v10.3.3 release notes

Fix KeyError: 'dpi' when using --threshold on image to PDF
Fixes #607
2020-08-07 02:23:21 -07:00 · 2020-08-07 02:21:02 -07:00 · 2020-08-05 01:36:56 -07:00 · 2020-08-05 01:35:26 -07:00 · 2020-08-03 16:04:16 -07:00 · 2020-08-03 16:03:54 -07:00
28 changed files with 1132 additions and 161 deletions
@@ -1,6 +1,6 @@
 repos:
  - repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v2.4.0
+    rev: v3.1.0
    hooks:
      - id: check-case-conflict
      - id: check-merge-conflict
@@ -8,16 +8,16 @@ repos:
      - id: check-yaml
      - id: debug-statements
  - repo: https://github.com/asottile/seed-isort-config
-    rev: v1.9.3
+    rev: v2.2.0
    hooks:
      - id: seed-isort-config
  - repo: https://github.com/pre-commit/mirrors-isort
-    rev: v4.3.21 # pick the isort version you'd like to use from https://github.com/pre-commit/mirrors-isort/releases
+    rev: v5.0.5 # pick the isort version you'd like to use from https://github.com/pre-commit/mirrors-isort/releases
    hooks:
      - id: isort
  - repo: https://github.com/psf/black
-    rev: stable
+    rev: 19.10b0
    hooks:
      - id: black
-        language_version: python3.7
+        language_version: python3.8
        exclude: ^src/ocrmypdf/lib/_leptonica.py
@@ -152,9 +152,9 @@ stages:
        strategy:
          matrix:
            Python37:
-              python.version: "3.7"
+              python.version: ""
-            # Python38:
+            Python38:
-            #   python.version: "3.8"
+              python.version: "python@3.8"
        steps:
          # https://github.com/actions/virtual-environments/issues/664
          # - task: UsePythonVersion@0
@@ -163,6 +163,13 @@ stages:
          - bash: |
              brew update
              brew unlink python@2
              if [ "$(python.version)" != "" ]; then
                brew upgrade $(python.version)
              else
                echo "Using Python `python3 --version`"
              fi
            displayName: "Update brew and Python"
          - bash: |
              brew install \
                exempi \
                ghostscript \
@@ -170,7 +177,6 @@ stages:
                leptonica \
                openjpeg \
                pngquant \
                python \
                tesseract \
                unpaper
            displayName: "Install system packages"
@@ -2,7 +2,6 @@ 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:
@@ -10,10 +9,24 @@ Copyright:
 (C) 2013-2016, 2015-2017 2016, 2017, 2017-2018, 2018 James R. Barlow
 License: GPL-3+
 Files: misc/watcher.py
 Copyright:
 (C) 2019 Ian Alexander: https://github.com/ianalexander
 (C) 2020 James R. Barlow
 License: GPL-3+
 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
@@ -30,7 +43,7 @@ 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 +92,20 @@ 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 +113,13 @@ 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>
@@ -124,6 +149,669 @@ 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
@@ -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"
@@ -665,6 +665,13 @@ instead use this for a system wide installation:
    pip3 install ocrmypdf
 .. note::
    AArch64 (ARM64) users: this process will be difficult because most
    Python packages are not available as binary wheels for your platform.
    You're probably better off using a platform install on Debian, Ubuntu,
    or Fedora.
 Requirements for pip and HEAD install
 -------------------------------------
@@ -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.
+plugins for all files.
 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.
 Script plugins
 ==============
 Script plugins may be called from the command line, by specifying the name of a file.
 Script plugins may be convenient for informal or "one-off" plugins, when a certain
 batch of files needs a special processing step for example.
 .. code-block:: bash
-    ocrmypdf --plugin example_plugin.py input.pdf output.pdf
+    ocrmypdf --plugin ocrmypdf_example_plugin.py input.pdf output.pdf
-Multiple plugins may be called by issuing the ``--plugin`` argument multiple times.
+Multiple plugins may be installed by issuing the ``--plugin`` argument multiple times.
 Packaged plugins
 ================
 Installed plugins may be installed into the same virtual environment as OCRmyPDF
 is installed into. They may be invoked using Python standard module naming.
 If you are intending to distribute a plugin, please package it.
