word' id='word_1_4' title='bbox 413 592 449 616; x_wconf 95'>be</span>
+      <span class='ocrx_word' id='word_1_3' title='bbox 413 592 449 617; x_wconf 95'>be</span>
-      <span class='ocrx_word' id='word_1_5' title='bbox 479 600 493 616; x_wconf 94'>a</span>
+      <span class='ocrx_word' id='word_1_4' title='bbox 479 599 493 617; x_wconf 95'>a</span>
-      <span class='ocrx_word' id='word_1_6' title='bbox 523 592 668 622; x_wconf 94'>perfect</span>
+      <span class='ocrx_word' id='word_1_5' title='bbox 523 592 668 622; x_wconf 95'>perfect</span>
-      <span class='ocrx_word' id='word_1_7' title='bbox 698 592 841 616; x_wconf 61'>circle:</span>
+      <span class='ocrx_word' id='word_1_6' title='bbox 698 592 841 617; x_wconf 25'>circle.</span>
      </span>
     </p>
    </div>

tests/cache/aspect/__-l__eng__000001_ocr.png__000001_ocr_hocr__hocr__txt/stderr.bin

@@ -1 +0,0 @@
-Tesseract Open Source OCR Engine v5.0.0-beta-20210916-12-g19cc9 with Leptonica

tests/cache/aspect/__-l__eng__000001_ocr.png__000001_ocr_hocr__hocr__txt/txt.bin

@@ -1,4 +1 @@
- 
+This should be a perfect circle.
-
-This should be a perfect circle:
-

tests/cache/aspect/__-l__eng__000001_ocr.png__000001_ocr_tess__pdf__txt/stderr.bin

@@ -1 +0,0 @@
-Tesseract Open Source OCR Engine v5.0.0-beta-20210916-12-g19cc9 with Leptonica

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

@@ -1,4 +1 @@
- 
+This should be a perfect circle.
-
-This should be a perfect circle:
-

tests/cache/cardinal/__-l__eng__000001_ocr.png__000001_ocr_hocr__hocr__txt/hocr.bin

