Fix issue #194 - --sidecar creates blank txt file

[ci skip]

.coveragerc

@@ -0,0 +1,16 @@
+# Coverage isn't really compatible with subprocesses so results are unreliable
+
+[run]
+branch = True
+#concurrency = multiprocessing
+source = ocrmypdf/
+
+[report]
+exclude_lines =
+	pragma: no cover
+	def __repr__
+	raise AssertionError
+	raise NotImplementedError
+	if 0:
+	if False:
+	if __name__ == .__main__.:

.gitignore

@@ -38,4 +38,7 @@ tests/cache/
 tests/output/
 tests/resources/private/
 tmp/
-pdfbox-app*.jar
+pdfbox-app*.jar
+.vscode/
+IDEAS
+_Dockerfile.local

.travis.yml

@@ -43,6 +43,7 @@ install:
 
 script:
 - mv ocrmypdf dont_import_this_ocrmypdf
+- tesseract --version
 - pytest -n auto
 - mv dont_import_this_ocrmypdf ocrmypdf
 
@@ -84,6 +85,7 @@ deploy:
   script: /usr/bin/true
   on:
     branch: master
+    tags: true
     condition: $TRAVIS_OS_NAME == "osx"
 
 after_deploy: |

.travis/autobrew.py

@@ -30,6 +30,7 @@ class Ocrmypdf < Formula
   depends_on "libjpeg"
   depends_on "webp"
   depends_on "little-cms2"
+  depends_on "zlib"
 
 ${resources}
   def install

Dockerfile

@@ -1,7 +1,6 @@
 # OCRmyPDF
 #
-# VERSION               4.4.2
-FROM      ubuntu:16.10
+FROM      ubuntu:17.04
 MAINTAINER James R. Barlow <jim@purplerock.ca>
 
 RUN apt-get update && apt-get install -y --no-install-recommends \
@@ -20,6 +19,8 @@ RUN apt-get update && apt-get install -y --no-install-recommends \
   tesseract-ocr-spa \
   tesseract-ocr-deu
 
+ENV LANG=C.UTF-8
+
 RUN python3 -m venv --system-site-packages /appenv
 
 # This installs the latest binary wheel instead of the code in the current

Dockerfile.polyglot

@@ -1,8 +1,6 @@
 # OCRmyPDF polyglot
 #
-# VERSION               4.4.2
 FROM      jbarlow83/ocrmypdf:latest
-MAINTAINER James R. Barlow <jim@purplerock.ca>
 
 USER root
 

Dockerfile.tess4

@@ -1,7 +1,6 @@
 # OCRmyPDF
 #
-# VERSION               4.4.2
-FROM 	ubuntu:16.10
+FROM 	ubuntu:17.04
 MAINTAINER James R. Barlow <jim@purplerock.ca>
 
 RUN apt-get update && apt-get install -y --no-install-recommends \
@@ -30,6 +29,8 @@ RUN apt-get update \
 		tesseract-ocr-rus \
 		tesseract-ocr-chi-sim 
 
+ENV LANG=C.UTF-8
+
 RUN python3 -m venv --system-site-packages /appenv
 
 # This installs the latest binary wheel instead of the code in the current

MANIFEST.in

@@ -7,12 +7,12 @@ include dev_requirements.txt
 include .git_archival.txt
 
 # docker
-include Dockerfile
-include Dockerfile.polyglot
+include Dockerfile*
 include .dockerignore
 
 # tests
 include pytest.ini
+include .coveragerc
 recursive-include tests *.jpg
 recursive-include tests *.png
 recursive-include tests *.pdf
@@ -38,11 +38,14 @@ recursive-exclude docs/_build *
 recursive-include ocrmypdf/data *
 include *.py
 exclude tasks.py
+exclude debug-runner.py
+recursive-exclude .travis *
+exclude .travis*
+
 
 # code
 recursive-include ocrmypdf *.py
 exclude ocrmypdf/lib/_leptonica.py
-include OCRmyPDF.sh
 include docker-wrapper.sh
 
 

docs/batch.rst

@@ -90,13 +90,83 @@ This user contributed script also provides an example of batch processing.
 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.
+OCRmyPDF is currently supported as a command line interface. This means that even if you are using OCRmyPDF in a Python script, you should run it in a subprocess rather importing the ocrmypdf package.
+
+The reason for this limitation is that the `ruffus <https://github.com/bunbun/ruffus/>`_ library that OCRmyPDF depends on is unfortunately not reentrant. OCRmyPDF works by defining each operation it does as a ruffus task that takes one or more files as input and generates one or more files as output. As such ruffus is fairly fundamental.
+
+(If you find individual functions implemented in OCRmyPDF useful (such as ``ocrmypdf.pdfinfo``), you can use these if you wish to.)
+
+
+Synology DiskStations
+"""""""""""""""""""""
+
+Synology DiskStations (Network Attached Storage devices) can run the Docker image of OCRmyPDF if the Synology `Docker package <https://www.synology.com/en-global/dsm/packages/Docker>`_ is installed. Attached is a script to address particular quirks of using OCRmyPDF on one of these devices.
+
+This is only possible for x86-based Synology products. Some Synology products use ARM or Power processors and do not support Docker. Further adjustments might be needed to deal with the Synology's relatively limited CPU and RAM.
+
+.. code-block:: python
+
+	#!/bin/env python3
+	# Contributed by github.com/Enantiomerie
+
+	# script needs 2 arguments
+	# 1. source dir with *.pdf - default is location of script
+	# 2. move dir where *.pdf and *_OCR.pdf are moved to
+
+	import logging
+	import os
+	import subprocess
+	import sys
+	import time
+	import shutil
+
+	script_dir = os.path.dirname(os.path.realpath(__file__))
+	timestamp = time.strftime("%Y-%m-%d-%H%M_")
+	log_file = script_dir + '/' + timestamp + 'ocrmypdf.log'
+	logging.basicConfig(level=logging.INFO, format='%(asctime)s %(message)s', filename=log_file, filemode='w')
+
+	if len(sys.argv) > 1:
+	    start_dir = sys.argv[1]
+	else:
+	    start_dir = '.'
+
+	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
+	            file_noext = os.path.splitext(filename)[0]
+	            timestamp_OCR = time.strftime("%Y-%m-%d-%H%M_OCR_")
+	            filename_OCR = timestamp_OCR + file_noext + '.pdf'
+	            docker_mount = dir_name + ':/home/docker'
+	# create string for pdf processing 
+	# diskstation needs a user:group docker:docker. find uid:gid of your diskstation docker:docker with id docker.
+	# use this uid:gid in -u flag
+	# rw rights for docker:docker at source dir are also necessary
+	# the script is processed as root user via chron 
+	            cmd = ['docker', 'run', '--rm', '-v', docker_mount, '-u="1030:65538"', 'jbarlow83/ocrmypdf', , '--deskew' , filename, filename_OCR]
+	            logging.info(cmd)
+	            proc = subprocess.Popen(cmd, stdout=subprocess.PIPE, stderr=subprocess.STDOUT)
+	            result = proc.stdout.read()
+	            logging.info(result)
+	            full_path_OCR = dir_name + '/' + filename_OCR
+	            os.chmod(full_path_OCR, 0o666)
+	            os.chmod(full_path, 0o666)
+	            full_path_OCR_archive = sys.argv[2]
+	            full_path_archive = sys.argv[2] + '/no_ocr'
+	            shutil.move(full_path_OCR,full_path_OCR_archive)
+	            shutil.move(full_path, full_path_archive)
+	logging.info('Finished.\n')
+
 
