v16.1.1 release notes

Appears inversion of CTM was incorrect, introduced in commit 9898904

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

@@ -21,7 +21,7 @@ body:
     id: reproduce
     attributes:
       label: Steps to reproduce
-      description: Please include steps to reproduce
+      description: Please include steps to reproduce.
       value: |
         1. Run ocrmypdf -v1 ...arguments... input.pdf output.pdf
         2. Open output.pdf
@@ -31,9 +31,8 @@ body:
     id: files
     attributes:
       label: Files
-      description: Please attach the input and output files, or any screenshots that may be helpful.
-      placeholder: |
-        Drag and drop files here.
+      description: |
+        Please attach the input and output files, or any screenshots that may be helpful.
 
         If you cannot provide a test file, we probably won't be able to help with the issue.
         PDF is a complex file format, and there may be technical details in the PDF that are
@@ -42,10 +41,11 @@ body:
         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.
+        - Encrypt the file to OCRmyPDF's private GPG key, and then zip the GPG file.
         - Use ``qpdf --json yourfile.pdf`` to produce a JSON representation of your file that
           omits personal information.
-
+      placeholder: |
+        Drag and drop files here.
   - type: dropdown
     id: packaging-system
     attributes:

.github/workflows/build.yml

@@ -32,8 +32,8 @@ jobs:
           - os: ubuntu-latest
             python: "3.12"
             tesseract5: true
-          # - os: ubuntu-latest
-          #   python: "pypy3.10"
+          - os: ubuntu-latest
+            python: "pypy3.10"
 
     env:
       OS: ${{ matrix.os }}
@@ -100,7 +100,7 @@ jobs:
           python -m pytest --cov-report xml --cov=ocrmypdf --cov=tests/ -n0 tests/
 
       - name: Upload coverage to Codecov
-        uses: codecov/codecov-action@v3
+        uses: codecov/codecov-action@v4
         with:
           files: ./coverage.xml
           env_vars: OS,PYTHON
@@ -158,7 +158,7 @@ jobs:
           python -m pytest --cov-report xml --cov=ocrmypdf --cov=tests/ -n0 tests/
 
       - name: Upload coverage to Codecov
-        uses: codecov/codecov-action@v3
+        uses: codecov/codecov-action@v4
         with:
           files: ./coverage.xml
           env_vars: OS,PYTHON
@@ -189,7 +189,7 @@ jobs:
       - name: Install system packages
         run: |
           choco install --yes --no-progress --pre tesseract
-          choco install --yes --no-progress --ignore-checksums ghostscript
+          choco install --yes --no-progress --ignore-checksums ghostscript --version 9.56.1
 
       - name: Install Python packages
         run: |
@@ -201,7 +201,7 @@ jobs:
           python -m pytest --cov-report xml --cov=ocrmypdf --cov=tests/ -n0 tests/
 
       - name: Upload coverage to Codecov
-        uses: codecov/codecov-action@v3
+        uses: codecov/codecov-action@v4
         with:
           files: ./coverage.xml
           env_vars: OS,PYTHON

docs/api.rst

@@ -112,7 +112,9 @@ OCRmyPDF is strict about not writing to standard output so that
 users can safely use it in a pipeline and produce a valid output
 file. A caller application will have to ensure it does not write to
 standard output either, if it wants to be compatible with this
-behavior and support piping to a file.
+behavior and support piping to a file. Another benefit of running
+OCRmyPDF in a child process, as recommended above, is that it will
+not interfere with the parent process's standard output.
 
 Exceptions
 ----------

docs/cookbook.rst

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

docs/installation.rst

@@ -139,6 +139,32 @@ from sources <#installing-head-revision-from-sources>`__.
 
 .. _ubuntu-lts-latest:
 
+RHEL 9
+------
+
+Prepare the environment by getting Python 3.11:
+
+.. code-block:: bash
+
+    dnf install python3.11 python3.11-pip
+
+Then, follow `Requirements for pip and HEAD install <#requirements-for-pip-and-head-install>`__ to instal dependencies:
+
+.. code-block:: bash
+
+    dnf install ghostscript tesseract
+
+and build ocrmypdf in virtual environment:
+
+.. code-block:: bash
+
+    python3.11 -m venv .venv
+
+To add JBIG2 encoding, see `Installing the JBIG2 encoder <jbig2>`__.
+
+Note Fedora packages for language data haven't been branched for RHEL/EPEL, but you can get traineddata files directly from `tesseract
+<https://github.com/tesseract-ocr/tessdata/>`__ and place them in ``/usr/share/tesseract/tessdata``.
+
 Installing the latest version on Ubuntu 22.04 LTS
 -------------------------------------------------
 
@@ -162,37 +188,13 @@ To add JBIG2 encoding, see :ref:`jbig2`.
 Ubuntu 20.04 LTS
 ----------------
 
-Ubuntu 20.04 includes ocrmypdf 9.6.0 - you can install that with ``apt``. To
-install a more recent version, uninstall the system-provided version of
-ocrmypdf, and install the following dependencies:
+Ubuntu 20.04 includes ocrmypdf 9.6.0 - you can install that with ``apt``. The
+most convenient way to install recent OCRmyPDF on older Ubuntu is to use
+Homebrew on Linux (Linuxbrew).
 
 .. code-block:: bash
 
-    sudo apt-get -y remove ocrmypdf  # remove system ocrmypdf, if installed
-    sudo apt-get -y update
-    sudo apt-get -y install \
-        ghostscript \
-        icc-profiles-free \
-        libxml2 \
-        pngquant \
-        python3-pip \
-        tesseract-ocr \
-        zlib1g
-
-To install ocrmypdf for the system:
-
-.. code-block:: bash
-
-    pip3 install ocrmypdf
-
-To install for the current user only:
-
-.. code-block:: bash
-
-    export PATH=$HOME/.local/bin:$PATH
-    pip3 install --user ocrmypdf
-
-To add JBIG2 encoding, see :ref:`jbig2`.
+    brew install ocrmypdf
 
 Arch Linux (AUR)
 ----------------
@@ -404,7 +406,7 @@ the following when running in an Administrator command prompt):
 * ``choco install --pre tesseract``
 * ``choco install pngquant`` (optional)
 
-Either set of commands will install the required software. At the mmoment there is no
+Either set of commands will install the required software. At the moment there is no
 single command to install Windows.
 
 You may then use ``pip`` to install ocrmypdf. (This can performed by a user or
@@ -540,9 +542,25 @@ try:
 
     pip install --user ocrmypdf
 
+(If the message appears ``Requirement already satisfied: ocrmypdf in...``,
+you will need to use ``pip install --user --upgrade ocrmypdf``.)
+
 You should then be able to run ``ocrmypdf --version`` and see that the
 latest version was located.
 
+Installing with pipx
+====================
+
+Some users may prefer pipx. As with the method above, you will need to
+satisfy all non-Python dependencies. Then if pipx is installed, you
+can use
+
+.. code-block:: bash
+
+    pipx run ocrmypdf
+
+(If not installed, pipx will install first.)
+
 Requirements for pip and HEAD install
 -------------------------------------
 
@@ -553,7 +571,7 @@ manager. ``pip`` cannot provide them.
 The following versions are required:
 
 -  Python 3.10 or newer
--  Ghostscript 9.55 or newer
+-  Ghostscript 9.54 or newer
 -  Tesseract 4.1.1 or newer
 -  jbig2enc 0.29 or newer
 -  pngquant 2.5 or newer
@@ -671,7 +689,7 @@ To manually install the ``fish`` completion, copy
 Note on 32-bit support
 ======================
 
-Many Python libraries no longer 32-bit binary wheels for Linux. This
+Many Python libraries no longer provide 32-bit binary wheels for Linux. This
 includes many of the libraries that OCRmyPDF depends on, such as
 Pillow. The easiest way to express this to end users is to say we don't
 support 32-bit Linux.
@@ -681,4 +699,4 @@ can still install and use OCRmyPDF. A warning message will appear.
 In practice, OCRmyPDF may need more than 32-bit memory space to run when
 large documents are processed, so there are practical limitations to what
 users can accomplish with it. Still, for the common use case of an 32-bit
-ARM NAS or Raspberry Pi processing small documents, it should work.
+ARM NAS or Raspberry Pi processing small documents, it should work.

docs/jbig2.rst

@@ -41,7 +41,15 @@ For all other platforms, you would need to build the JBIG2 encoder from source:
 
 Dependencies include libtoolize and libleptonica, which on Ubuntu systems
 are packaged as libtool and libleptonica-dev. On Fedora (35) they are packaged
-as libtool and leptonica-devel.
+as libtool and leptonica-devel. For this to work, please make sure to install
+``autotools``, ``automake``, ``libtool`` and ``leptonica`` first if not already
+installed.
+
+.. code-block:: bash
+
+    [sudo] apt install autotools-dev automake libtool libleptonica-dev
+..
+
 
 Lossy mode JBIG2
 ================

docs/languages.rst

@@ -18,16 +18,26 @@ Tesseract's documentation also lists the three-letter code for your language.
 Some are anglicized, e.g. Spanish is ``spa`` rather than ``esp``, while others
 are not, e.g. German is ``deu`` and French is ``fra``.
 
