v9.6.1 release notes

User submitted a PDF in which /Trailer /Info pointed to the XMP metadata
block instead of a DocumentInfo dictionary. Fix and add test.

.travis.yml

@@ -1,159 +0,0 @@
-branches:
-  except:
-    - azure
-
-cache:
-  pip: true
-  directories:
-    - $HOME/Library/Caches/Homebrew
-
-matrix:
-  include:
-    - os: linux
-      dist: trusty
-      sudo: required
-      language: python
-      python: "3.6"
-      env:
-        - DIST=trusty
-        - MINIMAL=true
-      addons:
-        apt:
-          update: true
-          sources:
-            - sourceline: "ppa:alex-p/tesseract-ocr"
-            - sourceline: "ppa:vshn/ghostscript"
-          packages:
-            - ghostscript
-            - libffi-dev
-            - tesseract-ocr
-            - tesseract-ocr-deu
-            - tesseract-ocr-eng
-            - tesseract-ocr-fra
-      before_install: |
-        pip3 install --upgrade pip
-        pip3 install --upgrade wheel
-    - os: linux
-      dist: trusty
-      sudo: required
-      language: python
-      python: "3.6"
-      env:
-        - DIST=trusty
-      addons:
-        apt:
-          update: true
-          sources:
-            - sourceline: "ppa:alex-p/tesseract-ocr"
-            - sourceline: "ppa:heyarje/libav-11"
-            - sourceline: "ppa:vshn/ghostscript"
-          packages:
-            - ghostscript
-            - libavcodec56
-            - libavformat56
-            - libavutil54
-            - libffi-dev
-            - tesseract-ocr
-            - tesseract-ocr-deu
-            - tesseract-ocr-eng
-            - tesseract-ocr-fra
-            - libexempi3 # --- optional extras from here ---
-            - pngquant
-            - poppler-utils
-      before_install: |
-        mkdir -p bin packages
-        pip3 install --upgrade pip
-        pip3 install --upgrade wheel
-    - os: linux
-      dist: xenial
-      sudo: required
-      language: python
-      python: "3.7"
-      env:
-        - DIST=xenial
-      addons:
-        apt:
-          update: true
-          sources:
-            - sourceline: "ppa:alex-p/tesseract-ocr"
-          packages:
-            - ghostscript
-            - libexempi3
-            - libffi-dev
-            - pngquant
-            - poppler-utils
-            - tesseract-ocr
-            - tesseract-ocr-deu
-            - tesseract-ocr-eng
-            - tesseract-ocr-fra
-            - unpaper
-    - os: linux
-      dist: bionic
-      sudo: required
-      language: python
-      python: "3.8"
-      env:
-        - DIST=bionic
-      addons:
-        apt:
-          update: true
-          sources:
-            - sourceline: "ppa:alex-p/tesseract-ocr"
-          packages:
-            - ghostscript
-            - libexempi3
-            - libffi-dev
-            - pngquant
-            - poppler-utils
-            - tesseract-ocr
-            - tesseract-ocr-deu
-            - tesseract-ocr-eng
-            - tesseract-ocr-fra
-            - unpaper
-    - os: osx
-      language: generic
-      addons:
-        homebrew:
-          update: true
-          packages:
-            - exempi
-            - ghostscript
-            - jbig2enc
-            - leptonica
-            - openjpeg
-            - pngquant
-            - python
-            - qpdf
-            - tesseract
-            - unpaper
-      before_install: |
-        pip3 install --upgrade pip
-        pip3 install wheel
-
-before_cache:
-  - rm -f $HOME/.cache/pip/log/debug.log
-
-install:
-  - mkdir -p bin
-  - export PATH=$PWD/bin:$PATH
-  - pip3 install -r requirements/main.txt -r requirements/test.txt .
-
-script:
-  - tesseract --version
-  - pytest -n auto
-# deploy:
-#   # release for main pypi
-#   # 3.7 is considered the build leader and does the deploy, otherwise there is
-#   # a race and all versions will try to deploy
-#   # OTOH if we ever need separate binary wheels then each version needs its
-#   # own deploy
-#   - provider: pypi
-#     user: ocrmypdf-travis
-#     password:
-#       secure: "DTFOmmNL6olA0+yXvp4u9jXZlZeqrJsJ0526jzqf4a3gZ6jnGTq5UI6WzRsslSyoMMfXKtHQebqHM6ogSgCZinyZ3ufHJo8fn9brxbEc2gsiWkbj5o3bGwdWMT1vNNE7XW0VCpw87rZ1EEwjl4FJHFudMlPR1yfU5+uq0k0PACo="
-#     distributions: "sdist bdist_wheel"
-#     on:
-#       branch: master
-#       tags: true
-#       condition: $TRAVIS_PYTHON_VERSION == "3.7" && $TRAVIS_OS_NAME == "linux"
-#     skip_upload_docs: true