 .. code-block:: bash
@@ -59,10 +59,45 @@ as packaged plugins, and these modules should begin with the name ``ocrmypdf_``
 similar to ``pytest`` packages such as ``pytest-cov`` (the package) and
 ``pytest_cov`` (the module).
 .. note::
    We strongly recommend plugin authors name their plugins with the prefix
    ``ocrmypdf-`` (for the package name on PyPI) and ``ocrmypdf_`` (for the
    module), just like pytest plugins.
 Plugin requirements
 ===================
 OCRmyPDF generally uses multiple worker processes. When a new worker is started,
 Python will import all plugins again, including all plugins that were imported earlier.
 This means that the global state of a plugin in one worker will not be shared with
 other workers. As such, plugin hook implementations should be stateless, relying
 only on their inputs. Hook implementations may use their input parameters to
 to obtain a reference to shared state prepared by another hook implementation.
 Plugins must expect that other instances of the plugin will be running
 simultaneously.
 The ``context`` object that is passed to many hooks can be used to share information
 about a file being worked on. Plugins must write private, plugin-specific data to
 a subfolder named ``{options.work_folder}/ocrmypdf-plugin-name``. Plugins MAY
 read and write files in ``options.work_folder``, but should be aware that their
 semantics are subject to change.
 OCRmyPDF will delete ``options.work_folder`` when it has finished OCRing
 a file, unless invoked with ``--keep-temporary-files``.
 The documentation for some plugin hooks contain a detailed description of the
 execution context in which they will be called.
 Plugins should be prepared to work whether executed in worker threads or worker
 processes. Generally, OCRmyPDF uses processes, but has a semi-hidden threaded
 argument that simplifies debugging.
 Plugin hooks
 ============
-A plugin may provide the following hooks. Hooks should be decorated with
+A plugin may provide the following hooks. Hooks must be decorated with
 ``ocrmypdf.hookimpl``, for example:
 .. code-block:: python
@@ -73,9 +108,21 @@ A plugin may provide the following hooks. Hooks should be decorated with
    def add_options(parser):
        pass
-The following is a complete list of hooks that may be installed and when
+The following is a complete list of hooks that are available, and when
 they are called.
 .. _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
 -----------------------------
@@ -16,6 +16,40 @@ Note that it is licensed under GPLv3, so scripts that
 ``import ocrmypdf`` and are released publicly should probably also be
 licensed under GPLv3.
 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 20200420.
 -  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
 =======
@@ -83,7 +83,7 @@ setup(
        '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',
+        'pdfminer.six >= 20191110, <= 20200726',
        'pikepdf >= 1.14.0, < 2',
        'Pillow >= 7.0.0',
        'pluggy >= 0.13.0',
@@ -18,6 +18,7 @@
 import logging
 import os
 import signal
 import sys
 from multiprocessing import set_start_method
@@ -26,11 +27,20 @@ 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 +72,9 @@ 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
@@ -28,6 +28,8 @@ from typing import Callable, Iterable, Optional
 from tqdm import tqdm
 from ocrmypdf.exceptions import InputFileError
 def log_listener(queue):
    """Listen to the worker processes and forward the messages to logging
@@ -53,12 +55,20 @@ def log_listener(queue):
            traceback.print_exc(file=sys.stderr)
 def process_sigbus(*args):
    raise InputFileError("A worker process lost access to an input file")
 def process_init(queue, user_init):
    """Initialize a process pool worker"""
    # Ignore SIGINT (our parent process will kill us gracefully)
    signal.signal(signal.SIGINT, signal.SIG_IGN)
    # Install SIGBUS handler (so our parent process can abort somewhat gracefully)
    if hasattr(signal, 'SIGBUS'):
        signal.signal(signal.SIGBUS, process_sigbus)
    # Reconfigure the root logger for this process to send all messages to a queue
    h = logging.handlers.QueueHandler(queue)
    root = logging.getLogger()
@@ -70,6 +80,9 @@ def process_init(queue, user_init):
 def thread_init(_queue, user_init):
