setup.py: for some reason, subpackages must be explicitly specified

There’s no reason text-only PDF shouldn’t become the default for
tesseract 4.

.dockerignore

@@ -0,0 +1,31 @@
+*.ipynb
+*.pdf
+*.pyc
+*.rst
+*.sublime*
+*/*.pyc
+*/*/*.pyc
+*/*/*/*.pyc
+*/*/*/*/*.pyc
+*/*/*/*/*/*.pyc
+*/*/*/*/*/*/*.pyc
+*/*/*/*/*/*/*/*.pyc
+.cache/
+.git/
+.ipynb_checkpoints/
+.ruffus_history.sqlite
+bin/
+build/
+dist/
+htmlcov/
+include/
+lib/
+MANIFEST.in
+ocrmypdf.egg-info/
+staging/
+tests/cache/
+tests/output/
+tests/resources/private/
+tmp/
+venv-3.4/
+venv-3.5/

.git_archival.txt

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

.gitattributes

@@ -0,0 +1,10 @@
+# Always use Unix convention for new lines
+* text eol=lf
+
+# These files are binary and should be left untouched
+# (binary is a macro for -text -diff)
+*.jar	binary
+*.pdf	binary
+*.PDF	binary
+
+.git_archival.txt  export-subst

.github/ISSUE_TEMPLATE

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

.gitignore

@@ -0,0 +1,34 @@
+# Development environment
+*.pyc
+*.sublime-*
+venv*/
+pyvenv.cfg
+tasks.py
+
+# Package building
+*.egg-info/
+.cache/
+.eggs/
+build/
+dist/
+wheelhouse/
+
+# Automatically generated files
+ocrmypdf/lib/_*.py
+ocrmypdf/version.py
+docs/_build/
+docs/_static/
+docs/_templates/
+
+# Code coverage
+.coverage
+htmlcov/
+
+# Testing
+log/
+/*.pdf
+.ipynb_checkpoints/
+tests/cache/
+tests/output/
+tests/resources/private/
+tmp/

.travis.yml

@@ -1,29 +1,46 @@
-
-language: generic
 sudo: required
 dist: trusty
+language: python
+
+cache: pip
+
+cache:
+    directories:
+        - $HOME/.ccache
+        - packages
+        - tests/cache
+
+python:
+    - "3.4"
+    - "3.5"
+    - "3.6"
+
+before_cache:
+    - rm -f $HOME/.cache/pip/log/debug.log
 
 before_install:
-  - sudo add-apt-repository ppa:heyarje/libav-11 -y
-  - sudo add-apt-repository ppa:alex-p/tesseract-ocr -y
-  - sudo add-apt-repository ppa:evl.ms/evil -y  # for a newer version (2.5.0) of pngquant
-  - sudo apt-get update -qq
-  - sudo apt-get install libleptonica-dev -y    # required to build jbig2enc
-  - sudo apt-get install zlib1g-dev -y          # required to build jbig2enc
- # - sudo apt-get install imagemagick -y         # required to convert logo to desktop icon
+    # 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
+
+install:
+    - pip install -r requirements.txt
+    - pip install -r test_requirements.txt
 
 script:
-  - export OCRMYPDF_VERSION=8.3.2
-  - bash build-appimage.sh
-  # remove previous installed libraries to ensure that the tests use the libraries of the AppImage
-  - sudo apt-get remove libleptonica-dev zlib1g-dev -y
-  - bash test/test-appimage.sh
-  - wget https://github.com/probonopd/uploadtool/raw/master/upload.sh
+    - python setup.py clean
+    - python setup.py install
+    - python setup.py test
 
-after_success:
-  - bash upload.sh OCRmyPDF*.AppImage
-
-branches:
-  except:
-    # Do not build tags that we create when we upload to GitHub Releases
-    - /^(?i:continuous)/
+os:
+    - linux

Dockerfile

@@ -0,0 +1,91 @@
+# OCRmyPDF
+#
+# VERSION               3.2
+FROM      debian:stretch
+MAINTAINER James R. Barlow <jim@purplerock.ca>
+
+# Add unprivileged user
+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"]

Dockerfile.polyglot

@@ -0,0 +1,16 @@
+# OCRmyPDF polyglot
+#
+# VERSION               3.2
+FROM      jbarlow83/ocrmypdf:latest
+MAINTAINER James R. Barlow <jim@purplerock.ca>
+
+# Update system and install our dependencies
+USER root
+RUN apt-get update && apt-get install -y --no-install-recommends \
+  tesseract-ocr-all 
+
+USER docker
+
+# Must use array form of ENTRYPOINT
+# Non-array form does not append other arguments, because that is "intuitive"
+ENTRYPOINT ["/application/docker-wrapper.sh"]

LICENSE.rst

@@ -0,0 +1,20 @@
+Copyright (c) 2013-2016, The OCRmyPDF Authors
+
+Permission is hereby granted, free of charge, to any person obtaining a
+copy of this software and associated documentation files (the
+"Software"), to deal in the Software without restriction, including
+without limitation the rights to use, copy, modify, merge, publish,
+distribute, sublicense, and/or sell copies of the Software, and to
+permit persons to whom the Software is furnished to do so, subject to
+the following conditions:
+
+The above copyright notice and this permission notice shall be included
+in all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS
+OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
+IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY
+CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT,
+TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE
+SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

MANIFEST.in

@@ -0,0 +1,49 @@
+# requirements
+include requirements.txt
+include test_requirements.txt
+include dev_requirements.txt
+
+# git
+include .git_archival.txt
+
+# docker
+include Dockerfile
+include Dockerfile.polyglot
+include .dockerignore
+
+# tests
+include pytest.ini
+recursive-include tests *.jpg
+recursive-include tests *.png
+recursive-include tests *.pdf
+recursive-include tests *.py
+recursive-include tests *.rst
+recursive-include tests *.txt
+recursive-exclude tests/output *
+recursive-exclude tests/output_pageinfo *
+recursive-exclude tests/resources/private *
+recursive-exclude tests/cache *
+
+# documentation
+include *.rst
+include pipeline.svg
+recursive-exclude .github * 
+recursive-include docs *.py
+recursive-include docs *.rst
+recursive-include docs *.svg
+recursive-exclude docs/_build *
+
+
+# support files
+recursive-include ocrmypdf/data *
+recursive-include share *
+include *.py
+exclude tasks.py
+
+# code
+recursive-include ocrmypdf *.py
+exclude ocrmypdf/lib/_leptonica.py
+include OCRmyPDF.sh
+include docker-wrapper.sh
+
+

OCRmyPDF.sh

@@ -0,0 +1,8 @@
+#!/bin/sh
+##############################################################################
+# Copyright (c) 2013-14: fritz-hh from Github (https://github.com/fritz-hh)
+##############################################################################
+
+echo "This script is deprecated. Use 'ocrmypdf' instead."
+
+python3 -m ocrmypdf.main "$@"

README.md

@@ -1,40 +0,0 @@
-# OCRmyPDF-AppImage  [![Build Status](https://travis-ci.com/FPille/OCRmyPDF-AppImage.svg?branch=master)](https://travis-ci.com/FPille/OCRmyPDF-AppImage)
-[AppImage][APPIMAGE] for [OCRmyPDF][OCRMYPDF]
-
-## Usage
-Download OCRmyPDF*.AppImage, make it executable and run it.
-```
-wget https://github.com/FPille/OCRmyPDF-AppImage/releases/download/continuous/OCRmyPDF-8.3.2-x86_64.AppImage
-chmod +x OCRmyPDF*.AppImage
-./OCRmyPDF*.AppImage --help
-```  
-  
-  Beside OCRmyPDF additional command line programs can be run with this AppImage like:
-* ghostscript
-* img2pdf
-* pngquant
-* python3.6
-* qpdf
-* tesseract
-* unpaper  
-
-Just use the program name as first parameter plus options:
-```
-./OCRmyPDF*.AppImage tesseract -v
-tesseract 4.1.0
- leptonica-1.76.0
-  libjpeg 8d (libjpeg-turbo 1.3.0) : libpng 1.2.50 : libtiff 4.0.3 : zlib 1.2.11 : libwebp 0.4.0 : libopenjp2 2.3.0
- Found AVX2
- Found AVX
- Found SSE
-```
-Or create a symlink for the corresponding program:
-```
-ln -s OCRmyPDF*.AppImage tesseract
-./tesseract --list-langs
-```
-
-
-[APPIMAGE]: https://appimage.org
-[OCRMYPDF]: https://github.com/jbarlow83/OCRmyPDF
-

README.rst

@@ -0,0 +1,119 @@
+OCRmyPDF
+========
+
+OCRmyPDF adds an OCR text layer to scanned PDF files, allowing them to
+be searched or copy-pasted.
+
+.. code-block:: bash
+
+   ocrmypdf                      # it's a scriptable command line program
+      -l eng+fra                 # it supports multiple languages
+      --rotate-pages             # it can fix pages that are misrotated
+      --deskew                   # it can deskew crooked PDFs!
+      --title "My PDF"           # it can change output metadata
+      --jobs 4                   # it uses multiple cores by default
+      --output-type pdfa         # it produces PDF/A by default
+      input_scanned.pdf          # takes PDF input (or images)
+      output_searchable.pdf      # produces validated PDF output
+
+
+Main features
+-------------
+
+-  Generates a searchable
+   `PDF/A <https://en.wikipedia.org/?title=PDF/A>`_ file from a regular PDF
+-  Places OCR text accurately below the image to ease copy / paste
+-  Keeps the exact resolution of the original embedded images
+-  When possible, inserts OCR information as a "lossless" operation without rendering vector information
+-  Keeps file size about the same
+-  If requested deskews and/or cleans the image before performing OCR
+-  Validates input and output files
+-  Provides debug mode to enable easy verification of the OCR results
+-  Processes pages in parallel when more than one CPU core is
+   available
+-  Uses `Tesseract OCR <https://github.com/tesseract-ocr/tesseract>`_ engine
+-  Supports 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>`_.
+
+Motivation
+----------
+
+I searched the web for a free command line tool to OCR PDF files on
+Linux/UNIX: I found many, but none of them were really satisfying.
+
+-  Either they produced PDF files with misplaced text under the image (making copy/paste impossible) 
+-  Or they did not handle accents and multilingual characters
+-  Or they changed the resolution of the embedded images
+-  Or they generated ridiculously large PDF files
+-  Or they crashed when trying to OCR some of my PDF files
+-  Or they did not produce valid PDF files (even though they were readable with my current PDF reader)
+-  On top of that none of them produced PDF/A files (format dedicated for long time storage)
+
+...so I decided to develop my own tool (using various existing scripts
+as an inspiration). 
+
+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``.
+
+For everyone else, `see our documentation <https://ocrmypdf.readthedocs.io/en/latest/installation.html>`_ for installation steps.
+
+Languages
+---------
+
+OCRmyPDF uses Tesseract for OCR, and relies on its language packs. For Linux users,
+you can often find packages that provide language packs:
+
+.. code-block:: bash
+
+   # Display a list of all Tesseract language packs
+   apt-cache search tesseract-ocr
+
+   # Debian/Ubuntu users
+   apt-get install tesseract-ocr-chi-sim  # Example: Install Chinese Simplified language back
+   
+You can then pass the ``-l LANG`` argument to OCRmyPDF to give a hint as to what languages it should search for. Multiple
+languages can be requested.
+
+Documentation and support
+-------------------------
+
+Once ocrmypdf is installed, the built-in help which explains the command syntax and options can be accessed via:
+
+.. code-block:: bash
+
+   ocrmypdf --help
+
+Our `documentation is served on Read the Docs <https://ocrmypdf.readthedocs.io/en/latest/index.html>`_.
+
+If you detect an issue, please:
+
+-  Check whether your issue is already known
+-  If no problem report exists on github, please create one here:
+   https://github.com/jbarlow83/OCRmyPDF/issues
+-  Describe your problem thoroughly
+-  Append the console output of the script when running the debug mode
+   (``-v 1`` option)
+-  If possible provide your input PDF file as well as the content of the
+   temporary folder (using a file sharing service like Dropbox)
+
+Press & Media
+-------------
+
+-  `c't 1-2014, page 59 <http://heise.de/-2279695>`_:
+   Detailed presentation of OCRmyPDF v1.0 in the leading German IT
+   magazine c't
+-  `heise Open Source, 09/2014: Texterkennung mit
+   OCRmyPDF <http://heise.de/-2356670>`_
+
+Disclaimer
+----------
+
+The software is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR
+CONDITIONS OF ANY KIND, either express or implied.

RELEASE_NOTES.rst

@@ -0,0 +1,489 @@
+RELEASE NOTES
+=============
+
+OCRmyPDF uses `semantic versioning <http://semver.org/>`_.
+
+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:
+=======
+
+-  Fixed a PDF/A creation issue with Ghostscript 9.20 (note: this fix did not actually work)
+
+
+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``
+-  Ability to specify multiple languages for multilingual documents is now advertised in documentation
+-  Reduced the file sizes of some test resources
+-  Cleaned up debug output
+-  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:
+=====
+
+-  New feature ``--remove-background`` to detect and erase the background of color and grayscale images
+-  Better documentation
+-  Fixed an issue with PDFs that draw images when the raster stack depth is zero 
+-  ocrmypdf can now redirect its output to stdout for use in a shell pipeline
+
+   +  This does not improve performance since temporary files are still used for buffering
+   +  Some output validation is disabled in this mode
+
+v4.2.5:
+=======
+
+-  Fixed an issue (#100) with PDFs that omit the optional /BitsPerComponent parameter on images
+-  Removed non-free file milk.pdf
+
+
+v4.2.4:
+=======
+
+-  Fixed an error (#90) caused by PDFs that use stencil masks properly
+-  Fixed handling of PDFs that try to draw images or stencil masks without properly setting up the graphics state (such images are now ignored for the purposes of calculating DPI)
+
+v4.2.3:
+=======
+
+-  Fixed an issue with PDFs that store page rotation (/Rotate) in an indirect object
+-  Integrated a few fixes to simplify downstream packaging (Debian)
+
+   +  The test suite no longer assumes it is installed
+   +  If running Linux, skip a test that passes Unicode on the command line
+
+-  Added a test case to check explicit masks and stencil masks
+-  Added a test case for indirect objects and linearized PDFs
+-  Deprecated the OCRmyPDF.sh shell script
+
+
+v4.2.2:
+=======
+
+-  Improvements to documentation
+
+
+v4.2.1:
+=======
+
+-  Fixed an issue where PDF pages that contained stencil masks would report an incorrect DPI and cause Ghostscript to abort
+-  Implemented stdin streaming
+
+
+v4.2:
+=====
+
+-  ocrmypdf will now try to convert single image files to PDFs if they are provided as input (#15)
+
+   +  This is a basic convenience feature. It only supports a single image and always makes the image fill the whole page.
+   +  For better control over image to PDF conversion, use ``img2pdf`` (one of ocrmypdf's dependencies)
+
+-  New argument ``--output-type {pdf|pdfa}`` allows disabling Ghostscript PDF/A generation
+
+   +  ``pdfa`` is the default, consistent with past behavior
+   +  ``pdf`` provides a workaround for users concerned about the increase in file size from Ghostscript forcing JBIG2 images to CCITT and transcoding JPEGs
+   +  ``pdf`` preserves as much as it can about the original file, including problems that PDF/A conversion fixes
+
+-  PDFs containing images with "non-square" pixel aspect ratios, such as 200x100 DPI, are now handled and converted properly (fixing a bug that caused to be cropped)
+-  ``--force-ocr`` rasterizes pages even if they contain no images
+
+   +  supports users who want to use OCRmyPDF to reconstruct text information in PDFs with damaged Unicode maps (copy and paste text does not match displayed text)
+   +  supports reinterpreting PDFs where text was rendered as curves for printing, and text needs to be recovered
+   +  fixes issue #82
+
+-  Fixes an issue where, with certain settings, monochrome images in PDFs would be converted to 8-bit grayscale, increasing file size (#79)
+-  Support for Ubuntu 12.04 LTS "precise" has been dropped in favor of (roughly) Ubuntu 14.04 LTS "trusty" 
+
+   +  Some Ubuntu "PPAs" (backports) are needed to make it work
+      
+-  Support for some older dependencies dropped
+
+   +  Ghostscript 9.15 or later is now required (available in Ubuntu trusty with backports)
+   +  Tesseract 3.03 or later is now required (available in Ubuntu trusty)
+
+-  Ghostscript now runs in "safer" mode where possible
+
+v4.1.4:
+=======
+
+-  Bug fix: monochrome images with an ICC profile attached were incorrectly converted to full color images if lossless reconstruction was not possible due to other settings; consequence was increased file size for these images
+
+
+v4.1.3:
+=======
+
+-  More helpful error message for PDFs with version 4 security handler
+-  Update usage instructions for Windows/Docker users
+-  Fix order of operations for matrix multiplication (no effect on most users)
+-  Add a few leptonica wrapper functions (no effect on most users)
+
+
+v4.1.2:
+=======
+
+-  Replace IEC sRGB ICC profile with Debian's sRGB (from icc-profiles-free) which is more compatible with the MIT license
+-  More helpful error message for an error related to certain types of malformed PDFs
+
+
+v4.1:
+=====
+
+-  ``--rotate-pages`` now only rotates pages when reasonably confidence in the orientation. This behavior can be adjusted with the new argument ``--rotate-pages-threshold``
+-  Fixed problems in error checking if ``unpaper`` is uninstalled or missing at run-time
+-  Fixed problems with "RethrownJobError" errors during error handling that suppressed the useful error messages
+
+
+v4.0.7:
+=======
+
+-  Minor correction to Ghostscript output settings
+
+
+v4.0.6:
+=======
+
+-  Update install instructions
+-  Provide a sRGB profile instead of using Ghostscript's
+
+
+v4.0.5:
+=======
+
+-  Remove some verbose debug messages from v4.0.4
+-  Fixed temporary that wasn't being deleted
+-  DPI is now calculated correctly for cropped images, along with other image transformations
+-  Inline images are now checked during DPI calculation instead of rejecting the image
+
+v4.0.4:
+=======
+
+Released with verbose debug message turned on. Do not use. Skip to v4.0.5.
+
+
+v4.0.3:
+=======
+
+New features
+------------
+
+-  Page orientations detected are now reported in a summary comment
+
+
+Fixes
+-----
+
+-  Show stack trace if unexpected errors occur
+-  Treat "too few characters" error message from Tesseract as a reason to skip that page rather than
+   abort the file
+-  Docker: fix blank JPEG2000 issue by insisting on Ghostscript versions that have this fixed
+
+
+v4.0.2:
+=======
+
+Fixes
+-----
+
+-  Fixed compatibility with Tesseract 3.04.01 release, particularly its different way of outputting
+   orientation information
+-  Improved handling of Tesseract errors and crashes
+-  Fixed use of chmod on Docker that broke most test cases
+
+
+v4.0.1:
+=======
+
+Fixes
+-----
+
+-  Fixed a KeyError if tesseract fails to find page orientation information
+
+
+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
+   fairly reliable but some false positives occur especially if there is not much text to work with. (#4) 
+-  Deskewing is now performed using Leptonica instead of unpaper. Leptonica is faster and more reliable
+   at image deskewing than unpaper.
+
+
+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)
+-  Fixed an issue where lossless reconstruction could misalign the graphics layer with respect to
+   text layer if the page had been cropped such that its origin is not (0, 0) (#49)
+
+
+Changes
+-------
+
+-  Logging output is now much easier to read
+-  ``--deskew`` is now performed by Leptonica instead of unpaper (#25)
+-  libffi is now required
+-  Some changes were made to the Docker and Travis build environments to support libffi
+-  ``--pdf-renderer=tesseract`` now displays a warning if the Tesseract version is less than 3.04.01,
+   the planned release that will include fixes to an important OCR text rendering bug in Tesseract 3.04.00.
+   You can also manually install ./share/sharp2.ttf on top of pdf.ttf in your Tesseract tessdata folder
+   to correct the problem.
+
+
+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:
+=====
+
+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
+   of vector and raster content would see the vector content preserved. Images may still be transcoded
+   during PDF/A conversion.  (``--deskew`` and ``--clean-final`` disable this mode, necessarily.)
+-  New argument ``--tesseract-pagesegmode`` allows you to pass page segmentation arguments to Tesseract OCR.
+   This helps for two column text and other situations that confuse Tesseract.
+-  Added a new "polyglot" version of the Docker image, that generates Tesseract with all languages packs installed,
+   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:
+=======
+
+Changes
+-------
+
+-  Fixed bug that caused incorrect page size and DPI calculations on documents with mixed page sizes
+
+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
+   needed to implement support
+-  Improved some error messages related to missing input files
+-  Fixed issue #20 - uppercase .PDF extension not accepted
+-  Fixed an issue where OCRmyPDF failed to text that certain pages contained previously OCR'ed text, 
+   such as OCR text produced by Tesseract 3.04
+-  Inserts /Creator tag into PDFs so that errors can be traced back to this project
+-  Added new option ``--pdf-renderer=auto``, to let OCRmyPDF pick the best PDF renderer. 
+   Currently it always chooses the 'hocrtransform' renderer but that behavior may change.
+-  Set up Travis CI automatic integration testing
+
+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
+-  Now installs ``ocrmypdf`` to ``/usr/local/bin`` or equivalent for system-wide
+   access and easier typing
+-  Improved command line syntax and usage help (``--help``)
+-  Tesseract 3.03+ PDF page rendering can be used instead for better positioning
+   of recognized text (``--pdf-renderer tesseract``)
+-  PDF metadata (title, author, keywords) are now transferred to the 
+   output PDF
+-  PDF metadata can also be set from the command line (``--title``, etc.)
+-  Automatic repairs malformed input PDFs if possible
+-  Added test cases to confirm everything is working
+-  Added option to skip extremely large pages that take too long to OCR and are 
+   often not OCRable (e.g. large scanned maps or diagrams); other pages are still
+   processed (``--skip-big``)
+-  Added option to kill Tesseract OCR process if it seems to be taking too long on
+   a page, while still processing other pages (``--tesseract-timeout``)
+-  Less common colorspaces (CMYK, palette) are now supported by conversion to RGB
+-  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
+-  OCR text is now rendered in the PDF as invisible text. Previous versions of OCRmyPDF
+   incorrectly rendered visible text with an image on top.
+-  All "tasks" in the pipeline can be executed in parallel on any
+   available CPUs, increasing performance
+-  The ``-o DPI`` argument has been phased out, in favor of ``--oversample DPI``, in
+   case we need ``-o OUTPUTFILE`` in the future
+-  Removed several dependencies, so it's easier to install.  We no 
+   longer use:
+   
+   - GNU parallel_
+   - ImageMagick_
+   - Python 2.7
+   - Poppler
+   - MuPDF_ tools
+   - shell scripts
+   - Java and JHOVE_
+   - libxml2
+
+-  Some new external dependencies are required or optional, compared to v2.x:
+
+   - Ghostscript 9.14+
+   - qpdf_ 5.0.0+
+   - Unpaper_ 6.1 (optional)
+   - some automatically managed Python packages
+  
+.. _ruffus: http://www.ruffus.org.uk/index.html
+.. _parallel: https://www.gnu.org/software/parallel/
+.. _ImageMagick: http://www.imagemagick.org/script/index.php
+.. _MuPDF: http://mupdf.com/docs/
+.. _qpdf: http://qpdf.sourceforge.net/
+.. _Unpaper: https://github.com/Flameeyes/unpaper
+.. _JHOVE: http://jhove.sourceforge.net/
+
+Release candidates
+------------------
+
+-  rc9:
+
+   - fix issue #118: report error if ghostscript iccprofiles are missing
+   - fixed another issue related to #111: PDF rasterized to palette file
+   - add support image files with a palette
+   - don't try to validate PDF file after an exception occurs
+
+-  rc8:
+
+   - fix issue #111: exception thrown if PDF is missing DocumentInfo dictionary
+
+-  rc7:
+
+   - fix error when installing direct from pip, "no such file 'requirements.txt'"
+
+-  rc6:
+
+   - dropped libxml2 (Python lxml) since Python 3's internal XML parser is sufficient
+   - set up Docker container
+   - fix Unicode errors if recognized text contains Unicode characters and system locale is not UTF-8
+
+-  rc5:
+
+   - dropped Java and JHOVE in favour of qpdf
+   - improved command line error output
+   - additional tests and bug fixes
+   - tested on Ubuntu 14.04 LTS
+
+-  rc4:
+
+   - dropped MuPDF in favour of qpdf
+   - fixed some installer issues and errors in installation instructions
+   - improve performance: run Ghostscript with multithreaded rendering
+   - improve performance: use multiple cores by default
+   - bug fix: checking for wrong exception on process timeout 
+
+-  rc3: skipping version number intentionally to avoid confusion with Tesseract
+-  rc2: first release for public testing to test-PyPI, Github
+-  rc1: testing release process
+
+Compatibility notes
+-------------------
+
+-  ``./OCRmyPDF.sh`` script is still available for now
+-  Stacking the verbosity option like ``-vvv`` is no longer supported
+
+-  The configuration file ``config.sh`` has been removed.  Instead, you can
+   feed a file to the arguments for common settings:
+
+::
+
+   ocrmypdf input.pdf output.pdf @settings.txt
+
+where ``settings.txt`` contains *one argument per line*, for example:
+
+::
+
+   -l 
+   deu 
+   --author 
+   A. Merkel 
+   --pdf-renderer 
+   tesseract
+
+
+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.
+
+-  ``--pdf-renderer tesseract`` will output files with an incorrect page size in Tesseract 3.03,
+   due to a bug in Tesseract.
+
+-  PDF files containing "inline images" are not supported and won't be for the 3.0 release. Scanned
+   images almost never contain inline images.
+
+
+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>`_.