 
 Huge batch jobs
 """""""""""""""
 
-If you have thousands of files to work with, contact the author.
+If you have thousands of files to work with, contact the author. Consulting work related to OCRmyPDF helps fund this open source project and all inquiries are appreciated.
 
 
 Hot (watched) folders

docs/installation.rst

@@ -105,6 +105,12 @@ In this worked example, the current working directory contains an input file cal
 
 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.
 
+In some environments the permissions associated with Docker can be complex to configure. The process that executes Docker may end up not having the permissions to write the specified file system. In that case one can stream the file into and out of the Docker process and avoid all permission hassles, using ``-`` as the input and output filename:
+
+.. code-block:: bash
+
+    docker run --rm -i   ocrmypdf <other arguments to ocrmypdf> - - <input.pdf >output.pdf
+
 For convenience, a shell alias can hide the docker command:
 
 .. code-block:: bash
@@ -214,15 +220,8 @@ follow these steps.
 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 and because OCRmyPDF depends on some packages newer than are available in the main distribution.
-
-Add new "apt" repositories needed for backports of Ghostscript 9.16, libav-11 (for unpaper 6.1) and Tesseract 4.00 (alpha). This will replace Ghostscript and Tesseract 3.x on your system. If you prefer to not modify your system in this matter, consider using a Docker container.
-
-.. code-block:: bash
-
-    sudo add-apt-repository ppa:vshn/ghostscript -y
-    sudo add-apt-repository ppa:heyarje/libav-11 -y
-    sudo add-apt-repository ppa:alex-p/tesseract-ocr
+Installing on Ubuntu 14.04 LTS (trusty) is more difficult than some other options,
+because it is older.
 
 Update apt-get:
 
@@ -239,39 +238,38 @@ Install system dependencies:
         zlib1g-dev \
         libjpeg-dev \
         libffi-dev \
-        libavformat56 libavcodec56 libavutil54 \
+        qpdf
+
+We will need backports of Ghostscript 9.16, libav-11 (for unpaper 6.1),
+Tesseract 4.00 (alpha), and Python 3.6. This will replace Ghostscript and
+Tesseract 3.x on your system. Python 3.6 will be installed alongside the system
+Python 3.
+
+If you prefer to not modify your system in this matter, consider using a Docker container.
+
+.. code-block:: bash
+
+    sudo add-apt-repository ppa:vshn/ghostscript -y
+    sudo add-apt-repository ppa:heyarje/libav-11 -y
+    sudo add-apt-repository ppa:alex-p/tesseract-ocr -y
+    sudo add-apt-repository ppa:jonathonf/python-3.6 -y
+
+    sudo apt-get update
+
+    sudo apt-get install \
+        python3.6 \
         ghostscript \
-        qpdf \
-        python3-pip \
-        python3-pil \
-        python3-pytest \
-        python3-reportlab \
-        python3-wheel \
-        python3-venv \
         tesseract-ocr \
-        tesseract-ocr-eng
+        tesseract-ocr-eng \
+        libavformat56 libavcodec56 libavutil54 \
+        wget
 
-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):
+Now we need to install ``pip`` and let it install ocrmypdf:
 
 .. 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
+    wget -O - -o /dev/null https://bootstrap.pypa.io/get-pip.py | python3.6
+    pip3.6 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):
 

docs/languages.rst

@@ -33,6 +33,34 @@ Docker users
 
 Users of the Docker image may use the alternative :ref:`"polyglot" container <docker-polyglot>` which includes all languages.
 
+Adding individual language packs to a Docker image
+""""""""""""""""""""""""""""""""""""""""""""""""""
+
+If you wish to add a single language pack, you could do the following:
+
+* Download the desired ``.trainedata`` file from the `tessdata <https://github.com/tesseract-ocr/tessdata>`_ repository. Let's use Hebrew in this example (``heb.traineddata``)
+
+* Copy the file to ``/home/user/downloads/heb.traineddata``.
+
+* Create a new container based on the ocrmypdf-tess4 image and jump into it with a terminal:
+
+.. code-block:: bash
+
+	host$ docker run  -v /home/user/downloads:/home/docker -it --entrypoint /bin/bash ocrmypdf-tess4
+
+* Put the file where Tesseract expects it:
+
+.. code-block:: bash
+
+	docker$ cp /home/docker/heb.traineddata /usr/share/tesseract-ocr/tessdata
+
+* Note the container id, and save it as a new image (in this example, ``ocrmypdf-tess4-heb``)
+
+.. code-block:: bash
+
+    host$ docker commit <container_id> ocrmypdf-tess4-heb
+
+
 Known limitations
 -----------------
 

docs/release_notes.rst

@@ -5,6 +5,33 @@ OCRmyPDF uses `semantic versioning <http://semver.org/>`_ for its command line i
 
 The OCRmyPDF package itself does not contain a public API, although it is fairly stable and breaking changes are usually timed with a major release. A future release will clearly define the stable public API.
 