@@ -5,11 +5,11 @@
  <head>
   <title></title>
   <meta http-equiv="Content-Type" content="text/html;charset=utf-8"/>
-  <meta name='ocr-system' content='tesseract 5.0.0-beta-20210916-12-g19cc9' />
+  <meta name='ocr-system' content='tesseract 5.3.2' />
   <meta name='ocr-capabilities' content='ocr_page ocr_carea ocr_par ocr_line ocrx_word ocrp_wconf'/>
  </head>
  <body>
-  <div class='ocr_page' id='page_1' title='image "/tmp/ocrmypdf.io.8je4vgpg/000001_ocr.png"; bbox 0 0 2550 3300; ppageno 0'>
+  <div class='ocr_page' id='page_1' title='image "/tmp/ocrmypdf.io.q0nk4qy2/000001_ocr.png"; bbox 0 0 2550 3300; ppageno 0; scan_res 300 300'>
    <div class='ocr_carea' id='block_1_1' title="bbox 582 131 1968 303">
     <p class='ocr_par' id='par_1_1' lang='eng' title="bbox 582 131 1968 303">
      <span class='ocr_header' id='line_1_1' title="bbox 882 131 1657 217; baseline 0.001 -17; x_size 85; x_descenders 16; x_ascenders 19">
@@ -136,9 +136,9 @@
    <div class='ocr_carea' id='block_1_5' title="bbox 349 748 2117 793">
     <p class='ocr_par' id='par_1_7' lang='eng' title="bbox 349 748 2117 793">
      <span class='ocr_header' id='line_1_10' title="bbox 349 748 2117 793; baseline 0 -9; x_size 45; x_descenders 9; x_ascenders 11">
-      <span class='ocrx_word' id='word_1_84' title='bbox 349 755 367 774; x_wconf 42'>©</span>
+      <span class='ocrx_word' id='word_1_84' title='bbox 349 755 367 774; x_wconf 50'>©</span>
-      <span class='ocrx_word' id='word_1_85' title='bbox 383 748 573 784; x_wconf 90'>Ultra-fast</span>
+      <span class='ocrx_word' id='word_1_85' title='bbox 383 748 573 784; x_wconf 91'>Ultra-fast</span>
-      <span class='ocrx_word' id='word_1_86' title='bbox 616 749 677 784; x_wconf 9'>32”</span>
+      <span class='ocrx_word' id='word_1_86' title='bbox 616 749 677 784; x_wconf 10'>32”</span>
       <span class='ocrx_word' id='word_1_87' title='bbox 694 748 775 784; x_wconf 96'>disk</span>
       <span class='ocrx_word' id='word_1_88' title='bbox 790 748 887 784; x_wconf 96'>drive</span>
       <span class='ocrx_word' id='word_1_89' title='bbox 901 754 1012 785; x_wconf 96'>stores</span>
@@ -150,7 +150,7 @@
       <span class='ocrx_word' id='word_1_95' title='bbox 1638 748 1746 784; x_wconf 96'>holds</span>
       <span class='ocrx_word' id='word_1_96' title='bbox 1761 759 1844 784; x_wconf 96'>over</span>
       <span class='ocrx_word' id='word_1_97' title='bbox 1859 749 2000 791; x_wconf 96'>110,000</span>
-      <span class='ocrx_word' id='word_1_98' title='bbox 2013 753 2117 784; x_wconf 97'>notes</span>
+      <span class='ocrx_word' id='word_1_98' title='bbox 2013 753 2117 784; x_wconf 96'>notes</span>
      </span>
     </p>
    </div>
@@ -165,13 +165,13 @@
    <div class='ocr_carea' id='block_1_7' title="bbox 349 855 2030 1016">
     <p class='ocr_par' id='par_1_9' lang='eng' title="bbox 349 855 2030 1016">
      <span class='ocr_header' id='line_1_12' title="bbox 350 855 1638 900; baseline 0.001 -9; x_size 45; x_descenders 9; x_ascenders 11">
-      <span class='ocrx_word' id='word_1_101' title='bbox 350 863 367 881; x_wconf 51'>¢</span>
+      <span class='ocrx_word' id='word_1_101' title='bbox 350 863 367 881; x_wconf 46'>¢</span>
-      <span class='ocrx_word' id='word_1_102' title='bbox 383 856 464 891; x_wconf 95'>One</span>
+      <span class='ocrx_word' id='word_1_102' title='bbox 383 856 464 891; x_wconf 96'>One</span>
       <span class='ocrx_word' id='word_1_103' title='bbox 478 866 520 891; x_wconf 95'>or</span>
       <span class='ocrx_word' id='word_1_104' title='bbox 534 855 580 891; x_wconf 96'>all</span>
       <span class='ocrx_word' id='word_1_105' title='bbox 594 856 712 892; x_wconf 95'>tracks</span>
       <span class='ocrx_word' id='word_1_106' title='bbox 726 867 811 900; x_wconf 96'>may</span>
-      <span class='ocrx_word' id='word_1_107' title='bbox 823 856 869 892; x_wconf 85'>be</span>
+      <span class='ocrx_word' id='word_1_107' title='bbox 823 856 869 892; x_wconf 84'>be</span>
       <span class='ocrx_word' id='word_1_108' title='bbox 882 856 1212 892; x_wconf 96'>TRANSPOSED</span>
       <span class='ocrx_word' id='word_1_109' title='bbox 1227 861 1264 892; x_wconf 96'>at</span>
       <span class='ocrx_word' id='word_1_110' title='bbox 1277 856 1338 892; x_wconf 96'>the</span>
@@ -256,8 +256,8 @@
    <div class='ocr_carea' id='block_1_12' title="bbox 346 1288 1239 1491">
     <p class='ocr_par' id='par_1_14' lang='eng' title="bbox 346 1288 749 1329">
      <span class='ocr_line' id='line_1_19' title="bbox 346 1288 749 1329; baseline 0.002 -9; x_size 42; x_descenders 9; x_ascenders 10">
-      <span class='ocrx_word' id='word_1_158' title='bbox 346 1288 535 1329; x_wconf 96'>Recording</span>
+      <span class='ocrx_word' id='word_1_158' title='bbox 346 1288 535 1329; x_wconf 95'>Recording</span>
-      <span class='ocrx_word' id='word_1_159' title='bbox 547 1298 567 1321; x_wconf 96'>a</span>
+      <span class='ocrx_word' id='word_1_159' title='bbox 547 1298 567 1321; x_wconf 95'>a</span>
       <span class='ocrx_word' id='word_1_160' title='bbox 579 1288 749 1328; x_wconf 96'>Sequence</span>
      </span>
     </p>
@@ -278,8 +278,8 @@
       <span class='ocrx_word' id='word_1_170' title='bbox 346 1379 411 1406; x_wconf 96'>then</span>
       <span class='ocrx_word' id='word_1_171' title='bbox 422 1378 483 1412; x_wconf 96'>play</span>
       <span class='ocrx_word' id='word_1_172' title='bbox 493 1387 562 1412; x_wconf 96'>your</span>
-      <span class='ocrx_word' id='word_1_173' title='bbox 572 1379 659 1405; x_wconf 95'>MIDI</span>
+      <span class='ocrx_word' id='word_1_173' title='bbox 572 1379 659 1405; x_wconf 96'>MIDI</span>
-      <span class='ocrx_word' id='word_1_174' title='bbox 671 1379 810 1412; x_wconf 95'>keyboard</span>
+      <span class='ocrx_word' id='word_1_174' title='bbox 671 1379 810 1412; x_wconf 96'>keyboard</span>
       <span class='ocrx_word' id='word_1_175' title='bbox 821 1379 848 1406; x_wconf 96'>in</span>
       <span class='ocrx_word' id='word_1_176' title='bbox 858 1379 923 1406; x_wconf 96'>time</span>
       <span class='ocrx_word' id='word_1_177' title='bbox 934 1384 963 1406; x_wconf 96'>to</span>
@@ -288,7 +288,7 @@
      </span>
      <span class='ocr_line' id='line_1_22' title="bbox 347 1417 1232 1452; baseline 0.002 -8; x_size 34; x_descenders 7; x_ascenders 8">
       <span class='ocrx_word' id='word_1_180' title='bbox 347 1417 414 1445; x_wconf 96'>click</span>
-      <span class='ocrx_word' id='word_1_181' title='bbox 425 1418 506 1445; x_wconf 91'>track.</span>
+      <span class='ocrx_word' id='word_1_181' title='bbox 425 1418 506 1445; x_wconf 92'>track.</span>
       <span class='ocrx_word' id='word_1_182' title='bbox 519 1418 609 1445; x_wconf 96'>When</span>
       <span class='ocrx_word' id='word_1_183' title='bbox 620 1419 665 1445; x_wconf 96'>the</span>
       <span class='ocrx_word' id='word_1_184' title='bbox 676 1426 810 1452; x_wconf 96'>sequence</span>
@@ -297,7 +297,7 @@
       <span class='ocrx_word' id='word_1_187' title='bbox 995 1419 1101 1446; x_wconf 96'>around</span>
       <span class='ocrx_word' id='word_1_188' title='bbox 1112 1423 1141 1446; x_wconf 96'>to</span>
       <span class='ocrx_word' id='word_1_189' title='bbox 1152 1419 1201 1446; x_wconf 96'>bar</span>
-      <span class='ocrx_word' id='word_1_190' title='bbox 1213 1419 1232 1450; x_wconf 88'>1,</span>
+      <span class='ocrx_word' id='word_1_190' title='bbox 1213 1419 1232 1450; x_wconf 85'>1,</span>
      </span>
      <span class='ocr_line' id='line_1_23' title="bbox 346 1457 1223 1491; baseline 0.001 -7; x_size 34; x_descenders 7; x_ascenders 8">
       <span class='ocrx_word' id='word_1_191' title='bbox 346 1457 430 1490; x_wconf 16'>you’</span>
@@ -620,7 +620,7 @@
      </span>
      <span class='ocr_line' id='line_1_50' title="bbox 1295 1565 1577 1593; baseline 0.004 -1; x_size 34.748871; x_descenders 6.7488689; x_ascenders 9">
       <span class='ocrx_word' id='word_1_423' title='bbox 1295 1565 1441 1592; x_wconf 96'>unwanted</span>
-      <span class='ocrx_word' id='word_1_424' title='bbox 1452 1565 1577 1593; x_wconf 94'>sections,</span>
+      <span class='ocrx_word' id='word_1_424' title='bbox 1452 1565 1577 1593; x_wconf 93'>sections,</span>
      </span>
     </p>
    </div>
@@ -668,8 +668,8 @@
       <span class='ocrx_word' id='word_1_454' title='bbox 1458 1768 1562 1796; x_wconf 96'>section</span>
       <span class='ocrx_word' id='word_1_455' title='bbox 1574 1769 1666 1802; x_wconf 96'>(verse,</span>
       <span class='ocrx_word' id='word_1_456' title='bbox 1679 1769 1788 1801; x_wconf 96'>chorus,</span>
-      <span class='ocrx_word' id='word_1_457' title='bbox 1800 1769 1865 1802; x_wconf 95'>etc.)</span>
+      <span class='ocrx_word' id='word_1_457' title='bbox 1800 1769 1865 1802; x_wconf 96'>etc.)</span>
-      <span class='ocrx_word' id='word_1_458' title='bbox 1876 1768 1904 1795; x_wconf 95'>in</span>
+      <span class='ocrx_word' id='word_1_458' title='bbox 1876 1768 1904 1795; x_wconf 96'>in</span>
       <span class='ocrx_word' id='word_1_459' title='bbox 1914 1768 2066 1796; x_wconf 96'>individual</span>
      </span>
      <span class='ocr_line' id='line_1_55' title="bbox 1296 1808 2215 1841; baseline 0 -6; x_size 32; x_descenders 5; x_ascenders 8">
@@ -697,7 +697,7 @@
       <span class='ocrx_word' id='word_1_477' title='bbox 1377 1887 1412 1914; x_wconf 96'>all</span>
       <span class='ocrx_word' id='word_1_478' title='bbox 1422 1887 1468 1914; x_wconf 96'>the</span>
       <span class='ocrx_word' id='word_1_479' title='bbox 1478 1891 1552 1920; x_wconf 96'>parts</span>
-      <span class='ocrx_word' id='word_1_480' title='bbox 1563 1887 1621 1914; x_wconf 96'>into</span>
+      <span class='ocrx_word' id='word_1_480' title='bbox 1563 1887 1621 1914; x_wconf 95'>into</span>
       <span class='ocrx_word' id='word_1_481' title='bbox 1632 1895 1649 1914; x_wconf 96'>a</span>
       <span class='ocrx_word' id='word_1_482' title='bbox 1659 1895 1718 1914; x_wconf 96'>new</span>
       <span class='ocrx_word' id='word_1_483' title='bbox 1729 1895 1870 1920; x_wconf 96'>sequence.</span>
@@ -829,9 +829,9 @@
    <div class='ocr_carea' id='block_1_23' title="bbox 347 2427 2145 2507">
     <p class='ocr_par' id='par_1_31' lang='eng' title="bbox 347 2427 2145 2507">
      <span class='ocr_header' id='line_1_67' title="bbox 347 2427 1468 2461; baseline 0.002 -8; x_size 34; x_descenders 7; x_ascenders 8">
-      <span class='ocrx_word' id='word_1_573' title='bbox 347 2432 361 2446; x_wconf 77'>*</span>
+      <span class='ocrx_word' id='word_1_573' title='bbox 347 2432 361 2446; x_wconf 75'>*</span>
       <span class='ocrx_word' id='word_1_574' title='bbox 373 2427 612 2454; x_wconf 91'>Non-destructive</span>
-      <span class='ocrx_word' id='word_1_575' title='bbox 622 2427 914 2461; x_wconf 84'>recording—existing</span>
+      <span class='ocrx_word' id='word_1_575' title='bbox 622 2427 914 2461; x_wconf 87'>recording—existing</span>
       <span class='ocrx_word' id='word_1_576' title='bbox 924 2432 1002 2455; x_wconf 96'>notes</span>
       <span class='ocrx_word' id='word_1_577' title='bbox 1013 2436 1057 2455; x_wconf 96'>are</span>
       <span class='ocrx_word' id='word_1_578' title='bbox 1068 2432 1116 2455; x_wconf 96'>not</span>
@@ -912,12 +912,12 @@
    <div class='ocr_carea' id='block_1_27' title="bbox 347 2648 2100 2727">
     <p class='ocr_par' id='par_1_35' lang='eng' title="bbox 347 2648 2100 2727">
      <span class='ocr_header' id='line_1_72' title="bbox 347 2648 1664 2682; baseline 0.001 -7; x_size 33; x_descenders 6; x_ascenders 8">
-      <span class='ocrx_word' id='word_1_630' title='bbox 347 2654 360 2667; x_wconf 47'>®</span>
+      <span class='ocrx_word' id='word_1_630' title='bbox 347 2654 360 2667; x_wconf 45'>®</span>
-      <span class='ocrx_word' id='word_1_631' title='bbox 372 2648 483 2675; x_wconf 96'>Utilizes</span>
+      <span class='ocrx_word' id='word_1_631' title='bbox 372 2648 483 2675; x_wconf 94'>Utilizes</span>
       <span class='ocrx_word' id='word_1_632' title='bbox 493 2648 564 2680; x_wconf 96'>ultra</span>
       <span class='ocrx_word' id='word_1_633' title='bbox 573 2648 744 2682; x_wconf 96'>high-speed,</span>
       <span class='ocrx_word' id='word_1_634' title='bbox 766 2649 772 2676; x_wconf 95'>8</span>
-      <span class='ocrx_word' id='word_1_635' title='bbox 783 2649 862 2675; x_wconf 94'>MHz</span>
+      <span class='ocrx_word' id='word_1_635' title='bbox 783 2649 862 2675; x_wconf 95'>MHz</span>
       <span class='ocrx_word' id='word_1_636' title='bbox 873 2649 954 2676; x_wconf 95'>80186</span>
       <span class='ocrx_word' id='word_1_637' title='bbox 965 2649 994 2676; x_wconf 96'>16</span>
       <span class='ocrx_word' id='word_1_638' title='bbox 1004 2648 1043 2676; x_wconf 96'>bit</span>
@@ -928,12 +928,12 @@
       <span class='ocrx_word' id='word_1_643' title='bbox 1512 2648 1664 2682; x_wconf 96'>operation.</span>
      </span>
      <span class='ocr_header' id='line_1_73' title="bbox 347 2694 2100 2727; baseline 0.001 -7; x_size 33; x_descenders 6; x_ascenders 8">
-      <span class='ocrx_word' id='word_1_644' title='bbox 347 2699 361 2713; x_wconf 52'>*</span>
+      <span class='ocrx_word' id='word_1_644' title='bbox 347 2699 361 2713; x_wconf 44'>*</span>
       <span class='ocrx_word' id='word_1_645' title='bbox 372 2694 504 2721; x_wconf 96'>TEMPO</span>
       <span class='ocrx_word' id='word_1_646' title='bbox 515 2702 578 2727; x_wconf 96'>may</span>
-      <span class='ocrx_word' id='word_1_647' title='bbox 589 2694 623 2721; x_wconf 96'>be</span>
+      <span class='ocrx_word' id='word_1_647' title='bbox 589 2694 623 2721; x_wconf 95'>be</span>
       <span class='ocrx_word' id='word_1_648' title='bbox 633 2694 764 2727; x_wconf 95'>specified</span>
-      <span class='ocrx_word' id='word_1_649' title='bbox 774 2694 802 2721; x_wconf 92'>in</span>
+      <span class='ocrx_word' id='word_1_649' title='bbox 774 2694 802 2721; x_wconf 93'>in</span>
       <span class='ocrx_word' id='word_1_650' title='bbox 814 2695 1172 2722; x_wconf 91'>BEATS-PER-MINUTE</span>
       <span class='ocrx_word' id='word_1_651' title='bbox 1183 2703 1215 2722; x_wconf 93'>or</span>
       <span class='ocrx_word' id='word_1_652' title='bbox 1225 2695 1567 2722; x_wconf 92'>FRAMES-PER-BEAT</span>
@@ -995,7 +995,7 @@
    <div class='ocr_carea' id='block_1_31' title="bbox 347 2861 1792 2940">
     <p class='ocr_par' id='par_1_39' lang='eng' title="bbox 347 2861 1792 2940">
      <span class='ocr_header' id='line_1_77' title="bbox 347 2861 1792 2895; baseline 0.001 -8; x_size 33; x_descenders 6; x_ascenders 8">
-      <span class='ocrx_word' id='word_1_687' title='bbox 347 2866 360 2880; x_wconf 62'>¢</span>
+      <span class='ocrx_word' id='word_1_687' title='bbox 347 2866 360 2880; x_wconf 59'>¢</span>
       <span class='ocrx_word' id='word_1_688' title='bbox 372 2861 504 2887; x_wconf 96'>TEMPO</span>
       <span class='ocrx_word' id='word_1_689' title='bbox 515 2861 696 2888; x_wconf 96'>CHANGES</span>
       <span class='ocrx_word' id='word_1_690' title='bbox 707 2869 771 2894; x_wconf 96'>may</span>
@@ -1011,7 +1011,7 @@
       <span class='ocrx_word' id='word_1_700' title='bbox 1679 2861 1792 2888; x_wconf 84'>desired.</span>
      </span>
      <span class='ocr_header' id='line_1_78' title="bbox 347 2906 1507 2940; baseline 0.002 -8; x_size 33; x_descenders 7; x_ascenders 8">
-      <span class='ocrx_word' id='word_1_701' title='bbox 347 2911 360 2925; x_wconf 76'>¢</span>
+      <span class='ocrx_word' id='word_1_701' title='bbox 347 2911 360 2925; x_wconf 79'>¢</span>
       <span class='ocrx_word' id='word_1_702' title='bbox 371 2906 434 2938; x_wconf 96'>Any</span>
       <span class='ocrx_word' id='word_1_703' title='bbox 444 2906 539 2932; x_wconf 96'>TIME</span>
       <span class='ocrx_word' id='word_1_704' title='bbox 550 2906 763 2933; x_wconf 96'>SIGNATURE</span>
@@ -1022,8 +1022,8 @@
       <span class='ocrx_word' id='word_1_709' title='bbox 1046 2915 1109 2940; x_wconf 96'>may</span>
       <span class='ocrx_word' id='word_1_710' title='bbox 1120 2907 1154 2934; x_wconf 96'>be</span>
       <span class='ocrx_word' id='word_1_711' title='bbox 1164 2907 1288 2940; x_wconf 96'>changed</span>
-      <span class='ocrx_word' id='word_1_712' title='bbox 1299 2907 1393 2934; x_wconf 96'>within</span>
+      <span class='ocrx_word' id='word_1_712' title='bbox 1299 2907 1393 2934; x_wconf 95'>within</span>
-      <span class='ocrx_word' id='word_1_713' title='bbox 1404 2915 1420 2934; x_wconf 96'>a</span>
+      <span class='ocrx_word' id='word_1_713' title='bbox 1404 2915 1420 2934; x_wconf 95'>a</span>
       <span class='ocrx_word' id='word_1_714' title='bbox 1431 2915 1507 2940; x_wconf 96'>song.</span>
      </span>
     </p>

tests/cache/cardinal/__-l__eng__000001_ocr.png__000001_ocr_hocr__hocr__txt/stderr.bin

@@ -1 +0,0 @@
-Tesseract Open Source OCR Engine v5.0.0-beta-20210916-12-g19cc9 with Leptonica

tests/cache/cardinal/__-l__eng__000001_ocr.png__000001_ocr_hocr__hocr__txt/txt.bin

@@ -120,4 +120,3 @@ Linn Electronics, Inc.
 
