v16.1.2 release notes

Ghostscript is more picky about a specific case with SMask that cannot be converted to PDF/A

Details here
https://github.com/ArtifexSoftware/ghostpdl/commit/4dcfae36bb4dcbc4ef3b5e5afc98bcde0d6b9ddc

.docker/Dockerfile

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

.docker/Dockerfile.alpine

@@ -1,7 +1,7 @@
 # SPDX-FileCopyrightText: 2023 James R. Barlow
 # SPDX-License-Identifier: MPL-2.0
 
-FROM alpine:3.18 as base
+FROM alpine:3.19 as base
 
 ENV LANG=C.UTF-8
 ENV TZ=UTC

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

@@ -1,4 +1,4 @@
-name: General issues
+name: Installation, packaging, dependencies
 description: Installation, packages, dependencies, "nothing works", test suite failures...
 title: "[Bug]: "
 labels: ["bug", "triage"]
@@ -9,6 +9,10 @@ body:
     attributes:
       value: |
         Thanks for taking the time to fill out this bug report!
+
+        If your issue involves using OCRmyPDF on specific file(s) and not getting
+        good results, this is the *wrong* issue template. Please use the recommended
+        template to ensure we have enough information to help.
   - type: textarea
     id: what-happened
     attributes:

.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
@@ -31,8 +31,21 @@ body:
     id: files
     attributes:
       label: Files
-      description: Please attach the input and output files, or any screenshots that may be helpful.
-      placeholder: Drag and drop files here
+      description: |
+        Please attach the input and output files, or any screenshots that may be helpful.
+
+        If you cannot provide a test file, we probably won't be able to help with the issue.
+        PDF is a complex file format, and there may be technical details in the PDF that are
+        causing the issue. There's really no substitute for a test file.
+
+        We understand files may contain personal or sensitive information. Here are some options:
+        - Try reproducing the issue with a file from the test suite. (See tests/resources)
+        - Try to create another file in the same way as your private file.
+        - Encrypt the file to OCRmyPDF's private GPG key, and then zip the GPG file.
+        - Use ``qpdf --json yourfile.pdf`` to produce a JSON representation of your file that
+          omits personal information.
+      placeholder: |
+        Drag and drop files here.
   - type: dropdown
     id: packaging-system
     attributes:

.github/workflows/build.yml

@@ -22,20 +22,18 @@ jobs:
     strategy:
       matrix:
         include:
-          - os: ubuntu-22.04
-            python: "3.9"
           - os: ubuntu-22.04
             python: "3.10"
           - os: ubuntu-22.04
             python: "3.11"
           - os: ubuntu-22.04
-            python: "3.9"
+            python: "3.10"
             tesseract5: true
           - os: ubuntu-latest
             python: "3.12"
             tesseract5: true
-            #- os: ubuntu-latest
-            #  python: "pypy3.9"
+          - os: ubuntu-latest
+            python: "pypy3.10"
 
     env:
       OS: ${{ matrix.os }}
@@ -46,7 +44,7 @@ jobs:
         with:
           fetch-depth: "0" # 0=all, needed for setuptools-scm to resolve version tags
 
-      - uses: actions/setup-python@v4
+      - uses: actions/setup-python@v5
         name: Setup Python
         with:
           python-version: ${{ matrix.python }}
@@ -102,7 +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
@@ -137,7 +135,7 @@ jobs:
             pngquant \
             tesseract
 
-      - uses: actions/setup-python@v4
+      - uses: actions/setup-python@v5
         name: Setup Python
         with:
           python-version: ${{ matrix.python }}
@@ -160,7 +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
@@ -182,7 +180,7 @@ jobs:
         with:
           fetch-depth: "0" # 0=all, needed for setuptools-scm to resolve version tags
 
-      - uses: actions/setup-python@v4
+      - uses: actions/setup-python@v5
         name: Setup Python
         with:
           python-version: ${{ matrix.python }}
@@ -191,7 +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: |
@@ -203,7 +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
@@ -216,10 +214,10 @@ jobs:
         with:
           fetch-depth: "0" # 0=all, needed for setuptools-scm to resolve version tags
 
-      - uses: actions/setup-python@v4
+      - uses: actions/setup-python@v5
         name: Setup Python
         with:
-          python-version: "3.9"
+          python-version: "3.10"
           cache: "pip"
 
       - name: Make wheels and sdist
@@ -227,8 +225,9 @@ jobs:
           python -m pip install --upgrade pip wheel build
           python -m build --sdist --wheel
 
-      - uses: actions/upload-artifact@v3
+      - uses: actions/upload-artifact@v4
         with:
+          name: artifact
           path: |
             ./dist/*.whl
             ./dist/*.tar.gz
@@ -242,7 +241,7 @@ jobs:
       id-token: write  # mandatory for PyPI publishing
     if: github.event_name == 'push' && startsWith(github.event.ref, 'refs/tags/v')
     steps:
-      - uses: actions/download-artifact@v3
+      - uses: actions/download-artifact@v4
         with:
           name: artifact
           path: dist
@@ -259,7 +258,7 @@ jobs:
       # Required to create a release
       contents: write
     steps:
-      - uses: actions/download-artifact@v3
+      - uses: actions/download-artifact@v4
         with:
           name: artifact
           path: dist

.readthedocs.yaml

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

.reuse/dep5

@@ -124,6 +124,14 @@ Copyright:  Kai-Uwe Behrmann <www.behrmann.name>
             ColorSolutions <www.basICColor.com>
 License: Zlib
 
+Files: src/ocrmypdf/data/pdf.ttf
+Copyright: (C) 2014 Ray Smith
+ (C) 2015 Ken Sharp
+ (C) 2016 James R. Barlow
+ (C) 2016 Jeff Breidenbach
+ (C) 2017 Zdenko Podobný
+License: Apache-2.0
+
 Files: tests/resources/3small.pdf
 Copyright: (C) 2014 Euskaldunaa
  (C) 2017 James R. Barlow

docs/advanced.rst

@@ -239,46 +239,46 @@ rendering
 OCRmyPDF has these PDF renderers: ``sandwich`` and ``hocr``. The
 renderer may be selected using ``--pdf-renderer``. The default is
 ``auto`` which lets OCRmyPDF select the renderer to use. Currently,
-``auto`` always selects ``sandwich``.
-
-The ``sandwich`` renderer
--------------------------
-
-The ``sandwich`` renderer uses Tesseract's new text-only PDF feature,
-which produces a PDF page that lays out the OCR in invisible text. This
-page is then "sandwiched" onto the original PDF page, allowing lossless
-application of OCR even to PDF pages that contain other vector objects.
-
-Currently this is the best renderer for most uses, however it is
-implemented in Tesseract so OCRmyPDF cannot influence it. Currently some
-problematic PDF viewers like Mozilla PDF.js and macOS Preview have
-problems with segmenting its text output, and
-mightrunseveralwordstogether.
-
-When image preprocessing features like ``--deskew`` are used, the
-original PDF will be rendered as a full page and the OCR layer will be
-placed on top.
+``auto`` always selects ``hocr``.
 
 The ``hocr`` renderer
 ---------------------
 
-The ``hocr`` renderer works with older versions of Tesseract. The image
-layer is copied from the original PDF page if possible, avoiding
-potentially lossy transcoding or loss of other PDF information. If
-preprocessing is specified, then the image layer is a new PDF. (You may
-need to disable PDF/A conversion nad optimization to eliminate all
-lossy transformations.)
+.. versionchanged:: 16.0.0
 
-Unlike ``sandwich`` this renderer is implemented within OCRmyPDF; anyone
-looking to customize how OCR is presented should look here. A major
-disadvantage of this renderer is it not capable of correctly handling
-text outside the Latin alphabet (specifically, it supports the ISO 8859-1
-character set). Pull requests to improve the situation are welcome.
+In both renderers, a text-only layer is rendered and sandwiched (overlaid)
+on to either the original PDF page, or newly rasterized version of the
+original PDF page (when ``--force-ocr`` is used). In this way, loss
+of PDF information is generally avoided. (You may need to disable PDF/A
+conversion and optimization to eliminate all lossy transformations.)
 
-Currently, this renderer has the best compatibility with Mozilla's
-PDF.js viewer.
+The current approach used by the new hOCR renderer is a re-implementation
+of Tesseract's PDF renderer, using the same Glyphless font and general
+ideas, but fixing many technical issues that impeded it. The new hocr
+provides better text placement accuracy, avoids issues with word
+segmentation, and provides better positioning of skewed text.
 
-This works in all versions of Tesseract.
+Using the experimental API, it is also possible to edit the OCR output
+from Tesseract, using any tool that is capable of editing hOCR files.
+
+Older versions of this renderer did not support non-Latin languages, but
+it is now universal.
+
+The ``sandwich`` renderer
+-------------------------
+
+The ``sandwich`` renderer uses Tesseract's text-only PDF feature,
+which produces a PDF page that lays out the OCR in invisible text.
+
+Currently some problematic PDF viewers like Mozilla PDF.js and macOS
+Preview have problems with segmenting its text output, and
+mightrunseveralwordstogether. It also does not implement right to left
+fonts (Arabic, Hebrew, Persian). The output of this renderer cannot
+be edited. The sandwich renderer is retained for testing.
+
+When image preprocessing features like ``--deskew`` are used, the
+original PDF will be rendered as a full page and the OCR layer will be
+placed on top.
 
 Rendering and rasterizing options
 =================================

docs/api.rst

@@ -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)
 ----------------
@@ -391,18 +393,20 @@ package manager:
 
 * ``winget install -e --id Python.Python.3.11``
 * ``winget install -e --id UB-Mannheim.TesseractOCR``
-* ``winget install -e --id ArtifexSoftware.GhostScript``
 
+You will need to install Ghostscript manually, `since it does not support automated
+installs anymore <https://artifex.com/news/ghostscript-10.01.0-disabling-silent-install-option>`_.
+
+* `Ghostscript download page <https://ghostscript.com/releases/gsdnld.html>`_.`
 
 (Or alternately, using the `Chocolatey <https://chocolatey.org/>`_ package manager, install
 the following when running in an Administrator command prompt):
 
 * ``choco install python3``
 * ``choco install --pre tesseract``
-* ``choco install ghostscript``
 * ``choco install pngquant`` (optional)
 
-Either set of commands will install the required software. At the mmoment there is no
+Either set of commands will install the required software. At the moment there is no
 single command to install Windows.
 
 You may then use ``pip`` to install ocrmypdf. (This can performed by a user or
@@ -452,7 +456,7 @@ Cygwin64
 
 First install the the following prerequisite Cygwin packages using ``setup-x86_64.exe``::
 
-    python39 (or later)
+    python310 (or later)
     python3?-devel
     python3?-pip
     python3?-lxml
@@ -538,9 +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
 -------------------------------------
 
@@ -550,8 +570,8 @@ manager. ``pip`` cannot provide them.
 
 The following versions are required:
 
--  Python 3.9 or newer
--  Ghostscript 9.55 or newer
+-  Python 3.10 or newer
+-  Ghostscript 9.54 or newer
 -  Tesseract 4.1.1 or newer
 -  jbig2enc 0.29 or newer
 -  pngquant 2.5 or newer
@@ -586,7 +606,7 @@ unfortunately, the ``pip install`` command cannot satisfy all of them.
 Installing HEAD revision from sources
 =====================================
 
-If you have ``git`` and Python 3.9 or newer installed, you can install
+If you have ``git`` and Python 3.10 or newer installed, you can install
 from source. When the ``pip`` installer runs, it will alert you if
 dependencies are missing.
 
@@ -669,7 +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.
@@ -679,4 +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/performance.rst

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

docs/release_notes.rst

@@ -20,6 +20,8 @@ The most recent release of OCRmyPDF is |OCRmyPDF PyPI|. Any newer versions
 referred to in these notes may exist the main branch but have not been
 tagged yet.
 
+OCRmyPDF typically supports the three most recent Python versions.
+
 .. note::
 
    Attention maintainers: these release notes may be updated with information
@@ -28,6 +30,89 @@ tagged yet.
 
 .. |OCRmyPDF PyPI| image:: https://img.shields.io/pypi/v/ocrmypdf.svg
 
+v16.1.2
+=======
+
+-  Fixed test suite failure when using Ghostscript 10.3.
+-  Other minor corrections.
+
+v16.1.1
+=======
+
+-  Fixed PyPy 3.10 support.
+
+v16.1.0
+=======
+
+-  Improved hOCR renderer is now default for left to right languages.
+-  Improved handling of rotated pages. Previously, OCR text might be missing for
+   pages that were rotated with a /Rotate tag on the page entry.
+-  Improved handling of cropped pages. Previously, in some cases a page with a
+   crop box would not have its OCR applied correctly and misalignment between
+   OCR text and visible text coudl occur.
+-  Documentation improvements, especially installation instructions for less
+   common platforms.
+
+v16.0.4
+=======
+
+-  Fixed some issues for left-to-right text with the new hOCR renderer. It is still
+   not default yet but will be made so soon. Right-to-left text is still in progress.
+-  Added an error to prevent use of several versions of Ghostscript that seem
+   corrupt existing text in input PDFs. Newly generated OCR is not affected.
+   For best results, use Ghostscript 10.02.1 or newer, which contains the fix
+   for the issue.
+
+v16.0.3
+=======
+
+-  Changed minimum required Ghostscript to 9.54, to support users of RHEL 9 and its
+   derivatives, since that is the latest version available there.
+-  Removed warning message about CVE-2023-43115, on the assumption that most
+   distributions have backported the patch by now.
+
+v16.0.2
+=======
+
+-  Temporarily changed PDF text renderer back to sandwich by default to address
+   regressions in macOS Preview.
+
+v16.0.1
+=======
+
+-  Fixed text rendering issue with new hOCR text renderer - extraneous byte order
+   marks.
+-  Tightened dependencies.
+
+v16.0.0
+=======
+
+-  Added OCR text renderer, combined the best ideas of Tesseract's PDF
+   generator and the older hOCR transformer renderer. The result is a hopefully
+   permanent fix for wordssmushedtogetherwithoutspaces issues in extracted text,
+   better registration/position of text on skewed baselines :issue:`1009`,
+   fixes to character output when the German Fraktur script is used :issue:`1191`,
+   proper rendering of right to left languages (Arabic, Hebrew, Persian) :issue:`1157`.
+   Asian languages may still have excessive word breaks compared to expectations.
+   The new renderer is the default; the old sandwich renderer is still available
+   using ``--pdf-renderer sandwich``; the old hOCR renderer is no more.
+-  The ``ocrmypdf.hocrtransform`` API has changed substantially.
+-  Support for Python 3.9 has been dropped. Python 3.10+ is now required.
+-  pikepdf >= 8.8.0 is now required.
+
+
+v15.4.4
+=======
+
+-  Fixed documentation for installing Ghostscript on Windows. :issue:`1198`
+-  Added warning message about security issue in older versions of Ghostscript.
+
+v15.4.3
+=======
+
+-  Fixed deprecation warning in pikepdf older than 8.7.1; pikepdf >= 8.7.1 is
+   now required.
+
 v15.4.2
 =======
 

misc/batch.py

@@ -1,5 +1,6 @@
 #!/usr/bin/env python3
 # SPDX-FileCopyrightText: 2016 findingorder <https://github.com/findingorder>
+# SPDX-FileCopyrightText: 2024 nilsro <https://github.com/nilsro>
 # SPDX-License-Identifier: MIT
 
 """Example of using ocrmypdf as a library in a script.
@@ -15,6 +16,10 @@ from __future__ import annotations
 
 import logging
 import sys
+import os
+import posixpath
+import shutil
+import filecmp
 from pathlib import Path
 
 import ocrmypdf
@@ -22,32 +27,62 @@ import ocrmypdf
 # pylint: disable=logging-format-interpolation
 # pylint: disable=logging-not-lazy
 
+def filecompare(a,b):
+    try:
+        return filecmp.cmp(a, b, shallow=True)
+    except FileNotFoundError:
+        return False
+
+
 script_dir = Path(__file__).parent
+# set archive_dir to a path for backup original documents. Leave empty if not required.
+archive_dir = "/pdfbak"
 
 if len(sys.argv) > 1:
     start_dir = Path(sys.argv[1])
 else:
-    start_dir = Path('.')
+    start_dir = Path(".")
 
 if len(sys.argv) > 2:
     log_file = Path(sys.argv[2])
 else:
-    log_file = script_dir.with_name('ocr-tree.log')
+    log_file = script_dir.with_name("ocr-tree.log")
 
 logging.basicConfig(
     level=logging.INFO,
-    format='%(asctime)s %(message)s',
+    format="%(asctime)s %(message)s",
     filename=log_file,
-    filemode='a',
+    filemode="a",
 )
 
+logging.info(f"Start directory {start_dir}")
+
 ocrmypdf.configure_logging(ocrmypdf.Verbosity.default)
 
-for filename in start_dir.glob("**/*.py"):
+for filename in start_dir.glob("**/*.pdf"):
     logging.info(f"Processing {filename}")
-    result = ocrmypdf.ocr(filename, filename, deskew=True)
-    if result == ocrmypdf.ExitCode.already_done_ocr:
-        logging.error("Skipped document because it already contained text")
-    elif result == ocrmypdf.ExitCode.ok:
+    if ocrmypdf.pdfa.file_claims_pdfa(filename)["pass"]:
+        logging.info("Skipped document because it already contained text")
+    else:
+        archive_filename = archive_dir + str(filename)
+        if len(archive_dir) > 0 and not filecompare(filename, archive_filename):
+            logging.info(f"Archiving document to {archive_filename}")
+            try:
+                shutil.copy2(filename, posixpath.dirname(archive_filename))
+            except IOError as io_err:
+                os.makedirs(posixpath.dirname(archive_filename))
+                shutil.copy2(filename, posixpath.dirname(archive_filename))
+        try:
+            result = ocrmypdf.ocr(filename, filename, deskew=True)
+            logging.info(result)
+        except ocrmypdf.exceptions.EncryptedPdfError:
+            logging.info("Skipped document because it is encrypted")
+        except ocrmypdf.exceptions.PriorOcrFoundError:
+            logging.info("Skipped document because it already contained text")
+        except ocrmypdf.exceptions.DigitalSignatureError:
+            logging.info("Skipped document because it has a digital signature")
+        except ocrmypdf.exceptions.TaggedPDFError:
+            logging.info("Skipped document because it does not need ocr as it is tagged")
+        except:
+            logging.error("Unhandled error occured")
         logging.info("OCR complete")
-    logging.info(result)

misc/watcher.py

@@ -7,7 +7,6 @@
 
 # Do not enable annotations!
 # https://github.com/tiangolo/typer/discussions/598
-# from __future__ import annotations
 
 import json
 import logging
@@ -131,7 +130,7 @@ def execute_ocrmypdf(
 
 
 class HandleObserverEvent(PatternMatchingEventHandler):
-    def __init__(
+    def __init__(  # noqa: D107
         self,
         patterns=None,
         ignore_patterns=None,
@@ -191,7 +190,7 @@ 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

@@ -10,18 +10,16 @@ dynamic = ["version"]
 description = "OCRmyPDF adds an OCR text layer to scanned PDF files, allowing them to be searched"
 readme = "README.md"
 license = { text = "MPL-2.0" }
-requires-python = ">=3.9"
+requires-python = ">=3.10"
 dependencies = [
   "Pillow>=10.0.1",
   "deprecation>=2.1.0",
-  "img2pdf>=0.4.4",
+  "img2pdf>=0.5",
   "packaging>=20",
   "pdfminer.six>=20220319",
-  "pikepdf>=8",
-  "pluggy>=0.13.0",
-  "reportlab>=3.6.8",
+  "pikepdf>=8.10.1",
+  "pluggy>=1",
   "rich>=13",
-  "typing-extensions>=4;python_version<'3.10'",
 ]
 authors = [{ name = "James R. Barlow", email = "james@purplerock.ca" }]
 classifiers = [
@@ -58,6 +56,7 @@ test = [
   "pytest-cov>=3.0.0",
   "pytest-xdist>=2.5.0",
   "python-xmp-toolkit==2.0.1", # also requires apt-get install libexempi3
+  "reportlab>=3.6.8",
   "types-Pillow",
   "types-humanfriendly",
 ]
@@ -77,11 +76,11 @@ namespaces = false
 [tool.setuptools_scm]
 
 [tool.distutils.bdist_wheel]
-python-tag = "py39"
+python-tag = "py310"
 
 [tool.black]
 line-length = 88
-target-version = ["py39", "py310", "py311"]
+target-version = ["py310", "py311", "py312"]
 skip-string-normalization = true
 include = '\.pyi?$'
 exclude = '''
@@ -132,7 +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]
 
@@ -150,7 +153,10 @@ module = [
 ignore_missing_imports = true
 
 [tool.ruff]
-select = [
+target-version = "py310"
+
+[tool.ruff.lint]
+"select" = [
   "D",    # pydocstyle
   "E",    # pycodestyle
   "W",    # pycodestyle
@@ -158,16 +164,14 @@ select = [
   "I001", # isort
   "UP",   # pyupgrade
 ]
-target-version = "py39"
 
-[tool.ruff.isort]
+[tool.ruff.lint.isort]
 known-first-party = ["ocrmypdf"]
-required-imports = ["from __future__ import annotations"]
 
-[tool.ruff.pydocstyle]
+[tool.ruff.lint.pydocstyle]
 convention = "google"
 
-[tool.ruff.per-file-ignores]
+[tool.ruff.lint.per-file-ignores]
 "docs/conf.py" = ["D100", "D101", "D105"]
 "tests/*.py" = ["D100", "D101", "D102", "D103", "D105"]
 "misc/*.py" = ["D103", "D101", "D102"]

src/ocrmypdf/_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 Callable, TypeVar
+from collections.abc import Callable, Iterable
+from typing import Any, TypeVar
 
 from ocrmypdf._progressbar import NullProgressBar, ProgressBar
 
@@ -19,6 +19,10 @@ def _task_noop(*_args, **_kwargs):
     return
 
 
+def _task_finished_noop(_result: Any, pbar: ProgressBar):
+    pbar.update()
+
+
 class Executor(ABC):
     """Abstract concurrent executor."""
 
@@ -66,7 +70,7 @@ class Executor(ABC):
         if not worker_initializer:
             worker_initializer = _task_noop
         if not task_finished:
-            task_finished = _task_noop
+            task_finished = _task_finished_noop
         if not task:
             task = _task_noop
 

src/ocrmypdf/_exec/unpaper.py

@@ -8,48 +8,26 @@ from __future__ import annotations
 import logging
 import os
 import shlex
-import sys
 from collections.abc import Iterator
 from contextlib import contextmanager
 from decimal import Decimal
 from pathlib import Path
 from subprocess import PIPE, STDOUT
-from typing import Union
+from tempfile import TemporaryDirectory
 
 from packaging.version import Version
 from PIL import Image
 
-from ocrmypdf.exceptions import MissingDependencyError, SubprocessOutputError
+from ocrmypdf.exceptions import SubprocessOutputError
 from ocrmypdf.subprocess import get_version, run
 
 # unpaper documentation:
 # https://github.com/Flameeyes/unpaper/blob/main/doc/basic-concepts.md
 
 
-if sys.version_info >= (3, 10):
-    from tempfile import TemporaryDirectory
-else:
-    from tempfile import TemporaryDirectory as _TemporaryDirectory
-
-    class TemporaryDirectory(_TemporaryDirectory):
-        """Shim to consume ignore_cleanup_errors kwarg on Python 3.9 and older.
-
-        The argument is consumed without action. If users are getting errors related
-        to temporary file cleanup, they should upgrade to Python 3.10 which properly
-        cleans up temporary directories on Windows.
-
-        See: https://github.com/python/cpython/pull/24793
-        """
-
-        def __init__(self, ignore_cleanup_errors=False, **kwargs):
-            super().__init__(**kwargs)
-
-    del _TemporaryDirectory
-
-
 UNPAPER_IMAGE_PIXEL_LIMIT = 256 * 1024 * 1024
 
-DecFloat = Union[Decimal, float]
+DecFloat = Decimal | float
 
 log = logging.getLogger(__name__)
 

src/ocrmypdf/_graft.py

@@ -12,12 +12,12 @@ from pathlib import Path
 
 from pikepdf import (
     Dictionary,
+    Matrix,
     Name,
     Operator,
     Page,
     Pdf,
     PdfError,
-    PdfMatrix,
     Stream,
     parse_content_stream,
     unparse_content_stream,
@@ -268,13 +268,13 @@ class OcrGrafter:
             mediabox = base_page.mediabox
             wp, hp = mediabox[2] - mediabox[0], mediabox[3] - mediabox[1]
 
-            translate = PdfMatrix().translated(-wt / 2, -ht / 2)
-            untranslate = PdfMatrix().translated(wp / 2, hp / 2)
-            corner = PdfMatrix().translated(mediabox[0], mediabox[1])
+            translate = Matrix().translated(-wt / 2, -ht / 2)
+            untranslate = Matrix().translated(wp / 2, hp / 2)
+            corner = Matrix().translated(mediabox[0], mediabox[1])
             # -rotation because the input is a clockwise angle and this formula
             # uses CCW
             text_rotation = -text_rotation % 360
-            rotate = PdfMatrix().rotated(text_rotation)
+            rotate = Matrix().rotated(text_rotation)
 
             # Because of rounding of DPI, we might get a text layer that is not
             # identically sized to the target page. Scale to adjust. Normally this
@@ -285,12 +285,13 @@ class OcrGrafter:
             scale_y = hp / ht
 
             # log.debug('%r', scale_x, scale_y)
-            scale = PdfMatrix().scaled(scale_x, scale_y)
+            scale = Matrix().scaled(scale_x, scale_y)
 
             # Translate the text so it is centered at (0, 0), rotate it there, adjust
             # for a size different between initial and text PDF, then untranslate, and
-            # finally move the lower left corner to match the mediabox
+            # finally move the lower left corner to match the mediabox.
             ctm = translate @ rotate @ scale @ untranslate @ corner
+            log.debug("Grafting with ctm %r", ctm)
 
             base_resources = _ensure_dictionary(base_page.obj, Name.Resources)
             base_xobjs = _ensure_dictionary(base_resources, Name.XObject)
@@ -310,9 +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.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'
-
-    hocrtransform = HocrTransform(hocr_filename=hocr, dpi=dpi.to_scalar())  # square
-    hocrtransform.to_pdf(
+    debug_kwargs = {}
+    if options.pdf_renderer == 'hocrdebug':
+        debug_kwargs = dict(
+            debug_render_options=DebugRenderOptions(
+                render_baseline=True,
+                render_triangle=True,
+                render_line_bbox=False,
+                render_word_bbox=True,
+                render_paragraph_bbox=False,
+                render_space_bbox=False,
+            ),
+            font=Courier(),
+        )
+    HocrTransform(
+        hocr_filename=hocr, dpi=dpi.to_scalar(), **debug_kwargs  # square
+    ).to_pdf(
         out_filename=output_file,
         image_filename=None,
-        show_bounding_boxes=False if not debug_mode else True,
-        invisible_text=True if not debug_mode else False,
-        interword_spaces=True,
+        invisible_text=True if not debug_kwargs else False,
     )
     return output_file
 
@@ -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:
@@ -992,10 +1064,3 @@ def copy_final(
             # get the appropriate umask, ownership, etc.
             with open(output_file, 'w+b') as output_stream:
                 copyfileobj(input_stream, output_stream)
-            # Attempt to copy file attributes from input to output
-            if original_file:
-                with suppress(OSError):
-                    # Copy original file's permissions, ownership, etc. if possible
-                    copystat(original_file, output_file)
-                    # Set output file's modification time to now
-                    Path(output_file).touch(exist_ok=True)

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/_validation.py

@@ -28,7 +28,6 @@ from ocrmypdf.exceptions import (
     OutputFileAccessError,
 )
 from ocrmypdf.helpers import is_file_writable, monotonic, safe_symlink
-from ocrmypdf.hocrtransform import HOCR_OK_LANGS
 from ocrmypdf.subprocess import check_external_program
 
 # -------------
@@ -83,15 +82,6 @@ def check_options_languages(
 
 
 def check_options_output(options: Namespace) -> None:
-    is_latin = set(options.languages).issubset(HOCR_OK_LANGS)
-
-    if options.pdf_renderer.startswith('hocr') and not is_latin:
-        log.warning(
-            "The 'hocr' PDF renderer is known to cause problems with one "
-            "or more of the languages in your document.  Use "
-            "`--pdf-renderer auto` (the default) to avoid this issue."
-        )
-
     if options.output_type == 'none' and options.output_file not in (os.devnull, '-'):
         raise BadArgsError(
             "Since you specified `--output-type none`, the output file "

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
 
@@ -25,13 +25,13 @@ 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]
 
-RichTqdmProgressAdapter = RichProgressBar  # Deprecated shim; remove in OCRmyPDF 16
-
 
 def log_listener(q: Queue):
     """Listen to the worker processes and forward the messages to logging.
@@ -130,11 +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

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

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(
@@ -216,7 +220,7 @@ class TesseractOcrEngine(OcrEngine):
 
     @staticmethod
     def creator_tag(options):
-        tag = '-PDF' if options.pdf_renderer == 'sandwich' else ''
+        tag = '-PDF' if options.pdf_renderer == 'sandwich' else 'hOCR'
         return f"Tesseract OCR{tag} {TesseractOcrEngine.version()}"
 
     def __str__(self):

src/ocrmypdf/cli.py

@@ -6,8 +6,8 @@
 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
@@ -390,7 +390,7 @@ Online documentation is located at:
         action='store',
         type=numeric(float, 0),
         metavar='MPixels',
-        help="Set maximum number of pixels to unpack before treating an image as a "
+        help="Set maximum number of megapixels to unpack before treating an image as a "
         "decompression bomb",
         default=250.0,
     )

