Fix pinned dependencies

v11.3.2 release notes (2)
Since we never tagged it, fix other things.
2020-11-03 04:12:47 -08:00 · 2020-11-03 02:03:25 -08:00 · 2020-11-03 01:45:06 -08:00 · 2020-11-03 01:44:35 -08:00 · 2020-11-03 01:34:28 -08:00 · 2020-11-03 01:30:31 -08:00
218 changed files with 8380 additions and 7493 deletions
@@ -11,8 +11,6 @@ concurrency =
 	multiprocessing
 source =
 	src/ocrmypdf
-omit =
-	tests/spoof/*

 [report]
 exclude_lines =
@@ -23,3 +21,4 @@ exclude_lines =
 	if 0:
 	if False:
 	if __name__ == .__main__.:
+	if TYPE_CHECKING:
@@ -1,6 +1,6 @@
 # OCRmyPDF
 #
-FROM ubuntu:19.10 as base
+FROM ubuntu:20.04 as base

 FROM base as builder

@@ -24,7 +24,7 @@ RUN \
 # Needs libleptonica-dev, zlib1g-dev
 RUN \
  mkdir jbig2 \
-  && curl -L https://github.com/agl/jbig2enc/archive/0.29.tar.gz | \
+  && curl -L https://github.com/agl/jbig2enc/archive/ea6a40a.tar.gz | \
  tar xz -C jbig2 --strip-components=1 \
  && cd jbig2 \
  && ./autogen.sh && ./configure && make && make install \
@@ -1,25 +1,44 @@
+# dotfiles
+.*
+!.coveragerc
+!.dockerignore
+!.git_archival.txt
+!.gitattributes
+!.gitignore
+!.pre-commit-config.yaml
+!.readthedocs.yml
+
+# Dev scratch
 *.ipynb
-*.pdf
-*.pyc
-*.rst
-*.sublime*
 **/*.pyc
-.*/
-!.git/
-.ruffus_history.sqlite
-bin/
-build/
-docs/
-dist/
-htmlcov/
-include/
-lib/
-MANIFEST.in
-ocrmypdf.egg-info/
-staging/
-tests/cache/
-tests/output/
+/*.pdf
+/*.qdf
+/*.png
+/scratch.py
+IDEAS
+log/
 tests/resources/private/
 tmp/
 venv*/
+/debug_tests.py
+*.traineddata
+/private
+
+# Package building
+*.egg-info/
+build/
+dist/
 wheelhouse/
+pip-wheel-metadata/
+
+# Code coverage
+htmlcov/
+
+# Docker specific
+bin/
+docs/
+include/
+lib/
+
+# Docker include .git/
+!.git/
@@ -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.
@@ -1,47 +1,43 @@
-# Development environment
-.bash_history
-.pylintrc
-.pytest_cache/
-.ruffus_history.sqlite
-.venv*/
-*.pyc
-*.sublime-*
-*.DS_Store
-.mypy_cache/
+# dotfiles
+.*
+!.coveragerc
+!.dockerignore
+!.git_archival.txt
+!.gitattributes
+!.gitignore
+!.pre-commit-config.yaml
+!.readthedocs.yml
+!.github/
+
+# Dev scratch
+*.ipynb
+**/*.pyc
+/*.pdf
+/*.qdf
+/*.png
+/scratch.py
+IDEAS
+log/
+tests/resources/private/
+tmp/
+venv*/
+/debug_tests.py
+*.traineddata
+/private

 # Package building
-.eggs/
 *.egg-info/
 build/
 dist/
 wheelhouse/
 pip-wheel-metadata/

+# Code coverage
+htmlcov/
+
 # Automatically generated files
 docs/_build/
 docs/_static/
 docs/_templates/
 docs/Makefile
 ocrmypdf/lib/_*.py
-
-# Code coverage
-.coverage*
-htmlcov/
-
-# Testing
-.ipynb_checkpoints/
-.vscode/
-*.ipynb
-*.profile
-/*.pdf
-/*.qdf
-/*.png
-/scratch.py
-IDEAS
-log/
-tests/output/
-tests/resources/private/
-tmp/
-/debug_tests.py
-*.traineddata
-/private
@@ -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: python
        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:

@@ -101,12 +92,14 @@ apt-get install tesseract-ocr-chi-sim  # Example: Install Chinese Simplified lan

 # Arch Linux users
 pacman -S tesseract-data-eng tesseract-data-deu # Example: Install the English and German language packs
+
+# brew macOS users
+brew install tesseract-lang
 ```

 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 +111,35 @@ 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.
@@ -149,12 +149,6 @@ stages:
      - job: "macOS_Mojave"
        pool:
          vmImage: "macos-10.14"
-        strategy:
-          matrix:
-            Python37:
-              python.version: "3.7"
-            # Python38:
-            #   python.version: "3.8"
        steps:
          # https://github.com/actions/virtual-environments/issues/664
          # - task: UsePythonVersion@0
@@ -162,7 +156,10 @@ stages:
          #     versionSpec: "$(python.version)"
          - bash: |
              brew update
-              brew unlink python@2
+              brew upgrade python
+              echo "Using `python3 --version`"
+            displayName: "Update brew and Python"
+          - bash: |
              brew install \
                exempi \
                ghostscript \
@@ -170,9 +167,7 @@ stages:
                leptonica \
                openjpeg \
                pngquant \
-                python \
-                tesseract \
-                unpaper
+                tesseract
            displayName: "Install system packages"
          - bash: |
              pip3 install --upgrade pip
@@ -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
@@ -184,7 +190,8 @@ of ocrmypdf, and install the following dependencies:
        python3-reportlab \
        qpdf \
        tesseract-ocr \
-        zlib1g
+        zlib1g \
+        unpaper

 We will need a newer version of ``pip`` then was available for Ubuntu 18.04:

@@ -265,68 +272,6 @@ 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 +352,43 @@ 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 +489,15 @@ 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 +505,7 @@ 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 +534,8 @@ 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 +554,8 @@ 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 +601,37 @@ 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 +666,13 @@ 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
@@ -70,11 +105,61 @@ A plugin may provide the following hooks. Hooks should be decorated with
    from ocrmpydf import hookimpl

    @hookimpl
-    def prepare(options):
+    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
@@ -5,18 +5,205 @@ Release notes
 OCRmyPDF uses `semantic versioning <http://semver.org/>`__ for its
 command line interface and its public API.

-The ``ocrmypdf`` package may now be imported. 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.
+OCRmyPDF's output messages are not considered part of the stable interface -
+that is, output messages may be improved at any release level, so parsing them
+may be unreliable. Use the API to depend on precise behavior.

-Note that it is licensed under GPLv3, so scripts that
-``import ocrmypdf`` and are released publicly should probably also be
-licensed under GPLv3.
+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.
+
+v11.3.2
+=======
+
+-  Explicitly require pikepdf 2.0.0 or newer when running on Python 3.9. (There are
+   concerns about the stability of pybind11 2.5.x with Python 3.9, which is used in
+   pikepdf 1.x.)
+-  Fixed another issue related to page rotation.
+-  Fixed an issue where image marked as image masks were not properly considered
+   as optimization candidates.
+-  On some systems, unpaper seems to be unable to process the PNGs we offer it
+   as input. We now convert the input to PNM format, which unpaper always accepts.
+   Fixes #665 and #667.
+-  DPI sent to unpaper is now rounded to a more reasonable number of decimal digits.
+-  Debug and error messages from unpaper were being suppressed.
+-  Some documentation tweaks.
+
+v11.3.1
+=======
+
+-  Declare support for new versions: pdfminer.six 20201018 and pikepdf 2.x
+-  Fix warning related to ``--pdfa-image-compression`` that appears at the wrong
+   time.
+
+v11.3.0
+=======
+
+-  The "OCR" step is describing as "Image processing" in the output messages when
+   OCR is disabled, to better explain the application's behavior.
+-  Debug logs are now only created when run as a command line, and not when OCR
+   is performed for an API call. It is the calling application's responsibility
+   to set up logging.
+-  For PDFs with a low number of pages, we gathered information about the input PDF
+   in a thread rather than process (when there are more pages). When run as a
+   thread, we did not close the file handle to the working PDF, leaking one file
+   handle per call of ``ocrmypdf.ocr``.
+-  Fixed an issue where debug messages send by child worker processes did not match
+   the log settings of parent process, causing messages to be dropped. This affected
+   macOS and Windows only where the parent process is not forked.
+-  Fixed the hookspec of rasterize_pdf_page to remove default parameters that
+   were not handled in an expected way by pluggy.
+-  Fixed another issue with automatic page rotation (#658) due to the issue above.
+
+v11.2.1
+=======
+
+-  Fixed an issue where optimization of a 1-bit image with a color palette or
+   associated ICC that was optimized to JBIG2 could have its colors inverted.
+
+v11.2.0
+=======
+
+-  Fixed an issue with optimizing PNG-type images that had soft masks or image masks.
+   This is a regression introduced in (or about) v11.1.0.
+-  Improved type checking of the ``plugins`` parameter for the ``ocrmypdf.ocr``
+   API call.
+
+v11.1.2
+=======
+
+-  Fixed hOCR renderer writing the text in roughly reverse order. This should not
+   affect reasonably smart PDF readers that properly locate the position of all
+   text, but may confuse those that rely on the order of objects in the content
+   stream. (#642)
+
+v11.1.1
+=======
+
+-  We now avoid using named temporary files when using pngquant allowing containerized
+   pngquant installs to be used.
+-  Clarified an error message.
+-  Highest number of 1's in a release ever!
+
+v11.1.0
+=======
+
+-  Fixed page rotation issues: #634, #589.
+-  Fixed some cases where optimization created an invalid image such as a
+   1-bit "RGB" image: #629, #620.
+-  Page numbers are now displayed in debug logs when pages are being grafted.
+-  ocrmypdf.optimize.rewrite_png and ocrmypdf.optimize.rewrite_png_as_g4 were
+   marked deprecated. Strictly speaking these should have been internal APIs,
+   but they were never hidden.
+-  As a precaution, pikepdf mmap-based file access has been disabled due to a
+   rare race condition that causes a crash when certain objects are deallocated.
+   The problem is likely in pikepdf's dependency pybind11.
+-  Extended the example plugin to demonstrate conversion to mono.
+
+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
+=======
+
+-  Update Docker image to use Ubuntu 20.04.
+-  Fixed issue PDF/A acquires title "Untitled" after conversion. (#582)
+-  Fixed a problem where, when using ``--pdf-renderer hocr``, some text would
+   be missing from the output when using a more recent version of Tesseract.
+   Tesseract began adding more detailed markup about the semantics of text
+   that our HOCR transform did not recognize, so it ignored them. This option is
+   not the default. If necessary ``--redo-ocr`` also redoing OCR to fix such issues.
+-  Fixed an error in Python 3.9 beta, due to removal of deprecated
+   ``Element.getchildren()``. (#584)
+-  Implemented support using the API with ``BytesIO`` and other file stream objects.
+   (#545)
+
+v10.1.1
+=======
+
+-  Fixed ``OMP_THREAD_LIMIT`` set to invalid value error messages on some input
+   files. (The error was harmless, apart from less than optimal performance in
+   some cases.)
+
+v10.1.0
+=======
+
+-  Previously, we ``--clean-final`` would cause an unpaper-cleaned page image to
+   be produced twice, which was necessary in some cases but not in general. We
+   now take this optimization opportunity and reuse the image if possible.
+-  We now provide PNG files as input to unpaper, since it accepts them, instead
+   of generating PPM files which can be very large. This can improve performance
+   and temporary disk usage.
+-  Documentation updated for plugins.

 v10.0.1
 =======

-  Fix regression when ``-l lang1+lang2`` is used from command line.
+-  Fixed regression when ``-l lang1+lang2`` is used from command line.

 v10.0.0
 =======
@@ -36,8 +223,12 @@ v10.0.0
 **New features and improvements**

 -  PDF page scanning is now parallelized across CPUs, speeding up this phase
-   for files with a high page count.
+   dramatically for files with a high page counts.
 -  PDF page scanning is optimized, addressing some performance regressions.
+-  PDF page scanning is no longer run on pages that are not selected when the
+   ``--pages`` argument is used.
+-  PDF page scanning is now independent of Ghostscript, ending our past reliance
+   on this occasionally unstable feature in Ghostscript.
 -  A plugin architecture has been added, currently allowing one to more easily
   use a different OCR engine or PDF renderer from Tesseract and Ghostscript,
   respectively. A plugin can also override some decisions, such changing
@@ -46,7 +237,7 @@ v10.0.0

 **Developer changes**

-  The test spoofing mechanism, used to correct handling of failures in
+-  The test spoofing mechanism, used to test correct handling of failures in
   Tesseract and Ghostscript, has been removed in favor of using plugins for
   testing. The spoofing mechanism was fairly complex and required many special
   hacks for Windows.
@@ -292,7 +483,7 @@ 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.
@@ -919,8 +1110,8 @@ 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 +1,41 @@
 # © 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.
+
+"""
+An example of an OCRmyPDF plugin.
+
+This plugin adds two new command line arguments
+    --grayscale-ocr: converts the image to grayscale before performing OCR on it
+        (This is occasionally useful for images whose color confounds OCR. It only
+        affects the image shown to OCR. The image is not saved.)
+    --mono-page: converts pages all pages in the output file to black and white
+
+To use this from the command line:
+    ocrmypdf --plugin path/to/example_plugin.py --mono-page input.pdf output.pdf
+
+To use this as an API:
+    import ocrmypdf
+    ocrmypdf.ocr('input.pdf', 'output.pdf',
+        plugins=['path/to/example_plugin.py'], mono_page=True
+    )
+"""

 import logging

@@ -25,6 +49,7 @@ log = logging.getLogger(__name__)
@hookimpl
 def add_options(parser):
    parser.add_argument('--grayscale-ocr', action='store_true')
+    parser.add_argument('--mono-page', action='store_true')


@hookimpl
@@ -47,7 +72,13 @@ def filter_ocr_image(page, image):

@hookimpl
 def filter_page_image(page, image_filename):
-    output = image_filename.with_suffix('.jpg')
-    with Image.open(image_filename) as im:
-        im.save(output)
-    return output
+    if page.options.mono_page:
+        with Image.open(image_filename) as im:
+            im = im.convert('1')
+            im.save(image_filename)
+        return image_filename
+    else:
+        output = image_filename.with_suffix('.jpg')
+        with Image.open(image_filename) as im:
+            im.save(output)
+        return output
@@ -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 = '''
@@ -1,12 +1,12 @@
 # requirements.txt can be used to replicate the developer's build environment
 # setup.py lists a separate set of requirements that are looser to simplify
 # installation
-cffi == 1.14.0
+cffi == 1.14.3
 coloredlogs == 14.0  # technically optional
-img2pdf == 0.3.4
-pdfminer.six == 20200517
-pikepdf == 1.14.0
+img2pdf == 0.4.0
+pdfminer.six == 20201018
+pikepdf == 2.0.0
 pluggy == 0.13.1
-Pillow == 7.1.1
-reportlab == 3.5.34
-tqdm == 4.45.0
+Pillow == 8.0.1
+reportlab == 3.5.55
+tqdm == 4.51.0
@@ -1,7 +1,7 @@
 pytest >= 5.0.0
 pytest-helpers-namespace >= 2019.1.8
 pytest-xdist >= 1.31.0
-pytest-cov >= 2.9.0
+pytest-cov >= 2.10.0
 python-xmp-toolkit == 2.0.1  # requires apt-get install libexempi3
                     # or brew install exempi
 #PyMuPDF == 1.13.4    # optional
@@ -1 +1 @@
-watchdog >= 0.8.2, < 1.0
+watchdog == 0.10.2
@@ -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",
@@ -72,7 +63,6 @@ setup(
    python_requires=' >= 3.6',
    setup_requires=[  # can be removed whenever we can drop pip 9 support
        'cffi >= 1.9.1',  # to build the leptonica module
-        'pytest-runner',  # to enable python setup.py test
        'setuptools_scm',  # so that version will work
        'setuptools_scm_git_archive',  # enable version from github tarballs
    ],
@@ -81,11 +71,12 @@ 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',
-        'pikepdf >= 1.14.0, < 2',
+        'img2pdf >= 0.3.0, < 0.5',  # pure Python, so track HEAD closely
+        'pdfminer.six >= 20191110, != 20200720, <= 20201018',
+        "pikepdf >= 1.14.0, < 3 ; python_version < '3.9'",
+        "pikepdf >= 2.0.0 ; python_version >= '3.9'",
        'Pillow >= 7.0.0',
-        'pluggy >= 0.13.0',
+        'pluggy >= 0.13.0, < 1.0',
        'reportlab >= 3.3.0',  # oldest released version with sane image handling
        'tqdm >= 4',
    ],
@@ -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
@@ -53,15 +45,24 @@ def log_listener(queue):
            traceback.print_exc(file=sys.stderr)


-def process_init(queue, user_init):
+def process_sigbus(*args):
+    raise InputFileError("A worker process lost access to an input file")
+
+
+def process_init(queue, user_init, loglevel):
    """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()
+    root.setLevel(loglevel)
    root.handlers = []
    root.addHandler(h)

@@ -69,7 +70,10 @@ def process_init(queue, user_init):
        user_init()


-def thread_init(_queue, user_init):
+def thread_init(_queue, user_init, _loglevel):
+    # 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 +88,7 @@ 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:
@@ -99,7 +103,7 @@ def exec_progress_pool(
        pool = pool_class(
            processes=max_workers,
            initializer=initializer,
-            initargs=(log_queue, task_initializer),
+            initargs=(log_queue, task_initializer, logging.getLogger("").level),
        )
        try:
            results = pool.imap_unordered(task, task_arguments)
@@ -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(
@@ -87,8 +81,8 @@ def rasterize_pdf(
    raster_device: str,
    raster_dpi: Resolution,
    pageno: int = 1,
-    page_dpi: Resolution = None,
-    rotation: int = None,
+    page_dpi: Optional[Resolution] = None,
+    rotation: Optional[int] = None,
    filter_vector: bool = False,
 ):
    """Rasterize one page of a PDF at resolution raster_dpi in canvas units."""
@@ -128,8 +122,6 @@ def rasterize_pdf(
        stderr = p.stderr.decode(errors='replace')
        if _gs_error_reported(stderr):
            log.error(stderr)
-        elif stderr:
-            log.debug(stderr)

    with Image.open(BytesIO(p.stdout)) as im:
        if rotation is not None:
@@ -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 +1,17 @@
 # © 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 contextlib import contextmanager
+from io import BytesIO
+from os import fspath
+from pathlib import Path
+from subprocess import PIPE
 from tempfile import NamedTemporaryFile

 from PIL import Image
@@ -37,32 +32,32 @@ def available():
    return True


-def quantize(input_file, output_file, quality_min, quality_max):
-    if input_file.endswith('.jpg'):
-        with Image.open(input_file) as im, NamedTemporaryFile(suffix='.png') as tmp:
-            im.save(tmp)
-            args = [
-                'pngquant',
-                '--force',
-                '--skip-if-larger',
-                '--output',
-                output_file,
-                '--quality',
-                f'{quality_min}-{quality_max}',
-                '--',
-                tmp.name,
-            ]
-            run(args)
+@contextmanager
+def input_as_png(input_file: Path):
+    if not input_file.name.endswith('.png'):
+        with Image.open(input_file) as im:
+            bio = BytesIO()
+            im.save(bio, format='png')
+            bio.seek(0)
+            yield bio
    else:
+        with open(input_file, 'rb') as f:
+            yield f
+
+
+def quantize(input_file: Path, output_file: Path, quality_min: int, quality_max: int):
+    with input_as_png(input_file) as input_stream:
        args = [
            'pngquant',
            '--force',
            '--skip-if-larger',
-            '--output',
-            output_file,
            '--quality',
            f'{quality_min}-{quality_max}',
-            '--',
-            input_file,
+            '--',  # pngquant: stop processing arguments
+            '-',  # pngquant: stream input and output
        ]
-        run(args)
+        result = run(args, stdin=input_stream, stdout=PIPE, stderr=PIPE, check=False)
+
+    if result.returncode == 0:
+        # input_file could be the same as output_file, so we defer the write
+        output_file.write_bytes(result.stdout)
@@ -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
@@ -26,6 +16,7 @@ import shlex
 from pathlib import Path
 from subprocess import PIPE, STDOUT, CalledProcessError
 from tempfile import TemporaryDirectory
+from typing import Tuple

 from PIL import Image

@@ -40,13 +31,11 @@ def version():
    return get_version('unpaper')


-def run(input_file, output_file, dpi, mode_args):
-    args_unpaper = ['unpaper', '-v', '--dpi', str(dpi)] + mode_args
-
+def _setup_unpaper_io(tmpdir: Path, input_file: Path) -> Tuple[Path, Path]:
    SUFFIXES = {'1': '.pbm', 'L': '.pgm', 'RGB': '.ppm'}
-
-    with TemporaryDirectory() as tmpdir, Image.open(input_file) as im:
-        if im.mode not in SUFFIXES.keys():
+    with Image.open(input_file) as im:
+        im_modified = False
+        if im.mode not in SUFFIXES:
            log.info("Converting image to other colorspace")
            try:
                if im.mode == 'P' and len(im.getcolors()) == 2:
@@ -54,11 +43,11 @@ def run(input_file, output_file, dpi, mode_args):
                else:
                    im = im.convert(mode='RGB')
            except IOError as e:
-                im.close()
                raise MissingDependencyError(
                    "Could not convert image with type " + im.mode
                ) from e
-
+            else:
+                im_modified = True
        try:
            suffix = SUFFIXES[im.mode]
        except KeyError:
@@ -66,9 +55,21 @@ def run(input_file, output_file, dpi, mode_args):
                "Failed to convert image to a supported format."
            ) from e

-        input_pnm = Path(tmpdir) / f'input{suffix}'
-        output_pnm = Path(tmpdir) / f'output{suffix}'
-        im.save(input_pnm, format='PPM')
+        if im_modified or input_file.suffix != '.pnm':
+            input_pnm = tmpdir / 'input.pnm'
+            im.save(input_pnm, format='PPM')
+        else:
+            # No changes, PNG input, just use the file we already have
+            input_pnm = input_file
+        output_pnm = tmpdir / f'output{suffix}'
+    return input_pnm, output_pnm
+
+
+def run(input_file, output_file, dpi, mode_args):
+    args_unpaper = ['unpaper', '-v', '--dpi', str(round(dpi, 6))] + mode_args
+
+    with TemporaryDirectory() as tmpdir:
+        input_pnm, output_pnm = _setup_unpaper_io(Path(tmpdir), input_file)

        # To prevent any shenanigans from accepting arbitrary parameters in
        # --unpaper-args, we:
@@ -78,36 +79,30 @@ def run(input_file, output_file, dpi, mode_args):
        # This should ensure that a user cannot clobber some other file with
        # their unpaper arguments (whether intentionally or otherwise)
        args_unpaper.extend([os.fspath(input_pnm), os.fspath(output_pnm)])
+        external_run(
+            args_unpaper,
+            close_fds=True,
+            check=True,
+            universal_newlines=True,
+            stderr=STDOUT,  # unpaper writes logging output to stdout and stderr
+            stdout=PIPE,  # and cannot send file output to stdout
+            cwd=tmpdir,
+            logs_errors_to_stdout=True,
+        )
        try:
-            proc = external_run(
-                args_unpaper,
-                check=True,
-                close_fds=True,
-                universal_newlines=True,
-                stderr=STDOUT,
-                cwd=tmpdir,
-                stdout=PIPE,
-            )
-        except CalledProcessError as e:
-            log.debug(e.output)
-            raise e from e
-        else:
-            log.debug(proc.stdout)
-            # unpaper sets dpi to 72; fix this
-            try:
-                with Image.open(output_pnm) as imout:
-                    imout.save(output_file, dpi=(dpi, dpi))
-            except (FileNotFoundError, OSError):
-                raise SubprocessOutputError(
-                    "unpaper: failed to produce the expected output file. "
-                    + " Called with: "
-                    + str(args_unpaper)
-                ) from None
+            with Image.open(output_pnm) as imout:
+                imout.save(output_file, dpi=(dpi, dpi))
+        except (FileNotFoundError, OSError):
+            raise SubprocessOutputError(
+                "unpaper: failed to produce the expected output file. "
+                + " Called with: "
+                + str(args_unpaper)
+            ) from None


 def validate_custom_args(args: str):
    unpaper_args = shlex.split(args)
-    if any('/' in arg for arg in unpaper_args):
+    if any(('/' in arg or arg == '.' or arg == '..') for arg in unpaper_args):
        raise ValueError('No filenames allowed in --unpaper-args')
    return unpaper_args

@@ -1,23 +1,14 @@
 # © 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
 from pathlib import Path
+from typing import Optional

 import pikepdf

@@ -108,7 +99,12 @@ class OcrGrafter:
        self.interim_count = 0

    def graft_page(
-        self, *, pageno: int, image: Path, textpdf: Path, autorotate_correction: int
+        self,
+        *,
+        pageno: int,
+        image: Optional[Path],
+        textpdf: Optional[Path],
+        autorotate_correction: int,
    ):
        if textpdf and not self.font:
            self.font, self.font_key = self._find_font(textpdf)
@@ -129,34 +125,38 @@ class OcrGrafter:
                del self.pdf_base.pages[-1]
            emplaced_page = True

+        # Calculate if the text is misaligned compared to the content
        if emplaced_page:
            content_rotation = autorotate_correction
        text_rotation = autorotate_correction
        text_misaligned = (text_rotation - content_rotation) % 360
        log.debug(
-            f"Rotations for page {pageno}: [text, auto, misalign, content] = "
-            f"{text_rotation}, {autorotate_correction}, "
-            f"{text_misaligned}, {content_rotation}"
+            f"Text rotation: (text, autorotate, content) -> text misalignment = "
+            f"({text_rotation}, {autorotate_correction}, {content_rotation}) -> {text_misaligned}"
        )

        if textpdf and self.font:
-            # Graft the text layer onto this page, whether new or old
+            # Graft the text layer onto this page, whether new or old, possibly
+            # rotating the text layer by the amount is misaligned.
            strip_old = self.context.options.redo_ocr
            self._graft_text_layer(
                page_num=pageno + 1,
                textpdf=textpdf,
                font=self.font,
                font_key=self.font_key,
-                rotation=text_misaligned,
+                text_rotation=text_misaligned,
                procset=self.procset,
                strip_old_text=strip_old,
            )

-        # Correct the rotation if applicable
-        self.pdf_base.pages[pageno].Rotate = (
-            content_rotation - autorotate_correction
-        ) % 360
-
+        # Correct the overall page rotation if needed, now that the text and content
+        # are aligned
+        page_rotation = (content_rotation - autorotate_correction) % 360
+        self.pdf_base.pages[pageno].Rotate = page_rotation
+        log.debug(
+            f"Page rotation: (content, auto) -> page = "
+            f"({content_rotation}, {autorotate_correction}) -> {page_rotation}"
+        )
        if self.emplacements % MAX_REPLACE_PAGES == 0:
            self.save_and_reload()

@@ -230,7 +230,7 @@ class OcrGrafter:
        font: pikepdf.Object,
        font_key: pikepdf.Object,
        procset: pikepdf.Object,
-        rotation: int,
+        text_rotation: int,
        strip_old_text: bool,
    ):
        """Insert the text layer from text page 0 on to pdf_base at page_num"""
@@ -260,13 +260,13 @@ class OcrGrafter:
            corner = pikepdf.PdfMatrix().translated(mediabox[0], mediabox[1])
            # -rotation because the input is a clockwise angle and this formula
            # uses CCW
-            rotation = -rotation % 360
-            rotate = pikepdf.PdfMatrix().rotated(rotation)
+            text_rotation = -text_rotation % 360
+            rotate = pikepdf.PdfMatrix().rotated(text_rotation)

            # Because of rounding of DPI, we might get a text layer that is not
            # identically sized to the target page. Scale to adjust. Normally this
            # is within 0.998.
-            if rotation in (90, 270):
+            if text_rotation in (90, 270):
                wt, ht = ht, wt
            scale_x = wp / wt
            scale_y = hp / ht
@@ -1,50 +1,43 @@
 # © 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
 import sys
+from argparse import Namespace
+from copy import copy
+from io import IOBase
 from pathlib import Path
+from typing import Iterator

-from ocrmypdf._plugin_manager import get_plugin_manager
+from ocrmypdf.pdfinfo import PdfInfo


 class PdfContext:
    """Holds our context for a particular run of the pipeline"""

    def __init__(
-        self, options, work_folder: Path, origin: Path, pdfinfo, plugin_manager
+        self,
+        options: Namespace,
+        work_folder: Path,
+        origin: Path,
+        pdfinfo: PdfInfo,
+        plugin_manager,
    ):
        self.options = options
-        self.work_folder = Path(work_folder)
-        self.origin = Path(origin)
+        self.work_folder = work_folder
+        self.origin = origin
        self.pdfinfo = pdfinfo
        self.plugin_manager = plugin_manager
-        if options:
-            self.name = os.path.basename(options.input_file)
-        else:
-            self.name = 'origin.pdf'
-        if self.name == '-':
-            self.name = 'stdin'

    def get_path(self, name: str) -> Path:
        return self.work_folder / name

-    def get_page_contexts(self):
+    def get_page_contexts(self) -> Iterator['PageContext']:
        npages = len(self.pdfinfo)
        for n in range(npages):
            yield PageContext(self, n)
@@ -53,14 +46,14 @@ class PdfContext:
 class PageContext:
    """Holds our context for a page

-    Must be pickable, so only store intrinsic/simple data elements
+    Must be pickable, so stores only intrinsic/simple data elements or those
+    capable of their serializing themselves via __getstate__.
