Fix Py3.5 not understanding os.path.exists(Path(...))

Leave PDF/A check alone for now, since pikepdf has no equivalent.

.coveragerc

@@ -0,0 +1,16 @@
+# Coverage isn't really compatible with subprocesses so results are unreliable
+
+[run]
+branch = True
+#concurrency = multiprocessing
+source = ocrmypdf/
+
+[report]
+exclude_lines =
+	pragma: no cover
+	def __repr__
+	raise AssertionError
+	raise NotImplementedError
+	if 0:
+	if False:
+	if __name__ == .__main__.:

.docker/Dockerfile

@@ -0,0 +1,50 @@
+# OCRmyPDF
+#
+FROM      ubuntu:18.04
+
+RUN apt-get update && apt-get install -y --no-install-recommends \
+  ocrmypdf \
+  unpaper \
+  tesseract-ocr-eng \
+  tesseract-ocr-fra \
+  tesseract-ocr-deu \
+  tesseract-ocr-spa \
+  tesseract-ocr-por \
+  tesseract-ocr-chi-sim \
+  python3-venv \
+  python3-pip
+
+ENV LANG=C.UTF-8
+
+RUN python3 -m venv --system-site-packages /appenv
+
+# This installs the latest binary wheel instead of the code in the current
+# folder. Installing from source will fail, apparently because cffi needs
+# build-essentials (gcc) to do a source installation 
+# (i.e. "pip install ."). It's unclear to me why this is the case.
+RUN . /appenv/bin/activate; \
+  pip install --upgrade pip \
+  && pip install ocrmypdf[fitz]
+
+# Now copy the application in, mainly to get the test suite.
+# Do this now to make the best use of Docker cache.
+COPY . /application
+RUN . /appenv/bin/activate; \
+  pip install -r /application/test_requirements.txt
+
+# Remove the junk, including the source version of application since it was
+# already installed
+RUN rm -rf /tmp/* /var/tmp/* /root/* /application/ocrmypdf \
+  && apt-get autoremove -y \
+  && apt-get autoclean -y
+
+RUN useradd docker \
+  && mkdir /home/docker \
+  && chown docker:docker /home/docker
+
+USER docker
+WORKDIR /home/docker
+
+# Must use array form of ENTRYPOINT
+# Non-array form does not append other arguments, because that is "intuitive"
+ENTRYPOINT ["/application/.docker/docker-wrapper.sh"]

.docker/Dockerfile.polyglot

@@ -0,0 +1,17 @@
+# OCRmyPDF polyglot
+#
+FROM      jbarlow83/ocrmypdf:latest
+
+USER root
+
+# Update system and install our dependencies
+RUN apt-get update && apt-get install -y --no-install-recommends \
+  tesseract-ocr-all 
+
+RUN apt-get autoremove -y && apt-get clean -y
+
+USER docker
+
+# Must use array form of ENTRYPOINT
+# Non-array form does not append other arguments, because that is "intuitive"
+ENTRYPOINT ["/application/.docker/docker-wrapper.sh"]

.docker/docker-wrapper.sh

@@ -0,0 +1,5 @@
+#!/bin/bash
+
+. /appenv/bin/activate
+cd /home/docker
+exec ocrmypdf "$@"

.dockerignore

@@ -0,0 +1,25 @@
+*.ipynb
+*.pdf
+*.pyc
+*.rst
+*.sublime*
+**/*.pyc
+.*/
+!.docker/
+.ruffus_history.sqlite
+bin/
+build/
+docs/
+dist/
+htmlcov/
+include/
+lib/
+MANIFEST.in
+ocrmypdf.egg-info/
+staging/
+tests/cache/
+tests/output/
+tests/resources/private/
+tmp/
+venv*/
+wheelhouse/

.git_archival.txt

@@ -0,0 +1 @@
+ref-names: $Format:%D$

.gitattributes

@@ -1,22 +1,13 @@
 # Always use Unix convention for new lines
 * text eol=lf
 
-# Custom for Visual Studio
-*.cs     diff=csharp
-*.sln    merge=union
-*.csproj merge=union
-*.vbproj merge=union
-*.fsproj merge=union
-*.dbproj merge=union
+# These files are binary and should be left untouched
+# (binary is a macro for -text -diff)
+*.jar	binary
+*.pdf	binary
+*.PDF	binary
+*.png	binary
+*.jpg	binary
+*.bin   binary
 
-# Standard to msysgit
-*.doc	 diff=astextplain
-*.DOC	 diff=astextplain
-*.docx diff=astextplain
-*.DOCX diff=astextplain
-*.dot  diff=astextplain
-*.DOT  diff=astextplain
-*.pdf  diff=astextplain
-*.PDF	 diff=astextplain
-*.rtf	 diff=astextplain
-*.RTF	 diff=astextplain
+.git_archival.txt  export-subst

.github/ISSUE_TEMPLATE

@@ -0,0 +1,12 @@
+Please include the command line and a test file with your issue report.
+
+If possible, please use a test file that we can include in future test cases (no personal information, no copyrighted material).
+
+If you wish to encrypt a test file so that only the maintainer of OCRmyPDF can view it, you may use:
+
+```bash
+
+gpg --recv-keys 4434eb74c4a35f7f --keyserver pgp.mit.edu
+gpg --output test.pdf.gpg --encrypt --receipient 4434eb74c4a35f7f test.pdf
+
+```

.gitignore

@@ -1,167 +1,45 @@
-releasePackage.sh
-tmp/
-log/
+# Development environment
+*.pyc
+*.sublime-*
+venv*/
+pyvenv.cfg
+tasks.py
+.bash_history
+.ruffus_history.sqlite
+.idea/
+.pytest_cache/
 
-#################
-## Eclipse
-#################
+# Package building
+*.egg-info/
+.cache/
+.eggs/
+build/
+dist/
+wheelhouse/
 
-*.pydevproject
-.project
-.metadata
-bin/
-tmp/
-*.tmp
-*.bak
-*.swp
-*~.nib
-local.properties
-.classpath
-.settings/
-.loadpath
+# Automatically generated files
+ocrmypdf/lib/_*.py
+ocrmypdf/version.py
+docs/_build/
+docs/_static/
+docs/_templates/
+docs/Makefile
 
-# External tool builders
-.externalToolBuilders/
-
-# Locally stored "Eclipse launch configurations"
-*.launch
-
-# CDT-specific
-.cproject
-
-# PDT-specific
-.buildpath
-
-
-#################
-## Visual Studio
-#################
-
-## Ignore Visual Studio temporary files, build results, and
-## files generated by popular Visual Studio add-ons.
-
-# User-specific files
-*.suo
-*.user
-*.sln.docstates
-
-# Build results
-[Dd]ebug/
-[Rr]elease/
-*_i.c
-*_p.c
-*.ilk
-*.meta
-*.obj
-*.pch
-*.pdb
-*.pgc
-*.pgd
-*.rsp
-*.sbr
-*.tlb
-*.tli
-*.tlh
-*.tmp
-*.vspscc
-.builds
-*.dotCover
-
-## TODO: If you have NuGet Package Restore enabled, uncomment this
-#packages/
-
-# Visual C++ cache files
-ipch/
-*.aps
-*.ncb
-*.opensdf
-*.sdf
-
-# Visual Studio profiler
-*.psess
-*.vsp
-
-# ReSharper is a .NET coding add-in
-_ReSharper*
-
-# Installshield output folder
-[Ee]xpress
-
-# DocProject is a documentation generator add-in
-DocProject/buildhelp/
-DocProject/Help/*.HxT
-DocProject/Help/*.HxC
-DocProject/Help/*.hhc
-DocProject/Help/*.hhk
-DocProject/Help/*.hhp
-DocProject/Help/Html2
-DocProject/Help/html
-
-# Click-Once directory
-publish
-
-# Others
-[Bb]in
-[Oo]bj
-sql
-TestResults
-*.Cache
-ClientBin
-stylecop.*
-~$*
-*.dbmdl
-Generated_Code #added for RIA/Silverlight projects
-
-# Backup & report files from converting an old project file to a newer
-# Visual Studio version. Backup files are not needed, because we have git ;-)
-_UpgradeReport_Files/
-Backup*/
-UpgradeLog*.XML
-
-
-
-############
-## Windows
-############
-
-# Windows image file caches
-Thumbs.db
-
-# Folder config file
-Desktop.ini
-
-
-#############
-## Python
-#############
-
-*.py[co]
-
-# Packages
-*.egg
-*.egg-info
-dist
-build
-eggs
-parts
-bin
-var
-sdist
-develop-eggs
-.installed.cfg
-
-# Installer logs
-pip-log.txt
-
-# Unit test / coverage reports
+# Code coverage
 .coverage
-.tox
+htmlcov/
 
-#Translations
-*.mo
-
-#Mr Developer
-.mr.developer.cfg
-
-# Mac crap
-.DS_Store
+# Testing
+log/
+/*.pdf
+/*.qdf
+*.ipynb
+.ipynb_checkpoints/
+tests/output/
+tests/resources/private/
+tmp/
+pdfbox-app*.jar
+.vscode/
+IDEAS
+_Dockerfile.local
+scratch.py

.travis.yml

@@ -0,0 +1,129 @@
+dist: trusty
+language: python
+cache:
+  pip: true
+  directories:
+  - $HOME/Library/Caches/Homebrew
+
+addons:
+  apt:
+    update: true
+    sources:
+    - sourceline: 'ppa:alex-p/tesseract-ocr'
+    - sourceline: 'ppa:heyarje/libav-11'
+    - sourceline: 'ppa:vshn/ghostscript'
+    packages:
+    - ghostscript
+    - libavcodec56
+    - libavformat56
+    - libavutil54
+    - libffi-dev
+    - pngquant
+    - poppler-utils
+    - qpdf
+    - tesseract-ocr
+    - tesseract-ocr-deu
+    - tesseract-ocr-eng
+    - tesseract-ocr-fra
+
+env:
+  global:
+    - secure: "hsf6MT+n2x3OiDM2fQyJZdV0/PWYmv81LdVqC6cfnHBE/8N3DloJRqQ7WfO14TxhiK9PEC7MpyCj0lSabUHEO7gSH6Vks6I1asoSkt8S9/bSMlhT4hei+pwVpeGEiU5xHVATNjY+D919VC3IFvc3XmjT74h/2SLhaZ+jhEmDggM="  # HOMEBREW_OCRMYPDF_TOKEN
+
+matrix:
+  include:
+    - os: linux
+      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 $HOME/.cache/pip/log/debug.log
+
+before_install: |
+  mkdir -p bin
+  if [[ "$TRAVIS_OS_NAME" == "linux" ]]; then
+    pip3 install --upgrade pip
+    pip3 install --upgrade wheel
+    mkdir -p packages
+    wget -q 'https://www.dropbox.com/s/vaq0kbwi6e6au80/unpaper_6.1-1.deb?raw=1' -O packages/unpaper_6.1-1.deb
+    sudo dpkg -i packages/unpaper_6.1-1.deb
+  elif [[ "$TRAVIS_OS_NAME" == "osx" ]]; then
+    brew update && brew bundle --file=.travis/Brewfile
+    pip3 install --upgrade pip
+    pip3 install wheel
+  fi
+
+install:
+- export PATH=$PWD/bin:$PATH
+- pip3 install ".$EXTRAS"
+- pip3 install -r test_requirements.txt
+
+script:
+- tesseract --version
+- qpdf --version
+- pytest -n auto
+
+deploy:
+  # release for main pypi
+  # 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
+  user: ocrmypdf-travis
+  password:
+    secure: "DTFOmmNL6olA0+yXvp4u9jXZlZeqrJsJ0526jzqf4a3gZ6jnGTq5UI6WzRsslSyoMMfXKtHQebqHM6ogSgCZinyZ3ufHJo8fn9brxbEc2gsiWkbj5o3bGwdWMT1vNNE7XW0VCpw87rZ1EEwjl4FJHFudMlPR1yfU5+uq0k0PACo="
+  distributions: "sdist bdist_wheel"
+  on:
+    branch: master
+    tags: true
+    condition: $TRAVIS_PYTHON_VERSION == "3.6" && $TRAVIS_OS_NAME == "linux" && $EXTRAS == ""
+  skip_upload_docs: true
+
+  # test pypi
+- provider: pypi
+  server: https://testpypi.pypi.org/legacy/
+  user: ocrmypdf-travis
+  password:
+    secure: "DTFOmmNL6olA0+yXvp4u9jXZlZeqrJsJ0526jzqf4a3gZ6jnGTq5UI6WzRsslSyoMMfXKtHQebqHM6ogSgCZinyZ3ufHJo8fn9brxbEc2gsiWkbj5o3bGwdWMT1vNNE7XW0VCpw87rZ1EEwjl4FJHFudMlPR1yfU5+uq0k0PACo="
+  distributions: "sdist"
+  on:
+    branch: develop
+    tags: false
+    condition: $TRAVIS_OS_NAME == "osx"
+  skip_upload_docs: true
+
+  # null deploy for osx
+  # we really just want to run after_deploy *after* pypi upload is done, but
+  # after_deploy on runs if a given box deployed
+- provider: script
+  script: /usr/bin/true
+  on:
+    branch: master
+    tags: true
+    condition: $TRAVIS_OS_NAME == "osx"
+
+after_deploy: |
+  if [[ "$TRAVIS_OS_NAME" == "osx" ]]; then
+    bash .travis/osx_brew.sh
+  fi

.travis/Brewfile

@@ -0,0 +1,15 @@
+brew 'python'
+
+brew 'ghostscript'
+brew 'jbig2dec'
+brew 'jbig2enc'
+brew 'leptonica'
+brew 'libffi'
+brew 'libtiff'
+brew 'libxml2'
+brew 'mupdf-tools'
+brew 'openjpeg'
+brew 'pngquant'
+brew 'qpdf'
+brew 'tesseract'
+brew 'unpaper'

.travis/autobrew.py

@@ -0,0 +1,93 @@
+#!/usr/bin/env python3
+# © 2017-18 James R. Barlow: github.com/jbarlow83
+
+from string import Template
+from subprocess import run, PIPE
+import re
+
+recipe_template = Template("""
+class Ocrmypdf < Formula
+  include Language::Python::Virtualenv
+
+  desc "Adds an OCR text layer to scanned PDF files"
+  homepage "https://github.com/jbarlow83/OCRmyPDF"
+  ${ocrmypdf_url}
+  ${ocrmypdf_sha256}
+
+  depends_on "pkg-config" => :build
+  depends_on "mupdf-tools" => :build  # statically links libmupdf.a
+  depends_on "freetype"
+  depends_on "ghostscript"
+  depends_on "jpeg"
+  depends_on "libpng"
+  depends_on "python"
+  depends_on "qpdf"
+  depends_on "tesseract"
+  depends_on "unpaper"
+
+${resources}
+  def install
+    venv = virtualenv_create(libexec, "python3")
+
+    resource("Pillow").stage do
+      inreplace "setup.py" do |s|
+        sdkprefix = MacOS::CLT.installed? ? "" : MacOS.sdk_path
+        s.gsub! "openjpeg.h", "probably_not_a_header_called_this_eh.h"
+        s.gsub! "ZLIB_ROOT = None", "ZLIB_ROOT = ('#{sdkprefix}/usr/lib', '#{sdkprefix}/usr/include')"
+        s.gsub! "JPEG_ROOT = None", "JPEG_ROOT = ('#{Formula["jpeg"].opt_prefix}/lib', '#{Formula["jpeg"].opt_prefix}/include')"
+        s.gsub! "FREETYPE_ROOT = None", "FREETYPE_ROOT = ('#{Formula["freetype"].opt_prefix}/lib', '#{Formula["freetype"].opt_prefix}/include')"
+      end
+
+      # avoid triggering "helpful" distutils code that doesn't recognize Xcode 7 .tbd stubs
+      ENV.append "CFLAGS", "-I#{MacOS.sdk_path}/System/Library/Frameworks/Tk.framework/Versions/8.5/Headers" unless MacOS::CLT.installed?
+      venv.pip_install Pathname.pwd
+    end
+
+    res = resources.map(&:name).to_set - ["Pillow"]
+
+    res.each do |r|
+      venv.pip_install resource(r)
+    end
+
+    venv.pip_install_and_link buildpath
+  end
+
+  test do
+    # Since we use Python 3, we require a UTF-8 locale
+    ENV["LC_ALL"] = "en_US.UTF-8"
+
+    system "#{bin}/ocrmypdf", "-f", "-q", "--deskew",
+                              test_fixtures("test.pdf"), "ocr.pdf"
+    assert_predicate testpath/"ocr.pdf", :exist?
+  end
+end
+""")
+
+def main():
+    p = run(['poet', '--single', 'ocrmypdf'],
+            encoding='utf-8', stdout=PIPE, check=True)
+
+    ocrmypdf_lines = p.stdout.splitlines()
+    ocrmypdf_url = ocrmypdf_lines[1].strip()
+    ocrmypdf_sha256 = ocrmypdf_lines[2].strip()
+
+    ocrmypdf_version = re.search(
+        r'ocrmypdf-(.+)\.tar.*', ocrmypdf_url).group(1)
+    print(f"Autobrewing {ocrmypdf_version}")
+
+    p = run(['poet', '--resources', 'ocrmypdf'],
+            encoding='utf-8', stdout=PIPE, check=True)
+
+    poet_resources = p.stdout
+
+    # Remove the duplicate "ocrmypdf" resource block
+    all_resources = poet_resources.split('resource')
+    kept_resources = [block for block in all_resources if 'ocrmypdf' not in block]
+    resources = 'resource'.join(kept_resources)
+
+    with open('ocrmypdf.rb', 'w') as out:
+        out.write(recipe_template.substitute(**locals()))
+
+
+if __name__ == '__main__':
+    main()

