v5.6.1 notes

Did not account for API difference in pathlib

.docker/Dockerfile

@@ -1,7 +1,6 @@
 # OCRmyPDF
 #
-FROM      ubuntu:17.04
-MAINTAINER James R. Barlow <jim@purplerock.ca>
+FROM      ubuntu:17.10
 
 RUN apt-get update && apt-get install -y --no-install-recommends \
   software-properties-common python-software-properties \
@@ -52,4 +51,4 @@ WORKDIR /home/docker
 
 # Must use array form of ENTRYPOINT
 # Non-array form does not append other arguments, because that is "intuitive"
-ENTRYPOINT ["/application/docker-wrapper.sh"]
+ENTRYPOINT ["/application/.docker/docker-wrapper.sh"]

.docker/Dockerfile.polyglot

@@ -14,4 +14,4 @@ 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"]
+ENTRYPOINT ["/application/.docker/docker-wrapper.sh"]

.docker/Dockerfile.tess4

@@ -1,7 +1,6 @@
 # OCRmyPDF
 #
-FROM 	ubuntu:17.04
-MAINTAINER James R. Barlow <jim@purplerock.ca>
+FROM 	ubuntu:17.10
 
 RUN apt-get update && apt-get install -y --no-install-recommends \
   software-properties-common python-software-properties \
@@ -62,4 +61,4 @@ WORKDIR /home/docker
 
 # Must use array form of ENTRYPOINT
 # Non-array form does not append other arguments, because that is "intuitive"
-ENTRYPOINT ["/application/docker-wrapper.sh"]
+ENTRYPOINT ["/application/.docker/docker-wrapper.sh"]

.dockerignore

@@ -3,18 +3,9 @@
 *.pyc
 *.rst
 *.sublime*
-*/*.pyc
-*/*/*.pyc
-*/*/*/*.pyc
-*/*/*/*/*.pyc
-*/*/*/*/*/*.pyc
-*/*/*/*/*/*/*.pyc
-*/*/*/*/*/*/*/*.pyc
-.cache/
-.eggs/
-.github/
-.git/
-.ipynb_checkpoints/
+**/*.pyc
+.*/
+!.docker/
 .ruffus_history.sqlite
 bin/
 build/

.travis.yml

@@ -34,7 +34,9 @@ before_install: |
   if [[ "$TRAVIS_OS_NAME" == "linux" ]]; then
     bash .travis/linux_before_install.sh
   elif [[ "$TRAVIS_OS_NAME" == "osx" ]]; then
-    bash .travis/osx_before_install.sh
+    brew update && brew bundle --file=.travis/Brewfile
+    pip3 install --upgrade pip
+    pip3 install wheel
   fi
 
 install:

.travis/Brewfile

@@ -0,0 +1,12 @@
+brew 'python'
+
+brew 'ghostscript'
+brew 'jbig2dec'
+brew 'leptonica'
+brew 'libffi'
+brew 'libtiff'
+brew 'libxml2'
+brew 'openjpeg'
+brew 'qpdf'
+brew 'tesseract'
+brew 'unpaper'

.travis/autobrew.py

@@ -1,5 +1,5 @@
 #!/usr/bin/env python3
-# © 2016 James R. Barlow: github.com/jbarlow83
+# © 2017-18 James R. Barlow: github.com/jbarlow83
 
 from string import Template
 from subprocess import run, PIPE
@@ -14,43 +14,50 @@ class Ocrmypdf < Formula
   ${ocrmypdf_url}
   ${ocrmypdf_sha256}
 
-  depends_on :python3
-  depends_on :x11  # Pillow needs XQuartz
   depends_on "pkg-config" => :build
-  depends_on "libffi"
-  depends_on "tesseract"
-  depends_on "ghostscript"
-  depends_on "unpaper"
-  depends_on "qpdf"
-
-  # mactex installs its own ghostscript by default which causes problems
-  # mactex users should use caskroom/cask/mactex-no-ghostscript instead
-  conflicts_with cask: "caskroom/cask/mactex"
-
-  # For Pillow source install
-  depends_on "openjpeg"
   depends_on "freetype"
+  depends_on "ghostscript"
+  depends_on "jpeg"
   depends_on "libpng"
-  depends_on "libjpeg"
-  depends_on "webp"
-  depends_on "little-cms2"
-  depends_on "zlib"
+  depends_on "python"
+  depends_on "qpdf"
+  depends_on "tesseract"
+  depends_on "unpaper"
 
 ${resources}
   def install
-    ENV.append ["SETUPTOOLS_SCM_PRETEND_VERSION"], "v${ocrmypdf_version}"
-    ENV.each do |key, value|
-      puts "#{key}:#{value}"
+    venv = virtualenv_create(libexec, "python3")
+
+    resource("Pillow").stage do
+      inreplace "setup.py" do |s|
+        sdkprefix = MacOS::CLT.installed? ? "" : MacOS.sdk_path
+        s.gsub! "openjpeg.h", "probably_not_a_header_called_this_eh.h"
+        s.gsub! "ZLIB_ROOT = None", "ZLIB_ROOT = ('#{sdkprefix}/usr/lib', '#{sdkprefix}/usr/include')"
+        s.gsub! "JPEG_ROOT = None", "JPEG_ROOT = ('#{Formula["jpeg"].opt_prefix}/lib', '#{Formula["jpeg"].opt_prefix}/include')"
+        s.gsub! "FREETYPE_ROOT = None", "FREETYPE_ROOT = ('#{Formula["freetype"].opt_prefix}/lib', '#{Formula["freetype"].opt_prefix}/include')"
+      end
+
+      # avoid triggering "helpful" distutils code that doesn't recognize Xcode 7 .tbd stubs
+      ENV.append "CFLAGS", "-I#{MacOS.sdk_path}/System/Library/Frameworks/Tk.framework/Versions/8.5/Headers" unless MacOS::CLT.installed?
+      venv.pip_install Pathname.pwd
     end
-    virtualenv_install_with_resources
+
+    res = resources.map(&:name).to_set - ["Pillow"]
+
+    res.each do |r|
+      venv.pip_install resource(r)
+    end
+
+    venv.pip_install_and_link buildpath
   end
 
   test do
-    # `test do` will create, run in and delete a temporary directory.
-    #
-    # The installed folder is not in the path, so use the entire path to any
-    # executables being tested: `system "#{bin}/program", "do", "something"`.
-    system "#{bin}/ocrmypdf", "--version"
+    # Since we use Python 3, we require a UTF-8 locale
+    ENV["LC_ALL"] = "en_US.UTF-8"
+
+    system "#{bin}/ocrmypdf", "-f", "-q", "--deskew",
+                              test_fixtures("test.pdf"), "ocr.pdf"
+    assert_predicate testpath/"ocr.pdf", :exist?
   end
 end
 """)