    """

    def __init__(self, pdf_context: PdfContext, pageno):
        self.work_folder = pdf_context.work_folder
        self.origin = pdf_context.origin
        self.options = pdf_context.options
-        self.name = pdf_context.name
        self.pageno = pageno
        self.pageinfo = pdf_context.pdfinfo[pageno]
        self.plugin_manager = pdf_context.plugin_manager
@@ -70,16 +63,16 @@ class PageContext:

    def __getstate__(self):
        state = self.__dict__.copy()
-        if state['plugin_manager'] is not None:
-            state['plugin_manager'] = None
+
+        state['options'] = copy(self.options)
+        if not isinstance(state['options'].input_file, (str, bytes, os.PathLike)):
+            state['options'].input_file = 'stream'
+        if not isinstance(state['options'].output_file, (str, bytes, os.PathLike)):
+            state['options'].output_file = 'stream'
        return state

-    def __setstate__(self, state):
-        self.__dict__.update(state)
-        self.plugin_manager = get_plugin_manager(self.options.plugins)

-
-def cleanup_working_files(work_folder, options):
+def cleanup_working_files(work_folder: Path, options: Namespace):
    if options.keep_temporary_files:
        print(f"Temporary working files retained at:\n{work_folder}", file=sys.stderr)
    else:
@@ -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
@@ -25,9 +15,9 @@ from tqdm import tqdm
 class PageNumberFilter(logging.Filter):
    def filter(self, record):
        pageno = getattr(record, 'pageno', None)
-        if pageno is not None:
+        if isinstance(pageno, int):
            record.pageno = f'{pageno:5d} '
-        else:
+        elif pageno is None:
            record.pageno = ''
        return True

@@ -1,26 +1,19 @@
 # © 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
 import re
 import sys
+from contextlib import suppress
 from datetime import datetime, timezone
+from pathlib import Path
 from shutil import copyfileobj
+from typing import BinaryIO, Dict, Iterable, Optional, Union, cast

 import img2pdf
 import pikepdf
@@ -29,6 +22,7 @@ from PIL import Image, ImageColor, ImageDraw

 from ocrmypdf import leptonica
 from ocrmypdf._exec import unpaper
+from ocrmypdf._jobcontext import PageContext, PdfContext
 from ocrmypdf._version import PROGRAM_NAME
 from ocrmypdf._version import __version__ as VERSION
 from ocrmypdf.exceptions import (
@@ -170,7 +164,7 @@ def get_pdfinfo(
        raise InputFileError()


-def validate_pdfinfo_options(context):
+def validate_pdfinfo_options(context: PdfContext):
    pdfinfo = context.pdfinfo
    options = context.options

@@ -255,7 +249,7 @@ def get_canvas_square_dpi(pageinfo, options) -> Resolution:
    return Resolution(units, units)


-def is_ocr_required(page_context):
+def is_ocr_required(page_context: PageContext):
    pageinfo = page_context.pageinfo
    options = page_context.options

@@ -329,7 +323,7 @@ def is_ocr_required(page_context):
    return ocr_required


-def rasterize_preview(input_file, page_context):
+def rasterize_preview(input_file: Path, page_context: PageContext):
    output_file = page_context.get_path('rasterize_preview.jpg')
    canvas_dpi = get_canvas_square_dpi(page_context.pageinfo, page_context.options)
    page_dpi = get_page_square_dpi(page_context.pageinfo, page_context.options)
@@ -338,13 +332,15 @@ def rasterize_preview(input_file, page_context):
        output_file=output_file,
        raster_device='jpeggray',
        raster_dpi=canvas_dpi,
-        page_dpi=page_dpi,
        pageno=page_context.pageinfo.pageno + 1,
+        page_dpi=page_dpi,
+        rotation=0,
+        filter_vector=False,
    )
    return output_file


-def describe_rotation(page_context, orient_conf, correction):
+def describe_rotation(page_context: PageContext, orient_conf, correction: int):
    """
    Describe the page rotation we are going to perform.
    """
@@ -373,7 +369,7 @@ def describe_rotation(page_context, orient_conf, correction):
    return f"{facing}, confidence {orient_conf.confidence:.2f} - {action}"


-def get_orientation_correction(preview, page_context):
+def get_orientation_correction(preview: Path, page_context: PageContext):
    """Work out orientation correct for each page.

    We ask Ghostscript to draw a preview page, which will rasterize with the
@@ -405,7 +401,11 @@ def get_orientation_correction(preview, page_context):


 def rasterize(
-    input_file, page_context, correction=0, output_tag='', remove_vectors=None
+    input_file: Path,
+    page_context: PageContext,
+    correction: int = 0,
+    output_tag: str = '',
+    remove_vectors=None,
 ):
    colorspaces = ['pngmono', 'pnggray', 'png256', 'png16m']
    device_idx = 0
@@ -435,7 +435,7 @@ def rasterize(

    device = colorspaces[device_idx]

-    log.debug(f"Rasterize with {device}")
+    log.debug(f"Rasterize with {device}, rotation {correction}")

    # Produce the page image with square resolution or else deskew and OCR
    # will not work properly.
@@ -455,7 +455,7 @@ def rasterize(
    return output_file


-def preprocess_remove_background(input_file, page_context):
+def preprocess_remove_background(input_file: Path, page_context: PageContext):
    if any(image.bpc > 1 for image in page_context.pageinfo.images):
        output_file = page_context.get_path('pp_rm_bg.png')
        leptonica.remove_background(input_file, output_file)
@@ -465,21 +465,21 @@ def preprocess_remove_background(input_file, page_context):
        return input_file


-def preprocess_deskew(input_file, page_context):
+def preprocess_deskew(input_file: Path, page_context: PageContext):
    output_file = page_context.get_path('pp_deskew.png')
    dpi = get_page_square_dpi(page_context.pageinfo, page_context.options)
    leptonica.deskew(input_file, output_file, dpi.x)
    return output_file


-def preprocess_clean(input_file, page_context):
+def preprocess_clean(input_file: Path, page_context: PageContext):
    output_file = page_context.get_path('pp_clean.png')
    dpi = get_page_square_dpi(page_context.pageinfo, page_context.options)
    unpaper.clean(input_file, output_file, dpi.x, page_context.options.unpaper_args)
    return output_file


-def create_ocr_image(image, page_context):
+def create_ocr_image(image: Path, page_context: PageContext):
    """Create the image we send for OCR. May not be the same as the display
    image depending on preprocessing. This image will never be shown to the
    user."""
@@ -522,7 +522,9 @@ def create_ocr_image(image, page_context):
        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

@@ -538,7 +540,7 @@ def create_ocr_image(image, page_context):
    return output_file


-def ocr_engine_hocr(input_file, page_context):
+def ocr_engine_hocr(input_file: Path, page_context: PageContext):
    hocr_out = page_context.get_path('ocr_hocr.hocr')
    hocr_text_out = page_context.get_path('ocr_hocr.txt')
    options = page_context.options
@@ -558,7 +560,7 @@ def should_visible_page_image_use_jpg(pageinfo):
    return pageinfo.images and all(im.enc == Encoding.jpeg for im in pageinfo.images)


-def create_visible_page_jpg(image, page_context):
+def create_visible_page_jpg(image: Path, page_context: PageContext) -> Path:
    output_file = page_context.get_path('visible.jpg')
    with Image.open(image) as im:
        # At this point the image should be a .png, but deskew, unpaper
@@ -577,7 +579,7 @@ def create_visible_page_jpg(image, page_context):
    return output_file


-def create_pdf_page_from_image(image, page_context):
+def create_pdf_page_from_image(image: Path, page_context: PageContext):
    # We rasterize a square DPI version of each page because most image
    # processing tools don't support rectangular DPI. Use the square DPI as it
    # accurately describes the image. It would be possible to resample the image
@@ -598,7 +600,7 @@ def create_pdf_page_from_image(image, page_context):
    return output_file


-def render_hocr_page(hocr, page_context):
+def render_hocr_page(hocr: Path, page_context: PageContext):
    output_file = page_context.get_path('ocr_hocr.pdf')
    dpi = get_page_square_dpi(page_context.pageinfo, page_context.options)
    hocrtransform = HocrTransform(hocr, dpi.x)  # square
@@ -612,7 +614,7 @@ def render_hocr_page(hocr, page_context):
    return output_file


-def ocr_engine_textonly_pdf(input_image, page_context):
+def ocr_engine_textonly_pdf(input_image: Path, page_context: PageContext):
    output_pdf = page_context.get_path('ocr_tess.pdf')
    output_text = page_context.get_path('ocr_tess.txt')
    options = page_context.options
@@ -627,7 +629,7 @@ def ocr_engine_textonly_pdf(input_image, page_context):
    return (output_pdf, output_text)


-def get_docinfo(base_pdf, context):
+def get_docinfo(base_pdf: pikepdf.Pdf, context: PdfContext) -> Dict[str, str]:
    options = context.options

    def from_document_info(key):
@@ -664,13 +666,13 @@ def get_docinfo(base_pdf, context):
    return pdfmark


-def generate_postscript_stub(context):
+def generate_postscript_stub(context: PdfContext):
    output_file = context.get_path('pdfa.ps')
    generate_pdfa_ps(output_file)
    return output_file


-def convert_to_pdfa(input_pdf, input_ps_stub, context):
+def convert_to_pdfa(input_pdf: Path, input_ps_stub: Path, context: PdfContext):
    options = context.options
    input_pdfinfo = context.pdfinfo
    fix_docinfo_file = context.get_path('fix_docinfo.pdf')
@@ -712,14 +714,14 @@ def convert_to_pdfa(input_pdf, input_ps_stub, context):
    return output_file


-def should_linearize(working_file, context):
+def should_linearize(working_file: Path, context: PdfContext):
    filesize = os.stat(working_file).st_size
    if filesize > (context.options.fast_web_view * 1_000_000):
        return True
    return False


-def metadata_fixup(working_file, context):
+def metadata_fixup(working_file: Path, context: PdfContext):
    output_file = context.get_path('metafix.pdf')
    options = context.options

@@ -749,6 +751,16 @@ def metadata_fixup(working_file, context):
            if 'xmp:CreateDate' not in meta:
                meta['xmp:CreateDate'] = meta.get('xmp:ModifyDate', '')

+            # Ghostscript likes to set title to Untitled if omitted from input.
+            # 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(
+                    set_pikepdf_as_editor=False, update_docinfo=False
+                ) as original_meta:
+                    if 'dc:title' not in original_meta:
+                        del meta['dc:title']
+
            meta_original = original.open_metadata()
            missing = set(meta_original.keys()) - set(meta.keys())
            report_on_metadata(missing)
@@ -768,7 +780,7 @@ def metadata_fixup(working_file, context):
    return output_file


-def optimize_pdf(input_file, context):
+def optimize_pdf(input_file: Path, context: PdfContext):
    output_file = context.get_path('optimize.pdf')
    save_settings = dict(
        compress_streams=True,
@@ -780,7 +792,7 @@ def optimize_pdf(input_file, context):
    return output_file


-def merge_sidecars(txt_files, context):
+def merge_sidecars(txt_files: Iterable[Optional[Path]], context: PdfContext):
    output_file = context.get_path('sidecar.txt')
    with open(output_file, 'w', encoding="utf-8") as stream:
        for page_num, txt_file in enumerate(txt_files):
@@ -801,12 +813,17 @@ def merge_sidecars(txt_files, context):
    return output_file


-def copy_final(input_file, output_file, _context):
+def copy_final(input_file, output_file, _context: PdfContext):
    log.debug('%s -> %s', input_file, output_file)
    with open(input_file, 'rb') as input_stream:
        if output_file == '-':
            copyfileobj(input_stream, sys.stdout.buffer)
            sys.stdout.flush()
+        elif hasattr(output_file, 'writable'):
+            output_stream = output_file
+            copyfileobj(input_stream, output_stream)
+            with suppress(AttributeError):
+                output_stream.flush()
        else:
            # At this point we overwrite the output_file specified by the user
            # use copyfileobj because then we use open() to create the file and
@@ -1,26 +1,17 @@
 # © 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
 import importlib.util
 import sys
+from functools import partial
 from pathlib import Path
-from typing import List
+from typing import Callable, List, Tuple, Union

 import pluggy

@@ -28,19 +19,57 @@ from ocrmypdf import pluginspec
 from ocrmypdf.cli import get_parser, plugins_only_parser


-def get_plugin_manager(plugins: List[str], builtins=True):
-    pm = pluggy.PluginManager('ocrmypdf')
+class OcrmypdfPluginManager(pluggy.PluginManager):
+    """pluggy.PluginManager that can fork.
+
+    Capable of reconstructing itself in child workers.
+
+    Arguments:
+        setup_func: callback that initializes the plugin manager with all
+            standard plugins
+    """
+
+    def __init__(
+        self, *args, setup_func: Callable[[pluggy.PluginManager], None], **kwargs
+    ):
+        self._init_args = args
+        self._setup_func = setup_func
+        self._init_kwargs = kwargs
+        super().__init__(*args, **kwargs)
+        setup_func(self)
+
+    def __getstate__(self):
+        state = dict(
+            _init_args=self._init_args,
+            _setup_func=self._setup_func,
+            _init_kwargs=self._init_kwargs,
+        )
+        return state
+
+    def __setstate__(self, state):
+        self.__init__(
+            *state['_init_args'],
+            setup_func=state['_setup_func'],
+            **state['_init_kwargs'],
+        )
+
+
+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)
@@ -51,12 +80,19 @@ def get_plugin_manager(plugins: List[str], builtins=True):
            # Import by dotted module name
            module = importlib.import_module(name)
        pm.register(module)
+
+
+def get_plugin_manager(plugins: List[str], builtins=True):
+    pm = OcrmypdfPluginManager(
+        project_name='ocrmypdf',
+        setup_func=partial(_setup_plugins, plugins=plugins, builtins=builtins),
+    )
    return pm


 def get_parser_options_plugins(
    args,
-) -> (argparse.ArgumentParser, argparse.Namespace, pluggy.PluginManager):
+) -> Tuple[argparse.ArgumentParser, argparse.Namespace, pluggy.PluginManager]:
    pre_options, _unused = plugins_only_parser.parse_known_args(args=args)
    plugin_manager = get_plugin_manager(pre_options.plugins)

@@ -1,35 +1,27 @@
 # © 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
 import os
 import sys
 import threading
-from collections import namedtuple
 from functools import partial
 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 PdfContext, cleanup_working_files
+from ocrmypdf._jobcontext import PageContext, PdfContext, cleanup_working_files
+from ocrmypdf._logging import PageNumberFilter
 from ocrmypdf._pipeline import (
    convert_to_pdfa,
    copy_final,
@@ -62,29 +54,29 @@ 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__)

-PageResult = namedtuple(
-    'PageResult', 'pageno, pdf_page_from_image, ocr, text, orientation_correction'
-)
+
+class PageResult(NamedTuple):
+    pageno: int
+    pdf_page_from_image: Optional[Path]
+    ocr: Optional[Path]
+    text: Optional[Path]
+    orientation_correction: int
+

 tls = threading.local()
 tls.pageno = None


-def preprocess(page_context, image, remove_background, deskew, clean):
-    if remove_background:
-        image = preprocess_remove_background(image, page_context)
-    if deskew:
-        image = preprocess_deskew(image, page_context)
-    if clean:
-        image = preprocess_clean(image, page_context)
-    return image
-
-
 old_factory = logging.getLogRecordFactory()


@@ -98,56 +90,71 @@ def record_factory(*args, **kwargs):
 logging.setLogRecordFactory(record_factory)


-def exec_page_sync(page_context):
+def preprocess(
+    page_context: PageContext,
+    image: Path,
+    remove_background: bool,
+    deskew: bool,
+    clean: bool,
+) -> Path:
+    if remove_background:
+        image = preprocess_remove_background(image, page_context)
+    if deskew:
+        image = preprocess_deskew(image, page_context)
+    if clean:
+        image = preprocess_clean(image, page_context)
+    return image
+
+
+def make_intermediate_images(
+    page_context: PageContext, orientation_correction: int
+) -> Tuple[Path, Optional[Path]]:
    options = page_context.options
-    tls.pageno = page_context.pageno + 1

-    orientation_correction = 0
-    pdf_page_from_image_out = None
-    ocr_out = None
-    text_out = None
-    if is_ocr_required(page_context):
-        if options.rotate_pages:
-            # Rasterize
-            rasterize_preview_out = rasterize_preview(page_context.origin, page_context)
-            orientation_correction = get_orientation_correction(
-                rasterize_preview_out, page_context
-            )
+    ocr_image = preprocess_out = None
+    rasterize_out = rasterize(
+        page_context.origin,
+        page_context,
+        correction=orientation_correction,
+        remove_vectors=False,
+    )

-        rasterize_out = rasterize(
-            page_context.origin,
+    if not any([options.clean, options.clean_final, options.remove_vectors]):
+        ocr_image = preprocess_out = preprocess(
            page_context,
-            correction=orientation_correction,
-            remove_vectors=False,
+            rasterize_out,
+            options.remove_background,
+            options.deskew,
+            clean=False,
        )
-
-        if not any([options.clean, options.clean_final, options.remove_vectors]):
-            ocr_image = preprocess_out = preprocess(
+    else:
+        if not options.lossless_reconstruction:
+            preprocess_out = preprocess(
                page_context,
                rasterize_out,
                options.remove_background,
                options.deskew,
-                clean=False,
+                clean=options.clean_final,
+            )
+        if options.remove_vectors:
+            rasterize_ocr_out = rasterize(
+                page_context.origin,
+                page_context,
+                correction=orientation_correction,
+                remove_vectors=True,
+                output_tag='_ocr',
            )
        else:
-            if not options.lossless_reconstruction:
-                preprocess_out = preprocess(
-                    page_context,
-                    rasterize_out,
-                    options.remove_background,
-                    options.deskew,
-                    clean=options.clean_final,
-                )
-            if options.remove_vectors:
-                rasterize_ocr_out = rasterize(
-                    page_context.origin,
-                    page_context,
-                    correction=orientation_correction,
-                    remove_vectors=True,
-                    output_tag='_ocr',
-                )
-            else:
-                rasterize_ocr_out = rasterize_out
+            rasterize_ocr_out = rasterize_out
+
+        if (
+            preprocess_out
+            and rasterize_ocr_out == rasterize_out
+            and options.clean == options.clean_final
+        ):
+            # Optimization: image for OCR is identical to presentation image
+            ocr_image = preprocess_out
+        else:
            ocr_image = preprocess(
                page_context,
                rasterize_ocr_out,
@@ -155,32 +162,57 @@ def exec_page_sync(page_context):
                options.deskew,
                clean=options.clean,
            )
+    return ocr_image, preprocess_out

-        ocr_image_out = create_ocr_image(ocr_image, page_context)

-        pdf_page_from_image_out = None
-        if not options.lossless_reconstruction:
-            visible_image_out = preprocess_out
-            if should_visible_page_image_use_jpg(page_context.pageinfo):
-                visible_image_out = create_visible_page_jpg(
-                    visible_image_out, page_context
-                )
-            visible_image_out = (
-                page_context.plugin_manager.hook.filter_page_image(
-                    page=page_context, image_filename=Path(visible_image_out)
-                )
-                or visible_image_out
-            )
-            pdf_page_from_image_out = create_pdf_page_from_image(
-                visible_image_out, page_context
-            )
+def exec_page_sync(page_context: PageContext):
+    options = page_context.options
+    tls.pageno = page_context.pageno + 1

-        if options.pdf_renderer == 'hocr':
-            (hocr_out, text_out) = ocr_engine_hocr(ocr_image_out, page_context)
-            ocr_out = render_hocr_page(hocr_out, page_context)
+    if not is_ocr_required(page_context):
+        return PageResult(
+            pageno=page_context.pageno,
+            pdf_page_from_image=None,
+            ocr=None,
+            text=None,
+            orientation_correction=0,
+        )

-        if options.pdf_renderer == 'sandwich':
-            (ocr_out, text_out) = ocr_engine_textonly_pdf(ocr_image_out, page_context)
+    orientation_correction = 0
+    if options.rotate_pages:
+        # Rasterize
+        rasterize_preview_out = rasterize_preview(page_context.origin, page_context)
+        orientation_correction = get_orientation_correction(
+            rasterize_preview_out, page_context
+        )
+
+    ocr_image, preprocess_out = make_intermediate_images(
+        page_context, orientation_correction
+    )
+    ocr_image_out = create_ocr_image(ocr_image, page_context)
+
+    pdf_page_from_image_out = None
+    if not options.lossless_reconstruction:
+        assert preprocess_out
+        visible_image_out = preprocess_out
+        if should_visible_page_image_use_jpg(page_context.pageinfo):
+            visible_image_out = create_visible_page_jpg(visible_image_out, page_context)
+        filtered_image = page_context.plugin_manager.hook.filter_page_image(
+            page=page_context, image_filename=visible_image_out
+        )
+        if filtered_image:
+            visible_image_out = filtered_image
+        pdf_page_from_image_out = create_pdf_page_from_image(
+            visible_image_out, page_context
+        )
+
+    if options.pdf_renderer == 'hocr':
+        (hocr_out, text_out) = ocr_engine_hocr(ocr_image_out, page_context)
+        ocr_out = render_hocr_page(hocr_out, page_context)
+    elif options.pdf_renderer == 'sandwich':
+        (ocr_out, text_out) = ocr_engine_textonly_pdf(ocr_image_out, page_context)
+    else:
+        raise NotImplementedError(f"pdf_renderer {options.pdf_renderer}")

    return PageResult(
        pageno=page_context.pageno,
@@ -191,7 +223,7 @@ def exec_page_sync(page_context):
    )


-def post_process(pdf_file, context):
+def post_process(pdf_file, context: PdfContext):
    pdf_out = pdf_file
    if context.options.output_type.startswith('pdfa'):
        ps_stub_out = generate_postscript_stub(context)
@@ -201,44 +233,50 @@ def post_process(pdf_file, context):
    return optimize_pdf(pdf_out, context)


-def worker_init(max_pixels):
+def worker_init(max_pixels: int):
    # In Windows, child process will not inherit our change to this value in
    # 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):
+def exec_concurrent(context: PdfContext):
    """Execute the pipeline concurrently"""

    # Run exec_page_sync on every page context
-    max_workers = min(len(context.pdfinfo), context.options.jobs)
+    options = context.options
+    max_workers = min(len(context.pdfinfo), options.jobs)
    if max_workers > 1:
        log.info("Start processing %d pages concurrently", max_workers)

-    sidecars = [None] * len(context.pdfinfo)
+    sidecars: List[Optional[Path]] = [None] * len(context.pdfinfo)
    ocrgraft = OcrGrafter(context)

-    def update_page(result, pbar):
-        sidecars[result.pageno] = result.text
-        pbar.update()
-        ocrgraft.graft_page(
-            pageno=result.pageno,
-            image=result.pdf_page_from_image,
-            textpdf=result.ocr,
-            autorotate_correction=result.orientation_correction,
-        )
-        pbar.update()
+    def update_page(result: PageResult, pbar):
+        try:
+            tls.pageno = result.pageno + 1
+            sidecars[result.pageno] = result.text
+            pbar.update()
+            ocrgraft.graft_page(
+                pageno=result.pageno,
+                image=result.pdf_page_from_image,
+                textpdf=result.ocr,
+                autorotate_correction=result.orientation_correction,
+            )
+            pbar.update()
+        finally:
+            tls.pageno = None

    exec_progress_pool(
-        use_threads=context.options.use_threads,
+        use_threads=options.use_threads,
        max_workers=max_workers,
        tqdm_kwargs=dict(
            total=(2 * len(context.pdfinfo)),
-            desc='OCR',
+            desc='OCR' if options.tesseract_timeout > 0 else 'Image processing',
            unit='page',
            unit_scale=0.5,
-            disable=not context.options.progress_bar,
+            disable=not options.progress_bar,
        ),
        task_initializer=partial(worker_init, PIL.Image.MAX_IMAGE_PIXELS),
        task=exec_page_sync,
@@ -247,19 +285,20 @@ def exec_concurrent(context):
    )

    # Output sidecar text
-    if context.options.sidecar:
+    if options.sidecar:
        text = merge_sidecars(sidecars, context)
        # Copy text file to destination
-        copy_final(text, context.options.sidecar, context)
+        copy_final(text, options.sidecar, context)

    # Merge layers to one single pdf
    pdf = ocrgraft.finalize()

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

    # Copy PDF file to destination
-    copy_final(pdf, context.options.output_file, context)
+    copy_final(pdf, options.output_file, context)


 class NeverRaise(Exception):
@@ -268,13 +307,21 @@ class NeverRaise(Exception):
    pass  # pylint: disable=unnecessary-pass


-def configure_debug_logging(log_filename, prefix=''):
+def configure_debug_logging(log_filename, prefix: str = ''):
+    """
+    Create a debug log file at a specified location.
