v4.2.5: update release notes, fix silly typo in pageinfo.py

`brew install tesseract` just installed the english language pack not French, German or Spanish

.git_archival.txt

@@ -0,0 +1 @@
+ref-names: $Format:%D$

.gitattributes

@@ -5,4 +5,6 @@
 # (binary is a macro for -text -diff)
 *.jar	binary
 *.pdf	binary
-*.PDF	binary
+*.PDF	binary
+
+.git_archival.txt  export-subst

.github/ISSUE_TEMPLATE

@@ -0,0 +1,3 @@
+Please include the command line and (if needed) a test file with your issue report.
+
+If possible, please use a test file that we can include in future test cases (no personal information, no copyrighted material).

.gitignore

@@ -3,6 +3,7 @@
 *.sublime-*
 venv-*/
 pyvenv.cfg
+tasks.py
 
 # Package building
 *.egg-info/
@@ -26,5 +27,5 @@ log/
 .ipynb_checkpoints/
 tests/cache/
 tests/output/
-tests/resources/private
+tests/resources/private/
 tmp/

.travis.yml

@@ -1,3 +1,5 @@
+sudo: required
+dist: trusty
 language: python
 
 cache: pip
@@ -5,33 +7,30 @@ cache: pip
 cache:
     directories:
         - $HOME/.ccache
-        - tarballs
+        - packages
         - tests/cache
 
 python:
     - 3.4
+    - 3.5
 
 before_cache:
     - rm -f $HOME/.cache/pip/log/debug.log
 
 before_install:
     # Ubuntu packages
-    - sudo add-apt-repository ppa:evl.ms/precise -y  # for Ghostscript 9.15
-    - sudo add-apt-repository ppa:lyrasis/precise-backports -y  # for Tesseract 3.03
-    - sudo add-apt-repository ppa:b-eltzner/qpdfview-exp -y  # for QPDF 5
-    - sudo add-apt-repository ppa:itachi-san/ffmpeg -y  # for libav 11.2 (for unpaper)
+    - sudo add-apt-repository ppa:vshn/ghostscript -y  # for ghostscript 9.16 (trusty has 9.10)
+    - sudo add-apt-repository ppa:heyarje/libav-11 -y  # for libav11, which is for unpaper
     - sudo apt-get update -qq  # must go after all add-apt-repo
-    - sudo apt-get install -y ghostscript tesseract-ocr tesseract-ocr-deu tesseract-ocr-eng tesseract-ocr-fra qpdf poppler-utils gcc libavformat-dev libavcodec-dev libavutil-dev automake make pkg-config xsltproc libffi-dev
+    - sudo apt-get install -y ghostscript tesseract-ocr tesseract-ocr-deu tesseract-ocr-eng tesseract-ocr-fra qpdf poppler-utils libavformat56 libavcodec56 libavutil54 libffi-dev
 
     # pip
     - pip install --upgrade pip
 
     # Download, make and install unpaper (using ccache)
-    - mkdir -p tarballs
-    - "[ -f tarballs/unpaper-6.1.tar.xz ] || wget -q https://www.flameeyes.eu/files/unpaper-6.1.tar.xz -O tarballs/unpaper-6.1.tar.xz"
-    - tar -xvf tarballs/unpaper-6.1.tar.xz
-    - export PATH="/usr/lib/ccache:$PATH"
-    - pushd unpaper-6.1 && ./configure --prefix=/usr && make -j && sudo make install && popd
+    - mkdir -p packages
+    - "[ -f packages/unpaper_6.1-1.deb ] || wget -q https://dl.dropboxusercontent.com/u/28971240/unpaper_6.1-1.deb -O packages/unpaper_6.1-1.deb"
+    - sudo dpkg -i packages/unpaper_6.1-1.deb
 
 install:
     - pip install -r requirements.txt

Dockerfile

@@ -23,12 +23,8 @@ RUN apt-get update && apt-get install -y --no-install-recommends \
 
 RUN apt-get install -y --no-install-recommends \
   unpaper \
-  libopenjpeg-dev \
-  ghostscript \
   qpdf \
-  poppler-utils
-
-RUN apt-get install -y --no-install-recommends \
+  poppler-utils \
   tesseract-ocr \
   tesseract-ocr-deu tesseract-ocr-spa tesseract-ocr-eng tesseract-ocr-fra
 
@@ -37,6 +33,14 @@ RUN apt-get install -qy --no-install-recommends \
   libpython3-dev \
   gcc
 
+# Install Ghostscript from Debian sid to work around JPEG 2000 issue in
+# Debian stretch libgs9 or gs 9.16~dfsg-2.1
+
+COPY ./share/etc-apt-sources.list /etc/apt/sources.list
+
+RUN apt-get update && apt-get install -y ghostscript/sid
+
+
 # Enforce UTF-8
 # Borrowed from https://index.docker.io/u/crosbymichael/python/ 
 RUN dpkg-reconfigure locales && \

LICENSE.rst

@@ -1,4 +1,4 @@
-Copyright (c) 2013-2015, The OCRmyPDF Authors
+Copyright (c) 2013-2016, The OCRmyPDF Authors
 
 Permission is hereby granted, free of charge, to any person obtaining a
 copy of this software and associated documentation files (the

MANIFEST.in

@@ -1,4 +1,43 @@
-recursive-exclude tests/output *
+# requirements
 include requirements.txt
 include test_requirements.txt
-include share/*
+include dev_requirements.txt
+
+# git
+include .git_archival.txt
+
+# docker
+include Dockerfile
+include Dockerfile.polyglot
+include .dockerignore
+
+# tests
+include pytest.ini
+recursive-include tests *.jpg
+recursive-include tests *.pdf
+recursive-include tests *.py
+recursive-include tests *.rst
+recursive-include tests *.txt
+recursive-exclude tests/output *
+recursive-exclude tests/output_pageinfo *
+recursive-exclude tests/resources/private *
+recursive-exclude tests/cache *
+
+# documentation
+include *.rst
+include pipeline.svg
+recursive-exclude .github * 
+
+# support files
+recursive-include ocrmypdf/data *
+recursive-include share *
+include *.py
+exclude tasks.py
+
+# code
+recursive-include ocrmypdf *.py
+exclude ocrmypdf/lib/_leptonica.py
+include OCRmyPDF.sh
+include docker-wrapper.sh
+
+

OCRmyPDF.sh

@@ -3,4 +3,6 @@
 # Copyright (c) 2013-14: fritz-hh from Github (https://github.com/fritz-hh)
 ##############################################################################
 
+echo "This script is deprecated. Use 'ocrmypdf' instead."
+
 python3 -m ocrmypdf.main "$@"

README.rst

@@ -8,7 +8,7 @@ Main features
 -------------
 
 -  Generates a searchable
-   `PDF/A <https://en.wikipedia.org/?title=PDF/A>`__ file from a regular PDF
+   `PDF/A <https://en.wikipedia.org/?title=PDF/A>`_ file from a regular PDF
 -  Places OCR text accurately below the image to ease copy / paste
 -  Keeps the exact resolution of the original embedded images
 -  When possible, inserts OCR information as a "lossless" operation without rendering vector information
@@ -18,11 +18,11 @@ Main features
 -  Provides debug mode to enable easy verification of the OCR results
 -  Processes pages in parallel when more than one CPU core is
    available
--  Uses `Tesseract OCR <https://github.com/tesseract-ocr/tesseract>`__ engine
--  Supports the `39 languages <https://code.google.com/p/tesseract-ocr/downloads/list>`__ recognized by Tesseract
+-  Uses `Tesseract OCR <https://github.com/tesseract-ocr/tesseract>`_ engine
+-  Supports more than `100 languages <https://github.com/tesseract-ocr/tessdata>`_ recognized by Tesseract
 -  Battle-tested on thousands of PDFs, a test suite and continuous integration
 
-For details: please consult the `release notes <RELEASE_NOTES.rst>`__.
+For details: please consult the `release notes <RELEASE_NOTES.rst>`_.
 
 Motivation
 ----------
@@ -31,9 +31,9 @@ I searched the web for a free command line tool to OCR PDF files on
 Linux/UNIX: I found many, but none of them were really satisfying.
 
 -  Either they produced PDF files with misplaced text under the image (making copy/paste impossible) 
--  Or they did not display correctly some escaped HTML characters located in the hOCR file produced by the OCR engine 
+-  Or they did not handle accents and multilingual characters
 -  Or they changed the resolution of the embedded images
--  Or they generated PDF files having a ridiculous big size
+-  Or they generated ridiculously large PDF files
 -  Or they crashed when trying to OCR some of my PDF files
 -  Or they did not produce valid PDF files (even though they were readable with my current PDF reader)
 -  On top of that none of them produced PDF/A files (format dedicated for long time storage)
@@ -46,22 +46,45 @@ Installation
 
 Download OCRmyPDF here: https://github.com/jbarlow83/OCRmyPDF/releases
 
-You can install it to a Python virtual environment or system-wide. 
+These steps describe how to install OCRmyPDF on your system.
+
+- `Installing on Debian and Ubuntu`_ (Debian stretch and Ubuntu 16.10 or later)
+- `Installing the Docker image`_
+- `Installing on Mac OS X`_
+- `Installing on Ubuntu 14.04 LTS`_
+- Installing and running on `Windows`_ using the Docker image
+
+If you prefer to install from source or install OCRmyPDF to a Python virtual environment, see steps for `Installing HEAD revision from sources`_.
+
+.. _Windows: `Installing on Windows`_
+
+
+Installing on Debian and Ubuntu
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Users of Debian 9 or later or Ubuntu 16.10 or later may simply
+``apt-get install ocrmypdf``.
+
+.. _Docker:
 
 Installing the Docker image
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
 For many users, installing the Docker image will be easier than installing all of OCRmyPDF's dependencies. For Windows, it is the only option.
 
-If you have `Docker <https://docs.docker.com/>`__ installed on your system, you can install
+If you have `Docker <https://docs.docker.com/>`_ installed on your system, you can install
 a Docker image of the latest release.
 
 Follow the Docker installation instructions for your platform.  If you can run this command
-successfully, your system is ready to download and execute the image::
+successfully, your system is ready to download and execute the image:
+
+.. code-block:: bash
 
    docker run hello-world
    
-OCRmyPDF will use all available CPU cores.  By default, the VirtualBox machine instance on Windows and OS X has only a single CPU core enabled. Use the VirtualBox Manager to determine the name of your Docker engine host, and then follow these optional steps to enable multiple CPUs::
+OCRmyPDF will use all available CPU cores.  By default, the VirtualBox machine instance on Windows and OS X has only a single CPU core enabled. Use the VirtualBox Manager to determine the name of your Docker engine host, and then follow these optional steps to enable multiple CPUs:
+
+.. code-block:: bash
 
    # Optional step for Mac OS X users
    docker-machine stop "yourVM"
@@ -70,29 +93,41 @@ OCRmyPDF will use all available CPU cores.  By default, the VirtualBox machine i
    eval $(docker-machine env "yourVM")
 
 Assuming you have a Docker engine running somewhere, you can run these commands to download
-the image::
+the image:
+
+.. code-block:: bash
 
    docker pull jbarlow83/ocrmypdf
 
-Then tag it to give a more convenient name, just ocrmypdf::
+Then tag it to give a more convenient name, just ocrmypdf:
+
+.. code-block:: bash
 
    docker tag jbarlow83/ocrmypdf ocrmypdf
 
-This image contains language packs for English, French, Spanish and German. The alternative "polyglot" image provides `all available language packs <https://github.com/tesseract-ocr/tesseract/blob/master/doc/tesseract.1.asc#languages>`__::
+This image contains language packs for English, French, Spanish and German. The alternative "polyglot" image provides `all available language packs <https://github.com/tesseract-ocr/tesseract/blob/master/doc/tesseract.1.asc#languages>`_:
+
+.. code-block:: bash
 
    # Alternative step: If you need all language packs
    docker pull jbarlow83/ocrmypdf-polyglot
    docker tag jbarlow83/ocrmypdf-polyglot ocrmypdf
 
-You can then run ocrmypdf using the command::
+You can then run ocrmypdf using the command:
+
+.. code-block:: bash
 
    docker run ocrmypdf --help
   
-To execute the OCRmyPDF on a local file, you must `provide a writable volume to the Docker image <https://docs.docker.com/userguide/dockervolumes/>`__, such as this in this template::
+To execute the OCRmyPDF on a local file, you must `provide a writable volume to the Docker image <https://docs.docker.com/userguide/dockervolumes/>`_, such as this in this template:
+
+.. code-block:: bash
 
    docker run -v "$(pwd):/home/docker" <other docker arguments>   ocrmypdf <your arguments to ocrmypdf>
 
-In this worked example, the current working directory contains an input file called ``test.pdf`` and the output will go to ``output.pdf``:: 
+In this worked example, the current working directory contains an input file called ``test.pdf`` and the output will go to ``output.pdf``: 
+
+.. code-block:: bash
 
    docker run -v "$(pwd):/home/docker"   ocrmypdf --skip-text test.pdf output.pdf
 
@@ -104,84 +139,135 @@ Installing on Mac OS X
 
 These instructions probably work on all Mac OS X versions later than 10.7 (Lion). OCRmyPDF is known to work on Yosemite and El Capitan, and regularly tested on El Capitan.
 
-If it's not already present, `install Homebrew <http://brew.sh/>`__.
+If it's not already present, `install Homebrew <http://brew.sh/>`_.
 
-Update Homebrew::
+Update Homebrew:
+
+.. code-block:: bash
 
    brew update
    
-Install or upgrade the required Homebrew packages, if any are missing::
+Install or upgrade the required Homebrew packages, if any are missing:
 
-   brew install libpng openjpeg jbig2dec     # image libraries
+.. code-block:: bash
+
+   brew install libpng openjpeg jbig2dec libtiff     # image libraries
    brew install qpdf
    brew install ghostscript
    brew install python3
-   brew install libxml2
-   brew install leptonica
-   brew install tesseract
+   brew install libxml2 libffi leptonica
+   brew install unpaper   # optional
    
-Update the homebrew pip and install Pillow::
+Install the required Tesseract OCR engine with the language packs you plan to use:
+   
+.. code-block:: bash
+
+   brew install tesseract                       # Option 1: for English
+   
+.. code-block:: bash
+   
+   brew install tesseract --with-all-languages  # Option 2: for all language packs 
+   
+Update the homebrew pip and install Pillow:
+
+.. code-block:: bash
 
    pip3 install --upgrade pip
    pip3 install --upgrade pillow
 
-You can then install OCRmyPDF from PyPI::
+You can then install OCRmyPDF from PyPI:
+
+.. code-block:: bash
 
    pip3 install ocrmypdf
 
-The command line program should now be available::
+The command line program should now be available:
+
+.. code-block:: bash
 
    ocrmypdf --help
 
 Installing on Ubuntu 14.04 LTS
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
-Installing on Ubuntu 14.04 LTS (trusty) is more difficult than other options, because of certain bugs in Python package installation.
+Installing on Ubuntu 14.04 LTS (trusty) is more difficult than some other options, because of bugs in Python package installation.
 
-Update apt-get::
+Add new "apt" repositories needed for backports of Ghostscript 9.16 and libav-11, which supports unpaper 6.1. This will replace Ghostscript on your system.
+
+.. code-block:: bash
+
+   sudo add-apt-repository ppa:vshn/ghostscript -y 
+   sudo add-apt-repository ppa:heyarje/libav-11 -y
+
+Update apt-get:
+
+.. code-block:: bash
 
    sudo apt-get update
    sudo apt-get upgrade
    
-Install system dependencies::
+Install system dependencies:
+
+.. code-block:: bash
 
    sudo apt-get install \
       zlib1g-dev \
       libjpeg-dev \
+      libffi-dev \
+      libavformat56 libavcodec56 libavutil54 \
       ghostscript \
       tesseract-ocr \
       qpdf \
-      unpaper \
       python3-pip \
       python3-pil \
       python3-pytest \
       python3-reportlab
 
 If you wish install OCRmyPDF to the system Python, then install as follows (note this installs new packages
-into your system Python, which could interfere with other programs)::
+into your system Python, which could interfere with other programs):
+
+.. code-block:: bash
 
    sudo pip3 install ocrmypdf
    
-If you wish to install OCRmyPDF to a virtual environment to isolate system Python from modified, you can
+If you wish to install OCRmyPDF to a virtual environment to isolate the system Python, you can
 follow these steps.  This includes a workaround `for a known, unresolved issue in Ubuntu 14.04's ensurepip
-package <http://www.thefourtheye.in/2014/12/Python-venv-problem-with-ensurepip-in-Ubuntu.html>`__::
+package <http://www.thefourtheye.in/2014/12/Python-venv-problem-with-ensurepip-in-Ubuntu.html>`_:
+
+.. code-block:: bash
 
    sudo apt-get install python3-venv
    python3 -m venv venv-ocrmypdf --without-pip
    source venv-ocrmypdf/bin/activate
    wget -O - -o /dev/null https://bootstrap.pypa.io/get-pip.py | python
    deactivate
-   pyvenv --system-site-packages venv-ocrmypdf
+   python3 -m venv --system-site-packages venv-ocrmypdf
    source venv-ocrmypdf/bin/activate
    pip install ocrmypdf
 
-Ubuntu 14.04 only installs ``unpaper`` version 0.4.2, which is not supported by OCRmyPDF because it is produces invalid output. This program is an optional dependency, and provides page deskewing and cleaning. See `Dockerfile <Dockerfile>`__ for an example of how to building unpaper 6.1 from source. If you choose to install unpaper later, OCRmyPDF will use the foremost version on the system PATH.
+These installation instructions omit the optional dependency ``unpaper``, which is only available at version 0.4.2 in Ubuntu 14.04. The author could not find a backport of ``unpaper`` and is not motivated to figure how to set up a Ubuntu PPA to distribute it. You can create a .deb package to do the job of installing unpaper 6.1 (for x86 64-bit only):
+
+.. code-block:: bash
+
+   wget -q https://dl.dropboxusercontent.com/u/28971240/unpaper_6.1-1.deb -O unpaper_6.1-1.deb
+   sudo dpkg -i unpaper_6.1-1.deb
+
 
