osx_brew: show output before letting “brew audit” check it

all(<empty generator>) is True.

.dockerignore

@@ -11,11 +11,14 @@
 */*/*/*/*/*/*.pyc
 */*/*/*/*/*/*/*.pyc
 .cache/
+.eggs/
+.github/
 .git/
 .ipynb_checkpoints/
 .ruffus_history.sqlite
 bin/
 build/
+docs/
 dist/
 htmlcov/
 include/
@@ -27,5 +30,5 @@ tests/cache/
 tests/output/
 tests/resources/private/
 tmp/
-venv-3.4/
-venv-3.5/
+venv*/
+wheelhouse/

.gitignore

@@ -4,6 +4,8 @@
 venv*/
 pyvenv.cfg
 tasks.py
+.bash_history
+.ruffus_history.sqlite
 
 # Package building
 *.egg-info/
@@ -27,8 +29,11 @@ htmlcov/
 # Testing
 log/
 /*.pdf
+/*.qdf
+*.ipynb
 .ipynb_checkpoints/
 tests/cache/
 tests/output/
 tests/resources/private/
 tmp/
+pdfbox-app*.jar

.travis.yml

@@ -1,45 +1,60 @@
-sudo: required
 dist: trusty
 language: python
-
-cache: pip
-
 cache:
-    directories:
-        - $HOME/.ccache
-        - packages
-        - tests/cache
+  pip: true
+  directories:
+  - packages
+  - tests/cache
+  - $HOME/Library/Caches/Homebrew
 
-python:
-    - 3.4
-    - 3.5
+matrix:
+  include:
+    - os: linux
+      sudo: required
+      language: python
+      python: 3.4
+    - os: linux
+      sudo: required
+      language: python
+      python: 3.5
+    - os: linux
+      sudo: required
+      language: python
+      python: 3.6
+    - os: osx
+      osx_image: xcode8
+      language: generic
 
 before_cache:
-    - rm -f $HOME/.cache/pip/log/debug.log
+- rm -f $HOME/.cache/pip/log/debug.log
 
 before_install:
-    # Ubuntu packages
-    - 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 libavformat56 libavcodec56 libavutil54 libffi-dev
-
-    # pip
-    - pip install --upgrade pip
-
-    # Download, make and install unpaper (using ccache)
-    - 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
+- if [[ "$TRAVIS_OS_NAME" == "linux" ]]; then bash .travis/linux_before_install.sh ; fi
+- if [[ "$TRAVIS_OS_NAME" == "osx" ]]; then bash .travis/osx_before_install.sh ; fi
 
 install:
-    - pip install -r requirements.txt
-    - pip install -r test_requirements.txt
+- pip3 install .
+- pip3 install -r requirements.txt -r test_requirements.txt
 
 script:
-    - python setup.py clean
-    - python setup.py install
-    - python setup.py test
+- mv ocrmypdf dont_import_this_ocrmypdf
+- pytest
+- mv dont_import_this_ocrmypdf ocrmypdf
 
-os:
-    - linux
+after_success:
+- if [[ "$TRAVIS_OS_NAME" == "osx" ]]; then bash .travis/osx_brew.sh ; fi
+
+# See https://www.appneta.com/blog/pypi-deployment-with-travis-ci/ for
+# steps to set up testpypi deploy for untagged builds if desired
+
+deploy:
+  provider: pypi
+  user: ocrmypdf-travis
+  password:
+    secure: DTFOmmNL6olA0+yXvp4u9jXZlZeqrJsJ0526jzqf4a3gZ6jnGTq5UI6WzRsslSyoMMfXKtHQebqHM6ogSgCZinyZ3ufHJo8fn9brxbEc2gsiWkbj5o3bGwdWMT1vNNE7XW0VCpw87rZ1EEwjl4FJHFudMlPR1yfU5+uq0k0PACo=
+  distributions: "sdist bdist_wheel"
+  on:
+    branch: master
+    tags: true
+    condition: $TRAVIS_PYTHON_VERSION == "3.6" && $TRAVIS_OS_NAME == "linux"
+  skip_upload_docs: true

.travis/autobrew.py

@@ -0,0 +1,74 @@
+from string import Template
+from subprocess import run, PIPE
+import re
+
+recipe_template = Template("""
+class Ocrmypdf < Formula
+  include Language::Python::Virtualenv
+
+  desc "Adds an OCR text layer to scanned PDF files"
+  homepage "https://github.com/jbarlow83/OCRmyPDF"
+  ${ocrmypdf_url}
+  ${ocrmypdf_sha256}
+
+  depends_on :python3
+  depends_on "pkg-config" => :build
+  depends_on "libffi"
+  depends_on "tesseract"
+  depends_on "ghostscript"
+  depends_on "unpaper"
+  depends_on "qpdf"
+
+  # For Pillow source install
+  depends_on "openjpeg"
+  depends_on "freetype"
+  depends_on "libpng"
+
+${resources}
+
+  def install
+    ENV.append ["SETUPTOOLS_SCM_PRETEND_VERSION"], "v${ocrmypdf_version}"
+    ENV.each do |key, value|
+      puts "#{key}:#{value}"
+    end
+    virtualenv_install_with_resources
+  end
+
+  test do
+    # `test do` will create, run in and delete a temporary directory.
+    #
+    # The installed folder is not in the path, so use the entire path to any
+    # executables being tested: `system "#{bin}/program", "do", "something"`.
+    system "#{bin}/ocrmypdf", "--version"
+  end
+end
+""")
+
+def main():
+    p = run(['poet', '--single', 'ocrmypdf'],
+            encoding='utf-8', stdout=PIPE, check=True)
+
+    ocrmypdf_lines = p.stdout.splitlines()
+    ocrmypdf_url = ocrmypdf_lines[1].strip()
+    ocrmypdf_sha256 = ocrmypdf_lines[2].strip()
+
+    ocrmypdf_version = re.search(
+        r'ocrmypdf-(.+)\.tar.*', ocrmypdf_url).group(1)
+    print(f"Autobrewing {ocrmypdf_version}")
+
+    p = run(['poet', '--resources', 'ocrmypdf'],
+            encoding='utf-8', stdout=PIPE, check=True)
+
+    poet_resources = p.stdout
+
+    # Remove the duplicate "ocrmypdf" resource block
+    all_resources = poet_resources.split('resource')
+    kept_resources = [block for block in all_resources if 'ocrmypdf' not in block]
+    resources = 'resource'.join(kept_resources)
+
+    with open('ocrmypdf.rb', 'w') as out:
+        out.write(recipe_template.substitute(**locals()))
+
+
+if __name__ == '__main__':
+    main()

.travis/linux_before_install.sh

@@ -0,0 +1,24 @@
+#!/bin/bash
+set -euo pipefail
+set -x
+
+sudo add-apt-repository ppa:vshn/ghostscript -y
+sudo add-apt-repository ppa:heyarje/libav-11 -y
+sudo apt-get update -qq
+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 install --upgrade pip
+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

.travis/osx_before_install.sh

@@ -0,0 +1,16 @@
+#!/bin/bash
+set -euo pipefail
+set -x
+
+brew update
+
+brew install openjpeg jbig2dec libtiff     # image libraries
+brew install qpdf
+brew install ghostscript
+brew install python3
+brew install libxml2 libffi leptonica
+brew install unpaper   # optional
+brew install tesseract
+
+pip3 install --upgrade pip
+pip3 install wheel

.travis/osx_brew.sh

@@ -0,0 +1,8 @@
+#!/bin/bash
+set -euo pipefail
+set -x
+
+pip3 install homebrew-pypi-poet
+python3 .travis/autobrew.py
+cat ocrmypdf.rb
+brew audit ocrmypdf.rb

Dockerfile

@@ -1,91 +1,54 @@
 # OCRmyPDF
 #
-# VERSION               3.2
-FROM      debian:stretch
+# VERSION               4.4.2
+FROM      ubuntu:16.10
 MAINTAINER James R. Barlow <jim@purplerock.ca>
 
-# Add unprivileged user
+RUN apt-get update && apt-get install -y --no-install-recommends \
+  software-properties-common python-software-properties \
+  python3-wheel \
+  python3-reportlab \
+  python3-venv \
+  ghostscript \
+  qpdf \
+  poppler-utils \
+  unpaper \
+  libffi-dev \ 
+  tesseract-ocr \
+  tesseract-ocr-eng \
+  tesseract-ocr-fra \
+  tesseract-ocr-spa \
+  tesseract-ocr-deu
+
+RUN python3 -m venv --system-site-packages /appenv
+
+# This installs the latest binary wheel instead of the code in the current
+# folder. Installing from source will fail, apparently because cffi needs
+# build-essentials (gcc) to do a source installation 
+# (i.e. "pip install ."). It's unclear to me why this is the case.
+RUN . /appenv/bin/activate; \
+  pip install --upgrade pip \
+  && pip install ocrmypdf
+
+# Now copy the application in, mainly to get the test suite.
+# Do this now to make the best use of Docker cache.
+COPY . /application
+RUN . /appenv/bin/activate; \
+  pip install -r /application/test_requirements.txt
+
+# Remove the junk, including the source version of application since it was
+# already installed
+RUN rm -rf /tmp/* /var/tmp/* /root/* /application/ocrmypdf \
+  && apt-get autoremove -y \
+  && apt-get autoclean -y
+
 RUN useradd docker \
   && mkdir /home/docker \
   && chown docker:docker /home/docker
 
-# Update system and install our dependencies
-# If this command takes too Docker hub's automated build will timeout,
-# so try it in portions
-RUN apt-get update && apt-get install -y --no-install-recommends \
-  locales \
-  python3 \
-  python3-pip \
-  python3-venv \
-  python3-reportlab \
-  python3-pil \
-  python3-wheel
-
-RUN apt-get install -y --no-install-recommends \
-  unpaper \
-  qpdf \
-  poppler-utils \
-  tesseract-ocr \
-  tesseract-ocr-deu tesseract-ocr-spa tesseract-ocr-eng tesseract-ocr-fra
-
-RUN apt-get install -qy --no-install-recommends \
-  libffi-dev \
-  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 && \
-  locale-gen C.UTF-8 && \
-  /usr/sbin/update-locale LANG=C.UTF-8
-ENV LC_ALL C.UTF-8
-
-
-# Set up a Python virtualenv and take all of the system packages, so we can
-# rely on the platform packages rather than importing GCC and compiling them
-RUN pyvenv /appenv \
-  && pyvenv --system-site-packages /appenv
-
-COPY . /application/
-
-# Replace stock Tesseract 3.04.00 font with improved sharp2.ttf that resolves
-# issues in many PDF viewers.
-# Discussion is in https://github.com/tesseract-ocr/tesseract/issues/182
-COPY ./share/sharp2.ttf /usr/share/tesseract-ocr/tessdata/pdf.ttf
-RUN chmod 644 /usr/share/tesseract-ocr/tessdata/pdf.ttf
-
-# Set this here to force a docker version, allowing non-tagged versions to
-# be built
-# ENV SETUPTOOLS_SCM_PRETEND_VERSION=v3.3.0
-
-# Install application and dependencies
-# In this arrangement Pillow and reportlab will be provided by the system
-# Even though ocrmypdf is locally present, pull from PyPI because
-# Dockerhub and setuptools_scm clash
-RUN . /appenv/bin/activate; \
-  pip install --upgrade pip \
-  && pip install ocrmypdf \
-  && pip install --no-cache-dir -r /application/test_requirements.txt
-
-# Remove the junk
-RUN apt-get remove -qy gcc
-RUN apt-get autoremove -y && apt-get clean -y
-RUN rm -rf /var/lib/apt/lists/* /tmp/* /var/tmp/* /root/*
-
 USER docker
 WORKDIR /home/docker
 
-ENV OCRMYPDF_TEST_OUTPUT=/tmp/test-output
-ENV OCRMYPDF_SHARP_TTF=1
-
 # Must use array form of ENTRYPOINT
 # Non-array form does not append other arguments, because that is "intuitive"
-ENTRYPOINT ["/application/docker-wrapper.sh"]
+ENTRYPOINT ["/application/docker-wrapper.sh"]

Dockerfile.polyglot

@@ -1,14 +1,17 @@
 # OCRmyPDF polyglot
 #
-# VERSION               3.2
+# VERSION               4.4.2
 FROM      jbarlow83/ocrmypdf:latest
 MAINTAINER James R. Barlow <jim@purplerock.ca>
 
-# Update system and install our dependencies
 USER root
+
+# Update system and install our dependencies
 RUN apt-get update && apt-get install -y --no-install-recommends \
   tesseract-ocr-all 
 
+RUN apt-get autoremove -y && apt-get clean -y
+
 USER docker
 
 # Must use array form of ENTRYPOINT

Dockerfile.tess4

@@ -0,0 +1,64 @@
+# OCRmyPDF
+#
+# VERSION               4.4.2
+FROM 	ubuntu:16.10
+MAINTAINER James R. Barlow <jim@purplerock.ca>
+
+RUN apt-get update && apt-get install -y --no-install-recommends \
+  software-properties-common python-software-properties \
+  python3-wheel \
+  python3-reportlab \
+  python3-venv \
+  ghostscript \
+  qpdf \
+  poppler-utils \
+  unpaper \
+  libffi-dev
+
+RUN add-apt-repository ppa:alex-p/tesseract-ocr
+
+RUN apt-get update \
+	&& apt-get autoremove -y \
+	&& apt-get install -y --no-install-recommends \
+		tesseract-ocr \
+		tesseract-ocr-eng \
+		tesseract-ocr-fra \
+		tesseract-ocr-deu \
+		tesseract-ocr-spa \
+		tesseract-ocr-por \
+		tesseract-ocr-ara \
+		tesseract-ocr-rus \
+		tesseract-ocr-chi-sim 
+
+RUN python3 -m venv --system-site-packages /appenv
+
+# This installs the latest binary wheel instead of the code in the current
+# folder. Installing from source will fail, apparently because cffi needs
+# build-essentials (gcc) to do a source installation 
+# (i.e. "pip install ."). It's unclear to me why this is the case.
+RUN . /appenv/bin/activate; \
+  pip install --upgrade pip \
+  && pip install ocrmypdf
+
+# Now copy the application in, mainly to get the test suite.
+# Do this now to make the best use of Docker cache.
+COPY . /application
+RUN . /appenv/bin/activate; \
+  pip install -r /application/test_requirements.txt
+
+# Remove the junk, including the source version of application since it was
+# already installed
+RUN rm -rf /tmp/* /var/tmp/* /root/* /application/ocrmypdf \
+  && apt-get autoremove -y \
+  && apt-get autoclean -y
+
+RUN useradd docker \
+  && mkdir /home/docker \
+  && chown docker:docker /home/docker
+
+USER docker
+WORKDIR /home/docker
+
+# Must use array form of ENTRYPOINT
+# Non-array form does not append other arguments, because that is "intuitive"
+ENTRYPOINT ["/application/docker-wrapper.sh"]

MANIFEST.in

@@ -14,6 +14,7 @@ include .dockerignore
 # tests
 include pytest.ini
 recursive-include tests *.jpg
+recursive-include tests *.png
 recursive-include tests *.pdf
 recursive-include tests *.py
 recursive-include tests *.rst
@@ -35,7 +36,6 @@ recursive-exclude docs/_build *
 
 # support files
 recursive-include ocrmypdf/data *
-recursive-include share *
 include *.py
 exclude tasks.py
 

README.rst

@@ -35,7 +35,7 @@ Main features
 -  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 `documentation <https://ocrmypdf.readthedocs.io/en/latest/>`_.
 
 Motivation
 ----------
@@ -60,7 +60,17 @@ Installation
 Linux, UNIX, and macOS are supported. Windows is not directly supported but there is a Docker image available that runs on Windows.
 
 Users of Debian 9 or later or Ubuntu 16.10 or later may simply
-``apt-get install ocrmypdf``.
+
+.. code-block:: bash
+
+   apt-get install ocrmypdf
+
+and macOS users may simply
+
+.. code-block:: bash
+
+   brew tap jbarlow83/ocrmypdf
+   brew install ocrmypdf
 
 For everyone else, `see our documentation <https://ocrmypdf.readthedocs.io/en/latest/installation.html>`_ for installation steps.
 

dev_requirements.txt

@@ -1,4 +1,10 @@
-check-manifest>=0.33
-setuptools-scm>=1.11.1
-twine>=1.8.1
-coverage>=4.2
+check-manifest >= 0.34
+twine >= 1.8.1
+coverage >= 4.3.1
+pytest-xdist >= 1.15.0
+GitPython == 2.1.0
+
+# Known good versions: 1.11.1
+# Known broken versions: 1.15.0
+setuptools-scm == 1.11.1
+setuptools-scm-git-archive == 1.0

