v4.5.6 release notes

Past behavior was to continue and let ruffus puke eventually

.gitignore

@@ -6,6 +6,7 @@ pyvenv.cfg
 tasks.py
 .bash_history
 .ruffus_history.sqlite
+.idea/
 
 # Package building
 *.egg-info/

.travis.yml

@@ -21,16 +21,23 @@ matrix:
       sudo: required
       language: python
       python: 3.6
+      env:
+        - secure: "oyX5xesoHD7qcDXKIxMyGZPi+H/WxcvfFkaviEmq84K1DDyHk48+9e92IKgrw8/lcTADnEo/AgVKfnhCPflFimk1xTkgaK4sUg1WLI2YjmaHcwl5SlBHa2rN3uGBwy1hyP92qyv/mMc9R59NtRJ8u76lbn6eN9wi7lkFWdE6BTw="  # DOCKERHUB_OCRMYPDF_TOKEN
     - os: osx
       osx_image: xcode8
       language: generic
+      env:
+        - secure: "hsf6MT+n2x3OiDM2fQyJZdV0/PWYmv81LdVqC6cfnHBE/8N3DloJRqQ7WfO14TxhiK9PEC7MpyCj0lSabUHEO7gSH6Vks6I1asoSkt8S9/bSMlhT4hei+pwVpeGEiU5xHVATNjY+D919VC3IFvc3XmjT74h/2SLhaZ+jhEmDggM="  # HOMEBREW_OCRMYPDF_TOKEN
 
 before_cache:
 - rm -f $HOME/.cache/pip/log/debug.log
 
-before_install:
+before_install: |
-- if [[ "$TRAVIS_OS_NAME" == "linux" ]]; then bash .travis/linux_before_install.sh ; fi
+  if [[ "$TRAVIS_OS_NAME" == "linux" ]]; then
-- if [[ "$TRAVIS_OS_NAME" == "osx" ]]; then bash .travis/osx_before_install.sh ; fi
+    bash .travis/linux_before_install.sh
+  elif [[ "$TRAVIS_OS_NAME" == "osx" ]]; then
+    bash .travis/osx_before_install.sh
+  fi
 
 install:
 - pip3 install .
@@ -41,20 +48,35 @@ script:
 - pytest
 - mv dont_import_this_ocrmypdf ocrmypdf
 
-after_success:
-- if [[ "$TRAVIS_OS_NAME" == "osx" ]]; then bash .travis/osx_brew.sh ; fi
-
-# See https://www.appneta.com/blog/pypi-deployment-with-travis-ci/ for
-# steps to set up testpypi deploy for untagged builds if desired
-
 deploy:
-  provider: pypi
+  # release for main pypi
+- provider: pypi
   user: ocrmypdf-travis
   password:
-    secure: DTFOmmNL6olA0+yXvp4u9jXZlZeqrJsJ0526jzqf4a3gZ6jnGTq5UI6WzRsslSyoMMfXKtHQebqHM6ogSgCZinyZ3ufHJo8fn9brxbEc2gsiWkbj5o3bGwdWMT1vNNE7XW0VCpw87rZ1EEwjl4FJHFudMlPR1yfU5+uq0k0PACo=
+    secure: "DTFOmmNL6olA0+yXvp4u9jXZlZeqrJsJ0526jzqf4a3gZ6jnGTq5UI6WzRsslSyoMMfXKtHQebqHM6ogSgCZinyZ3ufHJo8fn9brxbEc2gsiWkbj5o3bGwdWMT1vNNE7XW0VCpw87rZ1EEwjl4FJHFudMlPR1yfU5+uq0k0PACo="
   distributions: "sdist bdist_wheel"
   on:
     branch: master
     tags: true
     condition: $TRAVIS_PYTHON_VERSION == "3.6" && $TRAVIS_OS_NAME == "linux"
   skip_upload_docs: true
+
+  # test pypi
+- provider: pypi
+  server: https://testpypi.python.org/pypi
+  user: ocrmypdf-travis
+  password:
+    secure: "DTFOmmNL6olA0+yXvp4u9jXZlZeqrJsJ0526jzqf4a3gZ6jnGTq5UI6WzRsslSyoMMfXKtHQebqHM6ogSgCZinyZ3ufHJo8fn9brxbEc2gsiWkbj5o3bGwdWMT1vNNE7XW0VCpw87rZ1EEwjl4FJHFudMlPR1yfU5+uq0k0PACo="
+  distributions: "sdist"
+  on:
+    branch: develop
+    tags: false
+    condition: $TRAVIS_OS_NAME == "osx"
+  skip_upload_docs: true
+
+after_deploy: |
+  if [[ "$TRAVIS_OS_NAME" == "osx" ]]; then
+    bash .travis/osx_brew.sh
+  elif [[ "$TRAVIS_PYTHON_VERSION" == "3.6" && "$TRAVIS_OS_NAME" == "linux" ]]; then
+    curl -H "Content-Type: application/json" --data '{"build": true}' -X POST https://registry.hub.docker.com/u/jbarlow83/ocrmypdf/trigger/$DOCKERHUB_OCRMYPDF_TOKEN/
+  fi

.travis/autobrew.py

@@ -13,7 +13,6 @@ class Ocrmypdf < Formula
 
   depends_on :python3
   depends_on "pkg-config" => :build
-  depends_on "zlib"
   depends_on "libffi"
   depends_on "tesseract"
   depends_on "ghostscript"

.travis/osx_brew.sh

@@ -4,5 +4,17 @@ set -x
 
 pip3 install homebrew-pypi-poet
 python3 .travis/autobrew.py
-brew audit ocrmypdf.rb
 cat ocrmypdf.rb
+brew audit ocrmypdf.rb
+
+# Important: disable debug output so token is hidden
+set +x
+git clone https://$HOMEBREW_OCRMYPDF_TOKEN@github.com/jbarlow83/homebrew-ocrmypdf.git
+set -x
+
+pushd homebrew-ocrmypdf
+cp ../ocrmypdf.rb Formula/ocrmypdf.rb
+git add Formula/ocrmypdf.rb
+git commit -m "homebrew-ocrmypdf: automatic release $TRAVIS_BUILD_NUMBER $TRAVIS_TAG"
+git push origin master
+popd

README.rst

@@ -35,7 +35,7 @@ Main features
 -  Supports more than `100 languages <https://github.com/tesseract-ocr/tessdata>`_ recognized by Tesseract
 -  Battle-tested on thousands of PDFs, a test suite and continuous integration
 
-For details: please consult the `release notes <RELEASE_NOTES.rst>`_.
+For details: please consult the `documentation <https://ocrmypdf.readthedocs.io/en/latest/>`_.
 