appimage/AppRun.sh

@@ -1,105 +0,0 @@
-#! /bin/bash
-
-HERE="$(dirname "$(readlink -f "${0}")")"
-
-export PATH="$HERE/usr/bin:$HERE/usr/local/bin:$HERE/usr/python/bin:$PATH"
-export LD_PRELOAD="$HERE/usr/lib/liblept.so.5"
-export LD_LIBRARY_PATH="$HERE/usr/lib:$HERE/usr/lib/x86_64-linux-gnu:$LD_LIBRARY_PATH"
-export TESSDATA_PREFIX="$HERE/usr/share/tesseract-ocr/4.00/tessdata"
-export GS_LIB="$HERE/usr/share/ghostscript/9.26/lib:$HERE/usr/share/ghostscript/9.26/Resource:$HERE/usr/share/ghostscript/9.26/Resource/Init"
-
-# Allow the AppImage to be symlinked to e.g., /usr/bin/commandname
-# or called with ./Some*.AppImage commandname ...
-# refer to https://github.com/AppImage/AppImageKit/wiki/Bundling-command-line-tools
-
-if [ ! -z "$APPIMAGE" ] ; then
-  BINARY_NAME=$(basename "$ARGV0")
-else
-  BINARY_NAME=$(basename "$0")
-  export APPDIR="$HERE"       # required for the wrapper scripts of linuxdeploy-plugin-python
-fi
-
-usage() {
-echo "
-==============================================================================
-                          AppImage for OCRmyPDF
-==============================================================================
-OCRmyPDF adds an OCR text layer to scanned PDF files, allowing them to be
-searched or copy-pasted.
-
-usage:
-$ARGV0 [ocrmypdf] [--help] [--list-programs]
-                                 [--list-licenses] [--show-license]
-
-ocrmypdf                    execute OCRmyPDF
-
---help                      show this help message
-
---list-programs             list all programs contained in this AppImage
-
---list-licenses             list all licenses contained in this AppImage
-
---show-license [LICENSE]    show content of license file
-"
-}
-
-if [ "$1" == "--help" ] ; then
-    usage
-    exit $?
-fi
-
-if [ "$1" == "--list-programs" ] ; then
-    pushd "$HERE"
-    echo ""
-    echo "Run \"$ARGV0\" with one of the following arguments to run the respective program."
-    echo ""
-    find . -type f -perm /111 ! -path '*/lib/*' -execdir basename {} ";" | sort -u | column
-    echo ""
-    exit $?
-fi
-
-if [ "$1" == "--list-licenses" ] ; then
-    pushd "$HERE"
-    echo ""
-    echo "Run \"$ARGV0\" with one of the following arguments to display the respective license file."
-    echo ""
-    find . -type f \( ! -path '*/tesseract-ocr-*' -o -path '*/tesseract-ocr-eng/*' \) \
-        \( -iname "license*" -o -iname "*copyright*" -o -iname "*copying*" \) -printf "--show-license %P\n" | sort | column
-    echo ""
-    exit $?
-fi
-
-if [ "$1" == "--show-license" ] ; then
-    pushd "$HERE"
-    shift
-    if [ -f "$1" ] ; then
-        less -N "$1"
-        exit $?
-    else
-        echo "\"$1\" is not a valid license file path."
-        exit 1
-    fi
-fi
-
-if [ ! -z "$1" ] && [ -e "$HERE/bin/$1" ] ; then
-    MAIN="$HERE/bin/$1" ; shift
-elif [ ! -z "$1" ] && [ -e "$HERE/usr/bin/$1" ] ; then
-    MAIN="$HERE/usr/bin/$1" ; shift
-elif [ ! -z "$1" ] && [ -e "$HERE/usr/python/bin/$1" ] ; then
-    MAIN="$HERE/usr/python/bin/$1" ; shift
-elif [ ! -z "$1" ] && [ -e "$HERE/usr/local/bin/$1" ] ; then
-    MAIN="$HERE/usr/local/bin/$1" ; shift
-elif [ -e "$HERE/bin/$BINARY_NAME" ] ; then
-    MAIN="$HERE/bin/$BINARY_NAME"
-elif [ -e "$HERE/usr/bin/$BINARY_NAME" ] ; then
-    MAIN="$HERE/usr/bin/$BINARY_NAME"
-elif [ -e "$HERE/usr/python/bin/$BINARY_NAME" ] ; then
-    MAIN="$HERE/usr/python/bin/$BINARY_NAME"
-elif [ -e "$HERE/usr/local/bin/$BINARY_NAME" ] ; then
-    MAIN="$HERE/usr/local/bin/$BINARY_NAME"
-else
-    usage
-    exit $?
-fi
-
-exec "${MAIN}" "$@"

build-appimage.sh

@@ -1,120 +0,0 @@
-#! /bin/bash
-
-set -x
-set -e
-
-# use RAM disk if possible
-if [ "$CI" == "" ] && [ -d /dev/shm ]; then
-    TEMP_BASE=/dev/shm
-else
-    TEMP_BASE=/tmp
-fi
-
-BUILD_DIR=$(mktemp -d -p "$TEMP_BASE" OCRmyPDF-AppImage-build-XXXXXX)
-
-cleanup () {
-    if [ -d "$BUILD_DIR" ]; then
-        rm -rf "$BUILD_DIR"
-    fi
-}
-
-trap cleanup EXIT
-
-# store repo root as variable
-REPO_ROOT=$(readlink -f "$(dirname "$(dirname "$0")")")
-OLD_CWD=$(readlink -f .)
-
-pushd "$BUILD_DIR"
-
-mkdir -p AppDir
-mkdir -p PackageDir
-mkdir -p jbig2
-
-# download linuxdeploy AppImage and linuxdeploy-plugin-python AppImage
-wget https://github.com/TheAssassin/linuxdeploy/releases/download/continuous/linuxdeploy-x86_64.AppImage
-# wget https://github.com/niess/linuxdeploy-plugin-python/releases/download/continuous/linuxdeploy-plugin-python-x86_64.AppImage
-
-# use adapted linuxdeploy-plugin-python instead of the original one (otherwise OCRmyPDF breaks)
-wget https://github.com/FPille/linuxdeploy-plugin-python/releases/download/continuous/linuxdeploy-plugin-python-x86_64.AppImage
-
-chmod +x linuxdeploy*.AppImage
-
-
-ARCH=$(uname -i)
-export ARCH
-
-
-# .desktop file
-cat > ocrmypdf.desktop <<\EOF
-[Desktop Entry]
-Name=ocrmypdf
-Type=Application
-Exec=ocrmypdf
-Icon=ocrmypdf
-Terminal=true
-Comment=OCRmyPDF adds an OCR text layer to scanned PDF files, allowing them to be searched
-Categories=Graphics;Scanning;OCR;
-EOF
-
-
-# download logo and convert it to desktop icon
-# requires Imagemagick (convert)
-wget https://raw.githubusercontent.com/jbarlow83/OCRmyPDF/master/docs/images/logo-social.png
-convert logo-social.png -resize 512x512\> -size 512x512 xc:white +swap -gravity center -composite ocrmypdf.png
-
-
-# download and intsall packages required by OCRmyPDF
-pushd PackageDir
-packages=(tesseract-ocr tesseract-ocr-all libavformat56 ghostscript qpdf pngquant)
-
-for i in "${packages[@]}"
-do
-    apt-get -d -o dir::cache="$PWD" -o Debug::NoLocking=1 --reinstall install "$i" -y
-done
-
-wget -q 'https://www.dropbox.com/s/vaq0kbwi6e6au80/unpaper_6.1-1.deb?raw=1' -O unpaper_6.1-1.deb
-
-find . -type f -name \*.deb -exec dpkg-deb -X {} "$BUILD_DIR"/AppDir \;
-popd
-
-
-# compile and install jbig2
-# requires libleptonica-dev, zlib1g-dev
-wget -q https://github.com/agl/jbig2enc/archive/0.29.tar.gz -O - | \
-     tar xz -C jbig2 --strip-components=1
-pushd jbig2
-./autogen.sh
-./configure --prefix="$BUILD_DIR"/AppDir/usr
-make && make install
-popd
-
-pushd "$BUILD_DIR"/AppDir
-# add some tools to AppDir
-#cp -f   /usr/bin/column     ./usr/bin/
-#cp -f   /bin/less           ./usr/bin/
-
-# remove unnecessary data from AppDir
-[ -d bin ] && rm -rf ./bin
-[ -d etc ] && rm -rf ./etc
-[ -d var ] && rm -rf ./var
-popd
-
-
-# export LD_LIBRARY_PATH so that dependencies of shared libraries can be deployed by linuxdeploy-x86_64.AppImage
-export LD_LIBRARY_PATH="$BUILD_DIR/AppDir/usr/lib:$BUILD_DIR/AppDir/usr/lib/x86_64-linux-gnu:$LD_LIBRARY_PATH"
-
-#OCRMYPDF_VERSION=8.3.2   # exported in .travis.yml file
-export PIP_REQUIREMENTS="ocrmypdf==$OCRMYPDF_VERSION"
-export VERSION="$OCRMYPDF_VERSION"
-export OUTPUT=OCRmyPDF-"$VERSION"-"$ARCH".AppImage
-export PYTHON_SOURCE=https://www.python.org/ftp/python/3.6.8/Python-3.6.8.tgz
-
-./linuxdeploy-x86_64.AppImage --appdir AppDir --plugin python \
-    -d ocrmypdf.desktop -i ocrmypdf.png \
-    --custom-apprun "$REPO_ROOT"/appimage/AppRun.sh --output appimage
-
-
-# move AppImage back to old CWD
-mv "$OUTPUT" "$OLD_CWD"/
-
-popd

dev_requirements.txt

@@ -0,0 +1,10 @@
+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

docker-wrapper.sh

@@ -0,0 +1,5 @@
+#!/bin/bash
+
+. /appenv/bin/activate
+cd /home/docker
+exec ocrmypdf "$@"

docs/batch.rst

@@ -0,0 +1,124 @@
+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.
+
+.. code-block:: bash
+
+	parallel -j 2 ocrmypdf '{}' 'output/{}' ::: *.pdf
+
+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/bitmap_vs_svg.svg

@@ -0,0 +1,35 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<svg xmlns="http://www.w3.org/2000/svg" width="100%" height="100%" viewBox="0 0 915 585" xmlns:xlink="http://www.w3.org/1999/xlink">
+<defs>
+<linearGradient id="b" y2="445" gradientUnits="userSpaceOnUse" y1="179" gradientTransform="translate(0 -2.06)" x2="-29.7" x1="322">
+<stop stop-color="#333" offset="0"/>
+<stop stop-color="#fff" stop-opacity="0" offset="1"/>
+</linearGradient>
+<linearGradient id="a" y2="414" gradientUnits="userSpaceOnUse" y1="159" x2="490" x1="815">
+<stop stop-color="#33f" offset="0"/>
+<stop stop-color="#3f3fff" stop-opacity="0" offset="1"/>
+</linearGradient>
+</defs>
+<path fill="url(#b)" d="m403 247c-12 115-135 122-368 123-4.3-1.07-7.32-7.33-6-41 76-37 151-124 167-236 93 123 201 40.9 207 154z"/>
+<g stroke-width="3.45" fill="none">
+<path stroke="#000" d="m11.8 11.8h411v411l-411 0.01v-411z"/>
+<path stroke="#448" d="m489 11.7h415v411h-415v-411z"/>
+</g>
+<path d="m876 244c-12 115-133 120-366 121-6-14-10-40-3-43 76-37.3 136-106 152-218 38 48 209 101 217 140z" fill="url(#a)"/>
+<g id="RasterLarge" transform="matrix(1.36 0 0 1.28 -161 -636)">
+<path fill="#999" d="m287 730h-30v-60h20v20h10v10h10v10h20v10h40v-10h20v-20h10v-20h-10v-10h-10v-10h-40v-10h-30v-10h-20v-10h-10v-10h-10v-60h10v-10h10v-10h10v-10h90v10h30v60h-20v-10h-10v-20h-10v-10h-20v-10h-30v10h-20v10h-10v20h10v20h30v10h30v10h30v10h10v10h10v10h10v60h-10v10h-10v10h-10v10h-100v-10z"/>
+<path fill="#555" d="m297 730h-30v-10h-10v-50h20v20h10v20h10 10v10h60v-10h10v-10h10v-40h-20v-10h-20v-10h-40v-10h-20v-10h-20v-20h-10v-50h10v-10h10v-10h20v-10h70v10h30v10h10v50h-20v-20h-10v-20h-20v-10h-50v10h-10v10h-10v30h10v10h20v10h30v10h30v10h20v10h10v10h10v50h-10v20h-10v10h-20v10h-80z"/>
+<path d="m307 730h-30v-10h-20v-50h20v30h10v10h10v10h70v-10h20v-50h-10v-10h-20v-10h-40v-10h-30v-10h-10v-10h-10v-20h-10v-30h10v-20h20v-10h20v-10h50v10h30v10h20v50h-20v-30h-10v-10h-10v-10h-70v10h-10v40h10v10h10v10h30v10h40v10h20v10h10v20h10v40h-10v20h-20v10h-30v10h-50v-10z"/>
+</g>
+<g font-size="40" font-family="sans-serif" text-anchor="middle">
+<g font-size="100">
+<text y="518" x="210">Raster</text>
+<text y="518" x="695" fill="#338">Vector</text>
+</g>
+<text y="563" x="210">.jpeg  .gif  .png</text>
+<text y="563" x="696" fill="#338">.svg</text>
+</g>
+<path id="VectorLarge" fill="#005" d="m661 294v-62.5l23.4 0.184c0.678 20.8 7.32 36.3 19.9 46.4 12.7 9.93 32.1 14.9 57.9 14.9 24.1 0 42.5-4.29 55.1-12.9 12.7-8.71 19.1-21.3 19.1-37.9 0-13.2-3.86-23.4-11.6-30.5-7.59-7.11-23.7-14-48.4-20.8l-40.1-10.9c-29-7.97-49.5-17.9-61.4-29.8-11.8-11.9-17.7-28.2-17.7-48.9 0-23.3 9.15-41.4 27.4-54.3 18.3-12.9 44-19.3 77.1-19.3 14.1 0 29.6 1.41 46.4 4.23 16.8 2.7 34.7 6.68 53.7 12v58.5h-23c-2.3-19.4-9.49-33.4-21.6-41.9-11.9-8.71-30.2-13.1-54.7-13.1-21.4 0-37.7 3.99-49 12-11.1 7.85-16.7 19.3-16.7 34.4 0 13.1 4.2 23.4 12.6 30.9 8.4 7.48 26.2 14.9 53.5 22.3l37.6 10.1c27.5 7.48 47.1 17 58.8 28.7 11.8 11.5 17.7 27 17.7 46.5 0 26.6-9.42 46.7-28.3 60.2s-46.9 20.2-84.2 20.2c-16.7 0-33.7-1.53-51-4.6-18-3-35-7-53-13z"/>
+<use xlink:href="#VectorLarge" transform="matrix(.17 0 0 .17 392 313)"/>
+<use xlink:href="#RasterLarge" transform="matrix(.173 0 0 .173 -8.25 314)" height="100%" width="100%" y="0" x="0"/>
+</svg>

docs/conf.py

@@ -0,0 +1,350 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+#
+# ocrmypdf documentation build configuration file, created by
+# sphinx-quickstart on Sun Sep  4 14:29:43 2016.
+#
+# This file is execfile()d with the current directory set to its
+# containing dir.
+#
+# Note that not all possible configuration values are present in this
+# autogenerated file.
+#
+# All configuration values have a default; values that are commented out
+# serve to show the default.
+
+# If extensions (or modules to document with autodoc) are in another directory,
+# add these directories to sys.path here. If the directory is relative to the
+# documentation root, use os.path.abspath to make it absolute, like shown here.
+#
+# import os
+# import sys
+# sys.path.insert(0, os.path.abspath('.'))
+
+# -- General configuration ------------------------------------------------
+
+# If your documentation needs a minimal Sphinx version, state it here.
+#
+# needs_sphinx = '1.0'
+
+# Add any Sphinx extension module names here, as strings. They can be
+# extensions coming with Sphinx (named 'sphinx.ext.*') or your custom
+# ones.
+extensions = [
+    # 'sphinx.ext.mathjax',
+]
+
+# Add any paths that contain templates here, relative to this directory.
+templates_path = ['_templates']
+
+# The suffix(es) of source filenames.
+# You can specify multiple suffix as a list of string:
+#
+# source_suffix = ['.rst', '.md']
+source_suffix = '.rst'
+
+# The encoding of source files.
+#
+# source_encoding = 'utf-8-sig'
+
+# The master toctree document.
+master_doc = 'index'
+
+# General information about the project.
+project = 'ocrmypdf'
+copyright = '2017, James R. Barlow'
+author = 'James R. Barlow'
+
+# The version info for the project you're documenting, acts as replacement for
+# |version| and |release|, also used in various other places throughout the
+# built documents.
+#
+# The short X.Y version.
+from ocrmypdf import VERSION as OCRMYPDF_VERSION
+
+_version_parts = OCRMYPDF_VERSION.split('.')
+
+version = '.'.join(_version_parts[0:2])
+# The full version, including alpha/beta/rc tags.
+release = OCRMYPDF_VERSION
+
+# The language for content autogenerated by Sphinx. Refer to documentation
+# for a list of supported languages.
+#
+# This is also used if you do content translation via gettext catalogs.
+# Usually you set "language" from the command line for these cases.
+language = None
+
+# There are two options for replacing |today|: either, you set today to some
+# non-false value, then it is used:
+#
+# today = ''
+#
+# Else, today_fmt is used as the format for a strftime call.
+#
+today_fmt = '%Y-%m-%d'
+
+# List of patterns, relative to source directory, that match files and
+# directories to ignore when looking for source files.
+# This patterns also effect to html_static_path and html_extra_path
+exclude_patterns = ['_build', 'Thumbs.db', '.DS_Store']
+
+# The reST default role (used for this markup: `text`) to use for all
+# documents.
+#
+# default_role = None
+
+# If true, '()' will be appended to :func: etc. cross-reference text.
+#
+# add_function_parentheses = True
+
+# If true, the current module name will be prepended to all description
+# unit titles (such as .. function::).
+#
+# add_module_names = True
+
+# If true, sectionauthor and moduleauthor directives will be shown in the
+# output. They are ignored by default.
+#
+# show_authors = False
+
+# The name of the Pygments (syntax highlighting) style to use.
+pygments_style = 'sphinx'
+
+# A list of ignored prefixes for module index sorting.
+# modindex_common_prefix = []
+
+# If true, keep warnings as "system message" paragraphs in the built documents.
+# keep_warnings = False
+
+# If true, `todo` and `todoList` produce output, else they produce nothing.
+todo_include_todos = False
+
+
+# -- Options for HTML output ----------------------------------------------
+
+import sphinx_rtd_theme
+
+# The theme to use for HTML and HTML Help pages.  See the documentation for
+# a list of builtin themes.
+#
+html_theme = 'sphinx_rtd_theme'
+html_theme_path = [sphinx_rtd_theme.get_html_theme_path()]
+
+# Theme options are theme-specific and customize the look and feel of a theme
+# further.  For a list of options available for each theme, see the
+# documentation.
+#
+html_theme_options = {
+    'display_version': False
+}
+
+# Add any paths that contain custom themes here, relative to this directory.
+# html_theme_path = []
+
+# The name for this set of Sphinx documents.
+# "<project> v<release> documentation" by default.
+#
+# html_title = 'ocrmypdf v4.2'
+
+# A shorter title for the navigation bar.  Default is the same as html_title.
+#
+# html_short_title = None
+
+# The name of an image file (relative to this directory) to place at the top
+# of the sidebar.
+#
+# html_logo = None
+
+# The name of an image file (relative to this directory) to use as a favicon of
+# the docs.  This file should be a Windows icon file (.ico) being 16x16 or 32x32
+# pixels large.
+#
+# html_favicon = None
+
+# Add any paths that contain custom static files (such as style sheets) here,
+# relative to this directory. They are copied after the builtin static files,
+# so a file named "default.css" will overwrite the builtin "default.css".
+html_static_path = ['_static']
+
+# Add any extra paths that contain custom files (such as robots.txt or
+# .htaccess) here, relative to this directory. These files are copied
+# directly to the root of the documentation.
+#
+# html_extra_path = []
+
+# If not None, a 'Last updated on:' timestamp is inserted at every page
+# bottom, using the given strftime format.
+# The empty string is equivalent to '%b %d, %Y'.
+#
+# html_last_updated_fmt = None
+
+# If true, SmartyPants will be used to convert quotes and dashes to
+# typographically correct entities.
+#
+# html_use_smartypants = True
+
+# Custom sidebar templates, maps document names to template names.
+#
+# html_sidebars = {}
+
+# Additional templates that should be rendered to pages, maps page names to
+# template names.
+#
+# html_additional_pages = {}
+
+# If false, no module index is generated.
+#
+# html_domain_indices = True
+
+# If false, no index is generated.
+#
+# html_use_index = True
+
+# If true, the index is split into individual pages for each letter.
+#
+# html_split_index = False
+
+# If true, links to the reST sources are added to the pages.
+#
+# html_show_sourcelink = True
+
+# If true, "Created using Sphinx" is shown in the HTML footer. Default is True.
+#
+# html_show_sphinx = True
+
+# If true, "(C) Copyright ..." is shown in the HTML footer. Default is True.
+#
+# html_show_copyright = True
+
+# If true, an OpenSearch description file will be output, and all pages will
+# contain a <link> tag referring to it.  The value of this option must be the
+# base URL from which the finished HTML is served.
+#
+# html_use_opensearch = ''
+
+# This is the file name suffix for HTML files (e.g. ".xhtml").
+# html_file_suffix = None
+
+# Language to be used for generating the HTML full-text search index.
+# Sphinx supports the following languages:
+#   'da', 'de', 'en', 'es', 'fi', 'fr', 'h', 'it', 'ja'
+#   'nl', 'no', 'pt', 'ro', 'r', 'sv', 'tr', 'zh'
+#
+# html_search_language = 'en'
+
+# A dictionary with options for the search language support, empty by default.
+# 'ja' uses this config value.
+# 'zh' user can custom change `jieba` dictionary path.
+#
+# html_search_options = {'type': 'default'}
+
+# The name of a javascript file (relative to the configuration directory) that
+# implements a search results scorer. If empty, the default will be used.
+#
+# html_search_scorer = 'scorer.js'
+
+# Output file base name for HTML help builder.
+htmlhelp_basename = 'ocrmypdfdoc'
+
+# -- Options for LaTeX output ---------------------------------------------
+
+latex_elements = {
+     # The paper size ('letterpaper' or 'a4paper').
+     #
+     # 'papersize': 'letterpaper',
+
+     # The font size ('10pt', '11pt' or '12pt').
+     #
+     # 'pointsize': '10pt',
+
+     # Additional stuff for the LaTeX preamble.
+     #
+     # 'preamble': '',
+
+     # Latex figure (float) alignment
+     #
+     # 'figure_align': 'htbp',
+}
+
+# Grouping the document tree into LaTeX files. List of tuples
+# (source start file, target name, title,
+#  author, documentclass [howto, manual, or own class]).
+latex_documents = [
+    (master_doc, 'ocrmypdf.tex', 'ocrmypdf Documentation',
+     'James R. Barlow', 'manual'),
+]
+
+# The name of an image file (relative to this directory) to place at the top of
+# the title page.
+#
+# latex_logo = None
+
+# For "manual" documents, if this is true, then toplevel headings are parts,
+# not chapters.
+#
+# latex_use_parts = False
+
+# If true, show page references after internal links.
+#
+# latex_show_pagerefs = False
+
+# If true, show URL addresses after external links.
+#
+# latex_show_urls = False
+
+# Documents to append as an appendix to all manuals.
+#
+# latex_appendices = []
+
+# It false, will not define \strong, \code, 	itleref, \crossref ... but only
+# \sphinxstrong, ..., \sphinxtitleref, ... To help avoid clash with user added
+# packages.
+#
+# latex_keep_old_macro_names = True
+
+# If false, no module index is generated.
+#
+# latex_domain_indices = True
+
+
+# -- Options for manual page output ---------------------------------------
+
+# One entry per manual page. List of tuples
+# (source start file, name, description, authors, manual section).
+man_pages = [
+    (master_doc, 'ocrmypdf', 'ocrmypdf Documentation',
+     [author], 1)
+]
+
+# If true, show URL addresses after external links.
+#
+# man_show_urls = False
+
+
+# -- Options for Texinfo output -------------------------------------------
+
+# Grouping the document tree into Texinfo files. List of tuples
+# (source start file, target name, title, author,
+#  dir menu entry, description, category)
+texinfo_documents = [
+    (master_doc, 'ocrmypdf', 'ocrmypdf Documentation',
+     author, 'ocrmypdf', 'One line description of project.',
+     'Miscellaneous'),
+]
+
+# Documents to append as an appendix to all manuals.
+#
+# texinfo_appendices = []
+
+# If false, no module index is generated.
+#
+# texinfo_domain_indices = True
+
+# How to display URL addresses: 'footnote', 'no', or 'inline'.
+#
+# texinfo_show_urls = 'footnote'
+
+# If true, do not generate a @detailmenu in the "Top" node's menu.
+#
+# texinfo_no_detailmenu = False

docs/cookbook.rst

@@ -0,0 +1,142 @@
+Cookbook
+========
+
+Basic examples
+--------------
+
+Help!
+"""""
+
+ocrmypdf has built-in help.
+
+.. code-block:: bash
+
+	ocrmypdf --help
+
+
+Add an OCR layer and convert to PDF/A
+"""""""""""""""""""""""""""""""""""""
+
+.. code-block:: bash
+
+	ocrmypdf input.pdf output.pdf
+
+Add an OCR layer and output a standard PDF
+""""""""""""""""""""""""""""""""""""""""""
+
+.. code-block:: bash
+
+	ocrmypdf --output-type pdf input.pdf output.pdf
+
+Modify a file in place
+""""""""""""""""""""""
+
+The file will only be overwritten if OCRmyPDF is successful.
+
+.. code-block:: bash
+
+	ocrmypdf myfile.pdf myfile.pdf
+
+Correct page rotation
+"""""""""""""""""""""
+
+OCR will attempt to automatic correct the rotation of each page. This can help fix a scanning job that contains a mix of landscape and portrait pages.
+
+.. code-block:: bash
+
+	ocrmypdf --rotate-pages myfile.pdf myfile.pdf
+
+You can increase (decrease) the parameter ``--rotate-pages-threshold`` to make page rotation more (less) aggressive.
+
+
+OCR languages other than English
+""""""""""""""""""""""""""""""""
+
+By default OCRmyPDF assumes the document is English. 
+
+.. code-block:: bash
+
+	ocrmypdf -l fre LeParisien.pdf LeParisien.pdf
+	ocrmypdf -l eng+fre Bilingual-English-French.pdf Bilingual-English-French.pdf
+
+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
+
+
+OCR images, not PDFs
+--------------------
+
+Use a program like `img2pdf <https://gitlab.mister-muffin.de/josch/img2pdf>`_ to convert your images to PDFs, and then pipe the results to run ocrmypdf:
+
+.. code-block:: bash
+
+	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.  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:
+
+.. code-block:: bash
+
+	tesseract my-image.jpg output-prefix pdf 
+
+Image processing
+----------------
+
+OCRmyPDF perform some image processing on each page of a PDF, if desired.  The same processing is applied to each page.  It is suggested that the user review files after image processing as these commands might remove desirable content, especially from poor quality scans.
+
+* ``--rotate-pages`` attempts to determine the correct orientation for each page and rotates the page if necessary.
+
+* ``--remove-background`` attempts to detect and remove a noisy background from grayscale or color images.  Monochrome images are ignored. This should not be used on documents that contain color photos as it may remove them.
+
+* ``--deskew`` will correct pages were scanned at a skewed angle by rotating them back into place.  Skew determination and correction is performed using `Postl's variance of line sums <http://www.leptonica.com/skew-measurement.html>`_ algorithm as implemented in `Leptonica <http://www.leptonica.com/index.html>`_.
+  
+* ``--clean`` uses `unpaper <https://www.flameeyes.eu/projects/unpaper>`_ to clean up pages before OCR, but does not alter the final output.  This makes it less likely that OCR will try to find text in background noise.
+
+* ``--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.
+
+
+OCR and correct document skew (crooked scan)
+""""""""""""""""""""""""""""""""""""""""""""
+
+Deskew:
+
+.. code-block:: bash
+
+	ocrmypdf --deskew input.pdf output.pdf
+
+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
+
+	ocrmypdf --deskew --clean --rotate-pages input.pdf output.pdf
+
+Control of OCR options
+----------------------
+
+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. A skipped page will be inserted into the output without any OCR text.
+
+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.
+
+.. 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
+
+

docs/errors.rst

@@ -0,0 +1,33 @@
+Common error messages
+=====================
+
+Page already has text
+---------------------
+
+.. code::
+
+	ERROR -    1: page already has text! – aborting (use --force-ocr to force OCR)
+
+You ran ocrmypdf on a file that already contains printable text or a hidden OCR text layer (it can't quite tell the difference). You probably don't want to do this, because the file is already searchable.
+
+As the error message suggests, your options are:
+
+- ``ocrmypdf --force-ocr`` to :ref:`rasterize <raster-vector>` all vector content and run OCR on the images. This is useful if a previous OCR program failed, or if the document contains a text watermark.
+
+- ``ocrmypdf --skip-text`` to skip OCR and other processing on any pages that contain text. Text pages will be copied into the output PDF without modification.
+
+
+Input file 'filename' is not a valid PDF
+----------------------------------------
+
+OCRmyPDF passes files through qpdf, a program that fixes errors in PDFs, before it tries to work on them. In most cases this happens because the PDF is corrupt and
+truncated (incomplete file copying) and not much can be done.
+
+You can try rewriting the file with Ghostscript or pdftk:
+
+- ``gs -o output.pdf -dSAFER -sDEVICE=pdfwrite input.pdf``
+
+- ``pdftk input.pdf cat output output.pdf``
+
+Sometimes Acrobat can repair PDFs with its `Preflight tool <https://helpx.adobe.com/acrobat/using/correcting-problem-areas-preflight-tool.html>`_.
+

docs/index.rst

@@ -0,0 +1,36 @@
+.. ocrmypdf documentation master file, created by
+   sphinx-quickstart on Sun Sep  4 14:29:43 2016.
+   You can adapt this file completely to your liking, but it should at least
+   contain the root `toctree` directive.
+
+OCRmyPDF documentation
+======================
+
+OCRmyPDF adds an OCR text layer to scanned PDF files, allowing them to
+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
+
+   introduction
+   installation
+   languages
+   cookbook
+   batch
+   renderers
+   security
+   errors
+
+
+
+Indices and tables
+==================
+
+* :ref:`genindex`
+* :ref:`modindex`
+* :ref:`search`
+

