Fixed setup.py syntax error

Better get the last one out

.gitattributes

@@ -8,6 +8,6 @@
 *.PDF	binary
 *.png	binary
 *.jpg	binary
-
+*.bin   binary
 
 .git_archival.txt  export-subst

.gitignore

@@ -35,7 +35,6 @@ log/
 /*.qdf
 *.ipynb
 .ipynb_checkpoints/
-tests/cache/
 tests/output/
 tests/resources/private/
 tmp/

.travis.yml

@@ -4,13 +4,10 @@ cache:
   pip: true
   directories:
   - packages
-  - tests/cache
   - $HOME/Library/Caches/Homebrew
 
 env:
   global:
-    - secure: "oyX5xesoHD7qcDXKIxMyGZPi+H/WxcvfFkaviEmq84K1DDyHk48+9e92IKgrw8/lcTADnEo/AgVKfnhCPflFimk1xTkgaK4sUg1WLI2YjmaHcwl5SlBHa2rN3uGBwy1hyP92qyv/mMc9R59NtRJ8u76lbn6eN9wi7lkFWdE6BTw="  # DOCKERHUB_OCRMYPDF_TOKEN
-    - secure: "WlyII8YLsiUUyLtEA563GvEZmbneDb/T8q/P1uNbyQ2ps1U82tH0nSUV2CspSMxOFtZzPHCrRvnAmuTYKshBj+GNnBb1J9FKQmFwF+4NPeqsFdUkQ1NeeCmfIRShuNC3Otg2GGwj4Zssdg+QnVy43t2L11qizzfY+lY+MVzAYcM="  # DOCKERHUB_OCRMYPDF_TESS4_TOKEN
     - secure: "hsf6MT+n2x3OiDM2fQyJZdV0/PWYmv81LdVqC6cfnHBE/8N3DloJRqQ7WfO14TxhiK9PEC7MpyCj0lSabUHEO7gSH6Vks6I1asoSkt8S9/bSMlhT4hei+pwVpeGEiU5xHVATNjY+D919VC3IFvc3XmjT74h/2SLhaZ+jhEmDggM="  # HOMEBREW_OCRMYPDF_TOKEN
 
 matrix:
@@ -19,13 +16,25 @@ matrix:
       sudo: required
       language: python
       python: 3.5
+      env: EXTRAS=
     - os: linux
       sudo: required
       language: python
       python: 3.6
+      env: EXTRAS=
+    - os: linux
+      sudo: required
+      language: python
+      python: 3.6
+      env: EXTRAS=[fitz]
     - os: osx
       osx_image: xcode8
       language: generic
+      env: EXTRAS=
+    - os: osx
+      osx_image: xcode8
+      language: generic
+      env: EXTRAS=[fitz]
 
 before_cache:
 - rm -f $HOME/.cache/pip/log/debug.log
@@ -40,24 +49,21 @@ before_install: |
   fi
 
 install:
-- pip3 install .
+- pip3 install ".$EXTRAS"
 - pip3 install -r requirements.txt -r test_requirements.txt
 
 script:
-- mv ocrmypdf dont_import_this_ocrmypdf
 - tesseract --version
 - qpdf --version
 - pytest
-- mv dont_import_this_ocrmypdf ocrmypdf
 
 deploy:
   # release for main pypi
-  # 3.6 is considered the build leader and does the deploy, otherwise there is
+  # 3.6 w/o fitz is considered the build leader and does the deploy, otherwise there is
   # a race and all versions will try to deploy
   # OTOH if we ever need separate binary wheels then each version needs its
   # own deploy
 - provider: pypi
-  server: https://upload.pypi.org/legacy/
   user: ocrmypdf-travis
   password:
     secure: "DTFOmmNL6olA0+yXvp4u9jXZlZeqrJsJ0526jzqf4a3gZ6jnGTq5UI6WzRsslSyoMMfXKtHQebqHM6ogSgCZinyZ3ufHJo8fn9brxbEc2gsiWkbj5o3bGwdWMT1vNNE7XW0VCpw87rZ1EEwjl4FJHFudMlPR1yfU5+uq0k0PACo="
@@ -65,7 +71,7 @@ deploy:
   on:
     branch: master
     tags: true
-    condition: $TRAVIS_PYTHON_VERSION == "3.6" && $TRAVIS_OS_NAME == "linux"
+    condition: $TRAVIS_PYTHON_VERSION == "3.6" && $TRAVIS_OS_NAME == "linux" && $EXTRAS == ""
   skip_upload_docs: true
 
   # test pypi
@@ -94,7 +100,4 @@ deploy:
 after_deploy: |
   if [[ "$TRAVIS_OS_NAME" == "osx" ]]; then
     bash .travis/osx_brew.sh
-  elif [[ "$TRAVIS_PYTHON_VERSION" == "3.6" && "$TRAVIS_OS_NAME" == "linux" ]]; then
-    curl -H "Content-Type: application/json" --data '{"build": true}' -X POST https://registry.hub.docker.com/u/jbarlow83/ocrmypdf/trigger/$DOCKERHUB_OCRMYPDF_TOKEN/
-    curl -H "Content-Type: application/json" --data '{"build": true}' -X POST https://registry.hub.docker.com/u/jbarlow83/ocrmypdf-tess4/trigger/$DOCKERHUB_OCRMYPDF_TESS4_TOKEN/
-  fi
+  fi

.travis/Brewfile

@@ -6,6 +6,7 @@ brew 'leptonica'
 brew 'libffi'
 brew 'libtiff'
 brew 'libxml2'
+brew 'mupdf-tools'
 brew 'openjpeg'
 brew 'qpdf'
 brew 'tesseract'

.travis/autobrew.py

@@ -15,6 +15,7 @@ class Ocrmypdf < Formula
   ${ocrmypdf_sha256}
 
   depends_on "pkg-config" => :build
+  depends_on "mupdf-tools" => :build  # statically links libmupdf.a
   depends_on "freetype"
   depends_on "ghostscript"
   depends_on "jpeg"

.travis/osx_brew.sh

@@ -1,6 +1,6 @@
 #!/bin/bash
 # © 2017 James R. Barlow: github.com/jbarlow83
-set -euo pipefail
+set -uo pipefail
 set -x
 
 pip3 install homebrew-pypi-poet

LICENSE

@@ -0,0 +1,674 @@
+                    GNU GENERAL PUBLIC LICENSE
+                       Version 3, 29 June 2007
+
+ Copyright (C) 2007 Free Software Foundation, Inc. <https://fsf.org/>
+ Everyone is permitted to copy and distribute verbatim copies
+ of this license document, but changing it is not allowed.
+
+                            Preamble
+
+  The GNU General Public License is a free, copyleft license for
+software and other kinds of works.
+
+  The licenses for most software and other practical works are designed
+to take away your freedom to share and change the works.  By contrast,
+the GNU General Public License is 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.  We, the Free Software Foundation, use the
+GNU General Public License for most of our software; it applies also to
+any other work released this way by its authors.  You can apply it to
+your programs, too.
+
+  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.
+
+  To protect your rights, we need to prevent others from denying you
+these rights or asking you to surrender the rights.  Therefore, you have
+certain responsibilities if you distribute copies of the software, or if
+you modify it: responsibilities to respect the freedom of others.
+
+  For example, if you distribute copies of such a program, whether
+gratis or for a fee, you must pass on to the recipients the same
+freedoms that you received.  You must make sure that they, too, receive
+or can get the source code.  And you must show them these terms so they
+know their rights.
+
+  Developers that use the GNU GPL protect your rights with two steps:
+(1) assert copyright on the software, and (2) offer you this License
+giving you legal permission to copy, distribute and/or modify it.
+
+  For the developers' and authors' protection, the GPL clearly explains
+that there is no warranty for this free software.  For both users' and
+authors' sake, the GPL requires that modified versions be marked as
+changed, so that their problems will not be attributed erroneously to
+authors of previous versions.
+
+  Some devices are designed to deny users access to install or run
+modified versions of the software inside them, although the manufacturer
+can do so.  This is fundamentally incompatible with the aim of
+protecting users' freedom to change the software.  The systematic
+pattern of such abuse occurs in the area of products for individuals to
+use, which is precisely where it is most unacceptable.  Therefore, we
+have designed this version of the GPL to prohibit the practice for those
+products.  If such problems arise substantially in other domains, we
+stand ready to extend this provision to those domains in future versions
+of the GPL, as needed to protect the freedom of users.
+
+  Finally, every program is threatened constantly by software patents.
+States should not allow patents to restrict development and use of
+software on general-purpose computers, but in those that do, we wish to
+avoid the special danger that patents applied to a free program could
+make it effectively proprietary.  To prevent this, the GPL assures that
+patents cannot be used to render the program non-free.
+
+  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 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. Use with the GNU Affero General Public License.
+
+  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 Affero 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 special requirements of the GNU Affero General Public License,
+section 13, concerning interaction through a network will apply to the
+combination as such.
+
+  14. Revised Versions of this License.
+
+  The Free Software Foundation may publish revised and/or new versions of
+the GNU 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 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 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 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 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 General Public License for more details.
+
+    You should have received a copy of the GNU General Public License
+    along with this program.  If not, see <https://www.gnu.org/licenses/>.
+
+Also add information on how to contact you by electronic and paper mail.
+
+  If the program does terminal interaction, make it output a short
+notice like this when it starts in an interactive mode:
+
+    <program>  Copyright (C) <year>  <name of author>
+    This program comes with ABSOLUTELY NO WARRANTY; for details type `show w'.
+    This is free software, and you are welcome to redistribute it
+    under certain conditions; type `show c' for details.
+
+The hypothetical commands `show w' and `show c' should show the appropriate
+parts of the General Public License.  Of course, your program's commands
+might be different; for a GUI interface, you would use an "about box".
+
+  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 GPL, see
+<https://www.gnu.org/licenses/>.
+
+  The GNU General Public License does not permit incorporating your program
+into proprietary programs.  If your program is a subroutine library, you
+may consider it more useful to permit linking proprietary applications with
+the library.  If this is what you want to do, use the GNU Lesser General
+Public License instead of this License.  But first, please read
+<https://www.gnu.org/licenses/why-not-lgpl.html>.

LICENSE.rst

@@ -1,23 +0,0 @@
-Copyright (c) 2014-2017, James R. Barlow
-
-Copyright (c) 2013-2014, Julien Pfefferkorn
-Copyright (c) 2013-2017, The OCRmyPDF Authors
-
-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.

MANIFEST.in

@@ -7,11 +7,10 @@ include dev_requirements.txt
 include .git_archival.txt
 
 # docker
-include Dockerfile*
 include .dockerignore
+recursive-include .docker *
 
 # tests
-include pytest.ini
 include .coveragerc
 recursive-include tests *.jpg
 recursive-include tests *.png
@@ -19,14 +18,14 @@ recursive-include tests *.pdf
 recursive-include tests *.py
 recursive-include tests *.rst
 recursive-include tests *.txt
+recursive-include tests/cache *
 recursive-exclude tests/output *
 recursive-exclude tests/output_pageinfo *
 recursive-exclude tests/resources/private *
-recursive-exclude tests/cache *
 
 # documentation
+include LICENSE
 include *.rst
-include pipeline.svg
 recursive-exclude .github * 
 recursive-include docs *.py
 recursive-include docs *.rst
@@ -35,17 +34,16 @@ recursive-exclude docs/_build *
 
 
 # support files
-recursive-include ocrmypdf/data *
+recursive-include src/ocrmypdf/data *
 include *.py
 exclude tasks.py
-exclude debug-runner.py
 recursive-exclude .travis *
 exclude .travis*
 
 
 # code
-recursive-include ocrmypdf *.py
+recursive-include src/ocrmypdf *.py
 exclude ocrmypdf/lib/_leptonica.py
-include docker-wrapper.sh
+
 
 

README.rst

@@ -7,8 +7,10 @@ OCRmyPDF
 .. image:: https://img.shields.io/pypi/v/ocrmypdf.svg   
     :target: https://pypi.org/project/ocrmypdf/
 
-.. image:: https://img.shields.io/docker/build/jbarlow83/ocrmypdf.svg
-    :target: https://hub.docker.com/r/jbarlow83/ocrmypdf/
+.. image:: https://img.shields.io/homebrew/v/ocrmypdf.svg   
+    :alt: homebrew
+    :target: http://brewformulas.org/Ocrmypdf
+
 
 OCRmyPDF adds an OCR text layer to scanned PDF files, allowing them to
 be searched or copy-pasted.
@@ -137,6 +139,15 @@ Press & Media
 -  `heise Open Source, 09/2014: Texterkennung mit
    OCRmyPDF <http://heise.de/-2356670>`_
 
+License
+-------
+
+The OCRmyPDF software is licensed under the GNU GPLv3. Certain files are covered by other licenses, as noted in their source files. 
+
+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).
+
+OCRmyPDF versions prior to 6.0 were licensed under the MIT License.
+
 Disclaimer
 ----------
 

dev_requirements.txt

@@ -1,10 +1,4 @@
 check-manifest >= 0.35
 twine >= 1.8.1
 coverage >= 4.4
-pytest-xdist >= 1.16.0
 GitPython == 2.1.3
-
-# Known good versions: 1.11.1
-# Known broken versions: 1.15.0
-setuptools-scm == 1.11.1
-setuptools-scm-git-archive == 1.0

docs/advanced.rst

@@ -33,11 +33,7 @@ If you want to adjust the amount of time spent on OCR, change ``--tesseract-time
 Overriding default tesseract
 """"""""""""""""""""""""""""
 
-OCRmyPDF checks the environment variable ``OCRMYPDF_TESSERACT`` for the full path *to the tesseract binary* first. 
-
-.. envvar:: OCRMYPDF_TESSERACT
-
-	Specify the location of the Tesseract binary.
+OCRmyPDF checks the system ``PATH`` for the ``tesseract`` binary.
 
 .. envvar:: TESSDATA_PREFIX
 
@@ -48,11 +44,11 @@ For example, if you are testing tesseract 4.00 and don't wish to use an existing
 .. code-block:: bash
 
 	env \
-		OCRMYPDF_TESSERACT=/home/user/src/tesseract4/api/tesseract \
+		PATH=/home/user/src/tesseract4/api:$PATH \
 		TESSDATA_PREFIX=/home/user/src/tesseract4 \
 		ocrmypdf --tesseract-oem 2 input.pdf output.pdf
 
-In this example ``TESSDATA_PREFIX`` directs tesseract 4.0 to use LSTM training data. ``--tesseract-oem 1`` requests tesseract 4.0's new LSTM engine. (Tesseract 4.0 only.)
+In this example ``TESSDATA_PREFIX`` directs Tesseract 4.0 to use LSTM training data. ``--tesseract-oem 1`` requests tesseract 4.0's new LSTM engine. (Tesseract 4.0 only.)
 
