v11.0.2 release notes

metadata fixup: don't try to update original PDF's metadata with docinfo
Add "Postprocessing" message as a hint for long Ghostscript runs
2020-09-08 02:38:57 -07:00 · 2020-09-08 02:35:16 -07:00 · 2020-09-08 02:34:10 -07:00 · 2020-08-26 17:11:52 -07:00 · 2020-08-26 17:03:09 -07:00 · 2020-08-17 23:25:31 -07:00
93 changed files with 2418 additions and 2059 deletions
@@ -0,0 +1,28 @@
+---
+name: General issues
+about: Installation, packages, dependencies, "nothing works", test suite failures...
+title: ''
+labels: ''
+assignees: ''
+
+---
+
+**Describe the bug**
+What's the problem?
+
+**To Reproduce**
+Steps to reproduce the behavior.
+
+**Expected behavior**
+What did you expected to happen?
+
+**Screenshots**
+If applicable, add screenshots to help explain your problem.
+
+**System (please complete the following information):**
+ - OS:
+ - Python version: 
+ - OCRmyPDF version:
+
+**Additional context**
+Add any other context about the problem here.
@@ -1,6 +1,6 @@
 ---
-name: Bug report
-about: Create a report to help us improve
+name: Problem with a specific input file
+about: Something went wrong while trying to OCR a specific file
 title: ''
 labels: ''
 assignees: ''
@@ -20,13 +20,13 @@ ocrmypdf  ...arguments... input.pdf output.pdf
 Run with verbosity or higher `-v1` to see more detailed logging. This information may be helpful.

 **Example file**
-Include an input PDF or image that demonstrates your issue.
+If your issue is a problem that affects only certain files, and we will require an input file (PDF or image) that demonstrates your issue.

-Please provide an input file with no personal or confidential information. At your option you may `GPG-encrypt the file <https://github.com/jbarlow83/OCRmyPDF/wiki>` for OCRmyPDF's author only.
+Please provide an input file with no personal or confidential information. At your option you may [GPG-encrypt the file](https://github.com/jbarlow83/OCRmyPDF/wiki) for OCRmyPDF's author only.

 Links to files hosted elsewhere are perfectly acceptable. You could also look in ``tests/resources`` and see if any of those files reproduce your issue.

-(Exceptions: Issues with installation, command line argument parsing, test suite failures.Issues without example files usually cannot be resolved.)
+*(Issues without example files usually cannot be resolved. It's like reporting an issue against a web browser without providing a URL.)*

 **Expected behavior**
 A clear and concise description of what you expected to happen.
@@ -2,7 +2,7 @@
 name: Feature request
 about: Suggest an idea for this project
 title: ''
-labels: enhancement
+labels: ''
 assignees: ''

 ---
@@ -13,5 +13,8 @@ A clear and concise description of what the problem is. Ex. I'm always frustrate
 **Describe the solution you'd like**
 A clear and concise description of what you want to happen.

+**Describe alternatives you've considered**
+A clear and concise description of any alternative solutions or features you've considered.
+
 **Additional context**
 Add any other context or screenshots about the feature request here.
@@ -1,33 +0,0 @@
-**Describe the issue**
-A clear and concise description of what the issue is.
-
-**To Reproduce**
-What command line were you trying to run?
-
-```bash
-ocrmypdf  ...arguments... input.pdf output.pdf
-```
-
-**Example file**
-Please include an example *input* PDF (or image). The input file is more helpful.
-
-Please check any or all that apply about the test file:
-
- [ ] This is the input file
- [ ] The file contains no personal or confidential information
- [ ] I am the copyright holder for this file
- [ ] I permit this file to be included in the OCRmyPDF test suite under the CC-BY-SA 4.0 license
- [ ] I am not the copyright holder, but this file is available under a free software license
-
-Files that are not free for inclusion in this project are quite welcome, but we like to collect free files for our test suite when possible. Please do *not* submit files with confidential information. At your option you may encrypt files for OCRmyPDF's author only.
-
-**Expected behavior**
-A clear and concise description of what you expected to happen. Include screenshots if applicable.
-
-**System:**
-
- OS: [e.g. Linux, macOS]
- OCRmyPDF Version: [e.g. v7.4.0]
-
-**Additional context**
-Add any other context about the problem here.
@@ -7,6 +7,7 @@
 !.gitignore
 !.pre-commit-config.yaml
 !.readthedocs.yml
+!.github/

 # Dev scratch
 *.ipynb
@@ -1,6 +1,6 @@
 repos:
  - repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v2.4.0
+    rev: v3.1.0
    hooks:
      - id: check-case-conflict
      - id: check-merge-conflict
@@ -8,16 +8,16 @@ repos:
      - id: check-yaml
      - id: debug-statements
  - repo: https://github.com/asottile/seed-isort-config
-    rev: v1.9.3
+    rev: v2.2.0
    hooks:
      - id: seed-isort-config
  - repo: https://github.com/pre-commit/mirrors-isort
-    rev: v4.3.21 # pick the isort version you'd like to use from https://github.com/pre-commit/mirrors-isort/releases
+    rev: v5.0.5 # pick the isort version you'd like to use from https://github.com/pre-commit/mirrors-isort/releases
    hooks:
      - id: isort
  - repo: https://github.com/psf/black
-    rev: stable
+    rev: 19.10b0
    hooks:
      - id: black
-        language_version: python3.7
+        language_version: python3.8
        exclude: ^src/ocrmypdf/lib/_leptonica.py
@@ -3,15 +3,10 @@
 [![Build Status][azure]](https://dev.azure.com/jim0585/ocrmypdf/_build/latest?definitionId=2&branchName=master) [![PyPI version][pypi]](https://pypi.org/project/ocrmypdf/) ![Homebrew version][homebrew] ![ReadTheDocs][docs] ![Python versions][pyversions]

 [azure]: https://dev.azure.com/jim0585/ocrmypdf/_apis/build/status/jbarlow83.OCRmyPDF?branchName=master
-
 [travis]: https://travis-ci.org/jbarlow83/OCRmyPDF.svg?branch=master "Travis build status"
-
 [pypi]: https://img.shields.io/pypi/v/ocrmypdf.svg "PyPI version"
-
 [homebrew]: https://img.shields.io/homebrew/v/ocrmypdf.svg "Homebrew version"
-
 [docs]: https://readthedocs.org/projects/ocrmypdf/badge/?version=latest "RTD"
-
 [pyversions]: https://img.shields.io/pypi/pyversions/ocrmypdf "Supported Python versions"

 OCRmyPDF adds an OCR text layer to scanned PDF files, allowing them to be searched or copy-pasted.
@@ -30,8 +25,7 @@ ocrmypdf                      # it's a scriptable command line program

 [See the release notes for details on the latest changes](https://ocrmypdf.readthedocs.io/en/latest/release_notes.html).

-Main features
-------------
+## Main features

 - Generates a searchable [PDF/A](https://en.wikipedia.org/?title=PDF/A) file from a regular PDF
 - Places OCR text accurately below the image to ease copy / paste
@@ -47,8 +41,7 @@ Main features

 For details: please consult the [documentation](https://ocrmypdf.readthedocs.io/en/latest/).

-Motivation
----------
+## Motivation

 I searched the web for a free command line tool to OCR PDF files: I found many, but none of them were really satisfying:

@@ -62,8 +55,7 @@ I searched the web for a free command line tool to OCR PDF files: I found many,

 ...so I decided to develop my own tool.

-Installation
------------
+## Installation

 Linux, Windows, macOS and FreeBSD are supported. Docker images are also available.

@@ -87,8 +79,7 @@ brew install ocrmypdf

 For everyone else, [see our documentation](https://ocrmypdf.readthedocs.io/en/latest/installation.html) for installation steps.

-Languages
---------
+## Languages

 OCRmyPDF uses Tesseract for OCR, and relies on its language packs. For Linux users, you can often find packages that provide language packs:

@@ -105,8 +96,7 @@ pacman -S tesseract-data-eng tesseract-data-deu # Example: Install the English a

 You can then pass the `-l LANG` argument to OCRmyPDF to give a hint as to what languages it should search for. Multiple languages can be requested.

-Documentation and support
-------------------------
+## Documentation and support

 Once OCRmyPDF is installed, the built-in help which explains the command syntax and options can be accessed via:

@@ -118,35 +108,35 @@ Our [documentation is served on Read the Docs](https://ocrmypdf.readthedocs.io/e

 Please report issues on our [GitHub issues](https://github.com/jbarlow83/OCRmyPDF/issues) page, and follow the issue template for quick response.

-Requirements
------------
+## Requirements

 In addition to the required Python version (3.6+), OCRmyPDF requires external program installations of Ghostscript, Tesseract OCR, QPDF, and Leptonica. OCRmyPDF is pure Python, but uses CFFI to portably generate library bindings. OCRmyPDF works on pretty much everything: Linux, macOS, Windows and FreeBSD.

-Press & Media
-------------
+## Press & Media

 - [Going paperless with OCRmyPDF](https://medium.com/@ikirichenko/going-paperless-with-ocrmypdf-e2f36143f46a)
 - [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)
+- [Excellent Utilities: OCRmyPDF](https://www.linuxlinks.com/excellent-utilities-ocrmypdf-add-ocr-text-layer-scanned-pdfs/)

-Business enquiries
------------------
+## Business enquiries

 OCRmyPDF would not be the software that it is today without companies and users choosing to provide support for feature development and consulting enquiries. We are happy to discuss all enquiries, whether for extending the existing feature set, or integrating OCRmyPDF into a larger system.

-License
-------
+## License

-The OCRmyPDF software is licensed under the GNU GPLv3. Certain files are covered by other licenses, as noted in their source files.
+The OCRmyPDF software is licensed under the Mozilla Public License 2.0
+(MPL-2.0). This license permits integration of OCRmyPDF with other code,
+included commercial and closed source, but asks you to publish source-level
+modifications you make to OCRmyPDF.

-The license for each test file varies, and is noted in tests/resources/README.rst. The documentation is licensed under Creative Commons Attribution-ShareAlike 4.0 (CC-BY-SA 4.0).
+Some components of OCRmyPDF have other licenses, as noted in those files and the
+``debian/copyright`` file. Most files in ``misc/`` use the MIT license, and the
+documentation and test files are generally licensed under Creative Commons
+ShareAlike 4.0 (CC-BY-SA 4.0).

-OCRmyPDF versions prior to 6.0 were distributed under the MIT License.
-
-Disclaimer
----------
+## Disclaimer

 The software is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
@@ -152,9 +152,9 @@ stages:
        strategy:
          matrix:
            Python37:
-              python.version: "3.7"
-            # Python38:
-            #   python.version: "3.8"
+              python.version: ""
+            Python38:
+              python.version: "python@3.8"
        steps:
          # https://github.com/actions/virtual-environments/issues/664
          # - task: UsePythonVersion@0
@@ -163,6 +163,13 @@ stages:
          - bash: |
              brew update
              brew unlink python@2
+              if [ "$(python.version)" != "" ]; then
+                brew upgrade $(python.version)
+              else
+                echo "Using Python `python3 --version`"
+              fi
+            displayName: "Update brew and Python"
+          - bash: |
              brew install \
                exempi \
                ghostscript \
@@ -170,7 +177,6 @@ stages:
                leptonica \
                openjpeg \
                pngquant \
-                python \
                tesseract \
                unpaper
            displayName: "Install system packages"
@@ -2,35 +2,70 @@ Format: https://www.debian.org/doc/packaging-manuals/copyright-format/1.0/
 Upstream-Name: OCRmyPDF
 Upstream-Contact: James R. Barlow <barlow.jim@gmail.com>
 Source: https://github.com/jbarlow83/OCRmyPDF
-Files-Excluded: tests/resources/milk.pdf

 Files: *
 Copyright:
- (C) 2013-2017 The OCRmyPDF Authors
- (C) 2013-2016, 2015-2017 2016, 2017, 2017-2018, 2018 James R. Barlow
-License: GPL-3+
+ (C) 2013-2015 Julien Pfefferkorn
+ (C) 2015-2020 James R. Barlow
+ (C) 2019 Martin Wind
+License: MPL-2.0
+
+Files: misc/*
+Copyright:
+ (C) 2020 James R. Barlow
+License: Expat
+
+Files: misc/completion/ocrmypdf.bash
+Copyright:
+ (C) 2019 Frank Pille
+ (C) 2020 Alex Willner
+License: Expat
+
+Files: misc/completion/ocrmypdf.fish
+Copyright:
+ (C) 2020 James R. Barlow
+License: Expat
+
+Files: misc/batch.py
+Copyright:
+ (C) 2016 findingorder: https://github.com/findingorder
+License: Expat
+
+Files: misc/synology.py
+Copyright:
+ (C) github.com/Enantiomerie
+License: Expat
+
+Files: misc/watcher.py
+Copyright:
+ (C) 2019 Ian Alexander: https://github.com/ianalexander
+ (C) 2020 James R. Barlow
+License: Expat
+
+Files: misc/webservice.py
+Copyright: (C) 2019 James R. Barlow
+License: AGPL-3+

 Files: docs tests/resources/*
 Copyright: (C) 2013-2018 James R. Barlow
 License: CC-BY-SA-4.0

+Files: docs/images/bitmap_vs_svg.svg
+Copyright: (C) 2006 Yug
+License: CC-BY-SA-2.5
+
 Files: src/ocrmypdf/hocrtransform.py
 Copyright: (C) 2010 Jonathan Brinley <jonathanbrinley@gmail.com>
 (C) 2013-14 Julien Pfefferkorn
 (C) 2015-16 James R. Barlow
 License: Expat

-Files: src/ocrmypdf/pdfa.py
-Copyright: (C) 2015 James R. Barlow
- (C) 1986-2017 The authors of GhostScript
-License: GPL-3+
-
 Files: src/ocrmypdf/_unicodefun.py
 Copyright: (C) 2014 Armin Ronacher
 (C) 2017 James R. Barlow
 License: BSD-3-clause

-Files: tests/spoof/*
+Files: tests/plugins/*
 Copyright: (C) 2016, 2017, 2016-2018 James R. Barlow
 License: Expat

@@ -79,15 +114,20 @@ Copyright: held by the contributors to the Wikipedia article "Optical character
 (epson.pdf generated from Wikipedia article as of 2016-09-14)
 License: CC-BY-SA-3.0

-Files: tests/resources/typewriter.png tests/resources/2400dpi.pdf tests/resources/3small.pdf
+Files: tests/resources/typewriter.png tests/resources/2400dpi.pdf
 Copyright: (C) 2005 Ellywa
 License: GFDL-1.2+ or CC-BY-SA-1.0 or CC-BY-SA-2.0 or CC-BY-SA-2.5 or CC-BY-SA-3.0
+Comment:
+ Obtained from: https://commons.wikimedia.org/wiki/File:Triumph.typewriter_text_Linzensoep.gif

 Files: tests/resources/overlay.pdf
 Copyright: (C) 2017 Max Anderson
 License: Expat

-Files: tests/resources/baiona*.png tests/resources/3small.pdf
+Files:
+ tests/resources/baiona*.png
+ tests/resources/baiona*.jpg
+ tests/resources/link.pdf
 Copyright: (C) 2014 Euskaldunaa
 License: CC-BY-SA-4.0

@@ -95,6 +135,13 @@ Files: tests/resources/vector.pdf
 Copyright: (C) 2018 Catscratch
 License: Expat

+Files: tests/resources/3small.pdf
+Copyright: (C) 2014 Euskaldunaa
+ (C) 2017 James R. Barlow
+ (C) 2005 Ellywa
+License: CC-BY-SA-4.0 and (GFDL-1.2+ or CC-BY-SA-1.0 or CC-BY-SA-2.0 or CC-BY-SA-2.5 or CC-BY-SA-3.0)
+Comment: concatenation of baiona_gray.png, crom.png and typewriter.png/2400dpi.pdf
+
 Files: src/ocrmypdf/data/sRGB.icc
 Copyright:  Kai-Uwe Behrmann <www.behrmann.name>
            Marti Maria <www.littlecms.com>
@@ -107,6 +154,13 @@ Files: debian/*
 Copyright: (C) 2016 Sean Whitton <spwhitton@spwhitton.name>
 License: GPL-3+

+License: MPL-2.0
+ This Source Code Form is subject to the terms of the Mozilla Public
+ License, v. 2.0.
+ .
+ On Debian systems the full text of the MPL-2.0 can be found in
+ /usr/share/common-licenses/MPL-2.0.
+
 License: GPL-3+
 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
@@ -124,6 +178,669 @@ License: GPL-3+
 On Debian systems, the complete text of the GNU General
 Public License version 3 can be found in "/usr/share/common-licenses/GPL-3".

