Try to retain/copy xattrs

pip attempts to download musllinux_1_1 wheels and can't find pikepdf's which is only 1_2. Not clear how to fix.

.docker/Dockerfile.alpine

@@ -0,0 +1,83 @@
+# SPDX-FileCopyrightText: 2023 James R. Barlow
+# SPDX-License-Identifier: MPL-2.0
+
+FROM alpine:3.18 as base
+
+ENV LANG=C.UTF-8
+ENV TZ=UTC
+
+RUN apk add --no-cache \
+    python3 \
+    zlib
+
+FROM base as builder
+
+RUN apk add --no-cache \
+    ca-certificates \
+    git \
+    python3-dev \
+    py3-pip
+
+# On arm64, we need to build cffi from source.
+ARG TARGETPLATFORM
+
+RUN if [ "${TARGETPLATFORM}" == "linux/arm64" ]; then \
+    apk add --no-cache \
+    build-base \
+    autoconf \
+    automake \
+    libtool \
+    zlib-dev \
+    libffi-dev \
+    cairo-dev \
+    pkgconfig \
+    ;  \
+    fi
+
+COPY . /app
+
+WORKDIR /app
+
+RUN python3 -m venv .venv
+
+RUN source .venv/bin/activate \
+    && python3 -m pip install --no-cache-dir --upgrade pip \
+    && python3 -m pip install --no-cache-dir wheel \
+    && python3 -m pip install --no-cache-dir .[test,webservice,watcher]
+
+FROM base
+
+RUN apk add --no-cache \
+    ghostscript \
+    jbig2dec \
+    jbig2enc \
+    pngquant \
+    tesseract-ocr \
+    tesseract-ocr-data-chi_sim \
+    tesseract-ocr-data-deu \
+    tesseract-ocr-data-eng \
+    tesseract-ocr-data-fra \
+    tesseract-ocr-data-osd \
+    tesseract-ocr-data-por \
+    tesseract-ocr-data-spa \
+    ttf-droid \
+    unpaper \
+    && rm -rf /var/cache/apk/*
+
+WORKDIR /app
+
+COPY --from=builder /usr/local/lib/ /usr/local/lib/
+COPY --from=builder /usr/local/bin/ /usr/local/bin/
+
+COPY --from=builder /app/.venv/ /app/.venv/
+
+COPY --from=builder /app/misc/webservice.py /app/
+COPY --from=builder /app/misc/watcher.py /app/
+
+# Copy minimal project files to get the test suite.
+COPY --from=builder /app/pyproject.toml /app/README.md /app/
+COPY --from=builder /app/tests /app/tests
+
+ENV PATH="/app/.venv/bin:${PATH}"
+
+ENTRYPOINT ["/app/.venv/bin/ocrmypdf"]

.github/workflows/build.yml

@@ -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"
+            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"]
 
     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
 
@@ -142,13 +133,15 @@ jobs:
             ghostscript \
             jbig2enc \
             openjpeg \
+            openssl \
             pngquant \
             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 +171,22 @@ jobs:
     strategy:
       matrix:
         os: [windows-latest]
-        python: ["3.10", "3.11"]
+        python: ["3.10", "3.11", "3.12"]
 
     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 +212,15 @@ 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 +237,9 @@ jobs:
     name: Deploy artifacts to PyPI
     needs: [wheel_sdist_linux, test_linux, test_macos, test_windows]
     runs-on: ubuntu-latest
+    environment: release
+    permissions:
+      id-token: write  # mandatory for PyPI publishing
     if: github.event_name == 'push' && startsWith(github.event.ref, 'refs/tags/v')
     steps:
       - uses: actions/download-artifact@v3
@@ -249,14 +247,37 @@ jobs:
           name: artifact
           path: dist
 
-      - uses: pypa/gh-action-pypi-publish@release/v1
+      - name: Publish to PyPI
-        with:
+        uses: pypa/gh-action-pypi-publish@release/v1
-          user: __token__
-          password: ${{ secrets.TOKEN_PYPI }}
-          # repository_url: https://test.pypi.org/legacy/
 
-  docker:
+  create_release:
-    name: Build Docker images
+    name: Create GitHub release
+    needs: [wheel_sdist_linux, test_linux, test_macos, test_windows]
+    runs-on: ubuntu-latest
+    if: github.event_name == 'push' && startsWith(github.event.ref, 'refs/tags/v')
+    permissions:
+      # Required to create a release
+      contents: write
+    steps:
+      - uses: actions/download-artifact@v3
+        with:
+          name: artifact
+          path: dist
+
+      - name: Create Release
+        id: create-release
+        uses: shogo82148/actions-create-release@v1
+
+      - name: Upload Assets
+        uses: shogo82148/actions-upload-release-asset@v1
+        with:
+          upload_url: ${{ steps.create-release.outputs.upload_url }}
+          asset_path: |
+            ./dist/*.whl
+            ./dist/*.tar.gz
+
+  docker_ubuntu:
+    name: Build Ubuntu-based Docker image
     needs: [wheel_sdist_linux, test_linux, test_macos, test_windows]
     runs-on: ubuntu-latest
     if: github.event_name != 'pull_request'
@@ -274,22 +295,22 @@ jobs:
       - name: Set image name
         run: echo "DOCKER_IMAGE_NAME=ocrmypdf" >> $GITHUB_ENV
 
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
         with:
           fetch-depth: "0" # 0=all, needed for setuptools-scm to resolve version tags
 
       - name: Login to Docker Hub
-        uses: docker/login-action@v2
+        uses: docker/login-action@v3
         with:
           username: jbarlow83
           password: ${{ secrets.DOCKERHUB_TOKEN }}
 
       - name: Set up QEMU
-        uses: docker/setup-qemu-action@v2
+        uses: docker/setup-qemu-action@v3
 
       - name: Set up Docker Buildx
         id: buildx
-        uses: docker/setup-buildx-action@v2
+        uses: docker/setup-buildx-action@v3
 
       - name: Print image tag
         run: echo "Building image ${DOCKER_REPOSITORY}/${DOCKER_IMAGE_NAME}:${DOCKER_IMAGE_TAG}"
@@ -300,4 +321,52 @@ jobs:
             --push \
             --platform linux/arm64/v8,linux/amd64  \
             --tag "${DOCKER_REPOSITORY}/${DOCKER_IMAGE_NAME}:${DOCKER_IMAGE_TAG}" \
+            --tag "${DOCKER_REPOSITORY}/${DOCKER_IMAGE_NAME}-ubuntu:${DOCKER_IMAGE_TAG}" \
             --file .docker/Dockerfile .
+
+  docker_alpine:
+    name: Build Alpine-based Docker images
+    needs: [wheel_sdist_linux, test_linux, test_macos, test_windows]
+    runs-on: ubuntu-latest
+    if: github.event_name != 'pull_request'
+    steps:
+      - name: Set image tag to release or branch
+        run: echo "DOCKER_IMAGE_TAG=${GITHUB_REF##*/}" >> $GITHUB_ENV
+
+      - name: If main, set to latest
+        run: echo 'DOCKER_IMAGE_TAG=latest' >> $GITHUB_ENV
+        if: env.DOCKER_IMAGE_TAG == 'main'
+
+      - name: Set Docker Hub repository to username
+        run: echo "DOCKER_REPOSITORY=jbarlow83" >> $GITHUB_ENV
+
+      - name: Set image name
+        run: echo "DOCKER_IMAGE_NAME=ocrmypdf-alpine" >> $GITHUB_ENV
+
+      - uses: actions/checkout@v4
+        with:
+          fetch-depth: "0" # 0=all, needed for setuptools-scm to resolve version tags
+
+      - name: Login to Docker Hub
+        uses: docker/login-action@v3
+        with:
+          username: jbarlow83
+          password: ${{ secrets.DOCKERHUB_TOKEN }}
+
+      - name: Set up QEMU
+        uses: docker/setup-qemu-action@v3
+
+      - name: Set up Docker Buildx
+        id: buildx
+        uses: docker/setup-buildx-action@v3
+
+      - name: Print image tag
+        run: echo "Building image ${DOCKER_REPOSITORY}/${DOCKER_IMAGE_NAME}:${DOCKER_IMAGE_TAG}"
+
+      - name: Build
+        run: |
+          docker buildx build \
+            --push \
+            --platform linux/amd64  \
+            --tag "${DOCKER_REPOSITORY}/${DOCKER_IMAGE_NAME}:${DOCKER_IMAGE_TAG}" \
+            --file .docker/Dockerfile.alpine .

.gitignore

@@ -27,6 +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: .

README.md

@@ -39,8 +39,8 @@ ocrmypdf                      # it's a scriptable command line program
 - Distributes work across all available CPU cores
 - Uses [Tesseract OCR](https://github.com/tesseract-ocr/tesseract) engine to recognize more than [100 languages](https://github.com/tesseract-ocr/tessdata)
 - Keeps your private data private.
-- Scales properly to handle files with thousands of pages
+- Scales properly to handle files with thousands of pages.
-- Battle-tested on millions of PDFs
+- Battle-tested on millions of PDFs.
 
 <img src="misc/screencast/demo.svg" alt="Demo of OCRmyPDF in a terminal session">
 
@@ -70,7 +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

@@ -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
 --------------------------
@@ -111,6 +114,41 @@ exceed a certain number of megapixels with ``--skip-big``. (A 300 DPI,
     # 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.
 
@@ -234,7 +273,7 @@ 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.
@@ -247,11 +286,31 @@ 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
+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
 ==================
 

docs/api.rst

@@ -39,9 +39,7 @@ Parent process requirements
 The :func:`ocrmypdf.ocr` function runs OCRmyPDF similar to command line
 execution. To do this, it will:
 
-- create a monitoring thread
+- create worker processes or threads
-- create worker processes (on Linux, forking itself; on Windows and macOS, by
-  spawning)
 - manage the signal flags of its worker processes
 - execute other subprocesses (forking and executing other programs)
 
@@ -54,7 +52,19 @@ processes.
 
 Creating a child process to call :func:`ocrmypdf.ocr()` is suggested. That
 way your application will survive and remain interactive even if
-OCRmyPDF fails for any reason.
+OCRmyPDF fails for any reason. For example:
+
+.. code-block:: python
+
+    from multiprocessing import Process
+
+    def ocrmypdf_process():
+        ocrmypdf.ocr('input.pdf', 'output.pdf')
+
+    def call_ocrmypdf_from_my_app():
+        p = Process(target=ocrmypdf_process)
+        p.start()
+        p.join()
 
 Programs that call :func:`ocrmypdf.ocr()` should also install a SIGBUS signal
 handler (except on Windows), to raise an exception if access to a memory
@@ -89,12 +99,21 @@ your use case.
 Progress monitoring
 -------------------
 
-OCRmyPDF uses the ``tqdm`` package to implement its progress bars.
+OCRmyPDF uses the ``rich`` package to implement its progress bars.
 :func:`ocrmypdf.configure_logging` will set up logging output to
 ``sys.stderr`` in a way that is compatible with the display of the
 progress bar. Use ``ocrmypdf.ocr(...progress_bar=False)`` to disable
 the progress bar.
 
+Standard output
+---------------
+
+OCRmyPDF is strict about not writing to standard output so that
+users can safely use it in a pipeline and produce a valid output
+file. A caller application will have to ensure it does not write to
+standard output either, if it wants to be compatible with this
+behavior and support piping to a file.
+
 Exceptions
 ----------
 
@@ -104,9 +123,6 @@ exceptions, some exceptions related to multiprocessing, and
 handler. OCRmyPDF will clean up its temporary files and worker processes
 automatically when an exception occurs.
 
-Programs that call OCRmyPDF should consider trapping KeyboardInterrupt
-so that they allow OCR to terminate with the whole program terminating.
-
 When OCRmyPDF succeeds conditionally, it returns an integer exit code.
 
 Reference

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
@@ -153,7 +152,7 @@ The watcher service is included in the OCRmyPDF Docker image. To run it:
     docker run \
         --volume <path to files to convert>:/input \
         --volume <path to store results>:/output \
-        --volume <path to store processed originals>:/archive \
+        --volume <path to store processed originals>:/processed \
         --env OCR_OUTPUT_DIRECTORY_YEAR_MONTH=1 \
         --env OCR_ON_SUCCESS_ARCHIVE=1 \
         --env OCR_DESKEW=1 \
@@ -164,7 +163,7 @@ The watcher service is included in the OCRmyPDF Docker image. To run it:
 
 This service will watch for a file that matches ``/input/\*.pdf``,
 convert it to a OCRed PDF in ``/output/``, and move the processed
-original to ``/archive``. The parameters to this image are:
+original to ``/processed``. The parameters to this image are:
 
 .. csv-table:: watcher.py parameters for Docker
     :header: "Parameter", "Description"
@@ -172,7 +171,7 @@ original to ``/archive``. The parameters to this image are:
 
     "``--volume <path to files to convert>:/input``", "Files placed in this location will be OCRed"
     "``--volume <path to store results>:/output``", "This is where OCRed files will be stored"
-    "``--volume <path to store processed originals>:/archive``", "Archive processed originals here"
+    "``--volume <path to store processed originals>:/processed``", "Archive processed originals here"
     "``--env OCR_OUTPUT_DIRECTORY_YEAR_MONTH=1``", "Define environment variable ``OCR_OUTPUT_DIRECTORY_YEAR_MONTH=1`` to place files in the output in ``{output}/{year}/{month}/{filename}``"
     "``--env OCR_ON_SUCCESS_ARCHIVE=1``", "Define environment variable ``OCR_ON_SUCCESS_ARCHIVE`` to move processed originals"
     "``--env OCR_DESKEW=1``", "Define environment variable ``OCR_DESKEW``  to apply deskew to crooked input PDFs"

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

@@ -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/docker.rst

@@ -8,17 +8,16 @@
 OCRmyPDF Docker image
 =====================
 
-OCRmyPDF is also available in a Docker image that packages recent
+OCRmyPDF is also available in Docker images that packages recent
 versions of all dependencies.
 
 For users who already have Docker installed this may be an easy and
-convenient option. However, it is less performant than a system
+convenient option.
-installation and may require Docker engine configuration.
 
-OCRmyPDF needs a generous amount of RAM, CPU cores, temporary storage
+On platforms other than Linux, Docker runs in a virtual machine, and so may
-space, whether running in a Docker container or on its own. It may be
+be less performant. You may also want to adjust the Docker virtual machine's
-necessary to ensure the container is provisioned with additional
+memory and CPU allocation. On Linux, the Docker image runs natively and
-resources.
+performance is comparable to a system installation.
 
 .. _docker-install:
 
@@ -35,28 +34,37 @@ execute the image:
 
    docker run hello-world
 
-The recommended OCRmyPDF Docker image is currently named ``ocrmypdf``:
+.. list-table:: Docker images
+   :width: 30 20 50
+   :header-rows: 1
+
+   * - Image
+     - Architecture
+     - Description
+   * - ``jbarlow83/ocrmypdf-alpine``
+     - x86_64 only
+     - Recommended image, based on Alpine Linux.
+   * - ``jbarlow83/ocrmypdf-ubuntu``
+     - x86_64 and arm64
+     - Alternate image, based on Ubuntu. When the Alpine image is considered
+       stable and available for arm64, this image will be deprecated.
+   * - ``jbarlow83/ocrmypdf``
+     - x86_64 and arm64
+     - Currently an alias for ocrmypdf-ubuntu. When the Alpine image is
+       considered stable and available for arm64, this name point to the
+       Alpine image. If you don't about the difference between Alpine and
+       Ubuntu, use this image.
+
+To install:
 
 .. code-block:: bash
 
-   docker pull jbarlow83/ocrmypdf
+   docker pull jbarlow83/ocrmypdf-alpine
 
+The ``ocrmypdf`` image is also available, but is deprecated and will be removed
+in the future.
 
-OCRmyPDF will use all available CPU cores. By default, the VirtualBox
+OCRmyPDF will use all available CPU cores. See the Docker documentation for
-machine instance on Windows and macOS has only a single CPU core
-enabled. Use the VirtualBox Manager to determine the name of your Docker
-engine host, and then follow these optional steps to enable multiple
-CPUs:
-
-.. code-block:: bash
-
-   # Optional step for Mac OS X users
-   docker-machine stop "yourVM"
-   VBoxManage modifyvm "yourVM" --cpus 2  # or whatever number of core is desired
-   docker-machine start "yourVM"
-   eval $(docker-machine env "yourVM")
-
-See the Docker documentation for
 `adjusting memory and CPU on other platforms <https://docs.docker.com/config/containers/resource_constraints/>`__.
 
 Using the Docker image on the command line
@@ -66,6 +74,8 @@ Using the Docker image on the command line
 container is ephemeral – it runs for one OCR job and terminates, just like a
 command line program. We are using Docker to deliver an application (as opposed
 to the more conventional case, where a Docker container runs as a server).
+For that reason we usually use the ``--rm`` argument to delete the container
+when it exits.
 