docs/advanced.rst

@@ -0,0 +1,127 @@
+Advanced features
+=================
+
+Control of OCR options
+----------------------
+
+OCRmyPDF provides many features to control the behavior of the OCR engine, Tesseract.
+
+When OCR is skipped
+"""""""""""""""""""
+
+If a page in a PDF seems to have text, by default OCRmyPDF will exit without modifying the PDF. This is to ensure that PDFs that were previously OCRed or were "born digital" rather than scanned are not processed. 
+
+If ``--skip-text`` is issued, then no OCR will be performed on pages that already have text. The page will be copied to the output. This may be useful for documents that contain both "born digital" and scanned content, or to use OCRmyPDF to normalize and convert to PDF/A regardless of their contents.
+
+If ``--force-ocr`` is issued, then all pages will be rasterized to images, discarding any hidden OCR text, and rasterizing any printable text. This is useful for redoing OCR, for fixing OCR text with a damaged character map (text is selectable but not searchable), and destroying redacted information.
+
+
+Time and image size limits
+""""""""""""""""""""""""""
+
+By default, OCRmyPDF permits tesseract to run for only three minutes (180 seconds) per page. This is usually more than enough time to find all text on a reasonably sized page with modern hardware. 
+
+If a page is skipped, it will be inserted without OCR. If preprocessing was requested, the preprocessed image layer will be inserted.
+
+If you want to adjust the amount of time spent on OCR, change ``--tesseract-timeout``.  You can also automatically skip images that exceed a certain number of megapixels with ``--skip-big``. (A 300 DPI, 8.5×11" page is 8.4 megapixels.)
+
+.. code-block:: bash
+
+	# Allow 300 seconds for OCR; skip any page larger than 50 megapixels
+	ocrmypdf --tesseract-timeout 300 --skip-big 50 bigfile.pdf output.pdf
+
+Overriding default tesseract
+""""""""""""""""""""""""""""
+
+OCRmyPDF checks the environment variable ``OCRMYPDF_TESSERACT`` for the full path *to the tesseract executable* first. 
+
+For example, if you are testing tesseract 4.00 and don't wish to disturb your tesseract 3.04 installation, you can launch OCRmyPDF as follows:
+
+.. code-block:: bash
+
+	env \
+		OCRMYPDF_TESSERACT=/home/user/src/tesseract4/api/tesseract \
+		TESSDATA_PREFIX=/home/user/src/tesseract4 \
+		ocrmypdf --pdf-renderer tess4 --tesseract-oem 2 input.pdf output.pdf
+
+* ``TESSDATA_PREFIX`` directs tesseract 4.0 to use LSTM training data. This is a tesseract environment variable.
+* ``--pdf-renderer tess4`` takes advantage of new tesseract 4.0 PDF renderer in OCRmyPDF. (Tesseract 4.0 only.)
+* ``--tesseract-oem 1`` requests tesseract 4.0's new LSTM engine. (Tesseract 4.0 only.)
+
+Overriding other support programs
+"""""""""""""""""""""""""""""""""
+
+In addition to tesseract, OCRmyPDF uses the following external binaries:
+
+* ``gs`` (Ghostscript)
+* ``unpaper``
+* ``qpdf``
+
+In each case OCRmyPDF will check the environment variable ``OCRMYPDF_{program}`` before asking the system to find ``{program}`` on the PATH. For example, you could redirect OCRmyPDF to ``OCRMYPDF_GS`` to override Ghostscript.
+
+Changing tesseract configuration variables
+""""""""""""""""""""""""""""""""""""""""""
+
+You can override tesseract's default `control parameters <https://github.com/tesseract-ocr/tesseract/wiki/ControlParams>`_ with a configuration file.
+
+As an example, this configuration will disable Tesseract's dictionary for current language. Normally the dictionary is helpful for interpolating words that are unclear, but it may interfere with OCR if the document does not contain many words (for example, a list of part numbers).
+
+Create a file named "no-dict.cfg" with these contents:
+
+::
+
+	load_system_dawg 0
+	language_model_penalty_non_dict_word 0
+	language_model_penalty_non_freq_dict_word 0
+
+then run ocrmypdf as follows (along with any other desired arguments):
+
+.. code-block:: bash
+
+	ocrmypdf --tesseract-config no-dict.cfg input.pdf output.pdf
+
+.. warning::
+
+	Some combinations of control parameters will break Tesseract or break assumptions that OCRmyPDF makes about Tesseract's output.
+
+
+Changing the PDF renderer
+-------------------------
+
+rasterizing
+  Converting a PDF to an image for display.
+
+rendering
+  Creating a new PDF from other data (such as an existing PDF).
+
+
+OCRmyPDF has three PDF renderers: ``hocr``, ``tesseract`` and ``tess4``. The renderer may be selected using ``--pdf-renderer``. The default is ``auto`` which lets OCRmyPDF select the renderer to use. Currently, ``auto`` always selects ``hocr``. 
+
+The ``hocr`` renderer
+"""""""""""""""""""""
+
+The ``hocr`` renderer is the default because it works in most cases. In this mode the whole PDF is rasterized, the raster image is run through OCR to generate a .hocr file, which is an HTML-like file that specifies the location of all identified words.
+
+The .hocr file is then rendered as a PDF and merged with the image layer.
+
+The image layer is copied from the original PDF page if possible, avoiding potentially lossy transcoding or loss of other PDF information. If preprocessing is specified, then the image layer is a new PDF.
+
+This is the only option for tesseract 3.02 and older.
+
+
+The ``tesseract`` renderer
+""""""""""""""""""""""""""
+
+The tesseract renderer uses tesseract's capability to produce a PDF directly. In version 3, tesseract automatically combined the image layer and text, meaning that this mode *always* transcodes and loses potentially loses image quality and other PDF information.
+
+It does a much better job on non-Latin text.
+
+In a future release this will become the "tess3" renderer and ultimately will be dropped.
+
+
+The ``tess4`` renderer
+""""""""""""""""""""""
+
+The tess4 renderer uses tesseract 4.00 alpha's text-only PDF feature added in January 2017. This combines the advantages of the tesseract and hocr renderers, transcoding the image layer only if required by preprocessing options.
+
+Ghostscript PDF/A still sometimes inserts spaces between words when the tess4 renderer is used, affecting search quality.  ``--output-pdf pdf`` may be used to avoid this issue.

docs/batch.rst

@@ -0,0 +1,142 @@
+Batch processing
+================
+
+This article provides information about running OCRmyPDF on multiple files or configuring it as a service triggered by file system events.
+
+Batch jobs
+----------
+
+Consider using the excellent `GNU Parallel <https://www.gnu.org/software/parallel/>`_ to apply OCRmyPDF to multiple files at once.
+
+Both ``parallel`` and ``ocrmypdf`` will try to use all available processors. To maximize parallelism without overloading your system with processes, consider using ``parallel -j 2`` to limit parallel to running two jobs at once.
+
+This command will run all ocrmypdf all files named ``*.pdf`` in the current directory and write them to the previous created ``output/`` folder. It will not search subdirectories.
+
+The ``--tag`` argument tells parallel to print the filename as a prefix whenever a message is printed, so that one can trace any errors to the file that produced them.
+
+.. code-block:: bash
+
+	parallel --tag -j 2 ocrmypdf '{}' 'output/{}' ::: *.pdf
+
+Directory trees
+---------------
+
+This will walk through a directory tree and run OCR on all files in place, printing the output in a way that makes 
+
+.. code-block:: bash
+
+	find . --printf '%p' -name '*.pdf' -exec ocrmypdf '{}' '{}' \;
+
+This only runs one ``ocrmypdf`` process at a time. This variation uses ``find`` to create a directory list and ``parallel`` to parallelize runs of ``ocrmypdf``, again updating files in place.
+
+.. code-block:: bash
+
+	find . -name '*.pdf' | parallel --tag -j 2 ocrmypdf '{}' '{}'
+
+
+Sample script
+"""""""""""""
+
+This user contributed script also provides an example of batch processing.
+
+.. code-block:: python
+
+	#!/usr/bin/env python3
+	# Walk through directory tree, replacing all files with OCR'd version
+	# Contributed by DeliciousPickle@github
+
+	import logging
+	import os
+	import subprocess
+	import sys
+
+	script_dir = os.path.dirname(os.path.realpath(__file__))
+	print(script_dir + '/ocr-tree.py: Start')
+
+	if len(sys.argv) > 1:
+	    start_dir = sys.argv[1]
+	else:
+	    start_dir = '.'
+
+	if len(sys.argv) > 2:
+	    log_file = sys.argv[2]
+	else:
+	    log_file = script_dir + '/ocr-tree.log'
+
+	logging.basicConfig(
+			level=logging.INFO, format='%(asctime)s %(message)s', 
+			filename=log_file, filemode='w')
+
+	for dir_name, subdirs, file_list in os.walk(start_dir):
+	    logging.info('\n')
+	    logging.info(dir_name + '\n')
+	    os.chdir(dir_name)
+	    for filename in file_list:
+	        file_ext = os.path.splitext(filename)[1]
+	        if file_ext == '.pdf':
+	            full_path = dir_name + '/' + filename
+	            print(full_path)
+	            cmd = ["ocrmypdf",  "--deskew", filename, filename]
+	            logging.info(cmd)
+	            proc = subprocess.Popen(
+	            	cmd, stdout=subprocess.PIPE, stderr=subprocess.STDOUT)
+	            result = proc.stdout.read()
+	            if proc.returncode == 6:
+	                print("Skipped document because it already contained text")
+	            elif proc.returncode == 0:
+	                print("OCR complete")
+	            logging.info(result)
+
+API
+"""
+
+OCRmyPDF is currently supported as a command line interface. Due to limitations in one of the libraries OCRmyPDF depends on, it is not yet usable as an API.
+
+
+Huge batch jobs
+"""""""""""""""
+
+If you have thousands of files to work with, contact the author.
+
+
+Hot (watched) folders
+---------------------
+
+To set up a "hot folder" that will trigger OCR for every file inserted, use a program like Python `watchdog <https://pypi.python.org/pypi/watchdog>`_ (supports all major OS).
+
+One could then configure a scanner to automatically place scanned files in a hot folder, so that they will be queued for OCR and copied to the destination.
+
+.. code-block:: bash
+
+	pip install watchdog
+
+watchdog installs the command line program ``watchmedo``, which can be told to run ``ocrmypdf`` on any .pdf added to the current directory (``.``) and place the result in the previously created ``out/`` folder.
+
+.. code-block:: bash
+
+	cd hot-folder
+	mkdir out
+	watchmedo shell-command \
+		--patterns="*.pdf" \
+		--ignore-directories \
+		--command='ocrmypdf "${watch_src_path}" "out/${watch_src_path}" ' \
+		.  # don't forget the final dot
+
+For more complex behavior you can write a Python script around to use the watchdog API.
+
+On file servers, you could configure watchmedo as a system service so it will run all the time.
+
+Caveats
+"""""""
+
+* ``watchmedo`` may not work properly on a networked file system, depending on the capabilities of the file system client and server.
+* This simple recipe does not filter for the type of file system event, so file copies, deletes and moves, and directory operations, will all be sent to ocrmypdf, producing errors in several cases. Disable your watched folder if you are doing anything other than copying files to it.
+* If the source and destination directory are the same, watchmedo may create an infinite loop.
+* On BSD, FreeBSD and older versions of macOS, you may need to increase the number of file descriptors to monitor more files, using ``ulimit -n 1024`` to watch a folder of up to 1024 files.
+
+Alternatives
+""""""""""""
+
+* `Watchman <https://facebook.github.io/watchman/>`_ is a more powerful alternative to ``watchmedo``.
+
+

docs/conf.py

@@ -52,7 +52,7 @@ master_doc = 'index'
 
 # General information about the project.
 project = 'ocrmypdf'
-copyright = '2016, James R. Barlow'
+copyright = '2017, James R. Barlow'
 author = 'James R. Barlow'
 
 # The version info for the project you're documenting, acts as replacement for

docs/cookbook.rst

@@ -62,6 +62,23 @@ By default OCRmyPDF assumes the document is English.
 Language packs must be installed for all languages specified. See :ref:`Installing additional language packs <lang-packs>`.
 
 
+Produce PDF and text file containing OCR text
+"""""""""""""""""""""""""""""""""""""""""""""
+
+This produces a file named "output.pdf" and a companion text file named "output.txt". The ``pdftotext`` program from 
+`Poppler <https://poppler.freedesktop.org/>`_ is used to extract text from the finished PDF.
+
+
+.. code-block:: bash
+
+	ocrmypdf input.pdf - | tee output.pdf | pdftotext - output.txt
+
+.. note::
+
+	To get pdftotext, Debian/Ubuntu users may ``apt-get install poppler-utils`` 
+	and macOS users may ``brew install poppler`` respectively.
+
+
 OCR images, not PDFs
 --------------------
 
@@ -71,7 +88,13 @@ Use a program like `img2pdf <https://gitlab.mister-muffin.de/josch/img2pdf>`_ to
 
 	img2pdf my-images*.jpg | ocrmypdf - myfile.pdf
 
-If given a single image as input, OCRmyPDF will try converting it to a PDF on its own.  This feature may be removed at some point, because OCRmyPDF does not specialize in converting images to PDFs.
+If given a single image as input, OCRmyPDF will try converting it to a PDF on its own.  If the DPI specified in the image is incorrect, it can be overridden with ``--image-dpi``:
+
+.. code-block:: bash
+
+	ocrmypdf --image-dpi 300 image.png myfile.pdf
+
+This feature may be removed at some point, because OCRmyPDF does not specialize in converting images to PDFs.
 
 You can also use Tesseract 3.04+ directly to convert single page images or multi-page TIFFs to PDF:
 
@@ -94,60 +117,28 @@ OCRmyPDF perform some image processing on each page of a PDF, if desired.  The s
 
 * ``--clean-final`` uses unpaper to clean up pages before OCR and inserts the page into the final output.  You will want to review each page to ensure that unpaper did not remove something important.
 
+.. note::
+
+	In many cases image processing will rasterize PDF pages as images, potentially losing quality.
+
+.. warning::
+
+	``--clean-final`` and ``-remove-background`` may leave undesirable visual artifacts in some images where their algorithms have shortcomings. Files should be visually reviewed after using these options.
+
 
 OCR and correct document skew (crooked scan)
 """"""""""""""""""""""""""""""""""""""""""""
 
+Deskew:
+
 .. code-block:: bash
 
 	ocrmypdf --deskew input.pdf output.pdf
 
-
-Hot (watched) folders
----------------------
-
-To set up a "hot folder" that will trigger an OCR operation for every file inserted, use a program like Python `watchdog <https://pypi.python.org/pypi/watchdog>`_ (supports all major OS).
+Image processing commands can be combined. The order in which options are given does not matter. OCRmyPDF always applies the steps of the image processing pipeline in the same order (rotate, remove background, deskew, clean).
 
 .. code-block:: bash
 
-	pip install watchdog
-
-watchdog installs the command line program ``watchmedo``, which can be told to run ``ocrmypdf`` on any .pdf added to the current directory (``.``) and place the result in the previously created ``out/`` folder.
-
-.. code-block:: bash
-
-	cd hot-folder
-	mkdir out
-	watchmedo shell-command \
-		--patterns="*.pdf" \
-		--ignore-directories \
-		--command='ocrmypdf "${watch_src_path}" "out/${watch_src_path}" ' \
-		.  # don't forget the final dot
-
-For more complex behavior you can write a Python script around to use the watchdog API.
-
-On file servers, you could configure watchmedo as a system service so it will run all the time.
-
-Caveats
-"""""""
-
-* ``watchmedo`` may not work properly on a networked file system, depending on the capabilities of the file system client and server.
-* This simple recipe does not filter for the type of file system event, so file copies, deletes and moves, and directory operations, will all be sent to ocrmypdf, producing errors in several cases. Disable your watched folder if you are doing anything other than copying files to it.
-* If the source and destination directory are the same, watchmedo may create an infinite loop.
+	ocrmypdf --deskew --clean --rotate-pages input.pdf output.pdf
 
 
-Batch jobs
-----------
-
-Consider using the excellent `GNU Parallel <https://www.gnu.org/software/parallel/>`_ to apply OCRmyPDF to multiple files at once.
-
-Both ``parallel`` and ``ocrmypdf`` will try to use all available processors. To maximize parallelism without overloading your system with processes, consider using ``parallel -j 2`` to limit parallel to running two jobs at once.
-
-This command will run all ocrmypdf all files named ``*.pdf`` in the current directory and write them to the previous created ``output/`` folder.
-
-.. code-block:: bash
-
-	parallel -j 2 ocrmypdf '{}' 'output/{}' ::: *.pdf
-
-If you have thousands of files to work with, contact the author.
- 

docs/index.rst

@@ -11,20 +11,25 @@ be searched.
 
 PDFs are the best format for scanned documents.  Unfortunately, PDFs can be difficult to work with. OCRmyPDF makes it easy to apply image processing and OCR to existing PDFs.
 
-Contents:
-
 .. toctree::
-   :maxdepth: 2
+   :maxdepth: 1
 
    introduction
+   release_notes
    installation
    languages
+
+.. toctree::
+   :caption: Usage
+   :maxdepth: 2
+
    cookbook
+   advanced
+   batch
    security
    errors
 
 
-
 Indices and tables
 ==================
 

docs/installation.rst

@@ -10,6 +10,18 @@ Users of Debian 9 ("stretch") or later or Ubuntu 16.10 or later may simply
 
 	apt-get install ocrmypdf
 
+
+Installing on macOS
+-------------------
+
+.. code-block:: bash
+
+   brew tap jbarlow83/ocrmypdf
+   brew install ocrmypdf
+
+
+Users who previously installed OCRmyPDF on macOS may need to remove the ``pip`` based installation (``pip3 uninstall ocrmypdf``).
+
 .. _Docker:
 
 Installing the Docker image
@@ -27,7 +39,7 @@ successfully, your system is ready to download and execute the image:
 
    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 macOS 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
 
@@ -37,28 +49,34 @@ OCRmyPDF will use all available CPU cores.  By default, the VirtualBox machine i
    docker-machine start "yourVM"
    eval $(docker-machine env "yourVM")
 
-Assuming you have a Docker engine running somewhere, you can run these commands to download
-the image:
+Assuming you have a Docker engine running, you can download one of the three available images:
+
++-----------------------------+---------------------------------------------+---------------------------------------------------------------------------------+
+| Image name                  | Download command                            | Notes                                                                           |
++-----------------------------+---------------------------------------------+---------------------------------------------------------------------------------+
+| ocrmypdf                    | ``docker pull jbarlow83/ocrmypdf``          | Latest ocrmypdf with Tesseract 3.04. Includes English, French, German, Spanish. |
++-----------------------------+---------------------------------------------+---------------------------------------------------------------------------------+
+| ocrmypdf-polyglot           | ``docker pull jbarlow83/ocrmypdf-polyglot`` | As above, with all available language packs.                                    |
++-----------------------------+---------------------------------------------+---------------------------------------------------------------------------------+
+| ocrmypdf-tess4              | ``docker pull jbarlow83/ocrmypdf-tess4``    | Latest ocrmypdf with Tesseract 4.00.00alpha and English, French, German,        |
+|                             |                                             | Spanish, Portuguese, Chinese Simplified, Arabic and Russian (the top 8).        |
++-----------------------------+---------------------------------------------+---------------------------------------------------------------------------------+
+
+For example:
 
 .. code-block:: bash
 
-   docker pull jbarlow83/ocrmypdf
+   docker pull jbarlow83/ocrmypdf-tess4
 
 Then tag it to give a more convenient name, just ocrmypdf:
 
 .. code-block:: bash
 
-   docker tag jbarlow83/ocrmypdf ocrmypdf
+   docker tag jbarlow83/ocrmypdf-tess4 ocrmypdf
 
 .. _docker-polyglot:
 
-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
+The alternative "polyglot" image provides `all available language packs <https://github.com/tesseract-ocr/tesseract/blob/master/doc/tesseract.1.asc#languages>`_.
 
 You can then run ocrmypdf using the command:
 
@@ -78,13 +96,29 @@ In this worked example, the current working directory contains an input file cal
 
    docker run --rm -v "$(pwd):/home/docker"   ocrmypdf --skip-text test.pdf output.pdf
 
+.. note:: The working directory should be a writable local volume or Docker may not have permission to access it.
+
 Note that ``ocrmypdf`` has its own separate ``-v VERBOSITYLEVEL`` argument to control debug verbosity. All Docker arguments should before the ``ocrmypdf`` image name and all arguments to ``ocrmypdf`` should be listed after.
 
+For convenience, a shell alias can hide the docker command:
 
-Installing on macOS (formerly Mac OS X)
----------------------------------------
+.. code-block:: bash
 
-These instructions probably work on all macOS supported by Homebrew. OCRmyPDF is known to work on Yosemite and El Capitan, and regularly tested on El Capitan.
+   alias ocrmypdf='docker run --rm -v "$(pwd):/home/docker" ocrmypdf' 
+   ocrmypdf --version  # runs docker version
+
+Or in the wonderful `fish shell <https://fishshell.com/>`_:
+
+.. code-block:: fish
+
+   alias ocrmypdf 'docker run --rm -v (pwd):/home/docker ocrmypdf'
+   funcsave ocrmypdf
+
+
+Manual installation on macOS
+----------------------------
+
+These instructions probably work on all macOS supported by Homebrew.
 
 If it's not already present, `install Homebrew <http://brew.sh/>`_.
 