+Language packs (strictly speaking, Tesseract "traineddata" files) generally correspond
+to the language in question, but different language packs are used in certain
+situations. For German, the "Fraktur" language pack can assist with reading older
+materials in the Fraktur typeface family (``deu_frak``). Some communities have changed
+their script from Cyrillic to Latin; the Cyrillic version of Uzbek is available
+as ``uzb_cyrl`` and the Latin version is ``uzb``.
+
 After you have installed a language pack, you can use it with ``ocrmypdf -l <language>``,
 for example ``ocrmypdf -l spa``. For multilingual documents, you can specify
 all languages to be expected, e.g. ``ocrmypdf -l eng+fra`` for English and French.
 English is assumed by default unless other language(s) are specified.
 
 For Linux users, you can often find packages that provide language
-packs:
+packs.
 
-Debian and Ubuntu users
-=======================
+Platform install steps
+======================
+
+Debian and Ubuntu (apt)
+-----------------------
 
 .. code-block:: bash
 
@@ -42,8 +52,8 @@ to what languages it should search for. Multiple languages can be
 requested using either ``-l eng+fra`` (English and French) or
 ``-l eng -l fra``.
 
-Fedora users
-============
+Fedora
+------
 
 .. code-block:: bash
 
@@ -58,8 +68,8 @@ to what languages it should search for. Multiple languages can be
 requested using either ``-l eng+fra`` (English and French) or
 ``-l eng -l fra``.
 
-Gentoo users
-============
+Gentoo
+------
 
 On Gentoo the package ``app-text/tessdata_fast``, which ``app-text/tesseract`` depends on, handles Tesseract languages.
 It accepts USE flags to select what languages should be installed, these can be set in ``/etc/portage/package.use``.
@@ -85,23 +95,31 @@ to what languages it should search for. Multiple languages can be
 requested using either ``-l eng+fra`` (English and French) or
 ``-l eng -l fra``.
 
-macOS users
-===========
+macOS
+-----
 
 You can install additional language packs by
 :ref:`installing Tesseract using Homebrew with all language packs <macos-all-languages>`.
 
-Docker users
-============
+Docker
+------
 
 Users of the OCRmyPDF Docker image should install language packs into a
 derived Docker image as
 :ref:`described in that section <docker-lang-packs>`.
 
-Windows users
-=============
+Windows
+-------
 
 The Tesseract installer provided by Chocolatey currently includes only English language.
 To install other languages, download the respective language pack (``.traineddata`` file)
 from https://github.com/tesseract-ocr/tessdata/ and place it in
 ``C:\\Program Files\\Tesseract-OCR\\tessdata`` (or wherever Tesseract OCR is installed).
+
+Custom language packs
+=====================
+
+If you have fine-tuned or trained Tesseract and generated custom trained data, you can
+copy your ``customlang.traineddata`` file into your Tesseract "tessdata" folder, and
+then use the ``-l customlang`` argument to tell OCRmyPDF to pass that language on to
+Tesseract.

docs/release_notes.rst

@@ -30,6 +30,40 @@ OCRmyPDF typically supports the three most recent Python versions.
 
 .. |OCRmyPDF PyPI| image:: https://img.shields.io/pypi/v/ocrmypdf.svg
 
+v16.1.1
+=======
+
+-  Fixed PyPy 3.10 support.
+
+v16.1.0
+=======
+
+-  Improved hOCR renderer is now default for left to right languages.
+-  Improved handling of rotated pages. Previously, OCR text might be missing for
+   pages that were rotated with a /Rotate tag on the page entry.
+-  Improved handling of cropped pages. Previously, in some cases a page with a
+   crop box would not have its OCR applied correctly and misalignment between
+   OCR text and visible text coudl occur.
+-  Documentation improvements, especially installation instructions for less
+   common platforms.
+
+v16.0.4
+=======
+
+-  Fixed some issues for left-to-right text with the new hOCR renderer. It is still
+   not default yet but will be made so soon. Right-to-left text is still in progress.
+-  Added an error to prevent use of several versions of Ghostscript that seem
+   corrupt existing text in input PDFs. Newly generated OCR is not affected.
+   For best results, use Ghostscript 10.02.1 or newer, which contains the fix
+   for the issue.
+
+v16.0.3
+=======
+
+-  Changed minimum required Ghostscript to 9.54, to support users of RHEL 9 and its
+   derivatives, since that is the latest version available there.
+-  Removed warning message about CVE-2023-43115, on the assumption that most
+   distributions have backported the patch by now.
 
 v16.0.2
 =======

misc/watcher.py

@@ -8,6 +8,7 @@
 # Do not enable annotations!
 # https://github.com/tiangolo/typer/discussions/598
 # from __future__ import annotations
+from __future__ import annotations
 
 import json
 import logging
@@ -131,7 +132,7 @@ def execute_ocrmypdf(
 
 
 class HandleObserverEvent(PatternMatchingEventHandler):
-    def __init__(
+    def __init__(  # noqa: D107
         self,
         patterns=None,
         ignore_patterns=None,
@@ -191,7 +192,7 @@ def main(
         bool,
         typer.Option(
             envvar='OCR_OUTPUT_DIRECTORY_YEAR_MONTH',
-            help='Create a subdirectory in the output directory for each year and month',
+            help='Create a subdirectory in the output directory for each year/month',
         ),
     ] = False,
     on_success_delete: Annotated[

pyproject.toml

@@ -131,7 +131,11 @@ norecursedirs = ["lib", ".pc", ".git", "venv", "output", "cache", "resources"]
 testpaths = ["tests"]
 addopts = "-n auto"
 markers = ["slow"]
-filterwarnings = ["ignore:.*XMLParser.*:DeprecationWarning"]
+filterwarnings = [
+  "ignore:.*XMLParser.*:DeprecationWarning",
+  "ignore:.*ast.NameConstant.*:DeprecationWarning:reportlab",
+  "ignore:.*distutils.*:DeprecationWarning:libxmp",
+]
 
 [tool.mypy]
 
@@ -149,7 +153,10 @@ module = [
 ignore_missing_imports = true
 
 [tool.ruff]
-select = [
+target-version = "py310"
+
+[tool.ruff.lint]
+"select" = [
   "D",    # pydocstyle
   "E",    # pycodestyle
   "W",    # pycodestyle
@@ -157,16 +164,15 @@ select = [
   "I001", # isort
   "UP",   # pyupgrade
 ]
-target-version = "py310"
 
-[tool.ruff.isort]
+[tool.ruff.lint.isort]
 known-first-party = ["ocrmypdf"]
 required-imports = ["from __future__ import annotations"]
 
-[tool.ruff.pydocstyle]
+[tool.ruff.lint.pydocstyle]
 convention = "google"
 
-[tool.ruff.per-file-ignores]
+[tool.ruff.lint.per-file-ignores]
 "docs/conf.py" = ["D100", "D101", "D105"]
 "tests/*.py" = ["D100", "D101", "D102", "D103", "D105"]
 "misc/*.py" = ["D103", "D101", "D102"]

src/ocrmypdf/_concurrent.py

@@ -7,8 +7,8 @@ from __future__ import annotations
 
 import threading
 from abc import ABC, abstractmethod
-from collections.abc import Iterable
-from typing import Any, Callable, TypeVar
+from collections.abc import Callable, Iterable
+from typing import Any, TypeVar
 
 from ocrmypdf._progressbar import NullProgressBar, ProgressBar
 

src/ocrmypdf/_exec/unpaper.py

@@ -8,19 +8,17 @@ from __future__ import annotations
 import logging
 import os
 import shlex
-import sys
 from collections.abc import Iterator
 from contextlib import contextmanager
 from decimal import Decimal
 from pathlib import Path
 from subprocess import PIPE, STDOUT
 from tempfile import TemporaryDirectory
-from typing import Union
 
 from packaging.version import Version
 from PIL import Image
 
-from ocrmypdf.exceptions import MissingDependencyError, SubprocessOutputError
+from ocrmypdf.exceptions import SubprocessOutputError
 from ocrmypdf.subprocess import get_version, run
 