 18720 Oxnard Street, Tarzana, CA 91356
 (818) 708-8131 TELEX #298949 LINN UR
-

tests/cache/cardinal/__-l__eng__000001_ocr.png__000001_ocr_tess__pdf__txt/stderr.bin

@@ -1 +0,0 @@
-Tesseract Open Source OCR Engine v5.0.0-beta-20210916-12-g19cc9 with Leptonica

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

@@ -120,4 +120,3 @@ Linn Electronics, Inc.
 
 18720 Oxnard Street, Tarzana, CA 91356
 (818) 708-8131 TELEX #298949 LINN UR
-

tests/cache/cardinal/__-l__eng__000002_ocr.png__000002_ocr_hocr__hocr__txt/hocr.bin

@@ -5,11 +5,11 @@
  <head>
   <title></title>
   <meta http-equiv="Content-Type" content="text/html;charset=utf-8"/>
-  <meta name='ocr-system' content='tesseract 5.0.0-beta-20210916-12-g19cc9' />
+  <meta name='ocr-system' content='tesseract 5.3.2' />
   <meta name='ocr-capabilities' content='ocr_page ocr_carea ocr_par ocr_line ocrx_word ocrp_wconf'/>
  </head>
  <body>
-  <div class='ocr_page' id='page_1' title='image "/tmp/ocrmypdf.io.8je4vgpg/000002_ocr.png"; bbox 0 0 2550 3300; ppageno 0'>
+  <div class='ocr_page' id='page_1' title='image "/tmp/ocrmypdf.io.q0nk4qy2/000002_ocr.png"; bbox 0 0 2550 3300; ppageno 0; scan_res 300 300'>
    <div class='ocr_carea' id='block_1_1' title="bbox 582 131 1968 303">
     <p class='ocr_par' id='par_1_1' lang='eng' title="bbox 582 131 1968 303">
      <span class='ocr_header' id='line_1_1' title="bbox 882 131 1657 217; baseline 0.001 -17; x_size 85; x_descenders 16; x_ascenders 19">
@@ -136,9 +136,9 @@
    <div class='ocr_carea' id='block_1_5' title="bbox 349 748 2117 793">
     <p class='ocr_par' id='par_1_7' lang='eng' title="bbox 349 748 2117 793">
      <span class='ocr_header' id='line_1_10' title="bbox 349 748 2117 793; baseline 0 -9; x_size 45; x_descenders 9; x_ascenders 11">
-      <span class='ocrx_word' id='word_1_84' title='bbox 349 755 367 774; x_wconf 42'>©</span>
+      <span class='ocrx_word' id='word_1_84' title='bbox 349 755 367 774; x_wconf 50'>©</span>
-      <span class='ocrx_word' id='word_1_85' title='bbox 383 748 573 784; x_wconf 90'>Ultra-fast</span>
+      <span class='ocrx_word' id='word_1_85' title='bbox 383 748 573 784; x_wconf 91'>Ultra-fast</span>
-      <span class='ocrx_word' id='word_1_86' title='bbox 616 749 677 784; x_wconf 9'>32”</span>
+      <span class='ocrx_word' id='word_1_86' title='bbox 616 749 677 784; x_wconf 10'>32”</span>
       <span class='ocrx_word' id='word_1_87' title='bbox 694 748 775 784; x_wconf 96'>disk</span>
       <span class='ocrx_word' id='word_1_88' title='bbox 790 748 887 784; x_wconf 96'>drive</span>
       <span class='ocrx_word' id='word_1_89' title='bbox 901 754 1012 785; x_wconf 96'>stores</span>
@@ -150,7 +150,7 @@
       <span class='ocrx_word' id='word_1_95' title='bbox 1638 748 1746 784; x_wconf 96'>holds</span>
       <span class='ocrx_word' id='word_1_96' title='bbox 1761 759 1844 784; x_wconf 96'>over</span>
       <span class='ocrx_word' id='word_1_97' title='bbox 1859 749 2000 791; x_wconf 96'>110,000</span>
-      <span class='ocrx_word' id='word_1_98' title='bbox 2013 753 2117 784; x_wconf 97'>notes</span>
+      <span class='ocrx_word' id='word_1_98' title='bbox 2013 753 2117 784; x_wconf 96'>notes</span>
      </span>
     </p>
    </div>
@@ -165,13 +165,13 @@
    <div class='ocr_carea' id='block_1_7' title="bbox 349 855 2030 1016">
     <p class='ocr_par' id='par_1_9' lang='eng' title="bbox 349 855 2030 1016">
      <span class='ocr_header' id='line_1_12' title="bbox 350 855 1638 900; baseline 0.001 -9; x_size 45; x_descenders 9; x_ascenders 11">
-      <span class='ocrx_word' id='word_1_101' title='bbox 350 863 367 881; x_wconf 51'>¢</span>
+      <span class='ocrx_word' id='word_1_101' title='bbox 350 863 367 881; x_wconf 46'>¢</span>
-      <span class='ocrx_word' id='word_1_102' title='bbox 383 856 464 891; x_wconf 95'>One</span>
+      <span class='ocrx_word' id='word_1_102' title='bbox 383 856 464 891; x_wconf 96'>One</span>
       <span class='ocrx_word' id='word_1_103' title='bbox 478 866 520 891; x_wconf 95'>or</span>
       <span class='ocrx_word' id='word_1_104' title='bbox 534 855 580 891; x_wconf 96'>all</span>
       <span class='ocrx_word' id='word_1_105' title='bbox 594 856 712 892; x_wconf 95'>tracks</span>
       <span class='ocrx_word' id='word_1_106' title='bbox 726 867 811 900; x_wconf 96'>may</span>
-      <span class='ocrx_word' id='word_1_107' title='bbox 823 856 869 892; x_wconf 85'>be</span>
+      <span class='ocrx_word' id='word_1_107' title='bbox 823 856 869 892; x_wconf 84'>be</span>
       <span class='ocrx_word' id='word_1_108' title='bbox 882 856 1212 892; x_wconf 96'>TRANSPOSED</span>
       <span class='ocrx_word' id='word_1_109' title='bbox 1227 861 1264 892; x_wconf 96'>at</span>
       <span class='ocrx_word' id='word_1_110' title='bbox 1277 856 1338 892; x_wconf 96'>the</span>
@@ -256,8 +256,8 @@
    <div class='ocr_carea' id='block_1_12' title="bbox 346 1288 1239 1491">
     <p class='ocr_par' id='par_1_14' lang='eng' title="bbox 346 1288 749 1329">
      <span class='ocr_line' id='line_1_19' title="bbox 346 1288 749 1329; baseline 0.002 -9; x_size 42; x_descenders 9; x_ascenders 10">
-      <span class='ocrx_word' id='word_1_158' title='bbox 346 1288 535 1329; x_wconf 96'>Recording</span>
+      <span class='ocrx_word' id='word_1_158' title='bbox 346 1288 535 1329; x_wconf 95'>Recording</span>
-      <span class='ocrx_word' id='word_1_159' title='bbox 547 1298 567 1321; x_wconf 96'>a</span>
+      <span class='ocrx_word' id='word_1_159' title='bbox 547 1298 567 1321; x_wconf 95'>a</span>
       <span class='ocrx_word' id='word_1_160' title='bbox 579 1288 749 1328; x_wconf 96'>Sequence</span>
      </span>
     </p>
@@ -278,8 +278,8 @@
       <span class='ocrx_word' id='word_1_170' title='bbox 346 1379 411 1406; x_wconf 96'>then</span>
       <span class='ocrx_word' id='word_1_171' title='bbox 422 1378 483 1412; x_wconf 96'>play</span>
       <span class='ocrx_word' id='word_1_172' title='bbox 493 1387 562 1412; x_wconf 96'>your</span>
-      <span class='ocrx_word' id='word_1_173' title='bbox 572 1379 659 1405; x_wconf 95'>MIDI</span>
+      <span class='ocrx_word' id='word_1_173' title='bbox 572 1379 659 1405; x_wconf 96'>MIDI</span>
-      <span class='ocrx_word' id='word_1_174' title='bbox 671 1379 810 1412; x_wconf 95'>keyboard</span>
+      <span class='ocrx_word' id='word_1_174' title='bbox 671 1379 810 1412; x_wconf 96'>keyboard</span>
       <span class='ocrx_word' id='word_1_175' title='bbox 821 1379 848 1406; x_wconf 96'>in</span>
       <span class='ocrx_word' id='word_1_176' title='bbox 858 1379 923 1406; x_wconf 96'>time</span>
       <span class='ocrx_word' id='word_1_177' title='bbox 934 1384 963 1406; x_wconf 96'>to</span>
@@ -288,7 +288,7 @@
      </span>
      <span class='ocr_line' id='line_1_22' title="bbox 347 1417 1232 1452; baseline 0.002 -8; x_size 34; x_descenders 7; x_ascenders 8">
       <span class='ocrx_word' id='word_1_180' title='bbox 347 1417 414 1445; x_wconf 96'>click</span>
-      <span class='ocrx_word' id='word_1_181' title='bbox 425 1418 506 1445; x_wconf 91'>track.</span>
+      <span class='ocrx_word' id='word_1_181' title='bbox 425 1418 506 1445; x_wconf 92'>track.</span>
       <span class='ocrx_word' id='word_1_182' title='bbox 519 1418 609 1445; x_wconf 96'>When</span>
       <span class='ocrx_word' id='word_1_183' title='bbox 620 1419 665 1445; x_wconf 96'>the</span>
       <span class='ocrx_word' id='word_1_184' title='bbox 676 1426 810 1452; x_wconf 96'>sequence</span>
@@ -297,7 +297,7 @@
       <span class='ocrx_word' id='word_1_187' title='bbox 995 1419 1101 1446; x_wconf 96'>around</span>
       <span class='ocrx_word' id='word_1_188' title='bbox 1112 1423 1141 1446; x_wconf 96'>to</span>
       <span class='ocrx_word' id='word_1_189' title='bbox 1152 1419 1201 1446; x_wconf 96'>bar</span>
-      <span class='ocrx_word' id='word_1_190' title='bbox 1213 1419 1232 1450; x_wconf 88'>1,</span>
+      <span class='ocrx_word' id='word_1_190' title='bbox 1213 1419 1232 1450; x_wconf 85'>1,</span>
      </span>
      <span class='ocr_line' id='line_1_23' title="bbox 346 1457 1223 1491; baseline 0.001 -7; x_size 34; x_descenders 7; x_ascenders 8">
       <span class='ocrx_word' id='word_1_191' title='bbox 346 1457 430 1490; x_wconf 16'>you’</span>
@@ -620,7 +620,7 @@
      </span>
      <span class='ocr_line' id='line_1_50' title="bbox 1295 1565 1577 1593; baseline 0.004 -1; x_size 34.748871; x_descenders 6.7488689; x_ascenders 9">
       <span class='ocrx_word' id='word_1_423' title='bbox 1295 1565 1441 1592; x_wconf 96'>unwanted</span>
-      <span class='ocrx_word' id='word_1_424' title='bbox 1452 1565 1577 1593; x_wconf 94'>sections,</span>
+      <span class='ocrx_word' id='word_1_424' title='bbox 1452 1565 1577 1593; x_wconf 93'>sections,</span>
      </span>
     </p>
    </div>
@@ -668,8 +668,8 @@