 Installing on Windows
 ~~~~~~~~~~~~~~~~~~~~~
 
-Direct installation on Windows is not possible.  Install the Docker container as described above.
+Direct installation on Windows is not possible.  Install the _`Docker` container as described above.  Ensure that your command prompt can run the docker "hello world" container.
 
+Running on Windows
+~~~~~~~~~~~~~~~~~~
+
+The command line syntax to run ocrmypdf from a command prompt will resemble:
+
+.. code-block:: bat
+
+   docker run -v /c/Users/sampleuser:/home/docker ocrmypdf --skip-text test.pdf output.pdf
+
+where /c/Users/sampleuser is a Unix representation of the Windows path C:\\Users\\sampleuser, assuming a user named "sampleuser" is running ocrmypdf on a file in their home directory, and the files "test.pdf" and "output.pdf" are in the sampleuser folder. The Windows user must have read and write permissions.
       
 Installing HEAD revision from sources
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
@@ -189,24 +275,32 @@ Installing HEAD revision from sources
 If you have ``git`` and ``python3.4`` or ``python3.5`` installed, you can install from source. When the ``pip`` installer runs,
 it will alert you if dependencies are missing.
 
-To install the HEAD revision from sources in the current Python 3 environment::
+To install the HEAD revision from sources in the current Python 3 environment:
+
+.. code-block:: bash
 
    pip3 install git+https://github.com/jbarlow83/OCRmyPDF.git
 
-Or, to install in `development mode <https://pythonhosted.org/setuptools/setuptools.html#development-mode>`__,  allowing customization of OCRmyPDF, use the ``-e`` flag::
+Or, to install in `development mode <https://pythonhosted.org/setuptools/setuptools.html#development-mode>`_,  allowing customization of OCRmyPDF, use the ``-e`` flag:
+
+.. code-block:: bash
 
    pip3 install -e git+https://github.com/jbarlow83/OCRmyPDF.git
    
 On certain Linux distributions such as Ubuntu, you may need to use 
-run the install command as superuser::
+run the install command as superuser:
+
+.. code-block:: bash
 
    sudo pip3 install [-e] git+https://github.com/jbarlow83/OCRmyPDF.git
    
 Note that this will alter your system's Python distribution. If you prefer 
-to not install as superuser, you can install the package in a Python virtual environment::
+to not install as superuser, you can install the package in a Python virtual environment:
+
+.. code-block:: bash
 
    git clone -b master https://github.com/jbarlow83/OCRmyPDF.git
-   pyvenv venv
+   python3 -m venv
    source venv/bin/activate
    cd OCRmyPDF
    pip3 install .
@@ -214,7 +308,9 @@ to not install as superuser, you can install the package in a Python virtual env
 However, ``ocrmypdf`` will only be accessible on the system PATH after
 you activate the virtual environment.
 
-To run the program::
+To run the program:
+
+.. code-block:: bash
    
    ocrmypdf --help
 
@@ -227,10 +323,15 @@ Languages
 ---------
 
 OCRmyPDF uses Tesseract for OCR, and relies on its language packs. For Linux users,
-you can often find packages that provide language packs::
+you can often find packages that provide language packs:
+
+.. code-block:: bash
+
+   # Display a list of all Tesseract language packs
+   apt-cache search tesseract-ocr
 
    # Debian/Ubuntu users
-   sudo apt-get install tesseract-ocr-chi-sim
+   sudo apt-get install tesseract-ocr-chi-sim  # Example: Install Chinese Simplified language back
    
 You can then pass the ``-l LANG`` argument to OCRmyPDF to give a hint as to what languages it should search for. Multiple
 languages can be requested.
@@ -238,9 +339,17 @@ languages can be requested.
 Support
 -------
 
-In case you detect an issue, please:
+Once ocrmypdf is installed, the built-in help which explains the command syntax and options can be accessed via:
 
--  Check if your issue is already known
+.. code-block:: bash
+
+   ocrmypdf --help
+
+The `Wiki <https://github.com/jbarlow83/OCRmyPDF/wiki>`_ page also contains some tips and suggests.
+
+If you detect an issue, please:
+
+-  Check whether your issue is already known
 -  If no problem report exists on github, please create one here:
    https://github.com/jbarlow83/OCRmyPDF/issues
 -  Describe your problem thoroughly
@@ -252,11 +361,11 @@ In case you detect an issue, please:
 Press & Media
 -------------
 
--  `c't 1-2014, page 59 <http://www.heise.de/ct/inhalt/2014/1/58/>`__:
+-  `c't 1-2014, page 59 <http://heise.de/-2279695>`_:
    Detailed presentation of OCRmyPDF v1.0 in the leading German IT
    magazine c't
 -  `heise Open Source, 09/2014: Texterkennung mit
-   OCRmyPDF <http://www.heise.de/-2356670>`__
+   OCRmyPDF <http://heise.de/-2356670>`_
 
 Disclaimer
 ----------

RELEASE_NOTES.rst

@@ -1,9 +1,155 @@
 RELEASE NOTES
 =============
 
-Please always read this file before installing the package
+OCRmyPDF uses `semantic versioning <http://semver.org/>`_.
 
-Download software here: https://github.com/jbarlow83/OCRmyPDF/tags
+
+v4.2.5:
+=======
+
+-  Fixed an issue (#100) with PDFs that omit the optional /BitsPerComponent parameter on images
+-  Removed non-free file milk.pdf
+
+
+v4.2.4:
+=======
+
+-  Fixed an error (#90) caused by PDFs that use stencil masks properly
+-  Fixed handling of PDFs that try to draw images or stencil masks without properly setting up the graphics state (such images are now ignored for the purposes of calculating DPI)
+
+v4.2.3:
+=======
+
+-  Fixed an issue with PDFs that store page rotation (/Rotate) in an indirect object
+-  Integrated a few fixes to simplify downstream packaging (Debian)
+
+   +  The test suite no longer assumes it is installed
+   +  If running Linux, skip a test that passes Unicode on the command line
+
+-  Added a test case to check explicit masks and stencil masks
+-  Added a test case for indirect objects and linearized PDFs
+-  Deprecated the OCRmyPDF.sh shell script
+
+
+v4.2.2:
+=======
+
+-  Improvements to documentation
+
+
+v4.2.1:
+=======
+
+-  Fixed an issue where PDF pages that contained stencil masks would report an incorrect DPI and cause Ghostscript to abort
+-  Implemented stdin streaming
+
+
+v4.2:
+=====
+
+-  ocrmypdf will now try to convert single image files to PDFs if they are provided as input (#15)
+
+   +  This is a basic convenience feature. It only supports a single image and always makes the image fill the whole page.
+   +  For better control over image to PDF conversion, use ``img2pdf`` (one of ocrmypdf's dependencies)
+
+-  New argument ``--output-type {pdf|pdfa}`` allows disabling Ghostscript PDF/A generation
+
+   +  ``pdfa`` is the default, consistent with past behavior
+   +  ``pdf`` provides a workaround for users concerned about the increase in file size from Ghostscript forcing JBIG2 images to CCITT and transcoding JPEGs
+   +  ``pdf`` preserves as much as it can about the original file, including problems that PDF/A conversion fixes
+
+-  PDFs containing images with "non-square" pixel aspect ratios, such as 200x100 DPI, are now handled and converted properly (fixing a bug that caused to be cropped)
+-  ``--force-ocr`` rasterizes pages even if they contain no images
+
+   +  supports users who want to use OCRmyPDF to reconstruct text information in PDFs with damaged Unicode maps (copy and paste text does not match displayed text)
+   +  supports reinterpreting PDFs where text was rendered as curves for printing, and text needs to be recovered
+   +  fixes issue #82
+
+-  Fixes an issue where, with certain settings, monochrome images in PDFs would be converted to 8-bit grayscale, increasing file size (#79)
+-  Support for Ubuntu 12.04 LTS "precise" has been dropped in favor of (roughly) Ubuntu 14.04 LTS "trusty" 
+
+   +  Some Ubuntu "PPAs" (backports) are needed to make it work
+      
+-  Support for some older dependencies dropped
+
+   +  Ghostscript 9.15 or later is now required (available in Ubuntu trusty with backports)
+   +  Tesseract 3.03 or later is now required (available in Ubuntu trusty)
+
+-  Ghostscript now runs in "safer" mode where possible
+
+v4.1.4:
+=======
+
+-  Bug fix: monochrome images with an ICC profile attached were incorrectly converted to full color images if lossless reconstruction was not possible due to other settings; consequence was increased file size for these images
+
+
+v4.1.3:
+=======
+
+-  More helpful error message for PDFs with version 4 security handler
+-  Update usage instructions for Windows/Docker users
+-  Fix order of operations for matrix multiplication (no effect on most users)
+-  Add a few leptonica wrapper functions (no effect on most users)
+
+
+v4.1.2:
+=======
+
+-  Replace IEC sRGB ICC profile with Debian's sRGB (from icc-profiles-free) which is more compatible with the MIT license
+-  More helpful error message for an error related to certain types of malformed PDFs
+
+
+v4.1:
+=====
+
+-  ``--rotate-pages`` now only rotates pages when reasonably confidence in the orientation. This behavior can be adjusted with the new argument ``--rotate-pages-threshold``
+-  Fixed problems in error checking if ``unpaper`` is uninstalled or missing at run-time
+-  Fixed problems with "RethrownJobError" errors during error handling that suppressed the useful error messages
+
+
+v4.0.7:
+=======
+
+-  Minor correction to Ghostscript output settings
+
+
+v4.0.6:
+=======
+
+-  Update install instructions
+-  Provide a sRGB profile instead of using Ghostscript's
+
+
+v4.0.5:
+=======
+
+-  Remove some verbose debug messages from v4.0.4
+-  Fixed temporary that wasn't being deleted
+-  DPI is now calculated correctly for cropped images, along with other image transformations
+-  Inline images are now checked during DPI calculation instead of rejecting the image
+
+v4.0.4:
+=======
+
+Released with verbose debug message turned on. Do not use. Skip to v4.0.5.
+
+
+v4.0.3:
+=======
+
+New features
+------------
+
+-  Page orientations detected are now reported in a summary comment
+
+
+Fixes
+-----
+
+-  Show stack trace if unexpected errors occur
+-  Treat "too few characters" error message from Tesseract as a reason to skip that page rather than
+   abort the file
+-  Docker: fix blank JPEG2000 issue by insisting on Ghostscript versions that have this fixed
 
 
 v4.0.2:
@@ -273,363 +419,6 @@ Notes and known issues
 v2.2-stable (2014-09-29):
 =========================
 
-New features
-------------
+OCRmyPDF versions 1 and 2 were implemented as shell scripts. OCRmyPDF 3.0+ is a fork that gradually replaced all shell scripts with Python while maintaining the existing command line arguments. No one is maintaining old versions.
 
-- None
-
-Changes
--------
-
-- Update to jhove v1.11
-- Request the python library reportlab v3.0 or newer (So that we could remove a patch to the previous version of reportlab leading to issues for some users)
-
-Fixes
------
-
-- Fix bug on Mac OS X (resolution of simlink to OCRmyPDF.sh script) (thanks to jbarlow83)
-- Check if the input pdf file exists before to continue
-
-Tested with
------------
-
-- Operating system: FreeBSD 9.2
-- Dependencies:
-
-   - parallel 20140822
-   - poppler-utils 0.24.5
-   - ImageMagick 6.8.9-4 2014-09-17
-   - Unpaper 0.3
-   - tesseract 3.02.02
-   - Python 2.7.8
-   - ghostcript (gs): 9.06
-   - java: openjdk version "1.7.0_65"
-
-
-v2.1-stable (2014-09-20):
-=========================
-
-New features
-------------
-
--  None
-
-Changes
--------
-
--  None
-
-Fixes
------
-
--  Allow execution via simlink
--  Add support for tesseract 3.03
--  Add support for newer version of reportlab
--  Lowered minimum version of gnu parallel
--  Various typo
-
-Tested with
------------
-
--  Operating system: FreeBSD 9.1
--  Dependencies:
--  parallel 20130222
--  poppler-utils 0.22.2
--  ImageMagick 6.8.0-7 2013-03-30
--  Unpaper 0.3
--  tesseract 3.02.02
--  Python 2.7.3
--  ghoscript (gs): 9.06
--  java: openjdk version "1.7.0\_17"
-
-v2.0-stable (2014-01-25):
-=========================
-
-New features
-------------
-
--  Check if the language(s) passed using the -l option is supported by
-   tesseract (fixes #60)
-
-Changes
--------
-
--  Allow OCRmyPDF to be used with tesseract 3.02.01, even though OCR
-   might fail for few PDF file (see issue #28). Rationale: For some
-   linux distribution, no newer version than tesseract 3.02.01 is
-   available
-
-Fixes
------
-
--  More robust algorithm for checking the version of the installed
-   tesseract package
-
-Tested with
------------
-
--  Operating system: FreeBSD 9.1
--  Dependencies:
--  parallel 20130222
--  poppler-utils 0.22.2
--  ImageMagick 6.8.0-7 2013-03-30
--  Unpaper 0.3
--  tesseract 3.02.02
--  Python 2.7.3
--  ghoscript (gs): 9.06
--  java: openjdk version "1.7.0\_17"
-
-v2.0-rc2 (2014-01-16):
-======================
-
-New features
-------------
-
--  None
-
-Changes
--------
-
--  Size reduction of final PDF file: (fixes #50)
--  Support for monochrome (Black&White) images (massive size reduction
-   in final PDF: >80%)
--  Reduced size of grayscale images (by 13% on test PDF file)
--  Preventing fi, fl ligatures does not require anymore to pass an
-   additional config file to tesseract using the -C option (fixes #58)
--  Location of temporary folder according to content of environment
-   variable TMPDIR.
--  Dependency to pdftk removed
--  Check for compatible versions of dependencies: (fixes #51)
--  parallel and tesseract
--  python libraries reportlab and lxml
-
-Fixes
------
-
--  Improved portability with various shells (dash, bash, tcsh) and OS
-   (FreeBSD, MAC OSX, Linux) (fixes #59)
--  Corrected bug in case the input PDF file contains a space character
-   (fixes #48)
--  Prevent spurious error message in case there is no image in a PDF
-   page
--  Prevent collision of temporary folder names (fixes #57)
-
-Tested with
------------
-
--  Operating system: FreeBSD 9.1
--  Dependencies:
--  parallel 20130222
--  poppler-utils 0.22.2
--  ImageMagick 6.8.0-7 2013-03-30
--  Unpaper 0.3
--  tesseract 3.02.02
--  Python 2.7.3
--  ghoscript (gs): 9.06
--  java: openjdk version "1.7.0\_17"
-
-v2.0-rc1 (2014-01-07):
-======================
-
-New features
-------------
-
--  Huge performance improvement on machines having multiple CPU/cores
-   (processing of several pages concurrently) (fixes #18)
--  By default prevent from processing a PDF file already containing
-   fonts (i.e. text)(it can be overridden with the -f flag) (fixes #16)
--  Warn if the resolution is too low to get reasonable OCR results
-   (fixes #37)
--  New option (-o) to perform automatic oversampling if the image
-   resolution is too low. This can improve OCR results.
--  Warn if using a tesseract version older than v3.02.02 (as older
-   versions are known to produce invalid output) (fixes #41)
--  Echo version of the installed dependencies (e.g. tesseract) in debug
-   mode in order to ease support (fixes #35)
--  Echo the arguments passed to the script in debug mode to ease support
-
-Changes
--------
-
--  In debug mode: The debug page is now placed after the respective
-   "normal" page
--  Reduced disk space usage in temporary folder if -d (deskew) or -c
-   (cleanup) options are not selected
--  New file src/config.sh containing various configuration parameters
--  Documentation of the tesseract config file "tess-cfg/no\_ligature"
-   improved
--  Improved consistency of the temporary file names
-
-Fixes
------
-
--  Improved robustness:
--  in case vertical resolution differs from horizontal resolution (fixes
-   #38)
--  in case a PDF page contains more than one image (fixes #36)
--  Fix a problem occurring if python 3 is the standard interpreter
-   (fixes #33)
--  Fix a problem occurring if the input PDF file contains special
-   characters like "#" (fixes #34)
-
-Tested with
------------
-
--  Operating system: FreeBSD 9.1
--  Dependencies:
--  parallel 20130222
--  poppler-utils 0.22.2
--  ImageMagick 6.8.0-7 2013-03-30
--  Unpaper 0.3
--  tesseract 3.02.02
--  Python 2.7.3
--  pdftk 1.45
--  ghoscript (gs): 9.06
--  java: openjdk version "1.7.0\_17"
-
-v1.1-stable (2014-01-06):
-=========================
-
-New features
-------------
-
--  N/A
-
-Changes
--------
-
--  N/A
-
-Fixes
------
-
--  Fixed syntax error (bashism) leading to an error message on certain
-   systems (fixes #42)
-
-Tested with
------------
-
--  Operating system: FreeBSD 9.1
--  Dependencies:
--  poppler-utils 0.22.2
--  ImageMagick 6.8.0-7 2013-03-30
--  Unpaper 0.3
--  tesseract 3.02.02
--  Python 2.7.3
--  pdftk 1.45
--  ghoscript (gs): 9.06
--  java: openjdk version "1.7.0\_17"
-
-v1.0-stable (2013-05-06):
-=========================
-
-New features
-------------
-
--  In debug mode: compute and echo time required for processing (fixes
-   #26)
-
-Changes
--------
-
--  Removed feature to add metadata in final pdf file (because it lead to
-   to final PDF file that does not comply to the PDF/A-1 format)
--  Removed feature to set same owner & permissions in final PDF file
-   than in input file
--  Removed many unused jhove files (e.g. documentation, \*.java and
-   \*.class files)
-
-Fixes
------
-
--  Correction to handle correctly path and input PDF files having spaces
-   (fixes #31)
--  Resolutions (x/y) that are nearly equal are now supported (fixes #25)
--  Fix compatibility issue with Ubuntu server 12.04 / Ubuntu server
-   10.04 / Linux Mint 13 Maya and probably other Linux distributions
-   (fixes #27)
--  Commit missing jhove files (\*.jar mainly) due to wrong .gitignore
-
-Tested with
------------
-
--  Operating system: FreeBSD 9.1
--  Dependencies:
--  poppler-utils 0.22.2
--  ImageMagick 6.8.0-7 2013-03-30
--  Unpaper 0.3
--  tesseract 3.02.02
--  Python 2.7.3
--  pdftk 1.45
--  ghoscript (gs): 9.06
--  java: openjdk version "1.7.0\_17"
-
-v1.0-rc2 (2013-04-29):
-======================
-
-New features
-------------
-
--  Keep temporary files if debug mode is set (fixes #22)
--  Set same owner & permissions in final PDF file than in input file
-   (fixes #9)
--  Added metadata in final pdf file (fixes #4)
-
-Changes
--------
-
--  N/A
-
-Fixes
------
-
--  Fixed wrong image cropping when deskew option is activated
--  Exit with error message if page size is not found in hocr file (fixes
-   #21)
--  Various minor fixes in log messages
-
-Tested with
------------
-
--  Operating system: FreeBSD 9.1
--  Dependencies:
--  poppler-utils 0.22.2
--  ImageMagick 6.8.0-7 2013-03-30
--  Unpaper 0.3
--  tesseract 3.02.02
--  Python 2.7.3
--  pdftk 1.45
--  ghoscript (gs): 9.06
--  java: openjdk version "1.7.0\_17"
-
-v1.0-rc1 (2013-04-26):
-======================
-
-New features
-------------
-
--  First release candidate
-
-Changes
--------
-
--  N/A
-
-Fixes
------
-
--  N/A
-
-Tested with
------------
-
--  Operating system: FreeBSD 9.1
--  Dependencies:
--  poppler-utils 0.22.2
--  ImageMagick 6.8.0-7 2013-03-30
--  Unpaper 0.3
--  tesseract 3.02.02
--  Python 2.7.3
--  pdftk 1.45
--  ghoscript (gs): 9.06
--  java: openjdk version "1.7.0\_17"