 To start a Docker container (instance of the image):
 
@@ -132,17 +142,35 @@ You can then add new data with either a Dockerfile:
 
 .. code-block:: dockerfile
 
-   FROM jbarlow83/ocrmypdf
+   FROM jbarlow83/ocrmypdf:{TAG}
 
    # Example: add a tessdata_best file
    COPY chi_tra_vert.traineddata /usr/share/tesseract-ocr/<data version>/tessdata/
 
+When creating your own image, you should always pin a specific version of the
+OCRmyPDF Docker image. This ensures that your image will not break when a new
+version of OCRmyPDF is released.
+
 Alternately, you can copy training data into a Docker container as follows:
 
 .. code-block:: bash
 
    docker cp mycustomtraining.traineddata name_of_container:/usr/share/tesseract-ocr/<tesseract version>/tessdata/
 
+Extending the Docker image
+==========================
+
+You can extend the Docker image with your own customizations, similar to the way
+it is extended to add language packs.
+
+Note that the Docker image is subject to change at any time. For example, the base
+image may be updated to a newer version of Ubuntu or Debian. Such changes will be
+noted in the release notes but might occur at minor versions releases, unless the
+way a "casual" user of the Docker image is affected.
+
+If you extend the Docker image, you should pin a specific version of the OCRmyPDF
+Docker image.
+
 Executing the test suite
 ========================
 
@@ -150,16 +178,16 @@ The OCRmyPDF test suite is installed with image. To run it:
 
 .. code-block:: bash
 
-   docker run --entrypoint python3  jbarlow83/ocrmypdf -m pytest
+   docker run --rm --entrypoint python  jbarlow83/ocrmypdf -m pytest
 
 Accessing the shell
 ===================
 
-To use the bash shell in the Docker image:
+To use the shell in the Docker image:
 
 .. code-block:: bash
 
-   docker run -it --entrypoint bash  jbarlow83/ocrmypdf
+   docker run -it --entrypoint sh  jbarlow83/ocrmypdf
 
 Using the OCRmyPDF web service wrapper
 ======================================
@@ -169,7 +197,10 @@ service. The webservice may be launched as follows:
 
 .. code-block:: bash
 
-   docker run --entrypoint python3 -p 5000:5000  jbarlow83/ocrmypdf webservice.py
+   docker run --entrypoint python -p 5000:5000  jbarlow83/ocrmypdf webservice.py
+
+We omit the ``--rm`` parameter so that the container will not be
+automatically deleted when it exits.
 
 This will configure the machine to listen on port 5000. On Linux machines
 this is port 5000 of localhost. On macOS or Windows machines running

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
@@ -44,6 +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.
 
@@ -638,8 +616,8 @@ system-wide:
 .. code-block:: bash
 
     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 .
 
@@ -665,8 +643,8 @@ To install all of the development and test requirements:
 .. code-block:: bash
 
     git clone -b main https://github.com/ocrmypdf/OCRmyPDF.git
-    python -m venv
+    python -m .venv
-    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/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

@@ -45,8 +45,8 @@ 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.
 

docs/pdfsecurity.rst

@@ -54,31 +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.
 
-Password protection, digital signatures and certification
+Password protected PDFs
-=========================================================
+=======================
 
 Password protected PDFs usually have two passwords, and owner and user
 password. When the user password is set to empty, PDF readers will open
-the file automatically and marked it as "(SECURED)". While not as
+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 +28,101 @@ tagged yet.
 
 .. |OCRmyPDF PyPI| image:: https://img.shields.io/pypi/v/ocrmypdf.svg
 
+v15.3.1
+=======
+
+-  Fixed an issue with logging settings for misc/watcher.py introduced in the
+   previous release. :issue:`1180`
+-  Updated documentation on Docker performance concerns.
+
+v15.3.0
+=======
+
+-  Update misc/watcher.py to improve command line interface using Typer, and
+   support ``.env`` specification of environment variables. Improved error
+   messages. Thanks to @mflagg2814 for the PR that prompted this improvement.
+-  Improved error message when a file cannot be read because we are running in
+   a snap container.
+
+v15.2.0
+=======
+
+-  Added a Docker image based on Alpine Linux. This image is smaller than the
+   Ubuntu-based image and may be useful in some situations. Currently hosted at
+   jbarlow83/ocrmypdf-alpine. Currently not available in ARM flavor.
+-  The Ubuntu Docker is now aliased to jbarlow83/ocrmypdf-ubuntu.
+-  Updated Docker documentation.
+
+v15.1.0
+=======
+
+-  We now require Pillow 10.0.1, due a serious security vulnerability in all earlier
+   versions of that dependency. The vulnerability concerns WebP images and could
+   be triggered in OCRmyPDF when creating a PDF from a malicious WebP image.
+-  Added some keyword arguments to ``ocrmypdf.ocr`` that were previously accepted
+   but undocumented.
+-  Documentation updates and typing improvements.
+
+v15.0.2
+=======
+
+-  Added Python 3.12 to test matrix.
+-  Updated documentation for notes on Python 3.12, 32-bit support and some new
+   features in v15.
+
+v15.0.1
+=======
+
+-  Wheels Python tag changed to py39.
+-  Marked as a expected fail a test that fails on recent Ghostscript versions.
+-  Clarified documentation and release notes around the extent of 32-bit support.
+-  Updated installation documentation to changes in v15.
+
+v15.0.0
+=======
+
+-  Dropped support for Python 3.8.
+-  Dropped support some older dependencies, specifically ``coloredlogs`` and
+   ``tqdm`` in favor of rich - see ``pyproject.toml`` for details.
+   Generally speaking, Ubuntu 22.04 is our new baseline system.
+-  Tightened version requirements for some dependencies.
+-  Dropped support for 32-bit Linux wheels. We strongly recommend a 64-bit operating
+   system, and 64-bit versions of Python, Tesseract and Ghostscript to use OCRmyPDF.
+   Many of our dependencies are dropping 32-bit builds (e.g. Pillow), and we are
+   following suit. (Maintainers may still build 32-bit versions from source.)
+-  Changed to trusted release for PyPI publishing.
+-  pikepdf memory mapping is enabled again for improved performance, now that an
+   issue with feature in pikepdf is fixed.
+-  ``ocrmypdf.helpers.calculate_downsample`` previously had two variants, one
+   that took a ``PIL.Image`` and one that took a ``tuple[int, int]``. The latter
+   was removed.
+-  The snap version of ocrmypdf is now based on Ubuntu core22.
+-  We now account for situations where a small portion of an image on a page is drawn
+   at high DPI (resolution). Previously, the entire page would be rasterized at the
+   highest resolution of any feature, which caused performance problems. Now,
+   the page is rasterized
+   at a resolution based on the average DPI of the page, weighted by the area that
+   each feature occupies. Typically, small areas of high resolution in PDFs are
+   errors or quirks from the repeated use of assets and high resolution is not
+   beneficial. :issue:`1010,1104,1004,1079,1010`
+-  Ghostscript color conversion strategy is now configurable using
+   ``--color-conversion-strategy``. :issue:`1143`
+-  JBIG2 threshold for optimization is now configurable using
+   ``--jbig2-threshold``. :issue:`1133`
+
+v14.4.0
+=======
+
+-  Digitally signed PDFs are now detected. If the PDF is signed, OCRmyPDF will
+   refuse to modify it. Previously, only encrypted PDFs were detected, not
+   those that were signed but not encrypted. :issue:`1040`
+-  In addition, ``--invalidate-digital-signatures`` can be used to override the
+   above behavior and modify the PDF anyway. :issue:`1040`
+-  tqdm progress bars replaced with "rich" progress bars. The rich library is
+   a new dependency. Certain APIs that used tqdm are now deprecated and will
+   be removed in the next major release.
+-  Improved integration with GitHub Releases. Thanks to @stumpylog.
+
 v14.3.0
 =======
 
@@ -54,7 +149,7 @@ v14.2.1
 v14.2.0
 =======
 
--  Added `--tesseract-downsample-above` to downsample larger images even when
+-  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`

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/watcher.py

@@ -5,107 +5,122 @@
 
 """Watch a directory for new PDFs and OCR them."""
 
-from __future__ import annotations
+# Do not enable annotations!
+# https://github.com/tiangolo/typer/discussions/598
+# from __future__ import annotations
 
 import json
 import logging
-import os
 import shutil
 import sys
 import time
 from datetime import datetime
+from enum import Enum
 from pathlib import Path
+from typing import Annotated, Any
 
 import pikepdf
+import typer
+from dotenv import load_dotenv
 from watchdog.events import PatternMatchingEventHandler
 from watchdog.observers import Observer
 from watchdog.observers.polling import PollingObserver
 
 import ocrmypdf
 
+load_dotenv()
+
+
 # pylint: disable=logging-format-interpolation
-
+app = typer.Typer(name="ocrmypdf-watcher")
-
-def getenv_bool(name: str, default: str = 'False'):
-    return os.getenv(name, default).lower() in ('true', 'yes', 'y', '1')
-
-
-INPUT_DIRECTORY = os.getenv('OCR_INPUT_DIRECTORY', '/input')
-OUTPUT_DIRECTORY = os.getenv('OCR_OUTPUT_DIRECTORY', '/output')
-ARCHIVE_DIRECTORY = os.getenv('OCR_ARCHIVE_DIRECTORY', '/processed')
-OUTPUT_DIRECTORY_YEAR_MONTH = getenv_bool('OCR_OUTPUT_DIRECTORY_YEAR_MONTH')
-ON_SUCCESS_DELETE = getenv_bool('OCR_ON_SUCCESS_DELETE')
-ON_SUCCESS_ARCHIVE = getenv_bool('OCR_ON_SUCCESS_ARCHIVE')
-DESKEW = getenv_bool('OCR_DESKEW')
-OCR_JSON_SETTINGS = json.loads(os.getenv('OCR_JSON_SETTINGS', '{}'))
-POLL_NEW_FILE_SECONDS = int(os.getenv('OCR_POLL_NEW_FILE_SECONDS', '1'))
-USE_POLLING = getenv_bool('OCR_USE_POLLING')
-RETRIES_LOADING_FILE = int(os.getenv('OCR_RETRIES_LOADING_FILE', '5'))
-LOGLEVEL = os.getenv('OCR_LOGLEVEL', 'INFO')
-PATTERNS = ['*.pdf', '*.PDF']
 
 log = logging.getLogger('ocrmypdf-watcher')
 
 
-def get_output_dir(root, basename):
+class LoggingLevelEnum(str, Enum):
-    if OUTPUT_DIRECTORY_YEAR_MONTH:
+    """Enum for logging levels."""
+
+    DEBUG = "DEBUG"
+    INFO = "INFO"
+    WARNING = "WARNING"
+    ERROR = "ERROR"
+    CRITICAL = "CRITICAL"
+
+
+def get_output_dir(root: Path, basename: str, output_dir_year_month: bool) -> Path:
+    if output_dir_year_month:
         today = datetime.today()
-        output_directory_year_month = (
+        output_directory_year_month = root / str(today.year) / f'{today.month:02d}'
-            Path(root) / str(today.year) / f'{today.month:02d}'
-        )
         if not output_directory_year_month.exists():
             output_directory_year_month.mkdir(parents=True, exist_ok=True)
         output_path = Path(output_directory_year_month) / basename
     else:
-        output_path = Path(OUTPUT_DIRECTORY) / basename
+        output_path = root / basename
     return output_path
 
 
-def wait_for_file_ready(file_path):
+def wait_for_file_ready(
+    file_path: Path, poll_new_file_seconds: int, retries_loading_file: int
+):
     # This loop waits to make sure that the file is completely loaded on
     # disk before attempting to read. Docker sometimes will publish the
     # watchdog event before the file is actually fully on disk, causing
     # pikepdf to fail.
 
-    retries = RETRIES_LOADING_FILE
+    tries = retries_loading_file + 1
-    while retries:
+    while tries:
         try:
-            pdf = pikepdf.open(file_path)
+            with pikepdf.Pdf.open(file_path) as pdf:
-        except (FileNotFoundError, pikepdf.PdfError) as e:
+                log.debug(f"{file_path} ready with {pdf.pages} pages")
+                return True
+        except (FileNotFoundError, OSError) as e:
             log.info(f"File {file_path} is not ready yet")
             log.debug("Exception was", exc_info=e)
-            time.sleep(POLL_NEW_FILE_SECONDS)
+            time.sleep(poll_new_file_seconds)
-            retries -= 1
+            tries -= 1
-        else:
+        except pikepdf.PdfError as e:
-            pdf.close()
+            log.info(f"File {file_path} is not full written yet")
-            return True
+            log.debug("Exception was", exc_info=e)
+            time.sleep(poll_new_file_seconds)
+            tries -= 1
 
     return False
 
 
-def execute_ocrmypdf(file_path):
+def execute_ocrmypdf(
-    file_path = Path(file_path)
+    *,
-    output_path = get_output_dir(OUTPUT_DIRECTORY, file_path.name)
+    file_path: Path,
+    archive_dir: Path,
+    output_dir: Path,
+    deskew: bool,
+    ocrmypdf_kwargs: dict[str, Any],
+    on_success_delete: bool,
+    on_success_archive: bool,
+    poll_new_file_seconds: int,
+    retries_loading_file: int,
+    output_dir_year_month: bool,
+):
+    output_path = get_output_dir(output_dir, file_path.name, output_dir_year_month)
 
     log.info("-" * 20)
-    log.info(f'New file: {file_path}. Waiting until fully loaded...')
+    log.info(f'New file: {file_path}. Waiting until fully written...')
-    if not wait_for_file_ready(file_path):
+    if not wait_for_file_ready(file_path, poll_new_file_seconds, retries_loading_file):
         log.info(f"Gave up waiting for {file_path} to become ready")
         return
     log.info(f'Attempting to OCRmyPDF to: {output_path}')
     exit_code = ocrmypdf.ocr(
         input_file=file_path,
         output_file=output_path,
-        deskew=DESKEW,
+        deskew=deskew,
-        **OCR_JSON_SETTINGS,
+        **ocrmypdf_kwargs,
     )
     if exit_code == 0:
-        if ON_SUCCESS_DELETE:
+        if on_success_delete:
             log.info(f'OCR is done. Deleting: {file_path}')
             file_path.unlink()
-        elif ON_SUCCESS_ARCHIVE:
+        elif on_success_archive:
-            log.info(f'OCR is done. Archiving {file_path.name} to {ARCHIVE_DIRECTORY}')
+            log.info(f'OCR is done. Archiving {file_path.name} to {archive_dir}')
-            shutil.move(file_path, f'{ARCHIVE_DIRECTORY}/{file_path.name}')
+            shutil.move(file_path, f'{archive_dir}/{file_path.name}')
         else:
             log.info('OCR is done')
     else:
@@ -113,61 +128,202 @@ def execute_ocrmypdf(file_path):
 
 
 class HandleObserverEvent(PatternMatchingEventHandler):
+    def __init__(
+        self,
+        patterns=None,
+        ignore_patterns=None,
+        ignore_directories=False,
+        case_sensitive=False,
+        settings={},
+    ):
+        super().__init__(
+            patterns=patterns,
+            ignore_patterns=ignore_patterns,
+            ignore_directories=ignore_directories,
+            case_sensitive=case_sensitive,
+        )
+        self._settings = settings
+
     def on_any_event(self, event):
         if event.event_type in ['created']:
-            execute_ocrmypdf(event.src_path)
+            execute_ocrmypdf(event.src_path, **self._settings)
 