       <span class='ocrx_word' id='word_1_454' title='bbox 1458 1768 1562 1796; x_wconf 96'>section</span>
       <span class='ocrx_word' id='word_1_455' title='bbox 1574 1769 1666 1802; x_wconf 96'>(verse,</span>
       <span class='ocrx_word' id='word_1_456' title='bbox 1679 1769 1788 1801; x_wconf 96'>chorus,</span>
-      <span class='ocrx_word' id='word_1_457' title='bbox 1800 1769 1865 1802; x_wconf 95'>etc.)</span>
+      <span class='ocrx_word' id='word_1_457' title='bbox 1800 1769 1865 1802; x_wconf 96'>etc.)</span>
-      <span class='ocrx_word' id='word_1_458' title='bbox 1876 1768 1904 1795; x_wconf 95'>in</span>
+      <span class='ocrx_word' id='word_1_458' title='bbox 1876 1768 1904 1795; x_wconf 96'>in</span>
       <span class='ocrx_word' id='word_1_459' title='bbox 1914 1768 2066 1796; x_wconf 96'>individual</span>
      </span>
      <span class='ocr_line' id='line_1_55' title="bbox 1296 1808 2215 1841; baseline 0 -6; x_size 32; x_descenders 5; x_ascenders 8">
@@ -697,7 +697,7 @@
       <span class='ocrx_word' id='word_1_477' title='bbox 1377 1887 1412 1914; x_wconf 96'>all</span>
       <span class='ocrx_word' id='word_1_478' title='bbox 1422 1887 1468 1914; x_wconf 96'>the</span>
       <span class='ocrx_word' id='word_1_479' title='bbox 1478 1891 1552 1920; x_wconf 96'>parts</span>
-      <span class='ocrx_word' id='word_1_480' title='bbox 1563 1887 1621 1914; x_wconf 96'>into</span>
+      <span class='ocrx_word' id='word_1_480' title='bbox 1563 1887 1621 1914; x_wconf 95'>into</span>
       <span class='ocrx_word' id='word_1_481' title='bbox 1632 1895 1649 1914; x_wconf 96'>a</span>
       <span class='ocrx_word' id='word_1_482' title='bbox 1659 1895 1718 1914; x_wconf 96'>new</span>
       <span class='ocrx_word' id='word_1_483' title='bbox 1729 1895 1870 1920; x_wconf 96'>sequence.</span>
@@ -829,9 +829,9 @@
    <div class='ocr_carea' id='block_1_23' title="bbox 347 2427 2145 2507">
     <p class='ocr_par' id='par_1_31' lang='eng' title="bbox 347 2427 2145 2507">
      <span class='ocr_header' id='line_1_67' title="bbox 347 2427 1468 2461; baseline 0.002 -8; x_size 34; x_descenders 7; x_ascenders 8">
-      <span class='ocrx_word' id='word_1_573' title='bbox 347 2432 361 2446; x_wconf 77'>*</span>
+      <span class='ocrx_word' id='word_1_573' title='bbox 347 2432 361 2446; x_wconf 75'>*</span>
       <span class='ocrx_word' id='word_1_574' title='bbox 373 2427 612 2454; x_wconf 91'>Non-destructive</span>
-      <span class='ocrx_word' id='word_1_575' title='bbox 622 2427 914 2461; x_wconf 84'>recording—existing</span>
+      <span class='ocrx_word' id='word_1_575' title='bbox 622 2427 914 2461; x_wconf 87'>recording—existing</span>
       <span class='ocrx_word' id='word_1_576' title='bbox 924 2432 1002 2455; x_wconf 96'>notes</span>
       <span class='ocrx_word' id='word_1_577' title='bbox 1013 2436 1057 2455; x_wconf 96'>are</span>
       <span class='ocrx_word' id='word_1_578' title='bbox 1068 2432 1116 2455; x_wconf 96'>not</span>
@@ -912,12 +912,12 @@
    <div class='ocr_carea' id='block_1_27' title="bbox 347 2648 2100 2727">
     <p class='ocr_par' id='par_1_35' lang='eng' title="bbox 347 2648 2100 2727">
      <span class='ocr_header' id='line_1_72' title="bbox 347 2648 1664 2682; baseline 0.001 -7; x_size 33; x_descenders 6; x_ascenders 8">
-      <span class='ocrx_word' id='word_1_630' title='bbox 347 2654 360 2667; x_wconf 47'>®</span>
+      <span class='ocrx_word' id='word_1_630' title='bbox 347 2654 360 2667; x_wconf 45'>®</span>
-      <span class='ocrx_word' id='word_1_631' title='bbox 372 2648 483 2675; x_wconf 96'>Utilizes</span>
+      <span class='ocrx_word' id='word_1_631' title='bbox 372 2648 483 2675; x_wconf 94'>Utilizes</span>
       <span class='ocrx_word' id='word_1_632' title='bbox 493 2648 564 2680; x_wconf 96'>ultra</span>
       <span class='ocrx_word' id='word_1_633' title='bbox 573 2648 744 2682; x_wconf 96'>high-speed,</span>
       <span class='ocrx_word' id='word_1_634' title='bbox 766 2649 772 2676; x_wconf 95'>8</span>
-      <span class='ocrx_word' id='word_1_635' title='bbox 783 2649 862 2675; x_wconf 94'>MHz</span>
+      <span class='ocrx_word' id='word_1_635' title='bbox 783 2649 862 2675; x_wconf 95'>MHz</span>
       <span class='ocrx_word' id='word_1_636' title='bbox 873 2649 954 2676; x_wconf 95'>80186</span>
       <span class='ocrx_word' id='word_1_637' title='bbox 965 2649 994 2676; x_wconf 96'>16</span>
       <span class='ocrx_word' id='word_1_638' title='bbox 1004 2648 1043 2676; x_wconf 96'>bit</span>
@@ -928,12 +928,12 @@
       <span class='ocrx_word' id='word_1_643' title='bbox 1512 2648 1664 2682; x_wconf 96'>operation.</span>
      </span>
      <span class='ocr_header' id='line_1_73' title="bbox 347 2694 2100 2727; baseline 0.001 -7; x_size 33; x_descenders 6; x_ascenders 8">
-      <span class='ocrx_word' id='word_1_644' title='bbox 347 2699 361 2713; x_wconf 52'>*</span>
+      <span class='ocrx_word' id='word_1_644' title='bbox 347 2699 361 2713; x_wconf 44'>*</span>
       <span class='ocrx_word' id='word_1_645' title='bbox 372 2694 504 2721; x_wconf 96'>TEMPO</span>
       <span class='ocrx_word' id='word_1_646' title='bbox 515 2702 578 2727; x_wconf 96'>may</span>
-      <span class='ocrx_word' id='word_1_647' title='bbox 589 2694 623 2721; x_wconf 96'>be</span>
+      <span class='ocrx_word' id='word_1_647' title='bbox 589 2694 623 2721; x_wconf 95'>be</span>
       <span class='ocrx_word' id='word_1_648' title='bbox 633 2694 764 2727; x_wconf 95'>specified</span>
-      <span class='ocrx_word' id='word_1_649' title='bbox 774 2694 802 2721; x_wconf 92'>in</span>
+      <span class='ocrx_word' id='word_1_649' title='bbox 774 2694 802 2721; x_wconf 93'>in</span>
       <span class='ocrx_word' id='word_1_650' title='bbox 814 2695 1172 2722; x_wconf 91'>BEATS-PER-MINUTE</span>
       <span class='ocrx_word' id='word_1_651' title='bbox 1183 2703 1215 2722; x_wconf 93'>or</span>
       <span class='ocrx_word' id='word_1_652' title='bbox 1225 2695 1567 2722; x_wconf 92'>FRAMES-PER-BEAT</span>
@@ -995,7 +995,7 @@
    <div class='ocr_carea' id='block_1_31' title="bbox 347 2861 1792 2940">
     <p class='ocr_par' id='par_1_39' lang='eng' title="bbox 347 2861 1792 2940">
      <span class='ocr_header' id='line_1_77' title="bbox 347 2861 1792 2895; baseline 0.001 -8; x_size 33; x_descenders 6; x_ascenders 8">
-      <span class='ocrx_word' id='word_1_687' title='bbox 347 2866 360 2880; x_wconf 62'>¢</span>
+      <span class='ocrx_word' id='word_1_687' title='bbox 347 2866 360 2880; x_wconf 59'>¢</span>
       <span class='ocrx_word' id='word_1_688' title='bbox 372 2861 504 2887; x_wconf 96'>TEMPO</span>
       <span class='ocrx_word' id='word_1_689' title='bbox 515 2861 696 2888; x_wconf 96'>CHANGES</span>
       <span class='ocrx_word' id='word_1_690' title='bbox 707 2869 771 2894; x_wconf 96'>may</span>
@@ -1011,7 +1011,7 @@
       <span class='ocrx_word' id='word_1_700' title='bbox 1679 2861 1792 2888; x_wconf 84'>desired.</span>
      </span>
      <span class='ocr_header' id='line_1_78' title="bbox 347 2906 1507 2940; baseline 0.002 -8; x_size 33; x_descenders 7; x_ascenders 8">
-      <span class='ocrx_word' id='word_1_701' title='bbox 347 2911 360 2925; x_wconf 76'>¢</span>
+      <span class='ocrx_word' id='word_1_701' title='bbox 347 2911 360 2925; x_wconf 79'>¢</span>
       <span class='ocrx_word' id='word_1_702' title='bbox 371 2906 434 2938; x_wconf 96'>Any</span>
       <span class='ocrx_word' id='word_1_703' title='bbox 444 2906 539 2932; x_wconf 96'>TIME</span>
       <span class='ocrx_word' id='word_1_704' title='bbox 550 2906 763 2933; x_wconf 96'>SIGNATURE</span>
@@ -1022,8 +1022,8 @@
       <span class='ocrx_word' id='word_1_709' title='bbox 1046 2915 1109 2940; x_wconf 96'>may</span>
       <span class='ocrx_word' id='word_1_710' title='bbox 1120 2907 1154 2934; x_wconf 96'>be</span>
       <span class='ocrx_word' id='word_1_711' title='bbox 1164 2907 1288 2940; x_wconf 96'>changed</span>
-      <span class='ocrx_word' id='word_1_712' title='bbox 1299 2907 1393 2934; x_wconf 96'>within</span>
+      <span class='ocrx_word' id='word_1_712' title='bbox 1299 2907 1393 2934; x_wconf 95'>within</span>
-      <span class='ocrx_word' id='word_1_713' title='bbox 1404 2915 1420 2934; x_wconf 96'>a</span>
+      <span class='ocrx_word' id='word_1_713' title='bbox 1404 2915 1420 2934; x_wconf 95'>a</span>
       <span class='ocrx_word' id='word_1_714' title='bbox 1431 2915 1507 2940; x_wconf 96'>song.</span>
      </span>
     </p>

tests/cache/cardinal/__-l__eng__000002_ocr.png__000002_ocr_hocr__hocr__txt/stderr.bin

@@ -1 +0,0 @@
-Tesseract Open Source OCR Engine v5.0.0-beta-20210916-12-g19cc9 with Leptonica

tests/cache/cardinal/__-l__eng__000002_ocr.png__000002_ocr_hocr__hocr__txt/txt.bin

@@ -120,4 +120,3 @@ Linn Electronics, Inc.
 