 # unpaper documentation:
@@ -29,7 +27,7 @@ from ocrmypdf.subprocess import get_version, run
 
 UNPAPER_IMAGE_PIXEL_LIMIT = 256 * 1024 * 1024
 
-DecFloat = Union[Decimal, float]
+DecFloat = Decimal | float
 
 log = logging.getLogger(__name__)
 

src/ocrmypdf/_graft.py

@@ -289,9 +289,9 @@ class OcrGrafter:
 
             # Translate the text so it is centered at (0, 0), rotate it there, adjust
             # for a size different between initial and text PDF, then untranslate, and
-            # finally move the lower left corner to match the mediabox. All transforms
-            # must be premultiplied so they are applied in reverse order here.
-            ctm = corner @ untranslate @ scale @ rotate @ translate
+            # finally move the lower left corner to match the mediabox.
+            ctm = translate @ rotate @ scale @ untranslate @ corner
+            log.debug("Grafting with ctm %r", ctm)
 
             base_resources = _ensure_dictionary(base_page.obj, Name.Resources)
             base_xobjs = _ensure_dictionary(base_resources, Name.XObject)
@@ -311,9 +311,16 @@ class OcrGrafter:
 
             if strip_old_text:
                 strip_invisible_text(self.pdf_base, base_page)
-
+            base_page.contents_coalesce()
+            if self.render_mode == RenderMode.ON_TOP:
+                # Add q/Q to ensure content we append is drawn correctly
+                # Strictly speaking this needs to trace the whole q/Q stack in case
+                # stack is not balanced.
+                original = base_page.Contents.read_bytes()
+                base_page.Contents.write(b'q\n' + original + b'\nQ\n')
             base_page.contents_add(
-                new_text_layer, prepend=self.render_mode == RenderMode.ON_TOP
+                new_text_layer, prepend=self.render_mode == RenderMode.UNDERNEATH
             )
+            base_page.contents_coalesce()
 
             _update_resources(obj=base_page.obj, font=font, font_key=font_key)

src/ocrmypdf/_jobcontext.py

@@ -93,8 +93,8 @@ class PageContext:
         state = self.__dict__.copy()
 
         state['options'] = copy(self.options)
-        if not isinstance(state['options'].input_file, (str, bytes, os.PathLike)):
+        if not isinstance(state['options'].input_file, str | bytes | os.PathLike):
             state['options'].input_file = 'stream'
-        if not isinstance(state['options'].output_file, (str, bytes, os.PathLike)):
+        if not isinstance(state['options'].output_file, str | bytes | os.PathLike):
             state['options'].output_file = 'stream'
         return state

src/ocrmypdf/_pipeline.py

@@ -12,8 +12,9 @@ import re
 import sys
 from collections.abc import Iterable, Iterator, Sequence
 from contextlib import suppress
+from io import BytesIO
 from pathlib import Path
-from shutil import copyfileobj, copystat
+from shutil import copyfileobj
 from typing import Any, BinaryIO, TypeVar, cast
 
 import img2pdf
@@ -34,7 +35,8 @@ from ocrmypdf.exceptions import (
     UnsupportedImageFormatError,
 )
 from ocrmypdf.helpers import IMG2PDF_KWARGS, Resolution, safe_symlink
-from ocrmypdf.hocrtransform import HocrTransform
+from ocrmypdf.hocrtransform import DebugRenderOptions, HocrTransform
+from ocrmypdf.hocrtransform._font import Courier
 from ocrmypdf.pdfa import generate_pdfa_ps
 from ocrmypdf.pdfinfo import Colorspace, Encoding, PageInfo, PdfInfo
 from ocrmypdf.pluginspec import OrientationConfidence
@@ -712,19 +714,29 @@ def create_pdf_page_from_image(
     pageinfo = page_context.pageinfo
     pagesize = 72.0 * float(pageinfo.width_inches), 72.0 * float(pageinfo.height_inches)
     effective_rotation = (pageinfo.rotation - orientation_correction) % 360
-    if effective_rotation % 180 == 90:
+    swap_axis = effective_rotation % 180 == 90
+    if swap_axis:
         pagesize = pagesize[1], pagesize[0]
 
-    # This create a single page PDF
-    with open(image, 'rb') as imfile, open(output_file, 'wb') as pdf:
+    # Create a new single page PDF to hold
+    bio = BytesIO()
+    with open(image, 'rb') as imfile:
         log.debug('convert')
 
         layout_fun = img2pdf.get_layout_fun(pagesize)
         img2pdf.convert(
-            imfile, layout_fun=layout_fun, outputstream=pdf, **IMG2PDF_KWARGS
+            imfile,
+            layout_fun=layout_fun,
+            outputstream=bio,
+            engine=img2pdf.Engine.pikepdf,
+            rotation=img2pdf.Rotation.ifvalid,
         )
         log.debug('convert done')
 
+    # img2pdf does not generate boxes correctly, so we fix them
+    bio.seek(0)
+    fix_pagepdf_boxes(bio, output_file, page_context, swap_axis=swap_axis)
+
     output_file = page_context.plugin_manager.hook.filter_pdf_page(
         page=page_context, image_filename=image, output_pdf=output_file
     )
@@ -741,15 +753,25 @@ def render_hocr_page(hocr: Path, page_context: PageContext) -> Path:
         return output_file
 
     dpi = get_page_square_dpi(page_context, calculate_image_dpi(page_context))
-    debug_mode = options.pdf_renderer == 'hocrdebug'
-
+    debug_kwargs = {}
+    if options.pdf_renderer == 'hocrdebug':
+        debug_kwargs = dict(
+            debug_render_options=DebugRenderOptions(
+                render_baseline=True,
+                render_triangle=True,
+                render_line_bbox=False,
+                render_word_bbox=True,
+                render_paragraph_bbox=False,
+                render_space_bbox=False,
+            ),
+            font=Courier(),
+        )
     HocrTransform(
-        hocr_filename=hocr,
-        dpi=dpi.to_scalar(),  # square
-        debug=debug_mode,
+        hocr_filename=hocr, dpi=dpi.to_scalar(), **debug_kwargs  # square
     ).to_pdf(
         out_filename=output_file,
         image_filename=None,
+        invisible_text=True if not debug_kwargs else False,
     )
     return output_file
 
@@ -769,7 +791,57 @@ def ocr_engine_textonly_pdf(
         output_text=output_text,
         options=options,
     )
-    return (output_pdf, output_text)
+    return output_pdf, output_text
+
+
+def _offset_rect(rect: tuple[float, float, float, float], offset: tuple[float, float]):
+    """Offset a rectangle by a given amount."""
+    return (
+        rect[0] + offset[0],
+        rect[1] + offset[1],
+        rect[2] + offset[0],
+        rect[3] + offset[1],
+    )
+
+
+def fix_pagepdf_boxes(
+    infile: Path | BinaryIO,
+    out_file: Path,
+    page_context: PageContext,
+    swap_axis: bool = False,
+) -> Path:
+    """Fix the bounding boxes in a single page PDF.
+
+    The single page PDF is created with a normal MediaBox with its lower left corner
+    at (0, 0). infile is the single page PDF. page_context.mediabox has the original
+    file's mediabox, which may have a different origin. We needto adjust the other
+    boxes in the single page PDF to match the effect they had on the original page.
+
+    When correcting page rotation, we create a single page PDF that is correctly
+    rotated instead of an incorrectly rotated and then setting page.Rotate on it.
+    If rotation is either 90 or 270 degrees, then this function can be called
+    with swap_axis to swap the X and Y coordinates of all the boxes.
+
+    We are not concerned with solving degenerate cases where the boxes overlap or
+    or express invalid rectangles. We merely pass the boxes, producing a
+    transformation equivalent to the change made by constructing a new page image.
+    """
+    with pikepdf.open(infile) as pdf:
+        for page in pdf.pages:
+            # page.BleedBox = page_context.pageinfo.bleedbox
+            # page.ArtBox = page_context.pageinfo.artbox
+            mediabox = page_context.pageinfo.mediabox
+            offset = mediabox[0], mediabox[1]
+            cropbox = _offset_rect(page_context.pageinfo.cropbox, offset)
+            trimbox = _offset_rect(page_context.pageinfo.trimbox, offset)
+
+            if swap_axis:
+                cropbox = cropbox[1], cropbox[0], cropbox[3], cropbox[2]
+                trimbox = trimbox[1], trimbox[0], trimbox[3], trimbox[2]
+            page.CropBox = cropbox
+            page.TrimBox = trimbox
+        pdf.save(out_file)
+    return pdf
 
