v16.5.0 release notes

Fixes #1377

.docker/Dockerfile.alpine

@@ -1,7 +1,7 @@
 # SPDX-FileCopyrightText: 2023 James R. Barlow
 # SPDX-License-Identifier: MPL-2.0
 
-FROM alpine:3.19 as base
+FROM alpine:3.19.1 as base
 
 ENV LANG=C.UTF-8
 ENV TZ=UTC

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

@@ -1,7 +1,7 @@
 name: Installation, packaging, dependencies
 description: Installation, packages, dependencies, "nothing works", test suite failures...
 title: "[Bug]: "
-labels: ["bug", "triage"]
+labels: ["triage"]
 assignees:
   - jbarlow83
 body:
@@ -63,6 +63,7 @@ body:
       options:
         - label: Operating system is currently supported by its vendor (not end of life)
         - label: Python version is compatible with OCRmyPDF
+        - label: This issue is not about a specific input file
   - type: textarea
     id: logs
     attributes:

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

@@ -1,7 +1,7 @@
 name: Problem with specific file
 description: Something went wrong while trying to OCR a specific file
 title: "[Bug]: "
-labels: ["bug", "triage"]
+labels: ["triage"]
 assignees:
   - jbarlow83
 body:
@@ -39,7 +39,7 @@ body:
         causing the issue. There's really no substitute for a test file.
 
         We understand files may contain personal or sensitive information. Here are some options:
-        - Try reproducing the issue with a file from the test suite. (See tests/resources)
+        - Try reproducing the issue with a file from the OCRmyPDF test suite. (See tests/resources)
         - Try to create another file in the same way as your private file.
         - Encrypt the file to OCRmyPDF's private GPG key, and then zip the GPG file.
         - Use ``qpdf --json yourfile.pdf`` to produce a JSON representation of your file that

.github/ISSUE_TEMPLATE/3-app.yml

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

.github/workflows/build.yml

@@ -19,8 +19,10 @@ jobs:
   test_linux:
     name: Test ${{ matrix.os }} with Python ${{ matrix.python }}
     runs-on: ${{ matrix.os }}
+    continue-on-error: ${{ matrix.experimental }}
     strategy:
       matrix:
+        experimental: [false]
         include:
           - os: ubuntu-22.04
             python: "3.10"
@@ -34,6 +36,9 @@ jobs:
             tesseract5: true
           - os: ubuntu-latest
             python: "pypy3.10"
+          - os: ubuntu-22.04
+            python: "3.13"
+            experimental: true
 
     env:
       OS: ${{ matrix.os }}
@@ -49,6 +54,7 @@ jobs:
         with:
           python-version: ${{ matrix.python }}
           cache: "pip"
+          allow-prereleases: ${{ matrix.experimental }}
 
       - name: Install Tesseract 5
         if: matrix.tesseract5
@@ -61,6 +67,7 @@ jobs:
           sudo apt-get install -y --no-install-recommends \
             curl \
             ghostscript \
+            jbig2dec \
             img2pdf \
             libexempi8 \
             libffi-dev \
@@ -257,29 +264,45 @@ jobs:
 
   create_release:
     name: Create GitHub release
-    needs: [wheel_sdist_linux, test_linux, test_macos, test_windows]
+    needs: [upload_pypi]
     runs-on: ubuntu-latest
     if: github.event_name == 'push' && startsWith(github.event.ref, 'refs/tags/v')
     permissions:
       # Required to create a release
       contents: write
+      id-token: write
     steps:
       - uses: actions/download-artifact@v4
         with:
           name: artifact
           path: dist
 
-      - name: Create Release
+      - name: Sign the dists with Sigstore
-        id: create-release
+        uses: sigstore/gh-action-sigstore-python@v2.1.1
-        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 }}
+          inputs: >-
-          asset_path: |
-            ./dist/*.whl
             ./dist/*.tar.gz
+            ./dist/*.whl
+
+      - name: Create GitHub Release
+        env:
+          GITHUB_TOKEN: ${{ github.token }}
+        run: >-
+          gh release create
+          '${{ github.ref_name }}'
+          --repo '${{ github.repository }}'
+          --notes ""
+
+      - name: Upload artifact signatures to GitHub Release
+        env:
+          GITHUB_TOKEN: ${{ github.token }}
+        # Upload to GitHub Release using the `gh` CLI.
+        # `dist/` contains the built packages, and the
+        # sigstore-produced signatures and certificates.
+        run: >-
+          gh release upload
+          '${{ github.ref_name }}' dist/**
+          --repo '${{ github.repository }}'
 
   docker_ubuntu:
     name: Build Ubuntu-based Docker image
@@ -358,9 +381,6 @@ jobs:
           username: jbarlow83
           password: ${{ secrets.DOCKERHUB_TOKEN }}
 
-      - name: Set up QEMU
-        uses: docker/setup-qemu-action@v3
-
       - name: Set up Docker Buildx
         id: buildx
         uses: docker/setup-buildx-action@v3
@@ -372,6 +392,6 @@ jobs:
         run: |
           docker buildx build \
             --push \
-            --platform linux/amd64  \
+            --platform linux/amd64,linux/arm64  \
             --tag "${DOCKER_REPOSITORY}/${DOCKER_IMAGE_NAME}:${DOCKER_IMAGE_TAG}" \
             --file .docker/Dockerfile.alpine .