 
-def main():
+@app.command()
+def main(
+    input_dir: Annotated[
+        Path,
+        typer.Argument(
+            envvar='OCR_INPUT_DIRECTORY',
+            exists=True,
+            file_okay=False,
+            dir_okay=True,
+            readable=True,
+            resolve_path=True,
+        ),
+    ] = '/input',
+    output_dir: Annotated[
+        Path,
+        typer.Argument(
+            envvar='OCR_OUTPUT_DIRECTORY',
+            exists=True,
+            file_okay=False,
+            dir_okay=True,
+            writable=True,
+            resolve_path=True,
+        ),
+    ] = '/output',
+    archive_dir: Annotated[
+        Path,
+        typer.Argument(
+            envvar='OCR_ARCHIVE_DIRECTORY',
+            exists=True,
+            file_okay=False,
+            dir_okay=True,
+            writable=True,
+            resolve_path=True,
+        ),
+    ] = '/processed',
+    output_dir_year_month: Annotated[
+        bool,
+        typer.Option(
+            envvar='OCR_OUTPUT_DIRECTORY_YEAR_MONTH',
+            help='Create a subdirectory in the output directory for each year and month',
+        ),
+    ] = False,
+    on_success_delete: Annotated[
+        bool,
+        typer.Option(
+            envvar='OCR_ON_SUCCESS_DELETE',
+            help='Delete the input file after successful OCR',
+        ),
+    ] = False,
+    on_success_archive: Annotated[
+        bool,
+        typer.Option(
+            envvar='OCR_ON_SUCCESS_ARCHIVE',
+            help='Archive the input file after successful OCR',
+        ),
+    ] = False,
+    deskew: Annotated[
+        bool,
+        typer.Option(
+            envvar='OCR_DESKEW',
+            help='Deskew the input file before OCR',
+        ),
+    ] = False,
+    ocr_json_settings: Annotated[
+        typer.FileText,
+        typer.Option(
+            envvar='OCR_JSON_SETTINGS',
+            help='JSON settings to pass to OCRmyPDF',
+        ),
+    ] = None,
+    poll_new_file_seconds: Annotated[
+        int,
+        typer.Option(
+            envvar='OCR_POLL_NEW_FILE_SECONDS',
+            help='Seconds to wait before polling a new file',
+            min=0,
+        ),
+    ] = 1,
+    use_polling: Annotated[
+        bool,
+        typer.Option(
+            envvar='OCR_USE_POLLING',
+            help='Use polling instead of filesystem events',
+        ),
+    ] = False,
+    retries_loading_file: Annotated[
+        int,
+        typer.Option(
+            envvar='OCR_RETRIES_LOADING_FILE',
+            help='Number of times to retry loading a file before giving up',
+            min=0,
+        ),
+    ] = 5,
+    loglevel: Annotated[
+        LoggingLevelEnum,
+        typer.Option(
+            envvar='OCR_LOGLEVEL',
+            help='Logging level',
+        ),
+    ] = LoggingLevelEnum.INFO,
+    patterns: Annotated[
+        str,
+        typer.Option(
+            envvar='OCR_PATTERNS',
+            help='File patterns to watch',
+        ),
+    ] = '*.pdf,*.PDF',
+):
     ocrmypdf.configure_logging(
         verbosity=(
             ocrmypdf.Verbosity.default
-            if LOGLEVEL != 'DEBUG'
+            if loglevel != LoggingLevelEnum.DEBUG
             else ocrmypdf.Verbosity.debug
         ),
         manage_root_logger=True,
     )
-    log.setLevel(LOGLEVEL)
+    log.setLevel(loglevel.value)
     log.info(
         f"Starting OCRmyPDF watcher with config:\n"
-        f"Input Directory: {INPUT_DIRECTORY}\n"
+        f"Input Directory: {input_dir}\n"
-        f"Output Directory: {OUTPUT_DIRECTORY}\n"
+        f"Output Directory: {output_dir}\n"
-        f"Output Directory Year & Month: {OUTPUT_DIRECTORY_YEAR_MONTH}\n"
+        f"Output Directory Year & Month: {output_dir_year_month}\n"
-        f"Archive Directory: {ARCHIVE_DIRECTORY}"
+        f"Archive Directory: {archive_dir}"
     )
     log.debug(
-        f"INPUT_DIRECTORY: {INPUT_DIRECTORY}\n"
+        f"INPUT_DIRECTORY: {input_dir}\n"
-        f"OUTPUT_DIRECTORY: {OUTPUT_DIRECTORY}\n"
+        f"OUTPUT_DIRECTORY: {output_dir}\n"
-        f"OUTPUT_DIRECTORY_YEAR_MONTH: {OUTPUT_DIRECTORY_YEAR_MONTH}\n"
+        f"OUTPUT_DIRECTORY_YEAR_MONTH: {output_dir_year_month}\n"
-        f"ARCHIVE_DIRECTORY: {ARCHIVE_DIRECTORY}\n"
+        f"ARCHIVE_DIRECTORY: {archive_dir}\n"
-        f"ON_SUCCESS_DELETE: {ON_SUCCESS_DELETE}\n"
+        f"ON_SUCCESS_DELETE: {on_success_delete}\n"
-        f"ON_SUCCESS_ARCHIVE: {ON_SUCCESS_ARCHIVE}\n"
+        f"ON_SUCCESS_ARCHIVE: {on_success_archive}\n"
-        f"DESKEW: {DESKEW}\n"
+        f"DESKEW: {deskew}\n"
-        f"ARGS: {OCR_JSON_SETTINGS}\n"
+        f"ARGS: {ocr_json_settings}\n"
-        f"POLL_NEW_FILE_SECONDS: {POLL_NEW_FILE_SECONDS}\n"
+        f"POLL_NEW_FILE_SECONDS: {poll_new_file_seconds}\n"
-        f"RETRIES_LOADING_FILE: {RETRIES_LOADING_FILE}\n"
+        f"RETRIES_LOADING_FILE: {retries_loading_file}\n"
-        f"USE_POLLING: {USE_POLLING}\n"
+        f"USE_POLLING: {use_polling}\n"
-        f"LOGLEVEL: {LOGLEVEL}"
+        f"LOGLEVEL: {loglevel.value}"
     )
 
-    if 'input_file' in OCR_JSON_SETTINGS or 'output_file' in OCR_JSON_SETTINGS:
+    json_settings = json.loads(ocr_json_settings.read() if ocr_json_settings else '{}')
-        log.error('OCR_JSON_SETTINGS should not specify input file or output file')
+
+    if 'input_file' in json_settings or 'output_file' in json_settings:
+        log.error(
+            'OCR_JSON_SETTINGS (--ocr-json-settings) may not specify input/output file'
+        )
         sys.exit(1)
 
-    handler = HandleObserverEvent(patterns=PATTERNS)
+    handler = HandleObserverEvent(
-    if USE_POLLING:
+        patterns=patterns.split(','),
+        settings={
+            'archive_dir': archive_dir,
+            'output_dir': output_dir,
+            'deskew': deskew,
+            'ocrmypdf_kwargs': json_settings,
+            'on_success_delete': on_success_delete,
+            'on_success_archive': on_success_archive,
+            'poll_new_file_seconds': poll_new_file_seconds,
+            'retries_loading_file': retries_loading_file,
+            'output_dir_year_month': output_dir_year_month,
+        },
+    )
+    if use_polling:
         observer = PollingObserver()
     else:
         observer = Observer()
-    observer.schedule(handler, INPUT_DIRECTORY, recursive=True)
+    observer.schedule(handler, input_dir, recursive=True)
     observer.start()
+    typer.echo(f"Watching {input_dir} for new PDFs. Press Ctrl+C to exit.")
     try:
         while True:
-            time.sleep(1)
+            time.sleep(30)
     except KeyboardInterrupt:
         observer.stop()
     observer.join()
 
 
 if __name__ == "__main__":
-    main()
+    app()

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>=10.0.1",
-  "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",
@@ -47,13 +41,7 @@ classifiers = [
   "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/"
@@ -64,17 +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",
-  "hypothesis>=6.0.0",
+  "hypothesis>=6.36.0",
-  "pytest>=6.0.0",
+  "pytest>=6.2.5",
-  "pytest-cov>=2.11.1",
+  "pytest-cov>=3.0.0",
-  "pytest-xdist>=2.2.0",
+  "pytest-xdist>=2.5.0",
-  "python-xmp-toolkit==2.0.1",  # also requires apt-get install libexempi3
+  "python-xmp-toolkit==2.0.1", # also requires apt-get install libexempi3
   "types-Pillow",
   "types-humanfriendly",
 ]
-watcher = ["watchdog>=1.0.2"]
+watcher = ["watchdog>=1.0.2", "typer[all]", "python-dotenv"]
-webservice = ["Flask>=1"]
+webservice = ["Flask>=2.0.1"]
 
 [project.scripts]
 ocrmypdf = "ocrmypdf.__main__:run"
@@ -89,11 +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 = '''
@@ -134,7 +122,7 @@ exclude_lines = [
   "if 0:",
   "if False:",
   "if __name__ == .__main__.:",
-  "if TYPE_CHECKING:"
+  "if TYPE_CHECKING:",
 ]
 
 [tool.pytest.ini_options]
@@ -156,20 +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/_concurrent.py

@@ -7,7 +7,8 @@ from __future__ import annotations
 
 import threading
 from abc import ABC, abstractmethod
-from typing import Callable, Iterable
+from collections.abc import Iterable
+from typing import Callable
 
 
 def _task_noop(*_args, **_kwargs):

src/ocrmypdf/_exec/ghostscript.py

@@ -8,7 +8,6 @@ from __future__ import annotations
 import logging
 import os
 import re
-import sys
 from io import BytesIO
 from os import fspath
 from pathlib import Path
@@ -21,31 +20,49 @@ from ocrmypdf.exceptions import SubprocessOutputError
 from ocrmypdf.helpers import Resolution
 from ocrmypdf.subprocess import get_version, run, run_polling_stderr
 
-# Remove this workaround when we require Pillow >= 10
+COLOR_CONVERSION_STRATEGIES = frozenset(
-try:
+    [
-    Transpose = Image.Transpose  # type: ignore
+        'CMYK',
-except AttributeError:
+        'Gray',
-    # Pillow 9 shim
+        'LeaveColorUnchanged',
-    Transpose = Image  # type: ignore
+        'RGB',
+        'UseDeviceIndependentColor',
+    ]
+)
 
 log = logging.getLogger(__name__)
 
-# Most reliable way 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:
@@ -112,11 +129,11 @@ def rasterize_pdf(
                 # rotation is a clockwise angle and Image.ROTATE_* is
                 # counterclockwise so this cancels out the rotation
                 if rotation == 90:
-                    im = im.transpose(Transpose.ROTATE_90)
+                    im = im.transpose(Image.Transpose.ROTATE_90)
                 elif rotation == 180:
-                    im = im.transpose(Transpose.ROTATE_180)
+                    im = im.transpose(Image.Transpose.ROTATE_180)
                 elif rotation == 270:
-                    im = im.transpose(Transpose.ROTATE_270)
+                    im = im.transpose(Image.Transpose.ROTATE_270)
                 if rotation % 180 == 90:
                     page_dpi = page_dpi.flip_axis()
             im.save(fspath(output_file), dpi=page_dpi)
@@ -160,6 +177,7 @@ 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,
@@ -189,8 +207,7 @@ 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
@@ -209,16 +226,16 @@ def generate_pdfa(
             "-dBATCH",
             "-dNOPAUSE",
             "-dSAFER",
-            "-dCompatibilityLevel=" + str(pdf_version),
+            f"-dCompatibilityLevel={str(pdf_version)}",
             "-sDEVICE=pdfwrite",
             "-dAutoRotatePages=/None",
-            "-sColorConversionStrategy=" + strategy,
+            f"-sColorConversionStrategy={color_conversion_strategy}",
         ]
         + (['-dPDFSTOPONERROR'] if stop_on_error else [])
         + compression_args
         + [
             "-dJPEGQ=95",
-            "-dPDFA=" + pdfa_part,
+            f"-dPDFA={pdfa_part}",
             "-dPDFACompatibilityPolicy=1",
             "-o",
             "-",
@@ -249,14 +266,9 @@ def generate_pdfa(
         # If there is an error we log the whole stderr, except for filtering
         # duplicates.
         if _gs_error_reported(stderr):
-            last_part = None
+            # 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

@@ -7,6 +7,7 @@ from __future__ import annotations
 
 import logging
 import re
+from contextlib import suppress
 from math import pi
 from os import fspath
 from pathlib import Path
@@ -113,13 +114,13 @@ 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]:
@@ -350,7 +351,7 @@ def generate_hocr(
         tesseract_log_output(stdout)
         # The sidecar text file will get the suffix .txt; rename it to
         # whatever caller wants it named
-        if prefix.with_suffix('.txt').exists():
+        with suppress(FileNotFoundError):
             prefix.with_suffix('.txt').replace(output_text)
 
 
@@ -406,7 +407,7 @@ def generate_pdf(
     try:
         p = run(args_tesseract, stdout=PIPE, stderr=STDOUT, timeout=timeout, check=True)
         stdout = p.stdout
-        if prefix.with_suffix('.txt').exists():
+        with suppress(FileNotFoundError):
             prefix.with_suffix('.txt').replace(output_text)
     except TimeoutExpired:
         page_timedout(timeout)

src/ocrmypdf/_exec/unpaper.py

@@ -9,12 +9,14 @@ import logging
 import os
 import shlex
 import sys
+from collections.abc import Iterator
 from contextlib import contextmanager
 from decimal import Decimal
 from pathlib import Path
 from subprocess import PIPE, STDOUT
-from typing import Iterator, Union
+from typing import Union
 
+from packaging.version import Version
 from PIL import Image
 
 from ocrmypdf.exceptions import MissingDependencyError, SubprocessOutputError
@@ -67,8 +69,8 @@ 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/_jobcontext.py

@@ -9,9 +9,9 @@ import os
 import shutil
 import sys
 from argparse import Namespace
+from collections.abc import Iterator
 from copy import copy
 from pathlib import Path
-from typing import Iterator
 
 from pluggy import PluginManager
 

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

@@ -10,11 +10,12 @@ import logging
 import os
 import re
 import sys
+from collections.abc import Iterable, Iterator, Sequence
 from contextlib import suppress
 from datetime import datetime, timezone
 from pathlib import Path
-from shutil import copyfileobj
+from shutil import copyfileobj, copystat
-from typing import Any, BinaryIO, Iterable, Sequence, cast
+from typing import Any, BinaryIO, TypeVar, cast
 
 import img2pdf
 import pikepdf
@@ -27,10 +28,12 @@ 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,
     PriorOcrFoundError,
+    TaggedPDFError,
     UnsupportedImageFormatError,
 )
 from ocrmypdf.helpers import IMG2PDF_KWARGS, Resolution, safe_symlink
@@ -39,13 +42,7 @@ 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
+T = TypeVar("T")
-try:
-    BICUBIC = Image.Resampling.BICUBIC  # type: ignore
-except AttributeError:  # pragma: no cover
-    # Pillow 9 shim
-    BICUBIC = Image.BICUBIC  # type: ignore
-
 log = logging.getLogger(__name__)
 
 VECTOR_PAGE_DPI = 400
@@ -80,34 +77,32 @@ 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...")
@@ -125,7 +120,6 @@ 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
 
 
@@ -147,6 +141,7 @@ def _pdf_guess_version(input_file: Path, search_window=1024) -> str:
 def triage(
     original_filename: str, input_file: Path, output_file: Path, options
 ) -> Path:
+    """Triage the input file. We can handle PDFs and images."""
     try:
         if _pdf_guess_version(input_file):
             if options.image_dpi:
@@ -175,6 +170,7 @@ def get_pdfinfo(
     max_workers: int | None = None,
     check_pages=None,
 ) -> PdfInfo:
+    """Get the PDF info."""
     try:
         return PdfInfo(
             input_file,
@@ -191,22 +187,26 @@ def get_pdfinfo(
 
 
 def validate_pdfinfo_options(context: PdfContext) -> None:
+    """Validate the PDF info options."""
     pdfinfo = context.pdfinfo
     options = context.options
 
     if pdfinfo.needs_rendering:
-        log.error(
+        raise InputFileError(
             "This PDF contains dynamic XFA forms created by Adobe LiveCycle "
             "Designer and can only be read by Adobe Acrobat or Adobe Reader."
         )
-        raise InputFileError()
+    if pdfinfo.has_signature:
+        if options.invalidate_digital_signatures:
+            log.warning("All digital signatures will be invalidated")
+        else:
+            raise DigitalSignatureError()
     if pdfinfo.has_acroform:
         if options.redo_ocr:
-            log.error(
+            raise InputFileError(
                 "This PDF has a user fillable form. --redo-ocr is not "
                 "currently possible on such files."
             )
-            raise InputFileError()
         else:
             log.warning(
                 "This PDF has a fillable form. "
@@ -219,6 +219,16 @@ def validate_pdfinfo_options(context: PdfContext) -> None:
                     "form and all filled form fields. The output PDF will be "
                     "'flattened' and will no longer be fillable."
                 )
+    if pdfinfo.is_tagged:
+        if options.force_ocr or options.skip_text or options.redo_ocr:
+            log.warning(
+                "This PDF is marked as a Tagged PDF. This often indicates "
+                "that the PDF was generated from an office document and does "
+                "not need OCR. PDF pages processed by OCRmyPDF may not be "
+                "tagged correctly."
+            )
+        else:
+            raise TaggedPDFError()
     context.plugin_manager.hook.validate(pdfinfo=pdfinfo, options=options)
 
 
@@ -227,28 +237,19 @@ def _vector_page_dpi(pageinfo: PageInfo) -> int:
     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,
-        options.oversample or 0.0,
-        _vector_page_dpi(pageinfo),
-    )
-    yres = max(
-        pageinfo.dpi.y or VECTOR_PAGE_DPI,
-        options.oversample or 0,
-        _vector_page_dpi(pageinfo),
-    )
-    return Resolution(float(xres), float(yres))
-
-
-def get_page_square_dpi(pageinfo: PageInfo, options) -> Resolution:
     """Get the DPI when we require xres == yres, scaled to physical units.
 