README.md

@@ -130,6 +130,7 @@ Press & Media
 - [Converting a scanned document into a compressed searchable PDF with redactions](https://medium.com/@treyharris/converting-a-scanned-document-into-a-compressed-searchable-pdf-with-redactions-63f61c34fe4c)
 - [c't 1-2014, page 59](https://heise.de/-2279695): Detailed presentation of OCRmyPDF v1.0 in the leading German IT magazine c't
 - [heise Open Source, 09/2014: Texterkennung mit OCRmyPDF](https://heise.de/-2356670)
+- [heise Durchsuchbare PDF-Dokumente mit OCRmyPDF erstellen](https://www.heise.de/ratgeber/Durchsuchbare-PDF-Dokumente-mit-OCRmyPDF-erstellen-4607592.html)
 
 Business enquiries
 ------------------

debian/copyright

@@ -95,12 +95,6 @@ Files: tests/resources/vector.pdf
 Copyright: (C) 2018 Catscratch
 License: Expat
 
-Files: test/resources/enron*.pdf
-Copyright: EnronData.org
-License: CC-BY-3.0
- See: https://enrondata.readthedocs.io/en/latest/data/edo-enron-email-pst-dataset/
-Comment: Unprocessed.
-
 Files: src/ocrmypdf/data/sRGB.icc
 Copyright:  Kai-Uwe Behrmann <www.behrmann.name>
             Marti Maria <www.littlecms.com>

docs/batch.rst

@@ -69,53 +69,8 @@ Sample script
 This user contributed script also provides an example of batch
 processing.
 
-.. code-block:: python
-
-   #!/usr/bin/env python3
-   # Walk through directory tree, replacing all files with OCR'd version
-   # Original version by DeliciousPickle@github; modified
-
-   import logging
-   import os
-   import subprocess
-   import sys
-
-   import ocrmypdf
-
-   script_dir = os.path.dirname(os.path.realpath(__file__))
-   print(script_dir + '/ocr-tree.py: Start')
-
-   if len(sys.argv) > 1:
-       start_dir = sys.argv[1]
-   else:
-       start_dir = '.'
-
-   if len(sys.argv) > 2:
-       log_file = sys.argv[2]
-   else:
-       log_file = script_dir + '/ocr-tree.log'
-
-   logging.basicConfig(
-           level=logging.INFO, format='%(asctime)s %(message)s',
-           filename=log_file, filemode='w')
-
-   ocrmypdf.configure_logging(ocrmypdf.Verbosity.default)
-
-   for dir_name, subdirs, file_list in os.walk(start_dir):
-       logging.info('\n')
-       logging.info(dir_name + '\n')
-       os.chdir(dir_name)
-       for filename in file_list:
-           file_ext = os.path.splitext(filename)[1]
-           if file_ext == '.pdf':
-               full_path = dir_name + '/' + filename
-               print(full_path)
-               result = ocrmypdf.ocr(filename, filename, deskew=True)
-               if result == ocrmypdf.ExitCode.already_done_ocr:
-                   print("Skipped document because it already contained text")
-               elif result == ocrmypdf.ExitCode.ok:
-                   print("OCR complete")
-               logging.info(result)
+.. literalinclude:: ../misc/batch.py
+    :caption: misc/batch.py
 
 Synology DiskStations
 ---------------------
@@ -131,62 +86,8 @@ products use ARM or Power processors and do not support Docker. Further
 adjustments might be needed to deal with the Synology's relatively
 limited CPU and RAM.
 