.gitignore

@@ -44,3 +44,4 @@ docs/_build/
 docs/_static/
 docs/_templates/
 docs/Makefile
+src/ocrmypdf/_version.py

docs/advanced.rst

@@ -228,6 +228,59 @@ then run ocrmypdf as follows (along with any other desired arguments):
    Some combinations of control parameters will break Tesseract or break
    assumptions that OCRmyPDF makes about Tesseract's output.
 
+Changing page segmentation mode
+-------------------------------
+
+The directive ``--tesseract-pagesegmode Nmode`` forwards the desired page segmentation
+mode to Tesseract OCR. The default is 3.
+
+Page segmentation can improve OCR results when you know that a PDF ought to be
+analyzed a particular way, such as PDFs whose pages contain only a single line of 
+text. For the vast majority of users, changing the page segmentation mode will only
+make things worse.
+
+As of June 2024, the Tesseract page segmentation modes are:
+
++-----+----------------------------------------------------------------------------------+
+| ID  | Description                                                                      |
++=====+==================================================================================+
+|  0  | Orientation and script detection (OSD) only.                                      |
++-----+----------------------------------------------------------------------------------+
+|  1  | Automatic page segmentation with OSD.                                             |
++-----+----------------------------------------------------------------------------------+
+|  2  | Automatic page segmentation, but no OSD, or OCR. (not implemented)               |
++-----+----------------------------------------------------------------------------------+
+|  3  | Fully automatic page segmentation, but no OSD. (Default)                         |
++-----+----------------------------------------------------------------------------------+
+|  4  | Assume a single column of text of variable sizes.                                 |
++-----+----------------------------------------------------------------------------------+
+|  5  | Assume a single uniform block of vertically aligned text.                         |
++-----+----------------------------------------------------------------------------------+
+|  6  | Assume a single uniform block of text.                                            |
++-----+----------------------------------------------------------------------------------+
+|  7  | Treat the image as a single text line.                                            |
++-----+----------------------------------------------------------------------------------+
+|  8  | Treat the image as a single word.                                                 |
++-----+----------------------------------------------------------------------------------+
+|  9  | Treat the image as a single word in a circle.                                     |
++-----+----------------------------------------------------------------------------------+
+| 10  | Treat the image as a single character.                                            |
++-----+----------------------------------------------------------------------------------+
+| 11  | Sparse text. Find as much text as possible in no particular order.                |
++-----+----------------------------------------------------------------------------------+
+| 12  | Sparse text with OSD.                                                            |
++-----+----------------------------------------------------------------------------------+
+| 13  | Raw line. Treat the image as a single text line, bypassing hacks that are        |
+|     | Tesseract-specific.                                                               |
++-----+----------------------------------------------------------------------------------+
+
+Modes 0, 1, 2, and 12 (all of those that enable orientation and script detection) 
+are not compatible with OCRmyPDF, which performs OSD in a separate step from OCR.
+Their use may interfere with ``--rotate-pages`` and other features.
+
+It is currently not possible to use advanced Tesseract OCR features, such as creating
+OCR information, when using Tesseract through OCRmyPDF.
+
 Changing the PDF renderer
 =========================
 

docs/batch.rst

@@ -135,7 +135,7 @@ Users may need to customize the script to meet their requirements.
     "OCR_ON_SUCCESS_ARCHIVE", "This will move the processed original file to ``OCR_ARCHIVE_DIRECTORY`` if the exit code is 0 (OK). Note that ``OCR_ON_SUCCESS_DELETE`` takes precedence over this option, i.e. if both options are set, the input file will be deleted."
     "OCR_OUTPUT_DIRECTORY_YEAR_MONTH", "This will place files in the output in ``{output}/{year}/{month}/{filename}``"
     "OCR_DESKEW", "Apply deskew to crooked input PDFs"
-    "OCR_JSON_SETTINGS", "A JSON string specifying any other arguments for ``ocrmypdf.ocr``, e.g. ``'OCR_JSON_SETTINGS={""rotate_pages"": true}'``."
+    "OCR_JSON_SETTINGS", "A JSON string specifying any other arguments for ``ocrmypdf.ocr``, e.g. ``'OCR_JSON_SETTINGS={""rotate_pages"": true, ""optimize"": "3"}'``."
     "OCR_POLL_NEW_FILE_SECONDS", "Polling interval"
     "OCR_LOGLEVEL", "Level of log messages to report"
 

docs/docker.rst

@@ -42,7 +42,7 @@ execute the image:
      - Architecture
      - Description
    * - ``jbarlow83/ocrmypdf-alpine``
-     - x86_64 only
+     - x86_64 and arm64
      - Recommended image, based on Alpine Linux.
    * - ``jbarlow83/ocrmypdf-ubuntu``
      - x86_64 and arm64
@@ -81,7 +81,7 @@ To start a Docker container (instance of the image):
 
 .. code-block:: bash
 
-   docker tag jbarlow83/ocrmypdf ocrmypdf
+   docker tag jbarlow83/ocrmypdf-alpine ocrmypdf
    docker run --rm -i ocrmypdf (... all other arguments here...) - -
 
 For convenience, create a shell alias to hide the Docker command. It is

docs/installation.rst

@@ -224,7 +224,7 @@ standard tooling needed to build packages, such as a compiler and binary tools.
 