+License: AGPL-3+
+                     GNU AFFERO GENERAL PUBLIC LICENSE
+                        Version 3, 19 November 2007
+ .
+  Copyright (C) 2007 Free Software Foundation, Inc. <http://fsf.org/>
+  Everyone is permitted to copy and distribute verbatim copies
+  of this license document, but changing it is not allowed.
+ .
+                             Preamble
+ .
+   The GNU Affero General Public License is a free, copyleft license for
+ software and other kinds of works, specifically designed to ensure
+ cooperation with the community in the case of network server software.
+ .
+   The licenses for most software and other practical works are designed
+ to take away your freedom to share and change the works.  By contrast,
+ our General Public Licenses are intended to guarantee your freedom to
+ share and change all versions of a program--to make sure it remains free
+ software for all its users.
+ .
+   When we speak of free software, we are referring to freedom, not
+ price.  Our General Public Licenses are designed to make sure that you
+ have the freedom to distribute copies of free software (and charge for
+ them if you wish), that you receive source code or can get it if you
+ want it, that you can change the software or use pieces of it in new
+ free programs, and that you know you can do these things.
+ .
+   Developers that use our General Public Licenses protect your rights
+ with two steps: (1) assert copyright on the software, and (2) offer
+ you this License which gives you legal permission to copy, distribute
+ and/or modify the software.
+ .
+   A secondary benefit of defending all users' freedom is that
+ improvements made in alternate versions of the program, if they
+ receive widespread use, become available for other developers to
+ incorporate.  Many developers of free software are heartened and
+ encouraged by the resulting cooperation.  However, in the case of
+ software used on network servers, this result may fail to come about.
+ The GNU General Public License permits making a modified version and
+ letting the public access it on a server without ever releasing its
+ source code to the public.
+ .
+   The GNU Affero General Public License is designed specifically to
+ ensure that, in such cases, the modified source code becomes available
+ to the community.  It requires the operator of a network server to
+ provide the source code of the modified version running there to the
+ users of that server.  Therefore, public use of a modified version, on
+ a publicly accessible server, gives the public access to the source
+ code of the modified version.
+ .
+   An older license, called the Affero General Public License and
+ published by Affero, was designed to accomplish similar goals.  This is
+ a different license, not a version of the Affero GPL, but Affero has
+ released a new version of the Affero GPL which permits relicensing under
+ this license.
+ .
+   The precise terms and conditions for copying, distribution and
+ modification follow.
+ .
+                        TERMS AND CONDITIONS
+ .
+   0. Definitions.
+ .
+   "This License" refers to version 3 of the GNU Affero General Public License.
+ .
+   "Copyright" also means copyright-like laws that apply to other kinds of
+ works, such as semiconductor masks.
+ .
+   "The Program" refers to any copyrightable work licensed under this
+ License.  Each licensee is addressed as "you".  "Licensees" and
+ "recipients" may be individuals or organizations.
+ .
+   To "modify" a work means to copy from or adapt all or part of the work
+ in a fashion requiring copyright permission, other than the making of an
+ exact copy.  The resulting work is called a "modified version" of the
+ earlier work or a work "based on" the earlier work.
+ .
+   A "covered work" means either the unmodified Program or a work based
+ on the Program.
+ .
+   To "propagate" a work means to do anything with it that, without
+ permission, would make you directly or secondarily liable for
+ infringement under applicable copyright law, except executing it on a
+ computer or modifying a private copy.  Propagation includes copying,
+ distribution (with or without modification), making available to the
+ public, and in some countries other activities as well.
+ .
+   To "convey" a work means any kind of propagation that enables other
+ parties to make or receive copies.  Mere interaction with a user through
+ a computer network, with no transfer of a copy, is not conveying.
+ .
+   An interactive user interface displays "Appropriate Legal Notices"
+ to the extent that it includes a convenient and prominently visible
+ feature that (1) displays an appropriate copyright notice, and (2)
+ tells the user that there is no warranty for the work (except to the
+ extent that warranties are provided), that licensees may convey the
+ work under this License, and how to view a copy of this License.  If
+ the interface presents a list of user commands or options, such as a
+ menu, a prominent item in the list meets this criterion.
+ .
+   1. Source Code.
+ .
+   The "source code" for a work means the preferred form of the work
+ for making modifications to it.  "Object code" means any non-source
+ form of a work.
+ .
+   A "Standard Interface" means an interface that either is an official
+ standard defined by a recognized standards body, or, in the case of
+ interfaces specified for a particular programming language, one that
+ is widely used among developers working in that language.
+ .
+   The "System Libraries" of an executable work include anything, other
+ than the work as a whole, that (a) is included in the normal form of
+ packaging a Major Component, but which is not part of that Major
+ Component, and (b) serves only to enable use of the work with that
+ Major Component, or to implement a Standard Interface for which an
+ implementation is available to the public in source code form.  A
+ "Major Component", in this context, means a major essential component
+ (kernel, window system, and so on) of the specific operating system
+ (if any) on which the executable work runs, or a compiler used to
+ produce the work, or an object code interpreter used to run it.
+ .
+   The "Corresponding Source" for a work in object code form means all
+ the source code needed to generate, install, and (for an executable
+ work) run the object code and to modify the work, including scripts to
+ control those activities.  However, it does not include the work's
+ System Libraries, or general-purpose tools or generally available free
+ programs which are used unmodified in performing those activities but
+ which are not part of the work.  For example, Corresponding Source
+ includes interface definition files associated with source files for
+ the work, and the source code for shared libraries and dynamically
+ linked subprograms that the work is specifically designed to require,
+ such as by intimate data communication or control flow between those
+ subprograms and other parts of the work.
+ .
+   The Corresponding Source need not include anything that users
+ can regenerate automatically from other parts of the Corresponding
+ Source.
+ .
+   The Corresponding Source for a work in source code form is that
+ same work.
+ .
+   2. Basic Permissions.
+ .
+   All rights granted under this License are granted for the term of
+ copyright on the Program, and are irrevocable provided the stated
+ conditions are met.  This License explicitly affirms your unlimited
+ permission to run the unmodified Program.  The output from running a
+ covered work is covered by this License only if the output, given its
+ content, constitutes a covered work.  This License acknowledges your
+ rights of fair use or other equivalent, as provided by copyright law.
+ .
+   You may make, run and propagate covered works that you do not
+ convey, without conditions so long as your license otherwise remains
+ in force.  You may convey covered works to others for the sole purpose
+ of having them make modifications exclusively for you, or provide you
+ with facilities for running those works, provided that you comply with
+ the terms of this License in conveying all material for which you do
+ not control copyright.  Those thus making or running the covered works
+ for you must do so exclusively on your behalf, under your direction
+ and control, on terms that prohibit them from making any copies of
+ your copyrighted material outside their relationship with you.
+ .
+   Conveying under any other circumstances is permitted solely under
+ the conditions stated below.  Sublicensing is not allowed; section 10
+ makes it unnecessary.
+ .
+   3. Protecting Users' Legal Rights From Anti-Circumvention Law.
+ .
+   No covered work shall be deemed part of an effective technological
+ measure under any applicable law fulfilling obligations under article
+ 11 of the WIPO copyright treaty adopted on 20 December 1996, or
+ similar laws prohibiting or restricting circumvention of such
+ measures.
+ .
+   When you convey a covered work, you waive any legal power to forbid
+ circumvention of technological measures to the extent such circumvention
+ is effected by exercising rights under this License with respect to
+ the covered work, and you disclaim any intention to limit operation or
+ modification of the work as a means of enforcing, against the work's
+ users, your or third parties' legal rights to forbid circumvention of
+ technological measures.
+ .
+   4. Conveying Verbatim Copies.
+ .
+   You may convey verbatim copies of the Program's source code as you
+ receive it, in any medium, provided that you conspicuously and
+ appropriately publish on each copy an appropriate copyright notice;
+ keep intact all notices stating that this License and any
+ non-permissive terms added in accord with section 7 apply to the code;
+ keep intact all notices of the absence of any warranty; and give all
+ recipients a copy of this License along with the Program.
+ .
+   You may charge any price or no price for each copy that you convey,
+ and you may offer support or warranty protection for a fee.
+ .
+   5. Conveying Modified Source Versions.
+ .
+   You may convey a work based on the Program, or the modifications to
+ produce it from the Program, in the form of source code under the
+ terms of section 4, provided that you also meet all of these conditions:
+ .
+     a) The work must carry prominent notices stating that you modified
+     it, and giving a relevant date.
+ .
+     b) The work must carry prominent notices stating that it is
+     released under this License and any conditions added under section
+     7.  This requirement modifies the requirement in section 4 to
+     "keep intact all notices".
+ .
+     c) You must license the entire work, as a whole, under this
+     License to anyone who comes into possession of a copy.  This
+     License will therefore apply, along with any applicable section 7
+     additional terms, to the whole of the work, and all its parts,
+     regardless of how they are packaged.  This License gives no
+     permission to license the work in any other way, but it does not
+     invalidate such permission if you have separately received it.
+ .
+     d) If the work has interactive user interfaces, each must display
+     Appropriate Legal Notices; however, if the Program has interactive
+     interfaces that do not display Appropriate Legal Notices, your
+     work need not make them do so.
+ .
+   A compilation of a covered work with other separate and independent
+ works, which are not by their nature extensions of the covered work,
+ and which are not combined with it such as to form a larger program,
+ in or on a volume of a storage or distribution medium, is called an
+ "aggregate" if the compilation and its resulting copyright are not
+ used to limit the access or legal rights of the compilation's users
+ beyond what the individual works permit.  Inclusion of a covered work
+ in an aggregate does not cause this License to apply to the other
+ parts of the aggregate.
+ .
+   6. Conveying Non-Source Forms.
+ .
+   You may convey a covered work in object code form under the terms
+ of sections 4 and 5, provided that you also convey the
+ machine-readable Corresponding Source under the terms of this License,
+ in one of these ways:
+ .
+     a) Convey the object code in, or embodied in, a physical product
+     (including a physical distribution medium), accompanied by the
+     Corresponding Source fixed on a durable physical medium
+     customarily used for software interchange.
+ .
+     b) Convey the object code in, or embodied in, a physical product
+     (including a physical distribution medium), accompanied by a
+     written offer, valid for at least three years and valid for as
+     long as you offer spare parts or customer support for that product
+     model, to give anyone who possesses the object code either (1) a
+     copy of the Corresponding Source for all the software in the
+     product that is covered by this License, on a durable physical
+     medium customarily used for software interchange, for a price no
+     more than your reasonable cost of physically performing this
+     conveying of source, or (2) access to copy the
+     Corresponding Source from a network server at no charge.
+ .
+     c) Convey individual copies of the object code with a copy of the
+     written offer to provide the Corresponding Source.  This
+     alternative is allowed only occasionally and noncommercially, and
+     only if you received the object code with such an offer, in accord
+     with subsection 6b.
+ .
+     d) Convey the object code by offering access from a designated
+     place (gratis or for a charge), and offer equivalent access to the
+     Corresponding Source in the same way through the same place at no
+     further charge.  You need not require recipients to copy the
+     Corresponding Source along with the object code.  If the place to
+     copy the object code is a network server, the Corresponding Source
+     may be on a different server (operated by you or a third party)
+     that supports equivalent copying facilities, provided you maintain
+     clear directions next to the object code saying where to find the
+     Corresponding Source.  Regardless of what server hosts the
+     Corresponding Source, you remain obligated to ensure that it is
+     available for as long as needed to satisfy these requirements.
+ .
+     e) Convey the object code using peer-to-peer transmission, provided
+     you inform other peers where the object code and Corresponding
+     Source of the work are being offered to the general public at no
+     charge under subsection 6d.
+ .
+   A separable portion of the object code, whose source code is excluded
+ from the Corresponding Source as a System Library, need not be
+ included in conveying the object code work.
+ .
+   A "User Product" is either (1) a "consumer product", which means any
+ tangible personal property which is normally used for personal, family,
+ or household purposes, or (2) anything designed or sold for incorporation
+ into a dwelling.  In determining whether a product is a consumer product,
+ doubtful cases shall be resolved in favor of coverage.  For a particular
+ product received by a particular user, "normally used" refers to a
+ typical or common use of that class of product, regardless of the status
+ of the particular user or of the way in which the particular user
+ actually uses, or expects or is expected to use, the product.  A product
+ is a consumer product regardless of whether the product has substantial
+ commercial, industrial or non-consumer uses, unless such uses represent
+ the only significant mode of use of the product.
+ .
+   "Installation Information" for a User Product means any methods,
+ procedures, authorization keys, or other information required to install
+ and execute modified versions of a covered work in that User Product from
+ a modified version of its Corresponding Source.  The information must
+ suffice to ensure that the continued functioning of the modified object
+ code is in no case prevented or interfered with solely because
+ modification has been made.
+ .
+   If you convey an object code work under this section in, or with, or
+ specifically for use in, a User Product, and the conveying occurs as
+ part of a transaction in which the right of possession and use of the
+ User Product is transferred to the recipient in perpetuity or for a
+ fixed term (regardless of how the transaction is characterized), the
+ Corresponding Source conveyed under this section must be accompanied
+ by the Installation Information.  But this requirement does not apply
+ if neither you nor any third party retains the ability to install
+ modified object code on the User Product (for example, the work has
+ been installed in ROM).
+ .
+   The requirement to provide Installation Information does not include a
+ requirement to continue to provide support service, warranty, or updates
+ for a work that has been modified or installed by the recipient, or for
+ the User Product in which it has been modified or installed.  Access to a
+ network may be denied when the modification itself materially and
+ adversely affects the operation of the network or violates the rules and
+ protocols for communication across the network.
+ .
+   Corresponding Source conveyed, and Installation Information provided,
+ in accord with this section must be in a format that is publicly
+ documented (and with an implementation available to the public in
+ source code form), and must require no special password or key for
+ unpacking, reading or copying.
+ .
+   7. Additional Terms.
+ .
+   "Additional permissions" are terms that supplement the terms of this
+ License by making exceptions from one or more of its conditions.
+ Additional permissions that are applicable to the entire Program shall
+ be treated as though they were included in this License, to the extent
+ that they are valid under applicable law.  If additional permissions
+ apply only to part of the Program, that part may be used separately
+ under those permissions, but the entire Program remains governed by
+ this License without regard to the additional permissions.
+ .
+   When you convey a copy of a covered work, you may at your option
+ remove any additional permissions from that copy, or from any part of
+ it.  (Additional permissions may be written to require their own
+ removal in certain cases when you modify the work.)  You may place
+ additional permissions on material, added by you to a covered work,
+ for which you have or can give appropriate copyright permission.
+ .
+   Notwithstanding any other provision of this License, for material you
+ add to a covered work, you may (if authorized by the copyright holders of
+ that material) supplement the terms of this License with terms:
+ .
+     a) Disclaiming warranty or limiting liability differently from the
+     terms of sections 15 and 16 of this License; or
+ .
+     b) Requiring preservation of specified reasonable legal notices or
+     author attributions in that material or in the Appropriate Legal
+     Notices displayed by works containing it; or
+ .
+     c) Prohibiting misrepresentation of the origin of that material, or
+     requiring that modified versions of such material be marked in
+     reasonable ways as different from the original version; or
+ .
+     d) Limiting the use for publicity purposes of names of licensors or
+     authors of the material; or
+ .
+     e) Declining to grant rights under trademark law for use of some
+     trade names, trademarks, or service marks; or
+ .
+     f) Requiring indemnification of licensors and authors of that
+     material by anyone who conveys the material (or modified versions of
+     it) with contractual assumptions of liability to the recipient, for
+     any liability that these contractual assumptions directly impose on
+     those licensors and authors.
+ .
+   All other non-permissive additional terms are considered "further
+ restrictions" within the meaning of section 10.  If the Program as you
+ received it, or any part of it, contains a notice stating that it is
+ governed by this License along with a term that is a further
+ restriction, you may remove that term.  If a license document contains
+ a further restriction but permits relicensing or conveying under this
+ License, you may add to a covered work material governed by the terms
+ of that license document, provided that the further restriction does
+ not survive such relicensing or conveying.
+ .
+   If you add terms to a covered work in accord with this section, you
+ must place, in the relevant source files, a statement of the
+ additional terms that apply to those files, or a notice indicating
+ where to find the applicable terms.
+ .
+   Additional terms, permissive or non-permissive, may be stated in the
+ form of a separately written license, or stated as exceptions;
+ the above requirements apply either way.
+ .
+   8. Termination.
+ .
+   You may not propagate or modify a covered work except as expressly
+ provided under this License.  Any attempt otherwise to propagate or
+ modify it is void, and will automatically terminate your rights under
+ this License (including any patent licenses granted under the third
+ paragraph of section 11).
+ .
+   However, if you cease all violation of this License, then your
+ license from a particular copyright holder is reinstated (a)
+ provisionally, unless and until the copyright holder explicitly and
+ finally terminates your license, and (b) permanently, if the copyright
+ holder fails to notify you of the violation by some reasonable means
+ prior to 60 days after the cessation.
+ .
+   Moreover, your license from a particular copyright holder is
+ reinstated permanently if the copyright holder notifies you of the
+ violation by some reasonable means, this is the first time you have
+ received notice of violation of this License (for any work) from that
+ copyright holder, and you cure the violation prior to 30 days after
+ your receipt of the notice.
+ .
+   Termination of your rights under this section does not terminate the
+ licenses of parties who have received copies or rights from you under
+ this License.  If your rights have been terminated and not permanently
+ reinstated, you do not qualify to receive new licenses for the same
+ material under section 10.
+ .
+   9. Acceptance Not Required for Having Copies.
+ .
+   You are not required to accept this License in order to receive or
+ run a copy of the Program.  Ancillary propagation of a covered work
+ occurring solely as a consequence of using peer-to-peer transmission
+ to receive a copy likewise does not require acceptance.  However,
+ nothing other than this License grants you permission to propagate or
+ modify any covered work.  These actions infringe copyright if you do
+ not accept this License.  Therefore, by modifying or propagating a
+ covered work, you indicate your acceptance of this License to do so.
+ .
+   10. Automatic Licensing of Downstream Recipients.
+ .
+   Each time you convey a covered work, the recipient automatically
+ receives a license from the original licensors, to run, modify and
+ propagate that work, subject to this License.  You are not responsible
+ for enforcing compliance by third parties with this License.
+ .
+   An "entity transaction" is a transaction transferring control of an
+ organization, or substantially all assets of one, or subdividing an
+ organization, or merging organizations.  If propagation of a covered
+ work results from an entity transaction, each party to that
+ transaction who receives a copy of the work also receives whatever
+ licenses to the work the party's predecessor in interest had or could
+ give under the previous paragraph, plus a right to possession of the
+ Corresponding Source of the work from the predecessor in interest, if
+ the predecessor has it or can get it with reasonable efforts.
+ .
+   You may not impose any further restrictions on the exercise of the
+ rights granted or affirmed under this License.  For example, you may
+ not impose a license fee, royalty, or other charge for exercise of
+ rights granted under this License, and you may not initiate litigation
+ (including a cross-claim or counterclaim in a lawsuit) alleging that
+ any patent claim is infringed by making, using, selling, offering for
+ sale, or importing the Program or any portion of it.
+ .
+   11. Patents.
+ .
+   A "contributor" is a copyright holder who authorizes use under this
+ License of the Program or a work on which the Program is based.  The
+ work thus licensed is called the contributor's "contributor version".
+ .
+   A contributor's "essential patent claims" are all patent claims
+ owned or controlled by the contributor, whether already acquired or
+ hereafter acquired, that would be infringed by some manner, permitted
+ by this License, of making, using, or selling its contributor version,
+ but do not include claims that would be infringed only as a
+ consequence of further modification of the contributor version.  For
+ purposes of this definition, "control" includes the right to grant
+ patent sublicenses in a manner consistent with the requirements of
+ this License.
+ .
+   Each contributor grants you a non-exclusive, worldwide, royalty-free
+ patent license under the contributor's essential patent claims, to
+ make, use, sell, offer for sale, import and otherwise run, modify and
+ propagate the contents of its contributor version.
+ .
+   In the following three paragraphs, a "patent license" is any express
+ agreement or commitment, however denominated, not to enforce a patent
+ (such as an express permission to practice a patent or covenant not to
+ sue for patent infringement).  To "grant" such a patent license to a
+ party means to make such an agreement or commitment not to enforce a
+ patent against the party.
+ .
+   If you convey a covered work, knowingly relying on a patent license,
+ and the Corresponding Source of the work is not available for anyone
+ to copy, free of charge and under the terms of this License, through a
+ publicly available network server or other readily accessible means,
+ then you must either (1) cause the Corresponding Source to be so
+ available, or (2) arrange to deprive yourself of the benefit of the
+ patent license for this particular work, or (3) arrange, in a manner
+ consistent with the requirements of this License, to extend the patent
+ license to downstream recipients.  "Knowingly relying" means you have
+ actual knowledge that, but for the patent license, your conveying the
+ covered work in a country, or your recipient's use of the covered work
+ in a country, would infringe one or more identifiable patents in that
+ country that you have reason to believe are valid.
+ .
+   If, pursuant to or in connection with a single transaction or
+ arrangement, you convey, or propagate by procuring conveyance of, a
+ covered work, and grant a patent license to some of the parties
+ receiving the covered work authorizing them to use, propagate, modify
+ or convey a specific copy of the covered work, then the patent license
+ you grant is automatically extended to all recipients of the covered
+ work and works based on it.
+ .
+   A patent license is "discriminatory" if it does not include within
+ the scope of its coverage, prohibits the exercise of, or is
+ conditioned on the non-exercise of one or more of the rights that are
+ specifically granted under this License.  You may not convey a covered
+ work if you are a party to an arrangement with a third party that is
+ in the business of distributing software, under which you make payment
+ to the third party based on the extent of your activity of conveying
+ the work, and under which the third party grants, to any of the
+ parties who would receive the covered work from you, a discriminatory
+ patent license (a) in connection with copies of the covered work
+ conveyed by you (or copies made from those copies), or (b) primarily
+ for and in connection with specific products or compilations that
+ contain the covered work, unless you entered into that arrangement,
+ or that patent license was granted, prior to 28 March 2007.
+ .
+   Nothing in this License shall be construed as excluding or limiting
+ any implied license or other defenses to infringement that may
+ otherwise be available to you under applicable patent law.
+ .
+   12. No Surrender of Others' Freedom.
+ .
+   If conditions are imposed on you (whether by court order, agreement or
+ otherwise) that contradict the conditions of this License, they do not
+ excuse you from the conditions of this License.  If you cannot convey a
+ covered work so as to satisfy simultaneously your obligations under this
+ License and any other pertinent obligations, then as a consequence you may
+ not convey it at all.  For example, if you agree to terms that obligate you
+ to collect a royalty for further conveying from those to whom you convey
+ the Program, the only way you could satisfy both those terms and this
+ License would be to refrain entirely from conveying the Program.
+ .
+   13. Remote Network Interaction; Use with the GNU General Public License.
+ .
+   Notwithstanding any other provision of this License, if you modify the
+ Program, your modified version must prominently offer all users
+ interacting with it remotely through a computer network (if your version
+ supports such interaction) an opportunity to receive the Corresponding
+ Source of your version by providing access to the Corresponding Source
+ from a network server at no charge, through some standard or customary
+ means of facilitating copying of software.  This Corresponding Source
+ shall include the Corresponding Source for any work covered by version 3
+ of the GNU General Public License that is incorporated pursuant to the
+ following paragraph.
+ .
+   Notwithstanding any other provision of this License, you have
+ permission to link or combine any covered work with a work licensed
+ under version 3 of the GNU General Public License into a single
+ combined work, and to convey the resulting work.  The terms of this
+ License will continue to apply to the part which is the covered work,
+ but the work with which it is combined will remain governed by version
+ 3 of the GNU General Public License.
+ .
+   14. Revised Versions of this License.
+ .
+   The Free Software Foundation may publish revised and/or new versions of
+ the GNU Affero General Public License from time to time.  Such new versions
+ will be similar in spirit to the present version, but may differ in detail to
+ address new problems or concerns.
+ .
+   Each version is given a distinguishing version number.  If the
+ Program specifies that a certain numbered version of the GNU Affero General
+ Public License "or any later version" applies to it, you have the
+ option of following the terms and conditions either of that numbered
+ version or of any later version published by the Free Software
+ Foundation.  If the Program does not specify a version number of the
+ GNU Affero General Public License, you may choose any version ever published
+ by the Free Software Foundation.
+ .
+   If the Program specifies that a proxy can decide which future
+ versions of the GNU Affero General Public License can be used, that proxy's
+ public statement of acceptance of a version permanently authorizes you
+ to choose that version for the Program.
+ .
+   Later license versions may give you additional or different
+ permissions.  However, no additional obligations are imposed on any
+ author or copyright holder as a result of your choosing to follow a
+ later version.
+ .
+   15. Disclaimer of Warranty.
+ .
+   THERE IS NO WARRANTY FOR THE PROGRAM, TO THE EXTENT PERMITTED BY
+ APPLICABLE LAW.  EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT
+ HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY
+ OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO,
+ THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
+ PURPOSE.  THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE PROGRAM
+ IS WITH YOU.  SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF
+ ALL NECESSARY SERVICING, REPAIR OR CORRECTION.
+ .
+   16. Limitation of Liability.
+ .
+   IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING
+ WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MODIFIES AND/OR CONVEYS
+ THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES, INCLUDING ANY
+ GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING OUT OF THE
+ USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED TO LOSS OF
+ DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD
+ PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER PROGRAMS),
+ EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF
+ SUCH DAMAGES.
+ .
+   17. Interpretation of Sections 15 and 16.
+ .
+   If the disclaimer of warranty and limitation of liability provided
+ above cannot be given local legal effect according to their terms,
+ reviewing courts shall apply local law that most closely approximates
+ an absolute waiver of all civil liability in connection with the
+ Program, unless a warranty or assumption of liability accompanies a
+ copy of the Program in return for a fee.
+ .
+                      END OF TERMS AND CONDITIONS
+ .
+             How to Apply These Terms to Your New Programs
+ .
+   If you develop a new program, and you want it to be of the greatest
+ possible use to the public, the best way to achieve this is to make it
+ free software which everyone can redistribute and change under these terms.
+ .
+   To do so, attach the following notices to the program.  It is safest
+ to attach them to the start of each source file to most effectively
+ state the exclusion of warranty; and each file should have at least
+ the "copyright" line and a pointer to where the full notice is found.
+ .
+     <one line to give the program's name and a brief idea of what it does.>
+     Copyright (C) <year>  <name of author>
+ .
+     This program is free software: you can redistribute it and/or modify
+     it under the terms of the GNU Affero General Public License as published by
+     the Free Software Foundation, either version 3 of the License, or
+     (at your option) any later version.
+ .
+     This program is distributed in the hope that it will be useful,
+     but WITHOUT ANY WARRANTY; without even the implied warranty of
+     MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+     GNU Affero General Public License for more details.
+ .
+     You should have received a copy of the GNU Affero General Public License
+     along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ .
+ Also add information on how to contact you by electronic and paper mail.
+ .
+   If your software can interact with users remotely through a computer
+ network, you should also make sure that it provides a way for users to
+ get its source.  For example, if your program is a web application, its
+ interface could display a "Source" link that leads users to an archive
+ of the code.  There are many ways you could offer source, and different
+ solutions will be better for different programs; see section 13 for the
+ specific requirements.
+ .
+   You should also get your employer (if you work as a programmer) or school,
+ if any, to sign a "copyright disclaimer" for the program, if necessary.
+ For more information on this, and how to apply and follow the GNU AGPL, see
+ <http://www.gnu.org/licenses/>.
+
 License: Expat
 Permission is hereby granted, free of charge, to any person obtaining
 a copy of this software and associated documentation files (the
@@ -51,6 +51,10 @@ Forking a child process to call ``ocrmypdf.ocr()`` is suggested. That
 way your application will survive and remain interactive even if
 OCRmyPDF does not.

+Programs that call ``ocrmypdf.ocr()`` should also install a SIGBUS signal
+handler (except on Windows), to raise an exception if access to a memory
+mapped file fails. OCRmyPDF may use memory mapping.
+
 .. warning::

    On Windows, the script that calls ``ocrmypdf.ocr()`` must be protected
@@ -106,7 +110,3 @@ Reference
    :undoc-members:

 .. autofunction:: ocrmypdf.configure_logging
-
-.. automodule:: ocrmypdf.exceptions
-    :members:
-    :undoc-members:
@@ -0,0 +1,43 @@
+=============
+API Reference
+=============
+
+This page summarizes the rest of the public API. Generally speaking this
+should mainly of interest to plugin developers.
+
+ocrmypdf.exceptions
+===================
+
+.. automodule:: ocrmypdf.exceptions
+    :members:
+    :undoc-members:
+
+ocrmypdf.helpers
+================
+
+.. automodule:: ocrmypdf.helpers
+    :members:
+
+ocrmypdf.hocrtransform
+======================
+
+.. automodule:: ocrmypdf.hocrtransform
+    :members:
+
+ocrmypdf.pdfa
+=============
+
+.. automodule:: ocrmypdf.pdfa
+    :members:
+
+ocrmypdf.quality
+================
+
+.. automodule:: ocrmypdf.quality
+    :members:
+
+ocrmypdf.subprocess
+===================
+
+.. automodule:: ocrmypdf.subprocess
+    :members:
@@ -127,7 +127,7 @@ Users may need to customize the script to meet their requirements.
    "OCR_ON_SUCCESS_DELETE", "This will delete the input file if the exit code is 0 (OK)"
    "OCR_OUTPUT_DIRECTORY_YEAR_MONTH", "This will place files in the output in ``{output}/{year}/{month}/{filename}``"
    "OCR_DESKEW", "Apply deskew to crooked input PDFs"
-    "OCR_JSON_SETTINGS", "A JSON string specifying any other arguments for ``ocrmypdf.ocr``"
+    "OCR_JSON_SETTINGS", "A JSON string specifying any other arguments for ``ocrmypdf.ocr``, e.g. ``'OCR_JSON_SETTINGS={"rotate_pages": true}'``.
    "OCR_POLL_NEW_FILE_SECONDS", "Polling interval"
    "OCR_LOGLEVEL", "Level of log messages to report"

@@ -1,5 +1,4 @@
 #!/usr/bin/env python3
-# -*- coding: utf-8 -*-
 #
 # ocrmypdf documentation build configuration file, created by
 # sphinx-quickstart on Sun Sep  4 14:29:43 2016.
@@ -21,6 +20,8 @@
 # import sys
 # sys.path.insert(0, os.path.abspath('.'))