.travis/osx_before_install.sh

@@ -1,17 +0,0 @@
-#!/bin/bash
-# © 2017 James R. Barlow: github.com/jbarlow83
-set -euo pipefail
-set -x
-
-brew update
-
-brew install openjpeg jbig2dec libtiff     # image libraries
-brew install qpdf
-brew install ghostscript
-brew install python3
-brew install libxml2 libffi leptonica
-brew install unpaper   # optional
-brew install tesseract
-
-pip3 install --upgrade pip
-pip3 install wheel

README.rst

@@ -74,11 +74,10 @@ Users of Debian 9 or later or Ubuntu 16.10 or later may simply
 
    apt-get install ocrmypdf
 
-and macOS users may simply
+and macOS users with Homebrew may simply
 
 .. code-block:: bash
 
-   brew tap jbarlow83/ocrmypdf
    brew install ocrmypdf
 
 For everyone else, `see our documentation <https://ocrmypdf.readthedocs.io/en/latest/installation.html>`_ for installation steps.

docs/cookbook.rst

@@ -157,6 +157,29 @@ If you set ``--tesseract-timeout 0`` OCRmyPDF will apply its image processing wi
     ocrmypdf --tesseract-timeout=0 --remove-background input.pdf output.pdf
 
 
+Redo OCR
+""""""""
+
+To redo OCR on a file OCRed with other OCR software or a previous version of OCRmyPDF and/or Tesseract, you may use the ``--force-ocr`` argument. Normally, OCRmyPDF does not modify files that already appear to contain OCR text.
+
+.. code-block:: bash
+
+    ocrmypdf --force-ocr input.pdf output.pdf
+
+Note that the method above will force rasterization of all pages, potentially reducing quality or losing vector content. 
+
+To ensure quality is preserved, one could extract all of the images and rebuild the PDF for a lossless transformation. This recipe does not work when PDFs contain multiple images per page, as many do in practice. It will also lose any page rotation information.
+
+.. code-block:: bash
+
+    pdfimages -all old-ocr.pdf prefix  # extract all images
+    img2pdf -o temp.pdf prefix*        # construct new PDF from the images
+    # review the new PDF to ensure it visually matches the old one
+    ocrmypdf --output-type pdf temp.pdf new-ocr.pdf
+
+``--output-type pdf`` is used here to avoid using Ghostscript which will also rasterize images.
+
+
 Improving OCR quality
 ---------------------
 

docs/index.rst

@@ -9,7 +9,7 @@ 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.
+PDF is the best format for storing and exchanging scanned documents.  Unfortunately, PDFs can be difficult to modify. OCRmyPDF makes it easy to apply image processing and OCR to existing PDFs.
 
 .. toctree::
    :maxdepth: 1

docs/installation.rst

@@ -15,18 +15,20 @@ Users of Debian 9 ("stretch") or later or Ubuntu 16.10 or later may simply
 Installing on macOS
 -------------------
 
-A `Homebrew <https://brew.sh>`_ tap is available for macOS:
+OCRmyPDF is now a standard `Homebrew <https://brew.sh>`_ formula. To install on macOS:
 
 .. code-block:: bash
 
-    brew tap jbarlow83/ocrmypdf
     brew install ocrmypdf
 
-
-.. warning::
+.. note::
 
     Users who previously installed OCRmyPDF on macOS using ``pip install ocrmypdf`` should remove the pip version (``pip3 uninstall ocrmypdf``) before switching to the Homebrew version.
 
+.. note::
+
+    Users who previously installed OCRmyPDF from the private tap should switch to the mainline version (``brew untap jbarlow83/ocrmypdf``) and install from there.
+
 .. _Docker-install:
 
 Installing the Docker image
@@ -285,6 +287,8 @@ Now we need to install ``pip`` and let it install ocrmypdf:
     wget -O - -o /dev/null https://bootstrap.pypa.io/get-pip.py | python3.6
     pip3.6 install ocrmypdf
 
+The ``wget`` command will download a program and run it.
+
 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

docs/introduction.rst

@@ -16,7 +16,7 @@ OCRmyPDF uses `Tesseract <https://github.com/tesseract-ocr/tesseract>`_, the bes
 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.
+PDFs are page description files that attempts to preserve a layout exactly. They  contain `vector graphics <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
 
@@ -42,15 +42,13 @@ PDF/A has a few drawbacks.  Some PDF viewers include an alert that the file is 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.
+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 to create an OCR "layer". The layer is then grafted back onto the original PDF.
 
-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.
+While one can use a program like Ghostscript or ImageMagick to get an image and put the image through Tesseract, that actually creates a new PDF and many details may be lost. OCRmyPDF can produce a minimally changed PDF as output.
 
-Alternately, OCRmyPDF can use the Tesseract OCR engine to directly output PDFs for each page, then merge them.
+OCRmyPDF also some image processing options like deskew which improve the appearance of files and quality of OCR. When these are used, the OCR layer is grafted onto the processed image instead.
 
-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.
+By default, OCRmyPDF produces archival PDFs – PDF/A, which are a stricter subset of PDF features designed for long term archives. If regular PDFs are desired, this can be disabled with ``--output-type pdf``.
 
 
 Why you shouldn't do this manually

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.
 