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.py

@@ -1,461 +0,0 @@
-#!/usr/bin/env python3
-# SPDX-FileCopyrightText: 2010 Jonathan Brinley
-# SPDX-FileCopyrightText: 2013-2014 Julien Pfefferkorn
-# SPDX-FileCopyrightText: 2022 James R. Barlow
-# SPDX-License-Identifier: MIT
-
-"""Transform .hocr and page image to text PDF."""
-
-from __future__ import annotations
-
-import argparse
-import os
-import re
-import warnings
-from math import atan, cos, sin
-from pathlib import Path
-from typing import Any, NamedTuple
-from xml.etree import ElementTree
-
-with warnings.catch_warnings():
-    # reportlab uses deprecated load_module
-    # shim can be removed when we require reportlab >= 3.7
-    warnings.filterwarnings(
-        'ignore', category=DeprecationWarning, message=r".*load_module.*"
-    )
-    from reportlab.lib.colors import black, cyan, magenta, red
-    from reportlab.lib.units import inch
-    from reportlab.pdfgen.canvas import Canvas
-
-# According to Wikipedia these languages are supported in the ISO-8859-1 character
-# set, meaning reportlab can generate them and they are compatible with hocr,
-# assuming Tesseract has the necessary languages installed. Note that there may
-# not be language packs for them.
-HOCR_OK_LANGS = frozenset(
-    [
-        # Languages fully covered by Latin-1:
-        'afr',  # Afrikaans
-        'alb',  # Albanian
-        'ast',  # Leonese
-        'baq',  # Basque
-        'bre',  # Breton
-        'cos',  # Corsican
-        'eng',  # English
-        'eus',  # Basque
-        'fao',  # Faoese
-        'gla',  # Scottish Gaelic
-        'glg',  # Galician
-        'glv',  # Manx
-        'ice',  # Icelandic
-        'ind',  # Indonesian
-        'isl',  # Icelandic
-        'ita',  # Italian
-        'ltz',  # Luxembourgish
-        'mal',  # Malay Rumi
-        'mga',  # Irish
-        'nor',  # Norwegian
-        'oci',  # Occitan
-        'por',  # Portugeuse
-        'roh',  # Romansh
-        'sco',  # Scots
-        'sma',  # Sami
-        'spa',  # Spanish
-        'sqi',  # Albanian
-        'swa',  # Swahili
-        'swe',  # Swedish
-        'tgl',  # Tagalog
-        'wln',  # Walloon
-        # Languages supported by Latin-1 except for a few rare characters that OCR
-        # is probably not trained to recognize anyway:
-        'cat',  # Catalan
-        'cym',  # Welsh
-        'dan',  # Danish
-        'deu',  # German
-        'dut',  # Dutch
-        'est',  # Estonian
-        'fin',  # Finnish
-        'fra',  # French
-        'hun',  # Hungarian
-        'kur',  # Kurdish
-        'nld',  # Dutch
-        'wel',  # Welsh
-    ]
-)
-
-
-Element = ElementTree.Element
-
-
-class Rect(NamedTuple):
-    """A rectangle for managing PDF coordinates."""
-
-    x1: Any
-    y1: Any
-    x2: Any
-    y2: Any
-
-
-class HocrTransformError(Exception):
-    """Error while applying hOCR transform."""
-
-
-class HocrTransform:
-    """A class for converting documents from the hOCR format.
-
-    For details of the hOCR format, see:
-    http://kba.cloud/hocr-spec/.
-    """
-
-    box_pattern = re.compile(r'bbox((\s+\d+){4})')
-    baseline_pattern = re.compile(
-        r'''
-        baseline \s+
-        ([\-\+]?\d*\.?\d*) \s+  # +/- decimal float
-        ([\-\+]?\d+)            # +/- int''',
-        re.VERBOSE,
-    )
-    ligatures = str.maketrans(
-        {'ff': 'ff', 'ffi': 'f‌f‌i', 'ffl': 'f‌f‌l', 'fi': 'fi', 'fl': 'fl'}
-    )
-
-    def __init__(self, *, hocr_filename: str | Path, dpi: float):
-        """Initialize the HocrTransform object."""
-        self.dpi = dpi
-        self.hocr = ElementTree.parse(os.fspath(hocr_filename))
-
-        # if the hOCR file has a namespace, ElementTree requires its use to
-        # find elements
-        matches = re.match(r'({.*})html', self.hocr.getroot().tag)
-        self.xmlns = ''
-        if matches:
-            self.xmlns = matches.group(1)
-
-        # get dimension in pt (not pixel!!!!) of the OCRed image
-        self.width, self.height = None, None
-        for div in self.hocr.findall(self._child_xpath('div', 'ocr_page')):
-            coords = self.element_coordinates(div)
-            pt_coords = self.pt_from_pixel(coords)
-            self.width = pt_coords.x2 - pt_coords.x1
-            self.height = pt_coords.y2 - pt_coords.y1
-            # there shouldn't be more than one, and if there is, we don't want
-            # it
-            break
-        if self.width is None or self.height is None:
-            raise HocrTransformError("hocr file is missing page dimensions")
-
-    def __str__(self):  # pragma: no cover
-        """Return the textual content of the HTML body."""
-        if self.hocr is None:
-            return ''
-        body = self.hocr.find(self._child_xpath('body'))
-        if body:
-            return self._get_element_text(body)
-        else:
-            return ''
-
-    def _get_element_text(self, element: Element):
-        """Return the textual content of the element and its children."""
-        text = ''
-        if element.text is not None:
-            text += element.text
-        for child in element:
-            text += self._get_element_text(child)
-        if element.tail is not None:
-            text += element.tail
-        return text
-
-    @classmethod
-    def element_coordinates(cls, element: Element) -> Rect:
-        """Get coordinates of the bounding box around an element."""
-        out = Rect._make(0 for _ in range(4))
-        if 'title' in element.attrib:
-            matches = cls.box_pattern.search(element.attrib['title'])
-            if matches:
-                coords = matches.group(1).split()
-                out = Rect._make(int(coords[n]) for n in range(4))
-        return out
-
-    @classmethod
-    def baseline(cls, element: Element) -> tuple[float, float]:
-        """Get baseline's slope and intercept."""
-        if 'title' in element.attrib:
-            matches = cls.baseline_pattern.search(element.attrib['title'])
-            if matches:
-                return float(matches.group(1)), int(matches.group(2))
-        return (0.0, 0.0)
-
-    def pt_from_pixel(self, pxl) -> Rect:
-        """Returns the quantity in PDF units (pt) given quantity in pixels."""
-        return Rect._make((c / self.dpi * inch) for c in pxl)
-
-    def _child_xpath(self, html_tag: str, html_class: str | None = None) -> str:
-        xpath = f".//{self.xmlns}{html_tag}"
-        if html_class:
-            xpath += f"[@class='{html_class}']"
-        return xpath
-
-    @classmethod
-    def replace_unsupported_chars(cls, s: str) -> str:
-        """Replaces characters with those available in the Helvetica typeface."""
-        return s.translate(cls.ligatures)
-
-    def to_pdf(
-        self,
-        *,
-        out_filename: Path,
-        image_filename: Path | None = None,
-        show_bounding_boxes: bool = False,
-        fontname: str = "Helvetica",
-        invisible_text: bool = False,
-        interword_spaces: bool = False,
-    ) -> None:
-        """Creates a PDF file with an image superimposed on top of the text.
-
-        Text is positioned according to the bounding box of the lines in
-        the hOCR file.
-        The image need not be identical to the image used to create the hOCR
-        file.
-        It can have a lower resolution, different color mode, etc.
-
-        Arguments:
-            out_filename: Path of PDF to write.
-            image_filename: Image to use for this file. If omitted, the OCR text
-                is shown.
-            show_bounding_boxes: Show bounding boxes around various text regions,
-                for debugging.
-            fontname: Name of font to use.
-            invisible_text: If True, text is rendered invisible so that is
-                selectable but never drawn. If False, text is visible and may
-                be seen if the image is skipped or deleted in Acrobat.
-            interword_spaces: If True, insert spaces between words rather than
-                drawing each word without spaces. Generally this improves text
-                extraction.
-        """
-        # create the PDF file
-        # page size in points (1/72 in.)
-        pdf = Canvas(
-            os.fspath(out_filename),
-            pagesize=(self.width, self.height),
-            pageCompression=1,
-        )
-
-        # draw bounding box for each paragraph
-        # light blue for bounding box of paragraph
-        pdf.setStrokeColor(cyan)
-        # light blue for bounding box of paragraph
-        pdf.setFillColor(cyan)
-        pdf.setLineWidth(0)  # no line for bounding box
-        for elem in self.hocr.iterfind(self._child_xpath('p', 'ocr_par')):
-            elemtxt = self._get_element_text(elem).rstrip()
-            if len(elemtxt) == 0:
-                continue
-
-            pxl_coords = self.element_coordinates(elem)
-            pt = self.pt_from_pixel(pxl_coords)  # pylint: disable=invalid-name
-
-            # draw the bbox border
-            if show_bounding_boxes:  # pragma: no cover
-                pdf.rect(
-                    pt.x1, self.height - pt.y2, pt.x2 - pt.x1, pt.y2 - pt.y1, fill=1
-                )
-
-        found_lines = False
-        for line in (
-            element
-            for element in self.hocr.iterfind(self._child_xpath('span'))
-            if 'class' in element.attrib
-            and element.attrib['class'] in {'ocr_header', 'ocr_line', 'ocr_textfloat'}
-        ):
-            found_lines = True
-            self._do_line(
-                pdf,
-                line,
-                "ocrx_word",
-                fontname,
-                invisible_text,
-                interword_spaces,
-                show_bounding_boxes,
-            )
-
-        if not found_lines:
-            # Tesseract did not report any lines (just words)
-            root = self.hocr.find(self._child_xpath('div', 'ocr_page'))
-            self._do_line(
-                pdf,
-                root,
-                "ocrx_word",
-                fontname,
-                invisible_text,
-                interword_spaces,
-                show_bounding_boxes,
-            )
-        # put the image on the page, scaled to fill the page
-        if image_filename is not None:
-            pdf.drawImage(
-                os.fspath(image_filename), 0, 0, width=self.width, height=self.height
-            )
-
-        # finish up the page and save it
-        pdf.showPage()
-        pdf.save()
-
-    @classmethod
-    def polyval(cls, poly, x):  # pragma: no cover
-        """Calculate the value of a polynomial at a point."""
-        return x * poly[0] + poly[1]
-
-    def _do_line(
-        self,
-        pdf: Canvas,
-        line: Element | None,
-        elemclass: str,
-        fontname: str,
-        invisible_text: bool,
-        interword_spaces: bool,
-        show_bounding_boxes: bool,
-    ):
-        if line is None:
-            return
-        pxl_line_coords = self.element_coordinates(line)
-        line_box = self.pt_from_pixel(pxl_line_coords)
-        line_height = line_box.y2 - line_box.y1
-
-        slope, pxl_intercept = self.baseline(line)
-        if abs(slope) < 0.005:
-            slope = 0.0
-        angle = atan(slope)
-        cos_a, sin_a = cos(angle), sin(angle)
-
-        text = pdf.beginText()
-        intercept = pxl_intercept / self.dpi * inch
-
-        # Don't allow the font to break out of the bounding box. Division by
-        # cos_a accounts for extra clearance between the glyph's vertical axis
-        # on a sloped baseline and the edge of the bounding box.
-        fontsize = (line_height - abs(intercept)) / cos_a
-        text.setFont(fontname, fontsize)
-        if invisible_text:
-            text.setTextRenderMode(3)  # Invisible (indicates OCR text)
-
-        # Intercept is normally negative, so this places it above the bottom
-        # of the line box
-        baseline_y2 = self.height - (line_box.y2 + intercept)
-
-        if show_bounding_boxes:  # pragma: no cover
-            # draw the baseline in magenta, dashed
-            pdf.setDash()
-            pdf.setStrokeColor(magenta)
-            pdf.setLineWidth(0.5)
-            # negate slope because it is defined as a rise/run in pixel
-            # coordinates and page coordinates have the y axis flipped
-            pdf.line(
-                line_box.x1,
-                baseline_y2,
-                line_box.x2,
-                self.polyval((-slope, baseline_y2), line_box.x2 - line_box.x1),
-            )
-            # light green for bounding box of word/line
-            pdf.setDash(6, 3)
-            pdf.setStrokeColor(red)
-
-        text.setTextTransform(cos_a, -sin_a, sin_a, cos_a, line_box.x1, baseline_y2)
-        pdf.setFillColor(black)  # text in black
-
-        elements = line.findall(self._child_xpath('span', elemclass))
-        for elem in elements:
-            elemtxt = self._get_element_text(elem).strip()
-            elemtxt = self.replace_unsupported_chars(elemtxt)
-            if elemtxt == '':
-                continue
-
-            pxl_coords = self.element_coordinates(elem)
-            box = self.pt_from_pixel(pxl_coords)
-            if interword_spaces:
-                # if  `--interword-spaces` is true, append a space
-                # to the end of each text element to allow simpler PDF viewers
-                # such as PDF.js to better recognize words in search and copy
-                # and paste. Do not remove space from last word in line, even
-                # though it would look better, because it will interfere with
-                # naive text extraction. \n does not work either.
-                elemtxt += ' '
-                box = Rect._make(
-                    (
-                        box.x1,
-                        line_box.y1,
-                        box.x2 + pdf.stringWidth(' ', fontname, line_height),
-                        line_box.y2,
-                    )
-                )
-            box_width = box.x2 - box.x1
-            font_width = pdf.stringWidth(elemtxt, fontname, fontsize)
-
-            # draw the bbox border
-            if show_bounding_boxes:  # pragma: no cover
-                pdf.rect(
-                    box.x1, self.height - line_box.y2, box_width, line_height, fill=0
-                )
-
-            # Adjust relative position of cursor
-            # This is equivalent to:
-            #   text.setTextOrigin(pt.x1, self.height - line_box.y2)
-            # but the former generates a full text reposition matrix (Tm) in the
-            # content stream while this issues a "offset" (Td) command.
-            # .moveCursor() is relative to start of the text line, where the
-            # "text line" means whatever reportlab defines it as. Do not use
-            # use .getCursor(), since moveCursor() rather unintuitively plans
-            # its moves relative to .getStartOfLine().
-            # For skewed lines, in the text transform we set up a rotated
-            # coordinate system, so we don't have to account for the
-            # incremental offset. Surprisingly most PDF viewers can handle this.
-            cursor = text.getStartOfLine()
-            dx = box.x1 - cursor[0]
-            dy = baseline_y2 - cursor[1]
-            text.moveCursor(dx, dy)
-
-            # If reportlab tells us this word is 0 units wide, our best seems
-            # to be to suppress this text
-            if font_width > 0:
-                text.setHorizScale(100 * box_width / font_width)
-                text.textOut(elemtxt)
-        pdf.drawText(text)
-
-
-if __name__ == "__main__":
-    parser = argparse.ArgumentParser(description='Convert hocr file to PDF')
-    parser.add_argument(
-        '-b',
-        '--boundingboxes',
-        action="store_true",
-        default=False,
-        help='Show bounding boxes borders',
-    )
-    parser.add_argument(
-        '-r',
-        '--resolution',
-        type=int,
-        default=300,
-        help='Resolution of the image that was OCRed',
-    )
-    parser.add_argument(
-        '-i',
-        '--image',
-        default=None,
-        help='Path to the image to be placed above the text',
-    )
-    parser.add_argument(
-        '--interword-spaces',
-        action='store_true',
-        default=False,
-        help='Add spaces between words',
-    )
-    parser.add_argument('hocrfile', help='Path to the hocr file to be parsed')
-    parser.add_argument('outputfile', help='Path to the PDF file to be generated')
-    args = parser.parse_args()
-
-    hocr = HocrTransform(hocr_filename=args.hocrfile, dpi=args.resolution)
-    hocr.to_pdf(
-        out_filename=args.outputfile,
-        image_filename=args.image,
-        show_bounding_boxes=args.boundingboxes,
-        interword_spaces=args.interword_spaces,
-    )

src/ocrmypdf/hocrtransform/__init__.py

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

src/ocrmypdf/hocrtransform/__main__.py

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

src/ocrmypdf/hocrtransform/_font.py

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

src/ocrmypdf/hocrtransform/_hocr.py

@@ -0,0 +1,488 @@
+# SPDX-FileCopyrightText: 2010 Jonathan Brinley
+# SPDX-FileCopyrightText: 2013-2014 Julien Pfefferkorn
+# SPDX-FileCopyrightText: 2023 James R. Barlow
+# SPDX-License-Identifier: MIT
+
+"""hOCR transform implementation."""
+
+from __future__ import annotations
+
+import logging
+import os
+import re
+import unicodedata
+from dataclasses import dataclass
+from itertools import pairwise
+from math import atan, cos, pi
+from pathlib import Path
+from xml.etree import ElementTree
+
+from pikepdf import Matrix, Name, Rectangle
+from pikepdf.canvas import (
+    BLACK,
+    BLUE,
+    CYAN,
+    DARKGREEN,
+    GREEN,
+    MAGENTA,
+    RED,
+    Canvas,
+    Text,
+    TextDirection,
+)
+
+from ocrmypdf.hocrtransform._font import EncodableFont as Font
+from ocrmypdf.hocrtransform._font import GlyphlessFont
+
+log = logging.getLogger(__name__)
+
+INCH = 72.0
+
+Element = ElementTree.Element
+
+
+@dataclass
+class DebugRenderOptions:
+    """A class for managing rendering options."""
+
+    render_paragraph_bbox: bool = False
+    render_baseline: bool = False
+    render_triangle: bool = False
+    render_line_bbox: bool = False
+    render_word_bbox: bool = False
+    render_space_bbox: bool = False
+
+
+class HocrTransformError(Exception):
+    """Error while applying hOCR transform."""
+
+
+class HocrTransform:
+    """A class for converting documents from the hOCR format.
+
+    For details of the hOCR format, see:
+    http://kba.cloud/hocr-spec/.
+    """
+
+    box_pattern = re.compile(r'bbox (\d+) (\d+) (\d+) (\d+)')
+    baseline_pattern = re.compile(
+        r'''
+        baseline \s+
+        ([\-\+]?\d*\.?\d*) \s+  # +/- decimal float
+        ([\-\+]?\d+)            # +/- int''',
+        re.VERBOSE,
+    )
+
+    def __init__(
+        self,
+        *,
+        hocr_filename: str | Path,
+        dpi: float,
+        debug: bool = False,
+        fontname: Name = Name("/f-0-0"),
+        font: Font = GlyphlessFont(),
+        debug_render_options: DebugRenderOptions | None = None,
+    ):
+        """Initialize the HocrTransform object."""
+        if debug:
+            log.warning("Use debug_render_options instead", DeprecationWarning)
+            self.render_options = DebugRenderOptions(
+                render_baseline=debug,
+                render_triangle=debug,
+                render_line_bbox=False,
+                render_word_bbox=debug,
+                render_paragraph_bbox=False,
+                render_space_bbox=False,
+            )
+        else:
+            self.render_options = debug_render_options or DebugRenderOptions()
+        self.dpi = dpi
+        self.hocr = ElementTree.parse(os.fspath(hocr_filename))
+        self._fontname = fontname
+        self._font = font
+
+        # if the hOCR file has a namespace, ElementTree requires its use to
+        # find elements
+        matches = re.match(r'({.*})html', self.hocr.getroot().tag)
+        self.xmlns = ''
+        if matches:
+            self.xmlns = matches.group(1)
+
+        for div in self.hocr.findall(self._child_xpath('div', 'ocr_page')):
+            coords = self.element_coordinates(div)
+            if not coords:
+                raise HocrTransformError("hocr file is missing page dimensions")
+            self.width = (coords.urx - coords.llx) / (self.dpi / INCH)
+            self.height = (coords.ury - coords.lly) / (self.dpi / INCH)
+            # Stop after first div that has page coordinates
+            break
+
+    def _get_element_text(self, element: Element):
+        """Return the textual content of the element and its children."""
+        text = ''
+        if element.text is not None:
+            text += element.text
+        for child in element:
+            text += self._get_element_text(child)
+        if element.tail is not None:
+            text += element.tail
+        return text
+
+    @classmethod
+    def element_coordinates(cls, element: Element) -> Rectangle | None:
+        """Get coordinates of the bounding box around an element."""
+        matches = cls.box_pattern.search(element.attrib.get('title', ''))
+        if not matches:
+            return None
+        return Rectangle(
+            float(matches.group(1)),  # llx = left
+            float(matches.group(2)),  # lly = top
+            float(matches.group(3)),  # urx = right
+            float(matches.group(4)),  # ury = bottom
+        )
+
+    @classmethod
+    def baseline(cls, element: Element) -> tuple[float, float]:
+        """Get baseline's slope and intercept."""
+        matches = cls.baseline_pattern.search(element.attrib.get('title', ''))
+        if not matches:
+            return (0.0, 0.0)
+        return float(matches.group(1)), int(matches.group(2))
+
+    def _child_xpath(self, html_tag: str, html_class: str | None = None) -> str:
+        xpath = f".//{self.xmlns}{html_tag}"
+        if html_class:
+            xpath += f"[@class='{html_class}']"
+        return xpath
+
+    @classmethod
+    def normalize_text(cls, s: str) -> str:
+        """Normalize the given text using the NFKC normalization form."""
+        return unicodedata.normalize("NFKC", s)
+
+    def to_pdf(
+        self,
+        *,
+        out_filename: Path,
+        image_filename: Path | None = None,
+        invisible_text: bool = True,
+    ) -> None:
+        """Creates a PDF file with an image superimposed on top of the text.
+
+        Text is positioned according to the bounding box of the lines in
+        the hOCR file.
+        The image need not be identical to the image used to create the hOCR
+        file.
+        It can have a lower resolution, different color mode, etc.
+
+        Arguments:
+            out_filename: Path of PDF to write.
+            image_filename: Image to use for this file. If omitted, the OCR text
+                is shown.
+            invisible_text: If True, text is rendered invisible so that is
+                selectable but never drawn. If False, text is visible and may
+                be seen if the image is skipped or deleted in Acrobat.
+        """
+        # create the PDF file
+        # page size in points (1/72 in.)
+        canvas = Canvas(page_size=(self.width, self.height))
+        canvas.add_font(self._fontname, self._font)
+        page_matrix = (
+            Matrix()
+            .translated(0, self.height)
+            .scaled(1, -1)
+            .scaled(INCH / self.dpi, INCH / self.dpi)
+        )
+        log.debug(page_matrix)
+        with canvas.do.save_state(cm=page_matrix):
+            self._debug_draw_paragraph_boxes(canvas)
+            found_lines = False
+            for par in self.hocr.iterfind(self._child_xpath('p', 'ocr_par')):
+                for line in (
+                    element
+                    for element in par.iterfind(self._child_xpath('span'))
+                    if 'class' in element.attrib
+                    and element.attrib['class']
+                    in {'ocr_header', 'ocr_line', 'ocr_textfloat'}
+                ):
+                    found_lines = True
+                    direction = self._get_text_direction(par)
+                    inject_word_breaks = self._get_inject_word_breaks(par)
+                    self._do_line(
+                        canvas,
+                        line,
+                        "ocrx_word",
+                        invisible_text,
+                        direction,
+                        inject_word_breaks,
+                    )
+
+            if not found_lines:
+                # Tesseract did not report any lines (just words)
+                root = self.hocr.find(self._child_xpath('div', 'ocr_page'))
+                direction = self._get_text_direction(root)
+                self._do_line(
+                    canvas,
+                    root,
+                    "ocrx_word",
+                    invisible_text,
+                    direction,
+                    True,
+                )
+        # put the image on the page, scaled to fill the page
+        if image_filename is not None:
+            canvas.do.draw_image(
+                image_filename, 0, 0, width=self.width, height=self.height
+            )
+
+        # finish up the page and save it
+        canvas.to_pdf().save(out_filename)
+
+    def _get_text_direction(self, par):
+        """Get the text direction of the paragraph.
+
+        Arabic, Hebrew, Persian, are right-to-left languages.
+        """
+        return (
+            TextDirection.RTL
+            if par.attrib.get('dir', 'ltr') == 'rtl'
+            else TextDirection.LTR
+        )
+
+    def _get_inject_word_breaks(self, par):
+        """Determine whether word breaks should be injected.
+
+        In Chinese, Japanese, and Korean, word breaks are not injected, because
+        words are usually one or two characters and separators are usually explicit.
+        In all other languages, we inject word breaks to help word segmentation.
+        """
+        lang = par.attrib.get('lang', '')
+        log.debug(lang)
+        if lang in {'chi_sim', 'chi_tra', 'jpn', 'kor'}:
+            return False
+        return True
+
+    @classmethod
+    def polyval(cls, poly, x):  # pragma: no cover
+        """Calculate the value of a polynomial at a point."""
+        return x * poly[0] + poly[1]
+
+    def _do_line(
+        self,
+        canvas: Canvas,
+        line: Element | None,
+        elemclass: str,
+        invisible_text: bool,
+        text_direction: TextDirection,
+        inject_word_breaks: bool,
+    ):
+        """Render the text for a given line.
+
+        The canvas's coordinate system must be configured so that hOCR pixel
+        coordinates are mapped to PDF coordinates.
+        """
+        if line is None:
+            return
+        line_box = self.element_coordinates(line)
+        if not line_box:
+            return
+        assert line_box.ury > line_box.lly  # lly is top, ury is bottom
+
+        self._debug_draw_line_bbox(canvas, line_box)
+
+        # Baseline is a polynomial (usually straight line) that describes the
+        # text baseline relative to the bottom left corner of the line bounding
+        # box.
+        bottom_left_corner = line_box.llx, line_box.ury
+        slope, intercept = self.baseline(line)
+        if abs(slope) < 0.005:
+            slope = 0.0
+        angle = atan(slope)
+
+        # Setup a new coordinate system on the line box's intercept and rotated by
+        # its slope.
+        line_matrix = (
+            Matrix()
+            .translated(*bottom_left_corner)
+            .translated(0, intercept)
+            .rotated(angle / pi * 180)
+        )
+        log.debug(line_matrix)
+        with canvas.do.save_state(cm=line_matrix):
+            text = Text(direction=text_direction)
+
+            # Don't allow the font to break out of the bounding box. Division by
+            # cos_a accounts for extra clearance between the glyph's vertical axis
+            # on a sloped baseline and the edge of the bounding box.
+            line_box_height = abs(line_box.height) / cos(angle)
+            fontsize = line_box_height + intercept
+            text.font(self._fontname, fontsize)
+            text.render_mode(3 if invisible_text else 0)
+
+            self._debug_draw_baseline(
+                canvas, line_matrix.inverse().transform(line_box), 0
+            )
+
+            canvas.do.fill_color(BLACK)  # text in black
+            elements = line.findall(self._child_xpath('span', elemclass))
+            for elem, next_elem in pairwise(elements + [None]):
+                self._do_line_word(
+                    canvas,
+                    line_matrix,
+                    text,
+                    fontsize,
+                    elem,
+                    next_elem,
+                    text_direction,
+                    inject_word_breaks,
+                )
+            canvas.do.draw_text(text)
+
+    def _do_line_word(
+        self,
+        canvas: Canvas,
+        line_matrix: Matrix,
+        text: Text,
+        fontsize: float,
+        elem: Element,
+        next_elem: Element | None,
+        text_direction: TextDirection,
+        inject_word_breaks: bool,
+    ):
+        """Render the text for a single word."""
+        if elem is None:
+            return
+        elemtxt = self.normalize_text(self._get_element_text(elem).strip())
+        if elemtxt == '':
+            return
+
+        hocr_box = self.element_coordinates(elem)
+        if hocr_box is None:
+            return
+        box = line_matrix.inverse().transform(hocr_box)
+        font_width = self._font.text_width(elemtxt, fontsize)
+
+        # Debug sketches
+        self._debug_draw_word_triangle(canvas, box)
+        self._debug_draw_word_bbox(canvas, box)
+
+        # If this word is 0 units wide, our best bet seems to be to suppress this text
+        if text_direction == TextDirection.RTL:
+            log.info("RTL: %s", elemtxt)
+        if font_width > 0:
+            if text_direction == TextDirection.LTR:
+                text.text_transform(Matrix(1, 0, 0, -1, box.llx, 0))
+            elif text_direction == TextDirection.RTL:
+                text.text_transform(Matrix(-1, 0, 0, -1, box.llx + box.width, 0))
+            text.horiz_scale(100 * box.width / font_width)
+            text.show(self._font.text_encode(elemtxt))
+
+        # Get coordinates of the next word (if there is one)
+        hocr_next_box = (
+            self.element_coordinates(next_elem) if next_elem is not None else None
+        )
+        if hocr_next_box is None:
+            return
+        # Render a space this word and the next word. The explicit space helps
+        # PDF viewers identify the word break, and horizontally scaling it to
+        # occupy the space the between the words helps the PDF viewer
+        # avoid combiningthewordstogether.
+        if not inject_word_breaks:
+            return
+        next_box = line_matrix.inverse().transform(hocr_next_box)
+        if text_direction == TextDirection.LTR:
+            space_box = Rectangle(box.urx, box.lly, next_box.llx, next_box.ury)
+        elif text_direction == TextDirection.RTL:
+            space_box = Rectangle(next_box.urx, box.lly, box.llx, next_box.ury)
+        self._debug_draw_space_bbox(canvas, space_box)
+        space_width = self._font.text_width(' ', fontsize)
+        if space_width > 0:
+            if text_direction == TextDirection.LTR:
+                text.text_transform(Matrix(1, 0, 0, -1, space_box.llx, 0))
+            elif text_direction == TextDirection.RTL:
+                text.text_transform(
+                    Matrix(-1, 0, 0, -1, space_box.llx + space_box.width, 0)
+                )
+            text.horiz_scale(100 * space_box.width / space_width)
+            text.show(self._font.text_encode(' '))
+
+    def _debug_draw_paragraph_boxes(self, canvas: Canvas, color=CYAN):
+        """Draw boxes around paragraphs in the document."""
+        if not self.render_options.render_paragraph_bbox:  # pragma: no cover
+            return
+        with canvas.do.save_state():
+            # draw box around paragraph
+            canvas.do.stroke_color(color).line_width(0.1)
+            for elem in self.hocr.iterfind(self._child_xpath('p', 'ocr_par')):
+                elemtxt = self._get_element_text(elem).strip()
+                if len(elemtxt) == 0:
+                    continue
+                ocr_par = self.element_coordinates(elem)
+                if ocr_par is None:
+                    continue
+                canvas.do.rect(
+                    ocr_par.llx, ocr_par.lly, ocr_par.width, ocr_par.height, fill=0
+                )
+
+    def _debug_draw_line_bbox(self, canvas: Canvas, line_box: Rectangle, color=BLUE):
+        """Render the bounding box of a text line."""
+        if not self.render_options.render_line_bbox:  # pragma: no cover
+            return
+        with canvas.do.save_state():
+            canvas.do.stroke_color(color).line_width(0.15).rect(
+                line_box.llx, line_box.lly, line_box.width, line_box.height, fill=0
+            )
+
+    def _debug_draw_word_triangle(
+        self, canvas: Canvas, box: Rectangle, color=RED, line_width=0.1
+    ):
+        """Render a triangle that conveys word height and drawing direction."""
+        if not self.render_options.render_triangle:  # pragma: no cover
+            return
+        with canvas.do.save_state():
+            canvas.do.stroke_color(color).line_width(line_width).line(
+                box.llx, box.lly, box.urx, box.lly
+            ).line(box.urx, box.lly, box.llx, box.ury).line(
+                box.llx, box.lly, box.llx, box.ury
+            )
+
+    def _debug_draw_word_bbox(
+        self, canvas: Canvas, box: Rectangle, color=GREEN, line_width=0.1
+    ):
+        """Render a box depicting the word."""
+        if not self.render_options.render_word_bbox:  # pragma: no cover
+            return
+        with canvas.do.save_state():
+            canvas.do.stroke_color(color).line_width(line_width).rect(
+                box.llx, box.lly, box.width, box.height, fill=0
+            )
+
+    def _debug_draw_space_bbox(
+        self, canvas: Canvas, box: Rectangle, color=DARKGREEN, line_width=0.1
+    ):
+        """Render a box depicting the space between two words."""
+        if not self.render_options.render_space_bbox:  # pragma: no cover
+            return
+        with canvas.do.save_state():
+            canvas.do.fill_color(color).line_width(line_width).rect(
+                box.llx, box.lly, box.width, box.height, fill=1
+            )
+
+    def _debug_draw_baseline(
+        self,
+        canvas: Canvas,
+        line_box: Rectangle,
+        baseline_lly,
+        color=MAGENTA,
+        line_width=0.25,
+    ):
+        """Render the text baseline."""
+        if not self.render_options.render_baseline:
+            return
+        with canvas.do.save_state():
+            canvas.do.stroke_color(color).line_width(line_width).line(
+                line_box.llx,
+                baseline_lly,
+                line_box.urx,
+                baseline_lly,
+            )

src/ocrmypdf/imageops.py

@@ -7,17 +7,9 @@ from __future__ import annotations
 
 import logging
 from math import floor, sqrt
-from typing import Optional
 
 from PIL import Image
 
-# While from __future__ import annotations, we use singledispatch here, which
-# does not support annotations. Disable check about using old-style typing
-# until Python 3.10, OR when drop singledispatch in ocrmypdf 15.
-# ruff: noqa: UP006
-# ruff: noqa: UP007
-
-
 log = logging.getLogger(__name__)
 
 
@@ -38,9 +30,9 @@ def _calculate_downsample(
     image_size: tuple[int, int],
     bytes_per_pixel: int,
     *,
-    max_size: Optional[tuple[int, int]] = None,
-    max_pixels: Optional[int] = None,
-    max_bytes: Optional[int] = None,
+    max_size: tuple[int, int] | None = None,
+    max_pixels: int | None = None,
+    max_bytes: int | None = None,
 ) -> tuple[int, int]:
     """Calculate image size required to downsample an image to fit limits.
 
@@ -98,9 +90,9 @@ def _calculate_downsample(
 def calculate_downsample(
     image: Image.Image,
     *,
-    max_size: Optional[tuple[int, int]] = None,
-    max_pixels: Optional[int] = None,
-    max_bytes: Optional[int] = None,
+    max_size: tuple[int, int] | None = None,
+    max_pixels: int | None = None,
+    max_bytes: int | None = None,
 ) -> tuple[int, int]:
     """Calculate image size required to downsample an image to fit limits.
 

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
@@ -71,15 +70,9 @@ def jpg_name(root: Path, xref: Xref) -> Path:
 
 
 def extract_image_filter(
-    image: Stream, xref: Xref, *args
+    image: Stream, xref: Xref
 ) -> tuple[PdfImage, tuple[Name, Object]] | None:
     """Determine if an image is extractable."""
-    if isinstance(image, Pdf):
-        # Support deprecated old function signature
-        # TODO Remove for v16 and drop *args from current function signature
-        image, xref = args[0], args[1]
-        warn("extract_image_filter: pdf, root parameters ignored", DeprecationWarning)
-
     if image.Subtype != Name.Image:
         return None
     if image.Length < 100:
@@ -161,6 +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:
@@ -376,7 +376,7 @@ def _produce_jbig2_images(
                 options.jbig2_threshold,
             )
 
-    def jbig2_single_args(root, groups: dict[int, list[XrefExt]]):
+    def jbig2_single_args(root: Path, groups: dict[int, list[XrefExt]]):
         for group, xref_exts in groups.items():
             prefix = f'group{group:08d}'
             # Second loop is to ensure multiple images per page are unpacked

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
@@ -20,18 +19,18 @@ 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
 from pikepdf import (
+    Matrix,
     Name,
     Object,
     Page,
     Pdf,
     PdfImage,
     PdfInlineImage,
-    PdfMatrix,
     Stream,
     UnsupportedImageTypeError,
     parse_content_stream,
@@ -209,7 +208,7 @@ def _interpret_contents(contentstream: Object, initial_shorthand=UNIT_SQUARE):
     CTM unchanged.
     """
     stack = []
-    ctm = PdfMatrix(initial_shorthand)
+    ctm = Matrix(initial_shorthand)
     xobject_settings: list[XobjectSettings] = []
     inline_images: list[InlineSettings] = []
     name_index = defaultdict(lambda: [])
@@ -240,7 +239,7 @@ def _interpret_contents(contentstream: Object, initial_shorthand=UNIT_SQUARE):
                 # to do. Just pretend nothing happened, keep calm and carry on.
                 warn("PDF graphics stack underflowed - PDF may be malformed")
         elif operator == 'cm':
-            ctm = PdfMatrix(operands) @ ctm
+            ctm = Matrix(operands) @ ctm
         elif operator == 'Do':
             image_name = operands[0]
             settings = XobjectSettings(
@@ -614,12 +613,12 @@ def _process_content_streams(
     ):
         # Set the CTM to the state it was when the "Do" operator was
         # encountered that is drawing this instance of the Form XObject
-        ctm = PdfMatrix(shorthand) if shorthand else PdfMatrix.identity()
+        ctm = Matrix(shorthand) if shorthand else Matrix()
 
         # A Form XObject may provide its own matrix to map form space into
         # user space. Get this if one exists
-        form_shorthand = container.get(Name.Matrix, PdfMatrix.identity())
-        form_matrix = PdfMatrix(form_shorthand)
+        form_shorthand = container.get(Name.Matrix, Matrix())
+        form_matrix = Matrix(form_shorthand)
 
         # Concatenate form matrix with CTM to ensure CTM is correct for
         # drawing this instance of the XObject
@@ -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_hocr__hocr__txt/hocr.bin