+
+    Arguments:
+        log_filename: Where to the put the log file.
+        prefix: The logging domain prefix that should be sent to the log.
+    """
    log_file_handler = logging.FileHandler(log_filename, delay=True)
    log_file_handler.setLevel(logging.DEBUG)
    formatter = logging.Formatter(
        '[%(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

@@ -290,11 +337,16 @@ def run_pipeline(options, *, plugin_manager, api=False):

    work_folder = Path(mkdtemp(prefix="com.github.ocrmypdf."))
    debug_log_handler = None
-    if (options.keep_temporary_files or options.verbose >= 1) and not os.environ.get(
-        'PYTEST_CURRENT_TEST', ''
+    if (
+        (options.keep_temporary_files or options.verbose >= 1)
+        and not os.environ.get('PYTEST_CURRENT_TEST', '')
+        and not api
    ):
+        # Debug log for command line interface only with verbose output
        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)
@@ -323,6 +375,10 @@ def run_pipeline(options, *, plugin_manager, api=False):

        if options.output_file == '-':
            log.info("Output sent to stdout")
+        elif (
+            hasattr(options.output_file, 'writable') and options.output_file.writable()
+        ):
+            log.info("Output written to stream")
        elif samefile(options.output_file, os.devnull):
            pass  # Say nothing when sending to dev null
        else:
@@ -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
@@ -24,6 +13,7 @@ import sys
 import unicodedata
 from pathlib import Path
 from shutil import copyfileobj
+from typing import Tuple

 import pikepdf
 import PIL
@@ -223,12 +213,12 @@ def check_options_optimizing(options):


 def check_options_advanced(options):
-    if options.pdfa_image_compression != 'auto' and options.output_type.startswith(
+    if options.pdfa_image_compression != 'auto' and not options.output_type.startswith(
        'pdfa'
    ):
        log.warning(
-            "--pdfa-image-compression argument has no effect when "
-            "--output-type is not 'pdfa', 'pdfa-1', or 'pdfa-2'"
+            "--pdfa-image-compression argument only applies when "
+            "--output-type is one of 'pdfa', 'pdfa-1', or 'pdfa-2'"
        )


@@ -318,25 +308,22 @@ def check_closed_streams(options):  # pragma: no cover
    return True


-def log_page_orientations(pdfinfo):
-    direction = {0: 'n', 90: 'e', 180: 's', 270: 'w'}
-    orientations = []
-    for n, page in enumerate(pdfinfo):
-        angle = page.rotation or 0
-        if angle != 0:
-            orientations.append('{0}{1}'.format(n + 1, direction.get(angle, '')))
-    if orientations:
-        log.info('Page orientations detected: %s', ' '.join(orientations))
-
-
-def create_input_file(options, work_folder: Path) -> (Path, str):
+def create_input_file(options, work_folder: Path) -> Tuple[Path, str]:
    if options.input_file == '-':
        # stdin
        log.info('reading file from standard input')
        target = work_folder / 'stdin'
        with open(target, 'wb') as stream_buffer:
            copyfileobj(sys.stdin.buffer, stream_buffer)
-        return target, "<stdin>"
+        return target, "stdin"
+    elif hasattr(options.input_file, 'readable'):
+        if not options.input_file.readable():
+            raise InputFileError("Input file stream is not readable")
+        log.info('reading file from input stream')
+        target = work_folder / 'stream'
+        with open(target, 'wb') as stream_buffer:
+            copyfileobj(options.input_file, stream_buffer)
+        return target, "stream"
    else:
        try:
            target = work_folder / 'origin'
@@ -354,6 +341,9 @@ def check_requested_output_file(options):
                "is connected to a terminal.  Please redirect stdout to a "
                "file."
            )
+    elif hasattr(options.output_file, 'writable'):
+        if not options.output_file.writable():
+            raise OutputFileAccessError("Output stream is not writable")
    elif not is_file_writable(options.output_file):
        raise OutputFileAccessError(
            f"Output file location ({options.output_file}) is not a writable file."
@@ -404,6 +394,10 @@ 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
@@ -1,33 +1,24 @@
 # © 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 Iterable
+from typing import AnyStr, BinaryIO, Iterable, Optional, Union
+from warnings import warn

 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
@@ -35,6 +26,10 @@ except ModuleNotFoundError:
    coloredlogs = None


+StrPath = Union[os.PathLike, AnyStr]
+PathOrIO = Union[BinaryIO, StrPath]
+
+
 class Verbosity(IntEnum):
    """Verbosity level for configure_logging."""

@@ -51,16 +46,28 @@ def configure_logging(
 ):
    """Set up logging.

-    Library users may wish to use this function if they want their log output to be
-    similar to ocrmypdf command line interface. If not used, the external application
-    should configure logging on its own.
+    Before calling :func:`ocrmypdf.ocr()`, you can use this function to
+    configure logging, if you want ocrmypdf's output to look like the ocrmypdf
+    command line interface. It will register log handlers, log filters, and
+    formatters, configure color logging to standard error, and adjust the log
+    levels of third party libraries. Details of this are fine-tuned and subject
+    to change. The ``verbosity`` argument is equivalent to the argument
+    ``--verbose`` and applies those settings.

-    ocrmypdf will perform all of its logging under the ``"ocrmypdf"`` logging namespace.
-    In addition, ocrmypdf imports pdfminer, which logs under ``"pdfminer"``. A library
-    user may wish to configure both; note that pdfminer is extremely chatty at the log
-    level ``logging.INFO``.
+    If this function is not called, ocrmypdf will not configure logging, and it
+    is up to the caller of ``ocrmypdf.ocr()`` to set up logging as it wishes using
+    the Python standard library's logging module. If this function is called,
+    the caller may of course make further adjustments to logging.

-    Library users may perform additional configuration afterwards.
+    Regardless of whether this function is called, ocrmypdf will perform all of
+    its logging under the ``"ocrmypdf"`` logging namespace. In addition,
+    ocrmypdf imports pdfminer, which logs under ``"pdfminer"``. A library user
+    may wish to configure both; note that pdfminer is extremely chatty at the
+    log level ``logging.INFO``.
+
+    This function does not set up the ``debug.log`` log file that the command
+    line interface does at certain verbosity levels. Applications should configure
+    their own debug logging.

    Args:
        verbosity (Verbosity): Verbosity level.
@@ -127,11 +134,7 @@ def configure_logging(


 def create_options(
-    *,
-    input_file: os.PathLike,
-    output_file: os.PathLike,
-    parser: ArgumentParser,
-    **kwargs,
+    *, input_file: PathOrIO, output_file: PathOrIO, parser: ArgumentParser, **kwargs
 ):
    cmdline = []
    deferred = []
@@ -154,7 +157,7 @@ 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)
@@ -171,24 +174,36 @@ def create_options(
        else:
            raise TypeError(f"{arg}: {val} ({type(val)})")

-    cmdline.append(str(input_file))
-    cmdline.append(str(output_file))
+    try:
+        cmdline.append(os.fspath(input_file))
+    except TypeError:
+        cmdline.append('stream://input_file')
+    try:
+        cmdline.append(os.fspath(output_file))
+    except TypeError:
+        cmdline.append('stream://output_file')

    parser._api_mode = True
    options = parser.parse_args(cmdline)
    for keyword, val in deferred:
        setattr(options, keyword, val)
+
+    if options.input_file == 'stream://input_file':
+        options.input_file = input_file
+    if options.output_file == 'stream://output_file':
+        options.output_file = output_file
+
    return options


 def ocr(  # pylint: disable=unused-argument
-    input_file: os.PathLike,
-    output_file: os.PathLike,
+    input_file: PathOrIO,
+    output_file: PathOrIO,
    *,
    language: Iterable[str] = None,
    image_dpi: int = None,
    output_type=None,
-    sidecar: os.PathLike = None,
+    sidecar: Optional[StrPath] = None,
    jobs: int = None,
    use_threads: bool = None,
    title: str = None,
@@ -225,7 +240,7 @@ def ocr(  # pylint: disable=unused-argument
    user_words: os.PathLike = None,
    user_patterns: os.PathLike = None,
    fast_web_view: float = None,
-    plugins: Iterable[str] = None,
+    plugins: Iterable[StrPath] = None,
    keep_temporary_files: bool = None,
    progress_bar: bool = None,
    **kwargs,
@@ -236,9 +251,24 @@ def ocr(  # pylint: disable=unused-argument
    A few specific arguments are discussed here:

    Args:
-        use_threads (bool): Use worker threads instead of processes. This reduces
+        use_threads: Use worker threads instead of processes. This reduces
            performance but may make debugging easier since it is easier to set
            breakpoints.
+        input_file: If a :class:`pathlib.Path`, ``str`` or ``bytes``, this is
+            interpreted as file system path to the input file. If the object
+            appears to be a readable stream (with methods such as ``.read()``
+            and ``.seek()``), the object will be read in its entirety and saved to
+            a temporary file. If ``input_file`` is  ``"-"``, standard input will be
+            read.
+        output_file: If a :class:`pathlib.Path`, ``str`` or ``bytes``, this is
+            interpreted as file system path to the output file. If the object
+            appears to be a writable stream (with methods such as ``.write()`` and
+            ``.seek()``), the output will be written to this stream. If
+            ``output_file`` is ``"-"``, the output will be written to ``sys.stdout``
+            (provided that standard output does not seem to be a terminal device).
+            When a stream is used as output, whether via a writable object or
+            ``"-"``, some final validation steps are not performed (we do not read
+            back the stream after it is written).
    Raises:
        ocrmypdf.PdfMergeFailedError: If the input PDF is malformed, preventing merging
            with the OCR layer.
@@ -264,6 +294,10 @@ def ocr(  # pylint: disable=unused-argument
    """
    if not plugins:
        plugins = []
+    elif isinstance(plugins, (str, Path)):
+        plugins = [plugins]
+    else:
+        plugins = list(plugins)

    parser = get_parser()
    _plugin_manager = get_plugin_manager(plugins)
@@ -274,6 +308,9 @@ def ocr(  # pylint: disable=unused-argument
    }
    create_options_kwargs.update(kwargs)

+    if 'verbose' in kwargs:
+        warn("ocrmypdf.ocr(verbose=) is ignored. Use ocrmypdf.configure_logging().")
+
    options = create_options(**create_options_kwargs)
    check_options(options, _plugin_manager)
    return run_pipeline(options=options, plugin_manager=_plugin_manager, api=True)
@@ -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

@@ -49,13 +39,11 @@ def check_options(options):
    if gs_version < '9.20' and options.output_type != 'pdf' and not is_latin:
        # https://bugs.ghostscript.com/show_bug.cgi?id=696874
        # Ghostscript < 9.20 fails to encode multibyte characters properly
-        msg = (
-            "The installed version of Ghostscript does not work correctly "
-            "with the OCR languages you specified. Use --output-type pdf or "
+        log.warning(
+            f"The installed version of Ghostscript ({gs_version}) does not work "
+            "correctly with the OCR languages you specified. Use --output-type pdf or "
            "upgrade to Ghostscript 9.20 or later to avoid this issue."
        )
-        msg += f"Found Ghostscript {gs_version}"
-        log.warning(msg)

    if options.output_type == 'pdfa':
        options.output_type = 'pdfa-2'
@@ -73,9 +61,9 @@ def rasterize_pdf_page(
    raster_device,
    raster_dpi,
    pageno,
-    page_dpi=None,
-    rotation=None,
-    filter_vector=False,
+    page_dpi,
+    rotation,
+    filter_vector,
 ):
    ghostscript.rasterize_pdf(
        input_file,
@@ -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
@@ -22,6 +12,7 @@ from ocrmypdf import hookimpl
 from ocrmypdf._exec import tesseract
 from ocrmypdf.cli import numeric
 from ocrmypdf.exceptions import MissingDependencyError
+from ocrmypdf.helpers import clamp
 from ocrmypdf.pluginspec import OcrEngine
 from ocrmypdf.subprocess import check_external_program

@@ -126,13 +117,11 @@ def validate(pdfinfo, options):
    # constraint: (ocrmypdf workers) * (tesseract threads) <= max_workers.
    # As of Tesseract 4.1, 3 threads is the most effective on a 4 core/8 thread system.
    if not os.environ.get('OMP_THREAD_LIMIT', '').isnumeric():
-        tess_threads = min(3, options.jobs // len(pdfinfo), len(pdfinfo))
+        tess_threads = clamp(options.jobs // len(pdfinfo), 1, 3)
        os.environ['OMP_THREAD_LIMIT'] = str(tess_threads)
    else:
        tess_threads = int(os.environ['OMP_THREAD_LIMIT'])
-
-    if tess_threads > 1:
-        log.info("Using Tesseract OpenMP thread limit %d", tess_threads)
+    log.debug("Using Tesseract OpenMP thread limit %d", tess_threads)


 class TesseractOcrEngine(OcrEngine):
@@ -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
@@ -27,6 +17,7 @@ from functools import wraps
 from io import StringIO
 from math import isclose
 from pathlib import Path
+from typing import Any, Sequence, TypeVar

 import pikepdf

@@ -34,16 +25,18 @@ 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):
+    def round(self, ndigits: int):
        return Resolution(round(self.x, ndigits), round(self.y, ndigits))

    def to_int(self):
        return Resolution(int(round(self.x)), int(round(self.y)))

    @property
-    def is_square(self):
+    def is_square(self) -> bool:
        return isclose(self.x, self.y, rel_tol=1e-3)

    def take_max(self, vals, yvals=None):
@@ -104,28 +97,30 @@ def safe_symlink(input_file: os.PathLike, soft_link_name: os.PathLike):
    os.symlink(os.path.abspath(input_file), soft_link_name)


-def samefile(f1, f2):
+def samefile(f1: os.PathLike, f2: os.PathLike):
    if os.name == 'nt':
        return f1 == f2
    else:
        return os.path.samefile(f1, f2)


-def is_iterable_notstr(thing):
+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)


-def monotonic(L: Iterable):
+def monotonic(L: Sequence) -> bool:
    """Does list increase monotonically?"""
    return all(b > a for a, b in zip(L, L[1:]))


-def page_number(input_file: os.PathLike):
+def page_number(input_file: os.PathLike) -> int:
    """Get one-based page number implied by filename (000002.pdf -> 2)"""
    return int(os.path.basename(os.fspath(input_file))[0:6])


-def available_cpu_count():
+def available_cpu_count() -> int:
+    """Returns number of CPUs in the system."""
    try:
        return multiprocessing.cpu_count()
    except NotImplementedError:
@@ -136,7 +131,7 @@ def available_cpu_count():
    return 1


-def is_file_writable(test_file: os.PathLike):
+def is_file_writable(test_file: os.PathLike) -> bool:
    """Intentionally racy test if target is writable.

    We intend to write to the output file if and only if we succeed and
@@ -171,7 +166,11 @@ def is_file_writable(test_file: os.PathLike):
        return False


-def check_pdf(input_file):
+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)
@@ -205,6 +204,26 @@ def check_pdf(input_file):
            pdf.close()


+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")
+    # We found a race condition probably related to pybind issue #2252 that can
+    # cause a crash. For now, disable pikepdf mmap to be on the safe side.
+    log.debug("pikepdf mmap disabled")
+    return
+
+
 def deprecated(func):
    """Warn that function is deprecated"""

@@ -32,10 +32,13 @@ import argparse
 import os
 import re
 from collections import namedtuple
+from itertools import chain
 from math import atan, cos, sin
 from pathlib import Path
+from typing import Optional, Tuple, Union
 from xml.etree import ElementTree

+from reportlab.lib.colors import black, cyan, magenta, red
 from reportlab.lib.units import inch
 from reportlab.pdfgen.canvas import Canvas

@@ -66,9 +69,9 @@ class HocrTransform:
        {'ﬀ': 'ff', 'ﬃ': 'f‌f‌i', 'ﬄ': 'f‌f‌l', 'ﬁ': 'fi', 'ﬂ': 'fl'}
    )

-    def __init__(self, hocr_filename: str, dpi: float):
+    def __init__(self, hocr_filename: Union[str, Path], dpi: float):
        self.dpi = dpi
-        self.hocr = ElementTree.parse(hocr_filename)
+        self.hocr = ElementTree.parse(os.fspath(hocr_filename))

        # if the hOCR file has a namespace, ElementTree requires its use to
        # find elements
@@ -79,7 +82,7 @@ class HocrTransform:

        # get dimension in pt (not pixel!!!!) of the OCRed image
        self.width, self.height = None, None
-        for div in self.hocr.findall(".//%sdiv[@class='ocr_page']" % (self.xmlns)):
+        for div in self.hocr.findall(self._child_xpath('div', 'ocr_page')):
            coords = self.element_coordinates(div)
            pt_coords = self.pt_from_pixel(coords)
            self.width = pt_coords.x2 - pt_coords.x1
@@ -96,7 +99,7 @@ class HocrTransform:
        """
        if self.hocr is None:
            return ''
-        body = self.hocr.find(".//%sbody" % (self.xmlns))
+        body = self.hocr.find(self._child_xpath('body'))
        if body:
            return self._get_element_text(body)
        else:
@@ -109,7 +112,7 @@ class HocrTransform:
        text = ''
        if element.text is not None:
            text += element.text
-        for child in element.getchildren():
+        for child in element:
            text += self._get_element_text(child)
        if element.tail is not None:
            text += element.tail
@@ -130,7 +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.
        """
@@ -140,30 +143,44 @@ 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
        """
        return Rect._make((c / self.dpi * inch) for c in pxl)

+    def _child_xpath(self, html_tag, html_class=None):
+        xpath = f".//{self.xmlns}{html_tag}"
+        if html_class:
+            xpath += f"[@class='{html_class}']"
+        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)

+    def topdown_position(self, element):
+        pxl_line_coords = self.element_coordinates(element)
+        line_box = self.pt_from_pixel(pxl_line_coords)
+        # Coordinates here are still in the hocr coordinate system, so 0 on the y axis
+        # is the top of the page and increasing values of y will move towards the
+        # bottom of the page.
+        return line_box.y2
+
    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
@@ -171,6 +188,20 @@ 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.)
@@ -182,12 +213,11 @@ class HocrTransform:

        # draw bounding box for each paragraph
        # light blue for bounding box of paragraph
-        pdf.setStrokeColorRGB(0, 1, 1)
+        pdf.setStrokeColor(cyan)
        # light blue for bounding box of paragraph
-        pdf.setFillColorRGB(0, 1, 1)
+        pdf.setFillColor(cyan)
        pdf.setLineWidth(0)  # no line for bounding box
-        for elem in self.hocr.findall(".//%sp[@class='%s']" % (self.xmlns, "ocr_par")):
-
+        for elem in self.hocr.iterfind(self._child_xpath('p', 'ocr_par')):
            elemtxt = self._get_element_text(elem).rstrip()
            if len(elemtxt) == 0:
                continue
@@ -202,8 +232,13 @@ class HocrTransform:
                )

        found_lines = False
-        for line in self.hocr.findall(
-            ".//%sspan[@class='%s']" % (self.xmlns, "ocr_line")
+        for line in sorted(
+            chain(
+                self.hocr.iterfind(self._child_xpath('span', 'ocr_header')),
+                self.hocr.iterfind(self._child_xpath('span', 'ocr_line')),
+                self.hocr.iterfind(self._child_xpath('span', 'ocr_textfloat')),
+            ),
+            key=self.topdown_position,
        ):
            found_lines = True
            self._do_line(
@@ -218,7 +253,7 @@ class HocrTransform:

        if not found_lines:
            # Tesseract did not report any lines (just words)
-            root = self.hocr.find(".//%sdiv[@class='%s']" % (self.xmlns, "ocr_page"))
+            root = self.hocr.find(self._child_xpath('div', 'ocr_page'))
            self._do_line(
                pdf,
                root,
@@ -280,7 +315,7 @@ class HocrTransform:
        if show_bounding_boxes:  # pragma: no cover
            # draw the baseline in magenta, dashed
            pdf.setDash()
-            pdf.setStrokeColorRGB(0.95, 0.65, 0.95)
+            pdf.setStrokeColor(magenta)
            pdf.setLineWidth(0.5)
            # negate slope because it is defined as a rise/run in pixel
            # coordinates and page coordinates have the y axis flipped
@@ -292,12 +327,12 @@ class HocrTransform:
            )
            # light green for bounding box of word/line
            pdf.setDash(6, 3)
-            pdf.setStrokeColorRGB(1, 0, 0)
+            pdf.setStrokeColor(red)

        text.setTextTransform(cos_a, -sin_a, sin_a, cos_a, line_box.x1, baseline_y2)
-        pdf.setFillColorRGB(0, 0, 0)  # text in black
+        pdf.setFillColor(black)  # text in black

-        elements = line.findall(".//%sspan[@class='%s']" % (self.xmlns, elemclass))
+        elements = line.findall(self._child_xpath('span', elemclass))
        for elem in elements:
            elemtxt = self._get_element_text(elem).strip()
            elemtxt = self.replace_unsupported_chars(elemtxt)
@@ -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
@@ -66,6 +58,24 @@ if not _libpath:
        ---------------------------------------------------------------------
        """
    )
+if os.name == 'nt':  
+    # On Windows, recent versions of libpng require zlib. We have to make sure 
+    # the zlib version being loaded is the same one that libpng was built with. 
+    # This tries to import zlib from Tesseract's installation folder, falling back
+    # to find_library() if liblept is being loaded from somewhere else.
+    # Loading zlib from other places could cause a version mismatch
+    _zlib_path = os.path.join(os.path.dirname(_libpath), 'zlib1.dll')
+    if not os.path.exists(_zlib_path):
+        _zlib_path = find_library('zlib')
+    try:
+        zlib = ffi.dlopen(_zlib_path)
+    except ffi.error as e:
+        raise MissingDependencyError(
+            """
+            Could not load the zlib library. It could be that Tesseract is not installed properly,
+            we can't find the installation on your system PATH environment variable.
+            """
+        ) from e
 try:
    lept = ffi.dlopen(_libpath)
    lept.setMsgSeverity(lept.L_SEVERITY_WARNING)
@@ -75,7 +85,7 @@ except ffi.error as e:
    ) from e


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

@@ -90,19 +100,21 @@ 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 +126,10 @@ 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 +146,8 @@ 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 +165,62 @@ 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 +929,8 @@ 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 *));
 """
 )

@@ -1,30 +1,36 @@
 # © 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
 import tempfile
 from collections import defaultdict
 from functools import partial
+from io import BytesIO
 from os import fspath
 from pathlib import Path
+from typing import (
+    Any,
+    Callable,
+    Dict,
+    Iterator,
+    List,
+    MutableSet,
+    NamedTuple,
+    NewType,
+    Optional,
+    Sequence,
+    Tuple,
+    Union,
+)

+import img2pdf
 import pikepdf
-from pikepdf import Dictionary, Name
+from pikepdf import Dictionary, Name, Object, Pdf, PdfImage
 from PIL import Image
 from tqdm import tqdm

@@ -33,7 +39,7 @@ from ocrmypdf._concurrent import exec_progress_pool
 from ocrmypdf._exec import jbig2enc, pngquant
 from ocrmypdf._jobcontext import PdfContext
 from ocrmypdf.exceptions import OutputFileAccessError
-from ocrmypdf.helpers import safe_symlink
+from ocrmypdf.helpers import deprecated, safe_symlink

 log = logging.getLogger(__name__)

@@ -41,49 +47,64 @@ 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)
+        log.debug(f"Skipping small image, xref {xref}")
        return None

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

    if len(pim.filter_decodeparms) > 1:
-        log.debug("Skipping multiply filtered, xref %s", xref)
+        log.debug(f"Skipping multiply filtered image, xref {xref}")
        return None
    filtdp = pim.filter_decodeparms[0]

    if pim.bits_per_component > 8:
+        log.debug(f"Skipping wide gamut image, xref {xref}")
        return None  # Don't mess with wide gamut images

    if filtdp[0] == Name.JPXDecode:
+        log.debug(f"Skipping JPEG2000 iamge, xref {xref}")
        return None  # Don't do JPEG2000

    if Name.Decode in image:
+        log.debug(f"Skipping image with Decode table, xref {xref}")
        return None  # Don't mess with custom Decode tables

    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 +112,38 @@ 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}')
-            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
+        # Save any colorspace associated with the image, so that we
+        # will export a pure 1-bit PNG with no palette or ICC profile.
+        # Showing the palette or ICC to jbig2enc will cause it to perform
+        # colorspace transform to 1bpp, which will conflict the palette or
+        # ICC if it exists.
+        colorspace = pim.obj.get(pikepdf.Name.ColorSpace, None)
+        if colorspace is not None or pim.image_mask:
+            try:
+                # Set to DeviceGray temporarily; we already in 1 bpc.
+                pim.obj.ColorSpace = pikepdf.Name.DeviceGray
+                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
+            finally:
+                # Restore image colorspace after temporarily setting it to DeviceGray
+                if colorspace is not None:
+                    pim.obj.ColorSpace = colorspace
+                else:
+                    del pim.obj.ColorSpace
+            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 +176,13 @@ 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 +191,12 @@ 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 +207,14 @@ 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 +230,8 @@ 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):
@@ -202,12 +242,14 @@ 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)
+                log.debug(f"Skipping image {smask_xref} because it is an SMask")
            include_xrefs.add(xref)
+            log.debug(f"Treating {xref} as an optimization candidate")
            if xref not in pageno_for_xref:
                pageno_for_xref[xref] = pageno

@@ -224,31 +266,33 @@ 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 +302,12 @@ 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 +316,7 @@ 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 +352,9 @@ 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 +392,19 @@ 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 +415,55 @@ 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_png(pike: Pdf, filename: Path, xref: Xref) -> bool:
+    output = filename.with_suffix('.png.pdf')
+    with output.open('wb') as f:
+        img2pdf.convert(fspath(filename), outputstream=f)
+
+    with pikepdf.open(output) as pdf_image:
+        foreign_image = next(pdf_image.pages[0].images.values())
+        local_image = pike.copy_foreign(foreign_image)
+
+        im_obj = pike.get_object(xref, 0)
+        im_obj.write(
+            local_image.read_raw_bytes(),
+            filter=local_image.Filter,
+            decode_parms=local_image.DecodeParms,
+        )
+
+        # Don't copy keys from the new image...