.travis/osx_brew.sh

@@ -0,0 +1,23 @@
+#!/bin/bash
+# © 2017 James R. Barlow: github.com/jbarlow83
+set -uo pipefail
+set -x
+
+pip3 install homebrew-pypi-poet
+python3 .travis/autobrew.py
+cat ocrmypdf.rb
+
+# brew audit crashes Travis
+#brew audit ocrmypdf.rb
+
+# Important: disable debug output so token is hidden
+set +x
+git clone https://$HOMEBREW_OCRMYPDF_TOKEN@github.com/jbarlow83/homebrew-ocrmypdf.git
+set -x
+
+pushd homebrew-ocrmypdf
+cp ../ocrmypdf.rb Formula/ocrmypdf.rb
+git add Formula/ocrmypdf.rb
+git commit -m "homebrew-ocrmypdf: automatic release $TRAVIS_BUILD_NUMBER $TRAVIS_TAG"
+git push origin master
+popd

COPYRIGHT.md

@@ -1,17 +0,0 @@
-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.

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>.

MANIFEST.in

@@ -0,0 +1,49 @@
+# requirements
+include requirements.txt
+include test_requirements.txt
+include dev_requirements.txt
+
+# git
+include .git_archival.txt
+
+# docker
+include .dockerignore
+recursive-include .docker *
+
+# tests
+include .coveragerc
+recursive-include tests *.jpg
+recursive-include tests *.png
+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 *
+
+# documentation
+include LICENSE
+include *.rst
+recursive-exclude .github * 
+recursive-include docs *.py
+recursive-include docs *.rst
+recursive-include docs *.svg
+recursive-exclude docs/_build *
+
+
+# support files
+recursive-include src/ocrmypdf/data *
+include *.py
+exclude tasks.py
+recursive-exclude .travis *
+exclude .travis*
+
+
+# code
+recursive-include src/ocrmypdf *.py
+exclude ocrmypdf/lib/_leptonica.py
+
+
+

OCRmyPDF.sh

@@ -1,336 +0,0 @@
-#!/bin/sh
-##############################################################################
-# Copyright (c) 2013: fritz-hh from Github (https://github.com/fritz-hh)
-##############################################################################
-
-VERSION="alpha0"
-
-usage() {
-	cat << EOF
---------------------------------------------------------------------------------------
-Script aimed at generating a searchable PDF file from a PDF file containing only images.
-(The script performs optical character recognition of each respective page using the
-tesseract engine)
-
-Copyright: fritz from NAS4Free forum
-Version: $VERSION
-
-Usage: OCRmyPDF.sh  [-h] [-v] [-g] [-k] [-d] [-c] [-i] [-l language] [-C filename] inputfile outputfile
-
--h : Display this help message
--v : Increase the verbosity (this option can be used more than once)
--g : Activate debug mode:
-     - Generates a PDF file containing each page twice (once with the image, once without the image
-       but with the OCRed text as well as the detected bounding boxes)
-     - Set the verbosity to the highest possible 
--k : Do not delete the temporary files
--d : Deskew each page before performing OCR
--c : Clean each page before performing OCR
--i : Incorporate the cleaned image in the final PDF file (by default the original image	
-     image, or the deskewed image if the -d option is set, is incorporated)
--l : Set the language of the PDF file in order to improve OCR results (default "eng")
-     Any language supported by tesseract is supported.
--C : Pass an additional configuration file to the tesseract OCR engine.
-     (this option can be used more than once)
-     Note: The configuration file must be available in the "tessdata/configs" folder
-     of your tesseract installation
-inputfile  : PDF file to be OCRed
-outputfile : The PDF/A file to be generated 
---------------------------------------------------------------------------------------
-EOF
-}
-
-
-#################################################
-# Get an absolute path from a relative path to a file
-#
-# Param1 : Relative path
-# Returns: 1 if the folder in which the file is located does not exist
-#          0 otherwise
-################################################# 
-absolutePath() {
-	local wdsave absolutepath 
-	wdsave="`pwd`"
-	! cd "`dirname "$1"`" 1> /dev/null 2> /dev/null && return 1
-	absolutepath="`pwd`/`basename $1`"
-	cd "$wdsave"
-	echo "$absolutepath"
-	return 0
-}
-
-
-
-# Initialization of constants
-EXIT_BAD_ARGS="1"		# possible exit codes
-EXIT_BAD_INPUT_FILE="2"
-EXIT_MISSING_DEPENDENCY="3"
-EXIT_INVALID_OUPUT_PDFA="4"
-EXIT_OTHER_ERROR="5"
-LOG_ERR="0"			# 0=only error messages
-LOG_INFO="1"			# 1=error messages and some infos
-LOG_DEBUG="2"			# 2=debug level logging
-SRC="./src"				# location of the source folder (except source of external tools like jhove)
-JHOVE="./jhove/bin/JhoveApp.jar"	# java SW for validating the final PDF/A
-JHOVE_CFG="./jhove/conf/jhove.conf"	# location of the jhove config file
-
-# Initialization the configuration parameters with default values
-VERBOSITY="$LOG_ERR"		# default verbosity level
-LAN="eng"			# default language of the PDF file (required to get good OCR results)
-KEEP_TMP="0"			# do not delete the temporary files (default)
-PREPROCESS_DESKEW="0"		# 0=no, 1=yes (deskew image)
-PREPROCESS_CLEAN="0"		# 0=no, 1=yes (clean image to improve OCR)
-PREPROCESS_CLEANTOPDF="0"	# 0=no, 1=yes (put cleaned image in final PDF)
-DEBUG_MODE="0"			# 0=no, 1=yes (generates each PDF page twice, with and without image)
-TESS_CFG_FILES=""		# list of additional configuration files to be used by tesseract
-
-# Parse optional command line arguments
-while getopts ":hvgkdcil:C:" opt; do
-	case $opt in
-		h) usage ; exit 0 ;;
-		v) VERBOSITY=$(($VERBOSITY+1)) ;;
-		g) VERBOSITY="10"; DEBUG_MODE="1" ;;
-		k) KEEP_TMP="1" ;;
-		d) PREPROCESS_DESKEW="1" ;;
-		c) PREPROCESS_CLEAN="1" ;;
-		i) PREPROCESS_CLEANTOPDF="1" ;;
-		l) LAN="$OPTARG" ;;
-		C) TESS_CFG_FILES="$OPTARG $TESS_CFG_FILES" ;;
-		\?)
-			echo "Invalid option: -$OPTARG" >&2
-			usage
-			exit $EXIT_BAD_ARGS ;;
-		:)
-			echo "Option -$OPTARG requires an argument" >&2
-			usage
-			exit $EXIT_BAD_ARGS ;;
-	esac
-done
-
-# Remove the optional arguments parsed above.
-shift $((OPTIND-1))
-
-# Check if the number of mandatory parameters
-# provided is as expected
-if [ "$#" -ne "2" ]; then
-	echo "Exactly one mandatory argument shall be provided" >&2
-	usage
-	exit $EXIT_BAD_ARGS
-fi
-
-! absolutePath "$1" > /dev/null && echo "The folder in which the input file should be located does not exist. Exiting..." >&2 && exit $EXIT_BAD_ARGS
-FILE_INPUT_PDF="`absolutePath "$1"`"
-! absolutePath "$2" > /dev/null  && echo "The folder in which the output file should be generated does not exist. Exiting..." >&2 && exit $EXIT_BAD_ARGS
-FILE_OUTPUT_PDFA="`absolutePath "$2"`"
-
-
-
-# set script path as working directory
-cd "`dirname $0`"
-
-[ $VERBOSITY -ge $LOG_INFO ] && echo "OCRmyPDF version: $VERSION"
-
-# check if the required utilities are installed
-[ $VERBOSITY -ge $LOG_DEBUG ] && echo "Checking if all dependencies are installed"
-! command -v identify > /dev/null && echo "Please install ImageMagick. Exiting..." >&2 && exit $EXIT_MISSING_DEPENDENCY
-! command -v pdfimages > /dev/null && echo "Please install poppler-utils. Exiting..." >&2 && exit $EXIT_MISSING_DEPENDENCY
-! command -v pdftoppm > /dev/null && echo "Please install poppler-utils. Exiting..." >&2 && exit $EXIT_MISSING_DEPENDENCY
-! command -v pdftk > /dev/null && echo "Please install pdftk. Exiting..." >&2 && exit $EXIT_MISSING_DEPENDENCY
-[ $PREPROCESS_CLEAN -eq 1 ] && ! command -v unpaper > /dev/null && echo "Please install unpaper. Exiting..." >&2 && exit $EXIT_MISSING_DEPENDENCY
-! command -v tesseract > /dev/null && echo "Please install tesseract and tesseract-data. Exiting..." >&2 && exit $EXIT_MISSING_DEPENDENCY
-! command -v python > /dev/null && echo "Please install python, and the python libraries: reportlab, lxml. Exiting..." >&2 && exit $EXIT_MISSING_DEPENDENCY
-! command -v gs > /dev/null && echo "Please install ghostcript. Exiting..." >&2 && exit $EXIT_MISSING_DEPENDENCY
-! command -v java > /dev/null && echo "Please install java. Exiting..." >&2 && exit $EXIT_MISSING_DEPENDENCY
-
-
-
-
-# Initialize path to temporary files
-TMP_FLD="./tmp/`date +"%Y%m%d_%H%M"`.filename.`basename "$FILE_INPUT_PDF" | sed s/[.][^.]*//`"
-FILE_SIZE_PAGES="$TMP_FLD/page-sizes.txt"		# size in pt of the respective page of the input PDF file
-FILES_OCRed_PDFS="${TMP_FLD}/*-ocred.pdf"		# string matching all 1 page PDF files that need to be merged
-FILE_OUTPUT_PDF="${TMP_FLD}/ocred.pdf"			# name of the OCRed PDF file before conversion to PDF/A
-FILE_VALIDATION_LOG="${TMP_FLD}/pdf_validation.log"	# log file containing the results of the validation of the PDF/A file
-
-# Create tmp folder
-[ $VERBOSITY -ge $LOG_DEBUG ] && echo "Creating temporary folder"
-rm -r -f "${TMP_FLD}"
-mkdir -p "${TMP_FLD}"
-
-
-
-
-# get the size of each pdf page (width / height) in pt (inch*72)
-[ $VERBOSITY -ge $LOG_DEBUG ] && echo "Input file: Extracting size of each page (in pt)"
-! identify -format "%w %h\n" "$FILE_INPUT_PDF" > "$FILE_SIZE_PAGES" \
-	&& echo "Could not get size of PDF pages. Exiting..." >&2 && exit $EXIT_BAD_INPUT_FILE
-sed -I "" '/^$/d' "$FILE_SIZE_PAGES"	# removing empty lines (last one should be)
-numpages=`cat "$FILE_SIZE_PAGES" | wc -l | sed 's/^ *//g'`
-[ $VERBOSITY -ge $LOG_INFO ] && echo "Input file: The file has $numpages pages"
-
-# Itterate the pages of the input pdf file
-cpt="1"
-while read pageSize ; do
-
-	# add leading zeros to the page number
-	page=`printf "%04d" $cpt`
-	[ $VERBOSITY -ge $LOG_INFO ] && echo "Processing page $page"
-	
-	# create the name of the required file
-	curOrigImg="$TMP_FLD/${page}_Image"			# original image available in the current PDF page 
-							# (the image file may have a different orientation than in the pdf file)
-	curHocr="$TMP_FLD/$page.hocr"			# hocr file to be generated by the OCR SW for the current page
-	curOCRedPDF="$TMP_FLD/${page}-ocred.pdf"		# PDF file containing the image + the OCRed text for the current page
-	curOCRedPDFDebug="$TMP_FLD/${page}-debug-ocred.pdf"	# PDF file containing data required to find out if OCR worked correctly
-	
-	# get width / height of PDF page (in pt)
-	widthPDF=`echo $pageSize | cut -f1 -d" "`
-	heightPDF=`echo $pageSize | cut -f2 -d" "`
-	[ $VERBOSITY -ge $LOG_DEBUG ] && echo "Page $page: size ${heightPDF}x${widthPDF} (h*w in pt)"
-	# extract raw image from pdf file to compute resolution
-	# unfortunatelly this image can have another orientation than in the pdf...
-	# so we will have to extract it again later
-	pdfimages -f $page -l $page -j "$FILE_INPUT_PDF" "$curOrigImg" 1>&2	
-	# count number of extracted images
-	nbImg=`ls -1 "$curOrigImg"* | wc -l`
-	[ $nbImg -ne "1" ] && echo "Expecting exactly 1 image on page $page (found $nbImg). Exiting..." >&2 && exit $EXIT_BAD_INPUT_FILE
-	# Get characteristics of the extracted image
-	curImg=`ls -1 "$curOrigImg"*`
-	propCurImg=`identify -format "%w %h %[colorspace]" "$curImg"`
-	widthCurImg=`echo "$propCurImg" | cut -f1 -d" "`
-	heightCurImg=`echo "$propCurImg" | cut -f2 -d" "`
-	colorspaceCurImg=`echo "$propCurImg" | cut -f3 -d" "`
-	# switch height/width values if the image has not the right orientation
-	# we make here the assumption that vertical/horizontal dpi are equal
-	# we will check that later
-	if [ $((($heightPDF-$widthPDF)*($heightCurImg-$widthCurImg))) -lt 0 ]; then
-		[ $VERBOSITY -ge $LOG_DEBUG ] && echo "Page $page: Extracted image has wrong orientation. Inverting image height/width values"
-		tmpval=$heightCurImg
-		heightCurImg=$widthCurImg
-		widthCurImg=$tmpval
-	fi
-	[ $VERBOSITY -ge $LOG_DEBUG ] && echo "Page $page: size ${heightCurImg}x${widthCurImg} (h*w pixel)"	
-	# compute the resolution of the image
-	dpi_x=$(($widthCurImg*72/$widthPDF))
-	dpi_y=$(($heightCurImg*72/$heightPDF))
-	[ "$dpi_x" -ne "$dpi_y" ] && echo "X/Y resolutions not equal ($dpi_x/$dpi_y). Exiting..." >&2 && exit $EXIT_BAD_INPUT_FILE
-	dpi="$dpi_x"
-	
-	# Identify if page image should be saved as ppm (color) or pgm (gray)
-	ext="ppm"
-	opt=""		
-	if [ $colorspaceCurImg == "Gray" ]; then
-		ext="pgm"
-		opt="-gray"
-	fi
-	curImgPixmap="$TMP_FLD/$page.$ext"
-	curImgPixmapDeskewed="$TMP_FLD/$page.deskewed.$ext"
-	curImgPixmapClean="$TMP_FLD/$page.cleaned.$ext"
-	
-	# extract current page as image with right orientation and resoltution
-	[ $VERBOSITY -ge $LOG_DEBUG ] && echo "Page $page: Extracting image as $ext file (${dpi} dpi)"
-	! pdftoppm -f $page -l $page -r $dpi $opt "$FILE_INPUT_PDF" > "$curImgPixmap" \
-		&& echo "Could not extract page $page as $ext from $FILE_INPUT_PDF. Exiting..." >&2 && exit $EXIT_OTHER_ERROR
-
-	# if requested deskew image (without changing its size in pixel)
-	if [ "$PREPROCESS_DESKEW" -eq "1" ]; then
-		[ $VERBOSITY -ge $LOG_DEBUG ] && echo "Page $page: Deskewing image"
-		! convert "$curImgPixmap" -deskew 40% -gravity center -extent ${heightCurImg}x${widthCurImg} "$curImgPixmapDeskewed" \
-			&& echo "Could not deskew \"$curImgPixmap\". Exiting..." >&2 && exit $EXIT_OTHER_ERROR
-	else
-		cp "$curImgPixmap" "$curImgPixmapDeskewed"
-	fi
-
-	# if requested clean image with unpaper to get better OCR results
-	if [ "$PREPROCESS_CLEAN" -eq "1" ]; then
-		[ $VERBOSITY -ge $LOG_DEBUG ] && echo "Page $page: Cleaning image with unpaper"
-		! unpaper --dpi $dpi --mask-scan-size 100 \
-			--no-deskew --no-grayfilter --no-blackfilter --no-mask-center --no-border-align \
-			"$curImgPixmapDeskewed" "$curImgPixmapClean" 1> /dev/null \
-			&& echo "Could not clean \"$curImgPixmapDeskewed\". Exiting..." >&2 && exit $EXIT_OTHER_ERROR
-	else
-		cp "$curImgPixmapDeskewed" "$curImgPixmapClean"
-	fi
-
-	# perform OCR
-	[ $VERBOSITY -ge $LOG_DEBUG ] && echo "Page $page: Performing OCR"
-	! tesseract -l "$LAN" "$curImgPixmapClean" "$curHocr" hocr $TESS_CFG_FILES 1> /dev/null 2> /dev/null \
-		&& echo "Could not OCR file \"$curImgPixmapClean\". Exiting..." >&2 && exit $EXIT_OTHER_ERROR
-	mv "$curHocr.html" "$curHocr"
-
-	# embed text and image to new pdf file
-	if [ "$PREPROCESS_CLEANTOPDF" -eq "1" ]; then
-		image4finalPDF="$curImgPixmapClean"
-	else
-		image4finalPDF="$curImgPixmapDeskewed"	
-	fi
-	[ $VERBOSITY -ge $LOG_DEBUG ] && echo "Page $page: Embedding text in PDF"
-	! python $SRC/hocrTransform.py -r $dpi -i "$image4finalPDF" "$curHocr" "$curOCRedPDF" \
-		&& echo "Could not create PDF file from \"$curHocr\". Exiting..." >&2 && exit $EXIT_OTHER_ERROR
-	
-	# if requested generate special debug PDF page with visible OCR text
-	if [ $DEBUG_MODE -eq "1" ] ; then
-		[ $VERBOSITY -ge $LOG_DEBUG ] && echo "Page $page: Embedding text in PDF (debug page)"
-		! python $SRC/hocrTransform.py -b -r $dpi "$curHocr" "$curOCRedPDFDebug" \
-			&& echo "Could not create PDF file from \"$curHocr\". Exiting..." >&2 && exit $EXIT_OTHER_ERROR	
-	fi
-	
-	# delete temporary files created for the current page
-	# to avoid using to much disk space in case of PDF files having many pages
-	if [ $KEEP_TMP -eq 0 ]; then
-		rm "$curOrigImg"*.*
-		rm "$curHocr"
-		rm "$curImgPixmap"
-		rm "$curImgPixmapDeskewed"
-		rm "$curImgPixmapClean"
-	fi
-
-	# go to next page of the pdf
-	cpt=$(($cpt+1))
-	
-done < "$FILE_SIZE_PAGES"
-
-
-
-
-# concatenate all pages
-[ $VERBOSITY -ge $LOG_DEBUG ] && echo "Output file: Concatenating all pages"
-! pdftk $FILES_OCRed_PDFS cat output "$FILE_OUTPUT_PDF" \
-	&& echo "Could not concatenate individual PDF pages (\"$FILES_OCRed_PDFS\") to one file. Exiting..." >&2 && exit $EXIT_OTHER_ERROR
-
-# insert metadata (copy metadata from input file)
-#echo "Output file: Inserting metadata"
-# TODO (may work with pdftk update_info)
-# the name of the file may be used as title
-
-# convert the pdf file to match PDF/A format
-[ $VERBOSITY -ge $LOG_DEBUG ] && echo "Output file: Converting to PDF/A" 
-! gs -dQUIET -dPDFA -dBATCH -dNOPAUSE -dUseCIEColor \
-	-sProcessColorModel=DeviceCMYK -sDEVICE=pdfwrite -sPDFACompatibilityPolicy=2 \
-	-sOutputFile=$FILE_OUTPUT_PDFA "$FILE_OUTPUT_PDF" 1> /dev/null 2> /dev/null \
-	&& echo "Could not convert PDF file \"$FILE_OUTPUT_PDF\" to PDF/A. Exiting..." >&2 && exit $EXIT_OTHER_ERROR
-
-# validate generated pdf file (compliance to PDF/A)
-[ $VERBOSITY -ge $LOG_DEBUG ] && echo "Output file: Checking compliance to PDF/A standard" 
-java -jar "$JHOVE" -c "$JHOVE_CFG" -m PDF-hul "$FILE_OUTPUT_PDFA" > "$FILE_VALIDATION_LOG"
-grep -i "Status|Message" "$FILE_VALIDATION_LOG" # summary of the validation
-[ $VERBOSITY -ge $LOG_DEBUG ] && cat "$FILE_VALIDATION_LOG"
-# check the validation results
-pdf_valid=1
-grep -i 'ErrorMessage' "$FILE_VALIDATION_LOG" && pdf_valid=0
-grep -i 'Status.*not valid' "$FILE_VALIDATION_LOG" && pdf_valid=0
-grep -i 'Status.*Not well-formed' "$FILE_VALIDATION_LOG" && pdf_valid=0
-! grep -i 'Profile:.*PDF/A-1' "$FILE_VALIDATION_LOG" && pdf_valid=0
-
-
-
-# delete temporary files
-if [ $KEEP_TMP -eq 0 ]; then
-	rm -r -f "${TMP_FLD}"
-fi
-
-
-
-[ $pdf_valid -ne 1 ] && echo "Output file: The generated PDF/A file is INVALID" >&2 && exit $EXIT_INVALID_OUPUT_PDFA
-
-[ $VERBOSITY -ge $LOG_INFO ] && echo "Output file: The generated PDF/A file is VALID"
-exit 0

