v14.4.0 docs and release notes

Instead present error message in exception.

.docker/Dockerfile

@@ -59,6 +59,7 @@ RUN add-apt-repository -y ppa:alex-p/tesseract-ocr-devel
 
 RUN apt-get update && apt-get install -y --no-install-recommends \
   ghostscript \
+  fonts-droid-fallback \
   jbig2dec \
   img2pdf \
   libsm6 libxext6 libxrender-dev \

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

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

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

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

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

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

.github/ISSUE_TEMPLATE/feature_request.md

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

.github/ISSUE_TEMPLATE/general-issues.md

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

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

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

.github/workflows/build.yml

@@ -5,7 +5,7 @@ name: Test and deploy
 on:
   push:
     branches:
-      - master
+      - main
       - ci
       - release/*
       - feature/*
@@ -249,12 +249,38 @@ jobs:
           name: artifact
           path: dist
 
-      - uses: pypa/gh-action-pypi-publish@master
+      - uses: pypa/gh-action-pypi-publish@release/v1
         with:
           user: __token__
           password: ${{ secrets.TOKEN_PYPI }}
           # repository_url: https://test.pypi.org/legacy/
 
+  create_release:
+    name: Create GitHub release
+    needs: [wheel_sdist_linux, test_linux, test_macos, test_windows]
+    runs-on: ubuntu-latest
+    if: github.event_name == 'push' && startsWith(github.event.ref, 'refs/tags/v')
+    permissions:
+      # Required to create a release
+      contents: write
+    steps:
+      - uses: actions/download-artifact@v3
+        with:
+          name: artifact
+          path: dist
+
+      - name: Create Release
+        id: create-release
+        uses: shogo82148/actions-create-release@v1
+
+      - name: Upload Assets
+        uses: shogo82148/actions-upload-release-asset@v1
+        with:
+          upload_url: ${{ steps.create-release.outputs.upload_url }}
+          asset_path: |
+            ./dist/*.whl
+            ./dist/*.tar.gz
+
   docker:
     name: Build Docker images
     needs: [wheel_sdist_linux, test_linux, test_macos, test_windows]
@@ -264,9 +290,9 @@ jobs:
       - name: Set image tag to release or branch
         run: echo "DOCKER_IMAGE_TAG=${GITHUB_REF##*/}" >> $GITHUB_ENV
 
-      - name: If master, set to latest
+      - name: If main, set to latest
         run: echo 'DOCKER_IMAGE_TAG=latest' >> $GITHUB_ENV
-        if: env.DOCKER_IMAGE_TAG == 'master'
+        if: env.DOCKER_IMAGE_TAG == 'main'
 
       - name: Set Docker Hub repository to username
         run: echo "DOCKER_REPOSITORY=jbarlow83" >> $GITHUB_ENV

.reuse/dep5

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

README.md

@@ -42,6 +42,8 @@ ocrmypdf                      # it's a scriptable command line program
 - Scales properly to handle files with thousands of pages
 - Battle-tested on millions of PDFs
 
+<img src="misc/screencast/demo.svg" alt="Demo of OCRmyPDF in a terminal session">
+
 For details: please consult the [documentation](https://ocrmypdf.readthedocs.io/en/latest/).
 
 ## Motivation

docs/advanced.rst

@@ -10,7 +10,7 @@ Control of unpaper
 
 OCRmyPDF uses ``unpaper`` to provide the implementation of the
 ``--clean`` and ``--clean-final`` arguments.
-`unpaper <https://github.com/Flameeyes/unpaper/blob/master/doc/basic-concepts.md>`__
+`unpaper <https://github.com/Flameeyes/unpaper/blob/main/doc/basic-concepts.md>`__
 provides a variety of image processing filters to improve images.
 
 By default, OCRmyPDF uses only ``unpaper`` arguments that were found to
@@ -104,7 +104,7 @@ was requested, the preprocessed image layer will be inserted.
 If you want to adjust the amount of time spent on OCR, change
 ``--tesseract-timeout``. You can also automatically skip images that
 exceed a certain number of megapixels with ``--skip-big``. (A 300 DPI,
-8.5×11" page is 8.4 megapixels.)
+8.5×11" page image is 8.4 megapixels.)
 
 .. code-block:: bash
 
@@ -241,6 +241,17 @@ PDF.js viewer.
 
 This works in all versions of Tesseract.
 
+Rendering and rasterizing options
+=================================
+
+.. versionadded:: 14.3.0
+
+The ``--continue-on-soft-render-error`` option allows OCRmyPDF to
+proceed if a page cannot be rasterized rendered. This is useful if you are
+trying to get the best possible OCR from a PDF that is not well-formed,
+and you are willing to accept some pages that may not visually match the
+input, and that may not OCR well.
+
 Return code policy
 ==================
 
@@ -299,16 +310,31 @@ stable user interface. They may be imported from
         - The program was interrupted by pressing Ctrl+C.
 
 
+.. _tmpdir:
+
+Changing temporary storage location
+===================================
+
+OCRmyPDF generates many temporary files during processing.
+
+To change where temporary files are stored, change the ``TMPDIR``
+environment variable for ocrmypdf's environment. (Python's
+``tempfile.gettempdir()`` returns the root directory in which temporary
+files will be stored.) For example, one could redirect ``TMPDIR`` to a
+large RAM disk to avoid wear on HDD/SSD and potentially improve
+performance.
+
+On Windows, the ``TEMP`` environment variable is used instead.
+
 Debugging the intermediate files
 ================================
 
 OCRmyPDF normally saves its intermediate results to a temporary folder
 and deletes this folder when it exits, whether it succeeded or failed.
 
-If the ``-k`` argument is issued on the command line, OCRmyPDF will keep
-the temporary folder and print the location, whether it succeeded or
-failed (provided the Python interpreter did not crash). An example
-message is:
+If the ``--keep-temporary-files`` (``-k```) argument is issued on the
+command line, OCRmyPDF will keep the temporary folder and print the location,
+whether it succeeded or failed. An example message is:
 
 .. code-block:: none
 

docs/batch.rst

@@ -151,14 +151,14 @@ The watcher service is included in the OCRmyPDF Docker image. To run it:
 .. code-block:: bash
 
     docker run \
-        -v <path to files to convert>:/input \
-        -v <path to store results>:/output \
-        -v <path to store processed originals>:/archive \
-        -e OCR_OUTPUT_DIRECTORY_YEAR_MONTH=1 \
-        -e OCR_ON_SUCCESS_ARCHIVE=1 \
-        -e OCR_DESKEW=1 \
-        -e PYTHONUNBUFFERED=1 \
-        -it --entrypoint python3 \
+        --volume <path to files to convert>:/input \
+        --volume <path to store results>:/output \
+        --volume <path to store processed originals>:/archive \
+        --env OCR_OUTPUT_DIRECTORY_YEAR_MONTH=1 \
+        --env OCR_ON_SUCCESS_ARCHIVE=1 \
+        --env OCR_DESKEW=1 \
+        --env PYTHONUNBUFFERED=1 \
+        --interactive --tty --entrypoint python3 \
         jbarlow83/ocrmypdf \
         watcher.py
 
@@ -170,13 +170,13 @@ original to ``/archive``. The parameters to this image are:
     :header: "Parameter", "Description"
     :widths: 50, 50
 
-    "``-v <path to files to convert>:/input``", "Files placed in this location will be OCRed"
-    "``-v <path to store results>:/output``", "This is where OCRed files will be stored"
-    "``-v <path to store processed originals>:/archive``", "Archive processed originals here"
-    "``-e OCR_OUTPUT_DIRECTORY_YEAR_MONTH=1``", "Define environment variable ``OCR_OUTPUT_DIRECTORY_YEAR_MONTH=1`` to place files in the output in ``{output}/{year}/{month}/{filename}``"
-    "``-e OCR_ON_SUCCESS_ARCHIVE=1``", "Define environment variable ``OCR_ON_SUCCESS_ARCHIVE`` to move processed originals"
-    "``-e OCR_DESKEW=1``", "Define environment variable ``OCR_DESKEW``  to apply deskew to crooked input PDFs"
-    "``-e PYTHONBUFFERED=1``", "This will force ``STDOUT`` to be unbuffered and allow you to see messages in docker logs"
+    "``--volume <path to files to convert>:/input``", "Files placed in this location will be OCRed"
+    "``--volume <path to store results>:/output``", "This is where OCRed files will be stored"
+    "``--volume <path to store processed originals>:/archive``", "Archive processed originals here"
+    "``--env OCR_OUTPUT_DIRECTORY_YEAR_MONTH=1``", "Define environment variable ``OCR_OUTPUT_DIRECTORY_YEAR_MONTH=1`` to place files in the output in ``{output}/{year}/{month}/{filename}``"
+    "``--env OCR_ON_SUCCESS_ARCHIVE=1``", "Define environment variable ``OCR_ON_SUCCESS_ARCHIVE`` to move processed originals"
+    "``--env OCR_DESKEW=1``", "Define environment variable ``OCR_DESKEW``  to apply deskew to crooked input PDFs"
+    "``--env PYTHONBUFFERED=1``", "This will force ``STDOUT`` to be unbuffered and allow you to see messages in docker logs"
 
 This service relies on polling to check for changes to the filesystem. It
 may not be suitable for some environments, such as filesystems shared on a

docs/cloud.rst

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

docs/contributing.rst

@@ -18,7 +18,7 @@ work you're contemplating is already half-done in a development branch.
 Code style
 ==========
 
-We use PEP8, ``black`` for code formatting and ``isort`` for import sorting. The
+We use PEP8, ``black`` for code formatting and ``ruff`` for everything else. The
 settings for these programs are in ``pyproject.toml`` and ``setup.cfg``. Pull
 requests should follow the style guide. One difference we use from "black" style
 is that strings shown to the user are always in double quotes (``"``) and strings

docs/cookbook.rst

@@ -372,3 +372,17 @@ Some users may consider enabling lossy JBIG2. See: :ref:`jbig2-lossy`.
 