 
 Overriding other support programs
@@ -64,19 +60,7 @@ In addition to tesseract, OCRmyPDF uses the following external binaries:
 * ``unpaper``
 * ``qpdf``
 
-In each case OCRmyPDF will check the environment variable ``OCRMYPDF_{program}`` before asking the system to find ``{program}`` on the PATH. For example, you could redirect OCRmyPDF to ``OCRMYPDF_GS`` to override Ghostscript. The full list is below:
-
-.. envvar:: OCRMYPDF_GS
-
-	Specify the location of the Ghostscript binary.
-
-.. envvar:: OCRMYPDF_UNPAPER
-
-	Specify the location of the unpaper binary.
-
-.. envvar:: OCRMYPDF_QPDF
-
-	Specify the location of the qpdf binary.
+In each case OCRmyPDF will search the ``PATH`` environment variable to locate the binaries.
 
 
 Changing tesseract configuration variables

docs/batch.rst

@@ -18,6 +18,8 @@ The ``--tag`` argument tells parallel to print the filename as a prefix whenever
 
 	parallel --tag -j 2 ocrmypdf '{}' 'output/{}' ::: *.pdf
 
+OCRmyPDF automaticaly repairs PDFs before parsing and gathering information from them.  If you are already repairing PDFs with ``qpdf`` prior to attempting OCR, or you can use ``--skip-repair`` to skip this step.  It may improve performance for large files, since repairing PDFs is single-threaded.
+
 Directory trees
 ---------------
 

docs/conf.py

@@ -52,7 +52,7 @@ master_doc = 'index'
 
 # General information about the project.
 project = 'ocrmypdf'
-copyright = '2017, James R. Barlow'
+copyright = '2018, James R. Barlow. Licensed under Creative Commons Attribution-ShareAlike 4.0.'
 author = 'James R. Barlow'
 
 # The version info for the project you're documenting, acts as replacement for
@@ -60,7 +60,7 @@ author = 'James R. Barlow'
 # built documents.
 #
 # The short X.Y version.
-from ocrmypdf import VERSION as OCRMYPDF_VERSION
+from ocrmypdf import __version__ as OCRMYPDF_VERSION
 
 _version_parts = OCRMYPDF_VERSION.split('.')
 

docs/introduction.rst

@@ -104,5 +104,11 @@ To the author's knowledge, OCRmyPDF is the most feature-rich and thoroughly test
 * pypdfocr
 * pdfbeads
 
-If you are looking for a micro web-frontend for OCRmyPDF, consider the third-party `OCRmyPDF-web <https://github.com/sseemayer/OCRmyPDF-web>`_. Bear in mind that OCRmyPDF is not designed to be secure against malware-bearing PDFs (see `Using OCRmyPDF online`_).
+Web front-ends
+--------------
+
+* `Nextcloud OCR <https://github.com/janis91/ocr>`_ is a free software plugin for the Nextcloud private cloud software
+* `OCRmyPDF-web <https://github.com/sseemayer/OCRmyPDF-web>`_, a micro web-frontend for OCRmyPDF (third-party, not actively maintained)
+
+Bear in mind that OCRmyPDF is not designed to be secure against malware-bearing PDFs (see `Using OCRmyPDF online`_).
 

docs/release_notes.rst

@@ -5,6 +5,62 @@ OCRmyPDF uses `semantic versioning <http://semver.org/>`_ for its command line i
 
 The OCRmyPDF package itself does not contain a public API, although it is fairly stable and breaking changes are usually timed with a major release. A future release will clearly define the stable public API.
 
+v6.1.2
+------
+
+-   Upgrade to PyMuPDF v1.12.5 which includes a more complete fix to #239.
+
+-   Add ``defusedxml`` dependency.
+
+
+v6.1.1
+------
+
+-   Fix text being reported as found on all pages if PyMuPDF is not installed.
+
+
+v6.1.0
+------
+
+-   PyMuPDF is now an optional but recommended dependency, to alleviate installation difficulties on platforms that have less access to PyMuPDF than the author anticipated.  Install OCRmyPDF with ``pip install ocrmypdf[fitz]`` to use it to its full potential.
+
+-   Fix ``FileExistsError`` that could occur if OCR timed out while it was generating the output file. (#218)
+
+-   Fix table of contents/bookmarks all being redirected to page 1 when generating a PDF/A (with PyMuPDF).  (Without PyMuPDF the table of contents is removed in PDF/A mode.)
+
+-   Fix "RuntimeError: invalid key in dict" when table of contents/bookmarks titles contained the character ``)``. (#239)
+
+-   Added a new argument ``--skip-repair`` to skip the initial PDF repair step if the PDF is already well-formed (because another program repaired it).
+
+
+v6.0.0
+------
+
+-   The software license has been changed to GPLv3. 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.
+
+-   Other backward incompatible changes
+
+    + The ``OCRMYPDF_TESSERACT``, ``OCRMYPDF_QPDF``, ``OCRMYPDF_GS`` and ``OCRMYPDF_UNPAPER`` environment variables are no longer used. Change ``PATH`` if you need to override the external programs OCRmyPDF uses.
+
+    + The ``ocrmypdf`` package has been moved to ``src/ocrmypdf`` to avoid issues with accidental import.
+
+    + The function ``ocrmypdf.exec.get_program`` was removed.
+
+    + The deprecated module ``ocrmypdf.pageinfo`` was removed.
+
+    + The ``--pdf-renderer tess4`` alias for ``sandwich`` was removed.
+
+-   Fixed an issue where OCRmyPDF failed to detect existing text on pages, depending on how the text and fonts were encoded within the PDF. (#233, #232)
+
+-   Fixed an issue that caused dramatic inflation of file sizes when ``--skip-text --output-type pdf`` was used. OCRmyPDF now removes duplicate resources such as fonts, images and other objects that it generates. (#237)
+
+-   Improved performance of the initial page splitting step. Originally this step was not believed to be expensive and ran in a process. Large file testing revealed it to be a bottleneck, so it is now parallelized. On a 700 page file with quad core machine, this change saves about 2 minutes. (#234)
+
+-   The test suite now includes a cache that can be used to speed up test runs across platforms. This also does not require computing checksums, so it's faster. (#217)
+
+
 v5.7.0
 ------
 

ocrmypdf/__init__.py

@@ -1,10 +0,0 @@
-# © 2017 James R. Barlow: github.com/jbarlow83
-
-import pkg_resources
-
-PROGRAM_NAME = 'ocrmypdf'
-
-# Official PEP 396
-__version__ = pkg_resources.get_distribution('ocrmypdf').version
-
-VERSION = __version__

ocrmypdf/lib/__init__.py

@@ -1,2 +0,0 @@
-"""Bindings to external libraries"""
-# © 2017 James R. Barlow: github.com/jbarlow83