README.md

@@ -1,40 +0,0 @@
-OCRmyPDF
-========
-
-OCRmyPDF adds an OCR text layer to scanned PDF files, allowing them to be searched
-
-To get the script usage, call: ./OCmyPDF.sh -h
-
-Features
---------
-
-- Generate a searchable PDF/A file from a PDF file containing only images
-- Keep the exact resolution of the original embedded images
-- If requested deskew and / or clean the image before performing OCR
-- Validate the generated file against the PDF/A specification using jhove
-- Provides debug mode to enable easy verification of the OCR results
-
-Motivation
-----------
-
-I searched the web for a free command line tool to OCR PDF files on linux/unix:
-I found many, but none of them were really satisfying.
-- Either they produced PDF files with misplaced text under the image (making copy/paste impossible)
-- Or they changed the resolution of the embedded images
-- Or they generated PDF file having a ridiculous big size
-- Or they crashed when trying to OCR some of my PDF files
-- Or they did not produce valid PDF files (even though they were readable with my current PDF reader) 
-- On top of that none of them produced PDF/A files (format dedicated for long time storage / archiving)
-
-... so I decided to develop my own tool (using various existing scripts as an inspiration)
-
-Install
---------
-
-Download OCRmyPDF here: https://github.com/fritz-hh/OCRmyPDF/tags
-
-Copy the file in onto your linux/unix machine and extract it.
-
-Run: "sh ./OCRmyPDF.sh" to get the script usage
-
-If not yet installed, the script will notify you about dependencies that need to be installed

README.rst

@@ -0,0 +1,154 @@
+OCRmyPDF
+========
+
+.. image:: https://travis-ci.org/jbarlow83/OCRmyPDF.svg?branch=master
+    :target: https://travis-ci.org/jbarlow83/OCRmyPDF
+
+.. image:: https://img.shields.io/pypi/v/ocrmypdf.svg   
+    :target: https://pypi.org/project/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.
+
+.. code-block:: bash
+
+   ocrmypdf                      # it's a scriptable command line program
+      -l eng+fra                 # it supports multiple languages
+      --rotate-pages             # it can fix pages that are misrotated
+      --deskew                   # it can deskew crooked PDFs!
+      --title "My PDF"           # it can change output metadata
+      --jobs 4                   # it uses multiple cores by default
+      --output-type pdfa         # it produces PDF/A by default
+      input_scanned.pdf          # takes PDF input (or images)
+      output_searchable.pdf      # produces validated PDF output
+
+
+Main features
+-------------
+
+-  Generates a searchable
+   `PDF/A <https://en.wikipedia.org/?title=PDF/A>`_ file from a regular PDF
+-  Places OCR text accurately below the image to ease copy / paste
+-  Keeps the exact resolution of the original embedded images
+-  When possible, inserts OCR information as a "lossless" operation without rendering vector information
+-  Keeps file size about the same
+-  If requested deskews and/or cleans the image before performing OCR
+-  Validates input and output files
+-  Processes pages in parallel when more than one CPU core is
+   available
+-  Uses `Tesseract OCR <https://github.com/tesseract-ocr/tesseract>`_ engine
+-  Supports more than `100 languages <https://github.com/tesseract-ocr/tessdata>`_ recognized by Tesseract
+-  Battle-tested on thousands of PDFs, a test suite and continuous integration
+
+For details: please consult the `documentation <https://ocrmypdf.readthedocs.io/en/latest/>`_.
+
+Motivation
+----------
+
+I searched the web for a free command line tool to OCR PDF files on
+Linux/UNIX: I found many, but none of them were really satisfying.
+
+-  Either they produced PDF files with misplaced text under the image (making copy/paste impossible) 
+-  Or they did not handle accents and multilingual characters
+-  Or they changed the resolution of the embedded images
+-  Or they generated ridiculously large PDF files
+-  Or they crashed when trying to OCR some of my PDF files
+-  Or they did not produce valid PDF files (even though they were readable with my current PDF reader)
+-  On top of that none of them produced PDF/A files (format dedicated for long time storage)
+
+...so I decided to develop my own tool (using various existing scripts
+as an inspiration). 
+
+Installation
+------------
+
+Linux, UNIX, and macOS are supported. Windows is not directly supported but there is a Docker image available that runs on Windows.
+
+Users of Debian 9 or later or Ubuntu 16.10 or later may simply
+
+.. code-block:: bash
+
+   apt-get install ocrmypdf
+
+and macOS users with Homebrew may simply
+
+.. code-block:: bash
+
+   brew install ocrmypdf
+
+For everyone else, `see our documentation <https://ocrmypdf.readthedocs.io/en/latest/installation.html>`_ for installation steps.
+
+Languages
+---------
+
+OCRmyPDF uses Tesseract for OCR, and relies on its language packs. For Linux users,
+you can often find packages that provide language packs:
+
+.. code-block:: bash
+
+   # Display a list of all Tesseract language packs
+   apt-cache search tesseract-ocr
+
+   # Debian/Ubuntu users
+   apt-get install tesseract-ocr-chi-sim  # Example: Install Chinese Simplified language back
+   
+You can then pass the ``-l LANG`` argument to OCRmyPDF to give a hint as to what languages it should search for. Multiple
+languages can be requested.
+
+Documentation and support
+-------------------------
+
+Once ocrmypdf is installed, the built-in help which explains the command syntax and options can be accessed via:
+
+.. code-block:: bash
+
+   ocrmypdf --help
+
+Our `documentation is served on Read the Docs <https://ocrmypdf.readthedocs.io/en/latest/index.html>`_.
+
+If you detect an issue, please:
+
+-  Check whether your issue is already known
+-  If no problem report exists on github, please create one here:
+   https://github.com/jbarlow83/OCRmyPDF/issues
+-  Describe your problem thoroughly
+-  Append the console output of the script when running the debug mode
+   (``-v 1`` option)
+-  If possible provide your input PDF file as well as the content of the
+   temporary folder (using a file sharing service like Dropbox)
+
+Requirements
+------------
+
+Runs on CPython 3.6, and requires external program installations of Ghostscript, Tesseract OCR, QPDF, and Leptonica. ocrmypdf is pure Python, but uses CFFI to portably generate library bindings.
+
+Python 3.5 is also supported.
+
+Press & Media
+-------------
+
+-  `c't 1-2014, page 59 <http://heise.de/-2279695>`_:
+   Detailed presentation of OCRmyPDF v1.0 in the leading German IT
+   magazine c't
+-  `heise Open Source, 09/2014: Texterkennung mit
+   OCRmyPDF <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
+----------
+
+The software is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR
+CONDITIONS OF ANY KIND, either express or implied.