     Image processing and PDF/A conversion can also introduce lossy transformations
     to your PDF images, even when ``--optimize 1`` is in use.
+
+
+Digitally signed PDFs
+=====================
+
+OCRmyPDF cannot preserve digital signatures in PDFs and also add to OCR to them.
+By default, it will refuse to modify a signed PDF regardless of other settings. You can
+override this behavior with ``--invalidate-digital-signatures``; as the name suggests,
+any digital signatures will be invalidated.
+
+OCRmyPDF cannot open documents that are encrypted with a digital certificate.
+
+Versions of OCRmyPDF prior to 14.4.0 would invalidate existing digital signatures
+without warning.

docs/index.rst

@@ -20,7 +20,6 @@ image processing and OCR to existing PDFs.
    introduction
    release_notes
    installation
-   optimizer
    languages
    jbig2
 
@@ -29,9 +28,11 @@ image processing and OCR to existing PDFs.
    :maxdepth: 2
 
    cookbook
+   optimizer
    docker
    advanced
    batch
+   cloud
    performance
    pdfsecurity
    errors

docs/installation.rst

@@ -637,7 +637,7 @@ system-wide:
 
 .. code-block:: bash
 
-    git clone -b master https://github.com/ocrmypdf/OCRmyPDF.git
+    git clone -b main https://github.com/ocrmypdf/OCRmyPDF.git
     python3 -m venv venv
     source venv/bin/activate
     cd OCRmyPDF
@@ -664,7 +664,7 @@ To install all of the development and test requirements:
 
 .. code-block:: bash
 
-    git clone -b master https://github.com/ocrmypdf/OCRmyPDF.git
+    git clone -b main https://github.com/ocrmypdf/OCRmyPDF.git
     python -m venv
     source venv/bin/activate
     cd OCRmyPDF

docs/languages.rst

@@ -12,7 +12,7 @@ OCRmyPDF uses Tesseract for OCR, and relies on its language packs for all langua
 On most platforms, English is installed with Tesseract by default, but not always.
 
 Tesseract supports `most
-languages <https://github.com/tesseract-ocr/tesseract/blob/master/doc/tesseract.1.asc#languages>`__.
+languages <https://github.com/tesseract-ocr/tesseract/blob/main/doc/tesseract.1.asc#languages>`__.
 Languages are identified by standardized three-letter codes (called ISO 639-2 Alpha-3).
 Tesseract's documentation also lists the three-letter code for your language.
 Some are anglicized, e.g. Spanish is ``spa`` rather than ``esp``, while others
@@ -70,13 +70,13 @@ This enables these languages for all packages (e.g. including aspell).
 
    # Display a list of all Tesseract language packs
    equery uses app-text/tessdata_fast
-   
+
    # Add English and German language support for Tesseract only
    echo 'app-text/tessdata_fast l10n_de l10n_en' >> /etc/portage/package.use
-   
+
    # Add global English and German language support (the `l10n_` from equery has to be omitted)
    echo L10N="de en" >> /etc/portage/make.conf
-   
+
    # update system to reflect changed USE flags
    emerge --update --deep --newuse @world
 
@@ -101,7 +101,7 @@ derived Docker image as
 Windows users
 =============
 
-The Tesseract installer provided by Chocolatey currently includes only English language. 
-To install other languages, download the respective language pack (``.traineddata`` file) 
-from https://github.com/tesseract-ocr/tessdata/ and place it in 
+The Tesseract installer provided by Chocolatey currently includes only English language.
+To install other languages, download the respective language pack (``.traineddata`` file)
+from https://github.com/tesseract-ocr/tessdata/ and place it in
 ``C:\\Program Files\\Tesseract-OCR\\tessdata`` (or wherever Tesseract OCR is installed).

docs/optimizer.rst

@@ -13,14 +13,33 @@ tuned. Optimization occurs after OCR, and only if OCR succeeded.  It does not
 perform other possible optimizations such as deduplicating resources,
 consolidating fonts, simplifying vector drawings, or anything of that nature.
 
-Optimization ranges from ``-O0`` through ``-O3``, where ``0`` disables
-optimization and ``3`` implements all options. ``1``, the default, performs only
-safe and lossless optimizations. (This is similar to GCC's optimization
-parameter.) The exact type of optimizations performed will vary over time.
+.. list-table:: Title
+   :widths: 33 6 60
+   :header-rows: 1
 
-PDF optimization requires third-party, optional tools for certain optimizations.
-If these are not installed or cannot be found by OCRmyPDF, optimization will not
-be as good.
+    * - Optimization level
+      - Shorthand
+      - Description
+    * - ``--optimize 0``
+      - ``-O0``
+      - Disable most optimizations.
+    * - ``--optimize 1`` (default)
+      - ``-O1``
+      - Safe and lossless optimizations.
+    * - ``--optimize 2``
+      - ``-O2``
+      - Safe and lossy optimizations.
+    * - ``--optimize 3``
+      - ``-O3``
+      - Aggressive lossy optimizations.
+
+The exact type of optimizations performed will vary over time, and depend on
+the availability of third-party tools.
+
+Despite optimizations, OCRmyPDF might still increase the overall file size,
+since it must embed information about the recognized text, and depending on the
+settings chosen, may not be able to represent the output file as compactly as
+the input file.
 
 Optimizations that always occurs
 ================================
@@ -37,12 +56,14 @@ Fast web view
 OCRmyPDF automatically optimizes PDFs for "fast web view" in Adobe Acrobat's
 parlance, or equivalently, linearizes PDFs so that the resources they reference
 are presented in the order a viewer needs them for sequential display. This
-reduces the latency of viewing a PDF both online and from local storage. This
-actually slightly increases the file size.
+reduces the latency of viewing a PDF both online and from local storage, in
+exchange for a slight increase in file size.
 
 To disable this optimization and all others, use ``ocrmypdf --optimize 0 ...``
 or the shorthand ``-O0``.
 
+Adobe Acrobat might not report the file as being "fast web view".
+
 Lossless optimizations
 ======================
 

docs/pdfsecurity.rst

@@ -29,13 +29,9 @@ attack vectors.
 In short, PDFs `may contain
 viruses <https://security.stackexchange.com/questions/64052/can-a-pdf-file-contain-a-virus>`__.
 
-This
-`article <https://theinvisiblethings.blogspot.ca/2013/02/converting-untrusted-pdfs-into-trusted.html>`__
-describes a high-paranoia method which allows potentially hostile PDFs
-to be viewed and rasterized safely in a disposable virtual machine. A
-trusted PDF created in this manner is converted to images and loses all
-information making it searchable and losing all compression. OCRmyPDF
-could be used to restore searchability.
+If you do not trust a PDF or its source, do not open it or use OCRmyPDF
+on it. Consider using a Docker container or virtual machine to isolate
+an untrusted PDF from your system.
 
 How OCRmyPDF processes PDFs
 ===========================
@@ -43,11 +39,11 @@ How OCRmyPDF processes PDFs
 OCRmyPDF must open and interpret your PDF in order to insert an OCR
 layer. First, it runs all PDFs through
 `pikepdf <https://github.com/pikepdf/pikepdf>`__, a library based on
-`qpdf <https://github.com/qpdf/qpdf>`__, a program that repairs PDFs
+`QPDF <https://github.com/qpdf/qpdf>`__, a program that repairs PDFs
 with syntax errors. This is done because, in the author's experience, a
 significant number of PDFs in the wild, especially those created by
-scanners, are not well-formed files. qpdf makes it more likely that
-OCRmyPDF will succeed, but offers no security guarantees. qpdf is also
+scanners, are not well-formed files. QPDF makes it more likely that
+OCRmyPDF will succeed, but offers no security guarantees. QPDF is also
 used to split the PDF into single page PDFs.
 
 Finally, OCRmyPDF rasterizes each page of the PDF using
@@ -58,84 +54,6 @@ into the existing PDF or it may essentially reconstruct ("re-fry") a
 visually identical PDF that may be quite different at the binary level.
 That said, OCRmyPDF is not a tool designed for sanitizing PDFs.
 
-.. _ocr-service:
-
-Using OCRmyPDF online or as a service
-=====================================
-
-OCRmyPDF is not designed for use as a public web service where a
-malicious user could upload a chosen PDF. In particular, it is not
-necessarily secure against PDF malware or PDFs that cause denial of
-service. OCRmyPDF relies on Ghostscript, and therefore, if deployed
-online one should be prepared to comply with Ghostscript's Affero GPL
-license, and any other licenses.
-
-Setting aside these concerns, a side effect of OCRmyPDF is that it may
-incidentally sanitize PDFs containing certain types of malware. It
-repairs the PDF with pikepdf/libqpdf, which could correct malformed PDF
-structures that are part of an attack. When PDF/A output is selected
-(the default), the input PDF is partially reconstructed by Ghostscript.
-When ``--force-ocr`` is used, all pages are rasterized and reconverted
-to PDF, which could remove malware in embedded images.
-
-OCRmyPDF should be relatively safe to use in a trusted intranet, with
-some considerations:
-
-Limiting CPU usage
-------------------
-
-OCRmyPDF will attempt to use all available CPUs and storage, so
-executing ``nice ocrmypdf`` or limiting the number of jobs with the
-``-j`` argument may ensure the server remains available. Another option
-would be to run OCRmyPDF jobs inside a Docker container, a virtual machine,
-or a cloud instance, which can impose its own limits on CPU usage and be
-terminated "from orbit" if it fails to complete.
-
-Temporary storage requirements
-------------------------------
-
-OCRmyPDF will use a large amount of temporary storage for its work,
-proportional to the total number of pixels needed to rasterize the PDF.
-The raster image of a 8.5×11" color page at 300 DPI takes 25 MB
-uncompressed; OCRmyPDF saves its intermediates as PNG, but that still
-means it requires about 9 MB per intermediate based on average
-compression ratios. Multiple intermediates per page are also required,
-depending on the command line given. A rule of thumb would be to allow
-100 MB of temporary storage per page in a file – meaning that a small
-cloud servers or small VM partitions should be provisioned with plenty
-of extra space, if say, a 500 page file might be sent.
-
-To check temporary storage usage on actual files, run
-``ocrmypdf -k ...`` which will preserve and print the path to temporary
-storage when the job is done.
-
-To change where temporary files are stored, change the ``TMPDIR``
-environment variable for ocrmypdf's environment. (Python's
-``tempfile.gettempdir()`` returns the root directory in which temporary
-files will be stored.) For example, one could redirect ``TMPDIR`` to a
-large RAM disk to avoid wear on HDD/SSD and potentially improve
-performance. On Amazon Web Services, ``TMPDIR`` can be set to `empheral
-storage <https://docs.aws.amazon.com/AWSEC2/latest/UserGuide/InstanceStorage.html>`__.
-
-Timeouts
---------
-
-To prevent excessively long OCR jobs consider setting
-``--tesseract-timeout`` and/or ``--skip-big`` arguments. ``--skip-big``
-is particularly helpful if your PDFs include documents such as reports
-on standard page sizes with large images attached - often large images
-are not worth OCR'ing anyway.
-
-Commercial alternatives
------------------------
-
-The author also provides professional services that include OCR and
-building databases around PDFs, and is happy to provide consultation.
-
-Abbyy Cloud OCR is viable commercial alternative with a web services
-API. Amazon Textract, Google Cloud Vision, and Microsoft Azure 
-Computer Vision provide advanced OCR but have less PDF rendering capability.
-
 Password protection, digital signatures and certification
 =========================================================
 

docs/release_notes.rst

@@ -28,6 +28,42 @@ tagged yet.
 