+        del_keys = set(im_obj.keys()) - set(local_image.keys())
+        # ...except for the keep_fields, which are essential to displaying
+        # the image correctly and preserving its metadata. (/Decode arrays
+        # and /SMaskInData are implicitly discarded prior to this point.)
+        keep_fields = {
+            '/ID',
+            '/Intent',
+            '/Interpolate',
+            '/Mask',
+            '/Metadata',
+            '/OC',
+            '/OPI',
+            '/SMask',
+            '/StructParent',
+        }
+        del_keys -= keep_fields
+        for key in local_image.keys():
+            if key != Name.Length and str(key) not in keep_fields:
+                im_obj[key] = local_image[key]
+        for key in del_keys:
+            del im_obj[key]
+    return True
+
+
+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),
@@ -403,35 +498,12 @@ def transcode_pngs(pike, images, image_name_fn, root, options):
        )

    for xref in modified:
-        im_obj = pike.get_object(xref, 0)
-        try:
-            pix = leptonica.Pix.open(png_name(root, xref))
-            if pix.mode == '1':
-                compdata = pix.generate_pdf_ci_data(leptonica.lept.L_G4_ENCODE, 0)
-            else:
-                compdata = leptonica.CompressedData.open(png_name(root, xref))
-        except leptonica.LeptonicaError as e:
-            # Most likely this means file not found, i.e. quantize did not
-            # produce an improved version
-            log.error(e)
-            continue
-
-        # If re-coded image is larger don't use it - we test here because
-        # pngquant knows the size of the temporary output file but not the actual
-        # object in the PDF
-        if len(compdata) > int(im_obj.stream_dict.Length):
-            log.debug(
-                f"pngquant: pngquant did not improve over original image "
-                f"{len(compdata)} > {int(im_obj.stream_dict.Length)}"
-            )
-            continue
-        if compdata.type == leptonica.lept.L_FLATE_ENCODE:
-            rewrite_png(pike, im_obj, compdata)
-        elif compdata.type == leptonica.lept.L_G4_ENCODE:
-            rewrite_png_as_g4(pike, im_obj, compdata)
+        filename = png_name(root, xref)
+        _transcode_png(pike, filename, xref)


-def rewrite_png_as_g4(pike, im_obj, compdata):
+@deprecated
+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 +523,8 @@ def rewrite_png_as_g4(pike, im_obj, compdata):
    return


-def rewrite_png(pike, im_obj, compdata):
+@deprecated
+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 +577,7 @@ 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 +591,7 @@ 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 +604,12 @@ 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 "
@@ -544,7 +617,7 @@ def optimize(input_file, output_file, context, save_settings):
        )
    ratio = input_size / output_size
    savings = 1 - output_size / input_size
-    log.info(f"Optimize ratio: {ratio:.2f} savings: {(100 * savings):.1f}%")
+    log.info(f"Optimize ratio: {ratio:.2f} savings: {(savings):.1%}")

    if savings < 0:
        log.info("Image optimization did not improve the file - discarded")
@@ -557,8 +630,8 @@ 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 +649,7 @@ 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
@@ -25,6 +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, Optional, Union
 from warnings import warn

 import pikepdf
@@ -32,7 +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()
@@ -90,7 +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'])
@@ -236,7 +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
@@ -522,7 +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)
@@ -566,9 +557,9 @@ 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 = {}
+    pageinfo: Dict[str, Any] = {}
    pageinfo['pageno'] = pageno
    pageinfo['images'] = []

@@ -638,6 +629,10 @@ worker_pdf = None

 def _pdf_pageinfo_sync_init(infile):
    global worker_pdf  # pylint: disable=global-statement
+    pikepdf_enable_mmap()
+    # If this function is called as a thread initializer, we need a messy hack
+    # to close worker_pdf. If called as a process, it will be released when the
+    # process is terminated.
    worker_pdf = pikepdf.open(infile)


@@ -651,6 +646,7 @@ def _pdf_pageinfo_sync(args):
 def _pdf_pageinfo_concurrent(
    pdf, infile, progbar, max_workers, check_pages, detailed_analysis=False
 ):
+    global worker_pdf  # pylint: disable=global-statement
    pages = [None] * len(pdf.pages)

    def update_pageinfo(result, pbar):
@@ -671,17 +667,23 @@ def _pdf_pageinfo_concurrent(
        # a separate process.
        use_threads = True

-    exec_progress_pool(
-        use_threads=use_threads,
-        max_workers=n_workers,
-        tqdm_kwargs=dict(
-            total=total, desc="Scanning contents", unit='page', disable=not progbar
-        ),
-        task_initializer=partial(_pdf_pageinfo_sync_init, infile),
-        task=_pdf_pageinfo_sync,
-        task_arguments=contexts,
-        task_finished=update_pageinfo,
-    )
+    try:
+        exec_progress_pool(
+            use_threads=use_threads,
+            max_workers=n_workers,
+            tqdm_kwargs=dict(
+                total=total, desc="Scanning contents", unit='page', disable=not progbar
+            ),
+            task_initializer=partial(_pdf_pageinfo_sync_init, infile),
+            task=_pdf_pageinfo_sync,
+            task_arguments=contexts,
+            task_finished=update_pageinfo,
+        )
+    finally:
+        if worker_pdf and use_threads:
+            assert n_workers == 1, "Should have only one worker when threaded"
+            # This is messy, but if we ran in thread, close worker_pdf
+            worker_pdf.close()
    return pages


@@ -695,41 +697,41 @@ 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
@@ -743,7 +745,9 @@ 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:
@@ -766,15 +770,15 @@ 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:
@@ -794,9 +798,9 @@ 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
@@ -814,12 +818,12 @@ class PdfInfo:
                check_pages=check_pages,
                detailed_analysis=detailed_analysis,
            )
-            self._needs_rendering = pdf.root.get('/NeedsRendering', False)
+            self._needs_rendering = pdf.Root.get('/NeedsRendering', False)
            self._has_acroform = False
-            if '/AcroForm' in pdf.root:
-                if len(pdf.root.AcroForm.get('/Fields', [])) > 0:
+            if '/AcroForm' in pdf.Root:
+                if len(pdf.Root.AcroForm.get('/Fields', [])) > 0:
                    self._has_acroform = True
-                elif '/XFA' in pdf.root.AcroForm:
+                elif '/XFA' in pdf.Root.AcroForm:
                    self._has_acroform = True

    @property
@@ -827,29 +831,29 @@ 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)

@@ -1,31 +1,26 @@
 # © 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
 from collections import namedtuple
 from pathlib import Path
-from typing import AbstractSet, List, Optional
+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
+
 hookspec = pluggy.HookspecMarker('ocrmypdf')

 # pylint: disable=unused-argument
@@ -33,19 +28,37 @@ hookspec = pluggy.HookspecMarker('ocrmypdf')

@hookspec
 def add_options(parser: ArgumentParser) -> None:
-    """Allows the plugin to add its own command line arguments.
+    """Allows the plugin to add its own command line and API arguments.

-    Even if you do not intend to use plugins in a command line context, you
-    should use this function to create your options.
+    OCRmyPDF converts command line arguments to API arguments, so adding
+    arguments here will cause new arguments to be processed for API calls
+    to ``ocrmypdf.ocr``, or when invoked on the command line.
+
+    Note:
+        This hook will be called from the main process, and may modify global state
+        before child worker processes are forked.
    """


@hookspec
 def check_options(options: Namespace) -> None:
-    """Called to ask the plugin to check all of its options.
+    """Called to ask the plugin to check all of the options.

-	The plugin may modify the *options*. All objects that are in options must
-	be picklable so they can be marshalled to child worker processes.
+    The plugin may check if options that it added are valid.
+
+    Warnings or other messages may be passed to the user by creating a logger
+    object using ``log = logging.getLogger(__name__)`` and logging to this.
+
+    The plugin may also modify the *options*. All objects that are in options
+    must be picklable so they can be marshalled to child worker processes.
+
+    Raises:
+        ocrmypdf.exceptions.ExitCodeException: If options are not acceptable
+            and the application should terminate gracefully with an informative
+            message and error code.
+    Note:
+        This hook will be called from the main process, and may modify global state
+        before child worker processes are forked.
 	"""


@@ -59,12 +72,13 @@ def validate(pdfinfo: 'PdfInfo', options: Namespace) -> None:
    that a certain type of file should be treated with ``options.force_ocr = True``
    based on information in its *pdfinfo*.

-    The plugin may raise :class:`ocrmypdf.exceptions.InputFileError` or any
-    :class:`ocrmypdf.exceptions.ExitCodeException` to request
-    normal termination. ocrmypdf will hold the plugin responsible for raising
-    exceptions of any other type.
-
-    The return value is ignored. To abort processing, raise an ``ExitCodeException``.
+    Raises:
+        ocrmypdf.exceptions.ExitCodeException: If options or pdfinfo are not acceptable
+            and the application should terminate gracefully with an informative
+            message and error code.
+    Note:
+        This hook will be called from the main process, and may modify global state
+        before child worker processes are forked.
    """


@@ -75,9 +89,9 @@ def rasterize_pdf_page(
    raster_device: str,
    raster_dpi: Resolution,
    pageno: int,
-    page_dpi: Optional[Resolution] = None,
-    rotation: Optional[int] = None,
-    filter_vector: bool = False,
+    page_dpi: Optional[Resolution],
+    rotation: Optional[int],
+    filter_vector: bool,
 ) -> Path:
    """Rasterize one page of a PDF at resolution raster_dpi in canvas units.

@@ -86,23 +100,48 @@ def rasterize_pdf_page(
    be overridden with the values in page_dpi.

    Args:
-        raster_device: type of image to produce at output_file
-        raster_dpi: resolution at which to rasterize page
-        pageno: page number to rasterize (beginning at page 1)
-        page_dpi: resolution, overriding output image DPI
-        rotation: cardinal angle, clockwise, to rotate page
-        filter_vector: if True, remove vector graphics objects
+        input_file: The PDF to rasterize.
+        output_file: The desired name of the rasterized image.
+        raster_device: Type of image to produce at output_file
+        raster_dpi: Resolution at which to rasterize page
+        pageno: Page number to rasterize (beginning at page 1)
+        page_dpi: Resolution, overriding output image DPI
+        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>`.
    """


@@ -115,32 +154,85 @@ def filter_page_image(page: 'PageContext', image_filename: Path) -> Path:
    produced for a given page, this function will not be called. This is not
    the image that will be shown to OCR.

-    ocrmypdf will create the PDF page based on the image format used. If you
+    If the function does not want to modify the image, it should return
+    ``image_filename``. The hook may overwrite ``image_filename`` with a new file.
+
+    The output image should preserve the same physical unit dimensions, that is
+    (width * dpi_x, height * dpi_y). That is, if the image is resized, the DPI
+    must be adjusted by the reciprocal. If this is not preserved, the PDF page
+    will be resized and the OCR layer misaligned. OCRmyPDF does not nothing
+    to enforce these constraints; it is up to the plugin to do sensible things.
+
+    OCRmyPDF will create the PDF page based on the image format used. If you
    convert the image to a JPEG, the output page will be created as a JPEG, etc.
-    Note that the ocrmypdf image optimization stage may ultimately chose a
+    If you change the colorspace, that change will be kept. Note that the
+    OCRmyPDF image optimization stage, if enabled, may ultimately chose a
    different format.
+
+    If the return value is a file that does not exist, ``FileNotFoundError``
+    will occur. The return value should be a path to a file in the same folder
+    as ``image_filename``.
+
+    Implementation detail: If the value returned is falsy, OCRmyPDF will ignore
+    the return value and assume the input file was unmodified. This is deprecated.
+    To leave the image unmodified, ``image_filename`` should be returned.
+
+    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]:
-        """Returns set of languages that are supported."""
+        """Returns the set of all languages that are supported by the engine.
+
+        Languages are typically given in 3-letter ISO 3166-1 codes, but actually
+        can be any value understood by the OCR engine."""

    @abstractstaticmethod
    def get_orientation(input_file: Path, options: Namespace) -> OrientationConfidence:
@@ -150,18 +242,34 @@ class OcrEngine(ABC):
    def generate_hocr(
        input_file: Path, output_hocr: Path, output_text: Path, options: Namespace
    ) -> None:
-        """Called to produce a hOCR file."""
+        """Called to produce a hOCR file and sidecar text file."""

    @abstractstaticmethod
    def generate_pdf(
        input_file: Path, output_pdf: Path, output_text: Path, options: Namespace
    ) -> None:
-        """Called to produce a text only PDF (no image, invisible text)."""
+        """Called to produce a text only PDF.
+
+        Args:
+            input_file: A page image on which to perform OCR.
+            output_pdf: The expected name of the output PDF, which must be
+                a single page PDF with no visible content of any kind, sized
+                to the dimensions implied by the input_file's width, height
+                and DPI. The image will be grafted onto the input PDF page.
+        """


@hookspec(firstresult=True)
 def get_ocr_engine() -> OcrEngine:
-    pass
+    """Returns an OcrEngine to use for processing this file.
+
+    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>`.
+    """


@hookspec(firstresult=True)
@@ -175,21 +283,29 @@ def generate_pdfa(
 ) -> Path:
    """Generate a PDF/A.

-    The pdf_pages, a list of files, will be merged into output_file. One or more
-    PDF files may be merged. The pdfmark file is a PostScript.ps file that
-    provides Ghostscript with details on how to perform the PDF/A
-    conversion. By default with we pick PDF/A-2b, but this works for 1 or 3.
+    This API strongly assumes a PDF/A generator with Ghostscript's semantics.

-    compression can be 'jpeg', 'lossless', or an empty string. In 'jpeg',
-    Ghostscript is instructed to convert color and grayscale images to DCT
-    (JPEG encoding). In 'lossless' Ghostscript is told to convert images to
-    Flate (lossless/PNG). If the parameter is omitted Ghostscript is left to
-    make its own decisions about how to encode images; it appears to use a
-    heuristic to decide how to encode images. As of Ghostscript 9.25, we
-    support passthrough JPEG which allows Ghostscript to avoid transcoding
-    images entirely. (The feature was added in 9.23 but broken, and the 9.24
-    release of Ghostscript had regressions, so we don't support it until 9.25.)
+    OCRmyPDF will modify the metadata and possibly linearize the PDF/A after it
+    is generated.
+
+    Arguments:
+        pdf_pages: A list of one or more filenames, will be merged into output_file.
+        pdfmark: A PostScript file intended for Ghostscript with details on
+            how to perform the PDF/A conversion.
+        output_file: The name of the desired output file.
+        compression: One of ``'jpeg'``, ``'lossless'``, ``''``. For ``'jpeg'``,
+            the PDF/A generator should convert all images to JPEG encoding where
+            possible. For lossless, all images should be converted to FlateEncode
+            (lossless PNG). If an empty string, the PDF generator should make its
+            own decisions about how to encode images.
+        pdf_version: The minimum PDF version that the output file should be.
+            At its own discretion, the PDF/A generator may raise the version,
+            but should not lower it.
+        pdfa_part: The desired PDF/A compliance level, such as ``'2B'``.

    Returns:
-        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"""

@@ -35,19 +25,21 @@ from ocrmypdf.exceptions import MissingDependencyError
 log = logging.getLogger(__name__)


-def run(args, *, env=None, **kwargs):
-    """Wrapper around subprocess.run()
+def run(args, *, env=None, logs_errors_to_stdout=False, **kwargs):
+    """Wrapper around :py:func:`subprocess.run`

-    The main purpose of this wrapper is to log subprocess output.
+    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.

-    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.
+    Arguments should be identical to ``subprocess.run``, except for following:

+    Arguments:
+        logs_errors_to_stdout: If True, indicates that the process writes its error
+            messages to stdout rather than stderr, so stdout should be logged
+            if there is an error. If False, stderr is logged. Could be used with
+            stderr=STDOUT, stdout=PIPE for example.
    """
    if not env:
        env = os.environ
@@ -59,25 +51,29 @@ def run(args, *, env=None, **kwargs):
        args = _fix_windows_args(program, args, env)

    log.debug("Running: %s", args)
-    process_log = log.getChild('subprocess.' + os.path.basename(program))
+    process_log = log.getChild(os.path.basename(program))
    if sys.version_info < (3, 7) and os.name == 'nt':
        # Can't use close_fds=True on Windows with Python 3.6 or older
        # https://bugs.python.org/issue19575, etc.
        kwargs['close_fds'] = False

    stderr = None
+    stderr_name = 'stderr' if not logs_errors_to_stdout else 'stdout'
    try:
        proc = subprocess_run(args, env=env, **kwargs)
    except CalledProcessError as e:
-        stderr = getattr(e, 'stderr', None)
+        stderr = getattr(e, stderr_name, None)
        raise
    else:
-        stderr = getattr(proc, 'stderr', None)
+        stderr = getattr(proc, stderr_name, None)
    finally:
        if process_log.isEnabledFor(logging.DEBUG) and stderr:
            with suppress(AttributeError, UnicodeDecodeError):
                stderr = stderr.decode('utf-8', 'replace')
-            process_log.debug("stderr = %s", stderr)
+            if logs_errors_to_stdout:
+                process_log.debug("stdout/stderr = %s", stderr)
+            else:
+                process_log.debug("stderr = %s", stderr)
    return proc


@@ -106,8 +102,18 @@ 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 +1 @@
-Tesseract Open Source OCR Engine v4.0.0 with Leptonica
+Tesseract Open Source OCR Engine v4.1.1 with Leptonica
@@ -1 +1 @@
-Tesseract Open Source OCR Engine v4.1.0 with Leptonica
+Tesseract Open Source OCR Engine v4.1.1 with Leptonica
@@ -1 +1 @@
-Tesseract Open Source OCR Engine v4.1.0 with Leptonica
+Tesseract Open Source OCR Engine v4.1.1 with Leptonica
@@ -1 +1 @@
-Tesseract Open Source OCR Engine v4.1.0 with Leptonica
+Tesseract Open Source OCR Engine v4.1.1 with Leptonica
@@ -4,12 +4,12 @@
 <html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
 <head>
  <title></title>
-<meta http-equiv="Content-Type" content="text/html;charset=utf-8" />
-  <meta name='ocr-system' content='tesseract 4.0.0' />
+  <meta http-equiv="Content-Type" content="text/html;charset=utf-8"/>
+  <meta name='ocr-system' content='tesseract 4.1.1' />
  <meta name='ocr-capabilities' content='ocr_page ocr_carea ocr_par ocr_line ocrx_word ocrp_wconf'/>
-</head>
-<body>
-  <div class='ocr_page' id='page_1' title='image "/var/folders/2s/7t022mgj0h5cprbq0dtb1ksm0000gn/T/com.github.ocrmypdf.xam82ph5/000001_ocr.png"; bbox 0 0 1000 800; ppageno 0'>
+ </head>
+ <body>
+  <div class='ocr_page' id='page_1' title='image "/var/folders/2s/7t022mgj0h5cprbq0dtb1ksm0000gn/T/com.github.ocrmypdf.mrqsewbu/000001_ocr.png"; bbox 0 0 1000 800; ppageno 0'>
   <div class='ocr_carea' id='block_1_1' title="bbox 296 96 704 504">
    <p class='ocr_par' id='par_1_1' lang='eng' title="bbox 296 96 704 504">
     <span class='ocr_line' id='line_1_1' title="bbox 296 96 704 504; baseline 0 296; x_size 169.33333; x_descenders 42.333332; x_ascenders 42.333336">
@@ -1 +1 @@
-Tesseract Open Source OCR Engine v4.0.0 with Leptonica
+Tesseract Open Source OCR Engine v4.1.1 with Leptonica
@@ -1 +1 @@
-Tesseract Open Source OCR Engine v4.0.0 with Leptonica
+Tesseract Open Source OCR Engine v4.1.1 with Leptonica
@@ -4,19 +4,19 @@
 <html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
 <head>
  <title></title>
-<meta http-equiv="Content-Type" content="text/html;charset=utf-8" />
-  <meta name='ocr-system' content='tesseract 4.0.0' />
+  <meta http-equiv="Content-Type" content="text/html;charset=utf-8"/>
+  <meta name='ocr-system' content='tesseract 4.1.1' />
  <meta name='ocr-capabilities' content='ocr_page ocr_carea ocr_par ocr_line ocrx_word ocrp_wconf'/>
-</head>
-<body>
-  <div class='ocr_page' id='page_1' title='image "/var/folders/2s/7t022mgj0h5cprbq0dtb1ksm0000gn/T/com.github.ocrmypdf.6a60f5yy/000001_ocr.png"; bbox 0 0 2550 3300; ppageno 0'>
+ </head>
+ <body>
+  <div class='ocr_page' id='page_1' title='image "/var/folders/2s/7t022mgj0h5cprbq0dtb1ksm0000gn/T/com.github.ocrmypdf.ces85e5u/000001_ocr.png"; bbox 0 0 2550 3300; ppageno 0'>
   <div class='ocr_carea' id='block_1_1' title="bbox 582 131 1968 303">
    <p class='ocr_par' id='par_1_1' lang='eng' title="bbox 582 131 1968 303">
-     <span class='ocr_line' id='line_1_1' title="bbox 882 131 1657 217; baseline 0.001 -17; x_size 85; x_descenders 16; x_ascenders 19">
+     <span class='ocr_header' id='line_1_1' title="bbox 882 131 1657 217; baseline 0.001 -17; x_size 85; x_descenders 16; x_ascenders 19">
      <span class='ocrx_word' id='word_1_1' title='bbox 882 132 1036 202; x_wconf 93'>The</span>