    # As a thread, block SIGBUS so the main thread deals with it...
    if hasattr(signal, 'SIGBUS'):
        signal.pthread_sigmask(signal.SIG_BLOCK, {signal.SIGBUS})
    if user_init:
        user_init()
@@ -17,6 +17,7 @@
 """Interface to pngquant executable"""
 from os import fspath
 from tempfile import NamedTemporaryFile
 from PIL import Image
@@ -38,6 +39,8 @@ def available():
 def quantize(input_file, output_file, quality_min, quality_max):
    input_file = fspath(input_file)
    output_file = fspath(output_file)
    if input_file.endswith('.jpg'):
        with Image.open(input_file) as im, NamedTemporaryFile(suffix='.png') as tmp:
            im.save(tmp)
@@ -530,7 +530,9 @@ def create_ocr_image(image: Path, page_context: PageContext):
        if options.threshold:
            pix = leptonica.Pix.frompil(im)
            pix = pix.masked_threshold_on_background_norm()
-            im = pix.topil()
+            im_pix = pix.topil()
            im_pix.info['dpi'] = im.info['dpi']
            im = im_pix
        del draw
@@ -25,11 +25,13 @@ from pathlib import Path
 from tempfile import mkdtemp
 from typing import List, NamedTuple, Optional, Tuple
 import pikepdf
 import PIL
 from ocrmypdf._concurrent import exec_progress_pool
 from ocrmypdf._graft import OcrGrafter
 from ocrmypdf._jobcontext import PageContext, PdfContext, cleanup_working_files
 from ocrmypdf._logging import PageNumberFilter
 from ocrmypdf._pipeline import (
    convert_to_pdfa,
    copy_final,
@@ -62,7 +64,12 @@ from ocrmypdf._validation import (
    report_output_file_size,
 )
 from ocrmypdf.exceptions import ExitCode, ExitCodeException
-from ocrmypdf.helpers import available_cpu_count, check_pdf, samefile
+from ocrmypdf.helpers import (
    available_cpu_count,
    check_pdf,
    pikepdf_enable_mmap,
    samefile,
 )
 from ocrmypdf.pdfa import file_claims_pdfa
 log = logging.getLogger(__name__)
@@ -240,6 +247,7 @@ def worker_init(max_pixels: int):
    # the parent process, so ensure workers get it set. Not needed when running
    # threaded, but harmless to set again.
    PIL.Image.MAX_IMAGE_PIXELS = max_pixels
    pikepdf_enable_mmap()
 def exec_concurrent(context: PdfContext):
@@ -309,6 +317,7 @@ def configure_debug_logging(log_filename, prefix=''):
        '[%(asctime)s] - %(name)s - %(levelname)7s -%(pageno)s %(message)s'
    )
    log_file_handler.setFormatter(formatter)
    log_file_handler.addFilter(PageNumberFilter())
    logging.getLogger(prefix).addHandler(log_file_handler)
    return log_file_handler
@@ -329,6 +338,8 @@ def run_pipeline(options, *, plugin_manager, api=False):
    ):
        debug_log_handler = configure_debug_logging(Path(work_folder) / "debug.log")
    pikepdf_enable_mmap()
    try:
        check_requested_output_file(options)
        start_input_file, original_filename = create_input_file(options, work_folder)
@@ -416,6 +416,10 @@ 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"
@@ -83,8 +83,8 @@ 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
+contains losslessly compressed images, and images in the output file will be
-compressed as well.
+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 +103,8 @@ 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
+removes some features from the PDF such as Javascript or forms. If you want to
-as Javascript or forms. If you want to minimize the number of changes made to
+minimize the number of changes made to your PDF, use --output-type pdf.
 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 +112,7 @@ 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
+sending the result to OCRmyPDF through a pipe.
 ocrmypdf so it is already installed.
    img2pdf --pagesize A4 page*.png | ocrmypdf - myfile.pdf
@@ -462,7 +460,12 @@ 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(
@@ -222,6 +222,14 @@ def clamp(n: T, smallest: T, largest: T) -> T:
    return max(smallest, min(n, largest))
 def pikepdf_enable_mmap():
    try:
        if pikepdf._qpdf.set_access_default_mmap(True):
            log.debug("pikepdf mmap enabled")
    except AttributeError:
        log.debug("pikepdf mmap not available")
 def deprecated(func):
    """Warn that function is deprecated"""
@@ -24,7 +24,9 @@ import argparse
 import logging
 import os
 import sys
 import threading
 import warnings
 from collections import deque
 from collections.abc import Sequence
 from contextlib import suppress
 from ctypes.util import find_library
@@ -75,7 +77,7 @@ except ffi.error as e:
    ) from e
-class _LeptonicaErrorTrap:
+class _LeptonicaErrorTrap_Redirect:
    """
    Context manager to trap errors reported by Leptonica.