 
 def generate_postscript_stub(context: PdfContext) -> Path:

src/ocrmypdf/_pipelines/_common.py

@@ -11,13 +11,13 @@ import os
 import shutil
 import sys
 import threading
-from collections.abc import Sequence
+from collections.abc import Callable, Sequence
 from concurrent.futures.process import BrokenProcessPool
 from concurrent.futures.thread import BrokenThreadPool
 from contextlib import contextmanager
 from dataclasses import dataclass
 from pathlib import Path
-from typing import Callable, NamedTuple, cast
+from typing import NamedTuple, cast
 
 import PIL
 

src/ocrmypdf/_pipelines/ocr.py

@@ -80,7 +80,6 @@ def _exec_page_sync(page_context: PageContext) -> PageResult:
         page_context
     )
     ocr_out, text_out = _image_to_ocr_text(page_context, ocr_image_out)
-
     return PageResult(
         pageno=page_context.pageno,
         pdf_page_from_image=pdf_page_from_image_out,

src/ocrmypdf/api.py

@@ -14,7 +14,7 @@ from collections.abc import Iterable, Sequence
 from enum import IntEnum
 from io import IOBase
 from pathlib import Path
-from typing import AnyStr, BinaryIO, Union
+from typing import AnyStr, BinaryIO
 from warnings import warn
 
 import pluggy
@@ -28,8 +28,8 @@ from ocrmypdf._validation import check_options
 from ocrmypdf.cli import ArgumentParser, get_parser
 from ocrmypdf.helpers import is_iterable_notstr
 
-StrPath = Union[Path, AnyStr]
-PathOrIO = Union[BinaryIO, StrPath]
+StrPath = Path | AnyStr
+PathOrIO = BinaryIO | StrPath
 
 # Installing plugins affects the global state of the Python interpreter,
 # so we need to use a lock to prevent multiple threads from installing
@@ -169,7 +169,7 @@ def _kwargs_to_cmdline(
 
         # We have a parameter
         cmdline.append(f"--{cmd_style_arg}")
-        if isinstance(val, (int, float)):
+        if isinstance(val, int | float):
             cmdline.append(str(val))
         elif isinstance(val, str):
             cmdline.append(val)
@@ -201,11 +201,11 @@ def create_options(
         defer_kwargs={'progress_bar', 'plugins', 'parser', 'input_file', 'output_file'},
         **kwargs,
     )
-    if isinstance(input_file, (BinaryIO, IOBase)):
+    if isinstance(input_file, BinaryIO | IOBase):
         cmdline.append('stream://input_file')
     else:
         cmdline.append(os.fspath(input_file))
-    if isinstance(output_file, (BinaryIO, IOBase)):
+    if isinstance(output_file, BinaryIO | IOBase):
         cmdline.append('stream://output_file')
     else:
         cmdline.append(os.fspath(output_file))
@@ -343,7 +343,7 @@ def ocr(  # noqa: D417
 
     if not plugins:
         plugins = []
-    elif isinstance(plugins, (str, Path)):
+    elif isinstance(plugins, str | Path):
         plugins = [plugins]
     else:
         plugins = list(plugins)

src/ocrmypdf/builtin_plugins/concurrency.py

@@ -12,10 +12,10 @@ import queue
 import signal
 import sys
 import threading
-from collections.abc import Iterable
+from collections.abc import Callable, Iterable
 from concurrent.futures import ProcessPoolExecutor, ThreadPoolExecutor, as_completed
 from contextlib import suppress
-from typing import Callable, Union
+from typing import Union
 
 from rich.console import Console as RichConsole
 
@@ -25,8 +25,10 @@ from ocrmypdf._progressbar import RichProgressBar
 from ocrmypdf.exceptions import InputFileError
 from ocrmypdf.helpers import remove_all_log_handlers
 
-FuturesExecutorClass = Union[type[ThreadPoolExecutor], type[ProcessPoolExecutor]]
-Queue = Union[multiprocessing.Queue, queue.Queue]
+FuturesExecutorClass = Union[  # noqa: UP007
+    type[ThreadPoolExecutor], type[ProcessPoolExecutor]
+]
+Queue = Union[multiprocessing.Queue, queue.Queue]  # noqa: UP007
 UserInit = Callable[[], None]
 WorkerInit = Callable[[Queue, UserInit, int], None]
 
@@ -128,11 +130,14 @@ class StandardExecutor(Executor):
         listener = threading.Thread(target=log_listener, args=(log_queue,))
         listener.start()
 
-        with self.pbar_class(**progress_kwargs) as pbar, executor_class(
-            max_workers=max_workers,
-            initializer=initializer,
-            initargs=(log_queue, worker_initializer, logging.getLogger("").level),
-        ) as executor:
+        with (
+            self.pbar_class(**progress_kwargs) as pbar,
+            executor_class(
+                max_workers=max_workers,
+                initializer=initializer,
+                initargs=(log_queue, worker_initializer, logging.getLogger("").level),
+            ) as executor,
+        ):
             futures = [executor.submit(task, *args) for args in task_arguments]
             try:
                 for future in as_completed(futures):

src/ocrmypdf/builtin_plugins/ghostscript.py

@@ -17,7 +17,7 @@ log = logging.getLogger(__name__)
 
 # Currently all blacklisted versions are lower than 9.55, so none need to
 # be added here. If a future version is blacklisted, add it here.
-BLACKLISTED_GS_VERSIONS: frozenset[str] = frozenset()
+BLACKLISTED_GS_VERSIONS: frozenset[Version] = frozenset()
 
 
 @hookimpl
@@ -54,7 +54,7 @@ def check_options(options):
         program='gs',
         package='ghostscript',
         version_checker=ghostscript.version,
-        need_version='9.55',  # Ubuntu 22.04's version
+        need_version='9.54',  # RHEL 9's version; Ubuntu 22.04 has 9.55
     )
     gs_version = ghostscript.version()
     if gs_version in BLACKLISTED_GS_VERSIONS:
@@ -62,13 +62,16 @@ def check_options(options):
             f"Ghostscript {gs_version} contains serious regressions and is not "
             "supported. Please upgrade to a newer version."
         )
-    if gs_version < Version('10.02.0'):
-        log.warning(
-            f"The installed version of Ghostscript {gs_version}, contains a remote "
-            "code execution security vulnerability. Please upgrade to a newer "
-            "version. For details see CVE-2023-43115. The issue is not known to "
-            "affect OCRmyPDF or processing PDFs with Ghostscript, but upgrading "
-            "Ghostscript is recommended."
+    if Version('10.0.0') <= gs_version < Version('10.02.1') and (
+        options.skip_text or options.redo_ocr
+    ):
+        raise MissingDependencyError(
+            f"Ghostscript 10.0.0 through 10.02.0 (your version: {gs_version}) "
+            "contain serious regressions that corrupt PDFs with existing text, "
+            "such as those processed using --skip-text or --redo-ocr. "
+            "Please upgrade to a "
+            "newer version, or use --output-type pdf to avoid Ghostscript, or "
+            "use --force-ocr to discard existing text."
         )
 
     if options.output_type == 'pdfa':

src/ocrmypdf/builtin_plugins/tesseract_ocr.py

@@ -146,7 +146,11 @@ def check_options(options):
 