 18720 Oxnard Street, Tarzana, CA 91356
 (818) 708-8131 TELEX #298949 LINN UR
-

tests/cache/cardinal/__-l__eng__000002_ocr.png__000002_ocr_tess__pdf__txt/stderr.bin

@@ -1 +0,0 @@
-Tesseract Open Source OCR Engine v5.0.0-beta-20210916-12-g19cc9 with Leptonica

tests/cache/cardinal/__-l__eng__000002_ocr.png__000002_ocr_tess__pdf__txt/txt.bin

@@ -120,4 +120,3 @@ Linn Electronics, Inc.
 
 18720 Oxnard Street, Tarzana, CA 91356
 (818) 708-8131 TELEX #298949 LINN UR
-

tests/cache/cardinal/__-l__eng__000003_ocr.png__000003_ocr_hocr__hocr__txt/hocr.bin

@@ -5,11 +5,11 @@
  <head>
   <title></title>
   <meta http-equiv="Content-Type" content="text/html;charset=utf-8"/>
-  <meta name='ocr-system' content='tesseract 5.0.0-beta-20210916-12-g19cc9' />
+  <meta name='ocr-system' content='tesseract 5.3.2' />
   <meta name='ocr-capabilities' content='ocr_page ocr_carea ocr_par ocr_line ocrx_word ocrp_wconf'/>
  </head>
  <body>
-  <div class='ocr_page' id='page_1' title='image "/tmp/ocrmypdf.io.8je4vgpg/000003_ocr.png"; bbox 0 0 2550 3300; ppageno 0'>
+  <div class='ocr_page' id='page_1' title='image "/tmp/ocrmypdf.io.q0nk4qy2/000003_ocr.png"; bbox 0 0 2550 3300; ppageno 0; scan_res 300 300'>
    <div class='ocr_carea' id='block_1_1' title="bbox 582 131 1968 303">
     <p class='ocr_par' id='par_1_1' lang='eng' title="bbox 582 131 1968 303">
      <span class='ocr_header' id='line_1_1' title="bbox 882 131 1657 217; baseline 0.001 -17; x_size 85; x_descenders 16; x_ascenders 19">
@@ -136,9 +136,9 @@
    <div class='ocr_carea' id='block_1_5' title="bbox 349 748 2117 793">
     <p class='ocr_par' id='par_1_7' lang='eng' title="bbox 349 748 2117 793">
      <span class='ocr_header' id='line_1_10' title="bbox 349 748 2117 793; baseline 0 -9; x_size 45; x_descenders 9; x_ascenders 11">
-      <span class='ocrx_word' id='word_1_84' title='bbox 349 755 367 774; x_wconf 42'>©</span>
+      <span class='ocrx_word' id='word_1_84' title='bbox 349 755 367 774; x_wconf 50'>©</span>
-      <span class='ocrx_word' id='word_1_85' title='bbox 383 748 573 784; x_wconf 90'>Ultra-fast</span>
+      <span class='ocrx_word' id='word_1_85' title='bbox 383 748 573 784; x_wconf 91'>Ultra-fast</span>
-      <span class='ocrx_word' id='word_1_86' title='bbox 616 749 677 784; x_wconf 9'>32”</span>
+      <span class='ocrx_word' id='word_1_86' title='bbox 616 749 677 784; x_wconf 10'>32”</span>
       <span class='ocrx_word' id='word_1_87' title='bbox 694 748 775 784; x_wconf 96'>disk</span>
       <span class='ocrx_word' id='word_1_88' title='bbox 790 748 887 784; x_wconf 96'>drive</span>
       <span class='ocrx_word' id='word_1_89' title='bbox 901 754 1012 785; x_wconf 96'>stores</span>
@@ -150,7 +150,7 @@
       <span class='ocrx_word' id='word_1_95' title='bbox 1638 748 1746 784; x_wconf 96'>holds</span>
       <span class='ocrx_word' id='word_1_96' title='bbox 1761 759 1844 784; x_wconf 96'>over</span>
       <span class='ocrx_word' id='word_1_97' title='bbox 1859 749 2000 791; x_wconf 96'>110,000</span>
-      <span class='ocrx_word' id='word_1_98' title='bbox 2013 753 2117 784; x_wconf 97'>notes</span>
+      <span class='ocrx_word' id='word_1_98' title='bbox 2013 753 2117 784; x_wconf 96'>notes</span>
      </span>
     </p>
    </div>
@@ -165,13 +165,13 @@
    <div class='ocr_carea' id='block_1_7' title="bbox 349 855 2030 1016">
     <p class='ocr_par' id='par_1_9' lang='eng' title="bbox 349 855 2030 1016">
      <span class='ocr_header' id='line_1_12' title="bbox 350 855 1638 900; baseline 0.001 -9; x_size 45; x_descenders 9; x_ascenders 11">
-      <span class='ocrx_word' id='word_1_101' title='bbox 350 863 367 881; x_wconf 51'>¢</span>
+      <span class='ocrx_word' id='word_1_101' title='bbox 350 863 367 881; x_wconf 46'>¢</span>
-      <span class='ocrx_word' id='word_1_102' title='bbox 383 856 464 891; x_wconf 95'>One</span>
+      <span class='ocrx_word' id='word_1_102' title='bbox 383 856 464 891; x_wconf 96'>One</span>
       <span class='ocrx_word' id='word_1_103' title='bbox 478 866 520 891; x_wconf 95'>or</span>
       <span class='ocrx_word' id='word_1_104' title='bbox 534 855 580 891; x_wconf 96'>all</span>
       <span class='ocrx_word' id='word_1_105' title='bbox 594 856 712 892; x_wconf 95'>tracks</span>
       <span class='ocrx_word' id='word_1_106' title='bbox 726 867 811 900; x_wconf 96'>may</span>
-      <span class='ocrx_word' id='word_1_107' title='bbox 823 856 869 892; x_wconf 85'>be</span>
+      <span class='ocrx_word' id='word_1_107' title='bbox 823 856 869 892; x_wconf 84'>be</span>
       <span class='ocrx_word' id='word_1_108' title='bbox 882 856 1212 892; x_wconf 96'>TRANSPOSED</span>
       <span class='ocrx_word' id='word_1_109' title='bbox 1227 861 1264 892; x_wconf 96'>at</span>
       <span class='ocrx_word' id='word_1_110' title='bbox 1277 856 1338 892; x_wconf 96'>the</span>
@@ -256,8 +256,8 @@
    <div class='ocr_carea' id='block_1_12' title="bbox 346 1288 1239 1491">
     <p class='ocr_par' id='par_1_14' lang='eng' title="bbox 346 1288 749 1329">
      <span class='ocr_line' id='line_1_19' title="bbox 346 1288 749 1329; baseline 0.002 -9; x_size 42; x_descenders 9; x_ascenders 10">
-      <span class='ocrx_word' id='word_1_158' title='bbox 346 1288 535 1329; x_wconf 96'>Recording</span>
+      <span class='ocrx_word' id='word_1_158' title='bbox 346 1288 535 1329; x_wconf 95'>Recording</span>
-      <span class='ocrx_word' id='word_1_159' title='bbox 547 1298 567 1321; x_wconf 96'>a</span>
+      <span class='ocrx_word' id='word_1_159' title='bbox 547 1298 567 1321; x_wconf 95'>a</span>
       <span class='ocrx_word' id='word_1_160' title='bbox 579 1288 749 1328; x_wconf 96'>Sequence</span>
      </span>
     </p>
@@ -278,8 +278,8 @@
       <span class='ocrx_word' id='word_1_170' title='bbox 346 1379 411 1406; x_wconf 96'>then</span>
       <span class='ocrx_word' id='word_1_171' title='bbox 422 1378 483 1412; x_wconf 96'>play</span>
       <span class='ocrx_word' id='word_1_172' title='bbox 493 1387 562 1412; x_wconf 96'>your</span>
-      <span class='ocrx_word' id='word_1_173' title='bbox 572 1379 659 1405; x_wconf 95'>MIDI</span>
+      <span class='ocrx_word' id='word_1_173' title='bbox 572 1379 659 1405; x_wconf 96'>MIDI</span>
-      <span class='ocrx_word' id='word_1_174' title='bbox 671 1379 810 1412; x_wconf 95'>keyboard</span>
+      <span class='ocrx_word' id='word_1_174' title='bbox 671 1379 810 1412; x_wconf 96'>keyboard</span>
       <span class='ocrx_word' id='word_1_175' title='bbox 821 1379 848 1406; x_wconf 96'>in</span>
       <span class='ocrx_word' id='word_1_176' title='bbox 858 1379 923 1406; x_wconf 96'>time</span>
       <span class='ocrx_word' id='word_1_177' title='bbox 934 1384 963 1406; x_wconf 96'>to</span>
@@ -288,7 +288,7 @@
      </span>
      <span class='ocr_line' id='line_1_22' title="bbox 347 1417 1232 1452; baseline 0.002 -8; x_size 34; x_descenders 7; x_ascenders 8">
       <span class='ocrx_word' id='word_1_180' title='bbox 347 1417 414 1445; x_wconf 96'>click</span>
-      <span class='ocrx_word' id='word_1_181' title='bbox 425 1418 506 1445; x_wconf 91'>track.</span>
+      <span class='ocrx_word' id='word_1_181' title='bbox 425 1418 506 1445; x_wconf 92'>track.</span>
       <span class='ocrx_word' id='word_1_182' title='bbox 519 1418 609 1445; x_wconf 96'>When</span>
       <span class='ocrx_word' id='word_1_183' title='bbox 620 1419 665 1445; x_wconf 96'>the</span>
       <span class='ocrx_word' id='word_1_184' title='bbox 676 1426 810 1452; x_wconf 96'>sequence</span>
@@ -297,7 +297,7 @@
       <span class='ocrx_word' id='word_1_187' title='bbox 995 1419 1101 1446; x_wconf 96'>around</span>
       <span class='ocrx_word' id='word_1_188' title='bbox 1112 1423 1141 1446; x_wconf 96'>to</span>
       <span class='ocrx_word' id='word_1_189' title='bbox 1152 1419 1201 1446; x_wconf 96'>bar</span>
-      <span class='ocrx_word' id='word_1_190' title='bbox 1213 1419 1232 1450; x_wconf 88'>1,</span>
+      <span class='ocrx_word' id='word_1_190' title='bbox 1213 1419 1232 1450; x_wconf 85'>1,</span>
      </span>
      <span class='ocr_line' id='line_1_23' title="bbox 346 1457 1223 1491; baseline 0.001 -7; x_size 34; x_descenders 7; x_ascenders 8">
       <span class='ocrx_word' id='word_1_191' title='bbox 346 1457 430 1490; x_wconf 16'>you’</span>
@@ -620,7 +620,7 @@
      </span>
      <span class='ocr_line' id='line_1_50' title="bbox 1295 1565 1577 1593; baseline 0.004 -1; x_size 34.748871; x_descenders 6.7488689; x_ascenders 9">
       <span class='ocrx_word' id='word_1_423' title='bbox 1295 1565 1441 1592; x_wconf 96'>unwanted</span>
-      <span class='ocrx_word' id='word_1_424' title='bbox 1452 1565 1577 1593; x_wconf 94'>sections,</span>
+      <span class='ocrx_word' id='word_1_424' title='bbox 1452 1565 1577 1593; x_wconf 93'>sections,</span>
      </span>
     </p>
    </div>
