v16.4.2 release notes

Ghostscript now expects the pdfa.ps file to precede other files. Fixes #1359.

.docker/Dockerfile

@@ -64,6 +64,7 @@ RUN apt-get update && apt-get install -y --no-install-recommends \
   img2pdf \
   libsm6 libxext6 libxrender-dev \
   pngquant \
+  python-is-python3 \
   tesseract-ocr \
   tesseract-ocr-chi-sim \
   tesseract-ocr-deu \

.docker/Dockerfile.alpine

@@ -0,0 +1,83 @@
+# SPDX-FileCopyrightText: 2023 James R. Barlow
+# SPDX-License-Identifier: MPL-2.0
+
+FROM alpine:3.19.1 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/ISSUE_TEMPLATE/1-bug-report-general.yml

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

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

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

.github/ISSUE_TEMPLATE/3-app.yml

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

.github/workflows/build.yml

@@ -22,20 +22,18 @@ jobs:
     strategy:
       matrix:
         include:
-          - os: ubuntu-22.04
-            python: "3.9"
           - os: ubuntu-22.04
             python: "3.10"
           - os: ubuntu-22.04
             python: "3.11"
           - os: ubuntu-22.04
-            python: "3.9"
+            python: "3.10"
             tesseract5: true
           - os: ubuntu-latest
-            python: "3.12-dev"
+            python: "3.12"
             tesseract5: true
-            #- os: ubuntu-latest
-            #  python: "pypy3.9"
+          - os: ubuntu-latest
+            python: "pypy3.10"
 
     env:
       OS: ${{ matrix.os }}
@@ -46,7 +44,7 @@ jobs:
         with:
           fetch-depth: "0" # 0=all, needed for setuptools-scm to resolve version tags
 
-      - uses: actions/setup-python@v4
+      - uses: actions/setup-python@v5
         name: Setup Python
         with:
           python-version: ${{ matrix.python }}
@@ -55,7 +53,7 @@ jobs:
       - name: Install Tesseract 5
         if: matrix.tesseract5
         run: |
-          sudo add-apt-repository ppa:alex-p/tesseract-ocr-devel
+          sudo add-apt-repository -y ppa:alex-p/tesseract-ocr-devel
 
       - name: Install common packages
         run: |
@@ -63,6 +61,7 @@ jobs:
           sudo apt-get install -y --no-install-recommends \
             curl \
             ghostscript \
+            jbig2dec \
             img2pdf \
             libexempi8 \
             libffi-dev \
@@ -102,18 +101,21 @@ jobs:
           python -m pytest --cov-report xml --cov=ocrmypdf --cov=tests/ -n0 tests/
 
       - name: Upload coverage to Codecov
-        uses: codecov/codecov-action@v3
+        uses: codecov/codecov-action@v4
+        env:
+          CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}
         with:
           files: ./coverage.xml
           env_vars: OS,PYTHON
 
+
   test_macos:
     name: Test macOS
     runs-on: ${{ matrix.os }}
     strategy:
       matrix:
-        os: [macos-latest]
-        python: ["3.10", "3.11", "3.12-dev"]
+        os: [macos-latest, macos-13]  # macos-latest is arm64, macos-13 is x86_64
+        python: ["3.10", "3.11", "3.12"]
 
     env:
       OS: ${{ matrix.os }}
@@ -136,7 +138,7 @@ jobs:
             pngquant \
             tesseract
 
-      - uses: actions/setup-python@v4
+      - uses: actions/setup-python@v5
         name: Setup Python
         with:
           python-version: ${{ matrix.python }}
@@ -159,7 +161,9 @@ jobs:
           python -m pytest --cov-report xml --cov=ocrmypdf --cov=tests/ -n0 tests/
 
       - name: Upload coverage to Codecov
-        uses: codecov/codecov-action@v3
+        uses: codecov/codecov-action@v4
+        env:
+          CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}
         with:
           files: ./coverage.xml
           env_vars: OS,PYTHON
@@ -170,7 +174,7 @@ jobs:
     strategy:
       matrix:
         os: [windows-latest]
-        python: ["3.10", "3.11", "3.12-dev"]
+        python: ["3.10", "3.11", "3.12"]
 
     env:
       OS: ${{ matrix.os }}
@@ -181,7 +185,7 @@ jobs:
         with:
           fetch-depth: "0" # 0=all, needed for setuptools-scm to resolve version tags
 
-      - uses: actions/setup-python@v4
+      - uses: actions/setup-python@v5
         name: Setup Python
         with:
           python-version: ${{ matrix.python }}
@@ -190,7 +194,7 @@ jobs:
       - name: Install system packages
         run: |
           choco install --yes --no-progress --pre tesseract
-          choco install --yes --no-progress --ignore-checksums ghostscript
+          choco install --yes --no-progress --ignore-checksums ghostscript --version 9.56.1
 
       - name: Install Python packages
         run: |
@@ -202,7 +206,9 @@ jobs:
           python -m pytest --cov-report xml --cov=ocrmypdf --cov=tests/ -n0 tests/
 
       - name: Upload coverage to Codecov
-        uses: codecov/codecov-action@v3
+        uses: codecov/codecov-action@v4
+        env:
+          CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}
         with:
           files: ./coverage.xml
           env_vars: OS,PYTHON
@@ -215,10 +221,10 @@ jobs:
         with:
           fetch-depth: "0" # 0=all, needed for setuptools-scm to resolve version tags
 
-      - uses: actions/setup-python@v4
+      - uses: actions/setup-python@v5
         name: Setup Python
         with:
-          python-version: "3.9"
+          python-version: "3.10"
           cache: "pip"
 
       - name: Make wheels and sdist
@@ -226,8 +232,9 @@ jobs:
           python -m pip install --upgrade pip wheel build
           python -m build --sdist --wheel
 
-      - uses: actions/upload-artifact@v3
+      - uses: actions/upload-artifact@v4
         with:
+          name: artifact
           path: |
             ./dist/*.whl
             ./dist/*.tar.gz
@@ -241,7 +248,7 @@ jobs:
       id-token: write  # mandatory for PyPI publishing
     if: github.event_name == 'push' && startsWith(github.event.ref, 'refs/tags/v')
     steps:
-      - uses: actions/download-artifact@v3
+      - uses: actions/download-artifact@v4
         with:
           name: artifact
           path: dist
@@ -258,7 +265,7 @@ jobs:
       # Required to create a release
       contents: write
     steps:
-      - uses: actions/download-artifact@v3
+      - uses: actions/download-artifact@v4
         with:
           name: artifact
           path: dist
@@ -275,8 +282,8 @@ jobs:
             ./dist/*.whl
             ./dist/*.tar.gz
 
-  docker:
-    name: Build Docker images
+  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'
@@ -320,4 +327,49 @@ jobs:
             --push \
             --platform linux/arm64/v8,linux/amd64  \
             --tag "${DOCKER_REPOSITORY}/${DOCKER_IMAGE_NAME}:${DOCKER_IMAGE_TAG}" \
+            --tag "${DOCKER_REPOSITORY}/${DOCKER_IMAGE_NAME}-ubuntu:${DOCKER_IMAGE_TAG}" \
             --file .docker/Dockerfile .
+
+  docker_alpine:
+    name: Build Alpine-based Docker images
+    needs: [wheel_sdist_linux, test_linux, test_macos, test_windows]
+    runs-on: ubuntu-latest
+    if: github.event_name != 'pull_request'
+    steps:
+      - name: Set image tag to release or branch
+        run: echo "DOCKER_IMAGE_TAG=${GITHUB_REF##*/}" >> $GITHUB_ENV
+
+      - name: If main, set to latest
+        run: echo 'DOCKER_IMAGE_TAG=latest' >> $GITHUB_ENV
+        if: env.DOCKER_IMAGE_TAG == 'main'
+
+      - name: Set Docker Hub repository to username
+        run: echo "DOCKER_REPOSITORY=jbarlow83" >> $GITHUB_ENV
+
+      - name: Set image name
+        run: echo "DOCKER_IMAGE_NAME=ocrmypdf-alpine" >> $GITHUB_ENV
+
+      - uses: actions/checkout@v4
+        with:
+          fetch-depth: "0" # 0=all, needed for setuptools-scm to resolve version tags
+
+      - name: Login to Docker Hub
+        uses: docker/login-action@v3
+        with:
+          username: jbarlow83
+          password: ${{ secrets.DOCKERHUB_TOKEN }}
+
+      - name: Set up Docker Buildx
+        id: buildx
+        uses: docker/setup-buildx-action@v3
+
+      - name: Print image tag
+        run: echo "Building image ${DOCKER_REPOSITORY}/${DOCKER_IMAGE_NAME}:${DOCKER_IMAGE_TAG}"
+
+      - name: Build
+        run: |
+          docker buildx build \
+            --push \
+            --platform linux/amd64,linux/arm64  \
+            --tag "${DOCKER_REPOSITORY}/${DOCKER_IMAGE_NAME}:${DOCKER_IMAGE_TAG}" \
+            --file .docker/Dockerfile.alpine .

.readthedocs.yaml

@@ -19,7 +19,7 @@ formats:
 build:
   os: ubuntu-22.04
   tools:
-    python: "3.9"
+    python: "3.10"
 
 python:
   install:

.reuse/dep5

@@ -3,7 +3,6 @@ Upstream-Name: OCRmyPDF
 Upstream-Contact: James R. Barlow <james@purplerock.ca>
 Source: https://github.com/ocrmypdf/OCRmyPDF
 
-
 Files:
  .git_archival.txt
  docs/images/logo-social.png
@@ -11,14 +10,13 @@ Files:
  docs/images/logo-square.png
  docs/images/logo-square.svg
  docs/images/logo.svg
- setup.cfg
 Copyright: (C) 2022 James R. Barlow
 License: MPL-2.0
 
 Files:
- .github/ISSUE_TEMPLATE/*.md
+ .github/ISSUE_TEMPLATE/*.yml
  docs/images/macos-workflow.png
-Copyright: (C) 2022 James R. Barlow
+Copyright: (C) 2023 James R. Barlow
 License: CC-BY-SA-4.0
 
 Files:
@@ -34,15 +32,16 @@ Files:
  tests/resources/invalid.pdf
  tests/resources/kcs.pdf
  tests/resources/livecycle.pdf
+ tests/resources/meta.pdf
  tests/resources/missing_docinfo.pdf
  tests/resources/negzero.pdf
  tests/resources/no_contents.pdf
+ tests/resources/tagged*
  tests/resources/toc.pdf
  tests/resources/trivial.pdf
  tests/resources/truetype_font_nomapping.pdf
  tests/resources/type3_font_nomapping.pdf
- misc/screencast/*
-Copyright: (C) 2022 James R. Barlow
+Copyright: (C) 2023 James R. Barlow
 License: CC-BY-SA-4.0
 
 Files:
@@ -52,7 +51,6 @@ Copyright: (C) 2012 SmokeyJoe
 License: GFDL-1.2-or-later or CC-BY-SA-3.0
 
 Files: tests/resources/c02-22.pdf
- tests/resources/congress.jpg
  tests/resources/multipage.pdf
 Copyright: Public domain
 License: public-domain
@@ -72,6 +70,7 @@ Files: tests/resources/linn.png
  tests/resources/ccitt.pdf
  tests/resources/cardinal.pdf
  tests/resources/jbig2.pdf
+ tests/resources/jbig2_baddevicen.pdf
  tests/resources/skew.pdf
  tests/resources/rotated_skew.pdf
  tests/resources/poster.pdf
@@ -125,6 +124,14 @@ Copyright:  Kai-Uwe Behrmann <www.behrmann.name>
             ColorSolutions <www.basICColor.com>
 License: Zlib
 
+Files: src/ocrmypdf/data/pdf.ttf
+Copyright: (C) 2014 Ray Smith
+ (C) 2015 Ken Sharp
+ (C) 2016 James R. Barlow
+ (C) 2016 Jeff Breidenbach
+ (C) 2017 Zdenko Podobný
+License: Apache-2.0
+
 Files: tests/resources/3small.pdf
 Copyright: (C) 2014 Euskaldunaa
  (C) 2017 James R. Barlow

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
-- Battle-tested on millions of PDFs
+- Scales properly to handle files with thousands of pages.
+- Battle-tested on millions of PDFs.
 
 <img src="misc/screencast/demo.svg" alt="Demo of OCRmyPDF in a terminal session">
 
@@ -70,6 +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 (MacPorts)              | ``port install ocrmypdf``     |
 | macOS (nix)                   | ``nix-env -i ocrmypdf``       |
 | LinuxBrew                     | ``brew install ocrmypdf``     |
 | FreeBSD                       | ``pkg install py-ocrmypdf``   |

docs/advanced.rst

@@ -118,15 +118,16 @@ OCR for huge images
 -------------------
 
 Tesseract has internal limits on the size
-of images it will process. If you issue
-``--tesseract-downsample-large-images``, OCRmyPDF will downsample images
-to fit Tesseract limits. (The limits are usually entered only for scanned
-images of oversized media, such as large maps or blueprints exceeding
-110 cm or 43 inches in either dimension, and at high DPI.)
+of images it will process. By default,
+``--tesseract-downsample-large-images`` is enabled, and OCRmyPDF will
+downsample images to fit Tesseract limits. (The limits are usually encountered
+only for scanned images of oversized media, such as large maps or blueprints exceeding
+110 cm or 43 inches in either dimension, and at high DPI.) This feature can disabled
+using ``--no-tesseract-downsample-large-images``.
 
 ``--tesseract-downsample-above Npixels`` adjusts the threshold at which images
 will be downsampled. By default, only images that exceed any of Tesseract's
-internal limits are downsampled.
+internal limits are downsampled (32767 pixels on either dimension).
 
 You will also need to set ``--tesseract-timeout`` high enough to allow
 for processing.
@@ -227,6 +228,59 @@ then run ocrmypdf as follows (along with any other desired arguments):
    Some combinations of control parameters will break Tesseract or break
    assumptions that OCRmyPDF makes about Tesseract's output.
 
+Changing page segmentation mode
+-------------------------------
+
+The directive ``--tesseract-pagesegmode Nmode`` forwards the desired page segmentation
+mode to Tesseract OCR. The default is 3.
+
+Page segmentation can improve OCR results when you know that a PDF ought to be
+analyzed a particular way, such as PDFs whose pages contain only a single line of 
+text. For the vast majority of users, changing the page segmentation mode will only
+make things worse.
+
+As of June 2024, the Tesseract page segmentation modes are:
+
++-----+----------------------------------------------------------------------------------+
+| ID  | Description                                                                      |
++=====+==================================================================================+
+|  0  | Orientation and script detection (OSD) only.                                      |
++-----+----------------------------------------------------------------------------------+
+|  1  | Automatic page segmentation with OSD.                                             |
++-----+----------------------------------------------------------------------------------+
+|  2  | Automatic page segmentation, but no OSD, or OCR. (not implemented)               |
++-----+----------------------------------------------------------------------------------+
+|  3  | Fully automatic page segmentation, but no OSD. (Default)                         |
++-----+----------------------------------------------------------------------------------+
+|  4  | Assume a single column of text of variable sizes.                                 |
++-----+----------------------------------------------------------------------------------+
+|  5  | Assume a single uniform block of vertically aligned text.                         |
++-----+----------------------------------------------------------------------------------+
+|  6  | Assume a single uniform block of text.                                            |
++-----+----------------------------------------------------------------------------------+
+|  7  | Treat the image as a single text line.                                            |
++-----+----------------------------------------------------------------------------------+
+|  8  | Treat the image as a single word.                                                 |
++-----+----------------------------------------------------------------------------------+
+|  9  | Treat the image as a single word in a circle.                                     |
++-----+----------------------------------------------------------------------------------+
+| 10  | Treat the image as a single character.                                            |
++-----+----------------------------------------------------------------------------------+
+| 11  | Sparse text. Find as much text as possible in no particular order.                |
++-----+----------------------------------------------------------------------------------+
+| 12  | Sparse text with OSD.                                                            |
++-----+----------------------------------------------------------------------------------+
+| 13  | Raw line. Treat the image as a single text line, bypassing hacks that are        |
+|     | Tesseract-specific.                                                               |
++-----+----------------------------------------------------------------------------------+
+
+Modes 0, 1, 2, and 12 (all of those that enable orientation and script detection) 
+are not compatible with OCRmyPDF, which performs OSD in a separate step from OCR.
+Their use may interfere with ``--rotate-pages`` and other features.
+
+It is currently not possible to use advanced Tesseract OCR features, such as creating
+OCR information, when using Tesseract through OCRmyPDF.
+
 Changing the PDF renderer
 =========================
 
@@ -239,46 +293,46 @@ rendering
 OCRmyPDF has these PDF renderers: ``sandwich`` and ``hocr``. The
 renderer may be selected using ``--pdf-renderer``. The default is
 ``auto`` which lets OCRmyPDF select the renderer to use. Currently,
-``auto`` always selects ``sandwich``.
-
-The ``sandwich`` renderer
--------------------------
-
-The ``sandwich`` renderer uses Tesseract's new text-only PDF feature,
-which produces a PDF page that lays out the OCR in invisible text. This
-page is then "sandwiched" onto the original PDF page, allowing lossless
-application of OCR even to PDF pages that contain other vector objects.
-
-Currently this is the best renderer for most uses, however it is
-implemented in Tesseract so OCRmyPDF cannot influence it. Currently some
-problematic PDF viewers like Mozilla PDF.js and macOS Preview have
-problems with segmenting its text output, and
-mightrunseveralwordstogether.
-
-When image preprocessing features like ``--deskew`` are used, the
-original PDF will be rendered as a full page and the OCR layer will be
-placed on top.
+``auto`` always selects ``hocr``.
 
 The ``hocr`` renderer
 ---------------------
 
-The ``hocr`` renderer works with older versions of Tesseract. The image
-layer is copied from the original PDF page if possible, avoiding
-potentially lossy transcoding or loss of other PDF information. If
-preprocessing is specified, then the image layer is a new PDF. (You may
-need to disable PDF/A conversion nad optimization to eliminate all
-lossy transformations.)
+.. versionchanged:: 16.0.0
 
-Unlike ``sandwich`` this renderer is implemented within OCRmyPDF; anyone
-looking to customize how OCR is presented should look here. A major
-disadvantage of this renderer is it not capable of correctly handling
-text outside the Latin alphabet (specifically, it supports the ISO 8859-1
-character set). Pull requests to improve the situation are welcome.
+In both renderers, a text-only layer is rendered and sandwiched (overlaid)
+on to either the original PDF page, or newly rasterized version of the
+original PDF page (when ``--force-ocr`` is used). In this way, loss
+of PDF information is generally avoided. (You may need to disable PDF/A
+conversion and optimization to eliminate all lossy transformations.)
 
-Currently, this renderer has the best compatibility with Mozilla's
-PDF.js viewer.
+The current approach used by the new hOCR renderer is a re-implementation
+of Tesseract's PDF renderer, using the same Glyphless font and general
+ideas, but fixing many technical issues that impeded it. The new hocr
+provides better text placement accuracy, avoids issues with word
+segmentation, and provides better positioning of skewed text.
 
-This works in all versions of Tesseract.
+Using the experimental API, it is also possible to edit the OCR output
+from Tesseract, using any tool that is capable of editing hOCR files.
+
+Older versions of this renderer did not support non-Latin languages, but
+it is now universal.
+
+The ``sandwich`` renderer
+-------------------------
+
+The ``sandwich`` renderer uses Tesseract's text-only PDF feature,
+which produces a PDF page that lays out the OCR in invisible text.
+
+Currently some problematic PDF viewers like Mozilla PDF.js and macOS
+Preview have problems with segmenting its text output, and
+mightrunseveralwordstogether. It also does not implement right to left
+fonts (Arabic, Hebrew, Persian). The output of this renderer cannot
+be edited. The sandwich renderer is retained for testing.
+
+When image preprocessing features like ``--deskew`` are used, the
+original PDF will be rendered as a full page and the OCR layer will be
+placed on top.
 
 Rendering and rasterizing options
 =================================

docs/api.rst

@@ -39,9 +39,7 @@ Parent process requirements
 The :func:`ocrmypdf.ocr` function runs OCRmyPDF similar to command line
 execution. To do this, it will:
 
-- create a monitoring thread
-- create worker processes (on Linux, forking itself; on Windows and macOS, by
-  spawning)
+- create worker processes or threads
 - manage the signal flags of its worker processes
 - execute other subprocesses (forking and executing other programs)
 
@@ -54,7 +52,19 @@ processes.
 
 Creating a child process to call :func:`ocrmypdf.ocr()` is suggested. That
 way your application will survive and remain interactive even if
-OCRmyPDF fails for any reason.
+OCRmyPDF fails for any reason. For example:
+
+.. code-block:: python
+
+    from multiprocessing import Process
+
+    def ocrmypdf_process():
+        ocrmypdf.ocr('input.pdf', 'output.pdf')
+
+    def call_ocrmypdf_from_my_app():
+        p = Process(target=ocrmypdf_process)
+        p.start()
+        p.join()
 
 Programs that call :func:`ocrmypdf.ocr()` should also install a SIGBUS signal
 handler (except on Windows), to raise an exception if access to a memory
@@ -89,12 +99,23 @@ your use case.
 Progress monitoring
 -------------------
 
-OCRmyPDF uses the ``tqdm`` package to implement its progress bars.
+OCRmyPDF uses the ``rich`` package to implement its progress bars.
 :func:`ocrmypdf.configure_logging` will set up logging output to
 ``sys.stderr`` in a way that is compatible with the display of the
 progress bar. Use ``ocrmypdf.ocr(...progress_bar=False)`` to disable
 the progress bar.
 
+Standard output
+---------------
+
+OCRmyPDF is strict about not writing to standard output so that
+users can safely use it in a pipeline and produce a valid output
+file. A caller application will have to ensure it does not write to
+standard output either, if it wants to be compatible with this
+behavior and support piping to a file. Another benefit of running
+OCRmyPDF in a child process, as recommended above, is that it will
+not interfere with the parent process's standard output.
+
 Exceptions
 ----------
 
@@ -104,18 +125,4 @@ exceptions, some exceptions related to multiprocessing, and
 handler. OCRmyPDF will clean up its temporary files and worker processes
 automatically when an exception occurs.
 
-Programs that call OCRmyPDF should consider trapping KeyboardInterrupt
-so that they allow OCR to terminate with the whole program terminating.
-
 When OCRmyPDF succeeds conditionally, it returns an integer exit code.
-
-Reference
----------
-
-.. autofunction:: ocrmypdf.ocr
-
-.. autoclass:: ocrmypdf.Verbosity
-    :members:
-    :undoc-members:
-
-.. autofunction:: ocrmypdf.configure_logging

docs/apiref.rst

@@ -3,11 +3,11 @@
 .. SPDX-License-Identifier: CC-BY-SA-4.0
 
 =============
-API Reference
+API reference
 =============
 
 This page summarizes the rest of the public API. Generally speaking this
-should mainly of interest to plugin developers.
+should be mainly of interest to plugin developers.
 
 ocrmypdf
 ========
@@ -18,6 +18,18 @@ ocrmypdf
 .. autoclass:: ocrmypdf.PdfContext
     :members:
 
+.. autoclass:: ocrmypdf.Verbosity
+    :members:
+    :undoc-members:
+
+.. autofunction:: ocrmypdf.configure_logging
+
+.. autofunction:: ocrmypdf.ocr
+
+.. autofunction:: ocrmypdf.pdf_to_hocr
+
+.. autofunction:: ocrmypdf.hocr_to_ocr_pdf
+
 ocrmypdf.exceptions
 ===================
 

docs/batch.rst

@@ -152,7 +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 \
@@ -163,7 +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"
@@ -171,7 +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/cloud.rst

@@ -1,3 +1,8 @@
+.. SPDX-FileCopyrightText: 2023 James R. Barlow
+..
+.. SPDX-License-Identifier: CC-BY-SA-4.0
+
+
 .. _ocr-service:
 
 ==================

docs/contributing.rst

@@ -19,7 +19,7 @@ Code style
 ==========
 
 We use PEP8, ``black`` for code formatting and ``ruff`` for everything else. The
-settings for these programs are in ``pyproject.toml`` and ``setup.cfg``. Pull
+settings for these programs are in ``pyproject.toml``. Pull
 requests should follow the style guide. One difference we use from "black" style
 is that strings shown to the user are always in double quotes (``"``) and strings
 for internal uses are in single quotes (``'``).

docs/cookbook.rst

@@ -187,7 +187,7 @@ might remove desirable content, especially from poor quality scans.
    background from grayscale or color images. Monochrome images are
    ignored. This should not be used on documents that contain color
    photos as it may remove them.
--  ``--deskew`` will correct pages were scanned at a skewed angle by
+-  ``--deskew`` will correct pages that were scanned at a skewed angle by
    rotating them back into place.
 -  ``--clean`` uses
    `unpaper <https://www.flameeyes.eu/projects/unpaper>`__ to clean up
@@ -245,6 +245,20 @@ if all you want to is to apply image processing or PDF/A conversion.
     the case. Use ``--tesseract-non-ocr-timeout`` to control the timeout
     for non-OCR operations, if needed.
 
+Remove all text or OCR from my PDF
+----------------------------------
+
+This is getting ridiculous, but OCRmyPDF can complete strip all textual
+information from a PDF and reconstruct it as a "bag of images" PDF.
+
+.. code-block::
+
+    ocrmypdf --tesseract-timeout 0 --force-ocr input.pdf output.pdf
+
+Why would you want to do this? Perhaps you have a PDF where OCR
+fails to produce useful results, and just want to get rid of all OCR information.
+This command also removes OCR generated by third party tools.
+
 Optimize images without performing OCR
 --------------------------------------
 
@@ -393,4 +407,4 @@ any digital signatures will be invalidated.
 OCRmyPDF cannot open documents that are encrypted with a digital certificate.
 
 Versions of OCRmyPDF prior to 14.4.0 would invalidate existing digital signatures
-without warning.
+without warning.

docs/docker.rst

@@ -8,17 +8,16 @@
 OCRmyPDF Docker image
 =====================
 
-OCRmyPDF is also available in a Docker image that packages recent
+OCRmyPDF is also available in Docker images that packages recent
 versions of all dependencies.
 
 For users who already have Docker installed this may be an easy and
-convenient option. However, it is less performant than a system
-installation and may require Docker engine configuration.
+convenient option.
 
-OCRmyPDF needs a generous amount of RAM, CPU cores, temporary storage
-space, whether running in a Docker container or on its own. It may be
-necessary to ensure the container is provisioned with additional
-resources.
+On platforms other than Linux, Docker runs in a virtual machine, and so may
+be less performant. You may also want to adjust the Docker virtual machine's
+memory and CPU allocation. On Linux, the Docker image runs natively and
+performance is comparable to a system installation.
 
 .. _docker-install:
 
@@ -35,28 +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 and arm64
+     - Recommended image, based on Alpine Linux.
+   * - ``jbarlow83/ocrmypdf-ubuntu``
+     - x86_64 and arm64
+     - Alternate image, based on Ubuntu. When the Alpine image is considered
+       stable and available for arm64, this image will be deprecated.
+   * - ``jbarlow83/ocrmypdf``
+     - x86_64 and arm64
+     - Currently an alias for ocrmypdf-ubuntu. When the Alpine image is
+       considered stable and available for arm64, this name point to the
+       Alpine image. If you don't about the difference between Alpine and
+       Ubuntu, use this image.
+
+To install:
 
 .. code-block:: bash
 
-   docker pull jbarlow83/ocrmypdf
+   docker pull jbarlow83/ocrmypdf-alpine
 
+The ``ocrmypdf`` image is also available, but is deprecated and will be removed
+in the future.
 
-OCRmyPDF will use all available CPU cores. By default, the VirtualBox
-machine instance on Windows and macOS has only a single CPU core
-enabled. Use the VirtualBox Manager to determine the name of your Docker
-engine host, and then follow these optional steps to enable multiple
-CPUs:
-
-.. 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
+OCRmyPDF will use all available CPU cores. See the Docker documentation for
 `adjusting memory and CPU on other platforms <https://docs.docker.com/config/containers/resource_constraints/>`__.
 
 Using the Docker image on the command line
@@ -66,12 +74,14 @@ Using the Docker image on the command line
 container is ephemeral – it runs for one OCR job and terminates, just like a
 command line program. We are using Docker to deliver an application (as opposed
 to the more conventional case, where a Docker container runs as a server).
+For that reason we usually use the ``--rm`` argument to delete the container
+when it exits.
 
 To start a Docker container (instance of the image):
 
 .. code-block:: bash
 
-   docker tag jbarlow83/ocrmypdf ocrmypdf
+   docker tag jbarlow83/ocrmypdf-alpine ocrmypdf
    docker run --rm -i ocrmypdf (... all other arguments here...) - -
 
 For convenience, create a shell alias to hide the Docker command. It is
@@ -116,7 +126,7 @@ Dockerfile based on the public one.
    # Example: add Italian
    RUN apt install tesseract-ocr-ita
 
-To install language packs (training data) such as the 
+To install language packs (training data) such as the
 `tessdata_best <https://github.com/tesseract-ocr/tessdata_best>`_ suite or
 custom data, you first need to determine the version of Tesseract data files, which
 may differ from the Tesseract program version. Use this command to determine the data
@@ -132,17 +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/installation.rst

@@ -23,7 +23,9 @@ These platforms have one-liner installs:
 +-------------------------------+-----------------------------------------+
 | Fedora                        | ``dnf install ocrmypdf tesseract-osd``  |
 +-------------------------------+-----------------------------------------+
-| macOS                         | ``brew install ocrmypdf``               |
+| macOS (Homebrew)              | ``brew install ocrmypdf``               |
++-------------------------------+-----------------------------------------+
+| macOS (MacPorts)              | ``port install ocrmypdf``               |
 +-------------------------------+-----------------------------------------+
 | LinuxBrew                     | ``brew install ocrmypdf``               |
 +-------------------------------+-----------------------------------------+
@@ -99,12 +101,12 @@ For full details on version availability for your platform, check the
 Fedora
 ------
 
-.. |fedora-37| image:: https://repology.org/badge/version-for-repo/fedora_37/ocrmypdf.svg
-    :alt: Fedora 37
-
 .. |fedora-38| image:: https://repology.org/badge/version-for-repo/fedora_38/ocrmypdf.svg
     :alt: Fedora 38
 
+.. |fedora-39| image:: https://repology.org/badge/version-for-repo/fedora_39/ocrmypdf.svg
+    :alt: Fedora 39
+
 .. |fedora-rawhide| image:: https://repology.org/badge/version-for-repo/fedora_rawhide/ocrmypdf.svg
     :alt: Fedore Rawhide
 
@@ -113,7 +115,7 @@ Fedora
 +-----------------------------------------------+
 | |latest|                                      |
 +-----------------------------------------------+
-| |fedora-37| |fedora-38| |fedora-rawhide|      |
+| |fedora-38| |fedora-39| |fedora-rawhide|      |
 +-----------------------------------------------+
 
 Users of Fedora may simply
@@ -123,7 +125,7 @@ Users of Fedora may simply
     dnf install ocrmypdf tesseract-osd
 
 For full details on version availability, check the `Fedora Package
-Tracker <https://apps.fedoraproject.org/packages/ocrmypdf>`__.
+Tracker <https://packages.fedoraproject.org/pkgs/ocrmypdf/ocrmypdf/>`__.
 
 If the version available for your platform is out of date, you could opt
 to install the latest version from source. See `Installing HEAD revision
@@ -135,10 +137,36 @@ from sources <#installing-head-revision-from-sources>`__.
    issues. OCRmyPDF works fine without it but will produce larger output
    files. If you build jbig2enc from source, ocrmypdf 7.0.0 and later
    will automatically detect it on the ``PATH``. To add JBIG2 encoding,
-   see `Installing the JBIG2 encoder <jbig2>`__.
+   see :ref:`Installing the JBIG2 encoder <jbig2>`.
 
 .. _ubuntu-lts-latest:
 
+RHEL 9
+------
+
+Prepare the environment by getting Python 3.11:
+
+.. code-block:: bash
+
+    dnf install python3.11 python3.11-pip
+
+Then, follow `Requirements for pip and HEAD install <#requirements-for-pip-and-head-install>`__ to instal dependencies:
+
+.. code-block:: bash
+
+    dnf install ghostscript tesseract
+
+and build ocrmypdf in virtual environment:
+
+.. code-block:: bash
+
+    python3.11 -m venv .venv
+
+To add JBIG2 encoding, see :ref:`Installing the JBIG2 encoder <jbig2>`.
+
+Note Fedora packages for language data haven't been branched for RHEL/EPEL, but you can get traineddata files directly from `tesseract
+<https://github.com/tesseract-ocr/tessdata/>`__ and place them in ``/usr/share/tesseract/tessdata``.
+
 Installing the latest version on Ubuntu 22.04 LTS
 -------------------------------------------------
 
@@ -162,37 +190,13 @@ To add JBIG2 encoding, see :ref:`jbig2`.
 Ubuntu 20.04 LTS
 ----------------
 
-Ubuntu 20.04 includes ocrmypdf 9.6.0 - you can install that with ``apt``. To
-install a more recent version, uninstall the system-provided version of
-ocrmypdf, and install the following dependencies:
+Ubuntu 20.04 includes ocrmypdf 9.6.0 - you can install that with ``apt``. The
+most convenient way to install recent OCRmyPDF on older Ubuntu is to use
+Homebrew on Linux (Linuxbrew).
 
 .. code-block:: bash
 
-    sudo apt-get -y remove ocrmypdf  # remove system ocrmypdf, if installed
-    sudo apt-get -y update
-    sudo apt-get -y install \
-        ghostscript \
-        icc-profiles-free \
-        libxml2 \
-        pngquant \
-        python3-pip \
-        tesseract-ocr \
-        zlib1g
-
-To install ocrmypdf for the system:
-
-.. code-block:: bash
-
-    pip3 install ocrmypdf
-
-To install for the current user only:
-
-.. code-block:: bash
-
-    export PATH=$HOME/.local/bin:$PATH
-    pip3 install --user ocrmypdf
-
-To add JBIG2 encoding, see :ref:`jbig2`.
+    brew install ocrmypdf
 
 Arch Linux (AUR)
 ----------------
@@ -215,12 +219,12 @@ you are using a VM image, such as `the official Vagrant image
 be completed for you.
 
 Next you should install the `base-devel package group
-<https://www.archlinux.org/groups/x86_64/base-devel/>`__. This includes the
+<https://archlinux.org/packages/core/any/base-devel/>`__. This includes the
 standard tooling needed to build packages, such as a compiler and binary tools.
 
 .. code-block:: bash
 
-   sudo pacman -S base-devel
+   sudo pacman -S --needed base-devel
 
 Now you are ready to install the OCRmyPDF package.
 
@@ -258,7 +262,7 @@ page.
     <https://aur.archlinux.org/packages/jbig2enc-git/>`__ and may be installed
     using the same series of steps as for the installation OCRmyPDF AUR
     package. Alternatively, it may be built manually from source following the
-    instructions in `Installing the JBIG2 encoder <jbig2>`__.  If JBIG2 is
+    instructions in :ref:`Installing the JBIG2 encoder <jbig2>`.  If JBIG2 is
     installed, OCRmyPDF 7.0.0 and later will automatically detect it.
 
 Alpine Linux
@@ -323,6 +327,22 @@ languages you can optionally install them all:
 
     brew install tesseract-lang  # Optional: Install all language packs
 
+MacPorts
+--------
+
+.. image:: https://img.shields.io/badge/dynamic/json?url=https%3A%2F%2Fports.macports.org%2Fapi%2Fv1%2Fports%2Focrmypdf%2F%3Fformat%3Djson&query=version&label=MacPorts
+   :alt: Macports Version Information
+   :target: https://ports.macports.org/port/ocrmypdf
+
+OCRmyPDF is includes in MacPorts:
+
+.. code-block:: bash
+
+    sudo port install ocrmypdf
+
+Note that while this will install tesseract you will need to install
+the appropriate tesseract `language ports <https://ports.macports.org/search/?selected_facets=categories_exact%3Atextproc&installed_file=&q=tesseract&name=on>`__. 
+
 Manual installation on macOS
 ----------------------------
 
@@ -391,18 +411,20 @@ package manager:
 
 * ``winget install -e --id Python.Python.3.11``
 * ``winget install -e --id UB-Mannheim.TesseractOCR``
-* ``winget install -e --id ArtifexSoftware.GhostScript``
 
+You will need to install Ghostscript manually, `since it does not support automated
+installs anymore <https://artifex.com/news/ghostscript-10.01.0-disabling-silent-install-option>`_.
+
+* `Ghostscript download page <https://ghostscript.com/releases/gsdnld.html>`_.`
 
 (Or alternately, using the `Chocolatey <https://chocolatey.org/>`_ package manager, install
 the following when running in an Administrator command prompt):
 
 * ``choco install python3``
 * ``choco install --pre tesseract``
-* ``choco install ghostscript``
 * ``choco install pngquant`` (optional)
 
-Either set of commands will install the required software. At the mmoment there is no
+Either set of commands will install the required software. At the moment there is no
 single command to install Windows.
 
 You may then use ``pip`` to install ocrmypdf. (This can performed by a user or
@@ -452,7 +474,7 @@ Cygwin64
 
 First install the the following prerequisite Cygwin packages using ``setup-x86_64.exe``::
 
-    python39 (or later)
+    python310 (or later)
     python3?-devel
     python3?-pip
     python3?-lxml
@@ -538,9 +560,25 @@ try:
 
     pip install --user ocrmypdf
 
+(If the message appears ``Requirement already satisfied: ocrmypdf in...``,
+you will need to use ``pip install --user --upgrade ocrmypdf``.)
+
 You should then be able to run ``ocrmypdf --version`` and see that the
 latest version was located.
 
+Installing with pipx
+====================
+
+Some users may prefer pipx. As with the method above, you will need to
+satisfy all non-Python dependencies. Then if pipx is installed, you
+can use
+
+.. code-block:: bash
+
+    pipx run ocrmypdf
+
+(If not installed, pipx will install first.)
+
 Requirements for pip and HEAD install
 -------------------------------------
 
@@ -550,8 +588,8 @@ manager. ``pip`` cannot provide them.
 
 The following versions are required:
 
--  Python 3.9 or newer
--  Ghostscript 9.55 or newer
+-  Python 3.10 or newer
+-  Ghostscript 9.54 or newer
 -  Tesseract 4.1.1 or newer
 -  jbig2enc 0.29 or newer
 -  pngquant 2.5 or newer
@@ -586,7 +624,7 @@ unfortunately, the ``pip install`` command cannot satisfy all of them.
 Installing HEAD revision from sources
 =====================================
 
-If you have ``git`` and Python 3.9 or newer installed, you can install
+If you have ``git`` and Python 3.10 or newer installed, you can install
 from source. When the ``pip`` installer runs, it will alert you if
 dependencies are missing.
 
@@ -603,7 +641,7 @@ environment:
     pip install git+https://github.com/ocrmypdf/OCRmyPDF.git
 
 Or, to install in `development
-mode <https://pythonhosted.org/setuptools/setuptools.html#development-mode>`__,
+mode <https://packaging.python.org/en/latest/guides/distributing-packages-using-setuptools/#working-in-development-mode>`__,
 allowing customization of OCRmyPDF, use the ``-e`` flag:
 
 .. code-block:: bash
@@ -643,7 +681,7 @@ To install all of the development and test requirements:
 .. code-block:: bash
 
     git clone -b main https://github.com/ocrmypdf/OCRmyPDF.git
-    python -m .venv
+    python -m venv .venv
     source .venv/bin/activate
     cd OCRmyPDF
     pip install -e .[test]
@@ -669,7 +707,7 @@ To manually install the ``fish`` completion, copy
 Note on 32-bit support
 ======================
 
-Many Python libraries no longer 32-bit binary wheels for Linux. This
+Many Python libraries no longer provide 32-bit binary wheels for Linux. This
 includes many of the libraries that OCRmyPDF depends on, such as
 Pillow. The easiest way to express this to end users is to say we don't
 support 32-bit Linux.
@@ -679,4 +717,4 @@ can still install and use OCRmyPDF. A warning message will appear.
 In practice, OCRmyPDF may need more than 32-bit memory space to run when
 large documents are processed, so there are practical limitations to what
 users can accomplish with it. Still, for the common use case of an 32-bit
-ARM NAS or Raspberry Pi processing small documents, it should work.
+ARM NAS or Raspberry Pi processing small documents, it should work.

docs/introduction.rst

@@ -6,23 +6,23 @@
 Introduction
 ============
 
-OCRmyPDF is an application and library that adds text "layers" to images
-in PDFs, making scanned image PDFs searchable. It uses OCR to guess what text
-is contained in images. It is written in Python. OCRmyPDF supports plugins
-that allow customization of its processing steps, and is very tolerant of
-PDFs that contain scanned images and "born digital" content that needs no
-text recognition.
+OCRmyPDF is a Python application and library that adds text "layers" to images in
+PDFs, making scanned image PDFs searchable. It uses OCR to guess the text
+contained in images. OCRmyPDF also supports plugins
+that enable customization of its processing steps, and it is highly tolerant
+of PDFs containing scanned images and "born digital" content that doesn't
+require text recognition.
 
 About OCR
 =========
 
 `Optical character
 recognition <https://en.wikipedia.org/wiki/Optical_character_recognition>`__
-is technology that converts images of typed or handwritten text, such as
-in a scanned document, to computer text that can be selected, searched and copied.
+is a technology that converts images of typed or handwritten text, such as
+in a scanned document, into computer text that can be selected, searched and copied.
 
 OCRmyPDF uses
-`Tesseract <https://github.com/tesseract-ocr/tesseract>`__, the best
+`Tesseract <https://github.com/tesseract-ocr/tesseract>`__, a widely
 available open source OCR engine, to perform OCR.
 
 .. _raster-vector:
@@ -30,19 +30,19 @@ available open source OCR engine, to perform OCR.
 About PDFs
 ==========
 
-PDFs are page description files that attempts to preserve a layout
+PDFs are page description files that attempt to preserve a layout
 exactly. They contain `vector
 graphics <http://vector-conversions.com/vectorizing/raster_vs_vector.html>`__
-that can contain raster objects such as scanned images. Because PDFs can
+that can contain raster objects, such as scanned images. Because PDFs can
 contain multiple pages (unlike many image formats) and can contain fonts
-and text, it is a good format for exchanging scanned documents.
+and text, they are a suitable format for exchanging scanned documents.
 
 |image|
 
-A PDF page might contain multiple images, even if it only appears to
-have one image. Some scanners or scanning software will segment pages
-into monochromatic text and color regions for example, to improve the
-compression ratio and appearance of the page.
+A PDF page may contain multiple images, even if it appears to have only
+one image. Some scanners or scanning software may segment pages into
+monochromatic text and color regions, for example, to enhance the compression
+ratio and appearance of the page.
 
 Rasterizing a PDF is the process of generating corresponding raster images.
 OCR engines like Tesseract work with images, not scalable vector graphics
@@ -54,147 +54,131 @@ About PDF/A
 `PDF/A <https://en.wikipedia.org/wiki/PDF/A>`__ is an ISO-standardized
 subset of the full PDF specification that is designed for archiving (the
 'A' stands for Archive). PDF/A differs from PDF primarily by omitting
-features that would make it difficult to read the file in the future,
+features that could complicate future file readability,
 such as embedded Javascript, video, audio and references to external
 fonts. All fonts and resources needed to interpret the PDF must be
 contained within it. Because PDF/A disables Javascript and other types
-of embedded content, it is probably more secure.
+of embedded content, it is likely more secure.
 
 There are various conformance levels and versions, such as "PDF/A-2b".
 
-Generally speaking, the best format for scanned documents is PDF/A. Some
+In general, the preferred format for scanned documents is PDF/A. Some
 governments and jurisdictions, US Courts in particular, `mandate the use
 of PDF/A <https://pdfblog.com/2012/02/13/what-is-pdfa/>`__ for scanned
 documents.
 
-Since most people who scan documents are interested in reading them
-indefinitely into the future, OCRmyPDF generates PDF/A-2b by default.
+Since most individuals scanning documents aim for long-term readability,
+OCRmyPDF defaults to generating PDF/A-2b.
 
-PDF/A has a few drawbacks. Some PDF viewers include an alert that the
-file is a PDF/A, which may confuse some users. It also tends to produce
-larger files than PDF, because it embeds certain resources even if they
-are commonly available. PDF/A files can be digitally signed, but may not
-be encrypted, to ensure they can be read in the future. Fortunately,
-converting from PDF/A to a regular PDF is trivial, and any PDF viewer
-can view PDF/A.
+PDF/A does have a few drawbacks. Some PDF viewers display an alert
+indicating that the file is in PDF/A format, which may confuse some users.
+Additionally, it tends to result in larger files than standard PDFs because
+it embeds certain resources, even if they are widely available. PDF/A
+files can be digitally signed but may not be encrypted to ensure future
+readability. Fortunately, converting from PDF/A to a regular PDF is
+straightforward, and any PDF viewer can handle PDF/A files.
 
 What OCRmyPDF does
 ==================
 
-OCRmyPDF analyzes each page of a PDF to determine the colorspace and
-resolution (DPI) needed to capture all of the information on that page
-without losing content. It uses
-`Ghostscript <http://ghostscript.com/>`__ to rasterize the page, and
-then performs OCR on the rasterized image to create an OCR "layer".
-The layer is then grafted back onto the original PDF.
+OCRmyPDF analyzes each page of a PDF to determine the required colorspace
+and resolution (DPI) for capturing all the information on that page without
+losing content. It uses
+`Ghostscript <http://ghostscript.com/>`__ to rasterize each page and subsequently
+performs OCR on the rasterized image to generate an OCR "layer." This layer
+is then integrated back into the original PDF.
 
-While one can use a program like Ghostscript or ImageMagick to get an
-image and put the image through Tesseract, that actually creates a new
-PDF and many details may be lost. OCRmyPDF can produce a minimally
-changed PDF as output.
+While it is possible to use a program like Ghostscript or ImageMagick to
+obtain an image and then run that image through Tesseract OCR, this process
+actually generates a new PDF, potentially resulting in the loss of various
+details (such as the document's metadata). In contrast, OCRmyPDF can produce
+a minimally altered PDF as the output.
 
-OCRmyPDF also provides some image processing options, like deskew, which
-improves the appearance of files and quality of OCR. When these are used,
-the OCR layer is grafted onto the processed image instead.
+OCRmyPDF also offers several image processing options, such as deskew, which
+enhances the visual quality of files and the accuracy of OCR. When these
+options are utilized, the OCR layer is integrated into the processed image.
 
-By default, OCRmyPDF produces archival PDFs – PDF/A, which are a
-stricter subset of PDF features designed for long term archives. If
-regular PDFs are desired, this can be disabled with
-``--output-type pdf``.
+By default, OCRmyPDF generates archival PDFs in the PDF/A format, which is
+a more rigid subset of PDF features designed for long-term archives. If you
+prefer regular PDFs, you can disable this feature using the
+``--output-type pdf`` option.
 
 Why you shouldn't do this manually
 ==================================
 
 A PDF is similar to an HTML file, in that it contains document structure
-along with images. Sometimes a PDF does nothing more than present a full
-page image, but often there is additional content that would be lost.
+along with images. While some PDFs may solely display a full-page image,
+they often contain additional content that would be forfeited if not preserved.
 
-A manual process could work like either of these:
+A manual process could take one of these approaches:
 
-1. Rasterize each page as an image, OCR the images, and combine the
-   output into a PDF. This preserves the layout of each page, but
-   resamples all images (possibly losing quality, increasing file size,
-   introducing compression artifacts, etc.).
-2. Extract each image, OCR, and combine the output into a PDF. This
-   loses the context in which images are used in the PDF, meaning that
-   cropping, rotation and scaling of pages may be lost. Some scanned
-   PDFs use multiple images segmented into black and white, grayscale
+1. Rasterize each page as an image, perform OCR on the images, and then merge the
+   output into a PDF. This method preserves the layout of each page, but
+   resamples all images potentially leading to quality loss, increased file size,
+   and the introduction of compression artifacts, among other issues.
+2. Extract each image, OCR, and combine the output into a PDF. This approach
+   loses the context in which images are used in the PDF, potentially resulting
+   in loss of information related to scaling and position of images. Some scanned
+   PDFs contain multiple images segmented into black and white, grayscale
    and color regions, with stencil masks to prevent overlap, as this can
-   enhance the appearance of a file while reducing file size. Clearly,
-   reassembling these images will be easy. This also loses and text or
-   vector art on any pages in a PDF with both scanned and pure digital
-   content.
+   enhance the appearance of a file while reducing file size.
+   Reassembling these images can be challenging, and risks losing vector art
+   or text that is not part of an image.
 
-In the case of a PDF that is nothing other than a container of images
-(no rotation, scaling, cropping, one image per page), the second
-approach can be lossless.
+In cases where a PDF solely serves as a container for images without any
+rotation, scaling, or cropping, the second approach can be lossless.
 
-OCRmyPDF uses several strategies depending on input options and the
-input PDF itself, but generally speaking it rasterizes a page for OCR
-and then grafts the OCR back onto the original. As such it can handle
-complex PDFs and still preserve their contents as much as possible.
+OCRmyPDF uses various strategies depending on input options and the input PDF
+itself. Generally, it rasterizes a page for OCR and then integrates the OCR
+data back into the original PDF. This approach allows it to handle complex
+PDFs and preserve their content as much as possible.
 