      <span class='ocrx_word' id='word_1_2' title='bbox 1061 131 1657 217; x_wconf 91'>LinnSequencer</span>
     </span>
-     <span class='ocr_line' id='line_1_2' title="bbox 582 215 1968 303; baseline 0 -17; x_size 87; x_descenders 16; x_ascenders 21">
+     <span class='ocr_header' id='line_1_2' title="bbox 582 215 1968 303; baseline 0 -17; x_size 87; x_descenders 16; x_ascenders 21">
      <span class='ocrx_word' id='word_1_3' title='bbox 582 215 674 286; x_wconf 96'>32</span>
      <span class='ocrx_word' id='word_1_4' title='bbox 697 218 923 288; x_wconf 95'>Track</span>
      <span class='ocrx_word' id='word_1_5' title='bbox 948 218 1181 287; x_wconf 96'>MIDI</span>
@@ -27,27 +27,27 @@
   </div>
   <div class='ocr_carea' id='block_1_2' title="bbox 347 380 2188 574">
    <p class='ocr_par' id='par_1_2' lang='eng' title="bbox 347 380 2188 423">
-     <span class='ocr_line' id='line_1_3' title="bbox 347 380 2188 423; baseline -0.001 -12; x_size 38; x_descenders 8; x_ascenders 10">
+     <span class='ocr_header' id='line_1_3' title="bbox 347 380 2188 423; baseline -0.001 -12; x_size 38; x_descenders 8; x_ascenders 10">
      <span class='ocrx_word' id='word_1_8' title='bbox 347 380 412 410; x_wconf 93'>The</span>
-      <span class='ocrx_word' id='word_1_9' title='bbox 424 380 661 417; x_wconf 92'>LinnSequencer</span>
-      <span class='ocrx_word' id='word_1_10' title='bbox 663 380 712 411; x_wconf 96'>is</span>
+      <span class='ocrx_word' id='word_1_9' title='bbox 424 380 676 417; x_wconf 92'>LinnSequencer</span>
+      <span class='ocrx_word' id='word_1_10' title='bbox 688 380 712 411; x_wconf 96'>is</span>
      <span class='ocrx_word' id='word_1_11' title='bbox 724 390 743 411; x_wconf 96'>a</span>
      <span class='ocrx_word' id='word_1_12' title='bbox 754 381 1005 423; x_wconf 96'>state-of-the-art</span>
      <span class='ocrx_word' id='word_1_13' title='bbox 1017 380 1226 418; x_wconf 96'>composition</span>
      <span class='ocrx_word' id='word_1_14' title='bbox 1238 381 1299 411; x_wconf 96'>and</span>
-      <span class='ocrx_word' id='word_1_15' title='bbox 1311 380 1507 418; x_wconf 96'>performance</span>
-      <span class='ocrx_word' id='word_1_16' title='bbox 1509 385 1591 411; x_wconf 96'>tool</span>
-      <span class='ocrx_word' id='word_1_17' title='bbox 1593 380 1663 411; x_wconf 97'>for</span>
+      <span class='ocrx_word' id='word_1_15' title='bbox 1311 380 1525 418; x_wconf 96'>performance</span>
+      <span class='ocrx_word' id='word_1_16' title='bbox 1536 380 1602 411; x_wconf 96'>tool</span>
+      <span class='ocrx_word' id='word_1_17' title='bbox 1615 380 1663 411; x_wconf 97'>for</span>
      <span class='ocrx_word' id='word_1_18' title='bbox 1674 381 1725 410; x_wconf 96'>the</span>
      <span class='ocrx_word' id='word_1_19' title='bbox 1737 380 1940 417; x_wconf 95'>professional</span>
-      <span class='ocrx_word' id='word_1_20' title='bbox 1952 380 2103 411; x_wconf 96'>musician.</span>
-      <span class='ocrx_word' id='word_1_21' title='bbox 2106 381 2152 410; x_wconf 96'>It</span>
+      <span class='ocrx_word' id='word_1_20' title='bbox 1952 380 2112 411; x_wconf 96'>musician.</span>
+      <span class='ocrx_word' id='word_1_21' title='bbox 2127 381 2152 410; x_wconf 96'>It</span>
      <span class='ocrx_word' id='word_1_22' title='bbox 2164 380 2188 410; x_wconf 96'>is</span>
     </span>
    </p>

    <p class='ocr_par' id='par_1_3' lang='eng' title="bbox 347 430 1988 468">
-     <span class='ocr_line' id='line_1_4' title="bbox 347 430 1988 468; baseline 0 -8; x_size 37; x_descenders 7; x_ascenders 9">
+     <span class='ocr_header' id='line_1_4' title="bbox 347 430 1988 468; baseline 0 -8; x_size 37; x_descenders 7; x_ascenders 9">
      <span class='ocrx_word' id='word_1_23' title='bbox 347 430 507 467; x_wconf 96'>extremely</span>
      <span class='ocrx_word' id='word_1_24' title='bbox 518 430 677 467; x_wconf 96'>powerful,</span>
      <span class='ocrx_word' id='word_1_25' title='bbox 691 435 739 467; x_wconf 96'>yet</span>
@@ -66,7 +66,7 @@
    </p>

    <p class='ocr_par' id='par_1_4' lang='eng' title="bbox 350 482 2093 574">
-     <span class='ocr_line' id='line_1_5' title="bbox 350 482 2093 527; baseline 0 -9; x_size 43; x_descenders 7; x_ascenders 11">
+     <span class='ocr_header' id='line_1_5' title="bbox 350 482 2093 527; baseline 0 -9; x_size 43; x_descenders 7; x_ascenders 11">
      <span class='ocrx_word' id='word_1_37' title='bbox 350 490 368 508; x_wconf 73'>¢</span>
      <span class='ocrx_word' id='word_1_38' title='bbox 383 482 585 526; x_wconf 95'>Operation</span>
      <span class='ocrx_word' id='word_1_39' title='bbox 598 482 627 518; x_wconf 96'>is</span>
@@ -81,18 +81,18 @@
      <span class='ocrx_word' id='word_1_48' title='bbox 1741 483 1957 525; x_wconf 96'>RECORD,</span>
      <span class='ocrx_word' id='word_1_49' title='bbox 1974 483 2093 518; x_wconf 96'>FAST</span>
     </span>
-     <span class='ocr_line' id='line_1_6' title="bbox 383 532 1345 574; baseline 0.001 -7; x_size 43; x_descenders 7; x_ascenders 11">
+     <span class='ocr_header' id='line_1_6' title="bbox 383 532 1345 574; baseline 0.001 -7; x_size 43; x_descenders 7; x_ascenders 11">
      <span class='ocrx_word' id='word_1_50' title='bbox 383 532 635 574; x_wconf 96'>FORWARD,</span>
      <span class='ocrx_word' id='word_1_51' title='bbox 652 532 865 574; x_wconf 95'>REWIND,</span>
      <span class='ocrx_word' id='word_1_52' title='bbox 882 532 956 568; x_wconf 95'>and</span>
-      <span class='ocrx_word' id='word_1_53' title='bbox 971 532 1131 568; x_wconf 95'>LOCATE</span>
-      <span class='ocrx_word' id='word_1_54' title='bbox 1132 532 1345 568; x_wconf 95'>controls.</span>
+      <span class='ocrx_word' id='word_1_53' title='bbox 971 532 1163 568; x_wconf 95'>LOCATE</span>
+      <span class='ocrx_word' id='word_1_54' title='bbox 1177 532 1345 568; x_wconf 95'>controls.</span>
     </span>
    </p>
   </div>
   <div class='ocr_carea' id='block_1_3' title="bbox 349 589 2136 685">
    <p class='ocr_par' id='par_1_5' lang='eng' title="bbox 349 589 2136 685">
-     <span class='ocr_line' id='line_1_7' title="bbox 349 589 2136 634; baseline 0.001 -9; x_size 44; x_descenders 8; x_ascenders 11">
+     <span class='ocr_header' id='line_1_7' title="bbox 349 589 2136 634; baseline 0.001 -9; x_size 44; x_descenders 8; x_ascenders 11">
      <span class='ocrx_word' id='word_1_55' title='bbox 349 597 368 615; x_wconf 59'>e</span>
      <span class='ocrx_word' id='word_1_56' title='bbox 383 590 482 625; x_wconf 96'>Each</span>
      <span class='ocrx_word' id='word_1_57' title='bbox 496 589 539 625; x_wconf 96'>of</span>
@@ -108,7 +108,7 @@
      <span class='ocrx_word' id='word_1_67' title='bbox 1934 590 2035 626; x_wconf 96'>track</span>
      <span class='ocrx_word' id='word_1_68' title='bbox 2050 600 2136 634; x_wconf 96'>may</span>
     </span>
-     <span class='ocr_line' id='line_1_8' title="bbox 383 639 2022 685; baseline 0.001 -10; x_size 44; x_descenders 8; x_ascenders 11">
+     <span class='ocr_header' id='line_1_8' title="bbox 383 639 2022 685; baseline 0.001 -10; x_size 44; x_descenders 8; x_ascenders 11">
      <span class='ocrx_word' id='word_1_69' title='bbox 383 639 428 675; x_wconf 95'>be</span>
      <span class='ocrx_word' id='word_1_70' title='bbox 442 639 607 684; x_wconf 95'>assigned</span>
      <span class='ocrx_word' id='word_1_71' title='bbox 621 645 659 676; x_wconf 96'>to</span>
@@ -135,7 +135,7 @@
   </div>
   <div class='ocr_carea' id='block_1_5' title="bbox 349 748 2117 793">
    <p class='ocr_par' id='par_1_7' lang='eng' title="bbox 349 748 2117 793">
-     <span class='ocr_line' id='line_1_10' title="bbox 349 748 2117 793; baseline 0 -9; x_size 45; x_descenders 9; x_ascenders 11">
+     <span class='ocr_header' id='line_1_10' title="bbox 349 748 2117 793; baseline 0 -9; x_size 45; x_descenders 9; x_ascenders 11">
      <span class='ocrx_word' id='word_1_84' title='bbox 349 755 367 774; x_wconf 58'>¢</span>
      <span class='ocrx_word' id='word_1_85' title='bbox 383 748 573 784; x_wconf 91'>Ultra-fast</span>
      <span class='ocrx_word' id='word_1_86' title='bbox 588 749 677 784; x_wconf 22'>3%”</span>
@@ -147,8 +147,8 @@
      <span class='ocrx_word' id='word_1_92' title='bbox 1330 748 1368 784; x_wconf 96'>in</span>
      <span class='ocrx_word' id='word_1_93' title='bbox 1382 748 1535 785; x_wconf 96'>seconds</span>
      <span class='ocrx_word' id='word_1_94' title='bbox 1550 748 1624 784; x_wconf 96'>and</span>
-      <span class='ocrx_word' id='word_1_95' title='bbox 1638 748 1728 784; x_wconf 96'>holds</span>
-      <span class='ocrx_word' id='word_1_96' title='bbox 1730 759 1844 784; x_wconf 96'>over</span>
+      <span class='ocrx_word' id='word_1_95' title='bbox 1638 748 1746 784; x_wconf 96'>holds</span>
+      <span class='ocrx_word' id='word_1_96' title='bbox 1761 759 1844 784; x_wconf 96'>over</span>
      <span class='ocrx_word' id='word_1_97' title='bbox 1859 749 2000 791; x_wconf 96'>110,000</span>
      <span class='ocrx_word' id='word_1_98' title='bbox 2013 753 2117 784; x_wconf 96'>notes</span>
     </span>
@@ -164,23 +164,23 @@
   </div>
   <div class='ocr_carea' id='block_1_7' title="bbox 349 855 2030 1016">
    <p class='ocr_par' id='par_1_9' lang='eng' title="bbox 349 855 2030 1016">
-     <span class='ocr_line' id='line_1_12' title="bbox 350 855 1638 900; baseline 0.001 -9; x_size 45; x_descenders 9; x_ascenders 11">
+     <span class='ocr_header' id='line_1_12' title="bbox 350 855 1638 900; baseline 0.001 -9; x_size 45; x_descenders 9; x_ascenders 11">
      <span class='ocrx_word' id='word_1_101' title='bbox 350 863 367 881; x_wconf 45'>¢</span>
-      <span class='ocrx_word' id='word_1_102' title='bbox 383 856 444 891; x_wconf 95'>One</span>
-      <span class='ocrx_word' id='word_1_103' title='bbox 445 866 502 891; x_wconf 96'>or</span>
-      <span class='ocrx_word' id='word_1_104' title='bbox 503 855 580 891; x_wconf 96'>all</span>
+      <span class='ocrx_word' id='word_1_102' title='bbox 383 856 464 891; x_wconf 95'>One</span>
+      <span class='ocrx_word' id='word_1_103' title='bbox 478 866 520 891; x_wconf 96'>or</span>
+      <span class='ocrx_word' id='word_1_104' title='bbox 534 855 580 891; x_wconf 96'>all</span>
      <span class='ocrx_word' id='word_1_105' title='bbox 594 856 712 892; x_wconf 95'>tracks</span>
      <span class='ocrx_word' id='word_1_106' title='bbox 726 867 811 900; x_wconf 95'>may</span>
      <span class='ocrx_word' id='word_1_107' title='bbox 823 856 869 892; x_wconf 81'>be</span>
-      <span class='ocrx_word' id='word_1_108' title='bbox 882 856 1175 892; x_wconf 96'>TRANSPOSED</span>
-      <span class='ocrx_word' id='word_1_109' title='bbox 1178 857 1264 892; x_wconf 96'>at</span>
+      <span class='ocrx_word' id='word_1_108' title='bbox 882 856 1212 892; x_wconf 96'>TRANSPOSED</span>
+      <span class='ocrx_word' id='word_1_109' title='bbox 1227 861 1264 892; x_wconf 96'>at</span>
      <span class='ocrx_word' id='word_1_110' title='bbox 1277 856 1338 892; x_wconf 96'>the</span>
      <span class='ocrx_word' id='word_1_111' title='bbox 1351 856 1463 892; x_wconf 96'>touch</span>
-      <span class='ocrx_word' id='word_1_112' title='bbox 1477 867 1501 892; x_wconf 96'>of</span>
-      <span class='ocrx_word' id='word_1_113' title='bbox 1502 856 1554 892; x_wconf 96'>a</span>
+      <span class='ocrx_word' id='word_1_112' title='bbox 1477 856 1520 892; x_wconf 96'>of</span>
+      <span class='ocrx_word' id='word_1_113' title='bbox 1531 867 1554 892; x_wconf 96'>a</span>
      <span class='ocrx_word' id='word_1_114' title='bbox 1568 856 1638 900; x_wconf 96'>key.</span>
     </span>
-     <span class='ocr_line' id='line_1_13' title="bbox 350 913 1535 958; baseline 0.001 -9; x_size 44; x_descenders 8; x_ascenders 11">
+     <span class='ocr_header' id='line_1_13' title="bbox 350 913 1535 958; baseline 0.001 -9; x_size 44; x_descenders 8; x_ascenders 11">
      <span class='ocrx_word' id='word_1_115' title='bbox 350 921 367 939; x_wconf 45'>e</span>
      <span class='ocrx_word' id='word_1_116' title='bbox 383 913 568 950; x_wconf 96'>Exclusive</span>
      <span class='ocrx_word' id='word_1_117' title='bbox 581 913 756 950; x_wconf 96'>real-time</span>
@@ -190,7 +190,7 @@
      <span class='ocrx_word' id='word_1_121' title='bbox 1266 914 1400 958; x_wconf 96'>editing</span>
      <span class='ocrx_word' id='word_1_122' title='bbox 1414 915 1535 950; x_wconf 95'>FAST.</span>
     </span>
-     <span class='ocr_line' id='line_1_14' title="bbox 349 971 2030 1016; baseline 0.001 -10; x_size 44; x_descenders 8; x_ascenders 11">
+     <span class='ocr_header' id='line_1_14' title="bbox 349 971 2030 1016; baseline 0.001 -10; x_size 44; x_descenders 8; x_ascenders 11">
      <span class='ocrx_word' id='word_1_123' title='bbox 349 979 367 997; x_wconf 0'>*</span>
      <span class='ocrx_word' id='word_1_124' title='bbox 382 971 568 1007; x_wconf 95'>Exclusive</span>
      <span class='ocrx_word' id='word_1_125' title='bbox 582 972 773 1007; x_wconf 96'>REPEAT</span>
@@ -216,11 +216,11 @@
   </div>
   <div class='ocr_carea' id='block_1_9' title="bbox 349 1080 2174 1125">
    <p class='ocr_par' id='par_1_11' lang='eng' title="bbox 349 1080 2174 1125">
-     <span class='ocr_line' id='line_1_16' title="bbox 349 1080 2174 1125; baseline 0.001 -11; x_size 45; x_descenders 9; x_ascenders 11">
+     <span class='ocr_header' id='line_1_16' title="bbox 349 1080 2174 1125; baseline 0.001 -11; x_size 45; x_descenders 9; x_ascenders 11">
      <span class='ocrx_word' id='word_1_137' title='bbox 349 1087 367 1105; x_wconf 80'>¢</span>
      <span class='ocrx_word' id='word_1_138' title='bbox 382 1080 567 1115; x_wconf 95'>TIMING</span>
-      <span class='ocrx_word' id='word_1_139' title='bbox 582 1080 870 1116; x_wconf 95'>CORRECTION</span>
-      <span class='ocrx_word' id='word_1_140' title='bbox 872 1080 1041 1116; x_wconf 96'>works</span>
+      <span class='ocrx_word' id='word_1_139' title='bbox 582 1080 908 1116; x_wconf 95'>CORRECTION</span>
+      <span class='ocrx_word' id='word_1_140' title='bbox 921 1080 1041 1116; x_wconf 96'>works</span>
      <span class='ocrx_word' id='word_1_141' title='bbox 1056 1080 1186 1124; x_wconf 96'>during</span>
      <span class='ocrx_word' id='word_1_142' title='bbox 1199 1080 1378 1124; x_wconf 96'>playback</span>
      <span class='ocrx_word' id='word_1_143' title='bbox 1392 1080 1466 1116; x_wconf 96'>and</span>
@@ -233,11 +233,11 @@
   </div>
   <div class='ocr_carea' id='block_1_10' title="bbox 349 1137 1287 1182">
    <p class='ocr_par' id='par_1_12' lang='eng' title="bbox 349 1137 1287 1182">
-     <span class='ocr_line' id='line_1_17' title="bbox 349 1137 1287 1182; baseline 0.001 -9; x_size 45; x_descenders 9; x_ascenders 11">
+     <span class='ocr_textfloat' id='line_1_17' title="bbox 349 1137 1287 1182; baseline 0.001 -9; x_size 45; x_descenders 9; x_ascenders 11">
      <span class='ocrx_word' id='word_1_148' title='bbox 349 1145 367 1163; x_wconf 80'>¢</span>
      <span class='ocrx_word' id='word_1_149' title='bbox 382 1137 560 1182; x_wconf 95'>Optional</span>
-      <span class='ocrx_word' id='word_1_150' title='bbox 575 1138 708 1174; x_wconf 96'>SMPTE</span>
-      <span class='ocrx_word' id='word_1_151' title='bbox 709 1138 839 1174; x_wconf 96'>time</span>
+      <span class='ocrx_word' id='word_1_150' title='bbox 575 1138 739 1174; x_wconf 96'>SMPTE</span>
+      <span class='ocrx_word' id='word_1_151' title='bbox 752 1138 839 1174; x_wconf 96'>time</span>
      <span class='ocrx_word' id='word_1_152' title='bbox 853 1138 945 1174; x_wconf 95'>code</span>
      <span class='ocrx_word' id='word_1_153' title='bbox 959 1138 1287 1182; x_wconf 96'>synchronization.</span>
     </span>
@@ -278,9 +278,9 @@
      <span class='ocrx_word' id='word_1_170' title='bbox 346 1379 411 1406; x_wconf 96'>then</span>
      <span class='ocrx_word' id='word_1_171' title='bbox 422 1378 483 1412; x_wconf 96'>play</span>
      <span class='ocrx_word' id='word_1_172' title='bbox 493 1387 562 1412; x_wconf 96'>your</span>
-      <span class='ocrx_word' id='word_1_173' title='bbox 572 1379 646 1405; x_wconf 96'>MIDI</span>
-      <span class='ocrx_word' id='word_1_174' title='bbox 649 1379 792 1412; x_wconf 96'>keyboard</span>
-      <span class='ocrx_word' id='word_1_175' title='bbox 792 1379 848 1406; x_wconf 95'>in</span>
+      <span class='ocrx_word' id='word_1_173' title='bbox 572 1379 659 1405; x_wconf 96'>MIDI</span>
+      <span class='ocrx_word' id='word_1_174' title='bbox 671 1379 810 1412; x_wconf 96'>keyboard</span>
+      <span class='ocrx_word' id='word_1_175' title='bbox 821 1379 848 1406; x_wconf 95'>in</span>
      <span class='ocrx_word' id='word_1_176' title='bbox 858 1379 923 1406; x_wconf 95'>time</span>
      <span class='ocrx_word' id='word_1_177' title='bbox 934 1384 963 1406; x_wconf 96'>to</span>
      <span class='ocrx_word' id='word_1_178' title='bbox 974 1379 1019 1406; x_wconf 93'>the</span>
@@ -294,14 +294,14 @@
      <span class='ocrx_word' id='word_1_184' title='bbox 676 1426 810 1452; x_wconf 96'>sequence</span>
      <span class='ocrx_word' id='word_1_185' title='bbox 821 1419 901 1452; x_wconf 96'>loops</span>
      <span class='ocrx_word' id='word_1_186' title='bbox 912 1419 983 1446; x_wconf 96'>back</span>
-      <span class='ocrx_word' id='word_1_187' title='bbox 995 1427 1082 1446; x_wconf 96'>around</span>
-      <span class='ocrx_word' id='word_1_188' title='bbox 1084 1419 1141 1446; x_wconf 96'>to</span>
-      <span class='ocrx_word' id='word_1_189' title='bbox 1152 1419 1189 1446; x_wconf 96'>bar</span>
-      <span class='ocrx_word' id='word_1_190' title='bbox 1189 1419 1232 1450; x_wconf 74'>1,</span>
+      <span class='ocrx_word' id='word_1_187' title='bbox 995 1419 1101 1446; x_wconf 96'>around</span>
+      <span class='ocrx_word' id='word_1_188' title='bbox 1112 1423 1141 1446; x_wconf 96'>to</span>
+      <span class='ocrx_word' id='word_1_189' title='bbox 1152 1419 1201 1446; x_wconf 96'>bar</span>
+      <span class='ocrx_word' id='word_1_190' title='bbox 1213 1419 1232 1450; x_wconf 74'>1,</span>
     </span>
     <span class='ocr_line' id='line_1_23' title="bbox 346 1457 1223 1491; baseline 0.001 -7; x_size 34; x_descenders 7; x_ascenders 8">
-      <span class='ocrx_word' id='word_1_191' title='bbox 346 1465 400 1490; x_wconf 14'>you’</span>
-      <span class='ocrx_word' id='word_1_192' title='bbox 404 1457 430 1484; x_wconf 14'>ll</span>
+      <span class='ocrx_word' id='word_1_191' title='bbox 346 1457 430 1490; x_wconf 14'>you’</span>
+      <span class='ocrx_word' id='word_1_192' title='bbox 406 1453 436 1496; x_wconf 14'>ll</span>
      <span class='ocrx_word' id='word_1_193' title='bbox 441 1457 506 1485; x_wconf 96'>hear</span>
      <span class='ocrx_word' id='word_1_194' title='bbox 517 1458 590 1485; x_wconf 96'>what</span>
      <span class='ocrx_word' id='word_1_195' title='bbox 600 1466 654 1491; x_wconf 93'>you</span>
@@ -316,7 +316,7 @@
   </div>
   <div class='ocr_carea' id='block_1_13' title="bbox 346 1497 1245 1531">
    <p class='ocr_par' id='par_1_16' lang='eng' title="bbox 346 1497 1245 1531">
-     <span class='ocr_line' id='line_1_24' title="bbox 346 1497 1245 1531; baseline 0.001 -7; x_size 35; x_descenders 7; x_ascenders 9">
+     <span class='ocr_textfloat' id='line_1_24' title="bbox 346 1497 1245 1531; baseline 0.001 -7; x_size 35; x_descenders 7; x_ascenders 9">
      <span class='ocrx_word' id='word_1_202' title='bbox 346 1497 494 1524; x_wconf 96'>corrected!</span>
      <span class='ocrx_word' id='word_1_203' title='bbox 508 1497 628 1530; x_wconf 96'>(Timing</span>
      <span class='ocrx_word' id='word_1_204' title='bbox 638 1497 791 1525; x_wconf 95'>correction</span>
@@ -343,8 +343,8 @@
      <span class='ocrx_word' id='word_1_219' title='bbox 1111 1537 1186 1564; x_wconf 96'>track</span>
     </span>
     <span class='ocr_line' id='line_1_26' title="bbox 347 1575 1052 1610; baseline 0.001 -8; x_size 34; x_descenders 7; x_ascenders 8">
-      <span class='ocrx_word' id='word_1_220' title='bbox 347 1591 381 1594; x_wconf 0'>—</span>
-      <span class='ocrx_word' id='word_1_221' title='bbox 382 1575 495 1609; x_wconf 0'>existing</span>
+      <span class='ocrx_word' id='word_1_220' title='bbox 347 1591 372 1594; x_wconf 0'>—</span>
+      <span class='ocrx_word' id='word_1_221' title='bbox 371 1575 495 1609; x_wconf 0'>existing</span>
      <span class='ocrx_word' id='word_1_222' title='bbox 505 1580 582 1603; x_wconf 96'>notes</span>
      <span class='ocrx_word' id='word_1_223' title='bbox 593 1584 637 1603; x_wconf 96'>are</span>
      <span class='ocrx_word' id='word_1_224' title='bbox 648 1580 696 1603; x_wconf 97'>not</span>
@@ -358,10 +358,10 @@
     <span class='ocr_line' id='line_1_27' title="bbox 384 1616 1199 1648; baseline 0.001 -6; x_size 32; x_descenders 5; x_ascenders 8">
      <span class='ocrx_word' id='word_1_228' title='bbox 384 1616 471 1642; x_wconf 96'>FAST</span>
      <span class='ocrx_word' id='word_1_229' title='bbox 481 1616 671 1648; x_wconf 96'>FORWARD,</span>
-      <span class='ocrx_word' id='word_1_230' title='bbox 684 1617 838 1643; x_wconf 95'>REWIND,</span>
-      <span class='ocrx_word' id='word_1_231' title='bbox 839 1616 912 1648; x_wconf 95'>and</span>
-      <span class='ocrx_word' id='word_1_232' title='bbox 924 1616 1045 1643; x_wconf 96'>LOCATE</span>
-      <span class='ocrx_word' id='word_1_233' title='bbox 1046 1616 1199 1643; x_wconf 95'>controls</span>
+      <span class='ocrx_word' id='word_1_230' title='bbox 684 1617 844 1648; x_wconf 95'>REWIND,</span>
+      <span class='ocrx_word' id='word_1_231' title='bbox 857 1616 912 1643; x_wconf 95'>and</span>
+      <span class='ocrx_word' id='word_1_232' title='bbox 924 1616 1068 1643; x_wconf 96'>LOCATE</span>
+      <span class='ocrx_word' id='word_1_233' title='bbox 1079 1616 1199 1643; x_wconf 95'>controls</span>
     </span>
     <span class='ocr_line' id='line_1_28' title="bbox 346 1655 1202 1689; baseline 0 -7; x_size 34; x_descenders 6; x_ascenders 9">
      <span class='ocrx_word' id='word_1_234' title='bbox 346 1663 409 1688; x_wconf 92'>may</span>
@@ -385,8 +385,8 @@
      <span class='ocrx_word' id='word_1_250' title='bbox 860 1696 897 1722; x_wconf 93'>To</span>
      <span class='ocrx_word' id='word_1_251' title='bbox 908 1695 1028 1722; x_wconf 93'>overdub</span>
      <span class='ocrx_word' id='word_1_252' title='bbox 1039 1703 1056 1722; x_wconf 96'>a</span>
-      <span class='ocrx_word' id='word_1_253' title='bbox 1066 1703 1099 1722; x_wconf 96'>new</span>