     Page DPI includes UserUnit scaling.
     """
-    xres = pageinfo.dpi.x or 0.0
+    pageinfo = page_context.pageinfo
-    yres = pageinfo.dpi.y or 0.0
+    options = page_context.options
+    if not image_dpi:
+        image_dpi = pageinfo.dpi
+    xres = image_dpi.x or 0.0
+    yres = image_dpi.y or 0.0
     userunit = float(pageinfo.userunit) or 1.0
     units = float(
         max(
@@ -261,17 +262,23 @@ 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(
+    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,
         )
@@ -358,8 +365,10 @@ 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,
@@ -433,6 +442,38 @@ def get_orientation_correction(preview: Path, page_context: PageContext) -> int:
     return 0
 
 
+def calculate_image_dpi(page_context: PageContext) -> Resolution:
+    """Calculate the DPI for the page image."""
+    pageinfo = page_context.pageinfo
+    dpi_profile = pageinfo.page_dpi_profile()
+    if dpi_profile and dpi_profile.average_to_max_dpi_ratio < 0.8:
+        image_dpi = Resolution(dpi_profile.weighted_dpi, dpi_profile.weighted_dpi)
+    else:
+        image_dpi = pageinfo.dpi
+    return image_dpi
+
+
+def calculate_raster_dpi(page_context: PageContext):
+    """Calculate the DPI for rasterization."""
+    # Produce the page image with square resolution or else deskew and OCR
+    # will not work properly.
+    image_dpi = calculate_image_dpi(page_context)
+    dpi_profile = page_context.pageinfo.page_dpi_profile()
+    canvas_dpi = get_canvas_square_dpi(page_context, image_dpi)
+    page_dpi = get_page_square_dpi(page_context, image_dpi)
+    if dpi_profile and dpi_profile.average_to_max_dpi_ratio < 0.8:
+        log.warning(
+            "Weight average image DPI is %0.1f, max DPI is %0.1f. "
+            "The discrepancy may indicate a high detail region on this page, "
+            "but could also indicate a problem with the input PDF file. "
+            "Page image will be rendered at %0.1f DPI.",
+            dpi_profile.weighted_dpi,
+            dpi_profile.max_dpi,
+            canvas_dpi.to_scalar(),
+        )
+    return canvas_dpi, page_dpi
+
+
 def rasterize(
     input_file: Path,
     page_context: PageContext,
@@ -484,10 +525,7 @@ 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,
@@ -504,6 +542,7 @@ def rasterize(
 
 
 def preprocess_remove_background(input_file: Path, page_context: PageContext) -> Path:
+    """Remove the background from the input image (temporarily disabled)."""
     if any(image.bpc > 1 for image in page_context.pageinfo.images):
         raise NotImplementedError("--remove-background is temporarily not implemented")
         # output_file = page_context.get_path('pp_rm_bg.png')
@@ -524,7 +563,7 @@ def preprocess_deskew(input_file: Path, page_context: PageContext) -> Path:
         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)
@@ -534,7 +573,7 @@ def preprocess_deskew(input_file: Path, page_context: PageContext) -> Path:
         # resampling if image is mode '1' or 'P'
         deskewed = im.rotate(
             deskew_angle_degrees,
-            resample=BICUBIC,
+            resample=Image.Resampling.BICUBIC,
             fillcolor=ImageColor.getcolor('white', mode=im.mode),  # type: ignore
         )
         deskewed.save(output_file, dpi=dpi)
@@ -543,12 +582,13 @@ def preprocess_deskew(input_file: Path, page_context: PageContext) -> Path:
 
 
 def preprocess_clean(input_file: Path, page_context: PageContext) -> Path:
+    """Clean the input image using unpaper."""
     output_file = page_context.get_path('pp_clean.png')
-    dpi = get_page_square_dpi(page_context.pageinfo, page_context.options)
+    dpi = get_page_square_dpi(page_context, calculate_image_dpi(page_context))
     return unpaper.clean(
         input_file,
         output_file,
-        dpi=dpi.x,
+        dpi=dpi.to_scalar(),
         unpaper_args=page_context.options.unpaper_args,
     )
 
@@ -603,6 +643,7 @@ def create_ocr_image(image: Path, page_context: PageContext) -> Path:
 
 
 def ocr_engine_hocr(input_file: Path, page_context: PageContext) -> tuple[Path, Path]:
+    """Run the OCR engine and generate hOCR output."""
     hocr_out = page_context.get_path('ocr_hocr.hocr')
     hocr_text_out = page_context.get_path('ocr_hocr.txt')
     options = page_context.options
@@ -634,6 +675,10 @@ def should_visible_page_image_use_jpg(pageinfo: PageInfo) -> bool:
 
 
 def create_visible_page_jpg(image: Path, page_context: PageContext) -> Path:
+    """Create a visible page image in JPEG format.
+
+    This is intended to be used when all images on the page were originally JPEGs.
+    """
     output_file = page_context.get_path('visible.jpg')
     with Image.open(image) as im:
         # At this point the image should be a .png, but deskew, unpaper
@@ -645,7 +690,7 @@ 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())
@@ -655,6 +700,7 @@ def create_visible_page_jpg(image: Path, page_context: PageContext) -> Path:
 def create_pdf_page_from_image(
     image: Path, page_context: PageContext, orientation_correction: int
 ) -> Path:
+    """Create a PDF page from a page image."""
     # We rasterize a square DPI version of each page because most image
     # processing tools don't support rectangular DPI. Use the square DPI as it
     # accurately describes the image. It would be possible to resample the image
@@ -686,9 +732,10 @@ def create_pdf_page_from_image(
 
 
 def render_hocr_page(hocr: Path, page_context: PageContext) -> Path:
+    """Render the hOCR page to a PDF."""
     options = page_context.options
     output_file = page_context.get_path('ocr_hocr.pdf')
-    dpi = get_page_square_dpi(page_context.pageinfo, options)
+    dpi = get_page_square_dpi(page_context, calculate_image_dpi(page_context))
     debug_mode = options.pdf_renderer == 'hocrdebug'
 
     hocrtransform = HocrTransform(hocr_filename=hocr, dpi=dpi.x)  # square
@@ -705,6 +752,7 @@ def render_hocr_page(hocr: Path, page_context: PageContext) -> Path:
 def ocr_engine_textonly_pdf(
     input_image: Path, page_context: PageContext
 ) -> tuple[Path, Path]:
+    """Run the OCR engine and generate a text-only PDF (will look blank)."""
     output_pdf = page_context.get_path('ocr_tess.pdf')
     output_text = page_context.get_path('ocr_tess.txt')
     options = page_context.options
@@ -720,6 +768,7 @@ def ocr_engine_textonly_pdf(
 
 
 def get_docinfo(base_pdf: pikepdf.Pdf, context: PdfContext) -> dict[str, str]:
+    """Read the document info and store it in a dictionary."""
     options = context.options
 
     def from_document_info(key):
@@ -751,12 +800,28 @@ def get_docinfo(base_pdf: pikepdf.Pdf, context: PdfContext) -> dict[str, str]:
 
 
 def generate_postscript_stub(context: PdfContext) -> Path:
+    """Generates a PostScript file stub for the given PDF context.
+
+    Args:
+        context: The PDF context to generate the PostScript file stub for.
+
+    Returns:
+        Path: The path to the generated PostScript file stub.
+    """
     output_file = context.get_path('pdfa.ps')
     generate_pdfa_ps(output_file)
     return output_file
 
 
 def convert_to_pdfa(input_pdf: Path, input_ps_stub: Path, context: PdfContext) -> Path:
+    """Converts the given PDF to PDF/A.
+
+    Args:
+        input_pdf: The input PDF file path (presumably not PDF/A).
+        input_ps_stub: The input PostScript file path, containing instructions
+            for the PDF/A generator to use.
+        context: The PDF context.
+    """
     options = context.options
     input_pdfinfo = context.pdfinfo
     fix_docinfo_file = context.get_path('fix_docinfo.pdf')
@@ -767,21 +832,8 @@ 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)
@@ -791,7 +843,7 @@ 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()
@@ -804,7 +856,30 @@ def convert_to_pdfa(input_pdf: Path, input_ps_stub: Path, context: PdfContext) -
     return output_file
 
 
+def _repair_docinfo_nuls(pdf):
+    """If the DocumentInfo block contains NUL characters, remove them.
+
+    If the DocumentInfo block is malformed, log an error and continue.
+    """
+    modified = False
+    try:
+        if not isinstance(pdf.docinfo, pikepdf.Dictionary):
+            raise TypeError("DocumentInfo is not a dictionary")
+        for k, v in pdf.docinfo.items():
+            if isinstance(v, str) and b'\x00' in bytes(v):
+                pdf.docinfo[k] = bytes(v).replace(b'\x00', b'')
+                modified = True
+    except TypeError:
+        # TypeError can also be raised if dictionary items are unexpected types
+        log.error("File contains a malformed DocumentInfo block - continuing anyway.")
+    return modified
+
+
 def should_linearize(working_file: Path, context: PdfContext) -> bool:
+    """Determine whether the PDF should be linearized.
+
+    For smaller files, linearization is not worth the effort.
+    """
     filesize = os.stat(working_file).st_size
     if filesize > (context.options.fast_web_view * 1_000_000):
         return True
@@ -812,6 +887,11 @@ def should_linearize(working_file: Path, context: PdfContext) -> bool:
 
 
 def get_pdf_save_settings(output_type: str) -> dict[str, Any]:
+    """Get pikepdf.Pdf.save settings for the given output type.
+
+    Essentially, don't use features that are incompatible with a given
+    PDF/A specification.
+    """
     if output_type == 'pdfa-1':
         # Trigger recompression to ensure object streams are removed, because
         # Acrobat complains about them in PDF/A-1b validation.
@@ -830,6 +910,11 @@ def get_pdf_save_settings(output_type: str) -> dict[str, Any]:
 
 
 def metadata_fixup(working_file: Path, context: PdfContext) -> Path:
+    """Fix certain metadata fields after Ghostscript PDF/A conversion.
+
+    Also report on metadata in the input file that was not retained during
+    PDF/A conversion.
+    """
     output_file = context.get_path('metafix.pdf')
     options = context.options
 
@@ -852,43 +937,43 @@ def metadata_fixup(working_file: Path, context: PdfContext) -> Path:
 
     with pikepdf.open(context.origin) as original, pikepdf.open(working_file) as pdf:
         docinfo = get_docinfo(original, context)
-        with pdf.open_metadata() as meta_pdf:
+        with original.open_metadata(
-            meta_pdf.load_from_docinfo(docinfo, delete_missing=False, raise_failure=False)
+            set_pikepdf_as_editor=False, update_docinfo=False, strict=False
+        ) as meta_original, pdf.open_metadata() as meta_pdf:
+            meta_pdf.load_from_docinfo(
+                docinfo, delete_missing=False, raise_failure=False
+            )
             # If xmp:CreateDate is missing, set it to the modify date to
             # ensure consistency with Ghostscript.
             if 'xmp:CreateDate' not in meta_pdf:
                 meta_pdf['xmp:CreateDate'] = meta_pdf.get('xmp:ModifyDate', '')
-
+            if meta_pdf.get('dc:title') == 'Untitled':
-            with original.open_metadata(
+                # Ghostscript likes to set title to Untitled if omitted from input.
-                set_pikepdf_as_editor=False, update_docinfo=False, strict=False
+                # Reverse this, because PDF/A TechNote 0003:Metadata in PDF/A-1
-            ) as meta_original:
+                # and the XMP Spec do not make this recommendation.
-                if meta_pdf.get('dc:title') == 'Untitled':
+                if 'dc:title' not in meta_original:
-                    # Ghostscript likes to set title to Untitled if omitted from input.
+                    del meta_pdf['dc:title']
-                    # Reverse this, because PDF/A TechNote 0003:Metadata in PDF/A-1
+            # If the user explicitly specified an empty string for any of the
-                    # and the XMP Spec do not make this recommendation.
+            # following, they should be unset and not reported as missing in
-                    if 'dc:title' not in meta_original:
+            # the output pdf. Note that some metadata fields use differing names
-                        del meta_pdf['dc:title']
+            # between PDF-A and PDF.
-                # If the user explicitly specified an empty string for any of the
+            for meta in [meta_pdf, meta_original]:
-                # following, they should be unset and not reported as missing in
+                if options.title == '' and 'dc:title' in meta:
-                # the output pdf. Note that some metadata fields use differing names
+                    del meta['dc:title']  # PDF-A and PDF
-                # between PDF-A and PDF.
+                if options.author == '':
-                for meta in [meta_pdf, meta_original]:
+                    if 'dc:creator' in meta:
-                    if options.title == '' and 'dc:title' in meta:
+                        del meta['dc:creator']  # PDF-A (Not xmp:CreatorTool)
-                        del meta['dc:title']  # PDF-A and PDF
+                    if 'pdf:Author' in meta:
-                    if options.author == '':
+                        del meta['pdf:Author']  # PDF
-                        if 'dc:creator' in meta:
+                if options.subject == '':
-                            del meta['dc:creator']  # PDF-A (Not xmp:CreatorTool)
+                    if 'dc:description' in meta:
-                        if 'pdf:Author' in meta:
+                        del meta['dc:description']  # PDF-A
-                            del meta['pdf:Author']  # PDF
+                    if 'dc:subject' in meta:
-                    if options.subject == '':
+                        del meta['dc:subject']  # PDF
-                        if 'dc:description' in meta:
+                if options.keywords == '' and 'pdf:Keywords' in meta:
-                            del meta['dc:description']  # PDF-A
+                    del meta['pdf:Keywords']  # PDF-A and PDF
-                        if 'dc:subject' in meta:
+            meta_missing = set(meta_original.keys()) - set(meta_pdf.keys())
-                            del meta['dc:subject']  # PDF
+            report_on_metadata(meta_missing)
-                    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
@@ -907,6 +992,17 @@ def metadata_fixup(working_file: Path, context: PdfContext) -> Path:
 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:
@@ -919,6 +1015,7 @@ def _file_size_ratio(
 def optimize_pdf(
     input_file: Path, context: PdfContext, executor: Executor
 ) -> tuple[Path, Sequence[str]]:
+    """Optimize the given PDF file."""
     output_file = context.get_path('optimize.pdf')
     output_pdf, messages = context.plugin_manager.hook.optimize_pdf(
         input_pdf=input_file,
@@ -937,7 +1034,20 @@ def optimize_pdf(
     return output_pdf, messages
 
 
-def enumerate_compress_ranges(iterable):
+def enumerate_compress_ranges(
+    iterable: Iterable[T],
+) -> Iterator[tuple[tuple[int, int], T]]:
+    """Enumerate the ranges of non-empty elements in an iterable.
+
+    Compresses consecutive ranges of length 1 into single elements.
+
+    Args:
+        iterable: An iterable of elements to enumerate.
+
+    Yields:
+        A tuple containing a range of indices and the corresponding element.
+        If the element is None, the range represents a skipped range of indices.
+    """
     skipped_from, index = None, None
     for index, txt_file in enumerate(iterable):
         index += 1
@@ -954,21 +1064,22 @@ def enumerate_compress_ranges(iterable):
 
 
 def merge_sidecars(txt_files: Iterable[Path | None], context: PdfContext) -> Path:
+    """Merge the page sidecar files into a single file.
+
+    Sidecar files are created by the OCR engine and contain the text for each
+    page in the PDF. This function merges the sidecar files into a single file
+    and returns the path to the merged file.
+    """
     output_file = context.get_path('sidecar.txt')
     with open(output_file, 'w', encoding="utf-8") as stream:
         for (from_, to_), txt_file in enumerate_compress_ranges(txt_files):
             if from_ != 1:
-                stream.write('\f')  # Form feed between pages
+                stream.write('\f')  # Form feed between pages for all pages after first
             if txt_file:
-                with open(txt_file, encoding="utf-8") as in_:
+                txt = txt_file.read_text(encoding="utf-8")
-                    txt = in_.read()
+                # Some versions of Tesseract add a form feed at the end and
-                    # Some OCR engines (e.g. Tesseract v4 alpha) add form feeds
+                # others don't. Remove it if it exists, since we add one manually.
-                    # between pages, and some do not. For consistency, we ignore
+                stream.write(txt.removesuffix('\f'))
-                    # any added by the OCR engine and them on our own.
-                    if txt.endswith('\f'):
-                        stream.write(txt[:-1])
-                    else:
-                        stream.write(txt)
             else:
                 if from_ != to_:
                     pages = f'{from_}-{to_}'
@@ -979,8 +1090,18 @@ def merge_sidecars(txt_files: Iterable[Path | None], context: PdfContext) -> Pat
 
 
 def copy_final(
-    input_file: Path, output_file: str | Path | BinaryIO, _context: PdfContext
+    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 intermediate 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 == '-':
@@ -995,5 +1116,11 @@ def copy_final(
             # At this point we overwrite the output_file specified by the user
             # use copyfileobj because then we use open() to create the file and
             # get the appropriate umask, ownership, etc.
-            with open(output_file, 'wb') as output_stream:
+            with open(output_file, 'w+b') as output_stream:
                 copyfileobj(input_stream, output_stream)
+            # Attempt to copy file attributes from input to output
+            with suppress(OSError):
+                # Copy original file's permissions, ownership, etc. if possible
+                copystat(context.options.input_file, output_file)
+                # Set output file's modification time to now
+                Path(output_file).touch(exist_ok=True)

src/ocrmypdf/_plugin_manager.py

@@ -10,8 +10,8 @@ import importlib
 import importlib.util
 import pkgutil
 import sys
+from collections.abc import Sequence
 from pathlib import Path
-from typing import Sequence
 
 import pluggy
 
@@ -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/_sync.py

@@ -13,12 +13,13 @@ import logging.handlers
 import os
 import sys
 import threading
+from collections.abc import Sequence
 from concurrent.futures.process import BrokenProcessPool
 from concurrent.futures.thread import BrokenThreadPool
 from functools import partial
 from pathlib import Path
 from tempfile import mkdtemp
-from typing import NamedTuple, Sequence, cast
+from typing import NamedTuple, cast
 
 import PIL
 
@@ -104,6 +105,7 @@ def preprocess(
     deskew: bool,
     clean: bool,
 ) -> Path:
+    """Preprocess an image."""
     if remove_background:
         image = preprocess_remove_background(image, page_context)
     if deskew:
@@ -116,6 +118,7 @@ def preprocess(
 def make_intermediate_images(
     page_context: PageContext, orientation_correction: int
 ) -> tuple[Path, Path | None]:
+    """Create intermediate and preprocessed images for OCR."""
     options = page_context.options
 
     ocr_image = preprocess_out = None
@@ -173,6 +176,7 @@ def make_intermediate_images(
 
 
 def exec_page_sync(page_context: PageContext) -> PageResult:
+    """Execute a pipeline for a single page synchronously."""
     options = page_context.options
     tls.pageno = page_context.pageno + 1
 
@@ -233,6 +237,7 @@ def exec_page_sync(page_context: PageContext) -> PageResult:
 def post_process(
     pdf_file: Path, context: PdfContext, executor: Executor
 ) -> tuple[Path, Sequence[str]]:
+    """Postprocess the PDF file."""
     pdf_out = pdf_file
     if context.options.output_type.startswith('pdfa'):
         ps_stub_out = generate_postscript_stub(context)
@@ -243,6 +248,7 @@ def post_process(
 
 
 def worker_init(max_pixels: int) -> None:
+    """Initialize a worker thread or process."""
     # In Windows, child process will not inherit our change to this value in
     # the parent process, so ensure workers get it set. Not needed when running
     # threaded, but harmless to set again.
@@ -251,8 +257,8 @@ def worker_init(max_pixels: int) -> None:
 
 
 def exec_concurrent(context: PdfContext, executor: Executor) -> Sequence[str]:
-    """Execute the pipeline concurrently."""
+    """Execute the OCR pipeline concurrently."""
-    # Run exec_page_sync on every page context
+    # Run exec_page_sync on every page
     options = context.options
     max_workers = min(len(context.pdfinfo), options.jobs)
     if max_workers > 1:
@@ -262,6 +268,7 @@ def exec_concurrent(context: PdfContext, executor: Executor) -> Sequence[str]:
     ocrgraft = OcrGrafter(context)
 
     def update_page(result: PageResult, pbar):
+        """After OCR is complete for a page, update the PDF."""
         try:
             tls.pageno = result.pageno + 1
             sidecars[result.pageno] = result.text
@@ -317,7 +324,7 @@ def configure_debug_logging(
 ) -> logging.FileHandler:
     """Create a debug log file at a specified location.
 