 .. |OCRmyPDF PyPI| image:: https://img.shields.io/pypi/v/ocrmypdf.svg
 
+v14.4.0
+=======
+
+-  Digitally signed PDFs are now detected. If the PDF is signed, OCRmyPDF will
+   refuse to modify it. Previously, only encrypted PDFs were detected, not
+   those that were signed but not encrypted. :issue:`1040`
+-  In addition, `--invalidate-digital-signatures` can be used to override the
+   above behavior and modify the PDF anyway. :issue:`1040`
+-  tqdm progress bars replaced with "rich" progress bars. The rich library is
+   a new dependency. Certain APIs that used tqdm are now deprecated and will
+   be removed in the next major release.
+-  Improved integration with GitHub Releases. Thanks to @stumpylog.
+
+v14.3.0
+=======
+
+-  Renamed master branch to main.
+-  Improve PDF rasterization accuracy by using the ``-dPDFSTOPONERROR`` option
+   to Ghostscript. Use ``--continue-on-soft-render-error`` if you want to render
+   the PDF anyway. The plugin specification was adjusted to support this feature;
+   plugin authors may want to adapt PDF rasterizing and rendering
+   plugins. :issue:`1083`
+-  The calculated deskew angle is now recorded in the logged output. :issue:`1101`
+-  Metadata can now be unset by setting a metadata type such as ``--title`` to an
+   empty string. :issue:`1117,1059`
+-  Fixed random order of languages due to use of a set. This may have caused output
+   to vary when multiple languages were set for OCR. :issue:`1113`
+-  Clarified the optimization ratio reported in the log output.
+-  Documentation improvements.
+
+v14.2.1
+=======
+
+-  Fixed :issue:`977`, where images inside Form XObjects were always excluded
+   from image optimization.
+
 v14.2.0
 =======
 

misc/completion/ocrmypdf.bash

@@ -31,6 +31,7 @@ __ocrmypdf_arguments()
 --force-ocr              (OCR documents that already have printable text)
 --skip-text              (skip OCR on any pages that already contain text)
 --redo-ocr               (redo OCR on any pages that seem to have OCR already)
+--invalidate-digital-signatures (remove digital signatures from PDF)
 --skip-big               (skip OCR on pages larger than this many MPixels)
 --optimize               (select optimization level)
 --jpeg-quality           (JPEG quality [0..100])

misc/completion/ocrmypdf.fish

@@ -16,6 +16,7 @@ complete -c ocrmypdf -l remove-vectors -d "don't send vector objects to OCR"
 complete -c ocrmypdf -s f -l force-ocr -d "OCR documents that already have printable text"
 complete -c ocrmypdf -s s -l skip-ocr -d "skip OCR on pages that text, otherwise try OCR"
 complete -c ocrmypdf -l redo-ocr -d "redo OCR on any pages that seem to have OCR already"
+complete -c ocrmypdf -l invalidate-digital-signatures -d "invalidate digital signatures and allow OCR to proceed"
 
 complete -c ocrmypdf -s k -l keep-temporary-files -d "keep temporary files (debug)"
 

misc/screencast/README.md

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

misc/screencast/demo.cast

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

pyproject.toml

@@ -17,7 +17,6 @@ license = {text = "MPL-2.0"}
 requires-python = ">=3.8"
 dependencies = [
   "Pillow>=8.2.0",
-  "coloredlogs>=14.0",
   "deprecation>=2.1.0",
   "img2pdf>=0.3.0", # pure Python
   "packaging>=20",
@@ -25,6 +24,7 @@ dependencies = [
   "pikepdf>=5.0.1",
   "pluggy>=0.13.0",
   "reportlab>=3.5.66",
+  "rich>=13",
   "tqdm>=4",
   "importlib-resources>=5;python_version<'3.9'",  # until Python 3.9
   "typing-extensions>=4;python_version<'3.10'",
@@ -37,16 +37,12 @@ classifiers = [
   "Intended Audience :: Science/Research",
   "Intended Audience :: System Administrators",
   "License :: OSI Approved :: Mozilla Public License 2.0 (MPL 2.0)",
-  "Operating System :: MacOS :: MacOS X",
-  "Operating System :: Microsoft :: Windows :: Windows 10",
+  "Operating System :: MacOS",
+  "Operating System :: Microsoft :: Windows",
   "Operating System :: POSIX",
   "Operating System :: POSIX :: BSD",
   "Operating System :: POSIX :: Linux",
   "Programming Language :: Python :: 3",
-  "Programming Language :: Python :: 3 :: Only",
-  "Programming Language :: Python :: 3.8",
-  "Programming Language :: Python :: 3.9",
-  "Programming Language :: Python :: 3.10",
   "Topic :: Scientific/Engineering :: Image Recognition",
   "Topic :: Text Processing :: Indexing",
   "Topic :: Text Processing :: Linguistic",
@@ -141,27 +137,6 @@ exclude_lines = [
   "if TYPE_CHECKING:"
 ]
 
-[tool.isort]
-profile = "black"
-known_first_party = "ocrmypdf"
-known_third_party = [
-  "PIL",
-  "flask",
-  "img2pdf",
-  "ocrmypdf",
-  "pdfminer",
-  "pikepdf",
-  "pkg_resources",
-  "pluggy",
-  "pytest",
-  "reportlab",
-  "setuptools",
-  "sphinx_rtd_theme",
-  "tqdm",
-  "watchdog",
-  "werkzeug"
-]
-
 [tool.pytest.ini_options]
 minversion = "6.0"
 norecursedirs = ["lib", ".pc", ".git", "venv", "output", "cache", "resources"]

src/ocrmypdf/_exec/ghostscript.py

@@ -30,7 +30,7 @@ except AttributeError:
 
 log = logging.getLogger(__name__)
 
-# Most reliable what to get the bitness of Python interpreter, according to Python docs
+# Most reliable way to get the bitness of Python interpreter, according to Python docs
 _IS_64BIT = sys.maxsize > 2**32
 
 _GSWIN = None
@@ -63,6 +63,7 @@ def rasterize_pdf(
     page_dpi: Resolution | None = None,
     rotation: int | None = None,
     filter_vector: bool = False,
+    stop_on_error: bool = False,
 ):
     """Rasterize one page of a PDF at resolution raster_dpi in canvas units."""
     raster_dpi = raster_dpi.round(6)
@@ -83,6 +84,7 @@ def rasterize_pdf(
             f'-r{raster_dpi.x:f}x{raster_dpi.y:f}',
         ]
         + (['-dFILTERVECTOR'] if filter_vector else [])
+        + (['-dPDFSTOPONERROR'] if stop_on_error else [])
         + [
             '-o',
             '-',
@@ -161,6 +163,7 @@ def generate_pdfa(
     pdf_version: str = '1.5',
     pdfa_part: str = '2',
     progressbar_class=None,
+    stop_on_error: bool = False,
 ):
     # Ghostscript's compression is all or nothing. We can either force all images
     # to JPEG, force all to Flate/PNG, or let it decide how to encode the images.
@@ -193,6 +196,10 @@ def generate_pdfa(
         # https://bugs.ghostscript.com/show_bug.cgi?id=705187
         compression_args.append('-dNEWPDF=false')
 
+    if os.name == 'nt':
+        # Windows has lots of fatal "permission denied" errors
+        stop_on_error = False
+
     # nb no need to specify ProcessColorModel when ColorConversionStrategy
     # is set; see:
     # https://bugs.ghostscript.com/show_bug.cgi?id=699392
@@ -207,6 +214,7 @@ def generate_pdfa(
             "-dAutoRotatePages=/None",
             "-sColorConversionStrategy=" + strategy,
         ]
+        + (['-dPDFSTOPONERROR'] if stop_on_error else [])
         + compression_args
         + [
             "-dJPEGQ=95",

src/ocrmypdf/_exec/tesseract.py

@@ -233,6 +233,7 @@ def get_deskew(
     parsed = _parse_tesseract_output(p.stdout)
     deskew_radians = float(parsed.get('Deskew angle', 0))
     deskew_degrees = 180 / pi * deskew_radians
+    log.debug(f"Deskew angle: {deskew_degrees:.3f}")
     return deskew_degrees
 
 

src/ocrmypdf/_exec/unpaper.py

@@ -21,7 +21,7 @@ from ocrmypdf.exceptions import MissingDependencyError, SubprocessOutputError
 from ocrmypdf.subprocess import get_version, run
 
 # unpaper documentation:
-# https://github.com/Flameeyes/unpaper/blob/master/doc/basic-concepts.md
+# https://github.com/Flameeyes/unpaper/blob/main/doc/basic-concepts.md
 
 
 if sys.version_info >= (3, 10):

src/ocrmypdf/_logging.py

@@ -8,6 +8,17 @@ from __future__ import annotations
 import logging
 from contextlib import suppress
 
+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
 from tqdm import tqdm
 
 
@@ -41,3 +52,59 @@ class TqdmConsole:
     def flush(self):
         with suppress(AttributeError):
             self.file.flush()
+
+
+class RichLoggingHandler(RichHandler):
+    def __init__(self, console: Console, **kwargs):
+        super().__init__(
+            console=console, show_level=False, show_time=False, markup=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, 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/_pipeline.py

@@ -27,6 +27,7 @@ from ocrmypdf._jobcontext import PageContext, PdfContext
 from ocrmypdf._version import PROGRAM_NAME
 from ocrmypdf._version import __version__ as VERSION
 from ocrmypdf.exceptions import (
+    DigitalSignatureError,
     DpiError,
     EncryptedPdfError,
     InputFileError,
@@ -37,6 +38,7 @@ from ocrmypdf.helpers import IMG2PDF_KWARGS, Resolution, safe_symlink
 from ocrmypdf.hocrtransform import HocrTransform
 from ocrmypdf.pdfa import generate_pdfa_ps
 from ocrmypdf.pdfinfo import Colorspace, Encoding, PageInfo, PdfInfo
+from ocrmypdf.pluginspec import OrientationConfidence
 