+"""isort:skip_file"""
+
 # -- General configuration ------------------------------------------------

 # If your documentation needs a minimal Sphinx version, state it here.
@@ -32,6 +33,8 @@
 # ones.
 extensions = ['sphinx.ext.napoleon']

+napoleon_use_rtype = False
+
 # Add any paths that contain templates here, relative to this directory.
 templates_path = ['_templates']

@@ -51,7 +54,7 @@ master_doc = 'index'
 # General information about the project.
 project = 'ocrmypdf'
 copyright = (
-    '2019, James R. Barlow. Licensed under Creative Commons Attribution-ShareAlike 4.0.'
+    '2020, James R. Barlow. Licensed under Creative Commons Attribution-ShareAlike 4.0.'
 )
 author = 'James R. Barlow'

@@ -90,6 +93,7 @@ from pkg_resources import get_distribution, DistributionNotFound
 release = get_distribution('ocrmypdf').version
 version = '.'.join(release.split('.')[:2])

+
 # The language for content autogenerated by Sphinx. Refer to documentation
 # for a list of supported languages.
 #
@@ -174,7 +178,7 @@ html_theme_options = {'display_version': False}
 # The name of an image file (relative to this directory) to place at the top
 # of the sidebar.
 #
-# html_logo = None
+# html_logo = "images/logo.svg"  # looks bad

 # The name of an image file (relative to this directory) to use as a favicon of
 # the docs.  This file should be a Windows icon file (.ico) being 16x16 or 32x32
@@ -32,7 +32,8 @@ If you are proposing a change that will require a new Python dependency, we
 prefer dependencies that are already packaged by Debian or Red Hat. This makes
 life much easier for our downstream package maintainers.

-Python dependencies must also be GPLv3 compatible.
+Python dependencies must also be license-compatible. GPLv3 or AGPLv3 are likely
+incompatible with the project's license, but LGPLv3 is compatible.

 New non-Python dependencies
 ===========================
@@ -55,3 +56,12 @@ of that platform.

 Packager maintainers, please ensure that the command line completion scripts in
 ``misc/`` are installed.
+
+Copyright and license
+=====================
+
+For contributions over 10 lines of code, please include your name to list of
+copyright holders for that file. The core program is licensed under MPL-2.0,
+test files and documentation under CC-BY-SA 4.0, and miscellaneous files under
+MIT. Please contribute code only that you wrote and you have the permission to
+contribute or license to us.
@@ -163,8 +163,7 @@ complete. This may entail setting a long timeout; this interface is more
 useful for internal HTTP API calls.

 Unlike the rest of OCRmyPDF, this web service is licensed under the
-Affero GPLv3 (AGPLv3) since Ghostscript, a dependency of OCRmyPDF, is
-also licensed in this way.
+Affero GPLv3 (AGPLv3) since Ghostscript is also licensed in this way.

 In addition to the above, please read our
 :ref:`general remarks on using OCRmyPDF as a service <ocr-service>`.
@@ -36,6 +36,7 @@ image processing and OCR to existing PDFs.

   api
   plugins
+   apiref
   contributing

 Indices and tables
@@ -8,20 +8,26 @@ Installing OCRmyPDF
 |latest|

 The easiest way to install OCRmyPDF is to follow the steps for your operating
-system/platform, although sometimes this version may be out of date. This
-installation guide provides information allowing you to compare the current
-version to the one provided by your platform.
+system/platform. This version may be out of date, however.

-If you want to use the latest version of OCRmyPDF and all of its optional
-dependencies, the easiest way to get that is install the Homebrew package. Homebrew
-is best known as a macOS package manger, but also works for
-`Linux and Windows Subsystem for Linux <https://docs.brew.sh/Homebrew-on-Linux>`__.
-After Homebrew is installed, simply run ``brew install ocrmypdf``.
+These platforms have one-liner installs:

-You can also use the more detailed procedures here to manually install OCRmyPDF
-from source or with the ``pip`` package manager for binary wheels. The reason
-for these varied steps is that OCRmyPDF requires third-party executables that are
-not part of Python.
+-----------------------------+-------------------------------+
+| Debian, Ubuntu              | ``apt install ocrmypdf``      |
+-----------------------------+-------------------------------+
+| Windows Subsystem for Linux | ``apt install ocrmypdf``      |
+-----------------------------+-------------------------------+
+| Fedora                      | ``dnf install ocrmypdf``      |
+-----------------------------+-------------------------------+
+| macOS                       | ``brew install ocrmypdf``     |
+-----------------------------+-------------------------------+
+| LinuxBrew                   | ``brew install ocrmypdf``     |
+-----------------------------+-------------------------------+
+| FreeBSD                     | ``pkg install py37-ocrmypdf`` |
+-----------------------------+-------------------------------+
+
+More detailed procedures are outlined below. If you want to do a manual
+install, or install a more recent version than your platform provides, read on.

 .. contents:: Platform-specific steps
    :depth: 2
@@ -58,7 +64,7 @@ Debian and Ubuntu 18.04 or newer
 | |ubu-1804| |ubu-2004|                         |
 +-----------------------------------------------+

-Users of Debian 9 ("stretch") or later or Ubuntu 18.04 or later, including users
+Users of Debian 9 ("stretch") or later, or Ubuntu 18.04 or later, including users
 of Windows Subsystem for Linux, may simply

 .. code-block:: bash
@@ -87,11 +93,11 @@ For full details on version availability for your platform, check the
 Fedora 29 or newer
 ------------------

-.. |fedora-29| image:: https://repology.org/badge/version-for-repo/fedora_29/ocrmypdf.svg
-    :alt: Fedora 29
+.. |fedora-31| image:: https://repology.org/badge/version-for-repo/fedora_31/ocrmypdf.svg
+    :alt: Fedora 31

-.. |fedora-30| image:: https://repology.org/badge/version-for-repo/fedora_30/ocrmypdf.svg
-    :alt: Fedora 30
+.. |fedora-32| image:: https://repology.org/badge/version-for-repo/fedora_32/ocrmypdf.svg
+    :alt: Fedora 32

 .. |fedora-rawhide| image:: https://repology.org/badge/version-for-repo/fedora_rawhide/ocrmypdf.svg
    :alt: Fedore Rawhide
@@ -101,7 +107,7 @@ Fedora 29 or newer
 +-----------------------------------------------+
 | |latest|                                      |
 +-----------------------------------------------+
-| |fedora-29| |fedora-30| |fedora-rawhide|      |
+| |fedora-31| |fedora-32| |fedora-rawhide|      |
 +-----------------------------------------------+

 Users of Fedora 29 or later may simply
@@ -162,7 +168,7 @@ To install for the current user only:
    pip3 install --user ocrmypdf

 Ubuntu 18.04 LTS
-------------------------------------------------
+----------------

 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, uninstall the old version
@@ -265,68 +271,6 @@ environment variable contains ``$HOME/.local/bin``.

 To add JBIG2 encoding, see :ref:`jbig2`.

-Ubuntu 14.04 LTS
----------------
-
-Installing on Ubuntu 14.04 LTS (trusty) is more difficult than some
-other options, because of its age. Several backports are required. For
-explanations of some steps of this procedure, see the similar steps for
-Ubuntu 16.04.
-
-Install system dependencies:
-
-.. code-block:: bash
-
-    sudo apt-get update
-    sudo apt-get install \
-        software-properties-common python-software-properties \
-        zlib1g-dev \
-        libexempi3 \
-        libjpeg-dev \
-        libffi-dev \
-        pngquant \
-        qpdf
-
-We will need backports of Ghostscript 9.16, libav-11 (for unpaper 6.1),
-Tesseract 4.00 (alpha), and Python 3.6. This will replace Ghostscript
-and Tesseract 3.x on your system. Python 3.6 will be installed alongside
-the system Python 3.4.
-
-If you prefer to not modify your system in this matter, consider using a
-Docker container.
-
-.. code-block:: bash
-
-    sudo add-apt-repository ppa:vshn/ghostscript -y
-    sudo add-apt-repository ppa:heyarje/libav-11 -y
-    sudo add-apt-repository ppa:alex-p/tesseract-ocr -y
-    sudo add-apt-repository ppa:jonathonf/python-3.6 -y
-
-    sudo apt-get update
-
-    sudo apt-get install \
-        python3.6-dev \
-        ghostscript \
-        tesseract-ocr \
-        tesseract-ocr-eng \
-        libavformat56 libavcodec56 libavutil54 \
-        wget
-
-Now we need to install ``pip`` and let it install ocrmypdf:
-
-.. code-block:: bash
-
-    curl https://bootstrap.pypa.io/ez_setup.py -o - | python3.6 && python3.6 -m easy_install pip
-    pip3.6 install ocrmypdf
-
-The optional dependency ``unpaper`` is only available at 0.4.2 in Ubuntu 14.04,
-and no backports are available. Previously the author maintained a backported
-.deb package for unpaper 6.1, but since Ubuntu 14.04 is now end of life, this is
-not supported. As such, ``unpaper`` is not available on Ubuntu 14.04 or must by
-compiled by hand.
-
-To add JBIG2 encoding, see :ref:`jbig2`.
-
 Arch Linux (AUR)
 ----------------

@@ -407,6 +351,43 @@ To install OCRmyPDF for Alpine Linux:

    apk add ocrmypdf

+Mageia 7
+--------
+
+Install the following dependencies:
+
+.. code-block:: bash
+
+    # As root user
+    urpmi.update -a
+    urpmi \
+        ghostscript \
+        icc-profiles-openicc \
+        jbig2dec \
+        lib64leptonica5 \
+        pngquant \
+        python3-pip \
+        python3-cffi \
+        python3-distutils-extra \
+        python3-pkg-resources \
+        python3-reportlab \
+        qpdf \
+        tesseract \
+        tesseract-osd \
+        tesseract-eng \
+        tesseract-fra
+
+To install ocrmypdf for the system:
+
+    # As root user
+    pip3 install ocrmypdf
+    ldconfig
+
+Or, to install for the current user only:
+
+    export PATH=$HOME/.local/bin:$PATH
+    pip3 install --user ocrmypdf
+
 Other Linux packages
 --------------------

@@ -507,40 +488,15 @@ The command line program should now be available:

    ocrmypdf --help

-Installing on FreeBSD
-=====================
-
-.. image:: https://repology.org/badge/version-for-repo/freebsd/python:ocrmypdf.svg
-    :alt: FreeBSD
-    :target: https://repology.org/project/python:ocrmypdf/versions
-
-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 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``.
-
-Installing the Docker image
-===========================
-
-For some users, installing the Docker image will be easier than
-installing all of OCRmyPDF's dependencies.
-
-See `OCRmyPDF Docker Image <docker>`__ for more information.
-
 Installing on Windows
 =====================

-.. warning::
+Native Windows
+--------------

-    Native Windows support is new. Consider it "beta" software. Some
-    functionality is missing or may be more difficult to enable. If you need a
-    production-ready solution, use Windows Subsystem for Linux or a Docker
-    image.
+.. note::
+
+    It is easier to install OCRmyPDF on Windows Subsystem for Linux.

 .. note::

@@ -548,7 +504,7 @@ Installing on Windows

 You must install the following for Windows:

-* Python 3.7 (64-bit)
+* Python 3.7 (64-bit) or later
 * Tesseract 4.0 or later
 * Ghostscript 9.50 or later

@@ -577,8 +533,8 @@ You may then use pip to install ocrmypdf:

 * ``pip install ocrmypdf``

-Installing on Windows Subsystem for Linux
-=========================================
+Windows Subsystem for Linux
+---------------------------

 #. Install Ubuntu 18.04 for Windows Subsystem for Linux, if not already installed.
 #. Follow the procedure to install :ref:`OCRmyPDF on Ubuntu 18.04 <ubuntu-lts-latest>`.
@@ -597,14 +553,8 @@ Then confirm that the expected version from PyPI (|latest|) is installed:
 You can then run OCRmyPDF in the Windows command prompt or Powershell, prefixing
 ``wsl``, and call it from Windows programs or batch files.

-Docker
-^^^^^^
-
-You can also :ref:`Install the Docker <docker-install>` container on Windows. Ensure that
-your command prompt can run the docker "hello world" container.
-
-Installing on Cygwin64 under Windows
-====================================
+Cygwin64
+--------

 First install the the following prerequisite Cygwin packages using ``setup-x86_64.exe``::

@@ -650,6 +600,37 @@ The optional dependency "unpaper" that is currently not available under Cygwin.
 Without it, certain options such as ``--clean`` will produce an error message.
 However, the OCR-to-text-layer functionality is available.

+Docker
+------
+
+You can also :ref:`Install the Docker <docker-install>` container on Windows. Ensure that
+your command prompt can run the docker "hello world" container.
+
+Installing on FreeBSD
+=====================
+
+.. image:: https://repology.org/badge/version-for-repo/freebsd/python:ocrmypdf.svg
+    :alt: FreeBSD
+    :target: https://repology.org/project/python:ocrmypdf/versions
+
+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 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``.
+
+Installing the Docker image
+===========================
+
+For some users, installing the Docker image will be easier than
+installing all of OCRmyPDF's dependencies.
+
+See `OCRmyPDF Docker Image <docker>`__ for more information.
+
 Installing with Python pip
 ==========================

@@ -684,6 +665,13 @@ instead use this for a system wide installation:

    pip3 install ocrmypdf

+.. note::
+
+    AArch64 (ARM64) users: this process will be difficult because most
+    Python packages are not available as binary wheels for your platform.
+    You're probably better off using a platform install on Debian, Ubuntu,
+    or Fedora.
+
 Requirements for pip and HEAD install
 -------------------------------------

@@ -186,6 +186,11 @@ Ghostscript also imposes some limitations:
 -  Ghostscript's PDF/A conversion removes any XMP metadata that is not
   one of the standard XMP metadata namespaces for PDFs. In particular,
   PRISM Metdata is removed.
+-  Ghostscript's PDF/A conversion seems to remove or deactivate
+   hyperlinks and other active content.
+
+You can use ``--output-type pdf`` to disable PDF/A conversion and produce
+a standard, non-archival PDF.

 Regarding OCRmyPDF itself:

@@ -64,7 +64,7 @@ malicious user could upload a chosen PDF. In particular, it is not
 necessarily secure against PDF malware or PDFs that cause denial of
 service. OCRmyPDF relies on Ghostscript, and therefore, if deployed
 online one should be prepared to comply with Ghostscript's Affero GPL
-license, OCRmyPDF's GPL license, and any other licenses.
+license, and any other licenses.

 Setting aside these concerns, a side effect of OCRmyPDF is it may
 incidentally sanitize PDFs that contain certain types of malware. It
@@ -2,6 +2,11 @@
 Plugins
 =======

+    The key words "MUST", "MUST NOT", "REQUIRED", "SHALL", "SHALL
+    NOT", "SHOULD", "SHOULD NOT", "RECOMMENDED",  "MAY", and
+    "OPTIONAL" in this document are to be interpreted as described in
+    RFC 2119.
+
 You can use plugins to customize the behavior of OCRmyPDF at certain points of
 interest.

@@ -11,39 +16,34 @@ Currently, it is possible to:
 - override the decision for whether or not to perform OCR on a particular file
 - modify the image is about to be sent for OCR
 - modify the page image before it is converted to PDF
+- replace the Tesseract OCR with another OCR engine that has similar behavior
+- replace Ghostscript with another PDF to image converter (rasterizer) or
+  PDF/A generator

 OCRmyPDF plugins are based on the Python ``pluggy`` package and conform to its
 conventions. Note that: plugins installed with as setuptools entrypoints are
 not checked currently, because OCRmyPDF assumes you may not want to enable
-plugins for all files. Also, plugins must be functions, not classes.
-
-How plugins are imported
-========================
-
-Plugins are imported on demand, by the OCRmyPDF worker process that needs to use
-them. As such, plugins cannot share state with other plugins, cannot rely on
-their module's or the interpreter's global state, and should expect asynchronous
-copies of themselves to be running. Plugins can write intermediate files to the
-folder specified in ``options.work_folder``.
-
-Plugins should work whether executed in threads or processes.
+plugins for all files.

 Script plugins
 ==============

 Script plugins may be called from the command line, by specifying the name of a file.
+Script plugins may be convenient for informal or "one-off" plugins, when a certain
+batch of files needs a special processing step for example.

 .. code-block:: bash

-    ocrmypdf --plugin example_plugin.py input.pdf output.pdf
+    ocrmypdf --plugin ocrmypdf_example_plugin.py input.pdf output.pdf

-Multiple plugins may be called by issuing the ``--plugin`` argument multiple times.
+Multiple plugins may be installed by issuing the ``--plugin`` argument multiple times.

 Packaged plugins
 ================

 Installed plugins may be installed into the same virtual environment as OCRmyPDF
 is installed into. They may be invoked using Python standard module naming.
+If you are intending to distribute a plugin, please package it.

 .. code-block:: bash

@@ -59,10 +59,45 @@ as packaged plugins, and these modules should begin with the name ``ocrmypdf_``
 similar to ``pytest`` packages such as ``pytest-cov`` (the package) and
 ``pytest_cov`` (the module).

+.. note::
+
+    We strongly recommend plugin authors name their plugins with the prefix
+    ``ocrmypdf-`` (for the package name on PyPI) and ``ocrmypdf_`` (for the
+    module), just like pytest plugins.
+
+Plugin requirements
+===================
+
+OCRmyPDF generally uses multiple worker processes. When a new worker is started,
+Python will import all plugins again, including all plugins that were imported earlier.
+This means that the global state of a plugin in one worker will not be shared with
+other workers. As such, plugin hook implementations should be stateless, relying
+only on their inputs. Hook implementations may use their input parameters to
+to obtain a reference to shared state prepared by another hook implementation.
+Plugins must expect that other instances of the plugin will be running
+simultaneously.
+
+The ``context`` object that is passed to many hooks can be used to share information
+about a file being worked on. Plugins must write private, plugin-specific data to
+a subfolder named ``{options.work_folder}/ocrmypdf-plugin-name``. Plugins MAY
+read and write files in ``options.work_folder``, but should be aware that their
+semantics are subject to change.
+
+OCRmyPDF will delete ``options.work_folder`` when it has finished OCRing
+a file, unless invoked with ``--keep-temporary-files``.
+
+The documentation for some plugin hooks contain a detailed description of the
+execution context in which they will be called.
+
+Plugins should be prepared to work whether executed in worker threads or worker
+processes. Generally, OCRmyPDF uses processes, but has a semi-hidden threaded
+argument that simplifies debugging.
+
+
 Plugin hooks
 ============

-A plugin may provide the following hooks. Hooks should be decorated with
+A plugin may provide the following hooks. Hooks must be decorated with
 ``ocrmypdf.hookimpl``, for example:

 .. code-block:: python
@@ -73,8 +108,58 @@ A plugin may provide the following hooks. Hooks should be decorated with
    def add_options(parser):
        pass

-The following is a complete list of hooks that may be installed and when
+The following is a complete list of hooks that are available, and when
 they are called.

-.. automodule:: ocrmypdf.pluginspec
+.. _firstresult:
+
+**Note on firstresult hooks**
+
+If multiple plugins install implementations for this hook, they will be called in
+the reverse of the order in which they are installed (i.e., last plugin wins).
+When each hook implementation is called in order, the first implementation that
+returns a value other than ``None`` will "win" and prevent execution of all other
+hooks. As such, you cannot "chain" a series of plugin filters together in this
+way. Instead, a single hook implementation should be responsible for any such
+chaining operations.
+
+Custom command line arguments
+-----------------------------
+
+.. autofunction:: ocrmypdf.pluginspec.add_options
+
+.. autofunction:: ocrmypdf.pluginspec.check_options
+
+Applying special behavior before processing
+-------------------------------------------
+
+.. autofunction:: ocrmypdf.pluginspec.validate
+
+PDF page to image
+-----------------
+
+.. autofunction:: ocrmypdf.pluginspec.rasterize_pdf_page
+
+Modifying intermediate images
+-----------------------------
+
+.. autofunction:: ocrmypdf.pluginspec.filter_ocr_image
+
+.. autofunction:: ocrmypdf.pluginspec.filter_page_image
+
+OCR engine
+----------
+
+.. autofunction:: ocrmypdf.pluginspec.get_ocr_engine
+
+.. autoclass:: ocrmypdf.pluginspec.OcrEngine
    :members:
+
+    .. automethod:: __str__
+
+.. autoclass:: ocrmypdf.pluginspec.OrientationConfidence
+
+PDF/A production
+----------------
+
+.. autofunction:: ocrmypdf.pluginspec.generate_pdfa
@@ -12,9 +12,73 @@ may be unreliable. Use the API to depend on precise behavior.
 The public API may be useful in scripts that launch OCRmyPDF processes or that
 wish to use some of its features for working with PDFs.