RELEASE_NOTES.md

@@ -1,37 +0,0 @@
-RELEASE NOTES
-=============
-
-Please always read this file before installing the package
-
-Download software here: https://github.com/fritz-hh/OCRmyPDF/tags
-
-v1.0-rc1 (2013-04-26):
-====
-
-New features
-------------
-
-- First release candidate
-
-Changes
--------
-
-- N/A
-
-Fixes
------
-
-- N/A
-
-Tested with
------------
-
-- Operating system: FreeBSD 9.1
-- Dependencies:
-   - poppler-utils 0.22.2
-   - ImageMagick 6.8.0-7 2013-03-30
-   - tesseract 3.02.02
-   - Python 2.7.3
-   - pdftk 1.45
-   - ghoscript (gs): 9.06
-   - java: openjdk version "1.7.0_17"

dev_requirements.txt

@@ -0,0 +1,4 @@
+check-manifest >= 0.35
+twine >= 1.8.1
+coverage >= 4.4
+GitPython == 2.1.3

docs/advanced.rst

@@ -0,0 +1,189 @@
+Advanced features
+=================
+
+Control of OCR options
+----------------------
+
+OCRmyPDF provides many features to control the behavior of the OCR engine, Tesseract.
+
+When OCR is skipped
+"""""""""""""""""""
+
+If a page in a PDF seems to have text, by default OCRmyPDF will exit without modifying the PDF. This is to ensure that PDFs that were previously OCRed or were "born digital" rather than scanned are not processed. 
+
+If ``--skip-text`` is issued, then no OCR will be performed on pages that already have text. The page will be copied to the output. This may be useful for documents that contain both "born digital" and scanned content, or to use OCRmyPDF to normalize and convert to PDF/A regardless of their contents.
+
+If ``--force-ocr`` is issued, then all pages will be rasterized to images, discarding any hidden OCR text, and rasterizing any printable text. This is useful for redoing OCR, for fixing OCR text with a damaged character map (text is selectable but not searchable), and destroying redacted information.
+
+
+Time and image size limits
+""""""""""""""""""""""""""
+
+By default, OCRmyPDF permits tesseract to run for three minutes (180 seconds) per page. This is usually more than enough time to find all text on a reasonably sized page with modern hardware. 
+
+If a page is skipped, it will be inserted without OCR. If preprocessing was requested, the preprocessed image layer will be inserted.
+
+If you want to adjust the amount of time spent on OCR, change ``--tesseract-timeout``.  You can also automatically skip images that exceed a certain number of megapixels with ``--skip-big``. (A 300 DPI, 8.5×11" page is 8.4 megapixels.)
+
+.. code-block:: bash
+
+    # Allow 300 seconds for OCR; skip any page larger than 50 megapixels
+    ocrmypdf --tesseract-timeout 300 --skip-big 50 bigfile.pdf output.pdf
+
+Overriding default tesseract
+""""""""""""""""""""""""""""
+
+OCRmyPDF checks the system ``PATH`` for the ``tesseract`` binary.  
+
+Some relevant environment variables that influence Tesseract's behavior include:
+
+.. envvar:: TESSDATA_PREFIX
+
+    Overrides the path to Tesseract's data files. This can allow simultaneous installation of the "best" and "fast" training data sets. OCRmyPDF does not manage this environment variable.
+
+.. envvar:: OMP_THREAD_LIMIT
+
+    Controls the number of threads Tesseract will use. OCRmyPDF will manage this environment if it is not already set. (Currently, it will set it to 1 because this gives the best results in testing.)
+
+For example, if you are testing tesseract 4.00 and don't wish to use an existing tesseract 3.04 installation, you can launch OCRmyPDF as follows:
+
+.. code-block:: bash
+
+    env \
+        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.)
+
+
+Overriding other support programs
+"""""""""""""""""""""""""""""""""
+
+In addition to tesseract, OCRmyPDF uses the following external binaries:
+
+* ``gs`` (Ghostscript)
+* ``unpaper``
+* ``qpdf``
+
+In each case OCRmyPDF will search the ``PATH`` environment variable to locate the binaries.
+
+
+Changing tesseract configuration variables
+""""""""""""""""""""""""""""""""""""""""""
+
+You can override tesseract's default `control parameters <https://github.com/tesseract-ocr/tesseract/wiki/ControlParams>`_ with a configuration file.
+
+As an example, this configuration will disable Tesseract's dictionary for current language. Normally the dictionary is helpful for interpolating words that are unclear, but it may interfere with OCR if the document does not contain many words (for example, a list of part numbers).
+
+Create a file named "no-dict.cfg" with these contents:
+
+::
+
+    load_system_dawg 0
+    language_model_penalty_non_dict_word 0
+    language_model_penalty_non_freq_dict_word 0
+
+then run ocrmypdf as follows (along with any other desired arguments):
+
+.. code-block:: bash
+
+    ocrmypdf --tesseract-config no-dict.cfg input.pdf output.pdf
+
+.. warning::
+
+    Some combinations of control parameters will break Tesseract or break assumptions that OCRmyPDF makes about Tesseract's output.
+
+
+Changing the PDF renderer
+-------------------------
+
+rasterizing
+  Converting a PDF to an image for display.
+
+rendering
+  Creating a new PDF from other data (such as an existing PDF).
+
+
+OCRmyPDF has these PDF renderers: ``sandwich`` and ``hocr``. The renderer may be selected using ``--pdf-renderer``. The default is ``auto`` which lets OCRmyPDF select the renderer to use. Currently, ``auto`` selects ``sandwich`` for Tesseract 3.05.01 or newer, or ``hocr`` for older versions of Tesseract.
+
+The ``sandwich`` renderer
+"""""""""""""""""""""""""
+
+The ``sandwich`` renderer uses Tesseract's new text-only PDF feature, which produces a PDF page that lays out the OCR in invisible text. This page is then "sandwiched" onto the original PDF page, allowing lossless application of OCR even to PDF pages that contain other vector objects.
+
+Currently this is the best renderer for most uses, however it is implemented in Tesseract so OCRmyPDF cannot influence it. Currently some problematic PDF viewers like Mozilla PDF.js and macOS Preview have problems with segmenting its text output, and mightrunseveralwordstogether.
+
+When image preprocessing features like ``--deskew`` are used, the original PDF will be rendered as a full page and the OCR layer will be placed on top.
+
+If a PDF created with this renderer using Tesseract versions older than 3.05.00 is then passed through Ghostscript's pdfwrite feature, the OCR text *may* be corrupted. The ``--output-type=pdfa`` argument will produce a warning in this situation.  For this reason, OCRmyPDF automatically selects the ``hocr`` for older Tesseract versions.
+
+The ``hocr`` renderer
+"""""""""""""""""""""
+
+The ``hocr`` renderer works with older versions of Tesseract. The image layer is copied from the original PDF page if possible, avoiding potentially lossy transcoding or loss of other PDF information. If preprocessing is specified, then the image layer is a new PDF.
+
+Unlike ``sandwich`` this renderer is implemented within OCRmyPDF; anyone looking to customize how OCR is presented should look here. A major disadvantage of this renderer is it not capable of correctly handling text outside the Latin alphabet. Pull requests to improve the situation are welcome.
+
+Currently, this renderer has the best compatibility with Mozilla's PDF.js viewer.
+
+This works in all versions of Tesseract.
+
+The ``tesseract`` renderer
+""""""""""""""""""""""""""
+
+The ``tesseract`` renderer was removed. OCRmyPDF's new approach to text layer grafting makes it functionally equivalent to ``sandwich``.
+
+Return code policy
+------------------
+
+OCRmyPDF writes all messages to ``stderr``.  ``stdout`` is reserved for piping
+output files.  ``stdin`` is reserved for piping input files.
+
+The return codes generated by the OCRmyPDF are considered part of the stable 
+user interface.
+
+.. list-table:: Return codes
+    :widths: 5 35 60
+    :header-rows: 1
+
+    *	- Code
+        - Name
+        - Interpretation
+    *	- 0
+        - ``ocrmypdf.exceptions.ExitCode.ok``
+        - Everything worked as expected.
+    *	- 1
+        - ``ocrmypdf.exceptions.ExitCode.bad_args``
+        - Invalid arguments, exited with an error.
+    *	- 2
+        - ``ocrmypdf.exceptions.ExitCode.input_file``
+        - The input file does not seem to be a valid PDF.
+    *	- 3
+        - ``ocrmypdf.exceptions.missing_dependency``
+        - An external program required by OCRmyPDF is missing.
+    *	- 4
+        - ``ocrmypdf.exceptions.invalid_output_pdf``
+        - An output file was created, but it does not seem to be a valid PDF or
+          PDF/A. The file will be available.
+    *	- 5
+        - ``ocrmypdf.exceptions.file_access_error``
+        - The user running OCRmyPDF does not have sufficient permissions to read the input file and write the output file.
+    *	- 6
+        - ``ocrmypdf.exceptions.already_done_ocr``
+        - The file already appears to contain text so it may not need OCR. See output message.
+    *	- 7
+        - ``ocrmypdf.exceptions.child_process_error``
+        - An error occurred in an external program (child process) and OCRmyPDF cannot continue.
+    *	- 8
+        - ``ocrmypdf.exceptions.encrypted_pdf``
+        - The input PDF is encrypted. OCRmyPDF does not read encrypted PDFs. Use another program such as ``qpdf`` to remove encryption.
+    *	- 9
+        - ``ocrmypdf.exceptions.invalid_config``
+        - A custom configuration file was forwarded to Tesseract using ``--tesseract-config``, and Tesseract rejected this file.
+    *	- 15
+        - ``ocrmypdf.exceptions.other_error``
+        - Some other error occurred.
+    *	- 130
+        - ``ocrmypdf.exceptions.ctrl_c``
+        - The program was interrupted by pressing Ctrl+C.

docs/batch.rst

@@ -0,0 +1,214 @@
+Batch processing
+================
+
+This article provides information about running OCRmyPDF on multiple files or configuring it as a service triggered by file system events.
+
+Batch jobs
+----------
+
+Consider using the excellent `GNU Parallel <https://www.gnu.org/software/parallel/>`_ to apply OCRmyPDF to multiple files at once.
+
+Both ``parallel`` and ``ocrmypdf`` will try to use all available processors. To maximize parallelism without overloading your system with processes, consider using ``parallel -j 2`` to limit parallel to running two jobs at once.
+
+This command will run all ocrmypdf all files named ``*.pdf`` in the current directory and write them to the previous created ``output/`` folder. It will not search subdirectories.
+
+The ``--tag`` argument tells parallel to print the filename as a prefix whenever a message is printed, so that one can trace any errors to the file that produced them.
+
+.. code-block:: bash
+
+	parallel --tag -j 2 ocrmypdf '{}' 'output/{}' ::: *.pdf
+
+OCRmyPDF automatically 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
+---------------
+
+This will walk through a directory tree and run OCR on all files in place, printing the output in a way that makes 
+
+.. code-block:: bash
+
+	find . --printf '%p' -name '*.pdf' -exec ocrmypdf '{}' '{}' \;
+
+This only runs one ``ocrmypdf`` process at a time. This variation uses ``find`` to create a directory list and ``parallel`` to parallelize runs of ``ocrmypdf``, again updating files in place.
+
+.. code-block:: bash
+
+	find . -name '*.pdf' | parallel --tag -j 2 ocrmypdf '{}' '{}'
+
+
+Sample script
+"""""""""""""
+
+This user contributed script also provides an example of batch processing.
+
+.. code-block:: python
+
+	#!/usr/bin/env python3
+	# Walk through directory tree, replacing all files with OCR'd version
+	# Contributed by DeliciousPickle@github
+
+	import logging
+	import os
+	import subprocess
+	import sys
+
+	script_dir = os.path.dirname(os.path.realpath(__file__))
+	print(script_dir + '/ocr-tree.py: Start')
+
+	if len(sys.argv) > 1:
+	    start_dir = sys.argv[1]
+	else:
+	    start_dir = '.'
+
+	if len(sys.argv) > 2:
+	    log_file = sys.argv[2]
+	else:
+	    log_file = script_dir + '/ocr-tree.log'
+
+	logging.basicConfig(
+			level=logging.INFO, format='%(asctime)s %(message)s', 
+			filename=log_file, filemode='w')
+
+	for dir_name, subdirs, file_list in os.walk(start_dir):
+	    logging.info('\n')
+	    logging.info(dir_name + '\n')
+	    os.chdir(dir_name)
+	    for filename in file_list:
+	        file_ext = os.path.splitext(filename)[1]
+	        if file_ext == '.pdf':
+	            full_path = dir_name + '/' + filename
+	            print(full_path)
+	            cmd = ["ocrmypdf",  "--deskew", filename, filename]
+	            logging.info(cmd)
+	            proc = subprocess.Popen(
+	            	cmd, stdout=subprocess.PIPE, stderr=subprocess.STDOUT)
+	            result = proc.stdout.read()
+	            if proc.returncode == 6:
+	                print("Skipped document because it already contained text")
+	            elif proc.returncode == 0:
+	                print("OCR complete")
+	            logging.info(result)
+
+API
+"""
+
+OCRmyPDF is currently supported as a command line interface. This means that even if you are using OCRmyPDF in a Python script, you should run it in a subprocess rather importing the ocrmypdf package.
+
+The reason for this limitation is that the `ruffus <https://github.com/bunbun/ruffus/>`_ library that OCRmyPDF depends on is unfortunately not reentrant. OCRmyPDF works by defining each operation it does as a ruffus task that takes one or more files as input and generates one or more files as output. As such ruffus is fairly fundamental.
+
+(If you find individual functions implemented in OCRmyPDF useful (such as ``ocrmypdf.pdfinfo``), you can use these if you wish to.)
+
+
+Synology DiskStations
+"""""""""""""""""""""
+
+Synology DiskStations (Network Attached Storage devices) can run the Docker image of OCRmyPDF if the Synology `Docker package <https://www.synology.com/en-global/dsm/packages/Docker>`_ is installed. Attached is a script to address particular quirks of using OCRmyPDF on one of these devices.
+
+This is only possible for x86-based Synology products. Some Synology products use ARM or Power processors and do not support Docker. Further adjustments might be needed to deal with the Synology's relatively limited CPU and RAM.
+
+.. code-block:: python
+
+	#!/bin/env python3
+	# Contributed by github.com/Enantiomerie
+
+	# script needs 2 arguments
+	# 1. source dir with *.pdf - default is location of script
+	# 2. move dir where *.pdf and *_OCR.pdf are moved to
+
+	import logging
+	import os
+	import subprocess
+	import sys
+	import time
+	import shutil
+
+	script_dir = os.path.dirname(os.path.realpath(__file__))
+	timestamp = time.strftime("%Y-%m-%d-%H%M_")
+	log_file = script_dir + '/' + timestamp + 'ocrmypdf.log'
+	logging.basicConfig(level=logging.INFO, format='%(asctime)s %(message)s', filename=log_file, filemode='w')
+
+	if len(sys.argv) > 1:
+	    start_dir = sys.argv[1]
+	else:
+	    start_dir = '.'
+
+	for dir_name, subdirs, file_list in os.walk(start_dir):
+	    logging.info('\n')
+	    logging.info(dir_name + '\n')
+	    os.chdir(dir_name)
+	    for filename in file_list:
+	        file_ext = os.path.splitext(filename)[1]
+	        if file_ext == '.pdf':
+	            full_path = dir_name + '/' + filename
+	            file_noext = os.path.splitext(filename)[0]
+	            timestamp_OCR = time.strftime("%Y-%m-%d-%H%M_OCR_")
+	            filename_OCR = timestamp_OCR + file_noext + '.pdf'
+	            docker_mount = dir_name + ':/home/docker'
+	# create string for pdf processing 
+	# diskstation needs a user:group docker:docker. find uid:gid of your diskstation docker:docker with id docker.
+	# use this uid:gid in -u flag
+	# rw rights for docker:docker at source dir are also necessary
+	# the script is processed as root user via chron 
+	            cmd = ['docker', 'run', '--rm', '-v', docker_mount, '-u=1030:65538', 'jbarlow83/ocrmypdf', , '--deskew' , filename, filename_OCR]
+	            logging.info(cmd)
+	            proc = subprocess.Popen(cmd, stdout=subprocess.PIPE, stderr=subprocess.STDOUT)
+	            result = proc.stdout.read()
+	            logging.info(result)
+	            full_path_OCR = dir_name + '/' + filename_OCR
+	            os.chmod(full_path_OCR, 0o666)
+	            os.chmod(full_path, 0o666)
+	            full_path_OCR_archive = sys.argv[2]
+	            full_path_archive = sys.argv[2] + '/no_ocr'
+	            shutil.move(full_path_OCR,full_path_OCR_archive)
+	            shutil.move(full_path, full_path_archive)
+	logging.info('Finished.\n')
+
+
+
+Huge batch jobs
+"""""""""""""""
+
+If you have thousands of files to work with, contact the author. Consulting work related to OCRmyPDF helps fund this open source project and all inquiries are appreciated.
+
+
+Hot (watched) folders
+---------------------
+
+To set up a "hot folder" that will trigger OCR for every file inserted, use a program like Python `watchdog <https://pypi.python.org/pypi/watchdog>`_ (supports all major OS).
+
+One could then configure a scanner to automatically place scanned files in a hot folder, so that they will be queued for OCR and copied to the destination.
+
+.. code-block:: bash
+
+	pip install watchdog
+
+watchdog installs the command line program ``watchmedo``, which can be told to run ``ocrmypdf`` on any .pdf added to the current directory (``.``) and place the result in the previously created ``out/`` folder.
+
+.. code-block:: bash
+
+	cd hot-folder
+	mkdir out
+	watchmedo shell-command \
+		--patterns="*.pdf" \
+		--ignore-directories \
+		--command='ocrmypdf "${watch_src_path}" "out/${watch_src_path}" ' \
+		.  # don't forget the final dot
+
+For more complex behavior you can write a Python script around to use the watchdog API.
+
+On file servers, you could configure watchmedo as a system service so it will run all the time.
+
+Caveats
+"""""""
+
+* ``watchmedo`` may not work properly on a networked file system, depending on the capabilities of the file system client and server.
+* This simple recipe does not filter for the type of file system event, so file copies, deletes and moves, and directory operations, will all be sent to ocrmypdf, producing errors in several cases. Disable your watched folder if you are doing anything other than copying files to it.
+* If the source and destination directory are the same, watchmedo may create an infinite loop.
+* On BSD, FreeBSD and older versions of macOS, you may need to increase the number of file descriptors to monitor more files, using ``ulimit -n 1024`` to watch a folder of up to 1024 files.
+
+Alternatives
+""""""""""""
+
+* `Watchman <https://facebook.github.io/watchman/>`_ is a more powerful alternative to ``watchmedo``.
+
+