docs/installation.rst

@@ -0,0 +1,310 @@
+Installation
+============
+
+Installing on Debian and Ubuntu
+-------------------------------
+
+Users of Debian 9 ("stretch") or later or Ubuntu 16.10 or later may simply
+
+.. code-block:: bash
+
+	apt-get install ocrmypdf
+
+.. _Docker:
+
+Installing the Docker image
+---------------------------
+
+For many users, installing the Docker image will be easier than installing all of OCRmyPDF's dependencies. For Windows, it is the only option.
+
+If you have `Docker <https://docs.docker.com/>`_ installed on your system, you can install
+a Docker image of the latest release.
+
+Follow the Docker installation instructions for your platform.  If you can run this command
+successfully, your system is ready to download and execute the image:
+
+.. code-block:: bash
+
+   docker run hello-world
+   
+OCRmyPDF will use all available CPU cores.  By default, the VirtualBox machine instance on Windows and OS X has only a single CPU core enabled. Use the VirtualBox Manager to determine the name of your Docker engine host, and then follow these optional steps to enable multiple CPUs:
+
+.. code-block:: bash
+
+   # Optional step for Mac OS X users
+   docker-machine stop "yourVM"
+   VBoxManage modifyvm "yourVM" --cpus 2  # or whatever number of core is desired
+   docker-machine start "yourVM"
+   eval $(docker-machine env "yourVM")
+
+Assuming you have a Docker engine running somewhere, you can run these commands to download
+the image:
+
+.. code-block:: bash
+
+   docker pull jbarlow83/ocrmypdf
+
+Then tag it to give a more convenient name, just ocrmypdf:
+
+.. code-block:: bash
+
+   docker tag jbarlow83/ocrmypdf ocrmypdf
+
+.. _docker-polyglot:
+
+This image contains language packs for English, French, Spanish and German. The alternative "polyglot" image provides `all available language packs <https://github.com/tesseract-ocr/tesseract/blob/master/doc/tesseract.1.asc#languages>`_:
+
+.. code-block:: bash
+
+   # Alternative step: If you need all language packs
+   docker pull jbarlow83/ocrmypdf-polyglot
+   docker tag jbarlow83/ocrmypdf-polyglot ocrmypdf
+
+You can then run ocrmypdf using the command:
+
+.. code-block:: bash
+
+   docker run --rm ocrmypdf --help
+  
+To execute the OCRmyPDF on a local file, you must `provide a writable volume to the Docker image <https://docs.docker.com/userguide/dockervolumes/>`_, and both the input and output file must be inside the writable volume.  This example command uses the current working directory as the writable volume:
+
+.. code-block:: bash
+
+   docker run --rm -v "$(pwd):/home/docker" <other docker arguments>   ocrmypdf <your arguments to ocrmypdf>
+
+In this worked example, the current working directory contains an input file called ``test.pdf`` and the output will go to ``output.pdf``: 
+
+.. code-block:: bash
+
+   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.
+
+
+Installing on macOS (formerly Mac OS X)
+---------------------------------------
+
+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.
+
+If it's not already present, `install Homebrew <http://brew.sh/>`_.
+
+Update Homebrew:
+
+.. code-block:: bash
+
+   brew update
+   
+Install or upgrade the required Homebrew packages, if any are missing:
+
+.. code-block:: bash
+
+   brew install libpng openjpeg jbig2dec libtiff     # image libraries
+   brew install qpdf
+   brew install ghostscript
+   brew install python3
+   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
+
+   brew install tesseract                       # Option 1: for English, French, German, Spanish
+
+.. _macos-all-languages:
+
+.. code-block:: bash
+   
+   brew install tesseract --with-all-languages  # Option 2: for all language packs 
+   
+Update the homebrew pip and install Pillow:
+
+.. code-block:: bash
+
+   pip3 install --upgrade pip
+   pip3 install --upgrade pillow
+
+You can then install OCRmyPDF from PyPI:
+
+.. code-block:: bash
+
+   pip3 install ocrmypdf
+
+The command line program should now be available:
+
+.. code-block:: bash
+
+   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-pil \
+      python3-pytest \
+      python3-reportlab \
+      python3-ruffus \
+      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 --system-site-packages venv-ocrmypdf
+   source venv-ocrmypdf/bin/activate
+   pip3 install ocrmypdf
+
+
+Installing on Ubuntu 14.04 LTS
+------------------------------
+
+Installing on Ubuntu 14.04 LTS (trusty) is more difficult than some other options, because of bugs in Python package installation.
+
+Add new "apt" repositories needed for backports of Ghostscript 9.16 and libav-11, which supports unpaper 6.1. This will replace Ghostscript on your system.
+
+.. code-block:: bash
+
+   sudo add-apt-repository ppa:vshn/ghostscript -y 
+   sudo add-apt-repository ppa:heyarje/libav-11 -y
+
+Update apt-get:
+
+.. code-block:: bash
+
+   sudo apt-get update
+   
+Install system dependencies:
+
+.. code-block:: bash
+
+   sudo apt-get install \
+      zlib1g-dev \
+      libjpeg-dev \
+      libffi-dev \
+      libavformat56 libavcodec56 libavutil54 \
+      ghostscript \
+      tesseract-ocr \
+      qpdf \
+      python3-pip \
+      python3-pil \
+      python3-pytest \
+      python3-reportlab
+
+If you wish install OCRmyPDF to the system Python, then install as follows (note this installs new packages
+into your system Python, which could interfere with other programs):
+
+.. 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.  This includes a workaround `for a known, unresolved issue in Ubuntu 14.04's ensurepip
+package <http://www.thefourtheye.in/2014/12/Python-venv-problem-with-ensurepip-in-Ubuntu.html>`_:
+
+.. code-block:: bash
+
+   sudo apt-get install python3-venv
+   python3 -m venv venv-ocrmypdf --without-pip
+   source venv-ocrmypdf/bin/activate
+   wget -O - -o /dev/null https://bootstrap.pypa.io/get-pip.py | python
+   deactivate
+   python3 -m venv --system-site-packages venv-ocrmypdf
+   source venv-ocrmypdf/bin/activate
+   pip install ocrmypdf
+
+These installation instructions omit the optional dependency ``unpaper``, which is only available at version 0.4.2 in Ubuntu 14.04. The author could not find a backport of ``unpaper``, and created a .deb package to do the job of installing unpaper 6.1 (for x86 64-bit only):
+
+.. code-block:: bash
+
+   wget -q https://dl.dropboxusercontent.com/u/28971240/unpaper_6.1-1.deb -O unpaper_6.1-1.deb
+   sudo dpkg -i unpaper_6.1-1.deb
+
+
+Installing on Windows
+---------------------
+
+Direct installation on Windows is not possible.  Install the _`Docker` container as described above.  Ensure that your command prompt can run the docker "hello world" container.
+
+Running on Windows
+~~~~~~~~~~~~~~~~~~
+
+The command line syntax to run ocrmypdf from a command prompt will resemble:
+
+.. code-block:: bat
+
+   docker run -v /c/Users/sampleuser:/home/docker ocrmypdf --skip-text test.pdf output.pdf
+
+where /c/Users/sampleuser is a Unix representation of the Windows path C:\\Users\\sampleuser, assuming a user named "sampleuser" is running ocrmypdf on a file in their home directory, and the files "test.pdf" and "output.pdf" are in the sampleuser folder. The Windows user must have read and write permissions.
+      
+Installing HEAD revision from sources
+-------------------------------------
+
+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:
+
+.. code-block:: bash
+
+   pip3 install git+https://github.com/jbarlow83/OCRmyPDF.git
+
+Or, to install in `development mode <https://pythonhosted.org/setuptools/setuptools.html#development-mode>`_,  allowing customization of OCRmyPDF, use the ``-e`` flag:
+
+.. code-block:: bash
+
+   pip3 install -e git+https://github.com/jbarlow83/OCRmyPDF.git
+   
+On certain Linux distributions such as Ubuntu, you may need to use 
+run the install command as superuser:
+
+.. code-block:: bash
+
+   sudo pip3 install [-e] git+https://github.com/jbarlow83/OCRmyPDF.git
+   
+Note that this will alter your system's Python distribution. If you prefer 
+to not install as superuser, you can install the package in a Python virtual environment:
+
+.. code-block:: bash
+
+   git clone -b master https://github.com/jbarlow83/OCRmyPDF.git
+   python3 -m venv
+   source venv/bin/activate
+   cd OCRmyPDF
+   pip3 install .
+
+However, ``ocrmypdf`` will only be accessible on the system PATH after
+you activate the virtual environment.
+
+To run the program:
+
+.. code-block:: bash
+   
+   ocrmypdf --help
+
+If not yet installed, the script will notify you about dependencies that
+need to be installed. The script requires specific versions of the
+dependencies. Older version than the ones mentioned in the release notes
+are likely not to be compatible to OCRmyPDF.

docs/introduction.rst

@@ -0,0 +1,76 @@
+Introduction
+============
+
+OCRmyPDF is a Python 3 package that adds OCR layers to PDFs.
+
+
+About OCR
+---------
+
+`Optical character recognition <https://en.wikipedia.org/wiki/Optical_character_recognition>`_ is technology that converts images of typed or handwritten text, such as in a scanned document, to computer text that can be searched and copied.
+
+OCRmyPDF uses `Tesseract <https://github.com/tesseract-ocr/tesseract>`_, the best available open source OCR engine, to perform OCR.
+
+.. _raster-vector:
+
+About PDFs
+----------
+
+PDFs are page description files that attempts to preserve a layout exactly. They can contain `vector graphic files <http://vector-conversions.com/vectorizing/raster_vs_vector.html>`_ that can contain raster objects such as scanned images. Because PDFs can contain multiple pages (unlike many image formats) and can contain fonts and text, it is a good formats for exchanging scanned documents.
+
+.. image:: bitmap_vs_svg.svg
+
+A PDF page might contain multiple images, even if it only appears to have one image.  Some scanners or scanning software will segment pages into monochromatic text and color regions for example, to improve the compression ratio and appearance of the page.
+
+Rasterizing a PDF is the process of generating an image suitable for display or analyzing with an OCR engine.  OCR engines like Tesseract work with images, not vector objects.
+
+
+About PDF/A
+-----------
+
+`PDF/A <https://en.wikipedia.org/wiki/PDF/A>`_ is an ISO-standardized subset of the full PDF specification that is designed for archiving (the 'A' stands for Archive).  PDF/A differs from PDF primarily by omitting features that would make it difficult to read the file in the future, such as embedded Javascript, video, audio and references to external fonts.  All fonts and resources needed to interpret the PDF must be contained within it. Because PDF/A disables Javascript and other types of embedded content, it is probably more secure.
+
+There are various conformance levels and versions, such as "PDF/A-2b".
+
+Generally speaking, the best format for scanned documents is PDF/A. Some governments and jurisdictions, US Courts in particular, `mandate the use of PDF/A <https://pdfblog.com/2012/02/13/what-is-pdfa/>`_ for scanned documents.
+
+Since most people who scan documents are interested in reading them indefinitely into the future, OCRmyPDF generates PDF/A-2b by default.
+
+PDF/A has a few drawbacks.  Some PDF viewers include an alert that the file is a PDF/A, which may confuse some users.  It also tends to produce larger files than PDF, because it embeds certain resources even if they are commonly available. PDF/A files can be digitally signed, but may not be encrypted, to ensure they can be read in the future.  Fortunately, converting from PDF/A to a regular PDF is trivial, and any PDF viewer can view PDF/A.
+
+
+What OCRmyPDF does
+------------------
+
+OCRmyPDF analyzes each page of a PDF to determine the colorspace and resolution (DPI) needed to capture all of the information on that page without losing content.  It uses `Ghostscript <http://ghostscript.com/>`_ to rasterize the page, and then performs on OCR on the rasterized image.  It is not enough to simply extract the images from each page and run OCR on them individually.  Of course one could use Ghostscript or another PDF rasterizer and then pass the image to Tesseract.  OCRmyPDF automates this process and produces a minimally changed output file that contains the same information, colorspace and resolution.
+
+The Tesseract OCR engine can output 'hOCR' files, which are XML files that contain a description of the text it found on the page.  OCRmyPDF will render a new PDF that contains only the hidden text layer, and merge this with the original page.
+
+Alternately, OCRmyPDF can use the Tesseract OCR engine to directly output PDFs for each page, then merge them.
+
+By default, OCRmyPDF will convert the file to a PDF/A.  This behavior can be disabled with the ``--output-type pdf`` argument.
+
+Depending on the settings selected, OCRmyPDF may "graft" the OCR layer into the existing PDF, or reconstruct a visually equivalent new PDF.
+
+
+Limitations
+-----------
+
+OCRmyPDF is limited by the Tesseract OCR engine.  As such it experiences these limitations, as do any other programs that rely on Tesseract:
+
+* The OCR is not as accurate as commercial solutions such as Abbyy.
+* It is not capable of recognizing handwriting.
+* It may find gibberish and report this as OCR output.
+* If a document contains languages outside of those given in the ``-l LANG`` arguments, results may be poor.
+* It is not always good at analyzing the natural reading order of documents. For example, it may fail to recognize that a document contains two columns and join text across the columns.
+* Poor quality scans may produce poor quality OCR. Garbage in, garbage out.
+  
+OCRmyPDF is also limited by the PDF specification:
+
+* PDF encodes the position of text glyphs but does not encode document structure.  There is no markup that divides a document in sections, paragraphs, sentences, or even words (since blank spaces are not represented). As such all elements of document structure including the spaces between words must be derived heuristically.  Some PDF viewers do a better job of this than others.
+
+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.

docs/languages.rst

@@ -0,0 +1,48 @@
+.. _lang-packs:
+
+Installing additional language packs
+====================================
+
+OCRmyPDF uses Tesseract for OCR, and relies on its language packs for languages other than English. 
+
+Tesseract supports `most languages <https://github.com/tesseract-ocr/tesseract/blob/master/doc/tesseract.1.asc#languages>`_.
+
+For Linux users, you can often find packages that provide language packs:
+
+Debian and Ubuntu users
+-----------------------
+
+.. code-block:: bash
+
+   # Display a list of all Tesseract language packs
+   apt-cache search tesseract-ocr
+
+   # Debian/Ubuntu users
+   apt-get install tesseract-ocr-chi-sim  # Example: Install Chinese Simplified language back
+   
+You can then pass the ``-l LANG`` argument to OCRmyPDF to give a hint as to what languages it should search for. Multiple
+languages can be requested using either ``-l eng+fre`` (English and French) or ``-l eng -l fre``.
+
+macOS users
+-----------
+
+You can install additional language packs by :ref:`installing Tesseract using Homebrew with all language packs <macos-all-languages>`.
+
+Docker users
+------------
+
+Users of the Docker image may use the alternative :ref:`"polyglot" container <docker-polyglot>` which includes all languages.
+
+Known limitations
+-----------------
+
+As of v4.2, users of ocrmypdf working languages outside the Latin alphabet should use the following syntax:
+
+.. code-block:: bash
+
+	ocrmypdf -l eng+gre --output-type pdf --pdf-renderer tesseract
+
+The reasons for this are:
+
+* The latest version of Ghostscript (9.19 as of this writing) has unfixed bugs in Unicode handling that generate invalid character maps, so Ghostscript cannot be used for PDF/A conversion
+* The default "hocr" PDF renderer does not handle Asian fonts properly

docs/renderers.rst

@@ -0,0 +1,40 @@
+PDF Renderers
+=============
+
+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 it always uses ``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 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/security.rst

@@ -0,0 +1,44 @@
+PDF Security Issues
+===================
+
+	OCRmyPDF should only be used on PDFs you trust. It is not designed to protect you against malware. 
+
+Recognizing that many users have an interest in handling PDFs and applying OCR to PDFs they did not generate themselves, this article discusses the security implications of PDFs and how users can protect themselves.
+
+The disclaimer applies: this software has no warranties of any kind.
+
+PDFs may contain malware
+------------------------
+
+PDF is a rich, complex file format. The official PDF 1.7 specification, ISO 32000:2008, is hundreds of packages long and references several annexes each of which are similar in length. PDFs can contain video, audio, JavaScript and other programming, and forms. In some cases, they can open internet connections to pre-selected URLs. All of these possible attack vectors.
+
+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 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 must open and interpret your PDF in order to insert an OCR layer. First, it runs all PDFs through `qpdf <https://github.com/qpdf/qpdf>`_, a program that repairs PDFs with syntax errors. This is done because, in the author's experience, a significant number of PDFs in the wild especially those created by scanners are not well-formed files. qpdf makes it more likely that OCRmyPDF will succeed, but offers no security guarantees. qpdf is also used to split the PDF into single page PDFs.
+
+After qpdf, OCRmyPDF examines each page using `PyPDF2 <https://github.com/mstamy2/PyPDF2>`_. This library also has no warranties or guarantees.
+
+Finally, OCRmyPDF rasterizes each page of the PDF using `Ghostscript <http://ghostscript.com/>`_ in ``-dSAFER`` mode. 
+
+Depending on the options specified, OCRmyPDF may graft the OCR layer into the existing PDF or it may essentially reconstruct ("re-fry") a visually identical PDF that may be quite different at the binary level. That said, OCRmyPDF is not a tool designed for sanitizing PDFs.
+
+Using OCRmyPDF online
+---------------------
+
+OCRmyPDF is not designed to be deployed "as a service", in a setting where a user/attacker could upload a file for OCR processing online. It is not designed to be secure in this case.
+
+Abbyy Cloud OCR is a viable commercial alternative with a web services API. The author also provides professional services that include OCR and building databases around PDFs, and is happy to provide consultation.
+
+Password protection, digital signatures and certification
+---------------------------------------------------------
+
+OCRmyPDF cannot remove password protection from a PDF. ``qpdf``, one of its dependencies, has this capability. After OCR is applied, password protection is not permitted on PDF/A documents but the file can be converted to regular PDF.
+
+Many programs exist which are capable of inserting an image of someone's signature. On its own, this offers no security guarantees. It is trivial to remove the signature image and apply it to other files. This practice offers no real security.
+
+Important documents can be digitally signed and certified to attest to their authorship. OCRmyPDF cannot do this. Open source tools such as pdfbox (Java) have this capability as does Adobe Acrobat. 

ocrmypdf/__init__.py

@@ -0,0 +1,15 @@
+import pkg_resources
+
+PROGRAM_NAME = 'ocrmypdf'
+
+VERSION = pkg_resources.get_distribution('ocrmypdf').version
+
+
+# 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
+
+
+

ocrmypdf/__main__.py

@@ -0,0 +1,606 @@
+#!/usr/bin/env python3
+# © 2015-16 James R. Barlow: github.com/jbarlow83
+
+from contextlib import suppress
+from tempfile import mkdtemp
+from collections.abc import Sequence
+import sys
+import os
+import re
+import shutil
+import warnings
+import multiprocessing
+import atexit
+import textwrap
+import img2pdf
+import logging
+import argparse
+
+import PyPDF2 as pypdf
+from PIL import Image
+
+import ruffus.ruffus_exceptions as ruffus_exceptions
+import ruffus.cmdline as cmdline
+import ruffus.proxy_logger as proxy_logger
+
+from .pipeline import JobContext, JobContextManager, re_symlink, \
+    cleanup_working_files, build_pipeline
+from .pdfa import file_claims_pdfa
+from .helpers import is_iterable_notstr, re_symlink, is_file_writable
+from .exec import tesseract, qpdf
+from . import PROGRAM_NAME, VERSION
+
+from .exceptions import *
+from . import exceptions as ocrmypdf_exceptions
+
+warnings.simplefilter('ignore', pypdf.utils.PdfReadWarning)
+
+
+# -------------
+# External dependencies
+
+MINIMUM_TESS_VERSION = '3.02.02'
+
+
+def complain(message):
+    print(*textwrap.wrap(message), file=sys.stderr)
+
+
+if tesseract.version() < MINIMUM_TESS_VERSION:
+    complain(
+        "Please install tesseract {0} or newer "
+        "(currently installed version is {1})".format(
+            MINIMUM_TESS_VERSION, tesseract.version()))
+    sys.exit(ExitCode.missing_dependency)
+
+
+# -------------
+# Parser
+
+parser = cmdline.get_argparse(
+    prog=PROGRAM_NAME,
+    version=VERSION,
+    fromfile_prefix_chars='@',
+    ignored_args=[
+        'touch_files_only', 'recreate_database', 'checksum_file_name',
+        'key_legend_in_graph', 'draw_graph_horizontally', 'flowchart_format',
+        'forced_tasks', 'target_tasks', 'use_threads', 'jobs', 'log_file'],
+    formatter_class=argparse.RawDescriptionHelpFormatter,
+    description="""\
+Generates a searchable PDF or PDF/A from a regular PDF.
+
+OCRmyPDF rasterizes each page of the input PDF, optionally corrects page
+rotation and performs image processing, runs the Tesseract OCR engine on the
+image, and then creates a PDF from the OCR information.
+""",
+    epilog="""\
+OCRmyPDF attempts to keep the output file at about the same size.  If a file
+contains losslessly compressed images, and output file will be losslessly
+compressed as well.
+
+PDF is a page description file that attempts to preserve a layout exactly.
+A PDF can contain vector objects (such as text or lines) and raster objects
+(images).  A page might have multiple images.  OCRmyPDF is prepared to deal
+with the wide variety of PDFs that exist in the wild.
+
+When a PDF page contains text, OCRmyPDF assumes that the page has already
+been OCRed or is a "born digital" page that should not be OCRed.  The default
+behavior is to exit in this case without producing a file.  You can use the
+option --skip-text to ignore pages with text, or --force-ocr to rasterize
+all objects on the page and produce an image-only PDF as output.
+
+    ocrmypdf --skip-text file_with_some_text_pages.pdf output.pdf
+
+    ocrmypdf --force-ocr word_document.pdf output.pdf
+
+If you are concerned about long-term archiving of PDFs, use the default option
+--output-type pdfa which converts the PDF to a standardized PDF/A-2b.  This
+converts images to sRGB colorspace, removes some features from the PDF such
+as Javascript or forms. If you want to minimize the number of changes made to
+your PDF, use --output-type pdf.
+
+If OCRmyPDF is given an image file as input, it will attempt to convert the
+image to a PDF before processing.  For more control over the conversion of
+images to PDF, use the Python package img2pdf or other image to PDF software.
+
+For example, this command uses img2pdf to convert all .png files beginning
+with the 'page' prefix to a PDF, fitting each image on A4-sized paper, and
+sending the result to OCRmyPDF through a pipe.  img2pdf is a dependency of
+ocrmypdf so it is already installed.
+
+    img2pdf --pagesize A4 page*.png | ocrmypdf - myfile.pdf
+
+Online documentation is located at:
+    https://ocrmypdf.readthedocs.io/en/latest/introduction.html
+
+""")
+
+parser.add_argument(
+    'input_file',
+    help="PDF file containing the images to be OCRed (or '-' to read from "
+         "standard input)")
+parser.add_argument(
+    'output_file',
+    help="output searchable PDF file (or '-' to write to standard output)")
+parser.add_argument(
+    '-l', '--language', action='append',
+    help="Language(s) of the file to be OCRed (see tesseract --list-langs for "
+         "all language packs installed in your system). To specify multiple "
+         "languages, join them with '+' or issue this argument once for each "
+         "language.")
+parser.add_argument(
+    '-j', '--jobs', metavar='N', type=int,
+    help="Use up to N CPU cores simultaneously (default: use all)")
+parser.add_argument(
+    '--image-dpi', metavar='DPI', type=int,
+    help="for input image instead of PDF, use this DPI instead of file's")
+parser.add_argument(
+    '--output-type', choices=['pdfa', 'pdf'], default='pdfa',
+    help="Choose output type. 'pdfa' creates a PDF/A-2b compliant file for "
+         "long term archiving (default, recommended) but may not suitable "
+         "for users who want their file altered as little as possible. 'pdfa' "
+         "also has problems with full Unicode text. 'pdf' attempts to "
+         "preserve file contents as much as possible.")
+
+metadata = parser.add_argument_group(
+    "Metadata options",
+    "Set output PDF/A metadata (default: use input document's metadata)")
+metadata.add_argument(
+    '--title', type=str,
+    help="set document title (place multiple words in quotes)")
+metadata.add_argument(
+    '--author', type=str,
+    help="set document author")
+metadata.add_argument(
+    '--subject', type=str,
+    help="set document subject description")
+metadata.add_argument(
+    '--keywords', type=str,
+    help="set document keywords")
+
+preprocessing = parser.add_argument_group(
+    "Image preprocessing options",
+    "Options to improve the quality of the final PDF and OCR")
+preprocessing.add_argument(
+    '-r', '--rotate-pages', action='store_true',
+    help="automatically rotate pages based on detected text orientation")
+preprocessing.add_argument(
+    '--remove-background', action='store_true',
+    help="attempt to remove background from gray or color pages, setting it "
+         "to white ")
+preprocessing.add_argument(
+    '-d', '--deskew', action='store_true',
+    help="deskew each page before performing OCR")
+preprocessing.add_argument(
+    '-c', '--clean', action='store_true',
+    help="clean pages from scanning artifacts before performing OCR, and send "
+         "the cleaned page to OCR, but do not include the cleaned page in "
+         "the output ")
+preprocessing.add_argument(
+    '-i', '--clean-final', action='store_true',
+    help="clean page as above, and incorporate the cleaned image in the final "
+         "PDF")
+preprocessing.add_argument(
+    '--oversample', metavar='DPI', type=int, default=0,
+    help="oversample images to at least the specified DPI, to improve OCR "
+         "results slightly")
+
+ocrsettings = parser.add_argument_group(
+    "OCR options",
+    "Control how OCR is applied")
+ocrsettings.add_argument(
+    '-f', '--force-ocr', action='store_true',
+    help="rasterize any fonts or vector objects on each page, apply OCR, and "
+         "save the rastered output (this rewrites the PDF)")
+ocrsettings.add_argument(
+    '-s', '--skip-text', action='store_true',
+    help="skip OCR on any pages that already contain text, but include the "
+         "page in final output; useful for PDFs that contain a mix of "
+         "images, text pages, and/or previously OCRed pages")
+ocrsettings.add_argument(
+    '--skip-big', type=float, metavar='MPixels',
+    help="skip OCR on pages larger than the specified amount of megapixels, "
+         "but include skipped pages in final output")
+
+advanced = parser.add_argument_group(
+    "Advanced",
+    "Advanced options for power users")
+advanced.add_argument(
+    '--tesseract-config', action='append', metavar='CFG', default=[],
+    help="additional Tesseract configuration files")
+advanced.add_argument(
+    '--tesseract-pagesegmode', action='store', type=int, metavar='PSM',
+    choices=range(0, 14),
+    help="set Tesseract page segmentation mode (see tesseract --help)")
+advanced.add_argument(
+    '--tesseract-oem', action='store', type=int, metavar='MODE',
+    choices=range(0, 4),
+    help=("set Tesseract 4.0 OCR engine mode: "
+         "0 - original Tesseract only; "
+         "1 - neural nets LSTM only; "
+         "2 - Tesseract + LSTM; "
+         "3 - default.")
+    )
+advanced.add_argument(
+    '--pdf-renderer', choices=['auto', 'tesseract', 'hocr', 'tess4'], default='auto',
+    help="choose OCR PDF renderer - the default option is to let OCRmyPDF "
+         "choose.  The 'tesseract' PDF renderer is more accurate and does a "
+         "better job and document structure such as recognizing columns. It "
+         "also does a better job on non-Latin languages. However, it does "
+         "not work as well when older versions of Tesseract or Ghostscript "
+         "are installed, and some combinations of arguments to do not work "
+         "with --pdf-renderer tesseract.  The 'tess4' PDF renderer is similar "
+         "to 'tesseract', requires tesseract 4, and gives superior results.")
+advanced.add_argument(
+    '--tesseract-timeout', default=180.0, type=float, metavar='SECONDS',
+    help='give up on OCR after the timeout, but copy the preprocessed page '
+         'into the final output')
+advanced.add_argument(
+    '--rotate-pages-threshold', default=14.0, type=float, metavar='CONFIDENCE',
+    help="only rotate pages when confidence is above this value (arbitrary "
+         "units reported by tesseract)")
+
+debugging = parser.add_argument_group(
+    "Debugging",
+    "Arguments to help with troubleshooting and debugging")
+debugging.add_argument(
+    '-k', '--keep-temporary-files', action='store_true',
+    help="keep temporary files (helpful for debugging)")
+debugging.add_argument(
+    '-g', '--debug-rendering', action='store_true',
+    help="render each page twice with debug information on second page")
+
+
+def check_options_languages(options, _log):
+    if not options.language:
+        options.language = ['eng']  # Enforce English hegemony
+
+    # Support v2.x "eng+deu" language syntax
+    if '+' in options.language[0]:
+        options.language = options.language[0].split('+')
+
+    if not set(options.language).issubset(tesseract.languages()):
+        msg = (
+            "The installed version of tesseract does not have language "
+            "data for the following requested languages: \n")
+        for lang in (set(options.language) - tesseract.languages()):
+            msg += lang + '\n'
+        raise argparse.ArgumentError(msg)
+
+
+def check_options_output(options, log):
+    if options.pdf_renderer == 'auto':
+        options.pdf_renderer = 'hocr'
+
+    if options.pdf_renderer == 'tesseract' and \
+            tesseract.version() < '3.04.01' and \
+            os.environ.get('OCRMYPDF_SHARP_TTF', '') != '1':
+        log.warning(
+            "Your version of tesseract has problems with PDF output."
+            " Some PDF viewers will fail to find searchable text.\n"
+            "--pdf-renderer=tesseract is not recommended.")
+
+    if options.debug_rendering and options.pdf_renderer == 'tesseract':
+        log.info(
+            "Ignoring --debug-rendering because it is not supported with"
+            "--pdf-renderer=tesseract.")
+
+    lossless_reconstruction = False
+    if options.pdf_renderer == 'hocr':
+        if not any((options.deskew, options.clean_final, options.force_ocr,
+                   options.remove_background)):
+            lossless_reconstruction = True
+    options.lossless_reconstruction = lossless_reconstruction
+
+
+def check_options_preprocessing(options, log):
+    if any((options.clean, options.clean_final)):
+        from .exec import unpaper
+        try:
+            if unpaper.version() < '6.1':
+                raise MissingDependencyError(
+                    "The installed 'unpaper' is not supported. "
+                    "Install version 6.1 or newer.")
+        except FileNotFoundError:
+            raise MissingDependencyError(
+                "Install the 'unpaper' program to use --clean, --clean-final.")
+
+    if options.clean and \
+            not options.clean_final and \
+            options.pdf_renderer == 'tesseract':
+        log.info(
+            "Tesseract PDF renderer cannot render --clean pages without "
+            "also performing --clean-final, so --clean-final is assumed.")
+
+
+def check_options_ocr_behavior(options, log):
+    if options.force_ocr and options.skip_text:
+        raise argparse.ArgumentError(
+            "Error: --force-ocr and --skip-text are mutually incompatible.")
+
+    if set(options.language) & {'chi_sim', 'chi_tra'} and \
+            (options.pdf_renderer == 'hocr' or options.output_type == 'pdfa'):
+        log.warning(
+            "Your settings are known to cause problems with OCR of Chinese text. "
+            "Try adding these arguments: "
+            "    ocrmypdf --pdf-renderer tesseract --output-type pdf")
+
+
+def check_options_advanced(options, log):
+    if tesseract.v4():
+        log.info(
+            "Tesseract v4.x.alpha found. OCRmyPDF support is experimental.")
+    if options.tesseract_oem and not tesseract.v4():
+        log.warning(
+            "--tesseract-oem requires Tesseract 4.x -- argument ignored")
+
+
+def check_options(options, log):
+    try:
+        check_options_languages(options, log)
+        check_options_output(options, log)
+        check_options_preprocessing(options, log)
+        check_options_ocr_behavior(options, log)
+        check_options_advanced(options, log)
+    except argparse.ArgumentError as e:
+        log.error(e)
+        sys.exit(ExitCode.bad_args)
+    except MissingDependencyError as e:
+        log.error(e)
+        sys.exit(ExitCode.missing_dependency)
+
+
+
+
+
+# ----------
+# Logging
+
+
+def logging_factory(logger_name, listargs):
+    log_file_name, verbose = listargs
+
+    root_logger = logging.getLogger(logger_name)
+    root_logger.setLevel(logging.DEBUG)
+
+    handler = logging.StreamHandler(sys.stderr)
+    formatter_ = logging.Formatter("%(levelname)7s - %(message)s")
+    handler.setFormatter(formatter_)
+    if verbose:
+        handler.setLevel(logging.DEBUG)
+    else:
+        handler.setLevel(logging.INFO)
+    root_logger.addHandler(handler)
+    return root_logger
+
+
+def available_cpu_count():
+    try:
+        return multiprocessing.cpu_count()
+    except NotImplementedError:
+        pass
+
+    try:
+        import psutil
+        return psutil.cpu_count()
+    except (ImportError, AttributeError):
+        pass
+
+    complain(
+        "Could not get CPU count.  Assuming one (1) CPU."
+        "Use -j N to set manually.")
+    return 1
+
+
+def cleanup_ruffus_error_message(msg):
+    msg = re.sub(r'\s+', r' ', msg, re.MULTILINE)
+    msg = re.sub(r"\((.+?)\)", r'\1', msg)
+    msg = msg.strip()
+    return msg
+
+
+def do_ruffus_exception(ruffus_five_tuple, options, log):
+    """Replace the elaborate ruffus stack trace with a user friendly
+    description of the error message that occurred."""
+
+    task_name, job_name, exc_name, exc_value, exc_stack = ruffus_five_tuple
+    if exc_name == 'builtins.SystemExit':
+        match = re.search(r"\.(.+?)\)", exc_value)
+        exit_code_name = match.groups()[0]
+        exit_code = getattr(ExitCode, exit_code_name, 'other_error')
+        return exit_code
+    elif exc_name == 'ruffus.ruffus_exceptions.MissingInputFileError':
+        log.error(cleanup_ruffus_error_message(exc_value))
+        return ExitCode.input_file
+    elif exc_name == 'builtins.TypeError':
+        # Even though repair_pdf will fail, ruffus will still try
+        # to call split_pages with no input files, likely due to a bug
+        if task_name == 'split_pages':
+            log.error("Input file '{0}' is not a valid PDF".format(
+                options.input_file))
+            return ExitCode.input_file
+    elif exc_name == 'builtins.KeyboardInterrupt':
+        log.error("Interrupted by user")
+        return ExitCode.ctrl_c
+    elif exc_name == 'subprocess.CalledProcessError':
+        # It's up to the subprocess handler to report something useful
+        msg = "Error occurred while running this command:"
+        log.error(msg + '\n' + exc_value)
+        return ExitCode.child_process_error
+    elif exc_name == 'ocrmypdf.exceptions.PdfMergeFailedError':
+        log.error(textwrap.dedent("""\
+            Failed to merge PDF image layer with OCR layer
+
+            Usually this happens because the input PDF file is mal-formed and
+            ocrmypdf cannot automatically correct the problem on its own.
+
+            Try using
+                ocrmypdf --pdf-renderer tesseract  [..other args..]
+            """))
+        return ExitCode.input_file
+    elif exc_name.startswith('ocrmypdf.exceptions.'):
+        base_exc_name = exc_name.replace('ocrmypdf.exceptions.', '')
+        exc_class = getattr(ocrmypdf_exceptions, base_exc_name)
+        return exc_class.exit_code
+    elif exc_name == 'PyPDF2.utils.PdfReadError' and \
+            'not been decrypted' in exc_value:
+        log.error(textwrap.dedent("""\
+            Input PDF uses either an encryption algorithm or a PDF security
+            handler that is not supported by ocrmypdf.
+
+            For information about this PDF's security use
+                qpdf --show-encryption [...input PDF...]
+
+            (Only algorithms "R = 1" and "R = 2" are supported.)
+
+            """))
+        return ExitCode.encrypted_pdf
+
+    if not options.verbose:
+        log.error(exc_stack)
+    return ExitCode.other_error
+
+
+def traverse_ruffus_exception(e_args, options, log):
+    """Walk through a RethrownJobError and find the first exception.
+
+    The exit code will be based on this, even if multiple exceptions occurred
+    at the same time."""
+
+    if isinstance(e_args, Sequence) and isinstance(e_args[0], str) and \
+            len(e_args) == 5:
+        return do_ruffus_exception(e_args, options, log)
+    elif is_iterable_notstr(e_args):
+        for exc in e_args:
+            return traverse_ruffus_exception(exc, options, log)
+
+
+def run_pipeline():
+    options = parser.parse_args()
+    options.verbose_abbreviated_path = 1
+
+    _log, _log_mutex = proxy_logger.make_shared_logger_and_proxy(
+        logging_factory, __name__, [None, options.verbose])
+    _log.debug('ocrmypdf ' + VERSION)
+    _log.debug('tesseract ' + tesseract.version())
+
+    check_options(options, _log)
+
+    # Any changes to options will not take effect for options that are already
+    # bound to function parameters in the pipeline. (For example
+    # options.input_file, options.pdf_renderer are already bound.)
+    if not options.jobs:
+        options.jobs = available_cpu_count()
+    try:
+        work_folder = mkdtemp(prefix="com.github.ocrmypdf.")
+        options.history_file = os.path.join(
+            work_folder, 'ruffus_history.sqlite')
+        start_input_file = os.path.join(
+            work_folder, 'origin')
+
+        if options.input_file == '-':
+            # stdin
+            _log.info('reading file from standard input')
+            with open(start_input_file, 'wb') as stream_buffer:
+                from shutil import copyfileobj
+                copyfileobj(sys.stdin.buffer, stream_buffer)
+        else:
+            try:
+                re_symlink(options.input_file, start_input_file, _log)
+            except FileNotFoundError:
+                _log.error("File not found - " + options.input_file)
+                return ExitCode.input_file
+
+        if options.output_file == '-':
+            if sys.stdout.isatty():
+                _log.error(textwrap.dedent("""\
+                    Output was set to stdout '-' but it looks like stdout
+                    is connected to a terminal.  Please redirect stdout to a
+                    file."""))
+                return ExitCode.bad_args
+        elif not is_file_writable(options.output_file):
+                _log.error(textwrap.dedent("""\
+                    Cutput file location is not writable."""))
+                return ExitCode.file_access_error
+
+        manager = JobContextManager()
+        manager.register('JobContext', JobContext)
+        manager.start()
+
+        context = manager.JobContext()
+        context.set_options(options)
+        context.set_work_folder(work_folder)
+
+        build_pipeline(options, work_folder, _log, context)
+        atexit.register(cleanup_working_files, work_folder, options)
+        cmdline.run(options)
+    except ruffus_exceptions.RethrownJobError as e:
+        if options.verbose:
+            _log.debug(str(e))  # stringify exception so logger doesn't have to
+
+        # Ruffus flattens exception to 5 element tuples. Because of a bug
+        # in <= 2.6.3 it may present either the single:
+        #   (task, job, exc, value, stack)
+        # or something like:
+        #   [[(task, job, exc, value, stack)]]
+        #
+        # Generally cross-process exception marshalling doesn't work well
+        # and ruffus doesn't support because BaseException has its own
+        # implementation of __reduce__ that attempts to reconstruct the
+        # exception based on e.__init__(e.args).
+        #
+        # Attempting to log the exception directly marshalls it to the logger
+        # which is probably in another process, so it's better to log only
+        # data from the exception at this point.
+
+        exitcode = traverse_ruffus_exception(e.args, options, _log)
+        if exitcode is None:
+            _log.error("Unexpected ruffus exception: " + str(e))
+            _log.error(repr(e))
+            return ExitCode.other_error
+        else:
+            return exitcode
+    except ExitCodeException as e:
+        return e.exit_code
+    except Exception as e:
+        _log.error(e)
+        return ExitCode.other_error
+
+    if options.output_file != '-':
+        if options.output_type == 'pdfa':
+            pdfa_info = file_claims_pdfa(options.output_file)
+            if pdfa_info['pass']:
+                msg = 'Output file is a {} (as expected)'
+                _log.info(msg.format(pdfa_info['conformance']))
+            else:
+                msg = 'Output file is okay but is not PDF/A (seems to be {})'
+                _log.warning(msg.format(pdfa_info['conformance']))
+
+                return ExitCode.invalid_output_pdf
+        if not qpdf.check(options.output_file, _log):
+            _log.warning('Output file: The generated PDF is INVALID')
+            return ExitCode.invalid_output_pdf
+    else:
+        _log.info("Output sent to stdout")
+
+    pdfinfo = context.get_pdfinfo()
+    if options.verbose:
+        from pprint import pformat
+        _log.debug(pformat(pdfinfo))
+    direction = {0: 'n', 90: 'e',
+                 180: 's', 270: 'w'}
+    orientations = []
+    for n, page in enumerate(pdfinfo):
+        angle = pdfinfo[n].get('rotated', 0)
+        if angle != 0:
+            orientations.append('{0}{1}'.format(
+                n + 1,
+                direction.get(angle, '')))
+    if orientations:
+        _log.info('Page orientations detected: ' + ' '.join(orientations))
+
+    return ExitCode.ok
+
+
+if __name__ == '__main__':
+    sys.exit(run_pipeline())