@@ -668,8 +668,8 @@
       <span class='ocrx_word' id='word_1_454' title='bbox 1458 1768 1562 1796; x_wconf 96'>section</span>
       <span class='ocrx_word' id='word_1_455' title='bbox 1574 1769 1666 1802; x_wconf 96'>(verse,</span>
       <span class='ocrx_word' id='word_1_456' title='bbox 1679 1769 1788 1801; x_wconf 96'>chorus,</span>
-      <span class='ocrx_word' id='word_1_457' title='bbox 1800 1769 1865 1802; x_wconf 95'>etc.)</span>
+      <span class='ocrx_word' id='word_1_457' title='bbox 1800 1769 1865 1802; x_wconf 96'>etc.)</span>
-      <span class='ocrx_word' id='word_1_458' title='bbox 1876 1768 1904 1795; x_wconf 95'>in</span>
+      <span class='ocrx_word' id='word_1_458' title='bbox 1876 1768 1904 1795; x_wconf 96'>in</span>
       <span class='ocrx_word' id='word_1_459' title='bbox 1914 1768 2066 1796; x_wconf 96'>individual</span>
      </span>
      <span class='ocr_line' id='line_1_55' title="bbox 1296 1808 2215 1841; baseline 0 -6; x_size 32; x_descenders 5; x_ascenders 8">
@@ -697,7 +697,7 @@
       <span class='ocrx_word' id='word_1_477' title='bbox 1377 1887 1412 1914; x_wconf 96'>all</span>
       <span class='ocrx_word' id='word_1_478' title='bbox 1422 1887 1468 1914; x_wconf 96'>the</span>
       <span class='ocrx_word' id='word_1_479' title='bbox 1478 1891 1552 1920; x_wconf 96'>parts</span>
-      <span class='ocrx_word' id='word_1_480' title='bbox 1563 1887 1621 1914; x_wconf 96'>into</span>
+      <span class='ocrx_word' id='word_1_480' title='bbox 1563 1887 1621 1914; x_wconf 95'>into</span>
       <span class='ocrx_word' id='word_1_481' title='bbox 1632 1895 1649 1914; x_wconf 96'>a</span>
       <span class='ocrx_word' id='word_1_482' title='bbox 1659 1895 1718 1914; x_wconf 96'>new</span>
       <span class='ocrx_word' id='word_1_483' title='bbox 1729 1895 1870 1920; x_wconf 96'>sequence.</span>
@@ -829,9 +829,9 @@
    <div class='ocr_carea' id='block_1_23' title="bbox 347 2427 2145 2507">
     <p class='ocr_par' id='par_1_31' lang='eng' title="bbox 347 2427 2145 2507">
      <span class='ocr_header' id='line_1_67' title="bbox 347 2427 1468 2461; baseline 0.002 -8; x_size 34; x_descenders 7; x_ascenders 8">
-      <span class='ocrx_word' id='word_1_573' title='bbox 347 2432 361 2446; x_wconf 77'>*</span>
+      <span class='ocrx_word' id='word_1_573' title='bbox 347 2432 361 2446; x_wconf 75'>*</span>
       <span class='ocrx_word' id='word_1_574' title='bbox 373 2427 612 2454; x_wconf 91'>Non-destructive</span>
-      <span class='ocrx_word' id='word_1_575' title='bbox 622 2427 914 2461; x_wconf 84'>recording—existing</span>
+      <span class='ocrx_word' id='word_1_575' title='bbox 622 2427 914 2461; x_wconf 87'>recording—existing</span>
       <span class='ocrx_word' id='word_1_576' title='bbox 924 2432 1002 2455; x_wconf 96'>notes</span>
       <span class='ocrx_word' id='word_1_577' title='bbox 1013 2436 1057 2455; x_wconf 96'>are</span>
       <span class='ocrx_word' id='word_1_578' title='bbox 1068 2432 1116 2455; x_wconf 96'>not</span>
@@ -912,12 +912,12 @@
    <div class='ocr_carea' id='block_1_27' title="bbox 347 2648 2100 2727">
     <p class='ocr_par' id='par_1_35' lang='eng' title="bbox 347 2648 2100 2727">
      <span class='ocr_header' id='line_1_72' title="bbox 347 2648 1664 2682; baseline 0.001 -7; x_size 33; x_descenders 6; x_ascenders 8">
-      <span class='ocrx_word' id='word_1_630' title='bbox 347 2654 360 2667; x_wconf 47'>®</span>
+      <span class='ocrx_word' id='word_1_630' title='bbox 347 2654 360 2667; x_wconf 45'>®</span>
-      <span class='ocrx_word' id='word_1_631' title='bbox 372 2648 483 2675; x_wconf 96'>Utilizes</span>
+      <span class='ocrx_word' id='word_1_631' title='bbox 372 2648 483 2675; x_wconf 94'>Utilizes</span>
       <span class='ocrx_word' id='word_1_632' title='bbox 493 2648 564 2680; x_wconf 96'>ultra</span>
       <span class='ocrx_word' id='word_1_633' title='bbox 573 2648 744 2682; x_wconf 96'>high-speed,</span>
       <span class='ocrx_word' id='word_1_634' title='bbox 766 2649 772 2676; x_wconf 95'>8</span>
-      <span class='ocrx_word' id='word_1_635' title='bbox 783 2649 862 2675; x_wconf 94'>MHz</span>
+      <span class='ocrx_word' id='word_1_635' title='bbox 783 2649 862 2675; x_wconf 95'>MHz</span>
       <span class='ocrx_word' id='word_1_636' title='bbox 873 2649 954 2676; x_wconf 95'>80186</span>
       <span class='ocrx_word' id='word_1_637' title='bbox 965 2649 994 2676; x_wconf 96'>16</span>
       <span class='ocrx_word' id='word_1_638' title='bbox 1004 2648 1043 2676; x_wconf 96'>bit</span>
@@ -928,12 +928,12 @@
       <span class='ocrx_word' id='word_1_643' title='bbox 1512 2648 1664 2682; x_wconf 96'>operation.</span>
      </span>
      <span class='ocr_header' id='line_1_73' title="bbox 347 2694 2100 2727; baseline 0.001 -7; x_size 33; x_descenders 6; x_ascenders 8">
-      <span class='ocrx_word' id='word_1_644' title='bbox 347 2699 361 2713; x_wconf 52'>*</span>
+      <span class='ocrx_word' id='word_1_644' title='bbox 347 2699 361 2713; x_wconf 44'>*</span>
       <span class='ocrx_word' id='word_1_645' title='bbox 372 2694 504 2721; x_wconf 96'>TEMPO</span>
       <span class='ocrx_word' id='word_1_646' title='bbox 515 2702 578 2727; x_wconf 96'>may</span>
-      <span class='ocrx_word' id='word_1_647' title='bbox 589 2694 623 2721; x_wconf 96'>be</span>
+      <span class='ocrx_word' id='word_1_647' title='bbox 589 2694 623 2721; x_wconf 95'>be</span>
       <span class='ocrx_word' id='word_1_648' title='bbox 633 2694 764 2727; x_wconf 95'>specified</span>
-      <span class='ocrx_word' id='word_1_649' title='bbox 774 2694 802 2721; x_wconf 92'>in</span>
+      <span class='ocrx_word' id='word_1_649' title='bbox 774 2694 802 2721; x_wconf 93'>in</span>
       <span class='ocrx_word' id='word_1_650' title='bbox 814 2695 1172 2722; x_wconf 91'>BEATS-PER-MINUTE</span>
       <span class='ocrx_word' id='word_1_651' title='bbox 1183 2703 1215 2722; x_wconf 93'>or</span>
       <span class='ocrx_word' id='word_1_652' title='bbox 1225 2695 1567 2722; x_wconf 92'>FRAMES-PER-BEAT</span>
@@ -995,7 +995,7 @@
    <div class='ocr_carea' id='block_1_31' title="bbox 347 2861 1792 2940">
     <p class='ocr_par' id='par_1_39' lang='eng' title="bbox 347 2861 1792 2940">
      <span class='ocr_header' id='line_1_77' title="bbox 347 2861 1792 2895; baseline 0.001 -8; x_size 33; x_descenders 6; x_ascenders 8">
-      <span class='ocrx_word' id='word_1_687' title='bbox 347 2866 360 2880; x_wconf 62'>¢</span>
+      <span class='ocrx_word' id='word_1_687' title='bbox 347 2866 360 2880; x_wconf 59'>¢</span>
       <span class='ocrx_word' id='word_1_688' title='bbox 372 2861 504 2887; x_wconf 96'>TEMPO</span>
       <span class='ocrx_word' id='word_1_689' title='bbox 515 2861 696 2888; x_wconf 96'>CHANGES</span>
       <span class='ocrx_word' id='word_1_690' title='bbox 707 2869 771 2894; x_wconf 96'>may</span>
@@ -1011,7 +1011,7 @@
       <span class='ocrx_word' id='word_1_700' title='bbox 1679 2861 1792 2888; x_wconf 84'>desired.</span>
      </span>
      <span class='ocr_header' id='line_1_78' title="bbox 347 2906 1507 2940; baseline 0.002 -8; x_size 33; x_descenders 7; x_ascenders 8">
-      <span class='ocrx_word' id='word_1_701' title='bbox 347 2911 360 2925; x_wconf 76'>¢</span>
+      <span class='ocrx_word' id='word_1_701' title='bbox 347 2911 360 2925; x_wconf 79'>¢</span>
       <span class='ocrx_word' id='word_1_702' title='bbox 371 2906 434 2938; x_wconf 96'>Any</span>
       <span class='ocrx_word' id='word_1_703' title='bbox 444 2906 539 2932; x_wconf 96'>TIME</span>
       <span class='ocrx_word' id='word_1_704' title='bbox 550 2906 763 2933; x_wconf 96'>SIGNATURE</span>
@@ -1022,8 +1022,8 @@
       <span class='ocrx_word' id='word_1_709' title='bbox 1046 2915 1109 2940; x_wconf 96'>may</span>
       <span class='ocrx_word' id='word_1_710' title='bbox 1120 2907 1154 2934; x_wconf 96'>be</span>
       <span class='ocrx_word' id='word_1_711' title='bbox 1164 2907 1288 2940; x_wconf 96'>changed</span>
-      <span class='ocrx_word' id='word_1_712' title='bbox 1299 2907 1393 2934; x_wconf 96'>within</span>
+      <span class='ocrx_word' id='word_1_712' title='bbox 1299 2907 1393 2934; x_wconf 95'>within</span>
-      <span class='ocrx_word' id='word_1_713' title='bbox 1404 2915 1420 2934; x_wconf 96'>a</span>
+      <span class='ocrx_word' id='word_1_713' title='bbox 1404 2915 1420 2934; x_wconf 95'>a</span>
       <span class='ocrx_word' id='word_1_714' title='bbox 1431 2915 1507 2940; x_wconf 96'>song.</span>
      </span>
     </p>

tests/cache/cardinal/__-l__eng__000003_ocr.png__000003_ocr_hocr__hocr__txt/stderr.bin

@@ -1 +0,0 @@
-Tesseract Open Source OCR Engine v5.0.0-beta-20210916-12-g19cc9 with Leptonica

tests/cache/cardinal/__-l__eng__000003_ocr.png__000003_ocr_hocr__hocr__txt/txt.bin

@@ -120,4 +120,3 @@ Linn Electronics, Inc.
 