@@ -105,6 +139,8 @@ Install or upgrade the required Homebrew packages, if any are missing:
    brew install libxml2 libffi leptonica
    brew install unpaper   # optional
    
+Python 3.4, 3.5 and 3.6 are supported.
+
 Install the required Tesseract OCR engine with the language packs you plan to use:
    
 .. code-block:: bash
@@ -136,6 +172,40 @@ The command line program should now be available:
 
    ocrmypdf --help
 
+
+Installing on Ubuntu 16.04 LTS
+------------------------------
+
+No package is currently available for Ubuntu 16.04, but you can install the dependencies manually:
+
+.. code-block:: bash
+
+   sudo apt-get update
+   sudo apt-get install \
+      unpaper \
+      ghostscript \
+      tesseract-ocr \
+      qpdf \
+      python3-pip \
+      python3-cffi
+
+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):
+
+.. code-block:: bash
+
+   sudo pip3 install ocrmypdf
+
+If you wish to install OCRmyPDF to a virtual environment to isolate the system Python, you can
+follow these steps.
+
+.. code-block:: bash
+
+   python3 -m venv venv-ocrmypdf
+   source venv-ocrmypdf/bin/activate
+   pip3 install ocrmypdf
+
+
 Installing on Ubuntu 14.04 LTS
 ------------------------------
 
@@ -153,7 +223,6 @@ Update apt-get:
 .. code-block:: bash
 
    sudo apt-get update
-   sudo apt-get upgrade
    
 Install system dependencies:
 
@@ -221,7 +290,7 @@ where /c/Users/sampleuser is a Unix representation of the Windows path C:\\Users
 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,
+If you have ``git`` and Python 3.4 or newer 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:

docs/introduction.rst

@@ -53,6 +53,20 @@ By default, OCRmyPDF will convert the file to a PDF/A.  This behavior can be dis
 Depending on the settings selected, OCRmyPDF may "graft" the OCR layer into the existing PDF, or reconstruct a visually equivalent new PDF.
 
 
+Why you shouldn't do this manually
+----------------------------------
+
+There are two routes to manually applying OCR to an existing PDF, both of which destroy information in the original PDF.
+
+1. Rasterize each page as an image, OCR the images, and combine the output into a PDF. This preserves the appearance of each page, but resamples all images (possibly losing quality, increasing file size, introducing compression artifacts, etc.)
+
+2. Extract each image, OCR, and combine the output into a PDF. This loses the context in which images are used in the PDF, meaning that cropping, rotation and scaling of pages may be lost. Some PDFs use multiple images per page with stencil masks, which would quite difficult to reassemble correctly. This also loses and text or vector art on any pages in a PDF with both scanned and pure digital content.
+
+In the case of a PDF that is nothing other than a container of images (no rotation, scaling, cropping, one image per page), the second approach is can be lossless.
+
+OCRmyPDF uses several strategies depending on input options and the input PDF itself, but generally speaking it rasterizes a page for OCR and then grafts the OCR back onto the original. As such it can handle complex PDFs and still preserve their contents as much as possible.
+
+
 Limitations
 -----------
 
@@ -73,4 +87,15 @@ Ghostscript also imposes some limitations:
 
 * PDFs containing JBIG2-encoded content will be converted to CCITT Group4 encoding, which has lower compression ratios, if Ghostscript PDF/A is enabled.
   
-OCRmyPDF is currently not designed to be used as a Python API; it is designed to be run as a command line tool. ``import ocrmypf`` currently attempts to process the command line on ``sys.argv`` at import time so it has side effects that will interfere with its use as a package. The API it presents should not be considered stable.
+OCRmyPDF is currently not designed to be used as a Python API; it is designed to be run as a command line tool. ``import ocrmypf`` currently attempts to process the command line on ``sys.argv`` at import time so it has side effects that will interfere with its use as a package. The API it presents should not be considered stable.
+
+
+Similar programs
+----------------
+
+To the author's knowledge, OCRmyPDF is the most feature-rich and thoroughly tested command line OCR PDF conversion tool. If it doesn't meet your needs, consider of these similar open source programs:
+
+* pdf2pdfocr
+* pdfsandwich
+* pypdfocr
+* pdfbeads

docs/languages.rst

@@ -23,8 +23,8 @@ Debian and Ubuntu users
 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 using either ``-l eng+fre`` (English and French) or ``-l eng -l fre``.
 
-Mac OS X (macOS) users
-----------------------
+macOS users
+-----------
 
 You can install additional language packs by :ref:`installing Tesseract using Homebrew with all language packs <macos-all-languages>`.
 