+For details on older versions, see the `final version of its release notes <https://github.com/fritz-hh/OCRmyPDF/blob/7fd3dbdf42ca53a619412ce8add7532c5e81a9d1/RELEASE_NOTES.md>`_.

dev_requirements.txt

@@ -0,0 +1,4 @@
+check-manifest>=0.33
+setuptools-scm>=1.11.1
+twine>=1.8.1
+coverage>=4.2

ocrmypdf/__init__.py

@@ -1,5 +1,6 @@
 from enum import IntEnum
 import os
+from collections.abc import Iterable
 
 
 class ExitCode(IntEnum):
@@ -7,11 +8,13 @@ class ExitCode(IntEnum):
     bad_args = 1
     input_file = 2
     missing_dependency = 3
-    invalid_output_pdfa = 4
+    invalid_output_pdf = 4
     file_access_error = 5
     already_done_ocr = 6
     child_process_error = 7
+    encrypted_pdf = 8
     other_error = 15
+    ctrl_c = 130
 
 
 def get_program(name):
@@ -21,3 +24,7 @@ def get_program(name):
 
 def page_number(input_file):
     return int(os.path.basename(input_file)[0:6])
+
+
+def is_iterable_notstr(thing):
+    return isinstance(thing, Iterable) and not isinstance(thing, str)

ocrmypdf/ghostscript.py

@@ -5,6 +5,7 @@ from tempfile import NamedTemporaryFile
 from subprocess import Popen, PIPE, check_call
 from shutil import copy
 from . import get_program
+from .pdfa import SRGB_ICC_PROFILE
 
 
 def rasterize_pdf(input_file, output_file, xres, yres, raster_device, log,
@@ -13,6 +14,7 @@ def rasterize_pdf(input_file, output_file, xres, yres, raster_device, log,
         args_gs = [
             get_program('gs'),
             '-dQUIET',
+            '-dSAFER',
             '-dBATCH',
             '-dNOPAUSE',
             '-sDEVICE=%s' % raster_device,
@@ -52,7 +54,6 @@ def generate_pdfa(pdf_pages, output_file, threads=1):
             "-dJPEGQ=95",
             "-dPDFA=2",
             "-sPDFACompatibilityPolicy=2",
-            "-sOutputICCProfile=srgb.icc",
             "-sOutputFile=" + gs_pdf.name,
         ]
         args_gs.extend(pdf_pages)

ocrmypdf/leptonica.py

@@ -17,6 +17,7 @@ from tempfile import TemporaryFile
 from ctypes.util import find_library
 from .lib._leptonica import ffi
 from functools import lru_cache
+from enum import Enum
 
 lept = ffi.dlopen(find_library('lept'))
 
@@ -83,6 +84,13 @@ class LeptonicaIOError(LeptonicaError):
     pass
 
 
+class RemoveColormap(Enum):
+    to_binary = 0
+    to_grayscale = 1
+    to_full_color = 2
+    based_on_src = 3
+
+
 class Pix:
     """Wrapper around leptonica's PIX object.
 
@@ -98,27 +106,31 @@ class Pix:
     in a threadsafe manner if a Python threading.Lock protects the data.
     """
 
-    def __init__(self, cpix):
-        self.cpix = ffi.gc(cpix, Pix._pix_destroy)
+    def __init__(self, pix):
+        self._pix = ffi.gc(pix, Pix._pix_destroy)
 
     def __repr__(self):
-        if self.cpix:
+        if self._pix:
             s = "<leptonica.Pix image size={0}x{1} depth={2} at 0x{3:x}>"
-            return s.format(self.cpix.w, self.cpix.h, self.cpix.d,
-                            int(ffi.cast("intptr_t", self.cpix)))
+            return s.format(self._pix.w, self._pix.h, self._pix.d,
+                            int(ffi.cast("intptr_t", self._pix)))
         else:
             return "<leptonica.Pix image NULL>"
 
     def __getstate__(self):
-        data = ffi.new('l_uint32 *[]', 1)
-        size = ffi.new('size_t *', 0)
+        data = ffi.new('l_uint32 **')
+        size = ffi.new('size_t *')
 
-        err = lept.pixSerializeToMemory(self.cpix, data, size)
+        err = lept.pixSerializeToMemory(self._pix, data, size)
         if err != 0:
             raise LeptonicaIOError("pixSerializeToMemory")
 
         char_data = ffi.cast('char *', data[0])
+
+        # Copy from C bytes to python bytes()
         data_bytes = ffi.buffer(char_data, size[0])[:]
+
+        # Can now free C bytes
         lept.lept_free(char_data)
         return dict(data=data_bytes)
 
@@ -126,16 +138,41 @@ class Pix:
         cdata_bytes = ffi.new('char[]', state['data'])
         cdata_uint32 = ffi.cast('l_uint32 *', cdata_bytes)
 
-        self.cpix = lept.pixDeserializeFromMemory(
+        pix = lept.pixDeserializeFromMemory(
             cdata_uint32, len(state['data']))
+        Pix.__init__(self, pix)
 
     @property
     def width(self):
-        return self.cpix.w
+        return self._pix.w
 
     @property
     def height(self):
-        return self.cpix.h
+        return self._pix.h
+
+    @property
+    def depth(self):
+        return self._pix.d
+
+    @property
+    def size(self):
+        return (self._pix.w, self._pix.h)
+
+    @property
+    def info(self):
+        return {'dpi': (self._pix.xres, self._pix.yres)}
+
+    @property
+    def mode(self):
+        "Return mode like PIL.Image"
+        if self.depth == 1:
+            return '1'
+        elif self.depth >= 16:
+            return 'RGB'
+        elif not self._pix.colormap:
+            return 'L'
+        else:
+            return 'P'
 
     @classmethod
     def read(cls, filename):
@@ -158,7 +195,29 @@ class Pix:
         with LeptonicaErrorTrap():
             lept.pixWriteImpliedFormat(
                 filename.encode(sys.getfilesystemencoding()),
-                self.cpix, jpeg_quality, jpeg_progressive)
+                self._pix, jpeg_quality, jpeg_progressive)
+
+    def topil(self):
+        "Returns a PIL.Image version of this Pix"
+        from PIL import Image
+
+        with LeptonicaErrorTrap():
+            pix_swapped = Pix(lept.pixEndianByteSwapNew(self._pix))
+
+        size = (pix_swapped._pix.wpl * 4, pix_swapped._pix.h)
+        buf = ffi.buffer(pix_swapped._pix.data, size[0] * size[1])
+
+        im_raw = Image.frombytes(self.mode, size, buf, 'raw')
+
+        # Leptonica stores images in 32-bit words
+        # Need to crop the any trailing amount
+        box = (0, 0, self.width, self.height)
+        im = im_raw.crop(box)
+
+        return im
+
+    def show(self):
+        return self.topil().show()
 
     def deskew(self, reduction_factor=0):
         """Returns the deskewed pix object.
@@ -170,16 +229,21 @@ class Pix:
             for skew angle
         """
         with LeptonicaErrorTrap():
-            return Pix(lept.pixDeskew(self.cpix, reduction_factor))
+            return Pix(lept.pixDeskew(self._pix, reduction_factor))
 
     def scale(self, scalex, scaley):
         "Returns the pix object rescaled according to the proportions given."
         with LeptonicaErrorTrap():
-            return Pix(lept.pixScale(self.cpix, scalex, scaley))
+            return Pix(lept.pixScale(self._pix, scalex, scaley))
 
     def rotate180(self):
         with LeptonicaErrorTrap():
-            return Pix(lept.pixRotate180(ffi.NULL, self.cpix))
+            return Pix(lept.pixRotate180(ffi.NULL, self._pix))
+
+    def rotate_orth(self, quads):
+        "Orthographic rotation, quads: 0-3, number of clockwise rotations"
+        with LeptonicaErrorTrap():
+            return Pix(lept.pixRotateOrth(self._pix, quads))
 
     def find_skew(self):
         """Returns a tuple (deskew angle in degrees, confidence value).
@@ -189,27 +253,126 @@ class Pix:
         with LeptonicaErrorTrap():
             angle = ffi.new('float *', 0.0)
             confidence = ffi.new('float *', 0.0)
-            result = lept.pixFindSkew(self.cpix, angle, confidence)
+            result = lept.pixFindSkew(self._pix, angle, confidence)
             if result == 0:
                 return (angle[0], confidence[0])
             else:
                 return (None, None)
 
+    def convert_rgb_to_luminance(self):
+        with LeptonicaErrorTrap():
+            gray_pix = lept.pixConvertRGBToLuminance(self._pix)
+            if gray_pix:
+                return Pix(gray_pix)
+            return None
+
+    def remove_colormap(self, removal_type):
+        """Remove a palette
+
+            removal_type - RemovalColormap()
+        """
+
+        with LeptonicaErrorTrap():
+            return Pix(lept.pixRemoveColormap(self._pix, removal_type))
+
+    def otsu_adaptive_threshold(
+            self, tile_size=(300, 300), kernel_size=(4, 4), scorefract=0.1):
+        with LeptonicaErrorTrap():
+            sx, sy = tile_size
+            smoothx, smoothy = kernel_size
+            p_pix = ffi.new('PIX **')
+
+            result = lept.pixOtsuAdaptiveThreshold(
+                self._pix,
+                sx, sy,
+                smoothx, smoothy,
+                scorefract,
+                ffi.NULL,
+                p_pix)
+            if result == 0:
+                return Pix(p_pix[0])
+            else:
+                return None
+
+    def otsu_threshold_on_background_norm(
+            self, mask=None, tile_size=(10, 15), thresh=100, mincount=50,
+            bgval=255, kernel_size=(2, 2), scorefract=0.1):
+        with LeptonicaErrorTrap():
+            sx, sy = tile_size
+            smoothx, smoothy = kernel_size
+            if mask is None:
+                mask = ffi.NULL
+            if isinstance(mask, Pix):
+                mask = mask._pix
+
+            thresh_pix = lept.pixOtsuThreshOnBackgroundNorm(
+                self._pix,
+                mask,
+                sx, sy,
+                thresh, mincount, bgval,
+                smoothx, smoothy,
+                scorefract,
+                ffi.NULL
+                )
+            if thresh_pix == ffi.NULL:
+                return None
+            return Pix(thresh_pix)
+
+    def crop_to_foreground(
+            self, threshold=128, mindist=70, erasedist=30, pagenum=0,
+            showmorph=0, display=0, pdfdir=ffi.NULL):
+        with LeptonicaErrorTrap():
+            cropbox = Box(lept.pixFindPageForeground(
+                self._pix,
+                threshold,
+                mindist,
+                erasedist,
+                pagenum,
+                showmorph,
+                display,
+                pdfdir))
+
+            print(repr(cropbox))
+
+            cropped_pix = lept.pixClipRectangle(
+                self._pix,
+                cropbox._box,
+                ffi.NULL)
+
+            return Pix(cropped_pix)
+
+    def clean_background_to_white(
+            self, mask=None, grayscale=None, gamma=1.0, black=0, white=255):
+        with LeptonicaErrorTrap():
+            return Pix(lept.pixCleanBackgroundToWhite(
+                self._pix,
+                mask or ffi.NULL,
+                grayscale or ffi.NULL,
+                gamma,
+                black,
+                white))
+
+    @staticmethod
+    @lru_cache(maxsize=1)
+    def make_pixel_sum_tab8():
+        return lept.makePixelSumTab8()
+
     @staticmethod
     def correlation_binary(pix1, pix2):
         if get_leptonica_version() < 'leptonica-1.72':
             # Older versions of Leptonica (pre-1.72) have a buggy
             # implementation of pixCorrelationBinary that overflows on larger
-            # images.
-            pix1_count = ffi.new('l_int32 *', 0)
-            pix2_count = ffi.new('l_int32 *', 0)
-            pixn_count = ffi.new('l_int32 *', 0)
-            tab8 = lept.makePixelSumTab8()  # Small memory leak on each call
+            # images.  Ubuntu trusty has 1.70. Ubuntu PPA
+            # ppa:rebuntu16/avidemux+unofficial has "leptonlib" 1.73.
+            pix1_count = ffi.new('l_int32 *')
+            pix2_count = ffi.new('l_int32 *')
+            pixn_count = ffi.new('l_int32 *')
+            tab8 = Pix.make_pixel_sum_tab8()
 
-            lept.pixCountPixels(pix1.cpix, pix1_count, tab8)
-            lept.pixCountPixels(pix2.cpix, pix2_count, tab8)
-            pixn = Pix(lept.pixAnd(ffi.NULL, pix1.cpix, pix2.cpix))
-            lept.pixCountPixels(pixn.cpix, pixn_count, tab8)
+            lept.pixCountPixels(pix1._pix, pix1_count, tab8)
+            lept.pixCountPixels(pix2._pix, pix2_count, tab8)
+            pixn = Pix(lept.pixAnd(ffi.NULL, pix1._pix, pix2._pix))
+            lept.pixCountPixels(pixn._pix, pixn_count, tab8)
 
             # Python converts these int32s to larger units as needed
             # to avoid overflow. Overflow happens easily here.
@@ -220,7 +383,7 @@ class Pix:
             return correlation
         else:
             correlation = ffi.new('float *', 0.0)
-            result = lept.pixCorrelationBinary(pix1.cpix, pix2.cpix,
+            result = lept.pixCorrelationBinary(pix1._pix, pix2._pix,
                                                correlation)
             if result != 0:
                 raise LeptonicaError("Correlation failed")
@@ -228,11 +391,48 @@ class Pix:
 
     @staticmethod
     def _pix_destroy(pix):
-        ptr_to_pix = ffi.new('PIX **', pix)
-        lept.pixDestroy(ptr_to_pix)
+        p_pix = ffi.new('PIX **', pix)
+        lept.pixDestroy(p_pix)
         # print('pix destroy ' + repr(pix))
 
 
+class Box:
+    """Wrapper around Leptonica's BOX objects.
+
+    See class Pix for notes about reference counting.
+    """
+
+    def __init__(self, box):
+        self._box = ffi.gc(box, Box._box_destroy)
+
+    def __repr__(self):
+        if self._box:
+            return '<leptonica.Box x={0} y={1} w={2} h={3}>'.format(
+                self.x, self.y, self.w, self.h)
+        return '<leptonica.Box NULL>'
+
+    @property
+    def x(self):
+        return self._box.x
+
+    @property
+    def y(self):
+        return self._box.y
+
+    @property
+    def w(self):
+        return self._box.w
+
+    @property
+    def h(self):
+        return self._box.h
+
+    @staticmethod
+    def _box_destroy(box):
+        p_box = ffi.new('BOX **', box)
+        lept.boxDestroy(p_box)
+
+
 @lru_cache(maxsize=1)
 def get_leptonica_version():
     """Get Leptonica version string.

ocrmypdf/lib/compile_leptonica.py

@@ -42,6 +42,18 @@ struct PixColormap
     l_int32          n;         /* number of color entries used            */
 };
 typedef struct PixColormap  PIXCMAP;
+
+struct Box
+{
+    l_int32            x;
+    l_int32            y;
+    l_int32            w;
+    l_int32            h;
+    l_uint32           refcount;      /* reference count (1 if no clones)  */
+
+};
+typedef struct Box    BOX;
+
 """)
 
 ffi.cdef("""
@@ -50,10 +62,17 @@ PIX * pixScale ( PIX *pixs, l_float32 scalex, l_float32 scaley );
 l_int32 pixFindSkew ( PIX *pixs, l_float32 *pangle, l_float32 *pconf );
 l_int32 pixWriteImpliedFormat ( const char *filename, PIX *pix, l_int32 quality, l_int32 progressive );
 void pixDestroy ( PIX **ppix );
+
+PIX *
+pixEndianByteSwapNew(PIX  *pixs);
+
 PIX * pixDeskew ( PIX *pixs, l_int32 redsearch );
 char * getLeptonicaVersion (  );
 l_int32 pixCorrelationBinary(PIX *pix1, PIX *pix2, l_float32 *pval);
 PIX *pixRotate180(PIX *pixd, PIX *pixs);
+PIX *
+pixRotateOrth(PIX     *pixs,
+              l_int32  quads);
 
 l_int32 pixCountPixels ( PIX *pix, l_int32 *pcount, l_int32 *tab8 );
 PIX * pixAnd ( PIX *pixd, PIX *pixs1, PIX *pixs2 );
@@ -62,6 +81,59 @@ l_int32 * makePixelSumTab8 ( void );
 PIX * pixDeserializeFromMemory ( const l_uint32 *data, size_t nbytes );
 l_int32 pixSerializeToMemory ( PIX *pixs, l_uint32 **pdata, size_t *pnbytes );
 
+PIX * pixConvertRGBToLuminance(PIX *pixs);
+
+PIX * pixRemoveColormap(PIX *pixs, l_int32  type);
+
+l_int32
+pixOtsuAdaptiveThreshold(PIX       *pixs,
+                         l_int32    sx,
+                         l_int32    sy,
+                         l_int32    smoothx,
+                         l_int32    smoothy,
+                         l_float32  scorefract,
+                         PIX      **ppixth,
+                         PIX      **ppixd);
+
+PIX *
+pixOtsuThreshOnBackgroundNorm(PIX       *pixs,
+                              PIX       *pixim,
+                              l_int32    sx,
+                              l_int32    sy,
+                              l_int32    thresh,
+                              l_int32    mincount,
+                              l_int32    bgval,
+                              l_int32    smoothx,
+                              l_int32    smoothy,
+                              l_float32  scorefract,
+                              l_int32   *pthresh);
+
+PIX *
+pixCleanBackgroundToWhite(PIX       *pixs,
+                          PIX       *pixim,
+                          PIX       *pixg,
+                          l_float32  gamma,
+                          l_int32    blackval,
+                          l_int32    whiteval);
+
+BOX *
+pixFindPageForeground(PIX         *pixs,
+                      l_int32      threshold,
+                      l_int32      mindist,
+                      l_int32      erasedist,
+                      l_int32      pagenum,
+                      l_int32      showmorph,
+                      l_int32      display,
+                      const char  *pdfdir);
+
+PIX *
+pixClipRectangle(PIX   *pixs,
+                 BOX   *box,
+                 BOX  **pboxc);
+
+void
+boxDestroy(BOX  **pbox);
+
 void lept_free(void *ptr);
 """)
 

ocrmypdf/pageinfo.py

@@ -3,10 +3,13 @@
 
 from subprocess import Popen, PIPE
 from decimal import Decimal, getcontext
+from math import hypot
 import re
 import sys
 import PyPDF2 as pypdf
+from collections import namedtuple
 
+matrix_mult = pypdf.pdf.utils.matrixMultiply
 
 FRIENDLY_COLORSPACE = {
     '/DeviceGray': 'gray',
@@ -19,7 +22,11 @@ FRIENDLY_COLORSPACE = {
     '/Indexed': 'index',
     '/Separation': 'sep',
     '/DeviceN': 'devn',
-    '/Pattern': '-'
+    '/Pattern': '-',
+    '/G': 'gray',  # Abbreviations permitted in inline images
+    '/RGB': 'rgb',
+    '/CMYK': 'cmyk',
+    '/I': 'index',
 }
 
 FRIENDLY_ENCODING = {
@@ -27,6 +34,13 @@ FRIENDLY_ENCODING = {
     '/DCTDecode': 'jpeg',
     '/JPXDecode': 'jpx',
     '/JBIG2Decode': 'jbig2',
+    '/CCF': 'ccitt',  # Abbreviations permitted in inline images
+    '/DCT': 'jpeg',
+    '/AHx': 'asciihex',
+    '/A85': 'ascii85',
+    '/LZW': 'lzw',
+    '/Fl': 'flate',
+    '/RL': 'runlength'
 }
 
 FRIENDLY_COMP = {
@@ -38,50 +52,216 @@ FRIENDLY_COMP = {
 }
 
 
-def _page_has_inline_images(page):
-    # PDF always uses \r\n for separator regardless of platform
-    # Really basic heuristic that might trigger the odd false positive
-    # This is only finds the first image and is not quite spec compliant
-    try:
-        contents = page.getContents()
-        data = contents.getData()
-    except AttributeError:
-        # If we can't access the contents or data (empty page?) then there
-        # are no inline images
-        return False
+def _matrix_from_shorthand(shorthand):
+    """Convert from PDF matrix shorthand to full matrix
 
-    begin_image, image_data, end_image = False, False, False
-    for data in re.split(b'\s+', data):
-        if data == b'BI':
-            begin_image = True
-        elif data == b'ID':
-            image_data = True
-        elif data == b'EI':
-            end_image = True
-        if all((begin_image, image_data, end_image)):
-            return True
-    return False
+    PDF 1.7 spec defines a shorthand for describing the entries of a matrix
+    since the last column is always (0, 0, 1).
+    """
+
+    a, b, c, d, e, f = map(float, shorthand)
+    return ((a, b, 0),
+            (c, d, 0),