 # Remove this workaround when we require Pillow >= 10
 try:
@@ -51,6 +53,20 @@ VECTOR_PAGE_DPI = 400
 
 
 def triage_image_file(input_file: Path, output_file: Path, options) -> None:
+    """Triage the input image file.
+
+    If the input file is an image, check its resolution and convert it to PDF.
+
+    Args:
+        input_file: The path to the input file.
+        output_file: The path to the output file.
+        options: An object containing the options passed to the OCRmyPDF command.
+
+    Raises:
+        UnsupportedImageFormatError: If the input file is not a supported image format.
+        DpiError: If the input image has no resolution (DPI) in its metadata or if the
+            resolution is not credible.
+    """
     log.info("Input file is not a PDF, checking if it is an image...")
     try:
         im = Image.open(input_file)
@@ -65,34 +81,32 @@ def triage_image_file(input_file: Path, output_file: Path, options) -> None:
             if im.info['dpi'] <= (96, 96) and not options.image_dpi:
                 log.info("Image size: (%d, %d)", *im.size)
                 log.info("Image resolution: (%d, %d)", *im.info['dpi'])
-                log.error(
+                raise DpiError(
                     "Input file is an image, but the resolution (DPI) is "
                     "not credible.  Estimate the resolution at which the "
                     "image was scanned and specify it using --image-dpi."
                 )
-                raise DpiError()
         elif not options.image_dpi:
             log.info("Image size: (%d, %d)", *im.size)
-            log.error(
+            raise DpiError(
                 "Input file is an image, but has no resolution (DPI) "
                 "in its metadata.  Estimate the resolution at which "
                 "image was scanned and specify it using --image-dpi."
             )
-            raise DpiError()
 
         if im.mode in ('RGBA', 'LA'):
-            log.error(
+            raise UnsupportedImageFormatError(
                 "The input image has an alpha channel. Remove the alpha "
                 "channel first."
             )
-            raise UnsupportedImageFormatError()
 
         if 'iccprofile' not in im.info:
             if im.mode == 'RGB':
                 log.info("Input image has no ICC profile, assuming sRGB")
             elif im.mode == 'CMYK':
-                log.error("Input CMYK image has no ICC profile, not usable")
-                raise UnsupportedImageFormatError()
+                raise UnsupportedImageFormatError(
+                    "Input CMYK image has no ICC profile, not usable"
+                )
 
     try:
         log.info("Image seems valid. Try converting to PDF...")
@@ -110,7 +124,6 @@ def triage_image_file(input_file: Path, output_file: Path, options) -> None:
             )
         log.info("Successfully converted to PDF, processing...")
     except img2pdf.ImageOpenError as e:
-        log.error(e)
         raise UnsupportedImageFormatError() from e
 
 
@@ -180,18 +193,21 @@ def validate_pdfinfo_options(context: PdfContext) -> None:
     options = context.options
 
     if pdfinfo.needs_rendering:
-        log.error(
+        raise InputFileError(
             "This PDF contains dynamic XFA forms created by Adobe LiveCycle "
             "Designer and can only be read by Adobe Acrobat or Adobe Reader."
         )
-        raise InputFileError()
+    if pdfinfo.has_signature:
+        if options.invalidate_digital_signatures:
+            log.warning("All digital signatures will be invalidated")
+        else:
+            raise DigitalSignatureError()
     if pdfinfo.has_acroform:
         if options.redo_ocr:
-            log.error(
+            raise InputFileError(
                 "This PDF has a user fillable form. --redo-ocr is not "
                 "currently possible on such files."
             )
-            raise InputFileError()
         else:
             log.warning(
                 "This PDF has a fillable form. "
@@ -208,6 +224,7 @@ def validate_pdfinfo_options(context: PdfContext) -> None:
 
 
 def _vector_page_dpi(pageinfo: PageInfo) -> int:
+    """Get a DPI to use for vector pages, if the page has vector content."""
     return VECTOR_PAGE_DPI if pageinfo.has_vector or pageinfo.has_text else 0
 
 
@@ -227,7 +244,10 @@ def get_page_dpi(pageinfo: PageInfo, options) -> Resolution:
 
 
 def get_page_square_dpi(pageinfo: PageInfo, options) -> Resolution:
-    """Get the DPI when we require xres == yres, scaled to physical units."""
+    """Get the DPI when we require xres == yres, scaled to physical units.
+
+    Page DPI includes UserUnit scaling.
+    """
     xres = pageinfo.dpi.x or 0.0
     yres = pageinfo.dpi.y or 0.0
     userunit = float(pageinfo.userunit) or 1.0
@@ -243,7 +263,12 @@ def get_page_square_dpi(pageinfo: PageInfo, options) -> Resolution:
 
 
 def get_canvas_square_dpi(pageinfo: PageInfo, options) -> Resolution:
-    """Get the DPI when we require xres == yres, in Postscript units."""
+    """Get the DPI when we require xres == yres, in Postscript units.
+
+    Canvas DPI is independent of PDF UserUnit scaling, which is
+    used to describe situations where the PDF user space is not 1:1 with
+    the physical units of the page.
+    """
     units = float(
         max(
             (pageinfo.dpi.x) or VECTOR_PAGE_DPI,
@@ -256,6 +281,7 @@ def get_canvas_square_dpi(pageinfo: PageInfo, options) -> Resolution:
 
 
 def is_ocr_required(page_context: PageContext) -> bool:
+    """Check if the page needs to be OCR'd."""
     pageinfo = page_context.pageinfo
     options = page_context.options
 
@@ -331,6 +357,7 @@ def is_ocr_required(page_context: PageContext) -> bool:
 
 
 def rasterize_preview(input_file: Path, page_context: PageContext) -> Path:
+    """Generate a lower quality preview image."""
     output_file = page_context.get_path('rasterize_preview.jpg')
     canvas_dpi = get_canvas_square_dpi(page_context.pageinfo, page_context.options)
     page_dpi = get_page_square_dpi(page_context.pageinfo, page_context.options)
@@ -343,12 +370,15 @@ def rasterize_preview(input_file: Path, page_context: PageContext) -> Path:
         page_dpi=page_dpi,
         rotation=0,
         filter_vector=False,
+        stop_on_soft_error=not page_context.options.continue_on_soft_render_error,
     )
     return output_file
 
 
-def describe_rotation(page_context: PageContext, orient_conf, correction: int) -> str:
-    """Describe the page rotation we are going to perform."""
+def describe_rotation(
+    page_context: PageContext, orient_conf: OrientationConfidence, correction: int
+) -> str:
+    """Describe the page rotation we are going to perform (or not perform)."""
     direction = {0: '⇧', 90: '⇨', 180: '⇩', 270: '⇦'}
     turns = {0: ' ', 90: '⬏', 180: '↻', 270: '⬑'}
 
@@ -375,7 +405,7 @@ def describe_rotation(page_context: PageContext, orient_conf, correction: int) -
 
 
 def get_orientation_correction(preview: Path, page_context: PageContext) -> int:
-    """Work out orientation correct for each page.
+    """Work out orientation correction for each page.
 
     We ask Ghostscript to draw a preview page, which will rasterize with the
     current /Rotate applied, and then ask OCR which way the page is
@@ -409,8 +439,22 @@ def rasterize(
     page_context: PageContext,
     correction: int = 0,
     output_tag: str = '',
-    remove_vectors=None,
-):
+    remove_vectors: bool | None = None,
+) -> Path:
+    """Rasterize a PDF page to a PNG image.
+
+    Args:
+        input_file: The input PDF file path.
+        page_context: The page context object.
+        correction: The orientation correction angle. Defaults to 0.
+        output_tag: The output tag. Defaults to ''.
+        remove_vectors: Whether to remove vectors. Defaults to None, which means
+            the value from the page context options will be used. If the value
+            is True or False, it will override the page context options.
+
+    Returns:
+        Path: The output PNG file path.
+    """
     colorspaces = ['pngmono', 'pnggray', 'png256', 'png16m']
     device_idx = 0
 
@@ -455,6 +499,7 @@ def rasterize(
         pageno=pageinfo.pageno + 1,
         rotation=correction,
         filter_vector=remove_vectors,
+        stop_on_soft_error=not page_context.options.continue_on_soft_render_error,
     )
     return output_file
 
@@ -470,6 +515,15 @@ def preprocess_remove_background(input_file: Path, page_context: PageContext) ->
 
 
 def preprocess_deskew(input_file: Path, page_context: PageContext) -> Path:
+    """Deskews the input image using the OCR engine and saves the output to a file.
+
+    Args:
+        input_file: The input image file to deskew.
+        page_context: The context of the page being processed.
+
+    Returns:
+        Path: The path to the deskewed image file.
+    """
     output_file = page_context.get_path('pp_deskew.png')
     dpi = get_page_square_dpi(page_context.pageinfo, page_context.options)
 
@@ -565,7 +619,16 @@ def ocr_engine_hocr(input_file: Path, page_context: PageContext) -> tuple[Path,
 
 
 def should_visible_page_image_use_jpg(pageinfo: PageInfo) -> bool:
-    # If all images were JPEGs originally, produce a JPEG as output
+    """Determines whether the visible page image should be saved as a JPEG.
+
+    If all images were JPEGs originally, permit a JPEG as output.
+
+    Args:
+        pageinfo: The PageInfo object containing information about the page.
+
+    Returns:
+        A boolean indicating whether the visible page image should be saved as a JPEG.
+    """
     return bool(pageinfo.images) and all(
         im.enc == Encoding.jpeg for im in pageinfo.images
     )
@@ -736,6 +799,7 @@ def convert_to_pdfa(input_pdf: Path, input_ps_stub: Path, context: PdfContext) -
             if options.progress_bar
             else None
         ),
+        stop_on_soft_error=not options.continue_on_soft_render_error,
     )
 
     return output_file
@@ -789,24 +853,45 @@ def metadata_fixup(working_file: Path, context: PdfContext) -> Path:
 
     with pikepdf.open(context.origin) as original, pikepdf.open(working_file) as pdf:
         docinfo = get_docinfo(original, context)
-        with pdf.open_metadata() as meta:
-            meta.load_from_docinfo(docinfo, delete_missing=False, raise_failure=False)
+        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
-            # match Ghostscript, for consistency
-            if 'xmp:CreateDate' not in meta:
-                meta['xmp:CreateDate'] = meta.get('xmp:ModifyDate', '')
+            # 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.get('dc:title') == 'Untitled':
+                if meta_pdf.get('dc:title') == 'Untitled':
                     # Ghostscript likes to set title to Untitled if omitted from input.
                     # Reverse this, because PDF/A TechNote 0003:Metadata in PDF/A-1
                     # and the XMP Spec do not make this recommendation.
                     if 'dc:title' not in meta_original:
-                        del meta['dc:title']
-                missing = set(meta_original.keys()) - set(meta.keys())
-                report_on_metadata(missing)
+                        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
@@ -822,6 +907,18 @@ def metadata_fixup(working_file: Path, context: PdfContext) -> Path:
     return output_file
 