 Motivation
 ----------

docs/index.rst

@@ -11,14 +11,18 @@ be searched.
 
 PDFs are the best format for scanned documents.  Unfortunately, PDFs can be difficult to work with. OCRmyPDF makes it easy to apply image processing and OCR to existing PDFs.
 
-Contents:
-
 .. toctree::
-   :maxdepth: 2
+   :maxdepth: 1
 
    introduction
+   release_notes
    installation
    languages
+
+.. toctree::
+   :caption: Usage
+   :maxdepth: 2
+
    cookbook
    advanced
    batch
@@ -26,7 +30,6 @@ Contents:
    errors
 
 
-
 Indices and tables
 ==================
 

docs/introduction.rst

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

docs/release_notes.rst

@@ -1,11 +1,42 @@
-RELEASE NOTES
+Release notes
 =============
 
 OCRmyPDF uses `semantic versioning <http://semver.org/>`_.
 
 
+v4.5.6
+------
+
+-   Fixed issue #156, 'NoneType' object has no attribute 'getObject' on pages with no optional /Contents record.  This should resolve all issues related to pages with no /Contents record.
+-   Fixed issue #158, ocrmypdf now stops and terminates if Ghostscript fails on an intermediate step, as it is not possible to proceed.
+-   Fixed issue #160, exception thrown on certain invalid arguments instead of error message
+
+
+v4.5.5
+------
+
+-   Automated update of macOS homebrew tap
+-   Fixed issue #154, KeyError '/Contents' when searching for text on blank pages that have no /Contents record.  Note: incomplete fix for this issue.
+
+
+v4.5.4
+------
+
+-   Fix ``--skip-big`` raising an exception if a page contains no images (#152) (thanks to @TomRaz)
+-   Fix an issue where pages with no images might trigger "cannot write mode P as JPEG" (#151)
+
+
+v4.5.3
+------
+
+-  Added a workaround for Ghostscript 9.21 and probably earlier versions would fail with the error message "VMerror -25", due to a Ghostscript bug in XMP metadata handling
+-  High Unicode characters (U+10000 and up) are no longer accepted for setting metadata on the command line, as Ghostscript may not handle them correctly.
+-  Fixed an issue where the ``tess4`` renderer would duplicate content onto output pages if tesseract failed or timed out
+-  Fixed ``tess4`` renderer not recognized when lossless reconstruction is possible
+
+
 v4.5.2
-======
+------
 
 -  Fix issue #147. ``--pdf-renderer tess4 --clean`` will produce an oversized page containing the original image in the bottom left corner, due to loss DPI information.
 -  Make "using Tesseract 4.0" warning less ominous
@@ -13,13 +44,13 @@ v4.5.2
 
 
 v4.5.1
-======
+------
 
 -  Fix issue #137, proportions of images with a non-square pixel aspect ratio would be distorted in output for ``--force-ocr`` and some other combinations of flags
 
 
 v4.5
-====
+----
 
 -  Exotic PDFs containing "Form XObjects" are now supported (issue #134; PDF reference manual 8.10), and images they contain are taken into account when determining the resolution for rasterizing
 -  The Tesseract 4 Docker image no longer includes all languages, because it took so long to build something would tend to fail
@@ -27,7 +58,7 @@ v4.5
 
 
 v4.4.2
-======
+------
 
 -  The Docker images (ocrmypdf, ocrmypdf-polyglot, ocrmypdf-tess4) are now based on Ubuntu 16.10 instead of Debian stretch
 
@@ -38,7 +69,7 @@ v4.4.2
 
 
 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
@@ -47,7 +78,7 @@ v4.4.1
 -  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.
 
@@ -65,32 +96,32 @@ v4.4
 
 
 v4.3.5
-======
+------
 
 -  Update documentation to confirm Python 3.6.0 compatibility. No code changes were needed, so many earlier versions are likely supported.
 
 
 v4.3.4
-======
+------
 
 -  Fixed "decimal.InvalidOperation: quantize result has too many digits" for high DPI images
 
 
 v4.3.3
-======
+------
 
 -  Fixed PDF/A creation with Ghostscript 9.20 properly
 -  Fixed an exception on inline stencil masks with a missing optional parameter
 
 
 v4.3.2
-======
+------
 
 -  Fixed a PDF/A creation issue with Ghostscript 9.20 (note: this fix did not actually work)
 
 
 v4.3.1
-======
+------
 
 -  Fixed an issue where pages produced by the "hocr" renderer after a Tesseract timeout would be rotated incorrectly if the input page was rotated with a /Rotate marker
 -  Fixed a file handle leak in LeptonicaErrorTrap that would cause a "too many open files" error for files around hundred pages of pages long when ``--deskew`` or ``--remove-background`` or other Leptonica based image processing features were in use, depending on the system value of ``ulimit -n``
@@ -101,7 +132,7 @@ v4.3.1
 
 
 v4.3
-====
+----
 
 -  New feature ``--remove-background`` to detect and erase the background of color and grayscale images
 -  Better documentation
@@ -112,20 +143,20 @@ v4.3
    +  Some output validation is disabled in this mode
 
 v4.2.5
-======
+------
 
 -  Fixed an issue (#100) with PDFs that omit the optional /BitsPerComponent parameter on images
 -  Removed non-free file milk.pdf
 
 
 v4.2.4
-======
+------
 
 -  Fixed an error (#90) caused by PDFs that use stencil masks properly
 -  Fixed handling of PDFs that try to draw images or stencil masks without properly setting up the graphics state (such images are now ignored for the purposes of calculating DPI)
 
 v4.2.3
-======
+------
 
 -  Fixed an issue with PDFs that store page rotation (/Rotate) in an indirect object
 -  Integrated a few fixes to simplify downstream packaging (Debian)
@@ -139,20 +170,20 @@ v4.2.3
 
 
 v4.2.2
-======
+------
 
 -  Improvements to documentation
 
 
 v4.2.1
-======
+------
 
 -  Fixed an issue where PDF pages that contained stencil masks would report an incorrect DPI and cause Ghostscript to abort
 -  Implemented stdin streaming
 
 
 v4.2
-====
+----
 
 -  ocrmypdf will now try to convert single image files to PDFs if they are provided as input (#15)
 