-OCRmyPDF also supports a many, many edge cases that have cropped over
-several years of development. We support PDF features like images inside
-of Form XObjects, and pages with UserUnit scaling. We support rare image
-formats like non-monochrome 1-bit images. We warn about files you may
-not to OCR. Thanks to pikepdf and QPDF, we auto-repair PDFs that are
-damaged. (Not that you need to know what any of these are! You should be
-able to throw any PDF at it.)
+Furthermore, OCRmyPDF supports a wide range of edge cases that have emerged
+during several years of development. It accommodates PDF features like
+images within Form XObjects and pages with UserUnit scaling. It also
+supports less common image formats like non-monochrome 1-bit images and
+provides warnings about files you may not want to OCR. Thanks to tools
+like pikepdf and QPDF, it can auto-repair damaged PDFs. You don't need to
+understand the intricacies of these issues; you should be able to use
+OCRmyPDF with any PDF file, and expect reasonable results.
 
 Limitations
 ===========
 
-OCRmyPDF is limited by the Tesseract OCR engine. As such it experiences
-these limitations, as do any other programs that rely on Tesseract:
+OCRmyPDF is subject to limitations imposed by the Tesseract OCR engine.
+These limitations are inherent to any software relying on Tesseract:
 
--  The OCR is not as accurate as commercial OCR solutions.
--  It is not capable of recognizing handwriting.
--  It may find gibberish and report this as OCR output.
--  If a document contains languages outside of those given in the
-   ``-l LANG`` arguments, results may be poor.
--  It is not always good at analyzing the natural reading order of
-   documents. For example, it may fail to recognize that a document
-   contains two columns, and may try to join text across columns.
--  Poor quality scans may produce poor quality OCR. Garbage in, garbage
-   out.
--  It does not expose information about what font family text belongs
-   to.
-
-OCRmyPDF is also limited by the PDF specification:
-
--  PDF encodes the position of text glyphs but does not encode document
-   structure. There is no markup that divides a document in sections,
-   paragraphs, sentences, or even words (since blank spaces are not
-   represented). As such all elements of document structure including
-   the spaces between words must be derived heuristically. Some PDF
-   viewers do a better job of this than others.
--  Because some popular open source PDF viewers have a particularly hard
-   time with spaces between words, OCRmyPDF appends a space to each text
-   element as a workaround (when using ``--pdf-renderer hocr``). While
-   this mixes document structure with graphical information that ideally
-   should be left to the PDF viewer to interpret, it improves
-   compatibility with some viewers and does not cause problems for
-   better ones.
+-  The OCR accuracy may not match that of commercial OCR solutions.
+-  It is incapable of recognizing handwriting.
+-  It may detect gibberish and report it as OCR output.
+-  Results may be subpar when a document contains languages not specified
+   in the ``-l LANG`` argument.
+-  Tesseract may struggle to analyze the natural reading order of documents.
+   For instance, it might fail to recognize two columns in a document and
+   attempt to join text across columns.
+-  Poor quality scans can result in subpar OCR quality. In other words, the
+   quality of the OCR output depends on the quality of the input.
+-  Tesseract does not provide information about the font family to which text
+   belongs.
+-  Tesseract does not divide text into paragraphs or headings. It only provides
+   the text and its bounding box. As such, the generated PDF does not
+   contain any information about the document's structure.
 
 Ghostscript also imposes some limitations:
 
--  PDFs containing JBIG2-encoded content will be converted to CCITT
-   Group4 encoding, which has lower compression ratios, if Ghostscript
-   PDF/A is enabled.
--  PDFs containing JPEG 2000-encoded content will be converted to JPEG
+-  PDFs containing JPEG 2000-encoded content may be converted to JPEG
    encoding, which may introduce compression artifacts, if Ghostscript
    PDF/A is enabled.
--  Ghostscript may transcode grayscale and color images, either lossy to
-   lossless or lossless to lossy, based on an internal algorithm. This
+-  Ghostscript may transcode grayscale and color images, potentially
+   lossily, based on an internal algorithm. This
    behavior can be suppressed by setting ``--pdfa-image-compression`` to
    ``jpeg`` or ``lossless`` to set all images to one type or the other.
-   Ghostscript has no option to maintain the input image's format.
+   Ghostscript lacks an option to maintain the input image's format.
    (Modern Ghostscript can copy JPEG images without transcoding them.)
 -  Ghostscript's PDF/A conversion removes any XMP metadata that is not
    one of the standard XMP metadata namespaces for PDFs. In particular,
    PRISM Metadata is removed.
--  Ghostscript's PDF/A conversion seems to remove or deactivate
+-  Ghostscript's PDF/A conversion may remove or deactivate
    hyperlinks and other active content.
 
 You can use ``--output-type pdf`` to disable PDF/A conversion and produce
@@ -202,7 +186,7 @@ a standard, non-archival PDF.
 
 Regarding OCRmyPDF itself:
 
--  PDFs that use transparency are not currently represented in the test
+-  PDFs using transparency are not currently represented in the test
    suite
 
 Similar programs
@@ -210,11 +194,7 @@ Similar programs
 
 To the author's knowledge, OCRmyPDF is the most feature-rich and
 thoroughly tested command line OCR PDF conversion tool. If it does not
-meet your needs, contributions and suggestions are welcome. If not,
-consider one of these similar open source programs:
-
--  pdf2pdfocr
--  pdfsandwich
+meet your needs, contributions and suggestions are welcome.
 
 Ghostscript recently added three "pdfocr" output devices. They work by
 rasterizing all content and converting all pages to a single colour space.
@@ -222,16 +202,19 @@ rasterizing all content and converting all pages to a single colour space.
 Web front-ends
 ==============
 
-The Docker image ``ocrmypdf`` provides a web service front-end
-that allows files to submitted over HTTP and the results "downloaded".
-This is an HTTP server intended to simplify web services deployments; it
-is not intended to be deployed on the public internet and no real
-security measures to speak of.
+The Docker image of OCRmyPDF provides a web service front-end
+that allows files to submitted over HTTP, and the results can be downloaded.
+This is an HTTP server intended to demonstrate how OCRmyPDF can be
+integrated into a web service. It is not intended to be deployed on the
+public internet and does not provide any security measures.
 
 In addition, the following third-party integrations are available:
 
+-  `Paperless-ngx <https://docs.paperless-ngx.com/>`__ is a free software
+   document management system that uses OCRmyPDF to perform OCR on
+   uploaded documents.
 -  `Nextcloud OCR <https://github.com/janis91/ocr>`__ is a free software
-   plugin for the Nextcloud private cloud software
+   plugin for the Nextcloud private cloud software.
 
 OCRmyPDF is not designed to be secure against malware-bearing PDFs (see
 `Using OCRmyPDF online <ocr-service>`__). Users should ensure they

docs/jbig2.rst

@@ -14,17 +14,20 @@ expired as of 2017, but it is possible that unknown patents exist.
 
 JBIG2 encoding is recommended for OCRmyPDF and is used to losslessly
 create smaller PDFs. If JBIG2 encoding is not available, lower quality
-encodings will be used.
+CCITT encoding will be used for monochrome images.
 
 JBIG2 decoding is not patented and is performed automatically by most
 PDF viewers. It is widely supported and has been part of the PDF
 specification since 2001.
 
-On macOS, Homebrew packages jbig2enc and OCRmyPDF includes it by
-default. The Docker image for OCRmyPDF also builds its own JBIG2 encoder
-from source.
+JBIG encoding is automatically provided by these OCRmyPDF packages:
+- Docker image (both Ubuntu and Alpine)
+- Snap package
+- ArchLinux AUR package
+- Alpine Linux package
+- Homebrew on macOS
 
-For all other Linux, you must build a JBIG2 encoder from source:
+For all other platforms, you would need to build the JBIG2 encoder from source:
 
 .. code-block:: bash
 
@@ -38,21 +41,34 @@ For all other Linux, you must build a JBIG2 encoder from source:
 
 Dependencies include libtoolize and libleptonica, which on Ubuntu systems
 are packaged as libtool and libleptonica-dev. On Fedora (35) they are packaged
-as libtool and leptonica-devel.
+as libtool and leptonica-devel. For this to work, please make sure to install
+``autotools``, ``automake``, ``libtool`` and ``leptonica`` first if not already
+installed.
+
+.. code-block:: bash
+
+    [sudo] apt install autotools-dev automake libtool libleptonica-dev
+..
+
 
 Lossy mode JBIG2
 ================
 
-OCRmyPDF provides lossy mode JBIG2 as an advanced feature. Users should
+OCRmyPDF provides lossy mode JBIG2 as an advanced and potentially dangerous
+feature. Users should
 `review the technical concerns with JBIG2 in lossy
 mode <https://en.wikipedia.org/wiki/JBIG2#Disadvantages>`__
-and decide if this feature is acceptable for their use case.
+and decide if this feature is acceptable for their use case. In general,
+this mode should not be used for archival purposes, should not be used when
+the original document is not available or will be destroyed, and should
+not be used when numbers present in the document are important, because
+there is a risk of 6/8 and 8/6 substitution errors.
 
 JBIG2 lossy mode does achieve higher compression ratios than any other
 monochrome (bitonal) compression technology; for large text documents
 the savings are considerable. JBIG2 lossless still gives great
 compression ratios and is a major improvement over the older CCITT G4
-standard. As explained above, there is some risk of substitution errors.
+standard.
 
 To turn on JBIG2 lossy mode, add the argument ``--jbig2-lossy``.
 ``--optimize {1,2,3}`` are necessary for the argument to take effect

docs/languages.rst

@@ -18,16 +18,26 @@ Tesseract's documentation also lists the three-letter code for your language.
 Some are anglicized, e.g. Spanish is ``spa`` rather than ``esp``, while others
 are not, e.g. German is ``deu`` and French is ``fra``.
 
+Language packs (strictly speaking, Tesseract "traineddata" files) generally correspond
+to the language in question, but different language packs are used in certain
+situations. For German, the "Fraktur" language pack can assist with reading older
+materials in the Fraktur typeface family (``deu_frak``). Some communities have changed
+their script from Cyrillic to Latin; the Cyrillic version of Uzbek is available
+as ``uzb_cyrl`` and the Latin version is ``uzb``.
+
 After you have installed a language pack, you can use it with ``ocrmypdf -l <language>``,
 for example ``ocrmypdf -l spa``. For multilingual documents, you can specify
 all languages to be expected, e.g. ``ocrmypdf -l eng+fra`` for English and French.
 English is assumed by default unless other language(s) are specified.
 
 For Linux users, you can often find packages that provide language
-packs:
+packs.
 
-Debian and Ubuntu users
-=======================
+Platform install steps
+======================
+
+Debian and Ubuntu (apt)
+-----------------------
 
 .. code-block:: bash
 
@@ -42,8 +52,8 @@ to what languages it should search for. Multiple languages can be
 requested using either ``-l eng+fra`` (English and French) or
 ``-l eng -l fra``.
 
-Fedora users
-============
+Fedora
+------
 
 .. code-block:: bash
 
@@ -58,8 +68,24 @@ to what languages it should search for. Multiple languages can be
 requested using either ``-l eng+fra`` (English and French) or
 ``-l eng -l fra``.
 
-Gentoo users
-============
+Archlinux
+------
+
+.. code-block:: bash
+
+   # Display a list of all Tesseract language packs
+   pacman -Ss tesseract-data
+
+   # Install German language pack
+   pacman -S tesseract-data-deu
+
+You can then pass the ``-l LANG`` argument to OCRmyPDF to give a hint as
+to what languages it should search for. Multiple languages can be
+requested using either ``-l eng+fra`` (English and French) or
+``-l eng -l fra``.
+
+Gentoo
+------
 
 On Gentoo the package ``app-text/tessdata_fast``, which ``app-text/tesseract`` depends on, handles Tesseract languages.
 It accepts USE flags to select what languages should be installed, these can be set in ``/etc/portage/package.use``.
@@ -85,23 +111,31 @@ to what languages it should search for. Multiple languages can be
 requested using either ``-l eng+fra`` (English and French) or
 ``-l eng -l fra``.
 
-macOS users
-===========
+macOS
+-----
 
 You can install additional language packs by
 :ref:`installing Tesseract using Homebrew with all language packs <macos-all-languages>`.
 
-Docker users
-============
+Docker
+------
 
 Users of the OCRmyPDF Docker image should install language packs into a
 derived Docker image as
 :ref:`described in that section <docker-lang-packs>`.
 
-Windows users
-=============
+Windows
+-------
 
 The Tesseract installer provided by Chocolatey currently includes only English language.
 To install other languages, download the respective language pack (``.traineddata`` file)
 from https://github.com/tesseract-ocr/tessdata/ and place it in
 ``C:\\Program Files\\Tesseract-OCR\\tessdata`` (or wherever Tesseract OCR is installed).
+
+Custom language packs
+=====================
+
+If you have fine-tuned or trained Tesseract and generated custom trained data, you can
+copy your ``customlang.traineddata`` file into your Tesseract "tessdata" folder, and
+then use the ``-l customlang`` argument to tell OCRmyPDF to pass that language on to
+Tesseract.

docs/maintainers.rst

@@ -64,4 +64,13 @@ installation documentation.
 
 If you maintain a Linux distribution that supports 32-bit x86 or ARM, OCRmyPDF
 should continue to work as long as all of its dependencies continue to be
-available in 32-bit form. Please note we do not test on 32-bit platforms.
+available in 32-bit form. Please note we do not test on 32-bit platforms.
+
+HEIF/HEIC
+---------
+
+OCRmyPDF defaults to installing the pi-heif PyPI package, which supports converting
+HEIF (High Efficiency Image File Format) images to PDF from the command line.
+If your distribution does not have this library available, you can exclude it and
+OCRmyPDF will gracefully degrade automatically, losing only support for this
+feature.

docs/performance.rst

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

docs/plugins.rst

@@ -177,8 +177,13 @@ Custom command line arguments
 Execution and progress reporting
 --------------------------------
 
+.. autoclass:: ocrmypdf.pluginspec.ProgressBar
+    :members:
+    :special-members: __init__, __enter__, __exit__
+
 .. autoclass:: ocrmypdf.pluginspec.Executor
     :members:
+    :special-members: __call__
 
 .. autofunction:: ocrmypdf.pluginspec.get_logging_console
 

docs/release_notes.rst

@@ -20,6 +20,8 @@ The most recent release of OCRmyPDF is |OCRmyPDF PyPI|. Any newer versions
 referred to in these notes may exist the main branch but have not been
 tagged yet.
 
+OCRmyPDF typically supports the three most recent Python versions.
+
 .. note::
 
    Attention maintainers: these release notes may be updated with information
@@ -28,6 +30,247 @@ tagged yet.
 
 .. |OCRmyPDF PyPI| image:: https://img.shields.io/pypi/v/ocrmypdf.svg
 
+v16.4.2
+=======
+
+-  Fixed order of filenames passed to Ghostscript for PDF/A generation. :issue:`1359`
+-  Suppressed missing jbig2dec warning message. :issue:`1358`
+-  Fixed calculation of image size when soft mask dimensions don't match image
+   dimension. :issue:`1351`
+-  Several fixes to documentation. Thanks to users Iris and JoKalliauer
+   who contributed these changes.
+-  Fixed error on processing PDFs that are missing certain image metadata. :issue:`1315`
+
+v16.4.1
+=======
+
+-  Fixed calculation of image printed area (used in finding weighted DPI for OCR).
+   :issue:`1334`
+-  Fixed "NotImplementedError: not sure how to get colorspace" error
+   messages in logs which simply records a failure to optimize images with
+   print production colorspaces. :issue:`1315`
+
+v16.4.0
+=======
+
+-  Selecting the ``osd`` and ``equ`` pseudo-languages with ``-l/--language`` now
+   exits with an error when using Tesseract OCR, because these are not
+   regular Tesseract languages but implementation details implemented.
+   Using them can cause Tesseract to crash.
+-  The hOCR renderer is more tolerant of extra whitespace in input files.
+-  watcher.py now changes the output file extension to .pdf when the input is not
+   .pdf.
+-  Improved handling of PDFs that contain circularly referenced Form XObjects.
+   :issue:`1321`
+-  Fixed Alpine Docker image for ARM64, which was not building correctly.
+-  Docker images now use pikepdf 9.0.0.
+-  Prevent use of Tesseract OCR 5.4.0, a version with known regressions.
+-  Disabled progressbar for "Linearizing" when ``--no-progress-bar`` set.
+-  Fixed some tests that warn about missing JBIG2 decoding via pikepdf, by
+   installing the necessary libraries during tests.
+
+v16.3.1
+=======
+
+-  Fixed a test suite failure with Ghostscript 10.03.0+. :issue:`1316`
+-  Fixed an issue with the presentation of the "OCR" progress bar. :issue:`1313`
+
+v16.3.0
+=======
+
+-  Fixed progress bar not displaying for Ghostscript PDF/A conversion. :issue:`1313`
+-  Added progress bar for linearization. :issue:`1313`
+-  If `--rotate-pages-threshold` issued without `--rotate-pages` we now exit with
+   an error since the user likely intended to use `--rotate-pages`. :issue:`1309`
+-  If Tesseract hOCR gives an invalid line box, print an error message instead of
+   exiting with an error. :issue:`1312`
+
+v16.2.0
+=======
+
+-  Fixed issue 'NoneType' object has no attribute 'get' when optimizing certain PDFs.
+   :issue:`1293,1271`
+-  Switched formatting from black to ruff.
+-  Added support for sending sidecar output to io.BytesIO.
+-  Added support for converting HEIF/HEIC images (the native image of iPhones and
+   some other devices) to PDFs, when the appropriate pi-hief library is installed.
+   This library is marked as a dependency, but maintainers may opt out if needed.
+-  We now default to downsampling large images that would exceed Tesseract's internal
+   limits, but only if it cause processing to fail. Previously, this behavior only
+   occurred if specifically requested on command line. It can still be configured
+   and disabled. See the --tesseract command line options.
+-  Added Macports install instructions. Thanks @akierig.
+-  Improved logging output when an unexpected error occurs while trying to obtain
+   the version of a third party program.
+
+v16.1.2
+=======
+
+-  Fixed test suite failure when using Ghostscript 10.3.
+-  Other minor corrections.
+
+v16.1.1
+=======
+
+-  Fixed PyPy 3.10 support.
+
+v16.1.0
+=======
+
+-  Improved hOCR renderer is now default for left to right languages.
+-  Improved handling of rotated pages. Previously, OCR text might be missing for
+   pages that were rotated with a /Rotate tag on the page entry.
+-  Improved handling of cropped pages. Previously, in some cases a page with a
+   crop box would not have its OCR applied correctly and misalignment between
+   OCR text and visible text coudl occur.
+-  Documentation improvements, especially installation instructions for less
+   common platforms.
+
+v16.0.4
+=======
+
+-  Fixed some issues for left-to-right text with the new hOCR renderer. It is still
+   not default yet but will be made so soon. Right-to-left text is still in progress.
+-  Added an error to prevent use of several versions of Ghostscript that seem
+   corrupt existing text in input PDFs. Newly generated OCR is not affected.
+   For best results, use Ghostscript 10.02.1 or newer, which contains the fix
+   for the issue.
+
+v16.0.3
+=======
+
+-  Changed minimum required Ghostscript to 9.54, to support users of RHEL 9 and its
+   derivatives, since that is the latest version available there.
+-  Removed warning message about CVE-2023-43115, on the assumption that most
+   distributions have backported the patch by now.
+
+v16.0.2
+=======
+
+-  Temporarily changed PDF text renderer back to sandwich by default to address
+   regressions in macOS Preview.
+
+v16.0.1
+=======
+
+-  Fixed text rendering issue with new hOCR text renderer - extraneous byte order
+   marks.
+-  Tightened dependencies.
+
+v16.0.0
+=======
+
+-  Added OCR text renderer, combined the best ideas of Tesseract's PDF
+   generator and the older hOCR transformer renderer. The result is a hopefully
+   permanent fix for wordssmushedtogetherwithoutspaces issues in extracted text,
+   better registration/position of text on skewed baselines :issue:`1009`,
+   fixes to character output when the German Fraktur script is used :issue:`1191`,
+   proper rendering of right to left languages (Arabic, Hebrew, Persian) :issue:`1157`.
+   Asian languages may still have excessive word breaks compared to expectations.
+   The new renderer is the default; the old sandwich renderer is still available
+   using ``--pdf-renderer sandwich``; the old hOCR renderer is no more.
+-  The ``ocrmypdf.hocrtransform`` API has changed substantially.
+-  Support for Python 3.9 has been dropped. Python 3.10+ is now required.
+-  pikepdf >= 8.8.0 is now required.
+
+
+v15.4.4
+=======
+
+-  Fixed documentation for installing Ghostscript on Windows. :issue:`1198`
+-  Added warning message about security issue in older versions of Ghostscript.
+
+v15.4.3
+=======
+
+-  Fixed deprecation warning in pikepdf older than 8.7.1; pikepdf >= 8.7.1 is
+   now required.
+
+v15.4.2
+=======
+
+-  We now raise an exception on a certain class of PDFs that likely need an
+   explicit color conversion strategy selected to display correctly
+   for PDF/A conversion.
+-  Fixed an error that occurred while trying to write a log message after the
+   debug log handler was removed.
+
+v15.4.1
+=======
+
+-  Fixed misc/watcher.py regressions: accept ``--ocr-json-settings`` as either
+   filename or JSON string, as previously; and argument count mismatch.
+   :issue:`1183,1185`
+-  We no longer attempt to set /ProcSet in the PDF output, since this is an
+   obsolete PDF feature.
+-  Documentation improvements.
+
+v15.4.0
+=======
+
+-  Added new experimental APIs to support offline editing of the final text.
+   Specifically, one can now generate hOCR files with OCRmyPDF, edit them with
+   some other tool, and then finalize the PDF. They are experimental and
+   subject to change, including details of how the working folder is used.
+   There is no command line interface.
+-  Code reorganization: executors, progress bars, initialization and setup.
+-  Fixed test coverage in cases where the coverage tool did not properly trace
+   into threads or subprocesses. This code was still being tested but appeared
+   as not covered.
+-  In the test suite, reduced use of subprocesses and other techniques that
+   interfere with coverage measurement.
+-  Improved error check for when we appear to be running inside a snap container
+   and files are not available.
+-  Plugin specification now properly defines progress bars as a protocol rather
+   than defining them as "tqdm-like".
+-  We now default to using "forkserver" process creation on POSIX platforms
+   rather than fork, since this is method is more robust and avoids some
+   issues when threads are present.
+-  Fixed an instance where the user's request to ``--no-use-threads`` was ignored.
+-  If a PDF does not have language metadata on its top level object, we add
+   the OCR language.
+-  Replace some cryptic test error messages with more helpful ones.
+-  Debug messages for how OCRmyPDF picks the colorspace for a page are now
+   more descriptive.
+
+v15.3.1
+=======
+
+-  Fixed an issue with logging settings for misc/watcher.py introduced in the
+   previous release. :issue:`1180`
+-  We now attempt to preserve the input's extended attributes when creating
+   the output file.
+-  For some reason, the macOS build now needs OpenSSL explicitly installed.
+-  Updated documentation on Docker performance concerns.
+
+v15.3.0
+=======
+
+-  Update misc/watcher.py to improve command line interface using Typer, and
+   support ``.env`` specification of environment variables. Improved error
+   messages. Thanks to @mflagg2814 for the PR that prompted this improvement.
+-  Improved error message when a file cannot be read because we are running in
+   a snap container.
+
+v15.2.0
+=======
+
+-  Added a Docker image based on Alpine Linux. This image is smaller than the
+   Ubuntu-based image and may be useful in some situations. Currently hosted at
+   jbarlow83/ocrmypdf-alpine. Currently not available in ARM flavor.
+-  The Ubuntu Docker is now aliased to jbarlow83/ocrmypdf-ubuntu.
+-  Updated Docker documentation.
+
+v15.1.0
+=======
+
+-  We now require Pillow 10.0.1, due a serious security vulnerability in all earlier
+   versions of that dependency. The vulnerability concerns WebP images and could
+   be triggered in OCRmyPDF when creating a PDF from a malicious WebP image.
+-  Added some keyword arguments to ``ocrmypdf.ocr`` that were previously accepted
+   but undocumented.
+-  Documentation updates and typing improvements.
+
 v15.0.2
 =======
 
@@ -47,22 +290,25 @@ v15.0.0
 =======
 
 -  Dropped support for Python 3.8.
--  Dropped support many older dependencies - see ``pyproject.toml`` for details.
-   Generally speaking, Ubuntu 22.04 is our baseline system.
+-  Dropped support 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 an issue
-   with pikepdf has been fixed.
+-  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 situations where a small portion of an image on a page reports a
-   high DPI (resolution). Previously, the entire page would be rasterized at the
-   highest resolution, which caused performance problems. Now, the page is rasterized
+-  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

misc/batch.py

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

misc/synology.py

@@ -53,9 +53,10 @@ for dir_name, _subdirs, file_list in os.walk(start_dir):
         ]
         logging.info(cmd)
         full_path_ocr = os.path.join(dir_name, filename_ocr)
-        with open(filename, 'rb') as input_file, open(
-            full_path_ocr, 'wb'
-        ) as output_file:
+        with (
+            open(filename, 'rb') as input_file,
+            open(full_path_ocr, 'wb') as output_file,
+        ):
             proc = subprocess.run(
                 cmd,
                 stdin=input_file,

misc/watcher.py

@@ -5,107 +5,127 @@
 
 """Watch a directory for new PDFs and OCR them."""
 
-from __future__ import annotations
+# Do not enable annotations!
+# https://github.com/tiangolo/typer/discussions/598
 
 import json
 import logging
-import os
 import shutil
 import sys
 import time
 from datetime import datetime
+from enum import Enum
 from pathlib import Path
+from typing import Annotated, Any
 
 import pikepdf
+import typer
+from dotenv import load_dotenv
 from watchdog.events import PatternMatchingEventHandler
 from watchdog.observers import Observer
 from watchdog.observers.polling import PollingObserver
 
 import ocrmypdf
 
+load_dotenv()
+
+
 # pylint: disable=logging-format-interpolation
-
-
-def getenv_bool(name: str, default: str = 'False'):
-    return os.getenv(name, default).lower() in ('true', 'yes', 'y', '1')
-
-
-INPUT_DIRECTORY = os.getenv('OCR_INPUT_DIRECTORY', '/input')
-OUTPUT_DIRECTORY = os.getenv('OCR_OUTPUT_DIRECTORY', '/output')
-ARCHIVE_DIRECTORY = os.getenv('OCR_ARCHIVE_DIRECTORY', '/processed')
-OUTPUT_DIRECTORY_YEAR_MONTH = getenv_bool('OCR_OUTPUT_DIRECTORY_YEAR_MONTH')
-ON_SUCCESS_DELETE = getenv_bool('OCR_ON_SUCCESS_DELETE')
-ON_SUCCESS_ARCHIVE = getenv_bool('OCR_ON_SUCCESS_ARCHIVE')
-DESKEW = getenv_bool('OCR_DESKEW')
-OCR_JSON_SETTINGS = json.loads(os.getenv('OCR_JSON_SETTINGS', '{}'))
-POLL_NEW_FILE_SECONDS = int(os.getenv('OCR_POLL_NEW_FILE_SECONDS', '1'))
-USE_POLLING = getenv_bool('OCR_USE_POLLING')
-RETRIES_LOADING_FILE = int(os.getenv('OCR_RETRIES_LOADING_FILE', '5'))
-LOGLEVEL = os.getenv('OCR_LOGLEVEL', 'INFO')
-PATTERNS = ['*.pdf', '*.PDF']
+app = typer.Typer(name="ocrmypdf-watcher")
 
 log = logging.getLogger('ocrmypdf-watcher')
 
 
-def get_output_dir(root, basename):
-    if OUTPUT_DIRECTORY_YEAR_MONTH:
+class LoggingLevelEnum(str, Enum):
+    """Enum for logging levels."""
+
+    DEBUG = "DEBUG"
+    INFO = "INFO"
+    WARNING = "WARNING"
+    ERROR = "ERROR"
+    CRITICAL = "CRITICAL"
+
+
+def get_output_path(root: Path, basename: str, output_dir_year_month: bool) -> Path:
+    assert '/' not in basename, "basename must not contain '/'"
+    if output_dir_year_month:
         today = datetime.today()
-        output_directory_year_month = (
-            Path(root) / str(today.year) / f'{today.month:02d}'
-        )
+        output_directory_year_month = root / str(today.year) / f'{today.month:02d}'
         if not output_directory_year_month.exists():
             output_directory_year_month.mkdir(parents=True, exist_ok=True)
-        output_path = Path(output_directory_year_month) / basename
+        output_path = Path(output_directory_year_month) / Path(basename).with_suffix(
+            '.pdf'
+        )
     else:
-        output_path = Path(OUTPUT_DIRECTORY) / basename
+        output_path = root / Path(basename).with_suffix('.pdf')
     return output_path
 
 
-def wait_for_file_ready(file_path):
+def wait_for_file_ready(
+    file_path: Path, poll_new_file_seconds: int, retries_loading_file: int
+):
     # This loop waits to make sure that the file is completely loaded on
     # disk before attempting to read. Docker sometimes will publish the
     # watchdog event before the file is actually fully on disk, causing
     # pikepdf to fail.
 
-    retries = RETRIES_LOADING_FILE
-    while retries:
+    tries = retries_loading_file + 1
+    while tries:
         try:
-            pdf = pikepdf.open(file_path)
-        except (FileNotFoundError, pikepdf.PdfError) as e:
+            with pikepdf.Pdf.open(file_path) as pdf:
+                log.debug(f"{file_path} ready with {pdf.pages} pages")
+                return True
+        except (FileNotFoundError, OSError) as e:
             log.info(f"File {file_path} is not ready yet")
             log.debug("Exception was", exc_info=e)
-            time.sleep(POLL_NEW_FILE_SECONDS)
-            retries -= 1
-        else:
-            pdf.close()
-            return True
+            time.sleep(poll_new_file_seconds)
+            tries -= 1
+        except pikepdf.PdfError as e:
+            log.info(f"File {file_path} is not full written yet")
+            log.debug("Exception was", exc_info=e)
+            time.sleep(poll_new_file_seconds)
+            tries -= 1
 
     return False
 
 
-def execute_ocrmypdf(file_path):
-    file_path = Path(file_path)
-    output_path = get_output_dir(OUTPUT_DIRECTORY, file_path.name)
+def execute_ocrmypdf(
+    *,
+    file_path: Path,
+    archive_dir: Path,
+    output_dir: Path,
+    ocrmypdf_kwargs: dict[str, Any],
+    on_success_delete: bool,
+    on_success_archive: bool,
+    poll_new_file_seconds: int,
+    retries_loading_file: int,
+    output_dir_year_month: bool,
+):
+    output_path = get_output_path(output_dir, file_path.name, output_dir_year_month)
 
     log.info("-" * 20)
-    log.info(f'New file: {file_path}. Waiting until fully loaded...')
-    if not wait_for_file_ready(file_path):
+    log.info(f'New file: {file_path}. Waiting until fully written...')
+    if not wait_for_file_ready(file_path, poll_new_file_seconds, retries_loading_file):
         log.info(f"Gave up waiting for {file_path} to become ready")
         return
     log.info(f'Attempting to OCRmyPDF to: {output_path}')
+
+    log.debug(
+        f'OCRmyPDF input_file={file_path} output_file={output_path} '
+        f'kwargs: {ocrmypdf_kwargs}'
+    )
     exit_code = ocrmypdf.ocr(
         input_file=file_path,
         output_file=output_path,
-        deskew=DESKEW,
-        **OCR_JSON_SETTINGS,
+        **ocrmypdf_kwargs,
     )
     if exit_code == 0:
-        if ON_SUCCESS_DELETE:
+        if on_success_delete:
             log.info(f'OCR is done. Deleting: {file_path}')
             file_path.unlink()
-        elif ON_SUCCESS_ARCHIVE:
-            log.info(f'OCR is done. Archiving {file_path.name} to {ARCHIVE_DIRECTORY}')
-            shutil.move(file_path, f'{ARCHIVE_DIRECTORY}/{file_path.name}')
+        elif on_success_archive:
+            log.info(f'OCR is done. Archiving {file_path.name} to {archive_dir}')
+            shutil.move(file_path, f'{archive_dir}/{file_path.name}')
         else:
             log.info('OCR is done')
     else:
@@ -113,61 +133,204 @@ def execute_ocrmypdf(file_path):
 
 
 class HandleObserverEvent(PatternMatchingEventHandler):
+    def __init__(  # noqa: D107
+        self,
+        patterns=None,
+        ignore_patterns=None,
+        ignore_directories=False,
+        case_sensitive=False,
+        settings={},
+    ):
+        super().__init__(
+            patterns=patterns,
+            ignore_patterns=ignore_patterns,
+            ignore_directories=ignore_directories,
+            case_sensitive=case_sensitive,
+        )
+        self._settings = settings
+
     def on_any_event(self, event):
         if event.event_type in ['created']:
-            execute_ocrmypdf(event.src_path)
+            execute_ocrmypdf(file_path=Path(event.src_path), **self._settings)
 
 
-def main():
+@app.command()
+def main(
+    input_dir: Annotated[
+        Path,
+        typer.Argument(
+            envvar='OCR_INPUT_DIRECTORY',
+            exists=True,
+            file_okay=False,
+            dir_okay=True,
+            readable=True,
+            resolve_path=True,
+        ),
+    ] = '/input',
+    output_dir: Annotated[
+        Path,
+        typer.Argument(
+            envvar='OCR_OUTPUT_DIRECTORY',
+            exists=True,
+            file_okay=False,
+            dir_okay=True,
+            writable=True,
+            resolve_path=True,
+        ),
+    ] = '/output',
+    archive_dir: Annotated[
+        Path,
+        typer.Argument(
+            envvar='OCR_ARCHIVE_DIRECTORY',
+            exists=True,
+            file_okay=False,
+            dir_okay=True,
+            writable=True,
+            resolve_path=True,
+        ),
+    ] = '/processed',
+    output_dir_year_month: Annotated[
+        bool,
+        typer.Option(
+            envvar='OCR_OUTPUT_DIRECTORY_YEAR_MONTH',
+            help='Create a subdirectory in the output directory for each year/month',
+        ),
+    ] = False,
+    on_success_delete: Annotated[
+        bool,
+        typer.Option(
+            envvar='OCR_ON_SUCCESS_DELETE',
+            help='Delete the input file after successful OCR',
+        ),
+    ] = False,
+    on_success_archive: Annotated[
+        bool,
+        typer.Option(
+            envvar='OCR_ON_SUCCESS_ARCHIVE',
+            help='Archive the input file after successful OCR',
+        ),
+    ] = False,
+    deskew: Annotated[
+        bool,
+        typer.Option(
+            envvar='OCR_DESKEW',
+            help='Deskew the input file before OCR',
+        ),
+    ] = False,
+    ocr_json_settings: Annotated[
+        str,
+        typer.Option(
+            envvar='OCR_JSON_SETTINGS',
+            help='JSON settings to pass to OCRmyPDF (JSON string or file path)',
+        ),
+    ] = None,
+    poll_new_file_seconds: Annotated[
+        int,
+        typer.Option(
+            envvar='OCR_POLL_NEW_FILE_SECONDS',
+            help='Seconds to wait before polling a new file',
+            min=0,
+        ),
+    ] = 1,
+    use_polling: Annotated[
+        bool,
+        typer.Option(
+            envvar='OCR_USE_POLLING',
+            help='Use polling instead of filesystem events',
+        ),
+    ] = False,
+    retries_loading_file: Annotated[
+        int,
+        typer.Option(
+            envvar='OCR_RETRIES_LOADING_FILE',
+            help='Number of times to retry loading a file before giving up',
+            min=0,
+        ),
+    ] = 5,
+    loglevel: Annotated[
+        LoggingLevelEnum,
+        typer.Option(
+            envvar='OCR_LOGLEVEL',
+            help='Logging level',
+        ),
+    ] = LoggingLevelEnum.INFO,
+    patterns: Annotated[
+        str,
+        typer.Option(
+            envvar='OCR_PATTERNS',
+            help='File patterns to watch',
+        ),
+    ] = '*.pdf,*.PDF',
+):
     ocrmypdf.configure_logging(
         verbosity=(
             ocrmypdf.Verbosity.default
-            if LOGLEVEL != 'DEBUG'
+            if loglevel != LoggingLevelEnum.DEBUG
             else ocrmypdf.Verbosity.debug
         ),
         manage_root_logger=True,
     )
-    log.setLevel(LOGLEVEL)
+    log.setLevel(loglevel.value)
     log.info(
         f"Starting OCRmyPDF watcher with config:\n"
-        f"Input Directory: {INPUT_DIRECTORY}\n"
-        f"Output Directory: {OUTPUT_DIRECTORY}\n"
-        f"Output Directory Year & Month: {OUTPUT_DIRECTORY_YEAR_MONTH}\n"
-        f"Archive Directory: {ARCHIVE_DIRECTORY}"
+        f"Input Directory: {input_dir}\n"
+        f"Output Directory: {output_dir}\n"
+        f"Output Directory Year & Month: {output_dir_year_month}\n"
+        f"Archive Directory: {archive_dir}"
     )
     log.debug(
-        f"INPUT_DIRECTORY: {INPUT_DIRECTORY}\n"
-        f"OUTPUT_DIRECTORY: {OUTPUT_DIRECTORY}\n"
-        f"OUTPUT_DIRECTORY_YEAR_MONTH: {OUTPUT_DIRECTORY_YEAR_MONTH}\n"
-        f"ARCHIVE_DIRECTORY: {ARCHIVE_DIRECTORY}\n"
-        f"ON_SUCCESS_DELETE: {ON_SUCCESS_DELETE}\n"
-        f"ON_SUCCESS_ARCHIVE: {ON_SUCCESS_ARCHIVE}\n"
-        f"DESKEW: {DESKEW}\n"
-        f"ARGS: {OCR_JSON_SETTINGS}\n"
-        f"POLL_NEW_FILE_SECONDS: {POLL_NEW_FILE_SECONDS}\n"
-        f"RETRIES_LOADING_FILE: {RETRIES_LOADING_FILE}\n"
-        f"USE_POLLING: {USE_POLLING}\n"
-        f"LOGLEVEL: {LOGLEVEL}"
+        f"INPUT_DIRECTORY: {input_dir}\n"
+        f"OUTPUT_DIRECTORY: {output_dir}\n"
+        f"OUTPUT_DIRECTORY_YEAR_MONTH: {output_dir_year_month}\n"
+        f"ARCHIVE_DIRECTORY: {archive_dir}\n"
+        f"ON_SUCCESS_DELETE: {on_success_delete}\n"
+        f"ON_SUCCESS_ARCHIVE: {on_success_archive}\n"
+        f"DESKEW: {deskew}\n"
+        f"ARGS: {ocr_json_settings}\n"
+        f"POLL_NEW_FILE_SECONDS: {poll_new_file_seconds}\n"
+        f"RETRIES_LOADING_FILE: {retries_loading_file}\n"
+        f"USE_POLLING: {use_polling}\n"
+        f"LOGLEVEL: {loglevel.value}"
     )
 
-    if 'input_file' in OCR_JSON_SETTINGS or 'output_file' in OCR_JSON_SETTINGS:
-        log.error('OCR_JSON_SETTINGS should not specify input file or output file')
+    if ocr_json_settings and Path(ocr_json_settings).exists():
+        json_settings = json.loads(Path(ocr_json_settings).read_text())
+    else:
+        json_settings = json.loads(ocr_json_settings or '{}')
+
+    if 'input_file' in json_settings or 'output_file' in json_settings:
+        log.error(
+            'OCR_JSON_SETTINGS (--ocr-json-settings) may not specify input/output file'
+        )
         sys.exit(1)
 
-    handler = HandleObserverEvent(patterns=PATTERNS)
-    if USE_POLLING:
+    handler = HandleObserverEvent(
+        patterns=patterns.split(','),
+        settings={
+            'archive_dir': archive_dir,
+            'output_dir': output_dir,
+            'ocrmypdf_kwargs': json_settings | {'deskew': deskew},
+            'on_success_delete': on_success_delete,
+            'on_success_archive': on_success_archive,
+            'poll_new_file_seconds': poll_new_file_seconds,
+            'retries_loading_file': retries_loading_file,
+            'output_dir_year_month': output_dir_year_month,
+        },
+    )
+    if use_polling:
         observer = PollingObserver()
     else:
         observer = Observer()
-    observer.schedule(handler, INPUT_DIRECTORY, recursive=True)
+    observer.schedule(handler, input_dir, recursive=True)
     observer.start()
+    typer.echo(f"Watching {input_dir} for new PDFs. Press Ctrl+C to exit.")
     try:
         while True:
-            time.sleep(1)
+            time.sleep(30)
     except KeyboardInterrupt:
         observer.stop()
     observer.join()
 
 
 if __name__ == "__main__":
-    main()
+    app()

pyproject.toml

@@ -10,18 +10,17 @@ dynamic = ["version"]
 description = "OCRmyPDF adds an OCR text layer to scanned PDF files, allowing them to be searched"
 readme = "README.md"
 license = { text = "MPL-2.0" }
-requires-python = ">=3.9"
+requires-python = ">=3.10"
 dependencies = [
-  "Pillow>=9.0.1",
   "deprecation>=2.1.0",
-  "img2pdf>=0.4.4",
+  "img2pdf>=0.5",
   "packaging>=20",
   "pdfminer.six>=20220319",
-  "pikepdf>=8",
-  "pluggy>=0.13.0",
-  "reportlab>=3.6.8",
+  "pi-heif",                # Heif image format - maintainers: if this is removed, it will NOT break
+  "pikepdf>=8.10.1",
+  "Pillow>=10.0.1",
+  "pluggy>=1",
   "rich>=13",
-  "typing-extensions>=4;python_version<'3.10'",
 ]
 authors = [{ name = "James R. Barlow", email = "james@purplerock.ca" }]
 classifiers = [
@@ -50,7 +49,7 @@ Tracker = "https://github.com/ocrmypdf/OCRmyPDF/issues"
 
 [project.optional-dependencies]
 docs = ["sphinx", "sphinx-issues", "sphinx-rtd-theme"]
-extended_test = ["PyMuPDF==1.19.1"]
+extended_test = ["PyMuPDF>=1.19.1"]
 test = [
   "coverage[toml]>=6.2",
   "hypothesis>=6.36.0",
@@ -58,10 +57,11 @@ test = [
   "pytest-cov>=3.0.0",
   "pytest-xdist>=2.5.0",
   "python-xmp-toolkit==2.0.1", # also requires apt-get install libexempi3
+  "reportlab>=3.6.8",
   "types-Pillow",
   "types-humanfriendly",
 ]
-watcher = ["watchdog>=1.0.2"]
+watcher = ["watchdog>=1.0.2", "typer-slim[standard]", "python-dotenv"]
 webservice = ["Flask>=2.0.1"]
 
 [project.scripts]
@@ -77,35 +77,13 @@ namespaces = false
 [tool.setuptools_scm]
 
 [tool.distutils.bdist_wheel]
-python-tag = "py39"
-
-[tool.black]
-line-length = 88
-target-version = ["py39", "py310", "py311"]
-skip-string-normalization = true
-include = '\.pyi?$'
-exclude = '''
-/(
-    \.eggs
-  | \.git
-  | \.hg
-  | \.mypy_cache
-  | \.tox
-  | \.venv
-  | _build
-  | buck-out
-  | build
-  | dist
-  | docs
-  | misc
-  | \.egg-info
-)/
-'''
+python-tag = "py310"
 
 [tool.coverage.run]
 branch = true
 parallel = true
-concurrency = ["multiprocessing"]
+concurrency = ["multiprocessing", "thread"]
+sigterm = true
 
 [tool.coverage.paths]
 source = ["src/ocrmypdf"]
@@ -131,7 +109,11 @@ norecursedirs = ["lib", ".pc", ".git", "venv", "output", "cache", "resources"]
 testpaths = ["tests"]
 addopts = "-n auto"
 markers = ["slow"]
-filterwarnings = ["ignore:.*XMLParser.*:DeprecationWarning"]
+filterwarnings = [
+  "ignore:.*XMLParser.*:DeprecationWarning",
+  "ignore:.*ast.NameConstant.*:DeprecationWarning:reportlab",
+  "ignore:.*distutils.*:DeprecationWarning:libxmp",
+]
 
 [tool.mypy]
 
@@ -149,7 +131,10 @@ module = [
 ignore_missing_imports = true
 
 [tool.ruff]
-select = [
+target-version = "py310"
+
+[tool.ruff.lint]
+"select" = [
   "D",    # pydocstyle
   "E",    # pycodestyle
   "W",    # pycodestyle
@@ -157,17 +142,18 @@ select = [
   "I001", # isort
   "UP",   # pyupgrade
 ]
-target-version = "py39"
 
-[tool.ruff.isort]
+[tool.ruff.lint.isort]
 known-first-party = ["ocrmypdf"]
-required-imports = ["from __future__ import annotations"]
 
-[tool.ruff.pydocstyle]
+[tool.ruff.lint.pydocstyle]
 convention = "google"
 
-[tool.ruff.per-file-ignores]
+[tool.ruff.lint.per-file-ignores]
 "docs/conf.py" = ["D100", "D101", "D105"]
 "tests/*.py" = ["D100", "D101", "D102", "D103", "D105"]
 "misc/*.py" = ["D103", "D101", "D102"]
 "src/ocrmypdf/builtin_plugins/*.py" = ["D103", "D102", "D105"]
+
+[tool.ruff.format]
+quote-style = "preserve"

snapcraft.yaml

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

src/ocrmypdf/__init__.py

@@ -10,8 +10,15 @@ from pluggy import HookimplMarker as _HookimplMarker
 from ocrmypdf import helpers, hocrtransform, pdfa, pdfinfo
 from ocrmypdf._concurrent import Executor
 from ocrmypdf._jobcontext import PageContext, PdfContext
+from ocrmypdf._pipelines._common import (
+    configure_debug_logging,
+)
 from ocrmypdf._version import PROGRAM_NAME, __version__
-from ocrmypdf.api import Verbosity, configure_logging, ocr
+from ocrmypdf.api import (
+    Verbosity,
+    configure_logging,
+    ocr,
+)
 from ocrmypdf.exceptions import (
     BadArgsError,
     DpiError,
@@ -30,9 +37,11 @@ from ocrmypdf.pluginspec import OcrEngine, OrientationConfidence
 
 hookimpl = _HookimplMarker('ocrmypdf')
 
+
 __all__ = [
     '__version__',
     'BadArgsError',
+    'configure_debug_logging',
     'configure_logging',
     'DpiError',
     'EncryptedPdfError',

src/ocrmypdf/__main__.py

@@ -7,14 +7,15 @@
 from __future__ import annotations
 
 import logging
+import multiprocessing
 import os
 import signal
 import sys
 from contextlib import suppress
 
 from ocrmypdf import __version__
+from ocrmypdf._pipelines.ocr import run_pipeline_cli
 from ocrmypdf._plugin_manager import get_parser_options_plugins
-from ocrmypdf._sync import run_pipeline
 from ocrmypdf._validation import check_options
 from ocrmypdf.api import Verbosity, configure_logging
 from ocrmypdf.exceptions import (
@@ -71,9 +72,12 @@ def run(args=None):
     with suppress(AttributeError, OSError):
         signal.signal(signal.SIGBUS, sigbus)
 
-    result = run_pipeline(options=options, plugin_manager=plugin_manager)
+    result = run_pipeline_cli(options=options, plugin_manager=plugin_manager)
     return result
 
 
 if __name__ == '__main__':
+    multiprocessing.freeze_support()
+    if os.name == 'posix':
+        multiprocessing.set_start_method('forkserver')
     sys.exit(run())

src/ocrmypdf/_concurrent.py

@@ -7,27 +7,20 @@ from __future__ import annotations
 
 import threading
 from abc import ABC, abstractmethod
-from typing import Callable, Iterable
+from collections.abc import Callable, Iterable
+from typing import Any, TypeVar
+
+from ocrmypdf._progressbar import NullProgressBar, ProgressBar
+
+T = TypeVar('T')
 
 
 def _task_noop(*_args, **_kwargs):
     return
 
 
-class NullProgressBar:
-    """Progress bar API that takes no actions."""
-
-    def __init__(self, **kwargs):
-        pass
-
-    def __enter__(self):
-        return self
-
-    def __exit__(self, exc_type, exc_value, traceback):
-        return False
-
-    def update(self, _arg=None):
-        return
+def _task_finished_noop(_result: Any, pbar: ProgressBar):
+    pbar.update()
 
 
 class Executor(ABC):
@@ -45,11 +38,11 @@ class Executor(ABC):
         *,
         use_threads: bool,
         max_workers: int,
-        tqdm_kwargs: dict,
+        progress_kwargs: dict,
         worker_initializer: Callable | None = None,
-        task: Callable | None = None,
+        task: Callable[..., T] | None = None,
         task_arguments: Iterable | None = None,
-        task_finished: Callable | None = None,
+        task_finished: Callable[[T, ProgressBar], None] | None = None,
     ) -> None:
         """Set up parallel execution and progress reporting.
 