-    Arguments:
+    Args:
         log_filename: Where to the put the log file.
         prefix: The logging domain prefix that should be sent to the log.
     """
@@ -338,6 +345,17 @@ def run_pipeline(
     plugin_manager: OcrmypdfPluginManager | None,
     api: bool = False,
 ) -> ExitCode:
+    """Run the OCR pipeline.
+
+    Args:
+        options: The parsed command line options.
+        plugin_manager: The plugin manager to use. If not provided, one will be
+            created.
+        api: If ``True``, the pipeline is being run from the API. This is used
+            to manage exceptions in a way appropriate for API or CLI usage.
+            For CLI (``api=False``), exceptions are printed and described;
+            for API use, they are propagated to the caller.
+    """
     # Any changes to options will not take effect for options that are already
     # bound to function parameters in the pipeline. (For example
     # options.input_file, options.pdf_renderer are already bound.)

src/ocrmypdf/_validation.py

@@ -12,9 +12,9 @@ import os
 import sys
 import unicodedata
 from argparse import Namespace
+from collections.abc import Sequence
 from pathlib import Path
 from shutil import copyfileobj
-from typing import Sequence
 
 import pikepdf
 import PIL
@@ -43,10 +43,11 @@ 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."
         )
 
@@ -204,16 +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):
@@ -240,7 +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)
 
 
@@ -255,6 +245,18 @@ def check_options(options: Namespace, plugin_manager: PluginManager) -> None:
     _check_plugin_options(options, plugin_manager)
 
 
+def _in_docker():
+    return Path('/.dockerenv').exists()
+
+
+def _in_snap():
+    try:
+        cgroup_text = Path('/proc/self/cgroup').read_text()
+        return 'snap.ocrmypdf' in cgroup_text
+    except FileNotFoundError:
+        return False
+
+
 def create_input_file(options: Namespace, work_folder: Path) -> tuple[Path, str]:
     if options.input_file == '-':
         # stdin
@@ -278,7 +280,7 @@ def create_input_file(options: Namespace, work_folder: Path) -> tuple[Path, str]
             return target, os.fspath(options.input_file)
         except FileNotFoundError as e:
             msg = f"File not found - {options.input_file}"
-            if Path('/.dockerenv').exists():  # pragma: no cover
+            if _in_docker():  # pragma: no cover
                 msg += (
                     "\nDocker cannot your working directory unless you "
                     "explicitly share it with the Docker container and set up"
@@ -288,6 +290,15 @@ def create_input_file(options: Namespace, work_folder: Path) -> tuple[Path, str]
                     "\tdocker run -i --rm jbarlow83/ocrmypdf - - <input.pdf >output.pdf"
                     "\n"
                 )
+            elif _in_snap():  # pragma: no cover
+                msg += (
+                    "\nSnap applications cannot access files outside of "
+                    "your home directory unless you explicitly allow it. "
+                    "You may find it easier to use stdin/stdout:"
+                    "\n"
+                    "\tsnap run ocrmypdf - - <input.pdf >output.pdf"
+                    "\n"
+                )
             raise InputFileError(msg) from e
 
 

src/ocrmypdf/api.py

@@ -9,16 +9,17 @@ import logging
 import os
 import sys
 import threading
+from argparse import Namespace
+from collections.abc import Iterable
 from enum import IntEnum
 from io import IOBase
 from pathlib import Path
-from typing import AnyStr, BinaryIO, Iterable, Union
+from typing import AnyStr, BinaryIO, Union
 from warnings import warn
 
-import coloredlogs
+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 +47,7 @@ def configure_logging(
     *,
     progress_bar_friendly: bool = True,
     manage_root_logger: bool = False,
-    plugin_manager=None,
+    plugin_manager: pluggy.PluginManager | None = None,
 ):
     """Set up logging.
 
@@ -112,14 +113,7 @@ def configure_logging(
     else:
         fmt = '%(pageno)s%(message)s'
 
-    use_colors = progress_bar_friendly
     formatter = None
-    if use_colors:
-        use_colors = enable_ansi_support()
-        if use_colors:
-            use_colors = coloredlogs.terminal_supports_colors()
-        if use_colors:
-            formatter = coloredlogs.ColoredFormatter(fmt=fmt)
 
     if not formatter:
         formatter = logging.Formatter(fmt=fmt)
@@ -141,8 +135,21 @@ def configure_logging(
 
 def create_options(
     *, input_file: PathOrIO, output_file: PathOrIO, parser: ArgumentParser, **kwargs
-):
+) -> Namespace:
-    """Construct an options object from the input/output files and keyword arguments."""
+    """Construct an options object from the input/output files and keyword arguments.
+
+    Args:
+        input_file: Input file path or file object.
+        output_file: Output file path or file object.
+        parser: ArgumentParser object.
+        **kwargs: Keyword arguments.
+
+    Returns:
+        argparse.Namespace: A Namespace object containing the parsed arguments.
+
+    Raises:
+        TypeError: If the type of a keyword argument is not supported.
+    """
     cmdline = []
     deferred = []
 
@@ -203,7 +210,7 @@ def create_options(
     return options
 
 
-def ocr(  # noqa: ruff: disable=D417
+def ocr(  # noqa: D417
     input_file: PathOrIO,
     output_file: PathOrIO,
     *,
@@ -234,6 +241,7 @@ def ocr(  # noqa: ruff: disable=D417
     png_quality: int | None = None,
     jbig2_lossy: bool | None = None,
     jbig2_page_group_size: int | None = None,
+    jbig2_threshold: float | None = None,
     pages: str | None = None,
     max_image_mpixels: float | None = None,
     tesseract_config: Iterable[str] | None = None,
@@ -243,12 +251,16 @@ def ocr(  # noqa: ruff: disable=D417
     pdf_renderer: str | None = None,
     tesseract_timeout: float | None = None,
     tesseract_non_ocr_timeout: float | None = None,
+    tesseract_downsample_above: int | None = None,
+    tesseract_downsample_large_images: bool | None = None,
     rotate_pages_threshold: float | None = None,
     pdfa_image_compression: str | None = None,
+    color_conversion_strategy: str | None = None,
     user_words: os.PathLike | None = None,
     user_patterns: os.PathLike | None = None,
     fast_web_view: float | None = None,
     continue_on_soft_render_error: bool | None = None,
+    invalidate_digital_signatures: bool | None = None,
     plugins: Iterable[StrPath] | None = None,
     plugin_manager=None,
     keep_temporary_files: bool | None = None,
@@ -349,7 +361,6 @@ def ocr(  # noqa: ruff: disable=D417
 
 __all__ = [
     'PageNumberFilter',
-    'TqdmConsole',
     'Verbosity',
     'check_options',
     'configure_logging',

src/ocrmypdf/builtin_plugins/concurrency.py

@@ -12,18 +12,19 @@ import queue
 import signal
 import sys
 import threading
+from collections.abc import Iterable
 from concurrent.futures import ProcessPoolExecutor, ThreadPoolExecutor, as_completed
 from contextlib import suppress
-from typing import Callable, Iterable, Type, Union
+from typing import Callable, Union
 
-from tqdm import tqdm
+from rich.console import Console as RichConsole
 
 from ocrmypdf import Executor, hookimpl
-from ocrmypdf._logging import TqdmConsole
+from ocrmypdf._logging import RichLoggingHandler, RichTqdmProgressAdapter
 from ocrmypdf.exceptions import InputFileError
 from ocrmypdf.helpers import remove_all_log_handlers
 
-FuturesExecutorClass = Union[Type[ThreadPoolExecutor], Type[ProcessPoolExecutor]]
+FuturesExecutorClass = Union[type[ThreadPoolExecutor], type[ProcessPoolExecutor]]
 Queue = Union[multiprocessing.Queue, queue.Queue]
 UserInit = Callable[[], None]
 WorkerInit = Callable[[Queue, UserInit, int], None]
@@ -68,7 +69,7 @@ def process_init(q: Queue, user_init: UserInit, loglevel) -> None:
         # Windows and Cygwin do not have pthread_sigmask or SIGBUS
         signal.signal(signal.SIGBUS, process_sigbus)
 
-    # Remove any log handlers that belong to the parent process
+    # Remove any log handlers inherited from the parent process
     root = logging.getLogger()
     remove_all_log_handlers(root)
 
@@ -95,15 +96,6 @@ def thread_init(q: Queue, user_init: UserInit, loglevel) -> None:
 class StandardExecutor(Executor):
     """Standard OCRmyPDF concurrent task executor."""
 
-    def _cancel_futures_kwargs(self):
-        """Shim older Pythons that do not have Executor.shutdown(...cancel_futures=).
-
-        Remove this code when support for Python 3.8 is dropped.
-        """
-        if sys.version_info[:2] < (3, 9):
-            return {}
-        return dict(cancel_futures=True)
-
     def _execute(
         self,
         *,
@@ -127,6 +119,11 @@ class StandardExecutor(Executor):
         # Regardless of whether we use_threads for worker processes, the log_listener
         # must be a thread. Make sure we create the listener after the worker pool,
         # so that it does not get forked into the workers.
+        # If use_threads is False, we are currently guilty of creating a thread before
+        # forking on Linux, which is not recommended. However, we take a big
+        # performance hit in pdfinfo if we can't fork. Long term solution is to
+        # replace most of this with an asyncio implementation, and probably to
+        # migrate some of pdfinfo into C++ or Rust.
         listener = threading.Thread(target=log_listener, args=(log_queue,))
         listener.start()
 
@@ -142,7 +139,7 @@ class StandardExecutor(Executor):
                     task_finished(result, pbar)
             except KeyboardInterrupt:
                 # Terminate pool so we exit instantly
-                executor.shutdown(wait=False, **self._cancel_futures_kwargs())
+                executor.shutdown(wait=False, cancel_futures=True)
                 raise
             except Exception:
                 if not os.environ.get("PYTEST_CURRENT_TEST", ""):
@@ -151,7 +148,7 @@ class StandardExecutor(Executor):
                     # results will be discard. But if the condition above is True,
                     # then we are running in pytest, and we want everything to exit
                     # as cleanly as possible so that we get good error messages.
-                    executor.shutdown(wait=False, **self._cancel_futures_kwargs())
+                    executor.shutdown(wait=False, cancel_futures=True)
                 raise
             finally:
                 # Terminate log listener
@@ -168,13 +165,20 @@ 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
@@ -67,7 +109,7 @@ def generate_pdfa(
     pdf_pages,
     pdfmark,
     output_file,
-    compression,
+    context,
     pdf_version,
     pdfa_part,
     progressbar_class,
@@ -77,7 +119,8 @@ def generate_pdfa(
     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,

src/ocrmypdf/builtin_plugins/optimize.py

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

src/ocrmypdf/builtin_plugins/tesseract_ocr.py

@@ -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(
@@ -137,7 +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,
     )
 
@@ -175,6 +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:
@@ -200,7 +212,7 @@ class TesseractOcrEngine(OcrEngine):
 
     @staticmethod
     def version():
-        return tesseract.version()
+        return str(tesseract.version())
 
     @staticmethod
     def creator_tag(options):

src/ocrmypdf/cli.py

@@ -6,7 +6,8 @@
 from __future__ import annotations
 
 import argparse
-from typing import Any, Callable, Mapping, TypeVar
+from collections.abc import Mapping
+from typing import Any, Callable, TypeVar
 
 from ocrmypdf._version import PROGRAM_NAME as _PROGRAM_NAME
 from ocrmypdf._version import __version__ as _VERSION
@@ -15,7 +16,11 @@ T = TypeVar('T', int, float)
 
 
 def numeric(basetype: Callable[[Any], T], min_: T | None = None, max_: T | None = None):
-    """Validator for numeric params."""
+    """Validator for numeric command line parameters.
+
+    Stipulates that the value must be of type basetype (typically int or float), and
+    optionally, within the range [min_, max_].
+    """
     min_ = basetype(min_) if min_ is not None else None
     max_ = basetype(max_) if max_ is not None else None
 
@@ -177,7 +182,9 @@ Online documentation is located at:
         '--image-dpi',
         metavar='DPI',
         type=int,
-        help="For input image instead of PDF, use this DPI instead of file's.",
+        help="When the input file is an image, not a PDF, use this DPI instead "
+        "of the DPI claimed by the input file. If the input does not claim a "
+        "sensible DPI, this option will be required.",
     )
     parser.add_argument(
         '--output-type',
@@ -359,6 +366,13 @@ Online documentation is located at:
         help="Skip OCR on pages larger than the specified amount of megapixels, "
         "but include skipped pages in final output",
     )
+    ocrsettings.add_argument(
+        '--invalidate-digital-signatures',
+        action='store_true',
+        help="Normally, OCRmyPDF will refuse to OCR a PDF that has a digital "
+        "signature. This option allows OCR to proceed, but the digital signature "
+        "will be invalidated.",
+    )
 
     advanced = parser.add_argument_group(
         "Advanced", "Advanced options to control OCRmyPDF"
@@ -395,19 +409,6 @@ Online documentation is located at:
         help="Only rotate pages when confidence is above this value (arbitrary "
         "units reported by tesseract)",
     )
-    advanced.add_argument(
-        '--pdfa-image-compression',
-        choices=['auto', 'jpeg', 'lossless'],
-        default='auto',
-        help="Specify how to compress images in the output PDF/A. 'auto' lets "
-        "OCRmyPDF decide.  'jpeg' changes all grayscale and color images to "
-        "JPEG compression.  'lossless' uses PNG-style lossless compression "
-        "for all images.  Monochrome images are always compressed using a "
-        "lossless codec.  Compression settings "
-        "are applied to all pages, including those for which OCR was "
-        "skipped.  Not supported for --output-type=pdf ; that setting "
-        "preserves the original compression of all images.",
-    )
     advanced.add_argument(
         '--fast-web-view',
         type=numeric(float, 0),

src/ocrmypdf/exceptions.py

@@ -113,3 +113,27 @@ class TesseractConfigError(ExitCodeException):
 
     exit_code = ExitCode.invalid_config
     message = "Error occurred while parsing a Tesseract configuration file"
+
+
+class DigitalSignatureError(InputFileError):
+    """PDF has a digital signature."""
+
+    message = dedent(
+        """\
+        Input PDF has a digital signature. OCR would alter the document,
+        invalidating the signature.
+        """
+    )
+
+
+class TaggedPDFError(InputFileError):
+    """PDF is tagged."""
+
+    message = dedent(
+        """\
+        This PDF is marked as a Tagged PDF. This often indicates
+        that the PDF was generated from an office document and does
+        not need OCR. Use --force-ocr, --skip-text or --redo-ocr to
+        override this error.
+        """
+    )

src/ocrmypdf/extra_plugins/semfree.py

@@ -12,7 +12,7 @@ worker communicates only with the main process.
 