+v5.4.2
+------
+
+-   Fixed a regression from v5.4.1 that caused sidecar files to be created as empty files
+
+
+v5.4.1
+------
+
+-   Add workaround for Tesseract v4.00alpha crash when trying to obtain orientation and the latest language packs are installed
+
+
+v5.4
+----
+
+-   Change wording of a deprecation warning to improve clarity
+-   Added option to generate PDF/A-1b output if desired (``--output-type pdfa-1``); default remains PDF/A-2b generation
+-   Update documentation
+
+
+v5.3.3
+------
+
+-   Fixed missing error message that should occur when trying to force ``--pdf-renderer sandwich`` on old versions of Tesseract
+-   Update copyright information in test files
+-   Set system ``LANG`` to UTF-8 in Dockerfiles to avoid UTF-8 encoding errors
+
 
 v5.3.2
 ------
@@ -53,9 +80,9 @@ v5.0
 
 -   Backward incompatible changes
 
-    + Support for Python 3.4 dropped. Python 3.5 is now required.
-    + Support for Tesseract 3.02 and 3.03 dropped. Tesseract 3.04 or newer is required. Tesseract 4.00 (alpha) is supported.
-    + The OCRmyPDF.sh script was removed.
+     + Support for Python 3.4 dropped. Python 3.5 is now required.
+     + Support for Tesseract 3.02 and 3.03 dropped. Tesseract 3.04 or newer is required. Tesseract 4.00 (alpha) is supported.
+     + The OCRmyPDF.sh script was removed.
 
 -   Add a new feature, ``--sidecar``, which allows creating "sidecar" text files which contain the OCR results in plain text. These OCR text is more reliable than extracting text from PDFs. Closes #126.
 -   New feature: ``--pdfa-image-compression``, which allows overriding Ghostscript's lossy-or-lossless image encoding heuristic and making all images JPEG encoded or lossless encoded as desired. Fixes #163.
@@ -89,242 +116,242 @@ v4.5.4
 v4.5.3
 ------
 
--  Added a workaround for Ghostscript 9.21 and probably earlier versions would fail with the error message "VMerror -25", due to a Ghostscript bug in XMP metadata handling
--  High Unicode characters (U+10000 and up) are no longer accepted for setting metadata on the command line, as Ghostscript may not handle them correctly.
--  Fixed an issue where the ``tess4`` renderer would duplicate content onto output pages if tesseract failed or timed out
--  Fixed ``tess4`` renderer not recognized when lossless reconstruction is possible
+-   Added a workaround for Ghostscript 9.21 and probably earlier versions would fail with the error message "VMerror -25", due to a Ghostscript bug in XMP metadata handling
+-   High Unicode characters (U+10000 and up) are no longer accepted for setting metadata on the command line, as Ghostscript may not handle them correctly.
+-   Fixed an issue where the ``tess4`` renderer would duplicate content onto output pages if tesseract failed or timed out
+-   Fixed ``tess4`` renderer not recognized when lossless reconstruction is possible
 
 
 v4.5.2
 ------
 
--  Fix issue #147. ``--pdf-renderer tess4 --clean`` will produce an oversized page containing the original image in the bottom left corner, due to loss DPI information.
--  Make "using Tesseract 4.0" warning less ominous
--  Set up machinery for homebrew OCRmyPDF tap
+-   Fix issue #147. ``--pdf-renderer tess4 --clean`` will produce an oversized page containing the original image in the bottom left corner, due to loss DPI information.
+-   Make "using Tesseract 4.0" warning less ominous
+-   Set up machinery for homebrew OCRmyPDF tap
 
 
 v4.5.1
 ------
 
--  Fix issue #137, proportions of images with a non-square pixel aspect ratio would be distorted in output for ``--force-ocr`` and some other combinations of flags
+-   Fix issue #137, proportions of images with a non-square pixel aspect ratio would be distorted in output for ``--force-ocr`` and some other combinations of flags
 
 
 v4.5
 ----
 
--  Exotic PDFs containing "Form XObjects" are now supported (issue #134; PDF reference manual 8.10), and images they contain are taken into account when determining the resolution for rasterizing
--  The Tesseract 4 Docker image no longer includes all languages, because it took so long to build something would tend to fail
--  OCRmyPDF now warns about using ``--pdf-renderer tesseract`` with Tesseract 3.04 or lower due to issues with Ghostscript corrupting the OCR text in these cases
+-   Exotic PDFs containing "Form XObjects" are now supported (issue #134; PDF reference manual 8.10), and images they contain are taken into account when determining the resolution for rasterizing
+-   The Tesseract 4 Docker image no longer includes all languages, because it took so long to build something would tend to fail
+-   OCRmyPDF now warns about using ``--pdf-renderer tesseract`` with Tesseract 3.04 or lower due to issues with Ghostscript corrupting the OCR text in these cases
 
 
 v4.4.2
 ------
 
--  The Docker images (ocrmypdf, ocrmypdf-polyglot, ocrmypdf-tess4) are now based on Ubuntu 16.10 instead of Debian stretch
+-   The Docker images (ocrmypdf, ocrmypdf-polyglot, ocrmypdf-tess4) are now based on Ubuntu 16.10 instead of Debian stretch
 
-   + This makes supporting the Tesseract 4 image easier
-   + This could be a disruptive change for any Docker users who built customized these images with their own changes, and made those changes in a way that depends on Debian and not Ubuntu
+    + This makes supporting the Tesseract 4 image easier
+    + This could be a disruptive change for any Docker users who built customized these images with their own changes, and made those changes in a way that depends on Debian and not Ubuntu
 