-.. code-block:: python
-
-   #!/bin/env python3
-   # Contributed by github.com/Enantiomerie
-
-   # script needs 2 arguments
-   # 1. source dir with *.pdf - default is location of script
-   # 2. move dir where *.pdf and *_OCR.pdf are moved to
-
-   import logging
-   import os
-   import subprocess
-   import sys
-   import time
-   import shutil
-
-   script_dir = os.path.dirname(os.path.realpath(__file__))
-   timestamp = time.strftime("%Y-%m-%d-%H%M_")
-   log_file = script_dir + '/' + timestamp + 'ocrmypdf.log'
-   logging.basicConfig(level=logging.INFO, format='%(asctime)s %(message)s', filename=log_file, filemode='w')
-
-   if len(sys.argv) > 1:
-       start_dir = sys.argv[1]
-   else:
-       start_dir = '.'
-
-   for dir_name, subdirs, file_list in os.walk(start_dir):
-       logging.info('\n')
-       logging.info(dir_name + '\n')
-       os.chdir(dir_name)
-       for filename in file_list:
-           file_ext = os.path.splitext(filename)[1]
-           if file_ext == '.pdf':
-               full_path = dir_name + '/' + filename
-               file_noext = os.path.splitext(filename)[0]
-               timestamp_OCR = time.strftime("%Y-%m-%d-%H%M_OCR_")
-               filename_OCR = timestamp_OCR + file_noext + '.pdf'
-               docker_mount = dir_name + ':/home/docker'
-   # create string for pdf processing
-   # diskstation needs a user:group docker:docker. find uid:gid of your diskstation docker:docker with id docker.
-   # use this uid:gid in -u flag
-   # rw rights for docker:docker at source dir are also necessary
-   # the script is processed as root user via chron
-               cmd = ['docker', 'run', '--rm', '-v', docker_mount, '-u=1030:65538', 'jbarlow83/ocrmypdf', , '--deskew' , filename, filename_OCR]
-               logging.info(cmd)
-               proc = subprocess.run(cmd, stdout=subprocess.PIPE, stderr=subprocess.STDOUT)
-               result = proc.stdout.read()
-               logging.info(result)
-               full_path_OCR = dir_name + '/' + filename_OCR
-               os.chmod(full_path_OCR, 0o666)
-               os.chmod(full_path, 0o666)
-               full_path_OCR_archive = sys.argv[2]
-               full_path_archive = sys.argv[2] + '/no_ocr'
-               shutil.move(full_path_OCR,full_path_OCR_archive)
-               shutil.move(full_path, full_path_archive)
-   logging.info('Finished.\n')
+.. literalinclude:: ../misc/synology.py
+    :caption: misc/synology.py - Sample script for Synology DiskStations
 
 Huge batch jobs
 ---------------
@@ -235,14 +136,21 @@ This service relies on polling to check for changes to the filesystem. It
 may not be suitable for some environments, such as filesystems shared on a
 slow network.
 
+A configuration manager such as Docker Compose could be used to ensure that the
+service is always available.
+
+.. literalinclude:: ../misc/docker-compose.example.yml
+    :language: yaml
+    :caption: misc/docker-compose.example.yml
+
 Watched folders with watcher.py
 -------------------------------
 
-The watcher service may also be run natively.
+The watcher service may also be run natively, without Docker:
 
 .. code-block:: bash
 
-    pip3 install -r reqs/watcher.txt
+    pip3 install -r requirements/watcher.txt
 
     env OCR_INPUT_DIRECTORY=/mnt/input-pdfs \
         OCR_OUTPUT_DIRECTORY=/mnt/output-pdfs \
@@ -319,8 +227,7 @@ of Automator, the ``PATH`` may be set differently your Terminal's
 ``PATH``; you may need to explicitly set the PATH to include
 ``ocrmypdf``. The following example may serve as a starting point:
 
-|Example macOS Automator script|
+.. figure:: images/macos-workflow.png
+    :alt: Example macOS Automator workflow
 
 You may customize the command sent to ocrmypdf.
-
-.. |Example macOS Automator script| image:: images/macos-workflow.png

docs/cookbook.rst

@@ -237,6 +237,32 @@ You can also optimize all images without performing any OCR:
 
     ocrmypdf --tesseract-timeout=0 --optimize 3 --skip-text input.pdf output.pdf
 
+Perform OCR only certain pages
+------------------------------
+
+You can ask OCRmyPDF to only apply OCR to certain pages.
+
+.. code-block:: bash
+
+    ocrmypdf --pages 2,3,13-17 input.pdf output.pdf
+
+Hyphens denote a range of pages and commas separate page numbers. If you prefer
+to use spaces, quote all of the page numbers: ``--pages '2, 3, 5, 7'``.
+
+OCRmyPDF will warn if your list of page numbers contains duplicates or
+overlap pages. OCRmyPDF does not currently account for document page numbers,
+such as an introduction section of a book that uses Roman numerals. It simply
+counts the number of virtual pieces of paper since the start.
+
+Regardless of the argument to ``--pages``, OCRmyPDF will optimize all pages in
+the file and convert it to PDF/A, unless you disable those options. In this
+example, we want to OCR only the title and otherwise change the PDF as little
+as possible:
+
+.. code-block:: bash
+
+    ocrmypdf --pages 1 --output-type pdf --optimize 0 input.pdf output.pdf
+
 Redo existing OCR
 =================
 

docs/docker.rst

@@ -56,35 +56,34 @@ See the Docker documentation for
 Using the Docker image on the command line
 ==========================================
 
-**Unlike typical Docker containers**, in this mode we are using the
-OCRmyPDF Docker container is intended to be emphemeral – it runs for one
-OCR job and then terminates, just like a command line program. We are
-using Docker as a way of delivering an application, not a server.
+**Unlike typical Docker containers**, in this section the OCRmyPDF Docker
+container is emphemeral – it runs for one OCR job and terminates, just like a
+command line program. We are using Docker to deliver an application (as opposed
+to the more conventional case, where a Docker container runs as a server).
 