 This is not without drawbacks. If the tasks are not "even" in size, which cannot
 be guaranteed, some workers may end up with too much work while others are idle.
-It is less efficient than the standard implementation, so not th edefault.
+It is less efficient than the standard implementation, so not the default.
 """
 
 from __future__ import annotations
@@ -20,12 +20,13 @@ from __future__ import annotations
 import logging
 import logging.handlers
 import signal
+from collections.abc import Iterable, Iterator
 from contextlib import suppress
 from enum import Enum, auto
 from itertools import islice, repeat, takewhile, zip_longest
 from multiprocessing import Pipe, Process
 from multiprocessing.connection import Connection, wait
-from typing import Callable, Iterable, Iterator
+from typing import Callable
 
 from ocrmypdf import Executor, hookimpl
 from ocrmypdf._concurrent import NullProgressBar

src/ocrmypdf/helpers.py

@@ -10,30 +10,29 @@ import multiprocessing
 import os
 import shutil
 import warnings
-from collections.abc import Iterable
+from collections.abc import Iterable, Sequence
 from contextlib import suppress
+from decimal import Decimal
 from io import StringIO
 from math import isclose, isfinite
 from pathlib import Path
-from typing import Any, Generic, Sequence, SupportsFloat, SupportsRound, TypeVar
+from statistics import harmonic_mean
+from typing import (
+    Any,
+    Callable,
+    Generic,
+    TypeVar,
+)
 
 import img2pdf
 import pikepdf
-from packaging.version import Version
 
 log = logging.getLogger(__name__)
 
-if Version(img2pdf.__version__) < Version('0.4.0'):
+IMG2PDF_KWARGS = dict(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 +76,40 @@ 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 +121,11 @@ 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 +140,7 @@ 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 +155,7 @@ def safe_symlink(input_file: os.PathLike, soft_link_name: os.PathLike):
     # Guard against soft linking to oneself
     if input_file == soft_link_name:
         log.warning(
-            "No symbolic link created. You are using  the original data directory "
+            "No symbolic link created. You are using the original data directory "
             "as the working directory."
         )
         return
@@ -163,7 +181,7 @@ 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 +300,12 @@ 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 +318,13 @@ 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):
+        pikepdf._core.set_access_default_mmap(True)
-    #         log.debug("pikepdf mmap enabled")
+        log.debug(
-    # except AttributeError:
+            "pikepdf mmap "
-    #     log.debug("pikepdf mmap not available")
+            + ('enabled' if pikepdf._core.get_access_default_mmap() else 'disabled')
-    # We found a race condition probably related to pybind issue #2252 that can
+        )
-    # cause a crash. For now, disable pikepdf mmap to be on the safe side.
+    except AttributeError:
-    # Fix is not in pybind11 2.6.0
+        log.debug("pikepdf mmap not available")
-    # 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

@@ -6,20 +6,11 @@
 from __future__ import annotations
 
 import logging
-from functools import singledispatch
 from math import floor, sqrt
-from typing import Optional, Tuple
+from typing import Optional
 
 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.
@@ -43,15 +34,14 @@ def bytes_per_pixel(mode: str) -> int:
     return 4
 
 
-@singledispatch
+def _calculate_downsample(
-def calculate_downsample(
+    image_size: tuple[int, int],
-    image_size: Tuple[int, int],
     bytes_per_pixel: int,
     *,
-    max_size: Optional[Tuple[int, int]] = None,
+    max_size: Optional[tuple[int, int]] = None,
     max_pixels: Optional[int] = None,
     max_bytes: Optional[int] = None,
-) -> Tuple[int, int]:
+) -> 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.
@@ -105,15 +95,13 @@ def calculate_downsample(
     return size
 
 
-@calculate_downsample.register
+def calculate_downsample(
-def _(
     image: Image.Image,
-    arg: None = None,
     *,
-    max_size: Optional[Tuple[int, int]] = None,
+    max_size: Optional[tuple[int, int]] = None,
     max_pixels: Optional[int] = None,
     max_bytes: Optional[int] = None,
-) -> Tuple[int, int]:
+) -> 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.
@@ -126,7 +114,7 @@ def _(
         max_bytes: The maximum number of bytes in the image. RGB is counted as 4
             bytes; all other modes are counted as 1 byte.
     """
-    return calculate_downsample(
+    return _calculate_downsample(
         image.size,
         bytes_per_pixel(image.mode),
         max_size=max_size,
@@ -139,7 +127,7 @@ def downsample_image(
     image: Image.Image,
     new_size: tuple[int, int],
     *,
-    resample_mode: Image.Resampling = Resampling.BICUBIC,
+    resample_mode: Image.Resampling = Image.Resampling.BICUBIC,
     reducing_gap: int = 3,
 ) -> Image.Image:
     """Downsample an image to fit within the given limits.

src/ocrmypdf/optimize.py

@@ -11,9 +11,10 @@ import sys
 import tempfile
 import threading
 from collections import defaultdict
+from collections.abc import Iterator, MutableSet, Sequence
 from os import fspath
 from pathlib import Path
-from typing import Callable, Iterator, MutableSet, NamedTuple, NewType, Sequence
+from typing import Callable, NamedTuple, NewType
 from zlib import compress
 
 import img2pdf
@@ -68,10 +69,10 @@ 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 +127,12 @@ def extract_image_filter(
 
 
 def extract_image_jbig2(
-    *, pike: Pdf, root: Path, image: Stream, xref: Xref, options
+    *, pdf: Pdf, root: Path, image: Stream, xref: Xref, options
 ) -> XrefExt | None:
     """Extract an image, saving it as a JBIG2 file."""
     del options  # unused arg
 
-    result = extract_image_filter(pike, root, image, xref)
+    result = extract_image_filter(pdf, root, image, xref)
     if result is None:
         return None
     pim, filtdp = result
@@ -168,10 +169,10 @@ def extract_image_jbig2(
 
 
 def extract_image_generic(
-    *, pike: Pdf, root: Path, image: Stream, xref: Xref, options
+    *, pdf: Pdf, root: Path, image: Stream, xref: Xref, options
 ) -> XrefExt | None:
     """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
@@ -239,7 +240,7 @@ def _find_image_xrefs_container(
     pageno_for_xref: dict[Xref, int],
     depth: int = 0,
 ):
-    """Find all image XRefs in a page or Form XObject and add to the include/exclude sets."""
+    """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
@@ -290,7 +291,7 @@ def _find_image_xrefs(pdf: Pdf):
 
 
 def extract_images(
-    pike: Pdf,
+    pdf: Pdf,
     root: Path,
     options,
     extract_fn: Callable[..., XrefExt | None],
@@ -310,12 +311,12 @@ def extract_images(
     extension. extract_fn must also extract the file it finds interesting.
     """
     errors = 0
-    working_xrefs, pageno_for_xref = _find_image_xrefs(pike)
+    working_xrefs, pageno_for_xref = _find_image_xrefs(pdf)
     for xref in working_xrefs:
-        image = pike.get_object((xref, 0))
+        image = pdf.get_object((xref, 0))
         try:
             result = extract_fn(
-                pike=pike, root=root, image=image, xref=xref, options=options
+                pdf=pdf, root=root, image=image, xref=xref, options=options
             )
         except Exception:  # pylint: disable=broad-except
             log.exception(
@@ -329,12 +330,12 @@ def extract_images(
 
 
 def extract_images_generic(
-    pike: Pdf, root: Path, options
+    pdf: Pdf, root: Path, options
 ) -> tuple[list[Xref], list[Xref]]:
     """Extract any >=2bpp image we think we can improve."""
     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)
@@ -344,10 +345,10 @@ 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)
 
@@ -367,6 +368,7 @@ def _produce_jbig2_images(
                 fspath(root),  # =cwd
                 (img_name(root, xref, ext) for xref, ext in xref_exts),  # =infiles
                 prefix,  # =out_prefix
+                options.jbig2_threshold,
             )
 
     def jbig2_single_args(root, groups: dict[int, list[XrefExt]]):
@@ -379,6 +381,7 @@ def _produce_jbig2_images(
                     fspath(root),
                     img_name(root, xref, ext),
                     root / f'{prefix}.{n:04d}',
+                    options.jbig2_threshold,
                 )
 
     if options.jbig2_page_group_size > 1:
@@ -403,7 +406,7 @@ def _produce_jbig2_images(
 
 
 def convert_to_jbig2(
-    pike: Pdf,
+    pdf: Pdf,
     jbig2_groups: dict[int, list[XrefExt]],
     root: Path,
     options,
@@ -430,7 +433,7 @@ def convert_to_jbig2(
         jbig2_symfile = root / (prefix + '.sym')
         if jbig2_symfile.exists():
             jbig2_globals_data = jbig2_symfile.read_bytes()
-            jbig2_globals = Stream(pike, jbig2_globals_data)
+            jbig2_globals = Stream(pdf, jbig2_globals_data)
             jbig2_globals_dict = Dictionary(JBIG2Globals=jbig2_globals)
         elif options.jbig2_page_group_size == 1:
             jbig2_globals_dict = None
@@ -441,7 +444,7 @@ def convert_to_jbig2(
             xref, _ = xref_ext
             jbig2_im_file = root / (prefix + f'.{n:04d}')
             jbig2_im_data = jbig2_im_file.read_bytes()
-            im_obj = pike.get_object(xref, 0)
+            im_obj = pdf.get_object(xref, 0)
             im_obj.write(
                 jbig2_im_data, filter=Name.JBIG2Decode, decode_parms=jbig2_globals_dict
             )
@@ -461,7 +464,7 @@ 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."""
 
@@ -475,7 +478,7 @@ def transcode_jpegs(
         xref, opt_jpg = result
         if opt_jpg:
             compdata = opt_jpg.read_bytes()  # JPEG can inserted into PDF as is
-            im_obj = pike.get_object(xref, 0)
+            im_obj = pdf.get_object(xref, 0)
             im_obj.write(compdata, filter=Name.DCTDecode)
         pbar.update()
 
@@ -495,9 +498,9 @@ def transcode_jpegs(
 
 
 def _find_deflatable_jpeg(
-    *, pike: Pdf, root: Path, image: Stream, xref: Xref, options
+    *, pdf: Pdf, root: Path, image: Stream, xref: Xref, options
 ) -> XrefExt | None:
-    result = extract_image_filter(pike, root, image, xref)
+    result = extract_image_filter(pdf, root, image, xref)
     if result is None:
         return None
     _pim, filtdp = result
@@ -509,9 +512,9 @@ def _find_deflatable_jpeg(
 
 
 def _deflate_jpeg(args: tuple[Pdf, threading.Lock, Xref, int]) -> tuple[Xref, bytes]:
-    pike, lock, xref, complevel = args
+    pdf, lock, xref, complevel = args
     with lock:
-        xobj = pike.get_object(xref, 0)
+        xobj = pdf.get_object(xref, 0)
         try:
             data = xobj.read_raw_bytes()
         except PdfError:
@@ -522,7 +525,7 @@ 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,
@@ -530,7 +533,7 @@ 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)
@@ -542,13 +545,13 @@ def deflate_jpegs(pike: Pdf, root: Path, options, executor: Executor) -> None:
 
     def deflate_args() -> Iterator:
         for xref in jpegs:
-            yield pike, lock, xref, complevel
+            yield pdf, lock, xref, complevel
 
     def finish(result, pbar):
         xref, compdata = result
         if len(compdata) > 0:
             with lock:
-                xobj = pike.get_object(xref, 0)
+                xobj = pdf.get_object(xref, 0)
                 xobj.write(compdata, filter=[Name.FlateDecode, Name.DCTDecode])
         pbar.update()
 
@@ -567,16 +570,16 @@ def deflate_jpegs(pike: Pdf, root: Path, options, executor: Executor) -> None:
     )
 
 
-def _transcode_png(pike: Pdf, filename: Path, xref: Xref) -> bool:
+def _transcode_png(pdf: Pdf, filename: Path, xref: Xref) -> bool:
     output = filename.with_suffix('.png.pdf')
     with output.open('wb') as f:
         img2pdf.convert(fspath(filename), outputstream=f, **IMG2PDF_KWARGS)
 
     with Pdf.open(output) as pdf_image:
         foreign_image = next(iter(pdf_image.pages[0].images.values()))
-        local_image = pike.copy_foreign(foreign_image)
+        local_image = pdf.copy_foreign(foreign_image)
 
-        im_obj = pike.get_object(xref, 0)
+        im_obj = pdf.get_object(xref, 0)
         im_obj.write(
             local_image.read_raw_bytes(),
             filter=local_image.Filter,
@@ -609,7 +612,7 @@ 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,
@@ -650,7 +653,7 @@ def transcode_pngs(
 
     for xref in modified:
         filename = png_name(root, xref)
-        _transcode_png(pike, filename, xref)
+        _transcode_png(pdf, filename, xref)
 
 
 DEFAULT_EXECUTOR = SerialExecutor()
@@ -676,24 +679,24 @@ def optimize(
     if options.jbig2_page_group_size == 0:
         options.jbig2_page_group_size = 10 if options.jbig2_lossy else 1
 
-    with Pdf.open(input_file) as pike:
+    with Pdf.open(input_file) as pdf:
         root = output_file.parent / 'images'
         root.mkdir(exist_ok=True)
 
-        jpegs, pngs = extract_images_generic(pike, root, options)
+        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
@@ -710,9 +713,9 @@ 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)
 
@@ -737,6 +740,7 @@ def main(infile, outfile, level, jobs=1):
             self.png_quality = png_quality
             self.jbig2_page_group_size = 0
             self.jbig2_lossy = jb2lossy
+            self.jbig2_threshold = 0.85
             self.quiet = True
             self.progress_bar = False
 

src/ocrmypdf/pdfa.py

@@ -6,13 +6,9 @@
 from __future__ import annotations
 
 import base64
+from collections.abc import Iterator
+from importlib.resources import files as package_files
 from pathlib import Path
-from typing import Iterator
-
-try:
-    from importlib.resources import files as package_files
-except ImportError:
-    from importlib_resources import files as package_files  # type: ignore
 
 import pikepdf
 

src/ocrmypdf/pdfinfo/info.py

@@ -9,7 +9,10 @@ from __future__ import annotations
 import atexit
 import logging
 import re
+import statistics
+import sys
 from collections import defaultdict
+from collections.abc import Container, Iterable, Iterator, Mapping, Sequence
 from contextlib import ExitStack
 from decimal import Decimal
 from enum import Enum, auto
@@ -17,11 +20,14 @@ from functools import partial
 from math import hypot, inf, isclose
 from os import PathLike
 from pathlib import Path
-from typing import Container, Iterable, Iterator, Mapping, NamedTuple, Sequence, Tuple
+from typing import Callable, NamedTuple
 from warnings import warn
 
+from pdfminer.layout import LTPage, LTTextBox
 from pikepdf import (
+    Name,
     Object,
+    Page,
     Pdf,
     PdfImage,
     PdfInlineImage,
@@ -33,7 +39,7 @@ from pikepdf import (
 from ocrmypdf._concurrent import Executor, SerialExecutor
 from ocrmypdf.exceptions import EncryptedPdfError, InputFileError
 from ocrmypdf.helpers import Resolution, available_cpu_count, pikepdf_enable_mmap
-from ocrmypdf.pdfinfo.layout import get_page_analysis, get_text_boxes
+from ocrmypdf.pdfinfo.layout import LTStateAwareChar, get_page_analysis, get_text_boxes
 
 logger = logging.getLogger()
 
@@ -69,7 +75,7 @@ class Encoding(Enum):
     runlength = auto()
 
 
-FloatRect = Tuple[float, float, float, float]
+FloatRect = tuple[float, float, float, float]
 
 FRIENDLY_COLORSPACE: dict[str, Colorspace] = {
     '/DeviceGray': Colorspace.gray,
@@ -418,12 +424,12 @@ 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 +462,24 @@ 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 +504,15 @@ def _image_xobjects(container) -> Iterator[tuple[Object, str]]:
     since the object does not know its own name.
 
     """
-    if '/Resources' not in container:
+    if Name.Resources not in container:
         return
-    resources = container['/Resources']
+    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 +548,15 @@ 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 +594,19 @@ def _process_content_streams(
     downsampling.
 
     """
-    if container.get('/Type') == '/Page' and '/Contents' in container:
+    if container.get(Name.Type) == Name.Page and Name.Contents in container:
         initial_shorthand = shorthand or UNIT_SQUARE
-    elif container.get('/Type') == '/XObject' and container['/Subtype'] == '/Form':
+    elif (
+        container.get(Name.Type) == Name.XObject
+        and container[Name.Subtype] == Name.Form
+    ):
         # Set the CTM to the state it was when the "Do" operator was
         # encountered that is drawing this instance of the Form XObject
         ctm = PdfMatrix(shorthand) if shorthand else PdfMatrix.identity()
 
         # A Form XObject may provide its own matrix to map form space into
         # user space. Get this if one exists
-        form_shorthand = container.get('/Matrix', PdfMatrix.identity())
+        form_shorthand = container.get(Name.Matrix, PdfMatrix.identity())
         form_matrix = PdfMatrix(form_shorthand)
 
         # Concatenate form matrix with CTM to ensure CTM is correct for
@@ -640,7 +656,9 @@ def _page_has_text(text_blocks: Iterable[FloatRect], page_width, page_height) ->
     return has_text
 
 
-def simplify_textboxes(miner, textbox_getter) -> Iterator[TextboxInfo]:
+def simplify_textboxes(
+    miner: LTPage, textbox_getter: Callable[[LTPage], Iterator[LTTextBox]]
+) -> Iterator[TextboxInfo]:
     """Extract only limited content from text boxes.
 
     We do this to save memory and ensure that our objects are pickleable.
@@ -648,7 +666,8 @@ def simplify_textboxes(miner, textbox_getter) -> Iterator[TextboxInfo]:
     for box in textbox_getter(miner):
         first_line = box._objs[0]  # pylint: disable=protected-access
         first_char = first_line._objs[0]  # pylint: disable=protected-access
-
+        if not isinstance(first_char, LTStateAwareChar):
+            continue
         visible = first_char.rendermode != 3
         corrupt = first_char.get_text() == '\ufffd'
         yield TextboxInfo(box.bbox, visible, corrupt)
@@ -742,12 +761,38 @@ def _pdf_pageinfo_concurrent(
     return pages
 
 
+class PageResolutionProfile(NamedTuple):
+    """Information about the resolutions of a page."""
+
+    weighted_dpi: float
+    """The weighted average DPI of the page, weighted by the area of each image."""
+
+    max_dpi: float
+    """The maximum DPI of an image on the page."""
+
+    average_to_max_dpi_ratio: float
+    """The average DPI of the page divided by the maximum DPI of the page.
+
+    This indicates the intensity of the resolution variation on the page.
+
+    If the average is 1.0 or close to 1.0, has all of its content at a uniform
+    resolution. If the average is much lower than 1.0, some content is at a
+    higher resolution than the rest of the page.
+    """
+
+    area_ratio: float
+    """The maximum-DPI area of the page divided by the total drawn area.
+
+    This indicates the prevalence of high-resolution content on the page.
+    """
+
+
 class PageInfo:
     """Information about type of contents on each page in a PDF."""
 