 .. code-block:: bash
 
-   sudo pacman -S base-devel
+   sudo pacman -S --needed base-devel
 
 Now you are ready to install the OCRmyPDF package.
 
@@ -341,7 +341,7 @@ OCRmyPDF is includes in MacPorts:
     sudo port install ocrmypdf
 
 Note that while this will install tesseract you will need to install
-the appropriate tesseract `language ports <https://ports.macports.org/search/?selected_facets=categories_exact%3Atextproc&installed_file=&q=tesseract&name=on>`__. 
+the appropriate tesseract `language ports <https://ports.macports.org/search/?selected_facets=categories_exact%3Atextproc&installed_file=&q=tesseract&name=on>`__.
 
 Manual installation on macOS
 ----------------------------
@@ -640,8 +640,7 @@ environment:
 
     pip install git+https://github.com/ocrmypdf/OCRmyPDF.git
 
-Or, to install in `development
+Or, to install in editable mode
-mode <https://packaging.python.org/en/latest/guides/distributing-packages-using-setuptools/#working-in-development-mode>`__,
 allowing customization of OCRmyPDF, use the ``-e`` flag:
 
 .. code-block:: bash
@@ -681,7 +680,7 @@ To install all of the development and test requirements:
 .. code-block:: bash
 
     git clone -b main https://github.com/ocrmypdf/OCRmyPDF.git
-    python -m .venv
+    python -m venv .venv
     source .venv/bin/activate
     cd OCRmyPDF
     pip install -e .[test]

docs/maintainers.rst

@@ -38,12 +38,13 @@ on ARM and x86_64. Performance may be poor on other processor architectures.
 Versioning scheme
 -----------------
 
-OCRmyPDF uses setuptools-scm for versioning, which derives the version from
+OCRmyPDF uses hatch-vcs for versioning, which derives the version from
 Git as a single source of truth. This may be unsuitable for some distributions, e.g.
 to indicate that your distribution modifies OCRmyPDF in some way.
 
 You can patch the ``__version__`` variable in ``src/ocrmypdf/_version.py`` if
-necessary.
+necessary, or set the environment variable ``SETUPTOOLS_SCM_PRETEND_VERSION``
+to the required version, if you need to override versioning for some reason.
 
 jbig2enc
 --------

docs/plugins.rst

@@ -29,6 +29,9 @@ conventions. Note that: plugins installed with as setuptools entrypoints are
 not checked currently, because OCRmyPDF assumes you may not want to enable
 plugins for all files.
 
+See [OCRmyPDF-EasyOCR](https://github.com/ocrmypdf/OCRmyPDF-EasyOCR) for an
+example of a straightforward, fully working plugin.
+
 Script plugins
 ==============
 
@@ -70,14 +73,15 @@ similar to ``pytest`` packages such as ``pytest-cov`` (the package) and
     module), just like pytest plugins. At the same time, please make it clear
     that your package is not official.
 
-Setuptools plugins
+Plugins
-==================
+=======
 
 You can also create a plugin that OCRmyPDF will always automatically load if both are
-installed in the same virtual environment, using a setuptools entrypoint.
+installed in the same virtual environment, using a project entrypoint.
+OCRmyPDF uses the entrypoint namespace "ocrmypdf".
 
-Your package's ``pyproject.toml`` would need to contain the following, for a plugin
+For example, ``pyproject.toml`` would need to contain the following, for a plugin named
-named ``ocrmypdf-exampleplugin``:
+``ocrmypdf-exampleplugin``:
 
 .. code-block:: toml
 
@@ -87,13 +91,6 @@ named ``ocrmypdf-exampleplugin``:
     [project.entry-points."ocrmypdf"]
     exampleplugin = "exampleplugin.pluginmodule"
 
-.. code-block:: ini
-
-    # equivalent setup.cfg
-    [options.entry_points]
-    ocrmypdf =
-        exampleplugin = exampleplugin.pluginmodule
-
 Plugin requirements
 ===================
 

docs/release_notes.rst

@@ -30,6 +30,65 @@ OCRmyPDF typically supports the three most recent Python versions.
 