ocrmypdf/exceptions.py

@@ -0,0 +1,54 @@
+#!/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
+    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

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

@@ -0,0 +1,82 @@
+#!/usr/bin/env python3
+# © 2015 James R. Barlow: github.com/jbarlow83
+
+from tempfile import NamedTemporaryFile
+from subprocess import Popen, PIPE, STDOUT, check_call
+from shutil import copy
+from . import get_program
+from ..pdfa import SRGB_ICC_PROFILE
+
+
+def rasterize_pdf(input_file, output_file, xres, yres, raster_device, log,
+                  pageno=1):
+    with NamedTemporaryFile(delete=True) as tmp:
+        args_gs = [
+            get_program('gs'),
+            '-dQUIET',
+            '-dSAFER',
+            '-dBATCH',
+            '-dNOPAUSE',
+            '-sDEVICE=%s' % raster_device,
+            '-dFirstPage=%i' % pageno,
+            '-dLastPage=%i' % pageno,
+            '-o', tmp.name,
+            '-r{0}x{1}'.format(str(round(xres)), str(round(yres))),
+            input_file
+        ]
+
+        p = Popen(args_gs, close_fds=True, stdout=PIPE, stderr=STDOUT,
+                  universal_newlines=True)
+        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)
+        else:
+            log.error('Ghostscript rendering failed')
+
+
+def generate_pdfa(pdf_pages, output_file, log, threads=1):
+    with NamedTemporaryFile(delete=True) as gs_pdf:
+        args_gs = [
+            get_program("gs"),
+            "-dQUIET",
+            "-dBATCH",
+            "-dNOPAUSE",
+            '-dNumRenderingThreads=' + str(threads),
+            "-sDEVICE=pdfwrite",
+            "-dAutoRotatePages=/None",
+            "-sColorConversionStrategy=/RGB",
+            "-sProcessColorModel=DeviceRGB",
+            "-dJPEGQ=95",
+            "-dPDFA=2",
+            "-dPDFACompatibilityPolicy=1",
+            "-sOutputFile=" + gs_pdf.name,
+        ]
+        args_gs.extend(pdf_pages)
+        p = Popen(args_gs, close_fds=True, stdout=PIPE, stderr=STDOUT,
+                  universal_newlines=True)
+        stdout, _ = p.communicate()
+
+        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 p.returncode == 0:
+            # Ghostscript does not change return code when it fails to create
+            # PDF/A - check PDF/A status elsewhere
+            copy(gs_pdf.name, output_file)
+        else:
+            log.error('Ghostscript PDF/A failed')

ocrmypdf/exec/qpdf.py

@@ -0,0 +1,133 @@
+#!/usr/bin/env python3
+# © 2015 James R. Barlow: github.com/jbarlow83
+
+from subprocess import CalledProcessError, check_output, STDOUT, check_call
+from functools import lru_cache
+import sys
+import os
+import re
+
+from ..exceptions import InputFileError, SubprocessOutputError, \
+    MissingDependencyError, EncryptedPdfError
+from . import get_program
+
+
+@lru_cache(maxsize=1)
+def version():
+    args_qpdf = [
+        get_program('qpdf'),
+        '--version'
+    ]
+    try:
+        versions = check_output(
+            args_qpdf, close_fds=True, universal_newlines=True,
+            stderr=STDOUT)
+    except CalledProcessError 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=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:
+        if e.returncode == 2:
+            log.error("{0}: not a valid PDF, and could not repair it.".format(
+                input_file))
+            log.error("Details:")
+            log.error(e.output)
+        elif e.returncode == 3:
+            log.info("qpdf --check returned warnings:")
+            log.info(e.output)
+        else:
+            log.warning(e.output)
+        return False
+    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
+    ]
+    try:
+        check_output(args_qpdf, stderr=STDOUT, universal_newlines=True)
+    except CalledProcessError as e:
+        if e.returncode == 3 and e.output.find("operation succeeded"):
+            log.debug('qpdf found and fixed errors: ' + e.output)
+            log.debug(e.output)
+            return
+
+        if _probably_encrypted(e):
+            log.error("{0}: this PDF is password-protected - password must "
+                      "be removed for OCR".format(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)
+            raise InputFileError() from e
+        else:
+            log.error("{0}: unknown error".format(
+                      input_file))
+            log.error(e.output)
+            raise SubprocessOutputError() from e
+
+
+def get_npages(input_file, log):
+    try:
+        pages = check_output(
+            [get_program('qpdf'), '--show-npages', input_file],
+             universal_newlines=True, close_fds=True)
+    except CalledProcessError as e:
+        if e.returncode == 2 and e.output.find('No such file'):
+            log.error(e.output)
+            raise InputFileError() from e
+    return int(pages)
+
+
+def split_pages(input_file, work_folder, npages):
+    """Split multipage PDF into individual pages.
+
+    Incredibly enough, this multiple process approach is about 70 times
+    faster than using Ghostscript.
+    """
+    for n in range(int(npages)):
+        args_qpdf = [
+            get_program('qpdf'), input_file,
+            '--pages', input_file, '{0}'.format(n + 1), '--',
+            os.path.join(work_folder, '{0:06d}.page.pdf'.format(n + 1))
+        ]
+        check_call(args_qpdf)
+
+
+def merge(input_files, output_file):
+    """Merge the list of input files (all filenames) into the output file.
+
+    The input files may contain one or more pages.
+    """
+    args_qpdf = [
+        get_program('qpdf'), input_files[0], '--pages'
+    ] + input_files + ['--', output_file]
+    check_call(args_qpdf)
+

ocrmypdf/exec/tesseract.py

@@ -0,0 +1,313 @@
+#!/usr/bin/env python3
+# © 2015 James R. Barlow: github.com/jbarlow83
+
+import sys
+import os
+import re
+import shutil
+from functools import lru_cache
+from ..exceptions import MissingDependencyError
+from ..helpers import page_number
+from . import get_program
+from collections import namedtuple
+from textwrap import dedent
+
+from subprocess import Popen, PIPE, CalledProcessError, \
+    TimeoutExpired, check_output, STDOUT, DEVNULL
+
+
+OrientationConfidence = namedtuple(
+    'OrientationConfidence',
+    ('angle', 'confidence'))
+
+HOCR_TEMPLATE = '''<?xml version="1.0" encoding="UTF-8"?>
+<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN"
+    "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
+<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
+ <head>
+  <title></title>
+  <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
+  <meta name='ocr-system' content='tesseract 3.02.02' />
+  <meta name='ocr-capabilities' content='ocr_page ocr_carea ocr_par ocr_line ocrx_word'/>
+ </head>
+ <body>
+  <div class='ocr_page' id='page_1' title='image "x.tif"; bbox 0 0 {0} {1}; ppageno 0'>
+   <div class='ocr_carea' id='block_1_1' title="bbox 0 1 {0} {1}">
+    <p class='ocr_par' dir='ltr' id='par_1' title="bbox 0 1 {0} {1}">
+     <span class='ocr_line' id='line_1' title="bbox 0 1 {0} {1}"><span class='ocrx_word' id='word_1' title="bbox 0 1 {0} {1}"> </span>
+     </span>
+    </p>
+   </div>
+  </div>
+ </body>
+</html>'''
+
+
+@lru_cache(maxsize=1)
+def version():
+    args_tess = [
+        get_program('tesseract'),
+        '--version'
+    ]
+    try:
+        versions = check_output(
+                args_tess, close_fds=True, universal_newlines=True,
+                stderr=STDOUT)
+    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 = [
+        get_program('tesseract'),
+        '--list-langs'
+    ]
+    try:
+        langs = check_output(
+                args_tess, close_fds=True, universal_newlines=True,
+                stderr=STDOUT)
+    except CalledProcessError as e:
+        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 tess_base_args(languages, engine_mode):
+    args = [
+        get_program('tesseract'),
+    ]
+    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'
+    ]
+
+    try:
+        stdout = check_output(
+            args_tesseract, close_fds=True, stderr=STDOUT,
+            universal_newlines=True, timeout=timeout)
+    except TimeoutExpired:
+        return OrientationConfidence(angle=0, confidence=0.0)
+    except CalledProcessError as e:
+        tesseract_log_output(log, e.output, input_file)
+        if ('Too few characters. Skipping this page' in e.output or
+                'Image too large' in e.output):
+            return OrientationConfidence(0, 0)
+        raise e from e
+    else:
+        osd = {}
+        for line in stdout.splitlines():
+            line = line.strip()
+            parts = line.split(':', maxsplit=2)
+            if len(parts) == 2:
+                osd[parts[0].strip()] = parts[1].strip()
+
+        angle = int(osd.get('Orientation in degrees', 0))
+        if 'Orientation' in osd:
+            # Tesseract < 3.04.01
+            # reports "Orientation in degrees" as a counterclockwise angle
+            # We keep it clockwise
+            assert 'Rotate' not in osd
+            angle = -angle % 360
+        else:
+            # Tesseract == 3.04.01, hopefully also Tesseract > 3.04.01
+            # reports "Orientation in degrees" as a clockwise angle
+            assert 'Rotate' in osd
+
+        oc = OrientationConfidence(
+            angle=angle,
+            confidence=float(osd.get('Orientation confidence', 0)))
+        return oc
+
+
+def tesseract_log_output(log, stdout, input_file):
+    lines = stdout.splitlines()
+    prefix = "{0:4d}: [tesseract] ".format(page_number(input_file))
+    for line in lines:
+        if line.startswith("Tesseract Open Source"):
+            continue
+        elif line.startswith("Warning in pixReadMem"):
+            continue
+        elif 'diacritics' in line:
+            log.warning(prefix + "lots of diacritics - possibly poor OCR")
+        elif line.startswith('OSD: Weak margin'):
+            log.warning(prefix + "unsure about page orientation")
+        elif 'error' in line.lower() or 'exception' in line.lower():
+            log.error(prefix + line.strip())
+        else:
+            log.info(prefix + line.strip())
+
+
+def page_timedout(log, input_file):
+    prefix = "{0:4d}: [tesseract] ".format(page_number(input_file))
+    log.warning(prefix + " took too long to OCR - skipping")
+
+
+def _generate_null_hocr(output_hocr, image):
+    """Produce a .hocr file that reports no text detected on a page that is
+    the same size as the input image."""
+    from PIL import Image
+
+    im = Image.open(image)
+    w, h = im.size
+
+    with open(output_hocr, 'w', encoding="utf-8") as f:
+        f.write(HOCR_TEMPLATE.format(w, h))
+
+
+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 = tess_base_args(language, engine_mode)
+
+    if pagesegmode is not None:
+        args_tesseract.extend([psm(), str(pagesegmode)])
+
+    args_tesseract.extend([
+        input_file,
+        badxml,
+        'hocr'
+    ] + tessconfig)
+    try:
+        log.debug(args_tesseract)
+        stdout = check_output(
+            args_tesseract, close_fds=True, stderr=STDOUT,
+            universal_newlines=True, timeout=timeout)
+    except TimeoutExpired:
+        # Generate a HOCR file with no recognized text if tesseract times out
+        # Temporary workaround to hocrTransform not being able to function if
+        # it does not have a valid hOCR file.
+        page_timedout(log, input_file)
+        _generate_null_hocr(output_hocr, input_file)
+    except CalledProcessError as e:
+        tesseract_log_output(log, e.output, input_file)
+        if 'Image too large' in e.output:
+            _generate_null_hocr(output_hocr, input_file)
+            return
+
+        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)
+        elif os.path.exists(badxml + '.hocr'):
+            # Tesseract 3.03 appends suffix ".hocr" on its own (.badxml.hocr)
+            shutil.move(badxml + '.hocr', badxml)
+
+        # Tesseract 3.03 inserts source filename into hocr file without
+        # escaping it, creating invalid XML and breaking the parser.
+        # As a workaround, rewrite the hocr file, replacing the filename
+        # with a space.  Don't know if Tesseract 3.02 does the same.
+
+        regex_nested_single_quotes = re.compile(
+            r"""title='image "([^"]*)";""")
+        with open(badxml, mode='r', encoding='utf-8') as f_in, \
+                open(output_hocr, mode='w', encoding='utf-8') as f_out:
+            for line in f_in:
+                line = regex_nested_single_quotes.sub(
+                    r"""title='image " ";""", line)
+                f_out.write(line)
+
+
+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 = tess_base_args(language, engine_mode)
+
+    if pagesegmode is not None:
+        args_tesseract.extend([psm(), str(pagesegmode)])
+
+    if text_only:
+        args_tesseract.extend(['-c', 'textonly_pdf=1'])
+
+    args_tesseract.extend([
+        input_image,
+        os.path.splitext(output_pdf)[0],  # Tesseract appends suffix
+        'pdf'
+    ] + 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)
+    except CalledProcessError as e:
+        tesseract_log_output(log, e.output, input_image)
+        if 'Image too large' in e.output:
+            shutil.copy(skip_pdf, output_pdf)
+            return
+        raise e from e
+    else:
+        tesseract_log_output(log, stdout, input_image)

ocrmypdf/exec/unpaper.py

@@ -0,0 +1,104 @@
+#!/usr/bin/env python3
+# © 2015 James R. Barlow: github.com/jbarlow83
+# unpaper documentation:
+# https://github.com/Flameeyes/unpaper/blob/master/doc/basic-concepts.md
+
+from subprocess import CalledProcessError, STDOUT, check_output, check_call
+from tempfile import NamedTemporaryFile
+import sys
+import os
+from functools import lru_cache
+from ..exceptions import MissingDependencyError
+from . import get_program
+
+
+@lru_cache(maxsize=1)
+def version():
+    args_unpaper = [
+        get_program('unpaper'),
+        '--version'
+    ]
+    version = check_output(
+        args_unpaper, close_fds=True, universal_newlines=True,
+        stderr=STDOUT, timeout=5)
+    return version.strip()
+
+
+try:
+    from PIL import Image
+except ImportError:
+    print("Could not find Python3 imaging library", file=sys.stderr)
+    raise
+
+
+def run(input_file, output_file, dpi, log, mode_args):
+    args_unpaper = [
+        get_program('unpaper'),
+        '-v',
+        '--dpi', str(dpi)
+    ] + mode_args
+
+    SUFFIXES = {'1': '.pbm', 'L': '.pgm', 'RGB': '.ppm'}
+
+    im = Image.open(input_file)
+    if im.mode not in SUFFIXES.keys():
+        log.info("Converting image to other colorspace")
+        try:
+            if im.mode == 'P' and len(im.getcolors()) == 2:
+                im = im.convert(mode='1')
+            else:
+                im = im.convert(mode='RGB')
+        except IOError as e:
+            log.error(
+                    "Could not convert image with type " + im.mode)
+            raise MissingDependencyError() from e
+
+    try:
+        suffix = SUFFIXES[im.mode]
+    except KeyError:
+        log.error(
+                "Failed to convert image to a supported format.")
+        raise MissingDependencyError() from e
+
+    with NamedTemporaryFile(suffix=suffix) as input_pnm, \
+            NamedTemporaryFile(suffix=suffix, mode="r+b") as output_pnm:
+        im.save(input_pnm, format='PPM')
+        im.close()
+
+        os.unlink(output_pnm.name)
+
+        args_unpaper.extend([input_pnm.name, output_pnm.name])
+        try:
+            stdout = check_output(
+                args_unpaper, close_fds=True,
+                universal_newlines=True, stderr=STDOUT,
+                )
+        except CalledProcessError as e:
+            log.debug(e.output)
+            raise e from e
+        else:
+            log.debug(stdout)
+            Image.open(output_pnm.name).save(output_file)
+
+
+def deskew(input_file, output_file, dpi, log):
+    run(input_file, output_file, dpi, log, [
+        '--mask-scan-size', '100',  # don't blank out narrow columns
+        '--no-border-align',  # don't align visible content to borders
+        '--no-mask-center',   # don't center visible content within page
+        '--no-grayfilter',    # don't remove light gray areas
+        '--no-blackfilter',   # don't remove solid black areas
+        '--no-noisefilter',   # don't remove salt and pepper noise
+        '--no-blurfilter'     # don't remove blurry objects/debris
+    ])
+
+
+def clean(input_file, output_file, dpi, log):
+    run(input_file, output_file, dpi, log, [
+        '--mask-scan-size', '100',  # don't blank out narrow columns
+        '--no-border-align',  # don't align visible content to borders
+        '--no-mask-center',   # don't center visible content within page
+        '--no-grayfilter',    # don't remove light gray areas
+        '--no-blackfilter',   # don't remove solid black areas
+        '--no-deskew',        # don't deskew
+    ])