docs/pipeline.svg

@@ -0,0 +1,392 @@
+<?xml version="1.0" encoding="UTF-8" standalone="no"?>
+<!DOCTYPE svg PUBLIC "-//W3C//DTD SVG 1.1//EN"
+ "http://www.w3.org/Graphics/SVG/1.1/DTD/svg11.dtd">
+<!-- Generated by graphviz version 2.38.0 (20140413.2041)
+ -->
+<!-- Title: Pipeline: Pages: 1 -->
+<svg width="1544pt" height="1089pt"
+ viewBox="0.00 0.00 1544.00 1089.14" 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 1085.14)">
+<title>Pipeline:</title>
+<polygon fill="white" stroke="none" points="-4,4 -4,-1085.14 1540,-1085.14 1540,4 -4,4"/>
+<g id="clust1" class="cluster"><title>clustertasks</title>
+<polygon fill="none" stroke="black" points="8,-8 8,-1073.14 1528,-1073.14 1528,-8 8,-8"/>
+<text text-anchor="middle" x="768" y="-1045.14" 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="750.705,-1027.14 541.295,-1027.14 537.295,-1023.14 537.295,-991.141 746.705,-991.141 750.705,-995.141 750.705,-1027.14"/>
+<polyline fill="none" stroke="black" points="746.705,-1023.14 537.295,-1023.14 "/>
+<polyline fill="none" stroke="black" points="746.705,-1023.14 746.705,-991.141 "/>
+<polyline fill="none" stroke="black" points="746.705,-1023.14 750.705,-1027.14 "/>
+<text text-anchor="middle" x="644" y="-1003.14" font-family="Times,serif" font-size="20.00">ocrmypdf.pipeline.triage</text>
+</g>
+<!-- t1 -->
+<g id="node2" class="node"><title>t1</title>
+<polygon fill="#efa03b" stroke="black" points="769.969,-969.141 522.031,-969.141 518.031,-965.141 518.031,-933.141 765.969,-933.141 769.969,-937.141 769.969,-969.141"/>
+<polyline fill="none" stroke="black" points="765.969,-965.141 518.031,-965.141 "/>
+<polyline fill="none" stroke="black" points="765.969,-965.141 765.969,-933.141 "/>
+<polyline fill="none" stroke="black" points="765.969,-965.141 769.969,-969.141 "/>
+<text text-anchor="middle" x="644" y="-945.141" font-family="Times,serif" font-size="20.00">ocrmypdf.pipeline.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="M644,-991.035C644,-987.344 644,-983.354 644,-979.384"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="647.5,-979.142 644,-969.142 640.5,-979.142 647.5,-979.142"/>
+</g>
+<!-- t2 -->
+<g id="node3" class="node"><title>t2</title>
+<polygon fill="#efa03b" stroke="black" points="869.82,-890.215 644,-907.116 418.18,-890.215 418.391,-862.869 869.609,-862.869 869.82,-890.215"/>
+<polygon fill="none" stroke="black" points="873.852,-893.922 644,-911.125 414.148,-893.922 414.419,-858.871 873.581,-858.871 873.852,-893.922"/>
+<text text-anchor="middle" x="644" y="-876.657" font-family="Times,serif" font-size="20.00">ocrmypdf.pipeline.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="M644,-933.019C644,-929.4 644,-925.445 644,-921.399"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="647.5,-921.295 644,-911.295 640.5,-921.295 647.5,-921.295"/>
+</g>
+<!-- t18 -->
+<g id="node20" class="node"><title>t18</title>
+<polygon fill="#efa03b" stroke="black" points="383.516,-832.173 20.4844,-832.173 16.4844,-828.173 16.4844,-796.173 379.516,-796.173 383.516,-800.173 383.516,-832.173"/>
+<polyline fill="none" stroke="black" points="379.516,-828.173 16.4844,-828.173 "/>
+<polyline fill="none" stroke="black" points="379.516,-828.173 379.516,-796.173 "/>
+<polyline fill="none" stroke="black" points="379.516,-828.173 383.516,-832.173 "/>
+<text text-anchor="middle" x="200" y="-808.173" font-family="Times,serif" font-size="20.00">ocrmypdf.pipeline.generate_postscript_stub</text>
+</g>
+<!-- t1&#45;&gt;t18 -->
+<g id="edge29" class="edge"><title>t1&#45;&gt;t18</title>
+<path fill="none" stroke="#0044a0" d="M518.14,-936.259C481.198,-930.408 441.05,-922.284 405,-911.141 344.394,-892.407 278.709,-859.14 238.448,-837.118"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="239.963,-833.956 229.517,-832.188 236.581,-840.085 239.963,-833.956"/>
+</g>
+<!-- t21 -->
+<g id="node22" class="node"><title>t21</title>
+<polygon fill="#efa03b" stroke="black" points="751.49,-156.424 963,-129.109 1174.51,-156.424 1174.31,-200.62 751.688,-200.62 751.49,-156.424"/>
+<polygon fill="none" stroke="black" points="747.474,-152.906 963,-125.073 1178.53,-152.906 1178.29,-204.623 747.705,-204.623 747.474,-152.906"/>
+<text text-anchor="middle" x="963" y="-162.639" font-family="Times,serif" font-size="20.00">ocrmypdf.pipeline.merge_pages_qpdf</text>
+</g>
+<!-- t1&#45;&gt;t21 -->
+<g id="edge39" class="edge"><title>t1&#45;&gt;t21</title>
+<path fill="none" stroke="#0044a0" d="M769.832,-943.539C1011.96,-929.143 1519,-890.056 1519,-815.173 1519,-815.173 1519,-815.173 1519,-309.173 1519,-237.474 1342.87,-202.283 1188.87,-185.216"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="1189.08,-181.719 1178.76,-184.118 1188.32,-188.678 1189.08,-181.719"/>
+</g>
+<!-- t3 -->
+<g id="node4" class="node"><title>t3</title>
+<polygon fill="#efa03b" stroke="black" points="712.317,-832.173 405.683,-832.173 401.683,-828.173 401.683,-796.173 708.317,-796.173 712.317,-800.173 712.317,-832.173"/>
+<polyline fill="none" stroke="black" points="708.317,-828.173 401.683,-828.173 "/>
+<polyline fill="none" stroke="black" points="708.317,-828.173 708.317,-796.173 "/>
+<polyline fill="none" stroke="black" points="708.317,-828.173 712.317,-832.173 "/>
+<text text-anchor="middle" x="557" y="-808.173" font-family="Times,serif" font-size="20.00">ocrmypdf.pipeline.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="M614.06,-858.777C605.418,-852.173 595.983,-844.963 587.319,-838.342"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="589.37,-835.504 579.299,-832.213 585.119,-841.066 589.37,-835.504"/>
+</g>
+<!-- t4 -->
+<g id="node5" class="node"><title>t4</title>
+<polygon fill="#efa03b" stroke="black" points="688.082,-774.173 429.918,-774.173 425.918,-770.173 425.918,-738.173 684.082,-738.173 688.082,-742.173 688.082,-774.173"/>
+<polyline fill="none" stroke="black" points="684.082,-770.173 425.918,-770.173 "/>
+<polyline fill="none" stroke="black" points="684.082,-770.173 684.082,-738.173 "/>
+<polyline fill="none" stroke="black" points="684.082,-770.173 688.082,-774.173 "/>
+<text text-anchor="middle" x="557" y="-750.173" font-family="Times,serif" font-size="20.00">ocrmypdf.pipeline.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="M695.691,-858.661C705.833,-851.667 715.136,-842.912 721,-832.173 728.668,-818.13 730.919,-808.727 721,-796.173 714.915,-788.471 700.759,-782.127 683.18,-776.959"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="683.659,-773.462 673.091,-774.208 681.817,-780.216 683.659,-773.462"/>
+</g>
+<!-- t3&#45;&gt;t4 -->
+<g id="edge4" class="edge"><title>t3&#45;&gt;t4</title>
+<path fill="none" stroke="#0044a0" d="M557,-796.066C557,-792.375 557,-788.385 557,-784.415"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="560.5,-784.174 557,-774.174 553.5,-784.174 560.5,-784.174"/>
+</g>
+<!-- t5 -->
+<g id="node6" class="node"><title>t5</title>
+<polygon fill="#efa03b" stroke="black" points="1064.73,-716.173 689.268,-716.173 685.268,-712.173 685.268,-680.173 1060.73,-680.173 1064.73,-684.173 1064.73,-716.173"/>
+<polyline fill="none" stroke="black" points="1060.73,-712.173 685.268,-712.173 "/>
+<polyline fill="none" stroke="black" points="1060.73,-712.173 1060.73,-680.173 "/>
+<polyline fill="none" stroke="black" points="1060.73,-712.173 1064.73,-716.173 "/>
+<text text-anchor="middle" x="875" y="-692.173" font-family="Times,serif" font-size="20.00">ocrmypdf.pipeline.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="M653.706,-738.143C689.783,-731.789 730.943,-724.541 767.902,-718.033"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="768.965,-721.399 778.206,-716.218 767.751,-714.505 768.965,-721.399"/>
+</g>
+<!-- t15 -->
+<g id="node13" class="node"><title>t15</title>
+<polygon fill="#ff69b4" stroke="black" points="440.27,-396.173 59.7304,-396.173 55.7304,-392.173 55.7304,-360.173 436.27,-360.173 440.27,-364.173 440.27,-396.173"/>
+<polyline fill="none" stroke="black" points="436.27,-392.173 55.7304,-392.173 "/>
+<polyline fill="none" stroke="black" points="436.27,-392.173 436.27,-360.173 "/>
+<polyline fill="none" stroke="black" points="436.27,-392.173 440.27,-396.173 "/>
+<text text-anchor="middle" x="248" y="-372.173" font-family="Times,serif" font-size="20.00">ocrmypdf.pipeline.ocr_tesseract_textonly_pdf</text>
+</g>
+<!-- t4&#45;&gt;t15 -->
+<g id="edge14" class="edge"><title>t4&#45;&gt;t15</title>
+<path fill="none" stroke="#0044a0" d="M425.857,-745.263C361.241,-732.425 297,-703.891 297,-641.173 297,-641.173 297,-641.173 297,-523.173 297,-480.18 277.182,-433.63 262.754,-405.436"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="265.677,-403.477 257.916,-396.265 259.486,-406.743 265.677,-403.477"/>
+</g>
+<!-- t12 -->
+<g id="node15" class="node"><title>t12</title>
+<polygon fill="#00cc66" stroke="black" points="781,-406.173 458.414,-378.173 781,-350.173 1103.59,-378.173 781,-406.173"/>
+<text text-anchor="middle" x="781" y="-372.173" font-family="Times,serif" font-size="20.00">ocrmypdf.pipeline.select_image_layer</text>
+</g>
+<!-- t4&#45;&gt;t12 -->
+<g id="edge20" class="edge"><title>t4&#45;&gt;t12</title>
+<path fill="none" stroke="#0044a0" d="M471.449,-738.167C421.018,-722.605 367,-693.681 367,-641.173 367,-641.173 367,-641.173 367,-523.173 367,-480.717 347.218,-458.43 377,-428.173 392.917,-412.001 494.592,-399.721 591.948,-391.499"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="592.284,-394.983 601.96,-390.666 591.704,-388.007 592.284,-394.983"/>
+</g>
+<!-- t19 -->
+<g id="node18" class="node"><title>t19</title>
+<polygon fill="#efa03b" stroke="black" points="323.772,-270.173 78.2284,-270.173 74.2284,-266.173 74.2284,-234.173 319.772,-234.173 323.772,-238.173 323.772,-270.173"/>
+<polyline fill="none" stroke="black" points="319.772,-266.173 74.2284,-266.173 "/>
+<polyline fill="none" stroke="black" points="319.772,-266.173 319.772,-234.173 "/>
+<polyline fill="none" stroke="black" points="319.772,-266.173 323.772,-270.173 "/>
+<text text-anchor="middle" x="199" y="-246.173" font-family="Times,serif" font-size="20.00">ocrmypdf.pipeline.skip_page</text>
+</g>
+<!-- t4&#45;&gt;t19 -->
+<g id="edge26" class="edge"><title>t4&#45;&gt;t19</title>
+<path fill="none" stroke="#0044a0" d="M425.782,-752.078C271.736,-744.795 37,-720.655 37,-641.173 37,-641.173 37,-641.173 37,-377.173 37,-325.92 88.7624,-292.989 133.769,-274.043"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="135.289,-277.203 143.249,-270.211 132.666,-270.713 135.289,-277.203"/>
+</g>
+<!-- t17 -->
+<g id="node19" class="node"><title>t17</title>
+<polygon fill="#66ccff" stroke="black" points="1499.67,-328.173 1094.33,-328.173 1090.33,-324.173 1090.33,-292.173 1495.67,-292.173 1499.67,-296.173 1499.67,-328.173"/>
+<polyline fill="none" stroke="black" points="1495.67,-324.173 1090.33,-324.173 "/>
+<polyline fill="none" stroke="black" points="1495.67,-324.173 1495.67,-292.173 "/>
+<polyline fill="none" stroke="black" points="1495.67,-324.173 1499.67,-328.173 "/>
+<text text-anchor="middle" x="1295" y="-304.173" font-family="Times,serif" font-size="20.00">ocrmypdf.pipeline.ocr_tesseract_and_render_pdf</text>
+</g>
+<!-- t4&#45;&gt;t17 -->
+<g id="edge28" class="edge"><title>t4&#45;&gt;t17</title>
+<path fill="none" stroke="#0044a0" d="M688.477,-752.611C947.521,-745.804 1499,-721.841 1499,-641.173 1499,-641.173 1499,-641.173 1499,-455.173 1499,-407.201 1508.25,-383.766 1474,-350.173 1465.98,-342.302 1448.74,-335.804 1427.99,-330.522"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="1428.77,-327.11 1418.23,-328.18 1427.14,-333.917 1428.77,-327.11"/>
+</g>
+<!-- t6 -->
+<g id="node7" class="node"><title>t6</title>
+<polygon fill="#efa03b" stroke="black" points="1089.08,-658.173 664.92,-658.173 660.92,-654.173 660.92,-622.173 1085.08,-622.173 1089.08,-626.173 1089.08,-658.173"/>
+<polyline fill="none" stroke="black" points="1085.08,-654.173 660.92,-654.173 "/>
+<polyline fill="none" stroke="black" points="1085.08,-654.173 1085.08,-622.173 "/>
+<polyline fill="none" stroke="black" points="1085.08,-654.173 1089.08,-658.173 "/>
+<text text-anchor="middle" x="875" y="-634.173" font-family="Times,serif" font-size="20.00">ocrmypdf.pipeline.preprocess_remove_background</text>
+</g>
+<!-- t5&#45;&gt;t6 -->
+<g id="edge7" class="edge"><title>t5&#45;&gt;t6</title>
+<path fill="none" stroke="#0044a0" d="M875,-680.066C875,-676.375 875,-672.385 875,-668.415"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="878.5,-668.174 875,-658.174 871.5,-668.174 878.5,-668.174"/>
+</g>
+<!-- t11 -->
+<g id="node14" class="node"><title>t11</title>
+<polygon fill="#efa03b" stroke="black" points="1096,-484.173 712.187,-456.173 1096,-428.173 1479.81,-456.173 1096,-484.173"/>
+<text text-anchor="middle" x="1096" y="-450.173" font-family="Times,serif" font-size="20.00">ocrmypdf.pipeline.select_visible_page_image</text>
+</g>
+<!-- t5&#45;&gt;t11 -->
+<g id="edge18" class="edge"><title>t5&#45;&gt;t11</title>
+<path fill="none" stroke="#0044a0" d="M1051.07,-680.0px8C1072.76,-674.712 1090.1,-667.576 1098,-658.173 1136.53,-612.317 1122.5,-537.602 1109.06,-493.335"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="1112.33,-492.043 1105.96,-483.573 1105.65,-494.164 1112.33,-492.043"/>
+</g>
+<!-- t7 -->
+<g id="node8" class="node"><title>t7</title>
+<polygon fill="#efa03b" stroke="black" points="1039.68,-600.173 720.324,-600.173 716.324,-596.173 716.324,-564.173 1035.68,-564.173 1039.68,-568.173 1039.68,-600.173"/>
+<polyline fill="none" stroke="black" points="1035.68,-596.173 716.324,-596.173 "/>
+<polyline fill="none" stroke="black" points="1035.68,-596.173 1035.68,-564.173 "/>
+<polyline fill="none" stroke="black" points="1035.68,-596.173 1039.68,-600.173 "/>
+<text text-anchor="middle" x="878" y="-576.173" font-family="Times,serif" font-size="20.00">ocrmypdf.pipeline.preprocess_deskew</text>
+</g>
+<!-- t6&#45;&gt;t7 -->
+<g id="edge8" class="edge"><title>t6&#45;&gt;t7</title>
+<path fill="none" stroke="#0044a0" d="M875.916,-622.066C876.114,-618.375 876.328,-614.385 876.541,-610.415"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="880.049,-610.347 877.089,-600.174 873.059,-609.972 880.049,-610.347"/>
+</g>
+<!-- t6&#45;&gt;t11 -->
+<g id="edge17" class="edge"><title>t6&#45;&gt;t11</title>
+<path fill="none" stroke="#0044a0" d="M990.695,-622.152C1016.54,-616.369 1039.2,-609.066 1049,-600.173 1078.78,-573.156 1089.74,-526.964 1093.74,-494.403"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="1097.24,-494.666 1094.82,-484.351 1090.28,-493.924 1097.24,-494.666"/>
+</g>
+<!-- t8 -->
+<g id="node9" class="node"><title>t8</title>
+<polygon fill="#efa03b" stroke="black" points="1030.88,-542.173 729.117,-542.173 725.117,-538.173 725.117,-506.173 1026.88,-506.173 1030.88,-510.173 1030.88,-542.173"/>
+<polyline fill="none" stroke="black" points="1026.88,-538.173 725.117,-538.173 "/>
+<polyline fill="none" stroke="black" points="1026.88,-538.173 1026.88,-506.173 "/>
+<polyline fill="none" stroke="black" points="1026.88,-538.173 1030.88,-542.173 "/>
+<text text-anchor="middle" x="878" y="-518.173" font-family="Times,serif" font-size="20.00">ocrmypdf.pipeline.preprocess_clean</text>
+</g>
+<!-- t7&#45;&gt;t8 -->
+<g id="edge9" class="edge"><title>t7&#45;&gt;t8</title>
+<path fill="none" stroke="#0044a0" d="M878,-564.066C878,-560.375 878,-556.385 878,-552.415"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="881.5,-552.174 878,-542.174 874.5,-552.174 881.5,-552.174"/>
+</g>
+<!-- t7&#45;&gt;t11 -->
+<g id="edge16" class="edge"><title>t7&#45;&gt;t11</title>
+<path fill="none" stroke="#0044a0" d="M995.441,-564.147C1011.26,-558.713 1026.62,-551.566 1040,-542.173 1057.45,-529.919 1070.89,-510.334 1080.22,-493.051"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="1083.55,-494.243 1084.99,-483.747 1077.31,-491.053 1083.55,-494.243"/>
+</g>
+<!-- t9 -->
+<g id="node10" class="node"><title>t9</title>
+<polygon fill="#efa03b" stroke="black" points="694.109,-474.173 389.891,-474.173 385.891,-470.173 385.891,-438.173 690.109,-438.173 694.109,-442.173 694.109,-474.173"/>
+<polyline fill="none" stroke="black" points="690.109,-470.173 385.891,-470.173 "/>
+<polyline fill="none" stroke="black" points="690.109,-470.173 690.109,-438.173 "/>
+<polyline fill="none" stroke="black" points="690.109,-470.173 694.109,-474.173 "/>
+<text text-anchor="middle" x="540" y="-450.173" font-family="Times,serif" font-size="20.00">ocrmypdf.pipeline.select_ocr_image</text>
+</g>
+<!-- t8&#45;&gt;t9 -->
+<g id="edge10" class="edge"><title>t8&#45;&gt;t9</title>
+<path fill="none" stroke="#0044a0" d="M790.517,-506.09C743.487,-496.907 685.383,-485.561 636.976,-476.109"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="637.602,-472.665 627.116,-474.183 636.26,-479.535 637.602,-472.665"/>
+</g>
+<!-- t8&#45;&gt;t11 -->
+<g id="edge15" class="edge"><title>t8&#45;&gt;t11</title>
+<path fill="none" stroke="#0044a0" d="M934.424,-506.09C958.693,-498.742 987.536,-490.01 1014.09,-481.971"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="1015.2,-485.293 1023.75,-479.045 1013.17,-478.593 1015.2,-485.293"/>
+</g>
+<!-- t10 -->
+<g id="node11" class="node"><title>t10</title>
+<polygon fill="#00cc66" stroke="black" points="1440.1,-396.173 1125.9,-396.173 1121.9,-392.173 1121.9,-360.173 1436.1,-360.173 1440.1,-364.173 1440.1,-396.173"/>
+<polyline fill="none" stroke="black" points="1436.1,-392.173 1121.9,-392.173 "/>
+<polyline fill="none" stroke="black" points="1436.1,-392.173 1436.1,-360.173 "/>
+<polyline fill="none" stroke="black" points="1436.1,-392.173 1440.1,-396.173 "/>
+<text text-anchor="middle" x="1281" y="-372.173" font-family="Times,serif" font-size="20.00">ocrmypdf.pipeline.ocr_tesseract_hocr</text>
+</g>
+<!-- t9&#45;&gt;t10 -->
+<g id="edge11" class="edge"><title>t9&#45;&gt;t10</title>
+<path fill="none" stroke="#0044a0" d="M631.992,-438.111C655.104,-434.327 679.903,-430.697 703,-428.173 884.404,-408.343 931.549,-425.567 1113,-406.173 1133.45,-403.987 1155.2,-400.994 1176.03,-397.794"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="1176.83,-401.211 1186.17,-396.209 1175.75,-394.295 1176.83,-401.211"/>
+</g>
+<!-- t9&#45;&gt;t15 -->
+<g id="edge13" class="edge"><title>t9&#45;&gt;t15</title>
+<path fill="none" stroke="#0044a0" d="M474.47,-438.117C429.651,-426.452 370.0px1,-410.957 323.342,-398.782"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="324.123,-395.369 313.564,-396.237 322.36,-402.143 324.123,-395.369"/>
+</g>
+<!-- t13 -->
+<g id="node12" class="node"><title>t13</title>
+<polygon fill="#00cc66" stroke="black" points="683.043,-328.173 374.957,-328.173 370.957,-324.173 370.957,-292.173 679.043,-292.173 683.043,-296.173 683.043,-328.173"/>
+<polyline fill="none" stroke="black" points="679.043,-324.173 370.957,-324.173 "/>
+<polyline fill="none" stroke="black" points="679.043,-324.173 679.043,-292.173 "/>
+<polyline fill="none" stroke="black" points="679.043,-324.173 683.043,-328.173 "/>
+<text text-anchor="middle" x="527" y="-304.173" font-family="Times,serif" font-size="20.00">ocrmypdf.pipeline.render_hocr_page</text>
+</g>
+<!-- t10&#45;&gt;t13 -->
+<g id="edge12" class="edge"><title>t10&#45;&gt;t13</title>
+<path fill="none" stroke="#0044a0" d="M1186.17,-360.113C1162.35,-356.33 1136.79,-352.699 1113,-350.173 929.956,-330.738 880.531,-342.246 693.485,-328.255"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="693.548,-324.75 683.311,-327.48 693.016,-331.73 693.548,-324.75"/>
+</g>
+<!-- t14 -->
+<g id="node17" class="node"><title>t14</title>
+<polygon fill="#00cc66" stroke="black" points="1072.92,-328.173 705.08,-328.173 701.08,-324.173 701.08,-292.173 1068.92,-292.173 1072.92,-296.173 1072.92,-328.173"/>
+<polyline fill="none" stroke="black" points="1068.92,-324.173 701.08,-324.173 "/>
+<polyline fill="none" stroke="black" points="1068.92,-324.173 1068.92,-292.173 "/>
+<polyline fill="none" stroke="black" points="1068.92,-324.173 1072.92,-328.173 "/>
+<text text-anchor="middle" x="887" y="-304.173" font-family="Times,serif" font-size="20.00">ocrmypdf.pipeline.render_hocr_debug_page</text>
+</g>
+<!-- t10&#45;&gt;t14 -->
+<g id="edge25" class="edge"><title>t10&#45;&gt;t14</title>
+<path fill="none" stroke="#0044a0" d="M1179.28,-360.133C1124,-350.873 1055.54,-339.405 998.77,-329.896"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="999.118,-326.405 988.677,-328.205 997.962,-333.309 999.118,-326.405"/>
+</g>
+<!-- t16 -->
+<g id="node16" class="node"><title>t16</title>
+<polygon fill="#00cc66" stroke="black" points="636.299,-270.173 345.701,-270.173 341.701,-266.173 341.701,-234.173 632.299,-234.173 636.299,-238.173 636.299,-270.173"/>
+<polyline fill="none" stroke="black" points="632.299,-266.173 341.701,-266.173 "/>
+<polyline fill="none" stroke="black" points="632.299,-266.173 632.299,-234.173 "/>
+<polyline fill="none" stroke="black" points="632.299,-266.173 636.299,-270.173 "/>
+<text text-anchor="middle" x="489" y="-246.173" font-family="Times,serif" font-size="20.00">ocrmypdf.pipeline.combine_layers</text>
+</g>
+<!-- t13&#45;&gt;t16 -->
+<g id="edge22" class="edge"><title>t13&#45;&gt;t16</title>
+<path fill="none" stroke="#0044a0" d="M515.392,-292.066C512.519,-287.833 509.379,-283.205 506.299,-278.666"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="509.048,-276.483 500.537,-270.174 503.256,-280.414 509.048,-276.483"/>
+</g>
+<!-- t15&#45;&gt;t16 -->
+<g id="edge21" class="edge"><title>t15&#45;&gt;t16</title>
+<path fill="none" stroke="#0044a0" d="M263.466,-359.936C281.645,-340.695 313.598,-309.935 347,-292.173 361.3,-284.568 377.219,-278.339 393.079,-273.27"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="394.389,-276.53 402.932,-270.262 392.345,-269.835 394.389,-276.53"/>
+</g>
+<!-- t11&#45;&gt;t12 -->
+<g id="edge19" class="edge"><title>t11&#45;&gt;t12</title>
+<path fill="none" stroke="#0044a0" d="M1009.92,-434.405C967.591,-424.191 916.524,-411.87 873.373,-401.459"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="873.983,-398.006 863.441,-399.063 872.341,-404.811 873.983,-398.006"/>
+</g>
+<!-- t11&#45;&gt;t14 -->
+<g id="edge24" class="edge"><title>t11&#45;&gt;t14</title>
+<path fill="none" stroke="#0044a0" d="M1334.06,-445.464C1386.49,-438.209 1431.63,-426.12 1449,-406.173 1465.34,-387.403 1466.07,-368.289 1449,-350.173 1422.45,-321.987 1153.75,-330.0px 1083.05,-328.037"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="1083,-324.531 1072.85,-327.564 1082.68,-331.524 1083,-324.531"/>
+</g>
+<!-- t11&#45;&gt;t17 -->
+<g id="edge27" class="edge"><title>t11&#45;&gt;t17</title>
+<path fill="none" stroke="#0044a0" d="M1278.64,-441.463C1364.44,-433.122 1450.86,-421.174 1464,-406.173 1480.4,-387.448 1479.49,-369.65 1464,-350.173 1457.83,-342.418 1443.67,-336.074 1426.02,-330.926"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="1426.46,-327.418 1415.89,-328.188 1424.63,-334.176 1426.46,-327.418"/>
+</g>
+<!-- t12&#45;&gt;t16 -->
+<g id="edge23" class="edge"><title>t12&#45;&gt;t16</title>
+<path fill="none" stroke="#0044a0" d="M624.426,-363.718C509.174,-353.04 370.992,-338.277 362,-328.173 351.364,-316.22 352.491,-305.04 362,-292.173 366.819,-285.651 372.71,-280.186 379.287,-275.609"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="381.274,-278.496 387.956,-270.274 377.605,-272.534 381.274,-278.496"/>
+</g>
+<!-- t20 -->
+<g id="node21" class="node"><title>t20</title>
+<polygon fill="#efa03b" stroke="black" points="234.918,-156.426 480,-129.117 725.082,-156.426 724.853,-200.614 235.147,-200.614 234.918,-156.426"/>
+<polygon fill="none" stroke="black" points="230.903,-152.847 480,-125.09 729.097,-152.847 728.829,-204.616 231.171,-204.616 230.903,-152.847"/>
+<text text-anchor="middle" x="480" y="-162.639" font-family="Times,serif" font-size="20.00">ocrmypdf.pipeline.merge_pages_ghostscript</text>
+</g>
+<!-- t16&#45;&gt;t20 -->
+<g id="edge33" class="edge"><title>t16&#45;&gt;t20</title>
+<path fill="none" stroke="#0044a0" d="M487.091,-233.881C486.46,-228.165 485.726,-221.515 484.974,-214.703"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="488.446,-214.253 483.87,-204.697 481.488,-215.021 488.446,-214.253"/>
+</g>
+<!-- t16&#45;&gt;t21 -->
+<g id="edge37" class="edge"><title>t16&#45;&gt;t21</title>
+<path fill="none" stroke="#0044a0" d="M602.543,-234.159C645.082,-227.582 693.805,-219.809 738,-212.173 748.572,-210.346 759.416,-208.431 770.357,-206.468"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="771.206,-209.872 780.427,-204.653 769.964,-202.983 771.206,-209.872"/>
+</g>
+<!-- t14&#45;&gt;t20 -->
+<g id="edge34" class="edge"><title>t14&#45;&gt;t20</title>
+<path fill="none" stroke="#0044a0" d="M837.094,-292.063C776.411,-271.259 672.165,-235.52 591.922,-208.01"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="592.855,-204.63 582.26,-204.697 590.584,-211.251 592.855,-204.63"/>
+</g>
+<!-- t14&#45;&gt;t21 -->
+<g id="edge38" class="edge"><title>t14&#45;&gt;t21</title>
+<path fill="none" stroke="#0044a0" d="M896.319,-292.063C906.85,-272.729 924.406,-240.497 938.861,-213.958"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="942.118,-215.294 943.828,-204.838 935.971,-211.946 942.118,-215.294"/>
+</g>
+<!-- t19&#45;&gt;t20 -->
+<g id="edge30" class="edge"><title>t19&#45;&gt;t20</title>
+<path fill="none" stroke="#0044a0" d="M257.907,-234.081C284.597,-226.336 317.298,-216.848 349.316,-207.558"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="350.595,-210.831 359.224,-204.683 348.645,-204.108 350.595,-210.831"/>
+</g>
+<!-- t19&#45;&gt;t21 -->
+<g id="edge35" class="edge"><title>t19&#45;&gt;t21</title>
+<path fill="none" stroke="#0044a0" d="M323.792,-235.042C326.891,-234.738 329.964,-234.447 333,-234.173 512.532,-217.929 559.043,-233.851 738,-212.173 751.869,-210.493 766.169,-208.472 780.522,-206.237"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="781.136,-209.683 790.462,-204.657 780.037,-202.77 781.136,-209.683"/>
+</g>
+<!-- t17&#45;&gt;t20 -->
+<g id="edge32" class="edge"><title>t17&#45;&gt;t20</title>
+<path fill="none" stroke="#0044a0" d="M1195.47,-292.133C1071.63,-270.93 856.728,-234.138 694.688,-206.395"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="695.028,-202.903 684.581,-204.665 693.846,-209.802 695.028,-202.903"/>
+</g>
+<!-- t17&#45;&gt;t21 -->
+<g id="edge36" class="edge"><title>t17&#45;&gt;t21</title>
+<path fill="none" stroke="#0044a0" d="M1254.29,-292.063C1205.19,-271.428 1121.13,-236.1 1055.9,-208.683"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="1056.99,-205.345 1046.42,-204.697 1054.28,-211.799 1056.99,-205.345"/>
+</g>
+<!-- t18&#45;&gt;t20 -->
+<g id="edge31" class="edge"><title>t18&#45;&gt;t20</title>
+<path fill="none" stroke="#0044a0" d="M120.266,-796.105C70.9512,-780.34 17,-751.202 17,-699.173 17,-699.173 17,-699.173 17,-309.173 17,-269.597 31.8505,-255.79 65,-234.173 92.9782,-215.927 154.085,-202.475 221.024,-192.724"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="221.533,-196.187 230.939,-191.311 220.546,-189.256 221.533,-196.187"/>
+</g>
+<!-- t22 -->
+<g id="node23" class="node"><title>t22</title>
+<polygon fill="#efa03b" stroke="black" points="554.065,-47.332 721,-20.0049 887.935,-47.332 887.779,-91.5483 554.221,-91.5483 554.065,-47.332"/>
+<polygon fill="none" stroke="black" points="550.054,-43.9306 721,-15.9468 891.946,-43.9306 891.764,-95.5532 550.236,-95.5532 550.054,-43.9306"/>
+<text text-anchor="middle" x="721" y="-53.5531" font-family="Times,serif" font-size="20.00">ocrmypdf.pipeline.copy_final</text>
+</g>
+<!-- t20&#45;&gt;t22 -->
+<g id="edge41" class="edge"><title>t20&#45;&gt;t22</title>
+<path fill="none" stroke="#0044a0" d="M556.585,-133.609C580.784,-122.857 607.72,-110.888 632.67,-99.8018"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="634.408,-102.859 642.125,-95.6004 631.566,-96.4625 634.408,-102.859"/>
+</g>
+<!-- t21&#45;&gt;t22 -->
+<g id="edge40" class="edge"><title>t21&#45;&gt;t22</title>
+<path fill="none" stroke="#0044a0" d="M888.417,-134.636C863.556,-123.635 835.613,-111.27 809.783,-99.8401"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="810.933,-96.5216 800.372,-95.6756 808.1,-102.923 810.933,-96.5216"/>
+</g>
+</g>
+</svg>

docs/release_notes.rst

@@ -1,23 +1,112 @@
-RELEASE NOTES
+Release notes
 =============
 
 OCRmyPDF uses `semantic versioning <http://semver.org/>`_.
 