+            (e, f, 1))
 
 
-def _find_page_images(page, pageinfo):
+def _shorthand_from_matrix(matrix):
+    """Convert from transformation matrix to PDF shorthand."""
+    a, b = matrix[0][0], matrix[0][1]
+    c, d = matrix[1][0], matrix[1][1]
+    e, f = matrix[2][0], matrix[2][1]
+    return tuple(map(float, (a, b, c, d, e, f)))
+
+RasterSettings = namedtuple('RasterSettings',
+    ['name', 'shorthand', 'stack_depth'])
+
+InlineSettings = namedtuple('InlineSettings',
+    ['settings', 'shorthand', 'stack_depth'])
+
+ContentsInfo = namedtuple('ContentsInfo', ['raster_settings', 'inline_images'])
+
+
+def _interpret_contents(contentstream):
+    """Interpret the PDF content stream
+
+    The stack represents the state of the PDF graphics stack.  We are only
+    interested in the current transformation matrix (CTM) so we only track
+    this object; a full implementation would need to track many other items.
+
+    The CTM is initialized to the mapping from user space to device space.
+    PDF units are 1/72".  In a PDF viewer or printer this matrix is initialized
+    to the transformation to device space.  For example if set to
+    (1/72, 0, 0, 1/72, 0, 0) then all units would be calculated in inches.
+
+    Images are always considered to be (0, 0) -> (1, 1).  Before drawing an
+    image there should be a 'cm' that sets up an image coordinate system
+    where drawing from (0, 0) -> (1, 1) will draw on the desired area of the
+    page.
+
+    PDF units suit our needs so we initialize ctm to the identity matrix.
+
+    PyPDF2 replaces inline images with a fake "INLINE IMAGE" operator.
+
+    """
+
+    operations = contentstream.operations
+    stack = []
+    ctm = _matrix_from_shorthand((1, 0, 0, 1, 0, 0))
+    image_raster_settings = []
+    inline_images = []
+
+    for op in operations:
+        operands, command = op
+        if command == b'q':
+            stack.append(ctm)
+            if len(stack) > 32:
+                raise RuntimeError("PDF graphics stack overflow")
+        elif command == b'Q':
+            ctm = stack.pop()
+        elif command == b'cm':
+            ctm = matrix_mult(
+                _matrix_from_shorthand(operands), ctm)
+        elif command == b'Do':
+            image_name = operands[0]
+            raster = RasterSettings(
+                name=image_name, shorthand=_shorthand_from_matrix(ctm),
+                stack_depth=len(stack))
+            image_raster_settings.append(raster)
+        elif command == b'INLINE IMAGE':
+            settings = operands['settings']
+            inline = InlineSettings(
+                settings=settings, shorthand=_shorthand_from_matrix(ctm),
+                stack_depth=len(stack))
+            inline_images.append(inline)
+
+    return ContentsInfo(
+        raster_settings=image_raster_settings,
+        inline_images=inline_images)
+
+
+def _get_dpi(ctm_shorthand, image_size):
+    """Given the transformation matrix and image size, find the image DPI.
+
+    PDFs do not include image resolution information within image data.
+    Instead, the PDF page content stream describes the location where the
+    image will be rasterized, and the effective resolution is the ratio of the
+    pixel size to raster target size.
+
+    Normally a scanned PDF has the paper size set appropriately but this is
+    not guaranteed. The most common case is a cropped image will change the
+    page size (/CropBox) without altering the page content stream. That means
+    it is not sufficient to assume that the image fills the page, even though
+    that is the most common case.
+
+    A PDF image may be scaled (always), cropped, translated, rotated in place
+    to an arbitrary angle (rarely) and skewed. Only equal area mappings can
+    be expressed, that is, it is not necessary to consider distortions where
+    the effective DPI varies with position.
+
+    To determine the image scale, transform an offset axis vector v0 (0, 0),
+    width-axis vector v0 (1, 0), height-axis vector vh (0, 1) with the matrix,
+    which gives the dimensions of the image in PDF units. From there we can
+    compare to actual image dimensions. PDF uses
+    row vector * matrix_tranposed unlike the traditional
+    matrix * column vector.
+
+    The offset, width and height vectors can be combined in a matrix and
+    multiplied by the transform matrix. Then we want to calculated
+        magnitude(width_vector - offset_vector)
+    and
+        magnitude(height_vector - offset_vector)
+
+    When the above is worked out algebraically, the effect of translation
+    cancels out, and the vector magnitudes become functions of the nonzero
+    transformation matrix indices. The results of the derivation are used
+    in this code.
+
+    pdfimages -list does calculate the DPI in some way that is not completely
+    naive, but it does not get the DPI of rotated images right, so cannot be
+    used anymore to validate this. Photoshop works, or using Acrobat to
+    rotate the image back to normal.
+
+    It does not matter if the image is partially cropped, or even out of the
+    /MediaBox.
+
+    """
+
+    a, b, c, d, _, _ = ctm_shorthand
+
+    # Calculate the width and height of the image in PDF units
+    image_drawn_width = hypot(a, b)
+    image_drawn_height = hypot(c, d)
+
+    # The scale of the image is pixels per PDF unit (1/72")
+    scale_w = image_size[0] / image_drawn_width
+    scale_h = image_size[1] / image_drawn_height
+
+    # DPI = scale * 72
+    dpi_w = scale_w * 72.0
+    dpi_h = scale_h * 72.0
+
+    return (dpi_w, dpi_h)
+
+
+def _find_page_inline_images(page, pageinfo, contentsinfo):
+    "Find inline images on the page"
+
+    for n, inline in enumerate(contentsinfo.inline_images):
+        image = {}
+        image['name'] = str('inline-%02d' % n)
+        image['width'] = inline.settings['/W']
+        image['height'] = inline.settings['/H']
+        if '/BPC' in inline.settings:
+            image['bpc'] = inline.settings['/BPC']
+        else:
+            image['bpc'] = 8
+        image['color'] = FRIENDLY_COLORSPACE.get(inline.settings['/CS'], '-')
+        image['comp'] = FRIENDLY_COMP.get(image['color'], '?')
+        if '/F' in inline.settings:
+            filter_ = inline.settings['/F']
+            if isinstance(filter_, pypdf.generic.ArrayObject):
+                filter_ = filter_[0]
+            image['enc'] = FRIENDLY_ENCODING.get(filter_, 'image')
+        else:
+            image['enc'] = 'image'
+
+        dpi_w, dpi_h = _get_dpi(
+            inline.shorthand, (image['width'], image['height']))
+        image['dpi_w'], image['dpi_h'] = Decimal(dpi_w), Decimal(dpi_h)
+        yield image
+
+
+def _find_page_regular_images(page, pageinfo, contentsinfo):
+    "Find images stored in XObject resources"
+
     try:
         page['/Resources']['/XObject']
     except KeyError:
         return
-
-    # Look for XObject (out of line images)
     for xobj in page['/Resources']['/XObject']:
         # PyPDF2 returns the keys as an iterator
         pdfimage = page['/Resources']['/XObject'][xobj]
         if pdfimage['/Subtype'] != '/Image':
             continue
-        if '/ImageMask' in pdfimage:
-            if pdfimage['/ImageMask']:
-                continue
         image = {}
+        image['name'] = str(xobj)
         image['width'] = pdfimage['/Width']
         image['height'] = pdfimage['/Height']
-        image['bpc'] = pdfimage['/BitsPerComponent']
+        if '/BitsPerComponent' in pdfimage:
+            image['bpc'] = pdfimage['/BitsPerComponent']
+        else:
+            image['bpc'] = 8
+
+        # Fixme: this is incorrectly treats explicit masks as stencil masks,
+        # but good enough for now. Explicit masks have /ImageMask true but are
+        # never called for in content stream, instead are drawn as a /Mask on
+        # other images. For our purposes finding out the details of /Mask
+        # will seldom matter.
+        if '/ImageMask' in pdfimage:
+            image['type'] = 'stencil' if pdfimage['/ImageMask'].value \
+                            else 'image'
+        else:
+            image['type'] = 'image'
         if '/Filter' in pdfimage:
             filter_ = pdfimage['/Filter']
             if isinstance(filter_, pypdf.generic.ArrayObject):
@@ -98,12 +278,48 @@ def _find_page_images(page, pageinfo):
             image['color'] = 'jpx' if image['enc'] == 'jpx' else '?'
 
         image['comp'] = FRIENDLY_COMP.get(image['color'], '?')
-        image['dpi_w'] = image['width'] / pageinfo['width_inches']
-        image['dpi_h'] = image['height'] / pageinfo['height_inches']
+
+        # Bit of a hack... infer grayscale if component count is uncertain
+        # but encoding must be monochrome. This happens if a monochrome image
+        # has an ICC profile attached. Better solution would be to examine
+        # the ICC profile.
+        if image['comp'] == '?' and image['enc'] in ('ccitt', 'jbig2'):
+            image['comp'] = FRIENDLY_COMP['gray']
+
+        image['dpi_w'] = image['dpi_h'] = 0
+
+        for raster in contentsinfo.raster_settings:
+            # Loop in case the same image is display multiple times on a page
+            if raster.name != image['name']:
+                continue
+
+            if raster.stack_depth == 0:
+                # At least one PDF in the wild (and test suite) draws an image
+                # when the graphics stack depth is 0, meaning that the image
+                # gets drawn into a square of 1x1 PDF units (or 1/72",
+                # or 0.35 mm).  The equivalent DPI will be >100,000.  Exclude
+                # these from our DPI calculation for the page.
+                continue
+
+            dpi_w, dpi_h = _get_dpi(
+                raster.shorthand, (image['width'], image['height']))
+
+            # When image is used multiple times take the highest DPI it is
+            # rendered at
+            image['dpi_w'] = max(dpi_w, image.get('dpi_w', 0))
+            image['dpi_h'] = max(dpi_h, image.get('dpi_h', 0))
+
+        image['dpi_w'] = Decimal(image['dpi_w'])
+        image['dpi_h'] = Decimal(image['dpi_h'])
         image['dpi'] = (image['dpi_w'] * image['dpi_h']) ** Decimal(0.5)
         yield image
 
 
+def _find_page_images(page, pageinfo, contentsinfo):
+    yield from _find_page_inline_images(page, pageinfo, contentsinfo)
+    yield from _find_page_regular_images(page, pageinfo, contentsinfo)
+
+
 def _page_has_text(pdf, page):
     # Simple test
     text = page.extractText()
@@ -141,12 +357,14 @@ def _pdf_get_pageinfo(infile, pageno: int):
     pageinfo['width_inches'] = width_pt / Decimal(72.0)
     pageinfo['height_inches'] = height_pt / Decimal(72.0)
 
-    pageinfo['images'] = [im for im in _find_page_images(page, pageinfo)]
+    try:
+        contentstream = pypdf.pdf.ContentStream(page.getContents(), pdf)
+    except AttributeError as e:
+        return pageinfo
 
-    # Look for inline images
-    if _page_has_inline_images(page):
-        raise NotImplementedError(
-            "Warning: input PDF contains inline images - not supported")
+    contentsinfo = _interpret_contents(contentstream)
+    pageinfo['images'] = [im for im in _find_page_images(
+                                page, pageinfo, contentsinfo)]
 
     if pageinfo['images']:
         xres = max(image['dpi_w'] for image in pageinfo['images'])
@@ -164,3 +382,17 @@ def pdf_get_all_pageinfo(infile):
     pdf = pypdf.PdfFileReader(infile)
     getcontext().prec = 6
     return [_pdf_get_pageinfo(infile, n) for n in range(pdf.numPages)]
+
+
+def main():
+    import argparse
+    parser = argparse.ArgumentParser()
+    parser.add_argument('infile')
+    args = parser.parse_args()
+    info = pdf_get_all_pageinfo(args.infile)
+    from pprint import pprint
+    pprint(info)
+
+
+if __name__ == '__main__':
+    main()

ocrmypdf/pdfa.py

@@ -5,10 +5,14 @@
 
 from __future__ import print_function, absolute_import, division
 from string import Template
-from subprocess import Popen, PIPE
-import os
 import codecs
-from . import get_program
+import pkg_resources
+import PyPDF2 as pypdf
+
+ICC_PROFILE_RELPATH = 'data/sRGB.icc'
+
+SRGB_ICC_PROFILE = pkg_resources.resource_filename(
+    'ocrmypdf', ICC_PROFILE_RELPATH)
 
 
 # This is a template written in PostScript which is needed to create PDF/A
@@ -71,8 +75,14 @@ def encode_text_string(s: str) -> str:
     Postscript file to be completely ASCII and no escaping of Postscript
     characters is necessary.
     '''
+
+    # Sometimes lazy C programmer leave their NULs at the end of strings
+    # tests/resources/aspect.pdf is one example (created by ImageMagick)
+    s = s.replace('\x00', '')
+
     if s == '':
         return ''
+
     utf16_bytes = s.encode('utf-16be')
     ascii_hex_bytes = codecs.encode(b'\xfe\xff' + utf16_bytes, 'hex')
     ascii_hex_str = ascii_hex_bytes.decode('ascii').lower()
@@ -85,52 +95,65 @@ def _get_pdfa_def(icc_profile, icc_identifier, pdfmark):
     t = Template(pdfa_def_template)
     result = t.substitute(icc_profile=icc_profile,
                           icc_identifier=icc_identifier,
-                          title=pdfmark_utf16.get('title', ''),
-                          author=pdfmark_utf16.get('author', ''),
-                          subject=pdfmark_utf16.get('subject', ''),
-                          creator=pdfmark_utf16.get('creator', ''),
-                          keywords=pdfmark_utf16.get('keywords', ''))
+                          title=pdfmark_utf16.get('/Title', ''),
+                          author=pdfmark_utf16.get('/Author', ''),
+                          subject=pdfmark_utf16.get('/Subject', ''),
+                          creator=pdfmark_utf16.get('/Creator', ''),
+                          keywords=pdfmark_utf16.get('/Keywords', ''))
     return result
 
 
-def _get_postscript_icc_path():
-    "Parse Ghostscript's help message to find where iccprofiles are stored"
-
-    p_gs = Popen([get_program('gs'), '--help'], close_fds=True,
-                 universal_newlines=True,
-                 stdout=PIPE, stderr=PIPE)
-    out, _ = p_gs.communicate()
-    lines = out.splitlines()
-
-    def search_paths(lines):
-        seeking = True
-        for line in lines:
-            if seeking:
-                if line.startswith('Search path'):
-                    seeking = False
-                    continue
-            else:
-                if line.strip().startswith('/'):
-                    yield from (
-                        path.strip() for path in line.split(':')
-                        if path.strip() != '')
-    for root in search_paths(lines):
-        path = os.path.realpath(os.path.join(root, '../iccprofiles'))
-        if os.path.exists(path):
-            return path
-
-    raise FileNotFoundError("Could not find Ghostscript's iccprofiles")
-
-
 def generate_pdfa_def(target_filename, pdfmark, icc='sRGB'):
     if icc == 'sRGB':
-        icc_profile = os.path.join(_get_postscript_icc_path(), 'srgb.icc')
+        icc_profile = SRGB_ICC_PROFILE
     else:
         raise NotImplementedError("Only supporting sRGB")
 
     ps = _get_pdfa_def(icc_profile, icc, pdfmark)
 
-    # Since PostScript might not handle UTF-8 (it's hard to get a clear
-    # answer), insist on ascii
+    # We should have encoded everything to pure ASCII by this point, and
+    # to be safe, only allow ASCII in PostScript
     with open(target_filename, 'w', encoding='ascii') as f:
         f.write(ps)
+
+
+def file_claims_pdfa(filename):
+    """Determines if the file claims to be PDF/A compliant
+
+    Checking if a file is a truly compliant PDF/A is a massive undertaking
+    that no open source tool does properly.  Some commercial tools are
+    generally reliable (Acrobat).
+
+    This checks if the XMP metadata contains a PDF/A marker.
+    """
+
+    pdf = pypdf.PdfFileReader(filename)
+    xmp = pdf.getXmpMetadata()
+
+    try:
+        pdfa_nodes = xmp.getNodesInNamespace(
+            aboutUri='',
+            namespace='http://www.aiim.org/pdfa/ns/id/')
+    except AttributeError:
+        return {'pass': False, 'output': 'pdf',
+                'conformance': 'No XMP metadata'}
+
+    pdfa_dict = {attr.localName: attr.value for attr in pdfa_nodes}
+    pdfa_dict['pass'] = False
+    pdfa_dict['output'] = 'pdf'
+    if pdfa_dict:
+        part_conformance = pdfa_dict['part'] + pdfa_dict['conformance']
+        valid_part_conforms = {'1A', '1B', '2A', '2B', '2U', '3A', '3B', '3U'}
+
+        conformance = 'PDF/A-{}'.format(
+            part_conformance)
+
+        if part_conformance in valid_part_conforms:
+            pdfa_dict['pass'] = True
+            pdfa_dict['output'] = 'pdfa'
+        pdfa_dict['conformance'] = conformance
+    else:
+        pdfa_dict['conformance'] = 'PDF'
+
+    return pdfa_dict
+

ocrmypdf/qpdf.py

@@ -2,12 +2,32 @@
 # © 2015 James R. Barlow: github.com/jbarlow83
 
 from subprocess import CalledProcessError, check_output, STDOUT, check_call
+from functools import lru_cache
 import sys
 import os
+import re
 
 from . import ExitCode, get_program
 
 
+@lru_cache(maxsize=1)
+def version():
+    args_qpdf = [
+        get_program('qpdf'),
+        '--version'
+    ]
+    try:
+        versions = check_output(
+            args_qpdf, close_fds=True, universal_newlines=True,
+            stderr=STDOUT)
+    except CalledProcessError:
+        print("Could not find qpdf executable on system PATH.")
+        sys.exit(ExitCode.missing_dependency)
+
+    qpdf_version = re.match(r'qpdf version (.+)', versions).group(1)
+    return qpdf_version
+
+
 def check(input_file, log):
     args_qpdf = [
         get_program('qpdf'),
@@ -20,7 +40,7 @@ def check(input_file, log):
     except CalledProcessError as e:
         if e.returncode == 2:
             log.error("{0}: not a valid PDF, and could not repair it.".format(
-                    input_file))
+                input_file))
             log.error("Details:")
             log.error(e.output)
         elif e.returncode == 3:
@@ -85,3 +105,15 @@ def split_pages(input_file, work_folder, npages):
             os.path.join(work_folder, '{0:06d}.page.pdf'.format(n + 1))
         ]
         check_call(args_qpdf)
+
+
+def merge(input_files, output_file):
+    """Merge the list of input files (all filenames) into the output file.
+
+    The input files may contain one or more pages.
+    """
+    args_qpdf = [
+        get_program('qpdf'), input_files[0], '--pages'
+    ] + input_files + ['--', output_file]
+    check_call(args_qpdf)
+

ocrmypdf/tesseract.py

@@ -10,11 +10,7 @@ from . import ExitCode, get_program, page_number
 from collections import namedtuple
 
 from subprocess import Popen, PIPE, CalledProcessError, \
-    TimeoutExpired, check_output, STDOUT
-try:
-    from subprocess import DEVNULL
-except ImportError:
-    DEVNULL = open(os.devnull, 'wb')
+    TimeoutExpired, check_output, STDOUT, DEVNULL
 
 
 OrientationConfidence = namedtuple(