--  OCRmyPDF now prevents running the Tesseract 4 renderer with Tesseract 3.04, which was permitted in v4.4 and v4.4.1 but will not work
+-   OCRmyPDF now prevents running the Tesseract 4 renderer with Tesseract 3.04, which was permitted in v4.4 and v4.4.1 but will not work
 
 
 v4.4.1
 ------
 
--  To prevent a `TIFF output error <https://github.com/python-pillow/Pillow/issues/2206>`_ caused by img2pdf >= 0.2.1 and Pillow <= 3.4.2, dependencies have been tightened
--  The Tesseract 4.00 simultaneous process limit was increased from 1 to 2, since it was observed that 1 lowers performance
--  Documentation improvements to describe the ``--tesseract-config`` feature 
--  Added test cases and fixed error handling for ``--tesseract-config``
--  Tweaks to setup.py to deal with issues in the v4.4 release
+-   To prevent a `TIFF output error <https://github.com/python-pillow/Pillow/issues/2206>`_ caused by img2pdf >= 0.2.1 and Pillow <= 3.4.2, dependencies have been tightened
+-   The Tesseract 4.00 simultaneous process limit was increased from 1 to 2, since it was observed that 1 lowers performance
+-   Documentation improvements to describe the ``--tesseract-config`` feature 
+-   Added test cases and fixed error handling for ``--tesseract-config``
+-   Tweaks to setup.py to deal with issues in the v4.4 release
 
 v4.4
 ----
 
--  Tesseract 4.00 is now supported on an experimental basis.
+-   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
+    +  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.
+-   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.
+    + 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.
+-   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
+-   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
+-   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)
+-   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
+-   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
+-   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
+    +  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
+-   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)
+-   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)
+-   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
+    +  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
+-   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
+-   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
+-   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)
+-   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)
+    +  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
+-   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
+    +  ``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
+-   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
+    +  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" 
+-   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
+    +  Some Ubuntu "PPAs" (backports) are needed to make it work
 
-   +  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)
+-   Support for some older dependencies dropped
 
--  Ghostscript now runs in "safer" mode where possible
+    +  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
+-   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)
+-   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
+-   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
+-   ``--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
+-   Minor correction to Ghostscript output settings
 
 
 v4.0.6
 ------
 
--  Update install instructions
--  Provide a sRGB profile instead of using Ghostscript's
+-   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
+-   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
 ------
@@ -338,16 +365,16 @@ v4.0.3
 New features
 ^^^^^^^^^^^^
 
--  Page orientations detected are now reported in a summary comment
+-   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
+-   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
@@ -356,10 +383,10 @@ 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
+-   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
@@ -368,7 +395,7 @@ v4.0.1
 Fixes
 ^^^^^
 
--  Fixed a KeyError if tesseract fails to find page orientation information
+-   Fixed a KeyError if tesseract fails to find page orientation information
 
 
 v4.0
@@ -377,33 +404,33 @@ 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.
+-   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)
+-   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.
+-   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
@@ -412,8 +439,8 @@ v3.2.1
 Changes
 ^^^^^^^
 
--  Fixed issue #47 "convert() got and unexpected keyword argument 'dpi'" by upgrading to img2pdf 0.2
--  Tweaked the Dockerfiles
+-   Fixed issue #47 "convert() got and unexpected keyword argument 'dpi'" by upgrading to img2pdf 0.2
+-   Tweaked the Dockerfiles
 
 
 v3.2
@@ -422,19 +449,19 @@ 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.
+-   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.
+-   JPEG transcoding quality is now 95 instead of the default 75. Bigger file sizes for less degradation.
 
 
 
@@ -444,7 +471,7 @@ v3.1.1
 Changes
 ^^^^^^^
 
--  Fixed bug that caused incorrect page size and DPI calculations on documents with mixed page sizes
+-   Fixed bug that caused incorrect page size and DPI calculations on documents with mixed page sizes
 
 v3.1
 ----
@@ -452,17 +479,17 @@ 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
+-   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
 ----
@@ -470,55 +497,55 @@ 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
+-   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
+-   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:
+-   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
+    - 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/
@@ -531,87 +558,87 @@ Changes
 Release candidates
 ^^^^^^^^^^^^^^^^^^
 
--  rc9:
+-   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
+    - 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:
+-   rc8:
 
-   - fix issue #111: exception thrown if PDF is missing DocumentInfo dictionary
+    - fix issue #111: exception thrown if PDF is missing DocumentInfo dictionary
 
--  rc7:
+-   rc7:
 
-   - fix error when installing direct from pip, "no such file 'requirements.txt'"
+    - fix error when installing direct from pip, "no such file 'requirements.txt'"
 
--  rc6:
+-   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
+    - 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:
+-   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
+    - 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:
+-   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 
+    - 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
+-   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
+-   ``./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:
+-   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
+    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
+    -l 
+    deu 
+    --author 
+    A. Merkel 
+    --pdf-renderer 
+    tesseract
 
 
 Fixes
 ^^^^^
 
--  Handling of filenames containing spaces: fixed
+-   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.
+-   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-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.
+-   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/__main__.py

@@ -1,29 +1,25 @@
 #!/usr/bin/env python3
 # © 2015-17 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, \
+from .pipeline import JobContext, JobContextManager, \
     cleanup_working_files, build_pipeline
 from .pdfa import file_claims_pdfa
 from .helpers import is_iterable_notstr, re_symlink, is_file_writable
@@ -134,12 +130,15 @@ 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',
+    '--output-type', choices=['pdfa', 'pdf', 'pdfa-1', 'pdfa-2'], 
+    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.")
+         "preserve file contents as much as possible. 'pdf-a1' creates a "
+         "PDF/A1-b file. 'pdf-a2' is equivalent to 'pdfa'."
+         )
 
 # Use null string '\0' as sentinel to indicate the user supplied no argument,
 # since that is the only invalid character for filepaths on all platforms
@@ -332,19 +331,29 @@ def check_options_output(options, log):
         else:
             options.pdf_renderer = 'hocr'
 