@@ -59,7 +52,7 @@ class Executor(ABC):
                 heavily, and parallelizing it with threads is not expected to be
                 performant).
             max_workers: The maximum number of workers that should be run.
-            tqdm_kwargs: Arguments to set up the progress bar.
+            progress_kwargs: Arguments to set up the progress bar.
             worker_initializer: Called when a worker is initialized, in the worker's
                 execution context. If the child workers are processes, it must be
                 possible to marshall/pickle the worker initializer.
@@ -77,7 +70,7 @@ class Executor(ABC):
         if not worker_initializer:
             worker_initializer = _task_noop
         if not task_finished:
-            task_finished = _task_noop
+            task_finished = _task_finished_noop
         if not task:
             task = _task_noop
 
@@ -85,7 +78,7 @@ class Executor(ABC):
             self._execute(
                 use_threads=use_threads,
                 max_workers=max_workers,
-                tqdm_kwargs=tqdm_kwargs,
+                progress_kwargs=progress_kwargs,
                 worker_initializer=worker_initializer,
                 task=task,
                 task_arguments=task_arguments,
@@ -98,7 +91,7 @@ class Executor(ABC):
         *,
         use_threads: bool,
         max_workers: int,
-        tqdm_kwargs: dict,
+        progress_kwargs: dict,
         worker_initializer: Callable,
         task: Callable,
         task_arguments: Iterable,
@@ -124,13 +117,13 @@ class SerialExecutor(Executor):
         *,
         use_threads: bool,
         max_workers: int,
-        tqdm_kwargs: dict,
+        progress_kwargs: dict,
         worker_initializer: Callable,
         task: Callable,
         task_arguments: Iterable,
         task_finished: Callable,
     ):  # pylint: disable=unused-argument
-        with self.pbar_class(**tqdm_kwargs) as pbar:
+        with self.pbar_class(**progress_kwargs) as pbar:
             for args in task_arguments:
-                result = task(args)
+                result = task(*args)
                 task_finished(result, pbar)

src/ocrmypdf/_defaults.py

@@ -0,0 +1,8 @@
+# SPDX-FileCopyrightText: 2024 James R. Barlow
+# SPDX-License-Identifier: MPL-2.0
+
+# Enforce English hegemony
+DEFAULT_LANGUAGE = 'eng'
+
+# Default rotation threshold
+DEFAULT_ROTATE_PAGES_THRESHOLD = 14.0

src/ocrmypdf/_exec/ghostscript.py

@@ -8,7 +8,7 @@ from __future__ import annotations
 import logging
 import os
 import re
-import sys
+from collections import deque
 from io import BytesIO
 from os import fspath
 from pathlib import Path
@@ -17,18 +17,10 @@ from subprocess import PIPE, CalledProcessError
 from packaging.version import Version
 from PIL import Image, UnidentifiedImageError
 
-from ocrmypdf.exceptions import SubprocessOutputError
+from ocrmypdf.exceptions import ColorConversionNeededError, SubprocessOutputError
 from ocrmypdf.helpers import Resolution
 from ocrmypdf.subprocess import get_version, run, run_polling_stderr
 
-# Remove this workaround when we require Pillow >= 10
-try:
-    Transpose = Image.Transpose  # type: ignore
-except AttributeError:
-    # Pillow 9 shim
-    Transpose = Image  # type: ignore
-
-
 COLOR_CONVERSION_STRATEGIES = frozenset(
     [
         'CMYK',
@@ -38,38 +30,44 @@ COLOR_CONVERSION_STRATEGIES = frozenset(
         'UseDeviceIndependentColor',
     ]
 )
+# Ghostscript executable - gswin32c is not supported
+GS = 'gswin64c' if os.name == 'nt' else 'gs'
+
 
 log = logging.getLogger(__name__)
 
 
 class DuplicateFilter(logging.Filter):
-    """Filter out duplicate log messages."""
+    """Filter out duplicate log messages.
 
-    def __init__(self, logger: logging.Logger):
-        self.last: logging.LogRecord | None = None
-        self.count = 0
+    A context window of default 5 messages is used to determine if a message is a
+    duplicate. This is because some Ghostscript messages are word wrapped.
+    """
+
+    def __init__(self, logger: logging.Logger, context_window=5):
+        self.window: deque[str] = deque([], maxlen=context_window)
         self.logger = logger
+        self.levelno = logging.DEBUG
+        self.count = 0
 
     def filter(self, record):
-        if self.last and record.msg == self.last.msg:
+        if record.msg in self.window:
             self.count += 1
+            self.levelno = record.levelno
             return False
         else:
             if self.count >= 1:
-                rep_msg = f"(previous message repeated {self.count} times)"
+                rep_msg = f"(suppressed {self.count} repeated lines)"
                 self.count = 0  # Avoid infinite recursion
-                self.logger.log(self.last.levelno, rep_msg)
-            self.last = record
+                self.logger.log(self.levelno, rep_msg)
+                self.window.clear()
+            self.window.append(record.msg)
             return True
 
 
 log.addFilter(DuplicateFilter(log))
 
 
-# Ghostscript executable - gswin32c is not supported
-GS = 'gswin64c' if os.name == 'nt' else 'gs'
-
-
 def version() -> Version:
     return Version(get_version(GS))
 
@@ -79,6 +77,20 @@ def _gs_error_reported(stream) -> bool:
     return bool(match)
 
 
+def _gs_devicen_reported(stream) -> bool:
+    """Did Ghostscript warn about a DeviceN with inappropriate alternate?
+
+    If so, we need the user to select a color conversion, or the resulting PDF will
+    not present correctly in some PDF viewers.
+    """
+    match = re.search(
+        r'DeviceN.*inappropriate alternate',
+        stream,
+        flags=re.IGNORECASE | re.MULTILINE,
+    )
+    return bool(match)
+
+
 def rasterize_pdf(
     input_file: os.PathLike,
     output_file: os.PathLike,
@@ -138,11 +150,11 @@ 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)
@@ -165,6 +177,17 @@ class GhostscriptFollower:
         self.progressbar_class = progressbar_class
         self.progressbar = None
 
+    def __enter__(self):
+        # We can't actually set up the progressbar here, because we don't know
+        # how many pages there are until the first __call__() happens. So we
+        # do it in __call__().
+        return self
+
+    def __exit__(self, exc_type, exc_value, traceback):
+        if self.progressbar:
+            return self.progressbar.__exit__(exc_type, exc_value, traceback)
+        return False
+
     def __call__(self, line):
         if not self.progressbar_class:
             return
@@ -175,7 +198,8 @@ class GhostscriptFollower:
                 self.progressbar = self.progressbar_class(
                     total=self.count, desc="PDF/A conversion", unit='page'
                 )
-                return
+                # Now that we know the count, we can set up the progressbar.
+                self.progressbar.__enter__()
         else:
             if self.re_page.match(line.strip()):
                 self.progressbar.update()
@@ -252,9 +276,11 @@ def generate_pdfa(
         ]
     )
     args_gs.extend(fspath(s) for s in pdf_pages)  # Stringify Path objs
-
     try:
-        with Path(output_file).open('wb') as output:
+        with (
+            Path(output_file).open('wb') as output,
+            GhostscriptFollower(progressbar_class) as pbar,
+        ):
             p = run_polling_stderr(
                 args_gs,
                 stdout=output,
@@ -263,7 +289,7 @@ def generate_pdfa(
                 text=True,
                 encoding='utf-8',
                 errors='replace',
-                callback=GhostscriptFollower(progressbar_class),
+                callback=pbar,
             )
     except CalledProcessError as e:
         # Ghostscript does not change return code when it fails to create
@@ -281,3 +307,5 @@ def generate_pdfa(
             # the **** pattern to split the stderr into parts.
             for part in stderr.split('****'):
                 log.error(part)
+        if _gs_devicen_reported(stderr):
+            raise ColorConversionNeededError()

src/ocrmypdf/_exec/jbig2enc.py

@@ -25,7 +25,7 @@ def available():
     return True
 
 
-def convert_group(*, cwd, infiles, out_prefix, threshold):
+def convert_group(cwd, infiles, out_prefix, threshold):
     args = [
         'jbig2',
         '-b',
@@ -43,21 +43,9 @@ def convert_group(*, cwd, infiles, out_prefix, threshold):
     return proc
 
 
-def convert_group_mp(args):
-    return convert_group(
-        cwd=args[0], infiles=args[1], out_prefix=args[2], threshold=args[3]
-    )
-
-
-def convert_single(*, cwd, infile, outfile, threshold):
+def convert_single(cwd, infile, outfile, threshold):
     args = ['jbig2', '--pdf', '-t', str(threshold), infile]
     with open(outfile, 'wb') as fstdout:
         proc = run(args, cwd=cwd, stdout=fstdout, stderr=PIPE)
     proc.check_returncode()
     return proc
-
-
-def convert_single_mp(args):
-    return convert_single(
-        cwd=args[0], infile=args[1], outfile=args[2], threshold=args[3]
-    )

src/ocrmypdf/_exec/pngquant.py

@@ -5,13 +5,10 @@
 
 from __future__ import annotations
 
-from contextlib import contextmanager
-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
@@ -29,21 +26,16 @@ def available():
     return True
 
 
-@contextmanager
-def input_as_png(input_file: Path):
-    if not input_file.name.endswith('.png'):
-        with Image.open(input_file) as im:
-            bio = BytesIO()
-            im.save(bio, format='png')
-            bio.seek(0)
-            yield bio
-    else:
-        with open(input_file, 'rb') as f:
-            yield f
-
-
 def quantize(input_file: Path, output_file: Path, quality_min: int, quality_max: int):
-    with input_as_png(input_file) as input_stream:
+    """Quantize a PNG image using pngquant.
+
+    Args:
+        input_file: Input PNG image
+        output_file: Output PNG image
+        quality_min: Minimum quality to use
+        quality_max: Maximum quality to use
+    """
+    with open(input_file, 'rb') as input_stream:
         args = [
             'pngquant',
             '--force',
@@ -58,7 +50,3 @@ def quantize(input_file: Path, output_file: Path, quality_min: int, quality_max:
     if result.returncode == 0:
         # input_file could be the same as output_file, so we defer the write
         output_file.write_bytes(result.stdout)
-
-
-def quantize_mp(args):
-    return quantize(*args)

src/ocrmypdf/_exec/tesseract.py

@@ -7,13 +7,13 @@ from __future__ import annotations
 
 import logging
 import re
+from contextlib import suppress
 from math import pi
 from os import fspath
 from pathlib import Path
 from subprocess import PIPE, STDOUT, CalledProcessError, TimeoutExpired
 
 from packaging.version import Version
-from PIL import Image
 
 from ocrmypdf.exceptions import (
     MissingDependencyError,
@@ -26,25 +26,6 @@ from ocrmypdf.subprocess import get_version, run
 log = logging.getLogger(__name__)
 
 
-HOCR_TEMPLATE = """<?xml version="1.0" encoding="UTF-8"?>
-<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN"
-    "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
-<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
- <head>
-  <title></title>
-<meta http-equiv="Content-Type" content="text/html;charset=utf-8" />
-  <meta name='ocr-system' content='tesseract 4.1.1' />
-  <meta name='ocr-capabilities'
-    content='ocr_page ocr_carea ocr_par ocr_line ocrx_word ocrp_wconf'/>
-</head>
-<body>
-  <div class='ocr_page' id='page_1'
-    title='image "_blank.png"; bbox 0 0 {0} {1}; ppageno 0'>
-  </div>
- </body>
-</html>
-"""
-
 TESSERACT_THRESHOLDING_METHODS: dict[str, int] = {
     'auto': 0,
     'otsu': 0,
@@ -239,7 +220,8 @@ def get_deskew(
 
 def tesseract_log_output(stream: bytes) -> None:
     tlog = TesseractLoggerAdapter(
-        log, extra=log.extra if hasattr(log, 'extra') else None  # type: ignore
+        log,
+        extra=log.extra if hasattr(log, 'extra') else None,  # type: ignore
     )
 
     if not stream:
@@ -284,14 +266,11 @@ def page_timedout(timeout: float) -> None:
 
 
 def _generate_null_hocr(output_hocr: Path, output_text: Path, image: Path) -> None:
-    """Produce a .hocr file that reports no text detected.
+    """Produce an empty .hocr file.
 
     Ensures page is the same size as the input image.
     """
-    with Image.open(image) as im:
-        w, h = im.size
-
-    output_hocr.write_text(HOCR_TEMPLATE.format(w, h), encoding='utf-8')
+    output_hocr.write_text('', encoding='utf-8')
     output_text.write_text('[skipped page]', encoding='utf-8')
 
 
@@ -350,7 +329,7 @@ def generate_hocr(
         tesseract_log_output(stdout)
         # The sidecar text file will get the suffix .txt; rename it to
         # whatever caller wants it named
-        if prefix.with_suffix('.txt').exists():
+        with suppress(FileNotFoundError):
             prefix.with_suffix('.txt').replace(output_text)
 
 
@@ -406,7 +385,7 @@ def generate_pdf(
     try:
         p = run(args_tesseract, stdout=PIPE, stderr=STDOUT, timeout=timeout, check=True)
         stdout = p.stdout
-        if prefix.with_suffix('.txt').exists():
+        with suppress(FileNotFoundError):
             prefix.with_suffix('.txt').replace(output_text)
     except TimeoutExpired:
         page_timedout(timeout)

src/ocrmypdf/_exec/unpaper.py

@@ -8,47 +8,26 @@ from __future__ import annotations
 import logging
 import os
 import shlex
-import sys
+from collections.abc import Iterator
 from contextlib import contextmanager
 from decimal import Decimal
 from pathlib import Path
 from subprocess import PIPE, STDOUT
-from typing import Iterator, Union
+from tempfile import TemporaryDirectory
 
 from packaging.version import Version
 from PIL import Image
 
-from ocrmypdf.exceptions import MissingDependencyError, SubprocessOutputError
+from ocrmypdf.exceptions import SubprocessOutputError
 from ocrmypdf.subprocess import get_version, run
 
 # unpaper documentation:
 # https://github.com/Flameeyes/unpaper/blob/main/doc/basic-concepts.md
 
 
-if sys.version_info >= (3, 10):
-    from tempfile import TemporaryDirectory
-else:
-    from tempfile import TemporaryDirectory as _TemporaryDirectory
-
-    class TemporaryDirectory(_TemporaryDirectory):
-        """Shim to consume ignore_cleanup_errors kwarg on Python 3.9 and older.
-
-        The argument is consumed without action. If users are getting errors related
-        to temporary file cleanup, they should upgrade to Python 3.10 which properly
-        cleans up temporary directories on Windows.
-
-        See: https://github.com/python/cpython/pull/24793
-        """
-
-        def __init__(self, ignore_cleanup_errors=False, **kwargs):
-            super().__init__(**kwargs)
-
-    del _TemporaryDirectory
-
-
 UNPAPER_IMAGE_PIXEL_LIMIT = 256 * 1024 * 1024
 
-DecFloat = Union[Decimal, float]
+DecFloat = Decimal | float
 
 log = logging.getLogger(__name__)
 
@@ -72,52 +51,20 @@ def version() -> Version:
     return Version(get_version('unpaper'))
 
 
-SUPPORTED_MODES = {'1', 'L', 'RGB'}
-
-
-def _convert_image(im: Image.Image) -> tuple[Image.Image, bool]:
-    im_modified = False
-
-    if im.mode not in SUPPORTED_MODES:
-        log.info("Converting image to other colorspace")
-        try:
-            if im.mode == 'P' and len(im.getcolors()) == 2:
-                im = im.convert(mode='1')
-            else:
-                im = im.convert(mode='RGB')
-        except OSError as e:
-            raise MissingDependencyError(
-                "Could not convert image with type " + im.mode
-            ) from e
-        else:
-            im_modified = True
-        if im.mode not in SUPPORTED_MODES:
-            raise MissingDependencyError(
-                "Failed to convert image to a supported format."
-            ) from None
-    return im, im_modified
-
-
 @contextmanager
 def _setup_unpaper_io(input_file: Path) -> Iterator[tuple[Path, Path, Path]]:
     with Image.open(input_file) as im:
         if im.width * im.height >= UNPAPER_IMAGE_PIXEL_LIMIT:
             raise UnpaperImageTooLargeError(w=im.width, h=im.height)
-        im, im_modified = _convert_image(im)
 
-        with TemporaryDirectory(ignore_cleanup_errors=True) as tmpdir:
-            tmppath = Path(tmpdir)
-            if im_modified or input_file.suffix != '.png':
-                input_png = tmppath / 'input.png'
-                im.save(input_png, format='PNG')
-            else:
-                # No changes, PNG input, just use the file we already have
-                input_png = input_file
-
-            # unpaper can write .png too, but it seems to write them slowly
-            # adds a few seconds to test suite - so just use pnm
-            output_pnm = tmppath / 'output.pnm'
-            yield input_png, output_pnm, tmppath
+    with TemporaryDirectory(ignore_cleanup_errors=True) as tmpdir:
+        tmppath = Path(tmpdir)
+        # No changes, PNG input, just use the file we already have
+        input_png = input_file
+        # unpaper can write .png too, but it seems to write them slowly
+        # adds a few seconds to test suite - so just use pnm
+        output_pnm = tmppath / 'output.pnm'
+        yield input_png, output_pnm, tmppath
 
 
 def run_unpaper(

src/ocrmypdf/_graft.py

@@ -7,32 +7,46 @@ from __future__ import annotations
 
 import logging
 from contextlib import suppress
+from enum import Enum
 from pathlib import Path
 
 from pikepdf import (
     Dictionary,
+    Matrix,
     Name,
-    Object,
     Operator,
+    Page,
     Pdf,
     PdfError,
-    PdfMatrix,
     Stream,
     parse_content_stream,
     unparse_content_stream,
 )
 
+from ocrmypdf._jobcontext import PdfContext
+
+
+class RenderMode(Enum):
+    ON_TOP = 0
+    UNDERNEATH = 1
+
+
 log = logging.getLogger(__name__)
 MAX_REPLACE_PAGES = 100
 
 
-def _ensure_dictionary(obj, name):
+def _ensure_dictionary(obj: Dictionary | Stream, name: Name):
     if name not in obj:
         obj[name] = Dictionary({})
     return obj[name]
 
 
-def _update_resources(*, obj, font, font_key, procset):
+def _update_resources(
+    *,
+    obj: Dictionary | Stream,
+    font: Dictionary | None,
+    font_key: Name | None,
+):
     """Update this obj's fonts with a reference to the Glyphless font.
 
     obj can be a page or Form XObject.
@@ -42,13 +56,8 @@ def _update_resources(*, obj, font, font_key, procset):
     if font_key is not None and font_key not in fonts:
         fonts[font_key] = font
 
-    # Reassign /ProcSet to one that just lists everything - ProcSet is
-    # obsolete and doesn't matter but recommended for old viewer support
-    if procset:
-        resources['/ProcSet'] = procset
 
-
-def strip_invisible_text(pdf, page):
+def strip_invisible_text(pdf: Pdf, page: Page):
     stream = []
     in_text_obj = False
     render_mode = 0
@@ -79,22 +88,20 @@ def strip_invisible_text(pdf, page):
 class OcrGrafter:
     """Manages grafting text-only PDFs onto regular PDFs."""
 
-    def __init__(self, context):
+    def __init__(self, context: PdfContext):
         self.context = context
         self.path_base = context.origin
 
         self.pdf_base = Pdf.open(self.path_base)
-        self.font, self.font_key = None, None
+        self.font: Dictionary | None = None
+        self.font_key: Name | None = None
 
         self.pdfinfo = context.pdfinfo
         self.output_file = context.get_path('graft_layers.pdf')
 
-        self.procset = self.pdf_base.make_indirect(
-            Object.parse(b'[ /PDF /Text /ImageB /ImageC /ImageI ]')
-        )
-
         self.emplacements = 1
         self.interim_count = 0
+        self.render_mode = RenderMode.UNDERNEATH
 
     def graft_page(
         self,
@@ -119,7 +126,9 @@ class OcrGrafter:
                 foreign_image_page = pdf_image.pages[0]
                 self.pdf_base.pages.append(foreign_image_page)
                 local_image_page = self.pdf_base.pages[-1]
-                self.pdf_base.pages[pageno].emplace(local_image_page)
+                self.pdf_base.pages[pageno].emplace(
+                    local_image_page, retain=(Name.Parent,)
+                )
                 del self.pdf_base.pages[-1]
             emplaced_page = True
 
@@ -135,6 +144,8 @@ class OcrGrafter:
         )
 
         if textpdf and self.font:
+            if self.font_key is None:
+                raise ValueError("Font key is not set")
             # Graft the text layer onto this page, whether new or old, possibly
             # rotating the text layer by the amount is misaligned.
             strip_old = self.context.options.redo_ocr
@@ -144,7 +155,6 @@ class OcrGrafter:
                 font=self.font,
                 font_key=self.font_key,
                 text_rotation=text_misaligned,
-                procset=self.procset,
                 strip_old_text=strip_old,
             )
 
@@ -159,7 +169,7 @@ class OcrGrafter:
         if self.emplacements % MAX_REPLACE_PAGES == 0:
             self.save_and_reload()
 
-    def save_and_reload(self):
+    def save_and_reload(self) -> None:
         """Save and reload the Pdf.
 
         This will keep a lid on our memory usage for very large files. Attach
@@ -167,9 +177,7 @@ class OcrGrafter:
         back.
         """
         page0 = self.pdf_base.pages[0]
-        _update_resources(
-            obj=page0, font=self.font, font_key=self.font_key, procset=self.procset
-        )
+        _update_resources(obj=page0.obj, font=self.font, font_key=self.font_key)
 
         # We cannot read and write the same file, that will corrupt it
         # but we don't to keep more copies than we need to. Delete intermediates.
@@ -188,7 +196,6 @@ class OcrGrafter:
         self.pdf_base.close()
 
         self.pdf_base = Pdf.open(next_file)
-        self.procset = self.pdf_base.pages[0].Resources.ProcSet
         self.font, self.font_key = None, None  # Ensure we reacquire this information
         self.interim_count += 1
 
@@ -197,24 +204,32 @@ class OcrGrafter:
         self.pdf_base.close()
         return self.output_file
 
-    def _find_font(self, text):
+    def _find_font(self, text: Path) -> tuple[Dictionary | None, Name | None]:
         """Copy a font from the filename text into pdf_base."""
         font, font_key = None, None
         possible_font_names = ('/f-0-0', '/F1')
         try:
             with Pdf.open(text) as pdf_text:
                 try:
-                    pdf_text_fonts = pdf_text.pages[0].Resources.get('/Font', {})
+                    pdf_text_fonts = pdf_text.pages[0].Resources.get(
+                        Name.Font, Dictionary()
+                    )
                 except (AttributeError, IndexError, KeyError):
                     return None, None
+                if not isinstance(pdf_text_fonts, Dictionary):
+                    log.warning("Page fonts are not stored in a dictionary")
+                    return None, None
                 pdf_text_font = None
                 for f in possible_font_names:
                     pdf_text_font = pdf_text_fonts.get(f, None)
                     if pdf_text_font is not None:
-                        font_key = f
+                        font_key = Name(f)
                         break
                 if pdf_text_font:
                     font = self.pdf_base.copy_foreign(pdf_text_font)
+                if not isinstance(font, Dictionary):
+                    log.warning("Font is not a dictionary")
+                    font, font_key = None, None
                 return font, font_key
         except (FileNotFoundError, PdfError):
             # PdfError occurs if a 0-length file is written e.g. due to OCR timeout
@@ -225,9 +240,8 @@ class OcrGrafter:
         *,
         page_num: int,
         textpdf: Path,
-        font: Object,
-        font_key: Object,
-        procset: Object,
+        font: Dictionary,
+        font_key: Name,
         text_rotation: int,
         strip_old_text: bool,
     ):
@@ -248,19 +262,19 @@ class OcrGrafter:
             # content may have a rotation applied. Wrap the text stream with a rotation
             # so it will be oriented the same way as the rest of the page content.
             # (Previous versions OCRmyPDF rotated the content layer to match the text.)
-            mediabox = [float(pdf_text.pages[0].MediaBox[v]) for v in range(4)]
+            mediabox = pdf_text.pages[0].mediabox
             wt, ht = mediabox[2] - mediabox[0], mediabox[3] - mediabox[1]
 
-            mediabox = [float(base_page.MediaBox[v]) for v in range(4)]
+            mediabox = base_page.mediabox
             wp, hp = mediabox[2] - mediabox[0], mediabox[3] - mediabox[1]
 
-            translate = PdfMatrix().translated(-wt / 2, -ht / 2)
-            untranslate = PdfMatrix().translated(wp / 2, hp / 2)
-            corner = PdfMatrix().translated(mediabox[0], mediabox[1])
+            translate = Matrix().translated(-wt / 2, -ht / 2)
+            untranslate = Matrix().translated(wp / 2, hp / 2)
+            corner = Matrix().translated(mediabox[0], mediabox[1])
             # -rotation because the input is a clockwise angle and this formula
             # uses CCW
             text_rotation = -text_rotation % 360
-            rotate = PdfMatrix().rotated(text_rotation)
+            rotate = Matrix().rotated(text_rotation)
 
             # Because of rounding of DPI, we might get a text layer that is not
             # identically sized to the target page. Scale to adjust. Normally this
@@ -271,14 +285,15 @@ class OcrGrafter:
             scale_y = hp / ht
 
             # log.debug('%r', scale_x, scale_y)
-            scale = PdfMatrix().scaled(scale_x, scale_y)
+            scale = Matrix().scaled(scale_x, scale_y)
 
             # Translate the text so it is centered at (0, 0), rotate it there, adjust
             # for a size different between initial and text PDF, then untranslate, and
-            # finally move the lower left corner to match the mediabox
+            # finally move the lower left corner to match the mediabox.
             ctm = translate @ rotate @ scale @ untranslate @ corner
+            log.debug("Grafting with ctm %r", ctm)
 
-            base_resources = _ensure_dictionary(base_page, Name.Resources)
+            base_resources = _ensure_dictionary(base_page.obj, Name.Resources)
             base_xobjs = _ensure_dictionary(base_resources, Name.XObject)
             text_xobj_name = Name.random(prefix="OCR-")
             xobj = self.pdf_base.make_stream(pdf_text_contents)
@@ -287,9 +302,7 @@ class OcrGrafter:
             xobj.Subtype = Name.Form
             xobj.FormType = 1
             xobj.BBox = mediabox
-            _update_resources(
-                obj=xobj, font=font, font_key=font_key, procset=[Name.PDF]
-            )
+            _update_resources(obj=xobj, font=font, font_key=font_key)
 
             pdf_draw_xobj = (
                 (b'q %s cm\n' % ctm.encode()) + (b'%s Do\n' % text_xobj_name) + b'\nQ\n'
@@ -298,9 +311,16 @@ class OcrGrafter:
 
             if strip_old_text:
                 strip_invisible_text(self.pdf_base, base_page)
-
-            base_page.contents_add(new_text_layer, prepend=True)
-
-            _update_resources(
-                obj=base_page, font=font, font_key=font_key, procset=procset
+            base_page.contents_coalesce()
+            if self.render_mode == RenderMode.ON_TOP:
+                # Add q/Q to ensure content we append is drawn correctly
+                # Strictly speaking this needs to trace the whole q/Q stack in case
+                # stack is not balanced.
+                original = base_page.Contents.read_bytes()
+                base_page.Contents.write(b'q\n' + original + b'\nQ\n')
+            base_page.contents_add(
+                new_text_layer, prepend=self.render_mode == RenderMode.UNDERNEATH
             )
+            base_page.contents_coalesce()
+
+            _update_resources(obj=base_page.obj, font=font, font_key=font_key)

src/ocrmypdf/_jobcontext.py

@@ -6,12 +6,10 @@
 from __future__ import annotations
 
 import os
-import shutil
-import sys
 from argparse import Namespace
+from collections.abc import Iterator
 from copy import copy
 from pathlib import Path
-from typing import Iterator
 
 from pluggy import PluginManager
 
@@ -55,6 +53,12 @@ class PdfContext:
         for n in range(npages):
             yield PageContext(self, n)
 
+    def get_page_context_args(self) -> Iterator[tuple[PageContext]]:
+        """Get all ``PageContext`` for this PDF packaged in tuple for args-splatting."""
+        npages = len(self.pdfinfo)
+        for n in range(npages):
+            yield (PageContext(self, n),)
+
 
 class PageContext:
     """Holds our context for a page.
@@ -89,15 +93,8 @@ class PageContext:
         state = self.__dict__.copy()
 
         state['options'] = copy(self.options)
-        if not isinstance(state['options'].input_file, (str, bytes, os.PathLike)):
+        if not isinstance(state['options'].input_file, str | bytes | os.PathLike):
             state['options'].input_file = 'stream'
-        if not isinstance(state['options'].output_file, (str, bytes, os.PathLike)):
+        if not isinstance(state['options'].output_file, str | bytes | os.PathLike):
             state['options'].output_file = 'stream'
         return state
-
-
-def cleanup_working_files(work_folder: Path, options: Namespace):
-    if options.keep_temporary_files:
-        print(f"Temporary working files retained at:\n{work_folder}", file=sys.stderr)
-    else:
-        shutil.rmtree(work_folder, ignore_errors=True)

src/ocrmypdf/_logging.py

@@ -9,15 +9,6 @@ import logging
 
 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):
@@ -37,56 +28,3 @@ class RichLoggingHandler(RichHandler):
         super().__init__(
             console=console, show_level=False, show_time=False, markup=True, **kwargs
         )
-
-
-class RichTqdmProgressAdapter:
-    """Adapt tqdm API to rich progress bar."""
-
-    def __init__(
-        self,
-        *,
-        console: Console,
-        desc: str,
-        total: float | None = None,
-        unit: str | None = None,
-        unit_scale: float | None = 1.0,
-        disable: bool = False,
-        **kwargs,
-    ):
-        self.progress = Progress(
-            TextColumn(
-                "[progress.description]{task.description}",
-                table_column=Column(min_width=20),
-            ),
-            BarColumn(),
-            TaskProgressColumn(),
-            MofNCompleteColumn(),
-            TimeRemainingColumn(),
-            console=console,
-            auto_refresh=True,
-            redirect_stderr=True,
-            redirect_stdout=False,
-            disable=disable,
-            **kwargs,
-        )
-        self.unit_scale = unit_scale
-        self.progress_bar = self.progress.add_task(
-            desc,
-            total=total * self.unit_scale
-            if total is not None and self.unit_scale is not None
-            else None,
-            unit=unit,
-        )
-
-    def __enter__(self):
-        self.progress.start()
-        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/_metadata.py

@@ -0,0 +1,214 @@
+# SPDX-FileCopyrightText: 2023 James R. Barlow
+# SPDX-License-Identifier: MPL-2.0
+
+"""OCRmyPDF page processing pipeline functions."""
+
+from __future__ import annotations
+
+import logging
+import os
+from datetime import datetime, timezone
+from pathlib import Path
+from typing import Any
+
+from pikepdf import Dictionary, Name, Pdf
+from pikepdf import __version__ as PIKEPDF_VERSION
+from pikepdf.models.metadata import PdfMetadata, encode_pdf_date
+
+from ocrmypdf._jobcontext import PdfContext
+from ocrmypdf._version import PROGRAM_NAME
+from ocrmypdf._version import __version__ as OCRMYPF_VERSION
+from ocrmypdf.languages import iso_639_2_from_3
+
+log = logging.getLogger(__name__)
+
+
+def get_docinfo(base_pdf: Pdf, context: PdfContext) -> dict[str, str]:
+    """Read the document info and store it in a dictionary."""
+    options = context.options
+
+    def from_document_info(key):
+        try:
+            s = base_pdf.docinfo[key]
+            return str(s)
+        except (KeyError, TypeError):
+            return ''
+
+    pdfmark = {
+        k: from_document_info(k)
+        for k in ('/Title', '/Author', '/Keywords', '/Subject', '/CreationDate')
+    }
+    if options.title:
+        pdfmark['/Title'] = options.title
+    if options.author:
+        pdfmark['/Author'] = options.author
+    if options.keywords:
+        pdfmark['/Keywords'] = options.keywords
+    if options.subject:
+        pdfmark['/Subject'] = options.subject
+
+    creator_tag = context.plugin_manager.hook.get_ocr_engine().creator_tag(options)
+
+    pdfmark['/Creator'] = f'{PROGRAM_NAME} {OCRMYPF_VERSION} / {creator_tag}'
+    pdfmark['/Producer'] = f'pikepdf {PIKEPDF_VERSION}'
+    pdfmark['/ModDate'] = encode_pdf_date(datetime.now(timezone.utc))
+    return pdfmark
+
+
+def report_on_metadata(options, missing):
+    if not missing:
+        return
+    if options.output_type.startswith('pdfa'):
+        log.warning(
+            "Some input metadata could not be copied because it is not "
+            "permitted in PDF/A. You may wish to examine the output "
+            "PDF's XMP metadata."
+        )
+        log.debug("The following metadata fields were not copied: %r", missing)
+    else:
+        log.error(
+            "Some input metadata could not be copied."
+            "You may wish to examine the output PDF's XMP metadata."
+        )
+        log.info("The following metadata fields were not copied: %r", missing)
+
+
+def repair_docinfo_nuls(pdf):
+    """If the DocumentInfo block contains NUL characters, remove them.
+
+    If the DocumentInfo block is malformed, log an error and continue.
+    """
+    modified = False
+    try:
+        if not isinstance(pdf.docinfo, Dictionary):
+            raise TypeError("DocumentInfo is not a dictionary")
+        for k, v in pdf.docinfo.items():
+            if isinstance(v, str) and b'\x00' in bytes(v):
+                pdf.docinfo[k] = bytes(v).replace(b'\x00', b'')
+                modified = True
+    except TypeError:
+        # TypeError can also be raised if dictionary items are unexpected types
+        log.error("File contains a malformed DocumentInfo block - continuing anyway.")
+    return modified
+
+
+def should_linearize(working_file: Path, context: PdfContext) -> bool:
+    """Determine whether the PDF should be linearized.
+
+    For smaller files, linearization is not worth the effort.
+    """
+    filesize = os.stat(working_file).st_size
+    if filesize > (context.options.fast_web_view * 1_000_000):
+        return True
+    return False
+
+
+def _fix_metadata(meta_original: PdfMetadata, meta_pdf: PdfMetadata):
+    # If xmp:CreateDate is missing, set it to the modify date to
+    # ensure consistency with Ghostscript.
+    if 'xmp:CreateDate' not in meta_pdf:
+        meta_pdf['xmp:CreateDate'] = meta_pdf.get('xmp:ModifyDate', '')
+    if meta_pdf.get('dc:title') == 'Untitled':
+        # Ghostscript likes to set title to Untitled if omitted from input.
+        # Reverse this, because PDF/A TechNote 0003:Metadata in PDF/A-1
+        # and the XMP Spec do not make this recommendation.
+        if 'dc:title' not in meta_original:
+            del meta_pdf['dc:title']
+
+
+def _unset_empty_metadata(meta: PdfMetadata, options):
+    """Unset metadata fields that were explicitly set to empty strings.
+
+    If the user explicitly specified an empty string for any of the
+    following, they should be unset and not reported as missing in
+    the output pdf. Note that some metadata fields use differing names
+    between PDF/A and PDF.
+    """
+    if options.title == '' and 'dc:title' in meta:
+        del meta['dc:title']  # PDF/A and PDF
+    if options.author == '':
+        if 'dc:creator' in meta:
+            del meta['dc:creator']  # PDF/A (Not xmp:CreatorTool)
+        if 'pdf:Author' in meta:
+            del meta['pdf:Author']  # PDF
+    if options.subject == '':
+        if 'dc:description' in meta:
+            del meta['dc:description']  # PDF/A
+        if 'dc:subject' in meta:
+            del meta['dc:subject']  # PDF
+    if options.keywords == '' and 'pdf:Keywords' in meta:
+        del meta['pdf:Keywords']  # PDF/A and PDF
+
+
+def _set_language(pdf: Pdf, languages: list[str]):
+    """Set the language of the PDF."""
+    if Name.Lang in pdf.Root or not languages:
+        return  # Already set or can't change
+    primary_language_iso639_3 = languages[0]
+    if not primary_language_iso639_3:
+        return
+    iso639_2 = iso_639_2_from_3(primary_language_iso639_3)
+    if not iso639_2:
+        return
+    pdf.Root.Lang = iso639_2
+
+
+class MetadataProgress:
+    def __init__(self, progressbar_class, enable: bool = True):
+        self.progressbar_class = progressbar_class
+        self.progressbar = self.progressbar_class(
+            total=100, desc="Linearizing", unit='%', disable=not enable
+        )
+
+    def __enter__(self):
+        self.progressbar.__enter__()
+        return self
+
+    def __exit__(self, exc_type, exc_value, traceback):
+        return self.progressbar.__exit__(exc_type, exc_value, traceback)
+
+    def __call__(self, percent: int):
+        if not self.progressbar_class:
+            return
+        self.progressbar.update(completed=percent)
+
+
+def metadata_fixup(
+    working_file: Path, context: PdfContext, pdf_save_settings: dict[str, Any]
+) -> Path:
+    """Fix certain metadata fields whether PDF or PDF/A.
+
+    Override some of Ghostscript's metadata choices.
+
+    Also report on metadata in the input file that was not retained during
+    conversion.
+    """
+    output_file = context.get_path('metafix.pdf')
+    options = context.options
+
+    pbar_class = context.plugin_manager.hook.get_progressbar_class()
+    with (
+        Pdf.open(context.origin) as original,
+        Pdf.open(working_file) as pdf,
+        MetadataProgress(pbar_class, options.progress_bar) as pbar,
+    ):
+        docinfo = get_docinfo(original, context)
+        with (
+            original.open_metadata(
+                set_pikepdf_as_editor=False, update_docinfo=False, strict=False
+            ) as meta_original,
+            pdf.open_metadata() as meta_pdf,
+        ):
+            meta_pdf.load_from_docinfo(
+                docinfo, delete_missing=False, raise_failure=False
+            )
+            _fix_metadata(meta_original, meta_pdf)
+            _unset_empty_metadata(meta_original, options)
+            _unset_empty_metadata(meta_pdf, options)
+            meta_missing = set(meta_original.keys()) - set(meta_pdf.keys())
+            report_on_metadata(options, meta_missing)
+
+        _set_language(pdf, options.languages)
+        pdf.save(output_file, progress=pbar, **pdf_save_settings)
+
+    return output_file

src/ocrmypdf/_pipeline.py

@@ -10,48 +10,54 @@ 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 io import BytesIO
 from pathlib import Path
 from shutil import copyfileobj
-from typing import Any, BinaryIO, Iterable, Iterator, Sequence, cast
+from typing import Any, BinaryIO, TypeVar, cast
 
 import img2pdf
 import pikepdf
-from pikepdf.models.metadata import encode_pdf_date
 from PIL import Image, ImageColor, ImageDraw
 
 from ocrmypdf._concurrent import Executor
 from ocrmypdf._exec import unpaper
 from ocrmypdf._jobcontext import PageContext, PdfContext
-from ocrmypdf._version import PROGRAM_NAME
-from ocrmypdf._version import __version__ as VERSION
+from ocrmypdf._metadata import repair_docinfo_nuls
 from ocrmypdf.exceptions import (
     DigitalSignatureError,
     DpiError,
     EncryptedPdfError,
     InputFileError,
     PriorOcrFoundError,
+    TaggedPDFError,
     UnsupportedImageFormatError,
 )
 from ocrmypdf.helpers import IMG2PDF_KWARGS, Resolution, safe_symlink
-from ocrmypdf.hocrtransform import HocrTransform
+from ocrmypdf.hocrtransform import DebugRenderOptions, HocrTransform
+from ocrmypdf.hocrtransform._font import Courier
 from ocrmypdf.pdfa import generate_pdfa_ps
 from ocrmypdf.pdfinfo import Colorspace, Encoding, PageInfo, PdfInfo
 from ocrmypdf.pluginspec import OrientationConfidence
 
-# Remove this workaround when we require Pillow >= 10
 try:
-    BICUBIC = Image.Resampling.BICUBIC  # type: ignore
-except AttributeError:  # pragma: no cover
-    # Pillow 9 shim
-    BICUBIC = Image.BICUBIC  # type: ignore
+    from pi_heif import register_heif_opener
+except ImportError:
 
+    def register_heif_opener():
+        pass
+
+
+T = TypeVar("T")
 log = logging.getLogger(__name__)
 
 VECTOR_PAGE_DPI = 400
 
 
+register_heif_opener()
+
+
 def triage_image_file(input_file: Path, output_file: Path, options) -> None:
     """Triage the input image file.
 
@@ -136,7 +142,7 @@ def _pdf_guess_version(input_file: Path, search_window=1024) -> str:
     """
     with open(input_file, 'rb') as f:
         signature = f.read(search_window)
-    m = re.search(br'%PDF-(\d\.\d)', signature)
+    m = re.search(rb'%PDF-(\d\.\d)', signature)
     if m:
         return m.group(1).decode('ascii')
     return ''
@@ -145,6 +151,7 @@ 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:
@@ -171,14 +178,17 @@ def get_pdfinfo(
     detailed_analysis: bool = False,
     progbar: bool = False,
     max_workers: int | None = None,
+    use_threads: bool = True,
     check_pages=None,
 ) -> PdfInfo:
+    """Get the PDF info."""
     try:
         return PdfInfo(
             input_file,
             detailed_analysis=detailed_analysis,
             progbar=progbar,
             max_workers=max_workers,
+            use_threads=use_threads,
             check_pages=check_pages,
             executor=executor,
         )
@@ -189,6 +199,7 @@ def get_pdfinfo(
 
 
 def validate_pdfinfo_options(context: PdfContext) -> None:
+    """Validate the PDF info options."""
     pdfinfo = context.pdfinfo
     options = context.options
 
@@ -220,6 +231,16 @@ 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)
 
 
@@ -434,6 +455,7 @@ def get_orientation_correction(preview: Path, page_context: PageContext) -> int:
 
 
 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:
@@ -453,7 +475,7 @@ def calculate_raster_dpi(page_context: PageContext):
     page_dpi = get_page_square_dpi(page_context, image_dpi)
     if dpi_profile and dpi_profile.average_to_max_dpi_ratio < 0.8:
         log.warning(
-            "Weight average image DPI is %0.1f, max DPI is %0.1f. "
+            "Weighted average image DPI is %0.1f, max DPI is %0.1f. "
             "The discrepancy may indicate a high detail region on this page, "
             "but could also indicate a problem with the input PDF file. "
             "Page image will be rendered at %0.1f DPI.",
@@ -509,6 +531,7 @@ def rasterize(
                 device_idx = at_least('png16m')
 
     if pageinfo.has_vector:
+        log.debug("Page has vector content, using png16m")
         device_idx = at_least('png16m')
 
     device = colorspaces[device_idx]
@@ -532,6 +555,7 @@ 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')
@@ -562,7 +586,7 @@ 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)
@@ -571,6 +595,7 @@ 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, calculate_image_dpi(page_context))
     return unpaper.clean(
@@ -631,6 +656,7 @@ 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
@@ -642,7 +668,7 @@ def ocr_engine_hocr(input_file: Path, page_context: PageContext) -> tuple[Path,
         output_text=hocr_text_out,
         options=options,
     )
-    return (hocr_out, hocr_text_out)
+    return hocr_out, hocr_text_out
 
 
 def should_visible_page_image_use_jpg(pageinfo: PageInfo) -> bool:
@@ -662,6 +688,10 @@ 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
@@ -683,6 +713,7 @@ 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
@@ -694,19 +725,29 @@ def create_pdf_page_from_image(
     pageinfo = page_context.pageinfo
     pagesize = 72.0 * float(pageinfo.width_inches), 72.0 * float(pageinfo.height_inches)
     effective_rotation = (pageinfo.rotation - orientation_correction) % 360
-    if effective_rotation % 180 == 90:
+    swap_axis = effective_rotation % 180 == 90
+    if swap_axis:
         pagesize = pagesize[1], pagesize[0]
 
-    # This create a single page PDF
-    with open(image, 'rb') as imfile, open(output_file, 'wb') as pdf:
+    # Create a new single page PDF to hold
+    bio = BytesIO()
+    with open(image, 'rb') as imfile:
         log.debug('convert')
 
         layout_fun = img2pdf.get_layout_fun(pagesize)
         img2pdf.convert(
-            imfile, layout_fun=layout_fun, outputstream=pdf, **IMG2PDF_KWARGS
+            imfile,
+            layout_fun=layout_fun,
+            outputstream=bio,
+            engine=img2pdf.Engine.pikepdf,
+            rotation=img2pdf.Rotation.ifvalid,
         )
         log.debug('convert done')
 
+    # img2pdf does not generate boxes correctly, so we fix them
+    bio.seek(0)
+    fix_pagepdf_boxes(bio, output_file, page_context, swap_axis=swap_axis)
+
     output_file = page_context.plugin_manager.hook.filter_pdf_page(
         page=page_context, image_filename=image, output_pdf=output_file
     )
@@ -714,18 +755,36 @@ 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, calculate_image_dpi(page_context))
-    debug_mode = options.pdf_renderer == 'hocrdebug'
+    if hocr.stat().st_size == 0:
+        # If hOCR file is empty (skipped page marker), create an empty PDF file
+        output_file.touch()
+        return output_file
 
-    hocrtransform = HocrTransform(hocr_filename=hocr, dpi=dpi.x)  # square
-    hocrtransform.to_pdf(
+    dpi = get_page_square_dpi(page_context, calculate_image_dpi(page_context))
+    debug_kwargs = {}
+    if options.pdf_renderer == 'hocrdebug':
+        debug_kwargs = dict(
+            debug_render_options=DebugRenderOptions(
+                render_baseline=True,
+                render_triangle=True,
+                render_line_bbox=False,
+                render_word_bbox=True,
+                render_paragraph_bbox=False,
+                render_space_bbox=False,
+            ),
+            font=Courier(),
+        )
+    HocrTransform(
+        hocr_filename=hocr,
+        dpi=dpi.to_scalar(),
+        **debug_kwargs,  # square
+    ).to_pdf(
         out_filename=output_file,
         image_filename=None,
-        show_bounding_boxes=False if not debug_mode else True,
-        invisible_text=True if not debug_mode else False,
-        interword_spaces=True,
+        invisible_text=True if not debug_kwargs else False,
     )
     return output_file
 
@@ -733,6 +792,7 @@ 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
@@ -744,38 +804,57 @@ def ocr_engine_textonly_pdf(
         output_text=output_text,
         options=options,
     )
-    return (output_pdf, output_text)
+    return output_pdf, output_text
 
 
-def get_docinfo(base_pdf: pikepdf.Pdf, context: PdfContext) -> dict[str, str]:
-    options = context.options
+def _offset_rect(rect: tuple[float, float, float, float], offset: tuple[float, float]):
+    """Offset a rectangle by a given amount."""
+    return (
+        rect[0] + offset[0],
+        rect[1] + offset[1],
+        rect[2] + offset[0],
+        rect[3] + offset[1],
+    )
 
-    def from_document_info(key):
-        try:
-            s = base_pdf.docinfo[key]
-            return str(s)
-        except (KeyError, TypeError):
-            return ''
 
-    pdfmark = {
-        k: from_document_info(k)
-        for k in ('/Title', '/Author', '/Keywords', '/Subject', '/CreationDate')
-    }
-    if options.title:
-        pdfmark['/Title'] = options.title
-    if options.author:
-        pdfmark['/Author'] = options.author
-    if options.keywords:
-        pdfmark['/Keywords'] = options.keywords
-    if options.subject:
-        pdfmark['/Subject'] = options.subject
+def fix_pagepdf_boxes(
+    infile: Path | BinaryIO,
+    out_file: Path,
+    page_context: PageContext,
+    swap_axis: bool = False,
+) -> Path:
+    """Fix the bounding boxes in a single page PDF.
 
-    creator_tag = context.plugin_manager.hook.get_ocr_engine().creator_tag(options)
+    The single page PDF is created with a normal MediaBox with its lower left corner
+    at (0, 0). infile is the single page PDF. page_context.mediabox has the original
+    file's mediabox, which may have a different origin. We needto adjust the other
+    boxes in the single page PDF to match the effect they had on the original page.
 