+v5.6.1
+------
+
+-   Fix issue #219: change how the final output file is created to avoid triggering permission errors when the output is a special file such as ``/dev/null``
+-   Fix test suite failures due to a qpdf 8.0.0 regression and Python 3.5's handling of symlink
+-   The "encrypted PDF" error message was different depending on the type of PDF encryption. Now a single clear message appears for all types of PDF encryption.
+-   ocrmypdf is now in Homebrew. Homebrew users are advised to the version of ocrmypdf in the official homebrew-core formulas rather than the private tap.
+-   Some linting
+
+
+v5.6.0
+------
+
+-   Fix issue #216: preserve "text as curves" PDFs without rasterizing file
+-   Related to the above, messages about rasterizing are more consistent
+-   For consistency versions minor releases will now get the trailing .0 they always should have had.
+
+
+v5.5
+----
+
+-   Add new argument ``--max-image-mpixels``. Pillow 5.0 now raises an exception when images may be decompression bombs. This argument can be used to override the limit Pillow sets.
+-   Fix output page cropped when using the sandwich renderer and OCR is skipped on a rotated and image-processed page
+-   A warning is now issued when old versions of Ghostscript are used in cases known to cause issues with non-Latin characters
+-   Fix a few parameter validation checks for ``-output-type pdfa-1`` and ``pdfa-2`` 
+
+
 v5.4.4
 ------
 

docs/security.rst

@@ -30,14 +30,16 @@ Depending on the options specified, OCRmyPDF may graft the OCR layer into the ex
 Using OCRmyPDF online or as a service
 -------------------------------------
 
-OCRmyPDF should not be deployed as a public-facing service, like a website where a potential attacker could upload a PDF of their choice for OCR. OCRmyPDF is not designed to be secure against PDF malware. Another concern is PDFs specifically designed to be a denial of service attack: PDFs can contain recursive data structures that sometimes send parsers into infinite loops, and issue complex graphics drawing commands.
+OCRmyPDF should not be deployed as a public-facing service, such as a website where a potential attacker could upload a PDF of their choice for OCR. OCRmyPDF is not designed to be secure against PDF malware. Another concern is PDFs specifically designed to be a denial of service attack: PDFs can contain recursive data structures that sometimes send parsers into infinite loops, and issue complex graphics drawing commands.
+
+Setting aside these concerns, a side effect of OCRmyPDF is it may incidentally sanitize PDFs that contain malware. It runs ``qpdf`` to repair the PDF, which could correct malformed PDF structures that are part of an attack. When PDF/A output is selected (the default), the input PDF is partially reconstructed by Ghostscript. When ``--force-ocr`` is used, all pages are rasterized and reconverted to PDF, which could remove malware in embedded images. No guarantees.
 
 OCRmyPDF should be relatively safe to use in a trusted intranet, with some considerations:
 
 Limiting CPU usage
 ^^^^^^^^^^^^^^^^^^
 
-OCRmyPDF will attempt to use all available CPUs and storage, so executing ``nice ocrmypdf`` or limiting the number of jobs with the ``-j`` argument may ensure the server remains available. Another option would be run OCRmyPDF jobs inside a Docker container or virtual machine, which can impose its own limits on CPU usage.
+OCRmyPDF will attempt to use all available CPUs and storage, so executing ``nice ocrmypdf`` or limiting the number of jobs with the ``-j`` argument may ensure the server remains available. Another option would be run OCRmyPDF jobs inside a Docker container, a virtual machine, or a cloud instance, which can impose its own limits on CPU usage and be terminated "from orbit" if it fails to complete.
 
 Temporary storage requirements
 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
@@ -46,7 +48,7 @@ OCRmyPDF will use a large amount of temporary storage for its work, proportional
 
 To check temporary storage usage on actual files, run ``ocrmypdf -k ...`` which will preserve and print the path to temporary storage when the job is done.
 
-To change where temporary files are stored, change the ``TMPDIR`` environment variable for ocrmypdf's environment. (Python's ``tempfile.gettempdir()`` returns the root directory in which temporary files will be stored.)
+To change where temporary files are stored, change the ``TMPDIR`` environment variable for ocrmypdf's environment. (Python's ``tempfile.gettempdir()`` returns the root directory in which temporary files will be stored.) For example, one could redirect ``TMPDIR`` to a large RAM disk to avoid wear on HDD/SSD and potentially improve performance. On Amazon Web Services, ``TMPDIR`` can be set to `empheral storage <https://docs.aws.amazon.com/AWSEC2/latest/UserGuide/InstanceStorage.html>`_.
 
 Timeouts
 ^^^^^^^^
@@ -64,7 +66,13 @@ Abbyy Cloud OCR is a viable commercial alternative with a web services API.
 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.
+Password protected PDFs usually have two passwords, and owner and user password. When the user password is set to empty, PDF readers will open the file automatically and marked it as "(SECURED)". While not as reliable as a digital signature, this indicates that whoever set the password approved of the file at that time. When the user password is set, the document cannot be viewed without the password. 
+
+Either way, OCRmyPDF does not remove passwords from PDFs and exits with an error on encountering them.
+
+``qpdf``, one of OCRmyPDF's dependencies, can remove passwords. If the owner and user password are set, a password is required for ``qpdf``. If only the owner password is set, then the password can be stripped, even if one does not have the owner password.
+
+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.
 

ocrmypdf/__main__.py

@@ -14,6 +14,7 @@ import logging
 import argparse
 
 import PyPDF2 as pypdf
+import PIL
 
 import ruffus.ruffus_exceptions as ruffus_exceptions
 import ruffus.cmdline as cmdline
@@ -23,10 +24,10 @@ 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
-from .exec import tesseract, qpdf
+from .exec import tesseract, qpdf, ghostscript
 from . import PROGRAM_NAME, VERSION
 
-from .exceptions import *
+from .exceptions import ExitCode, ExitCodeException, MissingDependencyError
 from . import exceptions as ocrmypdf_exceptions
 from ._unicodefun import verify_python3_env
 
@@ -241,6 +242,11 @@ ocrsettings.add_argument(
 advanced = parser.add_argument_group(
     "Advanced",
     "Advanced options to control Tesseract's OCR behavior")
+advanced.add_argument(
+    '--max-image-mpixels', action='store', type=float, metavar='MPixels',
+    help="Set maximum number of pixels to unpack before treating an image as a "
+         "decompression bomb",
+    default=128.0)
 advanced.add_argument(
     '--tesseract-config', action='append', metavar='CFG', default=[],
     help="Additional Tesseract configuration files -- see documentation")
@@ -321,11 +327,12 @@ def check_options_languages(options, _log):
     if '+' in options.language[0]:
         options.language = options.language[0].split('+')
 
-    if not set(options.language).issubset(tesseract.languages()):
+    languages = set(options.language)
+    if not languages.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()):
+        for lang in (languages - tesseract.languages()):
             msg += lang + '\n'
         raise MissingDependencyError(msg)
 