 .. |OCRmyPDF PyPI| image:: https://img.shields.io/pypi/v/ocrmypdf.svg
 
+v16.5.0
+=======
+
+-  Fixed issue with interpreting PDFs that have images with array masks.
+   :issue:`1377`
+-  Enabled testing on Python 3.13.
+-  Fixed a test that did not work correctly but still passed. :issue:`1382`
+-  Improved "PDF/A conversion failed" warning message to better describe implications.
+-  Updated documentation to better explain OCR_JSON_SETTINGS in batch processing.
+-  Build backend changed from setuptools to hatchling.
+
+v16.4.3
+=======
+
+-  Work around pdfminer.six issue where a token on the buffer boundary is incorrectly
+   parsed as two tokens. :issue:`1361`
+-  New rules are applied to stencil masks and explicit masks when calculating the
+   optimal page DPI for rendering. :issue:`1362`
+-  Fixed attempts to use an incompatible jbig2.EXE provided by TeX Live. :issue:`1363`
+
+v16.4.2
+=======
+
+-  Fixed order of filenames passed to Ghostscript for PDF/A generation. :issue:`1359`
+-  Suppressed missing jbig2dec warning message. :issue:`1358`
+-  Fixed calculation of image size when soft mask dimensions don't match image
+   dimension. :issue:`1351`
+-  Several fixes to documentation. Thanks to users Iris and JoKalliauer
+   who contributed these changes.
+-  Fixed error on processing PDFs that are missing certain image metadata. :issue:`1315`
+
+v16.4.1
+=======
+
+-  Fixed calculation of image printed area (used in finding weighted DPI for OCR).
+   :issue:`1334`
+-  Fixed "NotImplementedError: not sure how to get colorspace" error
+   messages in logs which simply records a failure to optimize images with
+   print production colorspaces. :issue:`1315`
+
+v16.4.0
+=======
+
+-  Selecting the ``osd`` and ``equ`` pseudo-languages with ``-l/--language`` now
+   exits with an error when using Tesseract OCR, because these are not
+   regular Tesseract languages but implementation details implemented.
+   Using them can cause Tesseract to crash.
+-  The hOCR renderer is more tolerant of extra whitespace in input files.
+-  watcher.py now changes the output file extension to .pdf when the input is not
+   .pdf.
+-  Improved handling of PDFs that contain circularly referenced Form XObjects.
+   :issue:`1321`
+-  Fixed Alpine Docker image for ARM64, which was not building correctly.
+-  Docker images now use pikepdf 9.0.0.
+-  Prevent use of Tesseract OCR 5.4.0, a version with known regressions.
+-  Disabled progressbar for "Linearizing" when ``--no-progress-bar`` set.
+-  Fixed some tests that warn about missing JBIG2 decoding via pikepdf, by
+   installing the necessary libraries during tests.
+
 v16.3.1
 =======
 

misc/batch.py

@@ -14,12 +14,12 @@ You should edit this script to meet your needs.
 
 from __future__ import annotations
 
+import filecmp
 import logging
-import sys
 import os
 import posixpath
 import shutil
-import filecmp
+import sys
 from pathlib import Path
 
 import ocrmypdf
@@ -70,7 +70,7 @@ for filename in start_dir.glob("**/*.pdf"):
             logging.info(f"Archiving document to {archive_filename}")
             try:
                 shutil.copy2(filename, posixpath.dirname(archive_filename))
-            except IOError as io_err:
+            except OSError:
                 os.makedirs(posixpath.dirname(archive_filename))
                 shutil.copy2(filename, posixpath.dirname(archive_filename))
         try:
@@ -86,6 +86,6 @@ for filename in start_dir.glob("**/*.pdf"):
             logging.info(
                 "Skipped document because it does not need ocr as it is tagged"
             )
-        except:
+        except Exception:
             logging.error("Unhandled error occured")
         logging.info("OCR complete")

misc/watcher.py

@@ -46,15 +46,18 @@ class LoggingLevelEnum(str, Enum):
     CRITICAL = "CRITICAL"
 
 
-def get_output_dir(root: Path, basename: str, output_dir_year_month: bool) -> Path:
+def get_output_path(root: Path, basename: str, output_dir_year_month: bool) -> Path:
+    assert '/' not in basename, "basename must not contain '/'"
     if output_dir_year_month:
         today = datetime.today()
         output_directory_year_month = root / str(today.year) / f'{today.month:02d}'
         if not output_directory_year_month.exists():
             output_directory_year_month.mkdir(parents=True, exist_ok=True)
-        output_path = Path(output_directory_year_month) / basename
+        output_path = Path(output_directory_year_month) / Path(basename).with_suffix(
+            '.pdf'
+        )
     else:
-        output_path = root / basename
+        output_path = root / Path(basename).with_suffix('.pdf')
     return output_path
 
 
@@ -98,7 +101,7 @@ def execute_ocrmypdf(
     retries_loading_file: int,
     output_dir_year_month: bool,
 ):
-    output_path = get_output_dir(output_dir, file_path.name, output_dir_year_month)
+    output_path = get_output_path(output_dir, file_path.name, output_dir_year_month)
 
     log.info("-" * 20)
     log.info(f'New file: {file_path}. Waiting until fully written...')