@@ -0,0 +1,177 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN"
+    "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
+<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
+ <head>
+  <title></title>
+  <meta http-equiv="Content-Type" content="text/html;charset=utf-8"/>
+  <meta name='ocr-system' content='tesseract 5.3.2' />
+  <meta name='ocr-capabilities' content='ocr_page ocr_carea ocr_par ocr_line ocrx_word ocrp_wconf'/>
+ </head>
+ <body>
+  <div class='ocr_page' id='page_1' title='image "/tmp/ocrmypdf.io.jcdzf4up/000001_ocr.png"; bbox 0 0 4000 2864; ppageno 0; scan_res 2400 2400'>
+   <div class='ocr_carea' id='block_1_1' title="bbox 251 146 2173 237">
+    <p class='ocr_par' id='par_1_1' lang='eng' title="bbox 251 146 2173 237">
+     <span class='ocr_line' id='line_1_1' title="bbox 251 146 2173 237; baseline -0.006 5; x_size 99.418808; x_descenders 9.4188042; x_ascenders 32">
+      <span class='ocrx_word' id='word_1_1' title='bbox 251 154 274 176; x_wconf 89'>i</span>
+      <span class='ocrx_word' id='word_1_2' title='bbox 1080 146 1152 237; x_wconf 89'>a</span>
+      <span class='ocrx_word' id='word_1_3' title='bbox 1254 153 1406 235; x_wconf 92'>la</span>
+      <span class='ocrx_word' id='word_1_4' title='bbox 1500 153 2173 235; x_wconf 95'>Waterman</span>
+     </span>
+    </p>
+   </div>
+   <div class='ocr_separator' id='block_1_2' title="bbox 135 202 2180 295"></div>
+   <div class='ocr_carea' id='block_1_3' title="bbox 145 414 2929 1221">
+    <p class='ocr_par' id='par_1_2' lang='eng' title="bbox 145 414 1154 516">
+     <span class='ocr_line' id='line_1_2' title="bbox 145 414 1154 516; baseline -0.005 -4; x_size 122.38636; x_descenders 24.386362; x_ascenders 40">
+      <span class='ocrx_word' id='word_1_5' title='bbox 145 414 211 512; x_wconf 60'>4</span>
+      <span class='ocrx_word' id='word_1_6' title='bbox 318 453 551 516; x_wconf 93'>ons</span>
+      <span class='ocrx_word' id='word_1_7' title='bbox 660 430 1154 512; x_wconf 91'>linzen</span>
+     </span>
+    </p>
+
+    <p class='ocr_par' id='par_1_3' lang='eng' title="bbox 146 568 1239 667">
+     <span class='ocr_line' id='line_1_3' title="bbox 146 568 1239 667; baseline -0.004 -16; x_size 99; x_descenders 17; x_ascenders 24">
+      <span class='ocrx_word' id='word_1_8' title='bbox 146 569 209 667; x_wconf 94'>3</span>
+      <span class='ocrx_word' id='word_1_9' title='bbox 323 568 729 652; x_wconf 83'>liter</span>
+      <span class='ocrx_word' id='word_1_10' title='bbox 821 569 1239 650; x_wconf 96'>water</span>
+     </span>
+    </p>
+
+    <p class='ocr_par' id='par_1_4' lang='eng' title="bbox 148 705 645 804">
+     <span class='ocr_line' id='line_1_4' title="bbox 148 705 645 804; baseline -0.016 -14; x_size 103; x_descenders 19; x_ascenders 27">
+      <span class='ocrx_word' id='word_1_11' title='bbox 148 706 211 804; x_wconf 88'>3</span>
+      <span class='ocrx_word' id='word_1_12' title='bbox 311 705 645 789; x_wconf 52'>uien</span>
+     </span>
+    </p>
+
+    <p class='ocr_par' id='par_1_5' lang='eng' title="bbox 147 832 1154 950">
+     <span class='ocr_line' id='line_1_5' title="bbox 147 832 1154 950; baseline -0.004 -27; x_size 118; x_descenders 28; x_ascenders 30">
+      <span class='ocrx_word' id='word_1_13' title='bbox 147 832 623 950; x_wconf 91'>bloem,</span>
+      <span class='ocrx_word' id='word_1_14' title='bbox 737 843 1154 924; x_wconf 91'>boter</span>
+     </span>
+    </p>
+
+    <p class='ocr_par' id='par_1_6' lang='eng' title="bbox 148 979 1241 1087">
+     <span class='ocr_line' id='line_1_6' title="bbox 148 979 1241 1087; baseline -0.005 -21; x_size 107; x_descenders 24; x_ascenders 24">
+      <span class='ocrx_word' id='word_1_15' title='bbox 148 983 215 1066; x_wconf 88'>2</span>
+      <span class='ocrx_word' id='word_1_16' title='bbox 312 983 807 1087; x_wconf 88'>kopjes</span>
+      <span class='ocrx_word' id='word_1_17' title='bbox 905 979 1241 1062; x_wconf 92'>melk</span>
+     </span>
+    </p>
+
+    <p class='ocr_par' id='par_1_7' lang='eng' title="bbox 154 1109 2929 1221">
+     <span class='ocr_line' id='line_1_7' title="bbox 154 1109 2929 1221; baseline -0.003 -21; x_size 112; x_descenders 28; x_ascenders 26">
+      <span class='ocrx_word' id='word_1_18' title='bbox 154 1117 791 1221; x_wconf 92'>laurier,</span>
+      <span class='ocrx_word' id='word_1_19' title='bbox 906 1111 1810 1219; x_wconf 90'>kruidnagel,</span>
+      <span class='ocrx_word' id='word_1_20' title='bbox 1927 1109 2490 1219; x_wconf 90'>kerrie,</span>
+      <span class='ocrx_word' id='word_1_21' title='bbox 2615 1110 2929 1195; x_wconf 91'>zout</span>
+     </span>
+    </p>
+   </div>
+   <div class='ocr_carea' id='block_1_4' title="bbox 147 1383 3706 2731">
+    <p class='ocr_par' id='par_1_8' lang='eng' title="bbox 147 1383 3706 2731">
+     <span class='ocr_line' id='line_1_8' title="bbox 149 1383 3612 1474; baseline -0.003 -2; x_size 107.01524; x_descenders 25.01524; x_ascenders 21">
+      <span class='ocrx_word' id='word_1_22' title='bbox 149 1395 303 1474; x_wconf 93'>De</span>
+      <span class='ocrx_word' id='word_1_23' title='bbox 411 1390 902 1473; x_wconf 80'>linzgen</span>
+      <span class='ocrx_word' id='word_1_24' title='bbox 996 1409 1497 1470; x_wconf 89'>wassen</span>
+      <span class='ocrx_word' id='word_1_25' title='bbox 1595 1409 1752 1470; x_wconf 88'>en</span>
+      <span class='ocrx_word' id='word_1_26' title='bbox 1853 1385 2166 1467; x_wconf 75'>in-l</span>
+      <span class='ocrx_word' id='word_1_27' title='bbox 2275 1383 2684 1466; x_wconf 93'>liter</span>
+      <span class='ocrx_word' id='word_1_28' title='bbox 2775 1383 3278 1464; x_wconf 91'>kokend</span>
+      <span class='ocrx_word' id='word_1_29' title='bbox 3368 1401 3612 1462; x_wconf 90'>wa-</span>
+     </span>
+     <span class='ocr_line' id='line_1_9' title="bbox 157 1516 3520 1632; baseline -0.004 -21; x_size 110; x_descenders 25; x_ascenders 25">
+      <span class='ocrx_word' id='word_1_30' title='bbox 157 1531 394 1611; x_wconf 94'>ter</span>
+      <span class='ocrx_word' id='word_1_31' title='bbox 495 1527 558 1609; x_wconf 93'>1</span>
+      <span class='ocrx_word' id='word_1_32' title='bbox 658 1530 903 1632; x_wconf 84'>dag</span>
+      <span class='ocrx_word' id='word_1_33' title='bbox 1002 1527 1415 1609; x_wconf 90'>laten</span>
+      <span class='ocrx_word' id='word_1_34' title='bbox 1505 1525 1979 1611; x_wconf 58'>weken,</span>
+      <span class='ocrx_word' id='word_1_35' title='bbox 2103 1521 2167 1603; x_wconf 96'>2</span>
+      <span class='ocrx_word' id='word_1_36' title='bbox 2275 1518 2683 1603; x_wconf 83'>liter</span>
+      <span class='ocrx_word' id='word_1_37' title='bbox 2777 1519 3194 1601; x_wconf 96'>water</span>
+      <span class='ocrx_word' id='word_1_38' title='bbox 3286 1516 3520 1599; x_wconf 89'>bij</span>
+     </span>
+     <span class='ocr_line' id='line_1_10' title="bbox 152 1651 3616 1767; baseline -0.004 -21; x_size 110; x_descenders 27; x_ascenders 23">
+      <span class='ocrx_word' id='word_1_39' title='bbox 152 1668 302 1747; x_wconf 92'>de</span>
+      <span class='ocrx_word' id='word_1_40' title='bbox 407 1662 905 1747; x_wconf 91'>linzen</span>
+      <span class='ocrx_word' id='word_1_41' title='bbox 996 1682 1559 1767; x_wconf 92'>voegen,</span>
+      <span class='ocrx_word' id='word_1_42' title='bbox 1680 1659 2176 1741; x_wconf 96'>zonder</span>
+      <span class='ocrx_word' id='word_1_43' title='bbox 2267 1655 2506 1737; x_wconf 96'>het</span>
+      <span class='ocrx_word' id='word_1_44' title='bbox 2606 1655 3023 1737; x_wconf 92'>water</span>
+      <span class='ocrx_word' id='word_1_45' title='bbox 3116 1651 3616 1735; x_wconf 91'>waarin</span>
+     </span>
+     <span class='ocr_line' id='line_1_11' title="bbox 153 1782 3704 1905; baseline -0.004 -20; x_size 117; x_descenders 23; x_ascenders 34">
+      <span class='ocrx_word' id='word_1_46' title='bbox 153 1824 305 1885; x_wconf 91'>ze</span>
+      <span class='ocrx_word' id='word_1_47' title='bbox 407 1800 979 1905; x_wconf 85'>geweekt</span>
+      <span class='ocrx_word' id='word_1_48' title='bbox 1089 1797 1412 1900; x_wconf 96'>zijn</span>
+      <span class='ocrx_word' id='word_1_49' title='bbox 1510 1796 1672 1878; x_wconf 96'>af</span>
+      <span class='ocrx_word' id='word_1_50' title='bbox 1770 1782 1914 1876; x_wconf 93'>te</span>
+      <span class='ocrx_word' id='word_1_51' title='bbox 2019 1792 2576 1899; x_wconf 54'>gieten,</span>
+      <span class='ocrx_word' id='word_1_52' title='bbox 2690 1790 2850 1874; x_wconf 93'>De</span>
+      <span class='ocrx_word' id='word_1_53' title='bbox 2948 1791 3357 1872; x_wconf 89'>helft</span>
+      <span class='ocrx_word' id='word_1_54' title='bbox 3452 1811 3704 1873; x_wconf 96'>van</span>
+     </span>
+     <span class='ocr_line' id='line_1_12' title="bbox 151 1928 3593 2035; baseline -0.003 -13; x_size 109; x_descenders 25; x_ascenders 25">
+      <span class='ocrx_word' id='word_1_55' title='bbox 151 1942 305 2024; x_wconf 92'>de</span>
+      <span class='ocrx_word' id='word_1_56' title='bbox 403 1940 735 2021; x_wconf 89'>uien</span>
+      <span class='ocrx_word' id='word_1_57' title='bbox 829 1938 1330 2022; x_wconf 91'>bakken</span>
+      <span class='ocrx_word' id='word_1_58' title='bbox 1419 1939 1659 2018; x_wconf 92'>met</span>
+      <span class='ocrx_word' id='word_1_59' title='bbox 1770 1933 2346 2016; x_wconf 91'>laurier</span>
+      <span class='ocrx_word' id='word_1_60' title='bbox 2447 1953 2603 2014; x_wconf 91'>en</span>
+      <span class='ocrx_word' id='word_1_61' title='bbox 2691 1928 3593 2035; x_wconf 63'>Kruidnagel.</span>
+     </span>
+     <span class='ocr_line' id='line_1_13' title="bbox 151 2067 3451 2180; baseline -0.004 -21; x_size 108; x_descenders 25; x_ascenders 24">
+      <span class='ocrx_word' id='word_1_62' title='bbox 151 2076 473 2159; x_wconf 92'>Alle</span>
+      <span class='ocrx_word' id='word_1_63' title='bbox 569 2076 965 2180; x_wconf 88'>uien,</span>
+      <span class='ocrx_word' id='word_1_64' title='bbox 1079 2072 1578 2156; x_wconf 90'>kerrie</span>
+      <span class='ocrx_word' id='word_1_65' title='bbox 1685 2092 1837 2153; x_wconf 93'>en</span>
+      <span class='ocrx_word' id='word_1_66' title='bbox 1938 2072 2254 2153; x_wconf 81'>zgout</span>
+      <span class='ocrx_word' id='word_1_67' title='bbox 2355 2068 2593 2172; x_wconf 43'>bij</span>
+      <span class='ocrx_word' id='word_1_68' title='bbox 2696 2071 2850 2150; x_wconf 91'>de</span>
+      <span class='ocrx_word' id='word_1_69' title='bbox 2957 2067 3451 2150; x_wconf 85'>linzen</span>
+     </span>
+     <span class='ocr_line' id='line_1_14' title="bbox 147 2205 3614 2318; baseline -0.003 -23; x_size 106; x_descenders 22; x_ascenders 25">
+      <span class='ocrx_word' id='word_1_70' title='bbox 147 2234 711 2318; x_wconf 88'>voegen,</span>
+      <span class='ocrx_word' id='word_1_71' title='bbox 826 2210 1234 2295; x_wconf 95'>Alles</span>
+      <span class='ocrx_word' id='word_1_72' title='bbox 1342 2232 1588 2295; x_wconf 95'>aan</span>
+      <span class='ocrx_word' id='word_1_73' title='bbox 1679 2212 1831 2291; x_wconf 96'>de</span>
+      <span class='ocrx_word' id='word_1_74' title='bbox 1928 2208 2263 2290; x_wconf 93'>kook</span>
+      <span class='ocrx_word' id='word_1_75' title='bbox 2355 2206 3000 2308; x_wconf 54'>brengen,</span>
+      <span class='ocrx_word' id='word_1_76' title='bbox 3117 2205 3367 2285; x_wconf 95'>Van</span>
+      <span class='ocrx_word' id='word_1_77' title='bbox 3462 2206 3614 2287; x_wconf 95'>de</span>
+     </span>
+     <span class='ocr_line' id='line_1_15' title="bbox 152 2341 3706 2447; baseline -0.003 -18; x_size 107; x_descenders 24; x_ascenders 24">
+      <span class='ocrx_word' id='word_1_78' title='bbox 152 2352 565 2434; x_wconf 91'>bloem</span>
+      <span class='ocrx_word' id='word_1_79' title='bbox 655 2351 896 2431; x_wconf 92'>met</span>
+      <span class='ocrx_word' id='word_1_80' title='bbox 997 2349 1669 2431; x_wconf 90'>boter</span>
+      <span class='ocrx_word' id='word_1_81' title='bbox 1514 2337 1683 2455; x_wconf 91'>en</span>
+      <span class='ocrx_word' id='word_1_82' title='bbox 1757 2343 2095 2426; x_wconf 88'>melk</span>
+      <span class='ocrx_word' id='word_1_83' title='bbox 2193 2364 2432 2427; x_wconf 93'>een</span>
+      <span class='ocrx_word' id='word_1_84' title='bbox 2527 2341 2935 2447; x_wconf 90'>papje</span>
+      <span class='ocrx_word' id='word_1_85' title='bbox 3029 2341 3453 2422; x_wconf 96'>maken</span>
+      <span class='ocrx_word' id='word_1_86' title='bbox 3549 2362 3706 2422; x_wconf 95'>en</span>
+     </span>
+     <span class='ocr_line' id='line_1_16' title="bbox 149 2477 3619 2586; baseline -0.003 -16; x_size 107; x_descenders 24; x_ascenders 23">
+      <span class='ocrx_word' id='word_1_87' title='bbox 149 2489 650 2571; x_wconf 86'>verder</span>
+      <span class='ocrx_word' id='word_1_88' title='bbox 750 2486 1330 2570; x_wconf 90'>afmaken</span>
+      <span class='ocrx_word' id='word_1_89' title='bbox 1420 2485 1660 2567; x_wconf 96'>met</span>
+      <span class='ocrx_word' id='word_1_90' title='bbox 1765 2485 1917 2566; x_wconf 93'>de</span>
+      <span class='ocrx_word' id='word_1_91' title='bbox 2025 2505 2409 2586; x_wconf 86'>soep,</span>
+      <span class='ocrx_word' id='word_1_92' title='bbox 2521 2479 2764 2564; x_wconf 96'>Als</span>
+      <span class='ocrx_word' id='word_1_93' title='bbox 2868 2480 3021 2561; x_wconf 92'>de</span>
+      <span class='ocrx_word' id='word_1_94' title='bbox 3127 2477 3619 2562; x_wconf 91'>linzen</span>
+     </span>
+     <span class='ocr_line' id='line_1_17' title="bbox 155 2619 2412 2731; baseline -0.005 -20; x_size 98; x_descenders 15; x_ascenders 23">
+      <span class='ocrx_word' id='word_1_95' title='bbox 155 2647 481 2731; x_wconf 35'>gfgaar</span>
+      <span class='ocrx_word' id='word_1_96' title='bbox 581 2624 909 2728; x_wconf 87'>Zijn</span>
+      <span class='ocrx_word' id='word_1_97' title='bbox 1005 2623 1153 2707; x_wconf 95'>is</span>
+      <span class='ocrx_word' id='word_1_98' title='bbox 1255 2624 1409 2706; x_wconf 93'>de</span>
+      <span class='ocrx_word' id='word_1_99' title='bbox 1522 2642 1840 2726; x_wconf 91'>soep</span>
+      <span class='ocrx_word' id='word_1_100' title='bbox 1929 2619 2412 2709; x_wconf 89'>klaar.</span>
+     </span>
+    </p>
+   </div>
+  </div>
+ </body>
+</html>

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

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

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

@@ -0,0 +1,89 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN"
+    "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
+<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
+ <head>
+  <title></title>
+  <meta http-equiv="Content-Type" content="text/html;charset=utf-8"/>
+  <meta name='ocr-system' content='tesseract 5.3.2' />
+  <meta name='ocr-capabilities' content='ocr_page ocr_carea ocr_par ocr_line ocrx_word ocrp_wconf'/>
+ </head>
+ <body>
+  <div class='ocr_page' id='page_1' title='image "/tmp/ocrmypdf.io.vh2to5iv/000001_ocr.png"; bbox 0 0 640 682; ppageno 0; scan_res 230 230'>
+   <div class='ocr_carea' id='block_1_1' title="bbox 365 15 429 29">
+    <p class='ocr_par' id='par_1_1' lang='eng' title="bbox 365 15 429 29">
+     <span class='ocr_line' id='line_1_1' title="bbox 365 15 429 29; baseline 0 0; x_size 19.238094; x_descenders 5.2380953; x_ascenders 4">
+      <span class='ocrx_word' id='word_1_1' title='bbox 365 15 429 29; x_wconf 92'>Tarnose</span>
+     </span>
+    </p>
+   </div>
+   <div class='ocr_photo' id='block_1_2' title="bbox 255 38 616 72"></div>
+   <div class='ocr_photo' id='block_1_3' title="bbox 273 38 349 57"></div>
+   <div class='ocr_carea' id='block_1_4' title="bbox 186 20 244 49">
+    <p class='ocr_par' id='par_1_2' lang='eng' title="bbox 186 20 345 49">
+     <span class='ocr_line' id='line_1_2' title="bbox 186 20 244 49; baseline -0.006 -10; x_size 20.454546; x_descenders 5.4545455; x_ascenders 5">
+      <span class='ocrx_word' id='word_1_2' title='bbox 186 20 244 49; x_wconf 92'>Bokale</span>
+      <span class='ocrx_word' id='word_1_3' title='bbox 299 28 345 46; x_wconf 42'>oa</span>
+     </span>
+    </p>
+   </div>
+   <div class='ocr_photo' id='block_1_5' title="bbox 64 38 186 72"></div>
+   <div class='ocr_carea' id='block_1_6' title="bbox 537 276 612 291">
+    <p class='ocr_par' id='par_1_3' lang='eng' title="bbox 537 276 612 291">
+     <span class='ocr_line' id='line_1_3' title="bbox 537 276 612 291; baseline 0 0; x_size 20.238094; x_descenders 5.2380953; x_ascenders 5">
+      <span class='ocrx_word' id='word_1_4' title='bbox 537 276 612 291; x_wconf 92'>Lehuntze</span>
+     </span>
+    </p>
+   </div>
+   <div class='ocr_photo' id='block_1_7' title="bbox 20 269 616 314"></div>
+   <div class='ocr_carea' id='block_1_8' title="bbox 480 323 550 341">
+    <p class='ocr_par' id='par_1_4' lang='eng' title="bbox 480 323 550 341">
+     <span class='ocr_line' id='line_1_4' title="bbox 480 323 550 341; baseline 0 -4; x_size 18; x_descenders 4; x_ascenders 4">
+      <span class='ocrx_word' id='word_1_5' title='bbox 480 323 550 341; x_wconf 91'>Mugerre</span>
+     </span>
+    </p>
+   </div>
+   <div class='ocr_photo' id='block_1_9' title="bbox 44 574 197 623"></div>
+   <div class='ocr_carea' id='block_1_10' title="bbox 204 542 603 574">
+    <p class='ocr_par' id='par_1_5' lang='eng' title="bbox 204 542 603 574">
+     <span class='ocr_line' id='line_1_5' title="bbox 204 542 603 574; baseline 0.018 -11; x_size 23.26087; x_descenders 5.2608695; x_ascenders 7">
+      <span class='ocrx_word' id='word_1_6' title='bbox 204 542 295 574; x_wconf 91'>Milafranga</span>
+      <span class='ocrx_word' id='word_1_7' title='bbox 439 552 603 569; x_wconf 90'>Komunikabideak</span>
+     </span>
+    </p>
+   </div>
+   <div class='ocr_carea' id='block_1_11' title="bbox 220 584 616 619">
+    <p class='ocr_par' id='par_1_6' lang='eng' title="bbox 220 584 616 625">
+     <span class='ocr_line' id='line_1_6' title="bbox 220 584 616 619; baseline -0.005 -1; x_size 43.666668; x_descenders 10.916667; x_ascenders 10.916667">
+      <span class='ocrx_word' id='word_1_8' title='bbox 220 585 404 619; x_wconf 2'>BAIONA</span>
+      <span class='ocrx_word' id='word_1_9' title='bbox 468 584 576 625; x_wconf 0'> zeiteninsiie</span>
+      <span class='ocrx_word' id='word_1_10' title='bbox 585 588 616 610; x_wconf 86'>—</span>
+     </span>
+    </p>
+   </div>
+   <div class='ocr_carea' id='block_1_12' title="bbox 393 623 598 634">
+    <p class='ocr_par' id='par_1_7' lang='eng' title="bbox 393 623 598 634">
+     <span class='ocr_line' id='line_1_7' title="bbox 393 623 598 634; baseline 0 0; x_size 22.75; x_descenders 5.5; x_ascenders 5.75">
+      <span class='ocrx_word' id='word_1_11' title='bbox 393 629 396 631; x_wconf 54'>7</span>
+      <span class='ocrx_word' id='word_1_12' title='bbox 470 623 539 634; x_wconf 24'>Trenbideak</span>
+      <span class='ocrx_word' id='word_1_13' title='bbox 550 628 598 630; x_wconf 24'>-----</span>
+     </span>
+    </p>
+   </div>
+   <div class='ocr_carea' id='block_1_13' title="bbox 81 633 613 667">
+    <p class='ocr_par' id='par_1_8' lang='eng' title="bbox 81 633 613 667">
+     <span class='ocr_line' id='line_1_8' title="bbox 81 633 613 667; baseline -0.002 -13; x_size 21; x_descenders 4; x_ascenders 7">
+      <span class='ocrx_word' id='word_1_14' title='bbox 81 637 111 653; x_wconf 0'>t\</span>
+      <span class='ocrx_word' id='word_1_15' title='bbox 123 633 201 663; x_wconf 22'>Basusarri</span>
+      <span class='ocrx_word' id='word_1_16' title='bbox 214 633 222 663; x_wconf 0'>—</span>
+      <span class='ocrx_word' id='word_1_17' title='bbox 230 647 325 656; x_wconf 0'>spmeans:20141004</span>
+      <span class='ocrx_word' id='word_1_18' title='bbox 373 633 415 667; x_wconf 42'>ae:</span>
+      <span class='ocrx_word' id='word_1_19' title='bbox 441 650 444 653; x_wconf 25'>.</span>
+      <span class='ocrx_word' id='word_1_20' title='bbox 521 649 544 657; x_wconf 17'>_</span>
+      <span class='ocrx_word' id='word_1_21' title='bbox 595 650 613 659; x_wconf 7'>~</span>
+     </span>
+    </p>
+   </div>
+  </div>
+ </body>
+</html>

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

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

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

@@ -0,0 +1,27 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN"
+    "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
+<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
+ <head>
+  <title></title>
+  <meta http-equiv="Content-Type" content="text/html;charset=utf-8"/>
+  <meta name='ocr-system' content='tesseract 5.3.2' />
+  <meta name='ocr-capabilities' content='ocr_page ocr_carea ocr_par ocr_line ocrx_word ocrp_wconf'/>
+ </head>
+ <body>
+  <div class='ocr_page' id='page_1' title='image "/tmp/ocrmypdf.io.vh2to5iv/000002_ocr.png"; bbox 0 0 400 50; ppageno 0; scan_res 200 200'>
+   <div class='ocr_carea' id='block_1_1' title="bbox 54 16 344 33">
+    <p class='ocr_par' id='par_1_1' lang='eng' title="bbox 54 16 344 33">
+     <span class='ocr_line' id='line_1_1' title="bbox 54 16 344 33; baseline 0 -4; x_size 25.75; x_descenders 5.5; x_ascenders 6.75">
+      <span class='ocrx_word' id='word_1_1' title='bbox 54 16 110 29; x_wconf 84'>Covfefe</span>
+      <span class='ocrx_word' id='word_1_2' title='bbox 115 17 127 29; x_wconf 95'>is</span>
+      <span class='ocrx_word' id='word_1_3' title='bbox 132 20 140 29; x_wconf 95'>a</span>
+      <span class='ocrx_word' id='word_1_4' title='bbox 145 16 212 33; x_wconf 85'>perfectly</span>
+      <span class='ocrx_word' id='word_1_5' title='bbox 217 16 296 29; x_wconf 85'>cromulent</span>
+      <span class='ocrx_word' id='word_1_6' title='bbox 300 16 344 29; x_wconf 95'>word.</span>
+     </span>
+    </p>
+   </div>
+  </div>
+ </body>
+</html>

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

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

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

@@ -0,0 +1,177 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN"
+    "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
+<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
+ <head>
+  <title></title>
+  <meta http-equiv="Content-Type" content="text/html;charset=utf-8"/>
+  <meta name='ocr-system' content='tesseract 5.3.2' />
+  <meta name='ocr-capabilities' content='ocr_page ocr_carea ocr_par ocr_line ocrx_word ocrp_wconf'/>
+ </head>
+ <body>
+  <div class='ocr_page' id='page_1' title='image "/tmp/ocrmypdf.io.vh2to5iv/000003_ocr.png"; bbox 0 0 4000 2864; ppageno 0; scan_res 1440 1440'>
+   <div class='ocr_carea' id='block_1_1' title="bbox 142 146 2173 258">
+    <p class='ocr_par' id='par_1_1' lang='eng' title="bbox 142 146 2173 258">
+     <span class='ocr_line' id='line_1_1' title="bbox 142 146 2173 258; baseline -0.004 -19; x_size 113; x_descenders 23; x_ascenders 32">
+      <span class='ocrx_word' id='word_1_1' title='bbox 142 154 982 258; x_wconf 90'>Linzensoep</span>
+      <span class='ocrx_word' id='word_1_2' title='bbox 1080 146 1152 237; x_wconf 96'>a</span>
+      <span class='ocrx_word' id='word_1_3' title='bbox 1254 153 1406 235; x_wconf 96'>la</span>
+      <span class='ocrx_word' id='word_1_4' title='bbox 1500 153 2173 235; x_wconf 96'>Waterman</span>
+     </span>
+    </p>
+   </div>
+   <div class='ocr_separator' id='block_1_2' title="bbox 136 253 2180 275"></div>
+   <div class='ocr_carea' id='block_1_3' title="bbox 145 414 2929 1221">
+    <p class='ocr_par' id='par_1_2' lang='eng' title="bbox 145 414 1154 516">
+     <span class='ocr_line' id='line_1_2' title="bbox 145 414 1154 516; baseline -0.005 -4; x_size 122.38636; x_descenders 24.386362; x_ascenders 40">
+      <span class='ocrx_word' id='word_1_5' title='bbox 145 414 211 512; x_wconf 60'>4</span>
+      <span class='ocrx_word' id='word_1_6' title='bbox 318 453 551 516; x_wconf 93'>ons</span>
+      <span class='ocrx_word' id='word_1_7' title='bbox 660 430 1154 512; x_wconf 91'>linzen</span>
+     </span>
+    </p>
+
+    <p class='ocr_par' id='par_1_3' lang='eng' title="bbox 146 568 1239 667">
+     <span class='ocr_line' id='line_1_3' title="bbox 146 568 1239 667; baseline -0.004 -16; x_size 99; x_descenders 17; x_ascenders 24">
+      <span class='ocrx_word' id='word_1_8' title='bbox 146 569 209 667; x_wconf 94'>3</span>
+      <span class='ocrx_word' id='word_1_9' title='bbox 323 568 729 652; x_wconf 83'>liter</span>
+      <span class='ocrx_word' id='word_1_10' title='bbox 821 569 1239 650; x_wconf 96'>water</span>
+     </span>
+    </p>
+
+    <p class='ocr_par' id='par_1_4' lang='eng' title="bbox 148 705 645 804">
+     <span class='ocr_line' id='line_1_4' title="bbox 148 705 645 804; baseline -0.016 -14; x_size 103; x_descenders 19; x_ascenders 27">
+      <span class='ocrx_word' id='word_1_11' title='bbox 148 706 211 804; x_wconf 88'>3</span>
+      <span class='ocrx_word' id='word_1_12' title='bbox 311 705 645 789; x_wconf 52'>uien</span>
+     </span>
+    </p>
+
+    <p class='ocr_par' id='par_1_5' lang='eng' title="bbox 147 832 1154 950">
+     <span class='ocr_line' id='line_1_5' title="bbox 147 832 1154 950; baseline -0.004 -27; x_size 118; x_descenders 28; x_ascenders 30">
+      <span class='ocrx_word' id='word_1_13' title='bbox 147 832 623 950; x_wconf 91'>bloem,</span>
+      <span class='ocrx_word' id='word_1_14' title='bbox 737 843 1154 924; x_wconf 91'>boter</span>
+     </span>
+    </p>
+
+    <p class='ocr_par' id='par_1_6' lang='eng' title="bbox 148 979 1241 1087">
+     <span class='ocr_line' id='line_1_6' title="bbox 148 979 1241 1087; baseline -0.005 -21; x_size 107; x_descenders 24; x_ascenders 24">
+      <span class='ocrx_word' id='word_1_15' title='bbox 148 983 215 1066; x_wconf 88'>2</span>
+      <span class='ocrx_word' id='word_1_16' title='bbox 312 983 807 1087; x_wconf 88'>kopjes</span>
+      <span class='ocrx_word' id='word_1_17' title='bbox 905 979 1241 1062; x_wconf 92'>melk</span>
+     </span>
+    </p>
+
+    <p class='ocr_par' id='par_1_7' lang='eng' title="bbox 154 1109 2929 1221">
+     <span class='ocr_line' id='line_1_7' title="bbox 154 1109 2929 1221; baseline -0.003 -21; x_size 112; x_descenders 28; x_ascenders 26">
+      <span class='ocrx_word' id='word_1_18' title='bbox 154 1117 791 1221; x_wconf 92'>laurier,</span>
+      <span class='ocrx_word' id='word_1_19' title='bbox 906 1111 1810 1219; x_wconf 90'>kruidnagel,</span>
+      <span class='ocrx_word' id='word_1_20' title='bbox 1927 1109 2490 1219; x_wconf 90'>kerrie,</span>
+      <span class='ocrx_word' id='word_1_21' title='bbox 2615 1110 2929 1195; x_wconf 91'>zout</span>
+     </span>
+    </p>
+   </div>
+   <div class='ocr_carea' id='block_1_4' title="bbox 147 1383 3706 2731">
+    <p class='ocr_par' id='par_1_8' lang='eng' title="bbox 147 1383 3706 2731">
+     <span class='ocr_line' id='line_1_8' title="bbox 149 1383 3612 1474; baseline -0.003 -2; x_size 107.01524; x_descenders 25.01524; x_ascenders 21">
+      <span class='ocrx_word' id='word_1_22' title='bbox 149 1395 303 1474; x_wconf 93'>De</span>
+      <span class='ocrx_word' id='word_1_23' title='bbox 411 1390 902 1473; x_wconf 80'>linzgen</span>
+      <span class='ocrx_word' id='word_1_24' title='bbox 996 1409 1497 1470; x_wconf 89'>wassen</span>
+      <span class='ocrx_word' id='word_1_25' title='bbox 1595 1409 1752 1470; x_wconf 88'>en</span>
+      <span class='ocrx_word' id='word_1_26' title='bbox 1853 1385 2166 1467; x_wconf 75'>in-l</span>
+      <span class='ocrx_word' id='word_1_27' title='bbox 2275 1383 2684 1466; x_wconf 93'>liter</span>
+      <span class='ocrx_word' id='word_1_28' title='bbox 2775 1383 3278 1464; x_wconf 91'>kokend</span>
+      <span class='ocrx_word' id='word_1_29' title='bbox 3368 1401 3612 1462; x_wconf 90'>wa-</span>
+     </span>
+     <span class='ocr_line' id='line_1_9' title="bbox 157 1516 3521 1632; baseline -0.004 -21; x_size 110; x_descenders 25; x_ascenders 25">
+      <span class='ocrx_word' id='word_1_30' title='bbox 157 1531 394 1611; x_wconf 93'>ter</span>
+      <span class='ocrx_word' id='word_1_31' title='bbox 495 1527 558 1609; x_wconf 94'>1</span>
+      <span class='ocrx_word' id='word_1_32' title='bbox 658 1530 903 1632; x_wconf 75'>dag</span>
+      <span class='ocrx_word' id='word_1_33' title='bbox 1002 1527 1415 1609; x_wconf 85'>laten</span>
+      <span class='ocrx_word' id='word_1_34' title='bbox 1505 1525 1979 1611; x_wconf 86'>weken,</span>
+      <span class='ocrx_word' id='word_1_35' title='bbox 2103 1521 2167 1603; x_wconf 96'>2</span>
+      <span class='ocrx_word' id='word_1_36' title='bbox 2275 1518 2683 1603; x_wconf 93'>liter</span>
+      <span class='ocrx_word' id='word_1_37' title='bbox 2777 1519 3194 1601; x_wconf 96'>water</span>
+      <span class='ocrx_word' id='word_1_38' title='bbox 3286 1516 3521 1620; x_wconf 93'>bij</span>
+     </span>
+     <span class='ocr_line' id='line_1_10' title="bbox 152 1651 3616 1767; baseline -0.004 -21; x_size 110; x_descenders 27; x_ascenders 23">
+      <span class='ocrx_word' id='word_1_39' title='bbox 152 1668 302 1747; x_wconf 92'>de</span>
+      <span class='ocrx_word' id='word_1_40' title='bbox 407 1662 905 1747; x_wconf 91'>linzen</span>
+      <span class='ocrx_word' id='word_1_41' title='bbox 996 1682 1559 1767; x_wconf 92'>voegen,</span>
+      <span class='ocrx_word' id='word_1_42' title='bbox 1680 1659 2176 1741; x_wconf 96'>zonder</span>
+      <span class='ocrx_word' id='word_1_43' title='bbox 2267 1655 2506 1737; x_wconf 96'>het</span>
+      <span class='ocrx_word' id='word_1_44' title='bbox 2606 1655 3023 1737; x_wconf 92'>water</span>
+      <span class='ocrx_word' id='word_1_45' title='bbox 3116 1651 3616 1735; x_wconf 91'>waarin</span>
+     </span>
+     <span class='ocr_line' id='line_1_11' title="bbox 153 1782 3704 1905; baseline -0.004 -20; x_size 117; x_descenders 23; x_ascenders 34">
+      <span class='ocrx_word' id='word_1_46' title='bbox 153 1824 305 1885; x_wconf 91'>ze</span>
+      <span class='ocrx_word' id='word_1_47' title='bbox 407 1800 979 1905; x_wconf 85'>geweekt</span>
+      <span class='ocrx_word' id='word_1_48' title='bbox 1089 1797 1412 1900; x_wconf 96'>zijn</span>
+      <span class='ocrx_word' id='word_1_49' title='bbox 1510 1796 1672 1878; x_wconf 96'>af</span>
+      <span class='ocrx_word' id='word_1_50' title='bbox 1770 1782 1914 1876; x_wconf 93'>te</span>
+      <span class='ocrx_word' id='word_1_51' title='bbox 2019 1792 2576 1899; x_wconf 54'>gieten,</span>
+      <span class='ocrx_word' id='word_1_52' title='bbox 2690 1790 2850 1874; x_wconf 93'>De</span>
+      <span class='ocrx_word' id='word_1_53' title='bbox 2948 1791 3357 1872; x_wconf 89'>helft</span>
+      <span class='ocrx_word' id='word_1_54' title='bbox 3452 1811 3704 1873; x_wconf 96'>van</span>
+     </span>
+     <span class='ocr_line' id='line_1_12' title="bbox 151 1928 3593 2035; baseline -0.003 -13; x_size 109; x_descenders 25; x_ascenders 25">
+      <span class='ocrx_word' id='word_1_55' title='bbox 151 1942 305 2024; x_wconf 92'>de</span>
+      <span class='ocrx_word' id='word_1_56' title='bbox 403 1940 735 2021; x_wconf 89'>uien</span>
+      <span class='ocrx_word' id='word_1_57' title='bbox 829 1938 1330 2022; x_wconf 91'>bakken</span>
+      <span class='ocrx_word' id='word_1_58' title='bbox 1419 1939 1659 2018; x_wconf 92'>met</span>
+      <span class='ocrx_word' id='word_1_59' title='bbox 1770 1933 2346 2016; x_wconf 91'>laurier</span>
+      <span class='ocrx_word' id='word_1_60' title='bbox 2447 1953 2603 2014; x_wconf 91'>en</span>
+      <span class='ocrx_word' id='word_1_61' title='bbox 2691 1928 3593 2035; x_wconf 63'>Kruidnagel.</span>
+     </span>
+     <span class='ocr_line' id='line_1_13' title="bbox 151 2067 3451 2180; baseline -0.004 -21; x_size 108; x_descenders 25; x_ascenders 24">
+      <span class='ocrx_word' id='word_1_62' title='bbox 151 2076 473 2159; x_wconf 92'>Alle</span>
+      <span class='ocrx_word' id='word_1_63' title='bbox 569 2076 965 2180; x_wconf 88'>uien,</span>
+      <span class='ocrx_word' id='word_1_64' title='bbox 1079 2072 1578 2156; x_wconf 90'>kerrie</span>
+      <span class='ocrx_word' id='word_1_65' title='bbox 1685 2092 1837 2153; x_wconf 93'>en</span>
+      <span class='ocrx_word' id='word_1_66' title='bbox 1938 2072 2254 2153; x_wconf 81'>zgout</span>
+      <span class='ocrx_word' id='word_1_67' title='bbox 2355 2068 2593 2172; x_wconf 43'>bij</span>
+      <span class='ocrx_word' id='word_1_68' title='bbox 2696 2071 2850 2150; x_wconf 91'>de</span>
+      <span class='ocrx_word' id='word_1_69' title='bbox 2957 2067 3451 2150; x_wconf 85'>linzen</span>
+     </span>
+     <span class='ocr_line' id='line_1_14' title="bbox 147 2205 3614 2318; baseline -0.003 -23; x_size 106; x_descenders 22; x_ascenders 25">
+      <span class='ocrx_word' id='word_1_70' title='bbox 147 2234 711 2318; x_wconf 88'>voegen,</span>
+      <span class='ocrx_word' id='word_1_71' title='bbox 826 2210 1234 2295; x_wconf 95'>Alles</span>
+      <span class='ocrx_word' id='word_1_72' title='bbox 1342 2232 1588 2295; x_wconf 95'>aan</span>
+      <span class='ocrx_word' id='word_1_73' title='bbox 1679 2212 1831 2291; x_wconf 96'>de</span>
+      <span class='ocrx_word' id='word_1_74' title='bbox 1928 2208 2263 2290; x_wconf 93'>kook</span>
+      <span class='ocrx_word' id='word_1_75' title='bbox 2355 2206 3000 2308; x_wconf 54'>brengen,</span>
+      <span class='ocrx_word' id='word_1_76' title='bbox 3117 2205 3367 2285; x_wconf 95'>Van</span>
+      <span class='ocrx_word' id='word_1_77' title='bbox 3462 2206 3614 2287; x_wconf 95'>de</span>
+     </span>
+     <span class='ocr_line' id='line_1_15' title="bbox 152 2341 3706 2447; baseline -0.003 -18; x_size 107; x_descenders 24; x_ascenders 24">
+      <span class='ocrx_word' id='word_1_78' title='bbox 152 2352 565 2434; x_wconf 91'>bloem</span>
+      <span class='ocrx_word' id='word_1_79' title='bbox 655 2351 896 2431; x_wconf 92'>met</span>
+      <span class='ocrx_word' id='word_1_80' title='bbox 997 2349 1669 2431; x_wconf 90'>boter</span>
+      <span class='ocrx_word' id='word_1_81' title='bbox 1514 2337 1683 2455; x_wconf 91'>en</span>
+      <span class='ocrx_word' id='word_1_82' title='bbox 1757 2343 2095 2426; x_wconf 88'>melk</span>
+      <span class='ocrx_word' id='word_1_83' title='bbox 2193 2364 2432 2427; x_wconf 93'>een</span>
+      <span class='ocrx_word' id='word_1_84' title='bbox 2527 2341 2935 2447; x_wconf 90'>papje</span>
+      <span class='ocrx_word' id='word_1_85' title='bbox 3029 2341 3453 2422; x_wconf 96'>maken</span>
+      <span class='ocrx_word' id='word_1_86' title='bbox 3549 2362 3706 2422; x_wconf 95'>en</span>
+     </span>
+     <span class='ocr_line' id='line_1_16' title="bbox 149 2477 3619 2586; baseline -0.003 -16; x_size 107; x_descenders 24; x_ascenders 23">
+      <span class='ocrx_word' id='word_1_87' title='bbox 149 2489 650 2571; x_wconf 86'>verder</span>
+      <span class='ocrx_word' id='word_1_88' title='bbox 750 2486 1330 2570; x_wconf 90'>afmaken</span>
+      <span class='ocrx_word' id='word_1_89' title='bbox 1420 2485 1660 2567; x_wconf 96'>met</span>
+      <span class='ocrx_word' id='word_1_90' title='bbox 1765 2485 1917 2566; x_wconf 93'>de</span>
+      <span class='ocrx_word' id='word_1_91' title='bbox 2025 2505 2409 2586; x_wconf 86'>soep,</span>
+      <span class='ocrx_word' id='word_1_92' title='bbox 2521 2479 2764 2564; x_wconf 96'>Als</span>
+      <span class='ocrx_word' id='word_1_93' title='bbox 2868 2480 3021 2561; x_wconf 92'>de</span>
+      <span class='ocrx_word' id='word_1_94' title='bbox 3127 2477 3619 2562; x_wconf 91'>linzen</span>
+     </span>
+     <span class='ocr_line' id='line_1_17' title="bbox 155 2619 2412 2731; baseline -0.005 -20; x_size 98; x_descenders 15; x_ascenders 23">
+      <span class='ocrx_word' id='word_1_95' title='bbox 155 2647 481 2731; x_wconf 35'>gfgaar</span>
+      <span class='ocrx_word' id='word_1_96' title='bbox 581 2624 909 2728; x_wconf 87'>Zijn</span>
+      <span class='ocrx_word' id='word_1_97' title='bbox 1005 2623 1153 2707; x_wconf 95'>is</span>
+      <span class='ocrx_word' id='word_1_98' title='bbox 1255 2624 1409 2706; x_wconf 93'>de</span>
+      <span class='ocrx_word' id='word_1_99' title='bbox 1522 2642 1840 2726; x_wconf 91'>soep</span>
+      <span class='ocrx_word' id='word_1_100' title='bbox 1929 2619 2412 2709; x_wconf 89'>klaar.</span>
+     </span>
+    </p>
+   </div>
+  </div>
+ </body>
+</html>