@@ -348,7 +355,8 @@ def check_options_output(options, log):
         options.pdf_renderer = 'sandwich'
 
     if options.pdf_renderer == 'tesseract':
-        if tesseract.version() < '3.05' and options.output_type == 'pdfa':
+        if tesseract.version() < '3.05' and \
+                options.output_type.startswith('pdfa'):
             log.warning(
                 "For best results use --pdf-renderer=tesseract "
                 "--output-type=pdf to disable PDF/A generation via "
@@ -412,9 +420,9 @@ def check_options_ocr_behavior(options, log):
     # if options.redo_ocr and (options.skip_text or options.force_ocr):
     #     raise argparse.ArgumentError(
     #         "Error: --redo-ocr and other OCR options are incompatible.")
-
+    languages = set(options.language)
     if options.pdf_renderer == 'hocr' and \
-            not set(options.language).issubset(HOCR_OK_LANGS):
+            not languages.issubset(HOCR_OK_LANGS):
         msg = (
             "The 'hocr' PDF renderer is known to cause problems with one "
             "or more of the languages in your document. ")
@@ -427,6 +435,15 @@ def check_options_ocr_behavior(options, log):
                 "Use --pdf-renderer tesseract --output-type pdf to avoid "
                 "this issue")
         log.warning(msg)
+    elif ghostscript.version() < '9.20' and \
+            not languages.issubset(HOCR_OK_LANGS) \
+            and options.output_type != 'pdf':
+        msg = (
+            "The installed version of Ghostscript does not work correctly "
+            "with the OCR languages you specified. Use --output-type pdf or "
+            "upgrade to Ghostscript 9.20 or later to avoid this issue.")
+        msg += "Found Ghostscript {}".format(ghostscript.version())
+        log.warning(msg)
 
 
 def check_options_advanced(options, log):
@@ -441,10 +458,10 @@ def check_options_advanced(options, log):
             "--pdf-renderer tess4 requires Tesseract 4.x "
             "commit 3d9fb3b or later")
     if options.pdfa_image_compression != 'auto' and \
-            options.output_type != 'pdfa':
+            options.output_type.startswith('pdfa'):
         log.warning(
             "--pdfa-image-compression argument has no effect when "
-            "--output-type is not 'pdfa'"
+            "--output-type is not 'pdfa', 'pdfa-1', or 'pdfa-2'"
         )
 
 
@@ -537,6 +554,7 @@ def do_ruffus_exception(ruffus_five_tuple, options, log):
     exit_code = None
 
     task_name, job_name, exc_name, exc_value, exc_stack = ruffus_five_tuple
+    job_name = job_name  # unused
     if exc_name == 'builtins.SystemExit':
         match = re.search(r"\.(.+?)\)", exc_value)
         exit_code_name = match.groups()[0]
@@ -559,6 +577,21 @@ def do_ruffus_exception(ruffus_five_tuple, options, log):
         msg = "Error occurred while running this command:"
         log.error(msg + '\n' + exc_value)
         exit_code = ExitCode.child_process_error
+    elif (exc_name == 'PyPDF2.utils.PdfReadError' and \
+            'not been decrypted' in exc_value) or \
+            (exc_name == 'ocrmypdf.exceptions.EncryptedPdfError'):
+        log.error(textwrap.dedent("""\
+            Input PDF is encrypted. The encryption must be removed to
+            perform OCR. 
+
+            For information about this PDF's security use
+                qpdf --show-encryption infilename
+
+            You can remove the encryption using
+                qpdf --decrypt [--password=[password]] infilename
+
+            """))
+        exit_code = ExitCode.encrypted_pdf        
     elif exc_name == 'ocrmypdf.exceptions.PdfMergeFailedError':
         log.error(textwrap.dedent("""\
             Failed to merge PDF image layer with OCR layer
@@ -574,19 +607,12 @@ def do_ruffus_exception(ruffus_five_tuple, options, log):
         base_exc_name = exc_name.replace('ocrmypdf.exceptions.', '')
         exc_class = getattr(ocrmypdf_exceptions, base_exc_name)
         exit_code = 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.)
-
-            """))
-        exit_code = ExitCode.encrypted_pdf
+    elif exc_name == 'PIL.Image.DecompressionBombError':
+        msg = cleanup_ruffus_error_message(exc_value)
+        msg += ("\nUse the --max-image-mpixels argument to set increase the "
+                "maximum number of megapixels to accept.")
+        log.error(msg)
+        exit_code = ExitCode.input_file
 
     if exit_code is not None:
         return exit_code
@@ -660,7 +686,7 @@ def log_page_orientations(pdfinfo, _log):
                 180: 's', 270: 'w'}
     orientations = []
     for n, page in enumerate(pdfinfo):
-        angle = pdfinfo[n].rotation or 0
+        angle = page.rotation or 0
         if angle != 0:
             orientations.append('{0}{1}'.format(
                 n + 1,
@@ -686,6 +712,10 @@ def run_pipeline():
 
     check_options(options, _log)
 
+    PIL.Image.MAX_IMAGE_PIXELS = int(options.max_image_mpixels * 1000000)
+    if PIL.Image.MAX_IMAGE_PIXELS == 0:
+        PIL.Image.MAX_IMAGE_PIXELS = None
+
     # Complain about qpdf version < 7.0.0
     # Suppress the warning if in the test suite, since there are no PPAs
     # for qpdf 7.0.0 for Ubuntu trusty (i.e. Travis)
@@ -730,14 +760,14 @@ def run_pipeline():
         elif not is_file_writable(options.output_file):
             _log.error(
                 "Output file location (" + options.output_file + ") " +
-                "is not writable.")
+                "is not a writable file.")
             return ExitCode.file_access_error
 
         manager = JobContextManager()
-        manager.register('JobContext', JobContext)
+        manager.register('JobContext', JobContext)  # pylint: disable=no-member
         manager.start()
 
-        context = manager.JobContext()
+        context = manager.JobContext()  # pylint: disable=no-member
         context.set_options(options)
         context.set_work_folder(work_folder)
 
@@ -777,7 +807,11 @@ def run_pipeline():
 
     if options.flowchart:
         _log.info("Flowchart saved to {}".format(options.flowchart))
-    elif options.output_file != '-':
+    elif options.output_file == '-':
+        _log.info("Output sent to stdout")
+    elif os.path.samefile(options.output_file, os.devnull):
+        pass  # Say nothing when sending to dev null
+    else:
         if options.output_type.startswith('pdfa'):
             pdfa_info = file_claims_pdfa(options.output_file)
             if pdfa_info['pass']:
@@ -790,8 +824,6 @@ def run_pipeline():
         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:

ocrmypdf/_unicodefun.py

@@ -97,7 +97,7 @@ def verify_python3_env():
                 break
         if bad_locale is not None:
             extra += (
-                '\n\ocrmypdf discovered that you exported a UTF-8 locale\n'
+                '\nocrmypdf discovered that you exported a UTF-8 locale\n'
                 'but the locale system could not pick up from it because\n'
                 'it does not exist.  The exported locale is "%s" but it\n'
                 'is not supported'

ocrmypdf/exceptions.py

@@ -1,4 +1,3 @@
-#!/usr/bin/env python3
 # © 2016 James R. Barlow: github.com/jbarlow83
 