docs/bitmap_vs_svg.svg

@@ -0,0 +1,35 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<svg xmlns="http://www.w3.org/2000/svg" width="100%" height="100%" viewBox="0 0 915 585" xmlns:xlink="http://www.w3.org/1999/xlink">
+<defs>
+<linearGradient id="b" y2="445" gradientUnits="userSpaceOnUse" y1="179" gradientTransform="translate(0 -2.06)" x2="-29.7" x1="322">
+<stop stop-color="#333" offset="0"/>
+<stop stop-color="#fff" stop-opacity="0" offset="1"/>
+</linearGradient>
+<linearGradient id="a" y2="414" gradientUnits="userSpaceOnUse" y1="159" x2="490" x1="815">
+<stop stop-color="#33f" offset="0"/>
+<stop stop-color="#3f3fff" stop-opacity="0" offset="1"/>
+</linearGradient>
+</defs>
+<path fill="url(#b)" d="m403 247c-12 115-135 122-368 123-4.3-1.07-7.32-7.33-6-41 76-37 151-124 167-236 93 123 201 40.9 207 154z"/>
+<g stroke-width="3.45" fill="none">
+<path stroke="#000" d="m11.8 11.8h411v411l-411 0.01v-411z"/>
+<path stroke="#448" d="m489 11.7h415v411h-415v-411z"/>
+</g>
+<path d="m876 244c-12 115-133 120-366 121-6-14-10-40-3-43 76-37.3 136-106 152-218 38 48 209 101 217 140z" fill="url(#a)"/>
+<g id="RasterLarge" transform="matrix(1.36 0 0 1.28 -161 -636)">
+<path fill="#999" d="m287 730h-30v-60h20v20h10v10h10v10h20v10h40v-10h20v-20h10v-20h-10v-10h-10v-10h-40v-10h-30v-10h-20v-10h-10v-10h-10v-60h10v-10h10v-10h10v-10h90v10h30v60h-20v-10h-10v-20h-10v-10h-20v-10h-30v10h-20v10h-10v20h10v20h30v10h30v10h30v10h10v10h10v10h10v60h-10v10h-10v10h-10v10h-100v-10z"/>
+<path fill="#555" d="m297 730h-30v-10h-10v-50h20v20h10v20h10 10v10h60v-10h10v-10h10v-40h-20v-10h-20v-10h-40v-10h-20v-10h-20v-20h-10v-50h10v-10h10v-10h20v-10h70v10h30v10h10v50h-20v-20h-10v-20h-20v-10h-50v10h-10v10h-10v30h10v10h20v10h30v10h30v10h20v10h10v10h10v50h-10v20h-10v10h-20v10h-80z"/>
+<path d="m307 730h-30v-10h-20v-50h20v30h10v10h10v10h70v-10h20v-50h-10v-10h-20v-10h-40v-10h-30v-10h-10v-10h-10v-20h-10v-30h10v-20h20v-10h20v-10h50v10h30v10h20v50h-20v-30h-10v-10h-10v-10h-70v10h-10v40h10v10h10v10h30v10h40v10h20v10h10v20h10v40h-10v20h-20v10h-30v10h-50v-10z"/>
+</g>
+<g font-size="40" font-family="sans-serif" text-anchor="middle">
+<g font-size="100">
+<text y="518" x="210">Raster</text>
+<text y="518" x="695" fill="#338">Vector</text>
+</g>
+<text y="563" x="210">.jpeg  .gif  .png</text>
+<text y="563" x="696" fill="#338">.svg</text>
+</g>
+<path id="VectorLarge" fill="#005" d="m661 294v-62.5l23.4 0.184c0.678 20.8 7.32 36.3 19.9 46.4 12.7 9.93 32.1 14.9 57.9 14.9 24.1 0 42.5-4.29 55.1-12.9 12.7-8.71 19.1-21.3 19.1-37.9 0-13.2-3.86-23.4-11.6-30.5-7.59-7.11-23.7-14-48.4-20.8l-40.1-10.9c-29-7.97-49.5-17.9-61.4-29.8-11.8-11.9-17.7-28.2-17.7-48.9 0-23.3 9.15-41.4 27.4-54.3 18.3-12.9 44-19.3 77.1-19.3 14.1 0 29.6 1.41 46.4 4.23 16.8 2.7 34.7 6.68 53.7 12v58.5h-23c-2.3-19.4-9.49-33.4-21.6-41.9-11.9-8.71-30.2-13.1-54.7-13.1-21.4 0-37.7 3.99-49 12-11.1 7.85-16.7 19.3-16.7 34.4 0 13.1 4.2 23.4 12.6 30.9 8.4 7.48 26.2 14.9 53.5 22.3l37.6 10.1c27.5 7.48 47.1 17 58.8 28.7 11.8 11.5 17.7 27 17.7 46.5 0 26.6-9.42 46.7-28.3 60.2s-46.9 20.2-84.2 20.2c-16.7 0-33.7-1.53-51-4.6-18-3-35-7-53-13z"/>
+<use xlink:href="#VectorLarge" transform="matrix(.17 0 0 .17 392 313)"/>
+<use xlink:href="#RasterLarge" transform="matrix(.173 0 0 .173 -8.25 314)" height="100%" width="100%" y="0" x="0"/>
+</svg>

docs/conf.py

@@ -0,0 +1,350 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+#
+# ocrmypdf documentation build configuration file, created by
+# sphinx-quickstart on Sun Sep  4 14:29:43 2016.
+#
+# This file is execfile()d with the current directory set to its
+# containing dir.
+#
+# Note that not all possible configuration values are present in this
+# autogenerated file.
+#
+# All configuration values have a default; values that are commented out
+# serve to show the default.
+
+# If extensions (or modules to document with autodoc) are in another directory,
+# add these directories to sys.path here. If the directory is relative to the
+# documentation root, use os.path.abspath to make it absolute, like shown here.
+#
+# import os
+# import sys
+# sys.path.insert(0, os.path.abspath('.'))
+
+# -- General configuration ------------------------------------------------
+
+# If your documentation needs a minimal Sphinx version, state it here.
+#
+# needs_sphinx = '1.0'
+
+# Add any Sphinx extension module names here, as strings. They can be
+# extensions coming with Sphinx (named 'sphinx.ext.*') or your custom
+# ones.
+extensions = [
+    # 'sphinx.ext.mathjax',
+]
+
+# Add any paths that contain templates here, relative to this directory.
+templates_path = ['_templates']
+
+# The suffix(es) of source filenames.
+# You can specify multiple suffix as a list of string:
+#
+# source_suffix = ['.rst', '.md']
+source_suffix = '.rst'
+
+# The encoding of source files.
+#
+# source_encoding = 'utf-8-sig'
+
+# The master toctree document.
+master_doc = 'index'
+
+# General information about the project.
+project = 'ocrmypdf'
+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
+# |version| and |release|, also used in various other places throughout the
+# built documents.
+#
+# The short X.Y version.
+from ocrmypdf import __version__ as OCRMYPDF_VERSION
+
+_version_parts = OCRMYPDF_VERSION.split('.')
+
+version = '.'.join(_version_parts[0:2])
+# The full version, including alpha/beta/rc tags.
+release = OCRMYPDF_VERSION
+
+# The language for content autogenerated by Sphinx. Refer to documentation
+# for a list of supported languages.
+#
+# This is also used if you do content translation via gettext catalogs.
+# Usually you set "language" from the command line for these cases.
+language = None
+
+# There are two options for replacing |today|: either, you set today to some
+# non-false value, then it is used:
+#
+# today = ''
+#
+# Else, today_fmt is used as the format for a strftime call.
+#
+today_fmt = '%Y-%m-%d'
+
+# List of patterns, relative to source directory, that match files and
+# directories to ignore when looking for source files.
+# This patterns also effect to html_static_path and html_extra_path
+exclude_patterns = ['_build', 'Thumbs.db', '.DS_Store']
+
+# The reST default role (used for this markup: `text`) to use for all
+# documents.
+#
+# default_role = None
+
+# If true, '()' will be appended to :func: etc. cross-reference text.
+#
+# add_function_parentheses = True
+
+# If true, the current module name will be prepended to all description
+# unit titles (such as .. function::).
+#
+# add_module_names = True
+
+# If true, sectionauthor and moduleauthor directives will be shown in the
+# output. They are ignored by default.
+#
+# show_authors = False
+
+# The name of the Pygments (syntax highlighting) style to use.
+pygments_style = 'sphinx'
+
+# A list of ignored prefixes for module index sorting.
+# modindex_common_prefix = []
+
+# If true, keep warnings as "system message" paragraphs in the built documents.
+# keep_warnings = False
+
+# If true, `todo` and `todoList` produce output, else they produce nothing.
+todo_include_todos = False
+
+
+# -- Options for HTML output ----------------------------------------------
+
+import sphinx_rtd_theme
+
+# The theme to use for HTML and HTML Help pages.  See the documentation for
+# a list of builtin themes.
+#
+html_theme = 'sphinx_rtd_theme'
+html_theme_path = [sphinx_rtd_theme.get_html_theme_path()]
+
+# Theme options are theme-specific and customize the look and feel of a theme
+# further.  For a list of options available for each theme, see the
+# documentation.
+#
+html_theme_options = {
+    'display_version': False
+}
+
+# Add any paths that contain custom themes here, relative to this directory.
+# html_theme_path = []
+
+# The name for this set of Sphinx documents.
+# "<project> v<release> documentation" by default.
+#
+# html_title = 'ocrmypdf v4.2'
+
+# A shorter title for the navigation bar.  Default is the same as html_title.
+#
+# html_short_title = None
+
+# The name of an image file (relative to this directory) to place at the top
+# of the sidebar.
+#
+# html_logo = None
+
+# The name of an image file (relative to this directory) to use as a favicon of
+# the docs.  This file should be a Windows icon file (.ico) being 16x16 or 32x32
+# pixels large.
+#
+# html_favicon = None
+
+# Add any paths that contain custom static files (such as style sheets) here,
+# relative to this directory. They are copied after the builtin static files,
+# so a file named "default.css" will overwrite the builtin "default.css".
+html_static_path = ['_static']
+
+# Add any extra paths that contain custom files (such as robots.txt or
+# .htaccess) here, relative to this directory. These files are copied
+# directly to the root of the documentation.
+#
+# html_extra_path = []
+
+# If not None, a 'Last updated on:' timestamp is inserted at every page
+# bottom, using the given strftime format.
+# The empty string is equivalent to '%b %d, %Y'.
+#
+# html_last_updated_fmt = None
+
+# If true, SmartyPants will be used to convert quotes and dashes to
+# typographically correct entities.
+#
+# html_use_smartypants = True
+
+# Custom sidebar templates, maps document names to template names.
+#
+# html_sidebars = {}
+
+# Additional templates that should be rendered to pages, maps page names to
+# template names.
+#
+# html_additional_pages = {}
+
+# If false, no module index is generated.
+#
+# html_domain_indices = True
+
+# If false, no index is generated.
+#
+# html_use_index = True
+
+# If true, the index is split into individual pages for each letter.
+#
+# html_split_index = False
+
+# If true, links to the reST sources are added to the pages.
+#
+# html_show_sourcelink = True
+
+# If true, "Created using Sphinx" is shown in the HTML footer. Default is True.
+#
+# html_show_sphinx = True
+
+# If true, "(C) Copyright ..." is shown in the HTML footer. Default is True.
+#
+# html_show_copyright = True
+
+# If true, an OpenSearch description file will be output, and all pages will
+# contain a <link> tag referring to it.  The value of this option must be the
+# base URL from which the finished HTML is served.
+#
+# html_use_opensearch = ''
+
+# This is the file name suffix for HTML files (e.g. ".xhtml").
+# html_file_suffix = None
+
+# Language to be used for generating the HTML full-text search index.
+# Sphinx supports the following languages:
+#   'da', 'de', 'en', 'es', 'fi', 'fr', 'h', 'it', 'ja'
+#   'nl', 'no', 'pt', 'ro', 'r', 'sv', 'tr', 'zh'
+#
+# html_search_language = 'en'
+
+# A dictionary with options for the search language support, empty by default.
+# 'ja' uses this config value.
+# 'zh' user can custom change `jieba` dictionary path.
+#
+# html_search_options = {'type': 'default'}
+
+# The name of a javascript file (relative to the configuration directory) that
+# implements a search results scorer. If empty, the default will be used.
+#
+# html_search_scorer = 'scorer.js'
+
+# Output file base name for HTML help builder.
+htmlhelp_basename = 'ocrmypdfdoc'
+
+# -- Options for LaTeX output ---------------------------------------------
+
+latex_elements = {
+     # The paper size ('letterpaper' or 'a4paper').
+     #
+     # 'papersize': 'letterpaper',
+
+     # The font size ('10pt', '11pt' or '12pt').
+     #
+     # 'pointsize': '10pt',
+
+     # Additional stuff for the LaTeX preamble.
+     #
+     # 'preamble': '',
+
+     # Latex figure (float) alignment
+     #
+     # 'figure_align': 'htbp',
+}
+
+# Grouping the document tree into LaTeX files. List of tuples
+# (source start file, target name, title,
+#  author, documentclass [howto, manual, or own class]).
+latex_documents = [
+    (master_doc, 'ocrmypdf.tex', 'ocrmypdf Documentation',
+     'James R. Barlow', 'manual'),
+]
+
+# The name of an image file (relative to this directory) to place at the top of
+# the title page.
+#
+# latex_logo = None
+
+# For "manual" documents, if this is true, then toplevel headings are parts,
+# not chapters.
+#
+# latex_use_parts = False
+
+# If true, show page references after internal links.
+#
+# latex_show_pagerefs = False
+
+# If true, show URL addresses after external links.
+#
+# latex_show_urls = False
+
+# Documents to append as an appendix to all manuals.
+#
+# latex_appendices = []
+
+# It false, will not define \strong, \code, 	itleref, \crossref ... but only
+# \sphinxstrong, ..., \sphinxtitleref, ... To help avoid clash with user added
+# packages.
+#
+# latex_keep_old_macro_names = True
+
+# If false, no module index is generated.
+#
+# latex_domain_indices = True
+
+
+# -- Options for manual page output ---------------------------------------
+
+# One entry per manual page. List of tuples
+# (source start file, name, description, authors, manual section).
+man_pages = [
+    (master_doc, 'ocrmypdf', 'ocrmypdf Documentation',
+     [author], 1)
+]
+
+# If true, show URL addresses after external links.
+#
+# man_show_urls = False
+
+
+# -- Options for Texinfo output -------------------------------------------
+
+# Grouping the document tree into Texinfo files. List of tuples
+# (source start file, target name, title, author,
+#  dir menu entry, description, category)
+texinfo_documents = [
+    (master_doc, 'ocrmypdf', 'ocrmypdf Documentation',
+     author, 'ocrmypdf', 'One line description of project.',
+     'Miscellaneous'),
+]
+
+# Documents to append as an appendix to all manuals.
+#
+# texinfo_appendices = []
+
+# If false, no module index is generated.
+#
+# texinfo_domain_indices = True
+
+# How to display URL addresses: 'footnote', 'no', or 'inline'.
+#
+# texinfo_show_urls = 'footnote'
+
+# If true, do not generate a @detailmenu in the "Top" node's menu.
+#
+# texinfo_no_detailmenu = False