-    pdfmark['/Creator'] = f'{PROGRAM_NAME} {VERSION} / {creator_tag}'
-    pdfmark['/Producer'] = f'pikepdf {pikepdf.__version__}'
-    pdfmark['/ModDate'] = encode_pdf_date(datetime.now(timezone.utc))
-    return pdfmark
+    When correcting page rotation, we create a single page PDF that is correctly
+    rotated instead of an incorrectly rotated and then setting page.Rotate on it.
+    If rotation is either 90 or 270 degrees, then this function can be called
+    with swap_axis to swap the X and Y coordinates of all the boxes.
+
+    We are not concerned with solving degenerate cases where the boxes overlap or
+    or express invalid rectangles. We merely pass the boxes, producing a
+    transformation equivalent to the change made by constructing a new page image.
+    """
+    with pikepdf.open(infile) as pdf:
+        for page in pdf.pages:
+            # page.BleedBox = page_context.pageinfo.bleedbox
+            # page.ArtBox = page_context.pageinfo.artbox
+            mediabox = page_context.pageinfo.mediabox
+            offset = mediabox[0], mediabox[1]
+            cropbox = _offset_rect(page_context.pageinfo.cropbox, offset)
+            trimbox = _offset_rect(page_context.pageinfo.trimbox, offset)
+
+            if swap_axis:
+                cropbox = cropbox[1], cropbox[0], cropbox[3], cropbox[2]
+                trimbox = trimbox[1], trimbox[0], trimbox[3], trimbox[2]
+            page.CropBox = cropbox
+            page.TrimBox = trimbox
+        pdf.save(out_file)
+    return pdf
 
 
 def generate_postscript_stub(context: PdfContext) -> Path:
@@ -793,6 +872,14 @@ def generate_postscript_stub(context: PdfContext) -> Path:
 
 
 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')
@@ -804,7 +891,7 @@ def convert_to_pdfa(input_pdf: Path, input_ps_stub: Path, context: PdfContext) -
     # pikepdf can deal with this, but we make the world a better place by
     # stamping them out as soon as possible.
     with pikepdf.open(input_pdf) as pdf_file:
-        if _repair_docinfo_nuls(pdf_file):
+        if repair_docinfo_nuls(pdf_file):
             pdf_file.save(fix_docinfo_file)
         else:
             safe_symlink(input_pdf, fix_docinfo_file)
@@ -827,26 +914,11 @@ 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
@@ -854,6 +926,11 @@ 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.
@@ -871,83 +948,6 @@ def get_pdf_save_settings(output_type: str) -> dict[str, Any]:
         )
 
 
-def metadata_fixup(working_file: Path, context: PdfContext) -> Path:
-    output_file = context.get_path('metafix.pdf')
-    options = context.options
-
-    def report_on_metadata(missing):
-        if not missing:
-            return
-        if options.output_type.startswith('pdfa'):
-            log.warning(
-                "Some input metadata could not be copied because it is not "
-                "permitted in PDF/A. You may wish to examine the output "
-                "PDF's XMP metadata."
-            )
-            log.debug("The following metadata fields were not copied: %r", missing)
-        else:
-            log.error(
-                "Some input metadata could not be copied."
-                "You may wish to examine the output PDF's XMP metadata."
-            )
-            log.info("The following metadata fields were not copied: %r", missing)
-
-    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:
-            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', '')
-
-            with original.open_metadata(
-                set_pikepdf_as_editor=False, update_docinfo=False, strict=False
-            ) as meta_original:
-                if meta_pdf.get('dc:title') == 'Untitled':
-                    # Ghostscript likes to set title to Untitled if omitted from input.
-                    # Reverse this, because PDF/A TechNote 0003:Metadata in PDF/A-1
-                    # and the XMP Spec do not make this recommendation.
-                    if 'dc:title' not in meta_original:
-                        del meta_pdf['dc:title']
-                # If the user explicitly specified an empty string for any of the
-                # following, they should be unset and not reported as missing in
-                # the output pdf. Note that some metadata fields use differing names
-                # between PDF-A and PDF.
-                for meta in [meta_pdf, meta_original]:
-                    if options.title == '' and 'dc:title' in meta:
-                        del meta['dc:title']  # PDF-A and PDF
-                    if options.author == '':
-                        if 'dc:creator' in meta:
-                            del meta['dc:creator']  # PDF-A (Not xmp:CreatorTool)
-                        if 'pdf:Author' in meta:
-                            del meta['pdf:Author']  # PDF
-                    if options.subject == '':
-                        if 'dc:description' in meta:
-                            del meta['dc:description']  # PDF-A
-                        if 'dc:subject' in meta:
-                            del meta['dc:subject']  # PDF
-                    if options.keywords == '' and 'pdf:Keywords' in meta:
-                        del meta['pdf:Keywords']  # PDF-A and PDF
-                meta_missing = set(meta_original.keys()) - set(meta_pdf.keys())
-                report_on_metadata(meta_missing)
-
-        optimizing = context.plugin_manager.hook.is_optimization_enabled(
-            context=context
-        )
-        pdf.save(
-            output_file,
-            **get_pdf_save_settings(options.output_type),
-            linearize=(  # Don't linearize if optimize() will be linearizing too
-                not optimizing and should_linearize(working_file, context)
-            ),
-        )
-
-    return output_file
-
-
 def _file_size_ratio(
     input_file: Path, output_file: Path
 ) -> tuple[float | None, float | None]:
@@ -974,6 +974,7 @@ 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,
@@ -993,8 +994,8 @@ def optimize_pdf(
 
 
 def enumerate_compress_ranges(
-    iterable: Iterable,
-) -> Iterator[tuple[tuple[int, int], Any]]:
+    iterable: Iterable[T],
+) -> Iterator[tuple[tuple[int, int], T | None]]:
     """Enumerate the ranges of non-empty elements in an iterable.
 
     Compresses consecutive ranges of length 1 into single elements.
@@ -1022,21 +1023,22 @@ def enumerate_compress_ranges(
 
 
 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 = in_.read()
-                    # Some OCR engines (e.g. Tesseract v4 alpha) add form feeds
-                    # between pages, and some do not. For consistency, we ignore
-                    # any added by the OCR engine and them on our own.
-                    if txt.endswith('\f'):
-                        stream.write(txt[:-1])
-                    else:
-                        stream.write(txt)
+                txt = txt_file.read_text(encoding="utf-8")
+                # Some versions of Tesseract add a form feed at the end and
+                # others don't. Remove it if it exists, since we add one manually.
+                stream.write(txt.removesuffix('\f'))
             else:
                 if from_ != to_:
                     pages = f'{from_}-{to_}'
@@ -1047,14 +1049,14 @@ 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, original_file: Path | None
 ) -> None:
     """Copy the final temporary file to the output destination.
 
     Args:
-        input_file (Path): The input file to copy.
+        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.
+        original_file: The original file to copy attributes from.
 
     Returns:
         None
@@ -1073,5 +1075,5 @@ 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)

src/ocrmypdf/_pipelines/__init__.py

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

src/ocrmypdf/_pipelines/_common.py

@@ -1,65 +1,53 @@
-# SPDX-FileCopyrightText: 2019-2022 James R. Barlow
-# SPDX-FileCopyrightText: 2019 Martin Wind
+# SPDX-FileCopyrightText: 2023 James R. Barlow
 # SPDX-License-Identifier: MPL-2.0
 
-"""Implements the concurrent and page synchronous parts of the pipeline."""
-
-
 from __future__ import annotations
 
 import argparse
+import json
 import logging
 import logging.handlers
 import os
+import shutil
 import sys
 import threading
+from collections.abc import Callable, Sequence
 from concurrent.futures.process import BrokenProcessPool
 from concurrent.futures.thread import BrokenThreadPool
-from functools import partial
+from contextlib import contextmanager
+from dataclasses import dataclass
 from pathlib import Path
-from tempfile import mkdtemp
-from typing import NamedTuple, Sequence, cast
+from typing import NamedTuple, cast
 
 import PIL
 
 from ocrmypdf._concurrent import Executor, setup_executor
-from ocrmypdf._graft import OcrGrafter
-from ocrmypdf._jobcontext import PageContext, PdfContext, cleanup_working_files
+from ocrmypdf._jobcontext import PageContext, PdfContext
 from ocrmypdf._logging import PageNumberFilter
+from ocrmypdf._metadata import metadata_fixup
 from ocrmypdf._pipeline import (
     convert_to_pdfa,
-    copy_final,
     create_ocr_image,
     create_pdf_page_from_image,
     create_visible_page_jpg,
     generate_postscript_stub,
     get_orientation_correction,
-    get_pdfinfo,
-    is_ocr_required,
-    merge_sidecars,
-    metadata_fixup,
-    ocr_engine_hocr,
-    ocr_engine_textonly_pdf,
+    get_pdf_save_settings,
     optimize_pdf,
     preprocess_clean,
     preprocess_deskew,
     preprocess_remove_background,
     rasterize,
     rasterize_preview,
-    render_hocr_page,
+    should_linearize,
     should_visible_page_image_use_jpg,
-    triage,
-    validate_pdfinfo_options,
 )
-from ocrmypdf._plugin_manager import OcrmypdfPluginManager, get_plugin_manager
+from ocrmypdf._plugin_manager import OcrmypdfPluginManager
 from ocrmypdf._validation import (
-    check_requested_output_file,
-    create_input_file,
     report_output_file_size,
 )
 from ocrmypdf.exceptions import ExitCode, ExitCodeException
 from ocrmypdf.helpers import (
-    NeverRaise,
     available_cpu_count,
     check_pdf,
     pikepdf_enable_mmap,
@@ -68,33 +56,248 @@ from ocrmypdf.helpers import (
 from ocrmypdf.pdfa import file_claims_pdfa
 
 log = logging.getLogger(__name__)
+tls = threading.local()
+tls.pageno = None
+
+
+def _set_logging_tls(tls):
+    """Inject current page number (when available) into log records."""
+    old_factory = logging.getLogRecordFactory()
+
+    def wrapper(*args, **kwargs):
+        record = old_factory(*args, **kwargs)
+        if hasattr(tls, 'pageno'):
+            record.pageno = tls.pageno
+        return record
+
+    logging.setLogRecordFactory(wrapper)
+
+
+_set_logging_tls(tls)
+
+
+def set_thread_pageno(pageno: int | None):
+    """Set page number (1-based) that the current thread is processing."""
+    tls.pageno = pageno
 
 
 class PageResult(NamedTuple):
     """Result when a page is finished processing."""
 
     pageno: int
-    pdf_page_from_image: Path | None
-    ocr: Path | None
-    text: Path | None
-    orientation_correction: int
+    """Page number, 0-based."""
+
+    pdf_page_from_image: Path | None = None
+    """Single page PDF from image."""
+
+    ocr: Path | None = None
+    """Single page OCR PDF."""
+
+    text: Path | None = None
+    """Single page text file."""
+
+    orientation_correction: int = 0
+    """Orientation correction in degrees."""
 
 
-tls = threading.local()
-tls.pageno = None
+@dataclass
+class HOCRResult:
+    """Result when hOCR is finished processing."""
+
+    pageno: int
+    """Page number, 0-based."""
+
+    pdf_page_from_image: Path | None = None
+    """Single page PDF from image."""
+
+    hocr: Path | None = None
+    """Single page hOCR file."""
+
+    textpdf: Path | None = None
+    """hOCR file after conversion to PDF."""
+
+    orientation_correction: int = 0
+    """Orientation correction in degrees."""
+
+    def __getstate__(self):
+        """Return state values to be pickled."""
+        return {
+            k: (
+                ('Path://' + str(v))
+                if k in ('pdf_page_from_image', 'hocr', 'textpdf') and v is not None
+                else v
+            )
+            for k, v in self.__dict__.items()
+        }
+
+    def __setstate__(self, state):
+        """Restore state from the unpickled state values."""
+        self.__dict__.update(
+            {
+                k: (
+                    Path(v.removeprefix('Path://'))
+                    if k in ('pdf_page_from_image', 'hocr', 'textpdf') and v is not None
+                    else v
+                )
+                for k, v in state.items()
+            }
+        )
+
+    @classmethod
+    def from_json(cls, json_str: str) -> HOCRResult:
+        """Create an instance from a dict."""
+        return cls(**json.loads(json_str))
+
+    def to_json(self) -> str:
+        """Serialize to a JSON string."""
+        return json.dumps(self.__getstate__())
 
 
-old_factory = logging.getLogRecordFactory()
+def configure_debug_logging(
+    log_filename: Path, prefix: str = ''
+) -> tuple[logging.FileHandler, Callable[[], None]]:
+    """Create a debug log file at a specified location.
+
+    Returns the log handler, and a function to remove the handler.
+
+    Args:
+        log_filename: Where to the put the log file.
+        prefix: The logging domain prefix that should be sent to the log.
+    """
+    log_file_handler = logging.FileHandler(log_filename, delay=True)
+    log_file_handler.setLevel(logging.DEBUG)
+    formatter = logging.Formatter(
+        '[%(asctime)s] - %(name)s - %(levelname)7s -%(pageno)s %(message)s'
+    )
+    log_file_handler.setFormatter(formatter)
+    log_file_handler.addFilter(PageNumberFilter())
+    logging.getLogger(prefix).addHandler(log_file_handler)
+
+    def remover():
+        try:
+            logging.getLogger(prefix).removeHandler(log_file_handler)
+            log_file_handler.close()
+        except OSError as e:
+            print(e, file=sys.stderr)
+
+    return log_file_handler, remover
 
 
-def record_factory(*args, **kwargs):
-    record = old_factory(*args, **kwargs)
-    if hasattr(tls, 'pageno'):
-        record.pageno = tls.pageno
-    return record
+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.
+    PIL.Image.MAX_IMAGE_PIXELS = max_pixels
+    pikepdf_enable_mmap()
 
 
-logging.setLogRecordFactory(record_factory)
+@contextmanager
+def manage_debug_log_handler(
+    *,
+    options: argparse.Namespace,
+    work_folder: Path,
+):
+    remover = None
+    if (options.keep_temporary_files or options.verbose >= 1) and not os.environ.get(
+        'PYTEST_CURRENT_TEST', ''
+    ):
+        # Debug log for command line interface only with verbose output
+        # See https://github.com/pytest-dev/pytest/issues/5502 for why we skip this
+        # when pytest is running
+        _debug_log_handler, remover = configure_debug_logging(
+            work_folder / "debug.log", prefix=""
+        )  # pragma: no cover
+    try:
+        yield
+    finally:
+        if remover:
+            remover()
+
+
+@contextmanager
+def manage_work_folder(*, work_folder: Path, retain: bool, print_location: bool):
+    try:
+        yield work_folder
+    finally:
+        if retain:
+            if print_location:
+                print(
+                    f"Temporary working files retained at:\n{work_folder}",
+                    file=sys.stderr,
+                )
+        else:
+            shutil.rmtree(work_folder, ignore_errors=True)
+
+
+def cli_exception_handler(
+    fn: Callable[[argparse.Namespace, OcrmypdfPluginManager], ExitCode],
+    options: argparse.Namespace,
+    plugin_manager: OcrmypdfPluginManager,
+) -> ExitCode:
+    """Convert exceptions into command line error messages and exit codes.
+
+    When known exceptions are raised, the exception message is printed to stderr
+    and the program exits with a non-zero exit code. When unknown exceptions are
+    raised, the exception traceback is printed to stderr and the program exits
+    with a non-zero exit code.
+    """
+    try:
+        # We cannot use a generator and yield here, as would be the usual pattern
+        # for exception handling context managers, because we need to return an exit
+        # code.
+        return fn(options, plugin_manager)
+    except KeyboardInterrupt:
+        if options.verbose >= 1:
+            log.exception("KeyboardInterrupt")
+        else:
+            log.error("KeyboardInterrupt")
+        return ExitCode.ctrl_c
+    except ExitCodeException as e:
+        e = cast(ExitCodeException, e)
+        if options.verbose >= 1:
+            log.exception("ExitCodeException")
+        elif str(e):
+            log.error("%s: %s", type(e).__name__, str(e))
+        else:
+            log.error(type(e).__name__)
+        return e.exit_code
+    except PIL.Image.DecompressionBombError:
+        log.exception(
+            "A decompression bomb error was encountered while executing the "
+            "pipeline. Use the argument --max-image-mpixels to raise the maximum "
+            "image pixel limit."
+        )
+        return ExitCode.other_error
+    except (
+        BrokenProcessPool,
+        BrokenThreadPool,
+    ):
+        log.exception(
+            "A worker process was terminated unexpectedly. This is known to occur if "
+            "processing your file takes all available swap space and RAM. It may "
+            "help to try again with a smaller number of jobs, using the --jobs "
+            "argument."
+        )
+        return ExitCode.child_process_error
+    except Exception:  # pylint: disable=broad-except
+        log.exception("An exception occurred while executing the pipeline")
+        return ExitCode.other_error
+
+
+def setup_pipeline(
+    options: argparse.Namespace,
+    plugin_manager: OcrmypdfPluginManager,
+) -> Executor:
+    # Any changes to options will not take effect for options that are already
+    # bound to function parameters in the pipeline. (For example
+    # options.input_file, options.pdf_renderer are already bound.)
+    if not options.jobs:
+        options.jobs = available_cpu_count()
+
+    pikepdf_enable_mmap()
+    executor = setup_executor(plugin_manager)
+    return executor
 
 
 def preprocess(
@@ -104,6 +307,7 @@ def preprocess(
     deskew: bool,
     clean: bool,
 ) -> Path:
+    """Preprocess an image."""
     if remove_background:
         image = preprocess_remove_background(image, page_context)
     if deskew:
@@ -116,6 +320,7 @@ 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
@@ -172,19 +377,9 @@ def make_intermediate_images(
     return ocr_image, preprocess_out
 
 
-def exec_page_sync(page_context: PageContext) -> PageResult:
+def process_page(page_context: PageContext) -> tuple[Path, Path | None, int]:
+    """Process page to create OCR image, visible page image and orientation."""
     options = page_context.options
-    tls.pageno = page_context.pageno + 1
-
-    if not is_ocr_required(page_context):
-        return PageResult(
-            pageno=page_context.pageno,
-            pdf_page_from_image=None,
-            ocr=None,
-            text=None,
-            orientation_correction=0,
-        )
-
     orientation_correction = 0
     if options.rotate_pages:
         # Rasterize
@@ -212,255 +407,48 @@ def exec_page_sync(page_context: PageContext) -> PageResult:
         pdf_page_from_image_out = create_pdf_page_from_image(
             visible_image_out, page_context, orientation_correction
         )
-
-    if options.pdf_renderer.startswith('hocr'):
-        (hocr_out, text_out) = ocr_engine_hocr(ocr_image_out, page_context)
-        ocr_out = render_hocr_page(hocr_out, page_context)
-    elif options.pdf_renderer == 'sandwich':
-        (ocr_out, text_out) = ocr_engine_textonly_pdf(ocr_image_out, page_context)
-    else:
-        raise NotImplementedError(f"pdf_renderer {options.pdf_renderer}")
-
-    return PageResult(
-        pageno=page_context.pageno,
-        pdf_page_from_image=pdf_page_from_image_out,
-        ocr=ocr_out,
-        text=text_out,
-        orientation_correction=orientation_correction,
-    )
+    return ocr_image_out, pdf_page_from_image_out, orientation_correction
 
 
-def post_process(
+def postprocess(
     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)
         pdf_out = convert_to_pdfa(pdf_out, ps_stub_out, context)
 
-    pdf_out = metadata_fixup(pdf_out, context)
+    optimizing = context.plugin_manager.hook.is_optimization_enabled(context=context)
+    save_settings = get_pdf_save_settings(context.options.output_type)
+    save_settings['linearize'] = not optimizing and should_linearize(pdf_out, context)
+
+    pdf_out = metadata_fixup(pdf_out, context, pdf_save_settings=save_settings)
     return optimize_pdf(pdf_out, context, executor)
 
 
-def worker_init(max_pixels: int) -> None:
-    # In Windows, child process will not inherit our change to this value in
-    # the parent process, so ensure workers get it set. Not needed when running
-    # threaded, but harmless to set again.
-    PIL.Image.MAX_IMAGE_PIXELS = max_pixels
-    pikepdf_enable_mmap()
-
-
-def exec_concurrent(context: PdfContext, executor: Executor) -> Sequence[str]:
-    """Execute the pipeline concurrently."""
-    # Run exec_page_sync on every page context
-    options = context.options
-    max_workers = min(len(context.pdfinfo), options.jobs)
-    if max_workers > 1:
-        log.info("Start processing %d pages concurrently", max_workers)
-
-    sidecars: list[Path | None] = [None] * len(context.pdfinfo)
-    ocrgraft = OcrGrafter(context)
-
-    def update_page(result: PageResult, pbar):
-        try:
-            tls.pageno = result.pageno + 1
-            sidecars[result.pageno] = result.text
-            pbar.update()
-            ocrgraft.graft_page(
-                pageno=result.pageno,
-                image=result.pdf_page_from_image,
-                textpdf=result.ocr,
-                autorotate_correction=result.orientation_correction,
-            )
-            pbar.update()
-        finally:
-            tls.pageno = None
-
-    executor(
-        use_threads=options.use_threads,
-        max_workers=max_workers,
-        tqdm_kwargs=dict(
-            total=(2 * len(context.pdfinfo)),
-            desc='OCR' if options.tesseract_timeout > 0 else 'Image processing',
-            unit='page',
-            unit_scale=0.5,
-            disable=not options.progress_bar,
-        ),
-        worker_initializer=partial(worker_init, PIL.Image.MAX_IMAGE_PIXELS),
-        task=exec_page_sync,
-        task_arguments=context.get_page_contexts(),
-        task_finished=update_page,
-    )
-
-    # Output sidecar text
-    if options.sidecar:
-        text = merge_sidecars(sidecars, context)
-        # Copy text file to destination
-        copy_final(text, options.sidecar, context)
-
-    # Merge layers to one single pdf
-    pdf = ocrgraft.finalize()
-
-    messages: Sequence[str] = []
-    if options.output_type != 'none':
-        # PDF/A and metadata
-        log.info("Postprocessing...")
-        pdf, messages = post_process(pdf, context, executor)
-
-        # Copy PDF file to destination
-        copy_final(pdf, options.output_file, context)
-    return messages
-
-
-def configure_debug_logging(
-    log_filename: Path, prefix: str = ''
-) -> logging.FileHandler:
-    """Create a debug log file at a specified location.
-
-    Arguments:
-        log_filename: Where to the put the log file.
-        prefix: The logging domain prefix that should be sent to the log.
-    """
-    log_file_handler = logging.FileHandler(log_filename, delay=True)
-    log_file_handler.setLevel(logging.DEBUG)
-    formatter = logging.Formatter(
-        '[%(asctime)s] - %(name)s - %(levelname)7s -%(pageno)s %(message)s'
-    )
-    log_file_handler.setFormatter(formatter)
-    log_file_handler.addFilter(PageNumberFilter())
-    logging.getLogger(prefix).addHandler(log_file_handler)
-    return log_file_handler
-
-
-def run_pipeline(
-    options: argparse.Namespace,
-    *,
-    plugin_manager: OcrmypdfPluginManager | None,
-    api: bool = False,
-) -> ExitCode:
-    # Any changes to options will not take effect for options that are already
-    # bound to function parameters in the pipeline. (For example
-    # options.input_file, options.pdf_renderer are already bound.)
-    if not options.jobs:
-        options.jobs = available_cpu_count()
-    if not plugin_manager:
-        plugin_manager = get_plugin_manager(options.plugins)
-
-    work_folder = Path(mkdtemp(prefix="ocrmypdf.io."))
-    debug_log_handler = None
-    if (
-        (options.keep_temporary_files or options.verbose >= 1)
-        and not os.environ.get('PYTEST_CURRENT_TEST', '')
-        and not api
-    ):
-        # Debug log for command line interface only with verbose output
-        # See https://github.com/pytest-dev/pytest/issues/5502 for why we skip this
-        # when pytest is running
-        debug_log_handler = configure_debug_logging(
-            Path(work_folder) / "debug.log"
-        )  # pragma: no cover
-
-    pikepdf_enable_mmap()
-
-    executor = setup_executor(plugin_manager)
-    try:
-        check_requested_output_file(options)
-        start_input_file, original_filename = create_input_file(options, work_folder)
-
-        # Triage image or pdf
-        origin_pdf = triage(
-            original_filename, start_input_file, work_folder / 'origin.pdf', options
+def report_output_pdf(options, start_input_file, optimize_messages) -> ExitCode:
+    if options.output_file == '-':
+        log.info("Output sent to stdout")
+    elif hasattr(options.output_file, 'writable') and options.output_file.writable():
+        log.info("Output written to stream")
+    elif samefile(options.output_file, Path(os.devnull)):
+        pass  # Say nothing when sending to dev null
+    else:
+        if options.output_type.startswith('pdfa'):
+            pdfa_info = file_claims_pdfa(options.output_file)
+            if pdfa_info['pass']:
+                log.info("Output file is a %s (as expected)", pdfa_info['conformance'])
+            else:
+                log.warning(
+                    "Output file is okay but is not PDF/A (seems to be %s)",
+                    pdfa_info['conformance'],
+                )
+                return ExitCode.pdfa_conversion_failed
+        if not check_pdf(options.output_file):
+            log.warning('Output file: The generated PDF is INVALID')
+            return ExitCode.invalid_output_pdf
+        report_output_file_size(
+            options, start_input_file, options.output_file, optimize_messages
         )
-
-        # Gather pdfinfo and create context
-        pdfinfo = get_pdfinfo(
-            origin_pdf,
-            executor=executor,
-            detailed_analysis=options.redo_ocr,
-            progbar=options.progress_bar,
-            max_workers=options.jobs if not options.use_threads else 1,  # To help debug
-            check_pages=options.pages,
-        )
-
-        context = PdfContext(options, work_folder, origin_pdf, pdfinfo, plugin_manager)
-
-        # Validate options are okay for this pdf
-        validate_pdfinfo_options(context)
-
-        # Execute the pipeline
-        optimize_messages = exec_concurrent(context, executor)
-
-        if options.output_file == '-':
-            log.info("Output sent to stdout")
-        elif (
-            hasattr(options.output_file, 'writable') and options.output_file.writable()
-        ):
-            log.info("Output written to stream")
-        elif samefile(options.output_file, Path(os.devnull)):
-            pass  # Say nothing when sending to dev null
-        else:
-            if options.output_type.startswith('pdfa'):
-                pdfa_info = file_claims_pdfa(options.output_file)
-                if pdfa_info['pass']:
-                    log.info(
-                        "Output file is a %s (as expected)", pdfa_info['conformance']
-                    )
-                else:
-                    log.warning(
-                        "Output file is okay but is not PDF/A (seems to be %s)",
-                        pdfa_info['conformance'],
-                    )
-                    return ExitCode.pdfa_conversion_failed
-            if not check_pdf(options.output_file):
-                log.warning('Output file: The generated PDF is INVALID')
-                return ExitCode.invalid_output_pdf
-            report_output_file_size(
-                options, start_input_file, options.output_file, optimize_messages
-            )
-
-    except KeyboardInterrupt if not api else NeverRaise:
-        if options.verbose >= 1:
-            log.exception("KeyboardInterrupt")
-        else:
-            log.error("KeyboardInterrupt")
-        return ExitCode.ctrl_c
-    except ExitCodeException if not api else NeverRaise as e:
-        e = cast(ExitCodeException, e)
-        if options.verbose >= 1:
-            log.exception("ExitCodeException")
-        elif str(e):
-            log.error("%s: %s", type(e).__name__, str(e))
-        else:
-            log.error(type(e).__name__)
-        return e.exit_code
-    except PIL.Image.DecompressionBombError if not api else NeverRaise:
-        log.exception(
-            "A decompression bomb error was encountered while executing the "
-            "pipeline. Use the argument --max-image-mpixels to raise the maximum "
-            "image pixel limit."
-        )
-        return ExitCode.other_error
-    except (
-        BrokenProcessPool if not api else NeverRaise,
-        BrokenThreadPool if not api else NeverRaise,
-    ):
-        log.exception(
-            "A worker process was terminated unexpectedly. This is known to occur if "
-            "processing your file takes all available swap space and RAM. It may "
-            "help to try again with a smaller number of jobs, using the --jobs "
-            "argument."
-        )
-        return ExitCode.child_process_error
-    except Exception if not api else NeverRaise:  # pylint: disable=broad-except
-        log.exception("An exception occurred while executing the pipeline")
-        return ExitCode.other_error
-    finally:
-        if debug_log_handler:
-            try:
-                debug_log_handler.close()
-                log.removeHandler(debug_log_handler)
-            except OSError as e:
-                print(e, file=sys.stderr)
-        cleanup_working_files(work_folder, options)
-
     return ExitCode.ok

src/ocrmypdf/_pipelines/hocr_to_ocr_pdf.py

@@ -0,0 +1,133 @@
+# SPDX-FileCopyrightText: 2019-2023 James R. Barlow
+# SPDX-FileCopyrightText: 2019 Martin Wind
+# SPDX-License-Identifier: MPL-2.0
+
+"""Implements the concurrent and page synchronous parts of the pipeline."""
+
+from __future__ import annotations
+
+import argparse
+import logging
+import logging.handlers
+from collections.abc import Sequence
+from functools import partial
+
+import PIL
+
+from ocrmypdf._concurrent import Executor
+from ocrmypdf._graft import OcrGrafter
+from ocrmypdf._jobcontext import PageContext, PdfContext
+from ocrmypdf._pipeline import (
+    copy_final,
+    get_pdfinfo,
+    render_hocr_page,
+)
+from ocrmypdf._pipelines._common import (
+    HOCRResult,
+    manage_work_folder,
+    postprocess,
+    report_output_pdf,
+    set_thread_pageno,
+    setup_pipeline,
+    worker_init,
+)
+from ocrmypdf._plugin_manager import OcrmypdfPluginManager
+from ocrmypdf._progressbar import ProgressBar
+from ocrmypdf.exceptions import ExitCode
+
+log = logging.getLogger(__name__)
+
+
+def _exec_hocrtransform_sync(page_context: PageContext) -> HOCRResult:
+    """Process each page."""
+    hocr_json = page_context.get_path('hocr.json')
+    if not hocr_json.exists():
+        # No hOCR file, so no OCR was performed on this page.
+        return HOCRResult(pageno=page_context.pageno)
+    hocr_result = HOCRResult.from_json(hocr_json.read_text())
+    hocr_result.textpdf = render_hocr_page(
+        page_context.get_path('ocr_hocr.hocr'), page_context
+    )
+    return hocr_result
+
+
+def exec_hocr_to_ocr_pdf(context: PdfContext, executor: Executor) -> Sequence[str]:
+    """Convert hOCR files to OCR PDF."""
+    # Run exec_page_sync on every page
+    options = context.options
+    max_workers = min(len(context.pdfinfo), options.jobs)
+    if max_workers > 1:
+        log.info("Continue processing %d pages concurrently", max_workers)
+
+    ocrgraft = OcrGrafter(context)
+
+    def graft_page(result: HOCRResult, pbar: ProgressBar):
+        """Graft text only PDF on to main PDF's page."""
+        try:
+            set_thread_pageno(result.pageno + 1)
+            pbar.update()
+            ocrgraft.graft_page(
+                pageno=result.pageno,
+                image=result.pdf_page_from_image,
+                textpdf=result.textpdf,
+                autorotate_correction=result.orientation_correction,
+            )
+            pbar.update()
+        finally:
+            set_thread_pageno(None)
+
+    executor(
+        use_threads=options.use_threads,
+        max_workers=max_workers,
+        progress_kwargs=dict(
+            total=(2 * len(context.pdfinfo)),
+            desc='Grafting hOCR to PDF',
+            unit='page',
+            unit_scale=0.5,
+            disable=not options.progress_bar,
+        ),
+        worker_initializer=partial(worker_init, PIL.Image.MAX_IMAGE_PIXELS),
+        task=_exec_hocrtransform_sync,
+        task_arguments=context.get_page_context_args(),
+        task_finished=graft_page,
+    )
+
+    pdf = ocrgraft.finalize()
+    messages: Sequence[str] = []
+    if options.output_type != 'none':
+        # PDF/A and metadata
+        log.info("Postprocessing...")
+        pdf, messages = postprocess(pdf, context, executor)
+
+        # Copy PDF file to destination (we don't know the input PDF file name)
+        copy_final(pdf, options.output_file, None)
+    return messages
+
+
+def run_hocr_to_ocr_pdf_pipeline(
+    options: argparse.Namespace,
+    *,
+    plugin_manager: OcrmypdfPluginManager,
+) -> ExitCode:
+    """Run pipeline to convert hOCR to final output PDF."""
+    with manage_work_folder(
+        work_folder=options.work_folder, retain=True, print_location=False
+    ) as work_folder:
+        executor = setup_pipeline(options, plugin_manager)
+        origin_pdf = work_folder / 'origin.pdf'
+
+        # Gather pdfinfo and create context
+        pdfinfo = get_pdfinfo(
+            origin_pdf,
+            executor=executor,
+            detailed_analysis=options.redo_ocr,
+            progbar=options.progress_bar,
+            max_workers=options.jobs,
+            use_threads=options.use_threads,
+            check_pages=options.pages,
+        )
+        context = PdfContext(options, work_folder, origin_pdf, pdfinfo, plugin_manager)
+        plugin_manager.hook.check_options(options=options)
+        optimize_messages = exec_hocr_to_ocr_pdf(context, executor)
+
+        return report_output_pdf(options, origin_pdf, optimize_messages)

src/ocrmypdf/_pipelines/ocr.py

@@ -0,0 +1,223 @@
+# SPDX-FileCopyrightText: 2019-2023 James R. Barlow
+# SPDX-FileCopyrightText: 2019 Martin Wind
+# SPDX-License-Identifier: MPL-2.0
+
+"""Implements the concurrent and page synchronous parts of the pipeline."""
+
+from __future__ import annotations
+
+import argparse
+import logging
+import logging.handlers
+from collections.abc import Sequence
+from functools import partial
+from pathlib import Path
+from tempfile import mkdtemp
+
+import PIL
+
+from ocrmypdf._concurrent import Executor
+from ocrmypdf._graft import OcrGrafter
+from ocrmypdf._jobcontext import PageContext, PdfContext
+from ocrmypdf._pipeline import (
+    copy_final,
+    get_pdfinfo,
+    is_ocr_required,
+    merge_sidecars,
+    ocr_engine_hocr,
+    ocr_engine_textonly_pdf,
+    render_hocr_page,
+    triage,
+    validate_pdfinfo_options,
+)
+from ocrmypdf._pipelines._common import (
+    PageResult,
+    cli_exception_handler,
+    manage_debug_log_handler,
+    manage_work_folder,
+    postprocess,
+    process_page,
+    report_output_pdf,
+    set_thread_pageno,
+    setup_pipeline,
+    worker_init,
+)
+from ocrmypdf._plugin_manager import OcrmypdfPluginManager
+from ocrmypdf._progressbar import ProgressBar
+from ocrmypdf._validation import (
+    check_requested_output_file,
+    create_input_file,
+)
+from ocrmypdf.exceptions import ExitCode
+
+log = logging.getLogger(__name__)
+
+
+def _image_to_ocr_text(
+    page_context: PageContext, ocr_image_out: Path
+) -> tuple[Path, Path]:
+    """Run OCR engine on image to create OCR PDF and text file."""
+    options = page_context.options
+    if options.pdf_renderer.startswith('hocr'):
+        hocr_out, text_out = ocr_engine_hocr(ocr_image_out, page_context)
+        ocr_out = render_hocr_page(hocr_out, page_context)
+    elif options.pdf_renderer == 'sandwich':
+        ocr_out, text_out = ocr_engine_textonly_pdf(ocr_image_out, page_context)
+    else:
+        raise NotImplementedError(f"pdf_renderer {options.pdf_renderer}")
+    return ocr_out, text_out
+
+
+def _exec_page_sync(page_context: PageContext) -> PageResult:
+    """Execute a pipeline for a single page synchronously."""
+    set_thread_pageno(page_context.pageno + 1)
+
+    if not is_ocr_required(page_context):
+        return PageResult(pageno=page_context.pageno)
+
+    ocr_image_out, pdf_page_from_image_out, orientation_correction = process_page(
+        page_context
+    )
+    ocr_out, text_out = _image_to_ocr_text(page_context, ocr_image_out)
+    return PageResult(
+        pageno=page_context.pageno,
+        pdf_page_from_image=pdf_page_from_image_out,
+        ocr=ocr_out,
+        text=text_out,
+        orientation_correction=orientation_correction,
+    )
+
+
+def exec_concurrent(context: PdfContext, executor: Executor) -> Sequence[str]:
+    """Execute the OCR pipeline concurrently."""
+    options = context.options
+    max_workers = min(len(context.pdfinfo), options.jobs)
+    if max_workers > 1:
+        log.info("Start processing %d pages concurrently", max_workers)
+
+    sidecars: list[Path | None] = [None] * len(context.pdfinfo)
+    ocrgraft = OcrGrafter(context)
+
+    def update_page(result: PageResult, pbar: ProgressBar):
+        """After OCR is complete for a page, update the PDF."""
+        try:
+            set_thread_pageno(result.pageno + 1)
+            sidecars[result.pageno] = result.text
+            pbar.update(0.5)
+            ocrgraft.graft_page(
+                pageno=result.pageno,
+                image=result.pdf_page_from_image,
+                textpdf=result.ocr,
+                autorotate_correction=result.orientation_correction,
+            )
+            pbar.update(0.5)
+        finally:
+            set_thread_pageno(None)
+
+    executor(
+        use_threads=options.use_threads,
+        max_workers=max_workers,
+        progress_kwargs=dict(
+            total=len(context.pdfinfo),
+            desc='OCR' if options.tesseract_timeout > 0 else 'Image processing',
+            unit='page',
+            disable=not options.progress_bar,
+        ),
+        worker_initializer=partial(worker_init, PIL.Image.MAX_IMAGE_PIXELS),
+        task=_exec_page_sync,
+        task_arguments=context.get_page_context_args(),
+        task_finished=update_page,
+    )
+
+    # Output sidecar text
+    if options.sidecar:
+        text = merge_sidecars(sidecars, context)
+        # Copy text file to destination
+        copy_final(text, options.sidecar, options.input_file)
+
+    # Merge layers to one single pdf
+    pdf = ocrgraft.finalize()
+
+    messages: Sequence[str] = []
+    if options.output_type != 'none':
+        # PDF/A and metadata
+        log.info("Postprocessing...")
+        pdf, messages = postprocess(pdf, context, executor)
+
+        # Copy PDF file to destination
+        copy_final(pdf, options.output_file, options.input_file)
+    return messages
+
+
+def _run_pipeline(
+    options: argparse.Namespace,
+    plugin_manager: OcrmypdfPluginManager,
+) -> ExitCode:
+    with (
+        manage_work_folder(
+            work_folder=Path(mkdtemp(prefix="ocrmypdf.io.")),
+            retain=options.keep_temporary_files,
+            print_location=options.keep_temporary_files,
+        ) as work_folder,
+        manage_debug_log_handler(options=options, work_folder=work_folder),
+    ):
+        executor = setup_pipeline(options, plugin_manager)
+        check_requested_output_file(options)
+        start_input_file, original_filename = create_input_file(options, work_folder)
+
+        # Triage image or pdf
+        origin_pdf = triage(
+            original_filename, start_input_file, work_folder / 'origin.pdf', options
+        )
+
+        # Gather pdfinfo and create context
+        pdfinfo = get_pdfinfo(
+            origin_pdf,
+            executor=executor,
+            detailed_analysis=options.redo_ocr,
+            progbar=options.progress_bar,
+            max_workers=options.jobs,
+            use_threads=options.use_threads,
+            check_pages=options.pages,
+        )
+
+        context = PdfContext(options, work_folder, origin_pdf, pdfinfo, plugin_manager)
+
+        # Validate options are okay for this pdf
+        validate_pdfinfo_options(context)
+
+        # Execute the pipeline
+        optimize_messages = exec_concurrent(context, executor)
+
+        exitcode = report_output_pdf(options, start_input_file, optimize_messages)
+        return exitcode
+
+
+def run_pipeline_cli(
+    options: argparse.Namespace,
+    *,
+    plugin_manager: OcrmypdfPluginManager,
+) -> ExitCode:
+    """Run the OCR pipeline with command line exception handling.
+
+    Args:
+        options: The parsed command line options.
+        plugin_manager: The plugin manager to use. If not provided, one will be
+            created.
+    """
+    return cli_exception_handler(_run_pipeline, options, plugin_manager)
+
+
+def run_pipeline(
+    options: argparse.Namespace,
+    *,
+    plugin_manager: OcrmypdfPluginManager,
+) -> ExitCode:
+    """Run the OCR pipeline without command line exception handling.
+
+    Args:
+        options: The parsed command line options.
+        plugin_manager: The plugin manager to use. If not provided, one will be
+            created.
+    """
+    return _run_pipeline(options, plugin_manager)

src/ocrmypdf/_pipelines/pdf_to_hocr.py

@@ -0,0 +1,115 @@
+# SPDX-FileCopyrightText: 2019-2023 James R. Barlow
+# SPDX-FileCopyrightText: 2019 Martin Wind
+# SPDX-License-Identifier: MPL-2.0
+
+"""Implements the concurrent and page synchronous parts of the pipeline."""
+
+from __future__ import annotations
+
+import argparse
+import logging
+import logging.handlers
+import shutil
+from functools import partial
+
+import PIL
+
+from ocrmypdf._concurrent import Executor
+from ocrmypdf._jobcontext import PageContext, PdfContext
+from ocrmypdf._pipeline import (
+    get_pdfinfo,
+    is_ocr_required,
+    ocr_engine_hocr,
+    validate_pdfinfo_options,
+)
+from ocrmypdf._pipelines._common import (
+    HOCRResult,
+    manage_work_folder,
+    process_page,
+    set_thread_pageno,
+    setup_pipeline,
+    worker_init,
+)
+from ocrmypdf._plugin_manager import OcrmypdfPluginManager
+from ocrmypdf._validation import (
+    set_lossless_reconstruction,
+)
+
+log = logging.getLogger(__name__)
+
+
+def _exec_page_hocr_sync(page_context: PageContext) -> HOCRResult:
+    """Execute a pipeline for a single page hOCR."""
+    set_thread_pageno(page_context.pageno + 1)
+
+    if not is_ocr_required(page_context):
+        return HOCRResult(pageno=page_context.pageno)
+
+    ocr_image_out, pdf_page_from_image_out, orientation_correction = process_page(
+        page_context
+    )
+    hocr_out, _ = ocr_engine_hocr(ocr_image_out, page_context)
+
+    result = HOCRResult(
+        pageno=page_context.pageno,
+        pdf_page_from_image=pdf_page_from_image_out,
+        hocr=hocr_out,
+        orientation_correction=orientation_correction,
+    )
+    page_context.get_path('hocr.json').write_text(result.to_json())
+    return result
+
+
+def exec_pdf_to_hocr(context: PdfContext, executor: Executor) -> None:
+    """Execute the OCR pipeline concurrently and output hOCR."""
+    # Run exec_page_sync on every page
+    options = context.options
+    max_workers = min(len(context.pdfinfo), options.jobs)
+    if max_workers > 1:
+        log.info("Start processing %d pages concurrently", max_workers)
+
+    executor(
+        use_threads=options.use_threads,
+        max_workers=max_workers,
+        progress_kwargs=dict(
+            total=(2 * len(context.pdfinfo)),
+            desc='hOCR',
+            unit='page',
+            unit_scale=0.5,
+            disable=not options.progress_bar,
+        ),
+        worker_initializer=partial(worker_init, PIL.Image.MAX_IMAGE_PIXELS),
+        task=_exec_page_hocr_sync,
+        task_arguments=context.get_page_context_args(),
+    )
+
+
+def run_hocr_pipeline(
+    options: argparse.Namespace,
+    *,
+    plugin_manager: OcrmypdfPluginManager,
+) -> None:
+    """Run pipeline to output hOCR."""
+    with manage_work_folder(
+        work_folder=options.output_folder, retain=True, print_location=False
+    ) as work_folder:
+        executor = setup_pipeline(options, plugin_manager)
+        shutil.copy2(options.input_file, work_folder / 'origin.pdf')
+
+        # Gather pdfinfo and create context
+        pdfinfo = get_pdfinfo(
+            options.input_file,
+            executor=executor,
+            detailed_analysis=options.redo_ocr,
+            progbar=options.progress_bar,
+            max_workers=options.jobs,
+            use_threads=options.use_threads,
+            check_pages=options.pages,
+        )
+        context = PdfContext(
+            options, work_folder, options.input_file, pdfinfo, plugin_manager
+        )
+        # Validate options are okay for this pdf
+        set_lossless_reconstruction(options)
+        validate_pdfinfo_options(context)
+        exec_pdf_to_hocr(context, executor)

src/ocrmypdf/_plugin_manager.py

@@ -10,8 +10,8 @@ import importlib
 import importlib.util
 import pkgutil
 import sys
+from collections.abc import Sequence
 from pathlib import Path
-from typing import Sequence
 
 import pluggy
 
@@ -33,7 +33,7 @@ class OcrmypdfPluginManager(pluggy.PluginManager):
     def __init__(
         self,
         *args,
-        plugins: list[str | Path],
+        plugins: Sequence[str | Path],
         builtins: bool = True,
         **kwargs,
     ):
@@ -101,11 +101,11 @@ class OcrmypdfPluginManager(pluggy.PluginManager):
 
 
 def get_plugin_manager(
-    plugins: list[str | Path], builtins=True
+    plugins: Sequence[str | Path] | None = None, builtins=True
 ) -> OcrmypdfPluginManager:
     return OcrmypdfPluginManager(
         project_name='ocrmypdf',
-        plugins=plugins,
+        plugins=plugins if plugins is not None else [],
         builtins=builtins,
     )
 

src/ocrmypdf/_progressbar.py

@@ -0,0 +1,148 @@
+# SPDX-FileCopyrightText: 2023 James R. Barlow
+# SPDX-License-Identifier: MPL-2.0
+
+"""Defines progress bar API."""
+
+from __future__ import annotations
+
+from typing import Protocol
+
+from rich.console import Console
+from rich.progress import (
+    BarColumn,
+    MofNCompleteColumn,
+    Progress,
+    TaskProgressColumn,
+    TextColumn,
+    TimeRemainingColumn,
+)
+from rich.table import Column
+
+
+class ProgressBar(Protocol):
+    """The protocol that OCRmyPDF expects progress bar classes to be compatible with.
+
+    In practice this could be used for any time of monitoring, not just a progress bar.
+
+    Calling the class should return a new progress bar object, which is activated
+    with ``__enter__`` and terminated with ``__exit__``. An update method is called
+    whenever the progress bar is updated. Progress bar objects will not be reused;
+    a new one will be created for each group of tasks.
+
+    The progress bar is held in the main process/thread and not updated by child
+    process/threads. When a child notifies the parent of completed work, the
+    parent updates the progress bar.
+
+    Progress bars should never write to ``sys.stdout``, or they will corrupt the
+    output if OCRmyPDF writes a PDF to standard output.
+
+    The type of events that OCRmyPDF reports to a progress bar may change in
+    minor releases.
+    """
+
+    def __init__(
+        self,
+        *,
+        total: int | float | None,
+        desc: str | None,
+        unit: str | None,
+        disable: bool = False,
+        **kwargs,
+    ):
+        """Initialize a progress bar.
+
+        *total* indicates the total number of work units. If None, the total
+        number of work units is unknown. If *disable* is True, the progress bar
+        should be disabled. *unit* is a description of the work unit.
+        *desc* is a description of the overall task to be performed.
+
+        Unrecognized keyword arguments must be ignored, as the list of keyword
+        arguments may grow with time.
+        """
+
+    def __enter__(self):
+        """Enter a progress bar context."""
+
+    def __exit__(self, *args):
+        """Exit a progress bar context."""
+
+    def update(self, n=1, *, completed=None):
+        """Update the progress bar by an increment.
+
+        For use within a progress bar context.
+        """
+
+
+class NullProgressBar:
+    """Progress bar API that takes no actions."""
+
+    def __init__(self, **kwargs):
+        pass
+
+    def __enter__(self):
+        return self
+
+    def __exit__(self, exc_type, exc_value, traceback):
+        return False
+
+    def update(self, _arg=None, *, completed=None):
+        return
+
+
+class RichProgressBar:
+    """Display progress bar using rich."""
+
+    def __init__(
+        self,
+        *,
+        console: Console,
+        desc: str,
+        total: float | None = None,
+        unit: str | None = None,
+        unit_scale: float | None = 1.0,
+        disable: bool = False,
+        **kwargs,
+    ):
+        self._entered = False
+        self.progress = Progress(
+            TextColumn(
+                "[progress.description]{task.description}",
+                table_column=Column(min_width=20),
+            ),
+            BarColumn(),
+            TaskProgressColumn(),
+            MofNCompleteColumn(),
+            TimeRemainingColumn(),
+            console=console,
+            auto_refresh=True,
+            redirect_stderr=True,
+            redirect_stdout=False,
+            disable=disable,
+            **kwargs,
+        )
+        self.unit_scale = unit_scale
+        self.progress_bar = self.progress.add_task(
+            desc,
+            total=total * self.unit_scale
+            if total is not None and self.unit_scale is not None
+            else None,
+            unit=unit,
+        )
+
+    def __enter__(self):
+        self.progress.start()
+        self._entered = True
+        return self
+
+    def __exit__(self, exc_type, exc_value, traceback):
+        self.progress.refresh()
+        self.progress.stop()
+        return False
+
+    def update(self, n=1, *, completed=None):
+        assert self._entered, "Progress bar must be entered before updating"
+        if completed is None:
+            advance = self.unit_scale if n is None else n
+            self.progress.update(self.progress_bar, advance=advance)
+        else:
+            self.progress.update(self.progress_bar, completed=completed)

src/ocrmypdf/_validation.py

@@ -12,14 +12,15 @@ import os
 import sys
 import unicodedata
 from argparse import Namespace
+from collections.abc import Sequence
 from pathlib import Path
 from shutil import copyfileobj
-from typing import Sequence
 
 import pikepdf
 import PIL
 from pluggy import PluginManager
 
+from ocrmypdf._defaults import DEFAULT_LANGUAGE, DEFAULT_ROTATE_PAGES_THRESHOLD
 from ocrmypdf._exec import unpaper
 from ocrmypdf.exceptions import (
     BadArgsError,
@@ -28,20 +29,11 @@ from ocrmypdf.exceptions import (
     OutputFileAccessError,
 )
 from ocrmypdf.helpers import is_file_writable, monotonic, safe_symlink
-from ocrmypdf.hocrtransform import HOCR_OK_LANGS
 from ocrmypdf.subprocess import check_external_program
 
-# -------------
-# External dependencies
-
-DEFAULT_LANGUAGE = 'eng'  # Enforce English hegemony
-
 log = logging.getLogger(__name__)
 
 
-# --------
-
-
 def check_platform() -> None:
     if sys.maxsize <= 2**32:  # pragma: no cover
         log.warning(
@@ -62,6 +54,7 @@ def check_options_languages(
             log.debug("No language specified; assuming --language %s", DEFAULT_LANGUAGE)
     if not ocr_engine_languages:
         return
+
     missing_languages = set(options.languages) - set(ocr_engine_languages)
     if missing_languages:
         lang_text = '\n'.join(lang for lang in missing_languages)
@@ -83,15 +76,6 @@ def check_options_languages(
 
 
 def check_options_output(options: Namespace) -> None:
-    is_latin = set(options.languages).issubset(HOCR_OK_LANGS)
-
-    if options.pdf_renderer.startswith('hocr') and not is_latin:
-        log.warning(
-            "The 'hocr' PDF renderer is known to cause problems with one "
-            "or more of the languages in your document.  Use "
-            "`--pdf-renderer auto` (the default) to avoid this issue."
-        )
-
     if options.output_type == 'none' and options.output_file not in (os.devnull, '-'):
         raise BadArgsError(
             "Since you specified `--output-type none`, the output file "
@@ -99,6 +83,8 @@ def check_options_output(options: Namespace) -> None:
             f"`-` to suppress this message."
         )
 