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/hocrtransform.py

@@ -0,0 +1,230 @@
+#!/usr/bin/env python3
+##############################################################################
+# Copyright (c) 2013-14: fritz-hh from Github
+#   (https://github.com/fritz-hh)
+#
+# Copyright (c) 2010: Jonathan Brinley from Github
+#   (https://github.com/jbrinley/HocrConverter)
+#   Initial version by Jonathan Brinley, jonathanbrinley@gmail.com
+##############################################################################
+from reportlab.pdfgen.canvas import Canvas
+from reportlab.lib.units import inch
+from xml.etree import ElementTree
+from PIL import Image
+from collections import namedtuple
+import re
+import argparse
+
+
+Rect = namedtuple('Rect', ['x1', 'y1', 'x2', 'y2'])
+
+
+class HocrTransformError(Exception):
+    pass
+
+
+class HocrTransform():
+
+    """
+    A class for converting documents from the hOCR format.
+    For details of the hOCR format, see:
+    http://docs.google.com/View?docid=dfxcv4vc_67g844kf
+    """
+
+    def __init__(self, hocrFileName, dpi):
+        self.dpi = dpi
+        self.boxPattern = re.compile(r'bbox((\s+\d+){4})')
+
+        self.hocr = ElementTree.parse(hocrFileName)
+
+        # if the hOCR file has a namespace, ElementTree requires its use to
+        # find elements
+        matches = re.match(r'({.*})html', self.hocr.getroot().tag)
+        self.xmlns = ''
+        if matches:
+            self.xmlns = matches.group(1)
+
+        # get dimension in pt (not pixel!!!!) of the OCRed image
+        self.width, self.height = None, None
+        for div in self.hocr.findall(
+                ".//%sdiv[@class='ocr_page']" % (self.xmlns)):
+            coords = self.element_coordinates(div)
+            pt_coords = self.pt_from_pixel(coords)
+            self.width = pt_coords.x2 - pt_coords.x1
+            self.height = pt_coords.y2 - pt_coords.y1
+            # there shouldn't be more than one, and if there is, we don't want
+            # it
+            break
+        if self.width is None or self.height is None:
+            raise HocrTransformError("hocr file is missing page dimensions")
+
+    def __str__(self):
+        """
+        Return the textual content of the HTML body
+        """
+        if self.hocr is None:
+            return ''
+        body = self.hocr.find(".//%sbody" % (self.xmlns))
+        if body:
+            return self._get_element_text(body)
+        else:
+            return ''
+
+    def _get_element_text(self, element):
+        """
+        Return the textual content of the element and its children
+        """
+        text = ''
+        if element.text is not None:
+            text += element.text
+        for child in element.getchildren():
+            text += self._get_element_text(child)
+        if element.tail is not None:
+            text += element.tail
+        return text
+
+    def element_coordinates(self, element):
+        """
+        Returns a tuple containing the coordinates of the bounding box around
+        an element
+        """
+        out = (0, 0, 0, 0)
+        if 'title' in element.attrib:
+            matches = self.boxPattern.search(element.attrib['title'])
+            if matches:
+                coords = matches.group(1).split()
+                out = Rect._make(int(coords[n]) for n in range(4))
+        return out
+
+    def pt_from_pixel(self, pxl):
+        """
+        Returns the quantity in PDF units (pt) given quantity in pixels
+        """
+        return Rect._make(
+            (c / self.dpi * inch) for c in pxl)
+
+    def replace_unsupported_chars(self, s):
+        """
+        Given an input string, returns the corresponding string that:
+        - is available in the helvetica facetype
+        - does not contain any ligature (to allow easy search in the PDF file)
+        """
+        # The 'u' before the character to replace indicates that it is a
+        # unicode character
+        s = s.replace(u"fl", "fl")
+        s = s.replace(u"fi", "fi")
+        return s
+
+    def to_pdf(self, outFileName, imageFileName=None, showBoundingboxes=False,
+               fontname="Helvetica", invisibleText=False):
+        """
+        Creates a PDF file with an image superimposed on top of the text.
+        Text is positioned according to the bounding box of the lines in
+        the hOCR file.
+        The image need not be identical to the image used to create the hOCR
+        file.
+        It can have a lower resolution, different color mode, etc.
+        """
+        # create the PDF file
+        # page size in points (1/72 in.)
+        pdf = Canvas(
+            outFileName, pagesize=(self.width, self.height), pageCompression=1)
+
+        # draw bounding box for each paragraph
+        # light blue for bounding box of paragraph
+        pdf.setStrokeColorRGB(0, 1, 1)
+        # light blue for bounding box of paragraph
+        pdf.setFillColorRGB(0, 1, 1)
+        pdf.setLineWidth(0)		# no line for bounding box
+        for elem in self.hocr.findall(
+                ".//%sp[@class='%s']" % (self.xmlns, "ocr_par")):
+
+            elemtxt = self._get_element_text(elem).rstrip()
+            if len(elemtxt) == 0:
+                continue
+
+            pxl_coords = self.element_coordinates(elem)
+            pt = self.pt_from_pixel(pxl_coords)
+
+            # draw the bbox border
+            if showBoundingboxes:
+                pdf.rect(
+                    pt.x1, self.height - pt.y2, pt.x2 - pt.x1, pt.y2 - pt.y1,
+                    fill=1)
+
+        # check if element with class 'ocrx_word' are available
+        # otherwise use 'ocr_line' as fallback
+        elemclass = "ocr_line"
+        if self.hocr.find(
+                ".//%sspan[@class='ocrx_word']" % (self.xmlns)) is not None:
+            elemclass = "ocrx_word"
+
+        # itterate all text elements
+        # light green for bounding box of word/line
+        pdf.setStrokeColorRGB(1, 0, 0)
+        pdf.setLineWidth(0.5)		# bounding box line width
+        pdf.setDash(6, 3)		# bounding box is dashed
+        pdf.setFillColorRGB(0, 0, 0)  # text in black
+        for elem in self.hocr.findall(
+                ".//%sspan[@class='%s']" % (self.xmlns, elemclass)):
+
+            elemtxt = self._get_element_text(elem).rstrip()
+
+            elemtxt = self.replace_unsupported_chars(elemtxt)
+
+            if len(elemtxt) == 0:
+                continue
+
+            pxl_coords = self.element_coordinates(elem)
+            pt = self.pt_from_pixel(pxl_coords)
+
+            # draw the bbox border
+            if showBoundingboxes:
+                pdf.rect(
+                    pt.x1, self.height - pt.y2, pt.x2 - pt.x1, pt.y2 - pt.y1,
+                    fill=0)
+
+            text = pdf.beginText()
+            fontsize = pt.y2 - pt.y1
+            text.setFont(fontname, fontsize)
+            if invisibleText:
+                text.setTextRenderMode(3)  # Invisible (indicates OCR text)
+
+            # set cursor to bottom left corner of bbox (adjust for dpi)
+            text.setTextOrigin(pt.x1, self.height - pt.y2)
+
+            # scale the width of the text to fill the width of the bbox
+            text.setHorizScale(
+                100 * (pt.x2 - pt.x1) / pdf.stringWidth(
+                    elemtxt, fontname, fontsize))
+
+            # write the text to the page
+            text.textLine(elemtxt)
+            pdf.drawText(text)
+
+        # put the image on the page, scaled to fill the page
+        if imageFileName is not None:
+            pdf.drawImage(imageFileName, 0, 0,
+                          width=self.width, height=self.height)
+
+        # finish up the page and save it
+        pdf.showPage()
+        pdf.save()
+
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser(description='Convert hocr file to PDF')
+    parser.add_argument('-b', '--boundingboxes', action="store_true",
+                        default=False, help='Show bounding boxes borders')
+    parser.add_argument('-r', '--resolution', type=int,
+                        default=300,
+                        help='Resolution of the image that was OCRed')
+    parser.add_argument('-i', '--image', default=None,
+                        help='Path to the image to be placed above the text')
+    parser.add_argument('hocrfile', help='Path to the hocr file to be parsed')
+    parser.add_argument(
+        'outputfile', help='Path to the PDF file to be generated')
+    args = parser.parse_args()
+
+    hocr = HocrTransform(args.hocrfile, args.resolution)
+    hocr.to_pdf(args.outputfile, args.image, args.boundingboxes)

ocrmypdf/leptonica.py

@@ -0,0 +1,598 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+#
+# © 2013-16: jbarlow83 from Github (https://github.com/jbarlow83)
+#
+# Python FFI wrapper for Leptonica library
+
+import argparse
+import sys
+import os
+import logging
+from tempfile import TemporaryFile
+from ctypes.util import find_library
+from .lib._leptonica import ffi
+from functools import lru_cache
+from enum import Enum
+
+lept = ffi.dlopen(find_library('lept'))
+
+logger = logging.getLogger(__name__)
+
+
+def stderr(*objs):
+    """Python 2/3 compatible print to stderr.
+    """
+    print("leptonica.py:", *objs, file=sys.stderr)
+
+
+class LeptonicaErrorTrap(object):
+    """Context manager to trap errors reported by Leptonica.
+
+    Leptonica's error return codes are unreliable to the point of being
+    almost useless.  It does, however, write errors to stderr provided that is
+    not disabled at its compile time.  Fortunately this is done using error
+    macros so it is very self-consistent.
+
+    This context manager redirects stderr to a temporary file which is then
+    read and parsed for error messages.  As a side benefit, debug messages
+    from Leptonica are also suppressed.
+
+    """
+    def __enter__(self):
+        from io import UnsupportedOperation
+        self.tmpfile = TemporaryFile()
+
+        # Save the old stderr, and redirect stderr to temporary file
+        sys.stderr.flush()
+        try:
+            self.copy_of_stderr = os.dup(sys.stderr.fileno())
+            os.dup2(self.tmpfile.fileno(), sys.stderr.fileno(),
+                    inheritable=False)
+        except UnsupportedOperation:
+            self.copy_of_stderr = None
+        return
+
+    def __exit__(self, exc_type, exc_value, traceback):
+        # Restore old stderr
+        sys.stderr.flush()
+        if self.copy_of_stderr is not None:
+            os.dup2(self.copy_of_stderr, sys.stderr.fileno())
+            os.close(self.copy_of_stderr)
+
+        # Get data from tmpfile (in with block to ensure it is closed)
+        with self.tmpfile as tmpfile:
+            tmpfile.seek(0)  # Cursor will be at end, so move back to beginning
+            leptonica_output = tmpfile.read().decode(errors='replace')
+
+        assert self.tmpfile.closed
+        assert not sys.stderr.closed
+
+        # If there are Python errors, let them bubble up
+        if exc_type:
+            logger.warning(leptonica_output)
+            return False
+
+        # If there are Leptonica errors, wrap them in Python excpetions
+        if 'Error' in leptonica_output:
+            if 'image file not found' in leptonica_output:
+                raise FileNotFoundError()
+            if 'pixWrite: stream not opened' in leptonica_output:
+                raise LeptonicaIOError()
+            raise LeptonicaError(leptonica_output)
+
+        return False
+
+
+class LeptonicaError(Exception):
+    pass
+
+
+class LeptonicaIOError(LeptonicaError):
+    pass
+
+
+class RemoveColormap(Enum):
+    to_binary = 0
+    to_grayscale = 1
+    to_full_color = 2
+    based_on_src = 3
+
+
+class Pix:
+    """Wrapper around leptonica's PIX object.
+
+    Leptonica uses referencing counting on PIX objects. Also, many Leptonica
+    functions return the original object with an increased reference count
+    if the operation had no effect (for example, image skew was found to be 0).
+    This has complications for memory management in Python. Whenever Leptonica
+    returns a PIX object (new or old), we wrap it in this class, which
+    registers it with the FFI garbage collector. pixDestroy() decrements the
+    reference count and only destroys when the last reference is removed.
+
+    Leptonica's reference counting is not threadsafe. This class can be used
+    in a threadsafe manner if a Python threading.Lock protects the data.
+
+    This class treats Pix objects as immutable.  All methods return new
+    modified objects.  This allows convenient chaining:
+
+    >>>   Pix.read('filename.jpg').scale((0.5, 0.5)).deskew().show()
+
+    """
+
+    def __init__(self, pix):
+        self._pix = ffi.gc(pix, Pix._pix_destroy)
+
+    def __repr__(self):
+        if self._pix:
+            s = "<leptonica.Pix image size={0}x{1} depth={2} at 0x{3:x}>"
+            return s.format(self._pix.w, self._pix.h, self._pix.d,
+                            int(ffi.cast("intptr_t", self._pix)))
+        else:
+            return "<leptonica.Pix image NULL>"
+
+    def _repr_png_(self):
+        """iPython display hook
+
+        returns png version of image
+        """
+
+        data = ffi.new('l_uint8 **')
+        size = ffi.new('size_t *')
+
+        err = lept.pixWriteMemPng(data, size, self._pix, 0)
+        if err != 0:
+            raise LeptonicaIOError("pixWriteMemPng")
+
+        char_data = ffi.cast('char *', data[0])
+        return ffi.buffer(char_data, size[0])[:]
+
+    def __getstate__(self):
+        data = ffi.new('l_uint32 **')
+        size = ffi.new('size_t *')
+
+        err = lept.pixSerializeToMemory(self._pix, data, size)
+        if err != 0:
+            raise LeptonicaIOError("pixSerializeToMemory")
+
+        char_data = ffi.cast('char *', data[0])
+
+        # Copy from C bytes to python bytes()
+        data_bytes = ffi.buffer(char_data, size[0])[:]
+
+        # Can now free C bytes
+        lept.lept_free(char_data)
+        return dict(data=data_bytes)
+
+    def __setstate__(self, state):
+        cdata_bytes = ffi.new('char[]', state['data'])
+        cdata_uint32 = ffi.cast('l_uint32 *', cdata_bytes)
+
+        pix = lept.pixDeserializeFromMemory(
+            cdata_uint32, len(state['data']))
+        Pix.__init__(self, pix)
+
+    def __eq__(self, other):
+        return self.__getstate__() == other.__getstate__()
+
+    @property
+    def width(self):
+        return self._pix.w
+
+    @property
+    def height(self):
+        return self._pix.h
+
+    @property
+    def depth(self):
+        return self._pix.d
+
+    @property
+    def size(self):
+        return (self._pix.w, self._pix.h)
+
+    @property
+    def info(self):
+        return {'dpi': (self._pix.xres, self._pix.yres)}
+
+    @property
+    def mode(self):
+        "Return mode like PIL.Image"
+        if self.depth == 1:
+            return '1'
+        elif self.depth >= 16:
+            return 'RGB'
+        elif not self._pix.colormap:
+            return 'L'
+        else:
+            return 'P'
+
+    @classmethod
+    def read(cls, filename):
+        """Load an image file into a PIX object.
+
+        Leptonica can load TIFF, PNM (PBM, PGM, PPM), PNG, and JPEG.  If
+        loading fails then the object will wrap a C null pointer.
+        """
+        with LeptonicaErrorTrap():
+            return cls(lept.pixRead(
+                filename.encode(sys.getfilesystemencoding())))
+
+    def write_implied_format(
+            self, filename, jpeg_quality=0, jpeg_progressive=0):
+        """Write pix to the filename, with the extension indicating format.
+
+        jpeg_quality -- quality (iff JPEG; 1 - 100, 0 for default)
+        jpeg_progressive -- (iff JPEG; 0 for baseline seq., 1 for progressive)
+        """
+        with LeptonicaErrorTrap():
+            lept.pixWriteImpliedFormat(
+                filename.encode(sys.getfilesystemencoding()),
+                self._pix, jpeg_quality, jpeg_progressive)
+
+    def topil(self):
+        "Returns a PIL.Image version of this Pix"
+        from PIL import Image
+
+        # Leptonica manages data in words, so it implicitly does an endian
+        # swap.  Tell Pillow about this when it reads the data.
+        pix = self
+        if sys.byteorder == 'little':
+            if self.mode == 'RGB':
+                raw_mode = 'XBGR'
+            elif self.mode == 'RGBA':
+                raw_mode = 'ABGR'
+            elif self.mode == '1':
+                raw_mode = '1;I'
+                pix = Pix(lept.pixEndianByteSwapNew(pix._pix))
+            else:
+                raw_mode = self.mode
+                pix = Pix(lept.pixEndianByteSwapNew(pix._pix))
+        else:
+            raw_mode = self.mode  # no endian swap needed
+
+        size = (pix._pix.w, pix._pix.h)
+        bytecount = pix._pix.wpl * 4 * pix._pix.h
+        buf = ffi.buffer(pix._pix.data, bytecount)
+        stride = pix._pix.wpl * 4
+
+        im = Image.frombytes(self.mode, size, buf, 'raw', raw_mode, stride)
+
+        return im
+
+    def show(self):
+        return self.topil().show()
+
+    def deskew(self, reduction_factor=0):
+        """Returns the deskewed pix object.
+
+        A clone of the original is returned when the algorithm cannot find a
+        skew angle with sufficient confidence.
+
+        reduction_factor -- amount to downsample (0 for default) when searching
+            for skew angle
+        """
+        with LeptonicaErrorTrap():
+            return Pix(lept.pixDeskew(self._pix, reduction_factor))
+
+    def scale(self, scale_xy):
+        "Returns the pix object rescaled according to the proportions given."
+        with LeptonicaErrorTrap():
+            return Pix(lept.pixScale(self._pix, scale_xy[0], scale_xy[1]))
+
+    def rotate180(self):
+        with LeptonicaErrorTrap():
+            return Pix(lept.pixRotate180(ffi.NULL, self._pix))
+
+    def rotate_orth(self, quads):
+        "Orthographic rotation, quads: 0-3, number of clockwise rotations"
+        with LeptonicaErrorTrap():
+            return Pix(lept.pixRotateOrth(self._pix, quads))
+
+    def find_skew(self):
+        """Returns a tuple (deskew angle in degrees, confidence value).
+
+        Returns (None, None) if no angle is available.
+        """
+        with LeptonicaErrorTrap():
+            angle = ffi.new('float *', 0.0)
+            confidence = ffi.new('float *', 0.0)
+            result = lept.pixFindSkew(self._pix, angle, confidence)
+            if result == 0:
+                return (angle[0], confidence[0])
+            else:
+                return (None, None)
+
+    def convert_rgb_to_luminance(self):
+        with LeptonicaErrorTrap():
+            gray_pix = lept.pixConvertRGBToLuminance(self._pix)
+            if gray_pix:
+                return Pix(gray_pix)
+            return None
+
+    def remove_colormap(self, removal_type):
+        """Remove a palette
+
+            removal_type - RemovalColormap()
+        """
+
+        with LeptonicaErrorTrap():
+            return Pix(lept.pixRemoveColormap(self._pix, removal_type))
+
+    def otsu_adaptive_threshold(
+            self, tile_size=(300, 300), kernel_size=(4, 4), scorefract=0.1):
+        with LeptonicaErrorTrap():
+            sx, sy = tile_size
+            smoothx, smoothy = kernel_size
+            p_pix = ffi.new('PIX **')
+
+            result = lept.pixOtsuAdaptiveThreshold(
+                self._pix,
+                sx, sy,
+                smoothx, smoothy,
+                scorefract,
+                ffi.NULL,
+                p_pix)
+            if result == 0:
+                return Pix(p_pix[0])
+            else:
+                return None
+
+    def otsu_threshold_on_background_norm(
+            self, mask=None, tile_size=(10, 15), thresh=100, mincount=50,
+            bgval=255, kernel_size=(2, 2), scorefract=0.1):
+        with LeptonicaErrorTrap():
+            sx, sy = tile_size
+            smoothx, smoothy = kernel_size
+            if mask is None:
+                mask = ffi.NULL
+            if isinstance(mask, Pix):
+                mask = mask._pix
+
+            thresh_pix = lept.pixOtsuThreshOnBackgroundNorm(
+                self._pix,
+                mask,
+                sx, sy,
+                thresh, mincount, bgval,
+                smoothx, smoothy,
+                scorefract,
+                ffi.NULL
+                )
+            if thresh_pix == ffi.NULL:
+                return None
+            return Pix(thresh_pix)
+
+    def crop_to_foreground(
+            self, threshold=128, mindist=70, erasedist=30, pagenum=0,
+            showmorph=0, display=0, pdfdir=ffi.NULL):
+        with LeptonicaErrorTrap():
+            cropbox = Box(lept.pixFindPageForeground(
+                self._pix,
+                threshold,
+                mindist,
+                erasedist,
+                pagenum,
+                showmorph,
+                display,
+                pdfdir))
+
+            print(repr(cropbox))
+
+            cropped_pix = lept.pixClipRectangle(
+                self._pix,
+                cropbox._box,
+                ffi.NULL)
+
+            return Pix(cropped_pix)
+
+    def clean_background_to_white(
+            self, mask=None, grayscale=None, gamma=1.0, black=0, white=255):
+        with LeptonicaErrorTrap():
+            return Pix(lept.pixCleanBackgroundToWhite(
+                self._pix,
+                mask or ffi.NULL,
+                grayscale or ffi.NULL,
+                gamma,
+                black,
+                white))
+
+    def gamma_trc(self, gamma=1.0, minval=0, maxval=255):
+        with LeptonicaErrorTrap():
+            return Pix(lept.pixGammaTRC(
+                ffi.NULL,
+                self._pix,
+                gamma,
+                minval,
+                maxval
+                ))
+
+    def background_norm(
+            self, mask=None, grayscale=None, tile_size=(10, 15), fg_threshold=60,
+            min_count=40, bg_val=200, smooth_kernel=(2, 1)):
+        with LeptonicaErrorTrap():
+            return Pix(lept.pixBackgroundNorm(
+                self._pix,
+                mask or ffi.NULL,
+                grayscale or ffi.NULL,
+                tile_size[0],
+                tile_size[1],
+                fg_threshold,
+                min_count,
+                bg_val,
+                smooth_kernel[0],
+                smooth_kernel[1]
+                ))
+
+    @staticmethod
+    @lru_cache(maxsize=1)
+    def make_pixel_sum_tab8():
+        return lept.makePixelSumTab8()
+
+    @staticmethod
+    def correlation_binary(pix1, pix2):
+        if get_leptonica_version() < 'leptonica-1.72':
+            # Older versions of Leptonica (pre-1.72) have a buggy
+            # implementation of pixCorrelationBinary that overflows on larger
+            # images.  Ubuntu trusty has 1.70. Ubuntu PPA
+            # ppa:rebuntu16/avidemux+unofficial has "leptonlib" 1.73.
+            pix1_count = ffi.new('l_int32 *')
+            pix2_count = ffi.new('l_int32 *')
+            pixn_count = ffi.new('l_int32 *')
+            tab8 = Pix.make_pixel_sum_tab8()
+
+            lept.pixCountPixels(pix1._pix, pix1_count, tab8)
+            lept.pixCountPixels(pix2._pix, pix2_count, tab8)
+            pixn = Pix(lept.pixAnd(ffi.NULL, pix1._pix, pix2._pix))
+            lept.pixCountPixels(pixn._pix, pixn_count, tab8)
+
+            # Python converts these int32s to larger units as needed
+            # to avoid overflow. Overflow happens easily here.
+            correlation = (
+                    (pixn_count[0] * pixn_count[0]) /
+                    (pix1_count[0] * pix2_count[0])
+                    )
+            return correlation
+        else:
+            correlation = ffi.new('float *', 0.0)
+            result = lept.pixCorrelationBinary(pix1._pix, pix2._pix,
+                                               correlation)
+            if result != 0:
+                raise LeptonicaError("Correlation failed")
+            return correlation[0]
+
+    @staticmethod
+    def _pix_destroy(pix):
+        p_pix = ffi.new('PIX **', pix)
+        lept.pixDestroy(p_pix)
+        # print('pix destroy ' + repr(pix))
+
+
+class Box:
+    """Wrapper around Leptonica's BOX objects.
+
+    See class Pix for notes about reference counting.
+    """
+
+    def __init__(self, box):
+        self._box = ffi.gc(box, Box._box_destroy)
+
+    def __repr__(self):
+        if self._box:
+            return '<leptonica.Box x={0} y={1} w={2} h={3}>'.format(
+                self.x, self.y, self.w, self.h)
+        return '<leptonica.Box NULL>'
+
+    @property
+    def x(self):
+        return self._box.x
+
+    @property
+    def y(self):
+        return self._box.y
+
+    @property
+    def w(self):
+        return self._box.w
+
+    @property
+    def h(self):
+        return self._box.h
+
+    @staticmethod
+    def _box_destroy(box):
+        p_box = ffi.new('BOX **', box)
+        lept.boxDestroy(p_box)
+
+
+@lru_cache(maxsize=1)
+def get_leptonica_version():
+    """Get Leptonica version string.
+
+    Caveat: Leptonica expects the caller to free this memory.  We don't,
+    since that would involve binding to libc to access libc.free(),
+    a pointless effort to reclaim 100 bytes of memory.
+    """
+    return ffi.string(lept.getLeptonicaVersion()).decode()
+
+
+def deskew(infile, outfile, dpi):
+    try:
+        pix_source = Pix.read(infile)
+    except LeptonicaIOError:
+        raise LeptonicaIOError("Failed to open file: %s" % infile)
+
+    if dpi < 150:
+        reduction_factor = 1  # Don't downsample too much if DPI is already low
+    else:
+        reduction_factor = 0  # Use default
+    pix_deskewed = pix_source.deskew(reduction_factor)
+
+    try:
+        pix_deskewed.write_implied_format(outfile)
+    except LeptonicaIOError:
+        raise LeptonicaIOError("Failed to open destination file: %s" % outfile)
+
+
+def remove_background(infile, outfile, tile_size=(40, 60), gamma=1.0,
+                      black_threshold=70, white_threshold=190):
+    try:
+        pix = Pix.read(infile)
+    except LeptonicaIOError:
+        raise LeptonicaIOError("Failed to open file: %s" % infile)
+
+    pix = pix.background_norm(tile_size=tile_size).gamma_trc(
+            gamma, black_threshold, white_threshold)
+
+    try:
+        pix.write_implied_format(outfile)
+    except LeptonicaIOError:
+        raise LeptonicaIOError("Failed to open destination file: %s" % outfile)
+
+
+if __name__ == '__main__':
+    parser = argparse.ArgumentParser(
+        description="Python wrapper to access Leptonica")
+
+    subparsers = parser.add_subparsers(title='commands',
+                                       description='supported operations')
+
+    parser_deskew = subparsers.add_parser('deskew')
+    parser_deskew.add_argument('-r', '--dpi', dest='dpi', action='store',
+                               type=int, default=300, help='input resolution')
+    parser_deskew.add_argument('infile', help='image to deskew')
+    parser_deskew.add_argument('outfile', help='deskewed output image')
+    parser_deskew.set_defaults(func=deskew)
+
+    args = parser.parse_args()
+
+    if get_leptonica_version() != u'leptonica-1.69':
+        print("Unexpected leptonica version: %s" % getLeptonicaVersion())
+
+    args.func(args)
+
+
+def test_skew_angle():
+    from PIL import Image, ImageDraw
+    from tempfile import NamedTemporaryFile
+
+    im = Image.new(mode='1', size=(1000, 1000), color=1)
+
+    draw = ImageDraw.Draw(im)
+    for n in range(20):
+        draw.line([(50, 25 + 50*n), (950, 25 + 50*n)], width=1)
+    del draw
+
+    test_angles = [0.1 * ang for ang in range(1, 10)] + \
+                  [float(ang) for ang in range(1, 7)]
+    test_angles += [-ang for ang in test_angles]
+    test_angles = sorted(test_angles)
+
+    for rotate_angle in test_angles:
+        rotated_im = im.rotate(rotate_angle)
+        with NamedTemporaryFile(prefix='lept-skew', suffix='.png', delete=True) as tmpfile:
+            rotated_im.save(tmpfile)
+            pix = pixRead(tmpfile.name)
+            angle, confidence = pixFindSkew(pix)
+            print('{0} {1}  {2}'.format(rotate_angle, angle, confidence), file=sys.stderr)
+
+

ocrmypdf/lib/__init__.py

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

ocrmypdf/lib/compile_leptonica.py

@@ -0,0 +1,192 @@
+from cffi import FFI
+
+ffi = FFI()
+ffi.set_source("ocrmypdf.lib._leptonica", None)
+ffi.cdef("""
+typedef signed char             l_int8;
+typedef unsigned char           l_uint8;
+typedef short                   l_int16;
+typedef unsigned short          l_uint16;
+typedef int                     l_int32;
+typedef unsigned int            l_uint32;
+typedef float                   l_float32;
+typedef double                  l_float64;
+typedef long long               l_int64;
+typedef unsigned long long      l_uint64;
+
+struct Pix
+{
+    l_uint32             w;           /* width in pixels                   */
+    l_uint32             h;           /* height in pixels                  */
+    l_uint32             d;           /* depth in bits (bpp)               */
+    l_uint32             spp;         /* number of samples per pixel       */
+    l_uint32             wpl;         /* 32-bit words/line                 */
+    l_uint32             refcount;    /* reference count (1 if no clones)  */
+    l_int32              xres;        /* image res (ppi) in x direction    */
+                                      /* (use 0 if unknown)                */
+    l_int32              yres;        /* image res (ppi) in y direction    */
+                                      /* (use 0 if unknown)                */
+    l_int32              informat;    /* input file format, IFF_*          */
+    l_int32              special;     /* special instructions for I/O, etc */
+    char                *text;        /* text string associated with pix   */
+    struct PixColormap  *colormap;    /* colormap (may be null)            */
+    l_uint32            *data;        /* the image data                    */
+};
+typedef struct Pix PIX;
+
+struct PixColormap
+{
+    void            *array;     /* colormap table (array of RGBA_QUAD)     */
+    l_int32          depth;     /* of pix (1, 2, 4 or 8 bpp)               */
+    l_int32          nalloc;    /* number of color entries allocated       */
+    l_int32          n;         /* number of color entries used            */
+};
+typedef struct PixColormap  PIXCMAP;
+
+struct Box
+{
+    l_int32            x;
+    l_int32            y;
+    l_int32            w;
+    l_int32            h;
+    l_uint32           refcount;      /* reference count (1 if no clones)  */
+
+};
+typedef struct Box    BOX;
+
+""")
+
+ffi.cdef("""
+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 );
+l_int32 pixWriteImpliedFormat ( const char *filename, PIX *pix, l_int32 quality, l_int32 progressive );
+l_int32
+pixWriteMemPng(l_uint8  **pdata,
+               size_t    *psize,
+               PIX       *pix,
+               l_float32  gamma);
+
+void pixDestroy ( PIX **ppix );
+
+PIX *
+pixEndianByteSwapNew(PIX  *pixs);
+
+PIX * pixDeskew ( PIX *pixs, l_int32 redsearch );
+char * getLeptonicaVersion (  );
+l_int32 pixCorrelationBinary(PIX *pix1, PIX *pix2, l_float32 *pval);
+PIX *pixRotate180(PIX *pixd, PIX *pixs);
+PIX *
+pixRotateOrth(PIX     *pixs,
+              l_int32  quads);
+
+l_int32 pixCountPixels ( PIX *pix, l_int32 *pcount, l_int32 *tab8 );
+PIX * pixAnd ( PIX *pixd, PIX *pixs1, PIX *pixs2 );
+l_int32 * makePixelSumTab8 ( void );
+
+PIX * pixDeserializeFromMemory ( const l_uint32 *data, size_t nbytes );
+l_int32 pixSerializeToMemory ( PIX *pixs, l_uint32 **pdata, size_t *pnbytes );
+
+PIX * pixConvertRGBToLuminance(PIX *pixs);
+
+PIX * pixRemoveColormap(PIX *pixs, l_int32  type);
+
+l_int32
+pixOtsuAdaptiveThreshold(PIX       *pixs,
+                         l_int32    sx,
+                         l_int32    sy,
+                         l_int32    smoothx,
+                         l_int32    smoothy,
+                         l_float32  scorefract,
+                         PIX      **ppixth,
+                         PIX      **ppixd);
+
+PIX *
+pixOtsuThreshOnBackgroundNorm(PIX       *pixs,
+                              PIX       *pixim,
+                              l_int32    sx,
+                              l_int32    sy,
+                              l_int32    thresh,
+                              l_int32    mincount,
+                              l_int32    bgval,
+                              l_int32    smoothx,
+                              l_int32    smoothy,
+                              l_float32  scorefract,
+                              l_int32   *pthresh);
+
+PIX *
+pixCleanBackgroundToWhite(PIX       *pixs,
+                          PIX       *pixim,
+                          PIX       *pixg,
+                          l_float32  gamma,
+                          l_int32    blackval,
+                          l_int32    whiteval);
+
+BOX *
+pixFindPageForeground(PIX         *pixs,
+                      l_int32      threshold,
+                      l_int32      mindist,
+                      l_int32      erasedist,
+                      l_int32      pagenum,
+                      l_int32      showmorph,
+                      l_int32      display,
+                      const char  *pdfdir);
+
+PIX *
+pixClipRectangle(PIX   *pixs,
+                 BOX   *box,
+                 BOX  **pboxc);
+
+PIX *
+pixBackgroundNorm(PIX     *pixs,
+                  PIX     *pixim,
+                  PIX     *pixg,
+                  l_int32  sx,
+                  l_int32  sy,
+                  l_int32  thresh,
+                  l_int32  mincount,
+                  l_int32  bgval,
+                  l_int32  smoothx,
+                  l_int32  smoothy);
+
+PIX *
+pixGammaTRC(PIX       *pixd,
+            PIX       *pixs,
+            l_float32  gamma,
+            l_int32    minval,
+            l_int32    maxval);
+
+
+l_int32
+pixNumSignificantGrayColors(PIX       *pixs,
+                            l_int32    darkthresh,
+                            l_int32    lightthresh,
+                            l_float32  minfract,
+                            l_int32    factor,
+                            l_int32   *pncolors);
+
+l_int32
+pixColorFraction(PIX        *pixs,
+                 l_int32     darkthresh,
+                 l_int32     lightthresh,
+                 l_int32     diffthresh,
+                 l_int32     factor,
+                 l_float32  *ppixfract,
+                 l_float32  *pcolorfract);
+
+PIX *
+pixColorMagnitude(PIX     *pixs,
+                  l_int32  rwhite,
+                  l_int32  gwhite,
+                  l_int32  bwhite,
+                  l_int32  type);
+
+void
+boxDestroy(BOX  **pbox);
+
+void lept_free(void *ptr);
+""")
+
+
+if __name__ == '__main__':
+    ffi.compile()