 
+def _file_size_ratio(
+    input_file: Path, output_file: Path
+) -> tuple[float | None, float | None]:
+    input_size = input_file.stat().st_size
+    output_size = output_file.stat().st_size
+    if output_size == 0:
+        return None, None
+    ratio = input_size / output_size
+    savings = 1 - output_size / input_size
+    return ratio, savings
+
+
 def optimize_pdf(
     input_file: Path, context: PdfContext, executor: Executor
 ) -> tuple[Path, Sequence[str]]:
@@ -834,13 +931,12 @@ def optimize_pdf(
         linearize=should_linearize(input_file, context),
     )
 
-    input_size = input_file.stat().st_size
-    output_size = output_file.stat().st_size
-    if output_size > 0:
-        ratio = input_size / output_size
-        savings = 1 - output_size / input_size
-        log.info(f"Optimize ratio: {ratio:.2f} savings: {(savings):.1%}")
-
+    ratio, savings = _file_size_ratio(input_file, output_file)
+    if ratio:
+        log.info(f"Image optimization ratio: {ratio:.2f} savings: {(savings):.1%}")
+    ratio, savings = _file_size_ratio(context.origin, output_file)
+    if ratio:
+        log.info(f"Total file size ratio: {ratio:.2f} savings: {(savings):.1%}")
     return output_pdf, messages
 
 

src/ocrmypdf/_validation.py

@@ -51,15 +51,17 @@ def check_platform() -> None:
         )
 
 
-def check_options_languages(options: Namespace, ocr_engine_languages: set[str]) -> None:
+def check_options_languages(
+    options: Namespace, ocr_engine_languages: list[str]
+) -> None:
     if not options.languages:
-        options.languages = {DEFAULT_LANGUAGE}
+        options.languages = [DEFAULT_LANGUAGE]
         system_lang = locale.getlocale()[0]
         if system_lang and not system_lang.startswith('en'):
             log.debug("No language specified; assuming --language %s", DEFAULT_LANGUAGE)
     if not ocr_engine_languages:
         return
-    missing_languages = options.languages - ocr_engine_languages
+    missing_languages = set(options.languages) - set(ocr_engine_languages)
     if missing_languages:
         lang_text = '\n'.join(lang for lang in missing_languages)
         msg = (
@@ -71,15 +73,16 @@ def check_options_languages(options: Namespace, ocr_engine_languages: set[str])
             "See the online documentation for instructions:\n"
             "    https://ocrmypdf.readthedocs.io/en/latest/languages.html\n"
             "\n"
-            "Note: most languages are identified by a 3-digit ISO 639-2 Code.\n"
-            "For example, English is 'eng', German is 'deu', and Spanish is 'spa'."
+            "Note: most languages are identified by a 3-letter ISO 639-2 Code.\n"
+            "For example, English is 'eng', German is 'deu', and Spanish is 'spa'.\n"
+            "Simplified Chinese is 'chi_sim' and Traditional Chinese is 'chi_tra'."
             "\n"
         )
         raise MissingDependencyError(msg)
 
 
 def check_options_output(options: Namespace) -> None:
-    is_latin = options.languages.issubset(HOCR_OK_LANGS)
+    is_latin = set(options.languages).issubset(HOCR_OK_LANGS)
 
     if options.pdf_renderer.startswith('hocr') and not is_latin:
         log.warning(

src/ocrmypdf/api.py

@@ -15,9 +15,6 @@ from pathlib import Path
 from typing import AnyStr, BinaryIO, Iterable, Union
 from warnings import warn
 
-import coloredlogs
-from humanfriendly.terminal import enable_ansi_support
-
 from ocrmypdf._logging import PageNumberFilter, TqdmConsole
 from ocrmypdf._plugin_manager import get_plugin_manager
 from ocrmypdf._sync import run_pipeline
@@ -112,14 +109,7 @@ def configure_logging(
     else:
         fmt = '%(pageno)s%(message)s'
 
-    use_colors = progress_bar_friendly
     formatter = None
-    if use_colors:
-        use_colors = enable_ansi_support()
-        if use_colors:
-            use_colors = coloredlogs.terminal_supports_colors()
-        if use_colors:
-            formatter = coloredlogs.ColoredFormatter(fmt=fmt)
 
     if not formatter:
         formatter = logging.Formatter(fmt=fmt)
@@ -248,6 +238,7 @@ def ocr(  # noqa: ruff: disable=D417
     user_words: os.PathLike | None = None,
     user_patterns: os.PathLike | None = None,
     fast_web_view: float | None = None,
+    continue_on_soft_render_error: bool | None = None,
     plugins: Iterable[StrPath] | None = None,
     plugin_manager=None,
     keep_temporary_files: bool | None = None,

src/ocrmypdf/builtin_plugins/concurrency.py

@@ -16,10 +16,10 @@ from concurrent.futures import ProcessPoolExecutor, ThreadPoolExecutor, as_compl
 from contextlib import suppress
 from typing import Callable, Iterable, Type, Union
 
-from tqdm import tqdm
+from rich.console import Console as RichConsole
 
 from ocrmypdf import Executor, hookimpl
-from ocrmypdf._logging import TqdmConsole
+from ocrmypdf._logging import RichLoggingHandler, RichTqdmProgressAdapter
 from ocrmypdf.exceptions import InputFileError
 from ocrmypdf.helpers import remove_all_log_handlers
 
@@ -168,13 +168,20 @@ def get_executor(progressbar_class):
     return StandardExecutor(pbar_class=progressbar_class)
 
 
+RICH_CONSOLE = RichConsole(stderr=True)
+
+
 @hookimpl
 def get_progressbar_class():
     """Return the default progress bar class."""
-    return tqdm
+
+    def partial_RichTqdmProgressAdapter(*args, **kwargs):
+        return RichTqdmProgressAdapter(*args, **kwargs, console=RICH_CONSOLE)
+
+    return partial_RichTqdmProgressAdapter
 
 
 @hookimpl
 def get_logging_console():
     """Return the default logging console handler."""
-    return logging.StreamHandler(stream=TqdmConsole(sys.stderr))
+    return RichLoggingHandler(console=RICH_CONSOLE)

src/ocrmypdf/builtin_plugins/ghostscript.py

@@ -45,6 +45,7 @@ def rasterize_pdf_page(
     page_dpi,
     rotation,
     filter_vector,
+    stop_on_soft_error,
 ):
     """Rasterize a single page of a PDF file using Ghostscript."""
     ghostscript.rasterize_pdf(
@@ -56,6 +57,7 @@ def rasterize_pdf_page(
         page_dpi=page_dpi,
         rotation=rotation,
         filter_vector=filter_vector,
+        stop_on_error=stop_on_soft_error,
     )
     return output_file
 
@@ -69,6 +71,7 @@ def generate_pdfa(
     pdf_version,
     pdfa_part,
     progressbar_class,
+    stop_on_soft_error,
 ):
     """Generate a PDF/A from the list of PDF pages and PDF/A metadata."""
     ghostscript.generate_pdfa(
@@ -78,5 +81,6 @@ def generate_pdfa(
         pdf_version=pdf_version,
         pdfa_part=pdfa_part,
         progressbar_class=progressbar_class,
+        stop_on_error=stop_on_soft_error,
     )
     return output_file

src/ocrmypdf/cli.py

@@ -84,16 +84,16 @@ class LanguageSetAction(argparse.Action):
     def __init__(self, option_strings, dest, default=None, **kwargs):
         """Initialize the action."""
         if default is None:
-            default = set()
+            default = list()
         super().__init__(option_strings, dest, default=default, **kwargs)
 
     def __call__(self, parser, namespace, values, option_string=None):
         """Add a language to the set."""
         dest = getattr(namespace, self.dest)
         if '+' in values:
-            dest.update(lang for lang in values.split('+'))
+            [dest.append(lang) for lang in values.split('+')]
         else:
-            dest.add(values)
+            dest.append(values)
 
 
 def get_parser():
@@ -359,6 +359,13 @@ Online documentation is located at:
         help="Skip OCR on pages larger than the specified amount of megapixels, "
         "but include skipped pages in final output",
     )
+    ocrsettings.add_argument(
+        '--invalidate-digital-signatures',
+        action='store_true',
+        help="Normally, OCRmyPDF will refuse to OCR a PDF that has a digital "
+        "signature. This option allows OCR to proceed, but the digital signature "
+        "will be invalidated.",
+    )
 
     advanced = parser.add_argument_group(
         "Advanced", "Advanced options to control OCRmyPDF"
@@ -420,6 +427,14 @@ Online documentation is located at:
         "which do not benefit. If the threshold is 0 it will be apply to all files. "
         "Set the threshold very high to disable.",
     )
+    advanced.add_argument(
+        '--continue-on-soft-render-error',
+        action='store_true',
+        help="Continue processing pages after a recoverable PDF rendering error. "
+        "A recoverable error is one that does not prevent the page from being "
+        "rendered, but may result in visual differences compared to the input "
+        "file. Missing fonts are a typical source of these errors.",
+    )
     advanced.add_argument(
         '--plugin',
         dest='plugins',

src/ocrmypdf/exceptions.py

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

src/ocrmypdf/extra_plugins/semfree.py

@@ -12,7 +12,7 @@ worker communicates only with the main process.
 