@@ -185,13 +216,13 @@ v4.2
 -  Ghostscript now runs in "safer" mode where possible
 
 v4.1.4
-======
+------
 
 -  Bug fix: monochrome images with an ICC profile attached were incorrectly converted to full color images if lossless reconstruction was not possible due to other settings; consequence was increased file size for these images
 
 
 v4.1.3
-======
+------
 
 -  More helpful error message for PDFs with version 4 security handler
 -  Update usage instructions for Windows/Docker users
@@ -200,14 +231,14 @@ v4.1.3
 
 
 v4.1.2
-======
+------
 
 -  Replace IEC sRGB ICC profile with Debian's sRGB (from icc-profiles-free) which is more compatible with the MIT license
 -  More helpful error message for an error related to certain types of malformed PDFs
 
 
 v4.1
-====
+----
 
 -  ``--rotate-pages`` now only rotates pages when reasonably confidence in the orientation. This behavior can be adjusted with the new argument ``--rotate-pages-threshold``
 -  Fixed problems in error checking if ``unpaper`` is uninstalled or missing at run-time
@@ -215,20 +246,20 @@ v4.1
 
 
 v4.0.7
-======
+------
 
 -  Minor correction to Ghostscript output settings
 
 
 v4.0.6
-======
+------
 
 -  Update install instructions
 -  Provide a sRGB profile instead of using Ghostscript's
 
 
 v4.0.5
-======
+------
 
 -  Remove some verbose debug messages from v4.0.4
 -  Fixed temporary that wasn't being deleted
@@ -236,22 +267,22 @@ v4.0.5
 -  Inline images are now checked during DPI calculation instead of rejecting the image
 
 v4.0.4
-======
+------
 
 Released with verbose debug message turned on. Do not use. Skip to v4.0.5.
 
 
 v4.0.3
-======
+------
 
 New features
-------------
+^^^^^^^^^^^^
 
 -  Page orientations detected are now reported in a summary comment
 
 
 Fixes
------
+^^^^^
 
 -  Show stack trace if unexpected errors occur
 -  Treat "too few characters" error message from Tesseract as a reason to skip that page rather than
@@ -260,10 +291,10 @@ Fixes
 
 
 v4.0.2
-======
+------
 
 Fixes
------
+^^^^^
 
 -  Fixed compatibility with Tesseract 3.04.01 release, particularly its different way of outputting
    orientation information
@@ -272,19 +303,19 @@ Fixes
 
 
 v4.0.1
-======
+------
 
 Fixes
------
+^^^^^
 
 -  Fixed a KeyError if tesseract fails to find page orientation information
 
 
 v4.0
-====
+----
 
 New features
-------------
+^^^^^^^^^^^^
 
 -  Automatic page rotation (``-r``) is now available. It uses ignores any prior rotation information
    on PDFs and sets rotation based on the dominant orientation of detectable text. This feature is
@@ -294,7 +325,7 @@ New features
 
 
 Fixes
------
+^^^^^
 
 -  Fixed an issue where lossless reconstruction could cause some pages to be appear incorrectly
    if the page was rotated by the user in Acrobat after being scanned (specifically if it a /Rotate tag)
@@ -303,7 +334,7 @@ Fixes
 
 
 Changes
--------
+^^^^^^^
 
 -  Logging output is now much easier to read
 -  ``--deskew`` is now performed by Leptonica instead of unpaper (#25)
@@ -316,20 +347,20 @@ Changes
 
 
 v3.2.1
-======
+------
 
 Changes
--------
+^^^^^^^
 
 -  Fixed issue #47 "convert() got and unexpected keyword argument 'dpi'" by upgrading to img2pdf 0.2
 -  Tweaked the Dockerfiles
 
 
 v3.2
-====
+----
 
 New features
-------------
+^^^^^^^^^^^^
 
 -  Lossless reconstruction: when possible, OCRmyPDF will inject text layers without 
    otherwise manipulating the content and layout of a PDF page. For example, a PDF containing a mix
@@ -341,25 +372,25 @@ New features
    for the polyglots among us. It is much larger.
 
 Changes
--------
+^^^^^^^
 
 -  JPEG transcoding quality is now 95 instead of the default 75. Bigger file sizes for less degradation.
 
 
 
 v3.1.1
-======
+------
 
 Changes
--------
+^^^^^^^
 
 -  Fixed bug that caused incorrect page size and DPI calculations on documents with mixed page sizes
 
 v3.1
-====
+----
 
 Changes
--------
+^^^^^^^
 
 -  Default output format is now PDF/A-2b instead of PDF/A-1b
 -  Python 3.5 and macOS El Capitan are now supported platforms - no changes were
@@ -374,10 +405,10 @@ Changes
 -  Set up Travis CI automatic integration testing
 
 v3.0
-====
+----
 
 New features
-------------
+^^^^^^^^^^^^
 
 -  Easier installation with a Docker container or Python's ``pip`` package manager 
 -  Eliminated many external dependencies, so it's easier to setup
@@ -400,7 +431,7 @@ New features
 -  Multiple images on the same PDF page are now supported
 