     # Decide on what renderer to use
     if options.pdf_renderer == 'auto':
-        options.pdf_renderer = 'sandwich'
+        if {'ara', 'heb', 'fas', 'per'} & set(options.languages):
+            log.info("Using sandwich renderer since there is an RTL language")
+            options.pdf_renderer = 'sandwich'
+        else:
+            options.pdf_renderer = 'hocr'
 
     if not tesseract.has_thresholding() and options.tesseract_thresholding != 0:
         log.warning(

src/ocrmypdf/cli.py

@@ -6,8 +6,8 @@
 from __future__ import annotations
 
 import argparse
-from collections.abc import Mapping
-from typing import Any, Callable, TypeVar
+from collections.abc import Callable, Mapping
+from typing import Any, TypeVar
 
 from ocrmypdf._version import PROGRAM_NAME as _PROGRAM_NAME
 from ocrmypdf._version import __version__ as _VERSION

src/ocrmypdf/extra_plugins/semfree.py

@@ -20,13 +20,12 @@ from __future__ import annotations
 import logging
 import logging.handlers
 import signal
-from collections.abc import Iterable, Iterator
+from collections.abc import Callable, Iterable, Iterator
 from contextlib import suppress
 from enum import Enum, auto
 from itertools import islice, repeat, takewhile, zip_longest
 from multiprocessing import Pipe, Process
 from multiprocessing.connection import Connection, wait
-from typing import Callable
 
 from ocrmypdf import Executor, hookimpl
 from ocrmypdf._concurrent import NullProgressBar

src/ocrmypdf/helpers.py

@@ -10,7 +10,7 @@ import multiprocessing
 import os
 import shutil
 import warnings
-from collections.abc import Iterable, Sequence
+from collections.abc import Callable, Iterable, Sequence
 from contextlib import suppress
 from decimal import Decimal
 from io import StringIO
@@ -19,13 +19,13 @@ from pathlib import Path
 from statistics import harmonic_mean
 from typing import (
     Any,
-    Callable,
     Generic,
     TypeVar,
 )
 
 import img2pdf
 import pikepdf
+from deprecation import deprecated
 
 log = logging.getLogger(__name__)
 
@@ -136,6 +136,7 @@ class Resolution(Generic[T]):
         return self._isclose(self.x, other.x) and self._isclose(self.y, other.y)
 
 
+@deprecated(deprecated_in='15.4.0')
 class NeverRaise(Exception):
     """An exception that is never raised."""
 

src/ocrmypdf/hocrtransform/_font.py

@@ -18,7 +18,12 @@ from pikepdf.canvas import Font
 log = logging.getLogger(__name__)
 
 
-class GlyphlessFont(Font):
+class EncodableFont(Font):
+    def text_encode(self, text: str) -> bytes:
+        raise NotImplementedError()
+
+
+class GlyphlessFont(EncodableFont):
     CID_TO_GID_DATA = zlib.compress(b"\x00\x01" * 65536)
     GLYPHLESS_FONT_NAME = 'pdf.ttf'
     GLYPHLESS_FONT = (package_files('ocrmypdf.data') / GLYPHLESS_FONT_NAME).read_bytes()
@@ -27,11 +32,14 @@ class GlyphlessFont(Font):
     def __init__(self):
         pass
 
-    def text_width(self, text: str, fontsize: float) -> int:
+    def text_width(self, text: str, fontsize: float) -> float:
         """Estimate the width of a text string when rendered with the given font."""
         # NFKC: split ligatures, combine diacritics
         return len(unicodedata.normalize("NFKC", text)) * (fontsize / self.CHAR_ASPECT)
 
+    def text_encode(self, text: str) -> bytes:
+        return text.encode('utf-16be')
+
     def register(self, pdf: Pdf):
         """Register the glyphless font.
 
@@ -110,3 +118,24 @@ class GlyphlessFont(Font):
         font_descriptor.FontFile2 = pdf.make_stream(self.GLYPHLESS_FONT)
         cid_font_type2.FontDescriptor = font_descriptor
         return basefont
+
+
+class Courier(EncodableFont):
+    """Courier font."""
+
+    def text_width(self, text: str, fontsize: float) -> float:
+        """Estimate the width of a text string when rendered with the given font."""
+        return len(text) * fontsize
+
+    def text_encode(self, text: str) -> bytes:
+        return text.encode('pdfdoc', errors='ignore')
+
+    def register(self, pdf: Pdf) -> Dictionary:
+        """Register the font."""
+        return pdf.make_indirect(
+            Dictionary(
+                BaseFont=Name.Courier,
+                Type=Name.Font,
+                Subtype=Name.Type1,
+            )
+        )

src/ocrmypdf/hocrtransform/_hocr.py

@@ -27,11 +27,11 @@ from pikepdf.canvas import (
     MAGENTA,
     RED,
     Canvas,
-    Font,
     Text,
     TextDirection,
 )
 
+from ocrmypdf.hocrtransform._font import EncodableFont as Font
 from ocrmypdf.hocrtransform._font import GlyphlessFont
 
 log = logging.getLogger(__name__)
@@ -45,12 +45,12 @@ Element = ElementTree.Element
 class DebugRenderOptions:
     """A class for managing rendering options."""
 
-    render_paragraph_bbox: bool
-    render_baseline: bool
-    render_triangle: bool
-    render_line_bbox: bool
-    render_word_bbox: bool
-    render_space_bbox: bool
+    render_paragraph_bbox: bool = False
+    render_baseline: bool = False
+    render_triangle: bool = False
+    render_line_bbox: bool = False
+    render_word_bbox: bool = False
+    render_space_bbox: bool = False
 
 
 class HocrTransformError(Exception):
@@ -81,8 +81,21 @@ class HocrTransform:
         debug: bool = False,
         fontname: Name = Name("/f-0-0"),
         font: Font = GlyphlessFont(),
+        debug_render_options: DebugRenderOptions | None = None,
     ):
         """Initialize the HocrTransform object."""
+        if debug:
+            log.warning("Use debug_render_options instead", DeprecationWarning)
+            self.render_options = DebugRenderOptions(
+                render_baseline=debug,
+                render_triangle=debug,
+                render_line_bbox=False,
+                render_word_bbox=debug,
+                render_paragraph_bbox=False,
+                render_space_bbox=False,
+            )
+        else:
+            self.render_options = debug_render_options or DebugRenderOptions()
         self.dpi = dpi
         self.hocr = ElementTree.parse(os.fspath(hocr_filename))
         self._fontname = fontname
@@ -103,14 +116,6 @@ class HocrTransform:
             self.height = (coords.ury - coords.lly) / (self.dpi / INCH)
             # Stop after first div that has page coordinates
             break
-        self.render_options = DebugRenderOptions(
-            render_baseline=debug,
-            render_triangle=debug,
-            render_line_bbox=False,
-            render_word_bbox=debug,
-            render_paragraph_bbox=False,
-            render_space_bbox=False,
-        )
 
     def _get_element_text(self, element: Element):
         """Return the textual content of the element and its children."""
@@ -215,12 +220,13 @@ class HocrTransform:
             if not found_lines:
                 # Tesseract did not report any lines (just words)
                 root = self.hocr.find(self._child_xpath('div', 'ocr_page'))
+                direction = self._get_text_direction(root)
                 self._do_line(
                     canvas,
                     root,
                     "ocrx_word",
                     invisible_text,
-                    TextDirection.LTR,
+                    direction,
                     True,
                 )
         # put the image on the page, scaled to fill the page
@@ -311,8 +317,7 @@ class HocrTransform:
             line_box_height = abs(line_box.height) / cos(angle)
             fontsize = line_box_height + intercept
             text.font(self._fontname, fontsize)
-            if invisible_text or True:
-                text.render_mode(3)  # Invisible (indicates OCR text)
+            text.render_mode(3 if invisible_text else 0)
 
             self._debug_draw_baseline(
                 canvas, line_matrix.inverse().transform(line_box), 0
@@ -362,10 +367,15 @@ class HocrTransform:
         self._debug_draw_word_bbox(canvas, box)
 
         # If this word is 0 units wide, our best bet seems to be to suppress this text
+        if text_direction == TextDirection.RTL:
+            log.info("RTL: %s", elemtxt)
         if font_width > 0:
-            text.text_transform(Matrix(1, 0, 0, 1, box.llx, 0))
+            if text_direction == TextDirection.LTR:
+                text.text_transform(Matrix(1, 0, 0, -1, box.llx, 0))
+            elif text_direction == TextDirection.RTL:
+                text.text_transform(Matrix(-1, 0, 0, -1, box.llx + box.width, 0))
             text.horiz_scale(100 * box.width / font_width)
-            text.show(elemtxt.encode('utf-16be'))
+            text.show(self._font.text_encode(elemtxt))
 