 This is not without drawbacks. If the tasks are not "even" in size, which cannot
 be guaranteed, some workers may end up with too much work while others are idle.
-It is less efficient than the standard implementation, so not th edefault.
+It is less efficient than the standard implementation, so not the default.
 """
 
 from __future__ import annotations

src/ocrmypdf/optimize.py

@@ -230,6 +230,65 @@ def extract_image_generic(
     return None
 
 
+def _find_image_xrefs_container(
+    pdf: Pdf,
+    container: Object,
+    pageno: int,
+    include_xrefs: MutableSet[Xref],
+    exclude_xrefs: MutableSet[Xref],
+    pageno_for_xref: dict[Xref, int],
+    depth: int = 0,
+):
+    """Find all image XRefs in a page or Form XObject and add to the include/exclude sets."""
+    if depth > 10:
+        log.warning("Recursion depth exceeded in _find_image_xrefs_page")
+        return
+    try:
+        xobjs = container.Resources.XObject
+    except AttributeError:
+        return
+    for _imname, image in dict(xobjs).items():
+        if image.objgen[1] != 0:
+            continue  # Ignore images in an incremental PDF
+        if Name.Subtype in image and image.Subtype == Name.Form:
+            # Recurse into Form XObjects
+            log.debug(f"Recursing into Form XObject {_imname} in page {pageno}")
+            _find_image_xrefs_container(
+                pdf,
+                image,
+                pageno,
+                include_xrefs,
+                exclude_xrefs,
+                pageno_for_xref,
+                depth + 1,
+            )
+            continue
+        xref = Xref(image.objgen[0])
+        if Name.SMask in image:
+            # Ignore soft masks
+            smask_xref = Xref(image.SMask.objgen[0])
+            exclude_xrefs.add(smask_xref)
+            log.debug(f"xref {smask_xref}: skipping image because it is an SMask")
+        include_xrefs.add(xref)
+        log.debug(f"xref {xref}: treating as an optimization candidate")
+        if xref not in pageno_for_xref:
+            pageno_for_xref[xref] = pageno
+
+
+def _find_image_xrefs(pdf: Pdf):
+    include_xrefs: MutableSet[Xref] = set()
+    exclude_xrefs: MutableSet[Xref] = set()
+    pageno_for_xref: dict[Xref, int] = {}
+
+    for pageno, page in enumerate(pdf.pages):
+        _find_image_xrefs_container(
+            pdf, page, pageno, include_xrefs, exclude_xrefs, pageno_for_xref
+        )
+
+    working_xrefs = include_xrefs - exclude_xrefs
+    return working_xrefs, pageno_for_xref
+
+
 def extract_images(
     pike: Pdf,
     root: Path,
@@ -250,30 +309,8 @@ def extract_images(
     it does a tuple should be returned: (xref, ext) where .ext is the file
     extension. extract_fn must also extract the file it finds interesting.
     """
-    include_xrefs: MutableSet[Xref] = set()
-    exclude_xrefs: MutableSet[Xref] = set()
-    pageno_for_xref = {}
     errors = 0
-    for pageno, page in enumerate(pike.pages):
-        try:
-            xobjs = page.Resources.XObject
-        except AttributeError:
-            continue
-        for _imname, image in dict(xobjs).items():
-            if image.objgen[1] != 0:
-                continue  # Ignore images in an incremental PDF
-            xref = Xref(image.objgen[0])
-            if Name.SMask in image:
-                # Ignore soft masks
-                smask_xref = Xref(image.SMask.objgen[0])
-                exclude_xrefs.add(smask_xref)
-                log.debug(f"xref {smask_xref}: skipping image because it is an SMask")
-            include_xrefs.add(xref)
-            log.debug(f"xref {xref}: treating as an optimization candidate")
-            if xref not in pageno_for_xref:
-                pageno_for_xref[xref] = pageno
-
-    working_xrefs = include_xrefs - exclude_xrefs
+    working_xrefs, pageno_for_xref = _find_image_xrefs(pike)
     for xref in working_xrefs:
         image = pike.get_object((xref, 0))
         try:

src/ocrmypdf/pdfinfo/info.py

@@ -21,7 +21,9 @@ from typing import Container, Iterable, Iterator, Mapping, NamedTuple, Sequence,
 from warnings import warn
 
 from pikepdf import (
+    Name,
     Object,
+    Page,
     Pdf,
     PdfImage,
     PdfInlineImage,
@@ -491,15 +493,15 @@ def _image_xobjects(container) -> Iterator[tuple[Object, str]]:
     since the object does not know its own name.
 
     """
-    if '/Resources' not in container:
+    if Name.Resources not in container:
         return
-    resources = container['/Resources']
-    if '/XObject' not in resources:
+    resources = container[Name.Resources]
+    if Name.XObject not in resources:
         return
-    for key, candidate in resources['/XObject'].items():
-        if candidate is None or '/Subtype' not in candidate:
+    for key, candidate in resources[Name.XObject].items():
+        if candidate is None or Name.Subtype not in candidate:
             continue
-        if candidate['/Subtype'] == '/Image':
+        if candidate[Name.Subtype] == Name.Image:
             pdfimage = candidate
             yield (pdfimage, key)
 
@@ -535,15 +537,15 @@ def _find_form_xobject_images(pdf: Pdf, container: Object, contentsinfo: Content
     The container may be a page, or a parent Form XObject.
 
     """
-    if '/Resources' not in container:
+    if Name.Resources not in container:
         return
-    resources = container['/Resources']
-    if '/XObject' not in resources:
+    resources = container[Name.Resources]
+    if Name.XObject not in resources:
         return
-    xobjs = resources['/XObject'].as_dict()
+    xobjs = resources[Name.XObject].as_dict()
     for xobj in xobjs:
         candidate = xobjs[xobj]
-        if candidate is None or candidate['/Subtype'] != '/Form':
+        if candidate is None or candidate[Name.Subtype] != Name.Form:
             continue
 
         form_xobject = candidate
@@ -581,16 +583,19 @@ def _process_content_streams(
     downsampling.
 
     """
-    if container.get('/Type') == '/Page' and '/Contents' in container:
+    if container.get(Name.Type) == Name.Page and Name.Contents in container:
         initial_shorthand = shorthand or UNIT_SQUARE
-    elif container.get('/Type') == '/XObject' and container['/Subtype'] == '/Form':
+    elif (
+        container.get(Name.Type) == Name.XObject
+        and container[Name.Subtype] == Name.Form
+    ):
         # Set the CTM to the state it was when the "Do" operator was
         # encountered that is drawing this instance of the Form XObject
         ctm = PdfMatrix(shorthand) if shorthand else PdfMatrix.identity()
 
         # A Form XObject may provide its own matrix to map form space into
         # user space. Get this if one exists
-        form_shorthand = container.get('/Matrix', PdfMatrix.identity())
+        form_shorthand = container.get(Name.Matrix, PdfMatrix.identity())
         form_matrix = PdfMatrix(form_shorthand)
 
         # Concatenate form matrix with CTM to ensure CTM is correct for
@@ -771,7 +776,7 @@ class PageInfo:
         check_pages: Container[int],
         detailed_analysis: bool,
     ):
-        page = pdf.pages[pageno]
+        page: Page = pdf.pages[pageno]
         mediabox = [Decimal(d) for d in page.MediaBox.as_list()]
         width_pt = mediabox[2] - mediabox[0]
         height_pt = mediabox[3] - mediabox[1]
@@ -779,7 +784,7 @@ class PageInfo:
         check_this_page = pageno in check_pages
 
         if check_this_page and detailed_analysis:
-            pscript5_mode = str(pdf.docinfo.get('/Creator')).startswith('PScript5')
+            pscript5_mode = str(pdf.docinfo.get(Name.Creator)).startswith('PScript5')
             miner = get_page_analysis(infile, pageno, pscript5_mode)
             self._textboxes = list(simplify_textboxes(miner, get_text_boxes))
             bboxes = (box.bbox for box in self._textboxes)
@@ -789,17 +794,13 @@ class PageInfo:
             self._textboxes = []
             self._has_text = None  # i.e. "no information"
 
-        userunit = page.get('/UserUnit', Decimal(1.0))
+        userunit = page.get(Name.UserUnit, Decimal(1.0))
         if not isinstance(userunit, Decimal):
             userunit = Decimal(userunit)
         self._userunit = userunit
         self._width_inches = width_pt * userunit / Decimal(72.0)
         self._height_inches = height_pt * userunit / Decimal(72.0)
-
-        try:
-            self._rotate = int(page['/Rotate'])
-        except KeyError:
-            self._rotate = 0
+        self._rotate = int(getattr(page.obj, 'Rotate', 0))
 
         userunit_shorthand = (userunit, 0, 0, userunit, 0, 0)
 
@@ -953,6 +954,10 @@ DEFAULT_EXECUTOR = SerialExecutor()
 class PdfInfo:
     """Get summary information about a PDF."""
 
+    _has_acroform: bool = False
+    _has_signature: bool = False
+    _needs_rendering: bool = False
+
     def __init__(
         self,
         infile,
@@ -980,13 +985,13 @@ class PdfInfo:
                 check_pages=check_pages,
                 detailed_analysis=detailed_analysis,
             )
-            self._needs_rendering = pdf.Root.get('/NeedsRendering', False)
-            self._has_acroform = False
-            if '/AcroForm' in pdf.Root:
-                if len(pdf.Root.AcroForm.get('/Fields', [])) > 0:
+            self._needs_rendering = pdf.Root.get(Name.NeedsRendering, False)
+            if Name.AcroForm in pdf.Root:
+                if len(pdf.Root.AcroForm.get(Name.Fields, [])) > 0:
                     self._has_acroform = True
-                elif '/XFA' in pdf.Root.AcroForm:
+                elif Name.XFA in pdf.Root.AcroForm:
                     self._has_acroform = True
+                self._has_signature = bool(pdf.Root.AcroForm.get(Name.SigFlags, 0) & 1)
 
     @property
     def pages(self) -> Sequence[PageInfo | None]:
@@ -1006,9 +1011,14 @@ class PdfInfo:
 
     @property
     def has_acroform(self) -> bool:
-        """Return True if any page has an AcroForm."""
+        """Return True if the document catalog has an AcroForm."""
         return self._has_acroform
 
+    @property
+    def has_signature(self) -> bool:
+        """Return True if the document annotations has a digital signature."""
+        return self._has_signature
+
     @property
     def filename(self) -> str | Path:
         """Return filename of PDF."""

src/ocrmypdf/pluginspec.py

@@ -203,6 +203,7 @@ def rasterize_pdf_page(
     page_dpi: Resolution | None,
     rotation: int | None,
     filter_vector: bool,
+    stop_on_soft_error: bool,
 ) -> Path:
     """Rasterize one page of a PDF at resolution raster_dpi in canvas units.
 