 Changes
--------
+^^^^^^^
 
 -  New, robust rewrite in Python 3.4+ with ruffus_ pipelines
 -  Now uses Ghostscript 9.14's improved color conversion model to preserve PDF colors
@@ -438,7 +469,7 @@ Changes
 .. _JHOVE: http://jhove.sourceforge.net/
 
 Release candidates
-------------------
+^^^^^^^^^^^^^^^^^^
 
 -  rc9:
 
@@ -506,12 +537,12 @@ where ``settings.txt`` contains *one argument per line*, for example:
 
 
 Fixes
------
+^^^^^
 
 -  Handling of filenames containing spaces: fixed
 
 Notes and known issues
-----------------------
+^^^^^^^^^^^^^^^^^^^^^^
 
 -  Some dependencies may work with lower versions than tested, so try
    overriding dependencies if they are "in the way" to see if they work.
@@ -524,7 +555,7 @@ Notes and known issues
 
 
 v2.2-stable (2014-09-29)
-========================
+------------------------
 
 OCRmyPDF versions 1 and 2 were implemented as shell scripts. OCRmyPDF 3.0+ is a fork that gradually replaced all shell scripts with Python while maintaining the existing command line arguments. No one is maintaining old versions.
 

docs/security.rst

@@ -1,4 +1,4 @@
-PDF Security Issues
+PDF security issues
 ===================
 
 	OCRmyPDF should only be used on PDFs you trust. It is not designed to protect you against malware. 

ocrmypdf/__main__.py

@@ -46,6 +46,10 @@ def complain(message):
     print(*textwrap.wrap(message), file=sys.stderr)
 
 
+# Hack to help debugger context find /usr/local/bin
+if 'IDE_PROJECT_ROOTS' in os.environ:
+    os.environ['PATH'] = '/usr/local/bin:' + os.environ['PATH']
+
 if tesseract.version() < MINIMUM_TESS_VERSION:
     complain(
         "Please install tesseract {0} or newer "
@@ -53,7 +57,6 @@ if tesseract.version() < MINIMUM_TESS_VERSION:
             MINIMUM_TESS_VERSION, tesseract.version()))
     sys.exit(ExitCode.missing_dependency)
 
-
 # -------------
 # Parser
 
@@ -265,7 +268,7 @@ def check_options_languages(options, _log):
             "data for the following requested languages: \n")
         for lang in (set(options.language) - tesseract.languages()):
             msg += lang + '\n'
-        raise argparse.ArgumentError(msg)
+        raise argparse.ArgumentError(None, msg)
 
 
 def check_options_output(options, log):
@@ -291,7 +294,7 @@ def check_options_output(options, log):
             "--pdf-renderer=tesseract.")
 
     lossless_reconstruction = False
-    if options.pdf_renderer == 'hocr':
+    if options.pdf_renderer in ('hocr', 'tess4'):
         if not any((options.deskew, options.clean_final, options.force_ocr,
                    options.remove_background)):
             lossless_reconstruction = True
@@ -321,6 +324,7 @@ def check_options_preprocessing(options, log):
 def check_options_ocr_behavior(options, log):
     if options.force_ocr and options.skip_text:
         raise argparse.ArgumentError(
+            None,
             "Error: --force-ocr and --skip-text are mutually incompatible.")
 
     if set(options.language) & {'chi_sim', 'chi_tra'} and \
@@ -344,13 +348,31 @@ def check_options_advanced(options, log):
             "commit 3d9fb3b or later")
 
 
+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):
+        for c in s:
+            if unicodedata.category(c) == 'Co' or ord(c) >= 0x10000:
+                raise ValueError(
+                    "One of the metadata strings contains "
+                    "an unsupported Unicode character: '{}' (U+{})".format(
+                        c, hex(ord(c))[2:].upper()
+                ))
+
+
 def check_options(options, log):
     try:
         check_options_languages(options, log)
+        check_options_metadata(options, log)
         check_options_output(options, log)
         check_options_preprocessing(options, log)
         check_options_ocr_behavior(options, log)
         check_options_advanced(options, log)
+    except ValueError as e:
+        log.error(e)
+        sys.exit(ExitCode.bad_args)
     except argparse.ArgumentError as e:
         log.error(e)
         sys.exit(ExitCode.bad_args)
@@ -399,7 +421,7 @@ def available_cpu_count():
 
 
 def cleanup_ruffus_error_message(msg):
-    msg = re.sub(r'\s+', r' ', msg, re.MULTILINE)
+    msg = re.sub(r'\s+', r' ', msg)
     msg = re.sub(r"\((.+?)\)", r'\1', msg)
     msg = msg.strip()
     return msg

ocrmypdf/exceptions.py

@@ -48,7 +48,7 @@ class InputFileError(ExitCodeException):
 
 
 class SubprocessOutputError(ExitCodeException):
-    exit_code = ExitCode.other_error
+    exit_code = ExitCode.child_process_error
 
 
 class EncryptedPdfError(ExitCodeException):

ocrmypdf/exec/ghostscript.py

@@ -6,8 +6,9 @@ from subprocess import Popen, PIPE, STDOUT, check_call, CalledProcessError, \
     check_output
 from shutil import copy
 from functools import lru_cache
+import re
 from . import get_program
-from ..pdfa import SRGB_ICC_PROFILE
+from ..exceptions import SubprocessOutputError
 
 
 @lru_cache(maxsize=1)
@@ -28,6 +29,10 @@ def version():
     return version.strip()
 
 
+def _gs_error_reported(stream):
+    return re.search(r'error', stream, flags=re.IGNORECASE)
+
+
 def rasterize_pdf(input_file, output_file, xres, yres, raster_device, log,
                   pageno=1):
     with NamedTemporaryFile(delete=True) as tmp:
@@ -48,15 +53,16 @@ def rasterize_pdf(input_file, output_file, xres, yres, raster_device, log,
         p = Popen(args_gs, close_fds=True, stdout=PIPE, stderr=STDOUT,
                   universal_newlines=True)
         stdout, _ = p.communicate()
-        if 'error' in stdout:
+        if _gs_error_reported(stdout):
-            log.error(stdout)  # Ghostscript puts errors in stdout
+            log.error(stdout)
         else:
             log.debug(stdout)
 
         if p.returncode == 0:
             copy(tmp.name, output_file)
         else:
-            log.error('Ghostscript rendering failed')
+            log.error('Ghostscript rasterizing failed')
+            raise SubprocessOutputError()
 
 
 def generate_pdfa(pdf_pages, output_file, log, threads=1):
@@ -81,7 +87,7 @@ def generate_pdfa(pdf_pages, output_file, log, threads=1):
                   universal_newlines=True)
         stdout, _ = p.communicate()
 