ocrmypdf/pageinfo.py

@@ -1,538 +0,0 @@
-#!/usr/bin/env python3
-# © 2015 James R. Barlow: github.com/jbarlow83
-
-from subprocess import Popen, PIPE
-from decimal import Decimal
-from math import hypot, isclose
-import re
-import sys
-import PyPDF2 as pypdf
-from collections import namedtuple
-import warnings
-
-
-warnings.warn("ocrmypdf.pageinfo is deprecated'; use ocrmypdf.pdfinfo",
-              DeprecationWarning)
-
-matrix_mult = pypdf.pdf.utils.matrixMultiply
-
-FRIENDLY_COLORSPACE = {
-    '/DeviceGray': 'gray',
-    '/CalGray': 'gray',
-    '/DeviceRGB': 'rgb',
-    '/CalRGB': 'rgb',
-    '/DeviceCMYK': 'cmyk',
-    '/Lab': 'lab',
-    '/ICCBased': 'icc',
-    '/Indexed': 'index',
-    '/Separation': 'sep',
-    '/DeviceN': 'devn',
-    '/Pattern': '-',
-    '/G': 'gray',  # Abbreviations permitted in inline images
-    '/RGB': 'rgb',
-    '/CMYK': 'cmyk',
-    '/I': 'index',
-}
-
-FRIENDLY_ENCODING = {
-    '/CCITTFaxDecode': 'ccitt',
-    '/DCTDecode': 'jpeg',
-    '/JPXDecode': 'jpx',
-    '/JBIG2Decode': 'jbig2',
-    '/CCF': 'ccitt',  # Abbreviations permitted in inline images
-    '/DCT': 'jpeg',
-    '/AHx': 'asciihex',
-    '/A85': 'ascii85',
-    '/LZW': 'lzw',
-    '/Fl': 'flate',
-    '/RL': 'runlength'
-}
-
-FRIENDLY_COMP = {
-    'gray': 1,
-    'rgb': 3,
-    'cmyk': 4,
-    'lab': 3,
-    'index': 1
-}
-
-
-UNIT_SQUARE = (1.0, 0.0, 0.0, 1.0, 0.0, 0.0)
-
-
-def _matrix_from_shorthand(shorthand):
-    """Convert from PDF matrix shorthand to full matrix
-
-    PDF 1.7 spec defines a shorthand for describing the entries of a matrix
-    since the last column is always (0, 0, 1).
-    """
-
-    a, b, c, d, e, f = map(float, shorthand)
-    return ((a, b, 0),
-            (c, d, 0),
-            (e, f, 1))
-
-
-def _shorthand_from_matrix(matrix):
-    """Convert from transformation matrix to PDF shorthand."""
-    a, b = matrix[0][0], matrix[0][1]
-    c, d = matrix[1][0], matrix[1][1]
-    e, f = matrix[2][0], matrix[2][1]
-    return tuple(map(float, (a, b, c, d, e, f)))
-
-
-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])
-
-XobjectSettings = namedtuple('XobjectSettings',
-    ['name', 'shorthand', 'stack_depth'])
-
-InlineSettings = namedtuple('InlineSettings',
-    ['settings', 'shorthand', 'stack_depth'])
-
-ContentsInfo = namedtuple('ContentsInfo', ['xobject_settings', 'inline_images'])
-
-
-def _normalize_stack(operations):
-    """Fix runs of qQ's in the stack
-
-    For some reason PyPDF2 converts runs of qqq, QQ, QQQq, etc. into single
-    operations.  Break this silliness up and issue each stack operation
-    individually so we don't lose count.
-
-    """
-    for operands, command in operations:
-        if re.match(br'Q*q+$', command):   # Zero or more Q, one or more q
-            for char in command:           # Split into individual bytes
-                yield ([], bytes([char]))  # Yield individual bytes
-        else:
-            yield (operands, command)
-
-
-def _interpret_contents(contentstream, initial_shorthand=UNIT_SQUARE):
-    """Interpret the PDF content stream
-
-    The stack represents the state of the PDF graphics stack.  We are only
-    interested in the current transformation matrix (CTM) so we only track
-    this object; a full implementation would need to track many other items.
-
-    The CTM is initialized to the mapping from user space to device space.
-    PDF units are 1/72".  In a PDF viewer or printer this matrix is initialized
-    to the transformation to device space.  For example if set to
-    (1/72, 0, 0, 1/72, 0, 0) then all units would be calculated in inches.
-
-    Images are always considered to be (0, 0) -> (1, 1).  Before drawing an
-    image there should be a 'cm' that sets up an image coordinate system
-    where drawing from (0, 0) -> (1, 1) will draw on the desired area of the
-    page.
-
-    PDF units suit our needs so we initialize ctm to the identity matrix.
-
-    PyPDF2 replaces inline images with a fake "INLINE IMAGE" operator.
-
-    """
-
-    operations = contentstream.operations
-    stack = []
-    ctm = _matrix_from_shorthand(initial_shorthand)
-    xobject_settings = []
-    inline_images = []
-
-    for n, op in enumerate(_normalize_stack(operations)):
-        operands, command = op
-        if command == b'q':
-            stack.append(ctm)
-            if len(stack) > 32:
-                raise RuntimeError(
-                    "PDF graphics stack overflow, command %i" % n)
-        elif command == b'Q':
-            try:
-                ctm = stack.pop()
-            except IndexError:
-                raise RuntimeError(
-                    "PDF graphics stack underflow, command %i" % n)
-        elif command == b'cm':
-            ctm = matrix_mult(
-                _matrix_from_shorthand(operands), ctm)
-        elif command == b'Do':
-            image_name = operands[0]
-            settings = XobjectSettings(
-                name=image_name, shorthand=_shorthand_from_matrix(ctm),
-                stack_depth=len(stack))
-            xobject_settings.append(settings)
-        elif command == b'INLINE IMAGE':
-            settings = operands['settings']
-            inline = InlineSettings(
-                settings=settings, shorthand=_shorthand_from_matrix(ctm),
-                stack_depth=len(stack))
-            inline_images.append(inline)
-
-    return ContentsInfo(
-        xobject_settings=xobject_settings,
-        inline_images=inline_images)
-
-
-def _get_dpi(ctm_shorthand, image_size):
-    """Given the transformation matrix and image size, find the image DPI.
-
-    PDFs do not include image resolution information within image data.
-    Instead, the PDF page content stream describes the location where the
-    image will be rasterized, and the effective resolution is the ratio of the
-    pixel size to raster target size.
-
-    Normally a scanned PDF has the paper size set appropriately but this is
-    not guaranteed. The most common case is a cropped image will change the
-    page size (/CropBox) without altering the page content stream. That means
-    it is not sufficient to assume that the image fills the page, even though
-    that is the most common case.
-
-    A PDF image may be scaled (always), cropped, translated, rotated in place
-    to an arbitrary angle (rarely) and skewed. Only equal area mappings can
-    be expressed, that is, it is not necessary to consider distortions where
-    the effective DPI varies with position.
-
-    To determine the image scale, transform an offset axis vector v0 (0, 0),
-    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
-    matrix * column vector.
-
-    The offset, width and height vectors can be combined in a matrix and
-    multiplied by the transform matrix. Then we want to calculated
-        magnitude(width_vector - offset_vector)
-    and
-        magnitude(height_vector - offset_vector)
-
-    When the above is worked out algebraically, the effect of translation
-    cancels out, and the vector magnitudes become functions of the nonzero
-    transformation matrix indices. The results of the derivation are used
-    in this code.
-
-    pdfimages -list does calculate the DPI in some way that is not completely
-    naive, but it does not get the DPI of rotated images right, so cannot be
-    used anymore to validate this. Photoshop works, or using Acrobat to
-    rotate the image back to normal.
-
-    It does not matter if the image is partially cropped, or even out of the
-    /MediaBox.
-
-    """
-
-    a, b, c, d, _, _ = ctm_shorthand
-
-    # Calculate the width and height of the image in PDF units
-    image_drawn_width = hypot(a, b)
-    image_drawn_height = hypot(c, d)
-
-    # The scale of the image is pixels per PDF unit (1/72")
-    scale_w = image_size[0] / image_drawn_width
-    scale_h = image_size[1] / image_drawn_height
-
-    # DPI = scale * 72
-    dpi_w = scale_w * 72.0
-    dpi_h = scale_h * 72.0
-
-    return (dpi_w, dpi_h)
-
-
-def _find_inline_images(contentsinfo):
-    "Find inline images in the contentstream"
-
-    for n, inline in enumerate(contentsinfo.inline_images):
-        image = {}
-        image['name'] = str('inline-%02d' % n)
-        image['width'] = inline.settings['/W']
-        image['height'] = inline.settings['/H']
-        if '/BPC' in inline.settings:
-            image['bpc'] = inline.settings['/BPC']
-        else:
-            image['bpc'] = 8
-        if '/CS' in inline.settings:
-            image['color'] = FRIENDLY_COLORSPACE.get(inline.settings['/CS'], '-')
-        else:
-            image['color'] = '-'
-        image['comp'] = FRIENDLY_COMP.get(image['color'], '?')
-        if '/F' in inline.settings:
-            filter_ = inline.settings['/F']
-            if isinstance(filter_, pypdf.generic.ArrayObject):
-                filter_ = filter_[0]
-            image['enc'] = FRIENDLY_ENCODING.get(filter_, 'image')
-        else:
-            image['enc'] = 'image'
-
-        dpi_w, dpi_h = _get_dpi(
-            inline.shorthand, (image['width'], image['height']))
-        image['dpi_w'], image['dpi_h'] = Decimal(dpi_w), Decimal(dpi_h)
-        yield image
-
-
-def _image_xobjects(container):
-    """Search for all XObject-based images in the container
-
-    Usually the container is a page, but it could also be a Form XObject
-    that contains images. Filter out the Form XObjects which are dealt with
-    elsewhere.
-
-    Generate a sequence of tuples (image, xobj container), where container,
-    where xobj is the name of the object and image is the object itself,
-    since the object does not know its own name.
-
-    """
-
-    if '/Resources' not in container:
-        return
-    resources = container['/Resources']
-    if '/XObject' not in resources:
-        return
-    for xobj in resources['/XObject']:
-        candidate = resources['/XObject'][xobj]
-        if candidate['/Subtype'] == '/Image':
-            image = candidate
-            yield (image, xobj)
-
-
-def _find_regular_images(container, contentsinfo):
-    """Find images stored in the container's /Resources /XObject
-
-    Usually the container is a page, but it could also be a Form XObject
-    that contains images.
-
-    Generates images with their DPI at time of drawing.
-
-    """
-
-    for pdfimage, xobj in _image_xobjects(container):
-        image = {}
-        image['name'] = xobj
-        image['width'] = pdfimage['/Width']
-        image['height'] = pdfimage['/Height']
-        if '/BitsPerComponent' in pdfimage:
-            image['bpc'] = pdfimage['/BitsPerComponent']
-        else:
-            image['bpc'] = 8
-
-        # Fixme: this is incorrectly treats explicit masks as stencil masks,
-        # but good enough for now. Explicit masks have /ImageMask true but are
-        # never called for in content stream, instead are drawn as a /Mask on
-        # other images. For our purposes finding out the details of /Mask
-        # will seldom matter.
-        if '/ImageMask' in pdfimage:
-            image['type'] = 'stencil' if pdfimage['/ImageMask'].value \
-                            else 'image'
-        else:
-            image['type'] = 'image'
-        if '/Filter' in pdfimage:
-            filter_ = pdfimage['/Filter']
-            if isinstance(filter_, pypdf.generic.ArrayObject):
-                filter_ = filter_[0]
-            image['enc'] = FRIENDLY_ENCODING.get(filter_, 'image')
-        else:
-            image['enc'] = 'image'
-        if '/ColorSpace' in pdfimage:
-            cs = pdfimage['/ColorSpace']
-            if isinstance(cs, pypdf.generic.ArrayObject):
-                cs = cs[0]
-            image['color'] = FRIENDLY_COLORSPACE.get(cs, '-')
-        else:
-            image['color'] = 'jpx' if image['enc'] == 'jpx' else '?'
-
-        image['comp'] = FRIENDLY_COMP.get(image['color'], '?')
-
-        # Bit of a hack... infer grayscale if component count is uncertain
-        # but encoding must be monochrome. This happens if a monochrome image
-        # has an ICC profile attached. Better solution would be to examine
-        # the ICC profile.
-        if image['comp'] == '?' and image['enc'] in ('ccitt', 'jbig2'):
-            image['comp'] = FRIENDLY_COMP['gray']
-
-        image['dpi_w'] = image['dpi_h'] = 0
-
-        for xobj in contentsinfo.xobject_settings:
-            # Loop in case the same image is display multiple times on a page
-            if xobj.name != image['name']:
-                continue
-
-            if xobj.stack_depth == 0 and _is_unit_square(xobj.shorthand):
-                # At least one PDF in the wild (and test suite) draws an image
-                # when the graphics stack depth is 0, meaning that the image
-                # gets drawn into a square of 1x1 PDF units (or 1/72",
-                # or 0.35 mm).  The equivalent DPI will be >100,000.  Exclude
-                # these from our DPI calculation for the page.
-                continue
-
-            dpi_w, dpi_h = _get_dpi(
-                xobj.shorthand, (image['width'], image['height']))
-
-            # When image is used multiple times take the highest DPI it is
-            # rendered at
-            image['dpi_w'] = max(dpi_w, image.get('dpi_w', 0))
-            image['dpi_h'] = max(dpi_h, image.get('dpi_h', 0))
-
-        DPI_PREC = Decimal('1.000')
-        dpi = Decimal(image['dpi_w'] * image['dpi_h']).sqrt()
-        image['dpi_w'] = Decimal(image['dpi_w']).quantize(DPI_PREC)
-        image['dpi_h'] = Decimal(image['dpi_h']).quantize(DPI_PREC)
-        image['dpi'] = dpi.quantize(DPI_PREC)
-        yield image
-
-
-def _find_form_xobject_images(pdf, container, contentsinfo):
-    """Find any images that are in Form XObjects in the container
-
-    The container may be a page, or a parent Form XObject.
-
-    """
-    if '/Resources' not in container:
-        return
-    resources = container['/Resources']
-    if '/XObject' not in resources:
-        return
-    for xobj in resources['/XObject']:
-        candidate = resources['/XObject'][xobj]
-        if candidate['/Subtype'] != '/Form':
-            continue
-
-        form_xobject = candidate
-        for settings in contentsinfo.xobject_settings:
-            if settings.name != xobj:
-                continue
-
-            # Find images once for each time this Form XObject is drawn.
-            # This could be optimized to cache the multiple drawing events
-            # but in practice both Form XObjects and multiple drawing of the
-            # same object are both very rare.
-            ctm_shorthand = settings.shorthand
-            yield from _find_images(pdf, form_xobject, ctm_shorthand)
-
-
-def _find_images(pdf, container, shorthand=None):
-    """Find all individual instances of images drawn in the container
-
-    Usually the container is a page, but it may also be a Form XObject.
-
-    On a typical page images are stored inline or as regular images
-    in an XObject.
-
-    Form XObjects may include inline images, XObject images,
-    and recursively, other Form XObjects; and also vector drawing commands.
-
-    Every instance of an image being drawn somewhere is flattened and
-    treated as a unique image, since if the same image is drawn multiple times
-    on one page it may be drawn at differing resolutions, and our objective
-    is to find the resolution at which the page can be rastered without
-    downsampling.
-
-    """
-
-    if container.get('/Type') == '/Page' and '/Contents' in container:
-        # For a /Page the content stream is attached to the page's /Contents
-        page = container
-        contentstream = pypdf.pdf.ContentStream(page.getContents(), pdf)
-        initial_shorthand = shorthand or UNIT_SQUARE
-    elif container.get('/Type') == '/XObject' and \
-            container['/Subtype'] == '/Form':
-        # For a Form XObject that content stream is attached to the XObject
-        contentstream = pypdf.pdf.ContentStream(container, pdf)
-
-        # Set the CTM to the state it was when the "Do" operator was
-        # encountered that is drawing this instance of the Form XObject
-        ctm = _matrix_from_shorthand(shorthand or UNIT_SQUARE)
-
-        # A Form XObject may provide its own matrix to map form space into
-        # user space. Get this if one exists
-        form_matrix = _matrix_from_shorthand(
-                container.get('/Matrix', UNIT_SQUARE))
-
-        # Concatenate form matrix with CTM to ensure CTM is correct for
-        # drawing this instance of the XObject
-        ctm = matrix_mult(form_matrix, ctm)
-        initial_shorthand = _shorthand_from_matrix(ctm)
-    else:
-        return
-
-    contentsinfo = _interpret_contents(contentstream, initial_shorthand)
-
-    yield from _find_inline_images(contentsinfo)
-    yield from _find_regular_images(container, contentsinfo)
-    yield from _find_form_xobject_images(pdf, container, contentsinfo)
-
-
-def _page_has_text(pdf, page):
-    if not '/Contents' in page:
-        return False
-
-    # Simple test
-    text = page.extractText()
-    if text.strip() != '':
-        return True
-
-    # More nuanced test to deal with quirks of Tesseract PDF generation
-    # Check if there's a Glyphless font
-    try:
-        font = page['/Resources']['/Font']
-    except KeyError:
-        pass
-    else:
-        font_objects = list(font.keys())
-        for font_object in font_objects:
-            basefont = font[font_object]['/BaseFont']
-            if basefont.endswith('GlyphLessFont'):
-                return True
-
-    return False
-
-
-def _pdf_get_pageinfo(infile, pageno: int):
-    pageinfo = {}
-    pageinfo['pageno'] = pageno
-    pageinfo['images'] = []
-
-    pdf = pypdf.PdfFileReader(infile)
-    page = pdf.pages[pageno]
-
-    pageinfo['has_text'] = _page_has_text(pdf, page)
-
-    width_pt = page.mediaBox.getWidth()
-    height_pt = page.mediaBox.getHeight()
-    pageinfo['width_inches'] = width_pt / Decimal(72.0)
-    pageinfo['height_inches'] = height_pt / Decimal(72.0)
-
-    try:
-        pageinfo['rotate'] = int(page['/Rotate'])
-    except KeyError:
-        pageinfo['rotate'] = 0
-
-    pageinfo['images'] = [im for im in
-                          _find_images(pdf, page)]
-    if pageinfo['images']:
-        xres = max(image['dpi_w'] for image in pageinfo['images'])
-        yres = max(image['dpi_h'] for image in pageinfo['images'])
-        pageinfo['xres'], pageinfo['yres'] = xres, yres
-        pageinfo['width_pixels'] = \
-            int(round(xres * pageinfo['width_inches']))
-        pageinfo['height_pixels'] = \
-            int(round(yres * pageinfo['height_inches']))
-
-    return pageinfo
-
-
-def pdf_get_all_pageinfo(infile):
-    pdf = pypdf.PdfFileReader(infile)
-    return [_pdf_get_pageinfo(infile, n) for n in range(pdf.numPages)]
-
-
-def main():
-    import argparse
-    parser = argparse.ArgumentParser()
-    parser.add_argument('infile')
-    args = parser.parse_args()
-    info = pdf_get_all_pageinfo(args.infile)
-    from pprint import pprint
-    pprint(info)
-
-
-if __name__ == '__main__':
-    main()

requirements.txt

@@ -6,4 +6,5 @@ Pillow == 5.0.0
 reportlab == 3.4.0
 PyPDF2 == 1.26.0
 img2pdf == 0.2.4
-cffi == 1.11.2
+cffi == 1.11.5
+PyMuPDF == 1.12.4

setup.cfg

@@ -11,4 +11,7 @@ ignore =
 [tool:pytest]
 norecursedirs = lib .pc .git output cache resources
 testpaths = tests
-addopts = -n auto
+addopts = -n auto
+
+[metadata]
+license_file = LICENSE

setup.py

@@ -1,6 +1,21 @@
 #!/usr/bin/env python3
 # -*- 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/>.
 
 from __future__ import print_function, unicode_literals
 
@@ -197,8 +212,8 @@ setup(
     url='https://github.com/jbarlow83/OCRmyPDF',
     author='James R. Barlow',
     author_email='jim@purplerock.ca',
-    license='MIT',
-    packages=find_packages(exclude=["tests", "tests.*"]),
+    packages=find_packages('src', exclude=["tests", "tests.*"]),
+    package_dir={'': 'src'},
     keywords=['PDF', 'OCR', 'optical character recognition', 'PDF/A', 'scanning'],
     classifiers=[
         "Programming Language :: Python :: 3.5",
@@ -208,7 +223,7 @@ setup(
         "Intended Audience :: End Users/Desktop",
         "Intended Audience :: Science/Research",
         "Intended Audience :: System Administrators",
-        "License :: OSI Approved :: MIT License",
+        "License :: OSI Approved :: GNU General Public License v3 (GPLv3)",
         "Operating System :: MacOS :: MacOS X",
         "Operating System :: POSIX",
         "Operating System :: POSIX :: BSD",
@@ -217,24 +232,28 @@ setup(
         "Topic :: Text Processing :: Indexing",
         "Topic :: Text Processing :: Linguistic",
         ],
-    python_requires='>=3.5',
+    python_requires=' >= 3.5',
     setup_requires=[
+        'cffi >= 1.9.1',        # to build the leptonica module
+        'pytest-runner',        # to enable python setup.py test
         'setuptools_scm',       # so that version will work
-        'cffi>=1.9.1',          # to build the leptonica module
-        'pytest-runner'         # to enable python setup.py test
     ],
     use_scm_version={'version_scheme': 'post-release'},
     cffi_modules=[
-        'ocrmypdf/lib/compile_leptonica.py:ffibuilder'
+        'src/ocrmypdf/lib/compile_leptonica.py:ffibuilder'
     ],
     install_requires=[
-        'ruffus==2.6.3',        # pinned - ocrmypdf implements a 2.6.3 workaround
-        'Pillow>=4.0.0',        # Pillow < 4 has BytesIO/TIFF bug w/img2pdf 0.2.3
-        'reportlab>=3.3.0',     # oldest released version with sane image handling
-        'PyPDF2>=1.26',         # pure Python, so track HEAD closely
-        'img2pdf>=0.2.3',       # pure Python, so track HEAD closely
-        'cffi>=1.9.1'           # must be a setup and install requirement
+        'cffi >= 1.9.1',          # must be a setup and install requirement
+        'defusedxml >= 0.5.0',    # pure Python, so track HEAD closely
+        'img2pdf >= 0.2.4',       # pure Python, so track HEAD closely
+        'Pillow >= 4.0.0',        # Pillow < 4 has BytesIO/TIFF bug w/img2pdf 0.2.3
+        'PyPDF2 >= 1.26',         # pure Python, so track HEAD closely
+        'reportlab >= 3.3.0',     # oldest released version with sane image handling
+        'ruffus == 2.6.3',        # pinned - ocrmypdf implements a 2.6.3 workaround
     ],
+    extras_require={
+        'fitz': ['PyMuPDF >= 1.12.5']     # for table of contents bug
+    },
     tests_require=tests_require,
     entry_points={
         'console_scripts': [

src/ocrmypdf/__init__.py

@@ -0,0 +1,25 @@
+# © 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/>.
+
+import pkg_resources
+
+PROGRAM_NAME = 'ocrmypdf'
+
+# Official PEP 396
+__version__ = pkg_resources.get_distribution('ocrmypdf').version
+
+VERSION = __version__

src/ocrmypdf/__main__.py

@@ -1,8 +1,24 @@
 #!/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/>.
 