+    if options.pdf_renderer == 'sandwich' and not tesseract.has_textonly_pdf():
+        raise MissingDependencyError(
+            "The 'sandwich' renderer requires Tesseract 3.05.01 or newer; "
+            "or Tesseract 4.00 alpha newer than February 2017.")
+
     if options.pdf_renderer == 'tess4':
         log.warning("The 'tess4' PDF renderer has been renamed to 'sandwich'. "
                     "Please use --pdf-renderer=sandwich.")
         options.pdf_renderer = 'sandwich'
 
     if options.pdf_renderer == 'tesseract':
-        log.warning("The 'tesseract' PDF renderer is deprecated.")
         if tesseract.version() < '3.05' and options.output_type == 'pdfa':
             log.warning(
                 "For best results use --pdf-renderer=tesseract "
                 "--output-type=pdf to disable PDF/A generation via "
                 "Ghostscript, which is known to corrupt the OCR text of "
                 "some PDFs produced your version of Tesseract.")
+        elif tesseract.has_textonly_pdf():
+            log.warning(
+                "The argument --pdf-renderer=tesseract provides support for "
+                "versions of tesseract older than your version. For best "
+                "results omit this argument and let OCRmyPDF choose the "
+                "best available renderer.")
 
     if options.debug_rendering and options.pdf_renderer != 'hocr':
         log.info(
@@ -417,7 +426,7 @@ def check_options_ocr_behavior(options, log):
 def check_options_advanced(options, log):
     if tesseract.v4():
         log.info(
-            "Tesseract v4.x.alpha found. OCRmyPDF support is experimental.")
+            "Tesseract v4.x.alpha found.")
     if options.tesseract_oem and not tesseract.v4():
         log.warning(
             "--tesseract-oem requires Tesseract 4.x -- argument ignored")
@@ -435,9 +444,9 @@ def check_options_advanced(options, log):
 
 def check_options_metadata(options, log):
     import unicodedata
-    metadata = [options.title, options.author, options.keywords,
-                options.subject]
-    for s in (m for m in metadata if m):
+    docinfo = [options.title, options.author, options.keywords,
+               options.subject]
+    for s in (m for m in docinfo if m):
         for c in s:
             if unicodedata.category(c) == 'Co' or ord(c) >= 0x10000:
                 raise ValueError(
@@ -519,31 +528,31 @@ def cleanup_ruffus_error_message(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."""
+    exit_code = None
 
     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
+        exit_code = getattr(ExitCode, exit_code_name, 'other_error')        
     elif exc_name == 'ruffus.ruffus_exceptions.MissingInputFileError':
         log.error(cleanup_ruffus_error_message(exc_value))
-        return ExitCode.input_file
+        exit_code = 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
+            exit_code = ExitCode.input_file
     elif exc_name == 'builtins.KeyboardInterrupt':
         log.error("Interrupted by user")
-        return ExitCode.ctrl_c
+        exit_code = 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
+        exit_code = ExitCode.child_process_error
     elif exc_name == 'ocrmypdf.exceptions.PdfMergeFailedError':
         log.error(textwrap.dedent("""\
             Failed to merge PDF image layer with OCR layer
@@ -554,11 +563,11 @@ def do_ruffus_exception(ruffus_five_tuple, options, log):
             Try using
                 ocrmypdf --pdf-renderer tesseract  [..other args..]
             """))
-        return ExitCode.input_file
+        exit_code = 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
+        exit_code = exc_class.exit_code
     elif exc_name == 'PyPDF2.utils.PdfReadError' and \
             'not been decrypted' in exc_value:
         log.error(textwrap.dedent("""\
@@ -571,7 +580,10 @@ def do_ruffus_exception(ruffus_five_tuple, options, log):
             (Only algorithms "R = 1" and "R = 2" are supported.)
 
             """))
-        return ExitCode.encrypted_pdf
+        exit_code = ExitCode.encrypted_pdf
+
+    if exit_code is not None:
+        return exit_code
 
     if not options.verbose:
         log.error(exc_stack)
@@ -637,6 +649,20 @@ def check_closed_streams(options):
     return True
 
 
+def log_page_orientations(pdfinfo, _log):
+    direction = {0: 'n', 90: 'e',
+                180: 's', 270: 'w'}
+    orientations = []
+    for n, page in enumerate(pdfinfo):
+        angle = pdfinfo[n].rotation or 0
+        if angle != 0:
+            orientations.append('{0}{1}'.format(
+                n + 1,
+                direction.get(angle, '')))
+    if orientations:
+        _log.info('Page orientations detected: ' + ' '.join(orientations))
+
+
 def run_pipeline():
     options = parser.parse_args()
     options.verbose_abbreviated_path = 1
@@ -726,8 +752,7 @@ def run_pipeline():
             _log.error("Unexpected ruffus exception: " + str(e))
             _log.error(repr(e))
             return ExitCode.other_error
-        else:
-            return exitcode
+        return exitcode
     except ExitCodeException as e:
         return e.exit_code
     except Exception as e:
@@ -737,7 +762,7 @@ def run_pipeline():
     if options.flowchart:
         _log.info("Flowchart saved to {}".format(options.flowchart))
     elif options.output_file != '-':
-        if options.output_type == 'pdfa':
+        if options.output_type.startswith('pdfa'):
             pdfa_info = file_claims_pdfa(options.output_file)
             if pdfa_info['pass']:
                 msg = 'Output file is a {} (as expected)'
@@ -745,7 +770,6 @@ def run_pipeline():
             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')
@@ -757,17 +781,8 @@ def run_pipeline():
     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].rotation or 0
-        if angle != 0:
-            orientations.append('{0}{1}'.format(
-                n + 1,
-                direction.get(angle, '')))
-    if orientations:
-        _log.info('Page orientations detected: ' + ' '.join(orientations))
+
+    log_page_orientations(pdfinfo, _log)
 
     return ExitCode.ok
 

ocrmypdf/exceptions.py

@@ -20,7 +20,7 @@ class ExitCode(IntEnum):
 
 
 class ExitCodeException(Exception):
-    pass
+    exit_code = ExitCode.other_error
 
 
 class PdfMergeFailedError(ExitCodeException):

ocrmypdf/exec/__init__.py

@@ -7,5 +7,6 @@ import os
 
 
 def get_program(name):
+    "Check environment variables for overrides to this program"
     envvar = 'OCRMYPDF_' + name.upper()
     return os.environ.get(envvar, name)

ocrmypdf/exec/ghostscript.py

@@ -1,5 +1,5 @@
 #!/usr/bin/env python3
-# © 2015 James R. Barlow: github.com/jbarlow83
+# © 2017 James R. Barlow: github.com/jbarlow83
 
 from tempfile import NamedTemporaryFile
 from subprocess import run, PIPE, STDOUT, CalledProcessError
@@ -7,9 +7,9 @@ from shutil import copy
 from functools import lru_cache
 import re
 import sys
-from . import get_program
-from ..exceptions import SubprocessOutputError
 from PIL import Image
+from . import get_program
+from ..exceptions import SubprocessOutputError, MissingDependencyError
 from ..helpers import fspath
 