-        if 'error' in stdout:
+        if _gs_error_reported(stdout):
             log.error(stdout)
         elif 'overprint mode not set' in stdout:
             # Unless someone is going to print PDF/A documents on a
@@ -99,4 +105,5 @@ def generate_pdfa(pdf_pages, output_file, log, threads=1):
             # PDF/A - check PDF/A status elsewhere
             copy(gs_pdf.name, output_file)
         else:
-            log.error('Ghostscript PDF/A failed')
+            log.error('Ghostscript PDF/A rendering failed')
+            raise SubprocessOutputError()

ocrmypdf/exec/tesseract.py

@@ -11,6 +11,7 @@ from ..helpers import page_number
 from . import get_program
 from collections import namedtuple
 from textwrap import dedent
+import PyPDF2 as pypdf
 
 from subprocess import Popen, PIPE, CalledProcessError, \
     TimeoutExpired, check_output, STDOUT, DEVNULL
@@ -186,6 +187,8 @@ def tesseract_log_output(log, stdout, input_file):
             log.warning(prefix + "unsure about page orientation")
         elif 'error' in line.lower() or 'exception' in line.lower():
             log.error(prefix + line.strip())
+        elif 'warning' in line.lower():
+            log.warning(prefix + line.strip())
         elif 'read_params_file' in line.lower():
             log.error(prefix + line.strip())
         else:
@@ -270,6 +273,24 @@ def generate_hocr(input_file, output_hocr, language: list, engine_mode,
                 f_out.write(line)
 
 
+def use_skip_page(text_only, skip_pdf, output_pdf):
+    if not text_only:
+        os.symlink(skip_pdf, output_pdf)
+        return
+
+    # For text only we must create a blank page with dimensions identical
+    # to the skip page because this is equivalent to a page with no text
+
+    pdf_in = pypdf.PdfFileReader(skip_pdf)
+    page0 = pdf_in.pages[0]
+
+    with open(output_pdf, 'wb') as out:
+        pdf_out = pypdf.PdfFileWriter()
+        w, h = page0.mediaBox.getWidth(), page0.mediaBox.getHeight()
+        pdf_out.addBlankPage(w, h)
+        pdf_out.write(out)
+
+
 def generate_pdf(input_image, skip_pdf, output_pdf, language: list,
                  engine_mode, text_only: bool,
                  tessconfig: list, timeout: float, pagesegmode: int, log):
@@ -307,14 +328,14 @@ def generate_pdf(input_image, skip_pdf, output_pdf, language: list,
             universal_newlines=True, timeout=timeout)
     except TimeoutExpired:
         page_timedout(log, input_image)
-        shutil.copy(skip_pdf, output_pdf)
+        use_skip_page(text_only, skip_pdf, output_pdf)
     except CalledProcessError as e:
         tesseract_log_output(log, e.output, input_image)
         if 'read_params_file: parameter not found' in e.output:
             raise TesseractConfigError() from e
 
         if 'Image too large' in e.output:
-            shutil.copy(skip_pdf, output_pdf)
+            use_skip_page(text_only, skip_pdf, output_pdf)
             return
         raise e from e
     else:

ocrmypdf/pageinfo.py

@@ -430,7 +430,7 @@ def _find_images(pdf, container, shorthand=None):
 
     """
 
-    if container.get('/Type') == '/Page':
+    if container.get('/Type') == '/Page' and '/Contents' in container:
         # For a /Page the content stream is attached to the page's /Contents
         page = container
         contentstream = pypdf.pdf.ContentStream(page.getContents(), pdf)
@@ -464,6 +464,9 @@ def _find_images(pdf, container, shorthand=None):
 
 
 def _page_has_text(pdf, page):
+    if not '/Contents' in page:
+        return False
+
     # Simple test
     text = page.extractText()
     if text.strip() != '':

ocrmypdf/pdfa.py

@@ -26,11 +26,7 @@ pdfa_def_template = u"""%!
 /ICCProfile ($icc_profile)
 def
 
-[ /Title <$title>
+[$docinfo
-  /Author <$author>
-  /Subject <$subject>
-  /Keywords <$keywords>
-  /Creator <$creator>
   /DOCINFO pdfmark
 
 % Define an ICC profile :
@@ -89,20 +85,30 @@ def encode_text_string(s: str) -> str:
 
 
 def _get_pdfa_def(icc_profile, icc_identifier, pdfmark):
-    pdfmark_utf16 = {k: encode_text_string(v) for k, v in pdfmark.items()}
+    # Ghostscript <= 9.21 has a bug where null entries in DOCINFO might produce
+    # ERROR: VMerror (-25) on closing pdfwrite device.
+    # https://bugs.ghostscript.com/show_bug.cgi?id=697684
+    # Work around this by only adding keys that have a nontrivial value
+    docinfo_keys = ('/Title', '/Author', '/Subject', '/Creator', '/Keywords')
+    docinfo_line_template = '  {key} <{value}>'
+
+    def docinfo_gen():
+        for key in docinfo_keys:
+            if key in pdfmark and pdfmark[key].strip() != '':
+                line = docinfo_line_template.format(
+                    key=key, value=encode_text_string(pdfmark[key]))
+                yield line
+
+    docinfo = '\n'.join(docinfo_gen())
 
     t = Template(pdfa_def_template)
     result = t.substitute(icc_profile=icc_profile,
                           icc_identifier=icc_identifier,
-                          title=pdfmark_utf16.get('/Title', ''),
+                          docinfo=docinfo)
-                          author=pdfmark_utf16.get('/Author', ''),
-                          subject=pdfmark_utf16.get('/Subject', ''),
-                          creator=pdfmark_utf16.get('/Creator', ''),
-                          keywords=pdfmark_utf16.get('/Keywords', ''))
     return result
 