@@ -213,19 +214,26 @@ def rasterize_pdf_page(
     Args:
         input_file: The PDF to rasterize.
         output_file: The desired name of the rasterized image.
-        raster_device: Type of image to produce at output_file
-        raster_dpi: Resolution at which to rasterize page
-        pageno: Page number to rasterize (beginning at page 1)
-        page_dpi: Resolution, overriding output image DPI
-        rotation: Cardinal angle, clockwise, to rotate page
-        filter_vector: If True, remove vector graphics objects
+        raster_device: Type of image to produce at output_file.
+        raster_dpi: Resolution in dots per inch at which to rasterize page.
+        pageno: Page number to rasterize (beginning at page 1).
+        page_dpi: Resolution, overriding output image DPI.
+        rotation: Cardinal angle, clockwise, to rotate page.
+        filter_vector: If True, remove vector graphics objects.
+        stop_on_soft_error: If there is an "soft error" such that PDF page image
+            generation can proceed, but may visually differ from the original,
+            the implementer of this hook should raise a detailed exception. If
+            ``False``, continue processing and report by logging it. If the hook
+            cannot proceed, it should always raise an exception, regardless of
+            this setting. One "soft error" would be a missing font that is
+            required to properly rasterize the PDF.
+
     Returns:
         Path: output_file if successful
     Note:
         This hook will be called from child processes. Modifying global state
         will not affect the main process or other child processes.
 
-
     Note:
         This is a :ref:`firstresult hook<firstresult>`.
     """
@@ -462,6 +470,7 @@ def generate_pdfa(
     pdf_version: str,
     pdfa_part: str,
     progressbar_class,
+    stop_on_soft_error: bool,
 ) -> Path:
     """Generate a PDF/A.
 
@@ -492,6 +501,12 @@ def generate_pdfa(
             and the name of the work units ("page"). Then ``instance.update()``
             will be called when a work unit is completed. If ``None``, no
             progress information is reported.
+        stop_on_soft_error: If there is an "soft error" such that PDF/A generation
+            can proceed and produce a valid PDF/A, but output may be invalid or
+            may not visually resemble the original, the implementer of this hook
+            should raise a detailed exception. If ``False``, continue processing
+            and report by logging it. If the hook cannot proceed, it should always
+            raise an exception, regardless of this setting.
 
     Returns:
         Path: If successful, the hook should return ``output_file``.

src/ocrmypdf/subprocess/__init__.py

@@ -118,8 +118,6 @@ def run_polling_stderr(
 def _fix_process_args(
     args: Args, env: OsEnviron | None, kwargs
 ) -> tuple[Args, OsEnviron, logging.Logger, bool]:
-    assert 'universal_newlines' not in kwargs, "Use text= instead of universal_newlines"
-
     if not env:
         env = os.environ
 

tests/plugins/gs_feature_elision.py

@@ -31,6 +31,7 @@ def generate_pdfa(pdf_pages, pdfmark, output_file, compression, pdf_version, pdf
             pdf_version=pdf_version,
             pdfa_part=pdfa_part,
             progressbar_class=None,
+            stop_on_soft_error=True,
         )
         mock.assert_called_once()
     return output_file

tests/plugins/gs_pdfa_failure.py

@@ -33,6 +33,7 @@ def generate_pdfa(pdf_pages, pdfmark, output_file, compression, pdf_version, pdf
             pdf_version=pdf_version,
             pdfa_part=pdfa_part,
             progressbar_class=None,
+            stop_on_soft_error=True,
         )
         mock.assert_called()
         return output_file

tests/plugins/gs_raster_failure.py

@@ -39,6 +39,7 @@ def rasterize_pdf_page(
             page_dpi=page_dpi,
             rotation=rotation,
             filter_vector=filter_vector,
+            stop_on_soft_error=True,
         )
         mock.assert_called()
         return output_file

tests/plugins/gs_raster_soft_error.py

@@ -0,0 +1,47 @@
+# SPDX-FileCopyrightText: 2022 James R. Barlow
+# SPDX-License-Identifier: MIT
+
+from __future__ import annotations
+
+from pathlib import Path
+from subprocess import CalledProcessError
+from unittest.mock import patch
+
+from ocrmypdf import hookimpl
+from ocrmypdf.builtin_plugins import ghostscript
+from ocrmypdf.subprocess import run
+
+
+def fail_if_stoponerror(args, **kwargs):
+    if '-dPDFSTOPONERROR' in args:
+        raise CalledProcessError(1, 'gs', output=b"", stderr=b"PDF STOP ON ERROR")
+    return run(args, **kwargs)
+
+
+@hookimpl
+def rasterize_pdf_page(
+    input_file,
+    output_file,
+    raster_device,
+    raster_dpi,
+    pageno,
+    page_dpi,
+    rotation,
+    filter_vector,
+    stop_on_soft_error,
+) -> Path:
+    with patch('ocrmypdf._exec.ghostscript.run') as mock:
+        mock.side_effect = fail_if_stoponerror
+        ghostscript.rasterize_pdf_page(
+            input_file=input_file,
+            output_file=output_file,
+            raster_device=raster_device,
+            raster_dpi=raster_dpi,
+            pageno=pageno,
+            page_dpi=page_dpi,
+            rotation=rotation,
+            filter_vector=filter_vector,
+            stop_on_soft_error=stop_on_soft_error,
+        )
+        mock.assert_called()
+        return output_file

tests/plugins/gs_render_failure.py

@@ -28,6 +28,7 @@ def generate_pdfa(pdf_pages, pdfmark, output_file, compression, pdf_version, pdf
             pdf_version=pdf_version,
             pdfa_part=pdfa_part,
             progressbar_class=None,
+            stop_on_soft_error=True,
         )
         mock.assert_called()
         return output_file

tests/plugins/gs_render_soft_error.py

@@ -0,0 +1,44 @@
+# SPDX-FileCopyrightText: 2022 James R. Barlow
+# SPDX-License-Identifier: MIT
+
+from __future__ import annotations
+
+from pathlib import Path
+from subprocess import CalledProcessError
+from unittest.mock import patch
+
+from ocrmypdf import hookimpl
+from ocrmypdf.builtin_plugins import ghostscript
+from ocrmypdf.subprocess import run_polling_stderr
+
+
+def fail_if_stoponerror(args, **kwargs):
+    if '-dPDFSTOPONERROR' in args:
+        raise CalledProcessError(1, 'gs', output=b"", stderr=b"PDF STOP ON ERROR")
+    return run_polling_stderr(args, **kwargs)
+
+
+@hookimpl
+def generate_pdfa(
+    pdf_pages,
+    pdfmark,
+    output_file,
+    compression,
+    pdf_version,
+    pdfa_part,
+    stop_on_soft_error,
+):
+    with patch('ocrmypdf._exec.ghostscript.run_polling_stderr') as mock:
+        mock.side_effect = fail_if_stoponerror
+        ghostscript.generate_pdfa(
+            pdf_pages=pdf_pages,
+            pdfmark=pdfmark,
+            output_file=output_file,
+            compression=compression,
+            pdf_version=pdf_version,
+            pdfa_part=pdfa_part,
+            progressbar_class=None,
+            stop_on_soft_error=stop_on_soft_error,
+        )
+        mock.assert_called()
+        return output_file

tests/resources/meta.pdf

@@ -0,0 +1,115 @@
+%PDF-1.3
+%¿÷¢þ
+1 0 obj
+<< /Pages 2 0 R /Type /Catalog >>
+endobj
+2 0 obj
+<< /Count 1 /Kids [ 3 0 R ] /Type /Pages >>
+endobj
+3 0 obj
+<< /MediaBox [ 0 0 720 720 ] /Parent 2 0 R /Resources << >> /Type /Page >>
+endobj
+xref
+0 4
+0000000000 65535 f 
+0000000015 00000 n 
+0000000064 00000 n 
+0000000123 00000 n 
+trailer << /Root 1 0 R /Size 4 /ID [<52bba3c78160d0c6e851b59110e5d076><52bba3c78160d0c6e851b59110e5d076>] >>
+startxref
+213
+%%EOF
+%BeginExifToolUpdate
+1 0 obj
+<<
+/Pages 2 0 R
+/Type /Catalog
+/Metadata 5 0 R
+>>
+endobj
+4 0 obj
+<<
+/Author (yXaryipxyRk9dVjWjSSaVaNCKeLRgEVzPRMp)
+/Keywords (s9EeALwUg7urA7fnnhm5EtUyC54sW2WPUzqh)
+/Subject (t49vimctvnuH7ZeAjAkv52ACvWFjcnm5MPJr)
+/Title (NFY5f7Ft2DWMkxLhXwxvFf7eWR2KeK3vEDcd)
+>>
+endobj
+5 0 obj
+<<
+/Type /Metadata
+/Subtype /XML
+/Length 3232
+>>
+stream
+<?xpacket begin='' id='W5M0MpCehiHzreSzNTczkc9d'?>
+<x:xmpmeta xmlns:x='adobe:ns:meta/' x:xmptk='Image::ExifTool 12.60'>
+<rdf:RDF xmlns:rdf='http://www.w3.org/1999/02/22-rdf-syntax-ns#'>
+
+ <rdf:Description rdf:about=''
+  xmlns:dc='http://purl.org/dc/elements/1.1/'>
+  <dc:subject>
+   <rdf:Bag>
+    <rdf:li>t49vimctvnuH7ZeAjAkv52ACvWFjcnm5MPJr</rdf:li>
+   </rdf:Bag>
+  </dc:subject>
+  <dc:title>
+   <rdf:Alt>
+    <rdf:li xml:lang='x-default'>NFY5f7Ft2DWMkxLhXwxvFf7eWR2KeK3vEDcd</rdf:li>
+   </rdf:Alt>
+  </dc:title>
+ </rdf:Description>
+
+ <rdf:Description rdf:about=''
+  xmlns:pdf='http://ns.adobe.com/pdf/1.3/'>
+  <pdf:Author>yXaryipxyRk9dVjWjSSaVaNCKeLRgEVzPRMp</pdf:Author>
+  <pdf:Keywords>s9EeALwUg7urA7fnnhm5EtUyC54sW2WPUzqh</pdf:Keywords>
+ </rdf:Description>
+</rdf:RDF>
+</x:xmpmeta>
+                                                                                                    
+                                                                                                    
+                                                                                                    
+                                                                                                    
+                                                                                                    
+                                                                                                    
+                                                                                                    
+                                                                                                    
+                                                                                                    
+                                                                                                    
+                                                                                                    
+                                                                                                    
+                                                                                                    
+                                                                                                    
+                                                                                                    
+                                                                                                    
+                                                                                                    
+                                                                                                    
+                                                                                                    
+                                                                                                    
+                                                                                                    
+                                                                                                    
+                                                                                                    
+                                                                                                    
+<?xpacket end='w'?>
+endstream
+endobj
+xref
+0 2
+0000000000 65535 f 
+0000000452 00000 n 
+4 2
+0000000517 00000 n 
+0000000728 00000 n 
+trailer
+<<
+/Root 1 0 R
+/Size 6
+/ID [ <52bba3c78160d0c6e851b59110e5d076> <54bba3c78160d0c6e851b59110e5d076> ]
+/Info 4 0 R
+/Prev 213
+>>
+%EndExifToolUpdate 431
+startxref
+4043
+%%EOF

tests/test_acroform.py

@@ -5,6 +5,7 @@ from __future__ import annotations
 
 import logging
 
+import pikepdf
 import pytest
 
 import ocrmypdf
@@ -19,10 +20,11 @@ def acroform(resources):
     return resources / 'acroform.pdf'
 