 To start a Docker container (instance of the image):
 
 .. code-block:: bash
 
    docker tag jbarlow83/ocrmypdf ocrmypdf
-   docker run --rm -i ocrmypdf (... all other arguments here...)
+   docker run --rm -i ocrmypdf (... all other arguments here...) - -
 
 For convenience, create a shell alias to hide the Docker command. It is
-easier to send the input file to file stdin and read the output from
-stdout – this avoids the occasionally messy permission issues with
-Docker entirely.
+easier to send the input file as stdin and read the output from
+stdout – **this avoids the messy permission issues with Docker entirely**.
 
 .. code-block:: bash
 
-   alias ocrmypdf='docker run --rm -i ocrmypdf'
-   ocrmypdf --version  # runs docker version
-   ocrmypdf <input.pdf >output.pdf
+   alias docker_ocrmypdf='docker run --rm -i ocrmypdf'
+   docker_ocrmypdf --version  # runs docker version
+   docker_ocrmypdf - - <input.pdf >output.pdf
 
 Or in the wonderful `fish shell <https://fishshell.com/>`__:
 
 .. code-block:: fish
 
-   alias ocrmypdf 'docker run --rm ocrmypdf'
-   funcsave ocrmypdf
+   alias docker_ocrmypdf 'docker run --rm ocrmypdf'
+   funcsave docker_ocrmypdf
 
 Alternately, you could mount the local current working directory as a
 Docker volume:
@@ -93,15 +92,18 @@ Docker volume:
 
    docker run --rm -v $(pwd):/data ocrmypdf /data/input.pdf /data/output.pdf
 
+(However, when done this way, ``output.pdf`` may be owned by the root
+user.)
+
 .. _docker-lang-packs:
 
 Adding languages to the Docker image
 ====================================
 
-By default the Docker image includes English, German and Simplified
-Chinese, the most popular languages for OCRmyPDF users based on
-feedback. You may add other languages by creating a new Dockerfile based
-on the public one:
+By default the Docker image includes English, German, Simplified Chinese,
+French, Portuguese and Spanish, the most popular languages for OCRmyPDF
+users based on feedback. You may add other languages by creating a new
+Dockerfile based on the public one:
 
 .. code-block:: dockerfile
 

docs/index.rst

@@ -1,8 +1,8 @@
 OCRmyPDF documentation
 ======================
 
-OCRmyPDF adds an OCR text layer to scanned PDF files, allowing them to
-be searched.
+OCRmyPDF adds an optical charcter recognition (OCR) text layer to scanned PDF
+files, allowing them to be searched.
 
 PDF is the best format for storing and exchanging scanned documents.
 Unfortunately, PDFs can be difficult to modify. OCRmyPDF makes it easy to apply

docs/installation.rst

@@ -110,7 +110,7 @@ Fedora 29 or newer
 | |fedora-29| |fedora-30| |fedora-rawhide|      |
 +-----------------------------------------------+
 
-Users of Fedora 29 later may simply
+Users of Fedora 29 or later may simply
 
 .. code-block:: bash
 
@@ -136,8 +136,9 @@ from sources <#installing-head-revision-from-sources>`__.
 Installing the latest version on Ubuntu 18.04 LTS
 -------------------------------------------------
 
-Ubuntu 18.04 includes ocrmypdf 6.1.2. To install a more recent version,
-first install the system version to get most of the dependencies:
+Ubuntu 18.04 includes ocrmypdf 6.1.2 - you can install that with ``apt``, but
+it is quite old now. To install a more recent version, first install several
+system dependencies:
 
 .. code-block:: bash
 
@@ -216,7 +217,8 @@ of ``pip`` at ``/usr/local/bin/pip``.
 **Install OCRmyPDF**
 
 OCRmyPDF requires the locale to be set for UTF-8. **On some minimal
-Ubuntu installations systems**, it may be necessary to set the locale.
+Ubuntu installations**, such as the Ubuntu 16.04 Docker images it may be
+necessary to set the locale.
 
 .. code-block:: bash
 
@@ -296,23 +298,86 @@ compiled by hand.
 
 To add JBIG2 encoding, see :ref:`jbig2`.
 