-v4.3.3:
-=======
+
+v4.5.4
+------
+
+-   Fix ``--skip-big`` raising an exception if a page contains no images (#152) (thanks to @TomRaz)
+-   Fix an issue where pages with no images might trigger "cannot write mode P as JPEG" (#151)
+
+
+v4.5.3
+------
+
+-  Added a workaround for Ghostscript 9.21 and probably earlier versions would fail with the error message "VMerror -25", due to a Ghostscript bug in XMP metadata handling
+-  High Unicode characters (U+10000 and up) are no longer accepted for setting metadata on the command line, as Ghostscript may not handle them correctly.
+-  Fixed an issue where the ``tess4`` renderer would duplicate content onto output pages if tesseract failed or timed out
+-  Fixed ``tess4`` renderer not recognized when lossless reconstruction is possible
+
+
+v4.5.2
+------
+
+-  Fix issue #147. ``--pdf-renderer tess4 --clean`` will produce an oversized page containing the original image in the bottom left corner, due to loss DPI information.
+-  Make "using Tesseract 4.0" warning less ominous
+-  Set up machinery for homebrew OCRmyPDF tap
+
+
+v4.5.1
+------
+
+-  Fix issue #137, proportions of images with a non-square pixel aspect ratio would be distorted in output for ``--force-ocr`` and some other combinations of flags
+
+
+v4.5
+----
+
+-  Exotic PDFs containing "Form XObjects" are now supported (issue #134; PDF reference manual 8.10), and images they contain are taken into account when determining the resolution for rasterizing
+-  The Tesseract 4 Docker image no longer includes all languages, because it took so long to build something would tend to fail
+-  OCRmyPDF now warns about using ``--pdf-renderer tesseract`` with Tesseract 3.04 or lower due to issues with Ghostscript corrupting the OCR text in these cases
+
+
+v4.4.2
+------
+
+-  The Docker images (ocrmypdf, ocrmypdf-polyglot, ocrmypdf-tess4) are now based on Ubuntu 16.10 instead of Debian stretch
+
+   + This makes supporting the Tesseract 4 image easier
+   + This could be a disruptive change for any Docker users who built customized these images with their own changes, and made those changes in a way that depends on Debian and not Ubuntu
+
+-  OCRmyPDF now prevents running the Tesseract 4 renderer with Tesseract 3.04, which was permitted in v4.4 and v4.4.1 but will not work
+
+
+v4.4.1
+------
+
+-  To prevent a `TIFF output error <https://github.com/python-pillow/Pillow/issues/2206>`_ caused by img2pdf >= 0.2.1 and Pillow <= 3.4.2, dependencies have been tightened
+-  The Tesseract 4.00 simultaneous process limit was increased from 1 to 2, since it was observed that 1 lowers performance
+-  Documentation improvements to describe the ``--tesseract-config`` feature 
+-  Added test cases and fixed error handling for ``--tesseract-config``
+-  Tweaks to setup.py to deal with issues in the v4.4 release
+
+v4.4
+----
+
+-  Tesseract 4.00 is now supported on an experimental basis.
+
+   +  A new rendering option ``--pdf-renderer tess4`` exploits Tesseract 4's new text-only output PDF mode. See the documentation on PDF Renderers for details.
+   +  The ``--tesseract-oem`` argument allows control over the Tesseract 4 OCR engine mode (tesseract's ``--oem``). Use ``--tesseract-oem 2`` to enforce the new LSTM mode.
+   +  Fixed poor performance with Tesseract 4.00 on Linux
+
+-  Fixed an issue that caused corruption of output to stdout in some cases
+-  Removed test for Pillow JPEG and PNG support, as the minimum supported version of Pillow now enforces this
+-  OCRmyPDF now tests that the intended destination file is writable before proceeding
+-  The test suite now requires ``pytest-helpers-namespace`` to run (but not install)
+-  Significant code reorganization to make OCRmyPDF re-entrant and improve performance. All changes should be backward compatible for the v4.x series.
+
+   + However, OCRmyPDF's dependency "ruffus" is not re-entrant, so no Python API is available. Scripts should continue to use the command line interface.
+
+
+v4.3.5
+------
+
+-  Update documentation to confirm Python 3.6.0 compatibility. No code changes were needed, so many earlier versions are likely supported.
+
+
+v4.3.4
+------
+
+-  Fixed "decimal.InvalidOperation: quantize result has too many digits" for high DPI images
+
+
+v4.3.3
+------
 
 -  Fixed PDF/A creation with Ghostscript 9.20 properly
 -  Fixed an exception on inline stencil masks with a missing optional parameter
 
 
-v4.3.2:
-=======
+v4.3.2
+------
 
 -  Fixed a PDF/A creation issue with Ghostscript 9.20 (note: this fix did not actually work)
 
 
-v4.3.1:
-=======
+v4.3.1
+------
 
 -  Fixed an issue where pages produced by the "hocr" renderer after a Tesseract timeout would be rotated incorrectly if the input page was rotated with a /Rotate marker
 -  Fixed a file handle leak in LeptonicaErrorTrap that would cause a "too many open files" error for files around hundred pages of pages long when ``--deskew`` or ``--remove-background`` or other Leptonica based image processing features were in use, depending on the system value of ``ulimit -n``
@@ -27,8 +116,8 @@ v4.3.1:
 -  Tesseract caching in test cases is now more cautious about false cache hits and reproducing exact output, not that any problems were observed
 
 
-v4.3:
-=====
+v4.3
+----
 
 -  New feature ``--remove-background`` to detect and erase the background of color and grayscale images
 -  Better documentation
@@ -38,21 +127,21 @@ v4.3:
    +  This does not improve performance since temporary files are still used for buffering
    +  Some output validation is disabled in this mode
 
-v4.2.5:
-=======
+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:
-=======
+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:
-=======
+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)
@@ -65,21 +154,21 @@ v4.2.3:
 -  Deprecated the OCRmyPDF.sh shell script
 
 
-v4.2.2:
-=======
+v4.2.2
+------
 
 -  Improvements to documentation
 
 
-v4.2.1:
-=======
+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:
-=====
+v4.2
+----
 
 -  ocrmypdf will now try to convert single image files to PDFs if they are provided as input (#15)
 
@@ -111,14 +200,14 @@ v4.2:
 
 -  Ghostscript now runs in "safer" mode where possible
 
-v4.1.4:
-=======
+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:
-=======
+v4.1.3
+------
 
 -  More helpful error message for PDFs with version 4 security handler
 -  Update usage instructions for Windows/Docker users
@@ -126,59 +215,59 @@ v4.1.3:
 -  Add a few leptonica wrapper functions (no effect on most users)
 
 
-v4.1.2:
-=======
+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:
-=====
+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:
-=======
+v4.0.7
+------
 
 -  Minor correction to Ghostscript output settings
 
 
-v4.0.6:
-=======
+v4.0.6
+------
 
 -  Update install instructions
 -  Provide a sRGB profile instead of using Ghostscript's
 
 
-v4.0.5:
-=======
+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:
-=======
+v4.0.4
+------
 
 Released with verbose debug message turned on. Do not use. Skip to v4.0.5.
 
 
-v4.0.3:
-=======
+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
@@ -186,11 +275,11 @@ Fixes
 -  Docker: fix blank JPEG2000 issue by insisting on Ghostscript versions that have this fixed
 
 
-v4.0.2:
-=======
+v4.0.2
+------
 
 Fixes
------
+^^^^^
 
 -  Fixed compatibility with Tesseract 3.04.01 release, particularly its different way of outputting
    orientation information
@@ -198,20 +287,20 @@ Fixes
 -  Fixed use of chmod on Docker that broke most test cases
 
 
-v4.0.1:
-=======
+v4.0.1
+------
 
 Fixes
------
+^^^^^
 
 -  Fixed a KeyError if tesseract fails to find page orientation information
 
 
-v4.0:
-=====
+v4.0
+----
 
 New features
-------------
+^^^^^^^^^^^^
 
 -  Automatic page rotation (``-r``) is now available. It uses ignores any prior rotation information
    on PDFs and sets rotation based on the dominant orientation of detectable text. This feature is
@@ -221,7 +310,7 @@ New features
 
 
 Fixes
------
+^^^^^
 
 -  Fixed an issue where lossless reconstruction could cause some pages to be appear incorrectly
    if the page was rotated by the user in Acrobat after being scanned (specifically if it a /Rotate tag)
@@ -230,7 +319,7 @@ Fixes
 
 
 Changes
--------
+^^^^^^^
 
 -  Logging output is now much easier to read
 -  ``--deskew`` is now performed by Leptonica instead of unpaper (#25)
@@ -242,21 +331,21 @@ Changes
    to correct the problem.
 
 
-v3.2.1:
-=======
+v3.2.1
+------
 
 Changes
--------
+^^^^^^^
 
 -  Fixed issue #47 "convert() got and unexpected keyword argument 'dpi'" by upgrading to img2pdf 0.2
 -  Tweaked the Dockerfiles
 
 
-v3.2:
-=====
+v3.2
+----
 
 New features
-------------
+^^^^^^^^^^^^
 
 -  Lossless reconstruction: when possible, OCRmyPDF will inject text layers without 
    otherwise manipulating the content and layout of a PDF page. For example, a PDF containing a mix
@@ -268,25 +357,25 @@ New features
    for the polyglots among us. It is much larger.
 
 Changes
--------
+^^^^^^^
 
 -  JPEG transcoding quality is now 95 instead of the default 75. Bigger file sizes for less degradation.
 
 
 
-v3.1.1:
-=======
+v3.1.1
+------
 
 Changes
--------
+^^^^^^^
 
 -  Fixed bug that caused incorrect page size and DPI calculations on documents with mixed page sizes
 
-v3.1:
-=====
+v3.1
+----
 
 Changes
--------
+^^^^^^^
 
 -  Default output format is now PDF/A-2b instead of PDF/A-1b
 -  Python 3.5 and macOS El Capitan are now supported platforms - no changes were
@@ -300,11 +389,11 @@ Changes
    Currently it always chooses the 'hocrtransform' renderer but that behavior may change.
 -  Set up Travis CI automatic integration testing
 
-v3.0:
-=====
+v3.0
+----
 
 New features
-------------
+^^^^^^^^^^^^
 
 -  Easier installation with a Docker container or Python's ``pip`` package manager 
 -  Eliminated many external dependencies, so it's easier to setup
@@ -327,7 +416,7 @@ New features
 -  Multiple images on the same PDF page are now supported
 
 Changes
--------
+^^^^^^^
 
 -  New, robust rewrite in Python 3.4+ with ruffus_ pipelines
 -  Now uses Ghostscript 9.14's improved color conversion model to preserve PDF colors
@@ -365,7 +454,7 @@ Changes
 .. _JHOVE: http://jhove.sourceforge.net/
 
 Release candidates
-------------------
+^^^^^^^^^^^^^^^^^^
 
 -  rc9:
 
@@ -433,12 +522,12 @@ where ``settings.txt`` contains *one argument per line*, for example:
 
 
 Fixes
------
+^^^^^
 
 -  Handling of filenames containing spaces: fixed
 
 Notes and known issues
-----------------------
+^^^^^^^^^^^^^^^^^^^^^^
 
 -  Some dependencies may work with lower versions than tested, so try
    overriding dependencies if they are "in the way" to see if they work.
@@ -450,9 +539,9 @@ Notes and known issues
    images almost never contain inline images.
 
 
-v2.2-stable (2014-09-29):
-=========================
+v2.2-stable (2014-09-29)
+------------------------
 
 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.
 
-For details on older versions, see the `final version of its release notes <https://github.com/fritz-hh/OCRmyPDF/blob/7fd3dbdf42ca53a619412ce8add7532c5e81a9d1/RELEASE_NOTES.md>`_.
+For details on older versions, see the `final version of its release notes <https://github.com/fritz-hh/OCRmyPDF/blob/7fd3dbdf42ca53a619412ce8add7532c5e81a9d1/RELEASE_NOTES.md>`_.

docs/security.rst

@@ -1,4 +1,4 @@
-PDF Security Issues
+PDF security issues
 ===================
 
 	OCRmyPDF should only be used on PDFs you trust. It is not designed to protect you against malware. 
@@ -14,7 +14,7 @@ PDF is a rich, complex file format. The official PDF 1.7 specification, ISO 3200
 
 In short, PDFs `may contain viruses <https://security.stackexchange.com/questions/64052/can-a-pdf-file-contain-a-virus>`_.
 
-This `article <https://theinvisiblethings.blogspot.ca/2013/02/converting-untrusted-pdfs-into-trusted.html>`_ describes a method which allows potentially hostile PDFs to be viewed and rasterized safely in a disposable virtual machine. A trusted PDF created in this manner is converted to images and loses all information making it searchable. OCRmyPDF could be used restore searchability.
+This `article <https://theinvisiblethings.blogspot.ca/2013/02/converting-untrusted-pdfs-into-trusted.html>`_ describes a high-paranoia method which allows potentially hostile PDFs to be viewed and rasterized safely in a disposable virtual machine. A trusted PDF created in this manner is converted to images and loses all information making it searchable and losing all compression. OCRmyPDF could be used restore searchability.
 
 How OCRmyPDF processes PDFs
 ---------------------------

ocrmypdf/__init__.py

@@ -1,34 +1,15 @@
-from enum import IntEnum
-import os
-from collections.abc import Iterable
 import pkg_resources
 
+PROGRAM_NAME = 'ocrmypdf'
+
 VERSION = pkg_resources.get_distribution('ocrmypdf').version
 
 
-class ExitCode(IntEnum):
-    ok = 0
-    bad_args = 1
-    input_file = 2
-    missing_dependency = 3
-    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
+# These imports are for v4.x backward compatibility for consumers of ocrmypdf
+# (if any). They are deprecated and will be removed in v5.x.
+from .exec import ghostscript, qpdf, tesseract, unpaper, get_program
+from .exceptions import ExitCode
+from .helpers import page_number, is_iterable_notstr
 
 
-def get_program(name):
-    envvar = 'OCRMYPDF_' + name.upper()
-    return os.environ.get(envvar, 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/exceptions.py

@@ -0,0 +1,59 @@
+#!/usr/bin/env python3
+# © 2016 James R. Barlow: github.com/jbarlow83
+
+
+from enum import IntEnum
+
+class ExitCode(IntEnum):
+    ok = 0
+    bad_args = 1
+    input_file = 2
+    missing_dependency = 3
+    invalid_output_pdf = 4
+    file_access_error = 5
+    already_done_ocr = 6
+    child_process_error = 7
+    encrypted_pdf = 8
+    invalid_config = 9
+    other_error = 15
+    ctrl_c = 130
+
+
+class ExitCodeException(Exception):
+    pass
+
+
+class PdfMergeFailedError(ExitCodeException):
+    exit_code = ExitCode.input_file
+
+
+class MissingDependencyError(ExitCodeException):
+    exit_code = ExitCode.missing_dependency
+
+
+class UnsupportedImageFormatError(ExitCodeException):
+    exit_code = ExitCode.input_file
+
+
+class DpiError(ExitCodeException):
+    exit_code = ExitCode.input_file
+
+
+class PriorOcrFoundError(ExitCodeException):
+    exit_code = ExitCode.already_done_ocr
+
+
+class InputFileError(ExitCodeException):
+    exit_code = ExitCode.input_file
+
+
+class SubprocessOutputError(ExitCodeException):
+    exit_code = ExitCode.other_error
+
+
+class EncryptedPdfError(ExitCodeException):
+    exit_code = ExitCode.encrypted_pdf
+
+
+class TesseractConfigError(ExitCodeException):
+    exit_code = ExitCode.invalid_config

ocrmypdf/exec/__init__.py

@@ -0,0 +1,11 @@
+#!/usr/bin/env python3
+# © 2016 James R. Barlow: github.com/jbarlow83
+
+"""Wrappers to manage subprocess calls"""
+
+import os
+
+
+def get_program(name):
+    envvar = 'OCRMYPDF_' + name.upper()
+    return os.environ.get(envvar, name)

ocrmypdf/exec/ghostscript.py

@@ -2,10 +2,30 @@
 # © 2015 James R. Barlow: github.com/jbarlow83
 
 from tempfile import NamedTemporaryFile
-from subprocess import Popen, PIPE, check_call
+from subprocess import Popen, PIPE, STDOUT, check_call, CalledProcessError, \
+    check_output
 from shutil import copy
+from functools import lru_cache
 from . import get_program
-from .pdfa import SRGB_ICC_PROFILE
+from ..pdfa import SRGB_ICC_PROFILE
+
+
+@lru_cache(maxsize=1)
+def version():
+    args_gs = [
+        get_program('gs'),
+        '--version'
+    ]
+    try:
+        version = check_output(
+                args_gs, close_fds=True, universal_newlines=True,
+                stderr=STDOUT)
+    except CalledProcessError as e:
+        print("Could not find Ghostscript executable on system PATH.",
+              file=sys.stderr)
+        raise MissingDependencyError from e
+
+    return version.strip()
 
 
 def rasterize_pdf(input_file, output_file, xres, yres, raster_device, log,
@@ -25,16 +45,13 @@ def rasterize_pdf(input_file, output_file, xres, yres, raster_device, log,
             input_file
         ]
 
-        p = Popen(args_gs, close_fds=True, stdout=PIPE, stderr=PIPE,
+        p = Popen(args_gs, close_fds=True, stdout=PIPE, stderr=STDOUT,
                   universal_newlines=True)
-        stdout, stderr = p.communicate()
-        if stdout:
-            if 'error' in stdout:
-                log.error(stdout)  # Ghostscript puts errors in stdout
-            else:
-                log.debug(stdout)
-        if stderr:
-            log.error(stderr)
+        stdout, _ = p.communicate()
+        if 'error' in stdout:
+            log.error(stdout)  # Ghostscript puts errors in stdout
+        else:
+            log.debug(stdout)
 
         if p.returncode == 0:
             copy(tmp.name, output_file)
@@ -60,24 +77,22 @@ def generate_pdfa(pdf_pages, output_file, log, threads=1):
             "-sOutputFile=" + gs_pdf.name,
         ]
         args_gs.extend(pdf_pages)
-        p = Popen(args_gs, close_fds=True, stdout=PIPE, stderr=PIPE,
+        p = Popen(args_gs, close_fds=True, stdout=PIPE, stderr=STDOUT,
                   universal_newlines=True)
-        stdout, stderr = p.communicate()
-        if stdout:
-            if 'error' in stdout:
-                log.error(stdout)
-            elif 'overprint mode not set' in stdout:
-                # Unless someone is going to print PDF/A documents on a
-                # magical sRGB printer I can't see the removal of overprinting
-                # being a problem....
-                log.debug(
-                    "Ghostscript had to remove PDF 'overprinting' from the "
-                    "input file to complete PDF/A conversion. "
-                    )
-            else:
-                log.debug(stdout)
-        if stderr:
-            log.error(stderr)
+        stdout, _ = p.communicate()
+
+        if 'error' in stdout or 'ERROR' in stdout:
+            log.error(stdout)
+        elif 'overprint mode not set' in stdout:
+            # Unless someone is going to print PDF/A documents on a
+            # magical sRGB printer I can't see the removal of overprinting
+            # being a problem....
+            log.debug(
+                "Ghostscript had to remove PDF 'overprinting' from the "
+                "input file to complete PDF/A conversion. "
+                )
+        else:
+            log.debug(stdout)
 
         if p.returncode == 0:
             # Ghostscript does not change return code when it fails to create

ocrmypdf/exec/qpdf.py

@@ -7,7 +7,9 @@ import sys
 import os
 import re
 
-from . import ExitCode, get_program
+from ..exceptions import InputFileError, SubprocessOutputError, \
+    MissingDependencyError, EncryptedPdfError
+from . import get_program
 