docs/cookbook.rst

@@ -0,0 +1,200 @@
+Cookbook
+========
+
+Basic examples
+--------------
+
+Help!
+"""""
+
+ocrmypdf has built-in help.
+
+.. code-block:: bash
+
+    ocrmypdf --help
+
+
+Add an OCR layer and convert to PDF/A
+"""""""""""""""""""""""""""""""""""""
+
+.. code-block:: bash
+
+    ocrmypdf input.pdf output.pdf
+
+Add an OCR layer and output a standard PDF
+""""""""""""""""""""""""""""""""""""""""""
+
+.. code-block:: bash
+
+    ocrmypdf --output-type pdf input.pdf output.pdf
+
+Create a PDF/A with all color and grayscale images converted to JPEG
+""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""
+
+.. code-block:: bash
+
+    ocrmypdf --output-type pdfa --pdfa-image-compression jpeg input.pdf output.pdf
+
+Modify a file in place
+""""""""""""""""""""""
+
+The file will only be overwritten if OCRmyPDF is successful.
+
+.. code-block:: bash
+
+    ocrmypdf myfile.pdf myfile.pdf
+
+Correct page rotation
+"""""""""""""""""""""
+
+OCR will attempt to automatic correct the rotation of each page. This can help fix a scanning job that contains a mix of landscape and portrait pages.
+
+.. code-block:: bash
+
+    ocrmypdf --rotate-pages myfile.pdf myfile.pdf
+
+You can increase (decrease) the parameter ``--rotate-pages-threshold`` to make page rotation more (less) aggressive.
+
+If the page is "just a little off horizontal", like a crooked picture, then you want ``--deskew``. ``--rotate-pages`` is for when the cardinal angle is wrong.
+
+
+OCR languages other than English
+""""""""""""""""""""""""""""""""
+
+By default OCRmyPDF assumes the document is English. 
+
+.. code-block:: bash
+
+    ocrmypdf -l fra LeParisien.pdf LeParisien.pdf
+    ocrmypdf -l eng+fra Bilingual-English-French.pdf Bilingual-English-French.pdf
+
+Language packs must be installed for all languages specified. See :ref:`Installing additional language packs <lang-packs>`.
+
+
+Produce PDF and text file containing OCR text
+"""""""""""""""""""""""""""""""""""""""""""""
+
+This produces a file named "output.pdf" and a companion text file named "output.txt".
+
+.. code-block:: bash
+
+    ocrmypdf --sidecar output.txt input.pdf output.pdf
+
+OCR images, not PDFs
+--------------------
+
+If you are starting with images, you can just use Tesseract 3.04 or later directly to convert images to PDFs:
+
+.. code-block:: bash
+
+    tesseract my-image.jpg output-prefix pdf
+
+.. code-block:: bash
+
+    # When there are multiple images
+    tesseract text-file-containing-list-of-image-filenames.txt output-prefix pdf
+
+Tesseract's PDF output is quite good – OCRmyPDF uses it by internally by default. However, OCRmyPDF has many features not available in Tesseract like like image processing, metadata control, and PDF/A generation.
+
+Use a program like `img2pdf <https://gitlab.mister-muffin.de/josch/img2pdf>`_ to convert your images to PDFs, and then pipe the results to run ocrmypdf.  The `-` tells ocrmypdf to read standard input.
+
+.. code-block:: bash
+
+    img2pdf my-images*.jpg | ocrmypdf - myfile.pdf
+
+``img2pdf`` is recommended because it does an excellent job at generating PDFs without transcoding images.
+
+For convenience, OCRmyPDF can also convert single images to PDFs on its own. If the resolution (dots per inch, DPI) of an image is not set or is incorrect, it can be overridden with ``--image-dpi``. (As 1 inch is 2.54 cm, 1 dpi = 0.39 dpcm).
+
+.. code-block:: bash
+
+    ocrmypdf --image-dpi 300 image.png myfile.pdf
+
+If you have multiple images, you must use ``img2pdf`` to convert the images to PDF.
+
+.. note::
+
+    ImageMagick ``convert`` can also convert a group of images to PDF, but in the author's experience it takes a long time, transcodes unnecessarily and gives poor results.
+
+
+Image processing
+----------------
+
+OCRmyPDF perform some image processing on each page of a PDF, if desired.  The same processing is applied to each page.  It is suggested that the user review files after image processing as these commands might remove desirable content, especially from poor quality scans.
+
+* ``--rotate-pages`` attempts to determine the correct orientation for each page and rotates the page if necessary.
+
+* ``--remove-background`` attempts to detect and remove a noisy background from grayscale or color images.  Monochrome images are ignored. This should not be used on documents that contain color photos as it may remove them.
+
+* ``--deskew`` will correct pages were scanned at a skewed angle by rotating them back into place.  Skew determination and correction is performed using `Postl's variance of line sums <http://www.leptonica.com/skew-measurement.html>`_ algorithm as implemented in `Leptonica <http://www.leptonica.com/index.html>`_.
+  
+* ``--clean`` uses `unpaper <https://www.flameeyes.eu/projects/unpaper>`_ to clean up pages before OCR, but does not alter the final output.  This makes it less likely that OCR will try to find text in background noise.
+
+* ``--clean-final`` uses unpaper to clean up pages before OCR and inserts the page into the final output.  You will want to review each page to ensure that unpaper did not remove something important.
+
+.. note::
+
+    In many cases image processing will rasterize PDF pages as images, potentially losing quality.
+
+.. warning::
+
+    ``--clean-final`` and ``-remove-background`` may leave undesirable visual artifacts in some images where their algorithms have shortcomings. Files should be visually reviewed after using these options.
+
+
+OCR and correct document skew (crooked scan)
+""""""""""""""""""""""""""""""""""""""""""""
+
+Deskew:
+
+.. code-block:: bash
+
+    ocrmypdf --deskew input.pdf output.pdf
+
+Image processing commands can be combined. The order in which options are given does not matter. OCRmyPDF always applies the steps of the image processing pipeline in the same order (rotate, remove background, deskew, clean).
+
+.. code-block:: bash
+
+    ocrmypdf --deskew --clean --rotate-pages input.pdf output.pdf
+
+
+Don't actually OCR my PDF
+"""""""""""""""""""""""""
+
+If you set ``--tesseract-timeout 0`` OCRmyPDF will apply its image processing without performing OCR, if all you want to is to apply image processing or PDF/A conversion.
+
+.. code-block:: bash
+
+    ocrmypdf --tesseract-timeout=0 --remove-background input.pdf output.pdf
+
+
+Redo OCR
+""""""""
+
+To redo OCR on a file OCRed with other OCR software or a previous version of OCRmyPDF and/or Tesseract, you may use the ``--force-ocr`` argument. Normally, OCRmyPDF does not modify files that already appear to contain OCR text.
+
+.. code-block:: bash
+
+    ocrmypdf --force-ocr input.pdf output.pdf
+
+Note that the method above will force rasterization of all pages, potentially reducing quality or losing vector content. 
+
+To ensure quality is preserved, one could extract all of the images and rebuild the PDF for a lossless transformation. This recipe does not work when PDFs contain multiple images per page, as many do in practice. It will also lose any page rotation information.
+
+.. code-block:: bash
+
+    pdfimages -all old-ocr.pdf prefix  # extract all images
+    img2pdf -o temp.pdf prefix*        # construct new PDF from the images
+    # review the new PDF to ensure it visually matches the old one
+    ocrmypdf --output-type pdf temp.pdf new-ocr.pdf
+
+``--output-type pdf`` is used here to avoid using Ghostscript which will also rasterize images.
+
+
+Improving OCR quality
+---------------------
+
+The `Image processing`_ features can improve OCR quality.
+
+Rotating pages and deskewing helps to ensure that the page orientation is correct before OCR begins. Removing the background and/or cleaning the page can also improve results. The ``--oversample DPI`` argument can be specified to resample images to higher resolution before attempting OCR; this can improve results as well.
+
+OCR quality will suffer if the resolution of input images is not correct (since the range of pixel sizes that will be checked for possible fonts will also be incorrect).

docs/errors.rst

@@ -0,0 +1,33 @@
+Common error messages
+=====================
+
+Page already has text
+---------------------
+
+.. code::
+
+	ERROR -    1: page already has text! – aborting (use --force-ocr to force OCR)
+
+You ran ocrmypdf on a file that already contains printable text or a hidden OCR text layer (it can't quite tell the difference). You probably don't want to do this, because the file is already searchable.
+
+As the error message suggests, your options are:
+
+- ``ocrmypdf --force-ocr`` to :ref:`rasterize <raster-vector>` all vector content and run OCR on the images. This is useful if a previous OCR program failed, or if the document contains a text watermark.
+
+- ``ocrmypdf --skip-text`` to skip OCR and other processing on any pages that contain text. Text pages will be copied into the output PDF without modification.
+
+
+Input file 'filename' is not a valid PDF
+----------------------------------------
+
+OCRmyPDF passes files through qpdf, a program that fixes errors in PDFs, before it tries to work on them. In most cases this happens because the PDF is corrupt and
+truncated (incomplete file copying) and not much can be done.
+
+You can try rewriting the file with Ghostscript or pdftk:
+
+- ``gs -o output.pdf -dSAFER -sDEVICE=pdfwrite input.pdf``
+
+- ``pdftk input.pdf cat output output.pdf``
+
+Sometimes Acrobat can repair PDFs with its `Preflight tool <https://helpx.adobe.com/acrobat/using/correcting-problem-areas-preflight-tool.html>`_.
+

docs/index.rst

@@ -0,0 +1,39 @@
+.. ocrmypdf documentation master file, created by
+   sphinx-quickstart on Sun Sep  4 14:29:43 2016.
+   You can adapt this file completely to your liking, but it should at least
+   contain the root `toctree` directive.
+
+OCRmyPDF documentation
+======================
+
+OCRmyPDF adds an OCR text layer to scanned PDF files, allowing them to
+be searched.
+
+PDF is the best format for storing and exchanging scanned documents.  Unfortunately, PDFs can be difficult to modify. OCRmyPDF makes it easy to apply image processing and OCR to existing PDFs.
+
+.. toctree::
+   :maxdepth: 1
+
+   introduction
+   release_notes
+   installation
+   languages
+
+.. toctree::
+   :caption: Usage
+   :maxdepth: 2
+
+   cookbook
+   advanced
+   batch
+   security
+   errors
+
+
+Indices and tables
+==================
+
+* :ref:`genindex`
+* :ref:`modindex`
+* :ref:`search`
+