 
@@ -20,15 +20,16 @@ def version():
         '--version'
     ]
     try:
-        version = check_output(
+        proc = run(
                 args_gs, close_fds=True, universal_newlines=True,
-                stderr=STDOUT)
+                stdout=PIPE, stderr=STDOUT, check=True)
+        ver = proc.stdout
     except CalledProcessError as e:
         print("Could not find Ghostscript executable on system PATH.",
               file=sys.stderr)
         raise MissingDependencyError from e
 
-    return version.strip()
+    return ver.strip()
 
 
 def _gs_error_reported(stream):
@@ -103,7 +104,7 @@ def rasterize_pdf(input_file, output_file, xres, yres, raster_device, log,
 
 
 def generate_pdfa(pdf_pages, output_file, compression, log,
-                  threads=1, pdf_version='1.5'):
+                  threads=1, pdf_version='1.5', pdfa_part='2'):
     compression_args = []
     if compression == 'jpeg':
         compression_args = [
@@ -139,7 +140,7 @@ def generate_pdfa(pdf_pages, output_file, compression, log,
             "-sProcessColorModel=DeviceRGB"
         ] + compression_args + [
             "-dJPEGQ=95",
-            "-dPDFA=2",
+            "-dPDFA=" + pdfa_part,
             "-dPDFACompatibilityPolicy=1",
             "-sOutputFile=" + gs_pdf.name,
         ]
@@ -166,4 +167,4 @@ def generate_pdfa(pdf_pages, output_file, compression, log,
             copy(gs_pdf.name, output_file)
         else:
             log.error('Ghostscript PDF/A rendering failed')
-            raise SubprocessOutputError()
+            raise SubprocessOutputError()

ocrmypdf/exec/qpdf.py

@@ -1,5 +1,5 @@
 #!/usr/bin/env python3
-# © 2015 James R. Barlow: github.com/jbarlow83
+# © 2017 James R. Barlow: github.com/jbarlow83
 
 from subprocess import CalledProcessError, STDOUT, PIPE, run, check_output
 from functools import lru_cache
@@ -134,4 +134,4 @@ def merge(input_files, output_file, min_version=None):
         input_files[0], '--pages'
     ] + input_files + ['--', output_file]
     run(args_qpdf, check=True)
-
+    

ocrmypdf/exec/tesseract.py

@@ -1,21 +1,20 @@
 #!/usr/bin/env python3
-# © 2015 James R. Barlow: github.com/jbarlow83
+# © 2017 James R. Barlow: github.com/jbarlow83
 
 import sys
 import os
 import re
 import shutil
 from functools import lru_cache
-from ..exceptions import MissingDependencyError, TesseractConfigError
-from ..helpers import page_number
-from . import get_program
 from collections import namedtuple
 from textwrap import dedent
 import PyPDF2 as pypdf
+from subprocess import PIPE, CalledProcessError, \
+    TimeoutExpired, check_output, STDOUT
 
-from subprocess import Popen, PIPE, CalledProcessError, \
-    TimeoutExpired, check_output, STDOUT, DEVNULL
-
+from ..exceptions import MissingDependencyError, TesseractConfigError
+from ..helpers import page_number
+from . import get_program
 
 OrientationConfidence = namedtuple(
     'OrientationConfidence',
@@ -60,7 +59,7 @@ def version():
 
 def v4():
     "Is this Tesseract v4.0?"
-    return (version() >= '4')
+    return version() >= '4'
 
 
 @lru_cache(maxsize=1)
@@ -74,6 +73,7 @@ def has_textonly_pdf():
         get_program('tesseract'),
         '--print-parameters'
     ]
+    params = ''
     try:
         params = check_output(
                 args_tess, close_fds=True, universal_newlines=True,
@@ -113,12 +113,12 @@ def languages():
     return set(lang.strip() for lang in langs.splitlines()[1:])
 
 
-def tess_base_args(languages, engine_mode):
+def tess_base_args(langs, engine_mode):
     args = [
         get_program('tesseract'),
     ]
-    if languages:
-        args.extend(['-l', '+'.join(languages)])
+    if langs:
+        args.extend(['-l', '+'.join(langs)])
     if engine_mode is not None and v4():
         args.extend(['--oem', str(engine_mode)])
     return args
@@ -126,7 +126,7 @@ def tess_base_args(languages, engine_mode):
 
 def get_orientation(input_file, language: list, engine_mode, timeout: float,
                     log):
-    args_tesseract = tess_base_args(language, engine_mode) + [
+    args_tesseract = tess_base_args(['osd'], engine_mode) + [
         psm(), '0',
         input_file,
         'stdout'

ocrmypdf/exec/unpaper.py

@@ -3,7 +3,7 @@
 # unpaper documentation:
 # https://github.com/Flameeyes/unpaper/blob/master/doc/basic-concepts.md
 
-from subprocess import CalledProcessError, STDOUT, check_output, check_call
+from subprocess import CalledProcessError, STDOUT, check_output
 from tempfile import NamedTemporaryFile
 import sys
 import os
@@ -18,10 +18,10 @@ def version():
         get_program('unpaper'),
         '--version'
     ]
-    version = check_output(
+    ver = check_output(
         args_unpaper, close_fds=True, universal_newlines=True,
         stderr=STDOUT, timeout=5)
-    return version.strip()
+    return ver.strip()
 
 
 try:

ocrmypdf/lib/compile_leptonica.py

@@ -183,10 +183,39 @@ pixColorMagnitude(PIX     *pixs,
                   l_int32  bwhite,
                   l_int32  type);
 