@@ -98,7 +94,8 @@ def get_orientation(input_file, language: list, timeout: float, log):
         return OrientationConfidence(angle=0, confidence=0.0)
     except CalledProcessError as e:
         tesseract_log_output(log, e.output, input_file)
-        if 'Image too large' in e.output:
+        if ('Too few characters. Skipping this page' in e.output or
+                'Image too large' in e.output):
             return OrientationConfidence(0, 0)
         raise e from e
     else:

ocrmypdf/unpaper.py

@@ -3,7 +3,7 @@
 # unpaper documentation:
 # https://github.com/Flameeyes/unpaper/blob/master/doc/basic-concepts.md
 
-from subprocess import Popen, PIPE
+from subprocess import CalledProcessError, STDOUT, check_output, check_call
 from tempfile import NamedTemporaryFile
 import sys
 import os
@@ -17,10 +17,9 @@ def version():
         get_program('unpaper'),
         '--version'
     ]
-    p_unpaper = Popen(args_unpaper, close_fds=True, universal_newlines=True,
-                      stdout=PIPE, stderr=PIPE)
-    version, _ = p_unpaper.communicate(timeout=5)
-
+    version = check_output(
+        args_unpaper, close_fds=True, universal_newlines=True,
+        stderr=STDOUT, timeout=5)
     return version.strip()
 
 
@@ -68,15 +67,17 @@ def run(input_file, output_file, dpi, log, mode_args):
         os.unlink(output_pnm.name)
 
         args_unpaper.extend([input_pnm.name, output_pnm.name])
-        p_unpaper = Popen(
-            args_unpaper, close_fds=True,
-            universal_newlines=True, stdout=PIPE, stderr=PIPE
-            )
-        out, err = p_unpaper.communicate()
-        log.debug(out)
-        log.debug(err)
-
-        Image.open(output_pnm.name).save(output_file)
+        try:
+            stdout = check_output(
+                args_unpaper, close_fds=True,
+                universal_newlines=True, stderr=STDOUT,
+                )
+        except CalledProcessError as e:
+            log.debug(e.output)
+            raise e from e
+        else:
+            log.debug(stdout)
+            Image.open(output_pnm.name).save(output_file)
 
 
 def deskew(input_file, output_file, dpi, log):

pipeline.svg

@@ -4,294 +4,335 @@
 <!-- Generated by graphviz version 2.38.0 (20140413.2041)
  -->
 <!-- Title: Pipeline: Pages: 1 -->
-<svg width="1452pt" height="824pt"
- viewBox="0.00 0.00 1452.00 824.08" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink">
-<g id="graph0" class="graph" transform="scale(1 1) rotate(0) translate(4 820.083)">
+<svg width="1444pt" height="973pt"
+ viewBox="0.00 0.00 1444.00 973.18" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink">
+<g id="graph0" class="graph" transform="scale(1 1) rotate(0) translate(4 969.181)">
 <title>Pipeline:</title>
-<polygon fill="white" stroke="none" points="-4,4 -4,-820.083 1448,-820.083 1448,4 -4,4"/>
+<polygon fill="white" stroke="none" points="-4,4 -4,-969.181 1440,-969.181 1440,4 -4,4"/>
 <g id="clust1" class="cluster"><title>clustertasks</title>
-<polygon fill="none" stroke="black" points="8,-8 8,-808.083 1436,-808.083 1436,-8 8,-8"/>
-<text text-anchor="middle" x="722" y="-780.083" font-family="Times,serif" font-size="30.00" fill="#ff3232">Pipeline:</text>
+<polygon fill="none" stroke="black" points="8,-8 8,-957.181 1428,-957.181 1428,-8 8,-8"/>
+<text text-anchor="middle" x="718" y="-929.181" font-family="Times,serif" font-size="30.00" fill="#ff3232">Pipeline:</text>
 </g>
 <!-- t0 -->
 <g id="node1" class="node"><title>t0</title>
-<polygon fill="#efa03b" stroke="black" points="1256.54,-762.083 1033.46,-762.083 1029.46,-758.083 1029.46,-726.083 1252.54,-726.083 1256.54,-730.083 1256.54,-762.083"/>
-<polyline fill="none" stroke="black" points="1252.54,-758.083 1029.46,-758.083 "/>
-<polyline fill="none" stroke="black" points="1252.54,-758.083 1252.54,-726.083 "/>
-<polyline fill="none" stroke="black" points="1252.54,-758.083 1256.54,-762.083 "/>
-<text text-anchor="middle" x="1143" y="-738.083" font-family="Times,serif" font-size="20.00">repair_pdf</text>
+<polygon fill="#efa03b" stroke="black" points="1219.77,-911.181 1034.23,-911.181 1030.23,-907.181 1030.23,-875.181 1215.77,-875.181 1219.77,-879.181 1219.77,-911.181"/>
+<polyline fill="none" stroke="black" points="1215.77,-907.181 1030.23,-907.181 "/>
+<polyline fill="none" stroke="black" points="1215.77,-907.181 1215.77,-875.181 "/>
+<polyline fill="none" stroke="black" points="1215.77,-907.181 1219.77,-911.181 "/>
+<text text-anchor="middle" x="1125" y="-887.181" font-family="Times,serif" font-size="20.00">triage</text>
 </g>
 <!-- t1 -->
 <g id="node2" class="node"><title>t1</title>
-<polygon fill="#efa03b" stroke="black" points="1234.11,-683.155 1030,-700.057 825.888,-683.155 826.078,-655.806 1233.92,-655.806 1234.11,-683.155"/>
-<polygon fill="none" stroke="black" points="1238.13,-686.834 1030,-704.069 821.866,-686.834 822.11,-651.808 1237.89,-651.808 1238.13,-686.834"/>
-<text text-anchor="middle" x="1030" y="-669.596" font-family="Times,serif" font-size="20.00">split_pages</text>
+<polygon fill="#efa03b" stroke="black" points="1238.54,-853.181 1015.46,-853.181 1011.46,-849.181 1011.46,-817.181 1234.54,-817.181 1238.54,-821.181 1238.54,-853.181"/>
+<polyline fill="none" stroke="black" points="1234.54,-849.181 1011.46,-849.181 "/>
+<polyline fill="none" stroke="black" points="1234.54,-849.181 1234.54,-817.181 "/>
+<polyline fill="none" stroke="black" points="1234.54,-849.181 1238.54,-853.181 "/>
+<text text-anchor="middle" x="1125" y="-829.181" font-family="Times,serif" font-size="20.00">repair_pdf</text>
 </g>
 <!-- t0&#45;&gt;t1 -->
 <g id="edge1" class="edge"><title>t0&#45;&gt;t1</title>
-<path fill="none" stroke="#0044a0" d="M1113.9,-725.961C1103.58,-719.89 1091.66,-712.873 1080.09,-706.069"/>
-<polygon fill="#0044a0" stroke="#0044a0" points="1081.75,-702.982 1071.35,-700.927 1078.2,-709.015 1081.75,-702.982"/>
-</g>
-<!-- t14 -->
-<g id="node16" class="node"><title>t14</title>
-<polygon fill="#efa03b" stroke="black" points="1428.08,-625.109 1089.92,-625.109 1085.92,-621.109 1085.92,-589.109 1424.08,-589.109 1428.08,-593.109 1428.08,-625.109"/>
-<polyline fill="none" stroke="black" points="1424.08,-621.109 1085.92,-621.109 "/>
-<polyline fill="none" stroke="black" points="1424.08,-621.109 1424.08,-589.109 "/>
-<polyline fill="none" stroke="black" points="1424.08,-621.109 1428.08,-625.109 "/>
-<text text-anchor="middle" x="1257" y="-601.109" font-family="Times,serif" font-size="20.00">generate_postscript_stub</text>
-</g>
-<!-- t0&#45;&gt;t14 -->
-<g id="edge22" class="edge"><title>t0&#45;&gt;t14</title>
-<path fill="none" stroke="#0044a0" d="M1219.32,-726.004C1229.98,-720.592 1239.75,-713.466 1247,-704.083 1261.92,-684.78 1263.1,-656.385 1261.35,-635.486"/>
-<polygon fill="#0044a0" stroke="#0044a0" points="1264.8,-634.881 1260.22,-625.328 1257.84,-635.653 1264.8,-634.881"/>
+<path fill="none" stroke="#0044a0" d="M1125,-875.075C1125,-871.384 1125,-867.394 1125,-863.424"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="1128.5,-863.182 1125,-853.182 1121.5,-863.182 1128.5,-863.182"/>
 </g>
 <!-- t2 -->
 <g id="node3" class="node"><title>t2</title>
-<polygon fill="#efa03b" stroke="black" points="1029.88,-625.109 748.117,-625.109 744.117,-621.109 744.117,-589.109 1025.88,-589.109 1029.88,-593.109 1029.88,-625.109"/>
-<polyline fill="none" stroke="black" points="1025.88,-621.109 744.117,-621.109 "/>
-<polyline fill="none" stroke="black" points="1025.88,-621.109 1025.88,-589.109 "/>
-<polyline fill="none" stroke="black" points="1025.88,-621.109 1029.88,-625.109 "/>
-<text text-anchor="middle" x="887" y="-601.109" font-family="Times,serif" font-size="20.00">rasterize_preview</text>
+<polygon fill="#efa03b" stroke="black" points="1329.11,-774.253 1125,-791.156 920.888,-774.253 921.078,-746.905 1328.92,-746.905 1329.11,-774.253"/>
+<polygon fill="none" stroke="black" points="1333.13,-777.932 1125,-795.167 916.866,-777.932 917.11,-742.906 1332.89,-742.906 1333.13,-777.932"/>
+<text text-anchor="middle" x="1125" y="-760.694" font-family="Times,serif" font-size="20.00">split_pages</text>
 </g>
 <!-- t1&#45;&gt;t2 -->
 <g id="edge2" class="edge"><title>t1&#45;&gt;t2</title>
-<path fill="none" stroke="#0044a0" d="M980.788,-651.715C965.266,-644.498 948.187,-636.558 932.905,-629.452"/>
-<polygon fill="#0044a0" stroke="#0044a0" points="934.195,-626.193 923.652,-625.15 931.244,-632.54 934.195,-626.193"/>
+<path fill="none" stroke="#0044a0" d="M1125,-817.059C1125,-813.44 1125,-809.484 1125,-805.438"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="1128.5,-805.334 1125,-795.334 1121.5,-805.334 1128.5,-805.334"/>
+</g>
+<!-- t15 -->
+<g id="node17" class="node"><title>t15</title>
+<polygon fill="#efa03b" stroke="black" points="632.082,-716.208 293.918,-716.208 289.918,-712.208 289.918,-680.208 628.082,-680.208 632.082,-684.208 632.082,-716.208"/>
+<polyline fill="none" stroke="black" points="628.082,-712.208 289.918,-712.208 "/>
+<polyline fill="none" stroke="black" points="628.082,-712.208 628.082,-680.208 "/>
+<polyline fill="none" stroke="black" points="628.082,-712.208 632.082,-716.208 "/>
+<text text-anchor="middle" x="461" y="-692.208" font-family="Times,serif" font-size="20.00">generate_postscript_stub</text>
+</g>
+<!-- t1&#45;&gt;t15 -->
+<g id="edge23" class="edge"><title>t1&#45;&gt;t15</title>
+<path fill="none" stroke="#0044a0" d="M1026.3,-817.165C989.157,-810.572 946.587,-802.788 908,-795.181 781.899,-770.319 636.479,-738.51 546.633,-718.49"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="547.289,-715.05 536.767,-716.289 545.765,-721.882 547.289,-715.05"/>
+</g>
+<!-- t18 -->
+<g id="node19" class="node"><title>t18</title>
+<polygon fill="#efa03b" stroke="black" points="1025.79,-156.452 1221,-129.134 1416.21,-156.452 1416.03,-200.654 1025.97,-200.654 1025.79,-156.452"/>
+<polygon fill="none" stroke="black" points="1021.78,-152.971 1221,-125.091 1420.22,-152.971 1420.01,-204.657 1021.99,-204.657 1021.78,-152.971"/>
+<text text-anchor="middle" x="1221" y="-162.669" font-family="Times,serif" font-size="20.00">merge_pages_qpdf</text>
+</g>
+<!-- t1&#45;&gt;t18 -->
+<g id="edge33" class="edge"><title>t1&#45;&gt;t18</title>
+<path fill="none" stroke="#0044a0" d="M1238.67,-826.639C1321.4,-814.236 1419,-782.049 1419,-699.208 1419,-699.208 1419,-699.208 1419,-319.208 1419,-280.294 1424,-263.161 1398,-234.208 1389.64,-224.894 1379.82,-216.923 1369.17,-210.101"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="1370.83,-207.019 1360.46,-204.872 1367.23,-213.02 1370.83,-207.019"/>
 </g>
 <!-- t3 -->
 <g id="node4" class="node"><title>t3</title>
-<polygon fill="#efa03b" stroke="black" points="1128.15,-567.109 893.852,-567.109 889.852,-563.109 889.852,-531.109 1124.15,-531.109 1128.15,-535.109 1128.15,-567.109"/>
-<polyline fill="none" stroke="black" points="1124.15,-563.109 889.852,-563.109 "/>
-<polyline fill="none" stroke="black" points="1124.15,-563.109 1124.15,-531.109 "/>
-<polyline fill="none" stroke="black" points="1124.15,-563.109 1128.15,-567.109 "/>
-<text text-anchor="middle" x="1009" y="-543.109" font-family="Times,serif" font-size="20.00">orient_page</text>
-</g>
-<!-- t1&#45;&gt;t3 -->
-<g id="edge4" class="edge"><title>t1&#45;&gt;t3</title>
-<path fill="none" stroke="#0044a0" d="M1037.63,-651.508C1042.21,-633.96 1045.92,-609.455 1039,-589.109 1037.4,-584.404 1034.98,-579.822 1032.19,-575.552"/>
-<polygon fill="#0044a0" stroke="#0044a0" points="1034.85,-573.258 1026.1,-567.282 1029.21,-577.409 1034.85,-573.258"/>
+<polygon fill="#efa03b" stroke="black" points="1186.88,-716.208 905.117,-716.208 901.117,-712.208 901.117,-680.208 1182.88,-680.208 1186.88,-684.208 1186.88,-716.208"/>
+<polyline fill="none" stroke="black" points="1182.88,-712.208 901.117,-712.208 "/>
+<polyline fill="none" stroke="black" points="1182.88,-712.208 1182.88,-680.208 "/>
+<polyline fill="none" stroke="black" points="1182.88,-712.208 1186.88,-716.208 "/>
+<text text-anchor="middle" x="1044" y="-692.208" font-family="Times,serif" font-size="20.00">rasterize_preview</text>
 </g>
 <!-- t2&#45;&gt;t3 -->
 <g id="edge3" class="edge"><title>t2&#45;&gt;t3</title>
-<path fill="none" stroke="#0044a0" d="M924.267,-589.003C936.328,-583.467 949.857,-577.257 962.502,-571.453"/>
-<polygon fill="#0044a0" stroke="#0044a0" points="964.333,-574.463 971.961,-567.111 961.413,-568.102 964.333,-574.463"/>
+<path fill="none" stroke="#0044a0" d="M1097.12,-742.813C1089.24,-736.345 1080.66,-729.296 1072.73,-722.788"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="1074.71,-719.888 1064.76,-716.249 1070.27,-725.299 1074.71,-719.888"/>
 </g>
 <!-- t4 -->
 <g id="node5" class="node"><title>t4</title>
-<polygon fill="#efa03b" stroke="black" points="1027.3,-509.109 676.701,-509.109 672.701,-505.109 672.701,-473.109 1023.3,-473.109 1027.3,-477.109 1027.3,-509.109"/>
-<polyline fill="none" stroke="black" points="1023.3,-505.109 672.701,-505.109 "/>
-<polyline fill="none" stroke="black" points="1023.3,-505.109 1023.3,-473.109 "/>
-<polyline fill="none" stroke="black" points="1023.3,-505.109 1027.3,-509.109 "/>
-<text text-anchor="middle" x="850" y="-485.109" font-family="Times,serif" font-size="20.00">rasterize_with_ghostscript</text>
+<polygon fill="#efa03b" stroke="black" points="1258.15,-658.208 1023.85,-658.208 1019.85,-654.208 1019.85,-622.208 1254.15,-622.208 1258.15,-626.208 1258.15,-658.208"/>
+<polyline fill="none" stroke="black" points="1254.15,-654.208 1019.85,-654.208 "/>
+<polyline fill="none" stroke="black" points="1254.15,-654.208 1254.15,-622.208 "/>
+<polyline fill="none" stroke="black" points="1254.15,-654.208 1258.15,-658.208 "/>
+<text text-anchor="middle" x="1139" y="-634.208" font-family="Times,serif" font-size="20.00">orient_page</text>
+</g>
+<!-- t2&#45;&gt;t4 -->
+<g id="edge5" class="edge"><title>t2&#45;&gt;t4</title>
+<path fill="none" stroke="#0044a0" d="M1171.65,-742.795C1181.42,-735.692 1190.44,-726.864 1196,-716.208 1203.4,-702.023 1203.46,-694.36 1196,-680.208 1192.84,-674.222 1188.31,-668.98 1183.15,-664.445"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="1185.3,-661.676 1175.25,-658.302 1181,-667.203 1185.3,-661.676"/>
 </g>
 <!-- t3&#45;&gt;t4 -->
-<g id="edge5" class="edge"><title>t3&#45;&gt;t4</title>
-<path fill="none" stroke="#0044a0" d="M960.431,-531.003C943.787,-525.141 924.999,-518.524 907.704,-512.433"/>
-<polygon fill="#0044a0" stroke="#0044a0" points="908.867,-509.132 898.272,-509.111 906.541,-515.734 908.867,-509.132"/>
-</g>
-<!-- t9 -->
-<g id="node11" class="node"><title>t9</title>
-<polygon fill="#efa03b" stroke="black" points="314.109,-277.109 19.8906,-277.109 15.8906,-273.109 15.8906,-241.109 310.109,-241.109 314.109,-245.109 314.109,-277.109"/>
-<polyline fill="none" stroke="black" points="310.109,-273.109 15.8906,-273.109 "/>
-<polyline fill="none" stroke="black" points="310.109,-273.109 310.109,-241.109 "/>
-<polyline fill="none" stroke="black" points="310.109,-273.109 314.109,-277.109 "/>
-<text text-anchor="middle" x="165" y="-253.109" font-family="Times,serif" font-size="20.00">select_image_layer</text>
-</g>
-<!-- t3&#45;&gt;t9 -->
-<g id="edge14" class="edge"><title>t3&#45;&gt;t9</title>
-<path fill="none" stroke="#0044a0" d="M889.675,-542.297C675.505,-530.255 248,-498.192 248,-434.109 248,-434.109 248,-434.109 248,-374.109 248,-337.597 219.83,-304.936 196.312,-284.031"/>
-<polygon fill="#0044a0" stroke="#0044a0" points="198.437,-281.243 188.562,-277.404 193.888,-286.563 198.437,-281.243"/>
-</g>
-<!-- t15 -->
-<g id="node14" class="node"><title>t15</title>
-<polygon fill="#efa03b" stroke="black" points="1391.34,-451.109 1170.66,-451.109 1166.66,-447.109 1166.66,-415.109 1387.34,-415.109 1391.34,-419.109 1391.34,-451.109"/>
-<polyline fill="none" stroke="black" points="1387.34,-447.109 1166.66,-447.109 "/>
-<polyline fill="none" stroke="black" points="1387.34,-447.109 1387.34,-415.109 "/>
-<polyline fill="none" stroke="black" points="1387.34,-447.109 1391.34,-451.109 "/>
-<text text-anchor="middle" x="1279" y="-427.109" font-family="Times,serif" font-size="20.00">skip_page</text>
-</g>
-<!-- t3&#45;&gt;t15 -->
-<g id="edge19" class="edge"><title>t3&#45;&gt;t15</title>
-<path fill="none" stroke="#0044a0" d="M1060.32,-531.078C1078.95,-524.591 1100.07,-516.881 1119,-509.109 1159.3,-492.568 1204.11,-471.304 1236.04,-455.645"/>
-<polygon fill="#0044a0" stroke="#0044a0" points="1237.67,-458.74 1245.1,-451.181 1234.58,-452.461 1237.67,-458.74"/>
-</g>
-<!-- t13 -->
-<g id="node15" class="node"><title>t13</title>
-<polygon fill="#efa03b" stroke="black" points="1388.24,-277.109 1007.76,-277.109 1003.76,-273.109 1003.76,-241.109 1384.24,-241.109 1388.24,-245.109 1388.24,-277.109"/>
-<polyline fill="none" stroke="black" points="1384.24,-273.109 1003.76,-273.109 "/>
-<polyline fill="none" stroke="black" points="1384.24,-273.109 1384.24,-241.109 "/>
-<polyline fill="none" stroke="black" points="1384.24,-273.109 1388.24,-277.109 "/>
-<text text-anchor="middle" x="1196" y="-253.109" font-family="Times,serif" font-size="20.00">tesseract_ocr_and_render_pdf</text>
-</g>
-<!-- t3&#45;&gt;t13 -->
-<g id="edge21" class="edge"><title>t3&#45;&gt;t13</title>
-<path fill="none" stroke="#0044a0" d="M1040.79,-531.094C1071.69,-511.983 1114,-477.834 1114,-434.109 1114,-434.109 1114,-434.109 1114,-374.109 1114,-337.749 1141.83,-305.063 1165.07,-284.11"/>
-<polygon fill="#0044a0" stroke="#0044a0" points="1167.46,-286.664 1172.72,-277.466 1162.87,-281.377 1167.46,-286.664"/>
+<g id="edge4" class="edge"><title>t3&#45;&gt;t4</title>
+<path fill="none" stroke="#0044a0" d="M1073.02,-680.102C1081.95,-674.836 1091.92,-668.963 1101.34,-663.407"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="1103.32,-666.302 1110.16,-658.209 1099.77,-660.272 1103.32,-666.302"/>
 </g>
 <!-- t5 -->
 <g id="node6" class="node"><title>t5</title>
-<polygon fill="#efa03b" stroke="black" points="830.742,-451.109 535.258,-451.109 531.258,-447.109 531.258,-415.109 826.742,-415.109 830.742,-419.109 830.742,-451.109"/>
-<polyline fill="none" stroke="black" points="826.742,-447.109 531.258,-447.109 "/>
-<polyline fill="none" stroke="black" points="826.742,-447.109 826.742,-415.109 "/>
-<polyline fill="none" stroke="black" points="826.742,-447.109 830.742,-451.109 "/>
-<text text-anchor="middle" x="681" y="-427.109" font-family="Times,serif" font-size="20.00">preprocess_deskew</text>
+<polygon fill="#efa03b" stroke="black" points="1271.3,-600.208 920.701,-600.208 916.701,-596.208 916.701,-564.208 1267.3,-564.208 1271.3,-568.208 1271.3,-600.208"/>
+<polyline fill="none" stroke="black" points="1267.3,-596.208 916.701,-596.208 "/>
+<polyline fill="none" stroke="black" points="1267.3,-596.208 1267.3,-564.208 "/>
+<polyline fill="none" stroke="black" points="1267.3,-596.208 1271.3,-600.208 "/>
+<text text-anchor="middle" x="1094" y="-576.208" font-family="Times,serif" font-size="20.00">rasterize_with_ghostscript</text>
 </g>
 <!-- t4&#45;&gt;t5 -->
 <g id="edge6" class="edge"><title>t4&#45;&gt;t5</title>
-<path fill="none" stroke="#0044a0" d="M798.376,-473.003C780.521,-467.087 760.346,-460.402 741.823,-454.264"/>