 
 @lru_cache(maxsize=1)
@@ -20,21 +22,25 @@ def version():
         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)
+    except CalledProcessError as e:
+        print("Could not find qpdf executable on system PATH.",
+              file=sys.stderr)
+        raise MissingDependencyError() from e
 
     qpdf_version = re.match(r'qpdf version (.+)', versions).group(1)
     return qpdf_version
 
 
-def check(input_file, log):
+def check(input_file, log=None):
     args_qpdf = [
         get_program('qpdf'),
         '--check',
         input_file
     ]
 
+    if log is None:
+        import logging as log
+
     try:
         check_output(args_qpdf, stderr=STDOUT, universal_newlines=True)
     except CalledProcessError as e:
@@ -52,6 +58,14 @@ def check(input_file, log):
     return True
 
 
+def _probably_encrypted(e):
+    """qpdf can report a false positive "file is encrypted" message for damaged
+    files - suppress this"""
+    return e.returncode == 2 and \
+        'invalid password' in e.output and \
+        'file is damaged' not in e.output
+
+
 def repair(input_file, output_file, log):
     args_qpdf = [
         get_program('qpdf'), input_file, output_file
@@ -64,20 +78,20 @@ def repair(input_file, output_file, log):
             log.debug(e.output)
             return
 
-        if e.returncode == 2 and e.output.find("invalid password"):
+        if _probably_encrypted(e):
             log.error("{0}: this PDF is password-protected - password must "
                       "be removed for OCR".format(input_file))
-            sys.exit(ExitCode.input_file)
+            raise EncryptedPdfError() from e
         elif e.returncode == 2:
             log.error("{0}: not a valid PDF, and could not repair it.".format(
                       input_file))
             log.error("Details: " + e.output)
-            sys.exit(ExitCode.input_file)
+            raise InputFileError() from e
         else:
             log.error("{0}: unknown error".format(
                       input_file))
             log.error(e.output)
-            sys.exit(ExitCode.unknown)
+            raise SubprocessOutputError() from e
 
 
 def get_npages(input_file, log):
@@ -88,7 +102,7 @@ def get_npages(input_file, log):
     except CalledProcessError as e:
         if e.returncode == 2 and e.output.find('No such file'):
             log.error(e.output)
-            sys.exit(ExitCode.input_file)
+            raise InputFileError() from e
     return int(pages)
 
 

ocrmypdf/exec/tesseract.py

@@ -6,8 +6,12 @@ import os
 import re
 import shutil
 from functools import lru_cache
-from . import ExitCode, get_program, page_number
+from ..exceptions import MissingDependencyError, TesseractConfigError
+from ..helpers import page_number
+from . import get_program
 from collections import namedtuple
+from textwrap import dedent
+import PyPDF2 as pypdf
 
 from subprocess import Popen, PIPE, CalledProcessError, \
     TimeoutExpired, check_output, STDOUT, DEVNULL
@@ -50,14 +54,47 @@ def version():
         versions = check_output(
                 args_tess, close_fds=True, universal_newlines=True,
                 stderr=STDOUT)
-    except CalledProcessError:
-        print("Could not find Tesseract executable on system PATH.")
-        sys.exit(ExitCode.missing_dependency)
+    except CalledProcessError as e:
+        print("Could not find Tesseract executable on system PATH.",
+              file=sys.stderr)
+        raise MissingDependencyError from e
 
     tesseract_version = re.match(r'tesseract\s(.+)', versions).group(1)
     return tesseract_version
 
 
+def v4():
+    "Is this Tesseract v4.0?"
+    return (version() >= '4')
+
+
+def has_textonly_pdf():
+    if version() == '4.00.00alpha':
+        # textonly_pdf added during the 4.00.00alpha cycle, so we must test
+        # more carefully to see if it is present
+        args_tess = [
+            get_program('tesseract'),
+            '--print-parameters'
+        ]
+        try:
+            params = check_output(
+                    args_tess, close_fds=True, universal_newlines=True,
+                    stderr=STDOUT)
+        except CalledProcessError as e:
+            print("Could not --print-parameters from tesseract",
+                  file=sys.stderr)
+            raise MissingDependencyError from e
+        if 'textonly_pdf' in params:
+            return True
+    else:
+        return v4()
+
+
+def psm():
+    "If Tesseract 4.0, use argument --psm instead of -psm"
+    return '--psm' if v4() else '-psm'
+
+
 @lru_cache(maxsize=1)
 def languages():
     args_tess = [
@@ -69,19 +106,31 @@ def languages():
                 args_tess, close_fds=True, universal_newlines=True,
                 stderr=STDOUT)
     except CalledProcessError as e:
-        print("Tesseract failed to report available languages.")
-        print("Output from Tesseract:")
-        print("-" * 40)
-        print(e.output)
-        sys.exit(ExitCode.missing_dependency)
+        msg = dedent("""Tesseract failed to report available languages.
+        Output from Tesseract:
+        -----------
+        """)
+        msg += e.output
+        print(msg, file=sys.stderr)
+        raise MissingDependencyError from e
     return set(lang.strip() for lang in langs.splitlines()[1:])
 
 
-def get_orientation(input_file, language: list, timeout: float, log):
-    args_tesseract = [
+def tess_base_args(languages, engine_mode):
+    args = [
         get_program('tesseract'),
-        '-l', '+'.join(language),
-        '-psm', '0',
+    ]
+    if languages:
+        args.extend(['-l', '+'.join(languages)])
+    if engine_mode is not None and v4():
+        args.extend(['--oem', str(engine_mode)])
+    return args
+
+
+def get_orientation(input_file, language: list, engine_mode, timeout: float,
+                    log):
+    args_tesseract = tess_base_args(language, engine_mode) + [
+        psm(), '0',
         input_file,
         'stdout'
     ]
@@ -138,6 +187,10 @@ def tesseract_log_output(log, stdout, input_file):
             log.warning(prefix + "unsure about page orientation")
         elif 'error' in line.lower() or 'exception' in line.lower():
             log.error(prefix + line.strip())
+        elif 'warning' in line.lower():
+            log.warning(prefix + line.strip())
+        elif 'read_params_file' in line.lower():
+            log.error(prefix + line.strip())
         else:
             log.info(prefix + line.strip())
 
@@ -159,18 +212,16 @@ def _generate_null_hocr(output_hocr, image):
         f.write(HOCR_TEMPLATE.format(w, h))
 
 
-def generate_hocr(input_file, output_hocr, language: list, tessconfig: list,
-                  timeout: float, pageinfo_getter, pagesegmode: int, log):
+def generate_hocr(input_file, output_hocr, language: list, engine_mode,
+                  tessconfig: list,
+                  timeout: float, pagesegmode: int, log):
 
     badxml = os.path.splitext(output_hocr)[0] + '.badxml'
 
-    args_tesseract = [
-        get_program('tesseract'),
-        '-l', '+'.join(language)
-    ]
+    args_tesseract = tess_base_args(language, engine_mode)
 
     if pagesegmode is not None:
-        args_tesseract.extend(['-psm', str(pagesegmode)])
+        args_tesseract.extend([psm(), str(pagesegmode)])
 
     args_tesseract.extend([
         input_file,
@@ -178,6 +229,7 @@ def generate_hocr(input_file, output_hocr, language: list, tessconfig: list,
         'hocr'
     ] + tessconfig)
     try:
+        log.debug(args_tesseract)
         stdout = check_output(
             args_tesseract, close_fds=True, stderr=STDOUT,
             universal_newlines=True, timeout=timeout)
@@ -189,6 +241,8 @@ def generate_hocr(input_file, output_hocr, language: list, tessconfig: list,
         _generate_null_hocr(output_hocr, input_file)
     except CalledProcessError as e:
         tesseract_log_output(log, e.output, input_file)
+        if 'read_params_file: parameter not found' in e.output:
+            raise TesseractConfigError() from e
         if 'Image too large' in e.output:
             _generate_null_hocr(output_hocr, input_file)
             return
@@ -196,6 +250,7 @@ def generate_hocr(input_file, output_hocr, language: list, tessconfig: list,
         raise e from e
     else:
         tesseract_log_output(log, stdout, input_file)
+
         if os.path.exists(badxml + '.html'):
             # Tesseract 3.02 appends suffix ".html" on its own (.badxml.html)
             shutil.move(badxml + '.html', badxml)
@@ -218,25 +273,47 @@ def generate_hocr(input_file, output_hocr, language: list, tessconfig: list,
                 f_out.write(line)
 
 
+def use_skip_page(text_only, skip_pdf, output_pdf):
+    if not text_only:
+        os.symlink(skip_pdf, output_pdf)
+        return
+
+    # For text only we must create a blank page with dimensions identical
+    # to the skip page because this is equivalent to a page with no text
+
+    pdf_in = pypdf.PdfFileReader(skip_pdf)
+    page0 = pdf_in.pages[0]
+
+    with open(output_pdf, 'wb') as out:
+        pdf_out = pypdf.PdfFileWriter()
+        w, h = page0.mediaBox.getWidth(), page0.mediaBox.getHeight()
+        pdf_out.addBlankPage(w, h)
+        pdf_out.write(out)
+
+
 def generate_pdf(input_image, skip_pdf, output_pdf, language: list,
+                 engine_mode, text_only: bool,
                  tessconfig: list, timeout: float, pagesegmode: int, log):
     '''Use Tesseract to render a PDF.
 
     input_image -- image to analyze
     skip_pdf -- if we time out, use this file as output
+    output_pdf -- file to generate
     language -- list of languages to consider
+    engine_mode -- engine mode argument for tess v4
+    text_only -- enable tesseract text only mode?
     tessconfig -- tesseract configuration
     timeout -- timeout (seconds)
     log -- logger object
     '''
 
-    args_tesseract = [
-        get_program('tesseract'),
-        '-l', '+'.join(language)
-    ]
+    args_tesseract = tess_base_args(language, engine_mode)
 
     if pagesegmode is not None:
-        args_tesseract.extend(['-psm', str(pagesegmode)])
+        args_tesseract.extend([psm(), str(pagesegmode)])
+
+    if text_only:
+        args_tesseract.extend(['-c', 'textonly_pdf=1'])
 
     args_tesseract.extend([
         input_image,
@@ -245,16 +322,20 @@ def generate_pdf(input_image, skip_pdf, output_pdf, language: list,
     ] + tessconfig)
 
     try:
+        log.debug(args_tesseract)
         stdout = check_output(
             args_tesseract, close_fds=True, stderr=STDOUT,
             universal_newlines=True, timeout=timeout)
     except TimeoutExpired:
         page_timedout(log, input_image)
-        shutil.copy(skip_pdf, output_pdf)
+        use_skip_page(text_only, skip_pdf, output_pdf)
     except CalledProcessError as e:
         tesseract_log_output(log, e.output, input_image)
+        if 'read_params_file: parameter not found' in e.output:
+            raise TesseractConfigError() from e
+
         if 'Image too large' in e.output:
-            shutil.copy(skip_pdf, output_pdf)
+            use_skip_page(text_only, skip_pdf, output_pdf)
             return
         raise e from e
     else:

ocrmypdf/exec/unpaper.py

@@ -8,7 +8,8 @@ from tempfile import NamedTemporaryFile
 import sys
 import os
 from functools import lru_cache
-from . import ExitCode, get_program
+from ..exceptions import MissingDependencyError
+from . import get_program
 
 
 @lru_cache(maxsize=1)
@@ -47,17 +48,17 @@ def run(input_file, output_file, dpi, log, mode_args):
                 im = im.convert(mode='1')
             else:
                 im = im.convert(mode='RGB')
-        except IOError:
+        except IOError as e:
             log.error(
                     "Could not convert image with type " + im.mode)
-            sys.exit(ExitCode.missing_dependency)
+            raise MissingDependencyError() from e
 
     try:
         suffix = SUFFIXES[im.mode]
     except KeyError:
         log.error(
                 "Failed to convert image to a supported format.")
-        sys.exit(ExitCode.missing_dependency)
+        raise MissingDependencyError() from e
 
     with NamedTemporaryFile(suffix=suffix) as input_pnm, \
             NamedTemporaryFile(suffix=suffix, mode="r+b") as output_pnm:
@@ -77,7 +78,8 @@ def run(input_file, output_file, dpi, log, mode_args):
             raise e from e
         else:
             log.debug(stdout)
-            Image.open(output_pnm.name).save(output_file)
+            # unpaper sets dpi to 72
+            Image.open(output_pnm.name).save(output_file, dpi=(dpi, dpi))
 
 
 def deskew(input_file, output_file, dpi, log):

ocrmypdf/helpers.py

@@ -0,0 +1,79 @@
+#!/usr/bin/env python3
+# © 2016 James R. Barlow: github.com/jbarlow83
+
+from functools import partial
+from collections.abc import Iterable
+from contextlib import suppress
+import sys
+import os
+
+
+def re_symlink(input_file, soft_link_name, log=None):
+    """
+    Helper function: relinks soft symbolic link if necessary
+    """
+
+    if log is None:
+        prdebug = partial(print, file=sys.stderr)
+    else:
+        prdebug = log.debug
+
+    # Guard against soft linking to oneself
+    if input_file == soft_link_name:
+        prdebug("Warning: No symbolic link made. You are using " +
+                "the original data directory as the working directory.")
+        return
+
+    # Soft link already exists: delete for relink?
+    if os.path.lexists(soft_link_name):
+        # do not delete or overwrite real (non-soft link) file
+        if not os.path.islink(soft_link_name):
+            raise FileExistsError(
+                "%s exists and is not a link" % soft_link_name)
+        try:
+            os.unlink(soft_link_name)
+        except:
+            prdebug("Can't unlink %s" % (soft_link_name))
+
+    if not os.path.exists(input_file):
+        raise FileNotFoundError(
+            "trying to create a broken symlink to %s" % input_file)
+
+    prdebug("os.symlink(%s, %s)" % (input_file, soft_link_name))
+
+    # Create symbolic link using absolute path
+    os.symlink(
+        os.path.abspath(input_file),
+        soft_link_name
+    )
+
+
+def is_iterable_notstr(thing):
+    return isinstance(thing, Iterable) and not isinstance(thing, str)
+
+
+def page_number(input_file):
+    return int(os.path.basename(input_file)[0:6])
+
+
+def is_file_writable(test_file):
+    """Intentionally racy test if target is writable.
+
+    We intend to write to the output file if and only if we succeed and
+    can replace it atomically. Before doing the OCR work, make sure
+    the location is writable.
+    """
+    if os.path.exists(test_file):
+        return os.access(
+            test_file, os.W_OK,
+            effective_ids=(os.access in os.supports_effective_ids))
+    else:
+        try:
+            fp = open(test_file, 'wb')
+        except OSError as e:
+            return False
+        else:
+            fp.close()
+            with suppress(OSError):
+                os.unlink(test_file)
+        return True

ocrmypdf/lib/__init__.py

@@ -0,0 +1 @@
+"""Bindings to external libraries"""

ocrmypdf/lib/compile_leptonica.py

@@ -1,8 +1,8 @@
 from cffi import FFI
 
-ffi = FFI()
-ffi.set_source("ocrmypdf.lib._leptonica", None)
-ffi.cdef("""
+ffibuilder = FFI()
+ffibuilder.set_source("ocrmypdf.lib._leptonica", None)
+ffibuilder.cdef("""
 typedef signed char             l_int8;
 typedef unsigned char           l_uint8;
 typedef short                   l_int16;
@@ -56,7 +56,7 @@ typedef struct Box    BOX;
 
 """)
 
-ffi.cdef("""
+ffibuilder.cdef("""
 PIX * pixRead ( const char *filename );
 PIX * pixScale ( PIX *pixs, l_float32 scalex, l_float32 scaley );
 l_int32 pixFindSkew ( PIX *pixs, l_float32 *pangle, l_float32 *pconf );
@@ -189,4 +189,4 @@ void lept_free(void *ptr);
 
 
 if __name__ == '__main__':
-    ffi.compile()
+    ffibuilder.compile(verbose=True)

ocrmypdf/pageinfo.py

@@ -2,7 +2,7 @@
 # © 2015 James R. Barlow: github.com/jbarlow83
 
 from subprocess import Popen, PIPE
-from decimal import Decimal, getcontext
+from decimal import Decimal
 from math import hypot
 import re
 import sys
@@ -89,16 +89,32 @@ def _is_unit_square(shorthand):
     pairwise = zip(values, UNIT_SQUARE)
     return all([isclose(a, b, rel_tol=1e-3) for a, b in pairwise])
 
-RasterSettings = namedtuple('RasterSettings',
+XobjectSettings = namedtuple('XobjectSettings',
     ['name', 'shorthand', 'stack_depth'])
 
 InlineSettings = namedtuple('InlineSettings',
     ['settings', 'shorthand', 'stack_depth'])
 
-ContentsInfo = namedtuple('ContentsInfo', ['raster_settings', 'inline_images'])
+ContentsInfo = namedtuple('ContentsInfo', ['xobject_settings', 'inline_images'])
 
 
-def _interpret_contents(contentstream):
+def _normalize_stack(operations):
+    """Fix runs of qQ's in the stack
+
+    For some reason PyPDF2 converts runs of qqq, QQ, QQQq, etc. into single
+    operations.  Break this silliness up and issue each stack operation
+    individually so we don't lose count.
+
+    """
+    for operands, command in operations:
+        if re.match(br'Q*q+$', command):   # Zero or more Q, one or more q
+            for char in command:           # Split into individual bytes
+                yield ([], bytes([char]))  # Yield individual bytes
+        else:
+            yield (operands, command)
+
+
+def _interpret_contents(contentstream, initial_shorthand=UNIT_SQUARE):
     """Interpret the PDF content stream
 
     The stack represents the state of the PDF graphics stack.  We are only
@@ -123,27 +139,32 @@ def _interpret_contents(contentstream):
 
     operations = contentstream.operations
     stack = []
-    ctm = _matrix_from_shorthand(UNIT_SQUARE)
-    image_raster_settings = []
+    ctm = _matrix_from_shorthand(initial_shorthand)
+    xobject_settings = []
     inline_images = []
 