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

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

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

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

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

@@ -9,7 +9,7 @@
   <meta name='ocr-capabilities' content='ocr_page ocr_carea ocr_par ocr_line ocrx_word ocrp_wconf'/>
  </head>
  <body>
-  <div class='ocr_page' id='page_1' title='image "/tmp/ocrmypdf.io.q0nk4qy2/000001_ocr.png"; bbox 0 0 2550 3300; ppageno 0; scan_res 300 300'>
+  <div class='ocr_page' id='page_1' title='image "/tmp/ocrmypdf.io.g296cpyi/000001_ocr.png"; bbox 0 0 2550 3300; ppageno 0; scan_res 300 300'>
    <div class='ocr_carea' id='block_1_1' title="bbox 582 131 1968 303">
     <p class='ocr_par' id='par_1_1' lang='eng' title="bbox 582 131 1968 303">
      <span class='ocr_header' id='line_1_1' title="bbox 882 131 1657 217; baseline 0.001 -17; x_size 85; x_descenders 16; x_ascenders 19">

tests/cache/cardinal/__-l__eng__000002_ocr.png__000002_ocr_hocr__hocr__txt/hocr.bin

@@ -9,7 +9,7 @@
   <meta name='ocr-capabilities' content='ocr_page ocr_carea ocr_par ocr_line ocrx_word ocrp_wconf'/>
  </head>
  <body>
-  <div class='ocr_page' id='page_1' title='image "/tmp/ocrmypdf.io.q0nk4qy2/000002_ocr.png"; bbox 0 0 2550 3300; ppageno 0; scan_res 300 300'>
+  <div class='ocr_page' id='page_1' title='image "/tmp/ocrmypdf.io.91dzclia/000002_ocr.png"; bbox 0 0 2550 3300; ppageno 0; scan_res 300 300'>
    <div class='ocr_carea' id='block_1_1' title="bbox 582 131 1968 303">
     <p class='ocr_par' id='par_1_1' lang='eng' title="bbox 582 131 1968 303">
      <span class='ocr_header' id='line_1_1' title="bbox 882 131 1657 217; baseline 0.001 -17; x_size 85; x_descenders 16; x_ascenders 19">

tests/cache/cardinal/__-l__eng__000003_ocr.png__000003_ocr_hocr__hocr__txt/hocr.bin

@@ -9,7 +9,7 @@
   <meta name='ocr-capabilities' content='ocr_page ocr_carea ocr_par ocr_line ocrx_word ocrp_wconf'/>
  </head>
  <body>
-  <div class='ocr_page' id='page_1' title='image "/tmp/ocrmypdf.io.q0nk4qy2/000003_ocr.png"; bbox 0 0 2550 3300; ppageno 0; scan_res 300 300'>
+  <div class='ocr_page' id='page_1' title='image "/tmp/ocrmypdf.io.91dzclia/000003_ocr.png"; bbox 0 0 2550 3300; ppageno 0; scan_res 300 300'>
    <div class='ocr_carea' id='block_1_1' title="bbox 582 131 1968 303">
     <p class='ocr_par' id='par_1_1' lang='eng' title="bbox 582 131 1968 303">
      <span class='ocr_header' id='line_1_1' title="bbox 882 131 1657 217; baseline 0.001 -17; x_size 85; x_descenders 16; x_ascenders 19">

tests/cache/cardinal/__-l__eng__000004_ocr.png__000004_ocr_hocr__hocr__txt/hocr.bin

@@ -9,7 +9,7 @@
   <meta name='ocr-capabilities' content='ocr_page ocr_carea ocr_par ocr_line ocrx_word ocrp_wconf'/>
  </head>
  <body>
-  <div class='ocr_page' id='page_1' title='image "/tmp/ocrmypdf.io.q0nk4qy2/000004_ocr.png"; bbox 0 0 2550 3300; ppageno 0; scan_res 300 300'>
+  <div class='ocr_page' id='page_1' title='image "/tmp/ocrmypdf.io.91dzclia/000004_ocr.png"; bbox 0 0 2550 3300; ppageno 0; scan_res 300 300'>
    <div class='ocr_carea' id='block_1_1' title="bbox 582 131 1968 303">
     <p class='ocr_par' id='par_1_1' lang='eng' title="bbox 582 131 1968 303">
      <span class='ocr_header' id='line_1_1' title="bbox 882 131 1657 217; baseline 0.001 -17; x_size 85; x_descenders 16; x_ascenders 19">

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

@@ -9,7 +9,7 @@
   <meta name='ocr-capabilities' content='ocr_page ocr_carea ocr_par ocr_line ocrx_word ocrp_wconf'/>
  </head>
  <body>
-  <div class='ocr_page' id='page_1' title='image "/tmp/ocrmypdf.io.zopxh6db/000001_ocr.png"; bbox 0 0 2550 3300; ppageno 0; scan_res 300 300'>
+  <div class='ocr_page' id='page_1' title='image "/tmp/ocrmypdf.io.bgz1p10r/000001_ocr.png"; bbox 0 0 2550 3300; ppageno 0; scan_res 300 300'>
    <div class='ocr_carea' id='block_1_1' title="bbox 582 131 1968 303">
     <p class='ocr_par' id='par_1_1' lang='eng' title="bbox 582 131 1968 303">
      <span class='ocr_header' id='line_1_1' title="bbox 882 131 1657 217; baseline 0.001 -17; x_size 85; x_descenders 16; x_ascenders 19">

tests/cache/francais/__-l__deu__000001_ocr.png__000001_ocr_hocr__hocr__txt/hocr.bin

@@ -0,0 +1,104 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN"
+    "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
+<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
+ <head>
+  <title></title>
+  <meta http-equiv="Content-Type" content="text/html;charset=utf-8"/>
+  <meta name='ocr-system' content='tesseract 5.3.2' />
+  <meta name='ocr-capabilities' content='ocr_page ocr_carea ocr_par ocr_line ocrx_word ocrp_wconf'/>
+ </head>
+ <body>
+  <div class='ocr_page' id='page_1' title='image "/tmp/ocrmypdf.io.9pz7mnez/000001_ocr.png"; bbox 0 0 900 900; ppageno 0; scan_res 300 300'>
+   <div class='ocr_carea' id='block_1_1' title="bbox 180 159 760 740">
+    <p class='ocr_par' id='par_1_1' lang='deu' title="bbox 180 159 760 740">
+     <span class='ocr_line' id='line_1_1' title="bbox 182 159 721 198; baseline 0 -8; x_size 39; x_descenders 8; x_ascenders 10">
+      <span class='ocrx_word' id='word_1_1' title='bbox 182 160 292 190; x_wconf 92'>Portez</span>
+      <span class='ocrx_word' id='word_1_2' title='bbox 307 169 344 190; x_wconf 93'>ce</span>
+      <span class='ocrx_word' id='word_1_3' title='bbox 357 160 449 190; x_wconf 92'>vieux</span>
+      <span class='ocrx_word' id='word_1_4' title='bbox 462 159 583 197; x_wconf 91'>whisky</span>
+      <span class='ocrx_word' id='word_1_5' title='bbox 595 169 633 190; x_wconf 92'>au</span>
+      <span class='ocrx_word' id='word_1_6' title='bbox 646 160 721 198; x_wconf 87'>juge</span>
+     </span>
+     <span class='ocr_line' id='line_1_2' title="bbox 181 209 640 247; baseline 0 -7; x_size 38; x_descenders 7; x_ascenders 10">
+      <span class='ocrx_word' id='word_1_7' title='bbox 181 209 276 240; x_wconf 95'>blond</span>
+      <span class='ocrx_word' id='word_1_8' title='bbox 293 210 343 247; x_wconf 93'>qui</span>
+      <span class='ocrx_word' id='word_1_9' title='bbox 358 210 448 240; x_wconf 91'>fume</span>
+      <span class='ocrx_word' id='word_1_10' title='bbox 463 219 516 240; x_wconf 96'>sur</span>
+      <span class='ocrx_word' id='word_1_11' title='bbox 529 219 587 240; x_wconf 96'>son</span>
+      <span class='ocrx_word' id='word_1_12' title='bbox 602 209 640 240; x_wconf 89'>Ile</span>
+     </span>
+     <span class='ocr_line' id='line_1_3' title="bbox 181 259 676 295; baseline 0 -5; x_size 36; x_descenders 5; x_ascenders 10">
+      <span class='ocrx_word' id='word_1_13' title='bbox 181 260 357 295; x_wconf 89'>interieure,</span>
+      <span class='ocrx_word' id='word_1_14' title='bbox 372 260 387 290; x_wconf 83'>a</span>
+      <span class='ocrx_word' id='word_1_15' title='bbox 404 260 478 290; x_wconf 61'>cöte</span>
+      <span class='ocrx_word' id='word_1_16' title='bbox 493 259 534 290; x_wconf 93'>de</span>
+      <span class='ocrx_word' id='word_1_17' title='bbox 551 259 676 290; x_wconf 81'>l&#39;alcöve</span>
+     </span>
+     <span class='ocr_line' id='line_1_4' title="bbox 180 309 613 345; baseline 0 -5; x_size 36; x_descenders 5; x_ascenders 10">
+      <span class='ocrx_word' id='word_1_18' title='bbox 180 309 305 345; x_wconf 92'>ovoide,</span>
+      <span class='ocrx_word' id='word_1_19' title='bbox 321 310 362 340; x_wconf 38'>oU</span>
+      <span class='ocrx_word' id='word_1_20' title='bbox 380 309 423 340; x_wconf 92'>les</span>
+      <span class='ocrx_word' id='word_1_21' title='bbox 440 309 562 340; x_wconf 92'>büches</span>
+      <span class='ocrx_word' id='word_1_22' title='bbox 577 319 613 340; x_wconf 96'>se</span>
+     </span>
+     <span class='ocr_line' id='line_1_5' title="bbox 180 359 693 397; baseline 0 -7; x_size 36; x_descenders 5; x_ascenders 10">
+      <span class='ocrx_word' id='word_1_23' title='bbox 180 362 375 390; x_wconf 92'>consument</span>
+      <span class='ocrx_word' id='word_1_24' title='bbox 389 359 469 390; x_wconf 92'>dans</span>
+      <span class='ocrx_word' id='word_1_25' title='bbox 485 359 575 395; x_wconf 86'>l&#39;ätre,</span>
+      <span class='ocrx_word' id='word_1_26' title='bbox 591 369 628 390; x_wconf 96'>ce</span>
+      <span class='ocrx_word' id='word_1_27' title='bbox 643 360 693 397; x_wconf 96'>qui</span>
+     </span>
+     <span class='ocr_line' id='line_1_6' title="bbox 181 409 617 447; baseline 0 -7; x_size 38; x_descenders 7; x_ascenders 10">
+      <span class='ocrx_word' id='word_1_28' title='bbox 181 409 217 440; x_wconf 49'>ui</span>
+      <span class='ocrx_word' id='word_1_29' title='bbox 234 412 359 447; x_wconf 91'>permet</span>
+      <span class='ocrx_word' id='word_1_30' title='bbox 373 409 414 440; x_wconf 93'>de</span>
+      <span class='ocrx_word' id='word_1_31' title='bbox 430 419 548 447; x_wconf 90'>penser</span>
+      <span class='ocrx_word' id='word_1_32' title='bbox 556 405 568 451; x_wconf 73'>&amp;</span>
+      <span class='ocrx_word' id='word_1_33' title='bbox 594 409 617 440; x_wconf 96'>la</span>
+     </span>
+     <span class='ocr_line' id='line_1_7' title="bbox 180 459 680 498; baseline 0 -8; x_size 39; x_descenders 8; x_ascenders 10">
+      <span class='ocrx_word' id='word_1_34' title='bbox 180 460 402 498; x_wconf 79'>caenogenese</span>
+      <span class='ocrx_word' id='word_1_35' title='bbox 417 459 458 490; x_wconf 93'>de</span>
+      <span class='ocrx_word' id='word_1_36' title='bbox 475 459 557 490; x_wconf 42'>|&#39;etre</span>
+      <span class='ocrx_word' id='word_1_37' title='bbox 572 459 653 490; x_wconf 96'>dont</span>
+      <span class='ocrx_word' id='word_1_38' title='bbox 668 459 680 490; x_wconf 94'>il</span>
+     </span>
+     <span class='ocr_line' id='line_1_8' title="bbox 180 509 646 547; baseline 0 -7; x_size 38; x_descenders 7; x_ascenders 10">
+      <span class='ocrx_word' id='word_1_39' title='bbox 180 512 231 540; x_wconf 96'>est</span>
+      <span class='ocrx_word' id='word_1_40' title='bbox 245 510 396 547; x_wconf 96'>question</span>
+      <span class='ocrx_word' id='word_1_41' title='bbox 412 509 492 540; x_wconf 96'>dans</span>
+      <span class='ocrx_word' id='word_1_42' title='bbox 509 509 531 540; x_wconf 95'>la</span>
+      <span class='ocrx_word' id='word_1_43' title='bbox 548 519 646 540; x_wconf 96'>cause</span>
+     </span>
+     <span class='ocr_line' id='line_1_9' title="bbox 180 559 736 598; baseline 0 -8; x_size 36; x_descenders 5; x_ascenders 10">
+      <span class='ocrx_word' id='word_1_44' title='bbox 180 559 328 598; x_wconf 87'>ambigu&amp;</span>
+      <span class='ocrx_word' id='word_1_45' title='bbox 343 559 510 590; x_wconf 91'>entendue</span>
+      <span class='ocrx_word' id='word_1_46' title='bbox 525 560 541 590; x_wconf 93'>a</span>
+      <span class='ocrx_word' id='word_1_47' title='bbox 559 560 641 597; x_wconf 61'>MoY,</span>
+      <span class='ocrx_word' id='word_1_48' title='bbox 657 559 736 590; x_wconf 96'>dans</span>
+     </span>
+     <span class='ocr_line' id='line_1_10' title="bbox 181 609 719 647; baseline 0 -7; x_size 38; x_descenders 7; x_ascenders 10">
+      <span class='ocrx_word' id='word_1_49' title='bbox 181 619 221 640; x_wconf 93'>un</span>
+      <span class='ocrx_word' id='word_1_50' title='bbox 237 609 452 647; x_wconf 92'>capharnaüm</span>
+      <span class='ocrx_word' id='word_1_51' title='bbox 469 610 528 647; x_wconf 93'>qui,</span>
+      <span class='ocrx_word' id='word_1_52' title='bbox 545 609 719 647; x_wconf 91'>pense-t-il,</span>
+     </span>
+     <span class='ocr_line' id='line_1_11' title="bbox 180 659 760 697; baseline 0 -7; x_size 38; x_descenders 7; x_ascenders 10">
+      <span class='ocrx_word' id='word_1_53' title='bbox 180 659 319 690; x_wconf 90'>diminue</span>
+      <span class='ocrx_word' id='word_1_54' title='bbox 334 660 369 697; x_wconf 95'>ca</span>
+      <span class='ocrx_word' id='word_1_55' title='bbox 385 662 418 690; x_wconf 95'>et</span>
+      <span class='ocrx_word' id='word_1_56' title='bbox 434 659 457 690; x_wconf 94'>la</span>
+      <span class='ocrx_word' id='word_1_57' title='bbox 474 659 497 690; x_wconf 92'>la</span>
+      <span class='ocrx_word' id='word_1_58' title='bbox 514 659 630 697; x_wconf 75'>qualit&amp;</span>
+      <span class='ocrx_word' id='word_1_59' title='bbox 645 659 686 690; x_wconf 96'>de</span>
+      <span class='ocrx_word' id='word_1_60' title='bbox 701 669 760 690; x_wconf 96'>son</span>
+     </span>
+     <span class='ocr_line' id='line_1_12' title="bbox 180 719 300 740; baseline 0 0; x_size 39.328766; x_descenders 7.3287673; x_ascenders 10.5">
+      <span class='ocrx_word' id='word_1_61' title='bbox 180 719 300 740; x_wconf 66'>ceuvre.</span>
+     </span>
+    </p>
+   </div>
+  </div>
+ </body>
+</html>

tests/cache/francais/__-l__deu__000001_ocr.png__000001_ocr_hocr__hocr__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_hocr__hocr__txt/hocr.bin

@@ -0,0 +1,190 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN"
+    "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
+<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
+ <head>
+  <title></title>
+  <meta http-equiv="Content-Type" content="text/html;charset=utf-8"/>
+  <meta name='ocr-system' content='tesseract 5.3.2' />
+  <meta name='ocr-capabilities' content='ocr_page ocr_carea ocr_par ocr_line ocrx_word ocrp_wconf'/>
+ </head>
+ <body>
+  <div class='ocr_page' id='page_1' title='image "/tmp/ocrmypdf.io.2ahiyq00/000001_ocr.png"; bbox 0 0 3992 1667; ppageno 0; scan_res 400 400'>
+   <div class='ocr_separator' id='block_1_1' title="bbox 185 50 3278 54"></div>
+   <div class='ocr_separator' id='block_1_2' title="bbox 185 249 3278 254"></div>
+   <div class='ocr_separator' id='block_1_3' title="bbox 185 446 1721 450"></div>
+   <div class='ocr_separator' id='block_1_4' title="bbox 184 642 846 646"></div>
+   <div class='ocr_separator' id='block_1_5' title="bbox 184 842 966 846"></div>
+   <div class='ocr_separator' id='block_1_6' title="bbox 204 50 209 1257"></div>
+   <div class='ocr_separator' id='block_1_7' title="bbox 2937 446 3278 450"></div>
+   <div class='ocr_separator' id='block_1_8' title="bbox 1183 642 2438 646"></div>
+   <div class='ocr_separator' id='block_1_9' title="bbox 2930 642 3278 646"></div>
+   <div class='ocr_separator' id='block_1_10' title="bbox 1907 842 3278 846"></div>
+   <div class='ocr_separator' id='block_1_11' title="bbox 448 1037 2904 1042"></div>
+   <div class='ocr_separator' id='block_1_12' title="bbox 209 1220 1765 1261"></div>
+   <div class='ocr_separator' id='block_1_13' title="bbox 1725 1133 2047 1151"></div>
+   <div class='ocr_separator' id='block_1_14' title="bbox 1755 1229 3279 1243"></div>
+   <div class='ocr_carea' id='block_1_15' title="bbox 45 36 3110 1619">
+    <p class='ocr_par' id='par_1_1' lang='eng' title="bbox 45 36 3110 1619">
+     <span class='ocr_line' id='line_1_1' title="bbox 68 36 153 72; baseline 0 0; x_size 43.868851; x_descenders 7.8688521; x_ascenders 11.409836">
+      <span class='ocrx_word' id='word_1_1' title='bbox 68 36 153 72; x_wconf 95'>600</span>
+     </span>
+     <span class='ocr_line' id='line_1_2' title="bbox 69 66 388 446; baseline -0.006 -178; x_size 43.868851; x_descenders 7.8688521; x_ascenders 11.409836">
+      <span class='ocrx_word' id='word_1_2' title='bbox 69 232 153 268; x_wconf 96'>500</span>
+      <span class='ocrx_word' id='word_1_3' title='bbox 262 66 388 446; x_wconf 29'>.</span>
+     </span>
+     <span class='ocr_line' id='line_1_3' title="bbox 63 388 2969 642; baseline -0.009 -173.963; x_size 62.52; x_descenders 11.52; x_ascenders 15">
+      <span class='ocrx_word' id='word_1_4' title='bbox 63 413 158 484; x_wconf 96'>400</span>
+      <span class='ocrx_word' id='word_1_5' title='bbox 355 400 657 642; x_wconf 46'>_</span>
+      <span class='ocrx_word' id='word_1_6' title='bbox 2164 392 2374 463; x_wconf 28'>EB</span>
+      <span class='ocrx_word' id='word_1_7' title='bbox 2731 388 2788 458; x_wconf 23'>fp</span>
+      <span class='ocrx_word' id='word_1_8' title='bbox 2814 450 2969 627; x_wconf 0'>ys</span>
+     </span>
+     <span class='ocr_line' id='line_1_4' title="bbox 69 446 2897 771; baseline -0.009 -107; x_size 59; x_descenders 9; x_ascenders 14">
+      <span class='ocrx_word' id='word_1_9' title='bbox 69 610 153 677; x_wconf 96'>300</span>
+      <span class='ocrx_word' id='word_1_10' title='bbox 941 618 1130 666; x_wconf 0'>—f—</span>
+      <span class='ocrx_word' id='word_1_11' title='bbox 1679 446 1950 771; x_wconf 0'>EN</span>
+      <span class='ocrx_word' id='word_1_12' title='bbox 2031 446 2140 771; x_wconf 0'>/</span>
+      <span class='ocrx_word' id='word_1_13' title='bbox 2501 446 2706 655; x_wconf 73'>~/</span>
+      <span class='ocrx_word' id='word_1_14' title='bbox 2793 450 2897 642; x_wconf 19'>Y</span>
+     </span>
+     <span class='ocr_line' id='line_1_5' title="bbox 70 646 2737 964; baseline -0.016 -24; x_size 131; x_descenders 32; x_ascenders 39">
+      <span class='ocrx_word' id='word_1_15' title='bbox 70 828 365 964; x_wconf 0'>Tg</span>
+      <span class='ocrx_word' id='word_1_16' title='bbox 1494 670 2098 940; x_wconf 42'>ANA</span>
+      <span class='ocrx_word' id='word_1_17' title='bbox 2158 646 2737 948; x_wconf 40'>a3</span>
+     </span>
+     <span class='ocr_line' id='line_1_6' title="bbox 70 1024 2937 1141; baseline -0.002 -56; x_size 31.799999; x_descenders 4.7999997; x_ascenders 12">
+      <span class='ocrx_word' id='word_1_18' title='bbox 70 1024 152 1061; x_wconf 90'>100</span>
+      <span class='ocrx_word' id='word_1_19' title='bbox 184 1037 204 1042; x_wconf 50'>-</span>
+      <span class='ocrx_word' id='word_1_20' title='bbox 1247 1038 1428 1141; x_wconf 23'>nee</span>
+      <span class='ocrx_word' id='word_1_21' title='bbox 1453 1038 1642 1141; x_wconf 0'>-eemiae</span>
+     </span>
+     <span class='ocr_line' id='line_1_7' title="bbox 121 1154 2840 1292; baseline -0.008 -12; x_size 41; x_descenders 8; x_ascenders 12">
+      <span class='ocrx_word' id='word_1_22' title='bbox 121 1216 299 1292; x_wconf 0'>0-+—-*</span>
+      <span class='ocrx_word' id='word_1_23' title='bbox 1811 1243 1964 1263; x_wconf 13'>a</span>
+      <span class='ocrx_word' id='word_1_24' title='bbox 2167 1154 2307 1274; x_wconf 31'>ee</span>
+      <span class='ocrx_word' id='word_1_25' title='bbox 2377 1154 2477 1274; x_wconf 17'>ee</span>
+      <span class='ocrx_word' id='word_1_26' title='bbox 2527 1154 2617 1274; x_wconf 32'>ee</span>
+      <span class='ocrx_word' id='word_1_27' title='bbox 2667 1243 2840 1263; x_wconf 26'>eee</span>
+     </span>
+     <span class='ocr_line' id='line_1_8' title="bbox 248 1293 3058 1353; baseline -0.002 -14; x_size 50; x_descenders 11; x_ascenders 8">
+      <span class='ocrx_word' id='word_1_28' title='bbox 248 1300 279 1339; x_wconf 53'>S</span>
+      <span class='ocrx_word' id='word_1_29' title='bbox 395 1310 425 1339; x_wconf 49'>@</span>
+      <span class='ocrx_word' id='word_1_30' title='bbox 540 1300 572 1339; x_wconf 23'>s</span>
+      <span class='ocrx_word' id='word_1_31' title='bbox 979 1309 1012 1339; x_wconf 81'>&gt;</span>
+      <span class='ocrx_word' id='word_1_32' title='bbox 1121 1295 1155 1353; x_wconf 37'>oO</span>
+      <span class='ocrx_word' id='word_1_33' title='bbox 1278 1306 1304 1334; x_wconf 24'>©</span>
+      <span class='ocrx_word' id='word_1_34' title='bbox 1407 1295 1450 1353; x_wconf 20'>ve</span>
+      <span class='ocrx_word' id='word_1_35' title='bbox 1567 1308 1593 1338; x_wconf 61'>S</span>
+      <span class='ocrx_word' id='word_1_36' title='bbox 1712 1308 1740 1338; x_wconf 0'>)</span>
+      <span class='ocrx_word' id='word_1_37' title='bbox 1858 1308 1888 1338; x_wconf 61'>@</span>
+      <span class='ocrx_word' id='word_1_38' title='bbox 2004 1305 2037 1338; x_wconf 80'>+</span>
+      <span class='ocrx_word' id='word_1_39' title='bbox 2153 1308 2180 1336; x_wconf 7'>&amp;</span>
+      <span class='ocrx_word' id='word_1_40' title='bbox 2287 1305 2329 1347; x_wconf 88'>&amp;</span>
+      <span class='ocrx_word' id='word_1_41' title='bbox 2578 1293 2613 1351; x_wconf 51'>“A</span>
+      <span class='ocrx_word' id='word_1_42' title='bbox 2738 1308 2765 1335; x_wconf 41'>5</span>
+      <span class='ocrx_word' id='word_1_43' title='bbox 3014 1308 3058 1344; x_wconf 23'>oo</span>
+     </span>
+     <span class='ocr_line' id='line_1_9' title="bbox 184 1306 3034 1411; baseline -0.008 -16; x_size 63; x_descenders 14; x_ascenders 18">
+      <span class='ocrx_word' id='word_1_44' title='bbox 184 1327 400 1399; x_wconf 40'>Se</span>
+      <span class='ocrx_word' id='word_1_45' title='bbox 622 1308 718 1404; x_wconf 53'>°</span>
+      <span class='ocrx_word' id='word_1_46' title='bbox 774 1330 988 1397; x_wconf 28'>Ps</span>
+      <span class='ocrx_word' id='word_1_47' title='bbox 1194 1360 1251 1411; x_wconf 19'>as</span>
+      <span class='ocrx_word' id='word_1_48' title='bbox 1360 1324 1425 1390; x_wconf 33'>ge</span>
+      <span class='ocrx_word' id='word_1_49' title='bbox 1641 1325 1717 1401; x_wconf 5'>eS</span>
+      <span class='ocrx_word' id='word_1_50' title='bbox 1801 1328 1869 1393; x_wconf 11'>€</span>
+      <span class='ocrx_word' id='word_1_51' title='bbox 1941 1325 2017 1392; x_wconf 68'>x</span>
+      <span class='ocrx_word' id='word_1_52' title='bbox 2077 1326 2161 1406; x_wconf 28'>ro</span>
+      <span class='ocrx_word' id='word_1_53' title='bbox 2232 1337 2297 1403; x_wconf 43'>NS</span>
+      <span class='ocrx_word' id='word_1_54' title='bbox 2379 1306 2468 1394; x_wconf 38'>Po</span>
+      <span class='ocrx_word' id='word_1_55' title='bbox 2535 1323 2597 1391; x_wconf 8'>e?</span>
+      <span class='ocrx_word' id='word_1_56' title='bbox 2667 1324 2751 1406; x_wconf 66'>&amp;</span>
+      <span class='ocrx_word' id='word_1_57' title='bbox 2845 1308 2913 1376; x_wconf 28'>s</span>
+      <span class='ocrx_word' id='word_1_58' title='bbox 2959 1324 3034 1401; x_wconf 48'>AS</span>
+     </span>
+     <span class='ocr_line' id='line_1_10' title="bbox 161 1360 3110 1447; baseline -0.003 -5; x_size 64; x_descenders 16; x_ascenders 20">
+      <span class='ocrx_word' id='word_1_59' title='bbox 161 1382 207 1426; x_wconf 15'>a</span>
+      <span class='ocrx_word' id='word_1_60' title='bbox 436 1384 494 1430; x_wconf 17'>a</span>
+      <span class='ocrx_word' id='word_1_61' title='bbox 750 1395 758 1441; x_wconf 17'>©</span>
+      <span class='ocrx_word' id='word_1_62' title='bbox 1318 1378 1521 1443; x_wconf 61'>FF</span>
+      <span class='ocrx_word' id='word_1_63' title='bbox 1615 1387 1655 1435; x_wconf 48'>SF</span>
+      <span class='ocrx_word' id='word_1_64' title='bbox 1753 1385 1813 1434; x_wconf 41'>HY</span>
+      <span class='ocrx_word' id='word_1_65' title='bbox 1891 1382 1960 1442; x_wconf 40'>HK</span>
+      <span class='ocrx_word' id='word_1_66' title='bbox 2050 1399 2092 1430; x_wconf 17'>SK</span>
+      <span class='ocrx_word' id='word_1_67' title='bbox 2187 1388 2251 1441; x_wconf 52'>BM</span>
+      <span class='ocrx_word' id='word_1_68' title='bbox 2630 1396 2678 1435; x_wconf 0'>ee</span>
+      <span class='ocrx_word' id='word_1_69' title='bbox 2920 1393 3110 1442; x_wconf 44'>sO</span>
+     </span>
+     <span class='ocr_line' id='line_1_11' title="bbox 141 1413 3090 1485; baseline -0.005 -17; x_size 42.720001; x_descenders 6.7199998; x_ascenders 15">
+      <span class='ocrx_word' id='word_1_70' title='bbox 141 1416 171 1446; x_wconf 35'>e</span>
+      <span class='ocrx_word' id='word_1_71' title='bbox 266 1438 288 1467; x_wconf 87'>&lt;</span>
+      <span class='ocrx_word' id='word_1_72' title='bbox 413 1426 448 1477; x_wconf 28'>Na</span>
+      <span class='ocrx_word' id='word_1_73' title='bbox 569 1429 589 1458; x_wconf 0'>‘</span>
+      <span class='ocrx_word' id='word_1_74' title='bbox 975 1454 982 1462; x_wconf 8'>:</span>
+      <span class='ocrx_word' id='word_1_75' title='bbox 1142 1428 1183 1463; x_wconf 23'>&gt;</span>
+      <span class='ocrx_word' id='word_1_76' title='bbox 1300 1421 1334 1471; x_wconf 10'>cy</span>
+      <span class='ocrx_word' id='word_1_77' title='bbox 1417 1420 1471 1480; x_wconf 57'>xs</span>
+      <span class='ocrx_word' id='word_1_78' title='bbox 1566 1424 1625 1476; x_wconf 40'>eS</span>
+      <span class='ocrx_word' id='word_1_79' title='bbox 1882 1433 1910 1460; x_wconf 59'>@</span>
+      <span class='ocrx_word' id='word_1_80' title='bbox 2024 1417 2069 1456; x_wconf 59'>Ww</span>
+      <span class='ocrx_word' id='word_1_81' title='bbox 2878 1413 2934 1485; x_wconf 16'>a)</span>
+      <span class='ocrx_word' id='word_1_82' title='bbox 3029 1425 3090 1476; x_wconf 33'>Oo</span>
+     </span>
+     <span class='ocr_line' id='line_1_12' title="bbox 45 1433 3041 1546; baseline -0.011 -11; x_size 108.376; x_descenders 22; x_ascenders 27.375999">
+      <span class='ocrx_word' id='word_1_83' title='bbox 45 1433 279 1535; x_wconf 61'>ee</span>
+      <span class='ocrx_word' id='word_1_84' title='bbox 353 1450 430 1514; x_wconf 27'>S&amp;S</span>
+      <span class='ocrx_word' id='word_1_85' title='bbox 528 1445 722 1535; x_wconf 55'>FF</span>
+      <span class='ocrx_word' id='word_1_86' title='bbox 915 1443 1158 1546; x_wconf 49'>SF</span>
+      <span class='ocrx_word' id='word_1_87' title='bbox 1233 1445 1317 1518; x_wconf 42'>HK</span>
+      <span class='ocrx_word' id='word_1_88' title='bbox 1386 1462 1427 1518; x_wconf 63'>S</span>
+      <span class='ocrx_word' id='word_1_89' title='bbox 1833 1453 1889 1502; x_wconf 66'>e</span>
+      <span class='ocrx_word' id='word_1_90' title='bbox 2004 1440 2046 1476; x_wconf 33'>©</span>
+      <span class='ocrx_word' id='word_1_91' title='bbox 3006 1457 3041 1492; x_wconf 77'>4</span>
+     </span>
+     <span class='ocr_line' id='line_1_13' title="bbox 152 1516 1391 1593; baseline -0.006 -40; x_size 40; x_descenders 7; x_ascenders 13">
+      <span class='ocrx_word' id='word_1_92' title='bbox 152 1520 214 1575; x_wconf 71'>~</span>
+      <span class='ocrx_word' id='word_1_93' title='bbox 586 1526 646 1587; x_wconf 85'>&amp;</span>
+      <span class='ocrx_word' id='word_1_94' title='bbox 1304 1516 1391 1593; x_wconf 0'>e</span>
+     </span>
+     <span class='ocr_line' id='line_1_14' title="bbox 247 1567 597 1619; baseline -0.009 0; x_size 55.75; x_descenders 10; x_ascenders 14.5">
+      <span class='ocrx_word' id='word_1_95' title='bbox 247 1570 297 1619; x_wconf 32'>3</span>
+      <span class='ocrx_word' id='word_1_96' title='bbox 550 1567 597 1609; x_wconf 43'>x</span>
+     </span>
+    </p>
+   </div>
+   <div class='ocr_carea' id='block_1_16' title="bbox 3353 611 3919 1060">
+    <p class='ocr_par' id='par_1_2' lang='eng' title="bbox 3354 611 3660 656">
+     <span class='ocr_line' id='line_1_15' title="bbox 3354 611 3660 656; baseline -0.013 -5; x_size 46; x_descenders 9; x_ascenders 10">
+      <span class='ocrx_word' id='word_1_97' title='bbox 3354 611 3660 656; x_wconf 59'>—¢—Support</span>
+     </span>
+    </p>
+
+    <p class='ocr_par' id='par_1_3' lang='eng' title="bbox 3354 711 3831 960">
+     <span class='ocr_line' id='line_1_16' title="bbox 3354 711 3831 760; baseline 0 -9; x_size 49; x_descenders 9; x_ascenders 13">
+      <span class='ocrx_word' id='word_1_98' title='bbox 3354 712 3542 751; x_wconf 0'>—H—</span>
+      <span class='ocrx_word' id='word_1_99' title='bbox 3480 707 3524 765; x_wconf 90'>No</span>
+      <span class='ocrx_word' id='word_1_100' title='bbox 3555 711 3773 760; x_wconf 80'>vote[note</span>
+      <span class='ocrx_word' id='word_1_101' title='bbox 3790 711 3831 760; x_wconf 96'>1]</span>
+     </span>
+     <span class='ocr_line' id='line_1_17' title="bbox 3355 815 3652 860; baseline 0.003 -9; x_size 44; x_descenders 8; x_ascenders 9">
+      <span class='ocrx_word' id='word_1_102' title='bbox 3355 811 3457 864; x_wconf 29'>ir</span>
+      <span class='ocrx_word' id='word_1_103' title='bbox 3492 811 3652 864; x_wconf 96'>Oppose</span>
+     </span>
+     <span class='ocr_line' id='line_1_18' title="bbox 3354 912 3735 960; baseline 0.003 -9; x_size 50; x_descenders 10; x_ascenders 12">
+      <span class='ocrx_word' id='word_1_104' title='bbox 3354 912 3677 960; x_wconf 0'>—=—Net[note</span>
+      <span class='ocrx_word' id='word_1_105' title='bbox 3694 912 3735 960; x_wconf 96'>2]</span>
+     </span>
+    </p>
+
+    <p class='ocr_par' id='par_1_4' lang='eng' title="bbox 3353 1011 3919 1060">
+     <span class='ocr_line' id='line_1_19' title="bbox 3353 1011 3919 1060; baseline 0.004 -10; x_size 51; x_descenders 10; x_ascenders 13">
+      <span class='ocrx_word' id='word_1_106' title='bbox 3353 1007 3453 1066; x_wconf 23'>re</span>
+      <span class='ocrx_word' id='word_1_107' title='bbox 3486 1007 3723 1066; x_wconf 82'>Percentage</span>
+      <span class='ocrx_word' id='word_1_108' title='bbox 3749 1011 3864 1060; x_wconf 95'>[note</span>
+      <span class='ocrx_word' id='word_1_109' title='bbox 3877 1011 3919 1060; x_wconf 95'>3]</span>
+     </span>
+    </p>
+   </div>
+  </div>
+ </body>
+</html>

tests/cache/graph_ocred/__-l__eng__000001_ocr.png__000001_ocr_hocr__hocr__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/jbig2/__-l__eng__000001_ocr.png__000001_ocr_hocr__hocr__txt/hocr.bin