-      <span class='ocrx_word' id='word_1_254' title='bbox 1100 1699 1204 1728; x_wconf 96'>part,</span>
+      <span class='ocrx_word' id='word_1_253' title='bbox 1066 1703 1125 1722; x_wconf 96'>new</span>
+      <span class='ocrx_word' id='word_1_254' title='bbox 1135 1699 1204 1728; x_wconf 96'>part,</span>
     </span>
     <span class='ocr_line' id='line_1_30' title="bbox 347 1733 1150 1768; baseline 0.001 -8; x_size 35; x_descenders 7; x_ascenders 9">
      <span class='ocrx_word' id='word_1_255' title='bbox 347 1733 426 1761; x_wconf 97'>select</span>
@@ -401,8 +401,8 @@
     <span class='ocr_line' id='line_1_31' title="bbox 346 1773 1203 1808; baseline 0.001 -8; x_size 33; x_descenders 6; x_ascenders 8">
      <span class='ocrx_word' id='word_1_263' title='bbox 346 1774 448 1806; x_wconf 96'>record,</span>
      <span class='ocrx_word' id='word_1_264' title='bbox 460 1774 506 1801; x_wconf 97'>the</span>
-      <span class='ocrx_word' id='word_1_265' title='bbox 517 1773 577 1801; x_wconf 96'>first</span>
-      <span class='ocrx_word' id='word_1_266' title='bbox 581 1774 662 1801; x_wconf 96'>track</span>
+      <span class='ocrx_word' id='word_1_265' title='bbox 503 1769 577 1812; x_wconf 96'>first</span>
+      <span class='ocrx_word' id='word_1_266' title='bbox 581 1774 658 1801; x_wconf 96'>track</span>
      <span class='ocrx_word' id='word_1_267' title='bbox 673 1774 726 1801; x_wconf 96'>will</span>
      <span class='ocrx_word' id='word_1_268' title='bbox 736 1774 799 1807; x_wconf 96'>play</span>
      <span class='ocrx_word' id='word_1_269' title='bbox 809 1774 836 1801; x_wconf 96'>in</span>
@@ -412,12 +412,12 @@
      <span class='ocrx_word' id='word_1_273' title='bbox 1148 1782 1203 1807; x_wconf 96'>you</span>
     </span>
     <span class='ocr_line' id='line_1_32' title="bbox 346 1813 1191 1847; baseline 0.002 -8; x_size 33; x_descenders 5; x_ascenders 9">
-      <span class='ocrx_word' id='word_1_274' title='bbox 346 1813 431 1840; x_wconf 95'>MUTE</span>
-      <span class='ocrx_word' id='word_1_275' title='bbox 431 1813 492 1845; x_wconf 95'>it,</span>
+      <span class='ocrx_word' id='word_1_274' title='bbox 346 1813 454 1840; x_wconf 95'>MUTE</span>
+      <span class='ocrx_word' id='word_1_275' title='bbox 464 1813 492 1845; x_wconf 95'>it,</span>
      <span class='ocrx_word' id='word_1_276' title='bbox 505 1821 537 1840; x_wconf 95'>or</span>
      <span class='ocrx_word' id='word_1_277' title='bbox 547 1813 642 1840; x_wconf 95'>SOLO</span>
-      <span class='ocrx_word' id='word_1_278' title='bbox 653 1814 756 1841; x_wconf 95'>another</span>
-      <span class='ocrx_word' id='word_1_279' title='bbox 757 1814 875 1847; x_wconf 94'>track).</span>
+      <span class='ocrx_word' id='word_1_278' title='bbox 653 1814 769 1841; x_wconf 95'>another</span>
+      <span class='ocrx_word' id='word_1_279' title='bbox 779 1814 875 1847; x_wconf 94'>track).</span>
      <span class='ocrx_word' id='word_1_280' title='bbox 889 1814 920 1840; x_wconf 96'>In</span>
      <span class='ocrx_word' id='word_1_281' title='bbox 930 1813 984 1841; x_wconf 96'>this</span>
      <span class='ocrx_word' id='word_1_282' title='bbox 995 1822 1057 1847; x_wconf 96'>way,</span>
@@ -431,8 +431,8 @@
      <span class='ocrx_word' id='word_1_288' title='bbox 518 1853 552 1879; x_wconf 96'>be</span>
      <span class='ocrx_word' id='word_1_289' title='bbox 562 1853 748 1880; x_wconf 96'>overdubbed!</span>
      <span class='ocrx_word' id='word_1_290' title='bbox 761 1853 808 1880; x_wconf 94'>All</span>
-      <span class='ocrx_word' id='word_1_291' title='bbox 819 1854 892 1880; x_wconf 96'>MIDI</span>
-      <span class='ocrx_word' id='word_1_292' title='bbox 895 1853 1011 1880; x_wconf 96'>effects</span>
+      <span class='ocrx_word' id='word_1_291' title='bbox 819 1854 905 1880; x_wconf 96'>MIDI</span>
+      <span class='ocrx_word' id='word_1_292' title='bbox 917 1853 1011 1880; x_wconf 96'>effects</span>
      <span class='ocrx_word' id='word_1_293' title='bbox 1022 1861 1067 1880; x_wconf 96'>are</span>
      <span class='ocrx_word' id='word_1_294' title='bbox 1076 1853 1205 1880; x_wconf 96'>recorded</span>
     </span>
@@ -440,8 +440,8 @@
      <span class='ocrx_word' id='word_1_295' title='bbox 346 1891 485 1925; x_wconf 96'>including</span>
      <span class='ocrx_word' id='word_1_296' title='bbox 495 1891 570 1925; x_wconf 96'>pitch</span>
      <span class='ocrx_word' id='word_1_297' title='bbox 580 1892 663 1924; x_wconf 96'>bend,</span>
-      <span class='ocrx_word' id='word_1_298' title='bbox 675 1892 850 1920; x_wconf 96'>modulation,</span>
-      <span class='ocrx_word' id='word_1_299' title='bbox 854 1892 991 1926; x_wconf 93'>velocity,</span>
+      <span class='ocrx_word' id='word_1_298' title='bbox 675 1892 859 1924; x_wconf 96'>modulation,</span>
+      <span class='ocrx_word' id='word_1_299' title='bbox 872 1892 991 1926; x_wconf 93'>velocity,</span>
      <span class='ocrx_word' id='word_1_300' title='bbox 1004 1892 1168 1924; x_wconf 92'>aftertouch,</span>
     </span>
     <span class='ocr_line' id='line_1_35' title="bbox 346 1931 895 1965; baseline 0.002 -7; x_size 33; x_descenders 6; x_ascenders 8">
@@ -465,13 +465,13 @@
      <span class='ocrx_word' id='word_1_307' title='bbox 383 2050 419 2076; x_wconf 96'>To</span>
      <span class='ocrx_word' id='word_1_308' title='bbox 430 2057 503 2076; x_wconf 95'>erase</span>
      <span class='ocrx_word' id='word_1_309' title='bbox 514 2058 530 2077; x_wconf 96'>a</span>
-      <span class='ocrx_word' id='word_1_310' title='bbox 540 2058 617 2077; x_wconf 96'>wrong</span>
-      <span class='ocrx_word' id='word_1_311' title='bbox 618 2054 717 2083; x_wconf 96'>note,</span>
+      <span class='ocrx_word' id='word_1_310' title='bbox 540 2058 634 2083; x_wconf 96'>wrong</span>
+      <span class='ocrx_word' id='word_1_311' title='bbox 644 2054 717 2082; x_wconf 96'>note,</span>
      <span class='ocrx_word' id='word_1_312' title='bbox 729 2050 829 2083; x_wconf 96'>simply</span>
      <span class='ocrx_word' id='word_1_313' title='bbox 839 2050 905 2077; x_wconf 96'>hold</span>
-      <span class='ocrx_word' id='word_1_314' title='bbox 916 2051 1013 2077; x_wconf 96'>ERASE</span>
-      <span class='ocrx_word' id='word_1_315' title='bbox 1015 2051 1083 2077; x_wconf 96'>and</span>
-      <span class='ocrx_word' id='word_1_316' title='bbox 1085 2050 1186 2084; x_wconf 96'>press</span>
+      <span class='ocrx_word' id='word_1_314' title='bbox 916 2051 1037 2077; x_wconf 96'>ERASE</span>
+      <span class='ocrx_word' id='word_1_315' title='bbox 1048 2050 1103 2077; x_wconf 96'>and</span>
+      <span class='ocrx_word' id='word_1_316' title='bbox 1113 2059 1186 2084; x_wconf 96'>press</span>
     </span>
     <span class='ocr_line' id='line_1_38' title="bbox 346 2089 1212 2124; baseline 0.002 -8; x_size 33; x_descenders 6; x_ascenders 8">
      <span class='ocrx_word' id='word_1_317' title='bbox 346 2089 391 2116; x_wconf 96'>the</span>
@@ -480,16 +480,16 @@
      <span class='ocrx_word' id='word_1_320' title='bbox 515 2090 549 2117; x_wconf 97'>be</span>
      <span class='ocrx_word' id='word_1_321' title='bbox 559 2090 652 2117; x_wconf 96'>erased</span>
      <span class='ocrx_word' id='word_1_322' title='bbox 661 2090 718 2123; x_wconf 96'>just</span>
-      <span class='ocrx_word' id='word_1_323' title='bbox 729 2090 808 2117; x_wconf 96'>before</span>
-      <span class='ocrx_word' id='word_1_324' title='bbox 808 2090 852 2117; x_wconf 96'>it</span>
+      <span class='ocrx_word' id='word_1_323' title='bbox 729 2090 822 2117; x_wconf 96'>before</span>
+      <span class='ocrx_word' id='word_1_324' title='bbox 833 2090 852 2117; x_wconf 96'>it</span>
      <span class='ocrx_word' id='word_1_325' title='bbox 862 2090 937 2124; x_wconf 96'>plays</span>
      <span class='ocrx_word' id='word_1_326' title='bbox 947 2090 975 2117; x_wconf 96'>in</span>
      <span class='ocrx_word' id='word_1_327' title='bbox 986 2090 1032 2118; x_wconf 93'>the</span>
      <span class='ocrx_word' id='word_1_328' title='bbox 1043 2098 1212 2124; x_wconf 88'>sequence—</span>
     </span>
     <span class='ocr_line' id='line_1_39' title="bbox 346 2129 1134 2163; baseline 0.003 -8; x_size 34; x_descenders 7; x_ascenders 8">
-      <span class='ocrx_word' id='word_1_329' title='bbox 346 2129 406 2156; x_wconf 96'>when</span>
-      <span class='ocrx_word' id='word_1_330' title='bbox 407 2129 531 2162; x_wconf 96'>played</span>
+      <span class='ocrx_word' id='word_1_329' title='bbox 346 2129 425 2156; x_wconf 96'>when</span>
+      <span class='ocrx_word' id='word_1_330' title='bbox 435 2129 531 2162; x_wconf 96'>played</span>
      <span class='ocrx_word' id='word_1_331' title='bbox 542 2129 621 2161; x_wconf 96'>back,</span>
      <span class='ocrx_word' id='word_1_332' title='bbox 633 2129 652 2156; x_wconf 96'>it</span>
      <span class='ocrx_word' id='word_1_333' title='bbox 663 2129 716 2156; x_wconf 96'>will</span>
@@ -512,15 +512,15 @@
      <span class='ocrx_word' id='word_1_344' title='bbox 749 2169 829 2203; x_wconf 96'>using</span>
      <span class='ocrx_word' id='word_1_345' title='bbox 839 2169 885 2196; x_wconf 96'>the</span>
      <span class='ocrx_word' id='word_1_346' title='bbox 896 2170 1031 2196; x_wconf 96'>SINGLE</span>
-      <span class='ocrx_word' id='word_1_347' title='bbox 1042 2170 1107 2196; x_wconf 91'>STEP</span>
-      <span class='ocrx_word' id='word_1_348' title='bbox 1109 2169 1220 2196; x_wconf 91'>func-</span>
+      <span class='ocrx_word' id='word_1_347' title='bbox 1042 2170 1131 2196; x_wconf 91'>STEP</span>
+      <span class='ocrx_word' id='word_1_348' title='bbox 1143 2169 1220 2196; x_wconf 91'>func-</span>
     </span>
     <span class='ocr_line' id='line_1_41' title="bbox 345 2207 1228 2242; baseline 0.002 -8; x_size 35; x_descenders 7; x_ascenders 9">
      <span class='ocrx_word' id='word_1_349' title='bbox 345 2207 412 2234; x_wconf 96'>tion.</span>
      <span class='ocrx_word' id='word_1_350' title='bbox 424 2208 461 2235; x_wconf 93'>To</span>
      <span class='ocrx_word' id='word_1_351' title='bbox 472 2208 592 2235; x_wconf 91'>overdub</span>
-      <span class='ocrx_word' id='word_1_352' title='bbox 603 2212 667 2235; x_wconf 96'>notes</span>
-      <span class='ocrx_word' id='word_1_353' title='bbox 668 2212 718 2235; x_wconf 96'>at</span>
+      <span class='ocrx_word' id='word_1_352' title='bbox 603 2212 680 2235; x_wconf 96'>notes</span>
+      <span class='ocrx_word' id='word_1_353' title='bbox 691 2212 718 2235; x_wconf 96'>at</span>
      <span class='ocrx_word' id='word_1_354' title='bbox 729 2208 841 2242; x_wconf 96'>specific</span>
      <span class='ocrx_word' id='word_1_355' title='bbox 851 2209 943 2242; x_wconf 97'>points</span>
      <span class='ocrx_word' id='word_1_356' title='bbox 955 2208 1049 2236; x_wconf 96'>within</span>
@@ -544,10 +544,10 @@
      <span class='ocrx_word' id='word_1_362' title='bbox 1404 1297 1452 1316; x_wconf 96'>use</span>
      <span class='ocrx_word' id='word_1_363' title='bbox 1463 1290 1615 1321; x_wconf 96'>LOCATE,</span>
      <span class='ocrx_word' id='word_1_364' title='bbox 1628 1290 1716 1316; x_wconf 96'>FAST</span>
-      <span class='ocrx_word' id='word_1_365' title='bbox 1726 1289 1910 1316; x_wconf 95'>FORWARD,</span>
-      <span class='ocrx_word' id='word_1_366' title='bbox 1911 1297 1960 1321; x_wconf 96'>or</span>
-      <span class='ocrx_word' id='word_1_367' title='bbox 1972 1290 2098 1316; x_wconf 95'>REWIND</span>
-      <span class='ocrx_word' id='word_1_368' title='bbox 2100 1290 2165 1317; x_wconf 95'>to</span>
+      <span class='ocrx_word' id='word_1_365' title='bbox 1726 1289 1917 1321; x_wconf 95'>FORWARD,</span>
+      <span class='ocrx_word' id='word_1_366' title='bbox 1929 1297 1960 1317; x_wconf 96'>or</span>
+      <span class='ocrx_word' id='word_1_367' title='bbox 1972 1290 2126 1316; x_wconf 95'>REWIND</span>
+      <span class='ocrx_word' id='word_1_368' title='bbox 2136 1294 2165 1317; x_wconf 95'>to</span>
     </span>
     <span class='ocr_line' id='line_1_44' title="bbox 1297 1328 2033 1362; baseline 0.001 -7; x_size 32; x_descenders 5; x_ascenders 8">
      <span class='ocrx_word' id='word_1_369' title='bbox 1297 1328 1356 1355; x_wconf 96'>find</span>
@@ -564,8 +564,8 @@
    <p class='ocr_par' id='par_1_24' lang='eng' title="bbox 1295 1368 2160 1593">
     <span class='ocr_line' id='line_1_45' title="bbox 1332 1368 2160 1402; baseline 0.002 -8; x_size 34; x_descenders 7; x_ascenders 8">
      <span class='ocrx_word' id='word_1_377' title='bbox 1332 1368 1391 1395; x_wconf 93'>The</span>
-      <span class='ocrx_word' id='word_1_378' title='bbox 1402 1368 1626 1395; x_wconf 91'>INSERT/COPY</span>
-      <span class='ocrx_word' id='word_1_379' title='bbox 1626 1368 1789 1395; x_wconf 96'>function</span>
+      <span class='ocrx_word' id='word_1_378' title='bbox 1402 1368 1650 1395; x_wconf 91'>INSERT/COPY</span>
+      <span class='ocrx_word' id='word_1_379' title='bbox 1662 1368 1789 1395; x_wconf 96'>function</span>
      <span class='ocrx_word' id='word_1_380' title='bbox 1800 1368 1893 1395; x_wconf 96'>allows</span>
      <span class='ocrx_word' id='word_1_381' title='bbox 1904 1376 1958 1402; x_wconf 96'>you</span>
      <span class='ocrx_word' id='word_1_382' title='bbox 1968 1373 1997 1395; x_wconf 96'>to</span>
@@ -580,8 +580,8 @@
      <span class='ocrx_word' id='word_1_389' title='bbox 1616 1407 1796 1435; x_wconf 91'>another—in</span>
      <span class='ocrx_word' id='word_1_390' title='bbox 1806 1408 1852 1435; x_wconf 96'>the</span>
      <span class='ocrx_word' id='word_1_391' title='bbox 1863 1416 1937 1435; x_wconf 96'>same</span>
-      <span class='ocrx_word' id='word_1_392' title='bbox 1948 1416 2067 1441; x_wconf 96'>sequence</span>
-      <span class='ocrx_word' id='word_1_393' title='bbox 2068 1416 2125 1435; x_wconf 96'>or</span>
+      <span class='ocrx_word' id='word_1_392' title='bbox 1948 1416 2083 1441; x_wconf 96'>sequence</span>
+      <span class='ocrx_word' id='word_1_393' title='bbox 2093 1416 2125 1435; x_wconf 96'>or</span>
      <span class='ocrx_word' id='word_1_394' title='bbox 2135 1416 2151 1435; x_wconf 96'>a</span>
     </span>
     <span class='ocr_line' id='line_1_47' title="bbox 1296 1447 2160 1481; baseline 0.001 -7; x_size 34; x_descenders 7; x_ascenders 8">
@@ -603,15 +603,15 @@
      <span class='ocrx_word' id='word_1_408' title='bbox 1449 1487 1571 1514; x_wconf 96'>between</span>
      <span class='ocrx_word' id='word_1_409' title='bbox 1582 1487 1628 1514; x_wconf 96'>the</span>
      <span class='ocrx_word' id='word_1_410' title='bbox 1638 1487 1740 1514; x_wconf 96'>second</span>
-      <span class='ocrx_word' id='word_1_411' title='bbox 1751 1487 1838 1514; x_wconf 96'>chorus</span>
-      <span class='ocrx_word' id='word_1_412' title='bbox 1841 1495 1899 1514; x_wconf 96'>and</span>
-      <span class='ocrx_word' id='word_1_413' title='bbox 1901 1487 1975 1514; x_wconf 96'>the</span>
+      <span class='ocrx_word' id='word_1_411' title='bbox 1751 1487 1852 1514; x_wconf 96'>chorus</span>
+      <span class='ocrx_word' id='word_1_412' title='bbox 1863 1487 1919 1514; x_wconf 96'>and</span>
+      <span class='ocrx_word' id='word_1_413' title='bbox 1929 1487 1975 1514; x_wconf 96'>the</span>
      <span class='ocrx_word' id='word_1_414' title='bbox 1985 1487 2087 1521; x_wconf 96'>bridge.</span>
     </span>
     <span class='ocr_line' id='line_1_49' title="bbox 1296 1527 2047 1560; baseline 0.003 -8; x_size 32; x_descenders 6; x_ascenders 7">
      <span class='ocrx_word' id='word_1_415' title='bbox 1296 1527 1441 1553; x_wconf 95'>DELETE</span>
-      <span class='ocrx_word' id='word_1_416' title='bbox 1453 1527 1527 1553; x_wconf 96'>BARS</span>
-      <span class='ocrx_word' id='word_1_417' title='bbox 1529 1527 1681 1559; x_wconf 96'>operates</span>
+      <span class='ocrx_word' id='word_1_416' title='bbox 1453 1527 1546 1553; x_wconf 96'>BARS</span>
+      <span class='ocrx_word' id='word_1_417' title='bbox 1557 1531 1681 1559; x_wconf 96'>operates</span>
      <span class='ocrx_word' id='word_1_418' title='bbox 1691 1527 1737 1553; x_wconf 96'>the</span>
      <span class='ocrx_word' id='word_1_419' title='bbox 1748 1535 1823 1554; x_wconf 96'>same</span>
      <span class='ocrx_word' id='word_1_420' title='bbox 1833 1535 1891 1560; x_wconf 96'>way</span>
@@ -619,8 +619,8 @@
      <span class='ocrx_word' id='word_1_422' title='bbox 1940 1535 2047 1554; x_wconf 96'>remove</span>
     </span>
     <span class='ocr_line' id='line_1_50' title="bbox 1295 1565 1577 1593; baseline 0.004 -1; x_size 34.748871; x_descenders 6.7488689; x_ascenders 9">
-      <span class='ocrx_word' id='word_1_423' title='bbox 1295 1569 1422 1592; x_wconf 96'>unwanted</span>
-      <span class='ocrx_word' id='word_1_424' title='bbox 1423 1565 1577 1593; x_wconf 95'>sections,</span>
+      <span class='ocrx_word' id='word_1_423' title='bbox 1295 1565 1441 1592; x_wconf 96'>unwanted</span>
+      <span class='ocrx_word' id='word_1_424' title='bbox 1452 1565 1577 1593; x_wconf 95'>sections,</span>
     </span>
    </p>
   </div>
@@ -636,12 +636,12 @@
    <p class='ocr_par' id='par_1_26' lang='eng' title="bbox 1295 1690 2215 1960">
     <span class='ocr_line' id='line_1_52' title="bbox 1333 1690 2146 1723; baseline 0 -6; x_size 33; x_descenders 6; x_ascenders 8">
      <span class='ocrx_word' id='word_1_428' title='bbox 1333 1690 1394 1717; x_wconf 96'>One</span>
-      <span class='ocrx_word' id='word_1_429' title='bbox 1404 1698 1446 1717; x_wconf 96'>way</span>
-      <span class='ocrx_word' id='word_1_430' title='bbox 1445 1694 1500 1723; x_wconf 96'>to</span>
+      <span class='ocrx_word' id='word_1_429' title='bbox 1404 1698 1462 1723; x_wconf 96'>way</span>
+      <span class='ocrx_word' id='word_1_430' title='bbox 1472 1694 1500 1717; x_wconf 96'>to</span>
      <span class='ocrx_word' id='word_1_431' title='bbox 1511 1694 1598 1717; x_wconf 96'>create</span>
      <span class='ocrx_word' id='word_1_432' title='bbox 1608 1698 1625 1717; x_wconf 96'>a</span>
-      <span class='ocrx_word' id='word_1_433' title='bbox 1635 1698 1687 1717; x_wconf 95'>song</span>
-      <span class='ocrx_word' id='word_1_434' title='bbox 1688 1690 1736 1723; x_wconf 95'>is</span>
+      <span class='ocrx_word' id='word_1_433' title='bbox 1635 1698 1704 1723; x_wconf 95'>song</span>
+      <span class='ocrx_word' id='word_1_434' title='bbox 1715 1690 1736 1717; x_wconf 95'>is</span>
      <span class='ocrx_word' id='word_1_435' title='bbox 1747 1694 1776 1717; x_wconf 96'>to</span>
      <span class='ocrx_word' id='word_1_436' title='bbox 1787 1690 1880 1717; x_wconf 96'>record</span>
      <span class='ocrx_word' id='word_1_437' title='bbox 1891 1690 1958 1717; x_wconf 96'>each</span>
@@ -657,8 +657,8 @@
      <span class='ocrx_word' id='word_1_445' title='bbox 1592 1730 1644 1756; x_wconf 96'>999</span>
      <span class='ocrx_word' id='word_1_446' title='bbox 1654 1729 1738 1762; x_wconf 96'>bars).</span>
      <span class='ocrx_word' id='word_1_447' title='bbox 1751 1729 1878 1757; x_wconf 96'>Another</span>
-      <span class='ocrx_word' id='word_1_448' title='bbox 1888 1737 1930 1757; x_wconf 96'>way</span>
-      <span class='ocrx_word' id='word_1_449' title='bbox 1929 1729 1977 1762; x_wconf 96'>is</span>
+      <span class='ocrx_word' id='word_1_448' title='bbox 1888 1737 1945 1762; x_wconf 96'>way</span>
+      <span class='ocrx_word' id='word_1_449' title='bbox 1956 1729 1977 1757; x_wconf 96'>is</span>
      <span class='ocrx_word' id='word_1_450' title='bbox 1987 1733 2016 1757; x_wconf 96'>to</span>
      <span class='ocrx_word' id='word_1_451' title='bbox 2027 1729 2121 1757; x_wconf 96'>record</span>
     </span>
@@ -667,8 +667,8 @@
      <span class='ocrx_word' id='word_1_453' title='bbox 1373 1768 1448 1796; x_wconf 96'>basic</span>
      <span class='ocrx_word' id='word_1_454' title='bbox 1458 1768 1562 1796; x_wconf 96'>section</span>
      <span class='ocrx_word' id='word_1_455' title='bbox 1574 1769 1666 1802; x_wconf 96'>(verse,</span>
-      <span class='ocrx_word' id='word_1_456' title='bbox 1679 1769 1779 1796; x_wconf 96'>chorus,</span>
-      <span class='ocrx_word' id='word_1_457' title='bbox 1782 1769 1865 1802; x_wconf 96'>etc.)</span>
+      <span class='ocrx_word' id='word_1_456' title='bbox 1679 1769 1788 1801; x_wconf 96'>chorus,</span>
+      <span class='ocrx_word' id='word_1_457' title='bbox 1800 1769 1865 1802; x_wconf 96'>etc.)</span>
      <span class='ocrx_word' id='word_1_458' title='bbox 1876 1768 1904 1795; x_wconf 96'>in</span>
      <span class='ocrx_word' id='word_1_459' title='bbox 1914 1768 2066 1796; x_wconf 96'>individual</span>
     </span>
@@ -678,8 +678,8 @@
      <span class='ocrx_word' id='word_1_462' title='bbox 1538 1816 1587 1835; x_wconf 96'>use</span>
      <span class='ocrx_word' id='word_1_463' title='bbox 1597 1808 1643 1835; x_wconf 96'>the</span>
      <span class='ocrx_word' id='word_1_464' title='bbox 1653 1809 1799 1835; x_wconf 96'>CREATE</span>
-      <span class='ocrx_word' id='word_1_465' title='bbox 1810 1808 1883 1835; x_wconf 96'>SONG</span>
-      <span class='ocrx_word' id='word_1_466' title='bbox 1885 1808 2050 1836; x_wconf 96'>function</span>
+      <span class='ocrx_word' id='word_1_465' title='bbox 1810 1808 1911 1835; x_wconf 96'>SONG</span>
+      <span class='ocrx_word' id='word_1_466' title='bbox 1923 1808 2050 1836; x_wconf 96'>function</span>
      <span class='ocrx_word' id='word_1_467' title='bbox 2060 1812 2089 1835; x_wconf 96'>to</span>
      <span class='ocrx_word' id='word_1_468' title='bbox 2103 1808 2215 1836; x_wconf 93'>“chain”</span>
     </span>
@@ -687,14 +687,14 @@
      <span class='ocrx_word' id='word_1_469' title='bbox 1295 1848 1370 1874; x_wconf 96'>them</span>
      <span class='ocrx_word' id='word_1_470' title='bbox 1381 1848 1508 1881; x_wconf 95'>together.</span>
      <span class='ocrx_word' id='word_1_471' title='bbox 1521 1848 1667 1875; x_wconf 96'>CREATE</span>
-      <span class='ocrx_word' id='word_1_472' title='bbox 1678 1848 1751 1875; x_wconf 96'>SONG</span>
-      <span class='ocrx_word' id='word_1_473' title='bbox 1753 1847 1842 1874; x_wconf 96'>will</span>
+      <span class='ocrx_word' id='word_1_472' title='bbox 1678 1848 1779 1875; x_wconf 96'>SONG</span>
+      <span class='ocrx_word' id='word_1_473' title='bbox 1789 1847 1842 1874; x_wconf 96'>will</span>