 

ocrmypdf/exec/__init__.py

@@ -1,4 +1,3 @@
-#!/usr/bin/env python3
 # © 2016 James R. Barlow: github.com/jbarlow83
 
 """Wrappers to manage subprocess calls"""
@@ -29,8 +28,14 @@ def get_version(program, *,
             stdout=PIPE, stderr=STDOUT, check=True)
         output = proc.stdout
     except CalledProcessError as e:
-        raise MissingDependencyError(
-            "Could not find program '{}' on the PATH".format(program)) from e
+        if get_program(program) == program:
+            raise MissingDependencyError(
+                "Could not find program '{}' on the PATH".format(
+                    program)) from e
+        else:
+            raise MissingDependencyError(
+                "Could not find program '{}'".format(
+                    get_program(program))) from e            
 
     try:
         version = re.match(regex, output.strip()).group(1)
@@ -40,4 +45,4 @@ def get_version(program, *,
             "Message was:\n{}").format(program, output)
         )
 
-    return version
+    return version

ocrmypdf/exec/ghostscript.py

@@ -1,4 +1,3 @@
-#!/usr/bin/env python3
 # © 2017 James R. Barlow: github.com/jbarlow83
 
 from tempfile import NamedTemporaryFile
@@ -37,7 +36,7 @@ def rasterize_pdf(input_file, output_file, xres, yres, raster_device, log,
     :param yres: 
     :param raster_device: 
     :param log: 
-    :param pageno: page number to rasterize
+    :param pageno: page number to rasterize (beginning at page 1)
     :param page_dpi: resolution tuple (x, y) overriding output image DPI 
     :return: 
     """
@@ -55,11 +54,11 @@ def rasterize_pdf(input_file, output_file, xres, yres, raster_device, log,
             '-sDEVICE=%s' % raster_device,
             '-dFirstPage=%i' % pageno,
             '-dLastPage=%i' % pageno,
-            '-o', tmp.name,
             '-r{0}x{1}'.format(str(int_res[0]), str(int_res[1])),
+            '-o', tmp.name,
             fspath(input_file)
         ]
-
+        
         p = run(args_gs, stdout=PIPE, stderr=STDOUT,
                 universal_newlines=True)
         if _gs_error_reported(p.stdout):
@@ -75,6 +74,7 @@ def rasterize_pdf(input_file, output_file, xres, yres, raster_device, log,
         # if the resolution happens to be fractional, then the discrepancy
         # would change the size of the output page, especially if the DPI
         # is quite low. Resize the image to the expected size
+
         tmp.seek(0)
         with Image.open(tmp) as im:
             expected_size = round(im.size[0] / int_res[0] * res[0]), \

ocrmypdf/exec/qpdf.py

@@ -1,4 +1,3 @@
-#!/usr/bin/env python3
 # © 2017 James R. Barlow: github.com/jbarlow83
 
 from subprocess import CalledProcessError, STDOUT, PIPE, run
@@ -68,8 +67,6 @@ def repair(input_file, output_file, log):
             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(

ocrmypdf/exec/tesseract.py

@@ -1,4 +1,3 @@
-#!/usr/bin/env python3
 # © 2017 James R. Barlow: github.com/jbarlow83
 
 import sys
@@ -158,7 +157,7 @@ def tesseract_log_output(log, stdout, input_file):
 
     try:
         text = stdout.decode()
-    except UnicodeDecodeError as e:
+    except UnicodeDecodeError:
         log.error(prefix + "command line output was not utf-8. " +
             "This usually means Tesseract's language packs do not match "
             "the installed version of Tesseract.")
@@ -279,6 +278,10 @@ def use_skip_page(text_only, skip_pdf, output_pdf, output_text):
     with open(output_pdf, 'wb') as out:
         pdf_out = pypdf.PdfFileWriter()
         w, h = page0.mediaBox.getWidth(), page0.mediaBox.getHeight()
+        # If skip page has a /Rotate key, replicate the rotation
+        rotation = int(page0.get('/Rotate', 0))
+        if rotation % 180 == 90:
+            w, h = h, w
         pdf_out.addBlankPage(w, h)
         pdf_out.write(out)
 

ocrmypdf/exec/unpaper.py

@@ -1,4 +1,3 @@
-#!/usr/bin/env python3
 # © 2015 James R. Barlow: github.com/jbarlow83
 # unpaper documentation:
 # https://github.com/Flameeyes/unpaper/blob/master/doc/basic-concepts.md

ocrmypdf/helpers.py

@@ -1,9 +1,9 @@
-#!/usr/bin/env python3
 # © 2016 James R. Barlow: github.com/jbarlow83
 
 from functools import partial
 from collections.abc import Iterable
 from contextlib import suppress, contextmanager
+from pathlib import Path
 import sys
 import os
 
@@ -63,19 +63,33 @@ def is_file_writable(test_file):
     can replace it atomically. Before doing the OCR work, make sure
     the location is writable.
     """
-    if os.path.exists(test_file):
+    p = Path(test_file)
+
+    if p.is_symlink():
+        # Python 3.5 does not accept parameters for Path.resolve() and behaves
+        # as if strict=True (throws an exception on failure). Python 3.6 
+        # defaults to strict=False. This implements strict=False like behavior
+        # for Python 3.5.
+        if sys.version_info[0:2] <= (3, 5):
+            resolve = lambda: Path(os.path.realpath(str(p)))
+        else:
+            resolve = lambda: p.resolve(strict=False)
+        p = resolve()
+
+    # p.is_file() throws an exception in some cases
+    if p.exists() and p.is_file():
         return os.access(
-            test_file, os.W_OK,
+            str(p), os.W_OK,
             effective_ids=(os.access in os.supports_effective_ids))
     else:
         try:
-            fp = open(test_file, 'wb')
-        except OSError as e:
+            fp = p.open('wb')
+        except OSError:
             return False
         else:
             fp.close()
             with suppress(OSError):
-                os.unlink(test_file)
+                p.unlink()
         return True
 