+
+def set_lossless_reconstruction(options: Namespace) -> None:
     lossless_reconstruction = False
     if not any(
         (
@@ -138,6 +124,11 @@ def check_options_preprocessing(options: Namespace) -> None:
         options.clean = True
     if options.unpaper_args and not options.clean:
         raise BadArgsError("--clean is required for --unpaper-args")
+    if (
+        options.rotate_pages_threshold != DEFAULT_ROTATE_PAGES_THRESHOLD
+        and not options.rotate_pages
+    ):
+        raise BadArgsError("--rotate-pages is required for --rotate-pages-threshold")
     if options.clean:
         check_external_program(
             program='unpaper',
@@ -228,6 +219,7 @@ def _check_plugin_invariant_options(options: Namespace) -> None:
     check_platform()
     check_options_metadata(options)
     check_options_output(options)
+    set_lossless_reconstruction(options)
     check_options_sidecar(options)
     check_options_preprocessing(options)
     check_options_ocr_behavior(options)
@@ -245,6 +237,18 @@ 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
@@ -268,9 +272,9 @@ 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 "
+                    "\nDocker cannot access your working directory unless you "
                     "explicitly share it with the Docker container and set up"
                     "permissions correctly.\n"
                     "You may find it easier to use stdin/stdout:"
@@ -278,6 +282,15 @@ 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

@@ -10,24 +10,30 @@ import os
 import sys
 import threading
 from argparse import Namespace
+from collections.abc import Iterable, Sequence
 from enum import IntEnum
 from io import IOBase
 from pathlib import Path
-from typing import AnyStr, BinaryIO, Iterable, Union
+from typing import AnyStr, BinaryIO
 from warnings import warn
 
 import pluggy
 
 from ocrmypdf._logging import PageNumberFilter
+from ocrmypdf._pipelines.hocr_to_ocr_pdf import run_hocr_to_ocr_pdf_pipeline
+from ocrmypdf._pipelines.ocr import run_pipeline, run_pipeline_cli
+from ocrmypdf._pipelines.pdf_to_hocr import run_hocr_pipeline
 from ocrmypdf._plugin_manager import get_plugin_manager
-from ocrmypdf._sync import run_pipeline
 from ocrmypdf._validation import check_options
 from ocrmypdf.cli import ArgumentParser, get_parser
 from ocrmypdf.helpers import is_iterable_notstr
 
-StrPath = Union[Path, AnyStr]
-PathOrIO = Union[BinaryIO, StrPath]
+StrPath = Path | AnyStr
+PathOrIO = BinaryIO | StrPath
 
+# Installing plugins affects the global state of the Python interpreter,
+# so we need to use a lock to prevent multiple threads from installing
+# plugins at the same time.
 _api_lock = threading.Lock()
 
 
@@ -132,34 +138,19 @@ def configure_logging(
     return log
 
 
-def create_options(
-    *, input_file: PathOrIO, output_file: PathOrIO, parser: ArgumentParser, **kwargs
-) -> Namespace:
-    """Construct an options object from the input/output files and keyword arguments.
-
-    Args:
-        input_file: Input file path or file object.
-        output_file: Output file path or file object.
-        parser: ArgumentParser object.
-        **kwargs: Keyword arguments.
-
-    Returns:
-        argparse.Namespace: A Namespace object containing the parsed arguments.
-
-    Raises:
-        TypeError: If the type of a keyword argument is not supported.
-    """
+def _kwargs_to_cmdline(
+    *, defer_kwargs: set[str], **kwargs
+) -> tuple[list[str], dict[str, AnyStr]]:
+    """Convert kwargs to command line arguments."""
     cmdline = []
-    deferred = []
-
+    deferred = {}
     for arg, val in kwargs.items():
         if val is None:
             continue
 
-        # These arguments with special handling for which we bypass
-        # argparse
-        if arg in {'progress_bar', 'plugins'}:
-            deferred.append((arg, val))
+        # Skip arguments that are handled elsewhere
+        if arg in defer_kwargs:
+            deferred[arg] = val
             continue
 
         cmd_style_arg = arg.replace('_', '-')
@@ -178,7 +169,7 @@ def create_options(
 
         # We have a parameter
         cmdline.append(f"--{cmd_style_arg}")
-        if isinstance(val, (int, float)):
+        if isinstance(val, int | float):
             cmdline.append(str(val))
         elif isinstance(val, str):
             cmdline.append(val)
@@ -186,37 +177,65 @@ def create_options(
             cmdline.append(str(val))
         else:
             raise TypeError(f"{arg}: {val} ({type(val)})")
+    return cmdline, deferred
 
-    if isinstance(input_file, (BinaryIO, IOBase)):
+
+def create_options(
+    *, input_file: PathOrIO, output_file: PathOrIO, parser: ArgumentParser, **kwargs
+) -> Namespace:
+    """Construct an options object from the input/output files and keyword arguments.
+
+    Args:
+        input_file: Input file path or file object.
+        output_file: Output file path or file object.
+        parser: ArgumentParser object.
+        **kwargs: Keyword arguments.
+
+    Returns:
+        argparse.Namespace: A Namespace object containing the parsed arguments.
+
+    Raises:
+        TypeError: If the type of a keyword argument is not supported.
+    """
+    cmdline, deferred = _kwargs_to_cmdline(
+        defer_kwargs={'progress_bar', 'plugins', 'parser', 'input_file', 'output_file'},
+        **kwargs,
+    )
+    if isinstance(input_file, BinaryIO | IOBase):
         cmdline.append('stream://input_file')
     else:
         cmdline.append(os.fspath(input_file))
-    if isinstance(output_file, (BinaryIO, IOBase)):
+    if isinstance(output_file, BinaryIO | IOBase):
         cmdline.append('stream://output_file')
     else:
         cmdline.append(os.fspath(output_file))
+    if 'sidecar' in kwargs and isinstance(kwargs['sidecar'], BinaryIO | IOBase):
+        cmdline.append('--sidecar')
+        cmdline.append('stream://sidecar')
 
     parser.enable_api_mode()
     options = parser.parse_args(cmdline)
-    for keyword, val in deferred:
+    for keyword, val in deferred.items():
         setattr(options, keyword, val)
 
     if options.input_file == 'stream://input_file':
         options.input_file = input_file
     if options.output_file == 'stream://output_file':
         options.output_file = output_file
+    if options.sidecar == 'stream://sidecar':
+        options.sidecar = kwargs['sidecar']
 
     return options
 
 
-def ocr(  # noqa: ruff: disable=D417
+def ocr(  # noqa: D417
     input_file: PathOrIO,
     output_file: PathOrIO,
     *,
     language: Iterable[str] | None = None,
     image_dpi: int | None = None,
     output_type: str | None = None,
-    sidecar: StrPath | None = None,
+    sidecar: PathOrIO | None = None,
     jobs: int | None = None,
     use_threads: bool | None = None,
     title: str | None = None,
@@ -240,6 +259,7 @@ 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,
@@ -249,12 +269,16 @@ 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,
@@ -324,23 +348,21 @@ def ocr(  # noqa: ruff: disable=D417
 
     if not plugins:
         plugins = []
-    elif isinstance(plugins, (str, Path)):
+    elif isinstance(plugins, str | Path):
         plugins = [plugins]
     else:
         plugins = list(plugins)
 
     # No new variable names should be assigned until these two steps are run
-    create_options_kwargs = {k: v for k, v in locals().items() if k != 'kwargs'}
+    create_options_kwargs = {
+        k: v
+        for k, v in locals().items()
+        if k not in {'input_file', 'output_file', 'kwargs'}
+    }
     create_options_kwargs.update(kwargs)
 
     parser = get_parser()
-    create_options_kwargs['parser'] = parser
-
     with _api_lock:
-        # We can't allow multiple ocrmypdf.ocr() threads to run in parallel, because
-        # they might install different plugins, and generally speaking we have areas
-        # of code that use global state.
-
         if not plugin_manager:
             plugin_manager = get_plugin_manager(plugins)
         plugin_manager.hook.add_options(parser=parser)  # pylint: disable=no-member
@@ -348,9 +370,177 @@ def ocr(  # noqa: ruff: disable=D417
         if 'verbose' in kwargs:
             warn("ocrmypdf.ocr(verbose=) is ignored. Use ocrmypdf.configure_logging().")
 
-        options = create_options(**create_options_kwargs)
+        options = create_options(
+            input_file=input_file,
+            output_file=output_file,
+            parser=parser,
+            **create_options_kwargs,
+        )
         check_options(options, plugin_manager)
-        return run_pipeline(options=options, plugin_manager=plugin_manager, api=True)
+        return run_pipeline(options=options, plugin_manager=plugin_manager)
+
+
+def _pdf_to_hocr(  # noqa: D417
+    input_pdf: Path,
+    output_folder: Path,
+    *,
+    language: Iterable[str] | None = None,
+    image_dpi: int | None = None,
+    jobs: int | None = None,
+    use_threads: bool | None = None,
+    title: str | None = None,
+    author: str | None = None,
+    subject: str | None = None,
+    keywords: str | None = None,
+    rotate_pages: bool | None = None,
+    remove_background: bool | None = None,
+    deskew: bool | None = None,
+    clean: bool | None = None,
+    clean_final: bool | None = None,
+    unpaper_args: str | None = None,
+    oversample: int | None = None,
+    remove_vectors: bool | None = None,
+    force_ocr: bool | None = None,
+    skip_text: bool | None = None,
+    redo_ocr: bool | None = None,
+    skip_big: float | None = None,
+    pages: str | None = None,
+    max_image_mpixels: float | None = None,
+    tesseract_config: Iterable[str] | None = None,
+    tesseract_pagesegmode: int | None = None,
+    tesseract_oem: int | None = None,
+    tesseract_thresholding: int | None = None,
+    tesseract_timeout: float | None = None,
+    tesseract_non_ocr_timeout: float | None = None,
+    tesseract_downsample_above: int | None = None,
+    tesseract_downsample_large_images: bool | None = None,
+    rotate_pages_threshold: float | None = None,
+    user_words: os.PathLike | None = None,
+    user_patterns: os.PathLike | None = None,
+    continue_on_soft_render_error: bool | None = None,
+    invalidate_digital_signatures: bool | None = None,
+    plugin_manager=None,
+    plugins: Sequence[StrPath] | None = None,
+    keep_temporary_files: bool | None = None,
+    **kwargs,
+):
+    """Partially run OCRmyPDF and produces an output folder containing hOCR files.
+
+    Given a PDF file, this function will run OCRmyPDF up to the point where
+    the PDF is rasterized to images, OCRed, and the hOCR files are produced,
+    all of which are saved to the output folder. This is useful for applications
+    that want to provide an interface for users to edit the text before
+    rendering the final PDF.
+
+    Use :func:`hocr_to_ocr_pdf` to produce the final PDF.
+
+    For arguments not explicitly documented here, see documentation for the
+    equivalent command line parameter.
+
+    This API is **experimental** and subject to change.
+
+    Args:
+        input_pdf: Input PDF file path.
+        output_folder: Output folder path.
+        **kwargs: Keyword arguments.
+    """
+    # No new variable names should be assigned until these two steps are run
+    create_options_kwargs = {
+        k: v
+        for k, v in locals().items()
+        if k not in {'input_pdf', 'output_folder', 'kwargs'}
+    }
+    create_options_kwargs.update(kwargs)
+
+    parser = get_parser()
+
+    with _api_lock:
+        if not plugin_manager:
+            plugin_manager = get_plugin_manager(plugins)
+        plugin_manager.hook.add_options(parser=parser)  # pylint: disable=no-member
+
+        cmdline, deferred = _kwargs_to_cmdline(
+            defer_kwargs={'input_pdf', 'output_folder', 'plugins'},
+            **create_options_kwargs,
+        )
+        cmdline.append(str(input_pdf))
+        cmdline.append(str(output_folder))
+        parser.enable_api_mode()
+        options = parser.parse_args(cmdline)
+        for keyword, val in deferred.items():
+            setattr(options, keyword, val)
+        delattr(options, 'output_file')
+        setattr(options, 'output_folder', output_folder)
+
+        return run_hocr_pipeline(options=options, plugin_manager=plugin_manager)
+
+
+def _hocr_to_ocr_pdf(  # noqa: D417
+    work_folder: Path,
+    output_file: Path,
+    *,
+    jobs: int | None = None,
+    use_threads: bool | None = None,
+    optimize: int | None = None,
+    jpg_quality: int | None = None,
+    png_quality: int | None = None,
+    jbig2_lossy: bool | None = None,
+    jbig2_page_group_size: int | None = None,
+    jbig2_threshold: float | None = None,
+    pdfa_image_compression: str | None = None,
+    color_conversion_strategy: str | None = None,
+    fast_web_view: float | None = None,
+    plugin_manager=None,
+    plugins: Sequence[StrPath] | None = None,
+    **kwargs,
+):
+    """Run OCRmyPDF on a work folder and produce an output PDF.
+
+    After running :func:`pdf_to_hocr`, this function will run OCRmyPDF on the work
+    folder to produce an output PDF. This function consolidates any changes made
+    to the hOCR files in the work folder and produces a final PDF.
+
+    For arguments not explicitly documented here, see documentation for the
+    equivalent command line parameter.
+
+    This API is **experimental** and subject to change.
+
+    Args:
+        work_folder: Work folder path, as generated by :func:`pdf_to_hocr`.
+        output_file: Output PDF file path.
+        **kwargs: Keyword arguments.
+    """
+    # No new variable names should be assigned until these two steps are run
+    create_options_kwargs = {
+        k: v
+        for k, v in locals().items()
+        if k not in {'work_folder', 'output_pdf', 'kwargs'}
+    }
+    create_options_kwargs.update(kwargs)
+
+    parser = get_parser()
+
+    with _api_lock:
+        if not plugin_manager:
+            plugin_manager = get_plugin_manager(plugins)
+        plugin_manager.hook.add_options(parser=parser)  # pylint: disable=no-member
+
+        cmdline, deferred = _kwargs_to_cmdline(
+            defer_kwargs={'work_folder', 'output_file', 'plugins'},
+            **create_options_kwargs,
+        )
+        cmdline.append(str(work_folder))
+        cmdline.append(str(output_file))
+        parser.enable_api_mode()
+        options = parser.parse_args(cmdline)
+        for keyword, val in deferred.items():
+            setattr(options, keyword, val)
+        delattr(options, 'input_file')
+        setattr(options, 'work_folder', work_folder)
+
+        return run_hocr_to_ocr_pdf_pipeline(
+            options=options, plugin_manager=plugin_manager
+        )
 
 
 __all__ = [
@@ -363,4 +553,5 @@ __all__ = [
     'get_plugin_manager',
     'ocr',
     'run_pipeline',
+    'run_pipeline_cli',
 ]

src/ocrmypdf/builtin_plugins/concurrency.py

@@ -12,19 +12,23 @@ import queue
 import signal
 import sys
 import threading
+from collections.abc import Callable, Iterable
 from concurrent.futures import ProcessPoolExecutor, ThreadPoolExecutor, as_completed
 from contextlib import suppress
-from typing import Callable, Iterable, Type, Union
+from typing import Union
 
 from rich.console import Console as RichConsole
 
 from ocrmypdf import Executor, hookimpl
-from ocrmypdf._logging import RichLoggingHandler, RichTqdmProgressAdapter
+from ocrmypdf._logging import RichLoggingHandler
+from ocrmypdf._progressbar import RichProgressBar
 from ocrmypdf.exceptions import InputFileError
 from ocrmypdf.helpers import remove_all_log_handlers
 
-FuturesExecutorClass = Union[Type[ThreadPoolExecutor], Type[ProcessPoolExecutor]]
-Queue = Union[multiprocessing.Queue, queue.Queue]
+FuturesExecutorClass = Union[  # noqa: UP007
+    type[ThreadPoolExecutor], type[ProcessPoolExecutor]
+]
+Queue = Union[multiprocessing.Queue, queue.Queue]  # noqa: UP007
 UserInit = Callable[[], None]
 WorkerInit = Callable[[Queue, UserInit, int], None]
 
@@ -100,7 +104,7 @@ class StandardExecutor(Executor):
         *,
         use_threads: bool,
         max_workers: int,
-        tqdm_kwargs: dict,
+        progress_kwargs: dict,
         worker_initializer: Callable,
         task: Callable,
         task_arguments: Iterable,
@@ -118,15 +122,23 @@ class StandardExecutor(Executor):
         # Regardless of whether we use_threads for worker processes, the log_listener
         # must be a thread. Make sure we create the listener after the worker pool,
         # so that it does not get forked into the workers.
+        # If use_threads is False, we are currently guilty of creating a thread before
+        # forking on Linux, which is not recommended. However, we take a big
+        # performance hit in pdfinfo if we can't fork. Long term solution is to
+        # replace most of this with an asyncio implementation, and probably to
+        # migrate some of pdfinfo into C++ or Rust.
         listener = threading.Thread(target=log_listener, args=(log_queue,))
         listener.start()
 
-        with self.pbar_class(**tqdm_kwargs) as pbar, executor_class(
-            max_workers=max_workers,
-            initializer=initializer,
-            initargs=(log_queue, worker_initializer, logging.getLogger("").level),
-        ) as executor:
-            futures = [executor.submit(task, args) for args in task_arguments]
+        with (
+            self.pbar_class(**progress_kwargs) as pbar,
+            executor_class(
+                max_workers=max_workers,
+                initializer=initializer,
+                initargs=(log_queue, worker_initializer, logging.getLogger("").level),
+            ) as executor,
+        ):
+            futures = [executor.submit(task, *args) for args in task_arguments]
             try:
                 for future in as_completed(futures):
                     result = future.result()
@@ -166,10 +178,10 @@ RICH_CONSOLE = RichConsole(stderr=True)
 def get_progressbar_class():
     """Return the default progress bar class."""
 
-    def partial_RichTqdmProgressAdapter(*args, **kwargs):
-        return RichTqdmProgressAdapter(*args, **kwargs, console=RICH_CONSOLE)
+    def partial_RichProgressBar(*args, **kwargs):
+        return RichProgressBar(*args, **kwargs, console=RICH_CONSOLE)
 
-    return partial_RichTqdmProgressAdapter
+    return partial_RichProgressBar
 
 
 @hookimpl

src/ocrmypdf/builtin_plugins/default_filters.py

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

src/ocrmypdf/builtin_plugins/ghostscript.py

@@ -6,6 +6,8 @@ from __future__ import annotations
 
 import logging
 
+from packaging.version import Version
+
 from ocrmypdf import hookimpl
 from ocrmypdf._exec import ghostscript
 from ocrmypdf.exceptions import MissingDependencyError
@@ -15,7 +17,7 @@ log = logging.getLogger(__name__)
 
 # Currently all blacklisted versions are lower than 9.55, so none need to
 # be added here. If a future version is blacklisted, add it here.
-BLACKLISTED_GS_VERSIONS: frozenset[str] = frozenset()
+BLACKLISTED_GS_VERSIONS: frozenset[Version] = frozenset()
 
 
 @hookimpl
@@ -52,14 +54,24 @@ def check_options(options):
         program='gs',
         package='ghostscript',
         version_checker=ghostscript.version,
-        need_version='9.55',  # Ubuntu 22.04's version
+        need_version='9.54',  # RHEL 9's version; Ubuntu 22.04 has 9.55
     )
     gs_version = ghostscript.version()
     if gs_version in BLACKLISTED_GS_VERSIONS:
         raise MissingDependencyError(
             f"Ghostscript {gs_version} contains serious regressions and is not "
-            "supported. Please upgrade to a newer version, or downgrade to the "
-            "previous version."
+            "supported. Please upgrade to a newer version."
+        )
+    if Version('10.0.0') <= gs_version < Version('10.02.1') and (
+        options.skip_text or options.redo_ocr
+    ):
+        raise MissingDependencyError(
+            f"Ghostscript 10.0.0 through 10.02.0 (your version: {gs_version}) "
+            "contain serious regressions that corrupt PDFs with existing text, "
+            "such as those processed using --skip-text or --redo-ocr. "
+            "Please upgrade to a "
+            "newer version, or use --output-type pdf to avoid Ghostscript, or "
+            "use --force-ocr to discard existing text."
         )
 
     if options.output_type == 'pdfa':
@@ -117,7 +129,7 @@ def generate_pdfa(
 ):
     """Generate a PDF/A from the list of PDF pages and PDF/A metadata."""
     ghostscript.generate_pdfa(
-        pdf_pages=[*pdf_pages, pdfmark],
+        pdf_pages=[pdfmark, *pdf_pages],
         output_file=output_file,
         compression=context.options.pdfa_image_compression,
         color_conversion_strategy=context.options.color_conversion_strategy,

src/ocrmypdf/builtin_plugins/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

src/ocrmypdf/builtin_plugins/tesseract_ocr.py

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

src/ocrmypdf/cli.py

@@ -6,8 +6,10 @@
 from __future__ import annotations
 
 import argparse
-from typing import Any, Callable, Mapping, TypeVar
+from collections.abc import Callable, Mapping
+from typing import Any, TypeVar
 
+from ocrmypdf._defaults import DEFAULT_ROTATE_PAGES_THRESHOLD
 from ocrmypdf._version import PROGRAM_NAME as _PROGRAM_NAME
 from ocrmypdf._version import __version__ as _VERSION
 
@@ -192,8 +194,8 @@ Online documentation is located at:
         help="Choose output type. 'pdfa' creates a PDF/A-2b compliant file for "
         "long term archiving (default, recommended) but may not suitable "
         "for users who want their file altered as little as possible. 'pdfa' "
-        "also has problems with full Unicode text. 'pdf' attempts to "
-        "preserve file contents as much as possible. 'pdf-a1' creates a "
+        "also has problems with full Unicode text. 'pdf' minimizes changes "
+        "to the input file. 'pdf-a1' creates a "
         "PDF/A1-b file. 'pdf-a2' is equivalent to 'pdfa'. 'pdf-a3' creates a "
         "PDF/A3-b file. 'none' will produce no output, which may be helpful if "
         "only the --sidecar is desired.",
@@ -389,7 +391,7 @@ Online documentation is located at:
         action='store',
         type=numeric(float, 0),
         metavar='MPixels',
-        help="Set maximum number of pixels to unpack before treating an image as a "
+        help="Set maximum number of megapixels to unpack before treating an image as a "
         "decompression bomb",
         default=250.0,
     )
@@ -402,7 +404,7 @@ Online documentation is located at:
     )
     advanced.add_argument(
         '--rotate-pages-threshold',
-        default=14.0,
+        default=DEFAULT_ROTATE_PAGES_THRESHOLD,
         type=numeric(float, 0, 1000),
         metavar='CONFIDENCE',
         help="Only rotate pages when confidence is above this value (arbitrary "

src/ocrmypdf/exceptions.py

@@ -108,10 +108,16 @@ class EncryptedPdfError(ExitCodeException):
     )
 
 
-class DigitalSignatureError(ExitCodeException):
+class TesseractConfigError(ExitCodeException):
+    """Tesseract config can't be parsed."""
+
+    exit_code = ExitCode.invalid_config
+    message = "Error occurred while parsing a Tesseract configuration file"
+
+
+class DigitalSignatureError(InputFileError):
     """PDF has a digital signature."""
 
-    exit_code = ExitCode.input_file
     message = dedent(
         """\
         Input PDF has a digital signature. OCR would alter the document,
@@ -120,8 +126,27 @@ class DigitalSignatureError(ExitCodeException):
     )
 
 
-class TesseractConfigError(ExitCodeException):
-    """Tesseract config can't be parsed."""
+class TaggedPDFError(InputFileError):
+    """PDF is tagged."""
 
-    exit_code = ExitCode.invalid_config
-    message = "Error occurred while parsing a Tesseract configuration file"
+    message = dedent(
+        """\
+        This PDF is marked as a Tagged PDF. This often indicates
+        that the PDF was generated from an office document and does
+        not need OCR. Use --force-ocr, --skip-text or --redo-ocr to
+        override this error.
+        """
+    )
+
+
+class ColorConversionNeededError(BadArgsError):
+    """PDF needs color conversion."""
+
+    message = dedent(
+        """\
+        The input PDF has an unusual color space. Use
+        --color-conversion-strategy to convert to a common color space
+        such as RGB, or use --output-type pdf to skip PDF/A conversion
+        and retain the original color space.
+        """
+    )

src/ocrmypdf/extra_plugins/semfree.py

@@ -20,12 +20,12 @@ from __future__ import annotations
 import logging
 import logging.handlers
 import signal
+from collections.abc import Callable, Iterable, Iterator
 from contextlib import suppress
 from enum import Enum, auto
 from itertools import islice, repeat, takewhile, zip_longest
 from multiprocessing import Pipe, Process
 from multiprocessing.connection import Connection, wait
-from typing import Callable, Iterable, Iterator
 
 from ocrmypdf import Executor, hookimpl
 from ocrmypdf._concurrent import NullProgressBar
@@ -93,7 +93,7 @@ def process_loop(
 
     for args in task_args:
         try:
-            result = task(args)
+            result = task(*args)
         except Exception as e:  # pylint: disable=broad-except
             conn.send((MessageType.exception, e))
             break
@@ -113,16 +113,16 @@ class LambdaExecutor(Executor):
         *,
         use_threads: bool,
         max_workers: int,
-        tqdm_kwargs: dict,
+        progress_kwargs: dict,
         worker_initializer: Callable,
         task: Callable,
         task_arguments: Iterable,
         task_finished: Callable,
     ):
         if use_threads and max_workers == 1:
-            with self.pbar_class(**tqdm_kwargs) as pbar:
+            with self.pbar_class(**progress_kwargs) as pbar:
                 for args in task_arguments:
-                    result = task(args)
+                    result = task(*args)
                     task_finished(result, pbar)
             return
 
@@ -156,7 +156,7 @@ class LambdaExecutor(Executor):
         for process in processes:
             process.start()
 
-        with self.pbar_class(**tqdm_kwargs) as pbar:
+        with self.pbar_class(**progress_kwargs) as pbar:
             while connections:
                 for result in wait(connections):
                     if not isinstance(result, Connection):

src/ocrmypdf/helpers.py

@@ -10,7 +10,7 @@ import multiprocessing
 import os
 import shutil
 import warnings
-from collections.abc import Iterable
+from collections.abc import Callable, Iterable, Sequence
 from contextlib import suppress
 from decimal import Decimal
 from io import StringIO
@@ -19,16 +19,13 @@ from pathlib import Path
 from statistics import harmonic_mean
 from typing import (
     Any,
-    Callable,
     Generic,
-    Sequence,
-    SupportsFloat,
-    SupportsRound,
     TypeVar,
 )
 
 import img2pdf
 import pikepdf
+from deprecation import deprecated
 
 log = logging.getLogger(__name__)
 
@@ -139,6 +136,7 @@ class Resolution(Generic[T]):
         return self._isclose(self.x, other.x) and self._isclose(self.y, other.y)
 
 
+@deprecated(deprecated_in='15.4.0')
 class NeverRaise(Exception):
     """An exception that is never raised."""
 
@@ -270,7 +268,9 @@ def check_pdf(input_file: Path) -> bool:
         return False
     else:
         with pdf:
-            messages = pdf.check()
+            with warnings.catch_warnings():
+                warnings.filterwarnings('ignore', message=r'pikepdf.*JBIG2.*')
+                messages = pdf.check()
             success = True
             for msg in messages:
                 if 'error' in msg.lower():
@@ -322,10 +322,16 @@ def remove_all_log_handlers(logger: logging.Logger) -> None:
 
 
 def pikepdf_enable_mmap() -> None:
-    """Enable pikepdf mmap."""
+    """Enable pikepdf memory mapping."""
     try:
-        if pikepdf._core.set_access_default_mmap(True):
-            log.debug("pikepdf mmap enabled")
+        pikepdf._core.set_access_default_mmap(True)
+        log.debug(
+            "pikepdf mmap "
+            + (
+                'enabled'
+                if pikepdf._core.get_access_default_mmap()  # type: ignore[attr-defined]
+                else 'disabled'
+            )
+        )
     except AttributeError:
         log.debug("pikepdf mmap not available")
-    log.debug("pikepdf mmap disabled")

src/ocrmypdf/hocrtransform.py

@@ -1,461 +0,0 @@
-#!/usr/bin/env python3
-# SPDX-FileCopyrightText: 2010 Jonathan Brinley
-# SPDX-FileCopyrightText: 2013-2014 Julien Pfefferkorn
-# SPDX-FileCopyrightText: 2022 James R. Barlow
-# SPDX-License-Identifier: MIT
-
-"""Transform .hocr and page image to text PDF."""
-
-from __future__ import annotations
-
-import argparse
-import os
-import re
-import warnings
-from math import atan, cos, sin
-from pathlib import Path
-from typing import Any, NamedTuple
-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.*"
-    )
-    from reportlab.lib.colors import black, cyan, magenta, red
-    from reportlab.lib.units import inch
-    from reportlab.pdfgen.canvas import Canvas
-
-# According to Wikipedia these languages are supported in the ISO-8859-1 character
-# set, meaning reportlab can generate them and they are compatible with hocr,
-# assuming Tesseract has the necessary languages installed. Note that there may
-# not be language packs for them.
-HOCR_OK_LANGS = frozenset(
-    [
-        # Languages fully covered by Latin-1:
-        'afr',  # Afrikaans
-        'alb',  # Albanian
-        'ast',  # Leonese
-        'baq',  # Basque
-        'bre',  # Breton
-        'cos',  # Corsican
-        'eng',  # English
-        'eus',  # Basque
-        'fao',  # Faoese
-        'gla',  # Scottish Gaelic
-        'glg',  # Galician
-        'glv',  # Manx
-        'ice',  # Icelandic
-        'ind',  # Indonesian
-        'isl',  # Icelandic
-        'ita',  # Italian
-        'ltz',  # Luxembourgish
-        'mal',  # Malay Rumi
-        'mga',  # Irish
-        'nor',  # Norwegian
-        'oci',  # Occitan
-        'por',  # Portugeuse
-        'roh',  # Romansh
-        'sco',  # Scots
-        'sma',  # Sami
-        'spa',  # Spanish
-        'sqi',  # Albanian
-        'swa',  # Swahili
-        'swe',  # Swedish
-        'tgl',  # Tagalog
-        'wln',  # Walloon
-        # Languages supported by Latin-1 except for a few rare characters that OCR
-        # is probably not trained to recognize anyway:
-        'cat',  # Catalan
-        'cym',  # Welsh
-        'dan',  # Danish
-        'deu',  # German
-        'dut',  # Dutch
-        'est',  # Estonian
-        'fin',  # Finnish
-        'fra',  # French
-        'hun',  # Hungarian
-        'kur',  # Kurdish
-        'nld',  # Dutch
-        'wel',  # Welsh
-    ]
-)
-
-
-Element = ElementTree.Element
-
-
-class Rect(NamedTuple):
-    """A rectangle for managing PDF coordinates."""
-
-    x1: Any
-    y1: Any
-    x2: Any
-    y2: Any
-
-
-class HocrTransformError(Exception):
-    """Error while applying hOCR transform."""
-
-
-class HocrTransform:
-    """A class for converting documents from the hOCR format.
-
-    For details of the hOCR format, see:
-    http://kba.cloud/hocr-spec/.
-    """
-
-    box_pattern = re.compile(r'bbox((\s+\d+){4})')
-    baseline_pattern = re.compile(
-        r'''
-        baseline \s+
-        ([\-\+]?\d*\.?\d*) \s+  # +/- decimal float
-        ([\-\+]?\d+)            # +/- int''',
-        re.VERBOSE,
-    )
-    ligatures = str.maketrans(
-        {'ff': 'ff', 'ffi': 'f‌f‌i', 'ffl': 'f‌f‌l', 'fi': 'fi', 'fl': 'fl'}
-    )
-
-    def __init__(self, *, hocr_filename: str | Path, dpi: float):
-        """Initialize the HocrTransform object."""
-        self.dpi = dpi
-        self.hocr = ElementTree.parse(os.fspath(hocr_filename))
-
-        # if the hOCR file has a namespace, ElementTree requires its use to
-        # find elements
-        matches = re.match(r'({.*})html', self.hocr.getroot().tag)
-        self.xmlns = ''
-        if matches:
-            self.xmlns = matches.group(1)
-
-        # get dimension in pt (not pixel!!!!) of the OCRed image
-        self.width, self.height = None, None
-        for div in self.hocr.findall(self._child_xpath('div', 'ocr_page')):
-            coords = self.element_coordinates(div)
-            pt_coords = self.pt_from_pixel(coords)
-            self.width = pt_coords.x2 - pt_coords.x1
-            self.height = pt_coords.y2 - pt_coords.y1
-            # there shouldn't be more than one, and if there is, we don't want
-            # it
-            break
-        if self.width is None or self.height is None:
-            raise HocrTransformError("hocr file is missing page dimensions")
-
-    def __str__(self):  # pragma: no cover
-        """Return the textual content of the HTML body."""
-        if self.hocr is None:
-            return ''
-        body = self.hocr.find(self._child_xpath('body'))
-        if body:
-            return self._get_element_text(body)
-        else:
-            return ''
-
-    def _get_element_text(self, element: Element):
-        """Return the textual content of the element and its children."""
-        text = ''
-        if element.text is not None:
-            text += element.text
-        for child in element:
-            text += self._get_element_text(child)
-        if element.tail is not None:
-            text += element.tail
-        return text
-
-    @classmethod
-    def element_coordinates(cls, element: Element) -> Rect:
-        """Get coordinates of the bounding box around an element."""
-        out = Rect._make(0 for _ in range(4))
-        if 'title' in element.attrib:
-            matches = cls.box_pattern.search(element.attrib['title'])
-            if matches:
-                coords = matches.group(1).split()
-                out = Rect._make(int(coords[n]) for n in range(4))
-        return out
-
-    @classmethod
-    def baseline(cls, element: Element) -> tuple[float, float]:
-        """Get baseline's slope and intercept."""
-        if 'title' in element.attrib:
-            matches = cls.baseline_pattern.search(element.attrib['title'])
-            if matches:
-                return float(matches.group(1)), int(matches.group(2))
-        return (0.0, 0.0)
-
-    def pt_from_pixel(self, pxl) -> Rect:
-        """Returns the quantity in PDF units (pt) given quantity in pixels."""
-        return Rect._make((c / self.dpi * inch) for c in pxl)
-
-    def _child_xpath(self, html_tag: str, html_class: str | None = None) -> str:
-        xpath = f".//{self.xmlns}{html_tag}"
-        if html_class:
-            xpath += f"[@class='{html_class}']"
-        return xpath
-
-    @classmethod
-    def replace_unsupported_chars(cls, s: str) -> str:
-        """Replaces characters with those available in the Helvetica typeface."""
-        return s.translate(cls.ligatures)
-
-    def to_pdf(
-        self,
-        *,
-        out_filename: Path,
-        image_filename: Path | None = None,
-        show_bounding_boxes: bool = False,
-        fontname: str = "Helvetica",
-        invisible_text: bool = False,
-        interword_spaces: bool = False,
-    ) -> None:
-        """Creates a PDF file with an image superimposed on top of the text.
-
-        Text is positioned according to the bounding box of the lines in
-        the hOCR file.
-        The image need not be identical to the image used to create the hOCR
-        file.
-        It can have a lower resolution, different color mode, etc.
-
-        Arguments:
-            out_filename: Path of PDF to write.
-            image_filename: Image to use for this file. If omitted, the OCR text
-                is shown.
-            show_bounding_boxes: Show bounding boxes around various text regions,
-                for debugging.
-            fontname: Name of font to use.
-            invisible_text: If True, text is rendered invisible so that is
-                selectable but never drawn. If False, text is visible and may
-                be seen if the image is skipped or deleted in Acrobat.
-            interword_spaces: If True, insert spaces between words rather than
-                drawing each word without spaces. Generally this improves text
-                extraction.
-        """
-        # create the PDF file
-        # page size in points (1/72 in.)
-        pdf = Canvas(
-            os.fspath(out_filename),
-            pagesize=(self.width, self.height),
-            pageCompression=1,
-        )
-
-        # draw bounding box for each paragraph
-        # light blue for bounding box of paragraph
-        pdf.setStrokeColor(cyan)
-        # light blue for bounding box of paragraph
-        pdf.setFillColor(cyan)
-        pdf.setLineWidth(0)  # no line for bounding box
-        for elem in self.hocr.iterfind(self._child_xpath('p', 'ocr_par')):
-            elemtxt = self._get_element_text(elem).rstrip()
-            if len(elemtxt) == 0:
-                continue
-
-            pxl_coords = self.element_coordinates(elem)
-            pt = self.pt_from_pixel(pxl_coords)  # pylint: disable=invalid-name
-
-            # draw the bbox border
-            if show_bounding_boxes:  # pragma: no cover
-                pdf.rect(
-                    pt.x1, self.height - pt.y2, pt.x2 - pt.x1, pt.y2 - pt.y1, fill=1
-                )
-
-        found_lines = False
-        for line in (
-            element
-            for element in self.hocr.iterfind(self._child_xpath('span'))
-            if 'class' in element.attrib
-            and element.attrib['class'] in {'ocr_header', 'ocr_line', 'ocr_textfloat'}
-        ):
-            found_lines = True
-            self._do_line(
-                pdf,
-                line,
-                "ocrx_word",
-                fontname,
-                invisible_text,
-                interword_spaces,
-                show_bounding_boxes,
-            )
-
-        if not found_lines:
-            # Tesseract did not report any lines (just words)
-            root = self.hocr.find(self._child_xpath('div', 'ocr_page'))
-            self._do_line(
-                pdf,
-                root,
-                "ocrx_word",
-                fontname,
-                invisible_text,
-                interword_spaces,
-                show_bounding_boxes,
-            )
-        # put the image on the page, scaled to fill the page
-        if image_filename is not None:
-            pdf.drawImage(
-                os.fspath(image_filename), 0, 0, width=self.width, height=self.height
-            )
-
-        # finish up the page and save it
-        pdf.showPage()
-        pdf.save()
-
-    @classmethod
-    def polyval(cls, poly, x):  # pragma: no cover
-        """Calculate the value of a polynomial at a point."""
-        return x * poly[0] + poly[1]
-
-    def _do_line(
-        self,
-        pdf: Canvas,
-        line: Element | None,
-        elemclass: str,
-        fontname: str,
-        invisible_text: bool,
-        interword_spaces: bool,
-        show_bounding_boxes: bool,
-    ):
-        if line is None:
-            return
-        pxl_line_coords = self.element_coordinates(line)
-        line_box = self.pt_from_pixel(pxl_line_coords)
-        line_height = line_box.y2 - line_box.y1
-
-        slope, pxl_intercept = self.baseline(line)
-        if abs(slope) < 0.005:
-            slope = 0.0
-        angle = atan(slope)
-        cos_a, sin_a = cos(angle), sin(angle)
-
-        text = pdf.beginText()
-        intercept = pxl_intercept / self.dpi * inch
-
-        # Don't allow the font to break out of the bounding box. Division by
-        # cos_a accounts for extra clearance between the glyph's vertical axis
-        # on a sloped baseline and the edge of the bounding box.
-        fontsize = (line_height - abs(intercept)) / cos_a
-        text.setFont(fontname, fontsize)
-        if invisible_text:
-            text.setTextRenderMode(3)  # Invisible (indicates OCR text)
-
-        # Intercept is normally negative, so this places it above the bottom
-        # of the line box
-        baseline_y2 = self.height - (line_box.y2 + intercept)
-
-        if show_bounding_boxes:  # pragma: no cover
-            # draw the baseline in magenta, dashed
-            pdf.setDash()
-            pdf.setStrokeColor(magenta)
-            pdf.setLineWidth(0.5)
-            # negate slope because it is defined as a rise/run in pixel
-            # coordinates and page coordinates have the y axis flipped
-            pdf.line(
-                line_box.x1,
-                baseline_y2,
-                line_box.x2,
-                self.polyval((-slope, baseline_y2), line_box.x2 - line_box.x1),
-            )
-            # light green for bounding box of word/line
-            pdf.setDash(6, 3)
-            pdf.setStrokeColor(red)
-
-        text.setTextTransform(cos_a, -sin_a, sin_a, cos_a, line_box.x1, baseline_y2)
-        pdf.setFillColor(black)  # text in black
-
-        elements = line.findall(self._child_xpath('span', elemclass))
-        for elem in elements:
-            elemtxt = self._get_element_text(elem).strip()
-            elemtxt = self.replace_unsupported_chars(elemtxt)
-            if elemtxt == '':
-                continue
-
-            pxl_coords = self.element_coordinates(elem)
-            box = self.pt_from_pixel(pxl_coords)
-            if interword_spaces:
-                # if  `--interword-spaces` is true, append a space
-                # to the end of each text element to allow simpler PDF viewers
-                # such as PDF.js to better recognize words in search and copy
-                # and paste. Do not remove space from last word in line, even
-                # though it would look better, because it will interfere with
-                # naive text extraction. \n does not work either.
-                elemtxt += ' '
-                box = Rect._make(
-                    (
-                        box.x1,
-                        line_box.y1,
-                        box.x2 + pdf.stringWidth(' ', fontname, line_height),
-                        line_box.y2,
-                    )
-                )
-            box_width = box.x2 - box.x1
-            font_width = pdf.stringWidth(elemtxt, fontname, fontsize)
-
-            # draw the bbox border
-            if show_bounding_boxes:  # pragma: no cover
-                pdf.rect(
-                    box.x1, self.height - line_box.y2, box_width, line_height, fill=0
-                )
-
-            # Adjust relative position of cursor
-            # This is equivalent to:
-            #   text.setTextOrigin(pt.x1, self.height - line_box.y2)
-            # but the former generates a full text reposition matrix (Tm) in the
-            # content stream while this issues a "offset" (Td) command.
-            # .moveCursor() is relative to start of the text line, where the
-            # "text line" means whatever reportlab defines it as. Do not use
-            # use .getCursor(), since moveCursor() rather unintuitively plans
-            # its moves relative to .getStartOfLine().
-            # For skewed lines, in the text transform we set up a rotated
-            # coordinate system, so we don't have to account for the
-            # incremental offset. Surprisingly most PDF viewers can handle this.
-            cursor = text.getStartOfLine()
-            dx = box.x1 - cursor[0]
-            dy = baseline_y2 - cursor[1]
-            text.moveCursor(dx, dy)
-
-            # If reportlab tells us this word is 0 units wide, our best seems
-            # to be to suppress this text
-            if font_width > 0:
-                text.setHorizScale(100 * box_width / font_width)
-                text.textOut(elemtxt)
-        pdf.drawText(text)
-
-
-if __name__ == "__main__":
-    parser = argparse.ArgumentParser(description='Convert hocr file to PDF')
-    parser.add_argument(
-        '-b',
-        '--boundingboxes',
-        action="store_true",
-        default=False,
-        help='Show bounding boxes borders',
-    )
-    parser.add_argument(
-        '-r',
-        '--resolution',
-        type=int,
-        default=300,
-        help='Resolution of the image that was OCRed',
-    )
-    parser.add_argument(
-        '-i',
-        '--image',
-        default=None,
-        help='Path to the image to be placed above the text',
-    )
-    parser.add_argument(
-        '--interword-spaces',
-        action='store_true',
-        default=False,
-        help='Add spaces between words',
-    )
-    parser.add_argument('hocrfile', help='Path to the hocr file to be parsed')
-    parser.add_argument('outputfile', help='Path to the PDF file to be generated')
-    args = parser.parse_args()
-
-    hocr = HocrTransform(hocr_filename=args.hocrfile, dpi=args.resolution)
-    hocr.to_pdf(
-        out_filename=args.outputfile,
-        image_filename=args.image,
-        show_bounding_boxes=args.boundingboxes,
-        interword_spaces=args.interword_spaces,
-    )

src/ocrmypdf/hocrtransform/__init__.py

@@ -0,0 +1,18 @@
+# SPDX-FileCopyrightText: 2023 James R. Barlow
+# SPDX-License-Identifier: MIT
+
+"""Transform .hocr and page image to text PDF."""
+
+from __future__ import annotations
+
+from ocrmypdf.hocrtransform._hocr import (
+    DebugRenderOptions,
+    HocrTransform,
+    HocrTransformError,
+)
+
+__all__ = (
+    'HocrTransform',
+    'HocrTransformError',
+    'DebugRenderOptions',
+)

src/ocrmypdf/hocrtransform/__main__.py

@@ -0,0 +1,40 @@
+# SPDX-FileCopyrightText: 2023 James R. Barlow
+# SPDX-License-Identifier: MIT
+
+"""Simple CLI for testing HOCR."""
+
+import argparse
+
+from ocrmypdf.hocrtransform import HocrTransform
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser(description='Convert hocr file to PDF')
+    parser.add_argument(
+        '-b',
+        '--boundingboxes',
+        action="store_true",
+        default=False,
+        help='Show bounding boxes borders',
+    )
+    parser.add_argument(
+        '-r',
+        '--resolution',
+        type=int,
+        default=300,
+        help='Resolution of the image that was OCRed',
+    )
+    parser.add_argument(
+        '-i',
+        '--image',
+        default=None,
+        help='Path to the image to be placed above the text',
+    )
+    parser.add_argument('hocrfile', help='Path to the hocr file to be parsed')
+    parser.add_argument('outputfile', help='Path to the PDF file to be generated')
+    args = parser.parse_args()
+
+    hocr = HocrTransform(hocr_filename=args.hocrfile, dpi=args.resolution)
+    hocr.to_pdf(
+        out_filename=args.outputfile,
+        image_filename=args.image,
+    )

src/ocrmypdf/hocrtransform/_font.py

@@ -0,0 +1,141 @@
+# SPDX-FileCopyrightText: 2023 James R. Barlow
+# SPDX-License-Identifier: MPL-2.0
+
+from __future__ import annotations
+
+import logging
+import unicodedata
+import zlib
+from importlib.resources import files as package_files
+
+from pikepdf import (
+    Dictionary,
+    Name,
+    Pdf,
+)
+from pikepdf.canvas import Font
+
+log = logging.getLogger(__name__)
+
+
+class EncodableFont(Font):
+    def text_encode(self, text: str) -> bytes:
+        raise NotImplementedError()
+
+
+class GlyphlessFont(EncodableFont):
+    CID_TO_GID_DATA = zlib.compress(b"\x00\x01" * 65536)
+    GLYPHLESS_FONT_NAME = 'pdf.ttf'
+    GLYPHLESS_FONT = (package_files('ocrmypdf.data') / GLYPHLESS_FONT_NAME).read_bytes()
+    CHAR_ASPECT = 2
+
+    def __init__(self):
+        pass
+
+    def text_width(self, text: str, fontsize: float) -> float:
+        """Estimate the width of a text string when rendered with the given font."""
+        # NFKC: split ligatures, combine diacritics
+        return len(unicodedata.normalize("NFKC", text)) * (fontsize / self.CHAR_ASPECT)
+
+    def text_encode(self, text: str) -> bytes:
+        return text.encode('utf-16be')
+
+    def register(self, pdf: Pdf):
+        """Register the glyphless font.
+
+        Create several data structures in the Pdf to describe the font. While it create
+        the data, a reference should be set in at least one page's /Resources dictionary
+        to retain the font in the output PDF and ensure it is usable on that page.
+        """
+        PLACEHOLDER = Name.Placeholder
+
+        basefont = pdf.make_indirect(
+            Dictionary(
+                BaseFont=Name.GlyphLessFont,
+                DescendantFonts=[PLACEHOLDER],
+                Encoding=Name("/Identity-H"),
+                Subtype=Name.Type0,
+                ToUnicode=PLACEHOLDER,
+                Type=Name.Font,
+            )
+        )
+        cid_font_type2 = pdf.make_indirect(
+            Dictionary(
+                BaseFont=Name.GlyphLessFont,
+                CIDToGIDMap=PLACEHOLDER,
+                CIDSystemInfo=Dictionary(
+                    Ordering="Identity",
+                    Registry="Adobe",
+                    Supplement=0,
+                ),
+                FontDescriptor=PLACEHOLDER,
+                Subtype=Name.CIDFontType2,
+                Type=Name.Font,
+                DW=1000 // self.CHAR_ASPECT,
+            )
+        )
+        basefont.DescendantFonts = [cid_font_type2]
+        cid_font_type2.CIDToGIDMap = pdf.make_stream(
+            self.CID_TO_GID_DATA, Filter=Name.FlateDecode
+        )
+        basefont.ToUnicode = pdf.make_stream(
+            b"/CIDInit /ProcSet findresource begin\n"
+            b"12 dict begin\n"
+            b"begincmap\n"
+            b"/CIDSystemInfo\n"
+            b"<<\n"
+            b"  /Registry (Adobe)\n"
+            b"  /Ordering (UCS)\n"
+            b"  /Supplement 0\n"
+            b">> def\n"
+            b"/CMapName /Adobe-Identify-UCS def\n"
+            b"/CMapType 2 def\n"
+            b"1 begincodespacerange\n"
+            b"<0000> <FFFF>\n"
+            b"endcodespacerange\n"
+            b"1 beginbfrange\n"
+            b"<0000> <FFFF> <0000>\n"
+            b"endbfrange\n"
+            b"endcmap\n"
+            b"CMapName currentdict /CMap defineresource pop\n"
+            b"end\n"
+            b"end\n"
+        )
+        font_descriptor = pdf.make_indirect(
+            Dictionary(
+                Ascent=1000,
+                CapHeight=1000,
+                Descent=-1,
+                Flags=5,  # Fixed pitch and symbolic
+                FontBBox=[0, 0, 1000 // self.CHAR_ASPECT, 1000],
+                FontFile2=PLACEHOLDER,
+                FontName=Name.GlyphLessFont,
+                ItalicAngle=0,
+                StemV=80,
+                Type=Name.FontDescriptor,
+            )
+        )
+        font_descriptor.FontFile2 = pdf.make_stream(self.GLYPHLESS_FONT)
+        cid_font_type2.FontDescriptor = font_descriptor
+        return basefont
+
+
+class Courier(EncodableFont):
+    """Courier font."""
+
+    def text_width(self, text: str, fontsize: float) -> float:
+        """Estimate the width of a text string when rendered with the given font."""
+        return len(text) * fontsize
+
+    def text_encode(self, text: str) -> bytes:
+        return text.encode('pdfdoc', errors='ignore')
+
+    def register(self, pdf: Pdf) -> Dictionary:
+        """Register the font."""
+        return pdf.make_indirect(
+            Dictionary(
+                BaseFont=Name.Courier,
+                Type=Name.Font,
+                Subtype=Name.Type1,
+            )
+        )