pyproject.toml

@@ -1,8 +1,8 @@
 # SPDX-FileCopyrightText: 2022 James R. Barlow
 # SPDX-License-Identifier: MPL-2.0
 [build-system]
-requires = ["setuptools >= 61", "setuptools_scm[toml] >= 7.0.5", "wheel"]
+requires = ["hatchling", "hatch-vcs"]
-build-backend = "setuptools.build_meta"
+build-backend = "hatchling.build"
 
 [project]
 name = "ocrmypdf"
@@ -46,6 +46,7 @@ keywords = ["PDF", "OCR", "optical character recognition", "PDF/A", "scanning"]
 Documentation = "https://ocrmypdf.readthedocs.io/"
 Source = "https://github.com/ocrmypdf/OCRmyPDF"
 Tracker = "https://github.com/ocrmypdf/OCRmyPDF/issues"
+Changelog = "https://github.com/ocrmypdf/OCRmyPDF/docs/release_notes.rst"
 
 [project.optional-dependencies]
 docs = ["sphinx", "sphinx-issues", "sphinx-rtd-theme"]
@@ -67,14 +68,11 @@ webservice = ["Flask>=2.0.1"]
 [project.scripts]
 ocrmypdf = "ocrmypdf.__main__:run"
 
-[tool.setuptools.package-data]
+[tool.hatch.version]
-ocrmypdf = ["data/sRGB.icc", "py.typed"]
+source = "vcs"
 
-[tool.setuptools.packages.find]
+[tool.hatch.build.hooks.vcs]
-where = ["src"]
+version-file = "src/ocrmypdf/_version.py"
-namespaces = false
-
-[tool.setuptools_scm]
 
 [tool.distutils.bdist_wheel]
 python-tag = "py310"

snapcraft.yaml

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

src/ocrmypdf/__init__.py

@@ -9,11 +9,12 @@ from pluggy import HookimplMarker as _HookimplMarker
 
 from ocrmypdf import helpers, hocrtransform, pdfa, pdfinfo
 from ocrmypdf._concurrent import Executor
+from ocrmypdf._defaults import PROGRAM_NAME
 from ocrmypdf._jobcontext import PageContext, PdfContext
 from ocrmypdf._pipelines._common import (
     configure_debug_logging,
 )
-from ocrmypdf._version import PROGRAM_NAME, __version__
+from ocrmypdf._version import __version__
 from ocrmypdf.api import (
     Verbosity,
     configure_logging,
@@ -37,7 +38,6 @@ from ocrmypdf.pluginspec import OcrEngine, OrientationConfidence
 
 hookimpl = _HookimplMarker('ocrmypdf')
 
-
 __all__ = [
     '__version__',
     'BadArgsError',

src/ocrmypdf/_defaults.py

@@ -6,3 +6,5 @@ DEFAULT_LANGUAGE = 'eng'
 
 # Default rotation threshold
 DEFAULT_ROTATE_PAGES_THRESHOLD = 14.0
+
+PROGRAM_NAME = 'OCRmyPDF'

src/ocrmypdf/_exec/jbig2enc.py

@@ -5,7 +5,7 @@
 
 from __future__ import annotations
 
-from subprocess import PIPE
+from subprocess import PIPE, CalledProcessError
 
 from packaging.version import Version
 
@@ -14,7 +14,13 @@ from ocrmypdf.subprocess import get_version, run
 
 
 def version() -> Version:
-    return Version(get_version('jbig2', regex=r'jbig2enc (\d+(\.\d+)*).*'))
+    try:
+        version = get_version('jbig2', regex=r'jbig2enc (\d+(\.\d+)*).*')
+    except CalledProcessError as e:
+        # TeX Live for Windows provides an incompatible jbig2.EXE which may
+        # be on the PATH.
+        raise MissingDependencyError('jbig2enc') from e
+    return Version(version)
 
 
 def available():

src/ocrmypdf/_metadata.py

@@ -15,8 +15,8 @@ from pikepdf import Dictionary, Name, Pdf
 from pikepdf import __version__ as PIKEPDF_VERSION
 from pikepdf.models.metadata import PdfMetadata, encode_pdf_date
 
+from ocrmypdf._defaults import PROGRAM_NAME
 from ocrmypdf._jobcontext import PdfContext
-from ocrmypdf._version import PROGRAM_NAME
 from ocrmypdf._version import __version__ as OCRMYPF_VERSION
 from ocrmypdf.languages import iso_639_2_from_3
 