-ArchLinux (AUR)
----------------
+Arch Linux (AUR)
+----------------
 
 .. image:: https://repology.org/badge/version-for-repo/aur/ocrmypdf.svg
     :alt: ArchLinux
     :target: https://repology.org/metapackage/ocrmypdf
 
-There is an `ArchLinux User Repository package for
-ocrmypdf <https://aur.archlinux.org/packages/ocrmypdf/>`__. You can use
-the following command.
+There is an `Arch User Repository (AUR) package for OCRmyPDF
+<https://aur.archlinux.org/packages/ocrmypdf/>`__.
+
+Installing AUR packages as root is not allowed, so you must first `setup a
+non-root user
+<https://wiki.archlinux.org/index.php/Users_and_groups#User_management>`__ and
+`configure sudo <https://wiki.archlinux.org/index.php/Sudo#Configuration>`__.
+The standard Docker image, ``archlinux/base:latest``, does **not** have a
+non-root user configured, so users of that image must follow these guides. If
+you are using a VM image, such as `the official Vagrant image
+<https://app.vagrantup.com/archlinux/boxes/archlinux>`__, this work may already
+be completed for you.
+
+Next you should install the `base-devel package group
+<https://www.archlinux.org/groups/x86_64/base-devel/>`__. This includes the
+standard tooling needed to build packages, such as a compiler and binary tools.
 
 .. code-block:: bash
 
-    yaourt -S ocrmypdf
+   sudo pacman -S base-devel
 
-If you have any difficulties with installation, check the repository
-package page.
+The OCRmyPDF package depends on `the python-pdfminer.six AUR package
+<https://aur.archlinux.org/packages/python-pdfminer.six/>`__.  Dependencies on
+AUR packages are not automatically resolved, so this package must be manually
+installed first.
+
+.. code-block:: bash
+
+   curl -O https://aur.archlinux.org/cgit/aur.git/snapshot/python-pdfminer.six.tar.gz
+   tar xvzf python-pdfminer.six.tar.gz
+   cd python-pdfminer.six
+   makepkg -sri
+
+With that complete you can then repeat the same series of steps for the
+OCRmyPDF package.
+
+.. code-block:: bash
+
+   curl -O https://aur.archlinux.org/cgit/aur.git/snapshot/ocrmypdf.tar.gz
+   tar xvzf ocrmypdf.tar.gz
+   cd ocrmypdf
+   makepkg -sri
+
+At this point you will have a working install of OCRmyPDF, but the Tesseract
+install won’t include any OCR language data. You can install `the
+tesseract-data package group
+<https://www.archlinux.org/groups/any/tesseract-data/>`__ to add all supported
+languages, or use that package listing to identify the appropriate package for
+your desired language.
+
+.. code-block:: bash
+
+   sudo pacman -S tesseract-data-eng
+
+As an alternative to this manual procedure, consider using an `AUR helper
+<https://wiki.archlinux.org/index.php/AUR_helpers>`__. Such a tool will
+automatically fetch, build and install the AUR package, resolve dependencies
+(including dependencies on AUR packages), and ease the upgrade procedure.
+
+If you have any difficulties with installation, check the repository package
+page.
+
+.. note::
+
+    The OCRmyPDF AUR package currently omits the JBIG2 encoder. OCRmyPDF works
+    fine without it but will produce larger output files. The encoder is
+    available from `the jbig2enc-git AUR package
+    <https://aur.archlinux.org/packages/jbig2enc-git/>`__ and may be installed
+    using the same series of steps as for the installation of the pdfminer.six
+    and OCRmyPDF AUR packages. Alternatively, it may be built manually from
+    source following the instructions in `Installing the JBIG2 encoder
+    <jbig2>`__.  If JBIG2 is installed, OCRmyPDF 7.0.0 and later will
+    automatically detect it.
 
 Alpine Linux
 ------------
@@ -437,12 +502,12 @@ Installing on FreeBSD
     :alt: FreeBSD
     :target: https://repology.org/project/python:ocrmypdf/versions
 
-FreeBSD 11.2, 11.3, 12.0-RELEASE and 13.0-CURRENT are supported. Other
+FreeBSD 11.3, 12.0, 12.1-RELEASE and 13.0-CURRENT are supported. Other
 versions likely work but have not been tested.
 
 .. code-block:: bash
 
-    pkg install py36-ocrmypdf
+    pkg install py37-ocrmypdf
 
 To install a more recent version, you could attempt to first install the system
 version with ``pkg``, then use ``pip install --user ocrmypdf``.

docs/introduction.rst

@@ -10,7 +10,7 @@ About OCR
 `Optical character
 recognition <https://en.wikipedia.org/wiki/Optical_character_recognition>`__
 is technology that converts images of typed or handwritten text, such as
-in a scanned document, to computer text that can be searched and copied.
+in a scanned document, to computer text that can be selected, searched and copied.
 
 OCRmyPDF uses
 `Tesseract <https://github.com/tesseract-ocr/tesseract>`__, the best

docs/languages.rst

@@ -4,11 +4,20 @@
 Installing additional language packs
 ====================================
 
-OCRmyPDF uses Tesseract for OCR, and relies on its language packs for
-languages other than English.
+OCRmyPDF uses Tesseract for OCR, and relies on its language packs for all languages.
+On most platforms, English is installed with Tesseract by default, but not always.
 