     _has_text: bool | None
     _has_vector: bool | None
-    _images: list[ImageInfo]
+    _images: list[ImageInfo] = []
 
     def __init__(
         self,
@@ -771,7 +816,7 @@ class PageInfo:
         check_pages: Container[int],
         detailed_analysis: bool,
     ):
-        page = pdf.pages[pageno]
+        page: Page = pdf.pages[pageno]
         mediabox = [Decimal(d) for d in page.MediaBox.as_list()]
         width_pt = mediabox[2] - mediabox[0]
         height_pt = mediabox[3] - mediabox[1]
@@ -779,9 +824,12 @@ class PageInfo:
         check_this_page = pageno in check_pages
 
         if check_this_page and detailed_analysis:
-            pscript5_mode = str(pdf.docinfo.get('/Creator')).startswith('PScript5')
+            pscript5_mode = str(pdf.docinfo.get(Name.Creator)).startswith('PScript5')
             miner = get_page_analysis(infile, pageno, pscript5_mode)
-            self._textboxes = list(simplify_textboxes(miner, get_text_boxes))
+            if miner is not None:
+                self._textboxes = list(simplify_textboxes(miner, get_text_boxes))
+            else:
+                self._textboxes = []
             bboxes = (box.bbox for box in self._textboxes)
 
             self._has_text = _page_has_text(bboxes, width_pt, height_pt)
@@ -789,17 +837,13 @@ class PageInfo:
             self._textboxes = []
             self._has_text = None  # i.e. "no information"
 
-        userunit = page.get('/UserUnit', Decimal(1.0))
+        userunit = page.get(Name.UserUnit, Decimal(1.0))
         if not isinstance(userunit, Decimal):
             userunit = Decimal(userunit)
         self._userunit = userunit
         self._width_inches = width_pt * userunit / Decimal(72.0)
         self._height_inches = height_pt * userunit / Decimal(72.0)
-
+        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)
 
@@ -901,7 +945,9 @@ class PageInfo:
     def get_textareas(self, visible: bool | None = None, corrupt: bool | None = None):
         """Return textareas bounding boxes in PDF coordinates on the page."""
 
-        def predicate(obj, want_visible, want_corrupt):
+        def predicate(
+            obj: TextboxInfo, want_visible: bool | None, want_corrupt: bool | None
+        ) -> bool:
             result = True
             if want_visible is not None:
                 if obj.is_visible != want_visible:
@@ -938,6 +984,47 @@ 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 (
@@ -951,7 +1038,15 @@ DEFAULT_EXECUTOR = SerialExecutor()
 
 
 class PdfInfo:
-    """Get summary information about a PDF."""
+    """Extract summary information about a PDF without retaining the PDF itself.
+
+    Crucially this lets us get the information in a pure Python format so that
+    it can be pickled and passed to a worker process.
+    """
+
+    _has_acroform: bool = False
+    _has_signature: bool = False
+    _needs_rendering: bool = False
 
     def __init__(
         self,
@@ -980,13 +1075,16 @@ 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)
+            self._is_tagged = bool(
+                pdf.Root.get(Name.MarkInfo, {}).get(Name.Marked, False)
+            )
 
     @property
     def pages(self) -> Sequence[PageInfo | None]:
@@ -1006,9 +1104,19 @@ 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 is_tagged(self) -> bool:
+        """Return True if the document catalog indicates this is a Tagged PDF."""
+        return self._is_tagged
+
     @property
     def filename(self) -> str | Path:
         """Return filename of PDF."""

src/ocrmypdf/pdfinfo/layout.py

@@ -5,8 +5,12 @@
 from __future__ import annotations
 
 import re
+from collections.abc import Mapping
+from contextlib import contextmanager
 from math import copysign
+from os import PathLike
 from pathlib import Path
+from typing import Any, Iterator
 from unittest.mock import patch
 
 import pdfminer
@@ -15,10 +19,13 @@ import pdfminer.pdfdevice
 import pdfminer.pdfinterp
 from pdfminer.converter import PDFLayoutAnalyzer
 from pdfminer.layout import LAParams, LTChar, LTPage, LTTextBox
+from pdfminer.pdfcolor import PDFColorSpace
+from pdfminer.pdfdevice import PDFTextSeq
 from pdfminer.pdfdocument import PDFTextExtractionNotAllowed
-from pdfminer.pdffont import PDFSimpleFont, PDFUnicodeNotDefined
+from pdfminer.pdffont import FontWidthDict, PDFFont, PDFSimpleFont, PDFUnicodeNotDefined
+from pdfminer.pdfinterp import PDFGraphicState, PDFResourceManager, PDFTextState
 from pdfminer.pdfpage import PDFPage
-from pdfminer.utils import bbox2str, matrix2str
+from pdfminer.utils import Matrix, bbox2str, matrix2str
 
 from ocrmypdf.exceptions import EncryptedPdfError, InputFileError
 
@@ -28,7 +35,12 @@ STRIP_NAME = re.compile(r'[0-9]+')
 original_pdfsimplefont_init = PDFSimpleFont.__init__
 
 
-def pdfsimplefont__init__(self, descriptor, widths, spec):
+def pdfsimplefont__init__(
+    self,
+    descriptor: Mapping[str, Any],
+    widths: FontWidthDict,
+    spec: Mapping[str, Any],
+) -> None:
     """Monkeypatch pdfminer.six PDFSimpleFont.__init__.
 
     If there is no ToUnicode and no Encoding, pdfminer.six assumes that Unicode
@@ -44,7 +56,7 @@ def pdfsimplefont__init__(self, descriptor, widths, spec):
     return
 
 
-PDFSimpleFont.__init__ = pdfsimplefont__init__
+setattr(PDFSimpleFont, '__init__', pdfsimplefont__init__)
 
 #
 # pdfminer patches when creator is PScript5.dll
@@ -85,6 +97,11 @@ def pdftype3font__pscript5_get_ascent(self):
     return self.ascent * copysign(1.0, self.vscale)
 
 
+def _is_undefined_char(s: str) -> bool:
+    """Check if a string is an undefined character."""
+    return s.startswith('(cid:') and s.endswith(')')
+
+
 class LTStateAwareChar(LTChar):
     """A subclass of LTChar that tracks text render mode at time of drawing."""
 
@@ -107,18 +124,18 @@ class LTStateAwareChar(LTChar):
 
     def __init__(
         self,
-        matrix,
+        matrix: Matrix,
-        font,
+        font: PDFFont,
-        fontsize,
+        fontsize: float,
-        scaling,
+        scaling: float,
-        rise,
+        rise: float,
-        text,
+        text: str,
-        textwidth,
+        textwidth: float,
-        textdisp,
+        textdisp: float | tuple[float | None, float],
-        ncs,
+        ncs: PDFColorSpace,
-        graphicstate,
+        graphicstate: PDFGraphicState,
-        textstate,
+        textstate: PDFTextState,
-    ):
+    ) -> None:
         """Initialize."""
         super().__init__(
             matrix,
@@ -134,7 +151,7 @@ class LTStateAwareChar(LTChar):
         )
         self.rendermode = textstate.render
 
-    def is_compatible(self, obj):
+    def is_compatible(self, obj: object) -> bool:
         """Check if characters can be combined into a textline.
 
         We consider characters compatible if:
@@ -142,23 +159,22 @@ class LTStateAwareChar(LTChar):
             - the Unicode mapping is unknown but both are part of the same font
         """
         # pylint: disable=protected-access
-        both_unicode_mapped = isinstance(self._text, str) and isinstance(obj._text, str)
+        if not isinstance(obj, LTStateAwareChar):
-        try:
-            if both_unicode_mapped:
-                return self.rendermode == obj.rendermode
-            font0, _ = self._text
-            font1, _ = obj._text
-            return font0 == font1 and self.rendermode == obj.rendermode
-        except (ValueError, AttributeError):
             return False
+        both_unicode_mapped = not _is_undefined_char(
+            self._text
+        ) and not _is_undefined_char(obj._text)
+        if both_unicode_mapped:
+            return self.rendermode == obj.rendermode
+        return self.fontname == obj.fontname and self.rendermode == obj.rendermode
 
-    def get_text(self):
+    def get_text(self) -> str:
         """Get text from this character."""
-        if isinstance(self._text, tuple):
+        if _is_undefined_char(self._text):
             return '\ufffd'  # standard 'Unknown symbol'
         return self._text
 
-    def __repr__(self):
+    def __repr__(self) -> str:
         """Return a string representation of this object."""
         return (
             f"<{self.__class__.__name__} "
@@ -174,19 +190,24 @@ class LTStateAwareChar(LTChar):
 class TextPositionTracker(PDFLayoutAnalyzer):
     """A page layout analyzer that pays attention to text visibility."""
 
-    def __init__(self, rsrcmgr, pageno=1, laparams=None):
+    textstate: PDFTextState
+
+    def __init__(
+        self,
+        rsrcmgr: PDFResourceManager,
+        pageno: int = 1,
+        laparams: LAParams | None = None,
+    ):
         """Initialize the layout analyzer."""
         super().__init__(rsrcmgr, pageno, laparams)
-        self.textstate = None
+        self.result: LTPage | None = None
-        self.result = None
-        self.cur_item = None  # not defined in pdfminer code as it should be
 
-    def begin_page(self, page, ctm):
+    def begin_page(self, page: PDFPage, ctm: Matrix) -> None:
         """Begin processing of a page."""
         super().begin_page(page, ctm)
         self.cur_item = LTPage(self.pageno, page.mediabox)
 
-    def end_page(self, page):
+    def end_page(self, page: PDFPage) -> None:
         """End processing of a page."""
         assert not self._stack, str(len(self._stack))
         assert isinstance(self.cur_item, LTPage), str(type(self.cur_item))
@@ -195,14 +216,28 @@ class TextPositionTracker(PDFLayoutAnalyzer):
         self.pageno += 1
         self.receive_layout(self.cur_item)
 
-    def render_string(self, textstate, seq, ncs, graphicstate):
+    def render_string(
+        self,
+        textstate: PDFTextState,
+        seq: PDFTextSeq,
+        ncs: PDFColorSpace,
+        graphicstate: PDFGraphicState,
+    ) -> None:
         """Respond to render string event by updating text state."""
         self.textstate = textstate.copy()
         super().render_string(self.textstate, seq, ncs, graphicstate)
 
     def render_char(
-        self, matrix, font, fontsize, scaling, rise, cid, ncs, graphicstate
+        self,
-    ):
+        matrix: Matrix,
+        font: PDFFont,
+        fontsize: float,
+        scaling: float,
+        rise: float,
+        cid: int,
+        ncs: PDFColorSpace,
+        graphicstate: PDFGraphicState,
+    ) -> float:
         """Respond to render char event by updating text state."""
         try:
             text = font.to_unichr(cid)
@@ -227,21 +262,34 @@ class TextPositionTracker(PDFLayoutAnalyzer):
         self.cur_item.add(item)
         return item.adv
 
-    def handle_undefined_char(self, font, cid):
+    def receive_layout(self, ltpage: LTPage) -> None:
-        """Handle undefined character."""
-        # log.info('undefined: %r, %r', font, cid)
-        return (font.fontname, cid)
-
-    def receive_layout(self, ltpage):
         """Receive layout handler."""
         self.result = ltpage
 
-    def get_result(self):
+    def get_result(self) -> LTPage | None:
         """Get the result of the analysis."""
         return self.result
 
 
-def get_page_analysis(infile, pageno, pscript5_mode):
+@contextmanager
+def patch_pdfminer(pscript5_mode: bool):
+    """Patch pdfminer.six to work around bugs in PDFs created by PScript5."""
+    if pscript5_mode:
+        with patch.multiple(
+            'pdfminer.pdffont.PDFType3Font',
+            spec=True,
+            get_ascent=pdftype3font__pscript5_get_ascent,
+            get_descent=pdftype3font__pscript5_get_descent,
+            get_height=pdftype3font__pscript5_get_height,
+        ):
+            yield
+    else:
+        yield
+
+
+def get_page_analysis(
+    infile: PathLike, pageno: int, pscript5_mode: bool
+) -> LTPage | None:
     """Get the page analysis for a given page."""
     rman = pdfminer.pdfinterp.PDFResourceManager(caching=True)
     disable_boxes_flow = None
@@ -253,36 +301,23 @@ def get_page_analysis(infile, pageno, pscript5_mode):
     )
     interp = pdfminer.pdfinterp.PDFPageInterpreter(rman, dev)
 
-    patcher = None
+    with patch_pdfminer(pscript5_mode):
-    if pscript5_mode:
+        try:
-        patcher = patch.multiple(
+            with Path(infile).open('rb') as f:
-            'pdfminer.pdffont.PDFType3Font',
+                page_iter = PDFPage.get_pages(f, pagenos=[pageno], maxpages=0)
-            spec=True,
+                page = next(page_iter, None)
-            get_ascent=pdftype3font__pscript5_get_ascent,
+                if page is None:
-            get_descent=pdftype3font__pscript5_get_descent,
+                    raise InputFileError(
-            get_height=pdftype3font__pscript5_get_height,
+                        f"pdfminer could not process page {pageno} (counting from 0)."
-        )
+                    )
-        patcher.start()
+                interp.process_page(page)
-
+        except PDFTextExtractionNotAllowed as e:
-    try:
+            raise EncryptedPdfError() from e
-        with Path(infile).open('rb') as f:
-            page_iter = PDFPage.get_pages(f, pagenos=[pageno], maxpages=0)
-            page = next(page_iter, None)
-            if page is None:
-                raise InputFileError(
-                    f"pdfminer could not process page {pageno} (counting from 0)."
-                )
-            interp.process_page(page)
-    except PDFTextExtractionNotAllowed as e:
-        raise EncryptedPdfError() from e
-    finally:
-        if patcher is not None:
-            patcher.stop()
 
     return dev.get_result()
 
 
-def get_text_boxes(obj):
+def get_text_boxes(obj) -> Iterator[LTTextBox]:
     """Get the text boxes attached to the current node."""
     for child in obj:
         if isinstance(child, (LTTextBox)):

src/ocrmypdf/pluginspec.py

@@ -7,9 +7,10 @@ from __future__ import annotations
 
 from abc import ABC, abstractmethod
 from argparse import ArgumentParser, Namespace
+from collections.abc import Sequence, Set
 from logging import Handler
 from pathlib import Path
-from typing import TYPE_CHECKING, AbstractSet, NamedTuple, Sequence
+from typing import TYPE_CHECKING, NamedTuple
 
 import pluggy
 
@@ -351,7 +352,6 @@ 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>`.
     """
@@ -406,7 +406,7 @@ class OcrEngine(ABC):
 
     @staticmethod
     @abstractmethod
-    def languages(options: Namespace) -> AbstractSet[str]:
+    def languages(options: Namespace) -> Set[str]:
         """Returns the set of all languages that are supported by the engine.
 
         Languages are typically given in 3-letter ISO 3166-1 codes, but actually
@@ -466,7 +466,7 @@ def generate_pdfa(
     pdf_pages: list[Path],
     pdfmark: Path,
     output_file: Path,
-    compression: str,
+    context: PdfContext,
     pdf_version: str,
     pdfa_part: str,
     progressbar_class,
@@ -484,11 +484,7 @@ def generate_pdfa(
         pdfmark: A PostScript file intended for Ghostscript with details on
             how to perform the PDF/A conversion.
         output_file: The name of the desired output file.
-        compression: One of ``'jpeg'``, ``'lossless'``, ``''``. For ``'jpeg'``,
+        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.
@@ -514,6 +510,11 @@ 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/quality.py

@@ -7,7 +7,7 @@
 from __future__ import annotations
 
 import re
-from typing import Iterable
+from collections.abc import Iterable
 
 
 class OcrQualityDictionary:

src/ocrmypdf/subprocess/__init__.py

@@ -8,11 +8,12 @@ import logging
 import os
 import re
 import sys
+from collections.abc import Mapping, Sequence
 from contextlib import suppress
 from pathlib import Path
 from subprocess import PIPE, STDOUT, CalledProcessError, CompletedProcess, Popen
 from subprocess import run as subprocess_run
-from typing import Callable, Mapping, Sequence, Union
+from typing import Callable, Union
 
 from packaging.version import Version
 
@@ -292,21 +293,12 @@ def _error_old_version(
     _error_trailer(**locals())
 