ocrmypdf/main.py

@@ -0,0 +1,7 @@
+#!/usr/bin/env python3
+# © 2015-16 James R. Barlow: github.com/jbarlow83
+
+# This file is now an alias for __main__
+# Consider removing in future releases
+
+from ocrmypdf.__main__ import *

ocrmypdf/pageinfo.py

@@ -0,0 +1,445 @@
+#!/usr/bin/env python3
+# © 2015 James R. Barlow: github.com/jbarlow83
+
+from subprocess import Popen, PIPE
+from decimal import Decimal
+from math import hypot
+import re
+import sys
+import PyPDF2 as pypdf
+from collections import namedtuple
+
+try:
+    from math import isclose
+except ImportError:
+    def isclose(a, b, rel_tol=1e-9):
+        "Python 3.4 does not have math.isclose()"
+        diff = abs(b - a)
+        return diff <= abs(rel_tol * b) or diff <= abs(rel_tol * a)
+
+matrix_mult = pypdf.pdf.utils.matrixMultiply
+
+FRIENDLY_COLORSPACE = {
+    '/DeviceGray': 'gray',
+    '/CalGray': 'gray',
+    '/DeviceRGB': 'rgb',
+    '/CalRGB': 'rgb',
+    '/DeviceCMYK': 'cmyk',
+    '/Lab': 'lab',
+    '/ICCBased': 'icc',
+    '/Indexed': 'index',
+    '/Separation': 'sep',
+    '/DeviceN': 'devn',
+    '/Pattern': '-',
+    '/G': 'gray',  # Abbreviations permitted in inline images
+    '/RGB': 'rgb',
+    '/CMYK': 'cmyk',
+    '/I': 'index',
+}
+
+FRIENDLY_ENCODING = {
+    '/CCITTFaxDecode': 'ccitt',
+    '/DCTDecode': 'jpeg',
+    '/JPXDecode': 'jpx',
+    '/JBIG2Decode': 'jbig2',
+    '/CCF': 'ccitt',  # Abbreviations permitted in inline images
+    '/DCT': 'jpeg',
+    '/AHx': 'asciihex',
+    '/A85': 'ascii85',
+    '/LZW': 'lzw',
+    '/Fl': 'flate',
+    '/RL': 'runlength'
+}
+
+FRIENDLY_COMP = {
+    'gray': 1,
+    'rgb': 3,
+    'cmyk': 4,
+    'lab': 3,
+    'index': 1
+}
+
+
+UNIT_SQUARE = (1.0, 0.0, 0.0, 1.0, 0.0, 0.0)
+
+
+def _matrix_from_shorthand(shorthand):
+    """Convert from PDF matrix shorthand to full matrix
+
+    PDF 1.7 spec defines a shorthand for describing the entries of a matrix
+    since the last column is always (0, 0, 1).
+    """
+
+    a, b, c, d, e, f = map(float, shorthand)
+    return ((a, b, 0),
+            (c, d, 0),
+            (e, f, 1))
+
+
+def _shorthand_from_matrix(matrix):
+    """Convert from transformation matrix to PDF shorthand."""
+    a, b = matrix[0][0], matrix[0][1]
+    c, d = matrix[1][0], matrix[1][1]
+    e, f = matrix[2][0], matrix[2][1]
+    return tuple(map(float, (a, b, c, d, e, f)))
+
+
+def _is_unit_square(shorthand):
+    values = map(float, shorthand)
+    pairwise = zip(values, UNIT_SQUARE)
+    return all([isclose(a, b, rel_tol=1e-3) for a, b in pairwise])
+
+RasterSettings = namedtuple('RasterSettings',
+    ['name', 'shorthand', 'stack_depth'])
+
+InlineSettings = namedtuple('InlineSettings',
+    ['settings', 'shorthand', 'stack_depth'])
+
+ContentsInfo = namedtuple('ContentsInfo', ['raster_settings', 'inline_images'])
+
+
+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):
+    """Interpret the PDF content stream
+
+    The stack represents the state of the PDF graphics stack.  We are only
+    interested in the current transformation matrix (CTM) so we only track
+    this object; a full implementation would need to track many other items.
+
+    The CTM is initialized to the mapping from user space to device space.
+    PDF units are 1/72".  In a PDF viewer or printer this matrix is initialized
+    to the transformation to device space.  For example if set to
+    (1/72, 0, 0, 1/72, 0, 0) then all units would be calculated in inches.
+
+    Images are always considered to be (0, 0) -> (1, 1).  Before drawing an
+    image there should be a 'cm' that sets up an image coordinate system
+    where drawing from (0, 0) -> (1, 1) will draw on the desired area of the
+    page.
+
+    PDF units suit our needs so we initialize ctm to the identity matrix.
+
+    PyPDF2 replaces inline images with a fake "INLINE IMAGE" operator.
+
+    """
+
+    operations = contentstream.operations
+    stack = []
+    ctm = _matrix_from_shorthand(UNIT_SQUARE)
+    image_raster_settings = []
+    inline_images = []
+
+    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, command %i" % n)
+        elif command == b'Q':
+            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(
+                name=image_name, shorthand=_shorthand_from_matrix(ctm),
+                stack_depth=len(stack))
+            image_raster_settings.append(raster)
+        elif command == b'INLINE IMAGE':
+            settings = operands['settings']
+            inline = InlineSettings(
+                settings=settings, shorthand=_shorthand_from_matrix(ctm),
+                stack_depth=len(stack))
+            inline_images.append(inline)
+
+    return ContentsInfo(
+        raster_settings=image_raster_settings,
+        inline_images=inline_images)
+
+
+def _get_dpi(ctm_shorthand, image_size):
+    """Given the transformation matrix and image size, find the image DPI.
+
+    PDFs do not include image resolution information within image data.
+    Instead, the PDF page content stream describes the location where the
+    image will be rasterized, and the effective resolution is the ratio of the
+    pixel size to raster target size.
+
+    Normally a scanned PDF has the paper size set appropriately but this is
+    not guaranteed. The most common case is a cropped image will change the
+    page size (/CropBox) without altering the page content stream. That means
+    it is not sufficient to assume that the image fills the page, even though
+    that is the most common case.
+
+    A PDF image may be scaled (always), cropped, translated, rotated in place
+    to an arbitrary angle (rarely) and skewed. Only equal area mappings can
+    be expressed, that is, it is not necessary to consider distortions where
+    the effective DPI varies with position.
+
+    To determine the image scale, transform an offset axis vector v0 (0, 0),
+    width-axis vector v0 (1, 0), height-axis vector vh (0, 1) with the matrix,
+    which gives the dimensions of the image in PDF units. From there we can
+    compare to actual image dimensions. PDF uses
+    row vector * matrix_tranposed unlike the traditional
+    matrix * column vector.
+
+    The offset, width and height vectors can be combined in a matrix and
+    multiplied by the transform matrix. Then we want to calculated
+        magnitude(width_vector - offset_vector)
+    and
+        magnitude(height_vector - offset_vector)
+
+    When the above is worked out algebraically, the effect of translation
+    cancels out, and the vector magnitudes become functions of the nonzero
+    transformation matrix indices. The results of the derivation are used
+    in this code.
+
+    pdfimages -list does calculate the DPI in some way that is not completely
+    naive, but it does not get the DPI of rotated images right, so cannot be
+    used anymore to validate this. Photoshop works, or using Acrobat to
+    rotate the image back to normal.
+
+    It does not matter if the image is partially cropped, or even out of the
+    /MediaBox.
+
+    """
+
+    a, b, c, d, _, _ = ctm_shorthand
+
+    # Calculate the width and height of the image in PDF units
+    image_drawn_width = hypot(a, b)
+    image_drawn_height = hypot(c, d)
+
+    # The scale of the image is pixels per PDF unit (1/72")
+    scale_w = image_size[0] / image_drawn_width
+    scale_h = image_size[1] / image_drawn_height
+
+    # DPI = scale * 72
+    dpi_w = scale_w * 72.0
+    dpi_h = scale_h * 72.0
+
+    return (dpi_w, dpi_h)
+
+
+def _find_page_inline_images(page, pageinfo, contentsinfo):
+    "Find inline images on the page"
+
+    for n, inline in enumerate(contentsinfo.inline_images):
+        image = {}
+        image['name'] = str('inline-%02d' % n)
+        image['width'] = inline.settings['/W']
+        image['height'] = inline.settings['/H']
+        if '/BPC' in inline.settings:
+            image['bpc'] = inline.settings['/BPC']
+        else:
+            image['bpc'] = 8
+        if '/CS' in inline.settings:
+            image['color'] = FRIENDLY_COLORSPACE.get(inline.settings['/CS'], '-')
+        else:
+            image['color'] = '-'
+        image['comp'] = FRIENDLY_COMP.get(image['color'], '?')
+        if '/F' in inline.settings:
+            filter_ = inline.settings['/F']
+            if isinstance(filter_, pypdf.generic.ArrayObject):
+                filter_ = filter_[0]
+            image['enc'] = FRIENDLY_ENCODING.get(filter_, 'image')
+        else:
+            image['enc'] = 'image'
+
+        dpi_w, dpi_h = _get_dpi(
+            inline.shorthand, (image['width'], image['height']))
+        image['dpi_w'], image['dpi_h'] = Decimal(dpi_w), Decimal(dpi_h)
+        yield image
+
+
+def _find_page_regular_images(page, pageinfo, contentsinfo):
+    "Find images stored in XObject resources"
+
+    try:
+        page['/Resources']['/XObject']
+    except KeyError:
+        return
+    for xobj in page['/Resources']['/XObject']:
+        # PyPDF2 returns the keys as an iterator
+        pdfimage = page['/Resources']['/XObject'][xobj]
+        if pdfimage['/Subtype'] != '/Image':
+            continue
+        image = {}
+        image['name'] = str(xobj)
+        image['width'] = pdfimage['/Width']
+        image['height'] = pdfimage['/Height']
+        if '/BitsPerComponent' in pdfimage:
+            image['bpc'] = pdfimage['/BitsPerComponent']
+        else:
+            image['bpc'] = 8
+
+        # Fixme: this is incorrectly treats explicit masks as stencil masks,
+        # but good enough for now. Explicit masks have /ImageMask true but are
+        # never called for in content stream, instead are drawn as a /Mask on
+        # other images. For our purposes finding out the details of /Mask
+        # will seldom matter.
+        if '/ImageMask' in pdfimage:
+            image['type'] = 'stencil' if pdfimage['/ImageMask'].value \
+                            else 'image'
+        else:
+            image['type'] = 'image'
+        if '/Filter' in pdfimage:
+            filter_ = pdfimage['/Filter']
+            if isinstance(filter_, pypdf.generic.ArrayObject):
+                filter_ = filter_[0]
+            image['enc'] = FRIENDLY_ENCODING.get(filter_, 'image')
+        else:
+            image['enc'] = 'image'
+        if '/ColorSpace' in pdfimage:
+            cs = pdfimage['/ColorSpace']
+            if isinstance(cs, pypdf.generic.ArrayObject):
+                cs = cs[0]
+            image['color'] = FRIENDLY_COLORSPACE.get(cs, '-')
+        else:
+            image['color'] = 'jpx' if image['enc'] == 'jpx' else '?'
+
+        image['comp'] = FRIENDLY_COMP.get(image['color'], '?')
+
+        # Bit of a hack... infer grayscale if component count is uncertain
+        # but encoding must be monochrome. This happens if a monochrome image
+        # has an ICC profile attached. Better solution would be to examine
+        # the ICC profile.
+        if image['comp'] == '?' and image['enc'] in ('ccitt', 'jbig2'):
+            image['comp'] = FRIENDLY_COMP['gray']
+
+        image['dpi_w'] = image['dpi_h'] = 0
+
+        for raster in contentsinfo.raster_settings:
+            # Loop in case the same image is display multiple times on a page
+            if raster.name != image['name']:
+                continue
+
+            if raster.stack_depth == 0 and _is_unit_square(raster.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",
+                # or 0.35 mm).  The equivalent DPI will be >100,000.  Exclude
+                # these from our DPI calculation for the page.
+                continue
+
+            dpi_w, dpi_h = _get_dpi(
+                raster.shorthand, (image['width'], image['height']))
+
+            # When image is used multiple times take the highest DPI it is
+            # rendered at
+            image['dpi_w'] = max(dpi_w, image.get('dpi_w', 0))
+            image['dpi_h'] = max(dpi_h, image.get('dpi_h', 0))
+
+        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)
+        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 _page_has_text(pdf, page):
+    # Simple test
+    text = page.extractText()
+    if text.strip() != '':
+        return True
+
+    # More nuanced test to deal with quirks of Tesseract PDF generation
+    # Check if there's a Glyphless font
+    try:
+        font = page['/Resources']['/Font']
+    except KeyError:
+        pass
+    else:
+        font_objects = list(font.keys())
+        for font_object in font_objects:
+            basefont = font[font_object]['/BaseFont']
+            if basefont.endswith('GlyphLessFont'):
+                return True
+
+    return False
+
+
+def _pdf_get_pageinfo(infile, pageno: int):
+    pageinfo = {}
+    pageinfo['pageno'] = pageno
+    pageinfo['images'] = []
+
+    pdf = pypdf.PdfFileReader(infile)
+    page = pdf.pages[pageno]
+
+    pageinfo['has_text'] = _page_has_text(pdf, page)
+
+    width_pt = page.mediaBox.getWidth()
+    height_pt = page.mediaBox.getHeight()
+    pageinfo['width_inches'] = width_pt / Decimal(72.0)
+    pageinfo['height_inches'] = height_pt / Decimal(72.0)
+
+    try:
+        pageinfo['rotate'] = int(page['/Rotate'])
+    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)]
+
+    if pageinfo['images']:
+        xres = max(image['dpi_w'] for image in pageinfo['images'])
+        yres = max(image['dpi_h'] for image in pageinfo['images'])
+        pageinfo['xres'], pageinfo['yres'] = xres, yres
+        pageinfo['width_pixels'] = \
+            int(round(xres * pageinfo['width_inches']))
+        pageinfo['height_pixels'] = \
+            int(round(yres * pageinfo['height_inches']))
+
+    return pageinfo
+
+
+def pdf_get_all_pageinfo(infile):
+    pdf = pypdf.PdfFileReader(infile)
+    return [_pdf_get_pageinfo(infile, n) for n in range(pdf.numPages)]
+
+
+def main():
+    import argparse
+    parser = argparse.ArgumentParser()
+    parser.add_argument('infile')
+    args = parser.parse_args()
+    info = pdf_get_all_pageinfo(args.infile)
+    from pprint import pprint
+    pprint(info)
+
+
+if __name__ == '__main__':
+    main()

ocrmypdf/pdfa.py

@@ -0,0 +1,157 @@
+#!/usr/bin/env python3
+# © 2015 James R. Barlow: github.com/jbarlow83
+#
+# Generate a PDFA_def.ps file for Ghostscript >= 9.14
+
+from string import Template
+import codecs
+import pkg_resources
+import PyPDF2 as pypdf
+
+ICC_PROFILE_RELPATH = 'data/sRGB.icc'
+
+SRGB_ICC_PROFILE = pkg_resources.resource_filename(
+    'ocrmypdf', ICC_PROFILE_RELPATH)
+
+
+# This is a template written in PostScript which is needed to create PDF/A
+# files, from the Ghostscript documentation. Lines beginning with % are
+# comments. Python substitution variables have a '$' prefix.
+pdfa_def_template = u"""%!
+% This is derived from Ghostscript's template for creating a PDF/A document.
+% This is a small PostScript program that includes some necessary information
+% to create a PDF/A compliant file.
+
+% Define entries in the document Info dictionary :
+/ICCProfile ($icc_profile)
+def
+
+[ /Title <$title>
+  /Author <$author>
+  /Subject <$subject>
+  /Keywords <$keywords>
+  /Creator <$creator>
+  /DOCINFO pdfmark
+
+% Define an ICC profile :
+
+[/_objdef {icc_PDFA} /type /stream /OBJ pdfmark
+[{icc_PDFA}
+<<
+  /N currentpagedevice /ProcessColorModel known {
+    currentpagedevice /ProcessColorModel get dup /DeviceGray eq
+    {pop 1} {
+      /DeviceRGB eq
+      {3}{4} ifelse
+    } ifelse
+  } {
+    (ERROR, unable to determine ProcessColorModel) == flush
+  } ifelse
+>> /PUT pdfmark
+[{icc_PDFA} ICCProfile (r) file /PUT pdfmark
+
+% Define the output intent dictionary :
+
+[/_objdef {OutputIntent_PDFA} /type /dict /OBJ pdfmark
+[{OutputIntent_PDFA} <<
+  /Type /OutputIntent             % Must be so (the standard requires).
+  /S /GTS_PDFA1                   % Must be so (the standard requires).
+  /DestOutputProfile {icc_PDFA}            % Must be so (see above).
+  /OutputConditionIdentifier ($icc_identifier)
+>> /PUT pdfmark
+[{Catalog} <</OutputIntents [ {OutputIntent_PDFA} ]>> /PUT pdfmark
+"""
+
+
+def encode_text_string(s: str) -> str:
+    '''Encode text string to hex string for use in a PDF
+
+    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 could be encoded as PdfDocEncoding literals provided
+    that certain Postscript sequences are escaped.  But it's far simpler to
+    encode everything as UTF-16.
+    '''
+
+    # Sometimes lazy C programmers leave their NULs at the end of strings they
+    # insert into PDFs
+    # tests/resources/aspect.pdf is one example (created by ImageMagick)
+    s = s.replace('\x00', '')
+
+    if s == '':
+        return ''
+
+    utf16_bytes = s.encode('utf-16be')
+    ascii_hex_bytes = codecs.encode(b'\xfe\xff' + utf16_bytes, 'hex')
+    ascii_hex_str = ascii_hex_bytes.decode('ascii').lower()
+    return ascii_hex_str
+
+
+def _get_pdfa_def(icc_profile, icc_identifier, pdfmark):
+    pdfmark_utf16 = {k: encode_text_string(v) for k, v in pdfmark.items()}
+
+    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', ''))
+    return result
+
+
+def generate_pdfa_def(target_filename, pdfmark, icc='sRGB'):
+    if icc == 'sRGB':
+        icc_profile = SRGB_ICC_PROFILE
+    else:
+        raise NotImplementedError("Only supporting sRGB")
+
+    ps = _get_pdfa_def(icc_profile, icc, pdfmark)
+
+    # We should have encoded everything to pure ASCII by this point, and
+    # to be safe, only allow ASCII in PostScript
+    with open(target_filename, 'w', encoding='ascii') as f:
+        f.write(ps)
+
+
+def file_claims_pdfa(filename):
+    """Determines if the file claims to be PDF/A compliant
+
+    Checking if a file is a truly compliant PDF/A is a massive undertaking
+    that no open source tool does properly.  Some commercial tools are
+    generally reliable (Acrobat).
+
+    This checks if the XMP metadata contains a PDF/A marker.
+    """
+
+    pdf = pypdf.PdfFileReader(filename)
+    xmp = pdf.getXmpMetadata()
+
+    try:
+        pdfa_nodes = xmp.getNodesInNamespace(
+            aboutUri='',
+            namespace='http://www.aiim.org/pdfa/ns/id/')
+    except AttributeError:
+        return {'pass': False, 'output': 'pdf',
+                'conformance': 'No XMP metadata'}
+
+    pdfa_dict = {attr.localName: attr.value for attr in pdfa_nodes}
+    if not pdfa_dict:
+        return {'pass': False, 'output': 'pdf',
+                'conformance': 'No XMP metadata'}
+
+    part_conformance = pdfa_dict['part'] + pdfa_dict['conformance']
+    valid_part_conforms = {'1A', '1B', '2A', '2B', '2U', '3A', '3B', '3U'}
+
+    conformance = 'PDF/A-{}'.format(
+        part_conformance)
+
+    if part_conformance in valid_part_conforms:
+        pdfa_dict['pass'] = True
+        pdfa_dict['output'] = 'pdfa'
+    pdfa_dict['conformance'] = conformance
+
+    return pdfa_dict
+

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>

requirements.txt

@@ -0,0 +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 == 3.4.2
+reportlab == 3.3.0
+PyPDF2 == 1.26
+img2pdf == 0.2.1
+cffi == 1.9.1

setup.cfg

@@ -0,0 +1,13 @@
+[bdist_wheel]
+python-tag = py34
+
+[aliases]
+test=pytest
+
+[check-manifest]
+ignore =
+	.github
+
+[tool:pytest]
+norecursedirs = lib .pc .git output cache resources
+testpaths = tests

setup.py

@@ -0,0 +1,242 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+# © 2015 James R. Barlow: github.com/jbarlow83
+
+from __future__ import print_function, unicode_literals
+
+import sys
+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 subprocess import STDOUT, check_output, CalledProcessError  # nopep8
+from collections.abc import Mapping  # nopep8
+import re  # nopep8
+
+
+missing_program = '''
+The program '{program}' could not be executed or was not found on your
+system PATH.
+'''
+
+unknown_version = '''
+OCRmyPDF requires '{program}' {need_version} or higher.  Your system has
+'{program}' but we cannot tell what version is installed.  Contact the
+package maintainer.
+'''
+
+old_version = '''
+OCRmyPDF requires '{program}' {need_version} or higher.  Your system appears
+to have {found_version}.  Please update this program.
+'''
+
+okay_its_optional = '''
+This program is OPTIONAL, so installation of OCRmyPDF can proceed, but
+some functionality may be missing.
+'''
+
+not_okay_its_required = '''
+This program is REQUIRED for OCRmyPDF to work.  Installation will abort.
+'''
+
+osx_install_advice = '''
+If you have homebrew installed, try these command to install the missing
+packages:
+    brew update
+    brew upgrade
+    brew install {package}
+'''
+
+linux_install_advice = '''
+On systems with the aptitude package manager (Debian, Ubuntu), try these
+commands:
+    sudo apt-get update
+    sudo apt-get install {package}
+
+On RPM-based systems (Red Hat, Fedora), search for instructions on
+installing the RPM for {program}.
+'''
+
+
+def get_platform():
+    if sys.platform.startswith('freebsd'):
+        return 'freebsd'
+    elif sys.platform.startswith('linux'):
+        return 'linux'
+    return sys.platform
+
+
+def _error_trailer(program, package, optional, **kwargs):
+    if optional:
+        print(okay_its_optional.format(**locals()), file=sys.stderr)
+    else:
+        print(not_okay_its_required.format(**locals()), file=sys.stderr)
+
+    if isinstance(package, Mapping):
+        package = package[get_platform()]
+
+    if get_platform() == 'darwin':
+        print(osx_install_advice.format(**locals()), file=sys.stderr)
+    elif get_platform() == 'linux':
+        print(linux_install_advice.format(**locals()), file=sys.stderr)
+
+
+def error_missing_program(
+        program,
+        package,
+        optional
+        ):
+    print(missing_program.format(**locals()), file=sys.stderr)
+    _error_trailer(**locals())
+
+
+def error_unknown_version(
+        program,
+        package,
+        optional,
+        need_version
+        ):
+    print(unknown_version.format(**locals()), file=sys.stderr)
+    _error_trailer(**locals())
+
+
+def error_old_version(
+        program,
+        package,
+        optional,
+        need_version,
+        found_version
+        ):
+    print(old_version.format(**locals()), file=sys.stderr)
+    _error_trailer(**locals())
+
+
+def check_external_program(
+        program,
+        need_version,
+        package,
+        version_check_args=['--version'],
+        version_scrape_regex=re.compile(r'(\d+\.\d+(?:\.\d+)?)'),
+        optional=False):
+
+    print('Checking for {program} >= {need_version}...'.format(
+            program=program, need_version=need_version))
+    try:
+        result = check_output(
+                [program] + version_check_args,
+                universal_newlines=True, stderr=STDOUT)
+    except (CalledProcessError, FileNotFoundError):
+        error_missing_program(program, package, optional)
+        if not optional:
+            sys.exit(1)
+        print('Continuing install without {program}'.format(program=program))
+        return
+
+    try:
+        found_version = version_scrape_regex.search(result).group(1)
+    except AttributeError:
+        error_unknown_version(program, package, optional, need_version)
+        sys.exit(1)
+
+    if found_version < need_version:
+        error_old_version(program, package, optional, need_version,
+                          found_version)
+
+    print('Found {program} {found_version}'.format(
+            program=program, found_version=found_version))
+
+
+command = next((arg for arg in sys.argv[1:] if not arg.startswith('-')), '')
+forced = ('--force' in sys.argv)
+
+
+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 14.04 backports
+        package={'darwin': 'tesseract', 'linux': 'tesseract-ocr'}
+    )
+    check_external_program(
+        program='gs',
+        need_version='9.15',  # limited by Travis CI / Ubuntu 14.04 backports
+        package='ghostscript'
+    )
+    check_external_program(
+        program='unpaper',
+        need_version='6.1',   # latest sane version
+        package='unpaper',
+        optional=True
+    )
+    check_external_program(
+        program='qpdf',
+        need_version='5.1.1',   # limited by Travis CI / Ubuntu 14.04 backports
+        package='qpdf',
+        version_check_args=['--version']
+    )
+else:
+    print('Skipping external program tests because of --force')
+
+
+if 'upload' in sys.argv[1:]:
+    print('Use twine to upload the package - setup.py upload is insecure')
+    sys.exit(1)
+
+tests_require = open('test_requirements.txt').read().splitlines()
+
+setup(
+    name='ocrmypdf',
+    description='OCRmyPDF adds an OCR text layer to scanned PDF files, allowing them to be searched',
+    url='https://github.com/jbarlow83/OCRmyPDF',
+    author='James R. Barlow',
+    author_email='jim@purplerock.ca',
+    license='MIT',
+    packages=['ocrmypdf', 'ocrmypdf.exec'],
+    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",
+        "Intended Audience :: Science/Research",
+        "Intended Audience :: System Administrators",
+        "License :: OSI Approved :: MIT License",
+        "Operating System :: MacOS :: MacOS X",
+        "Operating System :: POSIX",
+        "Operating System :: POSIX :: BSD",
+        "Operating System :: POSIX :: Linux",
+        "Topic :: Scientific/Engineering :: Image Recognition",
+        "Topic :: Text Processing :: Indexing",
+        "Topic :: Text Processing :: Linguistic",
+        ],
+    setup_requires=[
+        'setuptools_scm',
+        'cffi>=1.5.0',
+        'pytest-runner',
+        'pytest-helpers-namespace'
+    ],
+    use_scm_version={'version_scheme': 'post-release'},
+    cffi_modules=[
+        'ocrmypdf/lib/compile_leptonica.py:ffi'
+    ],
+    install_requires=[
+        'ruffus==2.6.3',        # pinned - ocrmypdf implements a 2.6.3 workaround
+        'Pillow>=3.1.1',        # Pillow is pretty stable
+        'reportlab>=3.2.0',     # oldest released version with sane image handling
+        'PyPDF2>=1.26',         # pure Python, so track HEAD closely
+        'img2pdf>=0.2.1',       # pure Python, so track HEAD closely
+        'cffi>=1.5.0'           # oldest version ever tested
+    ],
+    tests_require=tests_require,
+    entry_points={
+        'console_scripts': [
+            'ocrmypdf = ocrmypdf.__main__:run_pipeline'
+        ],
+    },
+    package_data={'ocrmypdf': ['data/sRGB.icc']},
+    include_package_data=True,
+    zip_safe=False)