 
@@ -118,4 +132,4 @@ if sys.version_info[0:2] <= (3, 5):
 
 else:
     universal_open = open
-    fspath = os.fspath
+    fspath = os.fspath

ocrmypdf/leptonica.py

@@ -566,35 +566,4 @@ if __name__ == '__main__':
     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)
-
-
+    args.func(args)

ocrmypdf/lib/compile_leptonica.py

@@ -1,3 +1,4 @@
+#!/usr/bin/env python3
 # © 2017 James R. Barlow: github.com/jbarlow83
 
 from cffi import FFI

ocrmypdf/pdfa.py

@@ -1,4 +1,3 @@
-#!/usr/bin/env python3
 # © 2015 James R. Barlow: github.com/jbarlow83
 #
 # Generate a PDFA_def.ps file for Ghostscript >= 9.14

ocrmypdf/pdfinfo.py

@@ -662,10 +662,6 @@ class PageInfo:
         else:
             return '1.5'
 
-    @property
-    def images(self):
-        return self._pageinfo['images']
-
     def __repr__(self):
         return (
             '<PageInfo '

ocrmypdf/pipeline.py

@@ -1,7 +1,7 @@
-#!/usr/bin/env python3
 # © 2016 James R. Barlow: github.com/jbarlow83
 
 from contextlib import suppress
+from shutil import copyfileobj
 import sys
 import os
 import shutil
@@ -17,7 +17,8 @@ from .pdfinfo import PdfInfo, Encoding, Colorspace
 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 *
+from .exceptions import PdfMergeFailedError, UnsupportedImageFormatError, \
+    DpiError, PriorOcrFoundError, InputFileError
 from . import leptonica
 from . import PROGRAM_NAME, VERSION
 
@@ -159,7 +160,7 @@ def _pdf_guess_version(input_file, search_window=1024):
 
     with open(input_file, 'rb') as f:
         signature = f.read(1024)
-    m = re.search(b'%PDF-(\d\.\d)', signature)
+    m = re.search(br'%PDF-(\d\.\d)', signature)
     if m:
         return m.group(1)
     return ''
@@ -244,7 +245,30 @@ def get_canvas_square_dpi(pageinfo, options):
 def is_ocr_required(pageinfo, log, options):
     page = pageinfo.pageno + 1
     ocr_required = True
-    if not pageinfo.images:
+
+    if pageinfo.has_text:
+        msg = "{0:4d}: page already has text! – {1}"
+
+        if not options.force_ocr and not options.skip_text:
+            log.error(msg.format(page,
+                                 "aborting (use --force-ocr to force OCR)"))
+            raise PriorOcrFoundError()
+        elif options.force_ocr:
+            log.info(msg.format(page,
+                                "rasterizing text and running OCR anyway"))
+            ocr_required = True
+        elif options.skip_text:
+            log.info(msg.format(page,
+                                "skipping all processing on this page"))
+            ocr_required = False
+    elif not pageinfo.images and not options.lossless_reconstruction:
+        # We found a page with no images and no text. That means it may
+        # have vector art that the user wants to OCR. If we determined
+        # lossless reconstruction is not possible then we have to rasterize
+        # the image. So if OCR is being forced, take that to mean YES, go 
+        # ahead and rasterize. If not forced, then pretend there's no text
+        # on the page at all so we don't lose anything.
+        # This could be made smarter by explicitly searching for vector art.
         if options.force_ocr and options.oversample:
             # The user really wants to reprocess this file
             log.info(
@@ -263,23 +287,9 @@ def is_ocr_required(pageinfo, log, options):
         else:
             log.info(
                 "{0:4d}: page has no images - "
-                "skipping all processing on this page".format(page))
-            ocr_required = False
-
-    elif pageinfo.has_text:
-        msg = "{0:4d}: page already has text! – {1}"
-
-        if not options.force_ocr and not options.skip_text:
-            log.error(msg.format(page,
-                                 "aborting (use --force-ocr to force OCR)"))
-            raise PriorOcrFoundError()
-        elif options.force_ocr:
-            log.info(msg.format(page,
-                                "rasterizing text and running OCR anyway"))
-            ocr_required = True
-        elif options.skip_text:
-            log.info(msg.format(page,
-                                "skipping all processing on this page"))
+                "skipping all processing on this page to avoid losing detail. "
+                "Use --force-ocr if you wish to perform OCR on pages that "
+                "have vector content.".format(page))
             ocr_required = False
 
     if ocr_required and options.skip_big and pageinfo.images:
@@ -991,13 +1001,16 @@ def copy_final(
         context):
     input_file = next((ii for ii in input_files if ii.endswith('.pdf')))
 
-    if output_file == '-':
-        from shutil import copyfileobj
-        with open(input_file, 'rb') as input_stream:
+    with open(input_file, 'rb') as input_stream:
+        if output_file == '-':
             copyfileobj(input_stream, sys.stdout.buffer)
             sys.stdout.flush()
-    else:
-        shutil.copy(input_file, output_file)
+        else:
+            # At this point we overwrite the output_file specified by the user
+            # use copyfileobj because then we use open() to create the file and 
+            # get the appropriate umask, ownership, etc.
+            with open(output_file, 'wb') as output_stream:
+                copyfileobj(input_stream, output_stream)
 
 
 def build_pipeline(options, work_folder, log, context):
@@ -1226,7 +1239,7 @@ def build_pipeline(options, work_folder, log, context):
     task_merge_sidecars.active_if(options.sidecar)
 
     # Finalize
-    task_copy_final = main_pipeline.merge(
+    main_pipeline.merge(
         task_func=copy_final,
         input=[task_merge_pages_ghostscript, task_merge_pages_qpdf],
         output=options.output_file,

requirements.txt

@@ -2,7 +2,7 @@
 # setup.py lists a separate set of requirements that are looser to simplify
 # installation
 ruffus == 2.6.3
-Pillow == 4.3.0
+Pillow == 5.0.0
 reportlab == 3.4.0
 PyPDF2 == 1.26.0
 img2pdf == 0.2.4

tests/conftest.py

@@ -1,4 +1,3 @@
-#!/usr/bin/env python3
 # © 2017 James R. Barlow: github.com/jbarlow83
 
 import sys

tests/resources/README.rst

@@ -33,7 +33,7 @@ In some cases they were converted from one image format to another without other
         - Creative Commons BY-SA 3.0
     *   - typewriter.png, 2400dpi.pdf
         - `Wikimedia: Triumph typewrtier text Linzensoep`_
-        * Creative Commons BY-SA 2.5
+        - Creative Commons BY-SA 2.5
     *   - baiona.png
         - `Wikimedia: Baionako udalerri mugakideak`_
         - Creative Commons BY-SA 4.0
@@ -100,6 +100,9 @@ under the terms of the license in LICENSE.rst.
     *   - trivial.pdf
         - @jbarlow83
         - smallest possible valid PDF-1.3 with all required fields
+    *   - vector.pdf
+        - @Catscratch
+        - a PDF with vector art and text rendered as curves with no fonts
 