-Note that it is licensed under GPLv3, so scripts that
-``import ocrmypdf`` and are released publicly should probably also be
-licensed under GPLv3.
+v11.0.2
+=======
+
+-  Fixed issue #612, TypeError exception. Fixed by eliminating unnecessary repair of
+   input PDF metadata in memory.
+
+v11.0.1
+=======
+
+-  Blacklist pdfminer.six 20200720, which has a regression fixed in 20200726.
+-  Approve img2pdf 0.4 as it passes tests.
+-  Clarify that the GPL-3 portion of pdfa.py was removed with the changes in v11.0.0;
+   the debian/copyright file did not properly annotate this change.
+
+v11.0.0
+=======
+
+-  Project license changed to Mozilla Public License 2.0. Some miscellaneous
+   code is now under MIT license and non-code content/media remains under
+   CC-BY-SA 4.0. License changed with approval of all people who were found
+   to have contributed to GPLv3 licensed sections of the project. (#600)
+-  Because the license changed, this is being treated as a major version number
+   change; however, there are no known breaking changes in functional behavior
+   or API compared to v10.x.
+
+v10.3.3
+=======
+
+-  Fixed a "KeyError: 'dpi'" error message when using ``--threshold`` on an image.
+   (#607)
+
+v10.3.2
+=======
+
+-  Fixed a case where we reported "no reason" for a file size increase, when we
+   could determine the reason.
+-  Enabled support for pdfminer.six 20200726.
+
+v10.3.1
+=======
+
+-  Fixed a number of test suite failures with pdfminer.six older than veresion 20200402.
+-  Enabled support for pdfminer.six 20200720.
+
+v10.3.0
+=======
+
+-  Fixed an issue where we would consider images that were already JBIG2-encoded
+   for optimization, potentially producing a less optimized image than the original.
+   We do not believe this issue would ever cause an image to loss fidelity.
+-  Where available, pikepdf memory mapping is now used. This improves performance.
+-  When Leptonica 1.79+ is installed, use its new error handling API to avoid
+   a "messy" redirection of stderr which was necessary to capture its error
+   messages.
+-  For older versions of Leptonica, added a new thread level lock. This fixes a
+   possible race condition in handling error conditions in Leptonica (although
+   there is no evidence it ever caused issues in practice).
+-  Documentation improvements and more type hinting.
+
+v10.2.1
+=======
+
+-  Disabled calculation of text box order with pdfminer. We never needed this result
+   and it is expensive to calculate on files with complex pre-existing text.
+-  Fixed plugin manager to accept ``Path(plugin)`` as a path to a plugin.
+-  Fixed some typing errors.
+-  Documentation improvements.

 v10.2.0
 =======
@@ -332,7 +396,7 @@ v9.0.0

 -  Added a high level API for applications that want to integrate OCRmyPDF.
   Special thanks to Martin Wind (@mawi1988) whose made significant contributions
-   to this effort. OCRmyPDF is GPLv3-licensed.
+   to this effort.
 -  Added progress bars for long-running steps. ■■■■■■■□□
 -  We now create linearized ("fast web view") PDFs by default. The new parameter
   ``--fast-web-view`` provides control over when this feature is applied.
@@ -959,8 +1023,8 @@ v6.1.0
 v6.0.0
 ======

-  The software license has been changed to GPLv3. Test resource files
-   and some individual sources may have other licenses.
+-  The software license has been changed to GPLv3 [it has since changed again].
+   Test resource files and some individual sources may have other licenses.
 -  OCRmyPDF now depends on
   `PyMuPDF <https://pymupdf.readthedocs.io/en/latest/installation/>`__.
   Including PyMuPDF is the primary reason for the change to GPLv3.
@@ -1,5 +1,23 @@
 #!/usr/bin/env python3
-# Original version by DeliciousPickle@github; modified
+# Copyright 2016 findingorder: https://github.com/findingorder
+#
+# Permission is hereby granted, free of charge, to any person obtaining a copy
+# of this software and associated documentation files (the "Software"), to deal
+# in the Software without restriction, including without limitation the rights
+# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+# copies of the Software, and to permit persons to whom the Software is
+# furnished to do so, subject to the following conditions:
+#
+# The above copyright notice and this permission notice shall be included in all
+# copies or substantial portions of the Software.
+#
+# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+# SOFTWARE.

 # This script must be edited to meet your needs.

@@ -1,5 +1,26 @@
 # ocrmypdf completion                                     -*- shell-script -*-

+# Copyright 2019 Frank Pille
+# Copyright 2020 Alex Willner
+#
+# Permission is hereby granted, free of charge, to any person obtaining a copy
+# of this software and associated documentation files (the "Software"), to deal
+# in the Software without restriction, including without limitation the rights
+# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+# copies of the Software, and to permit persons to whom the Software is
+# furnished to do so, subject to the following conditions:
+#
+# The above copyright notice and this permission notice shall be included in all
+# copies or substantial portions of the Software.
+#
+# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+# SOFTWARE.
+
 set -o errexit

 _ocrmypdf()
@@ -1,3 +1,23 @@
+# Copyright 2020 James R. Barlow
+#
+# Permission is hereby granted, free of charge, to any person obtaining a copy
+# of this software and associated documentation files (the "Software"), to deal
+# in the Software without restriction, including without limitation the rights
+# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+# copies of the Software, and to permit persons to whom the Software is
+# furnished to do so, subject to the following conditions:
+#
+# The above copyright notice and this permission notice shall be included in all
+# copies or substantial portions of the Software.
+#
+# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+# SOFTWARE.
+
 complete -c ocrmypdf -x -n '__fish_is_first_arg' -l version
 complete -c ocrmypdf -x -n '__fish_is_first_arg' -s h -s "?" -l help

@@ -1,17 +1,22 @@
 # © 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
-# the Free Software Foundation, either version 3 of the License, or
-# (at your option) any later version.
+# Permission is hereby granted, free of charge, to any person obtaining a copy
+# of this software and associated documentation files (the "Software"), to deal
+# in the Software without restriction, including without limitation the rights
+# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+# copies of the Software, and to permit persons to whom the Software is
+# furnished to do so, subject to the following conditions:
 #
-# This program is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# GNU General Public License for more details.
+# The above copyright notice and this permission notice shall be included in all
+# copies or substantial portions of the Software.
 #
-# You should have received a copy of the GNU General Public License
-# along with this program.  If not, see <http://www.gnu.org/licenses/>.
+# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+# SOFTWARE.

 import logging

@@ -1,5 +1,23 @@
 #!/bin/env python3
-# Contributed by github.com/Enantiomerie
+# Copyright 2017 github.com/Enantiomerie
+#
+# Permission is hereby granted, free of charge, to any person obtaining a copy
+# of this software and associated documentation files (the "Software"), to deal
+# in the Software without restriction, including without limitation the rights
+# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+# copies of the Software, and to permit persons to whom the Software is
+# furnished to do so, subject to the following conditions:
+#
+# The above copyright notice and this permission notice shall be included in all
+# copies or substantial portions of the Software.
+#
+# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+# SOFTWARE.

 # This script must be edited to meet your needs.

@@ -1,18 +1,23 @@
 # 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
-# the Free Software Foundation, either version 3 of the License, or
-# (at your option) any later version.
+# Permission is hereby granted, free of charge, to any person obtaining a copy
+# of this software and associated documentation files (the "Software"), to deal
+# in the Software without restriction, including without limitation the rights
+# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+# copies of the Software, and to permit persons to whom the Software is
+# furnished to do so, subject to the following conditions:
 #
-# This program is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# GNU General Public License for more details.
+# The above copyright notice and this permission notice shall be included in all
+# copies or substantial portions of the Software.
 #
-# You should have received a copy of the GNU General Public License
-# along with this program.  If not, see <http://www.gnu.org/licenses/>.
+# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+# SOFTWARE.

 import json
 import logging
@@ -10,8 +10,7 @@ build-backend = "setuptools.build_meta"

 [tool.black]
 line-length = 88
-target-version = ["py36",
-"py37", "py38"]
+target-version = ["py36", "py37", "py38"]
 skip-string-normalization = true
 include = '\.pyi?$'
 exclude = '''
@@ -5,7 +5,7 @@ cffi == 1.14.0
 coloredlogs == 14.0  # technically optional
 img2pdf == 0.3.6
 pdfminer.six == 20200517
-pikepdf == 1.15.1
+pikepdf == 1.16.1
 pluggy == 0.13.1
 Pillow == 7.1.2
 reportlab == 3.5.42
@@ -2,20 +2,10 @@
 # -*- coding: utf-8 -*-
 # © 2015 James R. Barlow: github.com/jbarlow83
 #
-# This file is part of OCRmyPDF.
-#
-# OCRmyPDF is free software: you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation, either version 3 of the License, or
-# (at your option) any later version.
-#
-# OCRmyPDF is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
+# This Source Code Form is subject to the terms of the Mozilla Public
+# License, v. 2.0. If a copy of the MPL was not distributed with this
+# file, You can obtain one at http://mozilla.org/MPL/2.0/.
+

 from __future__ import print_function, unicode_literals

@@ -54,12 +44,13 @@ setup(
        "Programming Language :: Python :: 3.6",
        "Programming Language :: Python :: 3.7",
        "Programming Language :: Python :: 3.8",
+        "Programming Language :: Python :: 3.9",
        "Development Status :: 5 - Production/Stable",
        "Environment :: Console",
        "Intended Audience :: End Users/Desktop",
        "Intended Audience :: Science/Research",
        "Intended Audience :: System Administrators",
-        "License :: OSI Approved :: GNU General Public License v3 (GPLv3)",
+        "License :: OSI Approved :: Mozilla Public License 2.0 (MPL 2.0)",
        "Operating System :: MacOS :: MacOS X",
        "Operating System :: Microsoft :: Windows :: Windows 10",
        "Operating System :: POSIX",
@@ -81,8 +72,8 @@ setup(
    install_requires=[
        'cffi >= 1.9.1',  # must be a setup and install requirement
        'coloredlogs >= 14.0',  # strictly optional
-        'img2pdf >= 0.3.0, < 0.4',  # pure Python, so track HEAD closely
-        'pdfminer.six >= 20191110, <= 20200517',
+        'img2pdf >= 0.3.0, < 0.5',  # pure Python, so track HEAD closely
+        'pdfminer.six >= 20191110, != 20200720, <= 20200726',
        'pikepdf >= 1.14.0, < 2',
        'Pillow >= 7.0.0',
        'pluggy >= 0.13.0',
@@ -1,19 +1,8 @@
 # © 2017 James R. Barlow: github.com/jbarlow83
 #
-# This file is part of OCRmyPDF.
-#
-# OCRmyPDF is free software: you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation, either version 3 of the License, or
-# (at your option) any later version.
-#
-# OCRmyPDF is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
+# This Source Code Form is subject to the terms of the Mozilla Public
+# License, v. 2.0. If a copy of the MPL was not distributed with this
+# file, You can obtain one at http://mozilla.org/MPL/2.0/.


 from pluggy import HookimplMarker as _HookimplMarker
@@ -1,23 +1,14 @@
 #!/usr/bin/env python3
 # © 2015-19 James R. Barlow: github.com/jbarlow83
 #
-# This file is part of OCRmyPDF.
-#
-# OCRmyPDF is free software: you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation, either version 3 of the License, or
-# (at your option) any later version.
-#
-# OCRmyPDF is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
+# This Source Code Form is subject to the terms of the Mozilla Public
+# License, v. 2.0. If a copy of the MPL was not distributed with this
+# file, You can obtain one at http://mozilla.org/MPL/2.0/.
+

 import logging
 import os
+import signal
 import sys
 from multiprocessing import set_start_method

@@ -26,11 +17,20 @@ from ocrmypdf._plugin_manager import get_parser_options_plugins
 from ocrmypdf._sync import run_pipeline
 from ocrmypdf._validation import check_closed_streams, check_options
 from ocrmypdf.api import Verbosity, configure_logging
-from ocrmypdf.exceptions import BadArgsError, ExitCode, MissingDependencyError
+from ocrmypdf.exceptions import (
+    BadArgsError,
+    ExitCode,
+    InputFileError,
+    MissingDependencyError,
+)

 log = logging.getLogger('ocrmypdf')


+def sigbus(*args):
+    raise InputFileError("Lost access to the input file")
+
+
 def run(args=None):
    _parser, options, plugin_manager = get_parser_options_plugins(args=args)

@@ -62,6 +62,9 @@ def run(args=None):
        log.error(e)
        return ExitCode.missing_dependency

+    if hasattr(signal, 'SIGBUS'):
+        signal.signal(signal.SIGBUS, sigbus)
+
    result = run_pipeline(options=options, plugin_manager=plugin_manager)
    return result

@@ -1,19 +1,9 @@
 # © 2020 James R. Barlow: github.com/jbarlow83
 #
-# This file is part of OCRmyPDF.
-#
-# OCRmyPDF is free software: you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation, either version 3 of the License, or
-# (at your option) any later version.
-#
-# OCRmyPDF is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
+# This Source Code Form is subject to the terms of the Mozilla Public
+# License, v. 2.0. If a copy of the MPL was not distributed with this
+# file, You can obtain one at http://mozilla.org/MPL/2.0/.
+

 import logging
 import logging.handlers
@@ -28,6 +18,8 @@ from typing import Callable, Iterable, Optional

 from tqdm import tqdm

+from ocrmypdf.exceptions import InputFileError
+

 def log_listener(queue):
    """Listen to the worker processes and forward the messages to logging
@@ -53,12 +45,20 @@ def log_listener(queue):
            traceback.print_exc(file=sys.stderr)


+def process_sigbus(*args):
+    raise InputFileError("A worker process lost access to an input file")
+
+
 def process_init(queue, user_init):
    """Initialize a process pool worker"""

    # Ignore SIGINT (our parent process will kill us gracefully)
    signal.signal(signal.SIGINT, signal.SIG_IGN)

+    # Install SIGBUS handler (so our parent process can abort somewhat gracefully)
+    if hasattr(signal, 'SIGBUS'):
+        signal.signal(signal.SIGBUS, process_sigbus)
+
    # Reconfigure the root logger for this process to send all messages to a queue
    h = logging.handlers.QueueHandler(queue)
    root = logging.getLogger()
@@ -70,6 +70,9 @@ def process_init(queue, user_init):


 def thread_init(_queue, user_init):
+    # As a thread, block SIGBUS so the main thread deals with it...
+    if hasattr(signal, 'SIGBUS'):
+        signal.pthread_sigmask(signal.SIG_BLOCK, {signal.SIGBUS})
    if user_init:
        user_init()

@@ -84,7 +87,7 @@ def exec_progress_pool(
    task_arguments: Optional[Iterable] = None,
    task_finished: Optional[Callable] = None,
 ):
-    log_queue = multiprocessing.Queue(-1)
+    log_queue: multiprocessing.Queue = multiprocessing.Queue(-1)
    listener = threading.Thread(target=log_listener, args=(log_queue,))

    if use_threads:
@@ -1,18 +1,8 @@
 # © 2020 James R. Barlow: github.com/jbarlow83
 #
-# This file is part of OCRmyPDF.
-#
-# OCRmyPDF is free software: you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation, either version 3 of the License, or
-# (at your option) any later version.
-#
-# OCRmyPDF is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
+# This Source Code Form is subject to the terms of the Mozilla Public
+# License, v. 2.0. If a copy of the MPL was not distributed with this
+# file, You can obtain one at http://mozilla.org/MPL/2.0/.
+

 """Manage third party executables"""
@@ -1,19 +1,9 @@
 # © 2017 James R. Barlow: github.com/jbarlow83
 #
-# This file is part of OCRmyPDF.
-#
-# OCRmyPDF is free software: you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation, either version 3 of the License, or
-# (at your option) any later version.
-#
-# OCRmyPDF is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
+# This Source Code Form is subject to the terms of the Mozilla Public
+# License, v. 2.0. If a copy of the MPL was not distributed with this
+# file, You can obtain one at http://mozilla.org/MPL/2.0/.
+

 """Interface to Ghostscript executable"""

@@ -25,6 +15,7 @@ from os import fspath
 from pathlib import Path
 from shutil import which
 from subprocess import PIPE, CalledProcessError
+from typing import Optional, cast

 from PIL import Image

@@ -34,12 +25,12 @@ from ocrmypdf.subprocess import get_version, run

 log = logging.getLogger(__name__)

-GS = 'gs'
+_gswin = None
 if os.name == 'nt':
-    GS = which('gswin64c')
-    if not GS:
-        GS = which('gswin32c')
-        if not GS:
+    _gswin = which('gswin64c')
+    if not _gswin:
+        _gswin = which('gswin32c')
+        if not _gswin:
            raise MissingDependencyError(
                """
                ---------------------------------------------------------------------
@@ -52,7 +43,10 @@ if os.name == 'nt':
                ---------------------------------------------------------------------
                """
            )
-    GS = Path(GS).stem
+    _gswin = Path(_gswin).stem
+
+GS = _gswin if _gswin else 'gs'
+del _gswin


 def version():
@@ -77,7 +71,7 @@ def jpeg_passthrough_available() -> bool:


 def _gs_error_reported(stream) -> bool:
-    return re.search(r'error', stream, flags=re.IGNORECASE)
+    return True if re.search(r'error', stream, flags=re.IGNORECASE) else False


 def rasterize_pdf(
@@ -1,19 +1,9 @@
 # © 2018 James R. Barlow: github.com/jbarlow83
 #
-# This file is part of OCRmyPDF.
-#
-# OCRmyPDF is free software: you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation, either version 3 of the License, or
-# (at your option) any later version.
-#
-# OCRmyPDF is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
+# This Source Code Form is subject to the terms of the Mozilla Public
+# License, v. 2.0. If a copy of the MPL was not distributed with this
+# file, You can obtain one at http://mozilla.org/MPL/2.0/.
+

 """Interface to jbig2 executable"""

@@ -1,22 +1,13 @@
 # © 2018 James R. Barlow: github.com/jbarlow83
 #
-# This file is part of OCRmyPDF.
-#
-# OCRmyPDF is free software: you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation, either version 3 of the License, or
-# (at your option) any later version.
-#
-# OCRmyPDF is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
+# This Source Code Form is subject to the terms of the Mozilla Public
+# License, v. 2.0. If a copy of the MPL was not distributed with this
+# file, You can obtain one at http://mozilla.org/MPL/2.0/.
+

 """Interface to pngquant executable"""

+from os import fspath
 from tempfile import NamedTemporaryFile

 from PIL import Image
@@ -38,6 +29,8 @@ def available():


 def quantize(input_file, output_file, quality_min, quality_max):
+    input_file = fspath(input_file)
+    output_file = fspath(output_file)
    if input_file.endswith('.jpg'):
        with Image.open(input_file) as im, NamedTemporaryFile(suffix='.png') as tmp:
            im.save(tmp)
@@ -1,19 +1,9 @@
 # © 2017 James R. Barlow: github.com/jbarlow83
 #
-# This file is part of OCRmyPDF.
-#
-# OCRmyPDF is free software: you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation, either version 3 of the License, or
-# (at your option) any later version.
-#
-# OCRmyPDF is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
+# This Source Code Form is subject to the terms of the Mozilla Public
+# License, v. 2.0. If a copy of the MPL was not distributed with this
+# file, You can obtain one at http://mozilla.org/MPL/2.0/.
+

 """Interface to Tesseract executable"""

@@ -123,7 +113,7 @@ def get_languages():
    return set(lang.strip() for lang in rest)


-def tess_base_args(langs: List[str], engine_mode) -> List[str]:
+def tess_base_args(langs: List[str], engine_mode: int) -> List[str]:
    args = ['tesseract']
    if langs:
        args.extend(['-l', '+'.join(langs)])
@@ -132,7 +122,7 @@ def tess_base_args(langs: List[str], engine_mode) -> List[str]:
    return args


-def get_orientation(input_file: Path, engine_mode, timeout: float):
+def get_orientation(input_file: Path, engine_mode: int, timeout: float):
    args_tesseract = tess_base_args(['osd'], engine_mode) + [
        '--psm',
        '0',
@@ -229,9 +219,9 @@ def generate_hocr(
    input_file: Path,
    output_hocr: Path,
    output_text: Path,
-    languages: list,
-    engine_mode,
-    tessconfig: list,
+    languages: List[str],
+    engine_mode: int,
+    tessconfig: List[str],
    timeout: float,
    pagesegmode: int,
    user_words,
@@ -290,7 +280,7 @@ def generate_pdf(
    output_pdf: Path,
    output_text: Path,
    languages: List[str],
-    engine_mode,
+    engine_mode: int,
    tessconfig: List[str],
    timeout: float,
    pagesegmode: int,
@@ -1,19 +1,9 @@
 # © 2015 James R. Barlow: github.com/jbarlow83
 #
-# This file is part of OCRmyPDF.
-#
-# OCRmyPDF is free software: you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation, either version 3 of the License, or
-# (at your option) any later version.
-#
-# OCRmyPDF is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
+# This Source Code Form is subject to the terms of the Mozilla Public
+# License, v. 2.0. If a copy of the MPL was not distributed with this
+# file, You can obtain one at http://mozilla.org/MPL/2.0/.
+

 # unpaper documentation:
 # https://github.com/Flameeyes/unpaper/blob/master/doc/basic-concepts.md
@@ -1,19 +1,9 @@
 # © 2018 James R. Barlow: github.com/jbarlow83
 #
-# This file is part of OCRmyPDF.
-#
-# OCRmyPDF is free software: you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation, either version 3 of the License, or
-# (at your option) any later version.
-#
-# OCRmyPDF is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
+# This Source Code Form is subject to the terms of the Mozilla Public
+# License, v. 2.0. If a copy of the MPL was not distributed with this
+# file, You can obtain one at http://mozilla.org/MPL/2.0/.
+

 import logging
 from contextlib import suppress
@@ -1,19 +1,9 @@
 # © 2018 James R. Barlow: github.com/jbarlow83
 #
-# This file is part of OCRmyPDF.
-#
-# OCRmyPDF is free software: you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation, either version 3 of the License, or
-# (at your option) any later version.
-#
-# OCRmyPDF is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
+# This Source Code Form is subject to the terms of the Mozilla Public
+# License, v. 2.0. If a copy of the MPL was not distributed with this
+# file, You can obtain one at http://mozilla.org/MPL/2.0/.
+

 import os
 import shutil
@@ -1,19 +1,9 @@
 # © 2020 James R. Barlow: github.com/jbarlow83
 #
-# This file is part of OCRmyPDF.
-#
-# OCRmyPDF is free software: you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation, either version 3 of the License, or
-# (at your option) any later version.
-#
-# OCRmyPDF is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
+# This Source Code Form is subject to the terms of the Mozilla Public
+# License, v. 2.0. If a copy of the MPL was not distributed with this
+# file, You can obtain one at http://mozilla.org/MPL/2.0/.
+

 import logging
 import sys
@@ -1,19 +1,9 @@
 # © 2016 James R. Barlow: github.com/jbarlow83
 #
-# This file is part of OCRmyPDF.
-#
-# OCRmyPDF is free software: you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation, either version 3 of the License, or
-# (at your option) any later version.
-#
-# OCRmyPDF is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
+# This Source Code Form is subject to the terms of the Mozilla Public
+# License, v. 2.0. If a copy of the MPL was not distributed with this
+# file, You can obtain one at http://mozilla.org/MPL/2.0/.
+

 import logging
 import os
@@ -530,7 +520,9 @@ def create_ocr_image(image: Path, page_context: PageContext):
        if options.threshold:
            pix = leptonica.Pix.frompil(im)
            pix = pix.masked_threshold_on_background_norm()
-            im = pix.topil()
+            im_pix = pix.topil()
+            im_pix.info['dpi'] = im.info['dpi']
+            im = im_pix

        del draw

@@ -761,7 +753,9 @@ def metadata_fixup(working_file: Path, context: PdfContext):
            # Reverse this, because PDF/A TechNote 0003:Metadata in PDF/A-1
            # and the XMP Spec do not make this recommendation.
            if meta.get('dc:title') == 'Untitled':
-                with original.open_metadata() as original_meta:
+                with original.open_metadata(
+                    set_pikepdf_as_editor=False, update_docinfo=False
+                ) as original_meta:
                    if 'dc:title' not in original_meta:
                        del meta['dc:title']