 Tesseract supports `most
 languages <https://github.com/tesseract-ocr/tesseract/blob/master/doc/tesseract.1.asc#languages>`__.
+Languages are identified by standardized three-letter codes (called ISO 639-2 Alpha-3).
+Tesseract's documentation also lists the three-letter code for your language.
+Some are anglicized, e.g. Spanish is ``spa`` rather than ``esp``, while others
+are not, e.g. German is ``deu``.
+
+After you have installed a language pack, you can use it ``ocrmypdf -l <language>``,
+for example ``ocrmypdf -l spa``. For multilingual documents, you can specify
+all languages to be expected, e.g. ``ocrmypdf -l eng+fra`` for English and French.
+English is assumed by default unless other language(s) are specified.
 
 For Linux users, you can often find packages that provide language
 packs:

docs/release_notes.rst

@@ -13,6 +13,30 @@ Note that it is licensed under GPLv3, so scripts that
 ``import ocrmypdf`` and are released publicly should probably also be
 licensed under GPLv3.
 
+
+v9.6.1
+======
+
+-  Documentation improvements - thanks to many users for their contributions!
+
+      - Fixed installation instructions for ArchLinux (@pigmonkey)
+      - Updated installation instructions for FreeBSD and other OSes (@knobix)
+      - Added instructions for using Docker Compose with watchdog (@ianalexander,
+        @deisi)
+      - Other miscellany (@mb720, @toy, @caiofacchinato)
+      - Some scripts provided in the documentation have been migrated out so that
+        they can be copied out as whole files, and to ensure syntax checking
+        is maintained.
+
+-  Fixed an error that caused bash completions to fail on macOS. (#502, #504;
+   @AlexanderWillner)
+-  Fixed a rare case where OCRmyPDF threw an exception while processing a PDF
+   with the wrong object type in its ``/Trailer /Info``. The error is now logged
+   and incorrect object is ignored. (#497)
+-  Removed potentially non-free file ``enron1.pdf`` and simplified the test that
+   used it.
+-  Removed potentially non-free file ``misc/media/logo.afdesign``.
+
 v9.6.0
 ======
 

misc/batch.py

@@ -0,0 +1,50 @@
+#!/usr/bin/env python3
+# Original version by DeliciousPickle@github; modified
+
+# This script must be edited to meet your needs.
+
+import logging
+import os
+import sys
+
+import ocrmypdf
+
+# pylint: disable=logging-format-interpolation
+# pylint: disable=logging-not-lazy
+
+script_dir = os.path.dirname(os.path.realpath(__file__))
+print(script_dir + '/batch.py: Start')
+
+if len(sys.argv) > 1:
+    start_dir = sys.argv[1]
+else:
+    start_dir = '.'
+
+if len(sys.argv) > 2:
+    log_file = sys.argv[2]
+else:
+    log_file = script_dir + '/ocr-tree.log'
+
+logging.basicConfig(
+    level=logging.INFO,
+    format='%(asctime)s %(message)s',
+    filename=log_file,
+    filemode='w',
+)
+
+ocrmypdf.configure_logging(ocrmypdf.Verbosity.default)
+
+for dir_name, subdirs, file_list in os.walk(start_dir):
+    logging.info(dir_name + '\n')
+    os.chdir(dir_name)
+    for filename in file_list:
+        file_ext = os.path.splitext(filename)[1]
+        if file_ext == '.pdf':
+            full_path = dir_name + '/' + filename
+            print(full_path)
+            result = ocrmypdf.ocr(filename, filename, deskew=True)
+            if result == ocrmypdf.ExitCode.already_done_ocr:
+                print("Skipped document because it already contained text")
+            elif result == ocrmypdf.ExitCode.ok:
+                print("OCR complete")
+            logging.info(result)

misc/completion/ocrmypdf.bash

@@ -5,7 +5,33 @@ set -o errexit
 _ocrmypdf()
 {
     local cur prev cword words split
-    _init_completion -s || return
+
+    # Homebrew on Macs have version 1.3 of bash-completion which doesn't include - see #502
+    if declare -F _init_completions >/dev/null 2>&1; then
+        _init_completion -s || return
+    else
+        COMPREPLY=()
+        _get_comp_words_by_ref cur prev words cword
+    fi
+
+    if [[ $cur == -* ]]; then
+        COMPREPLY=( $( compgen -W '--language --image-dpi --output-type
+            --sidecar --version --jobs --quiet --verbose --title --author
+            --subject --keywords --rotate-pages --remove-background --deskew
+            --clean --clean-final --unpaper-args --oversample --remove-vectors
+            --threshold --force-ocr --skip-text --redo-ocr
+            --skip-big --jpeg-quality --png-quality --jbig2-lossy
+            --max-image-mpixels --tesseract-config --tesseract-pagesegmode
+            --help --tesseract-oem --pdf-renderer --tesseract-timeout
+            --rotate-pages-threshold --pdfa-image-compression --user-words
+            --user-patterns --keep-temporary-files --output-type
+            --no-progress-bar --pages --fast-web-view' \
+            --  "$cur" ) )
+        return
+    else
+        _filedir
+        return
+    fi
 
     case $prev in
         --version|-h|--help)
@@ -65,25 +91,6 @@ _ocrmypdf()
     esac
 