 
 Assemblies
@@ -116,7 +119,7 @@ These test resources are assemblies or derivatives from other previously mention
 - 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)
+- skew-encrypted.pdf (skew.pdf with encryption - access supported by PyPDF2, password is "password")
 - baiona_gray.png (from baiona.png)
 - poster.pdf (from LinnSequencer.jpg)
 

tests/spoof/gs_feature_elision.py

@@ -22,7 +22,7 @@ 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__))
+        print('SPOOFED: ' + os.path.basename(__file__))
         sys.exit(0)
 
     gs_args = ['gs'] + sys.argv[1:]

tests/spoof/gs_pdfa_failure.py

@@ -17,7 +17,7 @@ def real_ghostscript(argv):
 def main():
     if '--version' in sys.argv:
         print('9.20')
-        print('SPOOFED: ' + os.path.basename(__filename__))
+        print('SPOOFED: ' + os.path.basename(__file__))
         sys.exit(0)
 
     # Unless some argument is calling for PDFA generation, forward to

tests/spoof/gs_raster_failure.py

@@ -16,7 +16,7 @@ def real_ghostscript(argv):
 def main():
     if '--version' in sys.argv:
         print('9.20')
-        print('SPOOFED: ' + os.path.basename(__filename__))
+        print('SPOOFED: ' + os.path.basename(__file__))
         sys.exit(0)
 
     # For any rendering calls (device == pdfwrite) call real ghostscript

tests/spoof/gs_render_failure.py

@@ -1,5 +1,5 @@
 #!/usr/bin/env python3
-# © 2016 James R. Barlow: github.com/jbarlow83
+# © 2016-18 James R. Barlow: github.com/jbarlow83
 
 import sys
 import os
@@ -16,7 +16,7 @@ def real_ghostscript(argv):
 def main():
     if '--version' in sys.argv:
         print('9.20')
-        print('SPOOFED: ' + os.path.basename(__filename__))
+        print('SPOOFED: ' + os.path.basename(__file__))
         sys.exit(0)
 
     # For any rasterize calls (device != pdfwrite) call real ghostscript

tests/spoof/tesseract_badutf8.py

@@ -40,7 +40,7 @@ def main():
         sys.stdout.buffer.write(BAD_UTF8)
         sys.exit(1)
     elif sys.argv[-1] == 'stdout':
-        inputf = sys.argv[-2]
+        # input file is at sys.argv[-2] but we don't look at it
         print("""Orientation: 0
 Orientation in degrees: 0
 Orientation confidence: 100.00

tests/spoof/tesseract_noop.py

@@ -73,10 +73,11 @@ def main():
             output = sys.argv[-3]
             with Image.open(inputf) as im:
                 dpi = im.info['dpi']
-                imsize = im.size[0] * dpi[0] / 72, im.size[1] * dpi[1] / 72
+                pagesize = im.size[0] / dpi[0], im.size[1] / dpi[1]
+                ptsize = pagesize[0] * 72, pagesize[1] * 72
 
             pdf_out = pypdf.PdfFileWriter()
-            pdf_out.addBlankPage(imsize[0], imsize[1])
+            pdf_out.addBlankPage(ptsize[0], ptsize[1])
             with open(output + '.pdf', 'wb') as f:
                 pdf_out.write(f)
             with open(output + '.txt', 'w') as f:

tests/test_hocrtransform.py

@@ -1,4 +1,3 @@
-#!/usr/bin/env python3
 # © 2015 James R. Barlow: github.com/jbarlow83
 
 from ocrmypdf import hocrtransform

tests/test_main.py

@@ -1,6 +1,7 @@
 # © 2015-17 James R. Barlow: github.com/jbarlow83
 
 from subprocess import Popen, PIPE, check_output, check_call, DEVNULL
+from pathlib import Path
 import os
 import shutil
 import resource
@@ -14,6 +15,11 @@ from ocrmypdf.exec import ghostscript, tesseract, qpdf
 import logging
 from math import isclose
 
+import PIL
+
+# pytest.helpers is dynamic
+# pylint: disable=no-member
+# pylint: disable=w0612
 
 check_ocrmypdf = pytest.helpers.check_ocrmypdf
 run_ocrmypdf = pytest.helpers.run_ocrmypdf
@@ -69,11 +75,10 @@ def test_quick(spoof_tesseract_cache, resources, outpdf):
     check_ocrmypdf(resources / 'ccitt.pdf', outpdf, env=spoof_tesseract_cache)
 
 
-@pytest.mark.filterwarnings('ignore:Image size')
 def test_deskew(spoof_tesseract_noop, resources, outdir):
     # Run with deskew
     deskewed_pdf = check_ocrmypdf(
-        resources / 'skew.pdf', outdir / 'skew.pdf', '-d', '-v', '1',
+        resources / 'skew.pdf', outdir / 'skew.pdf', '-d',
         env=spoof_tesseract_noop)
 
     # Now render as an image again and use Leptonica to find the skew angle
@@ -88,7 +93,8 @@ def test_deskew(spoof_tesseract_noop, resources, outdir):
         xres=150,
         yres=150,
         raster_device='pngmono',
-        log=log)
+        log=log,
+        pageno=1)
 
     from ocrmypdf.leptonica import Pix
     pix = Pix.read(str(deskewed_png))
@@ -127,8 +133,8 @@ def test_remove_background(spoof_tesseract_noop, resources, outdir):
         xres=100,
         yres=100,
         raster_device='png16m',
-        log=log)
-
+        log=log,
+        pageno=1)
 
     # The output image should contain pure white and black
     im = Image.open(output_png)
@@ -431,7 +437,7 @@ def test_klingon(resources, outpdf):
 
 def test_missing_docinfo(spoof_tesseract_noop, resources, outpdf):
     p, out, err = run_ocrmypdf(
-        resources / 'missing_docinfo.pdf', outpdf, '-l', 'eng', '-c',
+        resources / 'missing_docinfo.pdf', outpdf, '-l', 'eng', '--skip-text',
         env=spoof_tesseract_noop)
     assert p.returncode == ExitCode.ok, err
 