@@ -90,19 +92,21 @@ 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):
+        self.leptonica_lock.acquire()
            sys.stderr.flush()
        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 +118,10 @@ 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 +138,8 @@ 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 +157,62 @@ 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 +921,8 @@ 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()
@@ -509,6 +509,8 @@ void selDestroy ( SEL **psel );
 l_int32
 setMsgSeverity(l_int32 newsev);
 void
 leptSetStderrHandler(void (*handler)(const char *));
 """
 )
@@ -22,9 +22,23 @@ from collections import defaultdict
 from functools import partial
 from os import fspath
 from pathlib import Path
 from typing import (
    Any,
    Callable,
    Dict,
    Iterator,
    List,
    MutableSet,
    NamedTuple,
    NewType,
    Optional,
    Sequence,
    Tuple,
    Union,
 )
 import pikepdf
-from pikepdf import Dictionary, Name
+from pikepdf import Dictionary, Name, Object, Pdf, PdfImage
 from PIL import Image
 from tqdm import tqdm
@@ -41,30 +55,40 @@ DEFAULT_JPEG_QUALITY = 75
 DEFAULT_PNG_QUALITY = 70
-def img_name(root, xref, ext):
+Xref = NewType('Xref', int)
    return fspath(root / f'{xref:08d}{ext}')
-def png_name(root, xref):
+class XrefExt(NamedTuple):
    xref: Xref
    ext: str
 def img_name(root: Path, xref: Xref, ext: str) -> Path:
    return root / f'{xref:08d}{ext}'
 def png_name(root: Path, xref: Xref) -> Path:
    return img_name(root, xref, '.png')
-def jpg_name(root, xref):
+def jpg_name(root: Path, xref: Xref) -> Path:
    return img_name(root, xref, '.jpg')
-def tif_name(root, xref):
+def tif_name(root: Path, xref: Xref) -> Path:
    return img_name(root, xref, '.tif')
-def extract_image_filter(pike, root, image, xref):
+def extract_image_filter(
    pike: Pdf, root: Path, image: Object, xref: Xref
 ) -> Optional[Tuple[PdfImage, Tuple[Name, Object]]]:
    if image.Subtype != Name.Image:
        return None
    if image.Length < 100:
        log.debug("Skipping small image, xref %s", xref)
        return None
-    pim = pikepdf.PdfImage(image)
+    pim = PdfImage(image)
    if len(pim.filter_decodeparms) > 1:
        log.debug("Skipping multiply filtered, xref %s", xref)
@@ -83,7 +107,9 @@ def extract_image_filter(pike, root, image, xref):
    return pim, filtdp
-def extract_image_jbig2(*, pike, root, image, xref, options):
+def extract_image_jbig2(
    *, pike: pikepdf.Pdf, root: Path, image: Object, xref: Xref, options
 ) -> Optional[XrefExt]:
    result = extract_image_filter(pike, root, image, xref)
    if result is None:
        return None
@@ -91,21 +117,23 @@ def extract_image_jbig2(*, pike, root, image, xref, options):
    if (
        pim.bits_per_component == 1
-        and filtdp != Name.JBIG2Decode
+        and filtdp[0] != Name.JBIG2Decode
        and jbig2enc.available()
    ):
        try:
-            imgname = Path(root / f'{xref:08d}')
+            imgname = root / f'{xref:08d}'
            with imgname.open('wb') as f:
                ext = pim.extract_to(stream=f)
            imgname.rename(imgname.with_suffix(ext))
        except pikepdf.UnsupportedImageTypeError:
            return None
-        return xref, ext
+        return XrefExt(xref, ext)
    return None
-def extract_image_generic(*, pike, root, image, xref, options):
+def extract_image_generic(
    *, pike: Pdf, root: Path, image: PdfImage, xref: Xref, options
 ) -> Optional[XrefExt]:
    result = extract_image_filter(pike, root, image, xref)
    if result is None:
        return None
@@ -138,13 +166,13 @@ 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 +181,12 @@ 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 +197,14 @@ 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 +220,8 @@ def extract_images(pike, root, options, extract_fn):
    extension. extract_fn must also extract the file it finds interesting.