     $split && return
-
-    if [[ $cur == -* ]]; then
-        COMPREPLY=( $( compgen -W '--language --image-dpi --output-type
-            --sidecar --version --jobs --quiet --verbose --title --author
-            --subject --keywords --rotate-pages --remove-background --deskew
-            --clean --clean-final --unpaper-args --oversample --remove-vectors
-            --threshold --force-ocr --skip-text --redo-ocr
-            --skip-big --jpeg-quality --png-quality --jbig2-lossy
-            --max-image-mpixels --tesseract-config --tesseract-pagesegmode
-            --help --tesseract-oem --pdf-renderer --tesseract-timeout
-            --rotate-pages-threshold --pdfa-image-compression --user-words
-            --user-patterns --keep-temporary-files --output-type
-            --no-progress-bar --pages --fast-web-view' \
-            --  "$cur" ) )
-        return
-    else
-        _filedir
-        return
-    fi
 } &&
 complete -F _ocrmypdf ocrmypdf
 

misc/docker-compose.example.yml

@@ -0,0 +1,15 @@
+---
+version: "3.3"
+services:
+  ocrmypdf:
+    restart: always
+    container_name: ocrmypdf
+    image: jbarlow83/ocrmypdf
+    volumes:
+      - "/media/scan:/input"
+      - "/mnt/scan:/output"
+    environment:
+      - OCR_OUTPUT_DIRECTORY_YEAR_MONT=0
+    user: "<SET TO YOUR USER ID>:<SET TO YOUR GROUP ID>"
+    entrypoint: python3
+    command: watcher.py

misc/synology.py

@@ -0,0 +1,72 @@
+#!/bin/env python3
+# Contributed by github.com/Enantiomerie
+
+# This script must be edited to meet your needs.
+
+import logging
+import os
+import shutil
+import subprocess
+import sys
+import time
+
+# pylint: disable=logging-format-interpolation
+# pylint: disable=logging-not-lazy
+
+script_dir = os.path.dirname(os.path.realpath(__file__))
+timestamp = time.strftime("%Y-%m-%d-%H%M_")
+log_file = script_dir + '/' + timestamp + 'ocrmypdf.log'
+logging.basicConfig(
+    level=logging.INFO,
+    format='%(asctime)s %(message)s',
+    filename=log_file,
+    filemode='w',
+)
+
+if len(sys.argv) > 1:
+    start_dir = sys.argv[1]
+else:
+    start_dir = '.'
+
+for dir_name, subdirs, file_list in os.walk(start_dir):
+    logging.info(dir_name)
+    os.chdir(dir_name)
+    for filename in file_list:
+        file_stem, file_ext = os.path.splitext(filename)
+        if file_ext != '.pdf':
+            continue
+        full_path = os.path.join(dir_name, filename)
+        timestamp_ocr = time.strftime("%Y-%m-%d-%H%M_OCR_")
+        filename_ocr = timestamp_ocr + file_stem + '.pdf'
+        # create string for pdf processing
+        # the script is processed as root user via chron
+        cmd = [
+            'docker',
+            'run',
+            '--rm',
+            '-i',
+            'jbarlow83/ocrmypdf',
+            '--deskew',
+            '-',
+            '-',
+        ]
+        logging.info(cmd)
+        full_path_ocr = os.path.join(dir_name, filename_ocr)
+        with open(filename, 'rb') as input_file, open(
+            full_path_ocr, 'wb'
+        ) as output_file:
+            proc = subprocess.run(
+                cmd,
+                stdin=input_file,
+                stdout=output_file,
+                stderr=subprocess.PIPE,
+                check=False,
+            )
+        logging.info(proc.stderr.read())
+        os.chmod(full_path_ocr, 0o664)
+        os.chmod(full_path, 0o664)
+        full_path_ocr_archive = sys.argv[2]
+        full_path_archive = sys.argv[2] + '/no_ocr'
+        shutil.move(full_path_ocr, full_path_ocr_archive)
+        shutil.move(full_path, full_path_archive)
+logging.info('Finished.\n')

misc/watcher.py

@@ -1,4 +1,5 @@
 # Copyright (C) 2019 Ian Alexander: https://github.com/ianalexander
+# Copyright (C) 2020 James R Barlow: https://github.com/jbarlow83
 #
 # This program is free software: you can redistribute it and/or modify
 # it under the terms of the GNU General Public License as published by