         # Get coordinates of the next word (if there is one)
         hocr_next_box = (
@@ -385,11 +395,16 @@ class HocrTransform:
         elif text_direction == TextDirection.RTL:
             space_box = Rectangle(next_box.urx, box.lly, box.llx, next_box.ury)
         self._debug_draw_space_bbox(canvas, space_box)
-        text.text_transform(Matrix(1, 0, 0, 1, space_box.llx, 0))
         space_width = self._font.text_width(' ', fontsize)
         if space_width > 0:
+            if text_direction == TextDirection.LTR:
+                text.text_transform(Matrix(1, 0, 0, -1, space_box.llx, 0))
+            elif text_direction == TextDirection.RTL:
+                text.text_transform(
+                    Matrix(-1, 0, 0, -1, space_box.llx + space_box.width, 0)
+                )
             text.horiz_scale(100 * space_box.width / space_width)
-            text.show(' '.encode('utf-16be'))
+            text.show(self._font.text_encode(' '))
 
     def _debug_draw_paragraph_boxes(self, canvas: Canvas, color=CYAN):
         """Draw boxes around paragraphs in the document."""

src/ocrmypdf/optimize.py

@@ -11,11 +11,10 @@ import sys
 import tempfile
 import threading
 from collections import defaultdict
-from collections.abc import Iterator, MutableSet, Sequence
+from collections.abc import Callable, Iterator, MutableSet, Sequence
 from os import fspath
 from pathlib import Path
-from typing import Any, Callable, NamedTuple, NewType
-from warnings import warn
+from typing import Any, NamedTuple, NewType
 from zlib import compress
 
 import img2pdf
@@ -155,6 +154,13 @@ def extract_image_jbig2(
                 with imgname.open('wb') as f:
                     ext = pim.extract_to(stream=f)
                 imgname.rename(imgname.with_suffix(ext))
+            except NotImplementedError as e:
+                if '/Decode' in str(e):
+                    log.debug(
+                        f"xref {xref}: skipping image with unsupported Decode table"
+                    )
+                    return None
+                raise
             except UnsupportedImageTypeError:
                 return None
             finally:

src/ocrmypdf/pdfinfo/info.py

@@ -10,9 +10,8 @@ import atexit
 import logging
 import re
 import statistics
-import sys
 from collections import defaultdict
-from collections.abc import Container, Iterable, Iterator, Mapping, Sequence
+from collections.abc import Callable, Container, Iterable, Iterator, Mapping, Sequence
 from contextlib import contextmanager
 from decimal import Decimal
 from enum import Enum, auto
@@ -20,7 +19,7 @@ from functools import partial
 from math import hypot, inf, isclose
 from os import PathLike
 from pathlib import Path
-from typing import Callable, NamedTuple
+from typing import NamedTuple
 from warnings import warn
 
 from pdfminer.layout import LTPage, LTTextBox
@@ -854,6 +853,12 @@ class PageInfo:
         width_pt = mediabox[2] - mediabox[0]
         height_pt = mediabox[3] - mediabox[1]
 
+        # self._artbox = [float(d) for d in page.artbox.as_list()]
+        # self._bleedbox = [float(d) for d in page.bleedbox.as_list()]
+        self._cropbox = [float(d) for d in page.cropbox.as_list()]
+        self._mediabox = [float(d) for d in page.mediabox.as_list()]
+        self._trimbox = [float(d) for d in page.trimbox.as_list()]
+
         check_this_page = pageno in check_pages
 
         if check_this_page and detailed_analysis:
@@ -970,6 +975,21 @@ class PageInfo:
         else:
             raise ValueError("rotation must be a cardinal angle")
 
+    @property
+    def cropbox(self) -> FloatRect:
+        """Return cropbox of page in PDF coordinates."""
+        return self._cropbox
+
+    @property
+    def mediabox(self) -> FloatRect:
+        """Return mediabox of page in PDF coordinates."""
+        return self._mediabox
+
+    @property
+    def trimbox(self) -> FloatRect:
+        """Return trimbox of page in PDF coordinates."""
+        return self._trimbox
+
     @property
     def images(self) -> list[ImageInfo]:
         """Return images."""
@@ -1039,12 +1059,7 @@ class PageInfo:
 
         weights = [area / total_drawn_area for area in image_areas]
         # Calculate harmonic mean of DPIs weighted by area
-        if sys.version_info >= (3, 10):
-            weighted_dpi = statistics.harmonic_mean(image_dpis, weights)
-        else:
-            weighted_dpi = sum(weights) / sum(
-                weight / dpi for weight, dpi in zip(weights, image_dpis)
-            )
+        weighted_dpi = statistics.harmonic_mean(image_dpis, weights)
         max_dpi = max(image_dpis)
         dpi_average_max_ratio = weighted_dpi / max_dpi
 
@@ -1155,7 +1170,7 @@ class PdfInfo:
     @property
     def filename(self) -> str | Path:
         """Return filename of PDF."""
-        if not isinstance(self._infile, (str, Path)):
+        if not isinstance(self._infile, str | Path):
             raise NotImplementedError("can't get filename from stream")
         return self._infile
 

src/ocrmypdf/pdfinfo/layout.py

@@ -5,12 +5,12 @@
 from __future__ import annotations
 
 import re
-from collections.abc import Mapping
+from collections.abc import Iterator, Mapping
 from contextlib import contextmanager
 from math import copysign
 from os import PathLike
 from pathlib import Path
-from typing import Any, Iterator
+from typing import Any
 from unittest.mock import patch
 
 import pdfminer

src/ocrmypdf/subprocess/__init__.py

@@ -8,12 +8,11 @@ import logging
 import os
 import re
 import sys
-from collections.abc import Mapping, Sequence
+from collections.abc import Callable, Mapping, Sequence
 from contextlib import suppress
 from pathlib import Path
 from subprocess import PIPE, STDOUT, CalledProcessError, CompletedProcess, Popen
 from subprocess import run as subprocess_run
-from typing import Callable, Union
 
 from packaging.version import Version
 
@@ -23,7 +22,7 @@ from ocrmypdf.exceptions import MissingDependencyError
 
 log = logging.getLogger(__name__)
 
-Args = Sequence[Union[Path, str]]
+Args = Sequence[Path | str]
 OsEnviron = os._Environ  # pylint: disable=protected-access
 
 

src/ocrmypdf/subprocess/_windows.py

@@ -9,18 +9,13 @@ import os
 import re
 import shutil
 import sys
-from collections.abc import Iterable, Iterator
+from collections.abc import Callable, Iterable, Iterator
 from itertools import chain
 from pathlib import Path
-from typing import Any, Callable, TypeVar
+from typing import Any, TypeAlias, TypeVar
 
 from packaging.version import InvalidVersion, Version
 
-if sys.version_info >= (3, 10):
-    from typing import TypeAlias
-else:
-    from typing_extensions import TypeAlias  # pragma: no cover
-
 if sys.platform == 'win32':
     # mypy understands 'if sys.platform' better than try/except ModuleNotFoundError
     import winreg  # pylint: disable=import-error

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

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

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

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

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

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

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

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

tests/cache/francais/__-l__deu__000001_ocr.png__000001_ocr_tess__pdf__txt/txt.bin

@@ -0,0 +1,12 @@
+Portez ce vieux whisky au juge
+blond qui fume sur son Ile
+interieure, a cöte de l'alcöve
+ovoide, oU les büches se
+consument dans l'ätre, ce qui
+ui permet de penser & la
+caenogenese de |'etre dont il
+est question dans la cause
+ambigu& entendue a MoY, dans
+un capharnaüm qui, pense-t-il,
+diminue ca et la la qualit& de son
+ceuvre.