-<polygon fill="#0044a0" stroke="#0044a0" points="742.901,-450.934 732.308,-451.111 740.699,-457.579 742.901,-450.934"/>
+<path fill="none" stroke="#0044a0" d="M1125.25,-622.102C1121.76,-617.759 1117.94,-613.003 1114.21,-608.353"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="1116.65,-605.812 1107.66,-600.209 1111.2,-610.197 1116.65,-605.812"/>
 </g>
-<!-- t8 -->
-<g id="node10" class="node"><title>t8</title>
-<polygon fill="#efa03b" stroke="black" points="980.119,-335.109 665.881,-335.109 661.881,-331.109 661.881,-299.109 976.119,-299.109 980.119,-303.109 980.119,-335.109"/>
-<polyline fill="none" stroke="black" points="976.119,-331.109 661.881,-331.109 "/>
-<polyline fill="none" stroke="black" points="976.119,-331.109 976.119,-299.109 "/>
-<polyline fill="none" stroke="black" points="976.119,-331.109 980.119,-335.109 "/>
-<text text-anchor="middle" x="821" y="-311.109" font-family="Times,serif" font-size="20.00">select_image_for_pdf</text>
+<!-- t10 -->
+<g id="node12" class="node"><title>t10</title>
+<polygon fill="#00cc66" stroke="black" points="334,-348.208 35.7812,-320.208 334,-292.208 632.219,-320.208 334,-348.208"/>
+<text text-anchor="middle" x="334" y="-314.208" font-family="Times,serif" font-size="20.00">select_image_layer</text>
 </g>
-<!-- t4&#45;&gt;t8 -->
-<g id="edge12" class="edge"><title>t4&#45;&gt;t8</title>
-<path fill="none" stroke="#0044a0" d="M848.03,-473.087C846.196,-457.857 843.261,-434.941 840,-415.109 836.1,-391.393 830.78,-364.592 826.761,-345.181"/>
-<polygon fill="#0044a0" stroke="#0044a0" points="830.152,-344.296 824.68,-335.224 823.3,-345.728 830.152,-344.296"/>
+<!-- t4&#45;&gt;t10 -->
+<g id="edge15" class="edge"><title>t4&#45;&gt;t10</title>
+<path fill="none" stroke="#0044a0" d="M1019.87,-634.085C799.18,-622.991 349,-592.156 349,-525.208 349,-525.208 349,-525.208 349,-465.208 349,-428.606 344.147,-387.052 339.961,-358.022"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="343.393,-357.303 338.46,-347.926 336.469,-358.332 343.393,-357.303"/>
+</g>
+<!-- t16 -->
+<g id="node15" class="node"><title>t16</title>
+<polygon fill="#efa03b" stroke="black" points="1380.34,-270.208 1159.66,-270.208 1155.66,-266.208 1155.66,-234.208 1376.34,-234.208 1380.34,-238.208 1380.34,-270.208"/>
+<polyline fill="none" stroke="black" points="1376.34,-266.208 1155.66,-266.208 "/>
+<polyline fill="none" stroke="black" points="1376.34,-266.208 1376.34,-234.208 "/>
+<polyline fill="none" stroke="black" points="1376.34,-266.208 1380.34,-270.208 "/>
+<text text-anchor="middle" x="1268" y="-246.208" font-family="Times,serif" font-size="20.00">skip_page</text>
+</g>
+<!-- t4&#45;&gt;t16 -->
+<g id="edge20" class="edge"><title>t4&#45;&gt;t16</title>
+<path fill="none" stroke="#0044a0" d="M1258.35,-631.473C1326.7,-619.809 1399,-591.745 1399,-525.208 1399,-525.208 1399,-525.208 1399,-397.208 1399,-350.33 1418.37,-328.748 1389,-292.208 1383.58,-285.469 1376.99,-279.879 1369.71,-275.244"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="1371.3,-272.123 1360.88,-270.231 1367.85,-278.211 1371.3,-272.123"/>
+</g>
+<!-- t14 -->
+<g id="node16" class="node"><title>t14</title>
+<polygon fill="#66ccff" stroke="black" points="1380.24,-338.208 999.76,-338.208 995.76,-334.208 995.76,-302.208 1376.24,-302.208 1380.24,-306.208 1380.24,-338.208"/>
+<polyline fill="none" stroke="black" points="1376.24,-334.208 995.76,-334.208 "/>
+<polyline fill="none" stroke="black" points="1376.24,-334.208 1376.24,-302.208 "/>
+<polyline fill="none" stroke="black" points="1376.24,-334.208 1380.24,-338.208 "/>
+<text text-anchor="middle" x="1188" y="-314.208" font-family="Times,serif" font-size="20.00">tesseract_ocr_and_render_pdf</text>
+</g>
+<!-- t4&#45;&gt;t14 -->
+<g id="edge22" class="edge"><title>t4&#45;&gt;t14</title>
+<path fill="none" stroke="#0044a0" d="M1244.5,-622.179C1297.25,-607.003 1350,-578.503 1350,-525.208 1350,-525.208 1350,-525.208 1350,-465.208 1350,-422.752 1366.76,-403.169 1340,-370.208 1330.4,-358.377 1317.91,-349.368 1304.22,-342.513"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="1305.62,-339.304 1295.07,-338.313 1302.7,-345.666 1305.62,-339.304"/>
 </g>
 <!-- t6 -->
 <g id="node7" class="node"><title>t6</title>
-<polygon fill="#efa03b" stroke="black" points="801.95,-393.109 524.05,-393.109 520.05,-389.109 520.05,-357.109 797.95,-357.109 801.95,-361.109 801.95,-393.109"/>
-<polyline fill="none" stroke="black" points="797.95,-389.109 520.05,-389.109 "/>
-<polyline fill="none" stroke="black" points="797.95,-389.109 797.95,-357.109 "/>
-<polyline fill="none" stroke="black" points="797.95,-389.109 801.95,-393.109 "/>
-<text text-anchor="middle" x="661" y="-369.109" font-family="Times,serif" font-size="20.00">preprocess_clean</text>
+<polygon fill="#efa03b" stroke="black" points="1074.74,-542.208 779.258,-542.208 775.258,-538.208 775.258,-506.208 1070.74,-506.208 1074.74,-510.208 1074.74,-542.208"/>
+<polyline fill="none" stroke="black" points="1070.74,-538.208 775.258,-538.208 "/>
+<polyline fill="none" stroke="black" points="1070.74,-538.208 1070.74,-506.208 "/>
+<polyline fill="none" stroke="black" points="1070.74,-538.208 1074.74,-542.208 "/>
+<text text-anchor="middle" x="925" y="-518.208" font-family="Times,serif" font-size="20.00">preprocess_deskew</text>
 </g>
 <!-- t5&#45;&gt;t6 -->
 <g id="edge7" class="edge"><title>t5&#45;&gt;t6</title>
-<path fill="none" stroke="#0044a0" d="M674.891,-415.003C673.495,-411.095 671.979,-406.852 670.48,-402.652"/>
-<polygon fill="#0044a0" stroke="#0044a0" points="673.731,-401.351 667.072,-393.111 667.139,-403.705 673.731,-401.351"/>
+<path fill="none" stroke="#0044a0" d="M1042.38,-564.102C1024.52,-558.185 1004.35,-551.5 985.823,-545.362"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="986.901,-542.032 976.308,-542.209 984.699,-548.677 986.901,-542.032"/>
 </g>
-<!-- t5&#45;&gt;t8 -->
-<g id="edge11" class="edge"><title>t5&#45;&gt;t8</title>
-<path fill="none" stroke="#0044a0" d="M781.944,-415.046C792.967,-409.579 803.051,-402.434 811,-393.109 822.009,-380.195 824.454,-361.215 824.174,-345.581"/>
-<polygon fill="#0044a0" stroke="#0044a0" points="827.659,-345.2 823.617,-335.407 820.669,-345.583 827.659,-345.2"/>
+<!-- t9 -->
+<g id="node11" class="node"><title>t9</title>
+<polygon fill="#efa03b" stroke="black" points="1013,-426.208 694.762,-398.208 1013,-370.208 1331.24,-398.208 1013,-426.208"/>
+<text text-anchor="middle" x="1013" y="-392.208" font-family="Times,serif" font-size="20.00">select_image_for_pdf</text>
+</g>
+<!-- t5&#45;&gt;t9 -->
+<g id="edge13" class="edge"><title>t5&#45;&gt;t9</title>
+<path fill="none" stroke="#0044a0" d="M1093.89,-563.996C1093.29,-548.44 1091.11,-525.146 1084,-506.208 1073.94,-479.426 1056.13,-452.609 1040.86,-432.521"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="1043.62,-430.369 1034.72,-424.619 1038.09,-434.663 1043.62,-430.369"/>
 </g>
 <!-- t7 -->
 <g id="node8" class="node"><title>t7</title>
-<polygon fill="#efa03b" stroke="black" points="643.666,-335.109 354.334,-335.109 350.334,-331.109 350.334,-299.109 639.666,-299.109 643.666,-303.109 643.666,-335.109"/>
-<polyline fill="none" stroke="black" points="639.666,-331.109 350.334,-331.109 "/>
-<polyline fill="none" stroke="black" points="639.666,-331.109 639.666,-299.109 "/>
-<polyline fill="none" stroke="black" points="639.666,-331.109 643.666,-335.109 "/>
-<text text-anchor="middle" x="497" y="-311.109" font-family="Times,serif" font-size="20.00">ocr_tesseract_hocr</text>
+<polygon fill="#efa03b" stroke="black" points="993.95,-484.208 716.05,-484.208 712.05,-480.208 712.05,-448.208 989.95,-448.208 993.95,-452.208 993.95,-484.208"/>
+<polyline fill="none" stroke="black" points="989.95,-480.208 712.05,-480.208 "/>
+<polyline fill="none" stroke="black" points="989.95,-480.208 989.95,-448.208 "/>
+<polyline fill="none" stroke="black" points="989.95,-480.208 993.95,-484.208 "/>
+<text text-anchor="middle" x="853" y="-460.208" font-family="Times,serif" font-size="20.00">preprocess_clean</text>
 </g>
 <!-- t6&#45;&gt;t7 -->
 <g id="edge8" class="edge"><title>t6&#45;&gt;t7</title>
-<path fill="none" stroke="#0044a0" d="M610.903,-357.003C593.736,-351.141 574.358,-344.524 556.518,-338.433"/>
-<polygon fill="#0044a0" stroke="#0044a0" points="557.384,-335.03 546.79,-335.111 555.122,-341.654 557.384,-335.03"/>
+<path fill="none" stroke="#0044a0" d="M903.006,-506.102C896.726,-501.216 889.771,-495.807 883.095,-490.615"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="884.901,-487.586 874.859,-484.209 880.604,-493.111 884.901,-487.586"/>
 </g>
-<!-- t6&#45;&gt;t8 -->
-<g id="edge10" class="edge"><title>t6&#45;&gt;t8</title>
-<path fill="none" stroke="#0044a0" d="M709.875,-357.003C726.624,-351.141 745.529,-344.524 762.933,-338.433"/>
-<polygon fill="#0044a0" stroke="#0044a0" points="764.142,-341.718 772.425,-335.111 761.83,-335.111 764.142,-341.718"/>
+<!-- t6&#45;&gt;t9 -->
+<g id="edge12" class="edge"><title>t6&#45;&gt;t9</title>
+<path fill="none" stroke="#0044a0" d="M977.454,-506.003C987.329,-500.504 996.562,-493.377 1003,-484.208 1012.67,-470.441 1015.74,-452.229 1016.16,-436.195"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="1019.66,-436.018 1016.09,-426.041 1012.66,-436.063 1019.66,-436.018"/>
 </g>
-<!-- t10 -->
-<g id="node9" class="node"><title>t10</title>
-<polygon fill="#efa03b" stroke="black" points="620.109,-277.109 335.891,-277.109 331.891,-273.109 331.891,-241.109 616.109,-241.109 620.109,-245.109 620.109,-277.109"/>
-<polyline fill="none" stroke="black" points="616.109,-273.109 331.891,-273.109 "/>
-<polyline fill="none" stroke="black" points="616.109,-273.109 616.109,-241.109 "/>
-<polyline fill="none" stroke="black" points="616.109,-273.109 620.109,-277.109 "/>
-<text text-anchor="middle" x="476" y="-253.109" font-family="Times,serif" font-size="20.00">render_hocr_page</text>
+<!-- t8 -->
+<g id="node9" class="node"><title>t8</title>
+<polygon fill="#00cc66" stroke="black" points="676.666,-416.208 387.334,-416.208 383.334,-412.208 383.334,-380.208 672.666,-380.208 676.666,-384.208 676.666,-416.208"/>
+<polyline fill="none" stroke="black" points="672.666,-412.208 383.334,-412.208 "/>
+<polyline fill="none" stroke="black" points="672.666,-412.208 672.666,-380.208 "/>
+<polyline fill="none" stroke="black" points="672.666,-412.208 676.666,-416.208 "/>
+<text text-anchor="middle" x="530" y="-392.208" font-family="Times,serif" font-size="20.00">ocr_tesseract_hocr</text>
 </g>
-<!-- t7&#45;&gt;t10 -->
-<g id="edge9" class="edge"><title>t7&#45;&gt;t10</title>
-<path fill="none" stroke="#0044a0" d="M490.585,-299.003C489.12,-295.095 487.528,-290.852 485.953,-286.652"/>
-<polygon fill="#0044a0" stroke="#0044a0" points="489.164,-285.245 482.376,-277.111 482.61,-287.703 489.164,-285.245"/>
+<!-- t7&#45;&gt;t8 -->
+<g id="edge9" class="edge"><title>t7&#45;&gt;t8</title>
+<path fill="none" stroke="#0044a0" d="M769.399,-448.125C724.645,-438.98 669.394,-427.691 623.252,-418.262"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="623.748,-414.791 613.25,-416.219 622.347,-421.65 623.748,-414.791"/>
+</g>
+<!-- t7&#45;&gt;t9 -->
+<g id="edge11" class="edge"><title>t7&#45;&gt;t9</title>
+<path fill="none" stroke="#0044a0" d="M894.62,-448.039C911.413,-441.112 931.162,-432.966 949.666,-425.333"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="951.009,-428.565 958.918,-421.516 948.339,-422.094 951.009,-428.565"/>
 </g>
 <!-- t11 -->
-<g id="node13" class="node"><title>t11</title>
-<polygon fill="#efa03b" stroke="black" points="985.486,-277.109 642.514,-277.109 638.514,-273.109 638.514,-241.109 981.486,-241.109 985.486,-245.109 985.486,-277.109"/>
-<polyline fill="none" stroke="black" points="981.486,-273.109 638.514,-273.109 "/>
-<polyline fill="none" stroke="black" points="981.486,-273.109 981.486,-241.109 "/>
-<polyline fill="none" stroke="black" points="981.486,-273.109 985.486,-277.109 "/>
-<text text-anchor="middle" x="812" y="-253.109" font-family="Times,serif" font-size="20.00">render_hocr_debug_page</text>
-</g>
-<!-- t7&#45;&gt;t11 -->
-<g id="edge18" class="edge"><title>t7&#45;&gt;t11</title>
-<path fill="none" stroke="#0044a0" d="M592.793,-299.079C628.531,-292.726 669.303,-285.478 705.912,-278.969"/>
-<polygon fill="#0044a0" stroke="#0044a0" points="706.887,-282.351 716.12,-277.155 705.661,-275.459 706.887,-282.351"/>
-</g>
-<!-- t12 -->
-<g id="node12" class="node"><title>t12</title>
-<polygon fill="#efa03b" stroke="black" points="607.082,-219.109 348.918,-219.109 344.918,-215.109 344.918,-183.109 603.082,-183.109 607.082,-187.109 607.082,-219.109"/>
-<polyline fill="none" stroke="black" points="603.082,-215.109 344.918,-215.109 "/>
-<polyline fill="none" stroke="black" points="603.082,-215.109 603.082,-183.109 "/>
-<polyline fill="none" stroke="black" points="603.082,-215.109 607.082,-219.109 "/>
-<text text-anchor="middle" x="476" y="-195.109" font-family="Times,serif" font-size="20.00">add_text_layer</text>
-</g>
-<!-- t10&#45;&gt;t12 -->
-<g id="edge15" class="edge"><title>t10&#45;&gt;t12</title>
-<path fill="none" stroke="#0044a0" d="M476,-241.003C476,-237.312 476,-233.322 476,-229.352"/>
-<polygon fill="#0044a0" stroke="#0044a0" points="479.5,-229.111 476,-219.111 472.5,-229.111 479.5,-229.111"/>
-</g>
-<!-- t8&#45;&gt;t9 -->
-<g id="edge13" class="edge"><title>t8&#45;&gt;t9</title>
-<path fill="none" stroke="#0044a0" d="M661.842,-299.864C658.871,-299.606 655.921,-299.354 653,-299.109 509.812,-287.095 471.159,-289.734 324.542,-277.219"/>
-<polygon fill="#0044a0" stroke="#0044a0" points="324.526,-273.705 314.262,-276.332 323.924,-280.679 324.526,-273.705"/>
+<g id="node10" class="node"><title>t11</title>
+<polygon fill="#00cc66" stroke="black" points="938.109,-338.208 653.891,-338.208 649.891,-334.208 649.891,-302.208 934.109,-302.208 938.109,-306.208 938.109,-338.208"/>
+<polyline fill="none" stroke="black" points="934.109,-334.208 649.891,-334.208 "/>
+<polyline fill="none" stroke="black" points="934.109,-334.208 934.109,-302.208 "/>
+<polyline fill="none" stroke="black" points="934.109,-334.208 938.109,-338.208 "/>
+<text text-anchor="middle" x="794" y="-314.208" font-family="Times,serif" font-size="20.00">render_hocr_page</text>
 </g>
 <!-- t8&#45;&gt;t11 -->
-<g id="edge17" class="edge"><title>t8&#45;&gt;t11</title>
-<path fill="none" stroke="#0044a0" d="M818.251,-299.003C817.64,-295.204 816.979,-291.087 816.322,-287.002"/>
-<polygon fill="#0044a0" stroke="#0044a0" points="819.775,-286.429 814.732,-277.111 812.864,-287.539 819.775,-286.429"/>
+<g id="edge10" class="edge"><title>t8&#45;&gt;t11</title>
+<path fill="none" stroke="#0044a0" d="M589.247,-380.152C629.442,-368.58 682.727,-353.241 724.863,-341.111"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="725.853,-344.468 734.495,-338.338 723.917,-337.741 725.853,-344.468"/>
 </g>
-<!-- t8&#45;&gt;t13 -->
-<g id="edge20" class="edge"><title>t8&#45;&gt;t13</title>
-<path fill="none" stroke="#0044a0" d="M935.04,-299.079C978.311,-292.618 1027.78,-285.23 1071.94,-278.636"/>
-<polygon fill="#0044a0" stroke="#0044a0" points="1072.48,-282.093 1081.86,-277.155 1071.45,-275.17 1072.48,-282.093"/>
+<!-- t12 -->
+<g id="node14" class="node"><title>t12</title>
+<polygon fill="#00cc66" stroke="black" points="1118.49,-270.208 775.514,-270.208 771.514,-266.208 771.514,-234.208 1114.49,-234.208 1118.49,-238.208 1118.49,-270.208"/>
+<polyline fill="none" stroke="black" points="1114.49,-266.208 771.514,-266.208 "/>
+<polyline fill="none" stroke="black" points="1114.49,-266.208 1114.49,-234.208 "/>
+<polyline fill="none" stroke="black" points="1114.49,-266.208 1118.49,-270.208 "/>
+<text text-anchor="middle" x="945" y="-246.208" font-family="Times,serif" font-size="20.00">render_hocr_debug_page</text>
+</g>
+<!-- t8&#45;&gt;t12 -->
+<g id="edge19" class="edge"><title>t8&#45;&gt;t12</title>
+<path fill="none" stroke="#0044a0" d="M620.537,-380.161C641.947,-376.512 664.736,-372.939 686,-370.208 714.866,-366.5 927.304,-369.633 947,-348.208 963.502,-330.256 960.281,-301.363 954.611,-280.149"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="957.925,-279.012 951.707,-270.433 951.218,-281.017 957.925,-279.012"/>
+</g>
+<!-- t13 -->
+<g id="node13" class="node"><title>t13</title>
+<polygon fill="#00cc66" stroke="black" points="753.082,-270.208 494.918,-270.208 490.918,-266.208 490.918,-234.208 749.082,-234.208 753.082,-238.208 753.082,-270.208"/>
+<polyline fill="none" stroke="black" points="749.082,-266.208 490.918,-266.208 "/>
+<polyline fill="none" stroke="black" points="749.082,-266.208 749.082,-234.208 "/>
+<polyline fill="none" stroke="black" points="749.082,-266.208 753.082,-270.208 "/>
+<text text-anchor="middle" x="622" y="-246.208" font-family="Times,serif" font-size="20.00">add_text_layer</text>
+</g>
+<!-- t11&#45;&gt;t13 -->
+<g id="edge16" class="edge"><title>t11&#45;&gt;t13</title>
+<path fill="none" stroke="#0044a0" d="M749.258,-302.039C726.862,-293.446 699.574,-282.975 676.019,-273.936"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="677.108,-270.605 666.518,-270.29 674.6,-277.14 677.108,-270.605"/>
+</g>
+<!-- t9&#45;&gt;t10 -->
+<g id="edge14" class="edge"><title>t9&#45;&gt;t10</title>
+<path fill="none" stroke="#0044a0" d="M877.633,-382.056C761.19,-369.023 593.788,-350.286 475.578,-337.054"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="475.697,-333.546 465.37,-335.912 474.919,-340.503 475.697,-333.546"/>
 </g>
 <!-- t9&#45;&gt;t12 -->
-<g id="edge16" class="edge"><title>t9&#45;&gt;t12</title>
-<path fill="none" stroke="#0044a0" d="M259.577,-241.079C294.86,-234.726 335.115,-227.478 371.259,-220.969"/>
-<polygon fill="#0044a0" stroke="#0044a0" points="372.116,-224.372 381.337,-219.155 370.875,-217.482 372.116,-224.372"/>
+<g id="edge18" class="edge"><title>t9&#45;&gt;t12</title>
+<path fill="none" stroke="#0044a0" d="M998.887,-371.447C994.931,-364.003 990.702,-355.831 987,-348.208 983.822,-341.663 967.96,-305.616 956.669,-279.865"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="959.82,-278.337 952.601,-270.582 953.409,-281.146 959.82,-278.337"/>
 </g>
-<!-- t16 -->
-<g id="node17" class="node"><title>t16</title>
-<polygon fill="#efa03b" stroke="black" points="1031.47,-105.333 1196,-78.005 1360.53,-105.333 1360.37,-149.551 1031.63,-149.551 1031.47,-105.333"/>
-<polygon fill="none" stroke="black" points="1027.46,-101.94 1196,-73.9453 1364.54,-101.94 1364.36,-153.556 1027.64,-153.556 1027.46,-101.94"/>
-<text text-anchor="middle" x="1196" y="-111.555" font-family="Times,serif" font-size="20.00">merge_pages</text>
+<!-- t9&#45;&gt;t14 -->
+<g id="edge21" class="edge"><title>t9&#45;&gt;t14</title>
+<path fill="none" stroke="#0044a0" d="M1065.03,-374.611C1088.59,-364.381 1116.27,-352.359 1139.4,-342.314"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="1140.9,-345.479 1148.68,-338.285 1138.11,-339.058 1140.9,-345.479"/>
 </g>
-<!-- t12&#45;&gt;t16 -->
-<g id="edge26" class="edge"><title>t12&#45;&gt;t16</title>
-<path fill="none" stroke="#0044a0" d="M607.222,-185.246C722.142,-172.229 890.172,-153.196 1017.34,-138.791"/>