@@ -154,10 +154,10 @@ def _set_language(pdf: Pdf, languages: list[str]):
 
 
 class MetadataProgress:
-    def __init__(self, progressbar_class):
+    def __init__(self, progressbar_class, enable: bool = True):
         self.progressbar_class = progressbar_class
         self.progressbar = self.progressbar_class(
-            total=100, desc="Linearizing", unit='%'
+            total=100, desc="Linearizing", unit='%', disable=not enable
         )
 
     def __enter__(self):
@@ -190,7 +190,7 @@ def metadata_fixup(
     with (
         Pdf.open(context.origin) as original,
         Pdf.open(working_file) as pdf,
-        MetadataProgress(pbar_class) as pbar,
+        MetadataProgress(pbar_class, options.progress_bar) as pbar,
     ):
         docinfo = get_docinfo(original, context)
         with (

src/ocrmypdf/_pipeline.py

@@ -475,7 +475,7 @@ def calculate_raster_dpi(page_context: PageContext):
     page_dpi = get_page_square_dpi(page_context, image_dpi)
     if dpi_profile and dpi_profile.average_to_max_dpi_ratio < 0.8:
         log.warning(
-            "Weight average image DPI is %0.1f, max DPI is %0.1f. "
+            "Weighted average image DPI is %0.1f, max DPI is %0.1f. "
             "The discrepancy may indicate a high detail region on this page, "
             "but could also indicate a problem with the input PDF file. "
             "Page image will be rendered at %0.1f DPI.",

src/ocrmypdf/_pipelines/_common.py

@@ -441,7 +441,8 @@ def report_output_pdf(options, start_input_file, optimize_messages) -> ExitCode:
                 log.info("Output file is a %s (as expected)", pdfa_info['conformance'])
             else:
                 log.warning(
-                    "Output file is okay but is not PDF/A (seems to be %s)",
+                    "Output file is a valid PDF, but conversion to PDF/A did not "
+                    "succeed (issue: %s)",
                     pdfa_info['conformance'],
                 )
                 return ExitCode.pdfa_conversion_failed

src/ocrmypdf/_validation.py

@@ -54,6 +54,7 @@ def check_options_languages(
             log.debug("No language specified; assuming --language %s", DEFAULT_LANGUAGE)
     if not ocr_engine_languages:
         return
+
     missing_languages = set(options.languages) - set(ocr_engine_languages)
     if missing_languages:
         lang_text = '\n'.join(lang for lang in missing_languages)

src/ocrmypdf/_version.py

@@ -1,16 +0,0 @@
-# SPDX-FileCopyrightText: 2022 James R. Barlow
-# SPDX-License-Identifier: MPL-2.0
-
-"""Get version by introspecting package information.
-
-OCRmyPDF uses setuptools_scm to derive version from git tags.
-"""
-
-from __future__ import annotations
-
-from importlib.metadata import version as _package_version
-
-PROGRAM_NAME = 'ocrmypdf'
-
-# Official PEP 396
-__version__ = _package_version('ocrmypdf')

src/ocrmypdf/builtin_plugins/ghostscript.py

@@ -129,7 +129,7 @@ def generate_pdfa(
 ):
     """Generate a PDF/A from the list of PDF pages and PDF/A metadata."""
     ghostscript.generate_pdfa(
-        pdf_pages=[*pdf_pages, pdfmark],
+        pdf_pages=[pdfmark, *pdf_pages],
         output_file=output_file,
         compression=context.options.pdfa_image_compression,
         color_conversion_strategy=context.options.color_conversion_strategy,

src/ocrmypdf/builtin_plugins/tesseract_ocr.py

@@ -14,6 +14,7 @@ from ocrmypdf import hookimpl
 from ocrmypdf._exec import tesseract
 from ocrmypdf._jobcontext import PageContext
 from ocrmypdf.cli import numeric, str_to_int
+from ocrmypdf.exceptions import BadArgsError, MissingDependencyError
 from ocrmypdf.helpers import clamp
 from ocrmypdf.imageops import calculate_downsample, downsample_image
 from ocrmypdf.pluginspec import OcrEngine
@@ -144,6 +145,12 @@ def check_options(options):
         need_version='4.1.1',  # Ubuntu 22.04 version (also 20.04)
         version_parser=tesseract.TesseractVersion,
     )
+    tess_version = tesseract.version()
+    if tess_version == tesseract.TesseractVersion('5.4.0'):
+        raise MissingDependencyError(
+            "Tesseract 5.4.0 is not supported due to regressions in this version. "
+            "Please upgrade to a newer or supported older version."
+        )
 
     # Decide on what renderer to use
     if options.pdf_renderer == 'auto':
@@ -164,6 +171,14 @@ def check_options(options):
             "The --tesseract-pagesegmode argument you select will disable OCR. "
             "This may cause processing to fail."
         )
+    DENIED_LANGUAGES = {'equ', 'osd'}
+    if DENIED_LANGUAGES & set(options.languages):
+        raise BadArgsError(
+            "The following languages for Tesseract's internal use and should not "
+            "be issued explicitly: "
+            f"{', '.join(DENIED_LANGUAGES & set(options.languages))}\n"
+            "Remove them from the -l/--language argument."
+        )
 
 
 @hookimpl

src/ocrmypdf/cli.py

@@ -10,7 +10,7 @@ from collections.abc import Callable, Mapping
 from typing import Any, TypeVar
 
 from ocrmypdf._defaults import DEFAULT_ROTATE_PAGES_THRESHOLD
-from ocrmypdf._version import PROGRAM_NAME as _PROGRAM_NAME
+from ocrmypdf._defaults import PROGRAM_NAME as _PROGRAM_NAME
 from ocrmypdf._version import __version__ as _VERSION
 
 T = TypeVar('T', int, float)

src/ocrmypdf/helpers.py

@@ -268,7 +268,9 @@ def check_pdf(input_file: Path) -> bool:
         return False
     else:
         with pdf:
-            messages = pdf.check()
+            with warnings.catch_warnings():
+                warnings.filterwarnings('ignore', message=r'pikepdf.*JBIG2.*')
+                messages = pdf.check()
             success = True
             for msg in messages:
                 if 'error' in msg.lower():

src/ocrmypdf/hocrtransform/_hocr.py

@@ -61,15 +61,25 @@ class HocrTransform:
     """A class for converting documents from the hOCR format.
 