 from tempfile import mkdtemp
 from collections.abc import Sequence
+from pathlib import Path
 import sys
 import os
 import re
@@ -23,8 +39,10 @@ import ruffus.proxy_logger as proxy_logger
 from .pipeline import JobContext, JobContextManager, \
     cleanup_working_files, build_pipeline
 from .pdfa import file_claims_pdfa
-from .helpers import is_iterable_notstr, re_symlink, is_file_writable
+from .helpers import is_iterable_notstr, re_symlink, is_file_writable, \
+    available_cpu_count
 from .exec import tesseract, qpdf, ghostscript
+from .lib import fitz
 from . import PROGRAM_NAME, VERSION
 
 from .exceptions import ExitCode, ExitCodeException, MissingDependencyError, \
@@ -266,7 +284,7 @@ advanced.add_argument(
     )
 advanced.add_argument(
     '--pdf-renderer',
-    choices=['auto', 'tesseract', 'hocr', 'tess4', 'sandwich'], default='auto',
+    choices=['auto', 'tesseract', 'hocr', 'sandwich'], default='auto',
     help="Choose OCR PDF renderer - the default option is to let OCRmyPDF "
          "choose."
          "auto - let OCRmyPDF choose; "
@@ -275,7 +293,6 @@ advanced.add_argument(
          "tesseract - gives better results for non-Latin languages and "
          "Tesseract older than 3.05.01 but has problems with some versions "
          " of Ghostscript; deprecated"
-         "tess4 - deprecated alias for 'sandwich'"
     )
 advanced.add_argument(
     '--tesseract-timeout', default=180.0, type=float, metavar='SECONDS',
@@ -305,6 +322,14 @@ advanced.add_argument(
 advanced.add_argument(
     '--user-patterns', metavar='FILE',
     help="Specify the location of the Tesseract user patterns file.")
+advanced.add_argument(
+    '--skip-repair', action='store_true',
+    help="Normally OCRmyPDF automatically repairs PDFs using qpdf before "
+         "processing.  If you have already run qpdf or a similar program "
+         "that repairs PDF errors, you can tell OCRmyPDF to skip repair with "
+         "this option.  This may be helpful in batch processing where all "
+         "files are repaired prior to OCR occurs, since repair is single "
+         "threaded and time consuming for large files.")
 
 debugging = parser.add_argument_group(
     "Debugging",
@@ -350,11 +375,6 @@ def check_options_output(options, log):
             "The 'sandwich' renderer requires Tesseract 3.05.01 or newer; "
             "or Tesseract 4.00 alpha newer than February 2017.")
 
-    if options.pdf_renderer == 'tess4':
-        log.warning("The 'tess4' PDF renderer has been renamed to 'sandwich'. "
-                    "Please use --pdf-renderer=sandwich.")
-        options.pdf_renderer = 'sandwich'
-
     if options.pdf_renderer == 'tesseract':
         if tesseract.version() < '3.05' and \
                 options.output_type.startswith('pdfa'):
@@ -448,15 +468,12 @@ def check_options_ocr_behavior(options, log):
 
 
 def check_options_advanced(options, log):
-    if tesseract.v4():
-        log.info(
-            "Tesseract v4.x.alpha found.")
     if options.tesseract_oem and not tesseract.v4():
         log.warning(
             "--tesseract-oem requires Tesseract 4.x -- argument ignored")
-    if options.pdf_renderer == 'tess4' and not tesseract.has_textonly_pdf():
+    if options.pdf_renderer == 'sandwich' and not tesseract.has_textonly_pdf():
         raise MissingDependencyError(
-            "--pdf-renderer tess4 requires Tesseract 4.x "
+            "--pdf-renderer sandwich requires Tesseract 4.x "
             "commit 3d9fb3b or later")
     if options.pdfa_image_compression != 'auto' and \
             options.output_type.startswith('pdfa'):
@@ -531,24 +548,6 @@ def logging_factory(logger_name, logger_args):
     return root_logger
 
 
-def available_cpu_count():
-    try:
-        return multiprocessing.cpu_count()
-    except NotImplementedError:
-        pass
-
-    try:
-        import psutil
-        return psutil.cpu_count()
-    except (ImportError, AttributeError):
-        pass
-
-    complain(
-        "Could not get CPU count.  Assuming one (1) CPU."
-        "Use -j N to set manually.")
-    return 1
-
-
 def cleanup_ruffus_error_message(msg):
     msg = re.sub(r'\s+', r' ', msg)
     msg = re.sub(r"\((.+?)\)", r'\1', msg)
@@ -725,6 +724,24 @@ def preamble(_log):
     _log.debug('ocrmypdf ' + VERSION)
     _log.debug('tesseract ' + tesseract.version())
     _log.debug('qpdf ' + qpdf.version())
+    if fitz:
+        _log.debug('PyMuPDF ' + fitz.version[0])
+        _log.debug('libmupdf ' + fitz.version[1])
+    else:
+        _log.debug('PyMuPDF not installed')
+
+
+def check_environ(options, _log):
+    old_envvars = (
+        'OCRMYPDF_TESSERACT',
+        'OCRMYPDF_QPDF',
+        'OCRMYPDF_GS',
+        'OCRMYPDF_UNPAPER')
+    for k in old_envvars:
+        if k in os.environ:
+            _log.warning(textwrap.dedent("""\
+                OCRmyPDF no longer uses the environment variable {}. 
+                Change PATH to select alternate programs.""".format(k)))
 
 
 def check_input_file(options, _log, start_input_file):
@@ -742,7 +759,7 @@ def check_input_file(options, _log, start_input_file):
             raise InputFileError()
 
 
-def check_output_file(options, _log):
+def check_requested_output_file(options, _log):
     if options.output_file == '-':
         if sys.stdout.isatty():
             _log.error(textwrap.dedent("""\
@@ -757,6 +774,35 @@ def check_output_file(options, _log):
         raise OutputFileAccessError()
 
 
+def report_output_file_size(options, _log, input_file, output_file):
+    try:
+        output_size = Path(output_file).stat().st_size
+        input_size = Path(input_file).stat().st_size
+    except FileNotFoundError:
+        return  # Outputting to stream or something
+    ratio = output_size / input_size
+    if ratio < 1.35 or input_size < 25000:
+        return  # Seems fine
+    
+    reasons = []
+    if not fitz:
+        reasons.append("The optional dependency PyMuPDF is not installed.")
+    if options.force_ocr:
+        reasons.append("The argument --force-ocr was issued.")
+
+    if reasons:
+        explanation = (
+            "Possible reasons for this include:\n" + '\n'.join(reasons) + "\n")
+    else:
+        explanation = (
+            "No reason for this increase is known.  Please report this issue.")
+
+    _log.warning(textwrap.dedent("""\
+        The output file size is {:.2f}× larger than the input file.
+        {}
+        """.format(ratio, explanation)))
+
+
 def run_pipeline():
     options = parser.parse_args()
     options.verbose_abbreviated_path = 1
@@ -791,6 +837,9 @@ def run_pipeline():
     # jobs run multithreaded.
     if tesseract.v4():
         os.environ.setdefault('OMP_THREAD_LIMIT', '1')
+    check_environ(options, _log)
+    if os.environ.get('PYTEST_CURRENT_TEST'):
+        os.environ['_OCRMYPDF_TEST_INFILE'] = options.input_file
 
     try:
         work_folder = mkdtemp(prefix="com.github.ocrmypdf.")
@@ -800,7 +849,7 @@ def run_pipeline():
             work_folder, 'origin')
 
         check_input_file(options, _log, start_input_file)
-        check_output_file(options, _log)
+        check_requested_output_file(options, _log)
 
         manager = JobContextManager()
         manager.register('JobContext', JobContext)  # pylint: disable=no-member
@@ -848,6 +897,9 @@ def run_pipeline():
             _log.warning('Output file: The generated PDF is INVALID')
             return ExitCode.invalid_output_pdf
 
+        report_output_file_size(options, _log, start_input_file, 
+                                options.output_file)
+
     pdfinfo = context.get_pdfinfo()
     if options.verbose:
         from pprint import pformat

src/ocrmypdf/exceptions.py

@@ -1,4 +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/>.
 
 
 from enum import IntEnum

src/ocrmypdf/exec/__init__.py

@@ -1,4 +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/>.
 
 """Wrappers to manage subprocess calls"""
 
@@ -9,17 +24,11 @@ from subprocess import run, STDOUT, PIPE, CalledProcessError
 from ..exceptions import MissingDependencyError
 
 
-def get_program(name):
-    "Check environment variables for overrides to this program"
-    envvar = 'OCRMYPDF_' + name.upper()
-    return os.environ.get(envvar, name)
-
-
 def get_version(program, *, 
         version_arg='--version', regex=r'(\d+(\.\d+)*)'):
-    "Get the version of the specified program, "
+    "Get the version of the specified program"
     args_prog = [
-        get_program(program),
+        program,
         version_arg
     ]
     try:
@@ -28,15 +37,9 @@ def get_version(program, *,
             stdout=PIPE, stderr=STDOUT, check=True)
         output = proc.stdout
     except CalledProcessError as e:
-        if get_program(program) == program:
-            raise MissingDependencyError(
-                "Could not find program '{}' on the PATH".format(
-                    program)) from e
-        else:
-            raise MissingDependencyError(
-                "Could not find program '{}'".format(
-                    get_program(program))) from e            
-
+        raise MissingDependencyError(
+            "Could not find program '{}' on the PATH".format(
+                program)) from e
     try:
         version = re.match(regex, output.strip()).group(1)
     except AttributeError as e:

src/ocrmypdf/exec/ghostscript.py

@@ -1,4 +1,19 @@
 # © 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/>.
 
 from tempfile import NamedTemporaryFile
 from subprocess import run, PIPE, STDOUT, CalledProcessError
@@ -7,7 +22,7 @@ from functools import lru_cache
 import re
 import sys
 from PIL import Image
-from . import get_program, get_version
+from . import get_version
 from ..exceptions import SubprocessOutputError, MissingDependencyError
 from ..helpers import fspath
 
@@ -46,7 +61,7 @@ def rasterize_pdf(input_file, output_file, xres, yres, raster_device, log,
         page_dpi = res
     with NamedTemporaryFile(delete=True) as tmp:
         args_gs = [
-            get_program('gs'),
+            'gs',
             '-dQUIET',
             '-dSAFER',
             '-dBATCH',
@@ -114,7 +129,7 @@ def generate_pdfa(pdf_pages, output_file, compression, log,
 
     with NamedTemporaryFile(delete=True) as gs_pdf:
         args_gs = [
-            get_program("gs"),
+            "gs",
             "-dQUIET",
             "-dBATCH",
             "-dNOPAUSE",

src/ocrmypdf/exec/qpdf.py

@@ -1,4 +1,19 @@
 # © 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/>.
 
 from subprocess import CalledProcessError, STDOUT, PIPE, run
 from functools import lru_cache
@@ -9,7 +24,7 @@ import resource
 
 from ..exceptions import InputFileError, SubprocessOutputError, \
     MissingDependencyError, EncryptedPdfError
-from . import get_program, get_version
+from . import  get_version
 from ..helpers import re_symlink
 
 
@@ -20,7 +35,7 @@ def version():
 
 def check(input_file, log=None):
     args_qpdf = [
-        get_program('qpdf'),
+        'qpdf',
         '--check',
         input_file
     ]
@@ -56,7 +71,7 @@ def _probably_encrypted(e):
 
 def repair(input_file, output_file, log):
     args_qpdf = [
-        get_program('qpdf'), input_file, output_file
+        'qpdf', input_file, output_file
     ]
     try:
         run(args_qpdf, stderr=STDOUT, stdout=PIPE, universal_newlines=True, 
@@ -83,7 +98,7 @@ def repair(input_file, output_file, log):
 def get_npages(input_file, log):
     try:
         pages = run(
-            [get_program('qpdf'), '--show-npages', input_file],
+            ['qpdf', '--show-npages', input_file],
             universal_newlines=True, check=True, stdout=PIPE, stderr=STDOUT)
     except CalledProcessError as e:
         if e.returncode == 2 and e.output.find('No such file'):
@@ -100,13 +115,22 @@ def split_pages(input_file, work_folder, npages):
     """
     for n in range(int(npages)):
         args_qpdf = [
-            get_program('qpdf'), input_file,
+            'qpdf', input_file,
             '--pages', input_file, '{0}'.format(n + 1), '--',
             os.path.join(work_folder, '{0:06d}.page.pdf'.format(n + 1))
         ]
         run(args_qpdf, check=True)
 
 
+def extract_page(input_file, output_file, pageno):
+    args_qpdf = [
+        'qpdf', input_file,
+        '--pages', input_file, '{0}'.format(pageno + 1), '--',
+        output_file
+    ]
+    run(args_qpdf, check=True)
+    
+
 def _merge_inner(input_files, output_file, min_version=None, log=None):
     """Merge the list of input files (all filenames) into the output file.
 