@@ -1,19 +1,9 @@
 # © 2020 James R. Barlow: github.com/jbarlow83
 #
-# This file is part of OCRmyPDF.
-#
-# OCRmyPDF is free software: you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation, either version 3 of the License, or
-# (at your option) any later version.
-#
-# OCRmyPDF is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
+# This Source Code Form is subject to the terms of the Mozilla Public
+# License, v. 2.0. If a copy of the MPL was not distributed with this
+# file, You can obtain one at http://mozilla.org/MPL/2.0/.
+

 import argparse
 import importlib
@@ -21,7 +11,7 @@ import importlib.util
 import sys
 from functools import partial
 from pathlib import Path
-from typing import Callable, List, Tuple
+from typing import Callable, List, Tuple, Union

 import pluggy

@@ -64,18 +54,22 @@ class OcrmypdfPluginManager(pluggy.PluginManager):
        )


-def _setup_plugins(pm: pluggy.PluginManager, plugins: List[str], builtins: bool = True):
+def _setup_plugins(
+    pm: pluggy.PluginManager, plugins: List[Union[str, Path]], builtins: bool = True
+):
    pm.add_hookspecs(pluginspec)

+    all_plugins: List[Union[str, Path]] = []
    if builtins:
-        all_plugins = [
-            'ocrmypdf.builtin_plugins.ghostscript',
-            'ocrmypdf.builtin_plugins.tesseract_ocr',
-        ] + plugins
-    else:
-        all_plugins = plugins
+        all_plugins.extend(
+            [
+                'ocrmypdf.builtin_plugins.ghostscript',
+                'ocrmypdf.builtin_plugins.tesseract_ocr',
+            ]
+        )
+    all_plugins.extend(plugins)
    for name in all_plugins:
-        if name.endswith('.py'):
+        if isinstance(name, Path) or name.endswith('.py'):
            # Import by filename
            module_name = Path(name).stem
            spec = importlib.util.spec_from_file_location(module_name, name)
@@ -1,19 +1,9 @@
 # © 2016 James R. Barlow: github.com/jbarlow83
 #
-# This file is part of OCRmyPDF.
-#
-# OCRmyPDF is free software: you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation, either version 3 of the License, or
-# (at your option) any later version.
-#
-# OCRmyPDF is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
+# This Source Code Form is subject to the terms of the Mozilla Public
+# License, v. 2.0. If a copy of the MPL was not distributed with this
+# file, You can obtain one at http://mozilla.org/MPL/2.0/.
+

 import logging
 import logging.handlers
@@ -25,11 +15,13 @@ from pathlib import Path
 from tempfile import mkdtemp
 from typing import List, NamedTuple, Optional, Tuple

+import pikepdf
 import PIL

 from ocrmypdf._concurrent import exec_progress_pool
 from ocrmypdf._graft import OcrGrafter
 from ocrmypdf._jobcontext import PageContext, PdfContext, cleanup_working_files
+from ocrmypdf._logging import PageNumberFilter
 from ocrmypdf._pipeline import (
    convert_to_pdfa,
    copy_final,
@@ -62,7 +54,12 @@ from ocrmypdf._validation import (
    report_output_file_size,
 )
 from ocrmypdf.exceptions import ExitCode, ExitCodeException
-from ocrmypdf.helpers import available_cpu_count, check_pdf, samefile
+from ocrmypdf.helpers import (
+    available_cpu_count,
+    check_pdf,
+    pikepdf_enable_mmap,
+    samefile,
+)
 from ocrmypdf.pdfa import file_claims_pdfa

 log = logging.getLogger(__name__)
@@ -240,6 +237,7 @@ def worker_init(max_pixels: int):
    # the parent process, so ensure workers get it set. Not needed when running
    # threaded, but harmless to set again.
    PIL.Image.MAX_IMAGE_PIXELS = max_pixels
+    pikepdf_enable_mmap()


 def exec_concurrent(context: PdfContext):
@@ -290,6 +288,7 @@ def exec_concurrent(context: PdfContext):
    pdf = ocrgraft.finalize()

    # PDF/A and metadata
+    log.info("Postprocessing...")
    pdf = post_process(pdf, context)

    # Copy PDF file to destination
@@ -309,6 +308,7 @@ def configure_debug_logging(log_filename, prefix=''):
        '[%(asctime)s] - %(name)s - %(levelname)7s -%(pageno)s %(message)s'
    )
    log_file_handler.setFormatter(formatter)
+    log_file_handler.addFilter(PageNumberFilter())
    logging.getLogger(prefix).addHandler(log_file_handler)
    return log_file_handler

@@ -329,6 +329,8 @@ def run_pipeline(options, *, plugin_manager, api=False):
    ):
        debug_log_handler = configure_debug_logging(Path(work_folder) / "debug.log")

+    pikepdf_enable_mmap()
+
    try:
        check_requested_output_file(options)
        start_input_file, original_filename = create_input_file(options, work_folder)
@@ -1,20 +1,9 @@
 #!/usr/bin/env python3
 # © 2015-17 James R. Barlow: github.com/jbarlow83
 #
-# This file is part of OCRmyPDF.
-#
-# OCRmyPDF is free software: you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation, either version 3 of the License, or
-# (at your option) any later version.
-#
-# OCRmyPDF is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
+# This Source Code Form is subject to the terms of the Mozilla Public
+# License, v. 2.0. If a copy of the MPL was not distributed with this
+# file, You can obtain one at http://mozilla.org/MPL/2.0/.


 import locale
@@ -416,6 +405,10 @@ def report_output_file_size(options, input_file, output_file):
                    f"The optional dependency '{name}' was not found, so some image "
                    f"optimizations could not be attempted."
                )
+    if options.output_type.startswith('pdfa'):
+        reasons.append("PDF/A conversion was enabled. (Try `--output-type pdf`.)")
+    if options.plugins:
+        reasons.append("Plugins were used.")

    if reasons:
        explanation = "Possible reasons for this include:\n" + '\n'.join(reasons) + "\n"
@@ -1,19 +1,8 @@
 # © 2017 James R. Barlow: github.com/jbarlow83
 #
-# This file is part of OCRmyPDF.
-#
-# OCRmyPDF is free software: you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation, either version 3 of the License, or
-# (at your option) any later version.
-#
-# OCRmyPDF is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
+# This Source Code Form is subject to the terms of the Mozilla Public
+# License, v. 2.0. If a copy of the MPL was not distributed with this
+# file, You can obtain one at http://mozilla.org/MPL/2.0/.


 import pkg_resources
@@ -1,24 +1,13 @@
 # © 2019 James R. Barlow: github.com/jbarlow83
 #
-# This file is part of OCRmyPDF.
-#
-# OCRmyPDF is free software: you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation, either version 3 of the License, or
-# (at your option) any later version.
-#
-# OCRmyPDF is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
+# This Source Code Form is subject to the terms of the Mozilla Public
+# License, v. 2.0. If a copy of the MPL was not distributed with this
+# file, You can obtain one at http://mozilla.org/MPL/2.0/.
+

 import logging
 import os
 import sys
-from argparse import ArgumentParser
 from enum import IntEnum
 from pathlib import Path
 from typing import BinaryIO, Iterable, Union
@@ -27,7 +16,8 @@ from ocrmypdf._logging import PageNumberFilter, TqdmConsole
 from ocrmypdf._plugin_manager import get_plugin_manager
 from ocrmypdf._sync import run_pipeline
 from ocrmypdf._validation import check_options
-from ocrmypdf.cli import get_parser
+from ocrmypdf.cli import ArgumentParser, get_parser
+from ocrmypdf.helpers import is_iterable_notstr

 try:
    import coloredlogs
@@ -153,7 +143,7 @@ def create_options(
                cmdline.append(f"--{cmd_style_arg}")
            continue

-        if isinstance(val, Iterable) and not isinstance(val, str):
+        if is_iterable_notstr(val):
            for elem in val:
                cmdline.append(f"--{cmd_style_arg}")
                cmdline.append(elem)
@@ -1,16 +1,5 @@
 # © 2020 James R. Barlow: github.com/jbarlow83
 #
-# This file is part of OCRmyPDF.
-#
-# OCRmyPDF is free software: you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation, either version 3 of the License, or
-# (at your option) any later version.
-#
-# OCRmyPDF is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
+# This Source Code Form is subject to the terms of the Mozilla Public
+# License, v. 2.0. If a copy of the MPL was not distributed with this
+# file, You can obtain one at http://mozilla.org/MPL/2.0/.
@@ -1,19 +1,9 @@
 # © 2020 James R. Barlow: github.com/jbarlow83
 #
-# This file is part of OCRmyPDF.
-#
-# OCRmyPDF is free software: you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation, either version 3 of the License, or
-# (at your option) any later version.
-#
-# OCRmyPDF is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
+# This Source Code Form is subject to the terms of the Mozilla Public
+# License, v. 2.0. If a copy of the MPL was not distributed with this
+# file, You can obtain one at http://mozilla.org/MPL/2.0/.
+

 import logging

@@ -1,19 +1,9 @@
 # © 2020 James R. Barlow: github.com/jbarlow83
 #
-# This file is part of OCRmyPDF.
-#
-# OCRmyPDF is free software: you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation, either version 3 of the License, or
-# (at your option) any later version.
-#
-# OCRmyPDF is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
+# This Source Code Form is subject to the terms of the Mozilla Public
+# License, v. 2.0. If a copy of the MPL was not distributed with this
+# file, You can obtain one at http://mozilla.org/MPL/2.0/.
+

 import logging
 import os
@@ -1,19 +1,9 @@
 # © 2015-19 James R. Barlow: github.com/jbarlow83
 #
-# This file is part of OCRmyPDF.
-#
-# OCRmyPDF is free software: you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation, either version 3 of the License, or
-# (at your option) any later version.
-#
-# OCRmyPDF is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
+# This Source Code Form is subject to the terms of the Mozilla Public
+# License, v. 2.0. If a copy of the MPL was not distributed with this
+# file, You can obtain one at http://mozilla.org/MPL/2.0/.
+

 import argparse

@@ -83,8 +73,8 @@ image, and then creates a PDF from the OCR information.
 """,
        epilog="""\
 OCRmyPDF attempts to keep the output file at about the same size.  If a file
-contains losslessly compressed images, and output file will be losslessly
-compressed as well.
+contains losslessly compressed images, and images in the output file will be
+losslessly compressed as well.

 PDF is a page description file that attempts to preserve a layout exactly.
 A PDF can contain vector objects (such as text or lines) and raster objects
@@ -103,9 +93,8 @@ all objects on the page and produce an image-only PDF as output.

 If you are concerned about long-term archiving of PDFs, use the default option
 --output-type pdfa which converts the PDF to a standardized PDF/A-2b.  This
-converts images to sRGB colorspace, removes some features from the PDF such
-as Javascript or forms. If you want to minimize the number of changes made to
-your PDF, use --output-type pdf.
+removes some features from the PDF such as Javascript or forms. If you want to
+minimize the number of changes made to your PDF, use --output-type pdf.

 If OCRmyPDF is given an image file as input, it will attempt to convert the
 image to a PDF before processing.  For more control over the conversion of
@@ -113,8 +102,7 @@ images to PDF, use the Python package img2pdf or other image to PDF software.

 For example, this command uses img2pdf to convert all .png files beginning
 with the 'page' prefix to a PDF, fitting each image on A4-sized paper, and
-sending the result to OCRmyPDF through a pipe.  img2pdf is a dependency of
-ocrmypdf so it is already installed.
+sending the result to OCRmyPDF through a pipe.

    img2pdf --pagesize A4 page*.png | ocrmypdf - myfile.pdf

@@ -462,7 +450,12 @@ Online documentation is located at:
        dest='plugins',
        action='append',
        default=[],
-        help="Name of plugin to import.",
+        help="Name of plugin to import. Argument may be issued multiple times to "
+        "import multiple plugins. Plugins may be specified as module names in "
+        "Python syntax, provided they are installed in the same Python (virtual) "
+        "environment as ocrmypdf; or you may give the path to the Python file that "
+        "contains the plugin. Plugins must conform to the specification in the "
+        "OCRmyPDF documentation.",
    )

    debugging = parser.add_argument_group(
@@ -1,19 +1,8 @@
 # © 2016 James R. Barlow: github.com/jbarlow83
 #
-# This file is part of OCRmyPDF.
-#
-# OCRmyPDF is free software: you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation, either version 3 of the License, or
-# (at your option) any later version.
-#
-# OCRmyPDF is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
+# This Source Code Form is subject to the terms of the Mozilla Public
+# License, v. 2.0. If a copy of the MPL was not distributed with this
+# file, You can obtain one at http://mozilla.org/MPL/2.0/.


 from enum import IntEnum
@@ -1,19 +1,9 @@
 # © 2016 James R. Barlow: github.com/jbarlow83
 #
-# This file is part of OCRmyPDF.
-#
-# OCRmyPDF is free software: you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation, either version 3 of the License, or
-# (at your option) any later version.
-#
-# OCRmyPDF is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
+# This Source Code Form is subject to the terms of the Mozilla Public
+# License, v. 2.0. If a copy of the MPL was not distributed with this
+# file, You can obtain one at http://mozilla.org/MPL/2.0/.
+

 import logging
 import multiprocessing
@@ -35,6 +25,8 @@ log = logging.getLogger(__name__)


 class Resolution(namedtuple('Resolution', ('x', 'y'))):
+    """The number of pixels per inch in each 2D direction."""
+
    __slots__ = ()

    def round(self, ndigits: int):
@@ -113,6 +105,7 @@ def samefile(f1: os.PathLike, f2: os.PathLike):


 def is_iterable_notstr(thing: Any) -> bool:
+    """Is this is an iterable type, other than a string?"""
    return isinstance(thing, Iterable) and not isinstance(thing, str)


@@ -127,6 +120,7 @@ def page_number(input_file: os.PathLike) -> int:


 def available_cpu_count() -> int:
+    """Returns number of CPUs in the system."""
    try:
        return multiprocessing.cpu_count()
    except NotImplementedError:
@@ -173,6 +167,10 @@ def is_file_writable(test_file: os.PathLike) -> bool:


 def check_pdf(input_file: Path) -> bool:
+    """Check if a PDF complies with the PDF specification.
+
+    Checks for proper formatting and proper linearization.
+    """
    pdf = None
    try:
        pdf = pikepdf.open(input_file)
@@ -210,9 +208,18 @@ T = TypeVar('T')


 def clamp(n: T, smallest: T, largest: T) -> T:
+    """Clamps the value of n to between smallest and largest."""
    return max(smallest, min(n, largest))


+def pikepdf_enable_mmap():
+    try:
+        if pikepdf._qpdf.set_access_default_mmap(True):
+            log.debug("pikepdf mmap enabled")
+    except AttributeError:
+        log.debug("pikepdf mmap not available")
+
+
 def deprecated(func):
    """Warn that function is deprecated"""

@@ -35,7 +35,7 @@ from collections import namedtuple
 from itertools import chain
 from math import atan, cos, sin
 from pathlib import Path
-from typing import Union
+from typing import Optional, Tuple, Union
 from xml.etree import ElementTree

 from reportlab.lib.colors import black, cyan, magenta, red
@@ -133,7 +133,7 @@ class HocrTransform:
        return out

    @classmethod
-    def baseline(cls, element):
+    def baseline(cls, element) -> Tuple[float, float]:
        """
        Returns a tuple containing the baseline slope and intercept.
        """
@@ -143,7 +143,7 @@ class HocrTransform:
                return float(matches.group(1)), int(matches.group(2))
        return (0.0, 0.0)

-    def pt_from_pixel(self, pxl):
+    def pt_from_pixel(self, pxl) -> Rect:
        """
        Returns the quantity in PDF units (pt) given quantity in pixels
        """
@@ -156,11 +156,11 @@ class HocrTransform:
        return xpath

    @classmethod
-    def replace_unsupported_chars(cls, s: str):
+    def replace_unsupported_chars(cls, s: str) -> str:
        """
        Given an input string, returns the corresponding string that:
-        - is available in the helvetica facetype
-        - does not contain any ligature (to allow easy search in the PDF file)
+        * is available in the Helvetica facetype
+        * does not contain any ligature (to allow easy search in the PDF file)
        """
        return s.translate(cls.ligatures)

@@ -172,12 +172,12 @@ class HocrTransform:
    def to_pdf(
        self,
        out_filename: Path,
-        image_filename: Path = None,
+        image_filename: Optional[Path] = None,
        show_bounding_boxes: bool = False,
        fontname: str = "Helvetica",
        invisible_text: bool = False,
        interword_spaces: bool = False,
-    ):
+    ) -> None:
        """
        Creates a PDF file with an image superimposed on top of the text.
        Text is positioned according to the bounding box of the lines in
@@ -185,6 +185,20 @@ class HocrTransform:
        The image need not be identical to the image used to create the hOCR
        file.
        It can have a lower resolution, different color mode, etc.
+
+        Arguments:
+            out_filename: Path of PDF to write.
+            image_filename: Image to use for this file. If omitted, the OCR text
+                is shown.
+            show_bounding_boxes: Show bounding boxes around various text regions,
+                for debugging.
+            fontname: Name of font to use.
+            invisible_text: If True, text is rendered invisible so that is
+                selectable but never drawn. If False, text is visible and may
+                be seen if the image is skipped or deleted in Acrobat.
+            interword_spaces: If True, insert spaces between words rather than
+                drawing each word without spaces. Generally this improves text
+                extraction.
        """
        # create the PDF file
        # page size in points (1/72 in.)
@@ -3,20 +3,10 @@
 #
 # © 2013-16: jbarlow83 from Github (https://github.com/jbarlow83)
 #
-# This file is part of OCRmyPDF.
-#
-# OCRmyPDF is free software: you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation, either version 3 of the License, or
-# (at your option) any later version.
-#
-# OCRmyPDF is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
+# This Source Code Form is subject to the terms of the Mozilla Public
+# License, v. 2.0. If a copy of the MPL was not distributed with this
+# file, You can obtain one at http://mozilla.org/MPL/2.0/.
+
 #
 # Python FFI wrapper for Leptonica library

@@ -24,7 +14,9 @@ import argparse
 import logging
 import os
 import sys
+import threading
 import warnings
+from collections import deque
 from collections.abc import Sequence
 from contextlib import suppress
 from ctypes.util import find_library
@@ -75,7 +67,7 @@ except ffi.error as e:
    ) from e


-class _LeptonicaErrorTrap:
+class _LeptonicaErrorTrap_Redirect:
    """
    Context manager to trap errors reported by Leptonica.

@@ -90,19 +82,21 @@ class _LeptonicaErrorTrap:

    """

+    leptonica_lock = threading.Lock()
+
    def __init__(self):
        self.tmpfile = None
        self.copy_of_stderr = -1
        self.no_stderr = False

    def __enter__(self):
-
        self.tmpfile = TemporaryFile()

        # Save the old stderr, and redirect stderr to temporary file
-        with suppress(AttributeError):
-            sys.stderr.flush()
+        self.leptonica_lock.acquire()
        try:
+            with suppress(AttributeError):
+                sys.stderr.flush()
            self.copy_of_stderr = os.dup(sys.stderr.fileno())
            os.dup2(self.tmpfile.fileno(), sys.stderr.fileno(), inheritable=False)
        except AttributeError:
@@ -114,7 +108,10 @@ class _LeptonicaErrorTrap:
            os.dup2(self.tmpfile.fileno(), 2, inheritable=False)
        except UnsupportedOperation:
            self.copy_of_stderr = None
-        return
+        except Exception:
+            self.leptonica_lock.release()
+            raise
+        return self

    def __exit__(self, exc_type, exc_value, traceback):
        # Restore old stderr
@@ -131,6 +128,8 @@ class _LeptonicaErrorTrap:
        self.tmpfile.seek(0)  # Cursor will be at end, so move back to beginning
        leptonica_output = self.tmpfile.read().decode(errors='replace')
        self.tmpfile.close()
+        self.leptonica_lock.release()
+
        # If there are Python errors, record them
        if exc_type:
            logger.warning(leptonica_output)
@@ -148,6 +147,62 @@ class _LeptonicaErrorTrap:
        return False


+tls = threading.local()
+tls.trap = None
+
+
+@ffi.callback("void(char *)")
+def _stderr_handler(cstr):
+    msg = ffi.string(cstr).decode(errors='replace')
+    if msg.startswith("Error"):
+        logger.error(msg)
+    elif msg.startswith("Warning"):
+        logger.warning(msg)
+    else:
+        logger.debug(msg)
+    if tls.trap is not None:
+        tls.trap.append(msg)
+    return
+
+
+class _LeptonicaErrorTrap_Queue:
+    def __init__(self):
+        self.queue = deque()
+
+    def __enter__(self):
+        self.queue.clear()
+        tls.trap = self.queue
+
+    def __exit__(self, exc_type, exc_value, traceback):
+        tls.trap = None
+        output = ''.join(self.queue)
+        self.queue.clear()
+
+        # If there are Python errors, record them
+        if exc_type:
+            logger.warning(output)
+
+        if 'Error' in output:
+            if 'image file not found' in output:
+                raise FileNotFoundError()
+            if 'pixWrite: stream not opened' in output:
+                raise LeptonicaIOError()
+            if 'index not valid' in output:
+                raise IndexError()
+            raise LeptonicaError(output)
+        return False
+
+
+try:
+    lept.leptSetStderrHandler(_stderr_handler)
+except ffi.error:
+    # Pre-1.79 Leptonica does not have leptSetStderrHandler
+    _LeptonicaErrorTrap = _LeptonicaErrorTrap_Redirect
+else:
+    # 1.79 have this new symbol
+    _LeptonicaErrorTrap = _LeptonicaErrorTrap_Queue
+
+
 class LeptonicaError(Exception):
    pass

@@ -856,6 +911,8 @@ def get_leptonica_version():
    Caveat: Leptonica expects the caller to free this memory.  We don't,
    since that would involve binding to libc to access libc.free(),
    a pointless effort to reclaim 100 bytes of memory.
+
+    Reminder that this returns "leptonica-1.xx" or "leptonica-1.yy.0".
    """
    return ffi.string(lept.getLeptonicaVersion()).decode()

@@ -1,18 +1,8 @@
 # © 2017 James R. Barlow: github.com/jbarlow83
 #
-# This file is part of OCRmyPDF.
-#
-# OCRmyPDF is free software: you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation, either version 3 of the License, or
-# (at your option) any later version.
-#
-# OCRmyPDF is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
+# This Source Code Form is subject to the terms of the Mozilla Public
+# License, v. 2.0. If a copy of the MPL was not distributed with this
+# file, You can obtain one at http://mozilla.org/MPL/2.0/.
+