     For details of the hOCR format, see:
-    http://kba.cloud/hocr-spec/.
+    http://kba.github.io/hocr-spec/1.2/.
     """
 
-    box_pattern = re.compile(r'bbox (\d+) (\d+) (\d+) (\d+)')
+    box_pattern = re.compile(
+        r'''
+        bbox \s+
+        (\d+) \s+   # left: uint
+        (\d+) \s+   # top: uint
+        (\d+) \s+   # right: uint
+        (\d+)       # bottom: uint
+        ''',
+        re.VERBOSE,
+    )
     baseline_pattern = re.compile(
         r'''
         baseline \s+
         ([\-\+]?\d*\.?\d*) \s+  # +/- decimal float
-        ([\-\+]?\d+)            # +/- int''',
+        ([\-\+]?\d+)            # +/- int
+        ''',
         re.VERBOSE,
     )
 
@@ -284,8 +294,11 @@ class HocrTransform:
         if not line_box:
             return
         if line_box.ury <= line_box.lly:
-            log.error("line box is invalid so we cannot render it: box=%s text=%s",
+            log.error(
-                      line_box, self._get_element_text(line))
+                "line box is invalid so we cannot render it: box=%s text=%s",
+                line_box,
+                self._get_element_text(line),
+            )
             return
 
         self._debug_draw_line_bbox(canvas, line_box)

src/ocrmypdf/optimize.py

@@ -28,6 +28,7 @@ from pikepdf import (
     Stream,
     UnsupportedImageTypeError,
 )
+from pikepdf.models.image import HifiPrintImageNotTranscodableError
 from PIL import Image
 
 from ocrmypdf._concurrent import Executor, SerialExecutor
@@ -200,7 +201,7 @@ def extract_image_generic(
             with imgname.open('wb') as f:
                 ext = pim.extract_to(stream=f)
             imgname.rename(imgname.with_suffix(ext))
-        except UnsupportedImageTypeError:
+        except (UnsupportedImageTypeError, HifiPrintImageNotTranscodableError):
             return None
         return XrefExt(xref, ext)
     elif (
@@ -256,6 +257,9 @@ def _find_image_xrefs_container(
     for _imname, image in dict(xobjs).items():
         if image.objgen[1] != 0:
             continue  # Ignore images in an incremental PDF
+        xref = Xref(image.objgen[0])
+        if xref in include_xrefs or xref in exclude_xrefs:
+            continue  # Already processed
         if Name.Subtype in image and image.Subtype == Name.Form:
             # Recurse into Form XObjects
             log.debug(f"Recursing into Form XObject {_imname} in page {pageno}")
@@ -269,7 +273,6 @@ def _find_image_xrefs_container(
                 depth + 1,
             )
             continue
-        xref = Xref(image.objgen[0])
         if Name.SMask in image:
             # Ignore soft masks
             smask_xref = Xref(image.SMask.objgen[0])

src/ocrmypdf/pdfinfo/info.py

@@ -369,8 +369,25 @@ class ImageInfo:
             pim = PdfImage(pdfimage)
         else:
             raise ValueError("Either pdfimage or inline must be set")
+
         self._width = pim.width
         self._height = pim.height
+        if (smask := pim.obj.get(Name.SMask, None)) is not None:
+            # SMask is pretty much an alpha channel, but in PDF it's possible
+            # for channel to have different dimensions than the image
+            # itself. Some PDF writers use this to create a grayscale stencil
+            # mask. For our purposes, the effective size is the size of the
+            # larger component (image or smask).
+            self._width = max(smask.get(Name.Width, 0), self._width)
+            self._height = max(smask.get(Name.Height, 0), self._height)
+        if (mask := pim.obj.get(Name.Mask, None)) is not None:
+            # If the image has a /Mask entry, it has an explicit mask.
+            # /Mask can be a Stream or an Array. If it's a Stream,
+            # use its /Width and /Height if they are larger than the main
+            # image's.
+            if isinstance(mask, Stream):
+                self._width = max(mask.get(Name.Width, 0), self._width)
+                self._height = max(mask.get(Name.Height, 0), self._height)
 
         # If /ImageMask is true, then this image is a stencil mask
         # (Images that draw with this stencil mask will have a reference to
@@ -474,9 +491,18 @@ class ImageInfo:
     def renderable(self) -> bool:
         """Whether the image is renderable.
 