@@ -123,7 +147,7 @@ def _merge_inner(input_files, output_file, min_version=None, log=None):
         import logging as log
 
     args_qpdf = [
-        get_program('qpdf')
+        'qpdf'
     ] + version_arg + [
         input_files[0], '--pages'
     ] + input_files + ['--', output_file]

src/ocrmypdf/exec/tesseract.py

@@ -1,4 +1,19 @@
 # © 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/>.
 
 import sys
 import os
@@ -7,13 +22,15 @@ import shutil
 from functools import lru_cache
 from collections import namedtuple
 from textwrap import dedent
-import PyPDF2 as pypdf
 from subprocess import PIPE, CalledProcessError, \
     TimeoutExpired, check_output, STDOUT
+from contextlib import suppress
+
+import PyPDF2 as pypdf
 
 from ..exceptions import MissingDependencyError, TesseractConfigError
 from ..helpers import page_number
-from . import get_program, get_version
+from . import get_version
 
 OrientationConfidence = namedtuple(
     'OrientationConfidence',
@@ -55,7 +72,7 @@ def has_textonly_pdf():
     parse the parameter list
     """
     args_tess = [
-        get_program('tesseract'),
+        'tesseract',
         '--print-parameters'
     ]
     params = ''
@@ -79,7 +96,7 @@ def psm():
 @lru_cache(maxsize=1)
 def languages():
     args_tess = [
-        get_program('tesseract'),
+        'tesseract',
         '--list-langs'
     ]
     try:
@@ -98,7 +115,7 @@ def languages():
 
 def tess_base_args(langs, engine_mode):
     args = [
-        get_program('tesseract'),
+        'tesseract',
     ]
     if langs:
         args.extend(['-l', '+'.join(langs)])
@@ -266,6 +283,8 @@ def use_skip_page(text_only, skip_pdf, output_pdf, output_text):
         f.write('[skipped page]')
 
     if not text_only:
+        with suppress(FileNotFoundError):
+            os.remove(output_pdf)  # In case it was partially created
         os.symlink(skip_pdf, output_pdf)
         return
 

src/ocrmypdf/exec/unpaper.py

@@ -1,4 +1,20 @@
 # © 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/>.
+
 # unpaper documentation:
 # https://github.com/Flameeyes/unpaper/blob/master/doc/basic-concepts.md
 
@@ -8,7 +24,7 @@ import sys
 import os
 from functools import lru_cache
 from ..exceptions import MissingDependencyError
-from . import get_program, get_version
+from . import get_version
 
 
 try:
@@ -25,7 +41,7 @@ def version():
 
 def run(input_file, output_file, dpi, log, mode_args):
     args_unpaper = [
-        get_program('unpaper'),
+        'unpaper',
         '-v',
         '--dpi', str(dpi)
     ] + mode_args

src/ocrmypdf/helpers.py

@@ -1,4 +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/>.
 
 from functools import partial
 from collections.abc import Iterable
@@ -6,6 +21,7 @@ from contextlib import suppress, contextmanager
 from pathlib import Path
 import sys
 import os
+import multiprocessing
 
 
 def re_symlink(input_file, soft_link_name, log=None):
@@ -53,9 +69,28 @@ def is_iterable_notstr(thing):
 
 
 def page_number(input_file):
+    "Get one-based page number implied by filename (000002.pdf -> 2)"
     return int(os.path.basename(input_file)[0:6])
 
 
+def available_cpu_count():
+    try:
+        return multiprocessing.cpu_count()
+    except NotImplementedError:
+        pass
+
+    try:
+        import psutil
+        return psutil.cpu_count()
+    except (ImportError, AttributeError):
+        pass
+
+    complain(
+        "Could not get CPU count.  Assuming one (1) CPU."
+        "Use -j N to set manually.")
+    return 1
+
+
 def is_file_writable(test_file):
     """Intentionally racy test if target is writable.
 

src/ocrmypdf/leptonica.py

@@ -3,6 +3,21 @@
 #
 # © 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/>.
+#
 # Python FFI wrapper for Leptonica library
 
 import argparse

src/ocrmypdf/lib/__init__.py

@@ -0,0 +1,28 @@
+# © 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/>.
+
+"""Bindings to external libraries"""
+
+import os as _os
+
+try:
+    import fitz
+except ImportError:
+    fitz = None
+
+if _os.environ.get('_OCRMYPDF_NO_FITZ'):
+    fitz = None

src/ocrmypdf/lib/_leptonica.py

@@ -0,0 +1,10 @@
+# auto-generated file
+import _cffi_backend
+
+ffi = _cffi_backend.FFI('ocrmypdf.lib._leptonica',
+    _version = 0x2601,
+    _types = b'\x00\x00\x0F\x0D\x00\x00\xBB\x03\x00\x00\x07\x01\x00\x00\x07\x01\x00\x00\x07\x01\x00\x00\x07\x01\x00\x00\x07\x01\x00\x00\x07\x01\x00\x00\xBE\x03\x00\x00\x00\x0F\x00\x00\x01\x0D\x00\x00\x01\x11\x00\x00\x00\x0F\x00\x00\x01\x0D\x00\x00\x01\x11\x00\x00\xBA\x03\x00\x00\x0F\x03\x00\x00\x00\x0F\x00\x00\x01\x0D\x00\x00\x01\x11\x00\x00\x01\x11\x00\x00\x00\x0F\x00\x00\x01\x0D\x00\x00\x01\x11\x00\x00\x01\x11\x00\x00\x01\x11\x00\x00\x00\x0F\x00\x00\x01\x0D\x00\x00\x01\x11\x00\x00\x01\x11\x00\x00\x01\x11\x00\x00\x0D\x01\x00\x00\x07\x01\x00\x00\x07\x01\x00\x00\x00\x0F\x00\x00\x01\x0D\x00\x00\x01\x11\x00\x00\x01\x11\x00\x00\x01\x11\x00\x00\x07\x01\x00\x00\x07\x01\x00\x00\x07\x01\x00\x00\x07\x01\x00\x00\x07\x01\x00\x00\x07\x01\x00\x00\x07\x01\x00\x00\x00\x0F\x00\x00\x01\x0D\x00\x00\x01\x11\x00\x00\x01\x11\x00\x00\x0D\x01\x00\x00\x07\x01\x00\x00\x07\x01\x00\x00\x00\x0F\x00\x00\x01\x0D\x00\x00\x01\x11\x00\x00\x01\x11\x00\x00\x07\x01\x00\x00\x07\x01\x00\x00\x07\x01\x00\x00\x07\x01\x00\x00\x00\x0F\x00\x00\x01\x0D\x00\x00\x01\x11\x00\x00\x01\x11\x00\x00\x07\x01\x00\x00\x07\x01\x00\x00\x07\x01\x00\x00\x07\x01\x00\x00\x07\x01\x00\x00\x07\x01\x00\x00\x07\x01\x00\x00\x0D\x01\x00\x00\x02\x03\x00\x00\x00\x0F\x00\x00\x01\x0D\x00\x00\x01\x11\x00\x00\x0D\x01\x00\x00\x0D\x01\x00\x00\x00\x0F\x00\x00\x01\x0D\x00\x00\x01\x11\x00\x00\x07\x01\x00\x00\x00\x0F\x00\x00\x01\x0D\x00\x00\x01\x11\x00\x00\x07\x01\x00\x00\x07\x01\x00\x00\x00\x0F\x00\x00\x01\x0D\x00\x00\x01\x11\x00\x00\x07\x01\x00\x00\x07\x01\x00\x00\x07\x01\x00\x00\x07\x01\x00\x00\x00\x0F\x00\x00\x01\x0D\x00\x00\x08\x11\x00\x00\x00\x0F\x00\x00\x01\x0D\x00\x00\xC7\x03\x00\x00\x1C\x01\x00\x00\x00\x0F\x00\x00\xBD\x0D\x00\x00\x00\x0F\x00\x00\x49\x0D\x00\x00\x00\x0F\x00\x00\x02\x0D\x00\x00\x01\x11\x00\x00\x01\x11\x00\x00\x1F\x03\x00\x00\x00\x0F\x00\x00\x02\x0D\x00\x00\x01\x11\x00\x00\x01\x11\x00\x00\x07\x01\x00\x00\x07\x01\x00\x00\x07\x01\x00\x00\x07\x01\x00\x00\x6E\x11\x00\x00\x6E\x11\x00\x00\x6E\x11\x00\x00\x00\x0F\x00\x00\x02\x0D\x00\x00\x01\x11\x00\x00\x6E\x11\x00\x00\x6E\x11\x00\x00\x00\x0F\x00\x00\x02\x0D\x00\x00\x01\x11\x00\x00\x49\x11\x00\x00\x49\x11\x00\x00\x00\x0F\x00\x00\x02\x0D\x00\x00\x01\x11\x00\x00\x07\x01\x00\x00\x07\x01\x00\x00\x0D\x01\x00\x00\x07\x01\x00\x00\x49\x11\x00\x00\x00\x0F\x00\x00\x02\x0D\x00\x00\x01\x11\x00\x00\x07\x01\x00\x00\x07\x01\x00\x00\x07\x01\x00\x00\x07\x01\x00\x00\x6E\x11\x00\x00\x6E\x11\x00\x00\x00\x0F\x00\x00\x02\x0D\x00\x00\x01\x11\x00\x00\x07\x01\x00\x00\x07\x01\x00\x00\x07\x01\x00\x00\x07\x01\x00\x00\x0D\x01\x00\x00\x01\x03\x00\x00\x9D\x11\x00\x00\x00\x0F\x00\x00\x02\x0D\x00\x00\x01\x11\x00\x00\xC6\x03\x00\x00\x65\x03\x00\x00\x00\x0F\x00\x00\x02\x0D\x00\x00\x08\x11\x00\x00\x01\x11\x00\x00\x07\x01\x00\x00\x07\x01\x00\x00\x00\x0F\x00\x00\x02\x0D\x00\x00\xC4\x03\x00\x00\xA3\x11\x00\x00\x01\x11\x00\x00\x0D\x01\x00\x00\x00\x0F\x00\x00\xCA\x0D\x00\x00\x10\x11\x00\x00\x00\x0F\x00\x00\xCA\x0D\x00\x00\x9D\x11\x00\x00\x00\x0F\x00\x00\xCA\x0D\x00\x00\xCA\x03\x00\x00\x00\x0F\x00\x00\x00\x09\x00\x00\x01\x09\x00\x00\x02\x09\x00\x00\xBE\x03\x00\x00\x02\x01\x00\x00\x0E\x01\x00\x00\x0B\x01\x00\x00\x05\x01\x00\x00\x03\x01\x00\x00\xBC\x03\x00\x00\xC5\x03\x00\x00\x04\x01\x00\x00\xC7\x03\x00\x00\x08\x01\x00\x00\x0C\x01\x00\x00\x06\x01\x00\x00\x00\x01',
+    _globals = (b'\x00\x00\xB1\x23boxDestroy',0,b'\x00\x00\x67\x23getLeptonicaVersion',0,b'\x00\x00\xB7\x23lept_free',0,b'\x00\x00\x69\x23makePixelSumTab8',0,b'\x00\x00\x16\x23pixAnd',0,b'\x00\x00\x23\x23pixBackgroundNorm',0,b'\x00\x00\x1B\x23pixCleanBackgroundToWhite',0,b'\x00\x00\x0D\x23pixClipRectangle',0,b'\x00\x00\x8D\x23pixColorFraction',0,b'\x00\x00\x59\x23pixColorMagnitude',0,b'\x00\x00\x0A\x23pixConvertRGBToLuminance',0,b'\x00\x00\x6B\x23pixCorrelationBinary',0,b'\x00\x00\x80\x23pixCountPixels',0,b'\x00\x00\x63\x23pixDeserializeFromMemory',0,b'\x00\x00\x50\x23pixDeskew',0,b'\x00\x00\xB4\x23pixDestroy',0,b'\x00\x00\x0A\x23pixEndianByteSwapNew',0,b'\x00\x00\x00\x23pixFindPageForeground',0,b'\x00\x00\x7B\x23pixFindSkew',0,b'\x00\x00\x2F\x23pixGammaTRC',0,b'\x00\x00\x70\x23pixGetAverageMaskedRGB',0,b'\x00\x00\x36\x23pixGlobalNormRGB',0,b'\x00\x00\x12\x23pixInvert',0,b'\x00\x00\x54\x23pixMaskOverColorPixels',0,b'\x00\x00\x85\x23pixNumSignificantGrayColors',0,b'\x00\x00\x96\x23pixOtsuAdaptiveThreshold',0,b'\x00\x00\x3E\x23pixOtsuThreshOnBackgroundNorm',0,b'\x00\x00\x60\x23pixRead',0,b'\x00\x00\x50\x23pixRemoveColormap',0,b'\x00\x00\x12\x23pixRotate180',0,b'\x00\x00\x50\x23pixRotateOrth',0,b'\x00\x00\x4B\x23pixScale',0,b'\x00\x00\xA0\x23pixSerializeToMemory',0,b'\x00\x00\xA5\x23pixWriteImpliedFormat',0,b'\x00\x00\xAB\x23pixWriteMemPng',0),
+    _struct_unions = ((b'\x00\x00\x00\xBA\x00\x00\x00\x02Box',b'\x00\x00\x02\x11x',b'\x00\x00\x02\x11y',b'\x00\x00\x02\x11w',b'\x00\x00\x02\x11h',b'\x00\x00\xC7\x11refcount'),(b'\x00\x00\x00\xBB\x00\x00\x00\x02Pix',b'\x00\x00\xC7\x11w',b'\x00\x00\xC7\x11h',b'\x00\x00\xC7\x11d',b'\x00\x00\xC7\x11spp',b'\x00\x00\xC7\x11wpl',b'\x00\x00\xC7\x11refcount',b'\x00\x00\x02\x11xres',b'\x00\x00\x02\x11yres',b'\x00\x00\x02\x11informat',b'\x00\x00\x02\x11special',b'\x00\x00\xBD\x11text',b'\x00\x00\xC3\x11colormap',b'\x00\x00\xC6\x11data'),(b'\x00\x00\x00\xBC\x00\x00\x00\x02PixColormap',b'\x00\x00\xB8\x11array',b'\x00\x00\x02\x11depth',b'\x00\x00\x02\x11nalloc',b'\x00\x00\x02\x11n')),
+    _typenames = (b'\x00\x00\x00\xBABOX',b'\x00\x00\x00\xBBPIX',b'\x00\x00\x00\xBCPIXCMAP',b'\x00\x00\x00\x1Fl_float32',b'\x00\x00\x00\xBFl_float64',b'\x00\x00\x00\xC1l_int16',b'\x00\x00\x00\x02l_int32',b'\x00\x00\x00\xC0l_int64',b'\x00\x00\x00\xC2l_int8',b'\x00\x00\x00\xC9l_uint16',b'\x00\x00\x00\xC7l_uint32',b'\x00\x00\x00\xC8l_uint64',b'\x00\x00\x00\xC5l_uint8'),
+)

src/ocrmypdf/lib/compile_leptonica.py

@@ -1,5 +1,20 @@
 #!/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/>.
 
 from cffi import FFI
 

src/ocrmypdf/pdfa.py

@@ -1,9 +1,24 @@
 # © 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/>.
+
 # Generate a PDFA_def.ps file for Ghostscript >= 9.14
 
 from string import Template
-import codecs
+from binascii import hexlify
 import pkg_resources
 import PyPDF2 as pypdf
 
@@ -78,7 +93,7 @@ def encode_text_string(s: str) -> str:
         return ''
 
     utf16_bytes = s.encode('utf-16be')
-    ascii_hex_bytes = codecs.encode(b'\xfe\xff' + utf16_bytes, 'hex')
+    ascii_hex_bytes = hexlify(b'\xfe\xff' + utf16_bytes)
     ascii_hex_str = ascii_hex_bytes.decode('ascii').lower()
     return ascii_hex_str
 

src/ocrmypdf/pdfinfo.py

@@ -1,18 +1,37 @@
 #!/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/>.
 