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

@@ -0,0 +1,22 @@
+600
+500 .
+400 _ EB fp ys
+300 —f— EN / ~/ Y
+Tg ANA a3
+100 - nee -eemiae
+0-+—-* a ee ee ee eee
+S @ s > oO © ve S ) @ + & & “A 5 oo
+Se ° Ps as ge eS € x ro NS Po e? & s AS
+a a © FF SF HY HK SK BM ee sO
+e < Na ‘ : > cy xs eS @ Ww a) Oo
+ee S&S FF SF HK S e © 4
+~ & e
+3 x
+
+—¢—Support
+
+—H— No vote[note 1]
+ir Oppose
+—=—Net[note 2]
+
+re Percentage [note 3]

tests/cache/manifest.jsonl

@@ -71,3 +71,15 @@
 {"tesseract_version": "5.3.2", "system": "Linux", "python": "3.11.6", "argv_slug": "__-l__eng__000001_ocr.png__000001_ocr_hocr__hocr__txt", "sourcefile": "resources/poster.pdf", "args": ["-l", "eng", "$TMPDIR/000001_ocr.png", "$TMPDIR/000001_ocr_hocr", "hocr", "txt"]}
 {"tesseract_version": "5.3.2", "system": "Linux", "python": "3.11.6", "argv_slug": "__-l__eng__000001_ocr.png__000001_ocr_tess__pdf__txt", "sourcefile": "resources/multipage.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000001_ocr.png", "$TMPDIR/000001_ocr_tess", "pdf", "txt"]}
 {"tesseract_version": "5.3.2", "system": "Linux", "python": "3.11.6", "argv_slug": "__-l__eng__000001_ocr.png__000001_ocr_hocr__hocr__txt", "sourcefile": "resources/poster.pdf", "args": ["-l", "eng", "$TMPDIR/000001_ocr.png", "$TMPDIR/000001_ocr_hocr", "hocr", "txt"]}
+{"tesseract_version": "5.3.2", "system": "Linux", "python": "3.11.7", "argv_slug": "__-l__deu__000001_ocr.png__000001_ocr_tess__pdf__txt", "sourcefile": "resources/francais.pdf", "args": ["-l", "deu", "-c", "textonly_pdf=1", "$TMPDIR/000001_ocr.png", "$TMPDIR/000001_ocr_tess", "pdf", "txt"]}
+{"tesseract_version": "5.3.2", "system": "Linux", "python": "3.11.7", "argv_slug": "__-l__eng__--oem__1__000001_ocr.png__000001_ocr_tess__pdf__txt", "sourcefile": "resources/trivial.pdf", "args": ["-l", "eng", "--oem", "1", "-c", "textonly_pdf=1", "$TMPDIR/000001_ocr.png", "$TMPDIR/000001_ocr_tess", "pdf", "txt"]}
+{"tesseract_version": "5.3.2", "system": "Linux", "python": "3.11.7", "argv_slug": "__-l__eng__000001_ocr.png__000001_ocr_tess__pdf__txt", "sourcefile": "resources/trivial.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000001_ocr.png", "$TMPDIR/000001_ocr_tess", "pdf", "txt"]}
+{"tesseract_version": "5.3.2", "system": "Linux", "python": "3.11.7", "argv_slug": "__-l__eng__000001_ocr.png__000001_ocr_tess__pdf__txt", "sourcefile": "resources/2400dpi.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000001_ocr.png", "$TMPDIR/000001_ocr_tess", "pdf", "txt"]}
+{"tesseract_version": "5.3.2", "system": "Linux", "python": "3.11.7", "argv_slug": "__-l__eng__thresholding_method=1__000001_ocr.png__000001_ocr_tess__pdf__txt", "sourcefile": "resources/trivial.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "-c", "thresholding_method=1", "$TMPDIR/000001_ocr.png", "$TMPDIR/000001_ocr_tess", "pdf", "txt"]}
+{"tesseract_version": "5.3.2", "system": "Linux", "python": "3.11.7", "argv_slug": "__-l__eng__thresholding_method=2__000001_ocr.png__000001_ocr_tess__pdf__txt", "sourcefile": "resources/trivial.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "-c", "thresholding_method=2", "$TMPDIR/000001_ocr.png", "$TMPDIR/000001_ocr_tess", "pdf", "txt"]}
+{"tesseract_version": "5.3.2", "system": "Linux", "python": "3.11.7", "argv_slug": "__-l__eng__000001_ocr.png__000001_ocr_tess__pdf__txt", "sourcefile": "resources/graph_ocred.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000001_ocr.png", "$TMPDIR/000001_ocr_tess", "pdf", "txt"]}
+{"tesseract_version": "5.3.2", "system": "Linux", "python": "3.11.7", "argv_slug": "__-l__eng__000002_ocr.png__000002_ocr_tess__pdf__txt", "sourcefile": "resources/3small.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000002_ocr.png", "$TMPDIR/000002_ocr_tess", "pdf", "txt"]}
+{"tesseract_version": "5.3.2", "system": "Linux", "python": "3.11.7", "argv_slug": "__-l__eng__000001_ocr.png__000001_ocr_tess__pdf__txt", "sourcefile": "resources/3small.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000001_ocr.png", "$TMPDIR/000001_ocr_tess", "pdf", "txt"]}
+{"tesseract_version": "5.3.2", "system": "Linux", "python": "3.11.7", "argv_slug": "__-l__eng__000003_ocr.png__000003_ocr_tess__pdf__txt", "sourcefile": "resources/3small.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000003_ocr.png", "$TMPDIR/000003_ocr_tess", "pdf", "txt"]}
+{"tesseract_version": "5.3.2", "system": "Linux", "python": "3.11.7", "argv_slug": "__-l__eng__000001_ocr.png__000001_ocr_tess__pdf__txt", "sourcefile": "resources/poster.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000001_ocr.png", "$TMPDIR/000001_ocr_tess", "pdf", "txt"]}
+{"tesseract_version": "5.3.2", "system": "Linux", "python": "3.11.7", "argv_slug": "__-l__eng__000001_ocr.png__000001_ocr_tess__pdf__txt", "sourcefile": "resources/poster.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000001_ocr.png", "$TMPDIR/000001_ocr_tess", "pdf", "txt"]}

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

@@ -0,0 +1,118 @@
+The LinnSequencer
+32 Track MIDI Sequence Recorder
+
+The LinnSequencer is a state-of-the-art composition and performance tool for the professional musician. It is
+extremely powerful, yet amazingly simple to learn and use. It’s many remarkable features include:
+
+© Operation is similar to multi-track tape recorder with PLAY, STOP, RECORD, FAST
+FORWARD, REWIND, and LOCATE controls.
+
+e Each of the 100 sequences contains 32 simultaneous, polyphonic tracks. Each track may
+be assigned to one of 16 MIDI channels. Simultaneously plays up to 16 polyphonic
+
+synthesizers!
+
+© Ultra-fast 3!” disk drive stores complex songs in seconds and holds over 110,000 notes
+
+per disk!
+
+¢ One or all tracks may be TRANSPOSED at the touch of a key.
+e Exclusive real-time ERASE function makes editing FAST.
+e Exclusive REPEAT function automatically repeats any held notes at a pre-selected
+
+rhythmic value.
+
+¢ TIMING CORRECTION works during playback and operates without ‘chopping’ notes.
+
+¢ Optional SMPTE time code synchronization.
+
+¢ Optional remote control.
+
+Recording a Sequence
+
+To record a sequence, simply press RECORD and PLAY,
+then play your MIDI keyboard in time to the Sequencer’s
+click track. When the sequence loops back around to bar 1,
+you’ ll hear what you played—only all timing errors will be
+corrected! (Timing correction may be adjusted or defeated).
+Any additional notes played will be added into the track
+—existing notes are not erased while recording!
+
+FAST FORWARD, REWIND, and LOCATE controls
+may be used at any time to quickly access any location in
+your sequence for spot-recording. To overdub a new part,
+select a different track and start recording—while you
+record, the first track will play in perfect sync (unless you
+MUTE it, or SOLO another track). In this way, up to 32
+tracks may be overdubbed! All MIDI effects are recorded
+including pitch bend, modulation, velocity, aftertouch,
+sustain pedal, and program changes!
+
+Editing
+
+To erase a wrong note, simply hold ERASE and press
+the note to be erased just before it plays in the sequence—
+when played back, it will be gone. Notes may also be
+added, erased, or changed using the SINGLE STEP func-
+tion. To overdub notes at specific points within a sequence,
+
+Additional Features
+
+simply use LOCATE, FAST FORWARD, or REWIND to
+find the desired bar number, then start recording.
+
+The INSERT/COPY function allows you to move bars
+from one location to another—in the same sequence or a
+different one. For example, you might insert a copy of the
+first verse between the second chorus and the bridge.
+DELETE BARS operates the same way to remove
+unwanted sections.
+
+Creating a Song
+
+One way to create a song is to record each track all the
+way through (up to 999 bars). Another way is to record
+each basic section (verse, chorus, etc.) in individual
+sequences, then use the CREATE SONG function to “chain”
+them together. CREATE SONG will then automatically
+copy all the parts into a new sequence. If desired, you can
+even set the last few bars to repeat infinitely, for a fadeout.
+
+Composition Without Compromise
+
+The technology you use should never be so complex that
+it interferes with the creative process. That’s precisely why
+the LinnSequencer is designed to let you compose, record
+and edit while devoting your undivided attention to your
+music. See your Linn dealer today for a demonstration!
+
+¢ Simple, easy to learn operation—the 32 character LCD display clearly guides you through all operations. If needed, the
+
+HELP button displays additional explanations.
+
+® Non-destructive recording—existing notes are not erased while recording.
+© Two FOOTSWITCH INPUTS may be assigned to remotely control many of the commonly used functions, including
+
+ERASE, REPEAT, PLAY/STOP, or LOCATE.
+
+¢ Two TRIGGER OUTPUTS may be programmed to output pulses at any selected note value.
+
+@ Will sync to standard LinnDrum or Linn 9000 sync tone.
+
+© Utilizes ultra high-speed, 8 MHz 80186 16 bit computer internally for FAST operation.
+¢ TEMPO may be specified in BEATS-PER-MINUTE or FRAMES-PER-BEAT at 24, 25, or 30 frames per second,
+
+(even drop frame!)
+
+¢ TEMPO may be entered numerically, adjustable in tenths of a Beat-Per-Minute increments, or by tapping quarter notes
+
+on the TAP TEMPO button.
+
+¢ TEMPO CHANGES may be programmed into a sequence, with smooth transitions if desired.
+e Any TIME SIGNATURE may be used, and may be changed within a song.
+
+linn
+Linn Electronics, Inc.
+
+18720 Oxnard Street, Tarzana, CA 91356
+(818) 708-8131 TELEX #298949 LINN UR