-<polygon fill="#0044a0" stroke="#0044a0" points="1018.04,-142.235 1027.58,-137.632 1017.25,-135.279 1018.04,-142.235"/>
-</g>
-<!-- t11&#45;&gt;t16 -->
-<g id="edge27" class="edge"><title>t11&#45;&gt;t16</title>
-<path fill="none" stroke="#0044a0" d="M859.086,-240.997C916.223,-220.232 1014.29,-184.591 1089.94,-157.099"/>
-<polygon fill="#0044a0" stroke="#0044a0" points="1091.32,-160.323 1099.52,-153.618 1088.92,-153.744 1091.32,-160.323"/>
-</g>
-<!-- t15&#45;&gt;t16 -->
-<g id="edge23" class="edge"><title>t15&#45;&gt;t16</title>
-<path fill="none" stroke="#0044a0" d="M1321.98,-414.938C1359.16,-396.916 1407,-364.681 1407,-318.109 1407,-318.109 1407,-318.109 1407,-258.109 1407,-211.469 1370.69,-179.509 1328.2,-158.076"/>
-<polygon fill="#0044a0" stroke="#0044a0" points="1329.57,-154.854 1319.04,-153.66 1326.53,-161.158 1329.57,-154.854"/>
-</g>
-<!-- t13&#45;&gt;t16 -->
-<g id="edge25" class="edge"><title>t13&#45;&gt;t16</title>
-<path fill="none" stroke="#0044a0" d="M1196,-240.997C1196,-221.914 1196,-190.265 1196,-163.926"/>
-<polygon fill="#0044a0" stroke="#0044a0" points="1199.5,-163.759 1196,-153.759 1192.5,-163.759 1199.5,-163.759"/>
-</g>
-<!-- t14&#45;&gt;t16 -->
-<g id="edge24" class="edge"><title>t14&#45;&gt;t16</title>
-<path fill="none" stroke="#0044a0" d="M1326.64,-588.956C1373.58,-572.748 1427,-543.103 1427,-492.109 1427,-492.109 1427,-492.109 1427,-258.109 1427,-220.539 1416.55,-207.537 1388,-183.109 1376.82,-173.542 1364.16,-165.377 1350.82,-158.413"/>
-<polygon fill="#0044a0" stroke="#0044a0" points="1351.99,-155.087 1341.47,-153.781 1348.88,-161.358 1351.99,-155.087"/>
+<!-- t10&#45;&gt;t13 -->
+<g id="edge17" class="edge"><title>t10&#45;&gt;t13</title>
+<path fill="none" stroke="#0044a0" d="M417.688,-300.029C455.345,-291.399 499.718,-281.231 537.473,-272.578"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="538.461,-275.943 547.427,-270.297 536.898,-269.12 538.461,-275.943"/>
 </g>
 <!-- t17 -->
 <g id="node18" class="node"><title>t17</title>
-<polygon fill="#efa03b" stroke="black" points="1310.18,-52 1085.82,-52 1081.82,-48 1081.82,-16 1306.18,-16 1310.18,-20 1310.18,-52"/>
-<polyline fill="none" stroke="black" points="1306.18,-48 1081.82,-48 "/>
-<polyline fill="none" stroke="black" points="1306.18,-48 1306.18,-16 "/>
-<polyline fill="none" stroke="black" points="1306.18,-48 1310.18,-52 "/>
-<text text-anchor="middle" x="1196" y="-28" font-family="Times,serif" font-size="20.00">copy_final</text>
+<polygon fill="#efa03b" stroke="black" points="540.724,-156.455 770,-129.143 999.276,-156.455 999.062,-200.646 540.938,-200.646 540.724,-156.455"/>
+<polygon fill="none" stroke="black" points="536.704,-152.903 770,-125.112 1003.3,-152.903 1003.05,-204.648 536.954,-204.648 536.704,-152.903"/>
+<text text-anchor="middle" x="770" y="-162.669" font-family="Times,serif" font-size="20.00">merge_pages_ghostscript</text>
+</g>
+<!-- t13&#45;&gt;t17 -->
+<g id="edge27" class="edge"><title>t13&#45;&gt;t17</title>
+<path fill="none" stroke="#0044a0" d="M653.026,-234.114C665.992,-226.971 681.653,-218.343 697.24,-209.755"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="699.319,-212.606 706.388,-204.715 695.941,-206.475 699.319,-212.606"/>
+</g>
+<!-- t13&#45;&gt;t18 -->
+<g id="edge31" class="edge"><title>t13&#45;&gt;t18</title>
+<path fill="none" stroke="#0044a0" d="M753.329,-235.235C756.584,-234.884 759.812,-234.541 763,-234.208 873.497,-222.668 902.059,-228.201 1012,-212.208 1023.74,-210.5 1035.81,-208.554 1047.95,-206.456"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="1048.91,-209.84 1058.16,-204.659 1047.7,-202.946 1048.91,-209.84"/>
+</g>
+<!-- t12&#45;&gt;t17 -->
+<g id="edge28" class="edge"><title>t12&#45;&gt;t17</title>
+<path fill="none" stroke="#0044a0" d="M908.314,-234.114C892.552,-226.77 873.424,-217.858 854.484,-209.033"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="855.759,-205.766 845.216,-204.715 852.803,-212.111 855.759,-205.766"/>
+</g>
+<!-- t12&#45;&gt;t18 -->
+<g id="edge32" class="edge"><title>t12&#45;&gt;t18</title>
+<path fill="none" stroke="#0044a0" d="M1002.86,-234.114C1029.07,-226.37 1061.19,-216.881 1092.64,-207.59"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="1093.77,-210.905 1102.37,-204.715 1091.79,-204.192 1093.77,-210.905"/>
 </g>
 <!-- t16&#45;&gt;t17 -->
-<g id="edge28" class="edge"><title>t16&#45;&gt;t17</title>
-<path fill="none" stroke="#0044a0" d="M1196,-73.8665C1196,-69.8921 1196,-65.942 1196,-62.1676"/>
-<polygon fill="#0044a0" stroke="#0044a0" points="1199.5,-62.1213 1196,-52.1214 1192.5,-62.1214 1199.5,-62.1213"/>
+<g id="edge24" class="edge"><title>t16&#45;&gt;t17</title>
+<path fill="none" stroke="#0044a0" d="M1155.57,-234.546C1111.13,-227.821 1059.63,-219.853 1013,-212.208 1001.53,-210.326 989.752,-208.365 977.872,-206.363"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="978.316,-202.888 967.872,-204.672 977.149,-209.79 978.316,-202.888"/>
+</g>
+<!-- t16&#45;&gt;t18 -->
+<g id="edge29" class="edge"><title>t16&#45;&gt;t18</title>
+<path fill="none" stroke="#0044a0" d="M1258.03,-233.915C1254.58,-227.933 1250.55,-220.928 1246.43,-213.785"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="1249.24,-211.645 1241.21,-204.729 1243.17,-215.141 1249.24,-211.645"/>
+</g>
+<!-- t14&#45;&gt;t17 -->
+<g id="edge26" class="edge"><title>t14&#45;&gt;t17</title>
+<path fill="none" stroke="#0044a0" d="M1172.36,-302.154C1164.33,-293.013 1154.66,-281.362 1147,-270.208 1136.64,-255.121 1141.88,-244.862 1127,-234.208 1125.19,-232.915 1055.67,-220.232 978.45,-206.446"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="978.964,-202.982 968.505,-204.672 977.735,-209.874 978.964,-202.982"/>
+</g>
+<!-- t14&#45;&gt;t18 -->
+<g id="edge30" class="edge"><title>t14&#45;&gt;t18</title>
+<path fill="none" stroke="#0044a0" d="M1310.22,-302.184C1345.8,-294.579 1378.07,-284.119 1389,-270.208 1408.78,-245.028 1391.25,-224.765 1361.2,-209.211"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="1362.48,-205.944 1351.96,-204.742 1359.44,-212.246 1362.48,-205.944"/>
+</g>
+<!-- t15&#45;&gt;t17 -->
+<g id="edge25" class="edge"><title>t15&#45;&gt;t17</title>
+<path fill="none" stroke="#0044a0" d="M289.656,-684.797C164.646,-670.853 17,-641.95 17,-583.208 17,-583.208 17,-583.208 17,-319.208 17,-213.417 306.554,-181.327 526.553,-172.213"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="526.794,-175.706 536.646,-171.808 526.514,-168.711 526.794,-175.706"/>
+</g>
+<!-- t19 -->
+<g id="node20" class="node"><title>t19</title>
+<polygon fill="#efa03b" stroke="black" points="844.361,-47.3406 995,-20.006 1145.64,-47.3406 1145.5,-91.5689 844.501,-91.5689 844.361,-47.3406"/>
+<polygon fill="none" stroke="black" points="840.355,-43.9965 995,-15.9349 1149.65,-43.9965 1149.48,-95.5749 840.519,-95.5749 840.355,-43.9965"/>
+<text text-anchor="middle" x="995" y="-53.565" font-family="Times,serif" font-size="20.00">copy_final</text>
+</g>
+<!-- t17&#45;&gt;t19 -->
+<g id="edge35" class="edge"><title>t17&#45;&gt;t19</title>
+<path fill="none" stroke="#0044a0" d="M841.81,-133.486C864.177,-122.839 889.024,-111.011 912.085,-100.034"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="913.64,-103.17 921.165,-95.7118 910.631,-96.8497 913.64,-103.17"/>
+</g>
+<!-- t18&#45;&gt;t19 -->
+<g id="edge34" class="edge"><title>t18&#45;&gt;t19</title>
+<path fill="none" stroke="#0044a0" d="M1151.35,-134.66C1128.23,-123.705 1102.26,-111.399 1078.23,-100.009"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="1079.66,-96.8131 1069.12,-95.6933 1076.66,-103.139 1079.66,-96.8131"/>
 </g>
 </g>
 </svg>

pytest.ini

@@ -1,2 +1,2 @@
 [pytest]
-norecursedirs = lib 
+norecursedirs = lib .pc .git

requirements.txt

@@ -1,6 +1,9 @@
+# requirements.txt can be used to replicate the developer's build environment
+# setup.py lists a separate set of requirements that are looser to simplify
+# installation
 ruffus==2.6.3
-Pillow==3.1.1
+Pillow==3.3.0
 reportlab==3.2.0
-PyPDF2==1.25.1
-img2pdf==0.2
+PyPDF2==1.26
+img2pdf==0.2.1
 cffi==1.5.2

setup.cfg

@@ -1,4 +1,9 @@
 [bdist_wheel]
 python-tag = py34
+
 [aliases]
-test=pytest
+test=pytest
+
+[check-manifest]
+ignore =
+	.github

setup.py

@@ -6,7 +6,7 @@ from __future__ import print_function, unicode_literals
 
 import sys
 if sys.version_info < (3, 4):
-    print("Python 3.4 or newer is required")
+    print("Python 3.4 or newer is required", file=sys.stderr)
     sys.exit(1)
 
 from setuptools import setup  # nopep8
@@ -154,23 +154,23 @@ if command.startswith('install') or \
         command in ['check', 'test', 'nosetests', 'easy_install']:
     check_external_program(
         program='tesseract',
-        need_version='3.02.02',
+        need_version='3.03',  # limited by Travis CI / Ubuntu 12.04 backports
         package={'darwin': 'tesseract', 'linux': 'tesseract-ocr'}
     )
     check_external_program(
         program='gs',
-        need_version='9.14',
+        need_version='9.15',  # limited by Travis CI / Ubuntu 12.04 backports
         package='ghostscript'
     )
     check_external_program(
         program='unpaper',
-        need_version='6.1',
+        need_version='6.1',   # latest sane version
         package='unpaper',
         optional=True
     )
     check_external_program(
         program='qpdf',
-        need_version='5.0.0',
+        need_version='5.0.0',   # limited by Travis CI / Ubuntu 12.04 backports
         package='qpdf',
         version_check_args=['--version']
     )
@@ -198,7 +198,7 @@ setup(
         "Intended Audience :: End Users/Desktop",
         "Intended Audience :: Science/Research",
         "Intended Audience :: System Administrators",
-        "License :: Public Domain",
+        "License :: OSI Approved :: MIT License",
         "Operating System :: MacOS :: MacOS X",
         "Operating System :: POSIX",
         "Operating System :: POSIX :: BSD",
@@ -209,7 +209,6 @@ setup(
         ],
     setup_requires=[
         'setuptools_scm',
-        'setuptools_scm_git_archive',
         'cffi>=1.5.0',
         'pytest-runner'
     ],
@@ -218,18 +217,19 @@ setup(
         'ocrmypdf/lib/compile_leptonica.py:ffi'
     ],
     install_requires=[
-        'ruffus>=2.6.3',
-        'Pillow>=3.0.0',
-        'reportlab>=3.1.44',
-        'PyPDF2>=1.25.1',
-        'img2pdf>=0.2.0',
-        'cffi>=1.5.0'
+        'ruffus==2.6.3',        # pinned - ocrmypdf implements a 2.6.3 workaround
+        'Pillow>=3.1.0',        # Pillow is pretty stable
+        'reportlab>=3.2.0',     # oldest released version with sane image handling
+        'PyPDF2>=1.26',         # pure Python, so track HEAD closely
+        'img2pdf>=0.2.1',       # pure Python, so track HEAD closely
+        'cffi>=1.5.0'           # oldest version ever tested
     ],
     tests_require=tests_require,
     entry_points={
         'console_scripts': [
-            'ocrmypdf = ocrmypdf.main:run_pipeline'
+            'ocrmypdf = ocrmypdf.__main__:run_pipeline'
         ],
     },
+    package_data={'ocrmypdf': ['data/sRGB.icc']},
     include_package_data=True,
     zip_safe=False)

share/etc-apt-sources.list

@@ -0,0 +1,4 @@
+deb http://httpredir.debian.org/debian stretch main
+deb http://httpredir.debian.org/debian stretch-updates main
+deb http://security.debian.org stretch/updates main
+deb http://ftp.de.debian.org/debian sid main contrib non-free

tests/resources/README.rst

@@ -9,21 +9,29 @@ Files derived from free sources
 These test resources come from free sources, under either public domain or Creative Commons licenses.
 In some cases they were converted from one image format to another without other changes.
 
-+---------------------+--------------------------------------------------------------------------------+
-| File                | Source                                                                         |
-+=====================+================================================================================+
-| c02-22.pdf          | `Project Gutenberg`_, Adventures of Huckleberry Finn, page 22                  |
-+---------------------+--------------------------------------------------------------------------------+
-| congress.jpg        | `US Congressional Records`_                                                    |
-+---------------------+--------------------------------------------------------------------------------+
-| graph.pdf           | `Wikimedia: Pandas text analysis.png`_                                         |
-+---------------------+--------------------------------------------------------------------------------+
-| lichtenstein.pdf    | `Wikimedia: JPEG2000 Lichtenstein`_ (Creative Commons BY-SA 3.0)               |
-+---------------------+--------------------------------------------------------------------------------+
-| LinnSequencer.jpg,  | `Wikimedia: LinnSequencer`_ (Creative Commons Attribution-ShareAlike 3.0)      |
-| linn.pdf, linn.txt  |                                                                                |
-+---------------------+--------------------------------------------------------------------------------+
- 
+.. list-table:: 
+    :widths: 20 50 30
+    :header-rows: 1
+
+    *   - File
+        - Source
+        - License
+    *   - c02-22.pdf
+        - `Project Gutenberg`_, Adventures of Huckleberry Finn, page 22
+        - Public Domain
+    *   - congress.jpg
+        - `US Congressional Records`_
+        - Public Domain
+    *   - graph.pdf
+        - `Wikimedia: Pandas text analysis.png`_
+        - Public Domain
+    *   - lichtenstein.pdf
+        - `Wikimedia: JPEG2000 Lichtenstein`_
+        - Creative Commons BY-SA 3.0
+    *   - LinnSequencer.jpg, linn.pdf, linn.txt
+        - `Wikimedia: LinnSequencer`_
+        - Creative Commons BY-SA 3.0
+
 
 Files generated for this project
 ================================
@@ -31,14 +39,43 @@ Files generated for this project
 The following test resources were crafted specifically for this project, and can be used
 under the terms of the license in LICENSE.rst.
 
-- blank.pdf (a blank PDF page)
-- cmyk.pdf (a CMYK image created in Photoshop)
-- enormous.pdf (a very lage page)
-- francais.pdf (a page containing French accented characters)
-- hugemono.pdf (large monochrome JBIG2 page with pixel dimensions of 35000x35000)
-- invalid.pdf (a PDF file header followed by EOF marker)
-- missing_docinfo.pdf (PDF file with no /DocumentInfo section)
+.. list-table:: 
+    :widths: 20 20 60
+    :header-rows: 1
 
+    *   - File
+        - Contributor
+        - Purpose
+    *   - aspect.pdf
+        - @jbarlow83
+        - test image with 200 x 100 DPI resolution
+    *   - blank.pdf
+        - @jbarlow83
+        - blank PDF
+    *   - cmyk.pdf
+        - @jbarlow83
+        - a CMYK image created in Photoshop
+    *   - enormous.pdf
+        - @jbarlow83
+        - very large PDF page
+    *   - epson.pdf
+        - @lowesjam
+        - a linearized PDF containing some unusual indirect objects, created by an Epson printer; printout of a Wikipedia article (CC BY-SA)
+    *   - francais.pdf
+        - @jbarlow83
+        - a page containing French accents (diacritics)  
+    *   - hugemono.pdf
+        - @jbarlow83
+        - large monochrome 35000x35000 image in JBIG2 encoding 
+    *   - invalid.pdf
+        - @jbarlow83
+        - a PDF file header followed by EOF marker
+    *   - masks.pdf
+        - @supergrobi
+        - file containing explicit masks and a stencil mask drawn without a proper transformation matrix; printout of a German Wikipedia article (CC BY-SA)
+    *   - missing_docinfo.pdf
+        - @jbarlow83
+        - PDF file with no /DocumentInfo section 
 
 Assemblies
 ==========
@@ -47,12 +84,13 @@ These test resources are assemblies from other previously mentioned files, relea
 
 - cardinal.pdf (four cardinal directions, rotated copies of LinnSequencer.jpg)
 - ccitt.pdf (LinnSequencer.jpg, converted to CCITT encoding)
+- encrypted_algo4.pdf (congress.jpg, encrypted with algorithm 4 - not supported by PyPDF2)
 - graph_ocred.pdf (from graph.pdf)
 - jbig2.pdf (congress.jpg, converted to JBIG2 encoding)
 - multipage.pdf (from several other files)
 - palette.pdf (congress.jpg, converted to a 256-color palette)
 - skew.pdf (from c02-22.pdf)
-- skew-encrypted.pdf (skew.pdf with encrypted applied)
+- skew-encrypted.pdf (skew.pdf with encryption - access supported by PyPDF2)
 
 
 .. _`Wikimedia: LinnSequencer`: https://upload.wikimedia.org/wikipedia/en/b/b7/LinnSequencer_hardware_MIDI_sequencer_brochure_page_2_300dpi.jpg
@@ -63,4 +101,6 @@ These test resources are assemblies from other previously mentioned files, relea
 
 .. _`Wikimedia: Pandas text analysis.png`: https://en.wikipedia.org/wiki/File:Pandas_text_analysis.png
 
-.. _`Wikimedia: JPEG2000 Lichtenstein`: https://en.wikipedia.org/wiki/JPEG_2000#/media/File:Jpeg2000_2-level_wavelet_transform-lichtenstein.png
+.. _`Wikimedia: JPEG2000 Lichtenstein`: https://en.wikipedia.org/wiki/JPEG_2000#/media/File:Jpeg2000_2-level_wavelet_transform-lichtenstein.png
+
+.. _`Linux (Wikipedia Article)`: https://de.wikipedia.org/wiki/Linux 

tests/spoof/tesseract_big_image_error.py

@@ -8,13 +8,7 @@ VERSION_STRING = '''tesseract 3.04.00
 SPOOFED: return error claiming image too big
 '''
 
-"""Simulates a Tesseract crash
-
-It isn't strictly necessary to crash the process and that has unwanted
-side effects like triggering core dumps or error reporting, logging and such.
-It's enough to dump some text to stderr and return an error code.
-
-Follows the POSIX? convention of returning 128 + signal number.
+"""Simulates an error of Tesseract failing on attempts to process large images
 
 """
 

tests/spoof/tesseract_cache.py

@@ -6,6 +6,25 @@ import shutil
 import subprocess
 
 
+"""Cache output of tesseract to speed up test suite
+
+The cache is keyed by a hash that includes the tesseract version, some of
+the command line, and the binary dump of the input file. The output file,
+stdout, and stderr are replicated on a cache hit.
+
+Page orientation checks are also cached (-psm 0 stdout)
+
+Errors and crashes are not cached.
+
+Things not checked:
+-changes to tesseract installation that don't affect --version
+
+Will fail on Tesseract 3.02.02 in "hocr" mode because it doesn't produce
+the incorrect file extension.
+
+"""
+
+
 CACHE_PATH = os.path.abspath(os.path.join(
         os.path.dirname(__file__), '..', 'cache'))
 

tests/spoof/tesseract_crash.py

@@ -10,13 +10,13 @@ VERSION_STRING = '''tesseract 3.04.00
 SPOOFED: CRASH ON OCR or -psm 0
 '''
 
-"""Simulates a Tesseract crash
+"""Simulates a Tesseract crash when asked to run OCR
 
 It isn't strictly necessary to crash the process and that has unwanted
 side effects like triggering core dumps or error reporting, logging and such.
 It's enough to dump some text to stderr and return an error code.
 
-Follows the POSIX? convention of returning 128 + signal number.
+Follows the POSIX(?) convention of returning 128 + signal number.
 
 """
 

tests/spoof/tesseract_noop.py

@@ -4,6 +4,18 @@ import img2pdf
 from PIL import Image
 
 
+"""Tesseract no-op spoof