@@ -478,7 +484,7 @@ 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')
+    assert out.find('encrypted')
 
 
 @pytest.mark.parametrize('renderer', [
@@ -521,7 +527,9 @@ 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)
+        '--pdf-renderer', renderer, 
+        '--max-image-mpixels', '0',
+        env=spoof_tesseract_big_image_error)
 
 
 def test_no_unpaper(resources, no_outpdf):
@@ -877,6 +885,8 @@ def test_gs_raster_failure(spoof_no_tess_gs_raster_fail, resources, outpdf):
     assert p.returncode == ExitCode.child_process_error
 
 
+@pytest.mark.skipif('8.0.0' <= qpdf.version() <= '8.0.1',
+                    reason="qpdf regression")
 def test_no_contents(spoof_tesseract_noop, resources, outpdf):
     check_ocrmypdf(resources / 'no_contents.pdf', outpdf, '--force-ocr',
                    env=spoof_tesseract_noop)
@@ -1037,3 +1047,95 @@ def test_bad_utf8(spoof_tess_bad_utf8, renderer, resources, no_outpdf):
     assert p.returncode != 0
     assert 'not utf-8' in err, "should whine about utf-8"
     assert '\\x96' in err, 'should repeat backslash encoded output'
+
+
+@pytest.mark.skipif(
+    not tesseract.has_textonly_pdf(), 
+    reason="issue only affects sandwich")
+def test_rotate_deskew_timeout(resources, outdir):
+    check_ocrmypdf(
+        resources / 'rotated_skew.pdf',
+        outdir / 'deskewed.pdf',
+        '--deskew',
+        '--tesseract-timeout', '0',
+        '--pdf-renderer', 'sandwich'
+    )
+
+    correlation = check_monochrome_correlation(
+        outdir,
+        reference_pdf=resources / 'ccitt.pdf',
+        reference_pageno=1,
+        test_pdf=outdir / 'deskewed.pdf',
+        test_pageno=1)
+
+    # Confirm that the page still got deskewed
+    assert correlation > 0.50
+
+
+@pytest.mark.skipif(
+    PIL.PILLOW_VERSION < '5.0.0',
+    reason="Pillow < 5.0.0 doesn't raise the exception")
+def test_decompression_bomb(resources, outpdf):
+    p, out, err = run_ocrmypdf(
+        resources / 'hugemono.pdf',
+        outpdf
+    )
+    assert 'decompression bomb' in err
+
+    p, out, err = run_ocrmypdf(
+        resources / 'hugemono.pdf',
+        outpdf,
+        '--max-image-mpixels', '2000'
+    )
+    assert p.returncode == 0
+
+
+def test_text_curves(spoof_tesseract_noop, resources, outpdf):
+    check_ocrmypdf(
+        resources / 'vector.pdf', outpdf, env=spoof_tesseract_noop)
+
+    info = PdfInfo(outpdf)
+    assert len(info.pages[0].images) == 0, "added images to the vector PDF"
+
+    check_ocrmypdf(
+        resources / 'vector.pdf', outpdf, '--force-ocr',
+        env=spoof_tesseract_noop)
+    
+    info = PdfInfo(outpdf)
+    assert len(info.pages[0].images) != 0, "force did not rasterize"
+    
+
+def test_dev_null(spoof_tesseract_noop, resources):
+    p, out, err = run_ocrmypdf(
+        resources / 'trivial.pdf',
+        os.devnull,
+        '--force-ocr',
+        env=spoof_tesseract_noop
+    )
+    assert p.returncode == 0, "could not send output to /dev/null"
+    assert len(out) == 0, "wrote to stdout"
+
+
+def test_output_is_dir(spoof_tesseract_noop, resources, outdir):
+    p, out, err = run_ocrmypdf(
+        resources / 'trivial.pdf',
+        outdir,
+        '--force-ocr',
+        env=spoof_tesseract_noop
+    )
+    assert p.returncode == ExitCode.file_access_error
+    assert 'is not a writable file' in err
+
+
+def test_output_is_symlink(spoof_tesseract_noop, resources, outdir):
+    sym = Path(outdir / 'this_is_a_symlink')
+    sym.symlink_to(outdir / 'out.pdf')
+    p, out, err = run_ocrmypdf(
+        resources / 'trivial.pdf',
+        sym,
+        '--force-ocr',
+        env=spoof_tesseract_noop
+    )
+    assert p.returncode == ExitCode.ok, err
+    assert (outdir / 'out.pdf').stat().st_size > 0, 'target file not created'
+    

tests/test_pageinfo.py

@@ -1,4 +1,3 @@
-#!/usr/bin/env python3
 # © 2015 James R. Barlow: github.com/jbarlow83
 
 from ocrmypdf import pdfinfo
@@ -122,4 +121,4 @@ def test_no_contents(resources):
 def test_oversized_page(resources):
     pdf = pdfinfo.PdfInfo(resources / 'poster.pdf')
     image = pdf[0].images[0]
-    assert image.width * image.xres > 200, "this is supposed to be oversized"
+    assert image.width * image.xres > 200, "this is supposed to be oversized"

tests/test_tess3.py

@@ -1,4 +1,3 @@
-#!/usr/bin/env python3
 # © 2017 James R. Barlow: github.com/jbarlow83
 
 import pytest

tests/test_tess4.py

@@ -1,4 +1,3 @@
-#!/usr/bin/env python3
 # © 2017 James R. Barlow: github.com/jbarlow83
 
 import pytest
@@ -10,7 +9,7 @@ import os
 import PyPDF2 as pypdf
 from contextlib import contextmanager
 
-
+# pylint: disable=no-member
 spoof = pytest.helpers.spoof
 
 
@@ -128,4 +127,4 @@ def test_content_preservation(ensure_tess4, resources, outpdf):
 
     info = pdfinfo.PdfInfo(outpdf)
     page = info[0]
-    assert len(page.images) > 1, "masks were rasterized"
+    assert len(page.images) > 1, "masks were rasterized"

tests/test_userunit.py

@@ -1,4 +1,3 @@
-#!/usr/bin/env python3
 # © 2017 James R. Barlow: github.com/jbarlow83
 
 from subprocess import Popen, PIPE, check_output, check_call, DEVNULL