src/ocrmypdf/hocrtransform/_hocr.py

@@ -0,0 +1,501 @@
+# SPDX-FileCopyrightText: 2010 Jonathan Brinley
+# SPDX-FileCopyrightText: 2013-2014 Julien Pfefferkorn
+# SPDX-FileCopyrightText: 2023 James R. Barlow
+# SPDX-License-Identifier: MIT
+
+"""hOCR transform implementation."""
+
+from __future__ import annotations
+
+import logging
+import os
+import re
+import unicodedata
+from dataclasses import dataclass
+from itertools import pairwise
+from math import atan, cos, pi
+from pathlib import Path
+from xml.etree import ElementTree
+
+from pikepdf import Matrix, Name, Rectangle
+from pikepdf.canvas import (
+    BLACK,
+    BLUE,
+    CYAN,
+    DARKGREEN,
+    GREEN,
+    MAGENTA,
+    RED,
+    Canvas,
+    Text,
+    TextDirection,
+)
+
+from ocrmypdf.hocrtransform._font import EncodableFont as Font
+from ocrmypdf.hocrtransform._font import GlyphlessFont
+
+log = logging.getLogger(__name__)
+
+INCH = 72.0
+
+Element = ElementTree.Element
+
+
+@dataclass
+class DebugRenderOptions:
+    """A class for managing rendering options."""
+
+    render_paragraph_bbox: bool = False
+    render_baseline: bool = False
+    render_triangle: bool = False
+    render_line_bbox: bool = False
+    render_word_bbox: bool = False
+    render_space_bbox: bool = False
+
+
+class HocrTransformError(Exception):
+    """Error while applying hOCR transform."""
+
+
+class HocrTransform:
+    """A class for converting documents from the hOCR format.
+
+    For details of the hOCR format, see:
+    http://kba.github.io/hocr-spec/1.2/.
+    """
+
+    box_pattern = re.compile(
+        r'''
+        bbox \s+
+        (\d+) \s+   # left: uint
+        (\d+) \s+   # top: uint
+        (\d+) \s+   # right: uint
+        (\d+)       # bottom: uint
+        ''',
+        re.VERBOSE,
+    )
+    baseline_pattern = re.compile(
+        r'''
+        baseline \s+
+        ([\-\+]?\d*\.?\d*) \s+  # +/- decimal float
+        ([\-\+]?\d+)            # +/- int
+        ''',
+        re.VERBOSE,
+    )
+
+    def __init__(
+        self,
+        *,
+        hocr_filename: str | Path,
+        dpi: float,
+        debug: bool = False,
+        fontname: Name = Name("/f-0-0"),
+        font: Font = GlyphlessFont(),
+        debug_render_options: DebugRenderOptions | None = None,
+    ):
+        """Initialize the HocrTransform object."""
+        if debug:
+            log.warning("Use debug_render_options instead", DeprecationWarning)
+            self.render_options = DebugRenderOptions(
+                render_baseline=debug,
+                render_triangle=debug,
+                render_line_bbox=False,
+                render_word_bbox=debug,
+                render_paragraph_bbox=False,
+                render_space_bbox=False,
+            )
+        else:
+            self.render_options = debug_render_options or DebugRenderOptions()
+        self.dpi = dpi
+        self.hocr = ElementTree.parse(os.fspath(hocr_filename))
+        self._fontname = fontname
+        self._font = font
+
+        # if the hOCR file has a namespace, ElementTree requires its use to
+        # find elements
+        matches = re.match(r'({.*})html', self.hocr.getroot().tag)
+        self.xmlns = ''
+        if matches:
+            self.xmlns = matches.group(1)
+
+        for div in self.hocr.findall(self._child_xpath('div', 'ocr_page')):
+            coords = self.element_coordinates(div)
+            if not coords:
+                raise HocrTransformError("hocr file is missing page dimensions")
+            self.width = (coords.urx - coords.llx) / (self.dpi / INCH)
+            self.height = (coords.ury - coords.lly) / (self.dpi / INCH)
+            # Stop after first div that has page coordinates
+            break
+
+    def _get_element_text(self, element: Element) -> str:
+        """Return the textual content of the element and its children."""
+        text = element.text if element.text is not None else ''
+        for child in element:
+            text += self._get_element_text(child)
+        text += element.tail if element.tail is not None else ''
+        return text
+
+    @classmethod
+    def element_coordinates(cls, element: Element) -> Rectangle | None:
+        """Get coordinates of the bounding box around an element."""
+        matches = cls.box_pattern.search(element.attrib.get('title', ''))
+        if not matches:
+            return None
+        return Rectangle(
+            float(matches.group(1)),  # llx = left
+            float(matches.group(2)),  # lly = top
+            float(matches.group(3)),  # urx = right
+            float(matches.group(4)),  # ury = bottom
+        )
+
+    @classmethod
+    def baseline(cls, element: Element) -> tuple[float, float]:
+        """Get baseline's slope and intercept."""
+        matches = cls.baseline_pattern.search(element.attrib.get('title', ''))
+        if not matches:
+            return (0.0, 0.0)
+        return float(matches.group(1)), int(matches.group(2))
+
+    def _child_xpath(self, html_tag: str, html_class: str | None = None) -> str:
+        xpath = f".//{self.xmlns}{html_tag}"
+        if html_class:
+            xpath += f"[@class='{html_class}']"
+        return xpath
+
+    @classmethod
+    def normalize_text(cls, s: str) -> str:
+        """Normalize the given text using the NFKC normalization form."""
+        return unicodedata.normalize("NFKC", s)
+
+    def to_pdf(
+        self,
+        *,
+        out_filename: Path,
+        image_filename: Path | None = None,
+        invisible_text: bool = True,
+    ) -> None:
+        """Creates a PDF file with an image superimposed on top of the text.
+
+        Text is positioned according to the bounding box of the lines in
+        the hOCR file.
+        The image need not be identical to the image used to create the hOCR
+        file.
+        It can have a lower resolution, different color mode, etc.
+
+        Arguments:
+            out_filename: Path of PDF to write.
+            image_filename: Image to use for this file. If omitted, the OCR text
+                is shown.
+            invisible_text: If True, text is rendered invisible so that is
+                selectable but never drawn. If False, text is visible and may
+                be seen if the image is skipped or deleted in Acrobat.
+        """
+        # create the PDF file
+        # page size in points (1/72 in.)
+        canvas = Canvas(page_size=(self.width, self.height))
+        canvas.add_font(self._fontname, self._font)
+        page_matrix = (
+            Matrix()
+            .translated(0, self.height)
+            .scaled(1, -1)
+            .scaled(INCH / self.dpi, INCH / self.dpi)
+        )
+        log.debug(page_matrix)
+        with canvas.do.save_state(cm=page_matrix):
+            self._debug_draw_paragraph_boxes(canvas)
+            found_lines = False
+            for par in self.hocr.iterfind(self._child_xpath('p', 'ocr_par')):
+                for line in (
+                    element
+                    for element in par.iterfind(self._child_xpath('span'))
+                    if 'class' in element.attrib
+                    and element.attrib['class']
+                    in {'ocr_header', 'ocr_line', 'ocr_textfloat'}
+                ):
+                    found_lines = True
+                    direction = self._get_text_direction(par)
+                    inject_word_breaks = self._get_inject_word_breaks(par)
+                    self._do_line(
+                        canvas,
+                        line,
+                        "ocrx_word",
+                        invisible_text,
+                        direction,
+                        inject_word_breaks,
+                    )
+
+            if not found_lines:
+                # Tesseract did not report any lines (just words)
+                root = self.hocr.find(self._child_xpath('div', 'ocr_page'))
+                direction = self._get_text_direction(root)
+                self._do_line(
+                    canvas,
+                    root,
+                    "ocrx_word",
+                    invisible_text,
+                    direction,
+                    True,
+                )
+        # put the image on the page, scaled to fill the page
+        if image_filename is not None:
+            canvas.do.draw_image(
+                image_filename, 0, 0, width=self.width, height=self.height
+            )
+
+        # finish up the page and save it
+        canvas.to_pdf().save(out_filename)
+
+    def _get_text_direction(self, par):
+        """Get the text direction of the paragraph.
+
+        Arabic, Hebrew, Persian, are right-to-left languages.
+        """
+        return (
+            TextDirection.RTL
+            if par.attrib.get('dir', 'ltr') == 'rtl'
+            else TextDirection.LTR
+        )
+
+    def _get_inject_word_breaks(self, par):
+        """Determine whether word breaks should be injected.
+
+        In Chinese, Japanese, and Korean, word breaks are not injected, because
+        words are usually one or two characters and separators are usually explicit.
+        In all other languages, we inject word breaks to help word segmentation.
+        """
+        lang = par.attrib.get('lang', '')
+        log.debug(lang)
+        if lang in {'chi_sim', 'chi_tra', 'jpn', 'kor'}:
+            return False
+        return True
+
+    @classmethod
+    def polyval(cls, poly, x):  # pragma: no cover
+        """Calculate the value of a polynomial at a point."""
+        return x * poly[0] + poly[1]
+
+    def _do_line(
+        self,
+        canvas: Canvas,
+        line: Element | None,
+        elemclass: str,
+        invisible_text: bool,
+        text_direction: TextDirection,
+        inject_word_breaks: bool,
+    ):
+        """Render the text for a given line.
+
+        The canvas's coordinate system must be configured so that hOCR pixel
+        coordinates are mapped to PDF coordinates.
+        """
+        if line is None:
+            return
+        line_box = self.element_coordinates(line)
+        if not line_box:
+            return
+        if line_box.ury <= line_box.lly:
+            log.error(
+                "line box is invalid so we cannot render it: box=%s text=%s",
+                line_box,
+                self._get_element_text(line),
+            )
+            return
+
+        self._debug_draw_line_bbox(canvas, line_box)
+
+        # Baseline is a polynomial (usually straight line) that describes the
+        # text baseline relative to the bottom left corner of the line bounding
+        # box.
+        bottom_left_corner = line_box.llx, line_box.ury
+        slope, intercept = self.baseline(line)
+        if abs(slope) < 0.005:
+            slope = 0.0
+        angle = atan(slope)
+
+        # Setup a new coordinate system on the line box's intercept and rotated by
+        # its slope.
+        line_matrix = (
+            Matrix()
+            .translated(*bottom_left_corner)
+            .translated(0, intercept)
+            .rotated(angle / pi * 180)
+        )
+        log.debug(line_matrix)
+        with canvas.do.save_state(cm=line_matrix):
+            text = Text(direction=text_direction)
+
+            # Don't allow the font to break out of the bounding box. Division by
+            # cos_a accounts for extra clearance between the glyph's vertical axis
+            # on a sloped baseline and the edge of the bounding box.
+            line_box_height = abs(line_box.height) / cos(angle)
+            fontsize = line_box_height + intercept
+            text.font(self._fontname, fontsize)
+            text.render_mode(3 if invisible_text else 0)
+
+            self._debug_draw_baseline(
+                canvas, line_matrix.inverse().transform(line_box), 0
+            )
+
+            canvas.do.fill_color(BLACK)  # text in black
+            elements = line.findall(self._child_xpath('span', elemclass))
+            for elem, next_elem in pairwise(elements + [None]):
+                self._do_line_word(
+                    canvas,
+                    line_matrix,
+                    text,
+                    fontsize,
+                    elem,
+                    next_elem,
+                    text_direction,
+                    inject_word_breaks,
+                )
+            canvas.do.draw_text(text)
+
+    def _do_line_word(
+        self,
+        canvas: Canvas,
+        line_matrix: Matrix,
+        text: Text,
+        fontsize: float,
+        elem: Element,
+        next_elem: Element | None,
+        text_direction: TextDirection,
+        inject_word_breaks: bool,
+    ):
+        """Render the text for a single word."""
+        if elem is None:
+            return
+        elemtxt = self.normalize_text(self._get_element_text(elem).strip())
+        if elemtxt == '':
+            return
+
+        hocr_box = self.element_coordinates(elem)
+        if hocr_box is None:
+            return
+        box = line_matrix.inverse().transform(hocr_box)
+        font_width = self._font.text_width(elemtxt, fontsize)
+
+        # Debug sketches
+        self._debug_draw_word_triangle(canvas, box)
+        self._debug_draw_word_bbox(canvas, box)
+
+        # If this word is 0 units wide, our best bet seems to be to suppress this text
+        if text_direction == TextDirection.RTL:
+            log.info("RTL: %s", elemtxt)
+        if font_width > 0:
+            if text_direction == TextDirection.LTR:
+                text.text_transform(Matrix(1, 0, 0, -1, box.llx, 0))
+            elif text_direction == TextDirection.RTL:
+                text.text_transform(Matrix(-1, 0, 0, -1, box.llx + box.width, 0))
+            text.horiz_scale(100 * box.width / font_width)
+            text.show(self._font.text_encode(elemtxt))
+
+        # Get coordinates of the next word (if there is one)
+        hocr_next_box = (
+            self.element_coordinates(next_elem) if next_elem is not None else None
+        )
+        if hocr_next_box is None:
+            return
+        # Render a space this word and the next word. The explicit space helps
+        # PDF viewers identify the word break, and horizontally scaling it to
+        # occupy the space the between the words helps the PDF viewer
+        # avoid combiningthewordstogether.
+        if not inject_word_breaks:
+            return
+        next_box = line_matrix.inverse().transform(hocr_next_box)
+        if text_direction == TextDirection.LTR:
+            space_box = Rectangle(box.urx, box.lly, next_box.llx, next_box.ury)
+        elif text_direction == TextDirection.RTL:
+            space_box = Rectangle(next_box.urx, box.lly, box.llx, next_box.ury)
+        self._debug_draw_space_bbox(canvas, space_box)
+        space_width = self._font.text_width(' ', fontsize)
+        if space_width > 0:
+            if text_direction == TextDirection.LTR:
+                text.text_transform(Matrix(1, 0, 0, -1, space_box.llx, 0))
+            elif text_direction == TextDirection.RTL:
+                text.text_transform(
+                    Matrix(-1, 0, 0, -1, space_box.llx + space_box.width, 0)
+                )
+            text.horiz_scale(100 * space_box.width / space_width)
+            text.show(self._font.text_encode(' '))
+
+    def _debug_draw_paragraph_boxes(self, canvas: Canvas, color=CYAN):
+        """Draw boxes around paragraphs in the document."""
+        if not self.render_options.render_paragraph_bbox:  # pragma: no cover
+            return
+        with canvas.do.save_state():
+            # draw box around paragraph
+            canvas.do.stroke_color(color).line_width(0.1)
+            for elem in self.hocr.iterfind(self._child_xpath('p', 'ocr_par')):
+                elemtxt = self._get_element_text(elem).strip()
+                if len(elemtxt) == 0:
+                    continue
+                ocr_par = self.element_coordinates(elem)
+                if ocr_par is None:
+                    continue
+                canvas.do.rect(
+                    ocr_par.llx, ocr_par.lly, ocr_par.width, ocr_par.height, fill=0
+                )
+
+    def _debug_draw_line_bbox(self, canvas: Canvas, line_box: Rectangle, color=BLUE):
+        """Render the bounding box of a text line."""
+        if not self.render_options.render_line_bbox:  # pragma: no cover
+            return
+        with canvas.do.save_state():
+            canvas.do.stroke_color(color).line_width(0.15).rect(
+                line_box.llx, line_box.lly, line_box.width, line_box.height, fill=0
+            )
+
+    def _debug_draw_word_triangle(
+        self, canvas: Canvas, box: Rectangle, color=RED, line_width=0.1
+    ):
+        """Render a triangle that conveys word height and drawing direction."""
+        if not self.render_options.render_triangle:  # pragma: no cover
+            return
+        with canvas.do.save_state():
+            canvas.do.stroke_color(color).line_width(line_width).line(
+                box.llx, box.lly, box.urx, box.lly
+            ).line(box.urx, box.lly, box.llx, box.ury).line(
+                box.llx, box.lly, box.llx, box.ury
+            )
+
+    def _debug_draw_word_bbox(
+        self, canvas: Canvas, box: Rectangle, color=GREEN, line_width=0.1
+    ):
+        """Render a box depicting the word."""
+        if not self.render_options.render_word_bbox:  # pragma: no cover
+            return
+        with canvas.do.save_state():
+            canvas.do.stroke_color(color).line_width(line_width).rect(
+                box.llx, box.lly, box.width, box.height, fill=0
+            )
+
+    def _debug_draw_space_bbox(
+        self, canvas: Canvas, box: Rectangle, color=DARKGREEN, line_width=0.1
+    ):
+        """Render a box depicting the space between two words."""
+        if not self.render_options.render_space_bbox:  # pragma: no cover
+            return
+        with canvas.do.save_state():
+            canvas.do.fill_color(color).line_width(line_width).rect(
+                box.llx, box.lly, box.width, box.height, fill=1
+            )
+
+    def _debug_draw_baseline(
+        self,
+        canvas: Canvas,
+        line_box: Rectangle,
+        baseline_lly,
+        color=MAGENTA,
+        line_width=0.25,
+    ):
+        """Render the text baseline."""
+        if not self.render_options.render_baseline:
+            return
+        with canvas.do.save_state():
+            canvas.do.stroke_color(color).line_width(line_width).line(
+                line_box.llx,
+                baseline_lly,
+                line_box.urx,
+                baseline_lly,
+            )

src/ocrmypdf/imageops.py

@@ -7,25 +7,9 @@ from __future__ import annotations
 
 import logging
 from math import floor, sqrt
-from typing import Optional, Tuple
 
 from PIL import Image
 
-# Remove this workaround when we require Pillow >= 9.1.0
-try:
-    Resampling = Image.Resampling  # type: ignore
-except AttributeError:
-    # Pillow 9 shim
-    Resampling = Image  # type: ignore
-
-
-# While from __future__ import annotations, we use singledispatch here, which
-# does not support annotations. Disable check about using old-style typing
-# until Python 3.10, OR when drop singledispatch in ocrmypdf 15.
-# ruff: noqa: UP006
-# ruff: noqa: UP007
-
-
 log = logging.getLogger(__name__)
 
 
@@ -43,13 +27,13 @@ def bytes_per_pixel(mode: str) -> int:
 
 
 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_pixels: Optional[int] = None,
-    max_bytes: Optional[int] = None,
-) -> Tuple[int, int]:
+    max_size: tuple[int, int] | None = None,
+    max_pixels: int | None = None,
+    max_bytes: int | None = None,
+) -> tuple[int, int]:
     """Calculate image size required to downsample an image to fit limits.
 
     If no limit is exceeded, the input image's size is returned.
@@ -106,10 +90,10 @@ def _calculate_downsample(
 def calculate_downsample(
     image: Image.Image,
     *,
-    max_size: Optional[Tuple[int, int]] = None,
-    max_pixels: Optional[int] = None,
-    max_bytes: Optional[int] = None,
-) -> Tuple[int, int]:
+    max_size: tuple[int, int] | None = None,
+    max_pixels: int | None = None,
+    max_bytes: int | None = None,
+) -> tuple[int, int]:
     """Calculate image size required to downsample an image to fit limits.
 
     If no limit is exceeded, the input image's size is returned.
@@ -135,7 +119,7 @@ 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/languages.py

@@ -0,0 +1,851 @@
+# SPDX-FileCopyrightText: 2023 James R. Barlow
+# SPDX-License-Identifier: MPL-2.0
+
+"""Language codes and names from ISO 639.
+
+Derived from
+https://www.loc.gov/standards/iso639-2/ascii_8bits.html
+"""
+
+from typing import NamedTuple
+
+
+class ISOCodeData(NamedTuple):
+    """Data for a single ISO 639 code."""
+
+    alt: str
+    alpha_2: str
+    english: str
+    french: str
+
+
+ISO_639_3 = {
+    'aar': ISOCodeData('', 'aa', 'Afar', 'afar'),
+    'abk': ISOCodeData('', 'ab', 'Abkhazian', 'abkhaze'),
+    'ace': ISOCodeData('', '', 'Achinese', 'aceh'),
+    'ach': ISOCodeData('', '', 'Acoli', 'acoli'),
+    'ada': ISOCodeData('', '', 'Adangme', 'adangme'),
+    'ady': ISOCodeData('', '', 'Adyghe; Adygei', 'adyghé'),
+    'afa': ISOCodeData(
+        '',
+        '',
+        'Afro-Asiatic languages',
+        'afro-asiatiques, langues',
+    ),
+    'afh': ISOCodeData('', '', 'Afrihili', 'afrihili'),
+    'afr': ISOCodeData('', 'af', 'Afrikaans', 'afrikaans'),
+    'ain': ISOCodeData('', '', 'Ainu', 'aïnou'),
+    'aka': ISOCodeData('', 'ak', 'Akan', 'akan'),
+    'akk': ISOCodeData('', '', 'Akkadian', 'akkadien'),
+    'alb': ISOCodeData('sqi', 'sq', 'Albanian', 'albanais'),
+    'ale': ISOCodeData('', '', 'Aleut', 'aléoute'),
+    'alg': ISOCodeData(
+        '',
+        '',
+        'Algonquian languages',
+        'algonquines, langues',
+    ),
+    'alt': ISOCodeData('', '', 'Southern Altai', 'altai du Sud'),
+    'amh': ISOCodeData('', 'am', 'Amharic', 'amharique'),
+    'ang': ISOCodeData(
+        '',
+        '',
+        'English, Old (ca.450-1100)',
+        'anglo-saxon (ca.450-1100)',
+    ),
+    'anp': ISOCodeData('', '', 'Angika', 'angika'),
+    'apa': ISOCodeData('', '', 'Apache languages', 'apaches, langues'),
+    'ara': ISOCodeData('', 'ar', 'Arabic', 'arabe'),
+    'arc': ISOCodeData(
+        '',
+        '',
+        'Official Aramaic (700-300 BCE); Imperial Aramaic (700-300 BCE)',
+        "araméen d'empire (700-300 BCE)",
+    ),
+    'arg': ISOCodeData('', 'an', 'Aragonese', 'aragonais'),
+    'arm': ISOCodeData('hye', 'hy', 'Armenian', 'arménien'),
+    'arn': ISOCodeData(
+        '',
+        '',
+        'Mapudungun; Mapuche',
+        'mapudungun; mapuche; mapuce',
+    ),
+    'arp': ISOCodeData('', '', 'Arapaho', 'arapaho'),
+    'art': ISOCodeData(
+        '',
+        '',
+        'Artificial languages',
+        'artificielles, langues',
+    ),
+    'arw': ISOCodeData('', '', 'Arawak', 'arawak'),
+    'asm': ISOCodeData('', 'as', 'Assamese', 'assamais'),
+    'ast': ISOCodeData(
+        '',
+        '',
+        'Asturian; Bable; Leonese; Asturleonese',
+        'asturien; bable; léonais; asturoléonais',
+    ),
+    'ath': ISOCodeData(
+        '',
+        '',
+        'Athapascan languages',
+        'athapascanes, langues',
+    ),
+    'aus': ISOCodeData(
+        '',
+        '',
+        'Australian languages',
+        'australiennes, langues',
+    ),
+    'ava': ISOCodeData('', 'av', 'Avaric', 'avar'),
+    'ave': ISOCodeData('', 'ae', 'Avestan', 'avestique'),
+    'awa': ISOCodeData('', '', 'Awadhi', 'awadhi'),
+    'aym': ISOCodeData('', 'ay', 'Aymara', 'aymara'),
+    'aze': ISOCodeData('', 'az', 'Azerbaijani', 'azéri'),
+    'bad': ISOCodeData('', '', 'Banda languages', 'banda, langues'),
+    'bai': ISOCodeData('', '', 'Bamileke languages', 'bamiléké, langues'),
+    'bak': ISOCodeData('', 'ba', 'Bashkir', 'bachkir'),
+    'bal': ISOCodeData('', '', 'Baluchi', 'baloutchi'),
+    'bam': ISOCodeData('', 'bm', 'Bambara', 'bambara'),
+    'ban': ISOCodeData('', '', 'Balinese', 'balinais'),
+    'baq': ISOCodeData('eus', 'eu', 'Basque', 'basque'),
+    'bas': ISOCodeData('', '', 'Basa', 'basa'),
+    'bat': ISOCodeData('', '', 'Baltic languages', 'baltes, langues'),
+    'bej': ISOCodeData('', '', 'Beja; Bedawiyet', 'bedja'),
+    'bel': ISOCodeData('', 'be', 'Belarusian', 'biélorusse'),
+    'bem': ISOCodeData('', '', 'Bemba', 'bemba'),
+    'ben': ISOCodeData('', 'bn', 'Bengali', 'bengali'),
+    'ber': ISOCodeData('', '', 'Berber languages', 'berbères, langues'),
+    'bho': ISOCodeData('', '', 'Bhojpuri', 'bhojpuri'),
+    'bih': ISOCodeData('', 'bh', 'Bihari languages', 'langues biharis'),
+    'bik': ISOCodeData('', '', 'Bikol', 'bikol'),
+    'bin': ISOCodeData('', '', 'Bini; Edo', 'bini; edo'),
+    'bis': ISOCodeData('', 'bi', 'Bislama', 'bichlamar'),
+    'bla': ISOCodeData('', '', 'Siksika', 'blackfoot'),
+    'bnt': ISOCodeData('', '', 'Bantu languages', 'bantou, langues'),
+    'bos': ISOCodeData('', 'bs', 'Bosnian', 'bosniaque'),
+    'bra': ISOCodeData('', '', 'Braj', 'braj'),
+    'bre': ISOCodeData('', 'br', 'Breton', 'breton'),
+    'btk': ISOCodeData('', '', 'Batak languages', 'batak, langues'),
+    'bua': ISOCodeData('', '', 'Buriat', 'bouriate'),
+    'bug': ISOCodeData('', '', 'Buginese', 'bugi'),
+    'bul': ISOCodeData('', 'bg', 'Bulgarian', 'bulgare'),
+    'bur': ISOCodeData('mya', 'my', 'Burmese', 'birman'),
+    'byn': ISOCodeData('', '', 'Blin; Bilin', 'blin; bilen'),
+    'cad': ISOCodeData('', '', 'Caddo', 'caddo'),
+    'cai': ISOCodeData(
+        '',
+        '',
+        'Central American Indian languages',
+        "amérindiennes de L'Amérique centrale, langues",
+    ),
+    'car': ISOCodeData('', '', 'Galibi Carib', 'karib; galibi; carib'),
+    'cat': ISOCodeData('', 'ca', 'Catalan; Valencian', 'catalan; valencien'),
+    'cau': ISOCodeData(
+        '',
+        '',
+        'Caucasian languages',
+        'caucasiennes, langues',
+    ),
+    'ceb': ISOCodeData('', '', 'Cebuano', 'cebuano'),
+    'cel': ISOCodeData(
+        '',
+        '',
+        'Celtic languages',
+        'celtiques, langues; celtes, langues',
+    ),
+    'cha': ISOCodeData('', 'ch', 'Chamorro', 'chamorro'),
+    'chb': ISOCodeData('', '', 'Chibcha', 'chibcha'),
+    'che': ISOCodeData('', 'ce', 'Chechen', 'tchétchène'),
+    'chg': ISOCodeData('', '', 'Chagatai', 'djaghataï'),
+    'chi': ISOCodeData('zho', 'zh', 'Chinese', 'chinois'),
+    'chk': ISOCodeData('', '', 'Chuukese', 'chuuk'),
+    'chm': ISOCodeData('', '', 'Mari', 'mari'),
+    'chn': ISOCodeData('', '', 'Chinook jargon', 'chinook, jargon'),
+    'cho': ISOCodeData('', '', 'Choctaw', 'choctaw'),
+    'chp': ISOCodeData('', '', 'Chipewyan; Dene Suline', 'chipewyan'),
+    'chr': ISOCodeData('', '', 'Cherokee', 'cherokee'),
+    'chu': ISOCodeData(
+        '',
+        'cu',
+        (
+            'Church Slavic; Old Slavonic; Church Slavonic;'
+            ' Old Bulgarian; Old Church Slavonic'
+        ),
+        "slavon d'église; vieux slave; slavon liturgique; vieux bulgare",
+    ),
+    'chv': ISOCodeData('', 'cv', 'Chuvash', 'tchouvache'),
+    'chy': ISOCodeData('', '', 'Cheyenne', 'cheyenne'),
+    'cmc': ISOCodeData('', '', 'Chamic languages', 'chames, langues'),
+    'cnr': ISOCodeData('', '', 'Montenegrin', 'monténégrin'),
+    'cop': ISOCodeData('', '', 'Coptic', 'copte'),
+    'cor': ISOCodeData('', 'kw', 'Cornish', 'cornique'),
+    'cos': ISOCodeData('', 'co', 'Corsican', 'corse'),
+    'cpe': ISOCodeData(
+        '',
+        '',
+        'Creoles and pidgins, English based',
+        "créoles et pidgins basés sur l'anglais",
+    ),
+    'cpf': ISOCodeData(
+        '',
+        '',
+        'Creoles and pidgins, French-based',
+        'créoles et pidgins basés sur le français',
+    ),
+    'cpp': ISOCodeData(
+        '',
+        '',
+        'Creoles and pidgins, Portuguese-based',
+        'créoles et pidgins basés sur le portugais',
+    ),
+    'cre': ISOCodeData('', 'cr', 'Cree', 'cree'),
+    'crh': ISOCodeData(
+        '',
+        '',
+        'Crimean Tatar; Crimean Turkish',
+        'tatar de Crimé',
+    ),
+    'crp': ISOCodeData('', '', 'Creoles and pidgins', 'créoles et pidgins'),
+    'csb': ISOCodeData('', '', 'Kashubian', 'kachoube'),
+    'cus': ISOCodeData('', '', 'Cushitic languages', 'couchitiques, langues'),
+    'cze': ISOCodeData('ces', 'cs', 'Czech', 'tchèque'),
+    'dak': ISOCodeData('', '', 'Dakota', 'dakota'),
+    'dan': ISOCodeData('', 'da', 'Danish', 'danois'),
+    'dar': ISOCodeData('', '', 'Dargwa', 'dargwa'),
+    'day': ISOCodeData('', '', 'Land Dayak languages', 'dayak, langues'),
+    'del': ISOCodeData('', '', 'Delaware', 'delaware'),
+    'den': ISOCodeData('', '', 'Slave (Athapascan)', 'esclave (athapascan)'),
+    'dgr': ISOCodeData('', '', 'Dogrib', 'dogrib'),
+    'din': ISOCodeData('', '', 'Dinka', 'dinka'),
+    'div': ISOCodeData('', 'dv', 'Divehi; Dhivehi; Maldivian', 'maldivien'),
+    'doi': ISOCodeData('', '', 'Dogri', 'dogri'),
+    'dra': ISOCodeData(
+        '',
+        '',
+        'Dravidian languages',
+        'dravidiennes, langues',
+    ),
+    'dsb': ISOCodeData('', '', 'Lower Sorbian', 'bas-sorabe'),
+    'dua': ISOCodeData('', '', 'Duala', 'douala'),
+    'dum': ISOCodeData(
+        '',
+        '',
+        'Dutch, Middle (ca.1050-1350)',
+        'néerlandais moyen (ca. 1050-1350)',
+    ),
+    'dut': ISOCodeData('nld', 'nl', 'Dutch; Flemish', 'néerlandais; flamand'),
+    'dyu': ISOCodeData('', '', 'Dyula', 'dioula'),
+    'dzo': ISOCodeData('', 'dz', 'Dzongkha', 'dzongkha'),
+    'efi': ISOCodeData('', '', 'Efik', 'efik'),
+    'egy': ISOCodeData('', '', 'Egyptian (Ancient)', 'égyptien'),
+    'eka': ISOCodeData('', '', 'Ekajuk', 'ekajuk'),
+    'elx': ISOCodeData('', '', 'Elamite', 'élamite'),
+    'eng': ISOCodeData('', 'en', 'English', 'anglais'),
+    'enm': ISOCodeData(
+        '',
+        '',
+        'English, Middle (1100-1500)',
+        'anglais moyen (1100-1500)',
+    ),
+    'epo': ISOCodeData('', 'eo', 'Esperanto', 'espéranto'),
+    'est': ISOCodeData('', 'et', 'Estonian', 'estonien'),
+    'ewe': ISOCodeData('', 'ee', 'Ewe', 'éwé'),
+    'ewo': ISOCodeData('', '', 'Ewondo', 'éwondo'),
+    'fan': ISOCodeData('', '', 'Fang', 'fang'),
+    'fao': ISOCodeData('', 'fo', 'Faroese', 'féroïen'),
+    'fat': ISOCodeData('', '', 'Fanti', 'fanti'),
+    'fij': ISOCodeData('', 'fj', 'Fijian', 'fidjien'),
+    'fil': ISOCodeData('', '', 'Filipino; Pilipino', 'filipino; pilipino'),
+    'fin': ISOCodeData('', 'fi', 'Finnish', 'finnois'),
+    'fiu': ISOCodeData(
+        '',
+        '',
+        'Finno-Ugrian languages',
+        'finno-ougriennes, langues',
+    ),
+    'fon': ISOCodeData('', '', 'Fon', 'fon'),
+    'fre': ISOCodeData('fra', 'fr', 'French', 'français'),
+    'frm': ISOCodeData(
+        '',
+        '',
+        'French, Middle (ca.1400-1600)',
+        'français moyen (1400-1600)',
+    ),
+    'fro': ISOCodeData(
+        '',
+        '',
+        'French, Old (842-ca.1400)',
+        'français ancien (842-ca.1400)',
+    ),
+    'frr': ISOCodeData('', '', 'Northern Frisian', 'frison septentrional'),
+    'frs': ISOCodeData('', '', 'Eastern Frisian', 'frison oriental'),
+    'fry': ISOCodeData('', 'fy', 'Western Frisian', 'frison occidental'),
+    'ful': ISOCodeData('', 'ff', 'Fulah', 'peul'),
+    'fur': ISOCodeData('', '', 'Friulian', 'frioulan'),
+    'gaa': ISOCodeData('', '', 'Ga', 'ga'),
+    'gay': ISOCodeData('', '', 'Gayo', 'gayo'),
+    'gba': ISOCodeData('', '', 'Gbaya', 'gbaya'),
+    'gem': ISOCodeData('', '', 'Germanic languages', 'germaniques, langues'),
+    'geo': ISOCodeData('kat', 'ka', 'Georgian', 'géorgien'),
+    'ger': ISOCodeData('deu', 'de', 'German', 'allemand'),
+    'gez': ISOCodeData('', '', 'Geez', 'guèze'),
+    'gil': ISOCodeData('', '', 'Gilbertese', 'kiribati'),
+    'gla': ISOCodeData(
+        '',
+        'gd',
+        'Gaelic; Scottish Gaelic',
+        'gaélique; gaélique écossais',
+    ),
+    'gle': ISOCodeData('', 'ga', 'Irish', 'irlandais'),
+    'glg': ISOCodeData('', 'gl', 'Galician', 'galicien'),
+    'glv': ISOCodeData('', 'gv', 'Manx', 'manx; mannois'),
+    'gmh': ISOCodeData(
+        '',
+        '',
+        'German, Middle High (ca.1050-1500)',
+        'allemand, moyen haut (ca. 1050-1500)',
+    ),
+    'goh': ISOCodeData(
+        '',
+        '',
+        'German, Old High (ca.750-1050)',
+        'allemand, vieux haut (ca. 750-1050)',
+    ),
+    'gon': ISOCodeData('', '', 'Gondi', 'gond'),
+    'gor': ISOCodeData('', '', 'Gorontalo', 'gorontalo'),
+    'got': ISOCodeData('', '', 'Gothic', 'gothique'),
+    'grb': ISOCodeData('', '', 'Grebo', 'grebo'),
+    'grc': ISOCodeData(
+        '',
+        '',
+        'Greek, Ancient (to 1453)',
+        "grec ancien (jusqu'à 1453)",
+    ),
+    'gre': ISOCodeData(
+        'ell',
+        'el',
+        'Greek, Modern (1453-)',
+        'grec moderne (après 1453)',
+    ),
+    'grn': ISOCodeData('', 'gn', 'Guarani', 'guarani'),
+    'gsw': ISOCodeData(
+        '',
+        '',
+        'Swiss German; Alemannic; Alsatian',
+        'suisse alémanique; alémanique; alsacien',
+    ),
+    'guj': ISOCodeData('', 'gu', 'Gujarati', 'goudjrati'),
+    'gwi': ISOCodeData('', '', "Gwich'in", "gwich'in"),
+    'hai': ISOCodeData('', '', 'Haida', 'haida'),
+    'hat': ISOCodeData(
+        '',
+        'ht',
+        'Haitian; Haitian Creole',
+        'haïtien; créole haïtien',
+    ),
+    'hau': ISOCodeData('', 'ha', 'Hausa', 'haoussa'),
+    'haw': ISOCodeData('', '', 'Hawaiian', 'hawaïen'),
+    'heb': ISOCodeData('', 'he', 'Hebrew', 'hébreu'),
+    'her': ISOCodeData('', 'hz', 'Herero', 'herero'),
+    'hil': ISOCodeData('', '', 'Hiligaynon', 'hiligaynon'),
+    'him': ISOCodeData(
+        '',
+        '',
+        'Himachali languages; Western Pahari languages',
+        'langues himachalis; langues paharis occidentales',
+    ),
+    'hin': ISOCodeData('', 'hi', 'Hindi', 'hindi'),
+    'hit': ISOCodeData('', '', 'Hittite', 'hittite'),
+    'hmn': ISOCodeData('', '', 'Hmong; Mong', 'hmong'),
+    'hmo': ISOCodeData('', 'ho', 'Hiri Motu', 'hiri motu'),
+    'hrv': ISOCodeData('', 'hr', 'Croatian', 'croate'),
+    'hsb': ISOCodeData('', '', 'Upper Sorbian', 'haut-sorabe'),
+    'hun': ISOCodeData('', 'hu', 'Hungarian', 'hongrois'),
+    'hup': ISOCodeData('', '', 'Hupa', 'hupa'),
+    'iba': ISOCodeData('', '', 'Iban', 'iban'),
+    'ibo': ISOCodeData('', 'ig', 'Igbo', 'igbo'),
+    'ice': ISOCodeData('isl', 'is', 'Icelandic', 'islandais'),
+    'ido': ISOCodeData('', 'io', 'Ido', 'ido'),
+    'iii': ISOCodeData('', 'ii', 'Sichuan Yi; Nuosu', 'yi de Sichuan'),
+    'ijo': ISOCodeData('', '', 'Ijo languages', 'ijo, langues'),
+    'iku': ISOCodeData('', 'iu', 'Inuktitut', 'inuktitut'),
+    'ile': ISOCodeData('', 'ie', 'Interlingue; Occidental', 'interlingue'),
+    'ilo': ISOCodeData('', '', 'Iloko', 'ilocano'),
+    'ina': ISOCodeData(
+        '',
+        'ia',
+        'Interlingua (International Auxiliary Language Association)',
+        'interlingua (langue auxiliaire internationale)',
+    ),
+    'inc': ISOCodeData('', '', 'Indic languages', 'indo-aryennes, langues'),
+    'ind': ISOCodeData('', 'id', 'Indonesian', 'indonésien'),
+    'ine': ISOCodeData(
+        '',
+        '',
+        'Indo-European languages',
+        'indo-européennes, langues',
+    ),
+    'inh': ISOCodeData('', '', 'Ingush', 'ingouche'),
+    'ipk': ISOCodeData('', 'ik', 'Inupiaq', 'inupiaq'),
+    'ira': ISOCodeData('', '', 'Iranian languages', 'iraniennes, langues'),
+    'iro': ISOCodeData('', '', 'Iroquoian languages', 'iroquoises, langues'),
+    'ita': ISOCodeData('', 'it', 'Italian', 'italien'),
+    'jav': ISOCodeData('', 'jv', 'Javanese', 'javanais'),
+    'jbo': ISOCodeData('', '', 'Lojban', 'lojban'),
+    'jpn': ISOCodeData('', 'ja', 'Japanese', 'japonais'),
+    'jpr': ISOCodeData('', '', 'Judeo-Persian', 'judéo-persan'),
+    'jrb': ISOCodeData('', '', 'Judeo-Arabic', 'judéo-arabe'),
+    'kaa': ISOCodeData('', '', 'Kara-Kalpak', 'karakalpak'),
+    'kab': ISOCodeData('', '', 'Kabyle', 'kabyle'),
+    'kac': ISOCodeData('', '', 'Kachin; Jingpho', 'kachin; jingpho'),
+    'kal': ISOCodeData('', 'kl', 'Kalaallisut; Greenlandic', 'groenlandais'),
+    'kam': ISOCodeData('', '', 'Kamba', 'kamba'),
+    'kan': ISOCodeData('', 'kn', 'Kannada', 'kannada'),
+    'kar': ISOCodeData('', '', 'Karen languages', 'karen, langues'),
+    'kas': ISOCodeData('', 'ks', 'Kashmiri', 'kashmiri'),
+    'kau': ISOCodeData('', 'kr', 'Kanuri', 'kanouri'),
+    'kaw': ISOCodeData('', '', 'Kawi', 'kawi'),
+    'kaz': ISOCodeData('', 'kk', 'Kazakh', 'kazakh'),
+    'kbd': ISOCodeData('', '', 'Kabardian', 'kabardien'),
+    'kha': ISOCodeData('', '', 'Khasi', 'khasi'),
+    'khi': ISOCodeData('', '', 'Khoisan languages', 'khoïsan, langues'),
+    'khm': ISOCodeData('', 'km', 'Central Khmer', 'khmer central'),
+    'kho': ISOCodeData('', '', 'Khotanese; Sakan', 'khotanais; sakan'),
+    'kik': ISOCodeData('', 'ki', 'Kikuyu; Gikuyu', 'kikuyu'),
+    'kin': ISOCodeData('', 'rw', 'Kinyarwanda', 'rwanda'),
+    'kir': ISOCodeData('', 'ky', 'Kirghiz; Kyrgyz', 'kirghiz'),
+    'kmb': ISOCodeData('', '', 'Kimbundu', 'kimbundu'),
+    'kok': ISOCodeData('', '', 'Konkani', 'konkani'),
+    'kom': ISOCodeData('', 'kv', 'Komi', 'kom'),
+    'kon': ISOCodeData('', 'kg', 'Kongo', 'kongo'),
+    'kor': ISOCodeData('', 'ko', 'Korean', 'coréen'),
+    'kos': ISOCodeData('', '', 'Kosraean', 'kosrae'),
+    'kpe': ISOCodeData('', '', 'Kpelle', 'kpellé'),
+    'krc': ISOCodeData('', '', 'Karachay-Balkar', 'karatchai balkar'),
+    'krl': ISOCodeData('', '', 'Karelian', 'carélien'),
+    'kro': ISOCodeData('', '', 'Kru languages', 'krou, langues'),
+    'kru': ISOCodeData('', '', 'Kurukh', 'kurukh'),
+    'kua': ISOCodeData('', 'kj', 'Kuanyama; Kwanyama', 'kuanyama; kwanyama'),
+    'kum': ISOCodeData('', '', 'Kumyk', 'koumyk'),
+    'kur': ISOCodeData('', 'ku', 'Kurdish', 'kurde'),
+    'kut': ISOCodeData('', '', 'Kutenai', 'kutenai'),
+    'lad': ISOCodeData('', '', 'Ladino', 'judéo-espagnol'),
+    'lah': ISOCodeData('', '', 'Lahnda', 'lahnda'),
+    'lam': ISOCodeData('', '', 'Lamba', 'lamba'),
+    'lao': ISOCodeData('', 'lo', 'Lao', 'lao'),
+    'lat': ISOCodeData('', 'la', 'Latin', 'latin'),
+    'lav': ISOCodeData('', 'lv', 'Latvian', 'letton'),
+    'lez': ISOCodeData('', '', 'Lezghian', 'lezghien'),
+    'lim': ISOCodeData(
+        '',
+        'li',
+        'Limburgan; Limburger; Limburgish',
+        'limbourgeois',
+    ),
+    'lin': ISOCodeData('', 'ln', 'Lingala', 'lingala'),
+    'lit': ISOCodeData('', 'lt', 'Lithuanian', 'lituanien'),
+    'lol': ISOCodeData('', '', 'Mongo', 'mongo'),
+    'loz': ISOCodeData('', '', 'Lozi', 'lozi'),
+    'ltz': ISOCodeData(
+        '',
+        'lb',
+        'Luxembourgish; Letzeburgesch',
+        'luxembourgeois',
+    ),
+    'lua': ISOCodeData('', '', 'Luba-Lulua', 'luba-lulua'),
+    'lub': ISOCodeData('', 'lu', 'Luba-Katanga', 'luba-katanga'),
+    'lug': ISOCodeData('', 'lg', 'Ganda', 'ganda'),
+    'lui': ISOCodeData('', '', 'Luiseno', 'luiseno'),
+    'lun': ISOCodeData('', '', 'Lunda', 'lunda'),
+    'luo': ISOCodeData(
+        '',
+        '',
+        'Luo (Kenya and Tanzania)',
+        'luo (Kenya et Tanzanie)',
+    ),
+    'lus': ISOCodeData('', '', 'Lushai', 'lushai'),
+    'mac': ISOCodeData('mkd', 'mk', 'Macedonian', 'macédonien'),
+    'mad': ISOCodeData('', '', 'Madurese', 'madourais'),
+    'mag': ISOCodeData('', '', 'Magahi', 'magahi'),
+    'mah': ISOCodeData('', 'mh', 'Marshallese', 'marshall'),
+    'mai': ISOCodeData('', '', 'Maithili', 'maithili'),
+    'mak': ISOCodeData('', '', 'Makasar', 'makassar'),
+    'mal': ISOCodeData('', 'ml', 'Malayalam', 'malayalam'),
+    'man': ISOCodeData('', '', 'Mandingo', 'mandingue'),
+    'mao': ISOCodeData('mri', 'mi', 'Maori', 'maori'),
+    'map': ISOCodeData(
+        '',
+        '',
+        'Austronesian languages',
+        'austronésiennes, langues',
+    ),
+    'mar': ISOCodeData('', 'mr', 'Marathi', 'marathe'),
+    'mas': ISOCodeData('', '', 'Masai', 'massaï'),
+    'may': ISOCodeData('msa', 'ms', 'Malay', 'malais'),
+    'mdf': ISOCodeData('', '', 'Moksha', 'moksa'),
+    'mdr': ISOCodeData('', '', 'Mandar', 'mandar'),
+    'men': ISOCodeData('', '', 'Mende', 'mendé'),
+    'mga': ISOCodeData(
+        '',
+        '',
+        'Irish, Middle (900-1200)',
+        'irlandais moyen (900-1200)',
+    ),
+    'mic': ISOCodeData('', '', "Mi'kmaq; Micmac", "mi'kmaq; micmac"),
+    'min': ISOCodeData('', '', 'Minangkabau', 'minangkabau'),
+    'mis': ISOCodeData('', '', 'Uncoded languages', 'langues non codées'),
+    'mkh': ISOCodeData('', '', 'Mon-Khmer languages', 'môn-khmer, langues'),
+    'mlg': ISOCodeData('', 'mg', 'Malagasy', 'malgache'),
+    'mlt': ISOCodeData('', 'mt', 'Maltese', 'maltais'),
+    'mnc': ISOCodeData('', '', 'Manchu', 'mandchou'),
+    'mni': ISOCodeData('', '', 'Manipuri', 'manipuri'),
+    'mno': ISOCodeData('', '', 'Manobo languages', 'manobo, langues'),
+    'moh': ISOCodeData('', '', 'Mohawk', 'mohawk'),
+    'mon': ISOCodeData('', 'mn', 'Mongolian', 'mongol'),
+    'mos': ISOCodeData('', '', 'Mossi', 'moré'),
+    'mul': ISOCodeData('', '', 'Multiple languages', 'multilingue'),
+    'mun': ISOCodeData('', '', 'Munda languages', 'mounda, langues'),
+    'mus': ISOCodeData('', '', 'Creek', 'muskogee'),
+    'mwl': ISOCodeData('', '', 'Mirandese', 'mirandais'),
+    'mwr': ISOCodeData('', '', 'Marwari', 'marvari'),
+    'myn': ISOCodeData('', '', 'Mayan languages', 'maya, langues'),
+    'myv': ISOCodeData('', '', 'Erzya', 'erza'),
+    'nah': ISOCodeData('', '', 'Nahuatl languages', 'nahuatl, langues'),
+    'nai': ISOCodeData(
+        '',
+        '',
+        'North American Indian languages',
+        'nord-amérindiennes, langues',
+    ),
+    'nap': ISOCodeData('', '', 'Neapolitan', 'napolitain'),
+    'nau': ISOCodeData('', 'na', 'Nauru', 'nauruan'),
+    'nav': ISOCodeData('', 'nv', 'Navajo; Navaho', 'navaho'),
+    'nbl': ISOCodeData(
+        '',
+        'nr',
+        'Ndebele, South; South Ndebele',
+        'ndébélé du Sud',
+    ),
+    'nde': ISOCodeData(
+        '',
+        'nd',
+        'Ndebele, North; North Ndebele',
+        'ndébélé du Nord',
+    ),
+    'ndo': ISOCodeData('', 'ng', 'Ndonga', 'ndonga'),
+    'nds': ISOCodeData(
+        '',
+        '',
+        'Low German; Low Saxon; German, Low; Saxon, Low',
+        'bas allemand; bas saxon; allemand, bas; saxon, bas',
+    ),
+    'nep': ISOCodeData('', 'ne', 'Nepali', 'népalais'),
+    'new': ISOCodeData('', '', 'Nepal Bhasa; Newari', 'nepal bhasa; newari'),
+    'nia': ISOCodeData('', '', 'Nias', 'nias'),
+    'nic': ISOCodeData(
+        '',
+        '',
+        'Niger-Kordofanian languages',
+        'nigéro-kordofaniennes, langues',
+    ),
+    'niu': ISOCodeData('', '', 'Niuean', 'niué'),
+    'nno': ISOCodeData(
+        '',
+        'nn',
+        'Norwegian Nynorsk; Nynorsk, Norwegian',
+        'norvégien nynorsk; nynorsk, norvégien',
+    ),
+    'nob': ISOCodeData(
+        '',
+        'nb',
+        'Bokmål, Norwegian; Norwegian Bokmål',
+        'norvégien bokmål',
+    ),
+    'nog': ISOCodeData('', '', 'Nogai', 'nogaï; nogay'),
+    'non': ISOCodeData('', '', 'Norse, Old', 'norrois, vieux'),
+    'nor': ISOCodeData('', 'no', 'Norwegian', 'norvégien'),
+    'nqo': ISOCodeData('', '', "N'Ko", "n'ko"),
+    'nso': ISOCodeData(
+        '',
+        '',
+        'Pedi; Sepedi; Northern Sotho',
+        'pedi; sepedi; sotho du Nord',
+    ),
+    'nub': ISOCodeData('', '', 'Nubian languages', 'nubiennes, langues'),
+    'nwc': ISOCodeData(
+        '',
+        '',
+        'Classical Newari; Old Newari; Classical Nepal Bhasa',
+        'newari classique',
+    ),
+    'nya': ISOCodeData(
+        '',
+        'ny',
+        'Chichewa; Chewa; Nyanja',
+        'chichewa; chewa; nyanja',
+    ),
+    'nym': ISOCodeData('', '', 'Nyamwezi', 'nyamwezi'),
+    'nyn': ISOCodeData('', '', 'Nyankole', 'nyankolé'),
+    'nyo': ISOCodeData('', '', 'Nyoro', 'nyoro'),
+    'nzi': ISOCodeData('', '', 'Nzima', 'nzema'),
+    'oci': ISOCodeData(
+        '',
+        'oc',
+        'Occitan (post 1500)',
+        'occitan (après 1500)',
+    ),
+    'oji': ISOCodeData('', 'oj', 'Ojibwa', 'ojibwa'),
+    'ori': ISOCodeData('', 'or', 'Oriya', 'oriya'),
+    'orm': ISOCodeData('', 'om', 'Oromo', 'galla'),
+    'osa': ISOCodeData('', '', 'Osage', 'osage'),
+    'oss': ISOCodeData('', 'os', 'Ossetian; Ossetic', 'ossète'),
+    'ota': ISOCodeData(
+        '',
+        '',
+        'Turkish, Ottoman (1500-1928)',
+        'turc ottoman (1500-1928)',
+    ),
+    'oto': ISOCodeData('', '', 'Otomian languages', 'otomi, langues'),
+    'paa': ISOCodeData('', '', 'Papuan languages', 'papoues, langues'),
+    'pag': ISOCodeData('', '', 'Pangasinan', 'pangasinan'),
+    'pal': ISOCodeData('', '', 'Pahlavi', 'pahlavi'),
+    'pam': ISOCodeData('', '', 'Pampanga; Kapampangan', 'pampangan'),
+    'pan': ISOCodeData('', 'pa', 'Panjabi; Punjabi', 'pendjabi'),
+    'pap': ISOCodeData('', '', 'Papiamento', 'papiamento'),
+    'pau': ISOCodeData('', '', 'Palauan', 'palau'),
+    'peo': ISOCodeData(
+        '',
+        '',
+        'Persian, Old (ca.600-400 B.C.)',
+        'perse, vieux (ca. 600-400 av. J.-C.)',
+    ),
+    'per': ISOCodeData('fas', 'fa', 'Persian', 'persan'),
+    'phi': ISOCodeData(
+        '',
+        '',
+        'Philippine languages',
+        'philippines, langues',
+    ),
+    'phn': ISOCodeData('', '', 'Phoenician', 'phénicien'),
+    'pli': ISOCodeData('', 'pi', 'Pali', 'pali'),
+    'pol': ISOCodeData('', 'pl', 'Polish', 'polonais'),
+    'pon': ISOCodeData('', '', 'Pohnpeian', 'pohnpei'),
+    'por': ISOCodeData('', 'pt', 'Portuguese', 'portugais'),
+    'pra': ISOCodeData('', '', 'Prakrit languages', 'prâkrit, langues'),
+    'pro': ISOCodeData(
+        '',
+        '',
+        'Provençal, Old (to 1500); Occitan, Old (to 1500)',
+        "provençal ancien (jusqu'à 1500); occitan ancien (jusqu'à 1500)",
+    ),
+    'pus': ISOCodeData('', 'ps', 'Pushto; Pashto', 'pachto'),
+    'qaa': ISOCodeData(
+        '',
+        '',
+        'Reserved for local use',
+        "réservée à l'usage local",
+    ),
+    'que': ISOCodeData('', 'qu', 'Quechua', 'quechua'),
+    'raj': ISOCodeData('', '', 'Rajasthani', 'rajasthani'),
+    'rap': ISOCodeData('', '', 'Rapanui', 'rapanui'),
+    'rar': ISOCodeData(
+        '',
+        '',
+        'Rarotongan; Cook Islands Maori',
+        'rarotonga; maori des îles Cook',
+    ),
+    'roa': ISOCodeData('', '', 'Romance languages', 'romanes, langues'),
+    'roh': ISOCodeData('', 'rm', 'Romansh', 'romanche'),
+    'rom': ISOCodeData('', '', 'Romany', 'tsigane'),
+    'rum': ISOCodeData(
+        'ron',
+        'ro',
+        'Romanian; Moldavian; Moldovan',
+        'roumain; moldave',
+    ),
+    'run': ISOCodeData('', 'rn', 'Rundi', 'rundi'),
+    'rup': ISOCodeData(
+        '',
+        '',
+        'Aromanian; Arumanian; Macedo-Romanian',
+        'aroumain; macédo-roumain',
+    ),
+    'rus': ISOCodeData('', 'ru', 'Russian', 'russe'),
+    'sad': ISOCodeData('', '', 'Sandawe', 'sandawe'),
+    'sag': ISOCodeData('', 'sg', 'Sango', 'sango'),
+    'sah': ISOCodeData('', '', 'Yakut', 'iakoute'),
+    'sai': ISOCodeData(
+        '',
+        '',
+        'South American Indian languages',
+        'sud-amérindiennes, langues',
+    ),
+    'sal': ISOCodeData('', '', 'Salishan languages', 'salishennes, langues'),
+    'sam': ISOCodeData('', '', 'Samaritan Aramaic', 'samaritain'),
+    'san': ISOCodeData('', 'sa', 'Sanskrit', 'sanskrit'),
+    'sas': ISOCodeData('', '', 'Sasak', 'sasak'),
+    'sat': ISOCodeData('', '', 'Santali', 'santal'),
+    'scn': ISOCodeData('', '', 'Sicilian', 'sicilien'),
+    'sco': ISOCodeData('', '', 'Scots', 'écossais'),
+    'sel': ISOCodeData('', '', 'Selkup', 'selkoupe'),
+    'sem': ISOCodeData('', '', 'Semitic languages', 'sémitiques, langues'),
+    'sga': ISOCodeData(
+        '',
+        '',
+        'Irish, Old (to 900)',
+        "irlandais ancien (jusqu'à 900)",
+    ),
+    'sgn': ISOCodeData('', '', 'Sign Languages', 'langues des signes'),
+    'shn': ISOCodeData('', '', 'Shan', 'chan'),
+    'sid': ISOCodeData('', '', 'Sidamo', 'sidamo'),
+    'sin': ISOCodeData('', 'si', 'Sinhala; Sinhalese', 'singhalais'),
+    'sio': ISOCodeData('', '', 'Siouan languages', 'sioux, langues'),
+    'sit': ISOCodeData(
+        '',
+        '',
+        'Sino-Tibetan languages',
+        'sino-tibétaines, langues',
+    ),
+    'sla': ISOCodeData('', '', 'Slavic languages', 'slaves, langues'),
+    'slo': ISOCodeData('slk', 'sk', 'Slovak', 'slovaque'),
+    'slv': ISOCodeData('', 'sl', 'Slovenian', 'slovène'),
+    'sma': ISOCodeData('', '', 'Southern Sami', 'sami du Sud'),
+    'sme': ISOCodeData('', 'se', 'Northern Sami', 'sami du Nord'),
+    'smi': ISOCodeData('', '', 'Sami languages', 'sames, langues'),
+    'smj': ISOCodeData('', '', 'Lule Sami', 'sami de Lule'),
+    'smn': ISOCodeData('', '', 'Inari Sami', "sami d'Inari"),
+    'smo': ISOCodeData('', 'sm', 'Samoan', 'samoan'),
+    'sms': ISOCodeData('', '', 'Skolt Sami', 'sami skolt'),
+    'sna': ISOCodeData('', 'sn', 'Shona', 'shona'),
+    'snd': ISOCodeData('', 'sd', 'Sindhi', 'sindhi'),
+    'snk': ISOCodeData('', '', 'Soninke', 'soninké'),
+    'sog': ISOCodeData('', '', 'Sogdian', 'sogdien'),
+    'som': ISOCodeData('', 'so', 'Somali', 'somali'),
+    'son': ISOCodeData('', '', 'Songhai languages', 'songhai, langues'),
+    'sot': ISOCodeData('', 'st', 'Sotho, Southern', 'sotho du Sud'),
+    'spa': ISOCodeData('', 'es', 'Spanish; Castilian', 'espagnol; castillan'),
+    'srd': ISOCodeData('', 'sc', 'Sardinian', 'sarde'),
+    'srn': ISOCodeData('', '', 'Sranan Tongo', 'sranan tongo'),
+    'srp': ISOCodeData('', 'sr', 'Serbian', 'serbe'),
+    'srr': ISOCodeData('', '', 'Serer', 'sérère'),
+    'ssa': ISOCodeData(
+        '',
+        '',
+        'Nilo-Saharan languages',
+        'nilo-sahariennes, langues',
+    ),
+    'ssw': ISOCodeData('', 'ss', 'Swati', 'swati'),
+    'suk': ISOCodeData('', '', 'Sukuma', 'sukuma'),
+    'sun': ISOCodeData('', 'su', 'Sundanese', 'soundanais'),
+    'sus': ISOCodeData('', '', 'Susu', 'soussou'),
+    'sux': ISOCodeData('', '', 'Sumerian', 'sumérien'),
+    'swa': ISOCodeData('', 'sw', 'Swahili', 'swahili'),
+    'swe': ISOCodeData('', 'sv', 'Swedish', 'suédois'),
+    'syc': ISOCodeData('', '', 'Classical Syriac', 'syriaque classique'),
+    'syr': ISOCodeData('', '', 'Syriac', 'syriaque'),
+    'tah': ISOCodeData('', 'ty', 'Tahitian', 'tahitien'),
+    'tai': ISOCodeData('', '', 'Tai languages', 'tai, langues'),
+    'tam': ISOCodeData('', 'ta', 'Tamil', 'tamoul'),
+    'tat': ISOCodeData('', 'tt', 'Tatar', 'tatar'),
+    'tel': ISOCodeData('', 'te', 'Telugu', 'télougou'),
+    'tem': ISOCodeData('', '', 'Timne', 'temne'),
+    'ter': ISOCodeData('', '', 'Tereno', 'tereno'),
+    'tet': ISOCodeData('', '', 'Tetum', 'tetum'),
+    'tgk': ISOCodeData('', 'tg', 'Tajik', 'tadjik'),
+    'tgl': ISOCodeData('', 'tl', 'Tagalog', 'tagalog'),
+    'tha': ISOCodeData('', 'th', 'Thai', 'thaï'),
+    'tib': ISOCodeData('bod', 'bo', 'Tibetan', 'tibétain'),
+    'tig': ISOCodeData('', '', 'Tigre', 'tigré'),
+    'tir': ISOCodeData('', 'ti', 'Tigrinya', 'tigrigna'),
+    'tiv': ISOCodeData('', '', 'Tiv', 'tiv'),
+    'tkl': ISOCodeData('', '', 'Tokelau', 'tokelau'),
+    'tlh': ISOCodeData('', '', 'Klingon; tlhIngan-Hol', 'klingon'),
+    'tli': ISOCodeData('', '', 'Tlingit', 'tlingit'),
+    'tmh': ISOCodeData('', '', 'Tamashek', 'tamacheq'),
+    'tog': ISOCodeData('', '', 'Tonga (Nyasa)', 'tonga (Nyasa)'),
+    'ton': ISOCodeData(
+        '',
+        'to',
+        'Tonga (Tonga Islands)',
+        'tongan (Îles Tonga)',
+    ),
+    'tpi': ISOCodeData('', '', 'Tok Pisin', 'tok pisin'),
+    'tsi': ISOCodeData('', '', 'Tsimshian', 'tsimshian'),
+    'tsn': ISOCodeData('', 'tn', 'Tswana', 'tswana'),
+    'tso': ISOCodeData('', 'ts', 'Tsonga', 'tsonga'),
+    'tuk': ISOCodeData('', 'tk', 'Turkmen', 'turkmène'),
+    'tum': ISOCodeData('', '', 'Tumbuka', 'tumbuka'),
+    'tup': ISOCodeData('', '', 'Tupi languages', 'tupi, langues'),
+    'tur': ISOCodeData('', 'tr', 'Turkish', 'turc'),
+    'tut': ISOCodeData('', '', 'Altaic languages', 'altaïques, langues'),
+    'tvl': ISOCodeData('', '', 'Tuvalu', 'tuvalu'),
+    'twi': ISOCodeData('', 'tw', 'Twi', 'twi'),
+    'tyv': ISOCodeData('', '', 'Tuvinian', 'touva'),
+    'udm': ISOCodeData('', '', 'Udmurt', 'oudmourte'),
+    'uga': ISOCodeData('', '', 'Ugaritic', 'ougaritique'),
+    'uig': ISOCodeData('', 'ug', 'Uighur; Uyghur', 'ouïgour'),
+    'ukr': ISOCodeData('', 'uk', 'Ukrainian', 'ukrainien'),
+    'umb': ISOCodeData('', '', 'Umbundu', 'umbundu'),
+    'und': ISOCodeData('', '', 'Undetermined', 'indéterminée'),
+    'urd': ISOCodeData('', 'ur', 'Urdu', 'ourdou'),
+    'uzb': ISOCodeData('', 'uz', 'Uzbek', 'ouszbek'),
+    'vai': ISOCodeData('', '', 'Vai', 'vaï'),
+    'ven': ISOCodeData('', 've', 'Venda', 'venda'),
+    'vie': ISOCodeData('', 'vi', 'Vietnamese', 'vietnamien'),
+    'vol': ISOCodeData('', 'vo', 'Volapük', 'volapük'),
+    'vot': ISOCodeData('', '', 'Votic', 'vote'),
+    'wak': ISOCodeData('', '', 'Wakashan languages', 'wakashanes, langues'),
+    'wal': ISOCodeData('', '', 'Wolaitta; Wolaytta', 'wolaitta; wolaytta'),
+    'war': ISOCodeData('', '', 'Waray', 'waray'),
+    'was': ISOCodeData('', '', 'Washo', 'washo'),
+    'wel': ISOCodeData('cym', 'cy', 'Welsh', 'gallois'),
+    'wen': ISOCodeData('', '', 'Sorbian languages', 'sorabes, langues'),
+    'wln': ISOCodeData('', 'wa', 'Walloon', 'wallon'),
+    'wol': ISOCodeData('', 'wo', 'Wolof', 'wolof'),
+    'xal': ISOCodeData('', '', 'Kalmyk; Oirat', 'kalmouk; oïrat'),
+    'xho': ISOCodeData('', 'xh', 'Xhosa', 'xhosa'),
+    'yao': ISOCodeData('', '', 'Yao', 'yao'),
+    'yap': ISOCodeData('', '', 'Yapese', 'yapois'),
+    'yid': ISOCodeData('', 'yi', 'Yiddish', 'yiddish'),
+    'yor': ISOCodeData('', 'yo', 'Yoruba', 'yoruba'),
+    'ypk': ISOCodeData('', '', 'Yupik languages', 'yupik, langues'),
+    'zap': ISOCodeData('', '', 'Zapotec', 'zapotèque'),
+    'zbl': ISOCodeData(
+        '',
+        '',
+        'Blissymbols; Blissymbolics; Bliss',
+        'symboles Bliss; Bliss',
+    ),
+    'zen': ISOCodeData('', '', 'Zenaga', 'zenaga'),
+    'zgh': ISOCodeData(
+        '',
+        '',
+        'Standard Moroccan Tamazight',
+        'amazighe standard marocain',
+    ),
+    'zha': ISOCodeData('', 'za', 'Zhuang; Chuang', 'zhuang; chuang'),
+    'znd': ISOCodeData('', '', 'Zande languages', 'zandé, langues'),
+    'zul': ISOCodeData('', 'zu', 'Zulu', 'zoulou'),
+    'zun': ISOCodeData('', '', 'Zuni', 'zuni'),
+    'zxx': ISOCodeData(
+        '',
+        '',
+        'No linguistic content; Not applicable',
+        'pas de contenu linguistique; non applicable',
+    ),
+    'zza': ISOCodeData(
+        '',
+        '',
+        'Zaza; Dimili; Dimli; Kirdki; Kirmanjki; Zazaki',
+        'zaza; dimili; dimli; kirdki; kirmanjki; zazaki',
+    ),
+}
+
+
+def iso_639_2_from_3(iso3: str) -> str:
+    """Convert ISO 639-3 code to ISO 639-2 code."""
+    if iso3 in ISO_639_3:
+        return ISO_639_3[iso3].alpha_2
+    else:
+        return ""