-void
+PIX *
+pixMaskOverColorPixels(PIX     *pixs,
+                       l_int32  threshdiff,
+                       l_int32  mindist);
+
+l_int32
+pixGetAverageMaskedRGB(PIX        *pixs,
+                       PIX        *pixm,
+                       l_int32     x,
+                       l_int32     y,
+                       l_int32     factor,
+                       l_int32     type,
+                       l_float32  *prval,
+                       l_float32  *pgval,
+                       l_float32  *pbval);
+
+PIX * 
+pixGlobalNormRGB(PIX * 	pixd,
+                 PIX * 	pixs,
+                 l_int32 	rval,
+                 l_int32 	gval,
+                 l_int32 	bval,
+                 l_int32 	mapval); 
+
+PIX *
+pixInvert(PIX * pixd,
+          PIX * pixs);
+
+void                 
 boxDestroy(BOX  **pbox);
 
-void lept_free(void *ptr);
+void
+lept_free(void *ptr);  
 """)
 
 

ocrmypdf/pipeline.py

@@ -2,19 +2,10 @@
 # © 2016 James R. Barlow: github.com/jbarlow83
 
 from contextlib import suppress
-from tempfile import mkdtemp
-from functools import partial
 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
@@ -23,7 +14,7 @@ from ruffus import formatter, regex, Pipeline, suffix
 
 from .hocrtransform import HocrTransform
 from .pdfinfo import PdfInfo, Encoding, Colorspace
-from .pdfa import generate_pdfa_ps, file_claims_pdfa
+from .pdfa import generate_pdfa_ps
 from .helpers import re_symlink, is_iterable_notstr, page_number
 from .exec import ghostscript, tesseract, qpdf
 from .exceptions import *
@@ -51,6 +42,8 @@ class JobContext:
 
     def __init__(self):
         self.pdfinfo = None
+        self.options = None
+        self.work_folder = None
 
     def generate_pdfinfo(self, infile):
         self.pdfinfo = PdfInfo(infile)
@@ -189,7 +182,8 @@ def repair_pdf(
     pdfinfo = PdfInfo(output_file)
 
     if pdfinfo.has_userunit and options.output_type == 'pdfa':
-        log.error("This input file uses a PDF feature that is not supported "
+        log.error(
+            "This input file uses a PDF feature that is not supported "
             "by Ghostscript, so you cannot use --output-type=pdfa for this "
             "file. (Specifically, it uses the PDF-1.6 /UserUnit feature to "
             "support very large or small page sizes, and Ghostscript cannot "
@@ -706,7 +700,7 @@ def combine_layers(
 
     if rotation != 0:
         log.info("{0:4d}: rotating image layer {1} degrees".format(
-            page_number(image), rotation, tx, ty))
+            page_number(image), rotation))
 
     try:
         page_text.mergeRotatedScaledTranslatedPage(
@@ -826,9 +820,9 @@ def get_pdfmark(base_pdf, options):
         renderer_tag = 'OCR'
 
     pdfmark['/Creator'] = '{0} {1} / Tesseract {2} {3}'.format(
-            PROGRAM_NAME, VERSION,
-            renderer_tag,
-            tesseract.version())
+        PROGRAM_NAME, VERSION,
+        renderer_tag,
+        tesseract.version())
     return pdfmark
 
 
@@ -885,7 +879,8 @@ def merge_pages_ghostscript(
         output_file=output_file,
         compression=options.pdfa_image_compression,
         log=log,
-        threads=options.jobs or 1)
+        threads=options.jobs or 1,
+        pdfa_part=('1' if options.output_type == 'pdfa-1' else '2'))
 
 
 def merge_pages_qpdf(
@@ -936,7 +931,6 @@ def merge_sidecars(
         output_file,
         log,
         context):
-    options = context.get_options()
     pdfinfo = context.get_pdfinfo()
 
     txt_files = [None] * len(pdfinfo)
@@ -947,21 +941,30 @@ def merge_sidecars(
             txt_files[idx] = infile
 
     def write_pages(stream):
-        for page_number, txt_file in enumerate(txt_files):
-            if page_number != 0:
+        for page_num, txt_file in enumerate(txt_files):
+            if page_num != 0:
                 stream.write('\f')  # Form feed between pages
             if txt_file:
-                with open(txt_file, 'r') as in_:
-                    stream.write(in_.read())
+                with open(txt_file, 'r', encoding="utf-8") as in_:
+                    txt = in_.read()
+                    # Tesseract v4 alpha started adding form feeds in 
+                    # commit aa6eb6b
+                    # No obvious way to detect what binaries will do this, so
+                    # for consistency just ignore its form feeds and insert our
+                    # own
+                    if txt.endswith('\f'):
+                        stream.write(txt[:-1])
+                    else:
+                        stream.write(txt)
             else:
                 stream.write('[OCR skipped on page {}]'.format(
-                        page_number + 1))
+                        page_num + 1))
 
     if output_file == '-':
         write_pages(sys.stdout)
         sys.stdout.flush()
     else:
-        with open(output_file, 'w', encoding='utf-8') as out:
+        with open(output_file, 'w', encoding="utf-8") as out:
             write_pages(out)
 
 
@@ -1139,7 +1142,8 @@ def build_pipeline(options, work_folder, log, context):
         output=os.path.join(work_folder, r'\1.rendered.pdf'),
         extras=[log, context])
     task_combine_layers.graphviz(fillcolor='"#00cc66"')
-    task_combine_layers.active_if(options.pdf_renderer == 'hocr' or options.pdf_renderer == 'sandwich')
+    task_combine_layers.active_if(options.pdf_renderer == 'hocr' or 
+                                  options.pdf_renderer == 'sandwich')
 
     # Tesseract OCR+PDF
     task_ocr_tesseract_and_render_pdf = main_pipeline.collate(
@@ -1161,7 +1165,7 @@ def build_pipeline(options, work_folder, log, context):
         filter=formatter(r'\.repaired\.pdf'),
         output=os.path.join(work_folder, 'pdfa.ps'),
         extras=[log, context])
-    task_generate_postscript_stub.active_if(options.output_type == 'pdfa')
+    task_generate_postscript_stub.active_if(options.output_type.startswith('pdfa'))
 