@@ -9,7 +9,7 @@
   <meta name='ocr-capabilities' content='ocr_page ocr_carea ocr_par ocr_line ocrx_word ocrp_wconf'/>
  </head>
  <body>
-  <div class='ocr_page' id='page_1' title='image "/tmp/ocrmypdf.io.zbey8lbq/000001_ocr.png"; bbox 0 0 2550 3300; ppageno 0; scan_res 300 300'>
+  <div class='ocr_page' id='page_1' title='image "/tmp/ocrmypdf.io.wtynt0r_/000001_ocr.png"; bbox 0 0 2550 3300; ppageno 0; scan_res 300 300'>
    <div class='ocr_carea' id='block_1_1' title="bbox 582 131 1968 303">
     <p class='ocr_par' id='par_1_1' lang='eng' title="bbox 582 131 1968 303">
      <span class='ocr_header' id='line_1_1' title="bbox 882 131 1657 217; baseline 0.001 -17; x_size 85; x_descenders 16; x_ascenders 19">

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

@@ -9,7 +9,7 @@
   <meta name='ocr-capabilities' content='ocr_page ocr_carea ocr_par ocr_line ocrx_word ocrp_wconf'/>
  </head>
  <body>
-  <div class='ocr_page' id='page_1' title='image "/tmp/ocrmypdf.io.bkzvxcfc/000001_ocr.png"; bbox 0 0 512 512; ppageno 0; scan_res 96 96'>
+  <div class='ocr_page' id='page_1' title='image "/tmp/ocrmypdf.io.4utqke6w/000001_ocr.png"; bbox 0 0 512 512; ppageno 0; scan_res 96 96'>
    <div class='ocr_photo' id='block_1_1' title="bbox 0 0 477 512"></div>
   </div>
  </body>

tests/cache/manifest.jsonl

@@ -1,57 +1,85 @@
-{"tesseract_version": "5.3.2", "system": "Linux", "python": "3.10.12", "argv_slug": "__-l__eng__000001_ocr.png__000001_ocr_tess__pdf__txt", "sourcefile": "resources/ccitt.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": "3.10.12", "argv_slug": "__-l__eng__000001_ocr.png__000001_ocr_hocr__hocr__txt", "sourcefile": "resources/skew.pdf", "args": ["-l", "eng", "$TMPDIR/000001_ocr.png", "$TMPDIR/000001_ocr_hocr", "hocr", "txt"]}
-{"tesseract_version": "5.3.2", "system": "Linux", "python": "3.10.12", "argv_slug": "__-l__eng__000001_ocr.png__000001_ocr_tess__pdf__txt", "sourcefile": "resources/skew.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": "3.10.12", "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": "3.10.12", "argv_slug": "__-l__eng__--psm__2__000003_rasterize.png__stdout", "sourcefile": "resources/multipage.pdf", "args": ["-l", "eng", "--psm", "2", "$TMPDIR/000003_rasterize.png", "stdout"]}
-{"tesseract_version": "5.3.2", "system": "Linux", "python": "3.10.12", "argv_slug": "__-l__eng__--psm__2__000005_rasterize.png__stdout", "sourcefile": "resources/multipage.pdf", "args": ["-l", "eng", "--psm", "2", "$TMPDIR/000005_rasterize.png", "stdout"]}
-{"tesseract_version": "5.3.2", "system": "Linux", "python": "3.10.12", "argv_slug": "__-l__eng__000003_ocr.png__000003_ocr_hocr__hocr__txt", "sourcefile": "resources/multipage.pdf", "args": ["-l", "eng", "$TMPDIR/000003_ocr.png", "$TMPDIR/000003_ocr_hocr", "hocr", "txt"]}
-{"tesseract_version": "5.3.2", "system": "Linux", "python": "3.10.12", "argv_slug": "__-l__eng__--psm__2__000004_rasterize.png__stdout", "sourcefile": "resources/multipage.pdf", "args": ["-l", "eng", "--psm", "2", "$TMPDIR/000004_rasterize.png", "stdout"]}
-{"tesseract_version": "5.3.2", "system": "Linux", "python": "3.10.12", "argv_slug": "__-l__eng__--psm__2__000006_rasterize.png__stdout", "sourcefile": "resources/multipage.pdf", "args": ["-l", "eng", "--psm", "2", "$TMPDIR/000006_rasterize.png", "stdout"]}
-{"tesseract_version": "5.3.2", "system": "Linux", "python": "3.10.12", "argv_slug": "__-l__eng__--psm__2__000001_rasterize.png__stdout", "sourcefile": "resources/multipage.pdf", "args": ["-l", "eng", "--psm", "2", "$TMPDIR/000001_rasterize.png", "stdout"]}
-{"tesseract_version": "5.3.2", "system": "Linux", "python": "3.10.12", "argv_slug": "__-l__eng__000005_ocr.png__000005_ocr_hocr__hocr__txt", "sourcefile": "resources/multipage.pdf", "args": ["-l", "eng", "$TMPDIR/000005_ocr.png", "$TMPDIR/000005_ocr_hocr", "hocr", "txt"]}
-{"tesseract_version": "5.3.2", "system": "Linux", "python": "3.10.12", "argv_slug": "__-l__eng__000004_ocr.png__000004_ocr_hocr__hocr__txt", "sourcefile": "resources/multipage.pdf", "args": ["-l", "eng", "$TMPDIR/000004_ocr.png", "$TMPDIR/000004_ocr_hocr", "hocr", "txt"]}
-{"tesseract_version": "5.3.2", "system": "Linux", "python": "3.10.12", "argv_slug": "__-l__eng__000006_ocr.png__000006_ocr_hocr__hocr__txt", "sourcefile": "resources/multipage.pdf", "args": ["-l", "eng", "$TMPDIR/000006_ocr.png", "$TMPDIR/000006_ocr_hocr", "hocr", "txt"]}
-{"tesseract_version": "5.3.2", "system": "Linux", "python": "3.10.12", "argv_slug": "__-l__eng__000001_ocr.png__000001_ocr_hocr__hocr__txt", "sourcefile": "resources/multipage.pdf", "args": ["-l", "eng", "$TMPDIR/000001_ocr.png", "$TMPDIR/000001_ocr_hocr", "hocr", "txt"]}
-{"tesseract_version": "5.3.2", "system": "Linux", "python": "3.10.12", "argv_slug": "__-l__eng__000003_ocr.png__000003_ocr_tess__pdf__txt", "sourcefile": "resources/multipage.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000003_ocr.png", "$TMPDIR/000003_ocr_tess", "pdf", "txt"]}
-{"tesseract_version": "5.3.2", "system": "Linux", "python": "3.10.12", "argv_slug": "__-l__eng__000005_ocr.png__000005_ocr_tess__pdf__txt", "sourcefile": "resources/multipage.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000005_ocr.png", "$TMPDIR/000005_ocr_tess", "pdf", "txt"]}
-{"tesseract_version": "5.3.2", "system": "Linux", "python": "3.10.12", "argv_slug": "__-l__eng__000006_ocr.png__000006_ocr_tess__pdf__txt", "sourcefile": "resources/multipage.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000006_ocr.png", "$TMPDIR/000006_ocr_tess", "pdf", "txt"]}
-{"tesseract_version": "5.3.2", "system": "Linux", "python": "3.10.12", "argv_slug": "__-l__eng__000004_ocr.png__000004_ocr_tess__pdf__txt", "sourcefile": "resources/multipage.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000004_ocr.png", "$TMPDIR/000004_ocr_tess", "pdf", "txt"]}
-{"tesseract_version": "5.3.2", "system": "Linux", "python": "3.10.12", "argv_slug": "__-l__eng__000001_ocr.png__000001_ocr_tess__pdf__txt", "sourcefile": "resources/multipage.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000001_ocr.png", "$TMPDIR/000001_ocr_tess", "pdf", "txt"]}
-{"tesseract_version": "5.3.2", "system": "Linux", "python": "3.10.12", "argv_slug": "__-l__deu__000001_ocr.png__000001_ocr_tess__pdf__txt", "sourcefile": "resources/francais.pdf", "args": ["-l", "deu", "-c", "textonly_pdf=1", "$TMPDIR/000001_ocr.png", "$TMPDIR/000001_ocr_tess", "pdf", "txt"]}
-{"tesseract_version": "5.3.2", "system": "Linux", "python": "3.10.12", "argv_slug": "__-l__eng__--psm__7__000001_ocr.png__000001_ocr_hocr__hocr__txt", "sourcefile": "resources/skew.pdf", "args": ["-l", "eng", "--psm", "7", "$TMPDIR/000001_ocr.png", "$TMPDIR/000001_ocr_hocr", "hocr", "txt"]}
-{"tesseract_version": "5.3.2", "system": "Linux", "python": "3.10.12", "argv_slug": "__-l__eng__--psm__7__000001_ocr.png__000001_ocr_tess__pdf__txt", "sourcefile": "resources/skew.pdf", "args": ["-l", "eng", "--psm", "7", "-c", "textonly_pdf=1", "$TMPDIR/000001_ocr.png", "$TMPDIR/000001_ocr_tess", "pdf", "txt"]}
-{"tesseract_version": "5.3.2", "system": "Linux", "python": "3.10.12", "argv_slug": "__-l__eng__--oem__1__000001_ocr.png__000001_ocr_tess__pdf__txt", "sourcefile": "resources/trivial.pdf", "args": ["-l", "eng", "--oem", "1", "-c", "textonly_pdf=1", "$TMPDIR/000001_ocr.png", "$TMPDIR/000001_ocr_tess", "pdf", "txt"]}
-{"tesseract_version": "5.3.2", "system": "Linux", "python": "3.10.12", "argv_slug": "__-l__eng__000001_ocr.png__000001_ocr_tess__pdf__txt", "sourcefile": "resources/trivial.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000001_ocr.png", "$TMPDIR/000001_ocr_tess", "pdf", "txt"]}
-{"tesseract_version": "5.3.2", "system": "Linux", "python": "3.10.12", "argv_slug": "__-l__eng__thresholding_method=1__000001_ocr.png__000001_ocr_tess__pdf__txt", "sourcefile": "resources/trivial.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "-c", "thresholding_method=1", "$TMPDIR/000001_ocr.png", "$TMPDIR/000001_ocr_tess", "pdf", "txt"]}
-{"tesseract_version": "5.3.2", "system": "Linux", "python": "3.10.12", "argv_slug": "__-l__eng__thresholding_method=2__000001_ocr.png__000001_ocr_tess__pdf__txt", "sourcefile": "resources/trivial.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "-c", "thresholding_method=2", "$TMPDIR/000001_ocr.png", "$TMPDIR/000001_ocr_tess", "pdf", "txt"]}
-{"tesseract_version": "5.3.2", "system": "Linux", "python": "3.10.12", "argv_slug": "__-l__eng__000001_ocr.png__000001_ocr_hocr__hocr__txt", "sourcefile": "resources/jbig2.pdf", "args": ["-l", "eng", "$TMPDIR/000001_ocr.png", "$TMPDIR/000001_ocr_hocr", "hocr", "txt"]}
-{"tesseract_version": "5.3.2", "system": "Linux", "python": "3.10.12", "argv_slug": "__-l__eng__000001_ocr.png__000001_ocr_tess__pdf__txt", "sourcefile": "resources/2400dpi.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000001_ocr.png", "$TMPDIR/000001_ocr_tess", "pdf", "txt"]}
-{"tesseract_version": "5.3.2", "system": "Linux", "python": "3.10.12", "argv_slug": "__-l__eng__000002_ocr.png__000002_ocr_tess__pdf__txt", "sourcefile": "resources/3small.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000002_ocr.png", "$TMPDIR/000002_ocr_tess", "pdf", "txt"]}
-{"tesseract_version": "5.3.2", "system": "Linux", "python": "3.10.12", "argv_slug": "__-l__eng__000001_ocr.png__000001_ocr_tess__pdf__txt", "sourcefile": "resources/3small.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000001_ocr.png", "$TMPDIR/000001_ocr_tess", "pdf", "txt"]}
-{"tesseract_version": "5.3.2", "system": "Linux", "python": "3.10.12", "argv_slug": "__-l__eng__000003_ocr.png__000003_ocr_tess__pdf__txt", "sourcefile": "resources/3small.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000003_ocr.png", "$TMPDIR/000003_ocr_tess", "pdf", "txt"]}
-{"tesseract_version": "5.3.2", "system": "Linux", "python": "3.10.12", "argv_slug": "__-l__eng__--psm__2__000001_rasterize.png__stdout", "sourcefile": "resources/palette.pdf", "args": ["-l", "eng", "--psm", "2", "$TMPDIR/000001_rasterize.png", "stdout"]}
-{"tesseract_version": "5.3.2", "system": "Linux", "python": "3.10.12", "argv_slug": "__-l__eng__000001_ocr.png__000001_ocr_tess__pdf__txt", "sourcefile": "resources/palette.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": "3.10.12", "argv_slug": "__-l__eng__--psm__2__000001_rasterize.png__stdout", "sourcefile": "resources/ccitt.pdf", "args": ["-l", "eng", "--psm", "2", "$TMPDIR/000001_rasterize.png", "stdout"]}
-{"tesseract_version": "5.3.2", "system": "Linux", "python": "3.10.12", "argv_slug": "__-l__eng__--psm__2__000001_rasterize.png__stdout", "sourcefile": "resources/jbig2.pdf", "args": ["-l", "eng", "--psm", "2", "$TMPDIR/000001_rasterize.png", "stdout"]}
-{"tesseract_version": "5.3.2", "system": "Linux", "python": "3.10.12", "argv_slug": "__-l__eng__000001_ocr.png__000001_ocr_tess__pdf__txt", "sourcefile": "resources/jbig2.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": "3.10.12", "argv_slug": "__-l__eng__--psm__2__000001_rasterize.png__stdout", "sourcefile": "resources/lichtenstein.pdf", "args": ["-l", "eng", "--psm", "2", "$TMPDIR/000001_rasterize.png", "stdout"]}
-{"tesseract_version": "5.3.2", "system": "Linux", "python": "3.10.12", "argv_slug": "__-l__eng__000001_ocr.png__000001_ocr_tess__pdf__txt", "sourcefile": "resources/lichtenstein.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000001_ocr.png", "$TMPDIR/000001_ocr_tess", "pdf", "txt"]}
-{"tesseract_version": "5.3.2", "system": "Linux", "python": "3.10.12", "argv_slug": "__-l__eng__000001_ocr.png__000001_ocr_hocr__hocr__txt", "sourcefile": "resources/palette.pdf", "args": ["-l", "eng", "$TMPDIR/000001_ocr.png", "$TMPDIR/000001_ocr_hocr", "hocr", "txt"]}
-{"tesseract_version": "5.3.2", "system": "Linux", "python": "3.10.12", "argv_slug": "__-l__eng__000001_ocr.png__000001_ocr_hocr__hocr__txt", "sourcefile": "resources/ccitt.pdf", "args": ["-l", "eng", "$TMPDIR/000001_ocr.png", "$TMPDIR/000001_ocr_hocr", "hocr", "txt"]}
-{"tesseract_version": "5.3.2", "system": "Linux", "python": "3.10.12", "argv_slug": "__-l__eng__000001_ocr.png__000001_ocr_hocr__hocr__txt", "sourcefile": "resources/lichtenstein.pdf", "args": ["-l", "eng", "$TMPDIR/000001_ocr.png", "$TMPDIR/000001_ocr_hocr", "hocr", "txt"]}
-{"tesseract_version": "5.3.2", "system": "Linux", "python": "3.10.12", "argv_slug": "__-l__eng__000001_ocr.png__000001_ocr_hocr__hocr__txt", "sourcefile": "resources/aspect.pdf", "args": ["-l", "eng", "$TMPDIR/000001_ocr.png", "$TMPDIR/000001_ocr_hocr", "hocr", "txt"]}
-{"tesseract_version": "5.3.2", "system": "Linux", "python": "3.10.12", "argv_slug": "__-l__eng__000001_ocr.png__000001_ocr_tess__pdf__txt", "sourcefile": "resources/aspect.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000001_ocr.png", "$TMPDIR/000001_ocr_tess", "pdf", "txt"]}
-{"tesseract_version": "5.3.2", "system": "Linux", "python": "3.10.12", "argv_slug": "__-l__osd__--psm__0__000001_rasterize_preview.jpg__stdout", "sourcefile": "resources/cardinal.pdf", "args": ["-l", "osd", "--psm", "0", "$TMPDIR/000001_rasterize_preview.jpg", "stdout"]}
-{"tesseract_version": "5.3.2", "system": "Linux", "python": "3.10.12", "argv_slug": "__-l__osd__--psm__0__000002_rasterize_preview.jpg__stdout", "sourcefile": "resources/cardinal.pdf", "args": ["-l", "osd", "--psm", "0", "$TMPDIR/000002_rasterize_preview.jpg", "stdout"]}
-{"tesseract_version": "5.3.2", "system": "Linux", "python": "3.10.12", "argv_slug": "__-l__osd__--psm__0__000003_rasterize_preview.jpg__stdout", "sourcefile": "resources/cardinal.pdf", "args": ["-l", "osd", "--psm", "0", "$TMPDIR/000003_rasterize_preview.jpg", "stdout"]}
-{"tesseract_version": "5.3.2", "system": "Linux", "python": "3.10.12", "argv_slug": "__-l__osd__--psm__0__000004_rasterize_preview.jpg__stdout", "sourcefile": "resources/cardinal.pdf", "args": ["-l", "osd", "--psm", "0", "$TMPDIR/000004_rasterize_preview.jpg", "stdout"]}
-{"tesseract_version": "5.3.2", "system": "Linux", "python": "3.10.12", "argv_slug": "__-l__eng__000001_ocr.png__000001_ocr_hocr__hocr__txt", "sourcefile": "resources/cardinal.pdf", "args": ["-l", "eng", "$TMPDIR/000001_ocr.png", "$TMPDIR/000001_ocr_hocr", "hocr", "txt"]}
-{"tesseract_version": "5.3.2", "system": "Linux", "python": "3.10.12", "argv_slug": "__-l__eng__000002_ocr.png__000002_ocr_hocr__hocr__txt", "sourcefile": "resources/cardinal.pdf", "args": ["-l", "eng", "$TMPDIR/000002_ocr.png", "$TMPDIR/000002_ocr_hocr", "hocr", "txt"]}
-{"tesseract_version": "5.3.2", "system": "Linux", "python": "3.10.12", "argv_slug": "__-l__eng__000003_ocr.png__000003_ocr_hocr__hocr__txt", "sourcefile": "resources/cardinal.pdf", "args": ["-l", "eng", "$TMPDIR/000003_ocr.png", "$TMPDIR/000003_ocr_hocr", "hocr", "txt"]}
-{"tesseract_version": "5.3.2", "system": "Linux", "python": "3.10.12", "argv_slug": "__-l__eng__000004_ocr.png__000004_ocr_hocr__hocr__txt", "sourcefile": "resources/cardinal.pdf", "args": ["-l", "eng", "$TMPDIR/000004_ocr.png", "$TMPDIR/000004_ocr_hocr", "hocr", "txt"]}
-{"tesseract_version": "5.3.2", "system": "Linux", "python": "3.10.12", "argv_slug": "__-l__eng__000003_ocr.png__000003_ocr_tess__pdf__txt", "sourcefile": "resources/cardinal.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000003_ocr.png", "$TMPDIR/000003_ocr_tess", "pdf", "txt"]}
-{"tesseract_version": "5.3.2", "system": "Linux", "python": "3.10.12", "argv_slug": "__-l__eng__000001_ocr.png__000001_ocr_tess__pdf__txt", "sourcefile": "resources/cardinal.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000001_ocr.png", "$TMPDIR/000001_ocr_tess", "pdf", "txt"]}
-{"tesseract_version": "5.3.2", "system": "Linux", "python": "3.10.12", "argv_slug": "__-l__eng__000004_ocr.png__000004_ocr_tess__pdf__txt", "sourcefile": "resources/cardinal.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000004_ocr.png", "$TMPDIR/000004_ocr_tess", "pdf", "txt"]}
-{"tesseract_version": "5.3.2", "system": "Linux", "python": "3.10.12", "argv_slug": "__-l__eng__000002_ocr.png__000002_ocr_tess__pdf__txt", "sourcefile": "resources/cardinal.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000002_ocr.png", "$TMPDIR/000002_ocr_tess", "pdf", "txt"]}
-{"tesseract_version": "5.3.2", "system": "Linux", "python": "3.10.12", "argv_slug": "__-l__eng__000001_ocr.png__000001_ocr_tess__pdf__txt", "sourcefile": "resources/poster.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000001_ocr.png", "$TMPDIR/000001_ocr_tess", "pdf", "txt"]}
-{"tesseract_version": "5.3.2", "system": "Linux", "python": "3.10.12", "argv_slug": "__-l__osd__--psm__0__000001_rasterize_preview.jpg__stdout", "sourcefile": "resources/poster.pdf", "args": ["-l", "osd", "--psm", "0", "$TMPDIR/000001_rasterize_preview.jpg", "stdout"]}
+{"tesseract_version": "5.3.2", "system": "Linux", "python": "3.11.6", "argv_slug": "__-l__eng__thresholding_method=1__000001_ocr.png__000001_ocr_hocr__hocr__txt", "sourcefile": "resources/trivial.pdf", "args": ["-l", "eng", "-c", "thresholding_method=1", "$TMPDIR/000001_ocr.png", "$TMPDIR/000001_ocr_hocr", "hocr", "txt"]}
+{"tesseract_version": "5.3.2", "system": "Linux", "python": "3.11.6", "argv_slug": "__-l__eng__000003_ocr.png__000003_ocr_hocr__hocr__txt", "sourcefile": "resources/multipage.pdf", "args": ["-l", "eng", "/tmp/pytest-of-jb/pytest-42/popen-gw1/test_hocr_api_multipage0/000003_ocr.png", "/tmp/pytest-of-jb/pytest-42/popen-gw1/test_hocr_api_multipage0/000003_ocr_hocr", "hocr", "txt"]}
+{"tesseract_version": "5.3.2", "system": "Linux", "python": "3.11.6", "argv_slug": "__-l__eng__thresholding_method=2__000001_ocr.png__000001_ocr_hocr__hocr__txt", "sourcefile": "resources/trivial.pdf", "args": ["-l", "eng", "-c", "thresholding_method=2", "$TMPDIR/000001_ocr.png", "$TMPDIR/000001_ocr_hocr", "hocr", "txt"]}
+{"tesseract_version": "5.3.2", "system": "Linux", "python": "3.11.6", "argv_slug": "__-l__eng__--psm__7__000001_ocr.png__000001_ocr_hocr__hocr__txt", "sourcefile": "resources/skew.pdf", "args": ["-l", "eng", "--psm", "7", "$TMPDIR/000001_ocr.png", "$TMPDIR/000001_ocr_hocr", "hocr", "txt"]}
+{"tesseract_version": "5.3.2", "system": "Linux", "python": "3.11.6", "argv_slug": "__-l__eng__--psm__2__000003_rasterize.png__stdout", "sourcefile": "resources/multipage.pdf", "args": ["-l", "eng", "--psm", "2", "$TMPDIR/000003_rasterize.png", "stdout"]}
+{"tesseract_version": "5.3.2", "system": "Linux", "python": "3.11.6", "argv_slug": "__-l__eng__--psm__2__000005_rasterize.png__stdout", "sourcefile": "resources/multipage.pdf", "args": ["-l", "eng", "--psm", "2", "$TMPDIR/000005_rasterize.png", "stdout"]}
+{"tesseract_version": "5.3.2", "system": "Linux", "python": "3.11.6", "argv_slug": "__-l__eng__000005_ocr.png__000005_ocr_hocr__hocr__txt", "sourcefile": "resources/multipage.pdf", "args": ["-l", "eng", "/tmp/pytest-of-jb/pytest-42/popen-gw1/test_hocr_api_multipage0/000005_ocr.png", "/tmp/pytest-of-jb/pytest-42/popen-gw1/test_hocr_api_multipage0/000005_ocr_hocr", "hocr", "txt"]}
+{"tesseract_version": "5.3.2", "system": "Linux", "python": "3.11.6", "argv_slug": "__-l__deu__000001_ocr.png__000001_ocr_hocr__hocr__txt", "sourcefile": "resources/francais.pdf", "args": ["-l", "deu", "$TMPDIR/000001_ocr.png", "$TMPDIR/000001_ocr_hocr", "hocr", "txt"]}
+{"tesseract_version": "5.3.2", "system": "Linux", "python": "3.11.6", "argv_slug": "__-l__eng__--psm__7__000001_ocr.png__000001_ocr_tess__pdf__txt", "sourcefile": "resources/skew.pdf", "args": ["-l", "eng", "--psm", "7", "-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__--psm__2__000004_rasterize.png__stdout", "sourcefile": "resources/multipage.pdf", "args": ["-l", "eng", "--psm", "2", "$TMPDIR/000004_rasterize.png", "stdout"]}
+{"tesseract_version": "5.3.2", "system": "Linux", "python": "3.11.6", "argv_slug": "__-l__eng__--oem__1__000001_ocr.png__000001_ocr_hocr__hocr__txt", "sourcefile": "resources/trivial.pdf", "args": ["-l", "eng", "--oem", "1", "$TMPDIR/000001_ocr.png", "$TMPDIR/000001_ocr_hocr", "hocr", "txt"]}
+{"tesseract_version": "5.3.2", "system": "Linux", "python": "3.11.6", "argv_slug": "__-l__eng__--psm__2__000006_rasterize.png__stdout", "sourcefile": "resources/multipage.pdf", "args": ["-l", "eng", "--psm", "2", "$TMPDIR/000006_rasterize.png", "stdout"]}
+{"tesseract_version": "5.3.2", "system": "Linux", "python": "3.11.6", "argv_slug": "__-l__eng__000002_ocr.png__000002_ocr_hocr__hocr__txt", "sourcefile": "resources/3small.pdf", "args": ["-l", "eng", "$TMPDIR/000002_ocr.png", "$TMPDIR/000002_ocr_hocr", "hocr", "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/ccitt.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_hocr__hocr__txt", "sourcefile": "resources/jbig2.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_hocr__hocr__txt", "sourcefile": "resources/3small.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_hocr__hocr__txt", "sourcefile": "resources/trivial.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_hocr__hocr__txt", "sourcefile": "resources/skew.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__--psm__2__000001_rasterize.png__stdout", "sourcefile": "resources/multipage.pdf", "args": ["-l", "eng", "--psm", "2", "$TMPDIR/000001_rasterize.png", "stdout"]}
+{"tesseract_version": "5.3.2", "system": "Linux", "python": "3.11.6", "argv_slug": "__-l__eng__000006_ocr.png__000006_ocr_hocr__hocr__txt", "sourcefile": "resources/multipage.pdf", "args": ["-l", "eng", "/tmp/pytest-of-jb/pytest-42/popen-gw1/test_hocr_api_multipage0/000006_ocr.png", "/tmp/pytest-of-jb/pytest-42/popen-gw1/test_hocr_api_multipage0/000006_ocr_hocr", "hocr", "txt"]}
+{"tesseract_version": "5.3.2", "system": "Linux", "python": "3.11.6", "argv_slug": "__-l__eng__000001_ocr.png__000001_ocr_hocr__hocr__txt", "sourcefile": "resources/ccitt.pdf", "args": ["-l", "eng", "$TMPDIR/000001_ocr.png", "$TMPDIR/000001_ocr_hocr", "hocr", "txt"]}
+{"tesseract_version": "5.3.2", "system": "Linux", "python": "3.11.6", "argv_slug": "__-l__eng__000001_ocr.png__000001_ocr_hocr__hocr__txt", "sourcefile": "resources/multipage.pdf", "args": ["-l", "eng", "/tmp/pytest-of-jb/pytest-42/popen-gw1/test_hocr_api_multipage0/000001_ocr.png", "/tmp/pytest-of-jb/pytest-42/popen-gw1/test_hocr_api_multipage0/000001_ocr_hocr", "hocr", "txt"]}
+{"tesseract_version": "5.3.2", "system": "Linux", "python": "3.11.6", "argv_slug": "__-l__eng__000003_ocr.png__000003_ocr_hocr__hocr__txt", "sourcefile": "resources/3small.pdf", "args": ["-l", "eng", "$TMPDIR/000003_ocr.png", "$TMPDIR/000003_ocr_hocr", "hocr", "txt"]}
+{"tesseract_version": "5.3.2", "system": "Linux", "python": "3.11.6", "argv_slug": "__-l__eng__000001_ocr.png__000001_ocr_hocr__hocr__txt", "sourcefile": "resources/2400dpi.pdf", "args": ["-l", "eng", "$TMPDIR/000001_ocr.png", "$TMPDIR/000001_ocr_hocr", "hocr", "txt"]}
+{"tesseract_version": "5.3.2", "system": "Linux", "python": "3.11.6", "argv_slug": "__-l__eng__000004_ocr.png__000004_ocr_hocr__hocr__txt", "sourcefile": "resources/multipage.pdf", "args": ["-l", "eng", "$TMPDIR/000004_ocr.png", "$TMPDIR/000004_ocr_hocr", "hocr", "txt"]}
+{"tesseract_version": "5.3.2", "system": "Linux", "python": "3.11.6", "argv_slug": "__-l__eng__--psm__2__000001_rasterize.png__stdout", "sourcefile": "resources/palette.pdf", "args": ["-l", "eng", "--psm", "2", "$TMPDIR/000001_rasterize.png", "stdout"]}
+{"tesseract_version": "5.3.2", "system": "Linux", "python": "3.11.6", "argv_slug": "__-l__eng__--psm__2__000001_rasterize.png__stdout", "sourcefile": "resources/palette.pdf", "args": ["-l", "eng", "--psm", "2", "$TMPDIR/000001_rasterize.png", "stdout"]}
+{"tesseract_version": "5.3.2", "system": "Linux", "python": "3.11.6", "argv_slug": "__-l__eng__000001_ocr.png__000001_ocr_tess__pdf__txt", "sourcefile": "resources/skew.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000001_ocr.png", "$TMPDIR/000001_ocr_tess", "pdf", "txt"]}
+{"tesseract_version": "5.3.2", "system": "Linux", "python": "3.11.6", "argv_slug": "__-l__eng__000001_ocr.png__000001_ocr_tess__pdf__txt", "sourcefile": "resources/palette.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000001_ocr.png", "$TMPDIR/000001_ocr_tess", "pdf", "txt"]}
+{"tesseract_version": "5.3.2", "system": "Linux", "python": "3.11.6", "argv_slug": "__-l__eng__000001_ocr.png__000001_ocr_hocr__hocr__txt", "sourcefile": "resources/palette.pdf", "args": ["-l", "eng", "$TMPDIR/000001_ocr.png", "$TMPDIR/000001_ocr_hocr", "hocr", "txt"]}
+{"tesseract_version": "5.3.2", "system": "Linux", "python": "3.11.6", "argv_slug": "__-l__eng__--psm__2__000001_rasterize.png__stdout", "sourcefile": "resources/lichtenstein.pdf", "args": ["-l", "eng", "--psm", "2", "$TMPDIR/000001_rasterize.png", "stdout"]}
+{"tesseract_version": "5.3.2", "system": "Linux", "python": "3.11.6", "argv_slug": "__-l__eng__--psm__2__000001_rasterize.png__stdout", "sourcefile": "resources/ccitt.pdf", "args": ["-l", "eng", "--psm", "2", "$TMPDIR/000001_rasterize.png", "stdout"]}
+{"tesseract_version": "5.3.2", "system": "Linux", "python": "3.11.6", "argv_slug": "__-l__eng__000001_ocr.png__000001_ocr_hocr__hocr__txt", "sourcefile": "resources/lichtenstein.pdf", "args": ["-l", "eng", "$TMPDIR/000001_ocr.png", "$TMPDIR/000001_ocr_hocr", "hocr", "txt"]}
+{"tesseract_version": "5.3.2", "system": "Linux", "python": "3.11.6", "argv_slug": "__-l__eng__--psm__2__000001_rasterize.png__stdout", "sourcefile": "resources/jbig2.pdf", "args": ["-l", "eng", "--psm", "2", "$TMPDIR/000001_rasterize.png", "stdout"]}
+{"tesseract_version": "5.3.2", "system": "Linux", "python": "3.11.6", "argv_slug": "__-l__eng__--psm__2__000001_rasterize.png__stdout", "sourcefile": "resources/jbig2.pdf", "args": ["-l", "eng", "--psm", "2", "$TMPDIR/000001_rasterize.png", "stdout"]}
+{"tesseract_version": "5.3.2", "system": "Linux", "python": "3.11.6", "argv_slug": "__-l__eng__000001_ocr.png__000001_ocr_hocr__hocr__txt", "sourcefile": "resources/aspect.pdf", "args": ["-l", "eng", "$TMPDIR/000001_ocr.png", "$TMPDIR/000001_ocr_hocr", "hocr", "txt"]}
+{"tesseract_version": "5.3.2", "system": "Linux", "python": "3.11.6", "argv_slug": "__-l__eng__000001_ocr.png__000001_ocr_tess__pdf__txt", "sourcefile": "resources/aspect.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000001_ocr.png", "$TMPDIR/000001_ocr_tess", "pdf", "txt"]}
+{"tesseract_version": "5.3.2", "system": "Linux", "python": "3.11.6", "argv_slug": "__-l__eng__000001_ocr.png__000001_ocr_tess__pdf__txt", "sourcefile": "resources/ccitt.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000001_ocr.png", "$TMPDIR/000001_ocr_tess", "pdf", "txt"]}
+{"tesseract_version": "5.3.2", "system": "Linux", "python": "3.11.6", "argv_slug": "__-l__eng__000001_ocr.png__000001_ocr_hocr__hocr__txt", "sourcefile": "resources/graph_ocred.pdf", "args": ["-l", "eng", "$TMPDIR/000001_ocr.png", "$TMPDIR/000001_ocr_hocr", "hocr", "txt"]}
+{"tesseract_version": "5.3.2", "system": "Linux", "python": "3.11.6", "argv_slug": "__-l__eng__000001_ocr.png__000001_ocr_tess__pdf__txt", "sourcefile": "resources/ccitt.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000001_ocr.png", "$TMPDIR/000001_ocr_tess", "pdf", "txt"]}
+{"tesseract_version": "5.3.2", "system": "Linux", "python": "3.11.6", "argv_slug": "__-l__osd__--psm__0__000001_rasterize_preview.jpg__stdout", "sourcefile": "resources/cardinal.pdf", "args": ["-l", "osd", "--psm", "0", "$TMPDIR/000001_rasterize_preview.jpg", "stdout"]}
+{"tesseract_version": "5.3.2", "system": "Linux", "python": "3.11.6", "argv_slug": "__-l__osd__--psm__0__000001_rasterize_preview.jpg__stdout", "sourcefile": "resources/cardinal.pdf", "args": ["-l", "osd", "--psm", "0", "$TMPDIR/000001_rasterize_preview.jpg", "stdout"]}
+{"tesseract_version": "5.3.2", "system": "Linux", "python": "3.11.6", "argv_slug": "__-l__eng__000002_ocr.png__000002_ocr_hocr__hocr__txt", "sourcefile": "resources/multipage.pdf", "args": ["-l", "eng", "/tmp/pytest-of-jb/pytest-42/popen-gw1/test_hocr_api_multipage0/000002_ocr.png", "/tmp/pytest-of-jb/pytest-42/popen-gw1/test_hocr_api_multipage0/000002_ocr_hocr", "hocr", "txt"]}
+{"tesseract_version": "5.3.2", "system": "Linux", "python": "3.11.6", "argv_slug": "__-l__eng__000001_ocr.png__000001_ocr_tess__pdf__txt", "sourcefile": "resources/jbig2.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000001_ocr.png", "$TMPDIR/000001_ocr_tess", "pdf", "txt"]}
+{"tesseract_version": "5.3.2", "system": "Linux", "python": "3.11.6", "argv_slug": "__-l__eng__000001_ocr.png__000001_ocr_tess__pdf__txt", "sourcefile": "resources/jbig2.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000001_ocr.png", "$TMPDIR/000001_ocr_tess", "pdf", "txt"]}
+{"tesseract_version": "5.3.2", "system": "Linux", "python": "3.11.6", "argv_slug": "__-l__osd__--psm__0__000001_rasterize_preview.jpg__stdout", "sourcefile": "resources/cardinal.pdf", "args": ["-l", "osd", "--psm", "0", "$TMPDIR/000001_rasterize_preview.jpg", "stdout"]}
+{"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/lichtenstein.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__osd__--psm__0__000002_rasterize_preview.jpg__stdout", "sourcefile": "resources/cardinal.pdf", "args": ["-l", "osd", "--psm", "0", "$TMPDIR/000002_rasterize_preview.jpg", "stdout"]}
+{"tesseract_version": "5.3.2", "system": "Linux", "python": "3.11.6", "argv_slug": "__-l__osd__--psm__0__000002_rasterize_preview.jpg__stdout", "sourcefile": "resources/cardinal.pdf", "args": ["-l", "osd", "--psm", "0", "$TMPDIR/000002_rasterize_preview.jpg", "stdout"]}
+{"tesseract_version": "5.3.2", "system": "Linux", "python": "3.11.6", "argv_slug": "__-l__osd__--psm__0__000003_rasterize_preview.jpg__stdout", "sourcefile": "resources/cardinal.pdf", "args": ["-l", "osd", "--psm", "0", "$TMPDIR/000003_rasterize_preview.jpg", "stdout"]}
+{"tesseract_version": "5.3.2", "system": "Linux", "python": "3.11.6", "argv_slug": "__-l__osd__--psm__0__000003_rasterize_preview.jpg__stdout", "sourcefile": "resources/cardinal.pdf", "args": ["-l", "osd", "--psm", "0", "$TMPDIR/000003_rasterize_preview.jpg", "stdout"]}
+{"tesseract_version": "5.3.2", "system": "Linux", "python": "3.11.6", "argv_slug": "__-l__osd__--psm__0__000004_rasterize_preview.jpg__stdout", "sourcefile": "resources/cardinal.pdf", "args": ["-l", "osd", "--psm", "0", "$TMPDIR/000004_rasterize_preview.jpg", "stdout"]}
+{"tesseract_version": "5.3.2", "system": "Linux", "python": "3.11.6", "argv_slug": "__-l__osd__--psm__0__000004_rasterize_preview.jpg__stdout", "sourcefile": "resources/cardinal.pdf", "args": ["-l", "osd", "--psm", "0", "$TMPDIR/000004_rasterize_preview.jpg", "stdout"]}
+{"tesseract_version": "5.3.2", "system": "Linux", "python": "3.11.6", "argv_slug": "__-l__osd__--psm__0__000004_rasterize_preview.jpg__stdout", "sourcefile": "resources/cardinal.pdf", "args": ["-l", "osd", "--psm", "0", "$TMPDIR/000004_rasterize_preview.jpg", "stdout"]}
+{"tesseract_version": "5.3.2", "system": "Linux", "python": "3.11.6", "argv_slug": "__-l__eng__000001_ocr.png__000001_ocr_hocr__hocr__txt", "sourcefile": "resources/cardinal.pdf", "args": ["-l", "eng", "$TMPDIR/000001_ocr.png", "$TMPDIR/000001_ocr_hocr", "hocr", "txt"]}
+{"tesseract_version": "5.3.2", "system": "Linux", "python": "3.11.6", "argv_slug": "__-l__eng__000001_ocr.png__000001_ocr_hocr__hocr__txt", "sourcefile": "resources/cardinal.pdf", "args": ["-l", "eng", "$TMPDIR/000001_ocr.png", "$TMPDIR/000001_ocr_hocr", "hocr", "txt"]}
+{"tesseract_version": "5.3.2", "system": "Linux", "python": "3.11.6", "argv_slug": "__-l__eng__000001_ocr.png__000001_ocr_tess__pdf__txt", "sourcefile": "resources/cardinal.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000001_ocr.png", "$TMPDIR/000001_ocr_tess", "pdf", "txt"]}
+{"tesseract_version": "5.3.2", "system": "Linux", "python": "3.11.6", "argv_slug": "__-l__eng__000003_ocr.png__000003_ocr_tess__pdf__txt", "sourcefile": "resources/multipage.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000003_ocr.png", "$TMPDIR/000003_ocr_tess", "pdf", "txt"]}
+{"tesseract_version": "5.3.2", "system": "Linux", "python": "3.11.6", "argv_slug": "__-l__eng__000002_ocr.png__000002_ocr_hocr__hocr__txt", "sourcefile": "resources/cardinal.pdf", "args": ["-l", "eng", "$TMPDIR/000002_ocr.png", "$TMPDIR/000002_ocr_hocr", "hocr", "txt"]}
+{"tesseract_version": "5.3.2", "system": "Linux", "python": "3.11.6", "argv_slug": "__-l__eng__000003_ocr.png__000003_ocr_hocr__hocr__txt", "sourcefile": "resources/cardinal.pdf", "args": ["-l", "eng", "$TMPDIR/000003_ocr.png", "$TMPDIR/000003_ocr_hocr", "hocr", "txt"]}
+{"tesseract_version": "5.3.2", "system": "Linux", "python": "3.11.6", "argv_slug": "__-l__eng__000002_ocr.png__000002_ocr_tess__pdf__txt", "sourcefile": "resources/cardinal.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000002_ocr.png", "$TMPDIR/000002_ocr_tess", "pdf", "txt"]}
+{"tesseract_version": "5.3.2", "system": "Linux", "python": "3.11.6", "argv_slug": "__-l__eng__000005_ocr.png__000005_ocr_tess__pdf__txt", "sourcefile": "resources/multipage.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000005_ocr.png", "$TMPDIR/000005_ocr_tess", "pdf", "txt"]}
+{"tesseract_version": "5.3.2", "system": "Linux", "python": "3.11.6", "argv_slug": "__-l__osd__--psm__0__000001_rasterize_preview.jpg__stdout", "sourcefile": "resources/poster.pdf", "args": ["-l", "osd", "--psm", "0", "$TMPDIR/000001_rasterize_preview.jpg", "stdout"]}
+{"tesseract_version": "5.3.2", "system": "Linux", "python": "3.11.6", "argv_slug": "__-l__eng__000004_ocr.png__000004_ocr_tess__pdf__txt", "sourcefile": "resources/multipage.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000004_ocr.png", "$TMPDIR/000004_ocr_tess", "pdf", "txt"]}
+{"tesseract_version": "5.3.2", "system": "Linux", "python": "3.11.6", "argv_slug": "__-l__eng__000003_ocr.png__000003_ocr_hocr__hocr__txt", "sourcefile": "resources/cardinal.pdf", "args": ["-l", "eng", "$TMPDIR/000003_ocr.png", "$TMPDIR/000003_ocr_hocr", "hocr", "txt"]}
+{"tesseract_version": "5.3.2", "system": "Linux", "python": "3.11.6", "argv_slug": "__-l__eng__000004_ocr.png__000004_ocr_hocr__hocr__txt", "sourcefile": "resources/cardinal.pdf", "args": ["-l", "eng", "$TMPDIR/000004_ocr.png", "$TMPDIR/000004_ocr_hocr", "hocr", "txt"]}
+{"tesseract_version": "5.3.2", "system": "Linux", "python": "3.11.6", "argv_slug": "__-l__eng__000003_ocr.png__000003_ocr_tess__pdf__txt", "sourcefile": "resources/cardinal.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": "3.11.6", "argv_slug": "__-l__eng__000006_ocr.png__000006_ocr_tess__pdf__txt", "sourcefile": "resources/multipage.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000006_ocr.png", "$TMPDIR/000006_ocr_tess", "pdf", "txt"]}
+{"tesseract_version": "5.3.2", "system": "Linux", "python": "3.11.6", "argv_slug": "__-l__eng__000004_ocr.png__000004_ocr_hocr__hocr__txt", "sourcefile": "resources/cardinal.pdf", "args": ["-l", "eng", "$TMPDIR/000004_ocr.png", "$TMPDIR/000004_ocr_hocr", "hocr", "txt"]}
+{"tesseract_version": "5.3.2", "system": "Linux", "python": "3.11.6", "argv_slug": "__-l__eng__000004_ocr.png__000004_ocr_tess__pdf__txt", "sourcefile": "resources/cardinal.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000004_ocr.png", "$TMPDIR/000004_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": "3.11.6", "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/multipage/__-l__eng__000001_ocr.png__000001_ocr_hocr__hocr__txt/hocr.bin