share/etc-apt-sources.list

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

test/test-appimage.sh

@@ -1,53 +0,0 @@
-#! /bin/bash
-
-set -x
-set -e
-
-chmod +x OCRmyPDF*.AppImage
-
-# run OCRmyPDF to test if the AppImage can ocr a test file
-run_appimage()
-{
-    echo ""
-    ./OCRmyPDF*.AppImage --help
-    echo ""
-    ./OCRmyPDF*.AppImage --list-programs
-    echo ""
-    ./OCRmyPDF*.AppImage --list-licenses
-    echo ""
-    ./OCRmyPDF*.AppImage ocrmypdf -l deu -s -d --jbig2-lossy --optimize 1 "$TRAVIS_BUILD_DIR"/test/test.pdf output.pdf
-    echo ""
-}
-
-
-# check AppImage for common issues
-run_appimagelint()
-{
-    wget https://github.com/TheAssassin/appimagelint/releases/download/continuous/appimagelint-x86_64.AppImage
-    chmod +x appimagelint-x86_64.AppImage
-    ./appimagelint-x86_64.AppImage OCRmyPDF*.AppImage
-}
-
-
-# extract the OCRmyPDF AppImage, install pytest & test requirements and run pytest
-run_pytest()
-{
-    git clone --depth=1 --branch "v$OCRMYPDF_VERSION" https://github.com/jbarlow83/OCRmyPDF.git
-    ./OCRmyPDF*.AppImage --appimage-extract
-
-    pushd squashfs-root
-    ./AppRun python3 -m pip install pytest
-    ./AppRun python3 -m pip install -r ../OCRmyPDF/requirements/test.txt
-    ./AppRun python3 -m pytest ../OCRmyPDF -n auto
-    popd
-}
-
-
-run_appimage
-
-run_appimagelint
-
-# run_pytest
-
-
-

test_requirements.txt

@@ -0,0 +1,2 @@
+pytest >= 2.8
+pytest-helpers-namespace

tests/conftest.py

@@ -0,0 +1,116 @@
+#!/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 running_in_docker():
+    # Docker creates a file named /.dockerinit
+    return os.path.exists('/.dockerinit')
+
+
+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
+    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

tests/resources/README.rst

@@ -0,0 +1,115 @@
+These test files are used in OCRmyPDF's test suite. They do not necessarily produce OCR results
+at all and are not meant as examples of OCR output. Some are even invalid PDFs that might
+crash certain PDF viewers.
+
+
+Files derived from free sources
+===============================
+
+These test resources come from free sources, under either public domain or Creative Commons licenses.
+In some cases they were converted from one image format to another without other changes.
+
+.. list-table:: 
+    :widths: 20 50 30
+    :header-rows: 1
+
+    *   - File
+        - Source
+        - License
+    *   - c02-22.pdf
+        - `Project Gutenberg`_, Adventures of Huckleberry Finn, page 22
+        - Public Domain
+    *   - congress.jpg
+        - `US Congressional Records`_
+        - Public Domain
+    *   - graph.pdf
+        - `Wikimedia: Pandas text analysis.png`_
+        - Public Domain
+    *   - lichtenstein.pdf
+        - `Wikimedia: JPEG2000 Lichtenstein`_
+        - Creative Commons BY-SA 3.0
+    *   - LinnSequencer.jpg, linn.pdf, linn.txt
+        - `Wikimedia: LinnSequencer`_
+        - Creative Commons BY-SA 3.0
+    *   - typewriter.png, 2400dpi.pdf
+        - `Wikimedia: Triumph typewrtier text Linzensoep`_
+        * Creative Commons BY-SA 2.5
+
+
+Files generated for this project
+================================
+
+The following test resources were crafted specifically for this project, and can be used
+under the terms of the license in LICENSE.rst.
+
+.. list-table:: 
+    :widths: 20 20 60
+    :header-rows: 1
+
+    *   - File
+        - Contributor
+        - Purpose
+    *   - aspect.pdf
+        - @jbarlow83
+        - test image with 200 x 100 DPI resolution
+    *   - blank.pdf
+        - @jbarlow83
+        - blank PDF
+    *   - cmyk.pdf
+        - @jbarlow83
+        - a CMYK image created in Photoshop
+    *   - enormous.pdf
+        - @jbarlow83
+        - very large PDF page
+    *   - epson.pdf
+        - @lowesjam
+        - a linearized PDF containing some unusual indirect objects, created by an Epson printer; printout of a Wikipedia article (CC BY-SA)
+    *   - francais.pdf
+        - @jbarlow83
+        - a page containing French accents (diacritics)  
+    *   - hugemono.pdf
+        - @jbarlow83
+        - large monochrome 35000x35000 image in JBIG2 encoding 
+    *   - invalid.pdf
+        - @jbarlow83
+        - a PDF file header followed by EOF marker
+    *   - masks.pdf
+        - @supergrobi
+        - file containing explicit masks and a stencil mask drawn without a proper transformation matrix; printout of a German Wikipedia article (CC BY-SA)
+    *   - missing_docinfo.pdf
+        - @jbarlow83
+        - PDF file with no /DocumentInfo section 
+    *   - overlay.pdf
+        - @maxandersen
+        - PDF file generated by PDFPen pro that triggered content stream parse errors
+
+Assemblies
+==========
+
+These test resources are assemblies from other previously mentioned files, released under the same license terms as their input files.
+
+- cardinal.pdf (four cardinal directions, baked-in rotated copies of LinnSequencer.jpg)
+- ccitt.pdf (LinnSequencer.jpg, converted to CCITT encoding)
+- encrypted_algo4.pdf (congress.jpg, encrypted with algorithm 4 - not supported by PyPDF2)
+- graph_ocred.pdf (from graph.pdf)
+- jbig2.pdf (congress.jpg, converted to JBIG2 encoding)
+- multipage.pdf (from several other files)
+- palette.pdf (congress.jpg, converted to a 256-color palette)
+- rotated_skew.pdf (a /Rotate'd and skewed document from LinnSequencer.jpg)
+- skew.pdf (from LinnSequencer.jpg, skew simulated by adjusting the transformation matrix)
+- skew-encrypted.pdf (skew.pdf with encryption - access supported by PyPDF2)
+
+
+.. _`Wikimedia: LinnSequencer`: https://upload.wikimedia.org/wikipedia/en/b/b7/LinnSequencer_hardware_MIDI_sequencer_brochure_page_2_300dpi.jpg
+
+.. _`Project Gutenberg`: https://www.gutenberg.org/files/76/76-h/76-h.htm#c2
+
+.. _`US Congressional Records`: http://www.baxleystamps.com/litho/meiji/courts_1871.jpg
+
+.. _`Wikimedia: Pandas text analysis.png`: https://en.wikipedia.org/wiki/File:Pandas_text_analysis.png
+
+.. _`Wikimedia: JPEG2000 Lichtenstein`: https://en.wikipedia.org/wiki/JPEG_2000#/media/File:Jpeg2000_2-level_wavelet_transform-lichtenstein.png
+
+.. _`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/resources/invalid.pdf

@@ -0,0 +1,3 @@
+%PDF-1.3
+This is not a valid PDF file
+%%EOF

tests/resources/linn.txt

@@ -0,0 +1,123 @@
+The LinnSequencer
+32 Track MIDI Sequence Recorder
+
+The LinnSequencer is a state—of—the-art composition and performance tool for the professional musician. It is
+
+extremely powerful, yet amazingly simple to learn and use. It’s many remarkable features include:
+
+0 Operation is similar to multi-track tape recorder with PLAY, STOP, RECORD, FAST
+FORWARD, REWIND, and LOCATE controls.
+
+0 Each of the 100 sequences contains 32 simultaneous, polyphonic tracks. Each track may
+be assigned to one of 16 MIDI channels. Simultaneously plays up to 16 polyphonic
+
+synthesizers !
+
+0 Ultra-fast 3 1/2 ” disk drive stores complex songs in seconds and holds over 110,000 notes
+
+per disk!
+
+0 One or all tracks may be TRANSPOSED at the touch of a key.
+0 Exclusive real—time ERASE function makes editing FAST.
+0 Exclusive REPEAT function automatically repeats any held notes at a pre-selected
+
+rhythmic value.
+
+0 TIMING CORRECTION works during playback and operates without ‘chopping’ notes.
+
+0 Optional SMPTE time code synchronization.
+
+0 Optional remote control.
+
+Recording a Sequence
+
+To record a sequence, simply press RECORD and PLAY,
+then play your MIDI keyboard in time to the Sequencer’s
+click track. When the sequence loops back around to bar 1,
+you’ll hear what you played—only all timing errors will be
+
+corrected! (Timing correction may be adjusted 0r defeated).
+
+Any additional notes played will be added into the track
+—existing notes are not erased while recording!
+
+FAST FORWARD, REWIND, and LOCATE controls
+may be used at any time to quickly access any location in
+your sequence for spot-recording. To overdub a new part,
+select a different track and start recording—while you
+record, the first‘track will play in perfect sync (unless you
+MUTE it, or SOLO another track). In this way, up to 32
+tracks may be overdubbed! All MIDI effects are recorded
+including pitch bend, modulation, velocity, aftertouch,
+sustain pedal, and program changes!
+
+Editing
+
+To erase a wrong note, simply hold ERASE and press
+the note to be erased just before it plays in the sequence-—
+when played back, it will be gone. Notes may also be
+
+added, erased, or changed using the SINGLE STEP func-
+tion. To overdub notes at specific points within a sequence,
+
+Additional Features
+
+simply use LOCATE, FAST FORWARD, or REWIND to
+find the desired bar number, then start recording.
+
+The INSERT/ COPY function allows you to move bars
+from one location to another—in the same sequence or a
+different one. For example, you might insert a copy of the
+first verse between the second chorus and the bridge.
+DELETE BARS operates the same way to remove
+unwanted sections.
+
+Creating a Song
+
+One way to create a song is to record each track all the
+way through (up to 999 bars). Another way is to record
+each basic section (verse, chorus, etc.) in individual
+sequences, then use the CREATE SONG function to “chain”
+them together. CREATE SONG will then automatically
+copy all the parts into a new sequence. If desired, you can
+even set the last few bars to repeat infinitely, for a fadeout.
+
+Composition Without Compromise
+
+The technology you use should never be so complex that
+it interferes with the creative process. That’s precisely why
+the LinnSequencer is designed to let you compose, record
+and edit while devoting your undivided attention to your
+music. See your Linn dealer today for a demonstration!
+
+0 Simple, easy to learn operation—the 32 character LCD display clearly guides you through all operations. If needed, the
+
+HELP button displays additional explanations.
+
+0 Non-destructive recording—existing notes are not erased while recording.
+0 Two FOOTSWIT CH INPUTS may be assigned to remotely control many of the commonly used functions, including
+
+ERASE, REPEAT, PLAY/ STOP, or LOCATE.
+
+0 Two TRIGGER OUTPUTS may be programmed to output pulses at any selected note value.
+
+0 Will sync to standard LinnDrum or Linn 9000 sync tone.
+
+0 Utilizes ultra high—speed, 8 MHZ 80186 16 bit computer internally for FAST operation.
+0 TEMPO may be specified in BEATS-PER—MINUTE or FRAMES-PER—BEAT at 24, 25, or 30 frames per second,
+
+(even drop frame!)
+
+0 TEMPO may be entered numerically, adjustable in tenths of a Beat-Per-Minute increments, or by tapping quarter notes
+
+on the TAP TEMPO button.
+
+0 TEMPO CHANGES may be programmed into a sequence, with smooth transitions if desired.
+0 Any TIME SIGNATURE may be used, and may be changed within a song.
+
+EDI]
+Linn Electronics, Inc.
+
+18720 Oxnard Street, Tarzana, CA 91356
+(818) 708-8131 TELEX #298949 LINN UR
+

tests/resources/missing_docinfo.pdf

@@ -0,0 +1,41 @@
+%PDF-1.3
+%¿÷¢þ
+1 0 obj
+<< /Outlines 2 0 R /PageMode /UseNone /Pages 3 0 R /Type /Catalog >>
+endobj
+2 0 obj
+<< /Count 0 /Type /Outlines >>
+endobj
+3 0 obj
+<< /Count 1 /Kids [ 4 0 R ] /Type /Pages >>
+endobj
+4 0 obj
+<< /Contents 5 0 R /MediaBox [ 0 0 595.2756 841.8898 ] /Parent 3 0 R /Resources << /Font 6 0 R /ProcSet [ /PDF /Text /ImageB /ImageC /ImageI ] >> /Rotate 0 /Trans << >> /Type /Page >>
+endobj
+5 0 obj
+<< /Length 104 /Filter /FlateDecode >>
+stream
+xœ-Œ1
+ƒ@{O1e´ˆûEI¢ Xþè⢉»[¨÷Wƒ<˜bž`ÎÉŸÖÃ[ÉA
+Ô!å³D;jMN/w*Æðªêyè4¯¸y™ú•É?Ñî~[\dX¢ý¥èÍ®’™…endstream
+endobj
+6 0 obj
+<< /F1 7 0 R >>
+endobj
+7 0 obj
+<< /BaseFont /Helvetica /Encoding /WinAnsiEncoding /Name /F1 /Subtype /Type1 /Type /Font >>
+endobj
+xref
+0 8
+0000000000 65535 f 
+0000000015 00000 n 
+0000000099 00000 n 
+0000000145 00000 n 
+0000000204 00000 n 
+0000000403 00000 n 
+0000000578 00000 n 
+0000000609 00000 n 
+trailer << /Root 1 0 R /Size 8 /ID [<85bf6c3c41ed927eb43bdfdfff4c0cb5><0304c5f87e589cb7b06f6f52dc6e6707>] >>
+startxref
+716
+%%EOF

tests/spoof/gs_feature_elision.py

@@ -0,0 +1,35 @@
+#!/usr/bin/env python3
+import sys
+import os
+from subprocess import check_call
+
+"""Replicate one type of Ghostscript feature elision warning during
+PDF/A creation."""
+
+
+def real_ghostscript(argv):
+    gs_args = ['gs'] + argv[1:]
+    os.execvp("gs", gs_args)
+    return  # Not reachable
+
+
+elision_warning = """GPL Ghostscript 9.20: Setting Overprint Mode to 1
+not permitted in PDF/A-2, overprint mode not set"""
+
+
+def main():
+    if '--version' in sys.argv:
+        print('9.20')
+        print('SPOOFED: ' + os.path.basename(__filename__))
+        sys.exit(0)
+
+    gs_args = ['gs'] + sys.argv[1:]
+    check_call(gs_args)
+
+    if '-sDEVICE=pdfwrite' in sys.argv[1:]:
+        print(elision_warning)
+
+    sys.exit(0)
+
+if __name__ == '__main__':
+    main()

tests/spoof/gs_pdfa_failure.py

@@ -0,0 +1,42 @@
+#!/usr/bin/env python3
+import sys
+import os
+
+"""Replicate Ghostscript PDF/A conversion failure by suppressing some
+arguments"""
+
+
+def real_ghostscript(argv):
+    gs_args = ['gs'] + argv[1:]
+    os.execvp("gs", gs_args)
+    return  # Not reachable
+
+
+def main():
+    if '--version' in sys.argv:
+        print('9.20')
+        print('SPOOFED: ' + os.path.basename(__filename__))
+        sys.exit(0)
+
+    # Unless some argument is calling for PDFA generation, forward to
+    # real ghostscript
+    if not any(arg.startswith('-dPDFA') for arg in sys.argv):
+        real_ghostscript(sys.argv)
+        return
+
+    # Remove the two arguments that tell ghostscript to create a PDF/A
+    # Does not remove the Postscript definition file - not necessary
+    # to cause PDF/A creation failure
+    argv = []
+    for arg in sys.argv:
+        if arg.startswith('-dPDFA'):
+            continue
+        elif arg.startswith('-dPDFACompatibilityPolicy'):
+            continue
+        argv.append(arg)
+
+    real_ghostscript(argv)
+
+
+if __name__ == '__main__':
+    main()

tests/spoof/qpdf_dummy_return2.py

@@ -0,0 +1,11 @@
+#!/usr/bin/env python3
+import sys
+
+
+def main():
+    print('qpdf dummy')
+    sys.exit(2)
+
+
+if __name__ == '__main__':
+    main()

tests/spoof/tesseract_big_image_error.py

@@ -0,0 +1,44 @@
+#!/usr/bin/env python3
+import sys
+
+
+VERSION_STRING = '''tesseract 3.04.00
+ leptonica-1.72
+  libjpeg 8d : libpng 1.6.19 : libtiff 4.0.6 : zlib 1.2.5
+SPOOFED: return error claiming image too big
+'''
+
+"""Simulates an error of Tesseract failing on attempts to process large images
+
+"""
+
+
+def main():
+    if sys.argv[1] == '--version':
+        print(VERSION_STRING, file=sys.stderr)
+        sys.exit(0)
+    elif sys.argv[1] == '--list-langs':
+        print('List of available languages (1):\neng', file=sys.stderr)
+        sys.exit(0)
+    elif sys.argv[-1] == 'hocr':
+        print("Image too large: (33830, 14959)\n"
+              "Error during processing.", file=sys.stderr)
+        sys.exit(1)
+    elif sys.argv[-1] == 'pdf':
+        print("Image too large: (33830, 14959)\n"
+              "Error during processing.", file=sys.stderr)
+        sys.exit(1)
+    elif sys.argv[-1] == 'stdout':
+        print("Image too large: (33830, 14959)\n"
+              "Error during processing.", file=sys.stderr)
+        sys.exit(1)
+    else:
+        print("Spoof doesn't understand arguments", file=sys.stderr)
+        print(sys.argv, file=sys.stderr)
+        sys.exit(1)
+
+    sys.exit(0)
+
+
+if __name__ == '__main__':
+    main()

tests/spoof/tesseract_cache.py

@@ -0,0 +1,142 @@
+#!/usr/bin/env python3
+import sys
+import os
+import hashlib
+import shutil
+import subprocess
+
+
+"""Cache output of tesseract to speed up test suite
+
+The cache is keyed by a hash that includes the tesseract version, some of
+the command line, and the binary dump of the input file. The output file,
+stdout, and stderr are replicated on a cache hit.
+
+Page orientation checks are also cached (-psm 0 stdout)
+
+Errors and crashes are not cached.
+
+Things not checked:
+-changes to tesseract installation that don't affect --version
+
+Will fail on Tesseract 3.02.02 in "hocr" mode because it doesn't produce
+the incorrect file extension.
+
+"""
+
+
+CACHE_PATH = os.path.abspath(os.path.join(
+        os.path.dirname(__file__), '..', 'cache'))
+
+
+def real_tesseract():
+    tess_args = ['tesseract'] + sys.argv[1:]
+    os.execvp("tesseract", tess_args)
+    return  # Not reachable
+
+def main():
+    operation = sys.argv[-1]
+    # For anything unexpected operation, defer to real tesseract binary
+    if operation != 'hocr' and operation != 'pdf' and operation != 'stdout':
+        real_tesseract()
+        return  # Not reachable
+
+    try:
+        os.makedirs(CACHE_PATH)
+    except FileExistsError:
+        pass
+
+    m = hashlib.sha1()
+
+    tess_version = subprocess.check_output(
+        ['tesseract', '--version'],
+        stderr=subprocess.STDOUT)
+
+    m.update(tess_version)
+
+    # Insert this source file into the hash function, to ensure that any
+    # changes to this file invalidate previous hashes
+    with open(__file__, 'rb') as f:
+        m.update(f.read())
+
+    m.update(operation.encode())
+
+    try:
+        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
+
+    if operation == 'stdout' and psm != '0':
+        real_tesseract()
+        return
+
+    if operation == 'stdout':
+        input_file = sys.argv[-2]
+        output_file = 'stdout'
+    else:
+        input_file = sys.argv[-3]
+        output_file = sys.argv[-2]
+
+    if operation == 'hocr':
+        output_file += '.hocr'
+    elif operation == 'pdf':
+        output_file += '.pdf'
+
+    with open(input_file, 'rb') as f:
+        m.update(f.read())
+    cache_name = os.path.join(CACHE_PATH, m.hexdigest())
+    print(cache_name)
+    if os.path.exists(cache_name):
+        # Cache hit
+        print("Tesseract cache hit", file=sys.stderr)
+        if operation != 'stdout':
+            shutil.copy(cache_name, output_file)
+
+        # Replicate output
+        with open(cache_name + '.stdout', 'rb') as f:
+            sys.stdout.buffer.write(f.read())
+        with open(cache_name + '.stderr', 'rb') as f:
+            sys.stderr.buffer.write(f.read())
+        sys.exit(0)
+
+    # Cache miss
+    print("Tesseract cache miss", file=sys.stderr)
+
+    # Call tesseract
+    p = subprocess.Popen(
+            ['tesseract'] + sys.argv[1:],
+            stdout=subprocess.PIPE, stderr=subprocess.PIPE)
+    stdout, stderr = p.communicate()
+
+    if p.returncode != 0:
+        # Do not cache errors or crashes
+        print("Tesseract error", file=sys.stderr)
+        sys.stdout.buffer.write(stdout)
+        sys.stderr.buffer.write(stderr)
+        return p.returncode
+
+    with open(cache_name + '.stdout', 'wb') as f:
+        f.write(stdout)
+    with open(cache_name + '.stderr', 'wb') as f:
+        f.write(stderr)
+    sys.stdout.buffer.write(stdout)
+    sys.stderr.buffer.write(stderr)
+
+    # Insert file into cache
+    if output_file != 'stdout':
+        if os.path.exists(output_file):
+            shutil.copy(output_file, cache_name)
+        else:
+            print("Could not find output file", file=sys.stderr)
+    else:
+        open(cache_name, 'w').close()
+
+
+if __name__ == '__main__':
+    main()

tests/spoof/tesseract_crash.py

@@ -0,0 +1,50 @@
+#!/usr/bin/env python3
+import sys
+import os
+import signal
+
+
+VERSION_STRING = '''tesseract 3.04.00
+ leptonica-1.72
+  libjpeg 8d : libpng 1.6.19 : libtiff 4.0.6 : zlib 1.2.5
+SPOOFED: CRASH ON OCR or -psm 0
+'''
+
+"""Simulates a Tesseract crash when asked to run OCR
+
+It isn't strictly necessary to crash the process and that has unwanted
+side effects like triggering core dumps or error reporting, logging and such.
+It's enough to dump some text to stderr and return an error code.
+
+Follows the POSIX(?) convention of returning 128 + signal number.
+
+"""
+
+
+def main():
+    if sys.argv[1] == '--version':
+        print(VERSION_STRING, file=sys.stderr)
+        sys.exit(0)
+    elif sys.argv[1] == '--list-langs':
+        print('List of available languages (1):\neng', file=sys.stderr)
+        sys.exit(0)
+    elif sys.argv[-1] == 'hocr':
+        print("KABOOM! Tesseract failed for some reason", file=sys.stderr)
+        sys.exit(128 + signal.SIGSEGV)
+    elif sys.argv[-1] == 'pdf':
+        print("KABOOM! Tesseract failed for some reason", file=sys.stderr)
+        sys.exit(128 + signal.SIGSEGV)
+    elif sys.argv[-1] == 'stdout':
+        print("libc++abi.dylib: terminating with uncaught exception of type "
+              "std::bad_alloc: std::bad_alloc", file=sys.stderr)
+        sys.exit(128 + signal.SIGABRT)
+    else:
+        print("Spoof doesn't understand arguments", file=sys.stderr)
+        print(sys.argv, file=sys.stderr)
+        sys.exit(1)
+
+    sys.exit(0)
+
+
+if __name__ == '__main__':
+    main()

tests/spoof/tesseract_noop.py

@@ -0,0 +1,84 @@
+#!/usr/bin/env python3
+import sys
+import img2pdf
+from PIL import Image
+
+
+"""Tesseract no-op spoof
+
+To quickly run tests where getting OCR output is not necessary.
+
+In 'hocr' mode, create a .hocr file that specifies no text found.
+
+In 'pdf' mode, convert the image to PDF using another program.
+
+In orientation check mode, report the orientation is upright.
+"""
+
+
+VERSION_STRING = '''tesseract 3.04.00
+ leptonica-1.72
+  libjpeg 8d : libpng 1.6.19 : libtiff 4.0.6 : zlib 1.2.5
+SPOOFED
+'''
+
+HOCR_TEMPLATE = '''<?xml version="1.0" encoding="UTF-8"?>
+<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN"
+    "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
+<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
+ <head>
+  <title></title>
+  <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
+  <meta name='ocr-system' content='tesseract 3.02.02' />
+  <meta name='ocr-capabilities' content='ocr_page ocr_carea ocr_par ocr_line ocrx_word'/>
+ </head>
+ <body>
+  <div class='ocr_page' id='page_1' title='image "x.tif"; bbox 0 0 {0} {1}; ppageno 0'>
+   <div class='ocr_carea' id='block_1_1' title="bbox 0 1 {0} {1}">
+    <p class='ocr_par' dir='ltr' id='par_1' title="bbox 0 1 {0} {1}">
+     <span class='ocr_line' id='line_1' title="bbox 0 1 {0} {1}"><span class='ocrx_word' id='word_1' title="bbox 0 1 {0} {1}"> </span>
+     </span>
+    </p>
+   </div>
+  </div>
+ </body>
+</html>'''
+
+
+def main():
+    if sys.argv[1] == '--version':
+        print(VERSION_STRING, file=sys.stderr)
+        sys.exit(0)
+    elif sys.argv[1] == '--list-langs':
+        print('List of available languages (1):\neng', file=sys.stderr)
+        sys.exit(0)
+    elif sys.argv[-1] == 'hocr':
+        inputf = sys.argv[-3]
+        output = sys.argv[-2]
+        with Image.open(inputf) as im, \
+                open(output + '.hocr', 'w', encoding='utf-8') as f:
+            w, h = im.size
+            f.write(HOCR_TEMPLATE.format(str(w), str(h)))
+    elif sys.argv[-1] == 'pdf':
+        inputf = sys.argv[-3]
+        output = sys.argv[-2]
+        pdf_bytes = img2pdf.convert([inputf], dpi=300)
+        with open(output + '.pdf', 'wb') as f:
+            f.write(pdf_bytes)
+    elif sys.argv[-1] == 'stdout':
+        inputf = sys.argv[-2]
+        print("""Orientation: 0
+Orientation in degrees: 0
+Orientation confidence: 100.00
+Script: 1
+Script confidence: 100.00""", file=sys.stderr)
+    else:
+        print("Spoof doesn't understand arguments", file=sys.stderr)
+        print(sys.argv, file=sys.stderr)
+        sys.exit(1)
+
+    sys.exit(0)
+
+
+if __name__ == '__main__':
+    main()

tests/spoof/unpaper_oldversion.py

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

tests/test_hocrtransform.py

@@ -0,0 +1,41 @@
+#!/usr/bin/env python3
+# © 2015 James R. Barlow: github.com/jbarlow83
+
+from ocrmypdf import hocrtransform
+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
+import img2pdf
+import pytest
+import sys
+
+
+@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 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(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_main.py