 
-def generate_pdfa_def(target_filename, pdfmark, icc='sRGB'):
+def generate_pdfa_ps(target_filename, pdfmark, icc='sRGB'):
     if icc == 'sRGB':
         icc_profile = SRGB_ICC_PROFILE
     else:
@@ -116,6 +122,10 @@ def generate_pdfa_def(target_filename, pdfmark, icc='sRGB'):
         f.write(ps)
 
 
+# The old name is generate_pdfa_def -- now deprecated
+generate_pdfa_def = generate_pdfa_ps
+
+
 def file_claims_pdfa(filename):
     """Determines if the file claims to be PDF/A compliant
 

ocrmypdf/pipeline.py

@@ -23,7 +23,7 @@ from ruffus import formatter, regex, Pipeline, suffix
 
 from .hocrtransform import HocrTransform
 from .pageinfo import pdf_get_all_pageinfo
-from .pdfa import generate_pdfa_def, file_claims_pdfa
+from .pdfa import generate_pdfa_ps, file_claims_pdfa
 from .helpers import re_symlink, is_iterable_notstr, page_number
 from .exec import ghostscript, tesseract, qpdf
 from .exceptions import *
@@ -247,7 +247,7 @@ def is_ocr_required(pageinfo, log, options):
                                 "skipping all processing on this page"))
             ocr_required = False
 
-    if ocr_required and options.skip_big:
+    if ocr_required and options.skip_big and pageinfo['images']:
         pixel_count = pageinfo['width_pixels'] * pageinfo['height_pixels']
         if pixel_count > (options.skip_big * 1000000):
             ocr_required = False
@@ -393,15 +393,16 @@ def rasterize_with_ghostscript(
     pageinfo = get_pageinfo(input_file, context)
 
     device = 'png16m'  # 24-bit
-    if all(image['comp'] == 1 for image in pageinfo['images']):
+    if pageinfo['images']:
-        if all(image['bpc'] == 1 for image in pageinfo['images']):
+        if all(image['comp'] == 1 for image in pageinfo['images']):
-            device = 'pngmono'
+            if all(image['bpc'] == 1 for image in pageinfo['images']):
-        elif all(image['bpc'] > 1 and image['color'] == 'index'
+                device = 'pngmono'
-                 for image in pageinfo['images']):
+            elif all(image['bpc'] > 1 and image['color'] == 'index'
-            device = 'png256'
+                     for image in pageinfo['images']):
-        elif all(image['bpc'] > 1 and image['color'] == 'gray'
+                device = 'png256'
-                 for image in pageinfo['images']):
+            elif all(image['bpc'] > 1 and image['color'] == 'gray'
-            device = 'pnggray'
+                     for image in pageinfo['images']):
+                device = 'pnggray'
 
     log.debug("Rasterize {0} with {1}".format(
               os.path.basename(input_file), device))
@@ -517,7 +518,8 @@ def select_visible_page_image(
     image = next(ii for ii in infiles if ii.endswith(image_suffix))
 
     pageinfo = get_pageinfo(image, context)
-    if all(orig_image['enc'] == 'jpeg' for orig_image in pageinfo['images']):
+    if pageinfo['images'] and \
+            all(im['enc'] == 'jpeg' for im in pageinfo['images']):
         # If all images were JPEGs originally, produce a JPEG as output
         im = Image.open(image)
 
@@ -767,13 +769,14 @@ def generate_postscript_stub(
     options = context.get_options()
     pdf = pypdf.PdfFileReader(input_file)
     pdfmark = get_pdfmark(pdf, options)
-    generate_pdfa_def(output_file, pdfmark)
+    generate_pdfa_ps(output_file, pdfmark)
 
 
 def skip_page(
         input_file,
         output_file,
-        log):
+        log,
+        context):
     # The purpose of this step is its filter to forward only the skipped
     # files (.skip.oriented.pdf) while disregarding the processed ones
     # (.ocr.oriented.pdf).  Alternative would be for merge_pages to filter
@@ -1036,7 +1039,7 @@ def build_pipeline(options, work_folder, log, context):
         task_func=generate_postscript_stub,
         input=task_repair_pdf,
         filter=formatter(r'\.repaired\.pdf'),
-        output=os.path.join(work_folder, 'pdfa_def.ps'),
+        output=os.path.join(work_folder, 'pdfa.ps'),
         extras=[log, context])
     task_generate_postscript_stub.active_if(options.output_type == 'pdfa')
 
@@ -1048,7 +1051,7 @@ def build_pipeline(options, work_folder, log, context):
         filter=suffix('.skip.oriented.pdf'),
         output='.done.pdf',
         output_dir=work_folder,
-        extras=[log])
+        extras=[log, context])
 
     # Merge pages
     task_merge_pages_ghostscript = main_pipeline.merge(

tests/resources/README.rst

@@ -85,6 +85,9 @@ 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
+        - @jbarlow83
+        - synthetic PDF with a blank page that has no /Contents entry
 