 
-def test_acroform_and_redo(acroform, caplog, no_outpdf):
-    with pytest.raises(ocrmypdf.exceptions.InputFileError):
+def test_acroform_and_redo(acroform, no_outpdf):
+    with pytest.raises(
+        ocrmypdf.exceptions.InputFileError, match='--redo-ocr is not currently possible'
+    ):
         check_ocrmypdf(acroform, no_outpdf, '--redo-ocr')
-    assert '--redo-ocr is not currently possible' in caplog.text
 
 
 def test_acroform_message(acroform, caplog, outpdf):
@@ -30,3 +32,23 @@ def test_acroform_message(acroform, caplog, outpdf):
     check_ocrmypdf(acroform, outpdf, '--plugin', 'tests/plugins/tesseract_noop.py')
     assert 'fillable form' in caplog.text
     assert '--force-ocr' in caplog.text
+
+
+@pytest.fixture
+def digitally_signed(acroform, outdir):
+    out = outdir / 'acroform_signed.pdf'
+    with pikepdf.open(acroform) as pdf:
+        pdf.Root.AcroForm.SigFlags = 3
+        pdf.save(out)
+    yield out
+
+
+def test_digital_signature(digitally_signed, no_outpdf):
+    with pytest.raises(ocrmypdf.exceptions.DigitalSignatureError):
+        check_ocrmypdf(digitally_signed, no_outpdf)
+
+
+def test_digital_signature_invalidate(digitally_signed, no_outpdf):
+    check_ocrmypdf(
+        digitally_signed, no_outpdf, '--force-ocr', '--invalidate-digital-signatures'
+    )

tests/test_helpers.py

@@ -17,6 +17,7 @@ from ocrmypdf import helpers
 from .conftest import running_in_docker
 
 needs_symlink = pytest.mark.skipif(os.name == 'nt', reason='needs posix symlink')
+windows_only = pytest.mark.skipif(os.name != 'nt', reason="Windows test")
 
 
 class TestSafeSymlink:
@@ -93,7 +94,7 @@ class TestFileIsWritable:
         assert not helpers.is_file_writable(pathmock)
 
 
-@pytest.mark.skipif(os.name != 'nt', reason="Windows test")
+@windows_only
 def test_gs_install_locations():
     # pylint: disable=import-outside-toplevel
     from ocrmypdf.subprocess._windows import _gs_version_in_path_key
@@ -104,7 +105,7 @@ def test_gs_install_locations():
     )
 
 
-@pytest.mark.skipif(os.name != 'nt', reason="Windows test")
+@windows_only
 def test_shim_paths(tmp_path):
     # pylint: disable=import-outside-toplevel
     from ocrmypdf.subprocess._windows import shim_env_path

tests/test_metadata.py

@@ -76,6 +76,50 @@ def test_override_metadata(output_type, resources, outpdf):
         assert pdfa_info['output'] == output_type
 
 
+@pytest.mark.parametrize('output_type', ['pdfa', 'pdf', 'pdfa-1', 'pdfa-2', 'pdfa-3'])
+@pytest.mark.parametrize('field', ['title', 'author', 'subject', 'keywords'])
+def test_unset_metadata(output_type, field, resources, outpdf):
+    input_file = resources / 'meta.pdf'
+
+    # magic strings contained in the input pdf metadata
+    meta = {
+        'title': b'NFY5f7Ft2DWMkxLhXwxvFf7eWR2KeK3vEDcd',
+        'author': b'yXaryipxyRk9dVjWjSSaVaNCKeLRgEVzPRMp',
+        'subject': b't49vimctvnuH7ZeAjAkv52ACvWFjcnm5MPJr',
+        'keywords': b's9EeALwUg7urA7fnnhm5EtUyC54sW2WPUzqh'}
+
+    p = run_ocrmypdf(
+        input_file,
+        outpdf,
+        f'--{field}',
+        '',
+        '--output-type',
+        output_type,
+        '--plugin',
+        'tests/plugins/tesseract_noop.py',
+    )
+
+    assert p.returncode == ExitCode.ok, p.stderr
+
+    # We mainly want to ensure that when '' is passed, the corresponding
+    # metadata is unset in the output pdf. Since metedata is not compressed,
+    # the best way to gaurentee the metadata of interest didn't carry
+    # forward is to just check to ensure the corresponding magic string
+    # isn't contained anywhere in the output pdf. We'll also check to ensure
+    # it's in the input pdf and that any values not unset are still in the
+    # output pdf.
+    with open(input_file, 'rb') as before, open(outpdf, 'rb') as after:
+        before_data = before.read()
+        after_data = after.read()
+
+    for k, v in meta.items():
+        assert v in before_data
+        if k == field:
+            assert v not in after_data
+        else:
+            assert v in after_data
+
+
 def test_high_unicode(resources, no_outpdf):
     # Ghostscript doesn't support high Unicode, so neither do we, to be
     # safe
@@ -350,7 +394,15 @@ def test_malformed_docinfo(caplog, resources, outdir):
         pike.save(outdir / 'layers.rendered.pdf', fix_metadata_version=False)
 
     options = get_parser().parse_args(
-        args=['-j', '1', '--output-type', 'pdfa-2', 'a.pdf', 'b.pdf']
+        args=[
+            '-j',
+            '1',
+            '--continue-on-soft-render-error',
+            '--output-type',
+            'pdfa-2',
+            'a.pdf',
+            'b.pdf',
+        ]
     )
     pdfinfo = PdfInfo(outdir / 'layers.rendered.pdf')
     context = PdfContext(

tests/test_optimize.py

@@ -204,3 +204,11 @@ def test_group3(resources, outdir):
         assert (
             opt.extract_image_filter(pdf, outdir, im, im.objgen[0]) is None
         ), "Group 3 should be disallowed"
+
+
+def test_find_formx(resources, outdir):
+    with pikepdf.open(resources / 'formxobject.pdf') as pdf:
+        working, pagenos = opt._find_image_xrefs(pdf)
+        assert len(working) == 1
+        xref = next(iter(working))
+        assert pagenos[xref] == 0

tests/test_rotation.py

@@ -275,6 +275,7 @@ def test_rasterize_rotates(resources, tmp_path):
         pageno=1,
         rotation=90,
         filter_vector=False,
+        stop_on_soft_error=True,
     )
     with Image.open(img) as im:
         assert im.size == (83, 200), "Image not rotated"
@@ -289,6 +290,7 @@ def test_rasterize_rotates(resources, tmp_path):
         pageno=1,
         rotation=180,
         filter_vector=False,
+        stop_on_soft_error=True,
     )
     assert Image.open(img).size == (200, 83), "Image not rotated"
 

tests/test_soft_error.py

@@ -0,0 +1,63 @@
+# SPDX-FileCopyrightText: 2023 James R. Barlow
+# SPDX-License-Identifier: MPL-2.0
+
+from __future__ import annotations
+
+import os
+
+import pytest
+
+from ocrmypdf.exceptions import ExitCode
+
+from .conftest import run_ocrmypdf
+
+
+def test_raster_continue_on_soft_error(resources, outpdf):
+    p = run_ocrmypdf(
+        resources / 'francais.pdf',
+        outpdf,
+        '--continue-on-soft-render-error',
+        '--plugin',
+        'tests/plugins/tesseract_noop.py',
+        '--plugin',
+        'tests/plugins/gs_raster_soft_error.py',
+    )
+    assert p.returncode == ExitCode.ok
+
+
+def test_raster_stop_on_soft_error(resources, outpdf):
+    p = run_ocrmypdf(
+        resources / 'francais.pdf',
+        outpdf,
+        '--plugin',
+        'tests/plugins/tesseract_noop.py',
+        '--plugin',
+        'tests/plugins/gs_raster_soft_error.py',
+    )
+    assert p.returncode == ExitCode.child_process_error
+
+
+def test_render_continue_on_soft_error(resources, outpdf):
+    p = run_ocrmypdf(
+        resources / 'francais.pdf',
+        outpdf,
+        '--continue-on-soft-render-error',
+        '--plugin',
+        'tests/plugins/tesseract_noop.py',
+        '--plugin',
+        'tests/plugins/gs_render_soft_error.py',
+    )
+    assert p.returncode == ExitCode.ok
+
+
+@pytest.mark.skipif(os.name == 'nt', reason='Ghostscript on Windows errors out')
+def test_render_stop_on_soft_error(resources, outpdf):
+    p = run_ocrmypdf(
+        resources / 'francais.pdf',
+        outpdf,
+        '--plugin',
+        'tests/plugins/tesseract_noop.py',
+        '--plugin',
+        'tests/plugins/gs_render_soft_error.py',
+    )
+    assert p.returncode == ExitCode.child_process_error

tests/test_validation.py

@@ -166,8 +166,8 @@ def test_language_warning(caplog):
     with patch(
         'ocrmypdf._validation.locale.getlocale', return_value=('en_US', 'UTF-8')
     ) as mock:
-        vd.check_options_languages(opts, {'eng'})
-        assert opts.languages == {'eng'}
+        vd.check_options_languages(opts, ['eng'])
+        assert opts.languages == ['eng']
         assert '' in caplog.text
         mock.assert_called_once()
 
@@ -175,8 +175,8 @@ def test_language_warning(caplog):
     with patch(
         'ocrmypdf._validation.locale.getlocale', return_value=('fr_FR', 'UTF-8')
     ) as mock:
-        vd.check_options_languages(opts, {'eng'})
-        assert opts.languages == {'eng'}
+        vd.check_options_languages(opts, ['eng'])
+        assert opts.languages == ['eng']
         assert 'assuming --language' in caplog.text
         mock.assert_called_once()
 
@@ -282,7 +282,7 @@ def test_two_languages():
             parser=get_parser(),
             language='fakelang1+fakelang2',
         ),
-        {'fakelang1', 'fakelang2'},
+        ['fakelang1', 'fakelang2'],
     )