 """Bindings to external libraries"""
@@ -1,20 +1,10 @@
 #!/usr/bin/env python3
 # © 2017 James R. Barlow: github.com/jbarlow83
 #
-# This file is part of OCRmyPDF.
-#
-# OCRmyPDF is free software: you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation, either version 3 of the License, or
-# (at your option) any later version.
-#
-# OCRmyPDF is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
+# This Source Code Form is subject to the terms of the Mozilla Public
+# License, v. 2.0. If a copy of the MPL was not distributed with this
+# file, You can obtain one at http://mozilla.org/MPL/2.0/.
+

 from pathlib import Path

@@ -509,6 +499,8 @@ void selDestroy ( SEL **psel );
 l_int32
 setMsgSeverity(l_int32 newsev);

+void
+leptSetStderrHandler(void (*handler)(const char *));
 """
 )

@@ -1,19 +1,9 @@
 # © 2018 James R. Barlow: github.com/jbarlow83
 #
-# This file is part of OCRmyPDF.
-#
-# OCRmyPDF is free software: you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation, either version 3 of the License, or
-# (at your option) any later version.
-#
-# OCRmyPDF is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
+# This Source Code Form is subject to the terms of the Mozilla Public
+# License, v. 2.0. If a copy of the MPL was not distributed with this
+# file, You can obtain one at http://mozilla.org/MPL/2.0/.
+

 import logging
 import sys
@@ -22,9 +12,23 @@ from collections import defaultdict
 from functools import partial
 from os import fspath
 from pathlib import Path
+from typing import (
+    Any,
+    Callable,
+    Dict,
+    Iterator,
+    List,
+    MutableSet,
+    NamedTuple,
+    NewType,
+    Optional,
+    Sequence,
+    Tuple,
+    Union,
+)

 import pikepdf
-from pikepdf import Dictionary, Name
+from pikepdf import Dictionary, Name, Object, Pdf, PdfImage
 from PIL import Image
 from tqdm import tqdm

@@ -41,30 +45,40 @@ DEFAULT_JPEG_QUALITY = 75
 DEFAULT_PNG_QUALITY = 70


-def img_name(root, xref, ext):
-    return fspath(root / f'{xref:08d}{ext}')
+Xref = NewType('Xref', int)


-def png_name(root, xref):
+class XrefExt(NamedTuple):
+    xref: Xref
+    ext: str
+
+
+def img_name(root: Path, xref: Xref, ext: str) -> Path:
+    return root / f'{xref:08d}{ext}'
+
+
+def png_name(root: Path, xref: Xref) -> Path:
    return img_name(root, xref, '.png')


-def jpg_name(root, xref):
+def jpg_name(root: Path, xref: Xref) -> Path:
    return img_name(root, xref, '.jpg')


-def tif_name(root, xref):
+def tif_name(root: Path, xref: Xref) -> Path:
    return img_name(root, xref, '.tif')


-def extract_image_filter(pike, root, image, xref):
+def extract_image_filter(
+    pike: Pdf, root: Path, image: Object, xref: Xref
+) -> Optional[Tuple[PdfImage, Tuple[Name, Object]]]:
    if image.Subtype != Name.Image:
        return None
    if image.Length < 100:
        log.debug("Skipping small image, xref %s", xref)
        return None

-    pim = pikepdf.PdfImage(image)
+    pim = PdfImage(image)

    if len(pim.filter_decodeparms) > 1:
        log.debug("Skipping multiply filtered, xref %s", xref)
@@ -83,7 +97,9 @@ def extract_image_filter(pike, root, image, xref):
    return pim, filtdp


-def extract_image_jbig2(*, pike, root, image, xref, options):
+def extract_image_jbig2(
+    *, pike: pikepdf.Pdf, root: Path, image: Object, xref: Xref, options
+) -> Optional[XrefExt]:
    result = extract_image_filter(pike, root, image, xref)
    if result is None:
        return None
@@ -91,21 +107,23 @@ def extract_image_jbig2(*, pike, root, image, xref, options):

    if (
        pim.bits_per_component == 1
-        and filtdp != Name.JBIG2Decode
+        and filtdp[0] != Name.JBIG2Decode
        and jbig2enc.available()
    ):
        try:
-            imgname = Path(root / f'{xref:08d}')
+            imgname = root / f'{xref:08d}'
            with imgname.open('wb') as f:
                ext = pim.extract_to(stream=f)
            imgname.rename(imgname.with_suffix(ext))
        except pikepdf.UnsupportedImageTypeError:
            return None
-        return xref, ext
+        return XrefExt(xref, ext)
    return None


-def extract_image_generic(*, pike, root, image, xref, options):
+def extract_image_generic(
+    *, pike: Pdf, root: Path, image: PdfImage, xref: Xref, options
+) -> Optional[XrefExt]:
    result = extract_image_filter(pike, root, image, xref)
    if result is None:
        return None
@@ -138,13 +156,13 @@ def extract_image_generic(*, pike, root, image, xref, options):
        #     with Image.open(stream) as im:
        #         im.save(jpg_name(root, xref), icc_profile=iccbytes)
        try:
-            imgname = Path(root / f'{xref:08d}')
+            imgname = root / f'{xref:08d}'
            with imgname.open('wb') as f:
                ext = pim.extract_to(stream=f)
            imgname.rename(imgname.with_suffix(ext))
        except pikepdf.UnsupportedImageTypeError:
            return None
-        return xref, ext
+        return XrefExt(xref, ext)
    elif (
        pim.indexed
        and pim.colorspace in pim.SIMPLE_COLORSPACES
@@ -153,12 +171,12 @@ def extract_image_generic(*, pike, root, image, xref, options):
        # Try to improve on indexed images - these are far from low hanging
        # fruit in most cases
        pim.as_pil_image().save(png_name(root, xref))
-        return xref, '.png'
+        return XrefExt(xref, '.png')
    elif not pim.indexed and pim.colorspace in pim.SIMPLE_COLORSPACES:
        # An optimization opportunity here, not currently taken, is directly
        # generating a PNG from compressed data
        pim.as_pil_image().save(png_name(root, xref))
-        return xref, '.png'
+        return XrefExt(xref, '.png')
    elif (
        not pim.indexed
        and pim.colorspace == Name.ICCBased
@@ -169,12 +187,14 @@ def extract_image_generic(*, pike, root, image, xref, options):
        # paying any attention to the ICC profile, provided we're not doing
        # lossy JBIG2
        pim.as_pil_image().save(png_name(root, xref))
-        return xref, '.png'
+        return XrefExt(xref, '.png')

    return None


-def extract_images(pike, root, options, extract_fn):
+def extract_images(
+    pike: Pdf, root: Path, options, extract_fn: Callable[..., Optional[XrefExt]],
+) -> Iterator[Tuple[int, XrefExt]]:
    """Extract image using extract_fn

    Enumerate images on each page, lookup their xref/ID number in the PDF.
@@ -190,8 +210,8 @@ def extract_images(pike, root, options, extract_fn):
    extension. extract_fn must also extract the file it finds interesting.
    """

-    include_xrefs = set()
-    exclude_xrefs = set()
+    include_xrefs: MutableSet[Xref] = set()
+    exclude_xrefs: MutableSet[Xref] = set()
    pageno_for_xref = {}
    errors = 0
    for pageno, page in enumerate(pike.pages):
@@ -202,10 +222,10 @@ def extract_images(pike, root, options, extract_fn):
        for _imname, image in dict(xobjs).items():
            if image.objgen[1] != 0:
                continue  # Ignore images in an incremental PDF
-            xref = image.objgen[0]
+            xref = Xref(image.objgen[0])
            if hasattr(image, 'SMask'):
                # Ignore soft masks
-                smask_xref = image.SMask.objgen[0]
+                smask_xref = Xref(image.SMask.objgen[0])
                exclude_xrefs.add(smask_xref)
            include_xrefs.add(xref)
            if xref not in pageno_for_xref:
@@ -224,31 +244,33 @@ def extract_images(pike, root, options, extract_fn):
        else:
            if result:
                _, ext = result
-                yield pageno_for_xref[xref], xref, ext
+                yield pageno_for_xref[xref], XrefExt(xref, ext)


-def extract_images_generic(pike, root, options):
+def extract_images_generic(
+    pike: Pdf, root: Path, options
+) -> Tuple[List[Xref], List[Xref]]:
    """Extract any >=2bpp image we think we can improve"""

    jpegs = []
    pngs = []
-    for _, xref, ext in extract_images(pike, root, options, extract_image_generic):
-        log.debug('xref = %s ext = %s', xref, ext)
-        if ext == '.png':
-            pngs.append(xref)
-        elif ext == '.jpg':
-            jpegs.append(xref)
+    for _, xref_ext in extract_images(pike, root, options, extract_image_generic):
+        log.debug('%s', xref_ext)
+        if xref_ext.ext == '.png':
+            pngs.append(xref_ext.xref)
+        elif xref_ext.ext == '.jpg':
+            jpegs.append(xref_ext.xref)
    log.debug("Optimizable images: JPEGs: %s PNGs: %s", len(jpegs), len(pngs))
    return jpegs, pngs


-def extract_images_jbig2(pike, root, options):
+def extract_images_jbig2(pike: Pdf, root: Path, options) -> Dict[int, List[XrefExt]]:
    """Extract any bitonal image that we think we can improve as JBIG2"""

    jbig2_groups = defaultdict(list)
-    for pageno, xref, ext in extract_images(pike, root, options, extract_image_jbig2):
+    for pageno, xref_ext in extract_images(pike, root, options, extract_image_jbig2):
        group = pageno // options.jbig2_page_group_size
-        jbig2_groups[group].append((xref, ext))
+        jbig2_groups[group].append(xref_ext)

    # Elide empty groups
    jbig2_groups = {
@@ -258,10 +280,12 @@ def extract_images_jbig2(pike, root, options):
    return jbig2_groups


-def _produce_jbig2_images(jbig2_groups, root, options):
+def _produce_jbig2_images(
+    jbig2_groups: Dict[int, List[XrefExt]], root: Path, options
+) -> None:
    """Produce JBIG2 images from their groups"""

-    def jbig2_group_args(root, groups):
+    def jbig2_group_args(root: Path, groups: Dict[int, List[XrefExt]]):
        for group, xref_exts in groups.items():
            prefix = f'group{group:08d}'
            yield dict(
@@ -270,7 +294,7 @@ def _produce_jbig2_images(jbig2_groups, root, options):
                out_prefix=prefix,
            )

-    def jbig2_single_args(root, groups):
+    def jbig2_single_args(root, groups: Dict[int, List[XrefExt]]):
        for group, xref_exts in groups.items():
            prefix = f'group{group:08d}'
            # Second loop is to ensure multiple images per page are unpacked
@@ -306,7 +330,9 @@ def _produce_jbig2_images(jbig2_groups, root, options):
    )


-def convert_to_jbig2(pike, jbig2_groups, root, options):
+def convert_to_jbig2(
+    pike: Pdf, jbig2_groups: Dict[int, List[XrefExt]], root: Path, options
+) -> None:
    """Convert images to JBIG2 and insert into PDF.

    When the JBIG2 page group size is > 1 we do several JBIG2 images at once
@@ -344,19 +370,19 @@ def convert_to_jbig2(pike, jbig2_groups, root, options):
            )


-def transcode_jpegs(pike, jpegs, root, options):
+def transcode_jpegs(pike: Pdf, jpegs: Sequence[Xref], root: Path, options) -> None:
    for xref in tqdm(
        jpegs, desc="JPEGs", unit='image', disable=not options.progress_bar
    ):
-        in_jpg = Path(jpg_name(root, xref))
+        in_jpg = jpg_name(root, xref)
        opt_jpg = in_jpg.with_suffix('.opt.jpg')

        # This produces a debug warning from PIL
        # DEBUG:PIL.Image:Error closing: 'NoneType' object has no attribute
        # 'close'.  Seems to be mostly harmless
        # https://github.com/python-pillow/Pillow/issues/1144
-        with Image.open(fspath(in_jpg)) as im:
-            im.save(fspath(opt_jpg), optimize=True, quality=options.jpeg_quality)
+        with Image.open(in_jpg) as im:
+            im.save(opt_jpg, optimize=True, quality=options.jpeg_quality)

        if opt_jpg.stat().st_size > in_jpg.stat().st_size:
            log.debug("xref %s, jpeg, made larger - skip", xref)
@@ -367,8 +393,14 @@ def transcode_jpegs(pike, jpegs, root, options):
        im_obj.write(compdata.read(), filter=Name.DCTDecode)


-def transcode_pngs(pike, images, image_name_fn, root, options):
-    modified = set()
+def transcode_pngs(
+    pike: Pdf,
+    images: Sequence[Xref],
+    image_name_fn: Callable[[Path, Xref], Path],
+    root: Path,
+    options,
+) -> None:
+    modified: MutableSet[Xref] = set()
    if options.optimize >= 2:
        png_quality = (
            max(10, options.png_quality - 10),
@@ -431,7 +463,7 @@ def transcode_pngs(pike, images, image_name_fn, root, options):
            rewrite_png_as_g4(pike, im_obj, compdata)


-def rewrite_png_as_g4(pike, im_obj, compdata):
+def rewrite_png_as_g4(pike: Pdf, im_obj: Object, compdata) -> None:
    im_obj.BitsPerComponent = 1
    im_obj.Width = compdata.w
    im_obj.Height = compdata.h
@@ -451,7 +483,7 @@ def rewrite_png_as_g4(pike, im_obj, compdata):
    return


-def rewrite_png(pike, im_obj, compdata):
+def rewrite_png(pike: Pdf, im_obj: Object, compdata) -> None:
    # When a PNG is inserted into a PDF, we more or less copy the IDAT section from
    # the PDF and transfer the rest of the PNG headers to PDF image metadata.
    # One thing we have to do is tell the PDF reader whether a predictor was used
@@ -504,7 +536,7 @@ def rewrite_png(pike, im_obj, compdata):
    im_obj.write(compdata.read(), filter=Name.FlateDecode, decode_parms=dparms)


-def optimize(input_file, output_file, context, save_settings):
+def optimize(input_file: Path, output_file: Path, context, save_settings) -> None:
    options = context.options
    if options.optimize == 0:
        safe_symlink(input_file, output_file)
@@ -518,7 +550,7 @@ def optimize(input_file, output_file, context, save_settings):
        options.jbig2_page_group_size = 10 if options.jbig2_lossy else 1

    with pikepdf.Pdf.open(input_file) as pike:
-        root = Path(output_file).parent / 'images'
+        root = output_file.parent / 'images'
        root.mkdir(exist_ok=True)

        jpegs, pngs = extract_images_generic(pike, root, options)
@@ -531,12 +563,12 @@ def optimize(input_file, output_file, context, save_settings):
        jbig2_groups = extract_images_jbig2(pike, root, options)
        convert_to_jbig2(pike, jbig2_groups, root, options)

-        target_file = Path(output_file).with_suffix('.opt.pdf')
+        target_file = output_file.with_suffix('.opt.pdf')
        pike.remove_unreferenced_resources()
        pike.save(target_file, **save_settings)

-    input_size = Path(input_file).stat().st_size
-    output_size = Path(target_file).stat().st_size
+    input_size = input_file.stat().st_size
+    output_size = target_file.stat().st_size
    if output_size == 0:
        raise OutputFileAccessError(
            f"Output file not created after optimizing. We probably ran "
@@ -557,8 +589,8 @@ def optimize(input_file, output_file, context, save_settings):


 def main(infile, outfile, level, jobs=1):
-    from tempfile import TemporaryDirectory  # pylint: disable=import-outside-toplevel
    from shutil import copy  # pylint: disable=import-outside-toplevel
+    from tempfile import TemporaryDirectory  # pylint: disable=import-outside-toplevel

    class OptimizeOptions:
        """Emulate ocrmypdf's options"""
@@ -576,6 +608,7 @@ def main(infile, outfile, level, jobs=1):
            self.quiet = True
            self.progress_bar = False

+    infile = Path(infile)
    options = OptimizeOptions(
        input_file=infile,
        jobs=jobs,
@@ -1,39 +1,17 @@
-# © 2015 James R. Barlow: github.com/jbarlow83
+# © 2020 James R. Barlow: github.com/jbarlow83
 #
-# This file is part of OCRmyPDF.
-#
-# OCRmyPDF is free software: you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation, either version 3 of the License, or
-# (at your option) any later version.
-#
-# OCRmyPDF is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
+# This Source Code Form is subject to the terms of the Mozilla Public
+# License, v. 2.0. If a copy of the MPL was not distributed with this
+# file, You can obtain one at http://mozilla.org/MPL/2.0/.
+

 """
-Generate a PDFMARK file for Ghostscript >= 9.14, for PDF/A conversion
-
-pdfmark is an extension to the Postscript language that describes some PDF
-features like bookmarks and annotations. It was originally specified Adobe
-Distiller, for Postscript to PDF conversion:
-https://www.adobe.com/content/dam/acom/en/devnet/acrobat/pdfs/pdfmark_reference.pdf
-
-Ghostscript uses pdfmark for PDF to PDF/A conversion as well. To use Ghostscript
-to create a PDF/A, we need to create a pdfmark file with the necessary metadata.
-
-This takes care of the many version-specific bugs and pecularities in
-Ghostscript's handling of pdfmark.
-
+Utilities for PDF/A production and confirmation with Ghostspcript.
 """

 import base64
 from pathlib import Path
-from string import Template
+from typing import Dict, Iterator, Union

 import pikepdf
 import pkg_resources
@@ -43,58 +21,88 @@ ICC_PROFILE_RELPATH = 'data/sRGB.icc'
 SRGB_ICC_PROFILE = pkg_resources.resource_filename('ocrmypdf', ICC_PROFILE_RELPATH)


-# This is a template written in PostScript which is needed to create PDF/A
-# files, from the Ghostscript documentation. Lines beginning with % are
-# comments. Python substitution variables have a '$' prefix.
-pdfa_def_template = u"""%!
-% Define an ICC profile :
-/ICCProfile $icc_profile
-def
+def _postscript_objdef(
+    alias: str,
+    dictionary: Dict[str, str],
+    *,
+    stream_name: str = None,
+    stream_data: bytes = None,
+) -> Iterator[str]:
+    assert (stream_name is None) == (stream_data is None)

-[/_objdef {icc_PDFA} /type /stream /OBJ pdfmark
-[{icc_PDFA} << /N 3 >> /PUT pdfmark
-[{icc_PDFA} ICCProfile /PUT pdfmark
+    objtype = '/stream' if stream_name else '/dict'

-% Define the output intent dictionary :
+    if stream_name:
+        a85_data = base64.a85encode(stream_data, adobe=True).decode('ascii')
+        yield f'{stream_name} ' + a85_data
+        yield 'def'

-[/_objdef {OutputIntent_PDFA} /type /dict /OBJ pdfmark
-[{OutputIntent_PDFA} <<
-  /Type /OutputIntent             % Must be so (the standard requires).
-  /S /GTS_PDFA1                   % Must be so (the standard requires).
-  /DestOutputProfile {icc_PDFA}            % Must be so (see above).
-  /OutputConditionIdentifier ($icc_identifier)
->> /PUT pdfmark
-[{Catalog} <</OutputIntents [ {OutputIntent_PDFA} ]>> /PUT pdfmark
-"""
+    if alias != '{Catalog}':  # Catalog needs no definition
+        yield f'[/_objdef {alias} /type {objtype} /OBJ pdfmark'
+
+    yield f'[{alias} <<'
+    for key, val in dictionary.items():
+        yield f'  {key} {val}'
+    yield '>> /PUT pdfmark'
+
+    if stream_name:
+        yield f'[{alias} {stream_name[1:]} /PUT pdfmark'


-def generate_pdfa_ps(target_filename, icc='sRGB'):
-    """Create a Postscript pdfmark file for Ghostscript PDF/A conversion
+def _make_postscript(icc_name: str, icc_data: bytes, colors: int) -> Iterator[str]:
+    yield '%!'
+    yield from _postscript_objdef(
+        '{icc_PDFA}',  # Not an f-string
+        {'/N': str(colors)},
+        stream_name='/ICCProfile',
+        stream_data=icc_data,
+    )
+    yield ''
+    yield from _postscript_objdef(
+        '{OutputIntent_PDFA}',
+        {
+            '/Type': '/OutputIntent',
+            '/S': '/GTS_PDFA1',
+            '/DestOutputProfile': '{icc_PDFA}',
+            '/OutputConditionIdentifier': f'({icc_name})',  # Only f-string
+        },
+    )
+    yield ''
+    yield from _postscript_objdef(
+        '{Catalog}', {'/OutputIntents': '[ {OutputIntent_PDFA} ]'}
+    )

-    A pdfmark file is a small Postscript program that provides some information
-    Ghostscript needs to perform PDF/A conversion. The only information we put
-    in specifies that we want the file to be a PDF/A, and we want to Ghostscript
-    to convert objects to the sRGB colorspace if it runs into any object that
-    it decides must be converted.