docs/installation.rst

@@ -0,0 +1,453 @@
+Installation
+============
+
+The easiest way to install OCRmyPDF to follow the steps for your operating system/platform. 
+
+If you want to use the latest version of OCRmyPDF, your best bet is to install the most recent version your platform provides, and then upgrade that version by installing the Python binary wheels.
+
+.. contents:: Platform-specific steps
+    :depth: 1
+    :local:
+
+Installing on Debian and Ubuntu 16.10 or newer
+----------------------------------------------
+
+Users of Debian 9 ("stretch") or later or Ubuntu 16.10 or later may simply
+
+.. code-block:: bash
+
+    apt-get install ocrmypdf
+
+To see what versions are available, check the `Debian Package Tracker <https://tracker.debian.org/pkg/ocrmypdf>`_ or `Ubuntu launchpad.net <https://launchpad.net/ocrmypdf>`_.
+
+Installing on macOS with Homebrew
+---------------------------------
+
+.. image:: https://img.shields.io/homebrew/v/ocrmypdf.svg   
+    :alt: homebrew
+    :target: http://brewformulas.org/Ocrmypdf
+
+OCRmyPDF is now a standard `Homebrew <https://brew.sh>`_ formula. To install on macOS:
+
+.. code-block:: bash
+
+    brew install ocrmypdf
+
+.. note::
+
+    Users who previously installed OCRmyPDF on macOS using ``pip install ocrmypdf`` should remove the pip version (``pip3 uninstall ocrmypdf``) before switching to the Homebrew version.
+
+.. note::
+
+    Users who previously installed OCRmyPDF from the private tap should switch to the mainline version (``brew untap jbarlow83/ocrmypdf``) and install from there.
+
+.. _Docker-install:
+
+Installing the Docker image
+---------------------------
+
+For many users, installing the Docker image will be easier than installing all of OCRmyPDF's dependencies. For Windows, it is the only option.
+
+If you have `Docker <https://docs.docker.com/>`_ installed on your system, you can install a Docker image of the latest release.
+
+Follow the Docker installation instructions for your platform.  If you can run this command successfully, your system is ready to download and execute the image:
+
+.. code-block:: bash
+
+    docker run hello-world
+   
+OCRmyPDF will use all available CPU cores.  By default, the VirtualBox machine instance on Windows and macOS has only a single CPU core enabled. Use the VirtualBox Manager to determine the name of your Docker engine host, and then follow these optional steps to enable multiple CPUs:
+
+.. code-block:: bash
+
+    # Optional step for Mac OS X users
+    docker-machine stop "yourVM"
+    VBoxManage modifyvm "yourVM" --cpus 2  # or whatever number of core is desired
+    docker-machine start "yourVM"
+    eval $(docker-machine env "yourVM")
+
+Assuming you have a Docker engine running, you can download one of the three available images:
+
+.. list-table::
+    :widths: auto
+    :header-rows: 1
+
+    *   - Image name
+        - Download command
+        - Notes
+    *   - ocrmypdf
+        - ``docker pull jbarlow83/ocrmypdf``
+        - Latest ocrmypdf with Tesseract 4.0.0-beta1 on Ubuntu 18.04. Includes English, French, German, Spanish, Portugeuse and Simplified Chinese.
+    *   - ocrmypdf-polyglot
+        - ``docker pull jbarlow83/ocrmypdf-polyglot``
+        - As above, with all available language packs.
+
+For example:
+
+.. code-block:: bash
+
+    docker pull jbarlow83/ocrmypdf
+
+Then tag it to give a more convenient name, just ocrmypdf:
+
+.. code-block:: bash
+
+    docker tag jbarlow83/ocrmypdf ocrmypdf
+
+.. _docker-polyglot:
+
+The alternative "polyglot" image provides `all available language packs <https://github.com/tesseract-ocr/tesseract/blob/master/doc/tesseract.1.asc#languages>`_.
+
+You can then run ocrmypdf using the command:
+
+.. code-block:: bash
+
+    docker run --rm ocrmypdf --help
+  
+To execute the OCRmyPDF on a local file, you must `provide a writable volume to the Docker image <https://docs.docker.com/userguide/dockervolumes/>`_, and both the input and output file must be inside the writable volume.  This example command uses the current working directory as the writable volume:
+
+.. code-block:: bash
+
+    docker run --rm -v "$(pwd):/home/docker" <other docker arguments>   ocrmypdf <your arguments to ocrmypdf>
+
+In this worked example, the current working directory contains an input file called ``test.pdf`` and the output will go to ``output.pdf``: 
+
+.. code-block:: bash
+
+    docker run --rm -v "$(pwd):/home/docker"   ocrmypdf --skip-text test.pdf output.pdf
+
+.. note:: The working directory should be a writable local volume or Docker may not have permission to access it.
+
+Note that ``ocrmypdf`` has its own separate ``-v VERBOSITYLEVEL`` argument to control debug verbosity. All Docker arguments should before the ``ocrmypdf`` image name and all arguments to ``ocrmypdf`` should be listed after.
+
+In some environments the permissions associated with Docker can be complex to configure. The process that executes Docker may end up not having the permissions to write the specified file system. In that case one can stream the file into and out of the Docker process and avoid all permission hassles, using ``-`` as the input and output filename:
+
+.. code-block:: bash
+
+    docker run --rm -i   ocrmypdf <other arguments to ocrmypdf> - - <input.pdf >output.pdf
+
+For convenience, a shell alias can hide the docker command:
+
+.. code-block:: bash
+
+    alias ocrmypdf='docker run --rm -v "$(pwd):/home/docker" ocrmypdf'
+    ocrmypdf --version  # runs docker version
+
+Or in the wonderful `fish shell <https://fishshell.com/>`_:
+
+.. code-block:: fish
+
+    alias ocrmypdf 'docker run --rm -v (pwd):/home/docker ocrmypdf'
+    funcsave ocrmypdf
+
+.. note::
+
+    The ocrmypdf Docker containers are designed to be used for a single OCR job. The ``docker run --rm`` argument tells Docker to delete temporary storage associated with container when it is done executing.
+
+Manual installation on macOS
+----------------------------
+
+These instructions probably work on all macOS supported by Homebrew.
+
+If it's not already present, `install Homebrew <http://brew.sh/>`_.
+
+Update Homebrew:
+
+.. code-block:: bash
+
+    brew update
+
+Install or upgrade the required Homebrew packages, if any are missing:
+
+.. code-block:: bash
+
+    brew install libpng openjpeg jbig2dec libtiff     # image libraries
+    brew install qpdf
+    brew install ghostscript
+    brew install python3
+    brew install libxml2 libffi leptonica
+    brew install unpaper   # optional
+   
+Python 3.5 and 3.6 are supported.
+
+Install the required Tesseract OCR engine with the language packs you plan to use:
+   
+.. code-block:: bash
+
+    brew install tesseract                       # Option 1: for English, French, German, Spanish
+
+.. _macos-all-languages:
+
+.. code-block:: bash
+
+    brew install tesseract --with-all-languages  # Option 2: for all language packs
+
+Update the homebrew pip:
+
+.. code-block:: bash
+
+    pip3 install --upgrade pip
+
+You can then install OCRmyPDF from PyPI, for the current user:
+
+.. code-block:: bash
+
+    pip3 install --user ocrmypdf[fitz]
+
+or system-wide:
+
+.. code-block:: bash
+
+    pip3 install ocrmypdf[fitz]
+
+``[fitz]`` includes the optional dependency on PyMuPDF, which improves OCRmyPDF's output in many cases.
+
+The command line program should now be available:
+
+.. code-block:: bash
+
+    ocrmypdf --help
+
+Installing the latest version on Ubuntu 18.04 LTS
+-------------------------------------------------
+
+Ubuntu 18.04 includes ocrmypdf 6.1.2. To install a more recent version, first
+install the system version to get all the dependencies:
+
+.. code-block:: bash
+
+    sudo apt-get update
+    sudo apt-get install \
+        ocrmypdf \
+        python3-pip
+
+Then install ocrmypdf 6.1.5 for the local user and set the user's ``PATH`` to check for the user's Python packages.
+
+.. code-block:: bash
+
+    export PATH=$HOME/.local/bin:$PATH
+    pip3 install --user ocrmypdf[fitz]
+
+
+Installing on Ubuntu 16.04 LTS
+------------------------------
+
+No package is currently available for Ubuntu 16.04, but you can install the dependencies manually:
+
+.. code-block:: bash
+
+    sudo apt-get update
+    sudo apt-get install \
+        unpaper \
+        ghostscript \
+        tesseract-ocr \
+        qpdf \
+        python3-pip \
+        python3-cffi
+
+If you wish install OCRmyPDF for the current user:
+
+.. code-block:: bash
+
+    pip3 install --user ocrmypdf[fitz]
+
+Alternately, system-wide. Note that this may modify the system Python environment:
+
+.. code-block:: bash
+
+    sudo pip3 install ocrmypdf[fitz]
+
+If you wish to install OCRmyPDF to a virtual environment to isolate the system Python, you can follow these steps.
+
+.. code-block:: bash
+
+    python3 -m venv venv-ocrmypdf
+    source venv-ocrmypdf/bin/activate
+    pip3 install ocrmypdf[fitz]
+
+``[fitz]`` includes the optional dependency on PyMuPDF, which improves OCRmyPDF's output in many cases.
+
+
+Installing on Ubuntu 14.04 LTS
+------------------------------
+
+Installing on Ubuntu 14.04 LTS (trusty) is more difficult than some other options, because it is older and does not provide ``pip``.
+
+Update apt-get:
+
+.. code-block:: bash
+
+    sudo apt-get update
+
+Install system dependencies:
+
+.. code-block:: bash
+
+    sudo apt-get install \
+        software-properties-common python-software-properties \
+        zlib1g-dev \
+        libjpeg-dev \
+        libffi-dev \
+        qpdf
+
+We will need backports of Ghostscript 9.16, libav-11 (for unpaper 6.1), Tesseract 4.00 (alpha), and Python 3.6. This will replace Ghostscript and Tesseract 3.x on your system. Python 3.6 will be installed alongside the system Python 3.
+
+If you prefer to not modify your system in this matter, consider using a Docker container.
+
+.. code-block:: bash
+
+    sudo add-apt-repository ppa:vshn/ghostscript -y
+    sudo add-apt-repository ppa:heyarje/libav-11 -y
+    sudo add-apt-repository ppa:alex-p/tesseract-ocr -y
+    sudo add-apt-repository ppa:jonathonf/python-3.6 -y
+
+    sudo apt-get update
+
+    sudo apt-get install \
+        python3.6-dev \
+        ghostscript \
+        tesseract-ocr \
+        tesseract-ocr-eng \
+        libavformat56 libavcodec56 libavutil54 \
+        wget
+
+Now we need to install ``pip`` and let it install ocrmypdf:
+
+.. code-block:: bash
+
+    curl https://bootstrap.pypa.io/ez_setup.py -o - | python3.6 && python3.6 -m easy_install pip
+    pip3.6 install ocrmypdf[fitz]
+
+The ``wget`` command will download a program and run it.
+
+These installation instructions omit the optional dependency ``unpaper``, which is only available at version 0.4.2 in Ubuntu 14.04. The author could not find a backport of ``unpaper``, and created a .deb package to do the job of installing unpaper 6.1 (for x86 64-bit only):
+
+.. code-block:: bash
+
+    wget -q 'https://www.dropbox.com/s/vaq0kbwi6e6au80/unpaper_6.1-1.deb?raw=1' -O unpaper_6.1-1.deb
+    sudo dpkg -i unpaper_6.1-1.deb
+
+
+Installing on ArchLinux
+-----------------------
+
+The author is aware of an `ArchLinux package for ocrmypdf <https://aur.archlinux.org/packages/ocrmypdf/>`_. It seems like the following command might work.
+
+.. code-block:: bash
+
+    pacman -S ocrmypdf
+
+
+Installing on Windows
+---------------------
+
+Direct installation on Windows is not possible.  Install the _`Docker` container as described above.  Ensure that your command prompt can run the docker "hello world" container.
+
+It would probably not be too difficult to run on Windows.  The main reason this has been avoided is the difficulty of packaging and installing the various non-Python dependencies: Tesseract, QPDF, Ghostscript, Leptonica.  Pull requests to add or improve Windows support would be quite welcome.
+
+
+Running on Windows
+~~~~~~~~~~~~~~~~~~
+
+The command line syntax to run ocrmypdf from a command prompt will resemble:
+
+.. code-block:: bat
+
+    docker run -v /c/Users/sampleuser:/home/docker ocrmypdf --skip-text test.pdf output.pdf
+
+where /c/Users/sampleuser is a Unix representation of the Windows path C:\\Users\\sampleuser, assuming a user named "sampleuser" is running ocrmypdf on a file in their home directory, and the files "test.pdf" and "output.pdf" are in the sampleuser folder. The Windows user must have read and write permissions.
+
+`Bash on Ubuntu on Windows <https://github.com/Microsoft/BashOnWindows>`_ should also be a viable route for running the OCRmyPDF Docker container.
+
+
+Installing with Python pip
+--------------------------
+
+First, install `your platform's version <https://repology.org/metapackage/ocrmypdf/versions>`_ of ``ocrmypdf``, if available, as a way of ensuring that external dependencies are (mostly) satisified, even though the platform version may be out of date. Use ``ocrmypdf --version`` to confirm what version was installed.
+
+Then you can install the latest OCRmyPDF from the Python wheels. First try:
+
+.. code-block:: bash
+
+    pip3 install --user ocrmypdf
+
+You should then be able to run ``ocrmypdf --version`` and see that the latest version was located.
+
+Since ``pip3 install --user`` does not work correctly on some platforms, notably Ubuntu 16.04 and older, and the Homebrew version of Python, instead use this for a system wide installation:
+
+.. code-block:: bash
+
+    pip3 install ocrmypdf
+
+Requirements for pip and HEAD install
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+OCRmyPDF currently requires these external programs to be installed:
+
+- Python 3.5 or newer
+- Tesseract 3.04 or newer
+- Ghostscript 9.15 or newer
+- qpdf 7.0.0 or newer
+
+The following dependencies are recommended:
+
+- Python 3.6
+- Tesseract 4.00 or newer
+- Ghostscript 9.22 or newer
+- qpdf 8.0.2 or newer
+- unpaper 6.1
+- PyMuPDF 1.12.5 or newer
+
+These are in addition to the Python packaging dependencies, meaning that unfortunately, the ``pip install`` command cannot satisfy all of them. 
+
+Python 3.6 and Tesseract 4.0.0-beta.1 are recommended for best OCR results and best performance.
+
+The library PyMuPDF is not widely available in platform distributions, and it improves OCRmyPDF in certain conditions. Consider installing OCRmyPDF from the Python binary wheels, which include a precompiled version of this library.
+
+
+Installing HEAD revision from sources
+-------------------------------------
+
+If you have ``git`` and Python 3.5 or newer installed, you can install from source. When the ``pip`` installer runs, it will alert you if dependencies are missing.
+
+To install the HEAD revision from sources in the current Python 3 environment:
+
+.. code-block:: bash
+
+    pip3 install git+https://github.com/jbarlow83/OCRmyPDF.git
+
+Or, to install in `development mode <https://pythonhosted.org/setuptools/setuptools.html#development-mode>`_,  allowing customization of OCRmyPDF, use the ``-e`` flag:
+
+.. code-block:: bash
+
+    pip3 install -e git+https://github.com/jbarlow83/OCRmyPDF.git
+
+You may find it easiest to install in a virtual environment, rather than system-wide:
+
+.. code-block:: bash
+
+    git clone -b master https://github.com/jbarlow83/OCRmyPDF.git
+    python3 -m venv
+    source venv/bin/activate
+    cd OCRmyPDF
+    pip3 install .
+
+However, ``ocrmypdf`` will only be accessible on the system PATH after
+you activate the virtual environment.
+
+To run the program:
+
+.. code-block:: bash
+
+    ocrmypdf --help
+
+If not yet installed, the script will notify you about dependencies that
+need to be installed. The script requires specific versions of the
+dependencies. Older version than the ones mentioned in the release notes
+are likely not to be compatible to OCRmyPDF.
+
+
+Other Linux packages
+--------------------
+
+See the `Repology <https://repology.org/metapackage/ocrmypdf/versions>`_ page.

docs/introduction.rst

@@ -0,0 +1,115 @@
+Introduction
+============
+
+OCRmyPDF is a Python 3 package that adds OCR layers to PDFs.
+
+
+About OCR
+---------
+
+`Optical character recognition <https://en.wikipedia.org/wiki/Optical_character_recognition>`_ is technology that converts images of typed or handwritten text, such as in a scanned document, to computer text that can be searched and copied.
+
+OCRmyPDF uses `Tesseract <https://github.com/tesseract-ocr/tesseract>`_, the best available open source OCR engine, to perform OCR.
+
+.. _raster-vector:
+
+About PDFs
+----------
+
+PDFs are page description files that attempts to preserve a layout exactly. They  contain `vector graphics <http://vector-conversions.com/vectorizing/raster_vs_vector.html>`_ that can contain raster objects such as scanned images. Because PDFs can contain multiple pages (unlike many image formats) and can contain fonts and text, it is a good formats for exchanging scanned documents.
+
+.. image:: bitmap_vs_svg.svg
+
+A PDF page might contain multiple images, even if it only appears to have one image.  Some scanners or scanning software will segment pages into monochromatic text and color regions for example, to improve the compression ratio and appearance of the page.
+
+Rasterizing a PDF is the process of generating an image suitable for display or analyzing with an OCR engine.  OCR engines like Tesseract work with images, not vector objects.
+
+
+About PDF/A
+-----------
+
+`PDF/A <https://en.wikipedia.org/wiki/PDF/A>`_ is an ISO-standardized subset of the full PDF specification that is designed for archiving (the 'A' stands for Archive).  PDF/A differs from PDF primarily by omitting features that would make it difficult to read the file in the future, such as embedded Javascript, video, audio and references to external fonts.  All fonts and resources needed to interpret the PDF must be contained within it. Because PDF/A disables Javascript and other types of embedded content, it is probably more secure.
+
+There are various conformance levels and versions, such as "PDF/A-2b".
+
+Generally speaking, the best format for scanned documents is PDF/A. Some governments and jurisdictions, US Courts in particular, `mandate the use of PDF/A <https://pdfblog.com/2012/02/13/what-is-pdfa/>`_ for scanned documents.
+
+Since most people who scan documents are interested in reading them indefinitely into the future, OCRmyPDF generates PDF/A-2b by default.
+
+PDF/A has a few drawbacks.  Some PDF viewers include an alert that the file is a PDF/A, which may confuse some users.  It also tends to produce larger files than PDF, because it embeds certain resources even if they are commonly available. PDF/A files can be digitally signed, but may not be encrypted, to ensure they can be read in the future.  Fortunately, converting from PDF/A to a regular PDF is trivial, and any PDF viewer can view PDF/A.
+
+
+What OCRmyPDF does
+------------------
+
+OCRmyPDF analyzes each page of a PDF to determine the colorspace and resolution (DPI) needed to capture all of the information on that page without losing content.  It uses `Ghostscript <http://ghostscript.com/>`_ to rasterize the page, and then performs on OCR on the rasterized image to create an OCR "layer". The layer is then grafted back onto the original PDF.
+
+While one can use a program like Ghostscript or ImageMagick to get an image and put the image through Tesseract, that actually creates a new PDF and many details may be lost. OCRmyPDF can produce a minimally changed PDF as output.
+
+OCRmyPDF also some image processing options like deskew which improve the appearance of files and quality of OCR. When these are used, the OCR layer is grafted onto the processed image instead.
+
+By default, OCRmyPDF produces archival PDFs – PDF/A, which are a stricter subset of PDF features designed for long term archives. If regular PDFs are desired, this can be disabled with ``--output-type pdf``.
+
+
+Why you shouldn't do this manually
+----------------------------------
+
+A PDF is similar to an HTML file, in that it contains document structure along with images.  Sometimes a PDF does nothing more than present a full page image, but often there is additional content that would be lost.
+
+A manual process could work like either of these:
+
+1. Rasterize each page as an image, OCR the images, and combine the output into a PDF. This preserves the layout of each page, but resamples all images (possibly losing quality, increasing file size, introducing compression artifacts, etc.).
+
+2. Extract each image, OCR, and combine the output into a PDF. This loses the context in which images are used in the PDF, meaning that cropping, rotation and scaling of pages may be lost. Some scanned PDFs use multiple images segmented into black and white, grayscale and color regions, with stencil masks to prevent overlap, as this can enhance the appearance of a file while reducing file size. Clearly, reassembling these images will be easy. This also loses and text or vector art on any pages in a PDF with both scanned and pure digital content.
+
+In the case of a PDF that is nothing other than a container of images (no rotation, scaling, cropping, one image per page), the second approach can be lossless.
+
+OCRmyPDF uses several strategies depending on input options and the input PDF itself, but generally speaking it rasterizes a page for OCR and then grafts the OCR back onto the original. As such it can handle complex PDFs and still preserve their contents as much as possible.
+
+
+Limitations
+-----------
+
+OCRmyPDF is limited by the Tesseract OCR engine.  As such it experiences these limitations, as do any other programs that rely on Tesseract:
+
+* The OCR is not as accurate as commercial solutions such as Abbyy.
+* It is not capable of recognizing handwriting.
+* It may find gibberish and report this as OCR output.
+* If a document contains languages outside of those given in the ``-l LANG`` arguments, results may be poor.
+* It is not always good at analyzing the natural reading order of documents. For example, it may fail to recognize that a document contains two columns and join text across the columns.
+* Poor quality scans may produce poor quality OCR. Garbage in, garbage out.
+* PDFs that use transparent layers are not currently checked in the test suite, so they may not work correctly.
+* It does not expose information about what font family text belongs to.
+
+OCRmyPDF is also limited by the PDF specification:
+
+* PDF encodes the position of text glyphs but does not encode document structure.  There is no markup that divides a document in sections, paragraphs, sentences, or even words (since blank spaces are not represented). As such all elements of document structure including the spaces between words must be derived heuristically.  Some PDF viewers do a better job of this than others.
+* Because some popular open source PDF viewers have a particularly hard time with spaces betweem words, OCRmyPDF appends a space to each text element as a workaround. While this mixes document structure with graphical information that ideally should be left to the PDF viewer to interpret, it improves compatibility with some viewers and does not cause problems for better ones.
+
+Ghostscript also imposes some limitations:
+
+* PDFs containing JBIG2-encoded content will be converted to CCITT Group4 encoding, which has lower compression ratios, if Ghostscript PDF/A is enabled.
+* PDFs containing JPEG 2000-encoded content will be converted to JPEG encoding, which may introduce compression artifacts, if Ghostscript PDF/A is enabled.
+* Ghostscript may transcode grayscale and color images, either lossy to lossless or lossless to lossy, based on an internal algorithm. This behavior can be suppressed by setting ``--pdfa-image-compression`` to ``jpeg`` or ``lossless`` to set all images to one type or the other. Ghostscript has no option to maintain the input image's format.
+  
+OCRmyPDF is currently not designed to be used as a Python API; it is designed to be run as a command line tool. ``import ocrmypf`` currently attempts to process the command line on ``sys.argv`` at import time so it has side effects that will interfere with its use as a package. The API it presents should not be considered stable.
+
+
+Similar programs
+----------------
+
+To the author's knowledge, OCRmyPDF is the most feature-rich and thoroughly tested command line OCR PDF conversion tool. If it does not meet your needs, contributions and suggestions are welcome. If not, consider one of these similar open source programs:
+
+* pdf2pdfocr
+* pdfsandwich
+* pypdfocr
+* pdfbeads
+
+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/languages.rst