 from subprocess import Popen, PIPE
 from decimal import Decimal
 from math import hypot, isclose
 import re
 import sys
-import PyPDF2 as pypdf
 from collections import namedtuple
 from collections.abc import MutableMapping, Mapping
 import warnings
 from pathlib import Path
 from enum import Enum
-from .helpers import universal_open
+from contextlib import contextmanager
+
+import PyPDF2 as pypdf
+from .lib import fitz
+from .helpers import universal_open, fspath
+
 
 
 matrix_mult = pypdf.pdf.utils.matrixMultiply
@@ -101,7 +120,8 @@ XobjectSettings = namedtuple('XobjectSettings',
 InlineSettings = namedtuple('InlineSettings',
     ['settings', 'shorthand', 'stack_depth'])
 
-ContentsInfo = namedtuple('ContentsInfo', ['xobject_settings', 'inline_images'])
+ContentsInfo = namedtuple('ContentsInfo', 
+    ['xobject_settings', 'inline_images', 'found_text'])
 
 
 def _normalize_stack(operations):
@@ -148,6 +168,7 @@ def _interpret_contents(contentstream, initial_shorthand=UNIT_SQUARE):
     ctm = _matrix_from_shorthand(initial_shorthand)
     xobject_settings = []
     inline_images = []
+    found_text = False
 
     for n, op in enumerate(_normalize_stack(operations)):
         operands, command = op
@@ -177,10 +198,14 @@ def _interpret_contents(contentstream, initial_shorthand=UNIT_SQUARE):
                 settings=settings, shorthand=_shorthand_from_matrix(ctm),
                 stack_depth=len(stack))
             inline_images.append(inline)
+        elif command in (b'Tj', b'TJ', b'"', b"'"):
+            found_text = True
+
 
     return ContentsInfo(
         xobject_settings=xobject_settings,
-        inline_images=inline_images)
+        inline_images=inline_images,
+        found_text=found_text)
 
 
 def _get_dpi(ctm_shorthand, image_size):
@@ -525,32 +550,47 @@ def _find_images(*, pdf, container, shorthand=None):
     yield from _find_form_xobject_images(pdf, container, contentsinfo)
 
 
-def _page_has_text(pdf, page):
-    if not '/Contents' in page:
+def _naive_find_text(*, pdf, page):
+    if not(page.get('/Type') == '/Page' and '/Contents' in page):
+        # Not a page, or has no /Contents => no text
         return False
 
-    # Simple test
-    text = page.extractText()
-    if text.strip() != '':
+    # First we check the main content stream    
+    contentstream = pypdf.pdf.ContentStream(page.getContents(), pdf)
+    contentsinfo = _interpret_contents(contentstream, UNIT_SQUARE)
+    if contentsinfo.found_text:
         return True
 
-    # More nuanced test to deal with quirks of Tesseract PDF generation
-    # Check if there's a Glyphless font
-    try:
-        font = page['/Resources']['/Font']
-    except KeyError:
-        pass
-    else:
-        font_objects = list(font.keys())
-        for font_object in font_objects:
-            basefont = font[font_object]['/BaseFont']
-            if basefont.endswith('GlyphLessFont'):
-                return True
-
+    # Then see if there is a Form XObject with with a content stream
+    # that might have text.  For full completeness we should recursively
+    # search nested Form XObjects, as we do with images.  But that is
+    # rare.
+    if '/Resources' in page:
+        resources = page['/Resources']
+        if '/XObject' in resources:    
+            for xobj in resources['/XObject']:
+                candidate = resources['/XObject'][xobj]
+                if candidate['/Subtype'] != '/Form':
+                    continue
+                form_xobject = candidate                
+                # Content stream is attached to Form XObject dictionary
+                contentstream = pypdf.pdf.ContentStream(form_xobject, pdf)
+                sub_contentsinfo = _interpret_contents(
+                    contentstream, UNIT_SQUARE)
+                if sub_contentsinfo.found_text:
+                    return True
     return False
 
 
-def _pdf_get_pageinfo(pdf, pageno: int):
+def _page_has_text(infile, pageno):
+    doc = fitz.Document(infile)
+    text = doc.getPageText(pageno)
+    if text.strip() != '':
+        return True
+    return False
+
+
+def _pdf_get_pageinfo(pdf, pageno: int, infile):
     pageinfo = {}
     pageinfo['pageno'] = pageno
     pageinfo['images'] = []
@@ -562,7 +602,10 @@ def _pdf_get_pageinfo(pdf, pageno: int):
 
     page = pdf.pages[pageno]
 
-    pageinfo['has_text'] = _page_has_text(pdf, page)
+    if fitz:
+        pageinfo['has_text'] = _page_has_text(str(infile), pageno)
+    else:
+        pageinfo['has_text'] = _naive_find_text(pdf=pdf, page=page)
 
     width_pt = page.mediaBox.getWidth()
     height_pt = page.mediaBox.getHeight()
@@ -596,13 +639,14 @@ def _pdf_get_pageinfo(pdf, pageno: int):
 def _pdf_get_all_pageinfo(infile):
     with universal_open(infile, 'rb') as f:
         pdf = pypdf.PdfFileReader(f)
-        return [PageInfo(pdf, n) for n in range(pdf.numPages)]
+        return [PageInfo(pdf, n, infile) for n in range(pdf.numPages)]
 
 
 class PageInfo:
-    def __init__(self, pdf, pageno):
+    def __init__(self, pdf, pageno, infile):
         self._pageno = pageno
-        self._pageinfo = _pdf_get_pageinfo(pdf, pageno)
+        self._infile = infile
+        self._pageinfo = _pdf_get_pageinfo(pdf, pageno, infile)
 
     @property
     def pageno(self):
@@ -679,6 +723,10 @@ class PdfInfo:
     def __init__(self, infile):
         self._infile = infile
         self._pages = _pdf_get_all_pageinfo(infile)
+        if fitz:
+            self._toc = fitz.Document(fspath(infile)).getToC()
+        else:
+            self._toc = []
 
     @property
     def pages(self):
@@ -693,6 +741,16 @@ class PdfInfo:
     def has_userunit(self):
         return any(page.userunit != 1.0 for page in self.pages)
 
+    @property
+    def filename(self):
+        if not isinstance(self._infile, (str, Path)):
+            raise NotImplementedError("can't get filename from stream")
+        return self._infile
+
+    @property
+    def table_of_contents(self):
+        return self._toc
+
     def __getitem__(self, item):
         return self._pages[item]
 

src/ocrmypdf/pipeline.py

@@ -1,15 +1,32 @@
 # © 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/>.
 
 from contextlib import suppress
 from shutil import copyfileobj
+from pathlib import Path
 import sys
 import os
 import shutil
-import img2pdf
 import re
-import PyPDF2 as pypdf
-from PIL import Image
 
+import img2pdf
+import PyPDF2 as pypdf
+
+from PIL import Image
 from ruffus import formatter, regex, Pipeline, suffix
 
 from .hocrtransform import HocrTransform
@@ -17,12 +34,14 @@ from .pdfinfo import PdfInfo, Encoding, Colorspace
 from .pdfa import generate_pdfa_ps
 from .helpers import re_symlink, is_iterable_notstr, page_number
 from .exec import ghostscript, tesseract, qpdf
+from .lib import fitz
 from .exceptions import PdfMergeFailedError, UnsupportedImageFormatError, \
     DpiError, PriorOcrFoundError, InputFileError
 from . import leptonica
 from . import PROGRAM_NAME, VERSION
 
 
+
 VECTOR_PAGE_DPI = 400
 
 # -------------
@@ -187,13 +206,19 @@ def triage(
     triage_image_file(input_file, output_file, log, options)
 
 
-def repair_pdf(
+def repair_and_parse_pdf(
         input_file,
         output_file,
         log,
         context):
     options = context.get_options()
-    qpdf.repair(input_file, output_file, log)
+    if not options.skip_repair:
+        log.debug("Beginning qpdf repair...")
+        qpdf.repair(input_file, output_file, log)
+        log.debug("Repair OK; beginning parse...")
+    else:
+        re_symlink(input_file, output_file, log)
+
     pdfinfo = PdfInfo(output_file)
 
     if pdfinfo.has_userunit and options.output_type == 'pdfa':
@@ -211,6 +236,7 @@ def repair_pdf(
 
 
 def get_pageinfo(input_file, context):
+    "Get zero-based page info implied by filename, e.g. 000002.pdf -> 1"
     pageno = page_number(input_file) - 1
     pageinfo = context.get_pdfinfo()[pageno]
     return pageinfo
@@ -303,7 +329,7 @@ def is_ocr_required(pageinfo, log, options):
     return ocr_required
 
 
-def split_pages(
+def pre_split_pages(
         input_files,
         output_files,
         log,
@@ -329,20 +355,45 @@ def split_pages(
 
     pdfinfo = context.get_pdfinfo()
     npages = len(pdfinfo)
-    qpdf.split_pages(input_file, work_folder, npages)
 
-    from glob import glob
-    for filename in glob(os.path.join(work_folder, '*.page.pdf')):
-        pageinfo = get_pageinfo(filename, context)
+    # Ruffus needs to see a file for any task it generates, so create
+    # empty placeholders for every page.
+    for n in range(npages):
+        page = Path(work_folder) / '{0:06d}.presplit.pdf'.format(n + 1)
+        page.touch()
 
+
+def split_page(
+        placeholder_file,
+        output_file,
+        log,
+        context):
+    pageno = page_number(placeholder_file) - 1
+    input_pdf = context.get_pdfinfo().filename
+    qpdf.extract_page(input_pdf, output_file, pageno)
+
+
+def ocr_or_skip(
+        input_files,
+        output_files,
+        log,
+        context):
+    options = context.get_options()
+    work_folder = context.get_work_folder()
+    pdfinfo =  context.get_pdfinfo()
+
+    for input_file in input_files:
+        pageno = page_number(input_file) - 1
+        pageinfo = pdfinfo[pageno]
         alt_suffix = \
             '.ocr.page.pdf' if is_ocr_required(pageinfo, log, options) \
             else '.skip.page.pdf'
+
         re_symlink(
-            filename,
+            input_file,
             os.path.join(
                 work_folder,
-                os.path.basename(filename)[0:6] + alt_suffix),
+                os.path.basename(input_file)[0:6] + alt_suffix),
             log)
 
 
@@ -678,8 +729,8 @@ def combine_layers(
     image = next(ii for ii in flatten_groups(infiles)
                  if ii.endswith('.image-layer.pdf'))
 
-    pdf_text = pypdf.PdfFileReader(open(text, "rb"))
-    pdf_image = pypdf.PdfFileReader(open(image, "rb"))
+    pdf_text = pypdf.PdfFileReader(text)
+    pdf_image = pypdf.PdfFileReader(image)
 
     page_text = pdf_text.getPage(0)
 
@@ -873,12 +924,21 @@ def skip_page(
     re_symlink(input_file, output_file, log)
 
 
-def merge_pages_ghostscript(
+def _merge_pages_common(
         input_files_groups,
         output_file,
         log,
         context):
-    options = context.get_options()
+    """Determine ordered list of PDF pages to merge. Returns PDF from which
+    metadata should be drawn if present (for qpdf)."""
+
+    input_files = list(f for f in flatten_groups(input_files_groups)
+                       if not f.endswith('.txt'))
+    metadata_file = next(
+        (ii for ii in input_files if ii.endswith('.repaired.pdf')), None)
+    if metadata_file in input_files:
+        input_files.remove(metadata_file)
+
     def input_file_order(s):
         '''Sort order: All rendered pages followed
         by their debug page, if any, followed by Postscript stub.
@@ -892,19 +952,35 @@ def merge_pages_ghostscript(
             key += 1
         return key
 
-    input_files = (f for f in flatten_groups(input_files_groups)
-                   if not f.endswith('.txt'))
     pdf_pages = sorted(input_files, key=input_file_order)
     log.debug("Final pages: " + "\n".join(pdf_pages))
+
+    return pdf_pages, metadata_file
+
+
+def merge_pages_ghostscript(
+        input_files_groups,
+        output_file,
+        log,
+        context):
+    options = context.get_options()
+    pdf_pages, _ = _merge_pages_common(
+        input_files_groups, output_file, log, context)
     input_pdfinfo = context.get_pdfinfo()
     ghostscript.generate_pdfa(
         pdf_version=input_pdfinfo.min_version,
         pdf_pages=pdf_pages,
-        output_file=output_file,
+        output_file=output_file + '_toc.pdf',
         compression=options.pdfa_image_compression,
         log=log,
         threads=options.jobs or 1,
         pdfa_part=('1' if options.output_type == 'pdfa-1' else '2'))
+    if fitz:
+        doc = fitz.Document(output_file + '_toc.pdf')
+        doc.setToC(input_pdfinfo.table_of_contents)
+        doc.save(output_file)
+    else:
+        os.replace(output_file + '_toc.pdf', output_file)
 
 
 def merge_pages_qpdf(
@@ -913,23 +989,8 @@ def merge_pages_qpdf(
         log,
         context):
     options = context.get_options()
-
-    input_files = list(f for f in flatten_groups(input_files_groups)
-                       if not f.endswith('.txt'))
-    metadata_file = next(
-        (ii for ii in input_files if ii.endswith('.repaired.pdf')))
-    input_files.remove(metadata_file)
-
-    def input_file_order(s):
-        '''Sort order: All rendered pages followed
-        by their debug page.'''
-        key = page_number(s) * 10
-        if 'debug' in os.path.basename(s):
-            key += 1
-        return key
-
-    pdf_pages = sorted(input_files, key=input_file_order)
-    log.debug("Final pages: " + "\n".join(pdf_pages))
+    pdf_pages, metadata_file = _merge_pages_common(
+        input_files_groups, output_file, log, context)
 
     reader_metadata = pypdf.PdfFileReader(metadata_file)
     pdfmark = get_pdfmark(reader_metadata, options)
@@ -938,7 +999,8 @@ def merge_pages_qpdf(
     first_page = pypdf.PdfFileReader(pdf_pages[0])
 
     writer = pypdf.PdfFileWriter()
-    writer._header = b'%PDF-' + _pdf_guess_version(pdf_pages[0])  # copy version from source
+    # copy version from source
+    writer._header = b'%PDF-' + _pdf_guess_version(pdf_pages[0])
     writer.appendPagesFromReader(first_page)
     writer.addMetadata(pdfmark)
     writer_file = pdf_pages[0].replace('.pdf', '.metadata.pdf')
@@ -952,6 +1014,36 @@ def merge_pages_qpdf(
                log=log)
 