@@ -9,328 +9,300 @@
   <meta name='ocr-capabilities' content='ocr_page ocr_carea ocr_par ocr_line ocrx_word ocrp_wconf'/>
  </head>
  <body>
-  <div class='ocr_page' id='page_1' title='image "/tmp/ocrmypdf.io.ok2cpo6d/000001_ocr.png"; bbox 0 0 1600 1962; ppageno 0; scan_res 300 300'>
-   <div class='ocr_photo' id='block_1_1' title="bbox 77 112 786 1596"></div>
-   <div class='ocr_carea' id='block_1_2' title="bbox 420 1296 617 1429">
-    <p class='ocr_par' id='par_1_1' lang='eng' title="bbox 420 1296 617 1429">
-     <span class='ocr_caption' id='line_1_1' title="bbox 420 1296 499 1326; baseline -0.013 -14; x_size 13.808511; x_descenders 2.8085105; x_ascenders 4.4468088">
-      <span class='ocrx_word' id='word_1_1' title='bbox 420 1306 438 1312; x_wconf 35'>ee</span>
-      <span class='ocrx_word' id='word_1_2' title='bbox 450 1297 458 1323; x_wconf 0'>if</span>
-      <span class='ocrx_word' id='word_1_3' title='bbox 462 1307 468 1319; x_wconf 0'>/)</span>
-      <span class='ocrx_word' id='word_1_4' title='bbox 476 1296 499 1326; x_wconf 21'>J:</span>
-     </span>
-     <span class='ocr_caption' id='line_1_2' title="bbox 451 1299 587 1389; baseline -0.015 -32; x_size 27.571428; x_descenders 5.5714288; x_ascenders 9">
-      <span class='ocrx_word' id='word_1_5' title='bbox 451 1299 464 1357; x_wconf 90'>(</span>
-      <span class='ocrx_word' id='word_1_6' title='bbox 474 1334 500 1389; x_wconf 31'>H}</span>
-      <span class='ocrx_word' id='word_1_7' title='bbox 510 1360 518 1379; x_wconf 51'>:</span>
-      <span class='ocrx_word' id='word_1_8' title='bbox 554 1339 587 1358; x_wconf 15'>cha</span>
-     </span>
-     <span class='ocr_caption' id='line_1_3' title="bbox 453 1371 617 1429; baseline -0.018 -25; x_size 30; x_descenders 7; x_ascenders 9">
-      <span class='ocrx_word' id='word_1_9' title='bbox 453 1371 503 1414; x_wconf 33'>iy</span>
-      <span class='ocrx_word' id='word_1_10' title='bbox 516 1405 528 1429; x_wconf 9'>‘</span>
-      <span class='ocrx_word' id='word_1_11' title='bbox 612 1386 617 1393; x_wconf 0'>H</span>
+  <div class='ocr_page' id='page_1' title='image "/tmp/pytest-of-jb/pytest-42/popen-gw1/test_hocr_api_multipage0/000001_ocr.png"; bbox 0 0 800 981; ppageno 0; scan_res 150 150'>
+   <div class='ocr_carea' id='block_1_1' title="bbox 240 16 750 154">
+    <p class='ocr_par' id='par_1_1' lang='eng' title="bbox 240 16 750 154">
+     <span class='ocr_line' id='line_1_1' title="bbox 240 16 750 154; baseline -0.018 -1; x_size 85; x_descenders 15; x_ascenders 30">
+      <span class='ocrx_word' id='word_1_1' title='bbox 240 33 599 154; x_wconf 87'>Chapter</span>
+      <span class='ocrx_word' id='word_1_2' title='bbox 636 16 750 120; x_wconf 21'>i</span>
      </span>
     </p>
    </div>
-   <div class='ocr_carea' id='block_1_3' title="bbox 294 1634 587 1652">
-    <p class='ocr_par' id='par_1_2' lang='eng' title="bbox 294 1634 587 1652">
-     <span class='ocr_line' id='line_1_4' title="bbox 294 1634 587 1652; baseline -0.01 0; x_size 20.60606; x_descenders 5.151515; x_ascenders 5.151515">
-      <span class='ocrx_word' id='word_1_12' title='bbox 294 1636 360 1652; x_wconf 93'>THEY</span>
-      <span class='ocrx_word' id='word_1_13' title='bbox 374 1635 488 1651; x_wconf 91'>TIP-TOED</span>
-      <span class='ocrx_word' id='word_1_14' title='bbox 502 1634 587 1650; x_wconf 92'>ALONG.</span>
-     </span>
-    </p>
-   </div>
-   <div class='ocr_carea' id='block_1_4' title="bbox 540 938 573 1064">
-    <p class='ocr_par' id='par_1_3' lang='eng' title="bbox 538 938 628 1064">
-     <span class='ocr_caption' id='line_1_5' title="bbox 540 938 573 1064; baseline -0.011 -0.022; x_size 140; x_descenders 21; x_ascenders 50">
-      <span class='ocrx_word' id='word_1_15' title='bbox 540 938 628 1064; x_wconf 4'>N</span>
-     </span>
-    </p>
-   </div>
-   <div class='ocr_carea' id='block_1_5' title="bbox 443 65 1501 328">
-    <p class='ocr_par' id='par_1_4' lang='eng' title="bbox 443 65 1501 328">
-     <span class='ocr_textfloat' id='line_1_6' title="bbox 443 65 1501 328; baseline -0.003 -121; x_size 188; x_descenders 42; x_ascenders 64">
-      <span class='ocrx_word' id='word_1_16' title='bbox 443 275 505 328; x_wconf 30'>:</span>
-      <span class='ocrx_word' id='word_1_17' title='bbox 578 65 1207 292; x_wconf 67'>chapter</span>
-      <span class='ocrx_word' id='word_1_18' title='bbox 1400 106 1501 187; x_wconf 31'>J</span>
-     </span>
-    </p>
-   </div>
-   <div class='ocr_carea' id='block_1_6' title="bbox 760 394 1534 436">
-    <p class='ocr_par' id='par_1_5' lang='eng' title="bbox 760 394 1534 436">
-     <span class='ocr_textfloat' id='line_1_7' title="bbox 760 394 1534 436; baseline -0.005 -9; x_size 41; x_descenders 10; x_ascenders 10">
-      <span class='ocrx_word' id='word_1_19' title='bbox 760 397 789 428; x_wconf 92'>E</span>
-      <span class='ocrx_word' id='word_1_20' title='bbox 822 399 905 427; x_wconf 93'>went</span>
-      <span class='ocrx_word' id='word_1_21' title='bbox 925 399 1099 436; x_wconf 90'>tip-toeing</span>
-      <span class='ocrx_word' id='word_1_22' title='bbox 1120 396 1215 436; x_wconf 96'>along</span>
-      <span class='ocrx_word' id='word_1_23' title='bbox 1243 406 1262 426; x_wconf 95'>a</span>
-      <span class='ocrx_word' id='word_1_24' title='bbox 1285 394 1364 435; x_wconf 96'>path</span>
-      <span class='ocrx_word' id='word_1_25' title='bbox 1388 399 1534 434; x_wconf 96'>amongst</span>
-     </span>
-    </p>
-   </div>
-   <div class='ocr_carea' id='block_1_7' title="bbox 820 450 1544 1688">
-    <p class='ocr_par' id='par_1_6' lang='eng' title="bbox 820 450 1541 1177">
-     <span class='ocr_line' id='line_1_8' title="bbox 820 450 1534 484; baseline -0.004 -1; x_size 41.3563; x_descenders 10.356298; x_ascenders 10">
-      <span class='ocrx_word' id='word_1_26' title='bbox 820 452 875 483; x_wconf 96'>the</span>
-      <span class='ocrx_word' id='word_1_27' title='bbox 896 454 978 484; x_wconf 96'>trees</span>
-      <span class='ocrx_word' id='word_1_28' title='bbox 1000 453 1081 483; x_wconf 96'>back</span>
-      <span class='ocrx_word' id='word_1_29' title='bbox 1103 451 1238 483; x_wconf 96'>towards</span>
-      <span class='ocrx_word' id='word_1_30' title='bbox 1262 451 1315 482; x_wconf 96'>the</span>
-      <span class='ocrx_word' id='word_1_31' title='bbox 1337 450 1399 482; x_wconf 95'>end</span>
-      <span class='ocrx_word' id='word_1_32' title='bbox 1421 450 1455 480; x_wconf 95'>of</span>
-      <span class='ocrx_word' id='word_1_33' title='bbox 1480 450 1534 480; x_wconf 96'>the</span>
-     </span>
-     <span class='ocr_line' id='line_1_9' title="bbox 822 508 1535 551; baseline -0.004 -11; x_size 41; x_descenders 11; x_ascenders 10">
-      <span class='ocrx_word' id='word_1_34' title='bbox 822 510 958 540; x_wconf 92'>widow’s</span>
-      <span class='ocrx_word' id='word_1_35' title='bbox 985 510 1116 551; x_wconf 96'>garden,</span>
-      <span class='ocrx_word' id='word_1_36' title='bbox 1141 508 1291 549; x_wconf 96'>stooping</span>
-      <span class='ocrx_word' id='word_1_37' title='bbox 1319 508 1410 538; x_wconf 96'>down</span>
-      <span class='ocrx_word' id='word_1_38' title='bbox 1440 517 1474 538; x_wconf 95'>so</span>
-      <span class='ocrx_word' id='word_1_39' title='bbox 1502 517 1535 537; x_wconf 96'>as</span>
-     </span>
-     <span class='ocr_line' id='line_1_10' title="bbox 822 564 1532 606; baseline -0.006 -8; x_size 41; x_descenders 10; x_ascenders 10">
-      <span class='ocrx_word' id='word_1_40' title='bbox 822 568 877 598; x_wconf 96'>the</span>
-      <span class='ocrx_word' id='word_1_41' title='bbox 889 567 1042 598; x_wconf 92'>branches</span>
-      <span class='ocrx_word' id='word_1_42' title='bbox 1057 566 1212 598; x_wconf 91'>wouldn’t</span>
-      <span class='ocrx_word' id='word_1_43' title='bbox 1233 575 1340 606; x_wconf 96'>scrape</span>
-      <span class='ocrx_word' id='word_1_44' title='bbox 1355 575 1413 596; x_wconf 96'>our</span>
-      <span class='ocrx_word' id='word_1_45' title='bbox 1428 564 1532 595; x_wconf 77'>heads.</span>
-     </span>
-     <span class='ocr_line' id='line_1_11' title="bbox 825 621 1536 664; baseline -0.007 -7; x_size 42; x_descenders 10; x_ascenders 11">
-      <span class='ocrx_word' id='word_1_46' title='bbox 825 624 930 656; x_wconf 96'>When</span>
-      <span class='ocrx_word' id='word_1_47' title='bbox 951 634 997 656; x_wconf 96'>we</span>
-      <span class='ocrx_word' id='word_1_48' title='bbox 1020 634 1082 656; x_wconf 96'>was</span>
-      <span class='ocrx_word' id='word_1_49' title='bbox 1116 623 1245 664; x_wconf 96'>passing</span>
-      <span class='ocrx_word' id='word_1_50' title='bbox 1265 623 1306 664; x_wconf 96'>by</span>
-      <span class='ocrx_word' id='word_1_51' title='bbox 1329 622 1382 653; x_wconf 96'>the</span>
-      <span class='ocrx_word' id='word_1_52' title='bbox 1407 621 1536 652; x_wconf 96'>kitchen</span>
-     </span>
-     <span class='ocr_line' id='line_1_12' title="bbox 825 678 1532 714; baseline -0.007 -1; x_size 41.3563; x_descenders 10.356298; x_ascenders 10">
-      <span class='ocrx_word' id='word_1_53' title='bbox 825 682 842 713; x_wconf 96'>I</span>
-      <span class='ocrx_word' id='word_1_54' title='bbox 869 682 926 714; x_wconf 96'>fell</span>
-      <span class='ocrx_word' id='word_1_55' title='bbox 955 692 1028 714; x_wconf 96'>over</span>
-      <span class='ocrx_word' id='word_1_56' title='bbox 1049 692 1068 713; x_wconf 94'>a</span>
-      <span class='ocrx_word' id='word_1_57' title='bbox 1088 684 1165 712; x_wconf 78'>root</span>
-      <span class='ocrx_word' id='word_1_58' title='bbox 1193 681 1256 712; x_wconf 95'>and</span>
-      <span class='ocrx_word' id='word_1_59' title='bbox 1285 680 1377 711; x_wconf 96'>made</span>
-      <span class='ocrx_word' id='word_1_60' title='bbox 1398 690 1416 710; x_wconf 96'>a</span>
-      <span class='ocrx_word' id='word_1_61' title='bbox 1438 678 1532 710; x_wconf 96'>noise.</span>
-     </span>
-     <span class='ocr_line' id='line_1_13' title="bbox 825 735 1538 771; baseline -0.006 1; x_size 42.86314; x_descenders 9.8631411; x_ascenders 13">
-      <span class='ocrx_word' id='word_1_62' title='bbox 825 738 883 771; x_wconf 88'>We</span>
-      <span class='ocrx_word' id='word_1_63' title='bbox 926 739 1101 771; x_wconf 85'>scrouched</span>
-      <span class='ocrx_word' id='word_1_64' title='bbox 1137 739 1228 769; x_wconf 96'>down</span>
-      <span class='ocrx_word' id='word_1_65' title='bbox 1265 738 1330 768; x_wconf 96'>and</span>
-      <span class='ocrx_word' id='word_1_66' title='bbox 1360 736 1426 767; x_wconf 92'>laid</span>
-      <span class='ocrx_word' id='word_1_67' title='bbox 1460 735 1538 768; x_wconf 88'>still.</span>
-     </span>
-     <span class='ocr_line' id='line_1_14' title="bbox 826 793 1539 836; baseline -0.007 -8; x_size 41; x_descenders 10; x_ascenders 10">
-      <span class='ocrx_word' id='word_1_68' title='bbox 826 797 904 828; x_wconf 92'>Miss</span>
-      <span class='ocrx_word' id='word_1_69' title='bbox 945 797 1103 828; x_wconf 91'>Watson’s</span>
-      <span class='ocrx_word' id='word_1_70' title='bbox 1152 795 1207 836; x_wconf 92'>big</span>
-      <span class='ocrx_word' id='word_1_71' title='bbox 1256 795 1378 835; x_wconf 94'>nigger,</span>
-      <span class='ocrx_word' id='word_1_72' title='bbox 1423 793 1539 824; x_wconf 96'>named</span>
-     </span>
-     <span class='ocr_line' id='line_1_15' title="bbox 827 850 1539 894; baseline -0.007 -9; x_size 42; x_descenders 11; x_ascenders 11">
-      <span class='ocrx_word' id='word_1_73' title='bbox 827 854 907 892; x_wconf 96'>Jim,</span>
-      <span class='ocrx_word' id='word_1_74' title='bbox 925 864 986 885; x_wconf 96'>was</span>
-      <span class='ocrx_word' id='word_1_75' title='bbox 1014 854 1134 894; x_wconf 96'>setting</span>
-      <span class='ocrx_word' id='word_1_76' title='bbox 1152 853 1186 883; x_wconf 96'>in</span>
-      <span class='ocrx_word' id='word_1_77' title='bbox 1208 852 1264 883; x_wconf 96'>the</span>
-      <span class='ocrx_word' id='word_1_78' title='bbox 1285 851 1419 882; x_wconf 96'>kitchen</span>
-      <span class='ocrx_word' id='word_1_79' title='bbox 1441 850 1539 888; x_wconf 85'>door</span>
-      <span class='ocrx_word' id='word_1_80' title='bbox 1520 846 1543 898; x_wconf 85'>;</span>
-     </span>
-     <span class='ocr_line' id='line_1_16' title="bbox 829 908 1539 950; baseline -0.008 -7; x_size 40; x_descenders 10; x_ascenders 9">
-      <span class='ocrx_word' id='word_1_81' title='bbox 829 922 875 943; x_wconf 96'>we</span>
-      <span class='ocrx_word' id='word_1_82' title='bbox 897 912 992 943; x_wconf 95'>could</span>
-      <span class='ocrx_word' id='word_1_83' title='bbox 1013 922 1062 943; x_wconf 96'>see</span>
-      <span class='ocrx_word' id='word_1_84' title='bbox 1077 911 1146 941; x_wconf 95'>him</span>
-      <span class='ocrx_word' id='word_1_85' title='bbox 1162 912 1267 950; x_wconf 95'>pretty</span>
-      <span class='ocrx_word' id='word_1_86' title='bbox 1291 909 1384 946; x_wconf 96'>clear,</span>
-      <span class='ocrx_word' id='word_1_87' title='bbox 1409 908 1539 938; x_wconf 96'>because</span>
-     </span>
-     <span class='ocr_line' id='line_1_17' title="bbox 832 961 1540 1006; baseline -0.01 -8; x_size 42; x_descenders 11; x_ascenders 11">
-      <span class='ocrx_word' id='word_1_88' title='bbox 832 967 921 998; x_wconf 96'>there</span>
-      <span class='ocrx_word' id='word_1_89' title='bbox 944 976 1004 997; x_wconf 96'>was</span>
-      <span class='ocrx_word' id='word_1_90' title='bbox 1037 976 1055 996; x_wconf 93'>a</span>
-      <span class='ocrx_word' id='word_1_91' title='bbox 1084 965 1167 1006; x_wconf 93'>light</span>
-      <span class='ocrx_word' id='word_1_92' title='bbox 1200 963 1318 995; x_wconf 96'>behind</span>
-      <span class='ocrx_word' id='word_1_93' title='bbox 1350 962 1430 992; x_wconf 95'>him.</span>
-      <span class='ocrx_word' id='word_1_94' title='bbox 1490 961 1540 992; x_wconf 95'>He</span>
-     </span>
-     <span class='ocr_line' id='line_1_18' title="bbox 835 1018 1541 1065; baseline -0.01 -10; x_size 41; x_descenders 10; x_ascenders 10">
-      <span class='ocrx_word' id='word_1_95' title='bbox 835 1026 890 1065; x_wconf 96'>got</span>
-      <span class='ocrx_word' id='word_1_96' title='bbox 926 1034 970 1064; x_wconf 95'>up</span>
-      <span class='ocrx_word' id='word_1_97' title='bbox 1006 1023 1068 1054; x_wconf 96'>and</span>
-      <span class='ocrx_word' id='word_1_98' title='bbox 1104 1021 1262 1052; x_wconf 95'>stretched</span>
-      <span class='ocrx_word' id='word_1_99' title='bbox 1297 1019 1347 1051; x_wconf 95'>his</span>
-      <span class='ocrx_word' id='word_1_100' title='bbox 1369 1018 1448 1050; x_wconf 96'>neck</span>
-      <span class='ocrx_word' id='word_1_101' title='bbox 1484 1020 1541 1048; x_wconf 96'>out</span>
-     </span>
-     <span class='ocr_line' id='line_1_19' title="bbox 835 1074 1540 1117; baseline -0.01 -5; x_size 41; x_descenders 10; x_ascenders 11">
-      <span class='ocrx_word' id='word_1_102' title='bbox 835 1081 932 1112; x_wconf 96'>about</span>
-      <span class='ocrx_word' id='word_1_103' title='bbox 955 1090 974 1111; x_wconf 96'>a</span>
-      <span class='ocrx_word' id='word_1_104' title='bbox 994 1080 1130 1116; x_wconf 96'>minute,</span>
-      <span class='ocrx_word' id='word_1_105' title='bbox 1161 1077 1320 1117; x_wconf 94'>listening.</span>
-      <span class='ocrx_word' id='word_1_106' title='bbox 1381 1075 1472 1106; x_wconf 95'>Then</span>
-      <span class='ocrx_word' id='word_1_107' title='bbox 1501 1074 1540 1105; x_wconf 96'>he</span>
-     </span>
-     <span class='ocr_line' id='line_1_20' title="bbox 830 1131 909 1177; baseline 0 -10; x_size 46; x_descenders 10; x_ascenders 15">
-      <span class='ocrx_word' id='word_1_108' title='bbox 830 1131 909 1177; x_wconf 96'>says,</span>
+   <div class='ocr_carea' id='block_1_2' title="bbox 250 187 768 275">
+    <p class='ocr_par' id='par_1_2' lang='eng' title="bbox 250 188 305 199">
+     <span class='ocr_line' id='line_1_2' title="bbox 250 188 305 199; baseline -0.036 0; x_size 21.5; x_descenders 5.5; x_ascenders 5.5">
+      <span class='ocrx_word' id='word_1_3' title='bbox 250 188 305 199; x_wconf 33'>lad</span>
      </span>
     </p>
 