    """
-    include_xrefs = set()
+    include_xrefs: MutableSet[Xref] = set()
-    exclude_xrefs = set()
+    exclude_xrefs: MutableSet[Xref] = set()
    pageno_for_xref = {}
    errors = 0
    for pageno, page in enumerate(pike.pages):
@@ -202,10 +232,10 @@ def extract_images(pike, root, options, extract_fn):
        for _imname, image in dict(xobjs).items():
            if image.objgen[1] != 0:
                continue  # Ignore images in an incremental PDF
-            xref = image.objgen[0]
+            xref = Xref(image.objgen[0])
            if hasattr(image, 'SMask'):
                # Ignore soft masks
-                smask_xref = image.SMask.objgen[0]
+                smask_xref = Xref(image.SMask.objgen[0])
                exclude_xrefs.add(smask_xref)
            include_xrefs.add(xref)
            if xref not in pageno_for_xref:
@@ -224,31 +254,33 @@ 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):
+    for _, xref_ext in extract_images(pike, root, options, extract_image_generic):
-        log.debug('xref = %s ext = %s', xref, ext)
+        log.debug('%s', xref_ext)
-        if ext == '.png':
+        if xref_ext.ext == '.png':
-            pngs.append(xref)
+            pngs.append(xref_ext.xref)
-        elif ext == '.jpg':
+        elif xref_ext.ext == '.jpg':
-            jpegs.append(xref)
+            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 +290,12 @@ 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 +304,7 @@ 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 +340,9 @@ 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 +380,19 @@ 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:
+        with Image.open(in_jpg) as im:
-            im.save(fspath(opt_jpg), optimize=True, quality=options.jpeg_quality)
+            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 +403,14 @@ def transcode_jpegs(pike, jpegs, root, options):
        im_obj.write(compdata.read(), filter=Name.DCTDecode)
-def transcode_pngs(pike, images, image_name_fn, root, options):
+def transcode_pngs(
-    modified = set()
+    pike: Pdf,
    images: Sequence[Xref],
    image_name_fn: Callable[[Path, Xref], Path],
    root: Path,
    options,
 ) -> None:
    modified: MutableSet[Xref] = set()
    if options.optimize >= 2:
        png_quality = (
            max(10, options.png_quality - 10),
@@ -431,7 +473,7 @@ def transcode_pngs(pike, images, image_name_fn, root, options):
            rewrite_png_as_g4(pike, im_obj, compdata)
-def rewrite_png_as_g4(pike, im_obj, compdata):
+def rewrite_png_as_g4(pike: Pdf, im_obj: Object, compdata) -> None:
    im_obj.BitsPerComponent = 1
    im_obj.Width = compdata.w
    im_obj.Height = compdata.h
@@ -451,7 +493,7 @@ def rewrite_png_as_g4(pike, im_obj, compdata):
    return
-def rewrite_png(pike, im_obj, compdata):
+def rewrite_png(pike: Pdf, im_obj: Object, compdata) -> None:
    # When a PNG is inserted into a PDF, we more or less copy the IDAT section from
    # the PDF and transfer the rest of the PNG headers to PDF image metadata.
    # One thing we have to do is tell the PDF reader whether a predictor was used
@@ -504,7 +546,7 @@ 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 +560,7 @@ 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 +573,12 @@ 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
+    input_size = input_file.stat().st_size
-    output_size = Path(target_file).stat().st_size
+    output_size = target_file.stat().st_size
    if output_size == 0:
        raise OutputFileAccessError(
            f"Output file not created after optimizing. We probably ran "
@@ -557,8 +599,8 @@ 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 +618,7 @@ def main(infile, outfile, level, jobs=1):
            self.quiet = True
            self.progress_bar = False
    infile = Path(infile)
    options = OptimizeOptions(
        input_file=infile,
        jobs=jobs,
@@ -33,7 +33,7 @@ from pikepdf import PdfMatrix
 from ocrmypdf._concurrent import exec_progress_pool
 from ocrmypdf.exceptions import EncryptedPdfError
-from ocrmypdf.helpers import Resolution, available_cpu_count
+from ocrmypdf.helpers import Resolution, available_cpu_count, pikepdf_enable_mmap
 from ocrmypdf.pdfinfo.layout import get_page_analysis, get_text_boxes
 logger = logging.getLogger()
@@ -91,7 +91,7 @@ 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'])
@@ -639,6 +639,7 @@ worker_pdf = None
 def _pdf_pageinfo_sync_init(infile):
    global worker_pdf  # pylint: disable=global-statement
    pikepdf_enable_mmap()
    worker_pdf = pikepdf.open(infile)
@@ -220,8 +220,16 @@ 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, boxes_flow=None)
+        rman,
        laparams=LAParams(
            all_texts=True, detect_vertical=True, boxes_flow=disable_boxes_flow
        ),
    )
    interp = pdfminer.pdfinterp.PDFPageInterpreter(rman, dev)
@@ -26,9 +26,10 @@ import pluggy
 from ocrmypdf.helpers import Resolution
 if TYPE_CHECKING:
    from PIL import Image
    from ocrmypdf._jobcontext import PageContext
    from ocrmypdf.pdfinfo import PdfInfo
    from PIL import Image
 hookspec = pluggy.HookspecMarker('ocrmypdf')
@@ -122,6 +123,8 @@ def rasterize_pdf_page(
    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>`.
    """
@@ -130,11 +133,25 @@ def filter_ocr_image(page: 'PageContext', image: 'Image') -> 'Image':
    """Called to filter the image before it is sent to OCR.
    This is the image that OCR sees, not what the user sees when they view the
-    PDF.
+    PDF. If ``redo_ocr`` is enabled, portions of the image will be masked so
    they are not shown to OCR. The main use of this hook is expected to be hiding
    content from OCR.
    The input image may be color, grayscale, or monochrome, and the
    output image may differ. The pixel width and height of the
    output image must be identical to the input image, or misalignment between
    the OCR text layer and visual position of the text will occur. Likewise,
    the output must be a faithful representation of the input, or alignment
    errors may occurs.
    Tesseract OCR only deals with monochrome images, and internally converts
    non-monochrome images to OCR.
    Note:
        This hook will be called from child processes. Modifying global state
        will not affect the main process or other child processes.
    Note:
        This is a :ref:`firstresult hook<firstresult>`.
    """
@@ -155,6 +172,8 @@ def filter_page_image(page: 'PageContext', image_filename: Path) -> Path:
    Note:
        This hook will be called from child processes. Modifying global state
        will not affect the main process or other child processes.
    Note:
        This is a :ref:`firstresult hook<firstresult>`.
    """
@@ -239,6 +258,9 @@ def get_ocr_engine() -> OcrEngine:
    The OcrEngine may be instantiated multiple times, by both the main process
    and child process. As such, it must be obtain store any state in ``options``
    or some common location.
    Note:
        This is a :ref:`firstresult hook<firstresult>`.
    """
@@ -275,4 +297,7 @@ def generate_pdfa(
    Returns:
        Path: If successful, the hook should return ``output_file``.
    Note:
        This is a :ref:`firstresult hook<firstresult>`.
    """