 
+def merge_pages_mupdf(
+        input_files_groups,
+        output_file,
+        log,
+        context):
+    assert fitz
+
+    options = context.get_options()
+
+    pdf_pages, metadata_file = _merge_pages_common(
+        input_files_groups, output_file, log, context)
+
+    doc = fitz.Document()
+
+    reader_metadata = pypdf.PdfFileReader(metadata_file)
+    pdfmark = get_pdfmark(reader_metadata, options)
+    pdfmark['/Producer'] = 'PyMuPDF ' + fitz.version[0]
+    pymupdf_metadata = {k[1:].lower() : v for k, v in pdfmark.items()}
+
+    for pdf_page in pdf_pages:
+        page = fitz.open(pdf_page)
+        doc.insertPDF(page)
+
+    metadata = fitz.open(metadata_file)
+    toc = metadata.getToC(simple=False)
+    doc.setToC(toc)
+    doc.setMetadata(pymupdf_metadata)
+    doc.save(output_file, garbage=4, deflate=True)
+
+
 def merge_sidecars(
         input_files_groups,
         output_file,
@@ -1024,8 +1116,8 @@ def build_pipeline(options, work_folder, log, context):
         output=os.path.join(work_folder, 'origin.pdf'),
         extras=[log, context])
 
-    task_repair_pdf = main_pipeline.transform(
-        task_func=repair_pdf,
+    task_repair_and_parse_pdf = main_pipeline.transform(
+        task_func=repair_and_parse_pdf,
         input=task_triage,
         filter=suffix('.pdf'),
         output='.repaired.pdf',
@@ -1033,16 +1125,31 @@ def build_pipeline(options, work_folder, log, context):
         extras=[log, context])
 
     # Split (kwargs for split seems to be broken, so pass plain args)
-    task_split_pages = main_pipeline.split(
-        split_pages,
-        task_repair_pdf,
-        os.path.join(work_folder, '*.page.pdf'),
+    task_pre_split_pages = main_pipeline.split(
+        pre_split_pages,
+        task_repair_and_parse_pdf,
+        os.path.join(work_folder, '*.presplit.pdf'),
+        extras=[log, context])
+
+    task_split_pages = main_pipeline.transform(
+        task_func=split_page,
+        input=task_pre_split_pages,
+        filter=suffix('.presplit.pdf'),
+        output='.page.pdf',
+        output_dir=work_folder,
+        extras=[log, context])
+
+    task_ocr_or_skip = main_pipeline.split(
+        ocr_or_skip,
+        task_split_pages,
+        [os.path.join(work_folder, '*.ocr.page.pdf'),
+         os.path.join(work_folder, '*.skip.page.pdf')],
         extras=[log, context])
 
     # Rasterize preview
     task_rasterize_preview = main_pipeline.transform(
         task_func=rasterize_preview,
-        input=task_split_pages,
+        input=task_ocr_or_skip,
         filter=suffix('.page.pdf'),
         output='.preview.jpg',
         output_dir=work_folder,
@@ -1052,7 +1159,7 @@ def build_pipeline(options, work_folder, log, context):
     # Orient
     task_orient_page = main_pipeline.collate(
         task_func=orient_page,
-        input=[task_split_pages, task_rasterize_preview],
+        input=[task_ocr_or_skip, task_rasterize_preview],
         filter=regex(r".*/(\d{6})(\.ocr|\.skip)(?:\.page\.pdf|\.preview\.jpg)"),
         output=os.path.join(work_folder, r'\1\2.oriented.pdf'),
         extras=[log, context])
@@ -1184,7 +1291,7 @@ def build_pipeline(options, work_folder, log, context):
     # PDF/A
     task_generate_postscript_stub = main_pipeline.transform(
         task_func=generate_postscript_stub,
-        input=task_repair_pdf,
+        input=task_repair_and_parse_pdf,
         filter=formatter(r'\.repaired\.pdf'),
         output=os.path.join(work_folder, 'pdfa.ps'),
         extras=[log, context])
@@ -1210,7 +1317,8 @@ def build_pipeline(options, work_folder, log, context):
                task_generate_postscript_stub],
         output=os.path.join(work_folder, 'merged.pdf'),
         extras=[log, context])
-    task_merge_pages_ghostscript.active_if(options.output_type.startswith('pdfa'))
+    task_merge_pages_ghostscript.active_if(
+        options.output_type.startswith('pdfa'))
 
     task_merge_pages_qpdf = main_pipeline.merge(
         task_func=merge_pages_qpdf,
@@ -1218,10 +1326,23 @@ def build_pipeline(options, work_folder, log, context):
                task_render_hocr_debug_page,
                task_skip_page,
                task_ocr_tesseract_and_render_pdf,
-               task_repair_pdf],
+               task_repair_and_parse_pdf],
         output=os.path.join(work_folder, 'merged.pdf'),
         extras=[log, context])
-    task_merge_pages_qpdf.active_if(options.output_type == 'pdf')
+    task_merge_pages_qpdf.active_if(
+        options.output_type == 'pdf' and not fitz)
+
+    task_merge_pages_mupdf = main_pipeline.merge(
+        task_func=merge_pages_mupdf,
+        input=[task_combine_layers,
+               task_render_hocr_debug_page,
+               task_skip_page,
+               task_ocr_tesseract_and_render_pdf,
+               task_repair_and_parse_pdf],
+        output=os.path.join(work_folder, 'merged.pdf'),
+        extras=[log, context])
+    task_merge_pages_mupdf.active_if(
+        options.output_type == 'pdf' and fitz)
 
     task_merge_sidecars = main_pipeline.merge(
         task_func=merge_sidecars,
@@ -1235,6 +1356,8 @@ def build_pipeline(options, work_folder, log, context):
     # Finalize
     main_pipeline.merge(
         task_func=copy_final,
-        input=[task_merge_pages_ghostscript, task_merge_pages_qpdf],
+        input=[task_merge_pages_ghostscript,
+               task_merge_pages_mupdf,
+               task_merge_pages_qpdf],
         output=options.output_file,
         extras=[log, context])

tests/cache/2400dpi/__-l__eng__-c__textonly_pdf=1__000001.ocr.png__000001.text__pdf__txt/stderr.bin

@@ -0,0 +1 @@
+Tesseract Open Source OCR Engine v4.0.0-beta.1 with Leptonica

tests/cache/2400dpi/__-l__eng__-c__textonly_pdf=1__000001.ocr.png__000001.text__pdf__txt/txt.bin

@@ -0,0 +1,25 @@
+a la Waterman
+
+4 ons linzen
+
+3 liter water
+
+3 uien
+
+bloem, boter
+
+2 kopjes melk
+
+laurier, kruidnagel, kerrie, zout
+
+De linzgen wassen en in -l liter kokend wa-
+ter 1 dag laten weken, 2 liter water bij
+de linzen voegen, zonder het water waarin
+ze geweekt zijn af te gieten, De helft van
+de uien bakken met laurier en Kruicdnagel.
+Alle uien, kerrie en gout bij de linzen
+voegen, Alles aan de kook brengen,. Van de
+bloem met boter en melk een papje maken en
+verder afmaken met de soep, Als de linzen
+gaar Zijn is de soep klaar.
+

tests/cache/aspect/__-l__eng__-c__textonly_pdf=1__000001.ocr.png__000001.text__pdf__txt/stderr.bin

@@ -0,0 +1,3 @@
+Tesseract Open Source OCR Engine v4.0.0-beta.1 with Leptonica
+Too few characters. Skipping this page
+OSD: Weak margin (0.00) for 24 blob text block, but using orientation anyway: 0

tests/cache/aspect/__-l__eng__-c__textonly_pdf=1__000001.ocr.png__000001.text__pdf__txt/txt.bin

@@ -0,0 +1,4 @@
+ 
+
+This should be a perfect circle:
+

tests/cache/aspect/__-l__eng__000001.image__000001.rendered__pdf__txt/stderr.bin

@@ -0,0 +1,3 @@
+Tesseract Open Source OCR Engine v4.0.0-beta.1 with Leptonica
+Too few characters. Skipping this page
+OSD: Weak margin (0.00) for 24 blob text block, but using orientation anyway: 0

tests/cache/aspect/__-l__eng__000001.image__000001.rendered__pdf__txt/txt.bin

@@ -0,0 +1,4 @@
+ 
+
+This should be a perfect circle:
+

tests/cache/aspect/__-l__eng__000001.ocr.png__000001__hocr__txt/hocr.bin

@@ -0,0 +1,27 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN"
+    "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
+<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-beta.1' />
+  <meta name='ocr-capabilities' content='ocr_page ocr_carea ocr_par ocr_line ocrx_word'/>
+</head>
+<body>
+  <div class='ocr_page' id='page_1' title='image "/var/folders/37/78_114p552q16vv6vmgm5kr00000gn/T/com.github.ocrmypdf.bp6c363s/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"><span class='ocrx_word' id='word_1_1' title='bbox 296 96 704 504; x_wconf 95'><strong> </strong></span> 
+     </span>
+    </p>
+   </div>
+   <div class='ocr_carea' id='block_1_2' title="bbox 150 592 841 622">
+    <p class='ocr_par' id='par_1_2' lang='eng' title="bbox 150 592 841 622">
+     <span class='ocr_line' id='line_1_2' title="bbox 150 592 841 622; baseline 0 -6; x_size 30; x_descenders 6; x_ascenders 8"><span class='ocrx_word' id='word_1_2' title='bbox 150 592 230 616; x_wconf 96'><strong>This</strong></span> <span class='ocrx_word' id='word_1_3' title='bbox 260 592 384 616; x_wconf 95'><strong>should</strong></span> <span class='ocrx_word' id='word_1_4' title='bbox 413 592 449 616; x_wconf 95'><strong>be</strong></span> <span class='ocrx_word' id='word_1_5' title='bbox 479 600 493 616; x_wconf 95'><strong>a</strong></span> <span class='ocrx_word' id='word_1_6' title='bbox 523 592 668 622; x_wconf 95'><strong>perfect</strong></span> <span class='ocrx_word' id='word_1_7' title='bbox 698 592 841 616; x_wconf 55'><strong>circle:</strong></span> 
+     </span>
+    </p>
+   </div>
+  </div>
+ </body>
+</html>

tests/cache/aspect/__-l__eng__000001.ocr.png__000001__hocr__txt/stderr.bin

@@ -0,0 +1,3 @@
+Tesseract Open Source OCR Engine v4.0.0-beta.1 with Leptonica
+Too few characters. Skipping this page
+OSD: Weak margin (0.00) for 24 blob text block, but using orientation anyway: 0

tests/cache/aspect/__-l__eng__000001.ocr.png__000001__hocr__txt/txt.bin

@@ -0,0 +1,4 @@
+ 
+
+This should be a perfect circle:
+

tests/cache/cardinal/__-l__eng__-c__textonly_pdf=1__000001.ocr.png__000001.text__pdf__txt/stderr.bin

@@ -0,0 +1 @@
+Tesseract Open Source OCR Engine v4.0.0-beta.1 with Leptonica

tests/cache/cardinal/__-l__eng__-c__textonly_pdf=1__000001.ocr.png__000001.text__pdf__txt/txt.bin

@@ -0,0 +1,123 @@
+The LinnSequencer
+32 Track MIDI Sequence Recorder
+
+The LinnSequencer is a state-of-the-art composition and performance tool for the professional musician. It is
+
+extremely powerful, yet amazingly simple to learn and use. It’s many remarkable features include:
+
+¢ Operation is similar to multi-track tape recorder with PLAY, STOP, RECORD, FAST
+FORWARD, REWIND, and LOCATE controls.
+
+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
+
+synthesizers!
+
+¢ Ultra-fast 3%” disk drive stores complex songs in seconds and holds over 110,000 notes
+
+per disk!
+
+¢ 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
+
+rhythmic value.
+
+¢ TIMING CORRECTION works during playback and operates without ‘chopping’ notes.
+
+¢ Optional SMPTE time code synchronization.
+
+© Optional remote control.
+
+Recording a Sequence
+
+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
+
+corrected! (Timing correction may be adjusted or defeated).
+
+Any additional notes played will be added into the track
+— existing notes are not erased while recording!
+
+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!
+
+Editing
+
+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
+
+added, erased, or changed using the SINGLE STEP func-
+tion. To overdub notes at specific points within a sequence,
+
+Additional Features
+
+simply use LOCATE, FAST FORWARD, or REWIND to
+find the desired bar number, then start recording.
+
+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,
+
+Creating a Song
+
+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.
+
+Composition Without Compromise
+
+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!
+
+* Simple, easy to learn operation—the 32 character LCD display clearly guides you through all operations. If needed, the
+
+HELP button displays additional explanations.
+
+* 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
+
+ERASE, REPEAT, PLAY/STOP, or LOCATE.
+
+¢ Iwo TRIGGER OUTPUTS may be programmed to output pulses at any selected note value.
+
+© Will sync to standard LinnDrum or Linn 9000 sync tone.
+
+© 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!)
+
+¢ TEMPO may be entered numerically, adjustable in tenths of a Beat-Per-Minute increments, or by tapping quarter notes
+
+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.
+
+18720 Oxnard Street, Tarzana, CA 91356
+(818) 708-8131 TELEX #298949 LINN UR
+

tests/cache/cardinal/__-l__eng__-c__textonly_pdf=1__000002.ocr.png__000002.text__pdf__txt/stderr.bin

@@ -0,0 +1 @@
+Tesseract Open Source OCR Engine v4.0.0-beta.1 with Leptonica

tests/cache/cardinal/__-l__eng__-c__textonly_pdf=1__000002.ocr.png__000002.text__pdf__txt/txt.bin

@@ -0,0 +1,123 @@
+The LinnSequencer
+32 Track MIDI Sequence Recorder
+
+The LinnSequencer is a state-of-the-art composition and performance tool for the professional musician. It is
+
+extremely powerful, yet amazingly simple to learn and use. It’s many remarkable features include:
+
+¢ Operation is similar to multi-track tape recorder with PLAY, STOP, RECORD, FAST
+FORWARD, REWIND, and LOCATE controls.
+
+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
+
+synthesizers!
+
+¢ Ultra-fast 3%” disk drive stores complex songs in seconds and holds over 110,000 notes
+
+per disk!
+
+¢ 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
+
+rhythmic value.
+
+¢ TIMING CORRECTION works during playback and operates without ‘chopping’ notes.
+
+¢ Optional SMPTE time code synchronization.
+
+© Optional remote control.
+
+Recording a Sequence
+
+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
+
+corrected! (Timing correction may be adjusted or defeated).
+
+Any additional notes played will be added into the track
+— existing notes are not erased while recording!
+
+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!
+
+Editing
+
+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
+
+added, erased, or changed using the SINGLE STEP func-
+tion. To overdub notes at specific points within a sequence,
+
+Additional Features
+
+simply use LOCATE, FAST FORWARD, or REWIND to
+find the desired bar number, then start recording.
+
+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,
+
+Creating a Song
+
+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.
+
+Composition Without Compromise
+
+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!
+
+* Simple, easy to learn operation—the 32 character LCD display clearly guides you through all operations. If needed, the
+
+HELP button displays additional explanations.
+
+* 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
+
+ERASE, REPEAT, PLAY/STOP, or LOCATE.
+
+¢ Iwo TRIGGER OUTPUTS may be programmed to output pulses at any selected note value.
+
+© Will sync to standard LinnDrum or Linn 9000 sync tone.
+
+© 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!)
+
+¢ TEMPO may be entered numerically, adjustable in tenths of a Beat-Per-Minute increments, or by tapping quarter notes
+
+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.
+
+18720 Oxnard Street, Tarzana, CA 91356
+(818) 708-8131 TELEX #298949 LINN UR
+

tests/cache/cardinal/__-l__eng__-c__textonly_pdf=1__000003.ocr.png__000003.text__pdf__txt/stderr.bin