 Assemblies
 ==========

tests/resources/no_contents.pdf

@@ -0,0 +1,21 @@
+%PDF-1.3
+%¿÷¢þ
+1 0 obj
+<< /Pages 2 0 R /Type /Catalog >>
+endobj
+2 0 obj
+<< /Count 1 /Kids [ 3 0 R ] /Type /Pages >>
+endobj
+3 0 obj
+<< /MediaBox [ 0 0 720 720 ] /Parent 2 0 R /Resources << >> /Type /Page >>
+endobj
+xref
+0 4
+0000000000 65535 f 
+0000000015 00000 n 
+0000000064 00000 n 
+0000000123 00000 n 
+trailer << /Root 1 0 R /Size 4 /ID [<52bba3c78160d0c6e851b59110e5d076><52bba3c78160d0c6e851b59110e5d076>] >>
+startxref
+213
+%%EOF

tests/spoof/gs_raster_failure.py

@@ -0,0 +1,31 @@
+#!/usr/bin/env python3
+import sys
+import os
+
+"""Replicate Ghostscript raster failure while allowing rendering"""
+
+
+def real_ghostscript(argv):
+    gs_args = ['gs'] + argv[1:]
+    os.execvp("gs", gs_args)
+    return  # Not reachable
+
+
+def main():
+    if '--version' in sys.argv:
+        print('9.20')
+        print('SPOOFED: ' + os.path.basename(__filename__))
+        sys.exit(0)
+
+    # For any rendering calls (device == pdfwrite) call real ghostscript
+    if '-sDEVICE=pdfwrite' in sys.argv:
+        real_ghostscript(sys.argv)
+        return
+
+    # Fail
+    print("ERROR: Ghost story archive not found")
+    sys.exit(1)
+
+
+if __name__ == '__main__':
+    main()

tests/spoof/gs_render_failure.py

@@ -0,0 +1,31 @@
+#!/usr/bin/env python3
+import sys
+import os
+
+"""Replicate Ghostscript render failure while allowing rasterizing"""
+
+
+def real_ghostscript(argv):
+    gs_args = ['gs'] + argv[1:]
+    os.execvp("gs", gs_args)
+    return  # Not reachable
+
+
+def main():
+    if '--version' in sys.argv:
+        print('9.20')
+        print('SPOOFED: ' + os.path.basename(__filename__))
+        sys.exit(0)
+
+    # For any rasterize calls (device != pdfwrite) call real ghostscript
+    if '-sDEVICE=pdfwrite' not in sys.argv:
+        real_ghostscript(sys.argv)
+        return
+
+    # Fail
+    print("ERROR: Casper is not a friendly ghost")
+    sys.exit(1)
+
+
+if __name__ == '__main__':
+    main()

tests/test_main.py

@@ -51,6 +51,16 @@ def spoof_no_tess_pdfa_warning():
     return spoof(tesseract='tesseract_noop.py', gs='gs_feature_elision.py')
 
 
+@pytest.fixture
+def spoof_no_tess_gs_render_fail():
+    return spoof(tesseract='tesseract_noop.py', gs='gs_render_failure.py')
+
+
+@pytest.fixture
+def spoof_no_tess_gs_raster_fail():
+    return spoof(tesseract='tesseract_noop.py', gs='gs_raster_failure.py')
+
+
 @pytest.fixture
 def spoof_qpdf_always_error():
     return spoof(qpdf='qpdf_dummy_return2.py')
@@ -167,55 +177,50 @@ def test_preserve_metadata(spoof_tesseract_noop, output_type,
     assert pdfa_info['output'] == output_type
 
 
-@pytest.mark.skipif(
-    pytest.helpers.is_linux() and not pytest.helpers.running_in_docker(),
-    reason="likely to fail if Linux locale is not configured correctly")
-@pytest.mark.skipif(
-    pytest.helpers.is_macos() and pytest.helpers.running_in_travis(),
-    reason="save Travis the trouble of installing poppler")
-@pytest.mark.xfail(
-    ghostscript.version() == '9.21',
-    reason="gs 9.21 has a regression that affects this"
-    )
 @pytest.mark.parametrize("output_type", [
     'pdfa', 'pdf'
     ])
 def test_override_metadata(spoof_tesseract_noop, output_type, resources,
                            outpdf):
     input_file = resources / 'c02-22.pdf'
-
     german = 'Du siehst den Wald vor lauter Bäumen nicht.'
     chinese = '孔子'
-    high_unicode = 'U+1030C is: 𐌌'
 
     p, out, err = run_ocrmypdf(
         input_file, outpdf,
         '--title', german,
         '--author', chinese,
-        '--subject', high_unicode,
         '--output-type', output_type,
         env=spoof_tesseract_noop)
 
     assert p.returncode == ExitCode.ok, err
 
-    pdf = str(outpdf)
+    reader = pypdf.PdfFileReader(outpdf)
 
-    out_pdfinfo = check_output(['pdfinfo', pdf], universal_newlines=True)
+    assert reader.documentInfo['/Title'] == german
-    lines_pdfinfo = out_pdfinfo.splitlines()
+    assert reader.documentInfo['/Author'] == chinese
-    pdfinfo = {}
+    assert reader.documentInfo.get('/Keywords', '') == ''
-    for line in lines_pdfinfo:
-        k, v = line.strip().split(':', maxsplit=1)
-        pdfinfo[k.strip()] = v.strip()
 
-    assert pdfinfo['Title'] == german
+    pdfa_info = file_claims_pdfa(outpdf)
-    assert pdfinfo['Author'] == chinese
-    assert pdfinfo['Subject'] == high_unicode
-    assert pdfinfo.get('Keywords', '') == ''
-
-    pdfa_info = file_claims_pdfa(pdf)
     assert pdfa_info['output'] == output_type
 
 
+def test_high_unicode(spoof_tesseract_noop, resources, no_outpdf):
+
+    # Ghostscript doesn't support high Unicode, so neither do we, to be
+    # safe
+    input_file = resources / 'c02-22.pdf'
+    high_unicode = 'U+1030C is: 𐌌'
+
+    p, out, err = run_ocrmypdf(
+        input_file, no_outpdf,
+        '--subject', high_unicode,
+        '--output-type', 'pdfa',
+        env=spoof_tesseract_noop)
+
+    assert p.returncode == ExitCode.bad_args, err
+
+
 @pytest.mark.parametrize('renderer', [
     'hocr',
     'tesseract',
@@ -842,3 +847,31 @@ def test_pagesize_consistency(renderer, resources, outpdf):
 