@@ -1,40 +0,0 @@
 # © 2019 James R. Barlow: github.com/jbarlow83
 #
 # Permission is hereby granted, free of charge, to any person obtaining a
 # copy of this software and associated documentation files (the
 # "Software"), to deal in the Software without restriction, including
 # without limitation the rights to use, copy, modify, merge, publish,
 # distribute, sublicense, and/or sell copies of the Software, and to
 # permit persons to whom the Software is furnished to do so, subject to
 # the following conditions:
 #
 # The above copyright notice and this permission notice shall be included
 # in all copies or substantial portions of the Software.
 #
 # THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS
 # OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
 # MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
 # IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY
 # CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT,
 # TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE
 # SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
 """Find Ghostscript executable"""
 import os
 import shutil
 def real_ghostscript(argv):
    if os.name != 'nt':
        gs = shutil.which('gs')
        gs_args = [gs] + argv[1:]
        os.execv(gs_args[0], gs_args)
    else:
        gs = shutil.which('gswin64c')
        if not gs:
            gs = shutil.which('gswin32c')
        os.execv(gs, argv[1:])
    return  # Not reachable
@@ -16,27 +16,25 @@
 # along with OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
 import os
 from os import fspath
 from pickle import dumps, loads
 from unittest.mock import patch
 import pytest
 from PIL import Image, ImageChops
-import ocrmypdf.leptonica as lept
+from ocrmypdf import leptonica as lp
 def test_colormap_backgroundnorm(resources):
    # Issue #262 - unclear how to reproduce exactly, so just ensure leptonica
    # can handle that case
-    pix = lept.Pix.open(resources / 'baiona_colormapped.png')
+    pix = lp.Pix.open(resources / 'baiona_colormapped.png')
    pix.background_norm()
@pytest.fixture
 def crom_pix(resources):
-    pix = lept.Pix.open(resources / 'crom.png')
+    pix = lp.Pix.open(resources / 'crom.png')
    im = Image.open(resources / 'crom.png')
    yield pix, im
    im.close()
@@ -64,17 +62,17 @@ def test_pix_otsu(crom_pix):
@pytest.mark.skipif(
-    lept.get_leptonica_version() < 'leptonica-1.76',
+    lp.get_leptonica_version() < 'leptonica-1.76',
    reason="needs new leptonica for API change",
 )
 def test_crop(resources):
-    pix = lept.Pix.open(resources / 'linn.png')
+    pix = lp.Pix.open(resources / 'linn.png')
    foreground = pix.crop_to_foreground()
    assert foreground.width < pix.width
 def test_clean_bg(resources):
-    pix = lept.Pix.open(resources / 'congress.jpg')
+    pix = lp.Pix.open(resources / 'congress.jpg')
    imbg = pix.clean_background_to_white()
@@ -96,4 +94,14 @@ def test_leptonica_compile(tmp_path):
 def test_file_not_found():
    with pytest.raises(FileNotFoundError):
-        lept.Pix.open("does_not_exist1")
+        lp.Pix.open("does_not_exist1")
@pytest.mark.skipif(
    lp.get_leptonica_version() < 'leptonica-1.79.0',
    reason="test not reliable on all platforms for old leptonica",
 )
 def test_error_trap():
    with pytest.raises(lp.LeptonicaError, match=r"Error in pixReadMem"):
        with lp._LeptonicaErrorTrap():
            lp.Pix(lp.lept.pixReadMem(lp.ffi.NULL, 0))
@@ -877,3 +877,17 @@ def test_image_dpi_not_image(caplog, resources, outpdf):
        'tests/plugins/tesseract_noop.py',
    )
    assert '--image-dpi is being ignored' in caplog.text
 def test_image_dpi_threshold(resources, outpdf):
    check_ocrmypdf(
        resources / 'typewriter.png',
        outpdf,
        '--threshold',
        '--image-dpi=170',
        '--output-type=pdf',
        '--optimize=0',
        '--plugin',
        'tests/plugins/tesseract_noop.py',
    )
    assert outpdf.exists()
@@ -21,7 +21,7 @@ from unittest.mock import patch
 import pikepdf
 import pytest
-import ocrmypdf._validation as vd
+from ocrmypdf import _validation as vd
 from ocrmypdf._plugin_manager import get_plugin_manager
 from ocrmypdf.api import create_options
 from ocrmypdf.cli import get_parser
@@ -141,7 +141,7 @@ def test_report_file_size(tmp_path, caplog):
    pdf = pikepdf.new()
    pdf.save(in_)
    pdf.save(out)
-    opts = make_opts()
+    opts = make_opts(output_type='pdf')
    vd.report_output_file_size(opts, in_, out)
    assert caplog.text == ''
    caplog.clear()
@@ -166,7 +166,7 @@ def test_report_file_size(tmp_path, caplog):
        assert 'optional dependency' in caplog.text
    caplog.clear()
-    opts = make_opts(in_, out, optimize=0)
+    opts = make_opts(in_, out, optimize=0, output_type='pdf')
    vd.report_output_file_size(opts, in_, out)
    assert 'disabled' in caplog.text
    caplog.clear()
Author	SHA1	Message	Date
James R. Barlow	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	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