@@ -0,0 +1 @@
+Tesseract Open Source OCR Engine v4.0.0-beta.1 with Leptonica

tests/cache/cardinal/__-l__eng__-c__textonly_pdf=1__000003.ocr.png__000003.text__pdf__txt/txt.bin

@@ -0,0 +1,123 @@
+The LinnSequencer
+32 Track MIDI Sequence Recorder
+
+The LinnSequencer is a state-of-the-art composition and performance tool for the professional musician. It is
+
+extremely powerful, yet amazingly simple to learn and use. It’s many remarkable features include:
+
+¢ Operation is similar to multi-track tape recorder with PLAY, STOP, RECORD, FAST
+FORWARD, REWIND, and LOCATE controls.
+
+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
+
+synthesizers!
+
+¢ Ultra-fast 3%” disk drive stores complex songs in seconds and holds over 110,000 notes
+
+per disk!
+
+¢ 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
+
+rhythmic value.
+
+¢ TIMING CORRECTION works during playback and operates without ‘chopping’ notes.
+
+¢ Optional SMPTE time code synchronization.
+
+© Optional remote control.
+
+Recording a Sequence
+
+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
+
+corrected! (Timing correction may be adjusted or defeated).
+
+Any additional notes played will be added into the track
+— existing notes are not erased while recording!
+
+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!
+
+Editing
+
+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
+
+added, erased, or changed using the SINGLE STEP func-
+tion. To overdub notes at specific points within a sequence,
+
+Additional Features
+
+simply use LOCATE, FAST FORWARD, or REWIND to
+find the desired bar number, then start recording.
+
+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,
+
+Creating a Song
+
+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.
+
+Composition Without Compromise
+
+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!
+
+* Simple, easy to learn operation—the 32 character LCD display clearly guides you through all operations. If needed, the
+
+HELP button displays additional explanations.
+
+* 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
+
+ERASE, REPEAT, PLAY/STOP, or LOCATE.
+
+¢ Iwo TRIGGER OUTPUTS may be programmed to output pulses at any selected note value.
+
+© Will sync to standard LinnDrum or Linn 9000 sync tone.
+
+© 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!)
+
+¢ TEMPO may be entered numerically, adjustable in tenths of a Beat-Per-Minute increments, or by tapping quarter notes
+
+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.
+
+18720 Oxnard Street, Tarzana, CA 91356
+(818) 708-8131 TELEX #298949 LINN UR
+

tests/cache/cardinal/__-l__eng__-c__textonly_pdf=1__000004.ocr.png__000004.text__pdf__txt/stderr.bin

@@ -0,0 +1 @@
+Tesseract Open Source OCR Engine v4.0.0-beta.1 with Leptonica

tests/cache/cardinal/__-l__eng__-c__textonly_pdf=1__000004.ocr.png__000004.text__pdf__txt/txt.bin

@@ -0,0 +1,123 @@
+The LinnSequencer
+32 Track MIDI Sequence Recorder
+
+The LinnSequencer is a state-of-the-art composition and performance tool for the professional musician. It is
+
+extremely powerful, yet amazingly simple to learn and use. It’s many remarkable features include:
+
+¢ Operation is similar to multi-track tape recorder with PLAY, STOP, RECORD, FAST
+FORWARD, REWIND, and LOCATE controls.
+
+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
+
+synthesizers!
+
+¢ Ultra-fast 3%” disk drive stores complex songs in seconds and holds over 110,000 notes
+
+per disk!
+
+¢ 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
+
+rhythmic value.
+
+¢ TIMING CORRECTION works during playback and operates without ‘chopping’ notes.
+
+¢ Optional SMPTE time code synchronization.
+
+© Optional remote control.
+
+Recording a Sequence
+
+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
+
+corrected! (Timing correction may be adjusted or defeated).
+
+Any additional notes played will be added into the track
+— existing notes are not erased while recording!
+
+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!
+
+Editing
+
+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
+
+added, erased, or changed using the SINGLE STEP func-
+tion. To overdub notes at specific points within a sequence,
+
+Additional Features
+
+simply use LOCATE, FAST FORWARD, or REWIND to
+find the desired bar number, then start recording.
+
+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,
+
+Creating a Song
+
+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.
+
+Composition Without Compromise
+
+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!
+
+* Simple, easy to learn operation—the 32 character LCD display clearly guides you through all operations. If needed, the
+
+HELP button displays additional explanations.
+
+* 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
+
+ERASE, REPEAT, PLAY/STOP, or LOCATE.
+
+¢ Iwo TRIGGER OUTPUTS may be programmed to output pulses at any selected note value.
+
+© Will sync to standard LinnDrum or Linn 9000 sync tone.
+
+© 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!)
+
+¢ TEMPO may be entered numerically, adjustable in tenths of a Beat-Per-Minute increments, or by tapping quarter notes
+
+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.
+
+18720 Oxnard Street, Tarzana, CA 91356
+(818) 708-8131 TELEX #298949 LINN UR
+

tests/cache/cardinal/__-l__osd__--psm__0__000001.ocr.preview.jpg__stdout/stderr.bin

@@ -0,0 +1 @@
+Warning. Invalid resolution 0 dpi. Using 70 instead.

tests/cache/cardinal/__-l__osd__--psm__0__000001.ocr.preview.jpg__stdout/stdout.bin

@@ -0,0 +1,6 @@
+Page number: 0
+Orientation in degrees: 0
+Rotate: 0
+Orientation confidence: 18.91
+Script: Latin
+Script confidence: 0.97

tests/cache/cardinal/__-l__osd__--psm__0__000002.ocr.preview.jpg__stdout/stderr.bin

@@ -0,0 +1 @@
+Warning. Invalid resolution 0 dpi. Using 70 instead.

tests/cache/cardinal/__-l__osd__--psm__0__000002.ocr.preview.jpg__stdout/stdout.bin

@@ -0,0 +1,6 @@
+Page number: 0
+Orientation in degrees: 90
+Rotate: 270
+Orientation confidence: 17.21
+Script: Latin
+Script confidence: 1.06

tests/cache/cardinal/__-l__osd__--psm__0__000003.ocr.preview.jpg__stdout/stderr.bin

@@ -0,0 +1 @@
+Warning. Invalid resolution 0 dpi. Using 70 instead.

tests/cache/cardinal/__-l__osd__--psm__0__000003.ocr.preview.jpg__stdout/stdout.bin

@@ -0,0 +1,6 @@
+Page number: 0
+Orientation in degrees: 180
+Rotate: 180
+Orientation confidence: 14.79
+Script: Latin
+Script confidence: 2.87

tests/cache/cardinal/__-l__osd__--psm__0__000004.ocr.preview.jpg__stdout/stderr.bin

@@ -0,0 +1 @@
+Warning. Invalid resolution 0 dpi. Using 70 instead.

tests/cache/cardinal/__-l__osd__--psm__0__000004.ocr.preview.jpg__stdout/stdout.bin

@@ -0,0 +1,6 @@
+Page number: 0
+Orientation in degrees: 270
+Rotate: 90
+Orientation confidence: 19.19
+Script: Latin
+Script confidence: 0.58

tests/cache/ccitt/__-l__eng__-c__textonly_pdf=1__000001.ocr.png__000001.text__pdf__txt/stderr.bin

@@ -0,0 +1 @@
+Tesseract Open Source OCR Engine v4.0.0-beta.1 with Leptonica

tests/cache/ccitt/__-l__eng__-c__textonly_pdf=1__000001.ocr.png__000001.text__pdf__txt/txt.bin

@@ -0,0 +1,123 @@
+The LinnSequencer
+32 Track MIDI Sequence Recorder
+
+The LinnSequencer is a state-of-the-art composition and performance tool for the professional musician. It is
+
+extremely powerful, yet amazingly simple to learn and use. It’s many remarkable features include:
+
+¢ Operation is similar to multi-track tape recorder with PLAY, STOP, RECORD, FAST
+FORWARD, REWIND, and LOCATE controls.
+
+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
+
+synthesizers!
+
+¢ Ultra-fast 3%” disk drive stores complex songs in seconds and holds over 110,000 notes
+
+per disk!
+
+¢ 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
+
+rhythmic value.
+
+¢ TIMING CORRECTION works during playback and operates without ‘chopping’ notes.
+
+¢ Optional SMPTE time code synchronization.
+
+© Optional remote control.
+
+Recording a Sequence
+
+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
+
+corrected! (Timing correction may be adjusted or defeated).
+
+Any additional notes played will be added into the track
+— existing notes are not erased while recording!
+
+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!
+
+Editing
+
+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
+
+added, erased, or changed using the SINGLE STEP func-
+tion. To overdub notes at specific points within a sequence,
+
+Additional Features
+
+simply use LOCATE, FAST FORWARD, or REWIND to
+find the desired bar number, then start recording.
+
+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,
+
+Creating a Song
+
+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.
+
+Composition Without Compromise
+
+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!
+
+* Simple, easy to learn operation—the 32 character LCD display clearly guides you through all operations. If needed, the
+
+HELP button displays additional explanations.
+
+* 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
+
+ERASE, REPEAT, PLAY/STOP, or LOCATE.
+
+¢ Iwo TRIGGER OUTPUTS may be programmed to output pulses at any selected note value.
+
+© Will sync to standard LinnDrum or Linn 9000 sync tone.
+
+© 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!)
+
+¢ TEMPO may be entered numerically, adjustable in tenths of a Beat-Per-Minute increments, or by tapping quarter notes
+
+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.
+
+18720 Oxnard Street, Tarzana, CA 91356
+(818) 708-8131 TELEX #298949 LINN UR
+

tests/cache/ccitt/__-l__eng__000001.image__000001.rendered__pdf__txt/stderr.bin

@@ -0,0 +1 @@
+Tesseract Open Source OCR Engine v4.0.0-beta.1 with Leptonica

tests/cache/ccitt/__-l__eng__000001.image__000001.rendered__pdf__txt/txt.bin

@@ -0,0 +1,123 @@
+The LinnSequencer
+32 Track MIDI Sequence Recorder
+
+The LinnSequencer is a state-of-the-art composition and performance tool for the professional musician. It is
+
+extremely powerful, yet amazingly simple to learn and use. It’s many remarkable features include:
+
+¢ Operation is similar to multi-track tape recorder with PLAY, STOP, RECORD, FAST
+FORWARD, REWIND, and LOCATE controls.
+
+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
+
+synthesizers!
+
+¢ Ultra-fast 3%” disk drive stores complex songs in seconds and holds over 110,000 notes
+
+per disk!
+
+¢ 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
+
+rhythmic value.
+
+¢ TIMING CORRECTION works during playback and operates without ‘chopping’ notes.
+
+¢ Optional SMPTE time code synchronization.
+
+© Optional remote control.
+
+Recording a Sequence
+
+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
+
+corrected! (Timing correction may be adjusted or defeated).
+
+Any additional notes played will be added into the track
+— existing notes are not erased while recording!
+
+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!
+
+Editing
+
+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
+
+added, erased, or changed using the SINGLE STEP func-
+tion. To overdub notes at specific points within a sequence,
+
+Additional Features
+
+simply use LOCATE, FAST FORWARD, or REWIND to
+find the desired bar number, then start recording.
+
+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,
+
+Creating a Song
+
+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.
+
+Composition Without Compromise
+
+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!
+
+* Simple, easy to learn operation—the 32 character LCD display clearly guides you through all operations. If needed, the
+
+HELP button displays additional explanations.
+
+* 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
+
+ERASE, REPEAT, PLAY/STOP, or LOCATE.
+
+¢ Iwo TRIGGER OUTPUTS may be programmed to output pulses at any selected note value.
+
+© Will sync to standard LinnDrum or Linn 9000 sync tone.
+
+© 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!)
+
+¢ TEMPO may be entered numerically, adjustable in tenths of a Beat-Per-Minute increments, or by tapping quarter notes
+
+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.
+
+18720 Oxnard Street, Tarzana, CA 91356
+(818) 708-8131 TELEX #298949 LINN UR
+

tests/cache/francais/__-l__fra__-c__textonly_pdf=1__000001.ocr.png__000001.text__pdf__txt/stderr.bin

@@ -0,0 +1 @@
+Tesseract Open Source OCR Engine v4.0.0-beta.1 with Leptonica

tests/cache/francais/__-l__fra__-c__textonly_pdf=1__000001.ocr.png__000001.text__pdf__txt/txt.bin

@@ -0,0 +1,13 @@
+Portez ce vieux whisky au juge
+blond qui fume sur son île
+intérieure, à côté de l'alcôve
+ovoide, où les bûches se
+consument dans l'âtre, ce qui
+lui permet de penser à la
+cænogénèse de l'être dont il
+est question dans la cause
+ambiguë entendue à Moÿ, dans
+un capharnaüm qui, pense-t-il,
+diminue cà et là la qualité de son
+œuvre.
+

tests/cache/graph_ocred/__-l__eng__-c__textonly_pdf=1__000001.ocr.png__000001.text__pdf__txt/stderr.bin

@@ -0,0 +1,2 @@
+Tesseract Open Source OCR Engine v4.0.0-beta.1 with Leptonica
+OSD: Weak margin (4.74) for 181 blob text block, but using orientation anyway: 0

tests/cache/graph_ocred/__-l__eng__-c__textonly_pdf=1__000001.ocr.png__000001.text__pdf__txt/txt.bin

@@ -0,0 +1,20 @@
+Replacement of "creationism" with "intelligent design"
+
+120
+
+ 
+
+—@— "Creation" and "creationist"
+—®@-— "Intelligent design"
+and "design proponent"
+
+Word count
+
+ 
+
+ 
+
+ 
+
+ 
+

tests/cache/jbig2/__-l__eng__-c__textonly_pdf=1__000001.ocr.png__000001.text__pdf__txt/stderr.bin

@@ -0,0 +1 @@
+Tesseract Open Source OCR Engine v4.0.0-beta.1 with Leptonica