+
+To quickly run tests where getting OCR output is not necessary.
+
+In 'hocr' mode, create a .hocr file that specifies no text found.
+
+In 'pdf' mode, convert the image to PDF using another program.
+
+In orientation check mode, report the orientation is upright.
+"""
+
+
 VERSION_STRING = '''tesseract 3.04.00
  leptonica-1.72
   libjpeg 8d : libpng 1.6.19 : libtiff 4.0.6 : zlib 1.2.5

tests/spoof/unpaper_oldversion.py

@@ -0,0 +1,14 @@
+#!/usr/bin/env python3
+import sys
+
+def main():
+    if sys.argv[1] == '--version':
+        print('0.5')
+        sys.exit(0)
+
+    print("Only supports --version")
+    sys.exit(1)
+
+
+if __name__ == '__main__':
+    main()

tests/test_main.py

@@ -2,7 +2,7 @@
 # © 2015 James R. Barlow: github.com/jbarlow83
 
 from __future__ import print_function
-from subprocess import Popen, PIPE, check_output, check_call
+from subprocess import Popen, PIPE, check_output, check_call, DEVNULL
 import os
 import shutil
 from contextlib import suppress
@@ -12,6 +12,8 @@ from ocrmypdf.pageinfo import pdf_get_all_pageinfo
 import PyPDF2 as pypdf
 from ocrmypdf import ExitCode
 from ocrmypdf import leptonica
+from ocrmypdf.pdfa import file_claims_pdfa
+import platform
 
 
 if sys.version_info.major < 3:
@@ -21,11 +23,11 @@ if sys.version_info.major < 3:
 TESTS_ROOT = os.path.abspath(os.path.dirname(__file__))
 SPOOF_PATH = os.path.join(TESTS_ROOT, 'spoof')
 PROJECT_ROOT = os.path.dirname(TESTS_ROOT)
-OCRMYPDF = os.path.join(PROJECT_ROOT, 'OCRmyPDF.sh')
 TEST_RESOURCES = os.path.join(PROJECT_ROOT, 'tests', 'resources')
 TEST_OUTPUT = os.environ.get(
     'OCRMYPDF_TEST_OUTPUT',
     default=os.path.join(PROJECT_ROOT, 'tests', 'output', 'main'))
+OCRMYPDF = [sys.executable, '-m', 'ocrmypdf']
 
 
 def running_in_docker():
@@ -33,6 +35,10 @@ def running_in_docker():
     return os.path.exists('/.dockerinit')
 
 
+def is_linux():
+    return platform.system() == 'Linux'
+
+
 def setup_module():
     with suppress(FileNotFoundError):
         shutil.rmtree(TEST_OUTPUT)
@@ -40,15 +46,6 @@ def setup_module():
         os.makedirs(TEST_OUTPUT)
 
 
-def run_ocrmypdf_sh(input_file, output_file, *args, env=None):
-    sh_args = ['sh', OCRMYPDF] + list(args) + [input_file, output_file]
-    sh = Popen(
-        sh_args, close_fds=True, stdout=PIPE, stderr=PIPE,
-        universal_newlines=True, env=env)
-    out, err = sh.communicate()
-    return sh, out, err
-
-
 def _infile(input_basename):
     return os.path.join(TEST_RESOURCES, input_basename)
 
@@ -58,29 +55,31 @@ def _outfile(output_basename):
 
 
 def check_ocrmypdf(input_basename, output_basename, *args, env=None):
+    "Run ocrmypdf and confirmed that a valid file was created"
     input_file = _infile(input_basename)
     output_file = _outfile(output_basename)
 
-    sh, out, err = run_ocrmypdf_sh(input_file, output_file, *args, env=env)
-    if sh.returncode != 0:
+    p, out, err = run_ocrmypdf(input_basename, output_basename, *args, env=env)
+    if p.returncode != 0:
         print('stdout\n======')
         print(out)
         print('stderr\n======')
         print(err)
-    assert sh.returncode == 0
+    assert p.returncode == 0
     assert os.path.exists(output_file), "Output file not created"
     assert os.stat(output_file).st_size > 100, "PDF too small or empty"
     return output_file
 
 
-def run_ocrmypdf_env(input_basename, output_basename, *args, env=None):
+def run_ocrmypdf(input_basename, output_basename, *args, env=None):
+    "Run ocrmypdf and let caller deal with results"
     input_file = _infile(input_basename)
     output_file = _outfile(output_basename)
 
     if env is None:
         env = os.environ
 
-    p_args = ['ocrmypdf'] + list(args) + [input_file, output_file]
+    p_args = OCRMYPDF + list(args) + [input_file, output_file]
     p = Popen(
         p_args, close_fds=True, stdout=PIPE, stderr=PIPE,
         universal_newlines=True, env=env)
@@ -125,8 +124,8 @@ def spoof_tesseract_big_image_error():
     return spoof('tesseract', 'tesseract_big_image_error.py')
 
 
-def test_quick(spoof_tesseract_noop):
-    check_ocrmypdf('c02-22.pdf', 'test_quick.pdf', env=spoof_tesseract_noop)
+def test_quick(spoof_tesseract_cache):
+    check_ocrmypdf('ccitt.pdf', 'test_quick.pdf', env=spoof_tesseract_cache)
 
 
 def test_deskew(spoof_tesseract_noop):
@@ -159,34 +158,34 @@ def test_deskew(spoof_tesseract_noop):
 
 
 def test_clean(spoof_tesseract_noop):
-    check_ocrmypdf('skew.pdf', 'test_clean.pdf', '-c', env=spoof_tesseract_noop)
+    check_ocrmypdf('skew.pdf', 'test_clean.pdf', '-c',
+                   env=spoof_tesseract_noop)
 
 
-@pytest.mark.parametrize("pdf,renderer", [
-    ('palette.pdf', 'hocr'),
-    ('palette.pdf', 'tesseract'),
-    ('cmyk.pdf', 'hocr'),
-    ('cmyk.pdf', 'tesseract'),
-    ('ccitt.pdf', 'hocr'),
-    ('ccitt.pdf', 'tesseract'),
-    ('jbig2.pdf', 'hocr'),
-    ('jbig2.pdf', 'tesseract'),
-    ('lichtenstein.pdf', 'hocr'),
-    ('lichtenstein.pdf', 'tesseract')
-])
-def test_exotic_image(spoof_tesseract_cache, pdf, renderer):
+# This will run 5 * 2 * 2 = 20 test cases
+@pytest.mark.parametrize(
+    "pdf",
+    ['palette.pdf', 'cmyk.pdf', 'ccitt.pdf', 'jbig2.pdf', 'lichtenstein.pdf'])
+@pytest.mark.parametrize("renderer", ['hocr', 'tesseract'])
+@pytest.mark.parametrize("output_type", ['pdf', 'pdfa'])
+def test_exotic_image(spoof_tesseract_cache, pdf, renderer, output_type):
     check_ocrmypdf(
         pdf,
         'test_{0}_{1}.pdf'.format(pdf, renderer),
         '-dc',
         '-v', '1',
+        '--output-type', output_type,
         '--pdf-renderer', renderer, env=spoof_tesseract_cache)
 
 
-def test_preserve_metadata(spoof_tesseract_noop):
+@pytest.mark.parametrize("output_type", [
+    'pdfa', 'pdf'
+    ])
+def test_preserve_metadata(spoof_tesseract_noop, output_type):
     pdf_before = pypdf.PdfFileReader(_infile('graph.pdf'))
 
     output = check_ocrmypdf('graph.pdf', 'test_metadata_preserve.pdf',
+                            '--output-type', output_type,
                             env=spoof_tesseract_noop)
 
     pdf_after = pypdf.PdfFileReader(output)
@@ -194,8 +193,17 @@ def test_preserve_metadata(spoof_tesseract_noop):
     for key in ('/Title', '/Author'):
         assert pdf_before.documentInfo[key] == pdf_after.documentInfo[key]
 
+    pdfa_info = file_claims_pdfa(output)
+    assert pdfa_info['output'] == output_type
 
-def test_override_metadata(spoof_tesseract_noop):
+
+@pytest.mark.skipif(
+    is_linux() and not running_in_docker(),
+    reason="likely to fail if Linux locale is not configured correctly")
+@pytest.mark.parametrize("output_type", [
+    'pdfa', 'pdf'
+    ])
+def test_override_metadata(spoof_tesseract_noop, output_type):
     input_file = _infile('c02-22.pdf')
     output_file = _outfile('test_override_metadata.pdf')
 
@@ -203,11 +211,12 @@ def test_override_metadata(spoof_tesseract_noop):
     chinese = '孔子'
     high_unicode = 'U+1030C is: 𐌌'
 
-    p, out, err = run_ocrmypdf_env(
+    p, out, err = run_ocrmypdf(
         input_file, output_file,
         '--title', german,
         '--author', chinese,
         '--subject', high_unicode,
+        '--output-type', output_type,
         env=spoof_tesseract_noop)
 
     assert p.returncode == ExitCode.ok
@@ -226,6 +235,9 @@ def test_override_metadata(spoof_tesseract_noop):
     assert pdfinfo['Subject'] == high_unicode
     assert pdfinfo.get('Keywords', '') == ''
 
+    pdfa_info = file_claims_pdfa(output_file)
+    assert pdfa_info['output'] == output_type
+
 
 @pytest.mark.parametrize('renderer', [
     'hocr',
@@ -244,8 +256,8 @@ def test_oversample(spoof_tesseract_cache, renderer):
 
 
 def test_repeat_ocr():
-    sh, _, _ = run_ocrmypdf_sh('graph_ocred.pdf', 'wontwork.pdf')
-    assert sh.returncode != 0
+    p, _, _ = run_ocrmypdf('graph_ocred.pdf', 'wontwork.pdf')
+    assert p.returncode != 0
 
 
 def test_force_ocr(spoof_tesseract_cache):
@@ -325,11 +337,6 @@ def test_monochrome_correlation():
     'tesseract',
     ])
 def test_autorotate(spoof_tesseract_cache, renderer):
-    import ocrmypdf.ghostscript as ghostscript
-    import logging
-
-    gslog = logging.getLogger()
-
     # cardinal.pdf contains four copies of an image rotated in each cardinal
     # direction - these ones are "burned in" not tagged with /Rotate
     out = check_ocrmypdf('cardinal.pdf', 'test_autorotate_%s.pdf' % renderer,
@@ -343,6 +350,36 @@ def test_autorotate(spoof_tesseract_cache, renderer):
         assert correlation > 0.80
 
 
+def test_autorotate_threshold_low(spoof_tesseract_cache):
+    out = check_ocrmypdf('cardinal.pdf', 'test_autorotate_threshold_low.pdf',
+                         '--rotate-pages-threshold', '1',
+                         '-r', '-v', '1', env=spoof_tesseract_cache)
+
+    # Low threshold -> always rotate -> expect high correlation between
+    # reference page and test page
+    correlation = check_monochrome_correlation(
+        reference_pdf=_infile('cardinal.pdf'),
+        reference_pageno=1,
+        test_pdf=out,
+        test_pageno=3)
+    assert correlation > 0.80
+
+
+def test_autorotate_threshold_high(spoof_tesseract_cache):
+    out = check_ocrmypdf('cardinal.pdf', 'test_autorotate_threshold_high.pdf',
+                         '--rotate-pages-threshold', '99',
+                         '-r', '-v', '1', env=spoof_tesseract_cache)
+
+    # High threshold -> never rotate -> expect low correlation since
+    # test page will not be rotated
+    correlation = check_monochrome_correlation(
+        reference_pdf=_infile('cardinal.pdf'),
+        reference_pageno=1,
+        test_pdf=out,
+        test_pageno=3)
+    assert correlation < 0.10
+
+
 @pytest.mark.parametrize('renderer', [
     'hocr',
     'tesseract',
@@ -361,16 +398,15 @@ def test_skip_big(spoof_tesseract_cache):
     assert not pdfinfo[0]['has_text']
 
 
-@pytest.mark.parametrize('renderer', [
-    'hocr',
-    'tesseract',
-    ])
-def test_maximum_options(spoof_tesseract_cache, renderer):
+@pytest.mark.parametrize('renderer', ['hocr', 'tesseract'])
+@pytest.mark.parametrize('output_type', ['pdf', 'pdfa'])
+def test_maximum_options(spoof_tesseract_cache, renderer, output_type):
     check_ocrmypdf(
         'multipage.pdf', 'test_multipage%s.pdf' % renderer,
         '-d', '-c', '-i', '-g', '-f', '-k', '--oversample', '300',
         '--skip-big', '10', '--title', 'Too Many Weird Files',
         '--author', 'py.test', '--pdf-renderer', renderer,
+        '--output-type', output_type,
         env=spoof_tesseract_cache)
 
 
@@ -378,38 +414,49 @@ def test_tesseract_missing_tessdata():
     env = os.environ.copy()
     env['TESSDATA_PREFIX'] = '/tmp'
 
-    p, _, err = run_ocrmypdf_env(
+    p, _, err = run_ocrmypdf(
         'graph_ocred.pdf', 'not_a_pdfa.pdf', '-v', '1', '--skip-text', env=env)
     assert p.returncode == ExitCode.missing_dependency, err
 
 
 def test_invalid_input_pdf():
-    p, out, err = run_ocrmypdf_env(
+    p, out, err = run_ocrmypdf(
         'invalid.pdf', 'wont_be_created.pdf')
     assert p.returncode == ExitCode.input_file, err
 
 
 def test_blank_input_pdf():
-    p, out, err = run_ocrmypdf_env(
+    p, out, err = run_ocrmypdf(
         'blank.pdf', 'still_blank.pdf')
     assert p.returncode == ExitCode.ok
 
 
+def test_force_ocr_on_pdf_with_no_images(spoof_tesseract_crash):
+    # As a correctness test, make sure that --force-ocr on a PDF with no
+    # content still triggers tesseract. If tesseract crashes, then it was
+    # called.
+    p, _, err = run_ocrmypdf(
+        'blank.pdf', 'wont_be_created.pdf', '--force-ocr',
+        env=spoof_tesseract_crash)
+    assert p.returncode == ExitCode.child_process_error, err
+    assert not os.path.exists(_outfile('wontwork.pdf'))
+
+
 def test_french(spoof_tesseract_cache):
-    p, out, err = run_ocrmypdf_env(
+    p, out, err = run_ocrmypdf(
         'francais.pdf', 'francais.pdf', '-l', 'fra', env=spoof_tesseract_cache)
     assert p.returncode == ExitCode.ok, \
         "This test may fail if Tesseract language packs are missing"
 
 
 def test_klingon():
-    p, out, err = run_ocrmypdf_env(
+    p, out, err = run_ocrmypdf(
         'francais.pdf', 'francais.pdf', '-l', 'klz')
     assert p.returncode == ExitCode.bad_args
 
 
 def test_missing_docinfo(spoof_tesseract_noop):
-    p, out, err = run_ocrmypdf_env(
+    p, out, err = run_ocrmypdf(
         'missing_docinfo.pdf', 'missing_docinfo.pdf', '-l', 'eng', '-c',
         env=spoof_tesseract_noop)
     assert p.returncode == ExitCode.ok, err
@@ -428,26 +475,26 @@ def test_uppercase_extension(spoof_tesseract_noop):
 
 def test_input_file_not_found():
     input_file = "does not exist.pdf"
-    sh, out, err = run_ocrmypdf_sh(
+    p, out, err = run_ocrmypdf(
         _infile(input_file),
         _outfile("will not happen.pdf"))
-    assert sh.returncode == ExitCode.input_file
+    assert p.returncode == ExitCode.input_file
     assert (input_file in out or input_file in err)
 
 
 def test_input_file_not_a_pdf():
     input_file = __file__  # Try to OCR this file
-    sh, out, err = run_ocrmypdf_sh(
+    p, out, err = run_ocrmypdf(
         _infile(input_file),
         _outfile("will not happen.pdf"))
-    assert sh.returncode == ExitCode.input_file
+    assert p.returncode == ExitCode.input_file
     assert (input_file in out or input_file in err)
 
 
 def test_qpdf_repair_fails():
     env = os.environ.copy()
     env['OCRMYPDF_QPDF'] = os.path.abspath('./spoof/qpdf_dummy_return2.py')
-    p, out, err = run_ocrmypdf_env(
+    p, out, err = run_ocrmypdf(
         '-v', '1',
         'c02-22.pdf', 'wont_be_created.pdf', env=env)
     print(out)
@@ -456,7 +503,7 @@ def test_qpdf_repair_fails():
 
 
 def test_encrypted():
-    p, out, err = run_ocrmypdf_env('skew-encrypted.pdf', 'wont_be_created.pdf')
+    p, out, err = run_ocrmypdf('skew-encrypted.pdf', 'wont_be_created.pdf')
     assert p.returncode == ExitCode.input_file
     assert out.find('password')
 
@@ -478,21 +525,23 @@ def test_pagesegmode(renderer, spoof_tesseract_cache):
     'tesseract',
     ])
 def test_tesseract_crash(renderer, spoof_tesseract_crash):
-    sh, out, err = run_ocrmypdf_env(
+    p, out, err = run_ocrmypdf(
         'ccitt.pdf', 'wontwork.pdf', '-v', '1',
         '--pdf-renderer', renderer, env=spoof_tesseract_crash)
-    assert sh.returncode == ExitCode.child_process_error
+    assert p.returncode == ExitCode.child_process_error
     assert not os.path.exists(_outfile('wontwork.pdf'))
     assert "ERROR" in err
 
 
 def test_tesseract_crash_autorotate(spoof_tesseract_crash):
-    sh, out, err = run_ocrmypdf_env(
+    p, out, err = run_ocrmypdf(
         'ccitt.pdf', 'wontwork.pdf',
         '-r', env=spoof_tesseract_crash)
-    assert sh.returncode == ExitCode.child_process_error
+    assert p.returncode == ExitCode.child_process_error
     assert not os.path.exists(_outfile('wontwork.pdf'))
     assert "ERROR" in err
+    print(out)
+    print(err)
 
 
 @pytest.mark.parametrize('renderer', [
@@ -503,3 +552,89 @@ def test_tesseract_image_too_big(renderer, spoof_tesseract_big_image_error):
     check_ocrmypdf(
         'hugemono.pdf', 'hugemono_%s.pdf' % renderer, '-r',
         '--pdf-renderer', renderer, env=spoof_tesseract_big_image_error)
+
+
+def test_no_unpaper():
+    env = os.environ.copy()
+    env['OCRMYPDF_UNPAPER'] = os.path.abspath('./spoof/no_unpaper_here.py')
+    p, out, err = run_ocrmypdf(
+        'c02-22.pdf', 'wont_be_created.pdf', '--clean', env=env)
+    assert p.returncode == ExitCode.missing_dependency
+
+
+def test_old_unpaper():
+    env = os.environ.copy()
+    env['OCRMYPDF_UNPAPER'] = os.path.abspath('./spoof/unpaper_oldversion.py')
+    p, out, err = run_ocrmypdf(
+        'c02-22.pdf', 'wont_be_created.pdf', '--clean', env=env)
+    assert p.returncode == ExitCode.missing_dependency
+
+
+def test_algo4():
+    p, _, _ = run_ocrmypdf('encrypted_algo4.pdf', 'wontwork.pdf')
+    assert p.returncode == ExitCode.encrypted_pdf
+
+
+@pytest.mark.parametrize('renderer', [
+    'hocr'])  # tesseract cannot pass this test - resamples to square image
+def test_non_square_resolution(renderer, spoof_tesseract_cache):
+    # Confirm input image is non-square resolution
+    in_pageinfo = pdf_get_all_pageinfo(_infile('aspect.pdf'))
+    assert in_pageinfo[0]['xres'] != in_pageinfo[0]['yres']
+
+    out = 'aspect_%s.pdf' % renderer
+    check_ocrmypdf(
+        'aspect.pdf', out,
+        '--pdf-renderer', renderer, env=spoof_tesseract_cache)
+
+    out_pageinfo = pdf_get_all_pageinfo(_outfile(out))
+
+    # Confirm resolution was kept the same
+    assert in_pageinfo[0]['xres'] == out_pageinfo[0]['xres']
+    assert in_pageinfo[0]['yres'] == out_pageinfo[0]['yres']
+
+
+def test_image_to_pdf(spoof_tesseract_noop):
+    check_ocrmypdf(
+        'LinnSequencer.jpg', 'image_to_pdf.pdf', '--image-dpi', '200',
+        env=spoof_tesseract_noop)
+
+
+def test_jbig2_passthrough(spoof_tesseract_cache):
+    out = check_ocrmypdf(
+        'jbig2.pdf', 'jbig2_out.pdf',
+        '--output-type', 'pdf',
+        '--pdf-renderer', 'hocr',
+        env=spoof_tesseract_cache)
+
+    out_pageinfo = pdf_get_all_pageinfo(out)
+    assert out_pageinfo[0]['images'][0]['enc'] == 'jbig2'
+
+
+def test_stdin(spoof_tesseract_noop):
+    input_file = _infile('francais.pdf')
+    output_file = _outfile('test_stdin.pdf')
+
+    # Runs: cat testfile.pdf | ocrmypdf - output.pdf
+
+    p1_args = ['cat', input_file]
+    p1 = Popen(p1_args, close_fds=True, stdin=DEVNULL, stdout=PIPE)
+
+    p2_args = OCRMYPDF + ['-', output_file]
+    p2 = Popen(
+        p2_args, close_fds=True, stdout=PIPE, stderr=PIPE,
+        stdin=p1.stdout, env=spoof_tesseract_noop)
+    p1.stdout.close()
+    out, err = p2.communicate()
+
+    assert p2.returncode == ExitCode.ok
+
+
+def test_masks(spoof_tesseract_noop):
+    check_ocrmypdf('masks.pdf', 'test_masks.pdf', env=spoof_tesseract_noop)
+
+
+def test_linearized_pdf_and_indirect_object(spoof_tesseract_noop):
+    check_ocrmypdf(
+        'epson.pdf', 'test_epson.pdf',
+        env=spoof_tesseract_noop)

tests/test_pageinfo.py

@@ -103,8 +103,8 @@ def test_single_page_image():
     assert pdfimage['bpc'] == 8
 
     # DPI in a 1"x1" is the image width
-    assert pdfimage['dpi_w'] == 8
-    assert pdfimage['dpi_h'] == 8
+    assert abs(pdfimage['dpi_w'] - 8) < 1e-5
+    assert abs(pdfimage['dpi_h'] - 8) < 1e-5
 
 
 def test_single_page_inline_image():
@@ -120,8 +120,12 @@ def test_single_page_inline_image():
         pdf.showPage()
         pdf.save()
 
-    with pytest.raises(NotImplementedError):
-        pageinfo.pdf_get_all_pageinfo(filename)
+    pdfinfo = pageinfo.pdf_get_all_pageinfo(filename)
+    print(pdfinfo)
+    pdfimage = pdfinfo[0]['images'][0]
+    assert (pdfimage['dpi_w'] - 8) < 1e-5
+    assert pdfimage['color'] != '-'
+    assert pdfimage['width'] == 8
 
 
 def test_jpeg():
@@ -131,4 +135,5 @@ def test_jpeg():
 
     pdfimage = pdfinfo[0]['images'][0]
     assert pdfimage['enc'] == 'jpeg'
+    assert (pdfimage['dpi_w'] - 150) < 1e-5