-    See the Adobe pdfmark Reference for details:
-    https://www.adobe.com/content/dam/acom/en/devnet/acrobat/pdfs/pdfmark_reference.pdf
+def generate_pdfa_ps(target_filename: Path, icc: str = 'sRGB'):
+    """Create a Postscript PDFMARK file for Ghostscript PDF/A conversion

-    :param target_filename: filename to save
-    :param icc: ICC identifier such as 'sRGB'
+    pdfmark is an extension to the Postscript language that describes some PDF
+    features like bookmarks and annotations. It was originally specified Adobe
+    Distiller, for Postscript to PDF conversion.
+
+    Ghostscript uses pdfmark for PDF to PDF/A conversion as well. To use Ghostscript
+    to create a PDF/A, we need to create a pdfmark file with the necessary metadata.
+
+    This function takes care of the many version-specific bugs and pecularities in
+    Ghostscript's handling of pdfmark.
+
+    The only information we put in specifies that we want the file to be a
+    PDF/A, and we want to Ghostscript to convert objects to the sRGB colorspace
+    if it runs into any object that it decides must be converted.
+
+    Arguments:
+        target_filename: filename to save
+        icc: ICC identifier such as 'sRGB'
+    References:
+        Adobe PDFMARK Reference: https://www.adobe.com/content/dam/acom/en/devnet/acrobat/pdfs/pdfmark_reference.pdf
    """
    if icc == 'sRGB':
        icc_profile = SRGB_ICC_PROFILE
    else:
        raise NotImplementedError("Only supporting sRGB")

-    # Read the ICC profile, encode as ASCII85 and convert to a string which we
-    # will insert in the .ps file
    bytes_icc_profile = Path(icc_profile).read_bytes()
-    icc_profile = base64.a85encode(bytes_icc_profile, adobe=True).decode('ascii')
-
-    t = Template(pdfa_def_template)
-    ps = t.substitute(icc_profile=icc_profile, icc_identifier=icc)
+    ps = '\n'.join(_make_postscript(icc, bytes_icc_profile, 3))

    # We should have encoded everything to pure ASCII by this point, and
    # to be safe, only allow ASCII in PostScript
@@ -102,7 +110,7 @@ def generate_pdfa_ps(target_filename, icc='sRGB'):
    return target_filename


-def file_claims_pdfa(filename):
+def file_claims_pdfa(filename: Path):
    """Determines if the file claims to be PDF/A compliant

    This only checks if the XMP metadata contains a PDF/A marker. It does not
@@ -119,7 +127,7 @@ def file_claims_pdfa(filename):
            }
        valid_part_conforms = {'1A', '1B', '2A', '2B', '2U', '3A', '3B', '3U'}
        conformance = f'PDF/A-{pdfmeta.pdfa_status}'
-        pdfa_dict = {}
+        pdfa_dict: Dict[str, Union[str, bool]] = {}
        if pdfmeta.pdfa_status in valid_part_conforms:
            pdfa_dict['pass'] = True
            pdfa_dict['output'] = 'pdfa'
@@ -1,19 +1,9 @@
 #!/usr/bin/env python3
 # © 2015 James R. Barlow: github.com/jbarlow83
 #
-# This file is part of OCRmyPDF.
-#
-# OCRmyPDF is free software: you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation, either version 3 of the License, or
-# (at your option) any later version.
-#
-# OCRmyPDF is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
+# This Source Code Form is subject to the terms of the Mozilla Public
+# License, v. 2.0. If a copy of the MPL was not distributed with this
+# file, You can obtain one at http://mozilla.org/MPL/2.0/.
+

 from ocrmypdf.pdfinfo.info import Colorspace, Encoding, PdfInfo
@@ -1,20 +1,10 @@
 #!/usr/bin/env python3
 # © 2015 James R. Barlow: github.com/jbarlow83
 #
-# This file is part of OCRmyPDF.
-#
-# OCRmyPDF is free software: you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation, either version 3 of the License, or
-# (at your option) any later version.
-#
-# OCRmyPDF is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
+# This Source Code Form is subject to the terms of the Mozilla Public
+# License, v. 2.0. If a copy of the MPL was not distributed with this
+# file, You can obtain one at http://mozilla.org/MPL/2.0/.
+

 import logging
 import re
@@ -25,7 +15,7 @@ from functools import partial
 from math import hypot, isclose
 from os import PathLike
 from pathlib import Path
-from typing import Any, Dict, List
+from typing import Any, Dict, List, Optional, Union
 from warnings import warn

 import pikepdf
@@ -33,7 +23,7 @@ from pikepdf import PdfMatrix

 from ocrmypdf._concurrent import exec_progress_pool
 from ocrmypdf.exceptions import EncryptedPdfError
-from ocrmypdf.helpers import Resolution, available_cpu_count
+from ocrmypdf.helpers import Resolution, available_cpu_count, pikepdf_enable_mmap
 from ocrmypdf.pdfinfo.layout import get_page_analysis, get_text_boxes

 logger = logging.getLogger()
@@ -91,7 +81,7 @@ UNIT_SQUARE = (1.0, 0.0, 0.0, 1.0, 0.0, 0.0)
 def _is_unit_square(shorthand):
    values = map(float, shorthand)
    pairwise = zip(values, UNIT_SQUARE)
-    return all([isclose(a, b, rel_tol=1e-3) for a, b in pairwise])
+    return all(isclose(a, b, rel_tol=1e-3) for a, b in pairwise)


 XobjectSettings = namedtuple('XobjectSettings', ['name', 'shorthand', 'stack_depth'])
@@ -237,7 +227,7 @@ def _get_dpi(ctm_shorthand, image_size):
    width-axis vector v0 (1, 0), height-axis vector vh (0, 1) with the matrix,
    which gives the dimensions of the image in PDF units. From there we can
    compare to actual image dimensions. PDF uses
-    row vector * matrix_tranposed unlike the traditional
+    row vector * matrix_transposed unlike the traditional
    matrix * column vector.

    The offset, width and height vectors can be combined in a matrix and
@@ -523,7 +513,7 @@ def _process_content_streams(*, pdf, container, shorthand=None):
    yield from _find_form_xobject_images(pdf, container, contentsinfo)


-def _page_has_text(text_blocks, page_width, page_height):
+def _page_has_text(text_blocks, page_width, page_height) -> bool:
    """Smarter text detection that ignores text in margins"""

    pw, ph = float(page_width), float(page_height)
@@ -567,7 +557,7 @@ def simplify_textboxes(miner, textbox_getter):


 def _pdf_get_pageinfo(
-    pdf, pageno: int, infile: PathLike, check_pages, detailed_analysis
+    pdf, pageno: int, infile: PathLike, check_pages, detailed_analysis: bool
 ):
    pageinfo: Dict[str, Any] = {}
    pageinfo['pageno'] = pageno
@@ -639,6 +629,7 @@ worker_pdf = None

 def _pdf_pageinfo_sync_init(infile):
    global worker_pdf  # pylint: disable=global-statement
+    pikepdf_enable_mmap()
    worker_pdf = pikepdf.open(infile)


@@ -696,41 +687,41 @@ class PageInfo:
        )

    @property
-    def pageno(self):
+    def pageno(self) -> int:
        return self._pageno

    @property
-    def has_text(self):
+    def has_text(self) -> bool:
        return self._pageinfo['has_text']

    @property
-    def has_corrupt_text(self):
+    def has_corrupt_text(self) -> bool:
        if not self._detailed_analysis:
            raise NotImplementedError('Did not do detailed analysis')
        return any(tbox.is_corrupt for tbox in self._pageinfo['textboxes'])

    @property
-    def has_vector(self):
+    def has_vector(self) -> bool:
        return self._pageinfo['has_vector']

    @property
-    def width_inches(self):
+    def width_inches(self) -> Decimal:
        return self._pageinfo['width_inches']

    @property
-    def height_inches(self):
+    def height_inches(self) -> Decimal:
        return self._pageinfo['height_inches']

    @property
-    def width_pixels(self):
+    def width_pixels(self) -> int:
        return int(round(float(self.width_inches) * self.dpi.x))

    @property
-    def height_pixels(self):
+    def height_pixels(self) -> int:
        return int(round(float(self.height_inches) * self.dpi.y))

    @property
-    def rotation(self):
+    def rotation(self) -> int:
        return self._pageinfo.get('rotate', None)

    @rotation.setter
@@ -744,7 +735,9 @@ class PageInfo:
    def images(self):
        return self._pageinfo['images']

-    def get_textareas(self, visible=None, corrupt=None):
+    def get_textareas(
+        self, visible: Optional[bool] = None, corrupt: Optional[bool] = None
+    ):
        def predicate(obj, want_visible, want_corrupt):
            result = True
            if want_visible is not None:
@@ -767,15 +760,15 @@ class PageInfo:
        )

    @property
-    def dpi(self):
+    def dpi(self) -> Resolution:
        return self._pageinfo.get('dpi', Resolution(0.0, 0.0))

    @property
-    def userunit(self):
+    def userunit(self) -> Decimal:
        return self._pageinfo.get('userunit', None)

    @property
-    def min_version(self):
+    def min_version(self) -> str:
        if self.userunit is not None:
            return '1.6'
        else:
@@ -795,9 +788,9 @@ class PdfInfo:
    def __init__(
        self,
        infile,
-        detailed_analysis=False,
-        progbar=False,
-        max_workers=None,
+        detailed_analysis: bool = False,
+        progbar: bool = False,
+        max_workers: int = None,
        check_pages=None,
    ):
        self._infile = infile
@@ -828,29 +821,29 @@ class PdfInfo:
        return self._pages

    @property
-    def min_version(self):
+    def min_version(self) -> str:
        # The minimum PDF is the maximum version that any particular page needs
        return max(page.min_version for page in self.pages)

    @property
-    def has_userunit(self):
+    def has_userunit(self) -> bool:
        return any(page.userunit != 1.0 for page in self.pages)

    @property
-    def has_acroform(self):
+    def has_acroform(self) -> bool:
        return self._has_acroform

    @property
-    def filename(self):
+    def filename(self) -> Union[str, Path]:
        if not isinstance(self._infile, (str, Path)):
            raise NotImplementedError("can't get filename from stream")
        return self._infile

    @property
-    def needs_rendering(self):
+    def needs_rendering(self) -> bool:
        return self._needs_rendering

-    def __getitem__(self, item):
+    def __getitem__(self, item) -> PageInfo:
        return self._pages[item]

    def __len__(self):
@@ -1,19 +1,9 @@
 # © 2018 James R. Barlow: github.com/jbarlow83
 #
-# This file is part of OCRmyPDF.
-#
-# OCRmyPDF is free software: you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation, either version 3 of the License, or
-# (at your option) any later version.
-#
-# OCRmyPDF is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
+# This Source Code Form is subject to the terms of the Mozilla Public
+# License, v. 2.0. If a copy of the MPL was not distributed with this
+# file, You can obtain one at http://mozilla.org/MPL/2.0/.
+

 import re
 from math import copysign
@@ -220,8 +210,16 @@ class TextPositionTracker(PDFLayoutAnalyzer):

 def get_page_analysis(infile, pageno, pscript5_mode):
    rman = pdfminer.pdfinterp.PDFResourceManager(caching=True)
+    if pdfminer.__version__ < '20200402':
+        # Workaround for https://github.com/pdfminer/pdfminer.six/issues/395
+        disable_boxes_flow = 2
+    else:
+        disable_boxes_flow = None
    dev = TextPositionTracker(
-        rman, laparams=LAParams(all_texts=True, detect_vertical=True)
+        rman,
+        laparams=LAParams(
+            all_texts=True, detect_vertical=True, boxes_flow=disable_boxes_flow
+        ),
    )
    interp = pdfminer.pdfinterp.PDFPageInterpreter(rman, dev)

@@ -1,19 +1,9 @@
 # © 2020 James R. Barlow: github.com/jbarlow83
 #
-# This file is part of OCRmyPDF.
-#
-# OCRmyPDF is free software: you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation, either version 3 of the License, or
-# (at your option) any later version.
-#
-# OCRmyPDF is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
+# This Source Code Form is subject to the terms of the Mozilla Public
+# License, v. 2.0. If a copy of the MPL was not distributed with this
+# file, You can obtain one at http://mozilla.org/MPL/2.0/.
+

 from abc import ABC, abstractmethod, abstractstaticmethod
 from argparse import ArgumentParser, Namespace
@@ -22,11 +12,12 @@ from pathlib import Path
 from typing import TYPE_CHECKING, AbstractSet, List, Optional

 import pluggy
-from PIL import Image

 from ocrmypdf.helpers import Resolution

 if TYPE_CHECKING:
+    from PIL import Image
+
    from ocrmypdf._jobcontext import PageContext
    from ocrmypdf.pdfinfo import PdfInfo

@@ -118,23 +109,39 @@ def rasterize_pdf_page(
        rotation: Cardinal angle, clockwise, to rotate page
        filter_vector: If True, remove vector graphics objects
    Returns:
-        output_file
+        Path: output_file if successful
    Note:
        This hook will be called from child processes. Modifying global state
        will not affect the main process or other child processes.
+    Note:
+        This is a :ref:`firstresult hook<firstresult>`.
    """


@hookspec(firstresult=True)
-def filter_ocr_image(page: 'PageContext', image: Image) -> Image:
+def filter_ocr_image(page: 'PageContext', image: 'Image') -> 'Image':
    """Called to filter the image before it is sent to OCR.

    This is the image that OCR sees, not what the user sees when they view the
-    PDF.
+    PDF. If ``redo_ocr`` is enabled, portions of the image will be masked so
+    they are not shown to OCR. The main use of this hook is expected to be hiding
+    content from OCR.
+
+    The input image may be color, grayscale, or monochrome, and the
+    output image may differ. The pixel width and height of the
+    output image must be identical to the input image, or misalignment between
+    the OCR text layer and visual position of the text will occur. Likewise,
+    the output must be a faithful representation of the input, or alignment
+    errors may occurs.
+
+    Tesseract OCR only deals with monochrome images, and internally converts
+    non-monochrome images to OCR.

    Note:
        This hook will be called from child processes. Modifying global state
        will not affect the main process or other child processes.
+    Note:
+        This is a :ref:`firstresult hook<firstresult>`.
    """


@@ -155,24 +162,52 @@ def filter_page_image(page: 'PageContext', image_filename: Path) -> Path:
    Note:
        This hook will be called from child processes. Modifying global state
        will not affect the main process or other child processes.
+    Note:
+        This is a :ref:`firstresult hook<firstresult>`.
    """


 OrientationConfidence = namedtuple('OrientationConfidence', ('angle', 'confidence'))
+"""Expresses an OCR engine's confidence in page rotation.
+
+Attributes:
+    angle (int): The clockwise angle (0, 90, 180, 270) that the page should be
+        rotated. 0 means no rotation.
+    confidence (float): How confident the OCR engine is that this the correct
+        rotation. 0 is not confident, 15 is very confident. Arbitrary units.
+"""


 class OcrEngine(ABC):
+    """A class representing an OCR engine with capabilities similar to Tesseract OCR.
+
+    This could be used to create a plugin for another OCR engine instead of
+    Tesseract OCR.
+    """
+
    @abstractstaticmethod
    def version() -> str:
        """Returns the version of the OCR engine."""

    @abstractstaticmethod
    def creator_tag(options: Namespace) -> str:
-        """Returns the creator tag to identify this software's role in creating the PDF."""
+        """Returns the creator tag to identify this software's role in creating the PDF.
+
+        This tag will be inserted in the XMP metadata and DocumentInfo dictionary
+        as appropriate. Ideally you should include the name of the OCR engine and its
+        version. The text should not contain line breaks. This is to help developers
+        like yourself identify the software that produced this file.
+
+        OCRmyPDF will always prepend its name to this value.
+        """

    @abstractmethod
    def __str__(self):
-        """Returns name of OCR engine and version."""
+        """Returns name of OCR engine and version.
+
+        This is used when OCRmyPDF wants to mention the name of the OCR engine
+        to the user, usually in an error message.
+        """

    @abstractstaticmethod
    def languages(options: Namespace) -> AbstractSet[str]:
@@ -213,6 +248,9 @@ def get_ocr_engine() -> OcrEngine:
    The OcrEngine may be instantiated multiple times, by both the main process
    and child process. As such, it must be obtain store any state in ``options``
    or some common location.
+
+    Note:
+        This is a :ref:`firstresult hook<firstresult>`.
    """


@@ -248,5 +286,8 @@ def generate_pdfa(
        pdfa_part: The desired PDF/A compliance level, such as ``'2B'``.

    Returns:
-        output_file: If successful, the hook should return ``output_file``.
+        Path: If successful, the hook should return ``output_file``.
+
+    Note:
+        This is a :ref:`firstresult hook<firstresult>`.
    """
@@ -1,37 +1,27 @@
 # © 2020 James R. Barlow: github.com/jbarlow83
 #
-# This file is part of OCRmyPDF.
-#
-# OCRmyPDF is free software: you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation, either version 3 of the License, or
-# (at your option) any later version.
-#
-# OCRmyPDF is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
+# This Source Code Form is subject to the terms of the Mozilla Public
+# License, v. 2.0. If a copy of the MPL was not distributed with this
+# file, You can obtain one at http://mozilla.org/MPL/2.0/.
+
+
+"""Utilities to measure OCR quality"""
+

 import re
 from typing import Iterable

-"""Utilities to measure OCR quality"""
-

 class OcrQualityDictionary:
    """Manages a dictionary for simple OCR quality checks."""

-    def __init__(self, *, wordlist: Iterable[str] = []):
+    def __init__(self, *, wordlist: Iterable[str]):
        """Construct a dictionary from a list of words.

        Words for which capitalization is important should be capitalized in the
        dictionary. Words that contain spaces or other punctuation will never match.
        """
-        self.dictionary = set()
-        self.dictionary.update(w for w in wordlist)
+        self.dictionary = set(wordlist)

    def measure_words_matched(self, ocr_text: str) -> float:
        """Check how many unique words in the OCR text match a dictionary.
@@ -1,19 +1,9 @@
 # © 2020 James R. Barlow: github.com/jbarlow83
 #
-# This file is part of OCRmyPDF.
-#
-# OCRmyPDF is free software: you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation, either version 3 of the License, or
-# (at your option) any later version.
-#
-# OCRmyPDF is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
+# This Source Code Form is subject to the terms of the Mozilla Public
+# License, v. 2.0. If a copy of the MPL was not distributed with this
+# file, You can obtain one at http://mozilla.org/MPL/2.0/.
+

 """Wrappers to manage subprocess calls"""

@@ -36,18 +26,12 @@ log = logging.getLogger(__name__)


 def run(args, *, env=None, **kwargs):
-    """Wrapper around subprocess.run()
-
-    The main purpose of this wrapper is to log subprocess output.
-
-    Secondly we have to account for behavioral differences in Windows in particular.
-    Creating symbolic links in Windows requires administrator privileges and
-    may not work if for some reason we're using a FAT file system or the temporary
-    folder is on a different drive from the working folder. The test suite
-    works around this by creating shim Python scripts that perform the same function
-    as a symbolic link, but those shims require support on this side, to ensure
-    we call them with Python.
+    """Wrapper around :py:func:`subprocess.run`

+    The main purpose of this wrapper is to log subprocess output in an orderly
+    fashion that indentifies the responsible subprocess. An additional
+    task is that this function goes to greater lengths to find possible Windows
+    locations of our dependencies when they are not on the system PATH.
    """
    if not env:
        env = os.environ
@@ -106,8 +90,18 @@ def _fix_windows_args(program, args, env):


@lru_cache(maxsize=None)
-def get_version(program, *, version_arg='--version', regex=r'(\d+(\.\d+)*)', env=None):
-    """Get the version of the specified program"""
+def get_version(
+    program: str, *, version_arg: str = '--version', regex=r'(\d+(\.\d+)*)', env=None
+):
+    """Get the version of the specified program
+
+    Arguments:
+        program: The program to version check.
+        version_arg: The argument needed to ask for its version, e.g. ``--version``.
+        regex: A regular expression to parse the program's output and obtain the
+            version.
+        env: Custom ``os.environ`` in which to run program.
+    """
    args_prog = [program, version_arg]
    try:
        proc = run(
@@ -1,19 +1,9 @@
 # © 2017 James R. Barlow: github.com/jbarlow83
 #
-# This file is part of OCRmyPDF.
-#
-# OCRmyPDF is free software: you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation, either version 3 of the License, or
-# (at your option) any later version.
-#
-# OCRmyPDF is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
+# This Source Code Form is subject to the terms of the Mozilla Public
+# License, v. 2.0. If a copy of the MPL was not distributed with this
+# file, You can obtain one at http://mozilla.org/MPL/2.0/.
+

 import os
 import platform
@@ -1,40 +0,0 @@
-# © 2019 James R. Barlow: github.com/jbarlow83
-#
-# Permission is hereby granted, free of charge, to any person obtaining a
-# copy of this software and associated documentation files (the
-# "Software"), to deal in the Software without restriction, including
-# without limitation the rights to use, copy, modify, merge, publish,
-# distribute, sublicense, and/or sell copies of the Software, and to
-# permit persons to whom the Software is furnished to do so, subject to
-# the following conditions:
-#
-# The above copyright notice and this permission notice shall be included
-# in all copies or substantial portions of the Software.
-#
-# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS
-# OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
-# MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
-# IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY
-# CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT,
-# TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE
-# SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
-
-"""Find Ghostscript executable"""
-
-
-import os
-import shutil
-
-
-def real_ghostscript(argv):
-    if os.name != 'nt':
-        gs = shutil.which('gs')
-        gs_args = [gs] + argv[1:]
-        os.execv(gs_args[0], gs_args)
-    else:
-        gs = shutil.which('gswin64c')
-        if not gs:
-            gs = shutil.which('gswin32c')
-        os.execv(gs, argv[1:])
-
-    return  # Not reachable
@@ -1,19 +1,9 @@
 # © 2019 James R. Barlow: github.com/jbarlow83
 #
-# This file is part of OCRmyPDF.
-#
-# OCRmyPDF is free software: you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation, either version 3 of the License, or
-# (at your option) any later version.
-#
-# OCRmyPDF is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
+# This Source Code Form is subject to the terms of the Mozilla Public
+# License, v. 2.0. If a copy of the MPL was not distributed with this
+# file, You can obtain one at http://mozilla.org/MPL/2.0/.
+

 import logging

@@ -1,19 +1,9 @@
 # © 2019 James R. Barlow: github.com/jbarlow83
 #
-# This file is part of OCRmyPDF.
-#
-# OCRmyPDF is free software: you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation, either version 3 of the License, or
-# (at your option) any later version.
-#
-# OCRmyPDF is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
+# This Source Code Form is subject to the terms of the Mozilla Public
+# License, v. 2.0. If a copy of the MPL was not distributed with this
+# file, You can obtain one at http://mozilla.org/MPL/2.0/.
+

 import logging
 from io import BytesIO, StringIO
@@ -1,19 +1,9 @@
 # © 2018 James R. Barlow: github.com/jbarlow83
 #
-# This file is part of OCRmyPDF.
-#
-# OCRmyPDF is free software: you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation, either version 3 of the License, or
-# (at your option) any later version.
-#
-# OCRmyPDF is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
+# This Source Code Form is subject to the terms of the Mozilla Public
+# License, v. 2.0. If a copy of the MPL was not distributed with this
+# file, You can obtain one at http://mozilla.org/MPL/2.0/.
+

 import pytest

@@ -1,19 +1,9 @@
 # © 2019 James R. Barlow: github.com/jbarlow83
 #
-# This file is part of OCRmyPDF.
-#
-# OCRmyPDF is free software: you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation, either version 3 of the License, or
-# (at your option) any later version.
-#
-# OCRmyPDF is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
+# This Source Code Form is subject to the terms of the Mozilla Public
+# License, v. 2.0. If a copy of the MPL was not distributed with this
+# file, You can obtain one at http://mozilla.org/MPL/2.0/.
+

 from subprocess import PIPE, run

@@ -1,19 +1,9 @@
 # © 2019 James R. Barlow: github.com/jbarlow83
 #
-# This file is part of OCRmyPDF.
-#
-# OCRmyPDF is free software: you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation, either version 3 of the License, or
-# (at your option) any later version.
-#
-# OCRmyPDF is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
+# This Source Code Form is subject to the terms of the Mozilla Public
+# License, v. 2.0. If a copy of the MPL was not distributed with this
+# file, You can obtain one at http://mozilla.org/MPL/2.0/.
+

 import logging
 from decimal import Decimal
@@ -1,19 +1,9 @@
 # © 2019 James R. Barlow: github.com/jbarlow83
 #
-# This file is part of OCRmyPDF.
-#
-# OCRmyPDF is free software: you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation, either version 3 of the License, or
-# (at your option) any later version.
-#
-# OCRmyPDF is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
+# This Source Code Form is subject to the terms of the Mozilla Public
+# License, v. 2.0. If a copy of the MPL was not distributed with this
+# file, You can obtain one at http://mozilla.org/MPL/2.0/.
+

 from unittest.mock import patch

@@ -1,19 +1,9 @@
 # © 2019 James R. Barlow: github.com/jbarlow83
 #
-# This file is part of OCRmyPDF.
-#
-# OCRmyPDF is free software: you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation, either version 3 of the License, or
-# (at your option) any later version.
-#
-# OCRmyPDF is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
+# This Source Code Form is subject to the terms of the Mozilla Public
+# License, v. 2.0. If a copy of the MPL was not distributed with this
+# file, You can obtain one at http://mozilla.org/MPL/2.0/.
+

 import logging
 import multiprocessing
@@ -22,7 +12,7 @@ from unittest.mock import MagicMock

 import pytest

-import ocrmypdf.helpers as helpers
+from ocrmypdf import helpers as helpers
 from ocrmypdf.subprocess import shim_paths_with_program_files


@@ -1,19 +1,9 @@
 # © 2015 James R. Barlow: github.com/jbarlow83
 #
-# This file is part of OCRmyPDF.
-#
-# OCRmyPDF is free software: you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation, either version 3 of the License, or
-# (at your option) any later version.
-#
-# OCRmyPDF is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
+# This Source Code Form is subject to the terms of the Mozilla Public
+# License, v. 2.0. If a copy of the MPL was not distributed with this
+# file, You can obtain one at http://mozilla.org/MPL/2.0/.
+

 import re
 from io import StringIO
@@ -1,19 +1,9 @@
 # © 2019 James R. Barlow: github.com/jbarlow83
 #
-# This file is part of OCRmyPDF.
-#
-# OCRmyPDF is free software: you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation, either version 3 of the License, or
-# (at your option) any later version.
-#
-# OCRmyPDF is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
+# This Source Code Form is subject to the terms of the Mozilla Public
+# License, v. 2.0. If a copy of the MPL was not distributed with this
+# file, You can obtain one at http://mozilla.org/MPL/2.0/.
+

 from unittest.mock import patch

@@ -1,42 +1,29 @@
 # © 2018 James R. Barlow: github.com/jbarlow83
 #
-# This file is part of OCRmyPDF.
-#
-# OCRmyPDF is free software: you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation, either version 3 of the License, or
-# (at your option) any later version.
-#
-# OCRmyPDF is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
+# This Source Code Form is subject to the terms of the Mozilla Public
+# License, v. 2.0. If a copy of the MPL was not distributed with this
+# file, You can obtain one at http://mozilla.org/MPL/2.0/.