 18720 Oxnard Street, Tarzana, CA 91356
 (818) 708-8131 TELEX #298949 LINN UR
-

tests/cache/cardinal/__-l__eng__000003_ocr.png__000003_ocr_tess__pdf__txt/stderr.bin

@@ -1 +0,0 @@
-Tesseract Open Source OCR Engine v5.0.0-beta-20210916-12-g19cc9 with Leptonica

tests/cache/cardinal/__-l__eng__000003_ocr.png__000003_ocr_tess__pdf__txt/txt.bin

@@ -120,4 +120,3 @@ Linn Electronics, Inc.
 
 18720 Oxnard Street, Tarzana, CA 91356
 (818) 708-8131 TELEX #298949 LINN UR
-

tests/cache/cardinal/__-l__eng__000004_ocr.png__000004_ocr_hocr__hocr__txt/hocr.bin

@@ -5,11 +5,11 @@
  <head>
   <title></title>
   <meta http-equiv="Content-Type" content="text/html;charset=utf-8"/>
-  <meta name='ocr-system' content='tesseract 5.0.0-beta-20210916-12-g19cc9' />
+  <meta name='ocr-system' content='tesseract 5.3.2' />
   <meta name='ocr-capabilities' content='ocr_page ocr_carea ocr_par ocr_line ocrx_word ocrp_wconf'/>
  </head>
  <body>
-  <div class='ocr_page' id='page_1' title='image "/tmp/ocrmypdf.io.8je4vgpg/000004_ocr.png"; bbox 0 0 2550 3300; ppageno 0'>
+  <div class='ocr_page' id='page_1' title='image "/tmp/ocrmypdf.io.q0nk4qy2/000004_ocr.png"; bbox 0 0 2550 3300; ppageno 0; scan_res 300 300'>
    <div class='ocr_carea' id='block_1_1' title="bbox 582 131 1968 303">
     <p class='ocr_par' id='par_1_1' lang='eng' title="bbox 582 131 1968 303">
      <span class='ocr_header' id='line_1_1' title="bbox 882 131 1657 217; baseline 0.001 -17; x_size 85; x_descenders 16; x_ascenders 19">
@@ -136,9 +136,9 @@
    <div class='ocr_carea' id='block_1_5' title="bbox 349 748 2117 793">
     <p class='ocr_par' id='par_1_7' lang='eng' title="bbox 349 748 2117 793">
      <span class='ocr_header' id='line_1_10' title="bbox 349 748 2117 793; baseline 0 -9; x_size 45; x_descenders 9; x_ascenders 11">
-      <span class='ocrx_word' id='word_1_84' title='bbox 349 755 367 774; x_wconf 42'>©</span>
+      <span class='ocrx_word' id='word_1_84' title='bbox 349 755 367 774; x_wconf 50'>©</span>
-      <span class='ocrx_word' id='word_1_85' title='bbox 383 748 573 784; x_wconf 90'>Ultra-fast</span>
+      <span class='ocrx_word' id='word_1_85' title='bbox 383 748 573 784; x_wconf 91'>Ultra-fast</span>
-      <span class='ocrx_word' id='word_1_86' title='bbox 616 749 677 784; x_wconf 9'>32”</span>
+      <span class='ocrx_word' id='word_1_86' title='bbox 616 749 677 784; x_wconf 10'>32”</span>
       <span class='ocrx_word' id='word_1_87' title='bbox 694 748 775 784; x_wconf 96'>disk</span>
       <span class='ocrx_word' id='word_1_88' title='bbox 790 748 887 784; x_wconf 96'>drive</span>
       <span class='ocrx_word' id='word_1_89' title='bbox 901 754 1012 785; x_wconf 96'>stores</span>
@@ -150,7 +150,7 @@
       <span class='ocrx_word' id='word_1_95' title='bbox 1638 748 1746 784; x_wconf 96'>holds</span>
       <span class='ocrx_word' id='word_1_96' title='bbox 1761 759 1844 784; x_wconf 96'>over</span>
       <span class='ocrx_word' id='word_1_97' title='bbox 1859 749 2000 791; x_wconf 96'>110,000</span>
-      <span class='ocrx_word' id='word_1_98' title='bbox 2013 753 2117 784; x_wconf 97'>notes</span>
+      <span class='ocrx_word' id='word_1_98' title='bbox 2013 753 2117 784; x_wconf 96'>notes</span>
      </span>
     </p>
    </div>
@@ -165,13 +165,13 @@
    <div class='ocr_carea' id='block_1_7' title="bbox 349 855 2030 1016">
     <p class='ocr_par' id='par_1_9' lang='eng' title="bbox 349 855 2030 1016">
      <span class='ocr_header' id='line_1_12' title="bbox 350 855 1638 900; baseline 0.001 -9; x_size 45; x_descenders 9; x_ascenders 11">
-      <span class='ocrx_word' id='word_1_101' title='bbox 350 863 367 881; x_wconf 51'>¢</span>
+      <span class='ocrx_word' id='word_1_101' title='bbox 350 863 367 881; x_wconf 46'>¢</span>
-      <span class='ocrx_word' id='word_1_102' title='bbox 383 856 464 891; x_wconf 95'>One</span>
+      <span class='ocrx_word' id='word_1_102' title='bbox 383 856 464 891; x_wconf 96'>One</span>
       <span class='ocrx_word' id='word_1_103' title='bbox 478 866 520 891; x_wconf 95'>or</span>
       <span class='ocrx_word' id='word_1_104' title='bbox 534 855 580 891; x_wconf 96'>all</span>
       <span class='ocrx_word' id='word_1_105' title='bbox 594 856 712 892; x_wconf 95'>tracks</span>
       <span class='ocrx_word' id='word_1_106' title='bbox 726 867 811 900; x_wconf 96'>may</span>
-      <span class='ocrx_word' id='word_1_107' title='bbox 823 856 869 892; x_wconf 85'>be</span>
+      <span class='ocrx_word' id='word_1_107' title='bbox 823 856 869 892; x_wconf 84'>be</span>
       <span class='ocrx_word' id='word_1_108' title='bbox 882 856 1212 892; x_wconf 96'>TRANSPOSED</span>
       <span class='ocrx_word' id='word_1_109' title='bbox 1227 861 1264 892; x_wconf 96'>at</span>
       <span class='ocrx_word' id='word_1_110' title='bbox 1277 856 1338 892; x_wconf 96'>the</span>
@@ -256,8 +256,8 @@
    <div class='ocr_carea' id='block_1_12' title="bbox 346 1288 1239 1491">
     <p class='ocr_par' id='par_1_14' lang='eng' title="bbox 346 1288 749 1329">
      <span class='ocr_line' id='line_1_19' title="bbox 346 1288 749 1329; baseline 0.002 -9; x_size 42; x_descenders 9; x_ascenders 10">
-      <span class='ocrx_word' id='word_1_158' title='bbox 346 1288 535 1329; x_wconf 96'>Recording</span>
+      <span class='ocrx_word' id='word_1_158' title='bbox 346 1288 535 1329; x_wconf 95'>Recording</span>
-      <span class='ocrx_word' id='word_1_159' title='bbox 547 1298 567 1321; x_wconf 96'>a</span>
+      <span class='ocrx_word' id='word_1_159' title='bbox 547 1298 567 1321; x_wconf 95'>a</span>
       <span class='ocrx_word' id='word_1_160' title='bbox 579 1288 749 1328; x_wconf 96'>Sequence</span>
      </span>
     </p>
@@ -278,8 +278,8 @@
       <span class='ocrx_word' id='word_1_170' title='bbox 346 1379 411 1406; x_wconf 96'>then</span>
       <span class='ocrx_word' id='word_1_171' title='bbox 422 1378 483 1412; x_wconf 96'>play</span>
       <span class='ocrx_word' id='word_1_172' title='bbox 493 1387 562 1412; x_wconf 96'>your</span>
-      <span class='ocrx_word' id='word_1_173' title='bbox 572 1379 659 1405; x_wconf 95'>MIDI</span>
+      <span class='ocrx_word' id='word_1_173' title='bbox 572 1379 659 1405; x_wconf 96'>MIDI</span>
-      <span class='ocrx_word' id='word_1_174' title='bbox 671 1379 810 1412; x_wconf 95'>keyboard</span>
+      <span class='ocrx_word' id='word_1_174' title='bbox 671 1379 810 1412; x_wconf 96'>keyboard</span>
       <span class='ocrx_word' id='word_1_175' title='bbox 821 1379 848 1406; x_wconf 96'>in</span>
       <span class='ocrx_word' id='word_1_176' title='bbox 858 1379 923 1406; x_wconf 96'>time</span>
       <span class='ocrx_word' id='word_1_177' title='bbox 934 1384 963 1406; x_wconf 96'>to</span>
@@ -288,7 +288,7 @@
      </span>
      <span class='ocr_line' id='line_1_22' title="bbox 347 1417 1232 1452; baseline 0.002 -8; x_size 34; x_descenders 7; x_ascenders 8">
       <span class='ocrx_word' id='word_1_180' title='bbox 347 1417 414 1445; x_wconf 96'>click</span>
-      <span class='ocrx_word' id='word_1_181' title='bbox 425 1418 506 1445; x_wconf 91'>track.</span>
+      <span class='ocrx_word' id='word_1_181' title='bbox 425 1418 506 1445; x_wconf 92'>track.</span>
       <span class='ocrx_word' id='word_1_182' title='bbox 519 1418 609 1445; x_wconf 96'>When</span>
       <span class='ocrx_word' id='word_1_183' title='bbox 620 1419 665 1445; x_wconf 96'>the</span>
       <span class='ocrx_word' id='word_1_184' title='bbox 676 1426 810 1452; x_wconf 96'>sequence</span>
@@ -297,7 +297,7 @@
       <span class='ocrx_word' id='word_1_187' title='bbox 995 1419 1101 1446; x_wconf 96'>around</span>
       <span class='ocrx_word' id='word_1_188' title='bbox 1112 1423 1141 1446; x_wconf 96'>to</span>
       <span class='ocrx_word' id='word_1_189' title='bbox 1152 1419 1201 1446; x_wconf 96'>bar</span>
-      <span class='ocrx_word' id='word_1_190' title='bbox 1213 1419 1232 1450; x_wconf 88'>1,</span>
+      <span class='ocrx_word' id='word_1_190' title='bbox 1213 1419 1232 1450; x_wconf 85'>1,</span>
      </span>
      <span class='ocr_line' id='line_1_23' title="bbox 346 1457 1223 1491; baseline 0.001 -7; x_size 34; x_descenders 7; x_ascenders 8">
       <span class='ocrx_word' id='word_1_191' title='bbox 346 1457 430 1490; x_wconf 16'>you’</span>
@@ -620,7 +620,7 @@
      </span>
      <span class='ocr_line' id='line_1_50' title="bbox 1295 1565 1577 1593; baseline 0.004 -1; x_size 34.748871; x_descenders 6.7488689; x_ascenders 9">
       <span class='ocrx_word' id='word_1_423' title='bbox 1295 1565 1441 1592; x_wconf 96'>unwanted</span>
-      <span class='ocrx_word' id='word_1_424' title='bbox 1452 1565 1577 1593; x_wconf 94'>sections,</span>
+      <span class='ocrx_word' id='word_1_424' title='bbox 1452 1565 1577 1593; x_wconf 93'>sections,</span>
      </span>
     </p>
    </div>
@@ -668,8 +668,8 @@
       <span class='ocrx_word' id='word_1_454' title='bbox 1458 1768 1562 1796; x_wconf 96'>section</span>