src/ocrmypdf/optimize.py

@@ -3,7 +3,6 @@
 
 """Post-processing image optimization of OCR PDFs."""
 
-
 from __future__ import annotations
 
 import logging
@@ -11,9 +10,10 @@ import sys
 import tempfile
 import threading
 from collections import defaultdict
+from collections.abc import Callable, Iterator, MutableSet, Sequence
 from os import fspath
 from pathlib import Path
-from typing import Callable, Iterator, MutableSet, NamedTuple, NewType, Sequence
+from typing import Any, NamedTuple, NewType
 from zlib import compress
 
 import img2pdf
@@ -28,11 +28,13 @@ from pikepdf import (
     Stream,
     UnsupportedImageTypeError,
 )
+from pikepdf.models.image import HifiPrintImageNotTranscodableError
 from PIL import Image
 
 from ocrmypdf._concurrent import Executor, SerialExecutor
 from ocrmypdf._exec import jbig2enc, pngquant
 from ocrmypdf._jobcontext import PdfContext
+from ocrmypdf._progressbar import ProgressBar
 from ocrmypdf.exceptions import OutputFileAccessError
 from ocrmypdf.helpers import IMG2PDF_KWARGS, safe_symlink
 
@@ -68,12 +70,9 @@ def jpg_name(root: Path, xref: Xref) -> Path:
 
 
 def extract_image_filter(
-    pdf: Pdf, root: Path, image: Stream, xref: Xref
+    image: Stream, xref: Xref
 ) -> tuple[PdfImage, tuple[Name, Object]] | None:
     """Determine if an image is extractable."""
-    del pdf  # unused args
-    del root
-
     if image.Subtype != Name.Image:
         return None
     if image.Length < 100:
@@ -91,6 +90,7 @@ def extract_image_filter(
         if (
             len(pim.filter_decodeparms) == 2
             and first_filtdp[0] == Name.FlateDecode
+            and first_filtdp[1] is not None
             and first_filtdp[1].get(Name.Predictor, 1) == 1
             and second_filtdp[0] == Name.DCTDecode
             and not second_filtdp[1]
@@ -131,7 +131,7 @@ def extract_image_jbig2(
     """Extract an image, saving it as a JBIG2 file."""
     del options  # unused arg
 
-    result = extract_image_filter(pdf, root, image, xref)
+    result = extract_image_filter(image, xref)
     if result is None:
         return None
     pim, filtdp = result
@@ -155,6 +155,13 @@ def extract_image_jbig2(
                 with imgname.open('wb') as f:
                     ext = pim.extract_to(stream=f)
                 imgname.rename(imgname.with_suffix(ext))
+            except NotImplementedError as e:
+                if '/Decode' in str(e):
+                    log.debug(
+                        f"xref {xref}: skipping image with unsupported Decode table"
+                    )
+                    return None
+                raise
             except UnsupportedImageTypeError:
                 return None
             finally:
@@ -171,7 +178,7 @@ def extract_image_generic(
     *, pdf: Pdf, root: Path, image: Stream, xref: Xref, options
 ) -> XrefExt | None:
     """Generic image extraction."""
-    result = extract_image_filter(pdf, root, image, xref)
+    result = extract_image_filter(image, xref)
     if result is None:
         return None
     pim, filtdp = result
@@ -194,7 +201,7 @@ def extract_image_generic(
             with imgname.open('wb') as f:
                 ext = pim.extract_to(stream=f)
             imgname.rename(imgname.with_suffix(ext))
-        except UnsupportedImageTypeError:
+        except (UnsupportedImageTypeError, HifiPrintImageNotTranscodableError):
             return None
         return XrefExt(xref, ext)
     elif (
@@ -250,6 +257,9 @@ def _find_image_xrefs_container(
     for _imname, image in dict(xobjs).items():
         if image.objgen[1] != 0:
             continue  # Ignore images in an incremental PDF
+        xref = Xref(image.objgen[0])
+        if xref in include_xrefs or xref in exclude_xrefs:
+            continue  # Already processed
         if Name.Subtype in image and image.Subtype == Name.Form:
             # Recurse into Form XObjects
             log.debug(f"Recursing into Form XObject {_imname} in page {pageno}")
@@ -263,7 +273,6 @@ def _find_image_xrefs_container(
                 depth + 1,
             )
             continue
-        xref = Xref(image.objgen[0])
         if Name.SMask in image:
             # Ignore soft masks
             smask_xref = Xref(image.SMask.objgen[0])
@@ -282,7 +291,7 @@ def _find_image_xrefs(pdf: Pdf):
 
     for pageno, page in enumerate(pdf.pages):
         _find_image_xrefs_container(
-            pdf, page, pageno, include_xrefs, exclude_xrefs, pageno_for_xref
+            pdf, page.obj, pageno, include_xrefs, exclude_xrefs, pageno_for_xref
         )
 
     working_xrefs = include_xrefs - exclude_xrefs
@@ -370,7 +379,7 @@ def _produce_jbig2_images(
                 options.jbig2_threshold,
             )
 
-    def jbig2_single_args(root, groups: dict[int, list[XrefExt]]):
+    def jbig2_single_args(root: Path, groups: dict[int, list[XrefExt]]):
         for group, xref_exts in groups.items():
             prefix = f'group{group:08d}'
             # Second loop is to ensure multiple images per page are unpacked
@@ -385,15 +394,15 @@ def _produce_jbig2_images(
 
     if options.jbig2_page_group_size > 1:
         jbig2_args = jbig2_group_args
-        jbig2_convert = jbig2enc.convert_group_mp
+        jbig2_convert = jbig2enc.convert_group
     else:
         jbig2_args = jbig2_single_args
-        jbig2_convert = jbig2enc.convert_single_mp
+        jbig2_convert = jbig2enc.convert_single
 
     executor(
         use_threads=True,
         max_workers=options.jobs,
-        tqdm_kwargs=dict(
+        progress_kwargs=dict(
             total=len(jbig2_groups),
             desc="JBIG2",
             unit='item',
@@ -449,9 +458,9 @@ def convert_to_jbig2(
             )
 
 
-def _optimize_jpeg(args: tuple[Xref, Path, Path, int]) -> tuple[Xref, Path | None]:
-    xref, in_jpg, opt_jpg, jpeg_quality = args
-
+def _optimize_jpeg(
+    xref: Xref, in_jpg: Path, opt_jpg: Path, jpeg_quality: int
+) -> tuple[Xref, Path | None]:
     with Image.open(in_jpg) as im:
         im.save(opt_jpg, optimize=True, quality=jpeg_quality)
 
@@ -473,7 +482,7 @@ def transcode_jpegs(
             opt_jpg = in_jpg.with_suffix('.opt.jpg')
             yield xref, in_jpg, opt_jpg, options.jpeg_quality
 
-    def finish_jpeg(result: tuple[Xref, Path | None], pbar):
+    def finish_jpeg(result: tuple[Xref, Path | None], pbar: ProgressBar):
         xref, opt_jpg = result
         if opt_jpg:
             compdata = opt_jpg.read_bytes()  # JPEG can inserted into PDF as is
@@ -484,7 +493,7 @@ def transcode_jpegs(
     executor(
         use_threads=True,  # Processes are significantly slower at this task
         max_workers=options.jobs,
-        tqdm_kwargs=dict(
+        progress_kwargs=dict(
             desc="Recompressing JPEGs",
             total=len(jpegs),
             unit='image',
@@ -499,7 +508,7 @@ def transcode_jpegs(
 def _find_deflatable_jpeg(
     *, pdf: Pdf, root: Path, image: Stream, xref: Xref, options
 ) -> XrefExt | None:
-    result = extract_image_filter(pdf, root, image, xref)
+    result = extract_image_filter(image, xref)
     if result is None:
         return None
     _pim, filtdp = result
@@ -510,8 +519,9 @@ def _find_deflatable_jpeg(
     return None
 
 
-def _deflate_jpeg(args: tuple[Pdf, threading.Lock, Xref, int]) -> tuple[Xref, bytes]:
-    pdf, lock, xref, complevel = args
+def _deflate_jpeg(
+    pdf: Pdf, lock: threading.Lock, xref: Xref, complevel: int
+) -> tuple[Xref, bytes]:
     with lock:
         xobj = pdf.get_object(xref, 0)
         try:
@@ -546,7 +556,7 @@ def deflate_jpegs(pdf: Pdf, root: Path, options, executor: Executor) -> None:
         for xref in jpegs:
             yield pdf, lock, xref, complevel
 
-    def finish(result, pbar):
+    def finish(result: tuple[Xref, bytes], pbar: ProgressBar):
         xref, compdata = result
         if len(compdata) > 0:
             with lock:
@@ -557,7 +567,7 @@ def deflate_jpegs(pdf: Pdf, root: Path, options, executor: Executor) -> None:
     executor(
         use_threads=True,  # We're sharing the pdf directly, must use threads
         max_workers=options.jobs,
-        tqdm_kwargs=dict(
+        progress_kwargs=dict(
             desc="Deflating JPEGs",
             total=len(jpegs),
             unit='image',
@@ -616,7 +626,7 @@ def transcode_pngs(
     image_name_fn: Callable[[Path, Xref], Path],
     root: Path,
     options,
-    executor,
+    executor: Executor,
 ) -> None:
     """Apply lossy transcoding to PNGs."""
     modified: MutableSet[Xref] = set()
@@ -640,13 +650,13 @@ def transcode_pngs(
         executor(
             use_threads=True,
             max_workers=options.jobs,
-            tqdm_kwargs=dict(
+            progress_kwargs=dict(
                 desc="PNGs",
                 total=len(images),
                 unit='image',
                 disable=not options.progress_bar,
             ),
-            task=pngquant.quantize_mp,
+            task=pngquant.quantize,
             task_arguments=pngquant_args(),
         )
 
@@ -661,8 +671,8 @@ DEFAULT_EXECUTOR = SerialExecutor()
 def optimize(
     input_file: Path,
     output_file: Path,
-    context,
-    save_settings,
+    context: PdfContext,
+    save_settings: dict[str, Any],
     executor: Executor = DEFAULT_EXECUTOR,
 ) -> Path:
     """Optimize images in a PDF file."""

src/ocrmypdf/pdfa.py

@@ -6,9 +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
 
 import pikepdf
 
@@ -90,7 +90,7 @@ def generate_pdfa_ps(target_filename: Path, icc: str = 'sRGB'):
         icc: ICC identifier such as 'sRGB'
     References:
         Adobe PDFMARK Reference:
-        https://www.adobe.com/content/dam/acom/en/devnet/acrobat/pdfs/pdfmark_reference.pdf
+        https://opensource.adobe.com/dc-acrobat-sdk-docs/library/pdfmark/
     """
     if icc != 'sRGB':
         raise NotImplementedError("Only supporting sRGB")

src/ocrmypdf/pdfinfo/info.py

@@ -10,34 +10,37 @@ import atexit
 import logging
 import re
 import statistics
-import sys
 from collections import defaultdict
-from contextlib import ExitStack
+from collections.abc import Callable, Container, Iterable, Iterator, Mapping, Sequence
+from contextlib import contextmanager
 from decimal import Decimal
 from enum import Enum, auto
 from functools import partial
 from math import hypot, inf, isclose
 from os import PathLike
 from pathlib import Path
-from typing import Container, Iterable, Iterator, Mapping, NamedTuple, Sequence, Tuple
+from typing import NamedTuple
 from warnings import warn
 
+from pdfminer.layout import LTPage, LTTextBox
 from pikepdf import (
+    Matrix,
     Name,
     Object,
     Page,
     Pdf,
     PdfImage,
     PdfInlineImage,
-    PdfMatrix,
+    Stream,
     UnsupportedImageTypeError,
     parse_content_stream,
 )
 
 from ocrmypdf._concurrent import Executor, SerialExecutor
+from ocrmypdf._progressbar import ProgressBar
 from ocrmypdf.exceptions import EncryptedPdfError, InputFileError
 from ocrmypdf.helpers import Resolution, available_cpu_count, pikepdf_enable_mmap
-from ocrmypdf.pdfinfo.layout import get_page_analysis, get_text_boxes
+from ocrmypdf.pdfinfo.layout import LTStateAwareChar, get_page_analysis, get_text_boxes
 
 logger = logging.getLogger()
 
@@ -73,7 +76,7 @@ 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,
@@ -205,7 +208,7 @@ def _interpret_contents(contentstream: Object, initial_shorthand=UNIT_SQUARE):
     CTM unchanged.
     """
     stack = []
-    ctm = PdfMatrix(initial_shorthand)
+    ctm = Matrix(initial_shorthand)
     xobject_settings: list[XobjectSettings] = []
     inline_images: list[InlineSettings] = []
     name_index = defaultdict(lambda: [])
@@ -236,7 +239,13 @@ def _interpret_contents(contentstream: Object, initial_shorthand=UNIT_SQUARE):
                 # to do. Just pretend nothing happened, keep calm and carry on.
                 warn("PDF graphics stack underflowed - PDF may be malformed")
         elif operator == 'cm':
-            ctm = PdfMatrix(operands) @ ctm
+            try:
+                ctm = Matrix(operands) @ ctm
+            except ValueError:
+                raise InputFileError(
+                    "PDF content stream is corrupt - this PDF is malformed. "
+                    "Use a PDF editor that is capable of visually inspecting the PDF."
+                )
         elif operator == 'Do':
             image_name = operands[0]
             settings = XobjectSettings(
@@ -355,13 +364,23 @@ class ImageInfo:
         if inline is not None:
             self._origin = 'inline'
             pim = inline
-        elif pdfimage is not None:
+        elif pdfimage is not None and isinstance(pdfimage, Stream):
             self._origin = 'xobject'
             pim = PdfImage(pdfimage)
         else:
             raise ValueError("Either pdfimage or inline must be set")
-        self._width = pim.width
-        self._height = pim.height
+        if pim.obj.get(Name.SMask, None) is not None:
+            # SMask is pretty much an alpha channel, but in PDF it's possible
+            # for channel to have different dimensions than the image
+            # itself. Some PDF writers use this to create a grayscale stencil
+            # mask. For our purposes, the effective size is the size of the
+            # larger component (image or smask).
+            smask = pim.obj[Name.SMask]
+            self._width = max(smask.get(Name.Width, 0), pim.width)
+            self._height = max(smask.get(Name.Height, 0), pim.height)
+        else:
+            self._width = pim.width
+            self._height = pim.height
 
         # If /ImageMask is true, then this image is a stencil mask
         # (Images that draw with this stencil mask will have a reference to
@@ -384,33 +403,43 @@ class ImageInfo:
         if self._enc == Encoding.jpeg2000:
             self._color = Colorspace.jpeg2000
 
-        if self._color == Colorspace.icc:
-            # Check the ICC profile to determine actual colorspace
-            try:
-                pim_icc = pim.icc
-                if pim_icc.profile.xcolor_space == 'GRAY':
-                    self._comp = 1
-                elif pim_icc.profile.xcolor_space == 'CMYK':
-                    self._comp = 4
-                else:
-                    self._comp = 3
-            except (AttributeError, UnsupportedImageTypeError) as ex:
-                self._comp = None
-                logger.warning(
-                    f"An image with a corrupt or unreadable ICC profile was found. "
-                    f"The output PDF may not match the input PDF visually: {ex}. {self}"
-                )
+        self._comp = None
+        if self._color == Colorspace.icc and isinstance(pim, PdfImage):
+            self._comp = self._init_icc(pim)
         else:
             if isinstance(self._color, Colorspace):
                 self._comp = FRIENDLY_COMP.get(self._color)
-            else:
-                self._comp = None
-
             # Bit of a hack... infer grayscale if component count is uncertain
             # but encoding only supports monochrome.
             if self._comp is None and self._enc in (Encoding.ccitt, Encoding.jbig2):
                 self._comp = FRIENDLY_COMP[Colorspace.gray]
 
+    def _init_icc(self, pim: PdfImage):
+        try:
+            icc = pim.icc
+        except UnsupportedImageTypeError as e:
+            logger.warning(
+                f"An image with a corrupt or unreadable ICC profile was found. "
+                f"Output PDF may not match the input PDF visually: {e}. {self}"
+            )
+            return None
+        # Check the ICC profile to determine actual colorspace
+        if icc is None or not hasattr(icc, 'profile'):
+            logger.warning(
+                f"An image with an ICC profile but no ICC profile data was found. "
+                f"The output PDF may not match the input PDF visually. {self}"
+            )
+            return None
+        try:
+            if icc.profile.xcolor_space == 'GRAY':
+                return 1
+            elif icc.profile.xcolor_space == 'CMYK':
+                return 4
+            else:
+                return 3
+        except AttributeError:
+            return None
+
     @property
     def name(self):
         """Name of the image as it appears in the PDF."""
@@ -472,7 +501,7 @@ class ImageInfo:
         """Physical area of the image in square inches."""
         if not self.renderable:
             return 0.0
-        return float(self.width * self.dpi.x * self.height * self.dpi.y)
+        return float((self.width / self.dpi.x) * (self.height / self.dpi.y))
 
     def __repr__(self):
         """Return a string representation of the image."""
@@ -554,7 +583,7 @@ def _find_form_xobject_images(pdf: Pdf, container: Object, contentsinfo: Content
     xobjs = resources[Name.XObject].as_dict()
     for xobj in xobjs:
         candidate = xobjs[xobj]
-        if candidate is None or candidate[Name.Subtype] != Name.Form:
+        if candidate is None or candidate.get(Name.Subtype) != Name.Form:
             continue
 
         form_xobject = candidate
@@ -600,12 +629,12 @@ def _process_content_streams(
     ):
         # 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()
+        ctm = Matrix(shorthand) if shorthand else Matrix()
 
         # A Form XObject may provide its own matrix to map form space into
         # user space. Get this if one exists
-        form_shorthand = container.get(Name.Matrix, PdfMatrix.identity())
-        form_matrix = PdfMatrix(form_shorthand)
+        form_shorthand = container.get(Name.Matrix, Matrix())
+        form_matrix = Matrix(form_shorthand)
 
         # Concatenate form matrix with CTM to ensure CTM is correct for
         # drawing this instance of the XObject
@@ -654,7 +683,9 @@ 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.
@@ -662,7 +693,8 @@ 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)
@@ -688,29 +720,41 @@ def _pdf_pageinfo_sync_init(pdf: Pdf, infile: Path, pdfminer_loglevel):
         atexit.register(on_process_close)
 
 
-def _pdf_pageinfo_sync(args):
-    pageno, thread_pdf, infile, check_pages, detailed_analysis = args
-    pdf = thread_pdf if thread_pdf is not None else worker_pdf
-    with ExitStack() as stack:
-        if not pdf:  # When called with SerialExecutor
-            pdf = stack.enter_context(Pdf.open(infile))
-        page = PageInfo(pdf, pageno, infile, check_pages, detailed_analysis)
-        return page
+@contextmanager
+def _pdf_pageinfo_sync_pdf(thread_pdf: Pdf | None, infile: Path):
+    if thread_pdf is not None:
+        yield thread_pdf
+    elif worker_pdf is not None:
+        yield worker_pdf
+    else:
+        with Pdf.open(infile) as pdf:
+            yield pdf
+
+
+def _pdf_pageinfo_sync(
+    pageno: int,
+    thread_pdf: Pdf | None,
+    infile: Path,
+    check_pages: Container[int],
+    detailed_analysis: bool,
+) -> PageInfo:
+    with _pdf_pageinfo_sync_pdf(thread_pdf, infile) as pdf:
+        return PageInfo(pdf, pageno, infile, check_pages, detailed_analysis)
 
 
 def _pdf_pageinfo_concurrent(
     pdf,
     executor: Executor,
+    max_workers: int,
+    use_threads: bool,
     infile,
     progbar,
-    max_workers,
     check_pages,
-    detailed_analysis=False,
+    detailed_analysis: bool = False,
 ) -> Sequence[PageInfo | None]:
-    pages: Sequence[PageInfo | None] = [None] * len(pdf.pages)
+    pages: list[PageInfo | None] = [None] * len(pdf.pages)
 
-    def update_pageinfo(result, pbar):
-        page = result
+    def update_pageinfo(page: PageInfo, pbar: ProgressBar):
         if not page:
             raise InputFileError("Could read a page in the PDF")
         pages[page.pageno] = page
@@ -721,13 +765,17 @@ def _pdf_pageinfo_concurrent(
 
     total = len(pdf.pages)
 
-    use_threads = False  # No performance gain if threaded due to GIL
     n_workers = min(1 + len(pages) // 4, max_workers)
     if n_workers == 1:
-        # But if we decided on only one worker, there is no point in using
+        # If we decided on only one worker, there is no point in using
         # a separate process.
         use_threads = True
 
+    if use_threads and n_workers > 1:
+        # If we are using threads, there is no point in using more than one
+        # worker thread - they will just fight over the GIL.
+        n_workers = 1
+
     # If we use a thread, we can pass the already-open Pdf for them to use
     # If we use processes, we pass a None which tells the init function to open its
     # own
@@ -737,10 +785,15 @@ def _pdf_pageinfo_concurrent(
         (n, initial_pdf, infile, check_pages, detailed_analysis) for n in range(total)
     )
     assert n_workers == 1 if use_threads else n_workers >= 1, "Not multithreadable"
+    logger.debug(
+        f"Gathering info with {n_workers} "
+        + ('thread' if use_threads else 'process')
+        + " workers"
+    )
     executor(
         use_threads=use_threads,
         max_workers=n_workers,
-        tqdm_kwargs=dict(
+        progress_kwargs=dict(
             total=total, desc="Scanning contents", unit='page', disable=not progbar
         ),
         worker_initializer=partial(
@@ -812,16 +865,25 @@ class PageInfo:
         detailed_analysis: bool,
     ):
         page: Page = pdf.pages[pageno]
-        mediabox = [Decimal(d) for d in page.MediaBox.as_list()]
+        mediabox = [Decimal(d) for d in page.mediabox.as_list()]
         width_pt = mediabox[2] - mediabox[0]
         height_pt = mediabox[3] - mediabox[1]
 
+        # self._artbox = [float(d) for d in page.artbox.as_list()]
+        # self._bleedbox = [float(d) for d in page.bleedbox.as_list()]
+        self._cropbox = [float(d) for d in page.cropbox.as_list()]
+        self._mediabox = [float(d) for d in page.mediabox.as_list()]
+        self._trimbox = [float(d) for d in page.trimbox.as_list()]
+
         check_this_page = pageno in check_pages
 
         if check_this_page and detailed_analysis:
             pscript5_mode = str(pdf.docinfo.get(Name.Creator)).startswith('PScript5')
             miner = get_page_analysis(infile, pageno, pscript5_mode)
-            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)
@@ -929,6 +991,21 @@ class PageInfo:
         else:
             raise ValueError("rotation must be a cardinal angle")
 
+    @property
+    def cropbox(self) -> FloatRect:
+        """Return cropbox of page in PDF coordinates."""
+        return self._cropbox
+
+    @property
+    def mediabox(self) -> FloatRect:
+        """Return mediabox of page in PDF coordinates."""
+        return self._mediabox
+
+    @property
+    def trimbox(self) -> FloatRect:
+        """Return trimbox of page in PDF coordinates."""
+        return self._trimbox
+
     @property
     def images(self) -> list[ImageInfo]:
         """Return images."""
@@ -937,7 +1014,9 @@ 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:
@@ -996,18 +1075,12 @@ class PageInfo:
 
         weights = [area / total_drawn_area for area in image_areas]
         # Calculate harmonic mean of DPIs weighted by area
-        if sys.version_info >= (3, 10):
-            weighted_dpi = statistics.harmonic_mean(image_dpis, weights)
-        else:
-            weighted_dpi = sum(weights) / sum(
-                weight / dpi for weight, dpi in zip(weights, image_dpis)
-            )
+        weighted_dpi = statistics.harmonic_mean(image_dpis, weights)
         max_dpi = max(image_dpis)
         dpi_average_max_ratio = weighted_dpi / max_dpi
 
         arg_max_dpi = image_dpis.index(max_dpi)
         max_area_ratio = image_areas[arg_max_dpi] / total_drawn_area
-
         return PageResolutionProfile(
             weighted_dpi,
             max_dpi,
@@ -1028,7 +1101,11 @@ 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
@@ -1036,11 +1113,12 @@ class PdfInfo:
 
     def __init__(
         self,
-        infile,
+        infile: Path,
         *,
         detailed_analysis: bool = False,
         progbar: bool = False,
         max_workers: int | None = None,
+        use_threads: bool = True,
         check_pages=None,
         executor: Executor = DEFAULT_EXECUTOR,
     ):
@@ -1055,9 +1133,10 @@ class PdfInfo:
             self._pages = _pdf_pageinfo_concurrent(
                 pdf,
                 executor,
+                max_workers,
+                use_threads,
                 infile,
                 progbar,
-                max_workers,
                 check_pages=check_pages,
                 detailed_analysis=detailed_analysis,
             )
@@ -1068,6 +1147,9 @@ class PdfInfo:
                 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]:
@@ -1095,10 +1177,15 @@ class PdfInfo:
         """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."""
-        if not isinstance(self._infile, (str, Path)):
+        if not isinstance(self._infile, str | Path):
             raise NotImplementedError("can't get filename from stream")
         return self._infile
 
@@ -1124,7 +1211,7 @@ class PdfInfo:
         return f"<PdfInfo('...'), page count={len(self)}>"
 
 
-def main():
+def main():  # pragma: no cover
     """Run as a script."""
     import argparse  # pylint: disable=import-outside-toplevel
     from pprint import pprint  # pylint: disable=import-outside-toplevel

src/ocrmypdf/pdfinfo/layout.py

@@ -5,8 +5,12 @@
 from __future__ import annotations
 
 import re
+from collections.abc import Iterator, Mapping
+from contextlib import contextmanager
 from math import copysign
+from os import PathLike
 from pathlib import Path
+from typing import Any
 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,
-        font,
-        fontsize,
-        scaling,
-        rise,
-        text,
-        textwidth,
-        textdisp,
-        ncs,
-        graphicstate,
-        textstate,
-    ):
+        matrix: Matrix,
+        font: PDFFont,
+        fontsize: float,
+        scaling: float,
+        rise: float,
+        text: str,
+        textwidth: float,
+        textdisp: float | tuple[float | None, float],
+        ncs: PDFColorSpace,
+        graphicstate: PDFGraphicState,
+        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)
-        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):
+        if not isinstance(obj, LTStateAwareChar):
             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 = None
-        self.cur_item = None  # not defined in pdfminer code as it should be
+        self.result: LTPage | None = None
 
-    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):
-        """Handle undefined character."""
-        # log.info('undefined: %r, %r', font, cid)
-        return (font.fontname, cid)
-
-    def receive_layout(self, ltpage):
+    def receive_layout(self, ltpage: LTPage) -> None:
         """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
-    if pscript5_mode:
-        patcher = 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,
-        )
-        patcher.start()
-
-    try:
-        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()
+    with patch_pdfminer(pscript5_mode):
+        try:
+            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
 
     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

@@ -7,13 +7,15 @@ 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
 
 from ocrmypdf import Executor, PdfContext
+from ocrmypdf._progressbar import ProgressBar
 from ocrmypdf.helpers import Resolution
 
 if TYPE_CHECKING:
@@ -101,7 +103,6 @@ def check_options(options: Namespace) -> None:
             and the application should terminate gracefully with an informative
             message and error code.
 
-
     Note:
         This hook will be called from the main process, and may modify global state
         before child worker processes are forked.
@@ -109,7 +110,7 @@ def check_options(options: Namespace) -> None:
 
 
 @hookspec(firstresult=True)
-def get_executor(progressbar_class) -> Executor:
+def get_executor(progressbar_class: type[ProgressBar]) -> Executor:
     """Called to obtain an object that manages parallel execution.
 
     This may be used to replace OCRmyPDF's default parallel execution system
@@ -131,41 +132,24 @@ def get_executor(progressbar_class) -> Executor:
         This hook will be called from the main process, and may modify global state
         before child worker processes are forked.
 
-
     Note:
         This is a :ref:`firstresult hook<firstresult>`.
     """
 
 
 @hookspec(firstresult=True)
-def get_progressbar_class():
+def get_progressbar_class() -> type[ProgressBar]:
     """Called to obtain a class that can be used to monitor progress.
 
-    A progress bar is assumed, but this could be used for any type of monitoring.
-
-    The class should follow a tqdm-like protocol. Calling the class should return
-    a new progress bar object, which is activated with ``__enter__`` and terminated
-    ``__exit__``. An update method is called whenever the progress bar is updated.
-    Progress bar objects will not be reused; a new one will be created for each
-    group of tasks.
-
-    The progress bar is held in the main process/thread and not updated by child
-    process/threads. When a child notifies the parent of completed work, the
-    parent updates the progress bar.
-
-    The arguments are the same as `tqdm <https://github.com/tqdm/tqdm>`_ accepts.
-
-    Progress bars should never write to ``sys.stdout``, or they will corrupt the
-    output if OCRmyPDF writes a PDF to standard output.
-
-    The type of events that OCRmyPDF reports to a progress bar may change in
-    minor releases.
+    OCRmyPDF will call this function when it wants to display a progress bar.
+    The class returned by this function must be compatible with the
+    :class:`ProgressBar` protocol.
 
     Here is how OCRmyPDF will use the progress bar:
 
     Example:
         pbar_class = pm.hook.get_progressbar_class()
-        with pbar_class(**tqdm_kwargs) as pbar:
+        with pbar_class(**progress_kwargs) as pbar:
             ...
             pbar.update(1)
     """
@@ -186,7 +170,6 @@ def validate(pdfinfo: PdfInfo, options: Namespace) -> None:
             and the application should terminate gracefully with an informative
             message and error code.
 
-
     Note:
         This hook will be called from the main process, and may modify global state
         before child worker processes are forked.
@@ -230,6 +213,7 @@ def rasterize_pdf_page(
 
     Returns:
         Path: output_file if successful
+
     Note:
         This hook will be called from child processes. Modifying global state
         will not affect the main process or other child processes.
@@ -269,7 +253,6 @@ def filter_ocr_image(page: PageContext, image: Image.Image) -> Image.Image:
         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>`.
     """
@@ -307,7 +290,6 @@ def filter_page_image(page: PageContext, image_filename: Path) -> 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>`.
     """
@@ -405,7 +387,7 @@ 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
@@ -427,21 +409,42 @@ class OcrEngine(ABC):
     def generate_hocr(
         input_file: Path, output_hocr: Path, output_text: Path, options: Namespace
     ) -> None:
-        """Called to produce a hOCR file and sidecar text file."""
+        """Called to produce a hOCR file from a page image and sidecar text file.
+
+        A hOCR file is an HTML-like file that describes the position of text on a
+        page. OCRmyPDF can create a text only PDF from the hOCR file and graft it
+        onto the output PDF.
+
+        This function executes in a worker thread or worker process. OCRmyPDF
+        automatically parallelizes OCR over pages. The OCR engine should not
+        introduce more parallelism.
+
+        Args:
+            input_file: A page image on which to perform OCR.
+            output_hocr: The expected name of the output hOCR file.
+            output_text: The expected name of a text file containing the
+                recognized text.
+            options: The command line options.
+        """
 
     @staticmethod
     @abstractmethod
     def generate_pdf(
         input_file: Path, output_pdf: Path, output_text: Path, options: Namespace
     ) -> None:
-        """Called to produce a text only PDF.
+        """Called to produce a text only PDF from a page image.
+
+        A text only PDF should contain no visible material of any kind, as it
+        will be grafted onto the input PDF page. It must be sized to the
+        exact dimensions of the input image.
+
+        This function executes in a worker thread or worker process. OCRmyPDF
+        automatically parallelizes OCR over pages. The OCR engine should not
+        introduce more parallelism.
 