-    <p class='ocr_par' id='par_1_7' lang='eng' title="bbox 898 1194 1129 1226">
-     <span class='ocr_line' id='line_1_21' title="bbox 898 1194 1129 1226; baseline -0.013 1; x_size 42.565586; x_descenders 10.5; x_ascenders 10.774194">
-      <span class='ocrx_word' id='word_1_109' title='bbox 898 1198 920 1212; x_wconf 43'>**</span>
-      <span class='ocrx_word' id='word_1_110' title='bbox 930 1195 1012 1226; x_wconf 63'>Who</span>
-      <span class='ocrx_word' id='word_1_111' title='bbox 1027 1194 1129 1225; x_wconf 94'>dah?”</span>
+    <p class='ocr_par' id='par_1_3' lang='eng' title="bbox 260 187 768 275">
+     <span class='ocr_line' id='line_1_3' title="bbox 260 187 767 218; baseline -0.004 -4; x_size 20; x_descenders 5; x_ascenders 5">
+      <span class='ocrx_word' id='word_1_4' title='bbox 260 201 264 204; x_wconf 29'>‘</span>
+      <span class='ocrx_word' id='word_1_5' title='bbox 344 187 394 216; x_wconf 79'>We</span>
+      <span class='ocrx_word' id='word_1_6' title='bbox 411 199 452 214; x_wconf 93'>went</span>
+      <span class='ocrx_word' id='word_1_7' title='bbox 463 198 550 218; x_wconf 78'>tip-toeing</span>
+      <span class='ocrx_word' id='word_1_8' title='bbox 560 198 608 218; x_wconf 96'>along</span>
+      <span class='ocrx_word' id='word_1_9' title='bbox 622 203 631 213; x_wconf 96'>a</span>
+      <span class='ocrx_word' id='word_1_10' title='bbox 643 197 682 217; x_wconf 96'>path</span>
+      <span class='ocrx_word' id='word_1_11' title='bbox 694 200 767 217; x_wconf 96'>amongst</span>
      </span>
-    </p>
-
-    <p class='ocr_par' id='par_1_8' lang='eng' title="bbox 833 1246 1544 1688">
-     <span class='ocr_line' id='line_1_22' title="bbox 896 1246 1542 1287; baseline -0.012 -3; x_size 41; x_descenders 9; x_ascenders 11">
-      <span class='ocrx_word' id='word_1_112' title='bbox 896 1252 948 1284; x_wconf 96'>He</span>
-      <span class='ocrx_word' id='word_1_113' title='bbox 975 1251 1111 1283; x_wconf 95'>listened</span>
-      <span class='ocrx_word' id='word_1_114' title='bbox 1134 1259 1219 1281; x_wconf 96'>some</span>
-      <span class='ocrx_word' id='word_1_115' title='bbox 1248 1258 1355 1287; x_wconf 96'>more;</span>
-      <span class='ocrx_word' id='word_1_116' title='bbox 1390 1247 1466 1278; x_wconf 96'>then</span>
-      <span class='ocrx_word' id='word_1_117' title='bbox 1504 1246 1542 1277; x_wconf 96'>he</span>
+     <span class='ocr_line' id='line_1_4' title="bbox 410 225 767 242; baseline -0.003 -1; x_size 20.238094; x_descenders 5.2380953; x_ascenders 5">
+      <span class='ocrx_word' id='word_1_12' title='bbox 410 226 438 241; x_wconf 96'>the</span>
+      <span class='ocrx_word' id='word_1_13' title='bbox 448 227 489 242; x_wconf 96'>trees</span>
+      <span class='ocrx_word' id='word_1_14' title='bbox 500 226 541 241; x_wconf 96'>back</span>
+      <span class='ocrx_word' id='word_1_15' title='bbox 552 226 619 241; x_wconf 96'>towards</span>
+      <span class='ocrx_word' id='word_1_16' title='bbox 631 225 657 241; x_wconf 97'>the</span>
+      <span class='ocrx_word' id='word_1_17' title='bbox 669 225 700 241; x_wconf 96'>end</span>
+      <span class='ocrx_word' id='word_1_18' title='bbox 711 225 727 240; x_wconf 96'>of</span>
+      <span class='ocrx_word' id='word_1_19' title='bbox 740 225 767 240; x_wconf 96'>the</span>
      </span>
-     <span class='ocr_line' id='line_1_23' title="bbox 834 1303 1542 1350; baseline -0.011 -8; x_size 42; x_descenders 10; x_ascenders 11">
-      <span class='ocrx_word' id='word_1_118' title='bbox 834 1320 923 1343; x_wconf 85'>come</span>
-      <span class='ocrx_word' id='word_1_119' title='bbox 974 1308 1147 1350; x_wconf 85'>tip-toeing</span>
-      <span class='ocrx_word' id='word_1_120' title='bbox 1195 1307 1286 1338; x_wconf 93'>down</span>
-      <span class='ocrx_word' id='word_1_121' title='bbox 1337 1306 1401 1336; x_wconf 46'>and-</span>
-      <span class='ocrx_word' id='word_1_122' title='bbox 1452 1303 1542 1335; x_wconf 96'>stood</span>
-     </span>
-     <span class='ocr_line' id='line_1_24' title="bbox 834 1359 1542 1407; baseline -0.011 -10; x_size 41; x_descenders 10; x_ascenders 10">
-      <span class='ocrx_word' id='word_1_123' title='bbox 834 1366 921 1407; x_wconf 95'>right</span>
-      <span class='ocrx_word' id='word_1_124' title='bbox 942 1366 1082 1396; x_wconf 95'>between</span>
-      <span class='ocrx_word' id='word_1_125' title='bbox 1104 1373 1161 1402; x_wconf 96'>us;</span>
-      <span class='ocrx_word' id='word_1_126' title='bbox 1184 1372 1228 1393; x_wconf 96'>we</span>
-      <span class='ocrx_word' id='word_1_127' title='bbox 1249 1361 1344 1392; x_wconf 96'>could</span>
-      <span class='ocrx_word' id='word_1_128' title='bbox 1365 1370 1382 1391; x_wconf 96'>a</span>
-      <span class='ocrx_word' id='word_1_129' title='bbox 1404 1359 1542 1390; x_wconf 96'>touched</span>
-     </span>
-     <span class='ocr_line' id='line_1_25' title="bbox 833 1416 1542 1463; baseline -0.013 -8; x_size 42; x_descenders 11; x_ascenders 10">
-      <span class='ocrx_word' id='word_1_130' title='bbox 833 1424 912 1462; x_wconf 95'>him,</span>
-      <span class='ocrx_word' id='word_1_131' title='bbox 929 1422 1046 1463; x_wconf 94'>nearly.</span>
-      <span class='ocrx_word' id='word_1_132' title='bbox 1092 1420 1185 1458; x_wconf 95'>Well,</span>
-      <span class='ocrx_word' id='word_1_133' title='bbox 1208 1418 1306 1460; x_wconf 96'>likely</span>
-      <span class='ocrx_word' id='word_1_134' title='bbox 1320 1418 1347 1448; x_wconf 91'>it</span>
-      <span class='ocrx_word' id='word_1_135' title='bbox 1376 1427 1438 1448; x_wconf 91'>was</span>
-      <span class='ocrx_word' id='word_1_136' title='bbox 1462 1416 1542 1447; x_wconf 91'>min-</span>
-     </span>
-     <span class='ocr_line' id='line_1_26' title="bbox 835 1473 1544 1512; baseline -0.014 1; x_size 41.3563; x_descenders 10.356298; x_ascenders 10">
-      <span class='ocrx_word' id='word_1_137' title='bbox 835 1484 905 1512; x_wconf 96'>utes</span>
-      <span class='ocrx_word' id='word_1_138' title='bbox 933 1481 996 1511; x_wconf 96'>and</span>
-      <span class='ocrx_word' id='word_1_139' title='bbox 1024 1478 1165 1510; x_wconf 96'>minutes</span>
-      <span class='ocrx_word' id='word_1_140' title='bbox 1185 1477 1259 1508; x_wconf 96'>that</span>
-      <span class='ocrx_word' id='word_1_141' title='bbox 1280 1475 1370 1507; x_wconf 93'>there</span>
-      <span class='ocrx_word' id='word_1_142' title='bbox 1385 1473 1498 1504; x_wconf 91'>warn’t</span>
-      <span class='ocrx_word' id='word_1_143' title='bbox 1526 1483 1544 1503; x_wconf 96'>a</span>
-     </span>
-     <span class='ocr_line' id='line_1_27' title="bbox 833 1530 1543 1575; baseline -0.014 -6; x_size 38; x_descenders 7; x_ascenders 10">
-      <span class='ocrx_word' id='word_1_144' title='bbox 833 1538 946 1575; x_wconf 96'>sound,</span>
-      <span class='ocrx_word' id='word_1_145' title='bbox 984 1536 1050 1568; x_wconf 96'>and</span>
-      <span class='ocrx_word' id='word_1_146' title='bbox 1083 1545 1129 1566; x_wconf 96'>we</span>
-      <span class='ocrx_word' id='word_1_147' title='bbox 1171 1533 1213 1564; x_wconf 96'>all</span>
-      <span class='ocrx_word' id='word_1_148' title='bbox 1254 1532 1344 1563; x_wconf 96'>there</span>
-      <span class='ocrx_word' id='word_1_149' title='bbox 1385 1540 1419 1562; x_wconf 89'>so</span>
-      <span class='ocrx_word' id='word_1_150' title='bbox 1461 1530 1543 1560; x_wconf 89'>close</span>
-     </span>
-     <span class='ocr_line' id='line_1_28' title="bbox 833 1587 1544 1634; baseline -0.014 -10; x_size 42; x_descenders 11; x_ascenders 10">
-      <span class='ocrx_word' id='word_1_151' title='bbox 833 1592 988 1634; x_wconf 93'>together.</span>
-      <span class='ocrx_word' id='word_1_152' title='bbox 1045 1590 1148 1621; x_wconf 67'>‘There</span>
-      <span class='ocrx_word' id='word_1_153' title='bbox 1176 1597 1240 1619; x_wconf 96'>was</span>
-      <span class='ocrx_word' id='word_1_154' title='bbox 1264 1598 1283 1619; x_wconf 96'>a</span>
-      <span class='ocrx_word' id='word_1_155' title='bbox 1310 1587 1399 1627; x_wconf 96'>place</span>
-      <span class='ocrx_word' id='word_1_156' title='bbox 1428 1595 1470 1616; x_wconf 96'>on</span>
-      <span class='ocrx_word' id='word_1_157' title='bbox 1491 1594 1544 1625; x_wconf 96'>my</span>
-     </span>
-     <span class='ocr_line' id='line_1_29' title="bbox 834 1641 1543 1688; baseline -0.014 -7; x_size 41; x_descenders 10; x_ascenders 10">
-      <span class='ocrx_word' id='word_1_158' title='bbox 834 1650 929 1682; x_wconf 96'>ankle</span>
-      <span class='ocrx_word' id='word_1_159' title='bbox 964 1648 1036 1680; x_wconf 96'>that</span>
-      <span class='ocrx_word' id='word_1_160' title='bbox 1070 1650 1126 1688; x_wconf 96'>got</span>
-      <span class='ocrx_word' id='word_1_161' title='bbox 1161 1648 1194 1678; x_wconf 96'>to</span>
-      <span class='ocrx_word' id='word_1_162' title='bbox 1230 1644 1385 1684; x_wconf 96'>itching;</span>
-      <span class='ocrx_word' id='word_1_163' title='bbox 1426 1642 1486 1672; x_wconf 96'>but</span>
-      <span class='ocrx_word' id='word_1_164' title='bbox 1528 1641 1543 1672; x_wconf 93'>I</span>
+     <span class='ocr_line' id='line_1_5' title="bbox 411 254 768 275; baseline -0.003 -5; x_size 20; x_descenders 5; x_ascenders 5">
+      <span class='ocrx_word' id='word_1_20' title='bbox 411 255 479 270; x_wconf 90'>widow’s</span>
+      <span class='ocrx_word' id='word_1_21' title='bbox 493 255 558 275; x_wconf 96'>garden,</span>
+      <span class='ocrx_word' id='word_1_22' title='bbox 571 254 645 274; x_wconf 96'>stooping</span>
+      <span class='ocrx_word' id='word_1_23' title='bbox 660 254 705 269; x_wconf 96'>down</span>
+      <span class='ocrx_word' id='word_1_24' title='bbox 720 259 737 269; x_wconf 95'>so</span>
+      <span class='ocrx_word' id='word_1_25' title='bbox 751 259 768 269; x_wconf 95'>as</span>
      </span>
     </p>
    </div>
-   <div class='ocr_carea' id='block_1_8' title="bbox 88 1699 1545 1927">
-    <p class='ocr_par' id='par_1_9' lang='eng' title="bbox 88 1699 1545 1927">
-     <span class='ocr_header' id='line_1_30' title="bbox 88 1699 1545 1752; baseline -0.013 -4; x_size 39; x_descenders 8; x_ascenders 10">
-      <span class='ocrx_word' id='word_1_165' title='bbox 88 1716 191 1747; x_wconf 91'>dasn’t</span>
-      <span class='ocrx_word' id='word_1_166' title='bbox 216 1714 339 1746; x_wconf 96'>scratch</span>
-      <span class='ocrx_word' id='word_1_167' title='bbox 356 1714 395 1752; x_wconf 96'>it;</span>
-      <span class='ocrx_word' id='word_1_168' title='bbox 417 1713 481 1744; x_wconf 96'>and</span>
-      <span class='ocrx_word' id='word_1_169' title='bbox 502 1711 580 1742; x_wconf 96'>then</span>
-      <span class='ocrx_word' id='word_1_170' title='bbox 602 1720 656 1751; x_wconf 93'>my</span>
-      <span class='ocrx_word' id='word_1_171' title='bbox 670 1719 722 1741; x_wconf 93'>ear</span>
-      <span class='ocrx_word' id='word_1_172' title='bbox 748 1709 852 1749; x_wconf 96'>begun</span>
-      <span class='ocrx_word' id='word_1_173' title='bbox 877 1709 910 1738; x_wconf 96'>to</span>
-      <span class='ocrx_word' id='word_1_174' title='bbox 932 1706 1014 1744; x_wconf 95'>itch;</span>
-      <span class='ocrx_word' id='word_1_175' title='bbox 1035 1705 1099 1736; x_wconf 96'>and</span>
-      <span class='ocrx_word' id='word_1_176' title='bbox 1114 1705 1191 1736; x_wconf 96'>next</span>
-      <span class='ocrx_word' id='word_1_177' title='bbox 1206 1713 1259 1744; x_wconf 96'>my</span>
-      <span class='ocrx_word' id='word_1_178' title='bbox 1273 1701 1366 1739; x_wconf 96'>back,</span>
-      <span class='ocrx_word' id='word_1_179' title='bbox 1384 1699 1472 1740; x_wconf 92'>right</span>
-      <span class='ocrx_word' id='word_1_180' title='bbox 1492 1699 1545 1729; x_wconf 92'>be-</span>
+   <div class='ocr_photo' id='block_1_3' title="bbox 40 28 402 806"></div>
+   <div class='ocr_carea' id='block_1_4' title="bbox 44 282 772 964">
+    <p class='ocr_par' id='par_1_4' lang='eng' title="bbox 411 282 770 588">
+     <span class='ocr_line' id='line_1_6' title="bbox 411 282 766 303; baseline -0.006 -4; x_size 20; x_descenders 5; x_ascenders 5">
+      <span class='ocrx_word' id='word_1_26' title='bbox 411 284 438 299; x_wconf 96'>the</span>
+      <span class='ocrx_word' id='word_1_27' title='bbox 444 284 521 299; x_wconf 93'>branches</span>
+      <span class='ocrx_word' id='word_1_28' title='bbox 528 283 606 299; x_wconf 92'>wouldn’t</span>
+      <span class='ocrx_word' id='word_1_29' title='bbox 616 288 670 303; x_wconf 96'>scrape</span>
+      <span class='ocrx_word' id='word_1_30' title='bbox 678 287 706 298; x_wconf 96'>our</span>
+      <span class='ocrx_word' id='word_1_31' title='bbox 714 282 766 297; x_wconf 96'>heads.</span>
      </span>
-     <span class='ocr_header' id='line_1_31' title="bbox 88 1756 1544 1813; baseline -0.012 -9; x_size 41; x_descenders 10; x_ascenders 10">
-      <span class='ocrx_word' id='word_1_181' title='bbox 88 1777 188 1804; x_wconf 96'>tween</span>
-      <span class='ocrx_word' id='word_1_182' title='bbox 214 1782 267 1813; x_wconf 96'>my</span>
-      <span class='ocrx_word' id='word_1_183' title='bbox 289 1771 462 1803; x_wconf 96'>shoulders.</span>
-      <span class='ocrx_word' id='word_1_184' title='bbox 520 1768 648 1800; x_wconf 94'>Seemed</span>
-      <span class='ocrx_word' id='word_1_185' title='bbox 672 1767 737 1798; x_wconf 93'>like</span>
-      <span class='ocrx_word' id='word_1_186' title='bbox 764 1766 813 1796; x_wconf 89'>I’d</span>
-      <span class='ocrx_word' id='word_1_187' title='bbox 836 1765 887 1796; x_wconf 96'>die</span>
-      <span class='ocrx_word' id='word_1_188' title='bbox 910 1764 937 1794; x_wconf 96'>if</span>
-      <span class='ocrx_word' id='word_1_189' title='bbox 960 1763 976 1794; x_wconf 92'>I</span>
-      <span class='ocrx_word' id='word_1_190' title='bbox 999 1762 1142 1794; x_wconf 88'>couldn’t</span>
-      <span class='ocrx_word' id='word_1_191' title='bbox 1168 1760 1301 1792; x_wconf 96'>scratch.</span>
-      <span class='ocrx_word' id='word_1_192' title='bbox 1360 1757 1453 1795; x_wconf 78'>Well,</span>
-      <span class='ocrx_word' id='word_1_193' title='bbox 1480 1756 1544 1787; x_wconf 95'>I’ve</span>
+     <span class='ocr_line' id='line_1_7' title="bbox 412 311 768 332; baseline -0.006 -4; x_size 21; x_descenders 5; x_ascenders 5">
+      <span class='ocrx_word' id='word_1_32' title='bbox 412 312 465 328; x_wconf 94'>When</span>
+      <span class='ocrx_word' id='word_1_33' title='bbox 476 317 498 328; x_wconf 96'>we</span>
+      <span class='ocrx_word' id='word_1_34' title='bbox 510 317 541 328; x_wconf 95'>was</span>
+      <span class='ocrx_word' id='word_1_35' title='bbox 558 312 623 332; x_wconf 95'>passing</span>
+      <span class='ocrx_word' id='word_1_36' title='bbox 633 312 653 332; x_wconf 96'>by</span>
+      <span class='ocrx_word' id='word_1_37' title='bbox 664 311 691 326; x_wconf 97'>the</span>
+      <span class='ocrx_word' id='word_1_38' title='bbox 704 311 768 326; x_wconf 96'>kitchen</span>
      </span>
-     <span class='ocr_header' id='line_1_32' title="bbox 88 1815 1544 1868; baseline -0.012 -7; x_size 42; x_descenders 11; x_ascenders 11">
-      <span class='ocrx_word' id='word_1_194' title='bbox 88 1830 214 1862; x_wconf 96'>noticed</span>
-      <span class='ocrx_word' id='word_1_195' title='bbox 237 1830 309 1860; x_wconf 96'>that</span>
-      <span class='ocrx_word' id='word_1_196' title='bbox 330 1828 425 1868; x_wconf 96'>thing</span>
-      <span class='ocrx_word' id='word_1_197' title='bbox 447 1827 554 1867; x_wconf 96'>plenty</span>
-      <span class='ocrx_word' id='word_1_198' title='bbox 577 1826 611 1856; x_wconf 96'>of</span>
-      <span class='ocrx_word' id='word_1_199' title='bbox 625 1824 718 1855; x_wconf 95'>times</span>
-      <span class='ocrx_word' id='word_1_200' title='bbox 734 1824 828 1855; x_wconf 95'>since.</span>
-      <span class='ocrx_word' id='word_1_201' title='bbox 875 1821 907 1852; x_wconf 96'>If</span>
-      <span class='ocrx_word' id='word_1_202' title='bbox 929 1831 991 1862; x_wconf 96'>you</span>
-      <span class='ocrx_word' id='word_1_203' title='bbox 1014 1830 1066 1851; x_wconf 96'>are</span>
-      <span class='ocrx_word' id='word_1_204' title='bbox 1081 1818 1158 1851; x_wconf 96'>with</span>
-      <span class='ocrx_word' id='word_1_205' title='bbox 1182 1818 1238 1849; x_wconf 96'>the</span>
-      <span class='ocrx_word' id='word_1_206' title='bbox 1260 1816 1393 1858; x_wconf 96'>quality,</span>
-      <span class='ocrx_word' id='word_1_207' title='bbox 1411 1825 1448 1845; x_wconf 96'>or</span>
-      <span class='ocrx_word' id='word_1_208' title='bbox 1471 1815 1504 1844; x_wconf 93'>at</span>
-      <span class='ocrx_word' id='word_1_209' title='bbox 1526 1823 1544 1844; x_wconf 93'>a</span>
+     <span class='ocr_line' id='line_1_8' title="bbox 412 339 766 357; baseline -0.008 0; x_size 21.207319; x_descenders 5.2073188; x_ascenders 6">
+      <span class='ocrx_word' id='word_1_39' title='bbox 412 341 421 357; x_wconf 96'>I</span>
+      <span class='ocrx_word' id='word_1_40' title='bbox 435 341 463 357; x_wconf 96'>fell</span>
+      <span class='ocrx_word' id='word_1_41' title='bbox 478 346 514 357; x_wconf 96'>over</span>
+      <span class='ocrx_word' id='word_1_42' title='bbox 525 346 534 356; x_wconf 95'>a</span>
+      <span class='ocrx_word' id='word_1_43' title='bbox 544 342 582 356; x_wconf 68'>root</span>
+      <span class='ocrx_word' id='word_1_44' title='bbox 597 341 628 356; x_wconf 96'>and</span>
+      <span class='ocrx_word' id='word_1_45' title='bbox 642 340 688 355; x_wconf 95'>made</span>
+      <span class='ocrx_word' id='word_1_46' title='bbox 699 346 702 355; x_wconf 95'>a</span>
+      <span class='ocrx_word' id='word_1_47' title='bbox 719 339 766 355; x_wconf 92'>noise.</span>
      </span>
-     <span class='ocr_header' id='line_1_33' title="bbox 88 1871 1544 1927; baseline -0.012 -7; x_size 41; x_descenders 10; x_ascenders 10">
-      <span class='ocrx_word' id='word_1_210' title='bbox 88 1888 224 1926; x_wconf 96'>funeral,</span>
-      <span class='ocrx_word' id='word_1_211' title='bbox 242 1898 278 1918; x_wconf 96'>or</span>
-      <span class='ocrx_word' id='word_1_212' title='bbox 299 1886 406 1927; x_wconf 95'>trying</span>
-      <span class='ocrx_word' id='word_1_213' title='bbox 428 1888 461 1916; x_wconf 96'>to</span>
-      <span class='ocrx_word' id='word_1_214' title='bbox 482 1894 523 1925; x_wconf 96'>go</span>
-      <span class='ocrx_word' id='word_1_215' title='bbox 544 1885 576 1914; x_wconf 96'>to</span>
-      <span class='ocrx_word' id='word_1_216' title='bbox 598 1882 684 1922; x_wconf 96'>sleep</span>
-      <span class='ocrx_word' id='word_1_217' title='bbox 705 1881 796 1912; x_wconf 96'>when</span>
-      <span class='ocrx_word' id='word_1_218' title='bbox 818 1890 879 1920; x_wconf 93'>you</span>
-      <span class='ocrx_word' id='word_1_219' title='bbox 905 1878 985 1910; x_wconf 91'>ain’t</span>
-      <span class='ocrx_word' id='word_1_220' title='bbox 1005 1875 1178 1918; x_wconf 92'>sleepy—if</span>
-      <span class='ocrx_word' id='word_1_221' title='bbox 1206 1884 1268 1916; x_wconf 96'>you</span>
-      <span class='ocrx_word' id='word_1_222' title='bbox 1290 1883 1342 1905; x_wconf 92'>are</span>
-      <span class='ocrx_word' id='word_1_223' title='bbox 1364 1871 1544 1914; x_wconf 92'>anywheres</span>
+     <span class='ocr_line' id='line_1_9' title="bbox 412 368 769 386; baseline -0.006 -1; x_size 21.207319; x_descenders 5.2073188; x_ascenders 6">
+      <span class='ocrx_word' id='word_1_48' title='bbox 412 369 441 386; x_wconf 93'>We</span>
+      <span class='ocrx_word' id='word_1_49' title='bbox 463 370 551 385; x_wconf 91'>scrouched</span>
+      <span class='ocrx_word' id='word_1_50' title='bbox 569 369 614 384; x_wconf 96'>down</span>
+      <span class='ocrx_word' id='word_1_51' title='bbox 633 369 665 384; x_wconf 96'>and</span>
+      <span class='ocrx_word' id='word_1_52' title='bbox 680 368 713 384; x_wconf 91'>laid</span>
+      <span class='ocrx_word' id='word_1_53' title='bbox 730 368 769 384; x_wconf 90'>still.</span>
+     </span>
+     <span class='ocr_line' id='line_1_10' title="bbox 413 397 769 418; baseline -0.006 -4; x_size 21; x_descenders 5; x_ascenders 5">
+      <span class='ocrx_word' id='word_1_54' title='bbox 413 399 452 414; x_wconf 90'>Miss</span>
+      <span class='ocrx_word' id='word_1_55' title='bbox 472 398 552 414; x_wconf 90'>Watson’s</span>
+      <span class='ocrx_word' id='word_1_56' title='bbox 576 398 604 418; x_wconf 95'>big</span>
+      <span class='ocrx_word' id='word_1_57' title='bbox 628 397 689 418; x_wconf 93'>nigger,</span>
+      <span class='ocrx_word' id='word_1_58' title='bbox 712 397 769 412; x_wconf 94'>named</span>
+     </span>
+     <span class='ocr_line' id='line_1_11' title="bbox 413 425 770 447; baseline -0.006 -5; x_size 19; x_descenders 4; x_ascenders 5">
+      <span class='ocrx_word' id='word_1_59' title='bbox 413 427 453 446; x_wconf 92'>Jim,</span>
+      <span class='ocrx_word' id='word_1_60' title='bbox 462 432 493 442; x_wconf 96'>was</span>
+      <span class='ocrx_word' id='word_1_61' title='bbox 507 427 567 447; x_wconf 96'>setting</span>
+      <span class='ocrx_word' id='word_1_62' title='bbox 576 427 593 441; x_wconf 96'>in</span>
+      <span class='ocrx_word' id='word_1_63' title='bbox 604 426 632 441; x_wconf 96'>the</span>
+      <span class='ocrx_word' id='word_1_64' title='bbox 643 426 710 441; x_wconf 95'>kitchen</span>
+      <span class='ocrx_word' id='word_1_65' title='bbox 720 425 770 444; x_wconf 69'>door;</span>
+     </span>
+     <span class='ocr_line' id='line_1_12' title="bbox 415 454 770 475; baseline -0.011 -3; x_size 19; x_descenders 4; x_ascenders 5">
+      <span class='ocrx_word' id='word_1_66' title='bbox 415 461 437 472; x_wconf 96'>we</span>
+      <span class='ocrx_word' id='word_1_67' title='bbox 448 456 496 472; x_wconf 96'>could</span>
+      <span class='ocrx_word' id='word_1_68' title='bbox 506 461 531 471; x_wconf 96'>see</span>
+      <span class='ocrx_word' id='word_1_69' title='bbox 539 456 573 471; x_wconf 96'>him</span>
+      <span class='ocrx_word' id='word_1_70' title='bbox 581 456 633 475; x_wconf 96'>pretty</span>
+      <span class='ocrx_word' id='word_1_71' title='bbox 646 455 692 473; x_wconf 96'>clear,</span>
+      <span class='ocrx_word' id='word_1_72' title='bbox 705 454 770 469; x_wconf 96'>because</span>
+     </span>
+     <span class='ocr_line' id='line_1_13' title="bbox 416 481 770 503; baseline -0.008 -4; x_size 21; x_descenders 5; x_ascenders 6">
+      <span class='ocrx_word' id='word_1_73' title='bbox 416 483 461 499; x_wconf 96'>there</span>
+      <span class='ocrx_word' id='word_1_74' title='bbox 472 488 502 499; x_wconf 96'>was</span>
+      <span class='ocrx_word' id='word_1_75' title='bbox 518 488 527 498; x_wconf 96'>a</span>
+      <span class='ocrx_word' id='word_1_76' title='bbox 542 483 584 503; x_wconf 96'>light</span>
+      <span class='ocrx_word' id='word_1_77' title='bbox 600 482 659 497; x_wconf 96'>behind</span>
+      <span class='ocrx_word' id='word_1_78' title='bbox 675 481 715 496; x_wconf 94'>him.</span>
+      <span class='ocrx_word' id='word_1_79' title='bbox 745 481 770 496; x_wconf 94'>He</span>
+     </span>
+     <span class='ocr_line' id='line_1_14' title="bbox 417 509 770 532; baseline -0.008 -5; x_size 21; x_descenders 5; x_ascenders 6">
+      <span class='ocrx_word' id='word_1_80' title='bbox 417 513 445 532; x_wconf 96'>got</span>
+      <span class='ocrx_word' id='word_1_81' title='bbox 463 517 485 532; x_wconf 92'>up</span>
+      <span class='ocrx_word' id='word_1_82' title='bbox 503 512 534 527; x_wconf 95'>and</span>
+      <span class='ocrx_word' id='word_1_83' title='bbox 552 510 631 526; x_wconf 95'>stretched</span>
+      <span class='ocrx_word' id='word_1_84' title='bbox 648 510 674 525; x_wconf 96'>his</span>
+      <span class='ocrx_word' id='word_1_85' title='bbox 685 509 724 525; x_wconf 96'>neck</span>
+      <span class='ocrx_word' id='word_1_86' title='bbox 742 510 770 524; x_wconf 96'>out</span>
+     </span>
+     <span class='ocr_line' id='line_1_15' title="bbox 417 537 770 558; baseline -0.011 -2; x_size 21; x_descenders 5; x_ascenders 6">
+      <span class='ocrx_word' id='word_1_87' title='bbox 417 541 466 556; x_wconf 96'>about</span>
+      <span class='ocrx_word' id='word_1_88' title='bbox 478 545 487 555; x_wconf 96'>a</span>
+      <span class='ocrx_word' id='word_1_89' title='bbox 497 540 565 558; x_wconf 96'>minute,</span>
+      <span class='ocrx_word' id='word_1_90' title='bbox 581 538 660 558; x_wconf 93'>listening.</span>
+      <span class='ocrx_word' id='word_1_91' title='bbox 690 538 736 553; x_wconf 93'>Then</span>
+      <span class='ocrx_word' id='word_1_92' title='bbox 750 537 770 552; x_wconf 96'>he</span>
+     </span>
+     <span class='ocr_line' id='line_1_16' title="bbox 415 573 454 588; baseline 0 -5; x_size 22.362431; x_descenders 5.5239363; x_ascenders 6.2304688">
+      <span class='ocrx_word' id='word_1_93' title='bbox 415 573 454 588; x_wconf 96'>says,</span>
+     </span>
+    </p>
+
+    <p class='ocr_par' id='par_1_5' lang='eng' title="bbox 449 597 565 613">
+     <span class='ocr_line' id='line_1_17' title="bbox 449 597 565 613; baseline -0.009 0; x_size 19.920811; x_descenders 4.9208112; x_ascenders 5.5502019">
+      <span class='ocrx_word' id='word_1_94' title='bbox 449 598 506 613; x_wconf 25'>«Who</span>
+      <span class='ocrx_word' id='word_1_95' title='bbox 514 597 565 612; x_wconf 91'>dah?”</span>
+     </span>
+    </p>
+
+    <p class='ocr_par' id='par_1_6' lang='eng' title="bbox 44 623 772 964">
+     <span class='ocr_line' id='line_1_18' title="bbox 448 623 771 644; baseline -0.012 -2; x_size 21; x_descenders 5; x_ascenders 6">
+      <span class='ocrx_word' id='word_1_96' title='bbox 448 626 474 642; x_wconf 95'>He</span>
+      <span class='ocrx_word' id='word_1_97' title='bbox 488 626 556 641; x_wconf 96'>listened</span>
+      <span class='ocrx_word' id='word_1_98' title='bbox 567 630 609 640; x_wconf 96'>some</span>
+      <span class='ocrx_word' id='word_1_99' title='bbox 624 629 677 644; x_wconf 96'>more;</span>
+      <span class='ocrx_word' id='word_1_100' title='bbox 695 624 733 639; x_wconf 95'>then</span>
+      <span class='ocrx_word' id='word_1_101' title='bbox 752 623 771 638; x_wconf 95'>he</span>
+     </span>
+     <span class='ocr_line' id='line_1_19' title="bbox 417 652 771 675; baseline -0.011 -4; x_size 20; x_descenders 5; x_ascenders 4">
+      <span class='ocrx_word' id='word_1_102' title='bbox 417 660 461 671; x_wconf 85'>come</span>
+      <span class='ocrx_word' id='word_1_103' title='bbox 487 654 573 675; x_wconf 85'>tip-toeing</span>
+      <span class='ocrx_word' id='word_1_104' title='bbox 598 654 643 669; x_wconf 96'>down</span>
+      <span class='ocrx_word' id='word_1_105' title='bbox 669 653 700 668; x_wconf 29'>and.</span>
+      <span class='ocrx_word' id='word_1_106' title='bbox 726 652 771 667; x_wconf 95'>stood</span>
+     </span>
+     <span class='ocr_line' id='line_1_20' title="bbox 417 680 771 703; baseline -0.014 -4; x_size 21; x_descenders 5; x_ascenders 6">
+      <span class='ocrx_word' id='word_1_107' title='bbox 417 683 461 703; x_wconf 92'>right</span>
+      <span class='ocrx_word' id='word_1_108' title='bbox 471 683 541 698; x_wconf 96'>between</span>
+      <span class='ocrx_word' id='word_1_109' title='bbox 552 687 581 701; x_wconf 96'>us;</span>
+      <span class='ocrx_word' id='word_1_110' title='bbox 592 686 614 697; x_wconf 96'>we</span>
+      <span class='ocrx_word' id='word_1_111' title='bbox 625 681 672 696; x_wconf 96'>could</span>
+      <span class='ocrx_word' id='word_1_112' title='bbox 683 685 691 695; x_wconf 96'>a</span>
+      <span class='ocrx_word' id='word_1_113' title='bbox 702 680 771 695; x_wconf 96'>touched</span>
+     </span>
+     <span class='ocr_line' id='line_1_21' title="bbox 416 708 771 731; baseline -0.011 -4; x_size 19; x_descenders 4; x_ascenders 5">
+      <span class='ocrx_word' id='word_1_114' title='bbox 416 712 456 731; x_wconf 96'>him,</span>
+      <span class='ocrx_word' id='word_1_115' title='bbox 465 711 523 731; x_wconf 88'>nearly.</span>
+      <span class='ocrx_word' id='word_1_116' title='bbox 546 710 592 729; x_wconf 91'>Well,</span>
+      <span class='ocrx_word' id='word_1_117' title='bbox 604 709 653 730; x_wconf 96'>likely</span>
+      <span class='ocrx_word' id='word_1_118' title='bbox 660 709 673 724; x_wconf 93'>it</span>
+      <span class='ocrx_word' id='word_1_119' title='bbox 688 714 719 724; x_wconf 91'>was</span>
+      <span class='ocrx_word' id='word_1_120' title='bbox 731 708 771 723; x_wconf 91'>min-</span>
+     </span>
+     <span class='ocr_line' id='line_1_22' title="bbox 418 737 772 756; baseline -0.014 0; x_size 21.207319; x_descenders 5.2073188; x_ascenders 6">
+      <span class='ocrx_word' id='word_1_121' title='bbox 418 742 452 756; x_wconf 96'>utes</span>
+      <span class='ocrx_word' id='word_1_122' title='bbox 466 740 498 756; x_wconf 96'>and</span>
+      <span class='ocrx_word' id='word_1_123' title='bbox 512 739 583 755; x_wconf 96'>minutes</span>
+      <span class='ocrx_word' id='word_1_124' title='bbox 593 739 630 754; x_wconf 96'>that</span>
+      <span class='ocrx_word' id='word_1_125' title='bbox 640 738 685 753; x_wconf 93'>there</span>
+      <span class='ocrx_word' id='word_1_126' title='bbox 693 737 749 752; x_wconf 91'>warn’t</span>
+      <span class='ocrx_word' id='word_1_127' title='bbox 763 742 772 752; x_wconf 96'>a</span>
+     </span>
+     <span class='ocr_line' id='line_1_23' title="bbox 417 765 771 788; baseline -0.011 -4; x_size 20; x_descenders 5; x_ascenders 5">
+      <span class='ocrx_word' id='word_1_128' title='bbox 417 769 473 788; x_wconf 96'>sound,</span>
+      <span class='ocrx_word' id='word_1_129' title='bbox 492 768 525 784; x_wconf 96'>and</span>
+      <span class='ocrx_word' id='word_1_130' title='bbox 542 773 565 783; x_wconf 96'>we</span>
+      <span class='ocrx_word' id='word_1_131' title='bbox 586 767 607 782; x_wconf 96'>all</span>
+      <span class='ocrx_word' id='word_1_132' title='bbox 627 766 672 781; x_wconf 95'>there</span>
+      <span class='ocrx_word' id='word_1_133' title='bbox 693 770 710 781; x_wconf 92'>so</span>
+      <span class='ocrx_word' id='word_1_134' title='bbox 730 765 771 780; x_wconf 89'>close</span>
+     </span>
+     <span class='ocr_line' id='line_1_24' title="bbox 417 793 772 817; baseline -0.014 -5; x_size 22; x_descenders 6; x_ascenders 6">
+      <span class='ocrx_word' id='word_1_135' title='bbox 417 796 494 817; x_wconf 85'>together.</span>
+      <span class='ocrx_word' id='word_1_136' title='bbox 522 795 574 810; x_wconf 88'>‘There</span>
+      <span class='ocrx_word' id='word_1_137' title='bbox 588 799 620 810; x_wconf 96'>was</span>
+      <span class='ocrx_word' id='word_1_138' title='bbox 632 799 641 809; x_wconf 96'>a</span>
+      <span class='ocrx_word' id='word_1_139' title='bbox 655 793 699 814; x_wconf 96'>place</span>
+      <span class='ocrx_word' id='word_1_140' title='bbox 714 797 735 808; x_wconf 95'>on</span>
+      <span class='ocrx_word' id='word_1_141' title='bbox 746 797 772 813; x_wconf 96'>my</span>
+     </span>
+     <span class='ocr_line' id='line_1_25' title="bbox 417 821 772 844; baseline -0.017 -3; x_size 21; x_descenders 5; x_ascenders 6">
+      <span class='ocrx_word' id='word_1_142' title='bbox 417 825 464 841; x_wconf 96'>ankle</span>
+      <span class='ocrx_word' id='word_1_143' title='bbox 482 824 518 840; x_wconf 96'>that</span>
+      <span class='ocrx_word' id='word_1_144' title='bbox 535 825 563 844; x_wconf 96'>got</span>
+      <span class='ocrx_word' id='word_1_145' title='bbox 581 824 597 839; x_wconf 96'>to</span>
+      <span class='ocrx_word' id='word_1_146' title='bbox 615 822 692 842; x_wconf 96'>itching;</span>
+      <span class='ocrx_word' id='word_1_147' title='bbox 713 821 743 836; x_wconf 96'>but</span>
+      <span class='ocrx_word' id='word_1_148' title='bbox 764 821 772 836; x_wconf 96'>I</span>
+     </span>
+     <span class='ocr_line' id='line_1_26' title="bbox 44 849 772 876; baseline -0.014 -2; x_size 20; x_descenders 4; x_ascenders 6">
+      <span class='ocrx_word' id='word_1_149' title='bbox 44 858 95 873; x_wconf 92'>dasn’t</span>
+      <span class='ocrx_word' id='word_1_150' title='bbox 108 857 170 873; x_wconf 90'>scratch</span>
+      <span class='ocrx_word' id='word_1_151' title='bbox 178 857 197 876; x_wconf 95'>it;</span>
+      <span class='ocrx_word' id='word_1_152' title='bbox 208 856 240 872; x_wconf 96'>and</span>
+      <span class='ocrx_word' id='word_1_153' title='bbox 251 856 290 871; x_wconf 96'>then</span>
+      <span class='ocrx_word' id='word_1_154' title='bbox 301 860 328 876; x_wconf 96'>my</span>
+      <span class='ocrx_word' id='word_1_155' title='bbox 335 860 361 870; x_wconf 96'>ear</span>
+      <span class='ocrx_word' id='word_1_156' title='bbox 374 855 426 874; x_wconf 96'>begun</span>
+      <span class='ocrx_word' id='word_1_157' title='bbox 438 854 455 869; x_wconf 96'>to</span>
+      <span class='ocrx_word' id='word_1_158' title='bbox 466 853 507 872; x_wconf 96'>itch;</span>
+      <span class='ocrx_word' id='word_1_159' title='bbox 518 853 550 868; x_wconf 94'>and</span>
+      <span class='ocrx_word' id='word_1_160' title='bbox 557 853 595 868; x_wconf 94'>next</span>
+      <span class='ocrx_word' id='word_1_161' title='bbox 603 857 630 872; x_wconf 96'>my</span>
+      <span class='ocrx_word' id='word_1_162' title='bbox 637 851 683 870; x_wconf 96'>back,</span>
+      <span class='ocrx_word' id='word_1_163' title='bbox 692 850 736 870; x_wconf 89'>right</span>
+      <span class='ocrx_word' id='word_1_164' title='bbox 746 849 772 865; x_wconf 90'>be-</span>
+     </span>
+     <span class='ocr_line' id='line_1_27' title="bbox 44 878 772 906; baseline -0.012 -4; x_size 21; x_descenders 5; x_ascenders 6">
+      <span class='ocrx_word' id='word_1_165' title='bbox 44 888 94 902; x_wconf 96'>tween</span>
+      <span class='ocrx_word' id='word_1_166' title='bbox 107 891 133 906; x_wconf 96'>my</span>
+      <span class='ocrx_word' id='word_1_167' title='bbox 145 885 231 902; x_wconf 94'>shoulders.</span>
+      <span class='ocrx_word' id='word_1_168' title='bbox 260 884 324 900; x_wconf 94'>Seemed</span>
+      <span class='ocrx_word' id='word_1_169' title='bbox 336 884 368 899; x_wconf 93'>like</span>
+      <span class='ocrx_word' id='word_1_170' title='bbox 382 883 406 898; x_wconf 90'>I’d</span>
+      <span class='ocrx_word' id='word_1_171' title='bbox 418 883 443 898; x_wconf 96'>die</span>
+      <span class='ocrx_word' id='word_1_172' title='bbox 455 882 468 897; x_wconf 96'>if</span>
+      <span class='ocrx_word' id='word_1_173' title='bbox 480 882 488 897; x_wconf 92'>I</span>
+      <span class='ocrx_word' id='word_1_174' title='bbox 500 881 571 897; x_wconf 88'>couldn’t</span>
+      <span class='ocrx_word' id='word_1_175' title='bbox 584 880 651 896; x_wconf 95'>scratch.</span>
+      <span class='ocrx_word' id='word_1_176' title='bbox 680 879 727 897; x_wconf 82'>Well,</span>
+      <span class='ocrx_word' id='word_1_177' title='bbox 740 878 772 894; x_wconf 85'>I’ve</span>
+     </span>
+     <span class='ocr_line' id='line_1_28' title="bbox 44 908 772 934; baseline -0.012 -3; x_size 21; x_descenders 5; x_ascenders 6">
+      <span class='ocrx_word' id='word_1_178' title='bbox 44 915 107 931; x_wconf 96'>noticed</span>
+      <span class='ocrx_word' id='word_1_179' title='bbox 119 915 154 930; x_wconf 96'>that</span>
+      <span class='ocrx_word' id='word_1_180' title='bbox 165 914 212 934; x_wconf 96'>thing</span>
+      <span class='ocrx_word' id='word_1_181' title='bbox 223 913 277 934; x_wconf 96'>plenty</span>
+      <span class='ocrx_word' id='word_1_182' title='bbox 289 913 305 928; x_wconf 95'>of</span>
+      <span class='ocrx_word' id='word_1_183' title='bbox 312 912 359 928; x_wconf 89'>times</span>
+      <span class='ocrx_word' id='word_1_184' title='bbox 367 912 414 927; x_wconf 89'>since.</span>
+      <span class='ocrx_word' id='word_1_185' title='bbox 438 911 453 926; x_wconf 95'>If</span>
+      <span class='ocrx_word' id='word_1_186' title='bbox 464 915 495 931; x_wconf 96'>you</span>
+      <span class='ocrx_word' id='word_1_187' title='bbox 507 915 533 925; x_wconf 96'>are</span>
+      <span class='ocrx_word' id='word_1_188' title='bbox 540 909 579 926; x_wconf 96'>with</span>
+      <span class='ocrx_word' id='word_1_189' title='bbox 591 909 619 924; x_wconf 96'>the</span>
+      <span class='ocrx_word' id='word_1_190' title='bbox 630 908 696 929; x_wconf 96'>quality,</span>
+      <span class='ocrx_word' id='word_1_191' title='bbox 706 912 724 923; x_wconf 96'>or</span>
+      <span class='ocrx_word' id='word_1_192' title='bbox 736 908 752 922; x_wconf 96'>at</span>
+      <span class='ocrx_word' id='word_1_193' title='bbox 763 912 772 922; x_wconf 96'>a</span>
+     </span>
+     <span class='ocr_line' id='line_1_29' title="bbox 44 932 772 964; baseline -0.012 -4; x_size 21; x_descenders 5; x_ascenders 5">
+      <span class='ocrx_word' id='word_1_194' title='bbox 44 944 112 963; x_wconf 93'>funeral,</span>
+      <span class='ocrx_word' id='word_1_195' title='bbox 121 949 139 959; x_wconf 93'>or</span>
+      <span class='ocrx_word' id='word_1_196' title='bbox 149 943 203 964; x_wconf 93'>trying</span>
+      <span class='ocrx_word' id='word_1_197' title='bbox 214 944 230 958; x_wconf 96'>to</span>
+      <span class='ocrx_word' id='word_1_198' title='bbox 241 947 261 962; x_wconf 96'>go</span>
+      <span class='ocrx_word' id='word_1_199' title='bbox 272 942 288 957; x_wconf 96'>to</span>
+      <span class='ocrx_word' id='word_1_200' title='bbox 299 941 342 961; x_wconf 94'>sleep</span>
+      <span class='ocrx_word' id='word_1_201' title='bbox 353 941 398 956; x_wconf 96'>when</span>
+      <span class='ocrx_word' id='word_1_202' title='bbox 409 945 440 960; x_wconf 93'>you</span>
+      <span class='ocrx_word' id='word_1_203' title='bbox 453 939 492 955; x_wconf 90'>ain’t</span>
+      <span class='ocrx_word' id='word_1_204' title='bbox 503 938 589 959; x_wconf 91'>sleepy—if</span>
+      <span class='ocrx_word' id='word_1_205' title='bbox 603 942 634 958; x_wconf 96'>you</span>
+      <span class='ocrx_word' id='word_1_206' title='bbox 645 942 671 952; x_wconf 96'>are</span>
+      <span class='ocrx_word' id='word_1_207' title='bbox 682 932 772 961; x_wconf 92'>anywheres</span>
+     </span>
+    </p>
+   </div>
+   <div class='ocr_carea' id='block_1_5' title="bbox 147 817 293 826">
+    <p class='ocr_par' id='par_1_7' lang='eng' title="bbox 147 817 293 826">
+     <span class='ocr_caption' id='line_1_30' title="bbox 147 817 293 826; baseline -0.007 0; x_size 20; x_descenders 5; x_ascenders 5">
+      <span class='ocrx_word' id='word_1_208' title='bbox 147 818 180 826; x_wconf 0'>‘qumY</span>
+      <span class='ocrx_word' id='word_1_209' title='bbox 187 818 244 825; x_wconf 85'>TIP-TOED</span>
+      <span class='ocrx_word' id='word_1_210' title='bbox 251 817 293 825; x_wconf 78'>ALONG.</span>
      </span>
     </p>
    </div>

tests/cache/multipage/__-l__eng__000001_ocr.png__000001_ocr_hocr__hocr__txt/txt.bin

@@ -1,41 +1,36 @@
-ee if /) J:
-( H} : cha
-iy ‘ H
+Chapter i
 
-THEY TIP-TOED ALONG.
-
-N
-
-: chapter J
-
-E went tip-toeing along a path amongst
+lad
 
+‘ We went tip-toeing along a path amongst
 the trees back towards the end of the
 widow’s garden, stooping down so as
+
 the branches wouldn’t scrape our heads.
 When we was passing by the kitchen
 I fell over a root and made a noise.
 We scrouched down and laid still.
 Miss Watson’s big nigger, named
-Jim, was setting in the kitchen door ;
+Jim, was setting in the kitchen door;
 we could see him pretty clear, because
 there was a light behind him. He
 got up and stretched his neck out
 about a minute, listening. Then he
 says,
 
-** Who dah?”
+«Who dah?”
 