      <span class='ocrx_word' id='word_1_474' title='bbox 1853 1848 1918 1875; x_wconf 96'>then</span>
      <span class='ocrx_word' id='word_1_475' title='bbox 1929 1848 2135 1881; x_wconf 96'>automatically</span>
     </span>
     <span class='ocr_line' id='line_1_57' title="bbox 1296 1887 2162 1920; baseline 0 -6; x_size 33; x_descenders 6; x_ascenders 8">
-      <span class='ocrx_word' id='word_1_476' title='bbox 1296 1895 1349 1920; x_wconf 96'>copy</span>
-      <span class='ocrx_word' id='word_1_477' title='bbox 1349 1887 1412 1920; x_wconf 96'>all</span>
+      <span class='ocrx_word' id='word_1_476' title='bbox 1296 1895 1366 1920; x_wconf 96'>copy</span>
+      <span class='ocrx_word' id='word_1_477' title='bbox 1377 1887 1412 1914; x_wconf 96'>all</span>
      <span class='ocrx_word' id='word_1_478' title='bbox 1422 1887 1468 1914; x_wconf 96'>the</span>
      <span class='ocrx_word' id='word_1_479' title='bbox 1478 1891 1552 1920; x_wconf 96'>parts</span>
      <span class='ocrx_word' id='word_1_480' title='bbox 1563 1887 1621 1914; x_wconf 95'>into</span>
@@ -714,8 +714,8 @@
      <span class='ocrx_word' id='word_1_492' title='bbox 1540 1926 1590 1953; x_wconf 96'>few</span>
      <span class='ocrx_word' id='word_1_493' title='bbox 1601 1927 1664 1953; x_wconf 96'>bars</span>
      <span class='ocrx_word' id='word_1_494' title='bbox 1675 1931 1704 1954; x_wconf 96'>to</span>
-      <span class='ocrx_word' id='word_1_495' title='bbox 1715 1935 1795 1960; x_wconf 96'>repeat</span>
-      <span class='ocrx_word' id='word_1_496' title='bbox 1795 1926 1955 1960; x_wconf 96'>infinitely,</span>
+      <span class='ocrx_word' id='word_1_495' title='bbox 1715 1931 1806 1960; x_wconf 96'>repeat</span>
+      <span class='ocrx_word' id='word_1_496' title='bbox 1816 1926 1955 1960; x_wconf 96'>infinitely,</span>
      <span class='ocrx_word' id='word_1_497' title='bbox 1968 1926 2011 1954; x_wconf 95'>for</span>
      <span class='ocrx_word' id='word_1_498' title='bbox 2022 1935 2038 1954; x_wconf 93'>a</span>
      <span class='ocrx_word' id='word_1_499' title='bbox 2049 1927 2169 1954; x_wconf 92'>fadeout.</span>
@@ -757,8 +757,8 @@
     </span>
     <span class='ocr_line' id='line_1_62' title="bbox 1293 2130 2156 2164; baseline 0 -7; x_size 34; x_descenders 7; x_ascenders 8">
      <span class='ocrx_word' id='word_1_522' title='bbox 1293 2130 1339 2157; x_wconf 93'>the</span>
-      <span class='ocrx_word' id='word_1_523' title='bbox 1350 2130 1562 2164; x_wconf 90'>LinnSequencer</span>
-      <span class='ocrx_word' id='word_1_524' title='bbox 1564 2130 1607 2157; x_wconf 97'>is</span>
+      <span class='ocrx_word' id='word_1_523' title='bbox 1350 2130 1576 2164; x_wconf 90'>LinnSequencer</span>
+      <span class='ocrx_word' id='word_1_524' title='bbox 1586 2130 1607 2157; x_wconf 97'>is</span>
      <span class='ocrx_word' id='word_1_525' title='bbox 1619 2130 1747 2164; x_wconf 96'>designed</span>
      <span class='ocrx_word' id='word_1_526' title='bbox 1758 2134 1787 2157; x_wconf 96'>to</span>
      <span class='ocrx_word' id='word_1_527' title='bbox 1798 2130 1834 2157; x_wconf 96'>let</span>
@@ -767,8 +767,8 @@
      <span class='ocrx_word' id='word_1_530' title='bbox 2063 2130 2156 2157; x_wconf 96'>record</span>
     </span>
     <span class='ocr_line' id='line_1_63' title="bbox 1294 2169 2145 2203; baseline 0 -6; x_size 33; x_descenders 6; x_ascenders 8">
-      <span class='ocrx_word' id='word_1_531' title='bbox 1294 2178 1330 2197; x_wconf 96'>and</span>
-      <span class='ocrx_word' id='word_1_532' title='bbox 1331 2169 1414 2197; x_wconf 96'>edit</span>
+      <span class='ocrx_word' id='word_1_531' title='bbox 1294 2170 1349 2197; x_wconf 96'>and</span>
+      <span class='ocrx_word' id='word_1_532' title='bbox 1360 2169 1414 2197; x_wconf 96'>edit</span>
      <span class='ocrx_word' id='word_1_533' title='bbox 1425 2170 1503 2197; x_wconf 96'>while</span>
      <span class='ocrx_word' id='word_1_534' title='bbox 1514 2170 1643 2203; x_wconf 96'>devoting</span>
      <span class='ocrx_word' id='word_1_535' title='bbox 1653 2178 1721 2203; x_wconf 96'>your</span>
@@ -792,7 +792,7 @@
   </div>
   <div class='ocr_carea' id='block_1_21' title="bbox 347 2343 2171 2378">
    <p class='ocr_par' id='par_1_29' lang='eng' title="bbox 347 2343 2171 2378">
-     <span class='ocr_line' id='line_1_65' title="bbox 347 2343 2171 2378; baseline 0.001 -8; x_size 34; x_descenders 7; x_ascenders 8">
+     <span class='ocr_header' id='line_1_65' title="bbox 347 2343 2171 2378; baseline 0.001 -8; x_size 34; x_descenders 7; x_ascenders 8">
      <span class='ocrx_word' id='word_1_549' title='bbox 347 2350 361 2363; x_wconf 58'>*</span>
      <span class='ocrx_word' id='word_1_550' title='bbox 373 2343 483 2377; x_wconf 96'>Simple,</span>
      <span class='ocrx_word' id='word_1_551' title='bbox 495 2352 559 2377; x_wconf 96'>easy</span>
@@ -806,8 +806,8 @@
      <span class='ocrx_word' id='word_1_559' title='bbox 1326 2345 1424 2378; x_wconf 97'>clearly</span>
      <span class='ocrx_word' id='word_1_560' title='bbox 1434 2345 1528 2378; x_wconf 96'>guides</span>
      <span class='ocrx_word' id='word_1_561' title='bbox 1539 2353 1594 2378; x_wconf 97'>you</span>
-      <span class='ocrx_word' id='word_1_562' title='bbox 1604 2345 1705 2378; x_wconf 96'>through</span>
-      <span class='ocrx_word' id='word_1_563' title='bbox 1706 2344 1770 2371; x_wconf 96'>all</span>
+      <span class='ocrx_word' id='word_1_562' title='bbox 1604 2345 1724 2378; x_wconf 96'>through</span>
+      <span class='ocrx_word' id='word_1_563' title='bbox 1735 2344 1770 2371; x_wconf 96'>all</span>
      <span class='ocrx_word' id='word_1_564' title='bbox 1781 2344 1947 2377; x_wconf 96'>operations.</span>
      <span class='ocrx_word' id='word_1_565' title='bbox 1961 2344 1989 2371; x_wconf 96'>If</span>
      <span class='ocrx_word' id='word_1_566' title='bbox 1997 2344 2112 2376; x_wconf 96'>needed,</span>
@@ -818,8 +818,8 @@
   <div class='ocr_carea' id='block_1_22' title="bbox 373 2381 1083 2415">
    <p class='ocr_par' id='par_1_30' lang='eng' title="bbox 373 2381 1083 2415">
     <span class='ocr_line' id='line_1_66' title="bbox 373 2381 1083 2415; baseline 0.003 -8; x_size 34; x_descenders 7; x_ascenders 8">
-      <span class='ocrx_word' id='word_1_568' title='bbox 373 2381 448 2407; x_wconf 96'>HELP</span>
-      <span class='ocrx_word' id='word_1_569' title='bbox 450 2381 583 2408; x_wconf 96'>button</span>
+      <span class='ocrx_word' id='word_1_568' title='bbox 373 2381 472 2407; x_wconf 96'>HELP</span>
+      <span class='ocrx_word' id='word_1_569' title='bbox 483 2381 583 2408; x_wconf 96'>button</span>
      <span class='ocrx_word' id='word_1_570' title='bbox 594 2381 711 2415; x_wconf 96'>displays</span>
      <span class='ocrx_word' id='word_1_571' title='bbox 722 2382 875 2409; x_wconf 96'>additional</span>
      <span class='ocrx_word' id='word_1_572' title='bbox 886 2382 1083 2415; x_wconf 96'>explanations.</span>
@@ -828,7 +828,7 @@
   </div>
   <div class='ocr_carea' id='block_1_23' title="bbox 347 2427 2145 2507">
    <p class='ocr_par' id='par_1_31' lang='eng' title="bbox 347 2427 2145 2507">
-     <span class='ocr_line' id='line_1_67' title="bbox 347 2427 1468 2461; baseline 0.002 -8; x_size 34; x_descenders 7; x_ascenders 8">
+     <span class='ocr_header' id='line_1_67' title="bbox 347 2427 1468 2461; baseline 0.002 -8; x_size 34; x_descenders 7; x_ascenders 8">
      <span class='ocrx_word' id='word_1_573' title='bbox 347 2432 361 2446; x_wconf 70'>*</span>
      <span class='ocrx_word' id='word_1_574' title='bbox 373 2427 612 2454; x_wconf 91'>Non-destructive</span>
      <span class='ocrx_word' id='word_1_575' title='bbox 622 2427 914 2461; x_wconf 89'>recording—existing</span>
@@ -839,14 +839,14 @@
      <span class='ocrx_word' id='word_1_580' title='bbox 1231 2428 1309 2455; x_wconf 96'>while</span>
      <span class='ocrx_word' id='word_1_581' title='bbox 1319 2428 1468 2461; x_wconf 92'>recording.</span>
     </span>
-     <span class='ocr_line' id='line_1_68' title="bbox 347 2473 2145 2507; baseline 0.001 -8; x_size 35; x_descenders 7; x_ascenders 9">
+     <span class='ocr_header' id='line_1_68' title="bbox 347 2473 2145 2507; baseline 0.001 -8; x_size 35; x_descenders 7; x_ascenders 9">
      <span class='ocrx_word' id='word_1_582' title='bbox 347 2478 361 2492; x_wconf 70'>¢</span>
      <span class='ocrx_word' id='word_1_583' title='bbox 372 2473 433 2500; x_wconf 93'>Two</span>
      <span class='ocrx_word' id='word_1_584' title='bbox 444 2473 689 2500; x_wconf 90'>FOOTSWITCH</span>
-      <span class='ocrx_word' id='word_1_585' title='bbox 701 2474 818 2500; x_wconf 95'>INPUTS</span>
-      <span class='ocrx_word' id='word_1_586' title='bbox 819 2474 894 2501; x_wconf 96'>may</span>
-      <span class='ocrx_word' id='word_1_587' title='bbox 893 2473 939 2507; x_wconf 96'>be</span>
-      <span class='ocrx_word' id='word_1_588' title='bbox 941 2473 1091 2507; x_wconf 96'>assigned</span>
+      <span class='ocrx_word' id='word_1_585' title='bbox 701 2474 837 2501; x_wconf 95'>INPUTS</span>
+      <span class='ocrx_word' id='word_1_586' title='bbox 848 2481 910 2507; x_wconf 96'>may</span>
+      <span class='ocrx_word' id='word_1_587' title='bbox 921 2473 955 2500; x_wconf 96'>be</span>
+      <span class='ocrx_word' id='word_1_588' title='bbox 966 2473 1091 2507; x_wconf 96'>assigned</span>
      <span class='ocrx_word' id='word_1_589' title='bbox 1101 2478 1130 2501; x_wconf 96'>to</span>
      <span class='ocrx_word' id='word_1_590' title='bbox 1141 2474 1271 2507; x_wconf 96'>remotely</span>
      <span class='ocrx_word' id='word_1_591' title='bbox 1281 2473 1387 2501; x_wconf 96'>control</span>
@@ -873,12 +873,12 @@
   </div>
   <div class='ocr_carea' id='block_1_25' title="bbox 347 2556 1768 2590">
    <p class='ocr_par' id='par_1_33' lang='eng' title="bbox 347 2556 1768 2590">
-     <span class='ocr_line' id='line_1_70' title="bbox 347 2556 1768 2590; baseline 0.001 -8; x_size 34; x_descenders 7; x_ascenders 8">
+     <span class='ocr_header' id='line_1_70' title="bbox 347 2556 1768 2590; baseline 0.001 -8; x_size 34; x_descenders 7; x_ascenders 8">
      <span class='ocrx_word' id='word_1_604' title='bbox 347 2561 361 2575; x_wconf 86'>¢</span>
      <span class='ocrx_word' id='word_1_605' title='bbox 372 2556 433 2583; x_wconf 85'>Iwo</span>
      <span class='ocrx_word' id='word_1_606' title='bbox 443 2556 612 2583; x_wconf 96'>TRIGGER</span>
-      <span class='ocrx_word' id='word_1_607' title='bbox 623 2556 778 2584; x_wconf 96'>OUTPUTS</span>
-      <span class='ocrx_word' id='word_1_608' title='bbox 780 2557 871 2590; x_wconf 96'>may</span>
+      <span class='ocrx_word' id='word_1_607' title='bbox 623 2556 797 2584; x_wconf 96'>OUTPUTS</span>
+      <span class='ocrx_word' id='word_1_608' title='bbox 808 2565 871 2590; x_wconf 96'>may</span>
      <span class='ocrx_word' id='word_1_609' title='bbox 881 2557 915 2584; x_wconf 96'>be</span>
      <span class='ocrx_word' id='word_1_610' title='bbox 925 2557 1119 2590; x_wconf 96'>programmed</span>
      <span class='ocrx_word' id='word_1_611' title='bbox 1129 2561 1158 2584; x_wconf 96'>to</span>
@@ -904,14 +904,14 @@
      <span class='ocrx_word' id='word_1_625' title='bbox 875 2610 907 2629; x_wconf 96'>or</span>
      <span class='ocrx_word' id='word_1_626' title='bbox 918 2602 989 2629; x_wconf 96'>Linn</span>
      <span class='ocrx_word' id='word_1_627' title='bbox 1000 2603 1069 2629; x_wconf 95'>9000</span>
-      <span class='ocrx_word' id='word_1_628' title='bbox 1080 2610 1129 2635; x_wconf 96'>sync</span>
-      <span class='ocrx_word' id='word_1_629' title='bbox 1131 2607 1226 2630; x_wconf 96'>tone.</span>
+      <span class='ocrx_word' id='word_1_628' title='bbox 1080 2610 1145 2635; x_wconf 96'>sync</span>
+      <span class='ocrx_word' id='word_1_629' title='bbox 1155 2607 1226 2630; x_wconf 96'>tone.</span>
     </span>
    </p>
   </div>
   <div class='ocr_carea' id='block_1_27' title="bbox 347 2648 2100 2727">
    <p class='ocr_par' id='par_1_35' lang='eng' title="bbox 347 2648 2100 2727">
-     <span class='ocr_line' id='line_1_72' title="bbox 347 2648 1664 2682; baseline 0.001 -7; x_size 33; x_descenders 6; x_ascenders 8">
+     <span class='ocr_header' id='line_1_72' title="bbox 347 2648 1664 2682; baseline 0.001 -7; x_size 33; x_descenders 6; x_ascenders 8">
      <span class='ocrx_word' id='word_1_630' title='bbox 347 2654 360 2667; x_wconf 45'>©</span>
      <span class='ocrx_word' id='word_1_631' title='bbox 372 2648 483 2675; x_wconf 95'>Utilizes</span>
      <span class='ocrx_word' id='word_1_632' title='bbox 493 2648 564 2680; x_wconf 96'>ultra</span>
@@ -927,17 +927,17 @@
      <span class='ocrx_word' id='word_1_642' title='bbox 1414 2649 1502 2676; x_wconf 96'>FAST</span>
      <span class='ocrx_word' id='word_1_643' title='bbox 1512 2648 1664 2682; x_wconf 96'>operation.</span>
     </span>
-     <span class='ocr_line' id='line_1_73' title="bbox 347 2694 2100 2727; baseline 0.001 -7; x_size 33; x_descenders 6; x_ascenders 8">
+     <span class='ocr_header' id='line_1_73' title="bbox 347 2694 2100 2727; baseline 0.001 -7; x_size 33; x_descenders 6; x_ascenders 8">
      <span class='ocrx_word' id='word_1_644' title='bbox 347 2699 361 2713; x_wconf 31'>*</span>
-      <span class='ocrx_word' id='word_1_645' title='bbox 372 2694 476 2720; x_wconf 96'>TEMPO</span>
-      <span class='ocrx_word' id='word_1_646' title='bbox 478 2694 562 2721; x_wconf 96'>may</span>
-      <span class='ocrx_word' id='word_1_647' title='bbox 561 2694 606 2727; x_wconf 95'>be</span>
-      <span class='ocrx_word' id='word_1_648' title='bbox 608 2694 764 2727; x_wconf 95'>specified</span>
+      <span class='ocrx_word' id='word_1_645' title='bbox 372 2694 504 2721; x_wconf 96'>TEMPO</span>
+      <span class='ocrx_word' id='word_1_646' title='bbox 515 2702 578 2727; x_wconf 96'>may</span>
+      <span class='ocrx_word' id='word_1_647' title='bbox 589 2694 623 2721; x_wconf 95'>be</span>
+      <span class='ocrx_word' id='word_1_648' title='bbox 633 2694 764 2727; x_wconf 95'>specified</span>
      <span class='ocrx_word' id='word_1_649' title='bbox 774 2694 802 2721; x_wconf 93'>in</span>
      <span class='ocrx_word' id='word_1_650' title='bbox 814 2695 1172 2722; x_wconf 91'>BEATS-PER-MINUTE</span>
      <span class='ocrx_word' id='word_1_651' title='bbox 1183 2703 1215 2722; x_wconf 93'>or</span>
-      <span class='ocrx_word' id='word_1_652' title='bbox 1225 2695 1547 2722; x_wconf 91'>FRAMES-PER-BEAT</span>
-      <span class='ocrx_word' id='word_1_653' title='bbox 1543 2695 1605 2721; x_wconf 96'>at</span>
+      <span class='ocrx_word' id='word_1_652' title='bbox 1225 2695 1567 2722; x_wconf 91'>FRAMES-PER-BEAT</span>
+      <span class='ocrx_word' id='word_1_653' title='bbox 1577 2698 1605 2721; x_wconf 96'>at</span>
      <span class='ocrx_word' id='word_1_654' title='bbox 1616 2695 1659 2726; x_wconf 96'>24,</span>
      <span class='ocrx_word' id='word_1_655' title='bbox 1672 2695 1716 2726; x_wconf 96'>25,</span>
      <span class='ocrx_word' id='word_1_656' title='bbox 1728 2702 1760 2721; x_wconf 96'>or</span>
@@ -959,11 +959,11 @@
   </div>
   <div class='ocr_carea' id='block_1_29' title="bbox 347 2777 2174 2811">
    <p class='ocr_par' id='par_1_37' lang='eng' title="bbox 347 2777 2174 2811">
-     <span class='ocr_line' id='line_1_75' title="bbox 347 2777 2174 2811; baseline 0.001 -8; x_size 33; x_descenders 5; x_ascenders 9">
+     <span class='ocr_header' id='line_1_75' title="bbox 347 2777 2174 2811; baseline 0.001 -8; x_size 33; x_descenders 5; x_ascenders 9">
      <span class='ocrx_word' id='word_1_664' title='bbox 347 2782 360 2796; x_wconf 81'>¢</span>
-      <span class='ocrx_word' id='word_1_665' title='bbox 372 2777 476 2803; x_wconf 94'>TEMPO</span>
-      <span class='ocrx_word' id='word_1_666' title='bbox 478 2777 562 2804; x_wconf 96'>may</span>
-      <span class='ocrx_word' id='word_1_667' title='bbox 561 2777 622 2810; x_wconf 96'>be</span>
+      <span class='ocrx_word' id='word_1_665' title='bbox 372 2777 504 2804; x_wconf 94'>TEMPO</span>
+      <span class='ocrx_word' id='word_1_666' title='bbox 515 2785 578 2810; x_wconf 96'>may</span>
+      <span class='ocrx_word' id='word_1_667' title='bbox 588 2777 622 2804; x_wconf 96'>be</span>
      <span class='ocrx_word' id='word_1_668' title='bbox 633 2778 741 2804; x_wconf 95'>entered</span>
      <span class='ocrx_word' id='word_1_669' title='bbox 751 2777 934 2811; x_wconf 96'>numerically,</span>
      <span class='ocrx_word' id='word_1_670' title='bbox 946 2777 1101 2811; x_wconf 95'>adjustable</span>
@@ -987,36 +987,36 @@
      <span class='ocrx_word' id='word_1_682' title='bbox 372 2822 410 2841; x_wconf 96'>on</span>
      <span class='ocrx_word' id='word_1_683' title='bbox 420 2815 466 2842; x_wconf 95'>the</span>
      <span class='ocrx_word' id='word_1_684' title='bbox 476 2815 545 2841; x_wconf 95'>TAP</span>
-      <span class='ocrx_word' id='word_1_685' title='bbox 556 2816 660 2842; x_wconf 95'>TEMPO</span>
-      <span class='ocrx_word' id='word_1_686' title='bbox 662 2815 808 2842; x_wconf 96'>button.</span>
+      <span class='ocrx_word' id='word_1_685' title='bbox 556 2815 689 2842; x_wconf 95'>TEMPO</span>
+      <span class='ocrx_word' id='word_1_686' title='bbox 699 2815 808 2842; x_wconf 96'>button.</span>
     </span>
    </p>
   </div>
   <div class='ocr_carea' id='block_1_31' title="bbox 347 2861 1792 2940">
    <p class='ocr_par' id='par_1_39' lang='eng' title="bbox 347 2861 1792 2940">
-     <span class='ocr_line' id='line_1_77' title="bbox 347 2861 1792 2895; baseline 0.001 -8; x_size 33; x_descenders 6; x_ascenders 8">
+     <span class='ocr_header' id='line_1_77' title="bbox 347 2861 1792 2895; baseline 0.001 -8; x_size 33; x_descenders 6; x_ascenders 8">
      <span class='ocrx_word' id='word_1_687' title='bbox 347 2866 360 2880; x_wconf 43'>¢</span>
      <span class='ocrx_word' id='word_1_688' title='bbox 372 2861 504 2887; x_wconf 96'>TEMPO</span>
-      <span class='ocrx_word' id='word_1_689' title='bbox 515 2861 677 2888; x_wconf 96'>CHANGES</span>
-      <span class='ocrx_word' id='word_1_690' title='bbox 679 2861 771 2894; x_wconf 96'>may</span>
+      <span class='ocrx_word' id='word_1_689' title='bbox 515 2861 696 2888; x_wconf 96'>CHANGES</span>
+      <span class='ocrx_word' id='word_1_690' title='bbox 707 2869 771 2894; x_wconf 96'>may</span>
      <span class='ocrx_word' id='word_1_691' title='bbox 781 2861 815 2888; x_wconf 96'>be</span>
-      <span class='ocrx_word' id='word_1_692' title='bbox 825 2869 1000 2894; x_wconf 96'>programmed</span>
-      <span class='ocrx_word' id='word_1_693' title='bbox 1001 2861 1087 2888; x_wconf 96'>into</span>
+      <span class='ocrx_word' id='word_1_692' title='bbox 825 2861 1019 2894; x_wconf 96'>programmed</span>
+      <span class='ocrx_word' id='word_1_693' title='bbox 1030 2861 1087 2888; x_wconf 96'>into</span>
      <span class='ocrx_word' id='word_1_694' title='bbox 1099 2869 1115 2888; x_wconf 95'>a</span>
      <span class='ocrx_word' id='word_1_695' title='bbox 1126 2870 1268 2895; x_wconf 96'>sequence,</span>
      <span class='ocrx_word' id='word_1_696' title='bbox 1280 2861 1344 2888; x_wconf 96'>with</span>
-      <span class='ocrx_word' id='word_1_697' title='bbox 1356 2866 1448 2888; x_wconf 95'>smooth</span>
-      <span class='ocrx_word' id='word_1_698' title='bbox 1450 2861 1635 2888; x_wconf 96'>transitions</span>
+      <span class='ocrx_word' id='word_1_697' title='bbox 1356 2862 1467 2888; x_wconf 95'>smooth</span>
+      <span class='ocrx_word' id='word_1_698' title='bbox 1478 2861 1635 2888; x_wconf 96'>transitions</span>
      <span class='ocrx_word' id='word_1_699' title='bbox 1646 2861 1670 2887; x_wconf 96'>if</span>
      <span class='ocrx_word' id='word_1_700' title='bbox 1679 2861 1792 2888; x_wconf 87'>desired.</span>
     </span>
-     <span class='ocr_line' id='line_1_78' title="bbox 347 2906 1507 2940; baseline 0.002 -8; x_size 33; x_descenders 7; x_ascenders 8">
+     <span class='ocr_header' id='line_1_78' title="bbox 347 2906 1507 2940; baseline 0.002 -8; x_size 33; x_descenders 7; x_ascenders 8">
      <span class='ocrx_word' id='word_1_701' title='bbox 347 2911 360 2925; x_wconf 69'>¢</span>
      <span class='ocrx_word' id='word_1_702' title='bbox 371 2906 434 2938; x_wconf 96'>Any</span>
      <span class='ocrx_word' id='word_1_703' title='bbox 444 2906 539 2932; x_wconf 96'>TIME</span>
-      <span class='ocrx_word' id='word_1_704' title='bbox 550 2906 739 2933; x_wconf 96'>SIGNATURE</span>
-      <span class='ocrx_word' id='word_1_705' title='bbox 740 2907 820 2933; x_wconf 96'>may</span>
-      <span class='ocrx_word' id='word_1_706' title='bbox 819 2907 880 2939; x_wconf 96'>be</span>
+      <span class='ocrx_word' id='word_1_704' title='bbox 550 2906 763 2933; x_wconf 96'>SIGNATURE</span>
+      <span class='ocrx_word' id='word_1_705' title='bbox 773 2915 836 2939; x_wconf 96'>may</span>
+      <span class='ocrx_word' id='word_1_706' title='bbox 846 2907 880 2933; x_wconf 96'>be</span>
      <span class='ocrx_word' id='word_1_707' title='bbox 891 2907 968 2938; x_wconf 96'>used,</span>
      <span class='ocrx_word' id='word_1_708' title='bbox 980 2907 1036 2934; x_wconf 96'>and</span>
      <span class='ocrx_word' id='word_1_709' title='bbox 1046 2915 1109 2940; x_wconf 96'>may</span>
@@ -1 +1 @@
-Tesseract Open Source OCR Engine v4.0.0 with Leptonica
+Tesseract Open Source OCR Engine v4.1.1 with Leptonica
@@ -1 +1 @@
-Tesseract Open Source OCR Engine v4.0.0 with Leptonica
+Tesseract Open Source OCR Engine v4.1.1 with Leptonica
@@ -1 +1 @@
-Tesseract Open Source OCR Engine v4.0.0 with Leptonica
+Tesseract Open Source OCR Engine v4.1.1 with Leptonica
@@ -103,7 +103,7 @@ ERASE, REPEAT, PLAY/STOP, or LOCATE.

 © Will sync to standard LinnDrum or Linn 9000 sync tone.

-© Utilizes ultra high-speed, 8 MHz 80186 16 bit computer internally for FAST operation.
+® Utilizes ultra high-speed, 8 MHz 80186 16 bit computer internally for FAST operation.
 * TEMPO may be specified in BEATS-PER-MINUTE or FRAMES-PER-BEAT at 24, 25, or 30 frames per second,

 (even drop frame!)
@@ -115,9 +115,9 @@ on the TAP TEMPO button.
 ¢ TEMPO CHANGES may be programmed into a sequence, with smooth transitions if desired.
 ¢ Any TIME SIGNATURE may be used, and may be changed within a song.

-linn
-Linn Electronics, Inc.
+nn

+Linn Electronics, Inc.