-        Some PDFs in the wild have invalid images that are not renderable.
+        Some PDFs in the wild have invalid images that are not renderable,
+        due to unusual dimensions.
+
+        Stencil masks are not also not renderable, since they are not
+        drawn, but rather they control how rendering happens.
         """
-        return self.dpi.is_finite and self.width >= 0 and self.height >= 0
+        return (
+            self.dpi.is_finite
+            and self.width >= 0
+            and self.height >= 0
+            and self.type_ != 'stencil'
+        )
 
     @property
     def dpi(self) -> Resolution:
@@ -491,7 +517,7 @@ class ImageInfo:
         """Physical area of the image in square inches."""
         if not self.renderable:
             return 0.0
-        return float(self.width * self.dpi.x * self.height * self.dpi.y)
+        return float((self.width / self.dpi.x) * (self.height / self.dpi.y))
 
     def __repr__(self):
         """Return a string representation of the image."""
@@ -573,7 +599,7 @@ def _find_form_xobject_images(pdf: Pdf, container: Object, contentsinfo: Content
     xobjs = resources[Name.XObject].as_dict()
     for xobj in xobjs:
         candidate = xobjs[xobj]
-        if candidate is None or candidate[Name.Subtype] != Name.Form:
+        if candidate is None or candidate.get(Name.Subtype) != Name.Form:
             continue
 
         form_xobject = candidate
@@ -1055,10 +1081,14 @@ class PageInfo:
 
         Returns None if there is no meaningful DPI for the page.
         """
-        image_dpis = [
+        image_dpis = []
-            image.dpi.to_scalar() for image in self._images if image.renderable
+        image_areas = []
-        ]
+        for image in self._images:
-        image_areas = [image.printed_area for image in self._images if image.renderable]
+            if not image.renderable:
+                continue
+            image_dpis.append(image.dpi.to_scalar())
+            image_areas.append(image.printed_area)
+
         total_drawn_area = sum(image_areas)
         if total_drawn_area == 0:
             return None
@@ -1071,7 +1101,6 @@ class PageInfo:
 
         arg_max_dpi = image_dpis.index(max_dpi)
         max_area_ratio = image_areas[arg_max_dpi] / total_drawn_area
-
         return PageResolutionProfile(
             weighted_dpi,
             max_dpi,

src/ocrmypdf/pdfinfo/layout.py

@@ -17,6 +17,7 @@ import pdfminer
 import pdfminer.encodingdb
 import pdfminer.pdfdevice
 import pdfminer.pdfinterp
+import pdfminer.psparser
 from pdfminer.converter import PDFLayoutAnalyzer
 from pdfminer.layout import LAParams, LTChar, LTPage, LTTextBox
 from pdfminer.pdfcolor import PDFColorSpace
@@ -58,9 +59,10 @@ def pdfsimplefont__init__(
 
 setattr(PDFSimpleFont, '__init__', pdfsimplefont__init__)
 
-#
+# Patch pdfminer.six buffer size
-# pdfminer patches when creator is PScript5.dll
+# The parser doesn't properly handle keyword tokens are split across the end of the
-#
+# buffer, so increase the buffer size something far larger than will ever be seen.
+pdfminer.psparser.PSBaseParser.BUFSIZ = 256 * 1024 * 1024
 
 
 def pdftype3font__pscript5_get_height(self):

tests/test_rotation.py

@@ -239,7 +239,9 @@ def make_rotate_test(imagefile, outdir, prefix, image_angle, page_angle):
 @pytest.mark.parametrize('image_angle', (0, 90, 180, 270))
 def test_rotate_page_level(image_angle, page_angle, resources, outdir, caplog):
     reference = make_rotate_test(resources / 'typewriter.png', outdir, 'ref', 0, 0)
-    test = make_rotate_test(resources, outdir, 'test', image_angle, page_angle)
+    test = make_rotate_test(
+        resources / 'typewriter.png', outdir, 'test', image_angle, page_angle
+    )
     out = test.with_suffix('.out.pdf')
 
     exitcode = run_ocrmypdf_api(

tests/test_tesseract.py

@@ -13,9 +13,9 @@ import pytest
 
 from ocrmypdf import pdfinfo
 from ocrmypdf._exec import tesseract
-from ocrmypdf.exceptions import MissingDependencyError
+from ocrmypdf.exceptions import BadArgsError, ExitCode, MissingDependencyError
 
-from .conftest import check_ocrmypdf
+from .conftest import check_ocrmypdf, run_ocrmypdf_api
 
 # pylint: disable=redefined-outer-name
 
@@ -144,3 +144,10 @@ def test_tesseract_log_output_raises(caplog):
     with pytest.raises(tesseract.TesseractConfigError):
         tesseract.tesseract_log_output(b'parameter not found: moo')
     assert 'not found' in caplog.text
+
+
+def test_blocked_language(resources, no_outpdf):
+    infile = resources / 'masks.pdf'
+    for bad_lang in ['osd', 'equ']:
+        with pytest.raises(BadArgsError):
+            run_ocrmypdf_api(infile, no_outpdf, '-l', bad_lang)