 He listened some more; then he
-come tip-toeing down and- stood
+come tip-toeing down and. stood
 right between us; we could a touched
 him, nearly. Well, likely it was min-
 utes and minutes that there warn’t a
 sound, and we all there so close
 together. ‘There was a place on my
 ankle that got to itching; but I
-
 dasn’t scratch it; and then my ear begun to itch; and next my back, right be-
 tween my shoulders. Seemed like I’d die if I couldn’t scratch. Well, I’ve
 noticed that thing plenty of times since. If you are with the quality, or at a
 funeral, or trying to go to sleep when you ain’t sleepy—if you are anywheres
+
+‘qumY TIP-TOED ALONG.

tests/cache/multipage/__-l__eng__000002_ocr.png__000002_ocr_hocr__hocr__txt/hocr.bin

@@ -9,7 +9,7 @@
   <meta name='ocr-capabilities' content='ocr_page ocr_carea ocr_par ocr_line ocrx_word ocrp_wconf'/>
  </head>
  <body>
-  <div class='ocr_page' id='page_1' title='image "/tmp/pytest-of-jb/pytest-25/popen-gw2/test_hocr_api0/000002_ocr.png"; bbox 0 0 9000 9000; ppageno 0; scan_res 300 300'>
+  <div class='ocr_page' id='page_1' title='image "/tmp/pytest-of-jb/pytest-42/popen-gw1/test_hocr_api_multipage0/000002_ocr.png"; bbox 0 0 9000 9000; ppageno 0; scan_res 300 300'>
    <div class='ocr_carea' id='block_1_1' title="bbox 791 740 4415 1463">
     <p class='ocr_par' id='par_1_1' lang='eng' title="bbox 791 740 4415 1463">
      <span class='ocr_line' id='line_1_1' title="bbox 793 740 4415 1009; baseline -0.001 -51; x_size 274.5; x_descenders 57.5; x_ascenders 55.5">

tests/cache/multipage/__-l__eng__000003_ocr.png__000003_ocr_hocr__hocr__txt/hocr.bin

@@ -9,51 +9,59 @@
   <meta name='ocr-capabilities' content='ocr_page ocr_carea ocr_par ocr_line ocrx_word ocrp_wconf'/>
  </head>
  <body>
-  <div class='ocr_page' id='page_1' title='image "/tmp/ocrmypdf.io.ok2cpo6d/000003_ocr.png"; bbox 0 0 2994 1250; ppageno 0; scan_res 300 300'>
-   <div class='ocr_separator' id='block_1_1' title="bbox 138 37 2459 41"></div>
-   <div class='ocr_separator' id='block_1_2' title="bbox 138 187 2459 191"></div>
-   <div class='ocr_separator' id='block_1_3' title="bbox 138 334 2459 338"></div>
-   <div class='ocr_separator' id='block_1_4' title="bbox 138 481 635 485"></div>
-   <div class='ocr_separator' id='block_1_5' title="bbox 884 481 1841 485"></div>
-   <div class='ocr_separator' id='block_1_6' title="bbox 1991 481 2459 485"></div>
-   <div class='ocr_separator' id='block_1_7' title="bbox 138 631 2459 635"></div>
-   <div class='ocr_separator' id='block_1_8' title="bbox 337 778 2178 781"></div>
-   <div class='ocr_separator' id='block_1_9' title="bbox 153 37 156 943"></div>
-   <div class='ocr_separator' id='block_1_10' title="bbox 220 921 2460 932"></div>
-   <div class='ocr_photo' id='block_1_11' title="bbox 30 23 2424 1210"></div>
-   <div class='ocr_carea' id='block_1_12' title="bbox 2515 458 2939 795">
-    <p class='ocr_par' id='par_1_1' lang='eng' title="bbox 2516 458 2746 491">
-     <span class='ocr_line' id='line_1_1' title="bbox 2516 458 2746 491; baseline -0.009 -4; x_size 34; x_descenders 6; x_ascenders 7">
-      <span class='ocrx_word' id='word_1_1' title='bbox 2516 458 2746 491; x_wconf 69'>—¢—Support</span>
+  <div class='ocr_page' id='page_1' title='image "/tmp/pytest-of-jb/pytest-42/popen-gw1/test_hocr_api_multipage0/000003_ocr.png"; bbox 0 0 958 400; ppageno 0; scan_res 96 96'>
+   <div class='ocr_separator' id='block_1_1' title="bbox 44 12 787 13"></div>
+   <div class='ocr_separator' id='block_1_2' title="bbox 44 60 787 61"></div>
+   <div class='ocr_separator' id='block_1_3' title="bbox 44 107 413 108"></div>
+   <div class='ocr_carea' id='block_1_4' title="bbox 16 108 879 165">
+    <p class='ocr_par' id='par_1_1' lang='eng' title="bbox 16 108 879 165">
+     <span class='ocr_line' id='line_1_1' title="bbox 86 108 879 165; baseline 0.001 -11; x_size 24.571428; x_descenders 5.5714288; x_ascenders 6">
+      <span class='ocrx_word' id='word_1_1' title='bbox 86 108 146 154; x_wconf 23'>—</span>
+      <span class='ocrx_word' id='word_1_2' title='bbox 801 133 879 165; x_wconf 5'>—esupport</span>
      </span>
-    </p>
-
-    <p class='ocr_par' id='par_1_2' lang='eng' title="bbox 2516 533 2873 720">
-     <span class='ocr_line' id='line_1_2' title="bbox 2516 533 2873 570; baseline 0 -7; x_size 37; x_descenders 7; x_ascenders 10">
-      <span class='ocrx_word' id='word_1_2' title='bbox 2516 534 2657 563; x_wconf 0'>==</span>
-      <span class='ocrx_word' id='word_1_3' title='bbox 2609 529 2644 574; x_wconf 47'>No</span>
-      <span class='ocrx_word' id='word_1_4' title='bbox 2665 534 2830 570; x_wconf 92'>vote[note</span>
-      <span class='ocrx_word' id='word_1_5' title='bbox 2842 533 2873 570; x_wconf 96'>1]</span>
-     </span>
-     <span class='ocr_line' id='line_1_3' title="bbox 2516 610 2739 644; baseline 0 0; x_size 45.969162; x_descenders 11.969163; x_ascenders 8">
-      <span class='ocrx_word' id='word_1_6' title='bbox 2516 606 2589 660; x_wconf 25'>ie</span>
-      <span class='ocrx_word' id='word_1_7' title='bbox 2615 606 2742 660; x_wconf 95'>Oppose</span>
-     </span>
-     <span class='ocr_line' id='line_1_4' title="bbox 2516 683 2802 720; baseline 0.003 -8; x_size 37; x_descenders 7; x_ascenders 10">
-      <span class='ocrx_word' id='word_1_8' title='bbox 2516 684 2758 720; x_wconf 63'>——Net[note</span>
-      <span class='ocrx_word' id='word_1_9' title='bbox 2770 683 2802 720; x_wconf 96'>2]</span>
-     </span>
-    </p>
-
-    <p class='ocr_par' id='par_1_3' lang='eng' title="bbox 2515 758 2939 795">
-     <span class='ocr_line' id='line_1_5' title="bbox 2515 758 2939 795; baseline 0 -7; x_size 37; x_descenders 7; x_ascenders 10">
-      <span class='ocrx_word' id='word_1_10' title='bbox 2511 754 2594 799; x_wconf 38'>=e</span>
-      <span class='ocrx_word' id='word_1_11' title='bbox 2612 754 2793 799; x_wconf 38'>Percentage</span>
-      <span class='ocrx_word' id='word_1_12' title='bbox 2812 759 2898 795; x_wconf 96'>[note</span>
-      <span class='ocrx_word' id='word_1_13' title='bbox 2906 758 2939 795; x_wconf 96'>3]</span>
+     <span class='ocr_line' id='line_1_2' title="bbox 16 151 37 159; baseline 0 0; x_size 27; x_descenders 6; x_ascenders 7">
+      <span class='ocrx_word' id='word_1_3' title='bbox 16 151 37 159; x_wconf 88'>300</span>
      </span>
     </p>
    </div>
+   <div class='ocr_carea' id='block_1_5' title="bbox 805 171 919 182">
+    <p class='ocr_par' id='par_1_2' lang='eng' title="bbox 805 171 919 182">
+     <span class='ocr_line' id='line_1_3' title="bbox 805 171 919 182; baseline 0.018 -2; x_size 20; x_descenders 5; x_ascenders 5">
+      <span class='ocrx_word' id='word_1_4' title='bbox 805 162 829 190; x_wconf 17'>BE</span>
+      <span class='ocrx_word' id='word_1_5' title='bbox 833 162 848 190; x_wconf 17'>No</span>
+      <span class='ocrx_word' id='word_1_6' title='bbox 852 171 905 182; x_wconf 18'>votefnote</span>
+      <span class='ocrx_word' id='word_1_7' title='bbox 910 171 919 182; x_wconf 83'>1]</span>
+     </span>
+    </p>
+   </div>
+   <div class='ocr_separator' id='block_1_6' title="bbox 44 154 787 155"></div>
+   <div class='ocr_carea' id='block_1_7' title="bbox 16 195 896 230">
+    <p class='ocr_par' id='par_1_3' lang='eng' title="bbox 16 195 896 230">
+     <span class='ocr_line' id='line_1_4' title="bbox 805 195 876 206; baseline 0 -2; x_size 35.333332; x_descenders 8.833333; x_ascenders 8.833333">
+      <span class='ocrx_word' id='word_1_8' title='bbox 805 195 876 206; x_wconf 66'>—</span>
+     </span>
+     <span class='ocr_line' id='line_1_5' title="bbox 16 199 896 230; baseline 0.002 -2; x_size 13.333334; x_descenders 3.3333335; x_ascenders 3.333333">
+      <span class='ocrx_word' id='word_1_9' title='bbox 16 199 49 207; x_wconf 29'>ay</span>
+      <span class='ocrx_word' id='word_1_10' title='bbox 805 219 823 228; x_wconf 0'>&gt;</span>
+      <span class='ocrx_word' id='word_1_11' title='bbox 832 219 882 230; x_wconf 0'>Net[note</span>
+      <span class='ocrx_word' id='word_1_12' title='bbox 886 219 896 230; x_wconf 86'>2]</span>
+     </span>
+    </p>
+   </div>
+   <div class='ocr_separator' id='block_1_8' title="bbox 457 202 787 203"></div>
+   <div class='ocr_separator' id='block_1_9' title="bbox 44 247 834 249"></div>
+   <div class='ocr_carea' id='block_1_10' title="bbox 836 243 940 254">
+    <p class='ocr_par' id='par_1_4' lang='eng' title="bbox 836 243 940 254">
+     <span class='ocr_line' id='line_1_6' title="bbox 836 243 940 254; baseline 0.019 -2; x_size 20; x_descenders 5; x_ascenders 5">
+      <span class='ocrx_word' id='word_1_13' title='bbox 836 244 896 254; x_wconf 93'>Percentage</span>
+      <span class='ocrx_word' id='word_1_14' title='bbox 900 243 940 254; x_wconf 95'>[note</span>
+      <span class='ocrx_word' id='word_1_15' title='bbox 932 235 944 263; x_wconf 89'>3]</span>
+     </span>
+    </p>
+   </div>
+   <div class='ocr_separator' id='block_1_11' title="bbox 49 12 50 302"></div>
+   <div class='ocr_separator' id='block_1_12' title="bbox 44 295 787 298"></div>
+   <div class='ocr_photo' id='block_1_13' title="bbox 7 242 770 392"></div>
   </div>
  </body>
 </html>

tests/cache/multipage/__-l__eng__000003_ocr.png__000003_ocr_hocr__hocr__txt/txt.bin

@@ -1,7 +1,10 @@
-—¢—Support
+— —esupport
+300
 
-== No vote[note 1]
-ie Oppose
-——Net[note 2]
+BE No votefnote 1]
+
+—
+ay > Net[note 2]
+
+Percentage [note 3]
 
-=e Percentage [note 3]

tests/cache/multipage/__-l__eng__000004_ocr.png__000004_ocr_hocr__hocr__txt/hocr.bin

@@ -9,7 +9,7 @@
   <meta name='ocr-capabilities' content='ocr_page ocr_carea ocr_par ocr_line ocrx_word ocrp_wconf'/>
  </head>
  <body>
-  <div class='ocr_page' id='page_1' title='image "/tmp/ocrmypdf.io.ok2cpo6d/000004_ocr.png"; bbox 0 0 3992 1667; ppageno 0; scan_res 400 400'>
+  <div class='ocr_page' id='page_1' title='image "/tmp/ocrmypdf.io.734tk458/000004_ocr.png"; bbox 0 0 3992 1667; ppageno 0; scan_res 400 400'>
    <div class='ocr_separator' id='block_1_1' title="bbox 185 50 3278 54"></div>
    <div class='ocr_separator' id='block_1_2' title="bbox 185 249 3278 254"></div>
    <div class='ocr_separator' id='block_1_3' title="bbox 185 446 1721 450"></div>
@@ -72,82 +72,82 @@
       <span class='ocrx_word' id='word_1_29' title='bbox 395 1310 425 1339; x_wconf 49'>@</span>
       <span class='ocrx_word' id='word_1_30' title='bbox 540 1300 572 1339; x_wconf 23'>s</span>
       <span class='ocrx_word' id='word_1_31' title='bbox 979 1309 1012 1339; x_wconf 81'>&gt;</span>
-      <span class='ocrx_word' id='word_1_32' title='bbox 1121 1295 1155 1353; x_wconf 37'>oO</span>
+      <span class='ocrx_word' id='word_1_32' title='bbox 1121 1295 1155 1353; x_wconf 35'>oO</span>
       <span class='ocrx_word' id='word_1_33' title='bbox 1278 1306 1304 1334; x_wconf 24'>©</span>
       <span class='ocrx_word' id='word_1_34' title='bbox 1407 1295 1450 1353; x_wconf 20'>ve</span>
       <span class='ocrx_word' id='word_1_35' title='bbox 1567 1308 1593 1338; x_wconf 61'>S</span>
-      <span class='ocrx_word' id='word_1_36' title='bbox 1712 1308 1740 1338; x_wconf 0'>)</span>
+      <span class='ocrx_word' id='word_1_36' title='bbox 1708 1295 1742 1353; x_wconf 0'>te)</span>
       <span class='ocrx_word' id='word_1_37' title='bbox 1858 1308 1888 1338; x_wconf 61'>@</span>
       <span class='ocrx_word' id='word_1_38' title='bbox 2004 1305 2037 1338; x_wconf 80'>+</span>
       <span class='ocrx_word' id='word_1_39' title='bbox 2153 1308 2180 1336; x_wconf 7'>&amp;</span>
       <span class='ocrx_word' id='word_1_40' title='bbox 2287 1305 2329 1347; x_wconf 88'>&amp;</span>
       <span class='ocrx_word' id='word_1_41' title='bbox 2578 1293 2613 1351; x_wconf 51'>“A</span>
       <span class='ocrx_word' id='word_1_42' title='bbox 2738 1308 2765 1335; x_wconf 41'>5</span>
-      <span class='ocrx_word' id='word_1_43' title='bbox 3014 1308 3058 1344; x_wconf 23'>oo</span>
+      <span class='ocrx_word' id='word_1_43' title='bbox 3014 1308 3058 1344; x_wconf 22'>oo</span>
      </span>
-     <span class='ocr_line' id='line_1_9' title="bbox 184 1306 3034 1411; baseline -0.008 -16; x_size 63; x_descenders 14; x_ascenders 18">
-      <span class='ocrx_word' id='word_1_44' title='bbox 184 1327 400 1399; x_wconf 40'>Se</span>
+     <span class='ocr_line' id='line_1_9' title="bbox 184 1302 3034 1411; baseline -0.008 -16; x_size 63; x_descenders 14; x_ascenders 18">
+      <span class='ocrx_word' id='word_1_44' title='bbox 184 1327 400 1399; x_wconf 42'>Se</span>
       <span class='ocrx_word' id='word_1_45' title='bbox 622 1308 718 1404; x_wconf 53'>°</span>
-      <span class='ocrx_word' id='word_1_46' title='bbox 774 1330 988 1397; x_wconf 28'>Ps</span>
-      <span class='ocrx_word' id='word_1_47' title='bbox 1194 1360 1251 1411; x_wconf 19'>as</span>
-      <span class='ocrx_word' id='word_1_48' title='bbox 1360 1324 1425 1390; x_wconf 33'>ge</span>
-      <span class='ocrx_word' id='word_1_49' title='bbox 1641 1325 1717 1401; x_wconf 5'>eS</span>
-      <span class='ocrx_word' id='word_1_50' title='bbox 1801 1328 1869 1393; x_wconf 11'>€</span>
-      <span class='ocrx_word' id='word_1_51' title='bbox 1941 1325 2017 1392; x_wconf 68'>x</span>
+      <span class='ocrx_word' id='word_1_46' title='bbox 774 1330 988 1397; x_wconf 33'>Fs</span>
+      <span class='ocrx_word' id='word_1_47' title='bbox 1194 1360 1251 1411; x_wconf 21'>as</span>
+      <span class='ocrx_word' id='word_1_48' title='bbox 1360 1324 1425 1390; x_wconf 36'>ge</span>
+      <span class='ocrx_word' id='word_1_49' title='bbox 1641 1325 1717 1401; x_wconf 16'>eS</span>
+      <span class='ocrx_word' id='word_1_50' title='bbox 1801 1328 1869 1393; x_wconf 5'>F</span>
+      <span class='ocrx_word' id='word_1_51' title='bbox 1941 1325 2017 1392; x_wconf 65'>x</span>
       <span class='ocrx_word' id='word_1_52' title='bbox 2077 1326 2161 1406; x_wconf 28'>ro</span>
       <span class='ocrx_word' id='word_1_53' title='bbox 2232 1337 2297 1403; x_wconf 43'>NS</span>
-      <span class='ocrx_word' id='word_1_54' title='bbox 2379 1306 2468 1394; x_wconf 38'>Po</span>
+      <span class='ocrx_word' id='word_1_54' title='bbox 2375 1302 2468 1398; x_wconf 33'>Pe</span>
       <span class='ocrx_word' id='word_1_55' title='bbox 2535 1323 2597 1391; x_wconf 8'>e?</span>
       <span class='ocrx_word' id='word_1_56' title='bbox 2667 1324 2751 1406; x_wconf 66'>&amp;</span>
-      <span class='ocrx_word' id='word_1_57' title='bbox 2845 1308 2913 1376; x_wconf 28'>s</span>
-      <span class='ocrx_word' id='word_1_58' title='bbox 2959 1324 3034 1401; x_wconf 48'>AS</span>
+      <span class='ocrx_word' id='word_1_57' title='bbox 2845 1308 2913 1376; x_wconf 25'>s</span>
+      <span class='ocrx_word' id='word_1_58' title='bbox 2959 1324 3034 1401; x_wconf 52'>AS</span>
      </span>
      <span class='ocr_line' id='line_1_10' title="bbox 161 1360 3110 1447; baseline -0.003 -5; x_size 64; x_descenders 16; x_ascenders 20">
-      <span class='ocrx_word' id='word_1_59' title='bbox 161 1382 207 1426; x_wconf 15'>a</span>
-      <span class='ocrx_word' id='word_1_60' title='bbox 436 1384 494 1430; x_wconf 17'>a</span>
-      <span class='ocrx_word' id='word_1_61' title='bbox 750 1395 758 1441; x_wconf 17'>©</span>
-      <span class='ocrx_word' id='word_1_62' title='bbox 1318 1378 1521 1443; x_wconf 61'>FF</span>
-      <span class='ocrx_word' id='word_1_63' title='bbox 1615 1387 1655 1435; x_wconf 48'>SF</span>
-      <span class='ocrx_word' id='word_1_64' title='bbox 1753 1385 1813 1434; x_wconf 41'>HY</span>
-      <span class='ocrx_word' id='word_1_65' title='bbox 1891 1382 1960 1442; x_wconf 40'>HK</span>
-      <span class='ocrx_word' id='word_1_66' title='bbox 2050 1399 2092 1430; x_wconf 17'>SK</span>
-      <span class='ocrx_word' id='word_1_67' title='bbox 2187 1388 2251 1441; x_wconf 52'>BM</span>
-      <span class='ocrx_word' id='word_1_68' title='bbox 2630 1396 2678 1435; x_wconf 0'>ee</span>
-      <span class='ocrx_word' id='word_1_69' title='bbox 2920 1393 3110 1442; x_wconf 44'>sO</span>
+      <span class='ocrx_word' id='word_1_59' title='bbox 161 1382 634 1447; x_wconf 14'>aa</span>
+      <span class='ocrx_word' id='word_1_60' title='bbox 750 1395 758 1433; x_wconf 14'>©</span>
+      <span class='ocrx_word' id='word_1_61' title='bbox 1318 1378 1521 1443; x_wconf 59'>FF</span>
+      <span class='ocrx_word' id='word_1_62' title='bbox 1615 1387 1655 1435; x_wconf 47'>SF</span>
+      <span class='ocrx_word' id='word_1_63' title='bbox 1753 1385 1813 1434; x_wconf 39'>HY</span>
+      <span class='ocrx_word' id='word_1_64' title='bbox 1891 1382 1960 1442; x_wconf 51'>HK</span>
+      <span class='ocrx_word' id='word_1_65' title='bbox 2050 1399 2092 1430; x_wconf 20'>SK</span>
+      <span class='ocrx_word' id='word_1_66' title='bbox 2187 1388 2251 1441; x_wconf 54'>HM</span>
+      <span class='ocrx_word' id='word_1_67' title='bbox 2630 1396 2678 1435; x_wconf 0'>ee</span>
+      <span class='ocrx_word' id='word_1_68' title='bbox 2920 1393 3110 1442; x_wconf 49'>sO</span>
      </span>
      <span class='ocr_line' id='line_1_11' title="bbox 141 1413 3090 1485; baseline -0.005 -17; x_size 42.720001; x_descenders 6.7199998; x_ascenders 15">
-      <span class='ocrx_word' id='word_1_70' title='bbox 141 1416 171 1446; x_wconf 35'>e</span>
-      <span class='ocrx_word' id='word_1_71' title='bbox 266 1438 288 1467; x_wconf 87'>&lt;</span>
-      <span class='ocrx_word' id='word_1_72' title='bbox 413 1426 448 1477; x_wconf 28'>Na</span>
-      <span class='ocrx_word' id='word_1_73' title='bbox 569 1429 589 1458; x_wconf 0'>‘</span>
-      <span class='ocrx_word' id='word_1_74' title='bbox 975 1454 982 1462; x_wconf 8'>:</span>
-      <span class='ocrx_word' id='word_1_75' title='bbox 1142 1428 1183 1463; x_wconf 23'>&gt;</span>
-      <span class='ocrx_word' id='word_1_76' title='bbox 1300 1421 1334 1471; x_wconf 10'>cy</span>
-      <span class='ocrx_word' id='word_1_77' title='bbox 1417 1420 1471 1480; x_wconf 57'>xs</span>
-      <span class='ocrx_word' id='word_1_78' title='bbox 1566 1424 1625 1476; x_wconf 40'>eS</span>
-      <span class='ocrx_word' id='word_1_79' title='bbox 1882 1433 1910 1460; x_wconf 59'>@</span>
-      <span class='ocrx_word' id='word_1_80' title='bbox 2024 1417 2069 1456; x_wconf 59'>Ww</span>
-      <span class='ocrx_word' id='word_1_81' title='bbox 2878 1413 2934 1485; x_wconf 16'>a)</span>
+      <span class='ocrx_word' id='word_1_69' title='bbox 141 1416 171 1446; x_wconf 35'>e</span>
+      <span class='ocrx_word' id='word_1_70' title='bbox 266 1438 288 1467; x_wconf 87'>&lt;</span>
+      <span class='ocrx_word' id='word_1_71' title='bbox 413 1426 448 1477; x_wconf 28'>Na</span>
+      <span class='ocrx_word' id='word_1_72' title='bbox 569 1429 589 1458; x_wconf 0'>‘</span>
+      <span class='ocrx_word' id='word_1_73' title='bbox 975 1454 982 1462; x_wconf 8'>:</span>
+      <span class='ocrx_word' id='word_1_74' title='bbox 1142 1428 1183 1463; x_wconf 23'>&gt;</span>
+      <span class='ocrx_word' id='word_1_75' title='bbox 1300 1421 1334 1471; x_wconf 10'>cy</span>
+      <span class='ocrx_word' id='word_1_76' title='bbox 1417 1420 1471 1480; x_wconf 57'>xs</span>
+      <span class='ocrx_word' id='word_1_77' title='bbox 1566 1424 1625 1476; x_wconf 40'>eS</span>
+      <span class='ocrx_word' id='word_1_78' title='bbox 1882 1433 1910 1460; x_wconf 59'>@</span>
+      <span class='ocrx_word' id='word_1_79' title='bbox 2024 1417 2069 1456; x_wconf 59'>Ww</span>
+      <span class='ocrx_word' id='word_1_80' title='bbox 2604 1423 2650 1468; x_wconf 19'>No</span>
+      <span class='ocrx_word' id='word_1_81' title='bbox 2878 1413 2934 1485; x_wconf 17'>a)</span>
       <span class='ocrx_word' id='word_1_82' title='bbox 3029 1425 3090 1476; x_wconf 33'>Oo</span>
      </span>
      <span class='ocr_line' id='line_1_12' title="bbox 45 1433 3041 1546; baseline -0.011 -11; x_size 108.376; x_descenders 22; x_ascenders 27.375999">
-      <span class='ocrx_word' id='word_1_83' title='bbox 45 1433 279 1535; x_wconf 61'>ee</span>
-      <span class='ocrx_word' id='word_1_84' title='bbox 353 1450 430 1514; x_wconf 27'>S&amp;S</span>
-      <span class='ocrx_word' id='word_1_85' title='bbox 528 1445 722 1535; x_wconf 55'>FF</span>
-      <span class='ocrx_word' id='word_1_86' title='bbox 915 1443 1158 1546; x_wconf 49'>SF</span>
-      <span class='ocrx_word' id='word_1_87' title='bbox 1233 1445 1317 1518; x_wconf 42'>HK</span>
-      <span class='ocrx_word' id='word_1_88' title='bbox 1386 1462 1427 1518; x_wconf 63'>S</span>
-      <span class='ocrx_word' id='word_1_89' title='bbox 1833 1453 1889 1502; x_wconf 66'>e</span>
-      <span class='ocrx_word' id='word_1_90' title='bbox 2004 1440 2046 1476; x_wconf 33'>©</span>
+      <span class='ocrx_word' id='word_1_83' title='bbox 45 1433 279 1535; x_wconf 63'>ee</span>
+      <span class='ocrx_word' id='word_1_84' title='bbox 353 1450 430 1514; x_wconf 22'>S&amp;S</span>
+      <span class='ocrx_word' id='word_1_85' title='bbox 528 1445 722 1535; x_wconf 56'>FF</span>
+      <span class='ocrx_word' id='word_1_86' title='bbox 915 1443 1158 1546; x_wconf 52'>SF</span>
+      <span class='ocrx_word' id='word_1_87' title='bbox 1233 1445 1317 1518; x_wconf 41'>LK</span>
+      <span class='ocrx_word' id='word_1_88' title='bbox 1386 1462 1427 1518; x_wconf 58'>S</span>
+      <span class='ocrx_word' id='word_1_89' title='bbox 1833 1453 1889 1502; x_wconf 59'>e</span>
+      <span class='ocrx_word' id='word_1_90' title='bbox 2004 1440 2046 1476; x_wconf 26'>©</span>
       <span class='ocrx_word' id='word_1_91' title='bbox 3006 1457 3041 1492; x_wconf 77'>4</span>
      </span>
      <span class='ocr_line' id='line_1_13' title="bbox 152 1516 1391 1593; baseline -0.006 -40; x_size 40; x_descenders 7; x_ascenders 13">
       <span class='ocrx_word' id='word_1_92' title='bbox 152 1520 214 1575; x_wconf 71'>~</span>
       <span class='ocrx_word' id='word_1_93' title='bbox 586 1526 646 1587; x_wconf 85'>&amp;</span>
-      <span class='ocrx_word' id='word_1_94' title='bbox 1304 1516 1391 1593; x_wconf 0'>e</span>
+      <span class='ocrx_word' id='word_1_94' title='bbox 1304 1516 1391 1593; x_wconf 4'>e&amp;</span>
      </span>
      <span class='ocr_line' id='line_1_14' title="bbox 247 1567 597 1619; baseline -0.009 0; x_size 55.75; x_descenders 10; x_ascenders 14.5">
-      <span class='ocrx_word' id='word_1_95' title='bbox 247 1570 297 1619; x_wconf 32'>3</span>
+      <span class='ocrx_word' id='word_1_95' title='bbox 247 1570 297 1619; x_wconf 1'>s</span>
       <span class='ocrx_word' id='word_1_96' title='bbox 550 1567 597 1609; x_wconf 43'>x</span>
      </span>
     </p>
@@ -162,8 +162,8 @@
     <p class='ocr_par' id='par_1_3' lang='eng' title="bbox 3354 711 3831 960">
      <span class='ocr_line' id='line_1_16' title="bbox 3354 711 3831 760; baseline 0 -9; x_size 49; x_descenders 9; x_ascenders 13">
       <span class='ocrx_word' id='word_1_98' title='bbox 3354 712 3542 751; x_wconf 0'>—H—</span>
-      <span class='ocrx_word' id='word_1_99' title='bbox 3480 707 3524 765; x_wconf 90'>No</span>
-      <span class='ocrx_word' id='word_1_100' title='bbox 3555 711 3773 760; x_wconf 80'>vote[note</span>
+      <span class='ocrx_word' id='word_1_99' title='bbox 3480 707 3524 765; x_wconf 92'>No</span>
+      <span class='ocrx_word' id='word_1_100' title='bbox 3555 711 3773 760; x_wconf 79'>vote[note</span>
       <span class='ocrx_word' id='word_1_101' title='bbox 3790 711 3831 760; x_wconf 96'>1]</span>
      </span>
      <span class='ocr_line' id='line_1_17' title="bbox 3355 815 3652 860; baseline 0.003 -9; x_size 44; x_descenders 8; x_ascenders 9">
@@ -171,15 +171,15 @@
       <span class='ocrx_word' id='word_1_103' title='bbox 3492 811 3652 864; x_wconf 96'>Oppose</span>
      </span>
      <span class='ocr_line' id='line_1_18' title="bbox 3354 912 3735 960; baseline 0.003 -9; x_size 50; x_descenders 10; x_ascenders 12">
-      <span class='ocrx_word' id='word_1_104' title='bbox 3354 912 3677 960; x_wconf 0'>—=—Net[note</span>
+      <span class='ocrx_word' id='word_1_104' title='bbox 3354 912 3677 960; x_wconf 12'>——Net[note</span>
       <span class='ocrx_word' id='word_1_105' title='bbox 3694 912 3735 960; x_wconf 96'>2]</span>
      </span>
     </p>
 
     <p class='ocr_par' id='par_1_4' lang='eng' title="bbox 3353 1011 3919 1060">
      <span class='ocr_line' id='line_1_19' title="bbox 3353 1011 3919 1060; baseline 0.004 -10; x_size 51; x_descenders 10; x_ascenders 13">
-      <span class='ocrx_word' id='word_1_106' title='bbox 3353 1007 3453 1066; x_wconf 23'>re</span>
-      <span class='ocrx_word' id='word_1_107' title='bbox 3486 1007 3723 1066; x_wconf 82'>Percentage</span>
+      <span class='ocrx_word' id='word_1_106' title='bbox 3353 1007 3453 1066; x_wconf 24'>re</span>
+      <span class='ocrx_word' id='word_1_107' title='bbox 3486 1007 3723 1066; x_wconf 88'>Percentage</span>
       <span class='ocrx_word' id='word_1_108' title='bbox 3749 1011 3864 1060; x_wconf 95'>[note</span>
       <span class='ocrx_word' id='word_1_109' title='bbox 3877 1011 3919 1060; x_wconf 95'>3]</span>
      </span>