 
-def _remove_leading_v(s: str) -> str:
-    if sys.version_info >= (3, 9):
-        return s.removeprefix('v')
-
-    if s.startswith('v'):
-        return s[1:]
-    return s
-
-
 def check_external_program(
     *,
     program: str,
     package: str,
-    version_checker: Callable[[], str],
+    version_checker: Callable[[], Version],
-    need_version: str,
+    need_version: str | Version,
     required_for: str | None = None,
     recommended: bool = False,
     version_parser: type[Version] = Version,
@@ -326,6 +318,8 @@ def check_external_program(
         version_parser: A class that should be used to parse and compare version
             numbers. Used when version numbers do not follow standard conventions.
     """
+    if not isinstance(need_version, Version):
+        need_version = version_parser(need_version)
     try:
         found_version = version_checker()
     except (CalledProcessError, FileNotFoundError) as e:
@@ -339,11 +333,10 @@ 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)
 

src/ocrmypdf/subprocess/_windows.py

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

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

tests/cache/cardinal/__-l__eng__000004_ocr.png__000004_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/ccitt/__-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.rvbrparf/000001_ocr.png"; bbox 0 0 2550 3300; ppageno 0'>
+  <div class='ocr_page' id='page_1' title='image "/tmp/ocrmypdf.io.zopxh6db/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">
@@ -29,7 +29,7 @@
     <p class='ocr_par' id='par_1_2' lang='eng' title="bbox 347 380 2188 423">
      <span class='ocr_header' id='line_1_3' title="bbox 347 380 2188 423; baseline -0.001 -12; x_size 38; x_descenders 8; x_ascenders 10">
       <span class='ocrx_word' id='word_1_8' title='bbox 347 380 412 410; x_wconf 93'>The</span>
-      <span class='ocrx_word' id='word_1_9' title='bbox 424 380 676 417; x_wconf 91'>LinnSequencer</span>
+      <span class='ocrx_word' id='word_1_9' title='bbox 424 380 676 417; x_wconf 90'>LinnSequencer</span>
       <span class='ocrx_word' id='word_1_10' title='bbox 688 380 712 411; x_wconf 96'>is</span>
       <span class='ocrx_word' id='word_1_11' title='bbox 724 390 743 411; x_wconf 96'>a</span>
       <span class='ocrx_word' id='word_1_12' title='bbox 754 381 1005 423; x_wconf 96'>state-of-the-art</span>
@@ -38,8 +38,8 @@
       <span class='ocrx_word' id='word_1_15' title='bbox 1311 380 1525 418; x_wconf 96'>performance</span>
       <span class='ocrx_word' id='word_1_16' title='bbox 1536 380 1602 411; x_wconf 96'>tool</span>
       <span class='ocrx_word' id='word_1_17' title='bbox 1615 380 1663 411; x_wconf 96'>for</span>
-      <span class='ocrx_word' id='word_1_18' title='bbox 1674 381 1725 410; x_wconf 97'>the</span>
+      <span class='ocrx_word' id='word_1_18' title='bbox 1674 381 1725 410; x_wconf 96'>the</span>
-      <span class='ocrx_word' id='word_1_19' title='bbox 1737 380 1940 417; x_wconf 96'>professional</span>
+      <span class='ocrx_word' id='word_1_19' title='bbox 1737 380 1940 417; x_wconf 95'>professional</span>
       <span class='ocrx_word' id='word_1_20' title='bbox 1952 380 2112 411; x_wconf 96'>musician.</span>
       <span class='ocrx_word' id='word_1_21' title='bbox 2127 381 2152 410; x_wconf 96'>It</span>
       <span class='ocrx_word' id='word_1_22' title='bbox 2164 380 2188 410; x_wconf 96'>is</span>
@@ -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>
@@ -209,7 +209,7 @@
    <div class='ocr_carea' id='block_1_8' title="bbox 382 1021 689 1065">
     <p class='ocr_par' id='par_1_10' lang='eng' title="bbox 382 1021 689 1065">
      <span class='ocr_line' id='line_1_15' title="bbox 382 1021 689 1065; baseline 0.003 -8; x_size 45; x_descenders 8; x_ascenders 12">
-      <span class='ocrx_word' id='word_1_135' title='bbox 382 1021 564 1065; x_wconf 96'>rhythmic</span>
+      <span class='ocrx_word' id='word_1_135' title='bbox 382 1021 564 1065; x_wconf 95'>rhythmic</span>
       <span class='ocrx_word' id='word_1_136' title='bbox 577 1021 689 1058; x_wconf 96'>value.</span>
      </span>
     </p>
@@ -249,15 +249,15 @@
       <span class='ocrx_word' id='word_1_154' title='bbox 349 1203 367 1222; x_wconf 73'>©</span>
       <span class='ocrx_word' id='word_1_155' title='bbox 382 1195 560 1240; x_wconf 96'>Optional</span>
       <span class='ocrx_word' id='word_1_156' title='bbox 573 1201 709 1233; x_wconf 96'>remote</span>
-      <span class='ocrx_word' id='word_1_157' title='bbox 723 1196 874 1233; x_wconf 96'>control.</span>
+      <span class='ocrx_word' id='word_1_157' title='bbox 723 1196 874 1233; x_wconf 95'>control.</span>
      </span>
     </p>
    </div>
    <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>
@@ -297,15 +297,15 @@
       <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 12'>you’</span>
+      <span class='ocrx_word' id='word_1_191' title='bbox 346 1457 430 1490; x_wconf 16'>you’</span>
-      <span class='ocrx_word' id='word_1_192' title='bbox 410 1453 432 1496; x_wconf 12'>ll</span>
+      <span class='ocrx_word' id='word_1_192' title='bbox 410 1453 436 1496; x_wconf 16'>ll</span>
-      <span class='ocrx_word' id='word_1_193' title='bbox 441 1457 506 1485; x_wconf 95'>hear</span>
+      <span class='ocrx_word' id='word_1_193' title='bbox 441 1457 506 1485; x_wconf 96'>hear</span>
       <span class='ocrx_word' id='word_1_194' title='bbox 517 1458 590 1485; x_wconf 96'>what</span>
       <span class='ocrx_word' id='word_1_195' title='bbox 600 1466 654 1491; x_wconf 93'>you</span>
-      <span class='ocrx_word' id='word_1_196' title='bbox 666 1458 865 1491; x_wconf 90'>played—only</span>
+      <span class='ocrx_word' id='word_1_196' title='bbox 666 1458 865 1491; x_wconf 91'>played—only</span>
       <span class='ocrx_word' id='word_1_197' title='bbox 876 1458 910 1485; x_wconf 96'>all</span>
       <span class='ocrx_word' id='word_1_198' title='bbox 921 1458 1018 1491; x_wconf 96'>timing</span>
       <span class='ocrx_word' id='word_1_199' title='bbox 1029 1466 1115 1485; x_wconf 96'>errors</span>
@@ -356,12 +356,12 @@
 
     <p class='ocr_par' id='par_1_18' lang='eng' title="bbox 346 1616 1205 1965">
      <span class='ocr_line' id='line_1_27' title="bbox 384 1616 1199 1648; baseline 0.001 -6; x_size 32; x_descenders 5; x_ascenders 8">
-      <span class='ocrx_word' id='word_1_228' title='bbox 384 1616 471 1642; x_wconf 96'>FAST</span>
+      <span class='ocrx_word' id='word_1_228' title='bbox 384 1616 471 1642; x_wconf 95'>FAST</span>
       <span class='ocrx_word' id='word_1_229' title='bbox 481 1616 671 1648; x_wconf 96'>FORWARD,</span>
       <span class='ocrx_word' id='word_1_230' title='bbox 684 1617 844 1648; x_wconf 95'>REWIND,</span>
       <span class='ocrx_word' id='word_1_231' title='bbox 857 1616 912 1643; x_wconf 95'>and</span>
       <span class='ocrx_word' id='word_1_232' title='bbox 924 1616 1068 1643; x_wconf 96'>LOCATE</span>
-      <span class='ocrx_word' id='word_1_233' title='bbox 1079 1616 1199 1643; x_wconf 96'>controls</span>
+      <span class='ocrx_word' id='word_1_233' title='bbox 1079 1616 1199 1643; x_wconf 95'>controls</span>
      </span>
      <span class='ocr_line' id='line_1_28' title="bbox 346 1655 1202 1689; baseline 0 -7; x_size 34; x_descenders 6; x_ascenders 9">
       <span class='ocrx_word' id='word_1_234' title='bbox 346 1663 409 1688; x_wconf 87'>may</span>
@@ -401,12 +401,12 @@
      <span class='ocr_line' id='line_1_31' title="bbox 346 1773 1203 1808; baseline 0.001 -8; x_size 33; x_descenders 6; x_ascenders 8">
       <span class='ocrx_word' id='word_1_263' title='bbox 346 1774 448 1806; x_wconf 96'>record,</span>
       <span class='ocrx_word' id='word_1_264' title='bbox 460 1774 506 1801; x_wconf 96'>the</span>
-      <span class='ocrx_word' id='word_1_265' title='bbox 517 1773 577 1801; x_wconf 96'>first</span>
+      <span class='ocrx_word' id='word_1_265' title='bbox 510 1769 577 1812; x_wconf 95'>first</span>
-      <span class='ocrx_word' id='word_1_266' title='bbox 587 1774 662 1801; x_wconf 96'>track</span>
+      <span class='ocrx_word' id='word_1_266' title='bbox 589 1774 658 1801; x_wconf 95'>track</span>
       <span class='ocrx_word' id='word_1_267' title='bbox 673 1774 726 1801; x_wconf 96'>will</span>
       <span class='ocrx_word' id='word_1_268' title='bbox 736 1774 799 1807; x_wconf 96'>play</span>
       <span class='ocrx_word' id='word_1_269' title='bbox 809 1774 836 1801; x_wconf 96'>in</span>
-      <span class='ocrx_word' id='word_1_270' title='bbox 847 1774 949 1808; x_wconf 97'>perfect</span>
+      <span class='ocrx_word' id='word_1_270' title='bbox 847 1774 949 1808; x_wconf 96'>perfect</span>
       <span class='ocrx_word' id='word_1_271' title='bbox 961 1782 1026 1808; x_wconf 96'>sync</span>
       <span class='ocrx_word' id='word_1_272' title='bbox 1037 1774 1137 1808; x_wconf 96'>(unless</span>
       <span class='ocrx_word' id='word_1_273' title='bbox 1148 1782 1203 1807; x_wconf 96'>you</span>
@@ -416,7 +416,7 @@
       <span class='ocrx_word' id='word_1_275' title='bbox 464 1813 492 1845; x_wconf 95'>it,</span>
       <span class='ocrx_word' id='word_1_276' title='bbox 505 1821 537 1840; x_wconf 95'>or</span>
       <span class='ocrx_word' id='word_1_277' title='bbox 547 1813 642 1840; x_wconf 95'>SOLO</span>
-      <span class='ocrx_word' id='word_1_278' title='bbox 653 1814 769 1841; x_wconf 96'>another</span>
+      <span class='ocrx_word' id='word_1_278' title='bbox 653 1814 769 1841; x_wconf 95'>another</span>
       <span class='ocrx_word' id='word_1_279' title='bbox 779 1814 875 1847; x_wconf 94'>track).</span>
       <span class='ocrx_word' id='word_1_280' title='bbox 889 1814 920 1840; x_wconf 96'>In</span>
       <span class='ocrx_word' id='word_1_281' title='bbox 930 1813 984 1841; x_wconf 96'>this</span>
@@ -523,8 +523,8 @@
       <span class='ocrx_word' id='word_1_353' title='bbox 691 2212 718 2235; x_wconf 96'>at</span>
       <span class='ocrx_word' id='word_1_354' title='bbox 729 2208 841 2242; x_wconf 96'>specific</span>
       <span class='ocrx_word' id='word_1_355' title='bbox 851 2209 943 2242; x_wconf 97'>points</span>
-      <span class='ocrx_word' id='word_1_356' title='bbox 955 2208 1049 2236; x_wconf 96'>within</span>
+      <span class='ocrx_word' id='word_1_356' title='bbox 955 2208 1049 2236; x_wconf 97'>within</span>
-      <span class='ocrx_word' id='word_1_357' title='bbox 1060 2217 1076 2236; x_wconf 96'>a</span>
+      <span class='ocrx_word' id='word_1_357' title='bbox 1060 2217 1076 2236; x_wconf 97'>a</span>
       <span class='ocrx_word' id='word_1_358' title='bbox 1086 2216 1228 2242; x_wconf 96'>sequence,</span>
      </span>
     </p>
@@ -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">
@@ -677,11 +677,11 @@
       <span class='ocrx_word' id='word_1_461' title='bbox 1463 1808 1528 1835; x_wconf 96'>then</span>
       <span class='ocrx_word' id='word_1_462' title='bbox 1538 1816 1587 1835; x_wconf 96'>use</span>
       <span class='ocrx_word' id='word_1_463' title='bbox 1597 1808 1643 1835; x_wconf 96'>the</span>
-      <span class='ocrx_word' id='word_1_464' title='bbox 1653 1809 1799 1835; x_wconf 96'>CREATE</span>
+      <span class='ocrx_word' id='word_1_464' title='bbox 1653 1809 1799 1835; x_wconf 95'>CREATE</span>
       <span class='ocrx_word' id='word_1_465' title='bbox 1810 1808 1911 1835; x_wconf 96'>SONG</span>
       <span class='ocrx_word' id='word_1_466' title='bbox 1923 1808 2050 1836; x_wconf 96'>function</span>
-      <span class='ocrx_word' id='word_1_467' title='bbox 2060 1812 2089 1835; x_wconf 95'>to</span>
+      <span class='ocrx_word' id='word_1_467' title='bbox 2060 1812 2089 1835; x_wconf 96'>to</span>
-      <span class='ocrx_word' id='word_1_468' title='bbox 2103 1808 2215 1836; x_wconf 92'>“chain”</span>
+      <span class='ocrx_word' id='word_1_468' title='bbox 2103 1808 2215 1836; x_wconf 93'>“chain”</span>
      </span>
      <span class='ocr_line' id='line_1_56' title="bbox 1295 1847 2135 1881; baseline 0.001 -7; x_size 34; x_descenders 7; x_ascenders 8">
       <span class='ocrx_word' id='word_1_469' title='bbox 1295 1848 1370 1874; x_wconf 96'>them</span>
@@ -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>
@@ -863,7 +863,7 @@
    <div class='ocr_carea' id='block_1_24' title="bbox 372 2510 1090 2543">
     <p class='ocr_par' id='par_1_32' lang='eng' title="bbox 372 2510 1090 2543">
      <span class='ocr_line' id='line_1_69' title="bbox 372 2510 1090 2543; baseline 0.001 -6; x_size 35.625; x_descenders 8.90625; x_ascenders 8.90625">
-      <span class='ocrx_word' id='word_1_599' title='bbox 372 2510 500 2542; x_wconf 95'>ERASE,</span>
+      <span class='ocrx_word' id='word_1_599' title='bbox 372 2510 500 2542; x_wconf 96'>ERASE,</span>
       <span class='ocrx_word' id='word_1_600' title='bbox 513 2511 660 2542; x_wconf 93'>REPEAT,</span>
       <span class='ocrx_word' id='word_1_601' title='bbox 673 2511 883 2543; x_wconf 91'>PLAY/STOP,</span>
       <span class='ocrx_word' id='word_1_602' title='bbox 896 2519 927 2538; x_wconf 96'>or</span>
@@ -874,10 +874,10 @@
    <div class='ocr_carea' id='block_1_25' title="bbox 347 2556 1768 2590">
     <p class='ocr_par' id='par_1_33' lang='eng' title="bbox 347 2556 1768 2590">
      <span class='ocr_header' id='line_1_70' title="bbox 347 2556 1768 2590; baseline 0.001 -8; x_size 34; x_descenders 7; x_ascenders 8">
-      <span class='ocrx_word' id='word_1_604' title='bbox 347 2561 361 2575; x_wconf 86'>¢</span>
+      <span class='ocrx_word' id='word_1_604' title='bbox 347 2561 361 2575; x_wconf 87'>¢</span>
-      <span class='ocrx_word' id='word_1_605' title='bbox 372 2556 433 2583; x_wconf 80'>Two</span>
+      <span class='ocrx_word' id='word_1_605' title='bbox 372 2556 433 2583; x_wconf 79'>Two</span>
       <span class='ocrx_word' id='word_1_606' title='bbox 443 2556 612 2583; x_wconf 95'>TRIGGER</span>
-      <span class='ocrx_word' id='word_1_607' title='bbox 623 2556 797 2584; x_wconf 95'>OUTPUTS</span>
+      <span class='ocrx_word' id='word_1_607' title='bbox 623 2556 797 2584; x_wconf 96'>OUTPUTS</span>
       <span class='ocrx_word' id='word_1_608' title='bbox 808 2565 871 2590; x_wconf 96'>may</span>
       <span class='ocrx_word' id='word_1_609' title='bbox 881 2557 915 2584; x_wconf 96'>be</span>
       <span class='ocrx_word' id='word_1_610' title='bbox 925 2557 1119 2590; x_wconf 96'>programmed</span>
@@ -911,10 +911,10 @@
    </div>
    <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 -7; x_size 33; x_descenders 6; x_ascenders 8">
+     <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 42'>®</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 95'>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 2677; x_wconf 96'>ultra</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 95'>MHz</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>
@@ -960,7 +960,7 @@
    <div class='ocr_carea' id='block_1_29' title="bbox 347 2777 2174 2811">
     <p class='ocr_par' id='par_1_37' lang='eng' title="bbox 347 2777 2174 2811">
      <span class='ocr_header' id='line_1_75' title="bbox 347 2777 2174 2811; baseline 0.001 -8; x_size 33; x_descenders 5; x_ascenders 9">
-      <span class='ocrx_word' id='word_1_664' title='bbox 347 2782 360 2796; x_wconf 74'>¢</span>
+      <span class='ocrx_word' id='word_1_664' title='bbox 347 2782 360 2796; x_wconf 78'>¢</span>
       <span class='ocrx_word' id='word_1_665' title='bbox 372 2777 504 2804; x_wconf 95'>TEMPO</span>
       <span class='ocrx_word' id='word_1_666' title='bbox 515 2785 578 2810; x_wconf 96'>may</span>
       <span class='ocrx_word' id='word_1_667' title='bbox 588 2777 622 2804; x_wconf 95'>be</span>
@@ -968,10 +968,10 @@
       <span class='ocrx_word' id='word_1_669' title='bbox 751 2777 934 2811; x_wconf 96'>numerically,</span>
       <span class='ocrx_word' id='word_1_670' title='bbox 946 2777 1101 2811; x_wconf 96'>adjustable</span>
       <span class='ocrx_word' id='word_1_671' title='bbox 1111 2777 1139 2804; x_wconf 95'>in</span>
-      <span class='ocrx_word' id='word_1_672' title='bbox 1149 2778 1239 2805; x_wconf 96'>tenths</span>
+      <span class='ocrx_word' id='word_1_672' title='bbox 1149 2778 1239 2805; x_wconf 95'>tenths</span>
       <span class='ocrx_word' id='word_1_673' title='bbox 1250 2778 1282 2805; x_wconf 96'>of</span>
       <span class='ocrx_word' id='word_1_674' title='bbox 1290 2786 1307 2805; x_wconf 93'>a</span>
-      <span class='ocrx_word' id='word_1_675' title='bbox 1317 2777 1567 2805; x_wconf 91'>Beat-Per-Minute</span>
+      <span class='ocrx_word' id='word_1_675' title='bbox 1317 2777 1567 2805; x_wconf 92'>Beat-Per-Minute</span>
       <span class='ocrx_word' id='word_1_676' title='bbox 1577 2777 1748 2809; x_wconf 96'>increments,</span>
       <span class='ocrx_word' id='word_1_677' title='bbox 1760 2785 1792 2804; x_wconf 96'>or</span>
       <span class='ocrx_word' id='word_1_678' title='bbox 1803 2777 1839 2810; x_wconf 96'>by</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/ccitt/__-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