tests/plugins/gs_render_soft_error.py

@@ -3,7 +3,6 @@
 
 from __future__ import annotations
 
-from pathlib import Path
 from subprocess import CalledProcessError
 from unittest.mock import patch
 

tests/test_concurrency.py

@@ -4,6 +4,7 @@
 from __future__ import annotations
 
 import os
+import platform
 
 import pytest
 
@@ -13,6 +14,9 @@ from .conftest import run_ocrmypdf_api
 
 
 @pytest.mark.skipif(os.name == 'nt', reason="Windows doesn't have SIGKILL")
+@pytest.mark.skipif(
+    platform.python_version_tuple() >= ('3', '12'), reason="can deadlock due to fork"
+)
 def test_simulate_oom_killer(multipage, no_outpdf):
     exitcode = run_ocrmypdf_api(
         multipage,

tests/test_main.py

@@ -17,7 +17,7 @@ from PIL import Image
 
 import ocrmypdf
 from ocrmypdf._exec import tesseract
-from ocrmypdf.exceptions import ExitCode, MissingDependencyError, OutputFileAccessError
+from ocrmypdf.exceptions import ExitCode, MissingDependencyError
 from ocrmypdf.pdfa import file_claims_pdfa
 from ocrmypdf.pdfinfo import Colorspace, Encoding, PdfInfo
 from ocrmypdf.subprocess import get_version

tests/test_optimize.py

@@ -176,9 +176,10 @@ def test_multiple_pngs(resources, outdir):
         )
         mock.assert_called()
 
-    with pikepdf.open(outdir / 'in.pdf') as inpdf, pikepdf.open(
-        outdir / 'out.pdf'
-    ) as outpdf:
+    with (
+        pikepdf.open(outdir / 'in.pdf') as inpdf,
+        pikepdf.open(outdir / 'out.pdf') as outpdf,
+    ):
         for n in range(len(inpdf.pages)):
             inim = next(iter(inpdf.pages[n].images.values()))
             outim = next(iter(outpdf.pages[n].images.values()))

tests/test_rotation.py

@@ -4,10 +4,10 @@
 from __future__ import annotations
 
 import operator
-import warnings
 from io import BytesIO
 from math import cos, pi, sin
 from os import fspath
+from subprocess import run
 
 import img2pdf
 import pikepdf
@@ -22,10 +22,6 @@ from ocrmypdf.pdfinfo import PdfInfo
 
 from .conftest import check_ocrmypdf, run_ocrmypdf_api
 
-warnings.filterwarnings(
-    "ignore", category=DeprecationWarning, module="reportlab.lib.rl_safe_eval"
-)
-
 # pylintx: disable=unused-variable
 
 RENDERERS = ['hocr', 'sandwich']
@@ -215,34 +211,35 @@ def test_rotate_deskew_ocr_timeout(resources, outdir):
     assert cmp > 0.95
 
 
+def make_rotate_test(imagefile, outdir, prefix, image_angle, page_angle):
+    memimg = BytesIO()
+    with Image.open(fspath(imagefile)) as im:
+        if image_angle != 0:
+            ccw_angle = -image_angle % 360
+            im = im.transpose(getattr(Image.Transpose, f'ROTATE_{ccw_angle}'))
+        im.save(memimg, format='PNG')
+    memimg.seek(0)
+    mempdf = BytesIO()
+    img2pdf.convert(
+        memimg.read(),
+        layout_fun=img2pdf.get_fixed_dpi_layout_fun((200, 200)),
+        outputstream=mempdf,
+        **IMG2PDF_KWARGS,
+    )
+    mempdf.seek(0)
+    with pikepdf.open(mempdf) as pdf:
+        pdf.pages[0].Rotate = page_angle
+        target = outdir / f'{prefix}_{image_angle}_{page_angle}.pdf'
+        pdf.save(target)
+        return target
+
+
 @pytest.mark.slow
 @pytest.mark.parametrize('page_angle', (0, 90, 180, 270))
 @pytest.mark.parametrize('image_angle', (0, 90, 180, 270))
 def test_rotate_page_level(image_angle, page_angle, resources, outdir, caplog):
-    def make_rotate_test(prefix, image_angle, page_angle):
-        memimg = BytesIO()
-        with Image.open(fspath(resources / 'typewriter.png')) as im:
-            if image_angle != 0:
-                ccw_angle = -image_angle % 360
-                im = im.transpose(getattr(Image.Transpose, f'ROTATE_{ccw_angle}'))
-            im.save(memimg, format='PNG')
-        memimg.seek(0)
-        mempdf = BytesIO()
-        img2pdf.convert(
-            memimg.read(),
-            layout_fun=img2pdf.get_fixed_dpi_layout_fun((200, 200)),
-            outputstream=mempdf,
-            **IMG2PDF_KWARGS,
-        )
-        mempdf.seek(0)
-        with pikepdf.open(mempdf) as pdf:
-            pdf.pages[0].Rotate = page_angle
-            target = outdir / f'{prefix}_{image_angle}_{page_angle}.pdf'
-            pdf.save(target)
-            return target
-
-    reference = make_rotate_test('ref', 0, 0)
-    test = make_rotate_test('test', image_angle, page_angle)
+    reference = make_rotate_test(resources / 'typewriter.png', outdir, 'ref', 0, 0)
+    test = make_rotate_test(resources, outdir, 'test', image_angle, page_angle)
     out = test.with_suffix('.out.pdf')
 
     exitcode = run_ocrmypdf_api(
@@ -258,6 +255,33 @@ def test_rotate_page_level(image_angle, page_angle, resources, outdir, caplog):
     assert compare_images_monochrome(outdir, reference, 1, out, 1) > 0.2
 
 
+@pytest.mark.slow
+@pytest.mark.parametrize('page_rotate_angle', (0, 90, 180, 270))
+def test_page_rotate_tag(page_rotate_angle, resources, outdir, caplog):
+    # Check that pages that have an image that is misrotated but restored to
+    # correct rotation with a /Rotate will be processed correct and yield text.
+    test = make_rotate_test(
+        resources / 'crom.png', outdir, 'test', -page_rotate_angle, page_rotate_angle
+    )
+    out = test.with_suffix('.out.pdf')
+    exitcode = run_ocrmypdf_api(
+        test,
+        out,
+        '-O0',
+    )
+    assert exitcode == 0, caplog.text
+
+    def pdftotext(filename):
+        return (
+            run(['pdftotext', '-enc', 'UTF-8', filename, '-'], capture_output=True)
+            .stdout.strip()
+            .decode('utf-8')
+        )
+
+    test_text = pdftotext(out)
+    assert 'is a' in test_text, test_text
+
+
 def test_rasterize_rotates(resources, tmp_path):
     pm = get_plugin_manager([])
 

tests/test_userunit.py

@@ -7,10 +7,9 @@ from math import isclose
 
 import pytest
 
-from ocrmypdf.exceptions import ExitCode
 from ocrmypdf.pdfinfo import PdfInfo
 
-from .conftest import check_ocrmypdf, run_ocrmypdf_api
+from .conftest import check_ocrmypdf
 
 # pylint: disable=redefined-outer-name