src/ocrmypdf/_pipeline.py

@@ -694,11 +694,18 @@ def convert_to_pdfa(input_pdf, input_ps_stub, context):
     # stamping them out as soon as possible.
     modified = False
     with pikepdf.open(input_pdf) as pdf_file:
-        if pdf_file.docinfo:
-            for k, v in pdf_file.docinfo.items():
-                if b'\x00' in bytes(v):
-                    pdf_file.docinfo[k] = bytes(v).replace(b'\x00', b'')
-                    modified = True
+        try:
+            len(pdf_file.docinfo)
+        except TypeError:
+            context.log.error(
+                "File contains a malformed DocumentInfo block - continuing anyway"
+            )
+        else:
+            if pdf_file.docinfo:
+                for k, v in pdf_file.docinfo.items():
+                    if b'\x00' in bytes(v):
+                        pdf_file.docinfo[k] = bytes(v).replace(b'\x00', b'')
+                        modified = True
         if modified:
             pdf_file.save(fix_docinfo_file)
         else:

tests/test_metadata.py

@@ -31,8 +31,11 @@ import pytest
 from pikepdf.models.metadata import decode_pdf_date
 
 from ocrmypdf._jobcontext import PDFContext
+from ocrmypdf._pipeline import convert_to_pdfa
+from ocrmypdf.cli import parser
 from ocrmypdf.exceptions import ExitCode
 from ocrmypdf.pdfa import SRGB_ICC_PROFILE, file_claims_pdfa, generate_pdfa_ps
+from ocrmypdf.pdfinfo import PdfInfo
 
 try:
     import fitz
@@ -313,19 +316,21 @@ def test_metadata_fixup_warning(resources, outdir, caplog):
 
 
 def test_prevent_gs_invalid_xml(resources, outdir):
-    from ocrmypdf.__main__ import parser
-    from ocrmypdf._pipeline import convert_to_pdfa
-    from ocrmypdf.pdfa import generate_pdfa_ps
-    from ocrmypdf.pdfinfo import PdfInfo
-
     generate_pdfa_ps(outdir / 'pdfa.ps')
-    copyfile(resources / 'enron1.pdf', outdir / 'layers.rendered.pdf')
+    copyfile(resources / 'trivial.pdf', outdir / 'layers.rendered.pdf')
+
+    # Inject a string with a trailing nul character into the DocumentInfo
+    # dictionary of this PDF, as often occurs in practice.
+    with pikepdf.open(outdir / 'layers.rendered.pdf') as pike:
+        pike.Root.DocumentInfo = pikepdf.Dictionary(
+            Title=b'String with trailing nul\x00'
+        )
 
     options = parser.parse_args(
         args=['-j', '1', '--output-type', 'pdfa-2', 'a.pdf', 'b.pdf']
     )
-    pdfinfo = PdfInfo(resources / 'enron1.pdf')
-    context = PDFContext(options, outdir, resources / 'enron1.pdf', pdfinfo)
+    pdfinfo = PdfInfo(outdir / 'layers.rendered.pdf')
+    context = PDFContext(options, outdir, outdir / 'layers.rendered.pdf', pdfinfo)
 
     convert_to_pdfa(
         str(outdir / 'layers.rendered.pdf'), str(outdir / 'pdfa.ps'), context
@@ -339,5 +344,30 @@ def test_prevent_gs_invalid_xml(resources, outdir):
             xmp_start = mm.find(XMP_MAGIC)
             xmp_end = mm.rfind(b'<?xpacket end', xmp_start)
             assert 0 < xmp_start < xmp_end
+            # Ensure we did not carry the nul forward.
             assert mm.find(b'&#0;', xmp_start, xmp_end) == -1, "found escaped nul"
             assert mm.find(b'\x00', xmp_start, xmp_end) == -1
+
+
+def test_malformed_docinfo(caplog, resources, outdir):
+    generate_pdfa_ps(outdir / 'pdfa.ps')
+    # copyfile(resources / 'trivial.pdf', outdir / 'layers.rendered.pdf')
+
+    with pikepdf.open(resources / 'trivial.pdf') as pike:
+        pike.trailer.Info = pikepdf.Stream(pike, b"<xml></xml>")
+        pike.save(outdir / 'layers.rendered.pdf', fix_metadata_version=False)
+
+    options = parser.parse_args(
+        args=['-j', '1', '--output-type', 'pdfa-2', 'a.pdf', 'b.pdf']
+    )
+    pdfinfo = PdfInfo(outdir / 'layers.rendered.pdf')
+    context = PDFContext(options, outdir, outdir / 'layers.rendered.pdf', pdfinfo)
+
+    convert_to_pdfa(
+        str(outdir / 'layers.rendered.pdf'), str(outdir / 'pdfa.ps'), context
+    )
+
+    print(caplog.records)
+    assert any(
+        'malformed DocumentInfo block' in record.message for record in caplog.records
+    )