@@ -0,0 +1,692 @@
+#!/usr/bin/env python3
+# © 2015 James R. Barlow: github.com/jbarlow83
+
+from subprocess import Popen, PIPE, check_output, check_call, DEVNULL
+import os
+import shutil
+from contextlib import suppress
+import sys
+import pytest
+from ocrmypdf.pageinfo import pdf_get_all_pageinfo
+import PyPDF2 as pypdf
+from ocrmypdf.exceptions import ExitCode
+from ocrmypdf import leptonica
+from ocrmypdf.pdfa import file_claims_pdfa
+
+
+check_ocrmypdf = pytest.helpers.check_ocrmypdf
+run_ocrmypdf = pytest.helpers.run_ocrmypdf
+spoof = pytest.helpers.spoof
+
+@pytest.fixture
+def spoof_tesseract_noop():
+    return spoof(tesseract='tesseract_noop.py')
+
+
+@pytest.fixture
+def spoof_tesseract_cache():
+    if pytest.helpers.running_in_docker():
+        return os.environ.copy()
+    return spoof(tesseract="tesseract_cache.py")
+
+
+@pytest.fixture
+def spoof_tesseract_crash():
+    return spoof(tesseract='tesseract_crash.py')
+
+
+@pytest.fixture
+def spoof_tesseract_big_image_error():
+    return spoof(tesseract='tesseract_big_image_error.py')
+
+
+@pytest.fixture
+def spoof_no_tess_no_pdfa():
+    return spoof(tesseract='tesseract_noop.py', gs='gs_pdfa_failure.py')
+
+
+@pytest.fixture
+def spoof_no_tess_pdfa_warning():
+    return spoof(tesseract='tesseract_noop.py', gs='gs_feature_elision.py')
+
+
+@pytest.fixture
+def spoof_qpdf_always_error():
+    return spoof(qpdf='qpdf_dummy_return2.py')
+
+
+def test_quick(spoof_tesseract_cache, resources, outpdf):
+    check_ocrmypdf(resources / 'ccitt.pdf', outpdf, env=spoof_tesseract_cache)
+
+
+def test_deskew(spoof_tesseract_noop, resources, outdir):
+    # Run with deskew
+    deskewed_pdf = check_ocrmypdf(
+        resources / 'skew.pdf', outdir / 'skew.pdf', '-d', '-v', '1',
+        env=spoof_tesseract_noop)
+
+    # Now render as an image again and use Leptonica to find the skew angle
+    # to confirm that it was deskewed
+    from ocrmypdf.exec.ghostscript import rasterize_pdf
+    import logging
+    log = logging.getLogger()
+
+    deskewed_png = outdir / 'deskewed.png'
+
+    rasterize_pdf(
+        str(deskewed_pdf),
+        str(deskewed_png),
+        xres=150,
+        yres=150,
+        raster_device='pngmono',
+        log=log)
+
+    from ocrmypdf.leptonica import Pix
+    pix = Pix.read(str(deskewed_png))
+    skew_angle, skew_confidence = pix.find_skew()
+
+    print(skew_angle)
+    assert -0.5 < skew_angle < 0.5, "Deskewing failed"
+
+
+def test_clean(spoof_tesseract_noop, resources, outpdf):
+    check_ocrmypdf(resources / 'skew.pdf', outpdf, '-c',
+                   env=spoof_tesseract_noop)
+
+
+def test_remove_background(spoof_tesseract_noop, resources, outdir):
+    from PIL import Image
+
+    # Ensure the input image does not contain pure white/black
+    im = Image.open(resources / 'congress.jpg')
+    assert im.getextrema() != ((0, 255), (0, 255), (0, 255))
+
+    output_pdf = check_ocrmypdf(
+        resources / 'congress.jpg',
+        outdir / 'test_remove_bg.pdf',
+        '--remove-background',
+        '--image-dpi', '150',
+        env=spoof_tesseract_noop)
+
+    from ocrmypdf.exec.ghostscript import rasterize_pdf
+    import logging
+    log = logging.getLogger()
+
+    output_png = outdir / 'remove_bg.png'
+
+    rasterize_pdf(
+        str(output_pdf),
+        str(output_png),
+        xres=100,
+        yres=100,
+        raster_device='png16m',
+        log=log)
+
+
+    # The output image should contain pure white and black
+    im = Image.open(output_png)
+    assert im.getextrema() == ((0, 255), (0, 255), (0, 255))
+
+
+# This will run 5 * 2 * 2 = 20 test cases
+@pytest.mark.parametrize(
+    "pdf",
+    ['palette.pdf', 'cmyk.pdf', 'ccitt.pdf', 'jbig2.pdf', 'lichtenstein.pdf'])
+@pytest.mark.parametrize("renderer", ['hocr', 'tesseract'])
+@pytest.mark.parametrize("output_type", ['pdf', 'pdfa'])
+def test_exotic_image(spoof_tesseract_cache, pdf, renderer, output_type,
+                      resources, outdir):
+    check_ocrmypdf(
+        resources / pdf,
+        outdir / 'test_{0}_{1}.pdf'.format(pdf, renderer),
+        '-dc',
+        '-v', '1',
+        '--output-type', output_type,
+        '--pdf-renderer', renderer, env=spoof_tesseract_cache)
+
+
+@pytest.mark.parametrize("output_type", [
+    'pdfa', 'pdf'
+    ])
+def test_preserve_metadata(spoof_tesseract_noop, output_type,
+                           resources, outpdf):
+    pdf_before = pypdf.PdfFileReader(str(resources / 'graph.pdf'))
+
+    output = check_ocrmypdf(
+            resources / 'graph.pdf', outpdf,
+            '--output-type', output_type,
+            env=spoof_tesseract_noop)
+
+    pdf_after = pypdf.PdfFileReader(str(output))
+
+    for key in ('/Title', '/Author'):
+        assert pdf_before.documentInfo[key] == pdf_after.documentInfo[key]
+
+    pdfa_info = file_claims_pdfa(str(output))
+    assert pdfa_info['output'] == output_type
+
+
+@pytest.mark.skipif(
+    pytest.helpers.is_linux() and not pytest.helpers.running_in_docker(),
+    reason="likely to fail if Linux locale is not configured correctly")
+@pytest.mark.parametrize("output_type", [
+    'pdfa', 'pdf'
+    ])
+def test_override_metadata(spoof_tesseract_noop, output_type, resources,
+                           outpdf):
+    input_file = resources / 'c02-22.pdf'
+
+    german = 'Du siehst den Wald vor lauter Bäumen nicht.'
+    chinese = '孔子'
+    high_unicode = 'U+1030C is: 𐌌'
+
+    p, out, err = run_ocrmypdf(
+        input_file, outpdf,
+        '--title', german,
+        '--author', chinese,
+        '--subject', high_unicode,
+        '--output-type', output_type,
+        env=spoof_tesseract_noop)
+
+    assert p.returncode == ExitCode.ok
+
+    pdf = str(outpdf)
+
+    out_pdfinfo = check_output(['pdfinfo', pdf], universal_newlines=True)
+    lines_pdfinfo = out_pdfinfo.splitlines()
+    pdfinfo = {}
+    for line in lines_pdfinfo:
+        k, v = line.strip().split(':', maxsplit=1)
+        pdfinfo[k.strip()] = v.strip()
+
+    assert pdfinfo['Title'] == german
+    assert pdfinfo['Author'] == chinese
+    assert pdfinfo['Subject'] == high_unicode
+    assert pdfinfo.get('Keywords', '') == ''
+
+    pdfa_info = file_claims_pdfa(pdf)
+    assert pdfa_info['output'] == output_type
+
+
+@pytest.mark.parametrize('renderer', [
+    'hocr',
+    'tesseract',
+    ])
+def test_oversample(spoof_tesseract_cache, renderer, resources, outpdf):
+    oversampled_pdf = check_ocrmypdf(
+        resources / 'skew.pdf', outpdf, '--oversample', '350',
+        '-f',
+        '--pdf-renderer', renderer, env=spoof_tesseract_cache)
+
+    pdfinfo = pdf_get_all_pageinfo(str(oversampled_pdf))
+
+    print(pdfinfo[0]['xres'])
+    assert abs(pdfinfo[0]['xres'] - 350) < 1
+
+
+def test_repeat_ocr(resources, no_outpdf):
+    p, _, _ = run_ocrmypdf(resources / 'graph_ocred.pdf', no_outpdf)
+    assert p.returncode != 0
+
+
+def test_force_ocr(spoof_tesseract_cache, resources, outpdf):
+    out = check_ocrmypdf(resources / 'graph_ocred.pdf', outpdf, '-f',
+                         env=spoof_tesseract_cache)
+    pdfinfo = pdf_get_all_pageinfo(out)
+    assert pdfinfo[0]['has_text']
+
+
+def test_skip_ocr(spoof_tesseract_cache, resources, outpdf):
+    check_ocrmypdf(resources / 'graph_ocred.pdf', outpdf, '-s',
+                   env=spoof_tesseract_cache)
+
+
+def test_argsfile(spoof_tesseract_noop, resources, outdir):
+    path_argsfile = outdir / 'test_argsfile.txt'
+    with open(str(path_argsfile), 'w') as argsfile:
+        print('--title', 'ArgsFile Test', '--author', 'Test Cases',
+              sep='\n', end='\n', file=argsfile)
+    check_ocrmypdf(resources / 'graph.pdf', path_argsfile,
+                   '@' + str(outdir / 'test_argsfile.txt'),
+                   env=spoof_tesseract_noop)
+
+
+def check_monochrome_correlation(
+        outdir,
+        reference_pdf, reference_pageno, test_pdf, test_pageno):
+
+    import ocrmypdf.exec.ghostscript as ghostscript
+    import logging
+
+    gslog = logging.getLogger()
+
+    reference_png = outdir / '{}.ref{:04d}.png'.format(
+        reference_pdf.name, reference_pageno)
+    test_png = outdir / '{}.test{:04d}.png'.format(
+        test_pdf.name, test_pageno)
+
+    def rasterize(pdf, pageno, png):
+        if png.exists():
+            print(png)
+            return
+        ghostscript.rasterize_pdf(
+            str(pdf),
+            str(png),
+            xres=100, yres=100,
+            raster_device='pngmono', log=gslog, pageno=pageno)
+
+    rasterize(reference_pdf, reference_pageno, reference_png)
+    rasterize(test_pdf, test_pageno, test_png)
+
+    pix_ref = leptonica.Pix.read(str(reference_png))
+    pix_test = leptonica.Pix.read(str(test_png))
+
+    return leptonica.Pix.correlation_binary(pix_ref, pix_test)
+
+
+def test_monochrome_correlation(resources, outdir):
+    # Verify leptonica: check that an incorrect rotated image has poor
+    # correlation with reference
+    corr = check_monochrome_correlation(
+        outdir,
+        reference_pdf=resources / 'cardinal.pdf',
+        reference_pageno=1,  # north facing page
+        test_pdf=resources / 'cardinal.pdf',
+        test_pageno=3,  # south facing page
+        )
+    assert corr < 0.10
+    corr = check_monochrome_correlation(
+        outdir,
+        reference_pdf=resources / 'cardinal.pdf',
+        reference_pageno=2,
+        test_pdf=resources / 'cardinal.pdf',
+        test_pageno=2,
+        )
+    assert corr > 0.90
+
+
+@pytest.mark.parametrize('renderer', [
+    'hocr',
+    'tesseract',
+    ])
+def test_autorotate(spoof_tesseract_cache, renderer, resources, outdir):
+    # cardinal.pdf contains four copies of an image rotated in each cardinal
+    # direction - these ones are "burned in" not tagged with /Rotate
+    out = check_ocrmypdf(resources / 'cardinal.pdf', outdir / 'out.pdf',
+                         '-r', '-v', '1', env=spoof_tesseract_cache)
+    for n in range(1, 4+1):
+        correlation = check_monochrome_correlation(
+            outdir,
+            reference_pdf=resources / 'cardinal.pdf',
+            reference_pageno=1,
+            test_pdf=outdir / 'out.pdf',
+            test_pageno=n)
+        assert correlation > 0.80
+
+
+@pytest.mark.parametrize('threshold, correlation_test', [
+    ('1', 'correlation > 0.80'),  # Low thresh -> always rotate -> high corr
+    ('99', 'correlation < 0.10'),  # High thres -> never rotate -> low corr
+])
+def test_autorotate_threshold(
+    spoof_tesseract_cache, threshold, correlation_test, resources, outdir):
+    out = check_ocrmypdf(resources / 'cardinal.pdf', outdir / 'out.pdf',
+                         '--rotate-pages-threshold', threshold,
+                         '-r', '-v', '1', env=spoof_tesseract_cache)
+
+    correlation = check_monochrome_correlation(
+        outdir,
+        reference_pdf=resources / 'cardinal.pdf',
+        reference_pageno=1,
+        test_pdf=outdir / 'out.pdf',
+        test_pageno=3)
+    assert eval(correlation_test)
+
+
+@pytest.mark.parametrize('renderer', [
+    'hocr',
+    'tesseract',
+    ])
+def test_ocr_timeout(renderer, resources, outpdf):
+    out = check_ocrmypdf(resources / 'skew.pdf', outpdf,
+                         '--tesseract-timeout', '1.0')
+    pdfinfo = pdf_get_all_pageinfo(str(out))
+    assert not pdfinfo[0]['has_text']
+
+
+def test_skip_big(spoof_tesseract_cache, resources, outpdf):
+    out = check_ocrmypdf(resources / 'enormous.pdf', outpdf,
+                         '--skip-big', '10', env=spoof_tesseract_cache)
+    pdfinfo = pdf_get_all_pageinfo(str(out))
+    assert not pdfinfo[0]['has_text']
+
+
+@pytest.mark.parametrize('renderer', ['hocr', 'tesseract'])
+@pytest.mark.parametrize('output_type', ['pdf', 'pdfa'])
+def test_maximum_options(spoof_tesseract_cache, renderer, output_type,
+                         resources, outpdf):
+    check_ocrmypdf(
+        resources / 'multipage.pdf', outpdf,
+        '-d', '-c', '-i', '-g', '-f', '-k', '--oversample', '300',
+        '--remove-background',
+        '--skip-big', '10', '--title', 'Too Many Weird Files',
+        '--author', 'py.test', '--pdf-renderer', renderer,
+        '--output-type', output_type,
+        env=spoof_tesseract_cache)
+
+
+def test_tesseract_missing_tessdata(resources, no_outpdf):
+    env = os.environ.copy()
+    env['TESSDATA_PREFIX'] = '/tmp'
+
+    p, _, err = run_ocrmypdf(
+        resources / 'graph_ocred.pdf', no_outpdf,
+        '-v', '1', '--skip-text', env=env)
+    assert p.returncode == ExitCode.missing_dependency, err
+
+
+def test_invalid_input_pdf(resources, no_outpdf):
+    p, out, err = run_ocrmypdf(
+        resources / 'invalid.pdf', no_outpdf)
+    assert p.returncode == ExitCode.input_file, err
+
+
+def test_blank_input_pdf(resources, outpdf):
+    p, out, err = run_ocrmypdf(
+        resources / 'blank.pdf', outpdf)
+    assert p.returncode == ExitCode.ok
+
+
+def test_force_ocr_on_pdf_with_no_images(spoof_tesseract_crash, resources,
+                                         no_outpdf):
+    # As a correctness test, make sure that --force-ocr on a PDF with no
+    # content still triggers tesseract. If tesseract crashes, then it was
+    # called.
+    p, _, err = run_ocrmypdf(
+        resources / 'blank.pdf', no_outpdf, '--force-ocr',
+        env=spoof_tesseract_crash)
+    assert p.returncode == ExitCode.child_process_error, err
+    assert not os.path.exists(no_outpdf)
+
+
+def test_french(spoof_tesseract_cache, resources, outpdf):
+    p, out, err = run_ocrmypdf(
+        resources / 'francais.pdf', outpdf, '-l', 'fra',
+        env=spoof_tesseract_cache)
+    assert p.returncode == ExitCode.ok, \
+        "This test may fail if Tesseract language packs are missing"
+
+
+def test_klingon(resources, outpdf):
+    p, out, err = run_ocrmypdf(
+        resources / 'francais.pdf', outpdf, '-l', 'klz')
+    assert p.returncode == ExitCode.bad_args
+
+
+def test_missing_docinfo(spoof_tesseract_noop, resources, outpdf):
+    p, out, err = run_ocrmypdf(
+        resources / 'missing_docinfo.pdf', outpdf, '-l', 'eng', '-c',
+        env=spoof_tesseract_noop)
+    assert p.returncode == ExitCode.ok, err
+
+
+@pytest.mark.skipif(pytest.helpers.running_in_docker(),
+                    reason="<no longer true> writes to tests/resources")
+def test_uppercase_extension(spoof_tesseract_noop, resources, outdir):
+    shutil.copy(
+        str(resources / "skew.pdf"),
+        str(outdir / "UPPERCASE.PDF"))
+
+    check_ocrmypdf(outdir / "UPPERCASE.PDF", outdir / "UPPERCASE_OUT.PDF",
+                   env=spoof_tesseract_noop)
+
+
+def test_input_file_not_found(no_outpdf):
+    input_file = "does not exist.pdf"
+    p, out, err = run_ocrmypdf(
+        input_file,
+        no_outpdf)
+    assert p.returncode == ExitCode.input_file
+    assert (input_file in out or input_file in err)
+
+
+def test_input_file_not_a_pdf(no_outpdf):
+    input_file = __file__  # Try to OCR this file
+    p, out, err = run_ocrmypdf(
+        input_file,
+        no_outpdf)
+    assert p.returncode == ExitCode.input_file
+    assert (input_file in out or input_file in err)
+
+
+def test_qpdf_repair_fails(spoof_qpdf_always_error, resources, no_outpdf):
+    p, out, err = run_ocrmypdf(
+        resources / 'c02-22.pdf', no_outpdf,
+        '-v', '1',
+        env=spoof_qpdf_always_error)
+    print(err)
+    assert p.returncode == ExitCode.input_file
+
+
+def test_encrypted(resources, no_outpdf):
+    p, out, err = run_ocrmypdf(
+        resources / 'skew-encrypted.pdf', no_outpdf)
+    assert p.returncode == ExitCode.encrypted_pdf
+    assert out.find('password')
+
+
+@pytest.mark.parametrize('renderer', [
+    'hocr',
+    'tesseract',
+    ])
+def test_pagesegmode(renderer, spoof_tesseract_cache, resources, outpdf):
+    check_ocrmypdf(
+        resources / 'skew.pdf', outpdf,
+        '--tesseract-pagesegmode', '7',
+        '-v', '1',
+        '--pdf-renderer', renderer, env=spoof_tesseract_cache)
+
+
+@pytest.mark.parametrize('renderer', [
+    'hocr',
+    'tesseract',
+    ])
+def test_tesseract_crash(renderer, spoof_tesseract_crash,
+                         resources, no_outpdf):
+    p, out, err = run_ocrmypdf(
+        resources / 'ccitt.pdf', no_outpdf, '-v', '1',
+        '--pdf-renderer', renderer, env=spoof_tesseract_crash)
+    assert p.returncode == ExitCode.child_process_error
+    assert not os.path.exists(no_outpdf)
+    assert "ERROR" in err
+
+
+def test_tesseract_crash_autorotate(spoof_tesseract_crash,
+                                    resources, no_outpdf):
+    p, out, err = run_ocrmypdf(
+        resources / 'ccitt.pdf', no_outpdf,
+        '-r', env=spoof_tesseract_crash)
+    assert p.returncode == ExitCode.child_process_error
+    assert not os.path.exists(no_outpdf)
+    assert "ERROR" in err
+    print(out)
+    print(err)
+
+
+@pytest.mark.parametrize('renderer', [
+    'hocr',
+    'tesseract',
+    ])
+def test_tesseract_image_too_big(renderer, spoof_tesseract_big_image_error,
+                                 resources, outpdf):
+    check_ocrmypdf(
+        resources / 'hugemono.pdf', outpdf, '-r',
+        '--pdf-renderer', renderer, env=spoof_tesseract_big_image_error)
+
+
+def test_no_unpaper(resources, no_outpdf):
+    env = os.environ.copy()
+    env['OCRMYPDF_UNPAPER'] = os.path.abspath('./spoof/no_unpaper_here.py')
+    p, out, err = run_ocrmypdf(
+        resources / 'c02-22.pdf', no_outpdf, '--clean', env=env)
+    assert p.returncode == ExitCode.missing_dependency
+
+
+def test_old_unpaper(resources, no_outpdf):
+    env = os.environ.copy()
+    env['OCRMYPDF_UNPAPER'] = os.path.abspath('./spoof/unpaper_oldversion.py')
+    p, out, err = run_ocrmypdf(
+        resources / 'c02-22.pdf', no_outpdf, '--clean', env=env)
+    assert p.returncode == ExitCode.missing_dependency
+
+
+def test_algo4(resources, no_outpdf):
+    p, _, _ = run_ocrmypdf(resources / 'encrypted_algo4.pdf', no_outpdf)
+    assert p.returncode == ExitCode.encrypted_pdf
+
+
+@pytest.mark.parametrize('renderer', [
+    'hocr'])  # tesseract cannot pass this test - resamples to square image
+def test_non_square_resolution(renderer, spoof_tesseract_cache,
+                               resources, outpdf):
+    # Confirm input image is non-square resolution
+    in_pageinfo = pdf_get_all_pageinfo(str(resources / 'aspect.pdf'))
+    assert in_pageinfo[0]['xres'] != in_pageinfo[0]['yres']
+
+    check_ocrmypdf(
+        resources / 'aspect.pdf', outpdf,
+        '--pdf-renderer', renderer, env=spoof_tesseract_cache)
+
+    out_pageinfo = pdf_get_all_pageinfo(str(outpdf))
+
+    # Confirm resolution was kept the same
+    assert in_pageinfo[0]['xres'] == out_pageinfo[0]['xres']
+    assert in_pageinfo[0]['yres'] == out_pageinfo[0]['yres']
+
+
+def test_image_to_pdf(spoof_tesseract_noop, resources, outpdf):
+    check_ocrmypdf(
+        resources / 'LinnSequencer.jpg', outpdf, '--image-dpi', '200',
+        env=spoof_tesseract_noop)
+
+
+def test_jbig2_passthrough(spoof_tesseract_cache, resources, outpdf):
+    out = check_ocrmypdf(
+        resources / 'jbig2.pdf', outpdf,
+        '--output-type', 'pdf',
+        '--pdf-renderer', 'hocr',
+        env=spoof_tesseract_cache)
+
+    out_pageinfo = pdf_get_all_pageinfo(str(out))
+    assert out_pageinfo[0]['images'][0]['enc'] == 'jbig2'
+
+
+def test_stdin(spoof_tesseract_noop, ocrmypdf_exec, resources, outpdf):
+    input_file = str(resources / 'francais.pdf')
+    output_file = str(outpdf)
+
+    # Runs: ocrmypdf - output.pdf < testfile.pdf
+    with open(input_file, 'rb') as input_stream:
+        p_args = ocrmypdf_exec + ['-', output_file]
+        p = Popen(
+            p_args, close_fds=True, stdout=PIPE, stderr=PIPE,
+            stdin=input_stream, env=spoof_tesseract_noop)
+        out, err = p.communicate()
+
+        assert p.returncode == ExitCode.ok
+
+
+def test_stdout(spoof_tesseract_noop, ocrmypdf_exec, resources, outpdf):
+    input_file = str(resources / 'francais.pdf')
+    output_file = str(outpdf)
+
+    # Runs: ocrmypdf francais.pdf - > test_stdout.pdf
+    with open(output_file, 'wb') as output_stream:
+        p_args = ocrmypdf_exec + [input_file, '-']
+        p = Popen(
+            p_args, close_fds=True, stdout=output_stream, stderr=PIPE,
+            stdin=DEVNULL, env=spoof_tesseract_noop)
+        out, err = p.communicate()
+
+        assert p.returncode == ExitCode.ok
+
+    from ocrmypdf.exec import qpdf
+    assert qpdf.check(output_file, log=None)
+
+
+def test_masks(spoof_tesseract_noop, resources, outpdf):
+    check_ocrmypdf(resources / 'masks.pdf', outpdf, env=spoof_tesseract_noop)
+
+
+def test_linearized_pdf_and_indirect_object(spoof_tesseract_noop,
+        resources, outpdf):
+    check_ocrmypdf(
+        resources / 'epson.pdf', outpdf,
+        env=spoof_tesseract_noop)
+
+
+def test_rotated_skew_timeout(resources, outpdf):
+    """This document contains an image that is rotated 90 into place with a
+    /Rotate tag and intentionally skewed by altering the transformation matrix.
+
+    This tests for a bug where the combinatino of preprocessing and a tesseract
+    timeout produced a page whose dimensions did not match the original's.
+    """
+
+    input_file = str(resources / 'rotated_skew.pdf')
+    in_pageinfo = pdf_get_all_pageinfo(input_file)[0]
+
+    assert in_pageinfo['height_pixels'] < in_pageinfo['width_pixels'], \
+        "Expected the input page to be landscape"
+    assert in_pageinfo['rotate'] == 90, "Expected a rotated page"
+
+    out = check_ocrmypdf(
+        input_file, outpdf,
+        '--pdf-renderer', 'hocr',
+        '--deskew', '--tesseract-timeout', '0')
+
+    out_pageinfo = pdf_get_all_pageinfo(str(out))[0]
+
+    assert out_pageinfo['height_pixels'] > out_pageinfo['width_pixels'], \
+        "Expected the output page to be portrait"
+
+    assert out_pageinfo['rotate'] == 0, \
+        "Expected no page rotation for output"
+
+    assert in_pageinfo['width_pixels'] == out_pageinfo['height_pixels'] and \
+        in_pageinfo['height_pixels'] == out_pageinfo['width_pixels'], \
+        "Expected page rotation to be baked in"
+
+
+def test_ghostscript_pdfa_failure(spoof_no_tess_no_pdfa, resources, outpdf):
+    p, out, err = run_ocrmypdf(
+        resources / 'ccitt.pdf', outpdf,
+        env=spoof_no_tess_no_pdfa)
+    assert p.returncode == 4, "Expected return code 4 when PDF/A fails"
+
+
+def test_ghostscript_feature_elision(spoof_no_tess_pdfa_warning,
+        resources, outpdf):
+    check_ocrmypdf(resources / 'ccitt.pdf', outpdf,
+                   env=spoof_no_tess_pdfa_warning)
+
+
+def test_very_high_dpi(spoof_tesseract_cache, resources, outpdf):
+    "Checks for a Decimal quantize error with high DPI, etc"
+    check_ocrmypdf(resources / '2400dpi.pdf', outpdf,
+                   env=spoof_tesseract_cache)
+
+
+def test_overlay(spoof_tesseract_noop, resources, outpdf):
+    check_ocrmypdf(resources / 'overlay.pdf', outpdf,
+                   env=spoof_tesseract_noop)
+
+
+def test_destination_not_writable(spoof_tesseract_noop, resources, outdir):
+    protected_file = outdir / 'protected.pdf'
+    protected_file.touch()
+    protected_file.chmod(0o400)  # Read-only
+    p, out, err = run_ocrmypdf(
+        resources / 'jbig2.pdf', protected_file,
+        env=spoof_tesseract_noop)
+    assert p.returncode == ExitCode.file_access_error, "Expected error"

tests/test_pageinfo.py

@@ -0,0 +1,103 @@
+#!/usr/bin/env python3
+# © 2015 James R. Barlow: github.com/jbarlow83
+
+from ocrmypdf import pageinfo
+from reportlab.pdfgen.canvas import Canvas
+from PIL import Image
+from tempfile import NamedTemporaryFile
+from contextlib import suppress
+import os
+import shutil
+import pytest
+import img2pdf
+import pytest
+import sys
+
+
+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)
+    text.textLine("Methink'st thou art a general offence and every"
+                  " man should beat thee.")
+    pdf.drawText(text)
+    pdf.showPage()
+    pdf.save()
+
+    pdfinfo = pageinfo.pdf_get_all_pageinfo(str(filename))
+
+    assert len(pdfinfo) == 1
+    page = pdfinfo[0]
+
+    assert page['has_text']
+    assert len(page['images']) == 0
+
+
+@pytest.mark.skipif(sys.version_info < (3, 5), reason="needs Path.read_bytes")
+def test_single_page_image(outdir):
+    filename = outdir / 'image-mono.pdf'
+
+    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)
+
+    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)
+
+    pdfinfo = pageinfo.pdf_get_all_pageinfo(str(filename))
+
+    assert len(pdfinfo) == 1
+    page = pdfinfo[0]
+
+    assert not page['has_text']
+    assert len(page['images']) == 1
+
+    pdfimage = page['images'][0]
+    assert pdfimage['width'] == 8
+    assert pdfimage['color'] == 'gray'
+
+    # DPI in a 1"x1" is the image width
+    assert abs(pdfimage['dpi_w'] - 8) < 1e-5
+    assert abs(pdfimage['dpi_h'] - 8) < 1e-5
+
+
+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):
+            im.putpixel((n, n), 1)
+        im.save(im_tmp.name, format='PNG')
+        # Draw image in a 72x72 pt or 1"x1" area
+        pdf.drawInlineImage(im_tmp.name, 0, 0, width=72, height=72)
+        pdf.showPage()
+        pdf.save()
+
+    pdfinfo = pageinfo.pdf_get_all_pageinfo(str(filename))
+    print(pdfinfo)
+    pdfimage = pdfinfo[0]['images'][0]
+    assert (pdfimage['dpi_w'] - 8) < 1e-5
+    assert pdfimage['color'] != '-'
+    assert pdfimage['width'] == 8
+
+
+def test_jpeg(resources, outdir):
+    filename = resources / 'c02-22.pdf'
+
+    pdfinfo = pageinfo.pdf_get_all_pageinfo(str(filename))
+
+    pdfimage = pdfinfo[0]['images'][0]
+    assert pdfimage['enc'] == 'jpeg'
+    assert (pdfimage['dpi_w'] - 150) < 1e-5
+

tests/test_tess4.py

@@ -0,0 +1,31 @@
+#!/usr/bin/env python3
+# © 2017 James R. Barlow: github.com/jbarlow83
+
+from subprocess import Popen, PIPE, check_output, check_call, DEVNULL
+import os
+import shutil
+from contextlib import suppress
+import sys
+import pytest
+from ocrmypdf.pageinfo import pdf_get_all_pageinfo
+import PyPDF2 as pypdf
+from ocrmypdf.exceptions import ExitCode
+from ocrmypdf import leptonica
+from ocrmypdf.pdfa import file_claims_pdfa
+from ocrmypdf.exec import tesseract
+
+
+# Skip all tests in this file if not tesseract 4
+pytestmark = pytest.mark.skipif(not tesseract.v4(),
+                                reason="tesseract 4.0 required")
+
+
+@pytest.mark.skipif(not tesseract.has_textonly_pdf(),
+                    reason="requires textonly_pdf feature")
+def test_textonly_pdf(resources, outdir):
+    pytest.helpers.check_ocrmypdf(
+        resources / 'linn.pdf',
+        outdir / 'linn_textonly.pdf', '--pdf-renderer', 'tess4')
+
+
+