 18720 Oxnard Street, Tarzana, CA 91356
 (818) 708-8131 TELEX #298949 LINN UR

@@ -1 +1 @@
-Tesseract Open Source OCR Engine v4.0.0 with Leptonica
+Tesseract Open Source OCR Engine v4.1.1 with Leptonica
@@ -1 +1 @@
-Tesseract Open Source OCR Engine v4.0.0 with Leptonica
+Tesseract Open Source OCR Engine v4.1.1 with Leptonica
@@ -1,123 +1,128 @@
-The LinnSequencer
-32 Track MIDI Sequence Recorder
+2A NNI‘I 6F6867# XATALL IE18-80L (818)

-The LinnSequencer is a state-of-the-art composition and performance tool for the professional musician. It is
+9SEI6 VO “BUBZIRY, “J0aNS PIPUXO OZLEI
+“Uy ‘soTUOMOI,q UUrT

-extremely powerful, yet amazingly simple to learn and use. It’s many remarkable features include:
+uut]

-¢ Operation is similar to multi-track tape recorder with PLAY, STOP, RECORD, FAST
-FORWARD, REWIND, and LOCATE controls.
+“‘SUOS B UIJIM pasueyo oq ABU pue ‘posn oq AWW AYN IVNOIS AWLL AUV
+“parlsop Jr SUOTIISUBI} YIOOUIS YIM “BoueNbas eB OJUI pourtueIZOId 9q ABU SFONWHO OdINAL e

-e Each of the 100 sequences contains 32 simultaneous, polyphonic tracks. Each track may
-be assigned to one of 16 MIDI channels. Simultaneously plays up to 16 polyphonic
+‘uonng OdNAL dV L 9) uO

-synthesizers!
+sojou Jayienb Suiddy} Aq 10 ‘syUSTIOIOUI oINUTIAI-J8g-Jesg & JO sys} UL ofquisn(pe ‘ATTeouIAUINU paiajus oq ABU OdINALL e

-¢ Ultra-fast 3%” disk drive stores complex songs in seconds and holds over 110,000 notes
+(jouer doup u3a9)

-per disk!
+“puooes Jed souely O€ 10 “SZ “pz 18 [LVAG-MAd-SHN VU 10 ALOANIWAAd-SLVAd U! patyoeds aq kewl OAL «
+‘uoTe1odo [SVx JO} Aj[eusoyUT JoyndUIOd 11g 9] 98108 ZHI 8g ‘poeds-ysry Bann soz] e

-¢ One or all tracks may be TRANSPOSED at the touch of a key.
-e Exclusive real-time ERASE function makes editing FAST.
-* Exclusive REPEAT function automatically repeats any held notes at a pre-selected
+"9U0} DUAS 0006 UUL] Jo wNIqUUr] prepue}s 0} OUAS [ITAA ©

-rhythmic value.
+“ONYBA 9}OU poloapes Aue Je sas—nd jndyno 07 pewureigold 3q ACW SL Ad LNO YADONAL OML

-¢ TIMING CORRECTION works during playback and operates without ‘chopping’ notes.
+"ALVOOT 10 GOLS/AV 1d ‘LWddad “ASV

-¢ Optional SMPTE time code synchronization.
+SUIpNpoUr ‘suOTIOUN] posn A[UOUILUOS 94] JO AUBUT [O1]UOD AJ9]OWIAI 0} PousIsse oq ACUI ST AdNI HOLIMSLOO OME «
+“SUIPIONAI I[IYM P2sesd JOU Iv $3}OU BUTISIXO—ZUIPIOIA SATON.ASOP-UON

-© Optional remote control.
+‘suoneurldxa peuoyippe sdeydsip uowng g1TqH

-Recording a Sequence
+oy] ‘pepsau JI ‘suoneiodo [ye yYsnosy] NOA sapins ApIespo Avfdsip QO] Joey Z7¢ 9y3—uoeIodo Urea] 0} Ased ‘aus «

-To record a sequence, simply press RECORD and PLAY,
-then play your MIDI keyboard in time to the Sequencer’s
-click track. When the sequence loops back around to bar 1,
-you’ ll hear what you played—only all timing errors will be
+jUorel]suowtap & IO} Aepol Jayeap uur’] INOA dag ‘dISHUL
+INOA 0} UONUS}]¥ PaplAIPUN INOA SUTJOASp ITY ps pue
+p1osai ‘asoduod no Jay 0} pausisap st 1s0uenbesuur’] oy)
+Aum Aposiooid $,Jeu], ‘SS9d0Id SATTBS1D OY} YIM SOIOJIOIUT
+yey) xo]dwWI0d Os dq JOA9U P[NoUsS osn NOA AZopOuYdE} oy

-corrected! (Timing correction may be adjusted or defeated).
+ISTUMOIAUIO?) NOAA UOHISOdWIO)

-Any additional notes played will be added into the track
-— existing notes are not erased while recording!
+"NOSpr] B Oy ‘AONUTJUT yada 0} seq Maz Se] BY] Jas UdAd
+uvd NOA ‘palisap JJ ‘souanbes Mou ¥B OVUT sjied ou] [Te Adoo
+ATesrewO Ne WI) [IM ONOS ALVAAO JeyIe80} wey}
+,deyd,, 0} UOTOUNJ ONOS ALVA ou] asn usy] ‘saouanbes
+JENPIAIpUt UI (“949 ‘snJOYD ‘aS1OA) UOTIDIS JIseq Yes
+Pl0da1 OF ST ABM JOuIOUY “(812g 666 01 dn) ysnory) ABM

-FAST FORWARD, REWIND, and LOCATE controls
-may be used at any time to quickly access any location in
-your sequence for spot-recording. To overdub a new part,
-select a different track and start recording—while you
-record, the first track will play in perfect sync (unless you
-MUTE it, or SOLO another track). In this way, up to 32
-tracks may be overdubbed! All MIDI effects are recorded
-including pitch bend, modulation, velocity, aftertouch,
-sustain pedal, and program changes!
+dU} [fe YORI] YORs p10991 0} ST SUOS B 9789I9 0} ABM SUG,

-Editing
+SUOS & SUTVAID

-To erase a wrong note, simply hold ERASE and press
-the note to be erased just before it plays in the sequence—
-when played back, it will be gone. Notes may also be
+*suoT}oes poJUBMUN

-added, erased, or changed using the SINGLE STEP func-
-tion. To overdub notes at specific points within a sequence,
+SAOUIOI 0} ABM SWS dU} SoyeIodo SUV ALATAaG

-Additional Features
+“OBPLIq dy} PUB SNIOY PUOdAS dT]] Ud9MIAQ SIDA ISI

-simply use LOCATE, FAST FORWARD, or REWIND to
-find the desired bar number, then start recording.
+ay) Jo Adoo B JJasuT WYSE NOAA ‘afdwexs 10.f ‘UO JUSIN]JIP

-The INSERT/COPY function allows you to move bars
-from one location to another—in the same sequence or a
-different one. For example, you might insert a copy of the
-first verse between the second chorus and the bridge.
-DELETE BARS operates the same way to remove
-unwanted sections,
+B IO aouaNbas sues OY} UI—JOY OUP 0} UOTIEIO] 9UO WOT]
+$1Bq JAOUI OF NOA sMOTIe WOTIOUNS AdOO/IMASNI OULL

-Creating a Song
+‘SUIPIONAI JIVIS Udy) “OQuINU eq porisop ay} puy

-One way to create a song is to record each track all the
-way through (up to 999 bars). Another way is to record
-each basic section (verse, chorus, etc.) in individual
-sequences, then use the CREATE SONG function to “chain”
-them together. CREATE SONG will then automatically
-copy all the parts into a new sequence. If desired, you can
-even set the last few bars to repeat infinitely, for a fadeout.
+0} CNIMAY 10 ‘CYVM Od LSWA “AEVOOT esn Apduns

-Composition Without Compromise
+sainjeay [PUOHIPPY

-The technology you use should never be so complex that
-it interferes with the creative process. That’s precisely why
-the LinnSequencer is designed to let you compose, record
-and edit while devoting your undivided attention to your
-music. See your Linn dealer today for a demonstration!
+‘gouanbas & UTYIIM s]UTOd a1y1dads 3¥ $9100 QnPIOAO OL "UOT}
+-ouns dALLS ATONIS 24) Suisn pasueyo Jo ‘pasesa ‘pappe
+aq osye ABUT S9]ON ‘U0 9q ]IIM 1 “yoeq podeyd uayM
+—aouanbas oy] ul skeyd 71 a10J9q Isnf posers oq 0} d]0U ayy
+ssaid pue ASvwug ploy Aydunis ‘jou Suomm & aseso OL

-* Simple, easy to learn operation—the 32 character LCD display clearly guides you through all operations. If needed, the
+sunipa

-HELP button displays additional explanations.
+jsesdueyo ureisoid pue ‘fepod ureysns
+‘yonoplalje ‘AWOOTOA ‘UOTyeTNpow ‘pusg youd Surpnyour
+pep10del are $199JJ2 TCTIN [WV iPeqqnpseao aq Aeur syoen
+Ze 07 dn ‘Kem sie Uy *(foeI} JOyOUR OJOS 10 ALLAN
+NOA ssofum) duAS yOaysod ul Avy [[IM Yow] ISI 93 “prooar
+NOA 3[IYM—SUIPIOIA LIBIS PU YORI) TUdIOTJIP B JOaTas
+*y1ed MOU B QNPIsA0 OL, “SuIps0daJ-jods 10} aouanbes mno0k
+UI UOHBIO] Aue ssad0e ATYOIND 0} owt} Aue ye pasn aq AvUE
+SJONUOD FLIVOOT pur ‘ANIMA ‘CYVMaYOd LSVd
+{SUIPIOSAI {IY posesa JOU se So]OU SuTsTXO—
+yous} 3U} OUT poppe aq JIM poteyd sajou yeuonippe Auy

-* Non-destructive recording—existing notes are not erased while recording.
-¢ Two FOOTSWITCH INPUTS may be assigned to remotely control many of the commonly used functions, including
+*(povesjap 10 poysn{pe oq ABW UOTIIII0D BUTUTT]) j{paqoeLI09

-ERASE, REPEAT, PLAY/STOP, or LOCATE.
+2q ][IM S1OLIe Sur [fe ATUO—patey]d nod Jey Jedy ]],NOA

-¢ Iwo TRIGGER OUTPUTS may be programmed to output pulses at any selected note value.
+‘] req 0] punose yoeq sdoo] sduanbas ay] Udy AA “YOu Yor

-© Will sync to standard LinnDrum or Linn 9000 sync tone.
+§,sa0uaNbas at} O] SUIT) UI preogday [IW] INO Avy usy3
+AV'1d pue (YOON ssoid Ayduus ‘aousnbes & p1o09es OF,

-© Utilizes ultra high-speed, 8 MHz 80186 16 bit computer internally for FAST operation.
-* TEMPO may be specified in BEATS-PER-MINUTE or FRAMES-PER-BEAT at 24, 25, or 30 frames per second,
+g0uaNbas & SUIP10I0y]

-(even drop frame!)
+‘JONWOD s}JouNaI TeuONdGO e

-¢ TEMPO may be entered numerically, adjustable in tenths of a Beat-Per-Minute increments, or by tapping quarter notes
+"UOTJEZIUOIYUAS OPOS UIT} FLAWS [euondo e

-on the TAP TEMPO button.
+‘sou .sulddoys, noyyM sayelodo pue yoegdvyd ZuLINp S¥IOM NOLLOANNYOO ONIWILL e

-¢ TEMPO CHANGES may be programmed into a sequence, with smooth transitions if desired.
-¢ Any TIME SIGNATURE may be used, and may be changed within a song.
+‘onqea ory AY

-linn
-Linn Electronics, Inc.
+pojoojes-oid & ye sajou pyoy Aue syeadas ATTeONewWO Ne UOTOUNS [WAdAY OAISNOX e
+‘LSVJ SUnIpS soyeu UOTOUN ASV UA OUlN-[eal SAISNIOXY e
+‘Koy B JO YONO} 941 12 CASOdSNVALL 0g ABU Syde] [Te 10 9UC e

-18720 Oxnard Street, Tarzana, CA 91356
-(818) 708-8131 TELEX #298949 LINN UR
+i ASIP Jed
+
+S9}0U OOO‘OTT JOA SpfOy puv SpUOdeS UT SBUOS Xa[AUIOD So10}S DALIP YSIP , 74 € ISCJ-CNIN
+
+jSIOZISOUJUAS
+
+stuoydAjod of 0} dn skeyd A[snoourynuls ‘spouueYd [IW 9T JO duo 0} pousisse oq
+ABUL YORI] YOR ‘syous) oruoydAjod ‘snoouelnurs 7¢ SuTeJUOS ssouUaNbas QO] OY} JO YORA e
+
+‘SJONUOS ATWOOT pur ‘GNIMAY ‘GaVM OA
+LSVd ‘GYOOde AOLS ‘AV Td YIM Jopsocas ade} Yowsj-N[NU O} eps st UOTLISdO @
+LOPNOUT SaINjeoy s[quyIeUlss AUB S.JJ ‘OSN pue UIes] 0} o[duns A[suIzeUe JOA ‘PnJsomod APOUIOITXO
+St 1] “UeIOIsNUL feUOIssajoid oY} 10 JOO} soUBULIOJIJAd pue UOTIsOduIOS 11e-dY1-JO-9}e)s B SI IONUANbDaguUT] ay
+
+JOps1odady soUINbIS [GTI YVAL ZE
+Jgouanbaguury oy

@@ -1 +1 @@
-Tesseract Open Source OCR Engine v4.0.0 with Leptonica
+Tesseract Open Source OCR Engine v4.1.1 with Leptonica
--- a/Show More
+++ b/Show More
Author	SHA1	Message	Date
James R. Barlow	14a85f9473	Fix pinned dependencies	2020-11-03 04:12:47 -08:00
James R. Barlow	d22a1b3367	v11.3.2 release notes (2) Since we never tagged it, fix other things.	2020-11-03 02:03:25 -08:00
James R. Barlow	b913e5dfef	ghostscript: don't repeat log in debug Subprocess already does this for us.	2020-11-03 01:45:06 -08:00
James R. Barlow	dd8a5a4c72	Fix log domain names ocrmypdf.subprocess.subprocess.ghostscript -> ocrmypdf.subprocess.ghostscript	2020-11-03 01:44:35 -08:00
James R. Barlow	36e9a54f02	Remove extraneous page rotation This was added in commit `b5ccbfd` but seems to have been ill-advised.	2020-11-03 01:34:28 -08:00
James R. Barlow	3707af3b74	Change pdf.root to pdf.Root	2020-11-03 01:30:31 -08:00
James R. Barlow	ced7ad9164	unpaper: round off DPI	2020-11-03 01:14:57 -08:00
James R. Barlow	54bbbfdeb3	Fix UnboundLocalError when considering ImageMasks for optimization Uncovered by test file in issue 667, although unrelated to that issue.	2020-11-03 01:08:14 -08:00
James R. Barlow	7f73a6ed1e	Some Python 3.9 fixes	2020-11-03 00:45:47 -08:00
James R. Barlow	dce206d3dc	Fix pre-commit for Py3.9	2020-11-03 00:20:25 -08:00
James R. Barlow	9304c856cf	Merge branch 'master' of github.com:jbarlow83/OCRmyPDF	2020-11-02 02:47:36 -08:00
James R. Barlow	e5df98cbdf	v11.3.2 release notes	2020-11-02 02:43:32 -08:00
James R. Barlow	19bf3aeb00	api: improve typing	2020-11-02 02:33:34 -08:00
James R. Barlow	e86be0031c	unpaper: fix process output handling With the ocrmypdf.subprocess wrapper, logging the output here is redundant and loses the page number context.	2020-11-02 01:07:41 -08:00
James R. Barlow	6425977998	unpaper: use pnm instead of png Some users reported problems with PNG recently; try PNM. Fixes #665 Fixes #667	2020-11-02 01:05:56 -08:00
James R. Barlow	d57df2d980	subprocess: support programs that write their messages to stdout	2020-11-02 01:00:59 -08:00
James R. Barlow	664d0c7969	Document configure_debug_logging	2020-11-02 00:59:00 -08:00
James R. Barlow	a354663ee1	Fix typo in API documentation	2020-11-02 00:58:28 -08:00
Graham MilnandGitHub	b21b048ec4	Add macOS brew language support (#615 ) Note `brew` command for installing additional languages on macOS.	2020-10-30 01:09:06 -07:00
James R. Barlow	709c65b41a	v11.3.1 release notes	2020-10-27 23:11:11 -07:00
James R. Barlow	67f99c5bb7	Endorse pdfminer.six 20201018	2020-10-27 23:09:45 -07:00
James R. Barlow	d55e673d9c	Fix warning about --pdfa-image-compression argument at wrong times Closes #663	2020-10-27 23:09:45 -07:00
James R. Barlow	21b90d2d14	Endorse pikepdf 2.x	2020-10-27 23:09:45 -07:00
Edward BettsandGitHub	2def7e3392	Use % for percentage in string format (#643 )	2020-10-27 23:09:14 -07:00
James R. Barlow	b0dcaa7512	v11.3.0 release notes	2020-10-24 03:19:32 -07:00
James R. Barlow	e8285b1d10	Add test to confirm rasterize_pdf_page rotates correct	2020-10-24 03:10:59 -07:00
James R. Barlow	5ba56adb53	Fix page rotation issue (again) Commit `1327ab3` introduced a fix for a regression, which was reported in #581, #634. It appears that the actual cause of this issue was default parameters to rasterize_pdf_page in pluggy not working as expected, causing a default rotation=0 even when a rotation was needed. As such the OCR image was generated with the wrong orientation, causing the initial regression and fix in commit `1327ab3`. Now that the real problem is identified, it's apparent that the logic prior to `1327ab3` was found and we can revert to `1327ab3` since it fixes all known cases including #658. This reverts `1327ab3` except for retaining improves to rotation output.	2020-10-24 02:45:21 -07:00
James R. Barlow	ca735278e0	setup: Version pluggy better	2020-10-24 02:35:41 -07:00
James R. Barlow	b5ccbfdf25	Fix hookspec of rasterize_pdf_page to remove default parameters	2020-10-24 02:35:18 -07:00
James R. Barlow	8c35d6e6e4	Fix debug log messages being suppressed from child processes	2020-10-22 02:20:06 -07:00
James R. Barlow	d1e0c81eda	Ensure worker_pdf is closed after gathering info in a thread This is hacky, uses global state, but it does improve the situation for now.	2020-10-22 00:38:24 -07:00
James R. Barlow	10c8e4f8b4	Only create debug.log when running from command line When used as a library ocrmypdf shouldn't make policy decisions, like where to put a log file. Unsurprisingly, creating it causes problems for library users because we deleted the temporary folder which held the log file and made no effort to move it to a new location. Also update the documentation to better described how an application should handle this. Closes #657	2020-10-20 01:29:36 -07:00
James R. Barlow	6be2242c21	Describe "OCR" step as "Image processing" when --tesseract-timeout=0 Fixes #647	2020-10-08 01:03:42 -07:00
James R. Barlow	204c9d6ae1	Fix inverted colors during JBIG2 optimization on paletted images Fixes #640	2020-10-07 04:08:50 -07:00
James R. Barlow	6eb393590b	v11.2.0 release notes Change v11.1.3 to v11.2.0 since it contains functional changes.	2020-10-06 03:24:31 -07:00
James R. Barlow	07c6654057	v11.1.3 release notes	2020-10-06 03:22:48 -07:00
James R. Barlow	4e15eb8d14	Fix image optimization discarding image masks and soft masks associated with PNGs Fixes #648	2020-10-06 03:20:54 -07:00
James R. Barlow	8b01ab8ad2	Better type checking on ocrmypdf.ocr(plugins=...)	2020-10-05 15:02:34 -07:00
James R. Barlow	e0a522ad50	Document the example plugin	2020-10-05 15:01:44 -07:00
James R. Barlow	a1a8788c5a	Merge branch 'master' of github.com:jbarlow83/OCRmyPDF	2020-09-29 02:46:27 -07:00
James R. Barlow	cccdc178c3	v11.1.2 release notes	2020-09-29 02:46:18 -07:00
James R. Barlow	4eacb3454f	hOCR: write text in correct order Fixes #642	2020-09-29 02:45:11 -07:00
Jimit DholakiaandGitHub	82b8b41e80	docs: Add 'unpaper' optional dependency for Ubuntu 18.04 (#639 )	2020-09-25 11:54:31 -07:00
James R. Barlow	581c5020ab	v11.1.1 release notes	2020-09-25 00:28:38 -07:00
James R. Barlow	3ef8872a1e	pngquant driver: refactor, use streams instead of temporary files	2020-09-25 00:18:02 -07:00
James R. Barlow	28eec73eed	Tighten unpaper-args validation to exclude . and .. Just in case	2020-09-25 00:18:02 -07:00
James R. Barlow	bfe4a5b329	Tidy a log message	2020-09-25 00:17:57 -07:00
James R. Barlow	29097837d6	Release notes typo	2020-09-19 00:49:36 -07:00
James R. Barlow	a40361db3c	Remove unpaper from macOS build Homebrew seems to be having issues with its deps?	2020-09-17 03:38:48 -07:00
James R. Barlow	8b29e3cbab	Merge commit '9a6cd95e5fe2826d40861229aaa0431b76e302e7'	2020-09-17 03:34:35 -07:00
James R. Barlow	b170be120b	v11.1.0 release notes	2020-09-17 03:21:06 -07:00
Suyash BeheraandGitHub	9a6cd95e5f	load zlib before liblept on windows (#633 ) fixes #631	2020-09-17 03:14:42 -07:00
James R. Barlow	d464d3122e	Use img2pdf to create optimized PNG images Fixes #629, #620	2020-09-17 03:11:26 -07:00
James R. Barlow	1327ab37d4	Fix page rotation regression Fixes #634, #581	2020-09-17 02:57:00 -07:00
James R. Barlow	67553fc5c6	Display page numbers in log messages when grafting	2020-09-17 01:20:50 -07:00
James R. Barlow	306a903854	Remove unused function log_page_orientations	2020-09-17 01:20:02 -07:00
James R. Barlow	b93cf51c0f	Disable pikepdf mmap Infrequently we can reproduce this error: terminating with uncaught exception of type std::runtime_error: pybind11_object_dealloc(): Tried to deallocate unregistered instance! The error is probably related to pybind11 issue #2252 and a bunch of other related issues. Until that is resolved in pybind11 and pikepdf we will disable the pikepdf mmap interface.	2020-09-16 23:48:55 -07:00
James R. Barlow	6b994221c6	Remove Python 3.7 from build since homebrew removed it	2020-09-16 23:44:18 -07:00
James R. Barlow	8b5b02e0d8	Expand documentation of filter_page_image	2020-09-14 14:36:17 -07:00
James R. Barlow	624df9bb23	Extend example plugin with example of mono conversion	2020-09-14 14:35:50 -07:00
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
James R. Barlow	66337813e6	Spell runslow correctly	2020-06-22 23:32:09 -07:00
James R. Barlow	eb5a211e72	New hocrtransform test isn't platform stable - mark runslow	2020-06-22 16:59:59 -07:00
James R. Barlow	5142933120	v10.2.0 release notes Closes #582, #584, #545	2020-06-22 16:37:51 -07:00
James R. Barlow	06ab114aa8	Update test cache	2020-06-22 16:31:34 -07:00
James R. Barlow	1257419465	test_hocrtransform: this test is worth not caching	2020-06-22 16:31:06 -07:00
James R. Barlow	30404f53f0	Add test to sanity check our pdf renderers	2020-06-22 16:18:38 -07:00
James R. Barlow	1ce8edbdfe	hocrtransform: some text not included in output after Tesseract changes	2020-06-22 15:48:23 -07:00
James R. Barlow	d4b704a0ae	hocrtransform: refactor colors	2020-06-22 15:22:48 -07:00
James R. Barlow	2d64e1536d	hocrtransform: refactor xpath manipulations	2020-06-22 14:44:34 -07:00
James R. Barlow	c8b581ac31	hoctransform: remove deprecated element.getchildren() Breaks Python 3.9.	2020-06-22 14:28:18 -07:00
James R. Barlow	ad8dead7df	Document that API accepts streams now	2020-06-22 14:27:27 -07:00
James R. Barlow	c9bd87254e	A few minor typing issues	2020-06-22 02:31:53 -07:00
James R. BarlowandJames R. Barlow	f4cb424451	Support input/output streams at API level	2020-06-22 02:02:18 -07:00
James R. Barlow	fef14778d5	Fix missing f-string in log message	2020-06-22 01:17:16 -07:00
James R. Barlow	86ec63f215	Decouple plugin manager forking from PdfContext/Pagecontext	2020-06-22 01:16:59 -07:00
James R. Barlow	5b10ec9d39	jobcontext.PdfContext: remove dead code, add annotations	2020-06-22 00:34:58 -07:00
James R. Barlow	800c75c4e5	Bump requirements (mainly for Docker's benefit)	2020-06-21 01:58:53 -07:00
James R. Barlow	24d64b04c3	Update Docker to Ubuntu 20.04 and jbig2-latest	2020-06-21 01:48:31 -07:00
James R. Barlow	48e2750551	Fix some tests that were failing in Docker	2020-06-21 01:48:13 -07:00
James R. Barlow	e182c5f63e	Update and sync .dockerignore, .gitignore Also blacklist .* and whitelist the ones we want.	2020-06-21 01:25:59 -07:00
James R. Barlow	06d52326db	Fix deleted path in .coveragerc	2020-06-21 01:24:23 -07:00
James R. Barlow	ebfe4f0d29	Fix issue #582 - PDF/A acquires title "Untitled" after conversion	2020-06-20 02:01:16 -07:00
James R. Barlow	ad22977c84	v10.1.1 release notes	2020-06-17 14:45:32 -07:00
James R. Barlow	6ac50646f0	Fix OMP_THREAD_LIMIT rounded down to 0 in some cases	2020-06-17 14:43:19 -07:00
James R. Barlow	24b6a4ad50	v10.1.0 notes	2020-06-16 00:55:28 -07:00
James R. Barlow	e802896d4d	unpaper: use PNG input where possible Unpaper accepts PNG as input now, so avoid generating a huge temporary PPM file if we can. If we must create a PNG, compress it lightly to keep our temp usage down.	2020-06-16 00:50:18 -07:00
James R. Barlow	0b5a20e593	coverage: ignore type checking	2020-06-15 15:55:39 -07:00
James R. Barlow	642998ead6	sync: refactor preprocess image filtering	2020-06-15 15:26:41 -07:00
James R. Barlow	698aab4f75	Add a lot of type annotations	2020-06-15 15:20:50 -07:00
James R. Barlow	34231ac667	sync: refactor intermediate image production	2020-06-15 15:02:28 -07:00
James R. Barlow	ddedf7cd2e	For --clean-final, use same image as --clean if possible	2020-06-15 13:48:49 -07:00
James R. Barlow	9d127d354c	docs: improve description of plugins	2020-06-15 12:51:49 -07:00
James R. Barlow	2d2a4894ab	Some corrections to release notes	2020-06-15 12:51:28 -07:00
James R. Barlow	862861e3ca	Fix error message in logging from repeated filtering If logging somehow triggers PageNumberFilter multiple times, it would fail on the second occurrence.	2020-06-13 14:50:58 -07:00