-    for op in operations:
+    for n, op in enumerate(_normalize_stack(operations)):
         operands, command = op
         if command == b'q':
             stack.append(ctm)
             if len(stack) > 32:
-                raise RuntimeError("PDF graphics stack overflow")
+                raise RuntimeError(
+                    "PDF graphics stack overflow, command %i" % n)
         elif command == b'Q':
-            ctm = stack.pop()
+            try:
+                ctm = stack.pop()
+            except IndexError:
+                raise RuntimeError(
+                    "PDF graphics stack underflow, command %i" % n)
         elif command == b'cm':
             ctm = matrix_mult(
                 _matrix_from_shorthand(operands), ctm)
         elif command == b'Do':
             image_name = operands[0]
-            raster = RasterSettings(
+            settings = XobjectSettings(
                 name=image_name, shorthand=_shorthand_from_matrix(ctm),
                 stack_depth=len(stack))
-            image_raster_settings.append(raster)
+            xobject_settings.append(settings)
         elif command == b'INLINE IMAGE':
             settings = operands['settings']
             inline = InlineSettings(
@@ -152,7 +173,7 @@ def _interpret_contents(contentstream):
             inline_images.append(inline)
 
     return ContentsInfo(
-        raster_settings=image_raster_settings,
+        xobject_settings=xobject_settings,
         inline_images=inline_images)
 
 
@@ -220,8 +241,8 @@ def _get_dpi(ctm_shorthand, image_size):
     return (dpi_w, dpi_h)
 
 
-def _find_page_inline_images(page, pageinfo, contentsinfo):
-    "Find inline images on the page"
+def _find_inline_images(contentsinfo):
+    "Find inline images in the contentstream"
 
     for n, inline in enumerate(contentsinfo.inline_images):
         image = {}
@@ -251,20 +272,44 @@ def _find_page_inline_images(page, pageinfo, contentsinfo):
         yield image
 
 
-def _find_page_regular_images(page, pageinfo, contentsinfo):
-    "Find images stored in XObject resources"
+def _image_xobjects(container):
+    """Search for all XObject-based images in the container
 
-    try:
-        page['/Resources']['/XObject']
-    except KeyError:
+    Usually the container is a page, but it could also be a Form XObject
+    that contains images. Filter out the Form XObjects which are dealt with
+    elsewhere.
+
+    Generate a sequence of tuples (image, xobj container), where container,
+    where xobj is the name of the object and image is the object itself,
+    since the object does not know its own name.
+
+    """
+
+    if '/Resources' not in container:
         return
-    for xobj in page['/Resources']['/XObject']:
-        # PyPDF2 returns the keys as an iterator
-        pdfimage = page['/Resources']['/XObject'][xobj]
-        if pdfimage['/Subtype'] != '/Image':
-            continue
+    resources = container['/Resources']
+    if '/XObject' not in resources:
+        return
+    for xobj in resources['/XObject']:
+        candidate = resources['/XObject'][xobj]
+        if candidate['/Subtype'] == '/Image':
+            image = candidate
+            yield (image, xobj)
+
+
+def _find_regular_images(container, contentsinfo):
+    """Find images stored in the container's /Resources /XObject
+
+    Usually the container is a page, but it could also be a Form XObject
+    that contains images.
+
+    Generates images with their DPI at time of drawing.
+
+    """
+
+    for pdfimage, xobj in _image_xobjects(container):
         image = {}
-        image['name'] = str(xobj)
+        image['name'] = xobj
         image['width'] = pdfimage['/Width']
         image['height'] = pdfimage['/Height']
         if '/BitsPerComponent' in pdfimage:
@@ -308,12 +353,12 @@ def _find_page_regular_images(page, pageinfo, contentsinfo):
 
         image['dpi_w'] = image['dpi_h'] = 0
 
-        for raster in contentsinfo.raster_settings:
+        for xobj in contentsinfo.xobject_settings:
             # Loop in case the same image is display multiple times on a page
-            if raster.name != image['name']:
+            if xobj.name != image['name']:
                 continue
 
-            if raster.stack_depth == 0 and _is_unit_square(raster.shorthand):
+            if xobj.stack_depth == 0 and _is_unit_square(xobj.shorthand):
                 # 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",
@@ -322,7 +367,7 @@ def _find_page_regular_images(page, pageinfo, contentsinfo):
                 continue
 
             dpi_w, dpi_h = _get_dpi(
-                raster.shorthand, (image['width'], image['height']))
+                xobj.shorthand, (image['width'], image['height']))
 
             # When image is used multiple times take the highest DPI it is
             # rendered at
@@ -330,16 +375,92 @@ def _find_page_regular_images(page, pageinfo, contentsinfo):
             image['dpi_h'] = max(dpi_h, image.get('dpi_h', 0))
 
         DPI_PREC = Decimal('1.000')
+        dpi = Decimal(image['dpi_w'] * image['dpi_h']).sqrt()
         image['dpi_w'] = Decimal(image['dpi_w']).quantize(DPI_PREC)
         image['dpi_h'] = Decimal(image['dpi_h']).quantize(DPI_PREC)
-        dpi = Decimal(image['dpi_w'] * image['dpi_h']).sqrt()
         image['dpi'] = dpi.quantize(DPI_PREC)
         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 _find_form_xobject_images(pdf, container, contentsinfo):
+    """Find any images that are in Form XObjects in the container
+
+    The container may be a page, or a parent Form XObject.
+
+    """
+    if '/Resources' not in container:
+        return
+    resources = container['/Resources']
+    if '/XObject' not in resources:
+        return
+    for xobj in resources['/XObject']:
+        candidate = resources['/XObject'][xobj]
+        if candidate['/Subtype'] != '/Form':
+            continue
+
+        form_xobject = candidate
+        for settings in contentsinfo.xobject_settings:
+            if settings.name != xobj:
+                continue
+
+            # Find images once for each time this Form XObject is drawn.
+            # This could be optimized to cache the multiple drawing events
+            # but in practice both Form XObjects and multiple drawing of the
+            # same object are both very rare.
+            ctm_shorthand = settings.shorthand
+            yield from _find_images(pdf, form_xobject, ctm_shorthand)
+
+
+def _find_images(pdf, container, shorthand=None):
+    """Find all individual instances of images drawn in the container
+
+    Usually the container is a page, but it may also be a Form XObject.
+
+    On a typical page images are stored inline or as regular images
+    in an XObject.
+
+    Form XObjects may include inline images, XObject images,
+    and recursively, other Form XObjects; and also vector drawing commands.
+
+    Every instance of an image being drawn somewhere is flattened and
+    treated as a unique image, since if the same image is drawn multiple times
+    on one page it may be drawn at differing resolutions, and our objective
+    is to find the resolution at which the page can be rastered without
+    downsampling.
+
+    """
+
+    if container.get('/Type') == '/Page':
+        # For a /Page the content stream is attached to the page's /Contents
+        page = container
+        contentstream = pypdf.pdf.ContentStream(page.getContents(), pdf)
+        initial_shorthand = shorthand or UNIT_SQUARE
+    elif container.get('/Type') == '/XObject' and \
+            container['/Subtype'] == '/Form':
+        # For a Form XObject that content stream is attached to the XObject
+        contentstream = pypdf.pdf.ContentStream(container, pdf)
+
+        # Set the CTM to the state it was when the "Do" operator was
+        # encountered that is drawing this instance of the Form XObject
+        ctm = _matrix_from_shorthand(shorthand or UNIT_SQUARE)
+
+        # A Form XObject may provide its own matrix to map form space into
+        # user space. Get this if one exists
+        form_matrix = _matrix_from_shorthand(
+                container.get('/Matrix', UNIT_SQUARE))
+
+        # Concatenate form matrix with CTM to ensure CTM is correct for
+        # drawing this instance of the XObject
+        ctm = matrix_mult(form_matrix, ctm)
+        initial_shorthand = _shorthand_from_matrix(ctm)
+    else:
+        return
+
+    contentsinfo = _interpret_contents(contentstream, initial_shorthand)
+
+    yield from _find_inline_images(contentsinfo)
+    yield from _find_regular_images(container, contentsinfo)
+    yield from _find_form_xobject_images(pdf, container, contentsinfo)
 
 
 def _page_has_text(pdf, page):
@@ -384,15 +505,8 @@ def _pdf_get_pageinfo(infile, pageno: int):
     except KeyError:
         pageinfo['rotate'] = 0
 
-    try:
-        contentstream = pypdf.pdf.ContentStream(page.getContents(), pdf)
-    except AttributeError as e:
-        return pageinfo
-
-    contentsinfo = _interpret_contents(contentstream)
-    pageinfo['images'] = [im for im in _find_page_images(
-                                page, pageinfo, contentsinfo)]
-
+    pageinfo['images'] = [im for im in
+                          _find_images(pdf, page)]
     if pageinfo['images']:
         xres = max(image['dpi_w'] for image in pageinfo['images'])
         yres = max(image['dpi_h'] for image in pageinfo['images'])
@@ -407,7 +521,6 @@ def _pdf_get_pageinfo(infile, pageno: int):
 
 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)]
 
 

ocrmypdf/pdfa.py

@@ -3,7 +3,6 @@
 #
 # Generate a PDFA_def.ps file for Ghostscript >= 9.14
 
-from __future__ import print_function, absolute_import, division
 from string import Template
 import codecs
 import pkg_resources
@@ -19,20 +18,15 @@ SRGB_ICC_PROFILE = pkg_resources.resource_filename(
 # files, from the Ghostscript documentation. Lines beginning with % are
 # comments. Python substitution variables have a '$' prefix.
 pdfa_def_template = u"""%!
-% This is a sample prefix file for creating a PDF/A document.
-% Feel free to modify entries marked with "Customize".
-% This assumes an ICC profile to reside in the file (ISO Coated sb.icc),
-% unless the user modifies the corresponding line below.
+% This is derived from Ghostscript's template for creating a PDF/A document.
+% This is a small PostScript program that includes some necessary information
+% to create a PDF/A compliant file.
 
 % Define entries in the document Info dictionary :
 /ICCProfile ($icc_profile)
 def
 
-[ /Title <$title>
-  /Author <$author>
-  /Subject <$subject>
-  /Keywords <$keywords>
-  /Creator <$creator>
+[$docinfo
   /DOCINFO pdfmark
 
 % Define an ICC profile :
@@ -71,7 +65,7 @@ def encode_text_string(s: str) -> str:
     From PDF 32000-1:2008 a string object may be included in hexademical form
     if it is enclosed in angle brackets.  For general Unicode the string should
     be UTF-16 (big endian) with byte order marks.  Many strings including all
-    ASCII strings fall could be encoded as PdfDocEncoding literals provided
+    ASCII strings could be encoded as PdfDocEncoding literals provided
     that certain Postscript sequences are escaped.  But it's far simpler to
     encode everything as UTF-16.
     '''
@@ -91,20 +85,30 @@ def encode_text_string(s: str) -> str:
 
 
 def _get_pdfa_def(icc_profile, icc_identifier, pdfmark):
-    pdfmark_utf16 = {k: encode_text_string(v) for k, v in pdfmark.items()}
+    # Ghostscript <= 9.21 has a bug where null entries in DOCINFO might produce
+    # ERROR: VMerror (-25) on closing pdfwrite device.
+    # https://bugs.ghostscript.com/show_bug.cgi?id=697684
+    # Work around this by only adding keys that have a nontrivial value
+    docinfo_keys = ('/Title', '/Author', '/Subject', '/Creator', '/Keywords')
+    docinfo_line_template = '  {key} <{value}>'
+
+    def docinfo_gen():
+        for key in docinfo_keys:
+            if key in pdfmark and pdfmark[key].strip() != '':
+                line = docinfo_line_template.format(
+                    key=key, value=encode_text_string(pdfmark[key]))
+                yield line
+
+    docinfo = '\n'.join(docinfo_gen())
 
     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', ''))
+                          docinfo=docinfo)
     return result
 
 
-def generate_pdfa_def(target_filename, pdfmark, icc='sRGB'):
+def generate_pdfa_ps(target_filename, pdfmark, icc='sRGB'):
     if icc == 'sRGB':
         icc_profile = SRGB_ICC_PROFILE
     else:
@@ -118,6 +122,10 @@ def generate_pdfa_def(target_filename, pdfmark, icc='sRGB'):
         f.write(ps)
 
 
+# The old name is generate_pdfa_def -- now deprecated
+generate_pdfa_def = generate_pdfa_ps
+
+
 def file_claims_pdfa(filename):
     """Determines if the file claims to be PDF/A compliant
 

pipeline.svg

@@ -1,338 +0,0 @@
-<?xml version="1.0" encoding="UTF-8" standalone="no"?>
-<!DOCTYPE svg PUBLIC "-//W3C//DTD SVG 1.1//EN"
- "http://www.w3.org/Graphics/SVG/1.1/DTD/svg11.dtd">
-<!-- Generated by graphviz version 2.38.0 (20140413.2041)
- -->
-<!-- Title: Pipeline: Pages: 1 -->
-<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,-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,-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="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="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="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="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="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="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="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="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="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="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="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>
-<!-- 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;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="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="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>
-<!-- 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="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="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;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>
-<!-- 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;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="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="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>
-<!-- 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="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>
-<!-- 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>
-<!-- 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="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="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 +0,0 @@
-[pytest]
-norecursedirs = lib .pc .git

requirements.txt

@@ -1,9 +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==3.3.0
-reportlab==3.2.0
-PyPDF2==1.26
-img2pdf==0.2.1
-cffi==1.5.2
+ruffus == 2.6.3
+Pillow == 4.0.0
+reportlab == 3.3.0
+PyPDF2 == 1.26
+img2pdf == 0.2.3
+cffi == 1.9.1

setup.cfg

@@ -6,4 +6,8 @@ test=pytest
 
 [check-manifest]
 ignore =
-	.github
+	.github
+
+[tool:pytest]
+norecursedirs = lib .pc .git output cache resources
+testpaths = tests

setup.py

@@ -9,7 +9,7 @@ if sys.version_info < (3, 4):
     print("Python 3.4 or newer is required", file=sys.stderr)
     sys.exit(1)
 
-from setuptools import setup  # nopep8
+from setuptools import setup, find_packages  # nopep8
 from subprocess import STDOUT, check_output, CalledProcessError  # nopep8
 from collections.abc import Mapping  # nopep8
 import re  # nopep8
@@ -155,12 +155,12 @@ if not forced and command.startswith('install') or \
         command in ['check', 'test', 'nosetests', 'easy_install']:
     check_external_program(
         program='tesseract',
-        need_version='3.03',  # limited by Travis CI / Ubuntu 12.04 backports
+        need_version='3.03',  # limited by Travis CI / Ubuntu 14.04 backports
         package={'darwin': 'tesseract', 'linux': 'tesseract-ocr'}
     )
     check_external_program(
         program='gs',
-        need_version='9.15',  # limited by Travis CI / Ubuntu 12.04 backports
+        need_version='9.15',  # limited by Travis CI / Ubuntu 14.04 backports
         package='ghostscript'
     )
     check_external_program(
@@ -171,7 +171,7 @@ if not forced and command.startswith('install') or \
     )
     check_external_program(
         program='qpdf',
-        need_version='5.0.0',   # limited by Travis CI / Ubuntu 12.04 backports
+        need_version='5.1.1',   # limited by Travis CI / Ubuntu 14.04 backports
         package='qpdf',
         version_check_args=['--version']
     )
@@ -191,11 +191,14 @@ setup(
     url='https://github.com/jbarlow83/OCRmyPDF',
     author='James R. Barlow',
     author_email='jim@purplerock.ca',
-    license='Public Domain',
-    packages=['ocrmypdf'],
+    license='MIT',
+    packages=find_packages(exclude=["tests", "tests.*"]),
     keywords=['PDF', 'OCR', 'optical character recognition', 'PDF/A', 'scanning'],
     classifiers=[
         "Programming Language :: Python :: 3",
+        "Programming Language :: Python :: 3.4",
+        "Programming Language :: Python :: 3.5",
+        "Programming Language :: Python :: 3.6",
         "Development Status :: 5 - Production/Stable",
         "Environment :: Console",
         "Intended Audience :: End Users/Desktop",
@@ -211,21 +214,20 @@ setup(
         "Topic :: Text Processing :: Linguistic",
         ],
     setup_requires=[
-        'setuptools_scm',
-        'cffi>=1.5.0',
-        'pytest-runner'
+        'setuptools_scm',       # so that version will work
+        'cffi>=1.9.1'           # to build the leptonica module
     ],
     use_scm_version={'version_scheme': 'post-release'},
     cffi_modules=[
-        'ocrmypdf/lib/compile_leptonica.py:ffi'
+        'ocrmypdf/lib/compile_leptonica.py:ffibuilder'
     ],
     install_requires=[
         'ruffus==2.6.3',        # pinned - ocrmypdf implements a 2.6.3 workaround
-        'Pillow>=3.1.0',        # Pillow is pretty stable
+        'Pillow>=4.0.0',        # Pillow < 4 has BytesIO/TIFF bug w/img2pdf 0.2.3
         '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
+        'img2pdf>=0.2.3',       # pure Python, so track HEAD closely
+        'cffi>=1.9.1'           # must be a setup and install requirement
     ],
     tests_require=tests_require,
     entry_points={