         Args:
             input_file: A page image on which to perform OCR.
-            output_pdf: The expected name of the output PDF, which must be
-                a single page PDF with no visible content of any kind, sized
-                to the dimensions implied by the input_file's width, height
-                and DPI. The image will be grafted onto the input PDF page.
+            output_pdf: The expected name of the output PDF.
             output_text: The expected name of a text file containing the
                 recognized text.
             options: The command line options.
@@ -468,7 +471,7 @@ def generate_pdfa(
     context: PdfContext,
     pdf_version: str,
     pdfa_part: str,
-    progressbar_class,
+    progressbar_class: type[ProgressBar] | None,
     stop_on_soft_error: bool,
 ) -> Path:
     """Generate a PDF/A.
@@ -488,14 +491,8 @@ def generate_pdfa(
             At its own discretion, the PDF/A generator may raise the version,
             but should not lower it.
         pdfa_part: The desired PDF/A compliance level, such as ``'2B'``.
-        progressbar_class: The class of a progress bar with a tqdm-like API. An
-            instance of this class will be initialized when PDF/A conversion
-            begins, using
-            ``instance = progressbar_class(total: int, desc: str, unit:str)``,
-            defining the number of work units, a user-visible description,
-            and the name of the work units ("page"). Then ``instance.update()``
-            will be called when a work unit is completed. If ``None``, no
-            progress information is reported.
+        progressbar_class: The class of a progress bar, which must implement
+            the ProgressBar protocol. If None, no progress is reported.
         stop_on_soft_error: If there is an "soft error" such that PDF/A generation
             can proceed and produce a valid PDF/A, but output may be invalid or
             may not visually resemble the original, the implementer of this hook
@@ -513,9 +510,6 @@ def generate_pdfa(
         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

@@ -3,11 +3,10 @@
 
 """Utilities to measure OCR quality."""
 
-
 from __future__ import annotations
 
 import re
-from typing import Iterable
+from collections.abc import Iterable
 
 
 class OcrQualityDictionary:

src/ocrmypdf/subprocess/__init__.py

@@ -8,11 +8,11 @@ import logging
 import os
 import re
 import sys
+from collections.abc import Callable, Mapping, Sequence
 from contextlib import suppress
 from pathlib import Path
 from subprocess import PIPE, STDOUT, CalledProcessError, CompletedProcess, Popen
 from subprocess import run as subprocess_run
-from typing import Callable, Mapping, Sequence, Union
 
 from packaging.version import Version
 
@@ -22,7 +22,7 @@ from ocrmypdf.exceptions import MissingDependencyError
 
 log = logging.getLogger(__name__)
 
-Args = Sequence[Union[Path, str]]
+Args = Sequence[Path | str]
 OsEnviron = os._Environ  # pylint: disable=protected-access
 
 
@@ -171,6 +171,7 @@ def get_version(
         ) from e
     except CalledProcessError as e:
         if e.returncode != 0:
+            log.exception(e)
             raise MissingDependencyError(
                 f"Ran program '{program}' but it exited with an error:\n{e.output}"
             ) from e

src/ocrmypdf/subprocess/_windows.py

@@ -9,17 +9,13 @@ import os
 import re
 import shutil
 import sys
+from collections.abc import Callable, Iterable, Iterator
 from itertools import chain
 from pathlib import Path
-from typing import Any, Callable, Iterable, Iterator, TypeVar
+from typing import Any, TypeAlias, TypeVar
 
 from packaging.version import InvalidVersion, Version
 
-if sys.version_info >= (3, 10):
-    from typing import TypeAlias
-else:
-    from typing_extensions import TypeAlias  # pragma: no cover
-
 if sys.platform == 'win32':
     # mypy understands 'if sys.platform' better than try/except ModuleNotFoundError
     import winreg  # pylint: disable=import-error
@@ -83,7 +79,7 @@ def registry_path_ghostscript(env=None) -> Iterator[Path]:
                 registry_subkeys(k), key=ghostscript_version_key, default=(0, 0, 0)
             )
         with winreg.OpenKey(
-            winreg.HKEY_LOCAL_MACHINE, fr"SOFTWARE\Artifex\GPL Ghostscript\{latest_gs}"
+            winreg.HKEY_LOCAL_MACHINE, rf"SOFTWARE\Artifex\GPL Ghostscript\{latest_gs}"
         ) as k:
             for _, gs_path, _ in registry_values(k):
                 yield Path(gs_path) / 'bin'

tests/cache/2400dpi/__-l__eng__000001_ocr.png__000001_ocr_hocr__hocr__txt/hocr.bin

@@ -0,0 +1,177 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN"
+    "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
+<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
+ <head>
+  <title></title>
+  <meta http-equiv="Content-Type" content="text/html;charset=utf-8"/>
+  <meta name='ocr-system' content='tesseract 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.jcdzf4up/000001_ocr.png"; bbox 0 0 4000 2864; ppageno 0; scan_res 2400 2400'>
+   <div class='ocr_carea' id='block_1_1' title="bbox 251 146 2173 237">
+    <p class='ocr_par' id='par_1_1' lang='eng' title="bbox 251 146 2173 237">
+     <span class='ocr_line' id='line_1_1' title="bbox 251 146 2173 237; baseline -0.006 5; x_size 99.418808; x_descenders 9.4188042; x_ascenders 32">
+      <span class='ocrx_word' id='word_1_1' title='bbox 251 154 274 176; x_wconf 89'>i</span>
+      <span class='ocrx_word' id='word_1_2' title='bbox 1080 146 1152 237; x_wconf 89'>a</span>
+      <span class='ocrx_word' id='word_1_3' title='bbox 1254 153 1406 235; x_wconf 92'>la</span>
+      <span class='ocrx_word' id='word_1_4' title='bbox 1500 153 2173 235; x_wconf 95'>Waterman</span>
+     </span>
+    </p>
+   </div>
+   <div class='ocr_separator' id='block_1_2' title="bbox 135 202 2180 295"></div>
+   <div class='ocr_carea' id='block_1_3' title="bbox 145 414 2929 1221">
+    <p class='ocr_par' id='par_1_2' lang='eng' title="bbox 145 414 1154 516">
+     <span class='ocr_line' id='line_1_2' title="bbox 145 414 1154 516; baseline -0.005 -4; x_size 122.38636; x_descenders 24.386362; x_ascenders 40">
+      <span class='ocrx_word' id='word_1_5' title='bbox 145 414 211 512; x_wconf 60'>4</span>
+      <span class='ocrx_word' id='word_1_6' title='bbox 318 453 551 516; x_wconf 93'>ons</span>
+      <span class='ocrx_word' id='word_1_7' title='bbox 660 430 1154 512; x_wconf 91'>linzen</span>
+     </span>
+    </p>
+
+    <p class='ocr_par' id='par_1_3' lang='eng' title="bbox 146 568 1239 667">
+     <span class='ocr_line' id='line_1_3' title="bbox 146 568 1239 667; baseline -0.004 -16; x_size 99; x_descenders 17; x_ascenders 24">
+      <span class='ocrx_word' id='word_1_8' title='bbox 146 569 209 667; x_wconf 94'>3</span>
+      <span class='ocrx_word' id='word_1_9' title='bbox 323 568 729 652; x_wconf 83'>liter</span>
+      <span class='ocrx_word' id='word_1_10' title='bbox 821 569 1239 650; x_wconf 96'>water</span>
+     </span>
+    </p>
+
+    <p class='ocr_par' id='par_1_4' lang='eng' title="bbox 148 705 645 804">
+     <span class='ocr_line' id='line_1_4' title="bbox 148 705 645 804; baseline -0.016 -14; x_size 103; x_descenders 19; x_ascenders 27">
+      <span class='ocrx_word' id='word_1_11' title='bbox 148 706 211 804; x_wconf 88'>3</span>
+      <span class='ocrx_word' id='word_1_12' title='bbox 311 705 645 789; x_wconf 52'>uien</span>
+     </span>
+    </p>
+
+    <p class='ocr_par' id='par_1_5' lang='eng' title="bbox 147 832 1154 950">
+     <span class='ocr_line' id='line_1_5' title="bbox 147 832 1154 950; baseline -0.004 -27; x_size 118; x_descenders 28; x_ascenders 30">
+      <span class='ocrx_word' id='word_1_13' title='bbox 147 832 623 950; x_wconf 91'>bloem,</span>
+      <span class='ocrx_word' id='word_1_14' title='bbox 737 843 1154 924; x_wconf 91'>boter</span>
+     </span>
+    </p>
+
+    <p class='ocr_par' id='par_1_6' lang='eng' title="bbox 148 979 1241 1087">
+     <span class='ocr_line' id='line_1_6' title="bbox 148 979 1241 1087; baseline -0.005 -21; x_size 107; x_descenders 24; x_ascenders 24">
+      <span class='ocrx_word' id='word_1_15' title='bbox 148 983 215 1066; x_wconf 88'>2</span>
+      <span class='ocrx_word' id='word_1_16' title='bbox 312 983 807 1087; x_wconf 88'>kopjes</span>
+      <span class='ocrx_word' id='word_1_17' title='bbox 905 979 1241 1062; x_wconf 92'>melk</span>
+     </span>
+    </p>
+
+    <p class='ocr_par' id='par_1_7' lang='eng' title="bbox 154 1109 2929 1221">
+     <span class='ocr_line' id='line_1_7' title="bbox 154 1109 2929 1221; baseline -0.003 -21; x_size 112; x_descenders 28; x_ascenders 26">
+      <span class='ocrx_word' id='word_1_18' title='bbox 154 1117 791 1221; x_wconf 92'>laurier,</span>
+      <span class='ocrx_word' id='word_1_19' title='bbox 906 1111 1810 1219; x_wconf 90'>kruidnagel,</span>
+      <span class='ocrx_word' id='word_1_20' title='bbox 1927 1109 2490 1219; x_wconf 90'>kerrie,</span>
+      <span class='ocrx_word' id='word_1_21' title='bbox 2615 1110 2929 1195; x_wconf 91'>zout</span>
+     </span>
+    </p>
+   </div>
+   <div class='ocr_carea' id='block_1_4' title="bbox 147 1383 3706 2731">
+    <p class='ocr_par' id='par_1_8' lang='eng' title="bbox 147 1383 3706 2731">
+     <span class='ocr_line' id='line_1_8' title="bbox 149 1383 3612 1474; baseline -0.003 -2; x_size 107.01524; x_descenders 25.01524; x_ascenders 21">
+      <span class='ocrx_word' id='word_1_22' title='bbox 149 1395 303 1474; x_wconf 93'>De</span>
+      <span class='ocrx_word' id='word_1_23' title='bbox 411 1390 902 1473; x_wconf 80'>linzgen</span>
+      <span class='ocrx_word' id='word_1_24' title='bbox 996 1409 1497 1470; x_wconf 89'>wassen</span>
+      <span class='ocrx_word' id='word_1_25' title='bbox 1595 1409 1752 1470; x_wconf 88'>en</span>
+      <span class='ocrx_word' id='word_1_26' title='bbox 1853 1385 2166 1467; x_wconf 75'>in-l</span>
+      <span class='ocrx_word' id='word_1_27' title='bbox 2275 1383 2684 1466; x_wconf 93'>liter</span>
+      <span class='ocrx_word' id='word_1_28' title='bbox 2775 1383 3278 1464; x_wconf 91'>kokend</span>
+      <span class='ocrx_word' id='word_1_29' title='bbox 3368 1401 3612 1462; x_wconf 90'>wa-</span>
+     </span>
+     <span class='ocr_line' id='line_1_9' title="bbox 157 1516 3520 1632; baseline -0.004 -21; x_size 110; x_descenders 25; x_ascenders 25">
+      <span class='ocrx_word' id='word_1_30' title='bbox 157 1531 394 1611; x_wconf 94'>ter</span>
+      <span class='ocrx_word' id='word_1_31' title='bbox 495 1527 558 1609; x_wconf 93'>1</span>
+      <span class='ocrx_word' id='word_1_32' title='bbox 658 1530 903 1632; x_wconf 84'>dag</span>
+      <span class='ocrx_word' id='word_1_33' title='bbox 1002 1527 1415 1609; x_wconf 90'>laten</span>
+      <span class='ocrx_word' id='word_1_34' title='bbox 1505 1525 1979 1611; x_wconf 58'>weken,</span>
+      <span class='ocrx_word' id='word_1_35' title='bbox 2103 1521 2167 1603; x_wconf 96'>2</span>
+      <span class='ocrx_word' id='word_1_36' title='bbox 2275 1518 2683 1603; x_wconf 83'>liter</span>
+      <span class='ocrx_word' id='word_1_37' title='bbox 2777 1519 3194 1601; x_wconf 96'>water</span>
+      <span class='ocrx_word' id='word_1_38' title='bbox 3286 1516 3520 1599; x_wconf 89'>bij</span>
+     </span>
+     <span class='ocr_line' id='line_1_10' title="bbox 152 1651 3616 1767; baseline -0.004 -21; x_size 110; x_descenders 27; x_ascenders 23">
+      <span class='ocrx_word' id='word_1_39' title='bbox 152 1668 302 1747; x_wconf 92'>de</span>
+      <span class='ocrx_word' id='word_1_40' title='bbox 407 1662 905 1747; x_wconf 91'>linzen</span>
+      <span class='ocrx_word' id='word_1_41' title='bbox 996 1682 1559 1767; x_wconf 92'>voegen,</span>
+      <span class='ocrx_word' id='word_1_42' title='bbox 1680 1659 2176 1741; x_wconf 96'>zonder</span>
+      <span class='ocrx_word' id='word_1_43' title='bbox 2267 1655 2506 1737; x_wconf 96'>het</span>
+      <span class='ocrx_word' id='word_1_44' title='bbox 2606 1655 3023 1737; x_wconf 92'>water</span>
+      <span class='ocrx_word' id='word_1_45' title='bbox 3116 1651 3616 1735; x_wconf 91'>waarin</span>
+     </span>
+     <span class='ocr_line' id='line_1_11' title="bbox 153 1782 3704 1905; baseline -0.004 -20; x_size 117; x_descenders 23; x_ascenders 34">
+      <span class='ocrx_word' id='word_1_46' title='bbox 153 1824 305 1885; x_wconf 91'>ze</span>
+      <span class='ocrx_word' id='word_1_47' title='bbox 407 1800 979 1905; x_wconf 85'>geweekt</span>
+      <span class='ocrx_word' id='word_1_48' title='bbox 1089 1797 1412 1900; x_wconf 96'>zijn</span>
+      <span class='ocrx_word' id='word_1_49' title='bbox 1510 1796 1672 1878; x_wconf 96'>af</span>
+      <span class='ocrx_word' id='word_1_50' title='bbox 1770 1782 1914 1876; x_wconf 93'>te</span>
+      <span class='ocrx_word' id='word_1_51' title='bbox 2019 1792 2576 1899; x_wconf 54'>gieten,</span>
+      <span class='ocrx_word' id='word_1_52' title='bbox 2690 1790 2850 1874; x_wconf 93'>De</span>
+      <span class='ocrx_word' id='word_1_53' title='bbox 2948 1791 3357 1872; x_wconf 89'>helft</span>
+      <span class='ocrx_word' id='word_1_54' title='bbox 3452 1811 3704 1873; x_wconf 96'>van</span>
+     </span>
+     <span class='ocr_line' id='line_1_12' title="bbox 151 1928 3593 2035; baseline -0.003 -13; x_size 109; x_descenders 25; x_ascenders 25">
+      <span class='ocrx_word' id='word_1_55' title='bbox 151 1942 305 2024; x_wconf 92'>de</span>
+      <span class='ocrx_word' id='word_1_56' title='bbox 403 1940 735 2021; x_wconf 89'>uien</span>
+      <span class='ocrx_word' id='word_1_57' title='bbox 829 1938 1330 2022; x_wconf 91'>bakken</span>
+      <span class='ocrx_word' id='word_1_58' title='bbox 1419 1939 1659 2018; x_wconf 92'>met</span>
+      <span class='ocrx_word' id='word_1_59' title='bbox 1770 1933 2346 2016; x_wconf 91'>laurier</span>
+      <span class='ocrx_word' id='word_1_60' title='bbox 2447 1953 2603 2014; x_wconf 91'>en</span>
+      <span class='ocrx_word' id='word_1_61' title='bbox 2691 1928 3593 2035; x_wconf 63'>Kruidnagel.</span>
+     </span>
+     <span class='ocr_line' id='line_1_13' title="bbox 151 2067 3451 2180; baseline -0.004 -21; x_size 108; x_descenders 25; x_ascenders 24">
+      <span class='ocrx_word' id='word_1_62' title='bbox 151 2076 473 2159; x_wconf 92'>Alle</span>
+      <span class='ocrx_word' id='word_1_63' title='bbox 569 2076 965 2180; x_wconf 88'>uien,</span>
+      <span class='ocrx_word' id='word_1_64' title='bbox 1079 2072 1578 2156; x_wconf 90'>kerrie</span>
+      <span class='ocrx_word' id='word_1_65' title='bbox 1685 2092 1837 2153; x_wconf 93'>en</span>
+      <span class='ocrx_word' id='word_1_66' title='bbox 1938 2072 2254 2153; x_wconf 81'>zgout</span>
+      <span class='ocrx_word' id='word_1_67' title='bbox 2355 2068 2593 2172; x_wconf 43'>bij</span>
+      <span class='ocrx_word' id='word_1_68' title='bbox 2696 2071 2850 2150; x_wconf 91'>de</span>
+      <span class='ocrx_word' id='word_1_69' title='bbox 2957 2067 3451 2150; x_wconf 85'>linzen</span>
+     </span>
+     <span class='ocr_line' id='line_1_14' title="bbox 147 2205 3614 2318; baseline -0.003 -23; x_size 106; x_descenders 22; x_ascenders 25">
+      <span class='ocrx_word' id='word_1_70' title='bbox 147 2234 711 2318; x_wconf 88'>voegen,</span>
+      <span class='ocrx_word' id='word_1_71' title='bbox 826 2210 1234 2295; x_wconf 95'>Alles</span>
+      <span class='ocrx_word' id='word_1_72' title='bbox 1342 2232 1588 2295; x_wconf 95'>aan</span>
+      <span class='ocrx_word' id='word_1_73' title='bbox 1679 2212 1831 2291; x_wconf 96'>de</span>
+      <span class='ocrx_word' id='word_1_74' title='bbox 1928 2208 2263 2290; x_wconf 93'>kook</span>
+      <span class='ocrx_word' id='word_1_75' title='bbox 2355 2206 3000 2308; x_wconf 54'>brengen,</span>
+      <span class='ocrx_word' id='word_1_76' title='bbox 3117 2205 3367 2285; x_wconf 95'>Van</span>
+      <span class='ocrx_word' id='word_1_77' title='bbox 3462 2206 3614 2287; x_wconf 95'>de</span>
+     </span>
+     <span class='ocr_line' id='line_1_15' title="bbox 152 2341 3706 2447; baseline -0.003 -18; x_size 107; x_descenders 24; x_ascenders 24">
+      <span class='ocrx_word' id='word_1_78' title='bbox 152 2352 565 2434; x_wconf 91'>bloem</span>
+      <span class='ocrx_word' id='word_1_79' title='bbox 655 2351 896 2431; x_wconf 92'>met</span>
+      <span class='ocrx_word' id='word_1_80' title='bbox 997 2349 1669 2431; x_wconf 90'>boter</span>
+      <span class='ocrx_word' id='word_1_81' title='bbox 1514 2337 1683 2455; x_wconf 91'>en</span>
+      <span class='ocrx_word' id='word_1_82' title='bbox 1757 2343 2095 2426; x_wconf 88'>melk</span>
+      <span class='ocrx_word' id='word_1_83' title='bbox 2193 2364 2432 2427; x_wconf 93'>een</span>
+      <span class='ocrx_word' id='word_1_84' title='bbox 2527 2341 2935 2447; x_wconf 90'>papje</span>
+      <span class='ocrx_word' id='word_1_85' title='bbox 3029 2341 3453 2422; x_wconf 96'>maken</span>
+      <span class='ocrx_word' id='word_1_86' title='bbox 3549 2362 3706 2422; x_wconf 95'>en</span>
+     </span>
+     <span class='ocr_line' id='line_1_16' title="bbox 149 2477 3619 2586; baseline -0.003 -16; x_size 107; x_descenders 24; x_ascenders 23">
+      <span class='ocrx_word' id='word_1_87' title='bbox 149 2489 650 2571; x_wconf 86'>verder</span>
+      <span class='ocrx_word' id='word_1_88' title='bbox 750 2486 1330 2570; x_wconf 90'>afmaken</span>
+      <span class='ocrx_word' id='word_1_89' title='bbox 1420 2485 1660 2567; x_wconf 96'>met</span>
+      <span class='ocrx_word' id='word_1_90' title='bbox 1765 2485 1917 2566; x_wconf 93'>de</span>
+      <span class='ocrx_word' id='word_1_91' title='bbox 2025 2505 2409 2586; x_wconf 86'>soep,</span>
+      <span class='ocrx_word' id='word_1_92' title='bbox 2521 2479 2764 2564; x_wconf 96'>Als</span>
+      <span class='ocrx_word' id='word_1_93' title='bbox 2868 2480 3021 2561; x_wconf 92'>de</span>
+      <span class='ocrx_word' id='word_1_94' title='bbox 3127 2477 3619 2562; x_wconf 91'>linzen</span>
+     </span>
+     <span class='ocr_line' id='line_1_17' title="bbox 155 2619 2412 2731; baseline -0.005 -20; x_size 98; x_descenders 15; x_ascenders 23">
+      <span class='ocrx_word' id='word_1_95' title='bbox 155 2647 481 2731; x_wconf 35'>gfgaar</span>
+      <span class='ocrx_word' id='word_1_96' title='bbox 581 2624 909 2728; x_wconf 87'>Zijn</span>
+      <span class='ocrx_word' id='word_1_97' title='bbox 1005 2623 1153 2707; x_wconf 95'>is</span>
+      <span class='ocrx_word' id='word_1_98' title='bbox 1255 2624 1409 2706; x_wconf 93'>de</span>
+      <span class='ocrx_word' id='word_1_99' title='bbox 1522 2642 1840 2726; x_wconf 91'>soep</span>
+      <span class='ocrx_word' id='word_1_100' title='bbox 1929 2619 2412 2709; x_wconf 89'>klaar.</span>
+     </span>
+    </p>
+   </div>
+  </div>
+ </body>
+</html>

tests/cache/2400dpi/__-l__eng__000001_ocr.png__000001_ocr_hocr__hocr__txt/txt.bin

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

tests/cache/3small/__-l__eng__000001_ocr.png__000001_ocr_hocr__hocr__txt/hocr.bin

@@ -0,0 +1,89 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN"
+    "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
+<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
+ <head>
+  <title></title>
+  <meta http-equiv="Content-Type" content="text/html;charset=utf-8"/>
+  <meta name='ocr-system' content='tesseract 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.vh2to5iv/000001_ocr.png"; bbox 0 0 640 682; ppageno 0; scan_res 230 230'>
+   <div class='ocr_carea' id='block_1_1' title="bbox 365 15 429 29">
+    <p class='ocr_par' id='par_1_1' lang='eng' title="bbox 365 15 429 29">
+     <span class='ocr_line' id='line_1_1' title="bbox 365 15 429 29; baseline 0 0; x_size 19.238094; x_descenders 5.2380953; x_ascenders 4">
+      <span class='ocrx_word' id='word_1_1' title='bbox 365 15 429 29; x_wconf 92'>Tarnose</span>
+     </span>
+    </p>
+   </div>
+   <div class='ocr_photo' id='block_1_2' title="bbox 255 38 616 72"></div>
+   <div class='ocr_photo' id='block_1_3' title="bbox 273 38 349 57"></div>
+   <div class='ocr_carea' id='block_1_4' title="bbox 186 20 244 49">
+    <p class='ocr_par' id='par_1_2' lang='eng' title="bbox 186 20 345 49">
+     <span class='ocr_line' id='line_1_2' title="bbox 186 20 244 49; baseline -0.006 -10; x_size 20.454546; x_descenders 5.4545455; x_ascenders 5">
+      <span class='ocrx_word' id='word_1_2' title='bbox 186 20 244 49; x_wconf 92'>Bokale</span>
+      <span class='ocrx_word' id='word_1_3' title='bbox 299 28 345 46; x_wconf 42'>oa</span>
+     </span>
+    </p>
+   </div>
+   <div class='ocr_photo' id='block_1_5' title="bbox 64 38 186 72"></div>
+   <div class='ocr_carea' id='block_1_6' title="bbox 537 276 612 291">
+    <p class='ocr_par' id='par_1_3' lang='eng' title="bbox 537 276 612 291">
+     <span class='ocr_line' id='line_1_3' title="bbox 537 276 612 291; baseline 0 0; x_size 20.238094; x_descenders 5.2380953; x_ascenders 5">
+      <span class='ocrx_word' id='word_1_4' title='bbox 537 276 612 291; x_wconf 92'>Lehuntze</span>
+     </span>
+    </p>
+   </div>
+   <div class='ocr_photo' id='block_1_7' title="bbox 20 269 616 314"></div>
+   <div class='ocr_carea' id='block_1_8' title="bbox 480 323 550 341">
+    <p class='ocr_par' id='par_1_4' lang='eng' title="bbox 480 323 550 341">
+     <span class='ocr_line' id='line_1_4' title="bbox 480 323 550 341; baseline 0 -4; x_size 18; x_descenders 4; x_ascenders 4">
+      <span class='ocrx_word' id='word_1_5' title='bbox 480 323 550 341; x_wconf 91'>Mugerre</span>
+     </span>
+    </p>
+   </div>
+   <div class='ocr_photo' id='block_1_9' title="bbox 44 574 197 623"></div>
+   <div class='ocr_carea' id='block_1_10' title="bbox 204 542 603 574">
+    <p class='ocr_par' id='par_1_5' lang='eng' title="bbox 204 542 603 574">
+     <span class='ocr_line' id='line_1_5' title="bbox 204 542 603 574; baseline 0.018 -11; x_size 23.26087; x_descenders 5.2608695; x_ascenders 7">
+      <span class='ocrx_word' id='word_1_6' title='bbox 204 542 295 574; x_wconf 91'>Milafranga</span>
+      <span class='ocrx_word' id='word_1_7' title='bbox 439 552 603 569; x_wconf 90'>Komunikabideak</span>
+     </span>
+    </p>
+   </div>
+   <div class='ocr_carea' id='block_1_11' title="bbox 220 584 616 619">
+    <p class='ocr_par' id='par_1_6' lang='eng' title="bbox 220 584 616 625">
+     <span class='ocr_line' id='line_1_6' title="bbox 220 584 616 619; baseline -0.005 -1; x_size 43.666668; x_descenders 10.916667; x_ascenders 10.916667">
+      <span class='ocrx_word' id='word_1_8' title='bbox 220 585 404 619; x_wconf 2'>BAIONA</span>
+      <span class='ocrx_word' id='word_1_9' title='bbox 468 584 576 625; x_wconf 0'> zeiteninsiie</span>
+      <span class='ocrx_word' id='word_1_10' title='bbox 585 588 616 610; x_wconf 86'>—</span>
+     </span>
+    </p>
+   </div>
+   <div class='ocr_carea' id='block_1_12' title="bbox 393 623 598 634">
+    <p class='ocr_par' id='par_1_7' lang='eng' title="bbox 393 623 598 634">
+     <span class='ocr_line' id='line_1_7' title="bbox 393 623 598 634; baseline 0 0; x_size 22.75; x_descenders 5.5; x_ascenders 5.75">
+      <span class='ocrx_word' id='word_1_11' title='bbox 393 629 396 631; x_wconf 54'>7</span>
+      <span class='ocrx_word' id='word_1_12' title='bbox 470 623 539 634; x_wconf 24'>Trenbideak</span>
+      <span class='ocrx_word' id='word_1_13' title='bbox 550 628 598 630; x_wconf 24'>-----</span>
+     </span>
+    </p>
+   </div>
+   <div class='ocr_carea' id='block_1_13' title="bbox 81 633 613 667">
+    <p class='ocr_par' id='par_1_8' lang='eng' title="bbox 81 633 613 667">
+     <span class='ocr_line' id='line_1_8' title="bbox 81 633 613 667; baseline -0.002 -13; x_size 21; x_descenders 4; x_ascenders 7">
+      <span class='ocrx_word' id='word_1_14' title='bbox 81 637 111 653; x_wconf 0'>t\</span>
+      <span class='ocrx_word' id='word_1_15' title='bbox 123 633 201 663; x_wconf 22'>Basusarri</span>
+      <span class='ocrx_word' id='word_1_16' title='bbox 214 633 222 663; x_wconf 0'>—</span>
+      <span class='ocrx_word' id='word_1_17' title='bbox 230 647 325 656; x_wconf 0'>spmeans:20141004</span>
+      <span class='ocrx_word' id='word_1_18' title='bbox 373 633 415 667; x_wconf 42'>ae:</span>
+      <span class='ocrx_word' id='word_1_19' title='bbox 441 650 444 653; x_wconf 25'>.</span>
+      <span class='ocrx_word' id='word_1_20' title='bbox 521 649 544 657; x_wconf 17'>_</span>
+      <span class='ocrx_word' id='word_1_21' title='bbox 595 650 613 659; x_wconf 7'>~</span>
+     </span>
+    </p>
+   </div>
+  </div>
+ </body>
+</html>

tests/cache/3small/__-l__eng__000001_ocr.png__000001_ocr_hocr__hocr__txt/txt.bin

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

tests/cache/3small/__-l__eng__000002_ocr.png__000002_ocr_hocr__hocr__txt/hocr.bin

@@ -0,0 +1,27 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN"
+    "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
+<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
+ <head>
+  <title></title>
+  <meta http-equiv="Content-Type" content="text/html;charset=utf-8"/>
+  <meta name='ocr-system' content='tesseract 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.vh2to5iv/000002_ocr.png"; bbox 0 0 400 50; ppageno 0; scan_res 200 200'>
+   <div class='ocr_carea' id='block_1_1' title="bbox 54 16 344 33">
+    <p class='ocr_par' id='par_1_1' lang='eng' title="bbox 54 16 344 33">
+     <span class='ocr_line' id='line_1_1' title="bbox 54 16 344 33; baseline 0 -4; x_size 25.75; x_descenders 5.5; x_ascenders 6.75">
+      <span class='ocrx_word' id='word_1_1' title='bbox 54 16 110 29; x_wconf 84'>Covfefe</span>
+      <span class='ocrx_word' id='word_1_2' title='bbox 115 17 127 29; x_wconf 95'>is</span>
+      <span class='ocrx_word' id='word_1_3' title='bbox 132 20 140 29; x_wconf 95'>a</span>
+      <span class='ocrx_word' id='word_1_4' title='bbox 145 16 212 33; x_wconf 85'>perfectly</span>
+      <span class='ocrx_word' id='word_1_5' title='bbox 217 16 296 29; x_wconf 85'>cromulent</span>
+      <span class='ocrx_word' id='word_1_6' title='bbox 300 16 344 29; x_wconf 95'>word.</span>
+     </span>
+    </p>
+   </div>
+  </div>
+ </body>
+</html>

tests/cache/3small/__-l__eng__000002_ocr.png__000002_ocr_hocr__hocr__txt/txt.bin

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

tests/cache/3small/__-l__eng__000003_ocr.png__000003_ocr_hocr__hocr__txt/hocr.bin

@@ -0,0 +1,177 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN"
+    "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
+<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
+ <head>
+  <title></title>
+  <meta http-equiv="Content-Type" content="text/html;charset=utf-8"/>
+  <meta name='ocr-system' content='tesseract 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.vh2to5iv/000003_ocr.png"; bbox 0 0 4000 2864; ppageno 0; scan_res 1440 1440'>
+   <div class='ocr_carea' id='block_1_1' title="bbox 142 146 2173 258">
+    <p class='ocr_par' id='par_1_1' lang='eng' title="bbox 142 146 2173 258">
+     <span class='ocr_line' id='line_1_1' title="bbox 142 146 2173 258; baseline -0.004 -19; x_size 113; x_descenders 23; x_ascenders 32">
+      <span class='ocrx_word' id='word_1_1' title='bbox 142 154 982 258; x_wconf 90'>Linzensoep</span>
+      <span class='ocrx_word' id='word_1_2' title='bbox 1080 146 1152 237; x_wconf 96'>a</span>
+      <span class='ocrx_word' id='word_1_3' title='bbox 1254 153 1406 235; x_wconf 96'>la</span>
+      <span class='ocrx_word' id='word_1_4' title='bbox 1500 153 2173 235; x_wconf 96'>Waterman</span>
+     </span>
+    </p>
+   </div>
+   <div class='ocr_separator' id='block_1_2' title="bbox 136 253 2180 275"></div>
+   <div class='ocr_carea' id='block_1_3' title="bbox 145 414 2929 1221">
+    <p class='ocr_par' id='par_1_2' lang='eng' title="bbox 145 414 1154 516">
+     <span class='ocr_line' id='line_1_2' title="bbox 145 414 1154 516; baseline -0.005 -4; x_size 122.38636; x_descenders 24.386362; x_ascenders 40">
+      <span class='ocrx_word' id='word_1_5' title='bbox 145 414 211 512; x_wconf 60'>4</span>
+      <span class='ocrx_word' id='word_1_6' title='bbox 318 453 551 516; x_wconf 93'>ons</span>
+      <span class='ocrx_word' id='word_1_7' title='bbox 660 430 1154 512; x_wconf 91'>linzen</span>
+     </span>
+    </p>
+
+    <p class='ocr_par' id='par_1_3' lang='eng' title="bbox 146 568 1239 667">
+     <span class='ocr_line' id='line_1_3' title="bbox 146 568 1239 667; baseline -0.004 -16; x_size 99; x_descenders 17; x_ascenders 24">
+      <span class='ocrx_word' id='word_1_8' title='bbox 146 569 209 667; x_wconf 94'>3</span>
+      <span class='ocrx_word' id='word_1_9' title='bbox 323 568 729 652; x_wconf 83'>liter</span>
+      <span class='ocrx_word' id='word_1_10' title='bbox 821 569 1239 650; x_wconf 96'>water</span>
+     </span>
+    </p>
+
+    <p class='ocr_par' id='par_1_4' lang='eng' title="bbox 148 705 645 804">
+     <span class='ocr_line' id='line_1_4' title="bbox 148 705 645 804; baseline -0.016 -14; x_size 103; x_descenders 19; x_ascenders 27">
+      <span class='ocrx_word' id='word_1_11' title='bbox 148 706 211 804; x_wconf 88'>3</span>
+      <span class='ocrx_word' id='word_1_12' title='bbox 311 705 645 789; x_wconf 52'>uien</span>
+     </span>
+    </p>
+
+    <p class='ocr_par' id='par_1_5' lang='eng' title="bbox 147 832 1154 950">
+     <span class='ocr_line' id='line_1_5' title="bbox 147 832 1154 950; baseline -0.004 -27; x_size 118; x_descenders 28; x_ascenders 30">
+      <span class='ocrx_word' id='word_1_13' title='bbox 147 832 623 950; x_wconf 91'>bloem,</span>
+      <span class='ocrx_word' id='word_1_14' title='bbox 737 843 1154 924; x_wconf 91'>boter</span>
+     </span>
+    </p>
+
+    <p class='ocr_par' id='par_1_6' lang='eng' title="bbox 148 979 1241 1087">
+     <span class='ocr_line' id='line_1_6' title="bbox 148 979 1241 1087; baseline -0.005 -21; x_size 107; x_descenders 24; x_ascenders 24">
+      <span class='ocrx_word' id='word_1_15' title='bbox 148 983 215 1066; x_wconf 88'>2</span>
+      <span class='ocrx_word' id='word_1_16' title='bbox 312 983 807 1087; x_wconf 88'>kopjes</span>
+      <span class='ocrx_word' id='word_1_17' title='bbox 905 979 1241 1062; x_wconf 92'>melk</span>
+     </span>
+    </p>
+
+    <p class='ocr_par' id='par_1_7' lang='eng' title="bbox 154 1109 2929 1221">
+     <span class='ocr_line' id='line_1_7' title="bbox 154 1109 2929 1221; baseline -0.003 -21; x_size 112; x_descenders 28; x_ascenders 26">
+      <span class='ocrx_word' id='word_1_18' title='bbox 154 1117 791 1221; x_wconf 92'>laurier,</span>
+      <span class='ocrx_word' id='word_1_19' title='bbox 906 1111 1810 1219; x_wconf 90'>kruidnagel,</span>
+      <span class='ocrx_word' id='word_1_20' title='bbox 1927 1109 2490 1219; x_wconf 90'>kerrie,</span>
+      <span class='ocrx_word' id='word_1_21' title='bbox 2615 1110 2929 1195; x_wconf 91'>zout</span>
+     </span>
+    </p>
+   </div>
+   <div class='ocr_carea' id='block_1_4' title="bbox 147 1383 3706 2731">
+    <p class='ocr_par' id='par_1_8' lang='eng' title="bbox 147 1383 3706 2731">
+     <span class='ocr_line' id='line_1_8' title="bbox 149 1383 3612 1474; baseline -0.003 -2; x_size 107.01524; x_descenders 25.01524; x_ascenders 21">
+      <span class='ocrx_word' id='word_1_22' title='bbox 149 1395 303 1474; x_wconf 93'>De</span>
+      <span class='ocrx_word' id='word_1_23' title='bbox 411 1390 902 1473; x_wconf 80'>linzgen</span>
+      <span class='ocrx_word' id='word_1_24' title='bbox 996 1409 1497 1470; x_wconf 89'>wassen</span>
+      <span class='ocrx_word' id='word_1_25' title='bbox 1595 1409 1752 1470; x_wconf 88'>en</span>
+      <span class='ocrx_word' id='word_1_26' title='bbox 1853 1385 2166 1467; x_wconf 75'>in-l</span>
+      <span class='ocrx_word' id='word_1_27' title='bbox 2275 1383 2684 1466; x_wconf 93'>liter</span>
+      <span class='ocrx_word' id='word_1_28' title='bbox 2775 1383 3278 1464; x_wconf 91'>kokend</span>
+      <span class='ocrx_word' id='word_1_29' title='bbox 3368 1401 3612 1462; x_wconf 90'>wa-</span>
+     </span>
+     <span class='ocr_line' id='line_1_9' title="bbox 157 1516 3521 1632; baseline -0.004 -21; x_size 110; x_descenders 25; x_ascenders 25">
+      <span class='ocrx_word' id='word_1_30' title='bbox 157 1531 394 1611; x_wconf 93'>ter</span>
+      <span class='ocrx_word' id='word_1_31' title='bbox 495 1527 558 1609; x_wconf 94'>1</span>
+      <span class='ocrx_word' id='word_1_32' title='bbox 658 1530 903 1632; x_wconf 75'>dag</span>
+      <span class='ocrx_word' id='word_1_33' title='bbox 1002 1527 1415 1609; x_wconf 85'>laten</span>
+      <span class='ocrx_word' id='word_1_34' title='bbox 1505 1525 1979 1611; x_wconf 86'>weken,</span>
+      <span class='ocrx_word' id='word_1_35' title='bbox 2103 1521 2167 1603; x_wconf 96'>2</span>
+      <span class='ocrx_word' id='word_1_36' title='bbox 2275 1518 2683 1603; x_wconf 93'>liter</span>
+      <span class='ocrx_word' id='word_1_37' title='bbox 2777 1519 3194 1601; x_wconf 96'>water</span>
+      <span class='ocrx_word' id='word_1_38' title='bbox 3286 1516 3521 1620; x_wconf 93'>bij</span>
+     </span>
+     <span class='ocr_line' id='line_1_10' title="bbox 152 1651 3616 1767; baseline -0.004 -21; x_size 110; x_descenders 27; x_ascenders 23">
+      <span class='ocrx_word' id='word_1_39' title='bbox 152 1668 302 1747; x_wconf 92'>de</span>
+      <span class='ocrx_word' id='word_1_40' title='bbox 407 1662 905 1747; x_wconf 91'>linzen</span>
+      <span class='ocrx_word' id='word_1_41' title='bbox 996 1682 1559 1767; x_wconf 92'>voegen,</span>
+      <span class='ocrx_word' id='word_1_42' title='bbox 1680 1659 2176 1741; x_wconf 96'>zonder</span>
+      <span class='ocrx_word' id='word_1_43' title='bbox 2267 1655 2506 1737; x_wconf 96'>het</span>
+      <span class='ocrx_word' id='word_1_44' title='bbox 2606 1655 3023 1737; x_wconf 92'>water</span>
+      <span class='ocrx_word' id='word_1_45' title='bbox 3116 1651 3616 1735; x_wconf 91'>waarin</span>
+     </span>
+     <span class='ocr_line' id='line_1_11' title="bbox 153 1782 3704 1905; baseline -0.004 -20; x_size 117; x_descenders 23; x_ascenders 34">
+      <span class='ocrx_word' id='word_1_46' title='bbox 153 1824 305 1885; x_wconf 91'>ze</span>
+      <span class='ocrx_word' id='word_1_47' title='bbox 407 1800 979 1905; x_wconf 85'>geweekt</span>
+      <span class='ocrx_word' id='word_1_48' title='bbox 1089 1797 1412 1900; x_wconf 96'>zijn</span>
+      <span class='ocrx_word' id='word_1_49' title='bbox 1510 1796 1672 1878; x_wconf 96'>af</span>
+      <span class='ocrx_word' id='word_1_50' title='bbox 1770 1782 1914 1876; x_wconf 93'>te</span>
+      <span class='ocrx_word' id='word_1_51' title='bbox 2019 1792 2576 1899; x_wconf 54'>gieten,</span>
+      <span class='ocrx_word' id='word_1_52' title='bbox 2690 1790 2850 1874; x_wconf 93'>De</span>
+      <span class='ocrx_word' id='word_1_53' title='bbox 2948 1791 3357 1872; x_wconf 89'>helft</span>
+      <span class='ocrx_word' id='word_1_54' title='bbox 3452 1811 3704 1873; x_wconf 96'>van</span>
+     </span>
+     <span class='ocr_line' id='line_1_12' title="bbox 151 1928 3593 2035; baseline -0.003 -13; x_size 109; x_descenders 25; x_ascenders 25">
+      <span class='ocrx_word' id='word_1_55' title='bbox 151 1942 305 2024; x_wconf 92'>de</span>
+      <span class='ocrx_word' id='word_1_56' title='bbox 403 1940 735 2021; x_wconf 89'>uien</span>
+      <span class='ocrx_word' id='word_1_57' title='bbox 829 1938 1330 2022; x_wconf 91'>bakken</span>
+      <span class='ocrx_word' id='word_1_58' title='bbox 1419 1939 1659 2018; x_wconf 92'>met</span>
+      <span class='ocrx_word' id='word_1_59' title='bbox 1770 1933 2346 2016; x_wconf 91'>laurier</span>
+      <span class='ocrx_word' id='word_1_60' title='bbox 2447 1953 2603 2014; x_wconf 91'>en</span>
+      <span class='ocrx_word' id='word_1_61' title='bbox 2691 1928 3593 2035; x_wconf 63'>Kruidnagel.</span>
+     </span>
+     <span class='ocr_line' id='line_1_13' title="bbox 151 2067 3451 2180; baseline -0.004 -21; x_size 108; x_descenders 25; x_ascenders 24">
+      <span class='ocrx_word' id='word_1_62' title='bbox 151 2076 473 2159; x_wconf 92'>Alle</span>
+      <span class='ocrx_word' id='word_1_63' title='bbox 569 2076 965 2180; x_wconf 88'>uien,</span>
+      <span class='ocrx_word' id='word_1_64' title='bbox 1079 2072 1578 2156; x_wconf 90'>kerrie</span>
+      <span class='ocrx_word' id='word_1_65' title='bbox 1685 2092 1837 2153; x_wconf 93'>en</span>
+      <span class='ocrx_word' id='word_1_66' title='bbox 1938 2072 2254 2153; x_wconf 81'>zgout</span>
+      <span class='ocrx_word' id='word_1_67' title='bbox 2355 2068 2593 2172; x_wconf 43'>bij</span>
+      <span class='ocrx_word' id='word_1_68' title='bbox 2696 2071 2850 2150; x_wconf 91'>de</span>
+      <span class='ocrx_word' id='word_1_69' title='bbox 2957 2067 3451 2150; x_wconf 85'>linzen</span>
+     </span>
+     <span class='ocr_line' id='line_1_14' title="bbox 147 2205 3614 2318; baseline -0.003 -23; x_size 106; x_descenders 22; x_ascenders 25">
+      <span class='ocrx_word' id='word_1_70' title='bbox 147 2234 711 2318; x_wconf 88'>voegen,</span>
+      <span class='ocrx_word' id='word_1_71' title='bbox 826 2210 1234 2295; x_wconf 95'>Alles</span>
+      <span class='ocrx_word' id='word_1_72' title='bbox 1342 2232 1588 2295; x_wconf 95'>aan</span>
+      <span class='ocrx_word' id='word_1_73' title='bbox 1679 2212 1831 2291; x_wconf 96'>de</span>
+      <span class='ocrx_word' id='word_1_74' title='bbox 1928 2208 2263 2290; x_wconf 93'>kook</span>
+      <span class='ocrx_word' id='word_1_75' title='bbox 2355 2206 3000 2308; x_wconf 54'>brengen,</span>
+      <span class='ocrx_word' id='word_1_76' title='bbox 3117 2205 3367 2285; x_wconf 95'>Van</span>
+      <span class='ocrx_word' id='word_1_77' title='bbox 3462 2206 3614 2287; x_wconf 95'>de</span>
+     </span>
+     <span class='ocr_line' id='line_1_15' title="bbox 152 2341 3706 2447; baseline -0.003 -18; x_size 107; x_descenders 24; x_ascenders 24">
+      <span class='ocrx_word' id='word_1_78' title='bbox 152 2352 565 2434; x_wconf 91'>bloem</span>
+      <span class='ocrx_word' id='word_1_79' title='bbox 655 2351 896 2431; x_wconf 92'>met</span>
+      <span class='ocrx_word' id='word_1_80' title='bbox 997 2349 1669 2431; x_wconf 90'>boter</span>
+      <span class='ocrx_word' id='word_1_81' title='bbox 1514 2337 1683 2455; x_wconf 91'>en</span>
+      <span class='ocrx_word' id='word_1_82' title='bbox 1757 2343 2095 2426; x_wconf 88'>melk</span>
+      <span class='ocrx_word' id='word_1_83' title='bbox 2193 2364 2432 2427; x_wconf 93'>een</span>
+      <span class='ocrx_word' id='word_1_84' title='bbox 2527 2341 2935 2447; x_wconf 90'>papje</span>
+      <span class='ocrx_word' id='word_1_85' title='bbox 3029 2341 3453 2422; x_wconf 96'>maken</span>
+      <span class='ocrx_word' id='word_1_86' title='bbox 3549 2362 3706 2422; x_wconf 95'>en</span>
+     </span>
+     <span class='ocr_line' id='line_1_16' title="bbox 149 2477 3619 2586; baseline -0.003 -16; x_size 107; x_descenders 24; x_ascenders 23">
+      <span class='ocrx_word' id='word_1_87' title='bbox 149 2489 650 2571; x_wconf 86'>verder</span>
+      <span class='ocrx_word' id='word_1_88' title='bbox 750 2486 1330 2570; x_wconf 90'>afmaken</span>
+      <span class='ocrx_word' id='word_1_89' title='bbox 1420 2485 1660 2567; x_wconf 96'>met</span>
+      <span class='ocrx_word' id='word_1_90' title='bbox 1765 2485 1917 2566; x_wconf 93'>de</span>
+      <span class='ocrx_word' id='word_1_91' title='bbox 2025 2505 2409 2586; x_wconf 86'>soep,</span>
+      <span class='ocrx_word' id='word_1_92' title='bbox 2521 2479 2764 2564; x_wconf 96'>Als</span>
+      <span class='ocrx_word' id='word_1_93' title='bbox 2868 2480 3021 2561; x_wconf 92'>de</span>
+      <span class='ocrx_word' id='word_1_94' title='bbox 3127 2477 3619 2562; x_wconf 91'>linzen</span>
+     </span>
+     <span class='ocr_line' id='line_1_17' title="bbox 155 2619 2412 2731; baseline -0.005 -20; x_size 98; x_descenders 15; x_ascenders 23">
+      <span class='ocrx_word' id='word_1_95' title='bbox 155 2647 481 2731; x_wconf 35'>gfgaar</span>
+      <span class='ocrx_word' id='word_1_96' title='bbox 581 2624 909 2728; x_wconf 87'>Zijn</span>
+      <span class='ocrx_word' id='word_1_97' title='bbox 1005 2623 1153 2707; x_wconf 95'>is</span>
+      <span class='ocrx_word' id='word_1_98' title='bbox 1255 2624 1409 2706; x_wconf 93'>de</span>
+      <span class='ocrx_word' id='word_1_99' title='bbox 1522 2642 1840 2726; x_wconf 91'>soep</span>
+      <span class='ocrx_word' id='word_1_100' title='bbox 1929 2619 2412 2709; x_wconf 89'>klaar.</span>
+     </span>
+    </p>
+   </div>
+  </div>
+ </body>
+</html>

tests/cache/3small/__-l__eng__000003_ocr.png__000003_ocr_hocr__hocr__txt/txt.bin

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

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

@@ -9,7 +9,7 @@
   <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.9_hn68nz/000001_ocr.png"; bbox 0 0 1000 800; ppageno 0; scan_res 200 200'>
+  <div class='ocr_page' id='page_1' title='image "/tmp/ocrmypdf.io.su6l_waz/000001_ocr.png"; bbox 0 0 1000 800; ppageno 0; scan_res 200 200'>
    <div class='ocr_photo' id='block_1_1' title="bbox 296 96 704 504"></div>
    <div class='ocr_carea' id='block_1_2' title="bbox 150 592 841 622">
     <p class='ocr_par' id='par_1_1' lang='eng' title="bbox 150 592 841 622">