 
     # Bypass valve
@@ -1183,7 +1187,7 @@ def build_pipeline(options, work_folder, log, context):
                task_generate_postscript_stub],
         output=os.path.join(work_folder, 'merged.pdf'),
         extras=[log, context])
-    task_merge_pages_ghostscript.active_if(options.output_type == 'pdfa')
+    task_merge_pages_ghostscript.active_if(options.output_type.startswith('pdfa'))
 
     task_merge_pages_qpdf = main_pipeline.merge(
         task_func=merge_pages_qpdf,

tests/resources/README.rst

@@ -57,7 +57,7 @@ under the terms of the license in LICENSE.rst.
         - test image with 200 x 100 DPI resolution
     *   - blank.pdf
         - @jbarlow83
-        - blank PDF
+        - blank PDF generated by Adobe Illustrator CC 17, containing a lot of application-specific metadata/bloat
     *   - cmyk.pdf
         - @jbarlow83
         - a CMYK image created in Photoshop
@@ -88,14 +88,18 @@ under the terms of the license in LICENSE.rst.
     *   - overlay.pdf
         - @maxandersen
         - PDF file generated by PDFPen pro that triggered content stream parse errors
-    *   - no_conentes.pdf
+    *   - no_contents.pdf
         - @jbarlow83
         - synthetic PDF with a blank page that has no /Contents entry
+    *   - crom.png
+        - @jbarlow83
+        - test for non-dictionary words
+
 
 Assemblies
 ==========
 
-These test resources are assemblies from other previously mentioned files, released under the same license terms as their input files.
+These test resources are assemblies or derivatives 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)
@@ -107,6 +111,9 @@ These test resources are assemblies from other previously mentioned files, relea
 - 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)
+- baiona_gray.png (from baiona.png)
+- poster.pdf (from LinnSequencer.jpg)
+
 
 
 .. _`Wikimedia: LinnSequencer`: https://upload.wikimedia.org/wikipedia/en/b/b7/LinnSequencer_hardware_MIDI_sequencer_brochure_page_2_300dpi.jpg

tests/spoof/tesseract_big_image_error.py

@@ -4,9 +4,9 @@
 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
+VERSION_STRING = '''tesseract 3.05.01
+ leptonica-1.74.4
+  libjpeg 9b : libpng 1.6.32 : libtiff 4.0.8 : zlib 1.2.8
 SPOOFED: return error claiming image too big
 '''
 
@@ -20,10 +20,10 @@ def main():
         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)
+        print('List of available languages (1):\neng\n', file=sys.stderr)
         sys.exit(0)
     elif sys.argv[1] == '--print-parameters':
-        print('A parameter list would go here', file=sys.stderr)
+        print('A parameter list would go here\ntextonly_pdf 0\n', file=sys.stderr)
         sys.exit(0)
     elif sys.argv[-2] == 'hocr':
         print("Image too large: (33830, 14959)\n"

tests/spoof/tesseract_crash.py

@@ -5,9 +5,9 @@ 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
+VERSION_STRING = '''tesseract 3.05.01
+ leptonica-1.74.4
+  libjpeg 9b : libpng 1.6.32 : libtiff 4.0.8 : zlib 1.2.8
 SPOOFED: CRASH ON OCR or -psm 0
 '''
 
@@ -30,7 +30,8 @@ def main():
         print('List of available languages (1):\neng', file=sys.stderr)
         sys.exit(0)
     elif sys.argv[1] == '--print-parameters':
-        print('List of parameters would go here', file=sys.stderr)
+        print('A parameter list would go here\ntextonly_pdf 0\n',
+              file=sys.stderr)
         sys.exit(0)
     elif sys.argv[-2] == 'hocr':
         print("KABOOM! Tesseract failed for some reason", file=sys.stderr)

tests/test_main.py

@@ -404,9 +404,13 @@ def test_force_ocr_on_pdf_with_no_images(spoof_tesseract_crash, resources,
 @pytest.mark.skipif(
     pytest.helpers.is_macos() and pytest.helpers.running_in_travis(),
     reason="takes too long to install language packs in Travis macOS homebrew")
-def test_french(spoof_tesseract_cache, resources, outpdf):
+def test_french(spoof_tesseract_cache, resources, outdir):
+    # Produce a sidecar too - implicit test that system locale is set up
+    # properly
+    sidecar = outdir / 'francais.txt'
     p, out, err = run_ocrmypdf(
-        resources / 'francais.pdf', outpdf, '-l', 'fra',
+        resources / 'francais.pdf', outdir / 'francais.pdf', '-l', 'fra',
+        '--sidecar', sidecar,
         env=spoof_tesseract_cache)
     print(os.environ)
     assert p.returncode == ExitCode.ok, \
@@ -801,7 +805,6 @@ def test_user_words(resources, outdir):
             '--image-dpi', 150,
             '--sidecar', sidecar_before
         )
-
         assert 'cromulent' not in sidecar_before.open().read()
 
     with word_list.open('w') as f:
@@ -978,3 +981,27 @@ def test_sidecar_pagecount(spoof_tesseract_cache, resources, outpdf):
     # formfeeds is the page count less one
     assert ocr_text.count('\f') == num_pages - 1, \
         "Sidecar page count does not match PDF page count"
+
+
+def test_sidecar_nonempty(spoof_tesseract_cache, resources, outpdf):
+    sidecar = outpdf + '.txt'
+    check_ocrmypdf(
+        resources / 'ccitt.pdf', outpdf,
+        '--sidecar', sidecar,
+        env=spoof_tesseract_cache
+    )
+
+    with open(sidecar, 'r') as f:
+        ocr_text = f.read()
+    assert 'the' in ocr_text
+
+
+def test_pdfa_1(spoof_tesseract_cache, resources, outpdf):
+    check_ocrmypdf(
+        resources / 'ccitt.pdf', outpdf,
+        '--output-type', 'pdfa-1',
+        env=spoof_tesseract_cache
+    )
+
+    pdfa_info = file_claims_pdfa(outpdf)
+    assert pdfa_info['conformance'] == 'PDF/A-1B'