-import os
 from os import fspath
 from pickle import dumps, loads
-from unittest.mock import patch

 import pytest
 from PIL import Image, ImageChops

-import ocrmypdf.leptonica as lept
+from ocrmypdf import leptonica as lp


 def test_colormap_backgroundnorm(resources):
    # Issue #262 - unclear how to reproduce exactly, so just ensure leptonica
    # can handle that case
-    pix = lept.Pix.open(resources / 'baiona_colormapped.png')
+    pix = lp.Pix.open(resources / 'baiona_colormapped.png')
    pix.background_norm()


@pytest.fixture
 def crom_pix(resources):
-    pix = lept.Pix.open(resources / 'crom.png')
+    pix = lp.Pix.open(resources / 'crom.png')
    im = Image.open(resources / 'crom.png')
    yield pix, im
    im.close()
@@ -64,17 +51,17 @@ def test_pix_otsu(crom_pix):


@pytest.mark.skipif(
-    lept.get_leptonica_version() < 'leptonica-1.76',
+    lp.get_leptonica_version() < 'leptonica-1.76',
    reason="needs new leptonica for API change",
 )
 def test_crop(resources):
-    pix = lept.Pix.open(resources / 'linn.png')
+    pix = lp.Pix.open(resources / 'linn.png')
    foreground = pix.crop_to_foreground()
    assert foreground.width < pix.width


 def test_clean_bg(resources):
-    pix = lept.Pix.open(resources / 'congress.jpg')
+    pix = lp.Pix.open(resources / 'congress.jpg')
    imbg = pix.clean_background_to_white()


@@ -96,4 +83,14 @@ def test_leptonica_compile(tmp_path):

 def test_file_not_found():
    with pytest.raises(FileNotFoundError):
-        lept.Pix.open("does_not_exist1")
+        lp.Pix.open("does_not_exist1")
+
+
+@pytest.mark.skipif(
+    lp.get_leptonica_version() < 'leptonica-1.79.0',
+    reason="test not reliable on all platforms for old leptonica",
+)
+def test_error_trap():
+    with pytest.raises(lp.LeptonicaError, match=r"Error in pixReadMem"):
+        with lp._LeptonicaErrorTrap():
+            lp.Pix(lp.lept.pixReadMem(lp.ffi.NULL, 0))
@@ -1,19 +1,9 @@
 # © 2015-19 James R. Barlow: github.com/jbarlow83
 #
-# This file is part of OCRmyPDF.
-#
-# OCRmyPDF is free software: you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation, either version 3 of the License, or
-# (at your option) any later version.
-#
-# OCRmyPDF is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
+# This Source Code Form is subject to the terms of the Mozilla Public
+# License, v. 2.0. If a copy of the MPL was not distributed with this
+# file, You can obtain one at http://mozilla.org/MPL/2.0/.
+

 import os
 import shutil
@@ -256,7 +246,7 @@ def test_missing_docinfo(resources, outpdf):
        'eng',
        '--skip-text',
        '--plugin',
-        'tests/plugins/tesseract_noop.py',
+        Path('tests/plugins/tesseract_noop.py'),
    )
    assert result == ExitCode.ok

@@ -877,3 +867,17 @@ def test_image_dpi_not_image(caplog, resources, outpdf):
        'tests/plugins/tesseract_noop.py',
    )
    assert '--image-dpi is being ignored' in caplog.text
+
+
+def test_image_dpi_threshold(resources, outpdf):
+    check_ocrmypdf(
+        resources / 'typewriter.png',
+        outpdf,
+        '--threshold',
+        '--image-dpi=170',
+        '--output-type=pdf',
+        '--optimize=0',
+        '--plugin',
+        'tests/plugins/tesseract_noop.py',
+    )
+    assert outpdf.exists()
@@ -1,19 +1,8 @@
 # © 2018 James R. Barlow: github.com/jbarlow83
 #
-# This file is part of OCRmyPDF.
-#
-# OCRmyPDF is free software: you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation, either version 3 of the License, or
-# (at your option) any later version.
-#
-# OCRmyPDF is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
+# This Source Code Form is subject to the terms of the Mozilla Public
+# License, v. 2.0. If a copy of the MPL was not distributed with this
+# file, You can obtain one at http://mozilla.org/MPL/2.0/.


 import datetime
@@ -1,19 +1,9 @@
 # © 2018 James R. Barlow: github.com/jbarlow83
 #
-# This file is part of OCRmyPDF.
-#
-# OCRmyPDF is free software: you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation, either version 3 of the License, or
-# (at your option) any later version.
-#
-# OCRmyPDF is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
+# This Source Code Form is subject to the terms of the Mozilla Public
+# License, v. 2.0. If a copy of the MPL was not distributed with this
+# file, You can obtain one at http://mozilla.org/MPL/2.0/.
+

 from os import fspath
 from pathlib import Path
@@ -1,19 +1,9 @@
 # © 2019 James R. Barlow: github.com/jbarlow83
 #
-# This file is part of OCRmyPDF.
-#
-# OCRmyPDF is free software: you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation, either version 3 of the License, or
-# (at your option) any later version.
-#
-# OCRmyPDF is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
+# This Source Code Form is subject to the terms of the Mozilla Public
+# License, v. 2.0. If a copy of the MPL was not distributed with this
+# file, You can obtain one at http://mozilla.org/MPL/2.0/.
+

 import pytest

@@ -1,19 +1,9 @@
 # © 2015 James R. Barlow: github.com/jbarlow83
 #
-# This file is part of OCRmyPDF.
-#
-# OCRmyPDF is free software: you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation, either version 3 of the License, or
-# (at your option) any later version.
-#
-# OCRmyPDF is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
+# This Source Code Form is subject to the terms of the Mozilla Public
+# License, v. 2.0. If a copy of the MPL was not distributed with this
+# file, You can obtain one at http://mozilla.org/MPL/2.0/.
+

 import pickle
 from math import isclose
@@ -1,19 +1,9 @@
 # © 2019 James R. Barlow: github.com/jbarlow83
 #
-# This file is part of OCRmyPDF.
-#
-# OCRmyPDF is free software: you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation, either version 3 of the License, or
-# (at your option) any later version.
-#
-# OCRmyPDF is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
+# This Source Code Form is subject to the terms of the Mozilla Public
+# License, v. 2.0. If a copy of the MPL was not distributed with this
+# file, You can obtain one at http://mozilla.org/MPL/2.0/.
+

 from math import isclose

@@ -1,23 +1,13 @@
 # © 2020 James R. Barlow: github.com/jbarlow83
 #
-# This file is part of OCRmyPDF.
-#
-# OCRmyPDF is free software: you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation, either version 3 of the License, or
-# (at your option) any later version.
-#
-# OCRmyPDF is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
+# This Source Code Form is subject to the terms of the Mozilla Public
+# License, v. 2.0. If a copy of the MPL was not distributed with this
+# file, You can obtain one at http://mozilla.org/MPL/2.0/.
+

 import pytest

-import ocrmypdf.quality as qual
+from ocrmypdf import quality as qual


 def test_quality_measurement():
@@ -1,19 +1,9 @@
 # © 2018 James R. Barlow: github.com/jbarlow83
 #
-# This file is part of OCRmyPDF.
-#
-# OCRmyPDF is free software: you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation, either version 3 of the License, or
-# (at your option) any later version.
-#
-# OCRmyPDF is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
+# This Source Code Form is subject to the terms of the Mozilla Public
+# License, v. 2.0. If a copy of the MPL was not distributed with this
+# file, You can obtain one at http://mozilla.org/MPL/2.0/.
+

 from io import BytesIO
 from os import fspath
@@ -1,19 +1,9 @@
 # © 2019 James R. Barlow: github.com/jbarlow83
 #
-# This file is part of OCRmyPDF.
-#
-# OCRmyPDF is free software: you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation, either version 3 of the License, or
-# (at your option) any later version.
-#
-# OCRmyPDF is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
+# This Source Code Form is subject to the terms of the Mozilla Public
+# License, v. 2.0. If a copy of the MPL was not distributed with this
+# file, You can obtain one at http://mozilla.org/MPL/2.0/.
+

 import os
 import sys
@@ -1,19 +1,9 @@
 # © 2017 James R. Barlow: github.com/jbarlow83
 #
-# This file is part of OCRmyPDF.
-#
-# OCRmyPDF is free software: you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation, either version 3 of the License, or
-# (at your option) any later version.
-#
-# OCRmyPDF is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
+# This Source Code Form is subject to the terms of the Mozilla Public
+# License, v. 2.0. If a copy of the MPL was not distributed with this
+# file, You can obtain one at http://mozilla.org/MPL/2.0/.
+

 import logging
 import os
@@ -1,19 +1,9 @@
 # © 2015-17 James R. Barlow: github.com/jbarlow83
 #
-# This file is part of OCRmyPDF.
-#
-# OCRmyPDF is free software: you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation, either version 3 of the License, or
-# (at your option) any later version.
-#
-# OCRmyPDF is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
+# This Source Code Form is subject to the terms of the Mozilla Public
+# License, v. 2.0. If a copy of the MPL was not distributed with this
+# file, You can obtain one at http://mozilla.org/MPL/2.0/.
+

 from os import fspath
 from unittest.mock import patch
@@ -1,19 +1,9 @@
 # © 2017 James R. Barlow: github.com/jbarlow83
 #
-# This file is part of OCRmyPDF.
-#
-# OCRmyPDF is free software: you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation, either version 3 of the License, or
-# (at your option) any later version.
-#
-# OCRmyPDF is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
+# This Source Code Form is subject to the terms of the Mozilla Public
+# License, v. 2.0. If a copy of the MPL was not distributed with this
+# file, You can obtain one at http://mozilla.org/MPL/2.0/.
+

 from math import isclose

@@ -1,19 +1,9 @@
 # © 2019 James R. Barlow: github.com/jbarlow83
 #
-# This file is part of OCRmyPDF.
-#
-# OCRmyPDF is free software: you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation, either version 3 of the License, or
-# (at your option) any later version.
-#
-# OCRmyPDF is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
+# This Source Code Form is subject to the terms of the Mozilla Public
+# License, v. 2.0. If a copy of the MPL was not distributed with this
+# file, You can obtain one at http://mozilla.org/MPL/2.0/.
+

 import logging
 from unittest.mock import patch
@@ -21,7 +11,7 @@ from unittest.mock import patch
 import pikepdf
 import pytest

-import ocrmypdf._validation as vd
+from ocrmypdf import _validation as vd
 from ocrmypdf._plugin_manager import get_plugin_manager
 from ocrmypdf.api import create_options
 from ocrmypdf.cli import get_parser
@@ -141,7 +131,7 @@ def test_report_file_size(tmp_path, caplog):
    pdf = pikepdf.new()
    pdf.save(in_)
    pdf.save(out)
-    opts = make_opts()
+    opts = make_opts(output_type='pdf')
    vd.report_output_file_size(opts, in_, out)
    assert caplog.text == ''
    caplog.clear()
@@ -166,7 +156,7 @@ def test_report_file_size(tmp_path, caplog):
        assert 'optional dependency' in caplog.text
    caplog.clear()

-    opts = make_opts(in_, out, optimize=0)
+    opts = make_opts(in_, out, optimize=0, output_type='pdf')
    vd.report_output_file_size(opts, in_, out)
    assert 'disabled' in caplog.text
    caplog.clear()
Author	SHA1	Message	Date
James R. Barlow	fa06ea3600	v11.0.2 release notes	2020-09-08 02:38:57 -07:00
James R. Barlow	31994258fb	metadata fixup: don't try to update original PDF's metadata with docinfo	2020-09-08 02:35:16 -07:00
James R. Barlow	1f15ecbca5	Add "Postprocessing" message as a hint for long Ghostscript runs	2020-09-08 02:34:10 -07:00
James R. Barlow	bcf5657e5c	Reorganize issue templates	2020-08-26 17:11:52 -07:00
jbarlow83andGitHub	2ae028bf38	Update issue templates	2020-08-26 17:03:09 -07:00
James R. Barlow	b51a5887e5	v11.0.1 release notes	2020-08-17 23:25:31 -07:00
James R. Barlow	fc523e837c	Clarify that the GPL-3 portion of pdfa.py was removed Removal was in `8c90f7c97`. pdfa.py now has no special licensing and falls unders the "Files: *" clause of debian/copyright.	2020-08-17 23:23:31 -07:00
James R. Barlow	caeba76a61	Approve img2pdf 0.4 as it passes tests	2020-08-14 01:34:04 -07:00
James R. Barlow	cd35216f21	setup: blacklist pdfminer.six 20200720 NotAllowedError is going to removed https://github.com/pdfminer/pdfminer.six/commit/99f0c09869370d74eb6a27234284b894c33414f4	2020-08-12 13:10:08 -07:00
James R. Barlow	e6a7b58863	Merge branch 'de-gpl'	2020-08-12 12:20:38 -07:00
James R. Barlow	56184a762f	Issue template:Give stronger hints about sample input files	2020-08-12 12:12:37 -07:00
James R. Barlow	07ab98f5af	docs: mention that Ghostscript PDF/A can swallow hyperlinks Addresses #605	2020-08-12 12:12:00 -07:00
James R. Barlow	04fb1892b4	Don't ask for sample files anymore	2020-08-12 11:40:42 -07:00
James R. Barlow	173ce2f215	v10.3.3 release notes	2020-08-07 02:23:21 -07:00
James R. Barlow	9b641055e1	Fix KeyError: 'dpi' when using --threshold on image to PDF Fixes #607	2020-08-07 02:21:02 -07:00
James R. Barlow	4fa28d7e74	v10.3.2 release notes	2020-08-05 01:36:56 -07:00
James R. Barlow	bed74501fc	Fix test breakage in validation Broken in commit 4cc0dc	2020-08-05 01:35:26 -07:00
James R. Barlow	8c90f7c972	Replace GPLv3-derived PDF/A template with PostScript generator	2020-08-05 01:30:45 -07:00
James R. Barlow	aa0ec40102	Change license of all GPLv3 files to MPL-2.0 https://github.com/jbarlow83/OCRmyPDF/issues/600	2020-08-05 00:44:42 -07:00
James R. Barlow	12c567ee10	Copyright cleanup: relicense example_plugin.py The author is relicensing this file to MIT.	2020-08-05 00:15:33 -07:00
James R. Barlow	d39778ce3a	Clarify copyright status of misc/batch.py, synology.py At the time these files were contributed there was no discussion of the license that the authors wanted to use, but the project was MIT licensed at the time. As such, these files deemed to be MIT licensed. https://github.com/jbarlow83/OCRmyPDF/issues/600	2020-08-05 00:12:44 -07:00
James R. Barlow	e824cdbc4e	Change license of misc/watcher.py to MIT The authors of this file all agreed to relicense it under the MIT license. https://github.com/jbarlow83/OCRmyPDF/issues/600	2020-08-04 23:57:41 -07:00
James R. Barlow	1d91c09963	Clarify license status of misc/completion/* files These files were contributed when the project license was GPLv3. On discussion, all known authors of these files agreed to place them under MIT license. See https://github.com/jbarlow83/OCRmyPDF/issues/600	2020-08-04 23:53:56 -07:00
James R. Barlow	e821ca46d5	Approve pdfminer.six 20200726	2020-08-03 16:04:16 -07:00
James R. Barlow	a29e4952fb	Document use of mmap	2020-08-03 16:03:54 -07:00
James R. Barlow	4cc0dc6b4a	Additional size increase reasons	2020-08-03 16:03:29 -07:00
James R. Barlow	7263702de9	Remove gs.py (spoofers entirely removed) and update copyright	2020-07-29 16:31:47 -07:00
James R. Barlow	0287d91874	v10.3.1 release notes	2020-07-26 21:53:08 -07:00
James R. Barlow	436af55050	Approve pdfminer.six 20200720	2020-07-26 21:51:49 -07:00
James R. Barlow	d6128e6937	Fix support for older versions of pdfminer.six (boxes_flow error)	2020-07-26 21:51:25 -07:00
James R. Barlow	642437e804	Merge branch 'master' of github.com:jbarlow83/OCRmyPDF	2020-07-22 00:34:33 -07:00
James R. Barlow	4ce802fdb2	v10.3.0 release notes	2020-07-22 00:34:27 -07:00
James R. Barlow	a672422b0b	Enable pikepdf mmap in other contexts	2020-07-22 00:20:07 -07:00
James R. Barlow	addc2cbad0	Enable pikepdf mmap and set up signal handlers	2020-07-22 00:19:50 -07:00
James R. Barlow	5f45f77b4e	docs: plugins update	2020-07-21 23:53:30 -07:00
James R. Barlow	93f9bffb37	Merge branch 'feature/leptonica-179'	2020-07-20 21:23:53 -07:00
James R. Barlow	44149ad319	Disable test_error_trap for Leptonica < 1.79 Old error trap seems unreliable in the first place so difficult to set up a test.	2020-07-20 21:12:00 -07:00
fcatusandGitHub	d80d963cea	pdfinfo: Replace list comp with gen expr'n	2020-07-20 02:21:58 -07:00
James R. Barlow	4da33b8050	Update debian/copyright from Debian, with fixes	2020-07-19 03:50:43 -07:00
James R. Barlow	5cbbff8472	For Leptonica 1.79+ use leptSetStderrHandler Lock free and considerably less dangerous to stderr messages.	2020-07-19 03:40:33 -07:00
James R. Barlow	fa6e47c277	Merge branch 'feature/optimize-cleanup'	2020-07-19 01:53:11 -07:00
James R. Barlow	4ea9cffebd	Add locking to Leptonica error trap To protect another thread from interfering with our redirection of stderr.	2020-07-19 01:51:58 -07:00
James R. Barlow	ae68edefc5	pipelines: fix Python 3.7/3.8 on macOS	2020-07-19 01:51:58 -07:00
James R. Barlow	1558e068f1	docs: explain firstresult hook behavior	2020-07-16 00:01:59 -07:00
James R. Barlow	d2a9c413f8	docs: install notes for ARM64	2020-07-14 01:25:16 -07:00
James R. Barlow	a510b21b20	optimize: add typing for Xref, remove fspath()'s	2020-07-09 14:06:41 -07:00
James R. Barlow	e33ba07aa4	Update pre-commit settings	2020-07-08 23:45:53 -07:00
James R. Barlow	373f27832b	optimize: improve typing of xref_exts	2020-07-07 22:41:29 -07:00
James R. Barlow	b20a6e4c5d	optimize: add type hints	2020-07-07 22:18:50 -07:00
James R. Barlow	49734d5456	optimize: fix incorrect to prevent re-optimizing JBIG2s	2020-07-07 21:52:11 -07:00
James R. Barlow	26a415c5dd	docs: Note usage of OCR_JSON_SETTINGS for watcher	2020-07-07 21:26:57 -07:00
James R. Barlow	60be64a5f1	Fix debug.log missing pageno handler	2020-07-04 03:59:38 -07:00
James R. Barlow	190294634c	docs: edit plugins	2020-07-03 16:16:01 -07:00
James R. Barlow	1722cb579d	v10.2.1 release notes	2020-07-01 03:26:57 -07:00
James R. Barlow	dc42beb6a8	More typing improvements Typing fixes bugs.	2020-06-30 15:02:30 -07:00
James R. Barlow	378f543619	TextPositionTracker: set boxes_flow=None We don't care about the order of lines in our analysis, and this is an expensive calculation in pdfminer.	2020-06-30 04:20:58 -07:00
James R. Barlow	62924ee280	Improve API documentation	2020-06-30 04:20:14 -07:00
James R. Barlow	86a73191b0	Plugin manager: accept Path(plugin)	2020-06-30 04:17:30 -07:00
James R. Barlow	86875997b8	Fix more mypy errors	2020-06-29 02:17:14 -07:00
James R. Barlow	b939584c7a	quality: fixing typing issues	2020-06-29 01:45:45 -07:00
James R. Barlow	bbd174071d	readme: markdown cleanup	2020-06-29 01:45:27 -07:00
James R. Barlow	e5b6fe1317	pyproject.toml: weird line wrapping?	2020-06-29 01:45:12 -07:00
James R. Barlow	f15d9049eb	install: add Mageia Closes #586. Thanks to @yannick56	2020-06-26 23:28:26 -07:00
James R. Barlow	7630c93e5b	install: drop Ubuntu 14.04 steps Bit rot must have set in.	2020-06-26 23:27:42 -07:00
James R. Barlow	638d68aa8a	docs: move Windows ahead of FreeBSD	2020-06-26 22:49:34 -07:00
James R. Barlow	a92dde058a	docs: promote one liner installs, reorg Windows	2020-06-26 22:47:44 -07:00
James R. Barlow	580f2ebb4b	Python 3.9beta is now known to work (Fedora)	2020-06-26 00:06:58 -07:00
James R. Barlow	01cae7a584	docs: Update Fedora versions	2020-06-23 02:08:24 -07:00