       <span class='ocrx_word' id='word_1_455' title='bbox 1574 1769 1666 1802; x_wconf 96'>(verse,</span>
       <span class='ocrx_word' id='word_1_456' title='bbox 1679 1769 1788 1801; x_wconf 96'>chorus,</span>
-      <span class='ocrx_word' id='word_1_457' title='bbox 1800 1769 1865 1802; x_wconf 95'>etc.)</span>
+      <span class='ocrx_word' id='word_1_457' title='bbox 1800 1769 1865 1802; x_wconf 96'>etc.)</span>
-      <span class='ocrx_word' id='word_1_458' title='bbox 1876 1768 1904 1795; x_wconf 95'>in</span>
+      <span class='ocrx_word' id='word_1_458' title='bbox 1876 1768 1904 1795; x_wconf 96'>in</span>
       <span class='ocrx_word' id='word_1_459' title='bbox 1914 1768 2066 1796; x_wconf 96'>individual</span>
      </span>
      <span class='ocr_line' id='line_1_55' title="bbox 1296 1808 2215 1841; baseline 0 -6; x_size 32; x_descenders 5; x_ascenders 8">
@@ -697,7 +697,7 @@
       <span class='ocrx_word' id='word_1_477' title='bbox 1377 1887 1412 1914; x_wconf 96'>all</span>
       <span class='ocrx_word' id='word_1_478' title='bbox 1422 1887 1468 1914; x_wconf 96'>the</span>
       <span class='ocrx_word' id='word_1_479' title='bbox 1478 1891 1552 1920; x_wconf 96'>parts</span>
-      <span class='ocrx_word' id='word_1_480' title='bbox 1563 1887 1621 1914; x_wconf 96'>into</span>
+      <span class='ocrx_word' id='word_1_480' title='bbox 1563 1887 1621 1914; x_wconf 95'>into</span>
       <span class='ocrx_word' id='word_1_481' title='bbox 1632 1895 1649 1914; x_wconf 96'>a</span>
       <span class='ocrx_word' id='word_1_482' title='bbox 1659 1895 1718 1914; x_wconf 96'>new</span>
       <span class='ocrx_word' id='word_1_483' title='bbox 1729 1895 1870 1920; x_wconf 96'>sequence.</span>
@@ -829,9 +829,9 @@
    <div class='ocr_carea' id='block_1_23' title="bbox 347 2427 2145 2507">
     <p class='ocr_par' id='par_1_31' lang='eng' title="bbox 347 2427 2145 2507">
      <span class='ocr_header' id='line_1_67' title="bbox 347 2427 1468 2461; baseline 0.002 -8; x_size 34; x_descenders 7; x_ascenders 8">
-      <span class='ocrx_word' id='word_1_573' title='bbox 347 2432 361 2446; x_wconf 77'>*</span>
+      <span class='ocrx_word' id='word_1_573' title='bbox 347 2432 361 2446; x_wconf 75'>*</span>
       <span class='ocrx_word' id='word_1_574' title='bbox 373 2427 612 2454; x_wconf 91'>Non-destructive</span>
-      <span class='ocrx_word' id='word_1_575' title='bbox 622 2427 914 2461; x_wconf 84'>recording—existing</span>
+      <span class='ocrx_word' id='word_1_575' title='bbox 622 2427 914 2461; x_wconf 87'>recording—existing</span>
       <span class='ocrx_word' id='word_1_576' title='bbox 924 2432 1002 2455; x_wconf 96'>notes</span>
       <span class='ocrx_word' id='word_1_577' title='bbox 1013 2436 1057 2455; x_wconf 96'>are</span>
       <span class='ocrx_word' id='word_1_578' title='bbox 1068 2432 1116 2455; x_wconf 96'>not</span>
@@ -912,12 +912,12 @@
    <div class='ocr_carea' id='block_1_27' title="bbox 347 2648 2100 2727">
     <p class='ocr_par' id='par_1_35' lang='eng' title="bbox 347 2648 2100 2727">
      <span class='ocr_header' id='line_1_72' title="bbox 347 2648 1664 2682; baseline 0.001 -7; x_size 33; x_descenders 6; x_ascenders 8">
-      <span class='ocrx_word' id='word_1_630' title='bbox 347 2654 360 2667; x_wconf 47'>®</span>
+      <span class='ocrx_word' id='word_1_630' title='bbox 347 2654 360 2667; x_wconf 45'>®</span>
-      <span class='ocrx_word' id='word_1_631' title='bbox 372 2648 483 2675; x_wconf 96'>Utilizes</span>
+      <span class='ocrx_word' id='word_1_631' title='bbox 372 2648 483 2675; x_wconf 94'>Utilizes</span>
       <span class='ocrx_word' id='word_1_632' title='bbox 493 2648 564 2680; x_wconf 96'>ultra</span>
       <span class='ocrx_word' id='word_1_633' title='bbox 573 2648 744 2682; x_wconf 96'>high-speed,</span>
       <span class='ocrx_word' id='word_1_634' title='bbox 766 2649 772 2676; x_wconf 95'>8</span>
-      <span class='ocrx_word' id='word_1_635' title='bbox 783 2649 862 2675; x_wconf 94'>MHz</span>
+      <span class='ocrx_word' id='word_1_635' title='bbox 783 2649 862 2675; x_wconf 95'>MHz</span>
       <span class='ocrx_word' id='word_1_636' title='bbox 873 2649 954 2676; x_wconf 95'>80186</span>
       <span class='ocrx_word' id='word_1_637' title='bbox 965 2649 994 2676; x_wconf 96'>16</span>
       <span class='ocrx_word' id='word_1_638' title='bbox 1004 2648 1043 2676; x_wconf 96'>bit</span>
@@ -928,12 +928,12 @@
       <span class='ocrx_word' id='word_1_643' title='bbox 1512 2648 1664 2682; x_wconf 96'>operation.</span>
      </span>
      <span class='ocr_header' id='line_1_73' title="bbox 347 2694 2100 2727; baseline 0.001 -7; x_size 33; x_descenders 6; x_ascenders 8">
-      <span class='ocrx_word' id='word_1_644' title='bbox 347 2699 361 2713; x_wconf 52'>*</span>
+      <span class='ocrx_word' id='word_1_644' title='bbox 347 2699 361 2713; x_wconf 44'>*</span>
       <span class='ocrx_word' id='word_1_645' title='bbox 372 2694 504 2721; x_wconf 96'>TEMPO</span>
       <span class='ocrx_word' id='word_1_646' title='bbox 515 2702 578 2727; x_wconf 96'>may</span>
-      <span class='ocrx_word' id='word_1_647' title='bbox 589 2694 623 2721; x_wconf 96'>be</span>
+      <span class='ocrx_word' id='word_1_647' title='bbox 589 2694 623 2721; x_wconf 95'>be</span>
       <span class='ocrx_word' id='word_1_648' title='bbox 633 2694 764 2727; x_wconf 95'>specified</span>
-      <span class='ocrx_word' id='word_1_649' title='bbox 774 2694 802 2721; x_wconf 92'>in</span>
+      <span class='ocrx_word' id='word_1_649' title='bbox 774 2694 802 2721; x_wconf 93'>in</span>
       <span class='ocrx_word' id='word_1_650' title='bbox 814 2695 1172 2722; x_wconf 91'>BEATS-PER-MINUTE</span>
       <span class='ocrx_word' id='word_1_651' title='bbox 1183 2703 1215 2722; x_wconf 93'>or</span>
       <span class='ocrx_word' id='word_1_652' title='bbox 1225 2695 1567 2722; x_wconf 92'>FRAMES-PER-BEAT</span>
@@ -995,7 +995,7 @@
    <div class='ocr_carea' id='block_1_31' title="bbox 347 2861 1792 2940">
     <p class='ocr_par' id='par_1_39' lang='eng' title="bbox 347 2861 1792 2940">
      <span class='ocr_header' id='line_1_77' title="bbox 347 2861 1792 2895; baseline 0.001 -8; x_size 33; x_descenders 6; x_ascenders 8">
-      <span class='ocrx_word' id='word_1_687' title='bbox 347 2866 360 2880; x_wconf 62'>¢</span>
+      <span class='ocrx_word' id='word_1_687' title='bbox 347 2866 360 2880; x_wconf 59'>¢</span>
       <span class='ocrx_word' id='word_1_688' title='bbox 372 2861 504 2887; x_wconf 96'>TEMPO</span>
       <span class='ocrx_word' id='word_1_689' title='bbox 515 2861 696 2888; x_wconf 96'>CHANGES</span>
       <span class='ocrx_word' id='word_1_690' title='bbox 707 2869 771 2894; x_wconf 96'>may</span>
@@ -1011,7 +1011,7 @@
       <span class='ocrx_word' id='word_1_700' title='bbox 1679 2861 1792 2888; x_wconf 84'>desired.</span>
      </span>
      <span class='ocr_header' id='line_1_78' title="bbox 347 2906 1507 2940; baseline 0.002 -8; x_size 33; x_descenders 7; x_ascenders 8">
-      <span class='ocrx_word' id='word_1_701' title='bbox 347 2911 360 2925; x_wconf 76'>¢</span>
+      <span class='ocrx_word' id='word_1_701' title='bbox 347 2911 360 2925; x_wconf 79'>¢</span>
       <span class='ocrx_word' id='word_1_702' title='bbox 371 2906 434 2938; x_wconf 96'>Any</span>
       <span class='ocrx_word' id='word_1_703' title='bbox 444 2906 539 2932; x_wconf 96'>TIME</span>
       <span class='ocrx_word' id='word_1_704' title='bbox 550 2906 763 2933; x_wconf 96'>SIGNATURE</span>
@@ -1022,8 +1022,8 @@
       <span class='ocrx_word' id='word_1_709' title='bbox 1046 2915 1109 2940; x_wconf 96'>may</span>
       <span class='ocrx_word' id='word_1_710' title='bbox 1120 2907 1154 2934; x_wconf 96'>be</span>
       <span class='ocrx_word' id='word_1_711' title='bbox 1164 2907 1288 2940; x_wconf 96'>changed</span>
-      <span class='ocrx_word' id='word_1_712' title='bbox 1299 2907 1393 2934; x_wconf 96'>within</span>
+      <span class='ocrx_word' id='word_1_712' title='bbox 1299 2907 1393 2934; x_wconf 95'>within</span>
-      <span class='ocrx_word' id='word_1_713' title='bbox 1404 2915 1420 2934; x_wconf 96'>a</span>
+      <span class='ocrx_word' id='word_1_713' title='bbox 1404 2915 1420 2934; x_wconf 95'>a</span>
       <span class='ocrx_word' id='word_1_714' title='bbox 1431 2915 1507 2940; x_wconf 96'>song.</span>
      </span>
     </p>

tests/cache/cardinal/__-l__eng__000004_ocr.png__000004_ocr_hocr__hocr__txt/stderr.bin

@@ -1 +0,0 @@
-Tesseract Open Source OCR Engine v5.0.0-beta-20210916-12-g19cc9 with Leptonica

tests/cache/cardinal/__-l__eng__000004_ocr.png__000004_ocr_hocr__hocr__txt/txt.bin

@@ -120,4 +120,3 @@ Linn Electronics, Inc.
 
 18720 Oxnard Street, Tarzana, CA 91356
 (818) 708-8131 TELEX #298949 LINN UR
-

tests/cache/cardinal/__-l__eng__000004_ocr.png__000004_ocr_tess__pdf__txt/stderr.bin

@@ -1 +0,0 @@
-Tesseract Open Source OCR Engine v5.0.0-beta-20210916-12-g19cc9 with Leptonica