share/etc-apt-sources.list

@@ -1,4 +0,0 @@
-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

test_requirements.txt

@@ -1 +1,2 @@
-pytest>=2.7.2
+pytest >= 3.0
+pytest-helpers-namespace

tests/conftest.py

@@ -0,0 +1,135 @@
+#!/usr/bin/env python3
+# © 2017 James R. Barlow: github.com/jbarlow83
+
+import sys
+import os
+import platform
+
+pytest_plugins = ['helpers_namespace']
+
+import pytest
+from pathlib import Path
+from subprocess import Popen, PIPE
+
+
+if sys.version_info.major < 3:
+    print("Requires Python 3.4+")
+    sys.exit(1)
+
+
+@pytest.helpers.register
+def is_linux():
+    return platform.system() == 'Linux'
+
+
+@pytest.helpers.register
+def is_macos():
+    return platform.system() == 'Darwin'
+
+
+@pytest.helpers.register
+def running_in_docker():
+    # Docker creates a file named /.dockerenv (newer versions) or
+    # /.dockerinit (older) -- this is undocumented, not an offical test
+    return os.path.exists('/.dockerenv') or os.path.exists('/.dockerinit')
+
+
+@pytest.helpers.register
+def running_in_travis():
+    return os.environ.get('TRAVIS') == 'true'
+
+
+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 = [sys.executable, '-m', 'ocrmypdf']
+
+
+@pytest.helpers.register
+def spoof(**kwargs):
+    """Modify environment variables to override subprocess executables
+
+    spoof(program1='replacement', ...)
+
+    Before running any executable, ocrmypdf checks the environment variable
+    OCRMYPDF_PROGRAMNAME to override default program name/location, e.g.
+    OCRMYPDF_GS redirects from the system path Ghostscript ("gs") to elsewhere.
+
+    """
+    env = os.environ.copy()
+
+    for replace_program, with_spoof in kwargs.items():
+        spoofer = os.path.join(SPOOF_PATH, with_spoof)
+        if not os.access(spoofer, os.X_OK):
+            os.chmod(spoofer, 0o755)
+        env['OCRMYPDF_' + replace_program.upper()] = spoofer
+    return env
+
+
+@pytest.fixture
+def resources():
+    return Path(TESTS_ROOT) / 'resources'
+
+
+@pytest.fixture
+def ocrmypdf_exec():
+    return OCRMYPDF
+
+
+@pytest.fixture(scope="function")
+def outdir(tmpdir):
+    return Path(str(tmpdir))
+
+
+@pytest.fixture(scope="function")
+def outpdf(tmpdir):
+    return str(Path(str(tmpdir)) / 'out.pdf')
+
+
+@pytest.fixture(scope="function")
+def no_outpdf(tmpdir):
+    """This just documents the fact that a test is not expected to produce
+    output. Unfortunately an assertion failure inside a test fixture produces
+    an error rather than a test failure, so no testing is done. It's up to
+    the test to confirm that no output file was created."""
+    return str(Path(str(tmpdir)) / 'no_output.pdf')
+
+
+@pytest.helpers.register
+def check_ocrmypdf(input_file, output_file, *args, env=None):
+    "Run ocrmypdf and confirmed that a valid file was created"
+
+    p, out, err = run_ocrmypdf(input_file, output_file, *args, env=env)
+    #print(err)  # ensure py.test collects the output, use -s to view
+    assert p.returncode == 0, "<stderr>\n" + err + "\n</stderr>"
+    assert os.path.exists(str(output_file)), "Output file not created"
+    assert os.stat(str(output_file)).st_size > 100, "PDF too small or empty"
+    assert out == "", \
+        "The following was written to stdout and should not have been: \n" + \
+        "<stdout>\n" + out + "\n</stdout>"
+    return output_file
+
+
+@pytest.helpers.register
+def run_ocrmypdf(input_file, output_file, *args, env=None):
+    "Run ocrmypdf and let caller deal with results"
+
+    if env is None:
+        env = os.environ
+
+    p_args = OCRMYPDF + list(args) + [str(input_file), str(output_file)]
+    p = Popen(
+        p_args, close_fds=True, stdout=PIPE, stderr=PIPE,
+        universal_newlines=True, env=env)
+    out, err = p.communicate()
+    #print(err)
+
+    return p, out, err
+
+
+@pytest.helpers.register
+def first_page_dimensions(pdf):
+    from ocrmypdf import pageinfo
+    info = pageinfo.pdf_get_all_pageinfo(str(pdf))
+    page0 = info[0]
+    return (page0['width_inches'], page0['height_inches'])

tests/resources/README.rst

@@ -31,6 +31,9 @@ In some cases they were converted from one image format to another without other
     *   - LinnSequencer.jpg, linn.pdf, linn.txt
         - `Wikimedia: LinnSequencer`_
         - Creative Commons BY-SA 3.0
+    *   - typewriter.png, 2400dpi.pdf
+        - `Wikimedia: Triumph typewrtier text Linzensoep`_
+        * Creative Commons BY-SA 2.5
 
 
 Files generated for this project
@@ -61,6 +64,9 @@ under the terms of the license in LICENSE.rst.
     *   - epson.pdf
         - @lowesjam
         - a linearized PDF containing some unusual indirect objects, created by an Epson printer; printout of a Wikipedia article (CC BY-SA)
+    *   - formxobject.pdf
+        - @jbarlow83
+        - hand-crafted exotic PDF containing an image inside a Form XObject
     *   - francais.pdf
         - @jbarlow83
         - a page containing French accents (diacritics)  
@@ -76,6 +82,9 @@ under the terms of the license in LICENSE.rst.
     *   - missing_docinfo.pdf
         - @jbarlow83
         - PDF file with no /DocumentInfo section 
+    *   - overlay.pdf
+        - @maxandersen
+        - PDF file generated by PDFPen pro that triggered content stream parse errors
 
 Assemblies
 ==========
@@ -104,4 +113,6 @@ These test resources are assemblies from other previously mentioned files, relea
 
 .. _`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 
+.. _`Linux (Wikipedia Article)`: https://de.wikipedia.org/wiki/Linux 
+
+.. _`Wikimedia: Triumph typewrtier text Linzensoep`: https://commons.wikimedia.org/wiki/File:Triumph.typewriter_text_Linzensoep.gif

tests/spoof/tesseract_cache.py

@@ -37,6 +37,7 @@ def real_tesseract():
 def main():
     operation = sys.argv[-1]
     # For anything unexpected operation, defer to real tesseract binary
+    # Currently this includes all use of "--tesseract-config"
     if operation != 'hocr' and operation != 'pdf' and operation != 'stdout':
         real_tesseract()
         return  # Not reachable
@@ -52,6 +53,11 @@ def main():
         ['tesseract', '--version'],
         stderr=subprocess.STDOUT)
 
+    if b'4.00.00alpha' in tess_version:
+        # Tesseract 4.x alpha is a moving target, don't cache it
+        real_tesseract()
+        return
+
     m.update(tess_version)
 
     # Insert this source file into the hash function, to ensure that any
@@ -65,12 +71,21 @@ def main():
         lang = sys.argv[sys.argv.index('-l') + 1]
         m.update(lang.encode())
     except ValueError:
-        pass
-    try:
-        psm = sys.argv[sys.argv.index('-psm') + 1]
-        m.update(psm.encode())
-    except ValueError:
-        pass
+        m.update(b'default-lang')
+
+    psm_arg = ''
+    if '--psm' in sys.argv:
+        psm_arg = '--psm'
+    elif '-psm' in sys.argv:
+        psm_arg = '-psm'
+    if psm_arg:
+        try:
+            psm = sys.argv[sys.argv.index(psm_arg) + 1]
+            m.update(psm.encode())
+        except ValueError:
+            m.update(b'default-psm')
+    else:
+        m.update(b'default-psm')
 
     if operation == 'stdout' and psm != '0':
         real_tesseract()

tests/test_hocrtransform.py

@@ -2,11 +2,13 @@
 # © 2015 James R. Barlow: github.com/jbarlow83
 
 from ocrmypdf import hocrtransform
-from ocrmypdf.tesseract import HOCR_TEMPLATE
+from ocrmypdf.exec.tesseract import HOCR_TEMPLATE
+from ocrmypdf.exec import qpdf
 from reportlab.pdfgen.canvas import Canvas
 from PIL import Image
 from tempfile import NamedTemporaryFile
 from contextlib import suppress
+from pathlib import Path
 import os
 import shutil
 import pytest
@@ -15,47 +17,25 @@ import pytest
 import sys
 
 
-if sys.version_info.major < 3:
-    print("Requires Python 3.4+")
-    sys.exit(1)
-
-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', 'hocrtransform'))
-
-
-def setup_module():
-    with suppress(FileNotFoundError):
-        shutil.rmtree(TEST_OUTPUT)
-    with suppress(FileExistsError):
-        os.makedirs(TEST_OUTPUT)
-    with open(_make_output('blank.hocr'), 'w') as f:
+@pytest.fixture
+def blank_hocr(tmpdir):
+    filename = Path(str(tmpdir)) / "blank.hocr"
+    with open(str(filename), 'w') as f:
         f.write(HOCR_TEMPLATE)
+    return filename
 
 
-def _make_input(input_basename):
-    return os.path.join(TEST_RESOURCES, input_basename)
-
-
-def _make_output(output_basename):
-    return os.path.join(TEST_OUTPUT, output_basename)
-
-
-def test_mono_image():
+def test_mono_image(blank_hocr, outdir):
     im = Image.new('1', (8, 8), 0)
     for n in range(8):
         im.putpixel((n, n), 1)
-    im.save(_make_output('mono.tif'), format='TIFF')
-
-    hocr = hocrtransform.HocrTransform(_make_output('blank.hocr'), 300)
-    hocr.to_pdf(_make_output('mono.pdf'), imageFileName=_make_output('mono.tif'))
-
+    im.save(outdir / 'mono.tif', format='TIFF')
 
+    hocr = hocrtransform.HocrTransform(str(blank_hocr), 300)
+    hocr.to_pdf(
+        str(outdir / 'mono.pdf'), imageFileName=str(outdir / 'mono.tif'))
+
+    qpdf.check(str(outdir / 'mono.pdf'))
 
 
 

tests/test_pageinfo.py

@@ -14,38 +14,9 @@ import pytest
 import sys
 
 
-if sys.version_info.major < 3:
-    print("Requires Python 3.4+")
-    sys.exit(1)
-
-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', 'pageinfo'))
-
-
-def setup_module():
-    with suppress(FileNotFoundError):
-        shutil.rmtree(TEST_OUTPUT)
-    with suppress(FileExistsError):
-        os.makedirs(TEST_OUTPUT)
-
-
-def _make_input(input_basename):
-    return os.path.join(TEST_RESOURCES, input_basename)
-
-
-def _make_output(output_basename):
-    return os.path.join(TEST_OUTPUT, output_basename)
-
-
-def test_single_page_text():
-    filename = os.path.join(TEST_OUTPUT, 'text.pdf')
-    pdf = Canvas(filename, pagesize=(8*72, 6*72))
+def test_single_page_text(outdir):
+    filename = outdir / 'text.pdf'
+    pdf = Canvas(str(filename), pagesize=(8*72, 6*72))
     text = pdf.beginText()
     text.setFont('Helvetica', 12)
     text.setTextOrigin(1*72, 3*72)
@@ -55,7 +26,7 @@ def test_single_page_text():
     pdf.showPage()
     pdf.save()
 
-    pdfinfo = pageinfo.pdf_get_all_pageinfo(filename)
+    pdfinfo = pageinfo.pdf_get_all_pageinfo(str(filename))
 
     assert len(pdfinfo) == 1
     page = pdfinfo[0]
@@ -64,28 +35,26 @@ def test_single_page_text():
     assert len(page['images']) == 0
 
 
-def test_single_page_image():
-    filename = os.path.join(TEST_OUTPUT, 'image-mono.pdf')
+@pytest.mark.skipif(sys.version_info < (3, 5), reason="needs Path.read_bytes")
+def test_single_page_image(outdir):
+    filename = outdir / 'image-mono.pdf'
 
-    with NamedTemporaryFile(mode='wb+', suffix='.png') as im_tmp:
-        im = Image.new('1', (8, 8), 0)
-        for n in range(8):
-            im.putpixel((n, n), 1)
-        im.save(im_tmp.name, format='PNG')
+    im_tmp = outdir / 'tmp.png'
+    im = Image.new('1', (8, 8), 0)
+    for n in range(8):
+        im.putpixel((n, n), 1)
+    im.save(str(im_tmp), format='PNG')
 
-        imgsize = ((img2pdf.ImgSize.dpi, 8), (img2pdf.ImgSize.dpi, 8))
-        layout_fun = img2pdf.get_layout_fun(None, imgsize, None, None, None)
+    imgsize = ((img2pdf.ImgSize.dpi, 8), (img2pdf.ImgSize.dpi, 8))
+    layout_fun = img2pdf.get_layout_fun(None, imgsize, None, None, None)
 
-        im_tmp.seek(0)
-        im_bytes = im_tmp.read()
-        pdf_bytes = img2pdf.convert(
-                im_bytes, producer="img2pdf", with_pdfrw=False,
-                layout_fun=layout_fun)
+    im_bytes = im_tmp.read_bytes()
+    pdf_bytes = img2pdf.convert(
+            im_bytes, producer="img2pdf", with_pdfrw=False,
+            layout_fun=layout_fun)
+    filename.write_bytes(pdf_bytes)
 
-        with open(filename, 'wb') as pdf:
-            pdf.write(pdf_bytes)
-
-    pdfinfo = pageinfo.pdf_get_all_pageinfo(filename)
+    pdfinfo = pageinfo.pdf_get_all_pageinfo(str(filename))
 
     assert len(pdfinfo) == 1
     page = pdfinfo[0]
@@ -102,9 +71,9 @@ def test_single_page_image():
     assert abs(pdfimage['dpi_h'] - 8) < 1e-5
 
 
-def test_single_page_inline_image():
-    filename = os.path.join(TEST_OUTPUT, 'image-mono-inline.pdf')
-    pdf = Canvas(filename, pagesize=(8*72, 6*72))
+def test_single_page_inline_image(outdir):
+    filename = outdir / 'image-mono-inline.pdf'
+    pdf = Canvas(str(filename), pagesize=(8*72, 6*72))
     with NamedTemporaryFile() as im_tmp:
         im = Image.new('1', (8, 8), 0)
         for n in range(8):
@@ -115,7 +84,7 @@ def test_single_page_inline_image():
         pdf.showPage()
         pdf.save()
 
-    pdfinfo = pageinfo.pdf_get_all_pageinfo(filename)
+    pdfinfo = pageinfo.pdf_get_all_pageinfo(str(filename))
     print(pdfinfo)
     pdfimage = pdfinfo[0]['images'][0]
     assert (pdfimage['dpi_w'] - 8) < 1e-5
@@ -123,12 +92,19 @@ def test_single_page_inline_image():
     assert pdfimage['width'] == 8
 
 
-def test_jpeg():
-    filename = _make_input('c02-22.pdf')
+def test_jpeg(resources, outdir):
+    filename = resources / 'c02-22.pdf'
 
-    pdfinfo = pageinfo.pdf_get_all_pageinfo(filename)
+    pdfinfo = pageinfo.pdf_get_all_pageinfo(str(filename))
 
     pdfimage = pdfinfo[0]['images'][0]
     assert pdfimage['enc'] == 'jpeg'
     assert (pdfimage['dpi_w'] - 150) < 1e-5
 
+
+def test_form_xobject(resources):
+    filename = resources / 'formxobject.pdf'
+
+    pdfinfo = pageinfo.pdf_get_all_pageinfo(str(filename))
+    pdfimage = pdfinfo[0]['images'][0]
+    assert pdfimage['width'] == 50

tests/test_tess3.py

@@ -0,0 +1,28 @@
+#!/usr/bin/env python3
+# © 2017 James R. Barlow: github.com/jbarlow83
+
+import pytest
+from ocrmypdf.exceptions import ExitCode
+from ocrmypdf.exec import tesseract
+
+
+# Skip all tests in this file if not tesseract 3
+pytestmark = pytest.mark.skipif(tesseract.v4(),
+                                reason="tesseract 3.x required")
+
+
+def test_textonly_pdf_on_tess3(resources, no_outpdf):
+    p, _, _ = pytest.helpers.run_ocrmypdf(
+        resources / 'linn.pdf',
+        no_outpdf, '--pdf-renderer', 'tess4')
+
+    assert p.returncode == ExitCode.missing_dependency
+
+
+def test_oem_on_tess3(resources, no_outpdf):
+    p, _, err = pytest.helpers.run_ocrmypdf(
+        resources / 'aspect.pdf',
+        no_outpdf, '--tesseract-oem', '1')
+
+    assert p.returncode == ExitCode.ok
+    assert 'argument ignored' in err

tests/test_tess4.py

@@ -0,0 +1,113 @@
+#!/usr/bin/env python3
+# © 2017 James R. Barlow: github.com/jbarlow83
+
+import pytest
+from ocrmypdf.exceptions import ExitCode
+from ocrmypdf.exec import tesseract
+from ocrmypdf import pageinfo
+import sys
+import os
+import PyPDF2 as pypdf
+
+
+spoof = pytest.helpers.spoof
+
+
+def tess4_possible_location():
+    """The location of tesseract 4 may be OCRMYPDF_TESS4, OCRMYPDF_TESSERACT,
+    or the installed version on PATH."""
+    return os.environ.get('OCRMYPDF_TESS4') or \
+           os.environ.get('OCRMYPDF_TESSERACT') or \
+            'tesseract'
+
+
+@pytest.fixture
+def ensure_tess4():
+    return spoof(tesseract=tess4_possible_location())
+
+
+def tess4_available():
+    """Check if a tesseract 4 binary is available, even if it's not the
+    official "tesseract" on PATH
+
+    """
+    old_environ = os.environ.copy()
+    try:
+        os.environ['OCRMYPDF_TESSERACT'] = tess4_possible_location()
+        return tesseract.v4() and tesseract.has_textonly_pdf()
+    finally:
+        os.environ = old_environ
+
+
+# Skip all tests in this file if not tesseract 4
+pytestmark = pytest.mark.skipif(
+    not tess4_available(),
+    reason="tesseract 4.0 with textonly_pdf feature required")
+
+check_ocrmypdf = pytest.helpers.check_ocrmypdf
+run_ocrmypdf = pytest.helpers.run_ocrmypdf
+spoof = pytest.helpers.spoof
+
+
+def test_textonly_pdf(ensure_tess4, resources, outdir):
+    check_ocrmypdf(
+        resources / 'linn.pdf',
+        outdir / 'linn_textonly.pdf', '--pdf-renderer', 'tess4',
+        env=ensure_tess4)
+
+
+@pytest.mark.skipif(sys.version_info < (3, 5), reason="needs math.isclose")
+def test_pagesize_consistency_tess4(ensure_tess4, resources, outpdf):
+    from math import isclose
+
+    infile = resources / 'linn.pdf'
+
+    before_dims = pytest.helpers.first_page_dimensions(infile)
+
+    check_ocrmypdf(
+        infile,
+        outpdf, '--pdf-renderer', 'tess4',
+        '--clean', '--deskew', '--remove-background', '--clean-final',
+        env=ensure_tess4)
+
+    after_dims = pytest.helpers.first_page_dimensions(outpdf)
+
+    assert isclose(before_dims[0], after_dims[0])
+    assert isclose(before_dims[1], after_dims[1])
+
+
+@pytest.mark.parametrize('basename', ['graph_ocred.pdf', 'cardinal.pdf'])
+def test_skip_pages_does_not_replicate(
+        ensure_tess4, resources, basename, outdir):
+    infile = resources / basename
+    outpdf = outdir / basename
+
+    check_ocrmypdf(
+        infile,
+        outpdf, '--pdf-renderer', 'tess4', '--force-ocr',
+        '--tesseract-timeout', '0',
+        env=ensure_tess4
+    )
+
+    info_in = pageinfo.pdf_get_all_pageinfo(str(infile))
+
+    info = pageinfo.pdf_get_all_pageinfo(str(outpdf))
+    for page in info:
+        assert len(page['images']) == 1, "skipped page was replicated"
+
+    for n in range(len(info_in)):
+        assert info[n]['width_inches'] == info_in[n]['width_inches']
+
+
+def test_content_preservation(ensure_tess4, resources, outpdf):
+    infile = resources / 'masks.pdf'
+
+    check_ocrmypdf(
+        infile,
+        outpdf, '--pdf-renderer', 'tess4', '--tesseract-timeout', '0',
+        env=ensure_tess4
+    )
+
+    info = pageinfo.pdf_get_all_pageinfo(str(outpdf))
+    page = info[0]
+    assert len(page['images']) > 1, "masked were rasterized"