     assert isclose(before_dims[0], after_dims[0])
     assert isclose(before_dims[1], after_dims[1])
+
+
+def test_skip_big_with_no_images(spoof_tesseract_noop, resources, outpdf):
+    check_ocrmypdf(resources / 'blank.pdf', outpdf,
+                   '--skip-big', '5',
+                   '--force-ocr',
+                   env=spoof_tesseract_noop)
+
+
+def test_gs_render_failure(spoof_no_tess_gs_render_fail, resources, outpdf):
+    p, out, err = run_ocrmypdf(
+        resources / 'blank.pdf', outpdf,
+        env=spoof_no_tess_gs_render_fail)
+    print(err)
+    assert p.returncode == ExitCode.child_process_error
+
+
+def test_gs_raster_failure(spoof_no_tess_gs_raster_fail, resources, outpdf):
+    p, out, err = run_ocrmypdf(
+        resources / 'ccitt.pdf', outpdf,
+        env=spoof_no_tess_gs_raster_fail)
+    print(err)
+    assert p.returncode == ExitCode.child_process_error
+
+
+def test_no_contents(spoof_tesseract_noop, resources, outpdf):
+    check_ocrmypdf(resources / 'no_contents.pdf', outpdf, '--force-ocr',
+                   env=spoof_tesseract_noop)

tests/test_pageinfo.py

@@ -108,3 +108,11 @@ def test_form_xobject(resources):
     pdfinfo = pageinfo.pdf_get_all_pageinfo(str(filename))
     pdfimage = pdfinfo[0]['images'][0]
     assert pdfimage['width'] == 50
+
+
+def test_no_contents(resources):
+    filename = resources / 'no_contents.pdf'
+
+    pdfinfo = pageinfo.pdf_get_all_pageinfo(str(filename))
+    assert len(pdfinfo[0]['images']) == 0
+    assert pdfinfo[0]['has_text'] == False

tests/test_tess4.py

@@ -6,11 +6,42 @@ from ocrmypdf.exceptions import ExitCode
 from ocrmypdf.exec import tesseract
 from ocrmypdf import pageinfo
 import sys
+import os
+import PyPDF2 as pypdf
+
+
+spoof = pytest.helpers.spoof
+
+
+def tess4_possible_location():
+    """The location of tesseract 4 may be OCRMYPDF_TESS4, OCRMYPDF_TESSERACT,
+    or the installed version on PATH."""
+    return os.environ.get('OCRMYPDF_TESS4') or \
+           os.environ.get('OCRMYPDF_TESSERACT') or \
+            'tesseract'
+
+
+@pytest.fixture
+def ensure_tess4():
+    return spoof(tesseract=tess4_possible_location())
+
+
+def tess4_available():
+    """Check if a tesseract 4 binary is available, even if it's not the
+    official "tesseract" on PATH
+
+    """
+    old_environ = os.environ.copy()
+    try:
+        os.environ['OCRMYPDF_TESSERACT'] = tess4_possible_location()
+        return tesseract.v4() and tesseract.has_textonly_pdf()
+    finally:
+        os.environ = old_environ
 
 
 # Skip all tests in this file if not tesseract 4
 pytestmark = pytest.mark.skipif(
-    not (tesseract.v4() and tesseract.has_textonly_pdf()),
+    not tess4_available(),
     reason="tesseract 4.0 with textonly_pdf feature required")
 
 check_ocrmypdf = pytest.helpers.check_ocrmypdf
@@ -18,14 +49,15 @@ run_ocrmypdf = pytest.helpers.run_ocrmypdf
 spoof = pytest.helpers.spoof
 
 
-def test_textonly_pdf(resources, outdir):
+def test_textonly_pdf(ensure_tess4, resources, outdir):
     check_ocrmypdf(
         resources / 'linn.pdf',
-        outdir / 'linn_textonly.pdf', '--pdf-renderer', 'tess4')
+        outdir / 'linn_textonly.pdf', '--pdf-renderer', 'tess4',
+        env=ensure_tess4)
 
 
 @pytest.mark.skipif(sys.version_info < (3, 5), reason="needs math.isclose")
-def test_pagesize_consistency_tess4(resources, outpdf):
+def test_pagesize_consistency_tess4(ensure_tess4, resources, outpdf):
     from math import isclose
 
     infile = resources / 'linn.pdf'
@@ -35,9 +67,47 @@ def test_pagesize_consistency_tess4(resources, outpdf):
     check_ocrmypdf(
         infile,
         outpdf, '--pdf-renderer', 'tess4',
-        '--clean', '--deskew', '--remove-background', '--clean-final')
+        '--clean', '--deskew', '--remove-background', '--clean-final',
+        env=ensure_tess4)
 
     after_dims = pytest.helpers.first_page_dimensions(outpdf)
 
     assert isclose(before_dims[0], after_dims[0])
     assert isclose(before_dims[1], after_dims[1])
+
+
+@pytest.mark.parametrize('basename', ['graph_ocred.pdf', 'cardinal.pdf'])
+def test_skip_pages_does_not_replicate(
+        ensure_tess4, resources, basename, outdir):
+    infile = resources / basename
+    outpdf = outdir / basename
+
+    check_ocrmypdf(
+        infile,
+        outpdf, '--pdf-renderer', 'tess4', '--force-ocr',
+        '--tesseract-timeout', '0',
+        env=ensure_tess4
+    )
+
+    info_in = pageinfo.pdf_get_all_pageinfo(str(infile))
+
+    info = pageinfo.pdf_get_all_pageinfo(str(outpdf))
+    for page in info:
+        assert len(page['images']) == 1, "skipped page was replicated"
+
+    for n in range(len(info_in)):
+        assert info[n]['width_inches'] == info_in[n]['width_inches']
+
+
+def test_content_preservation(ensure_tess4, resources, outpdf):
+    infile = resources / 'masks.pdf'
+
+    check_ocrmypdf(
+        infile,
+        outpdf, '--pdf-renderer', 'tess4', '--tesseract-timeout', '0',
+        env=ensure_tess4
+    )
+
+    info = pageinfo.pdf_get_all_pageinfo(str(outpdf))
+    page = info[0]
+    assert len(page['images']) > 1, "masked were rasterized"