@@ -0,0 +1,61 @@
+.. _lang-packs:
+
+Installing additional language packs
+====================================
+
+OCRmyPDF uses Tesseract for OCR, and relies on its language packs for languages other than English. 
+
+Tesseract supports `most languages <https://github.com/tesseract-ocr/tesseract/blob/master/doc/tesseract.1.asc#languages>`_.
+
+For Linux users, you can often find packages that provide language packs:
+
+Debian and Ubuntu users
+-----------------------
+
+.. code-block:: bash
+
+   # Display a list of all Tesseract language packs
+   apt-cache search tesseract-ocr
+
+   # Debian/Ubuntu users
+   apt-get install tesseract-ocr-chi-sim  # Example: Install Chinese Simplified language back
+   
+You can then pass the ``-l LANG`` argument to OCRmyPDF to give a hint as to what languages it should search for. Multiple
+languages can be requested using either ``-l eng+fre`` (English and French) or ``-l eng -l fre``.
+
+macOS users
+-----------
+
+You can install additional language packs by :ref:`installing Tesseract using Homebrew with all language packs <macos-all-languages>`.
+
+Docker users
+------------
+
+Users of the Docker image may use the alternative :ref:`"polyglot" container <docker-polyglot>` which includes all languages.
+
+Adding individual language packs to a Docker image
+""""""""""""""""""""""""""""""""""""""""""""""""""
+
+If you wish to add a single language pack, you could do the following:
+
+* Download the desired ``.trainedata`` file from the `tessdata <https://github.com/tesseract-ocr/tessdata>`_ repository. Let's use Hebrew in this example (``heb.traineddata``)
+
+* Copy the file to ``/home/user/downloads/heb.traineddata``.
+
+* Create a new container based on the ocrmypdf-tess4 image and jump into it with a terminal:
+
+.. code-block:: bash
+
+	host$ docker run  -v /home/user/downloads:/home/docker -it --entrypoint /bin/bash ocrmypdf-tess4
+
+* Put the file where Tesseract expects it:
+
+.. code-block:: bash
+
+	docker$ cp /home/docker/heb.traineddata /usr/share/tesseract-ocr/tessdata
+
+* Note the container id, and save it as a new image (in this example, ``ocrmypdf-tess4-heb``)
+
+.. code-block:: bash
+
+    host$ docker commit <container_id> ocrmypdf-tess4-heb

docs/pipeline.svg

@@ -0,0 +1,392 @@
+<?xml version="1.0" encoding="UTF-8" standalone="no"?>
+<!DOCTYPE svg PUBLIC "-//W3C//DTD SVG 1.1//EN"
+ "http://www.w3.org/Graphics/SVG/1.1/DTD/svg11.dtd">
+<!-- Generated by graphviz version 2.40.1 (20161225.0304)
+ -->
+<!-- Title: Pipeline: Pages: 1 -->
+<svg width="1484pt" height="1277pt"
+ viewBox="0.00 0.00 1484.00 1277.20" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink">
+<g id="graph0" class="graph" transform="scale(1 1) rotate(0) translate(4 1273.1977)">
+<title>Pipeline:</title>
+<polygon fill="#ffffff" stroke="transparent" points="-4,4 -4,-1273.1977 1480,-1273.1977 1480,4 -4,4"/>
+<g id="clust1" class="cluster">
+<title>clustertasks</title>
+<polygon fill="none" stroke="#000000" points="8,-8 8,-1261.1977 1468,-1261.1977 1468,-8 8,-8"/>
+<text text-anchor="middle" x="738" y="-1233.1977" font-family="Times,serif" font-size="30.00" fill="#ff3232">Pipeline:</text>
+</g>
+<!-- t0 -->
+<g id="node1" class="node">
+<title>t0</title>
+<polygon fill="#efa03b" stroke="#000000" points="1215.7053,-1215.1977 1006.2947,-1215.1977 1002.2947,-1211.1977 1002.2947,-1179.1977 1211.7053,-1179.1977 1215.7053,-1183.1977 1215.7053,-1215.1977"/>
+<polyline fill="none" stroke="#000000" points="1211.7053,-1211.1977 1002.2947,-1211.1977 "/>
+<polyline fill="none" stroke="#000000" points="1211.7053,-1211.1977 1211.7053,-1179.1977 "/>
+<polyline fill="none" stroke="#000000" points="1211.7053,-1211.1977 1215.7053,-1215.1977 "/>
+<text text-anchor="middle" x="1109" y="-1191.1977" font-family="Times,serif" font-size="20.00" fill="#000000">ocrmypdf.pipeline.triage</text>
+</g>
+<!-- t1 -->
+<g id="node2" class="node">
+<title>t1</title>
+<polygon fill="#efa03b" stroke="#000000" points="1280.0433,-1157.1977 941.9567,-1157.1977 937.9567,-1153.1977 937.9567,-1121.1977 1276.0433,-1121.1977 1280.0433,-1125.1977 1280.0433,-1157.1977"/>
+<polyline fill="none" stroke="#000000" points="1276.0433,-1153.1977 937.9567,-1153.1977 "/>
+<polyline fill="none" stroke="#000000" points="1276.0433,-1153.1977 1276.0433,-1121.1977 "/>
+<polyline fill="none" stroke="#000000" points="1276.0433,-1153.1977 1280.0433,-1157.1977 "/>
+<text text-anchor="middle" x="1109" y="-1133.1977" font-family="Times,serif" font-size="20.00" fill="#000000">ocrmypdf.pipeline.repair_and_parse_pdf</text>
+</g>
+<!-- t0&#45;&gt;t1 -->
+<g id="edge1" class="edge">
+<title>t0&#45;&gt;t1</title>
+<path fill="none" stroke="#0044a0" d="M1109,-1179.1641C1109,-1175.4895 1109,-1171.5395 1109,-1167.604"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="1112.5001,-1167.4199 1109,-1157.4199 1105.5001,-1167.42 1112.5001,-1167.4199"/>
+</g>
+<!-- t2 -->
+<g id="node3" class="node">
+<title>t2</title>
+<polygon fill="#efa03b" stroke="#000000" points="1030.0926,-1078.2732 785,-1095.1731 539.9074,-1078.2732 540.1362,-1050.9285 1029.8638,-1050.9285 1030.0926,-1078.2732"/>
+<polygon fill="none" stroke="#000000" points="1034.1249,-1082.0021 785,-1099.1801 535.8751,-1082.0021 536.1685,-1046.931 1033.8315,-1046.931 1034.1249,-1082.0021"/>
+<text text-anchor="middle" x="785" y="-1064.7153" font-family="Times,serif" font-size="20.00" fill="#000000">ocrmypdf.pipeline.marker_pages</text>
+</g>
+<!-- t1&#45;&gt;t2 -->
+<g id="edge2" class="edge">
+<title>t1&#45;&gt;t2</title>
+<path fill="none" stroke="#0044a0" d="M1023.449,-1121.1152C984.5695,-1112.8974 938.0675,-1103.0685 896.4957,-1094.2816"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="897.1066,-1090.8335 886.5989,-1092.1898 895.6589,-1097.6822 897.1066,-1090.8335"/>
+</g>
+<!-- t16 -->
+<g id="node17" class="node">
+<title>t16</title>
+<polygon fill="#00cc66" stroke="#000000" points="1215.5059,-328.1861 942.4941,-328.1861 938.4941,-324.1861 938.4941,-292.1861 1211.5059,-292.1861 1215.5059,-296.1861 1215.5059,-328.1861"/>
+<polyline fill="none" stroke="#000000" points="1211.5059,-324.1861 938.4941,-324.1861 "/>
+<polyline fill="none" stroke="#000000" points="1211.5059,-324.1861 1211.5059,-292.1861 "/>
+<polyline fill="none" stroke="#000000" points="1211.5059,-324.1861 1215.5059,-328.1861 "/>
+<text text-anchor="middle" x="1077" y="-304.1861" font-family="Times,serif" font-size="20.00" fill="#000000">ocrmypdf.pipeline.weave_layers</text>
+</g>
+<!-- t1&#45;&gt;t16 -->
+<g id="edge24" class="edge">
+<title>t1&#45;&gt;t16</title>
+<path fill="none" stroke="#0044a0" d="M1097.2373,-1120.9576C1077.987,-1088.7184 1043.7317,-1019.7372 1063,-963.2656 1106.87,-834.6914 1482.8098,-573.3183 1409,-459.2656 1362.7595,-387.8137 1273.2613,-350.2799 1198.8305,-330.7528"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="1199.4555,-327.3005 1188.9015,-328.2301 1197.7316,-334.0849 1199.4555,-327.3005"/>
+</g>
+<!-- t17 -->
+<g id="node18" class="node">
+<title>t17</title>
+<polygon fill="#efa03b" stroke="#000000" points="1439.5156,-1009.7492 1076.4844,-1009.7492 1072.4844,-1005.7492 1072.4844,-973.7492 1435.5156,-973.7492 1439.5156,-977.7492 1439.5156,-1009.7492"/>
+<polyline fill="none" stroke="#000000" points="1435.5156,-1005.7492 1072.4844,-1005.7492 "/>
+<polyline fill="none" stroke="#000000" points="1435.5156,-1005.7492 1435.5156,-973.7492 "/>
+<polyline fill="none" stroke="#000000" points="1435.5156,-1005.7492 1439.5156,-1009.7492 "/>
+<text text-anchor="middle" x="1256" y="-985.7492" font-family="Times,serif" font-size="20.00" fill="#000000">ocrmypdf.pipeline.generate_postscript_stub</text>
+</g>
+<!-- t1&#45;&gt;t17 -->
+<g id="edge25" class="edge">
+<title>t1&#45;&gt;t17</title>
+<path fill="none" stroke="#0044a0" d="M1127.0251,-1121.1176C1153.0342,-1095.0292 1201.2007,-1046.7157 1230.7429,-1017.0834"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="1233.2458,-1019.5302 1237.8275,-1009.9772 1228.2885,-1014.5879 1233.2458,-1019.5302"/>
+</g>
+<!-- t18 -->
+<g id="node19" class="node">
+<title>t18</title>
+<polygon fill="#efa03b" stroke="#000000" points="1070.189,-214.4288 1263,-187.1099 1455.811,-214.4288 1455.631,-258.6317 1070.369,-258.6317 1070.189,-214.4288"/>
+<polygon fill="none" stroke="#000000" points="1066.1715,-210.9543 1263,-183.0662 1459.8285,-210.9543 1459.6181,-262.6353 1066.3819,-262.6353 1066.1715,-210.9543"/>
+<text text-anchor="middle" x="1263" y="-220.6461" font-family="Times,serif" font-size="20.00" fill="#000000">ocrmypdf.pipeline.metadata_fixup</text>
+</g>
+<!-- t1&#45;&gt;t18 -->
+<g id="edge28" class="edge">
+<title>t1&#45;&gt;t18</title>
+<path fill="none" stroke="#0044a0" d="M1241.1115,-1121.1192C1311.0076,-1105.2558 1393.5851,-1075.5895 1449,-1020.2329 1458.4922,-1010.7507 1459,-1005.1661 1459,-991.7492 1459,-991.7492 1459,-991.7492 1459,-393.7258 1459,-341.9727 1441.8377,-325.2216 1402,-292.1861 1390.9869,-283.0534 1378.4885,-274.871 1365.6104,-267.6415"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="1367.1079,-264.4723 1356.6476,-262.7888 1363.775,-270.6279 1367.1079,-264.4723"/>
+</g>
+<!-- t3 -->
+<g id="node4" class="node">
+<title>t3</title>
+<polygon fill="#efa03b" stroke="#000000" points="1015.5194,-999.3074 785,-1016.2081 554.4806,-999.3074 554.6958,-971.9616 1015.3042,-971.9616 1015.5194,-999.3074"/>
+<polygon fill="none" stroke="#000000" points="1019.5491,-1003.0204 785,-1020.2165 550.4509,-1003.0204 550.7267,-967.9639 1019.2733,-967.9639 1019.5491,-1003.0204"/>
+<text text-anchor="middle" x="785" y="-985.7492" font-family="Times,serif" font-size="20.00" fill="#000000">ocrmypdf.pipeline.ocr_or_skip</text>
+</g>
+<!-- t2&#45;&gt;t3 -->
+<g id="edge3" class="edge">
+<title>t2&#45;&gt;t3</title>
+<path fill="none" stroke="#0044a0" d="M785,-1046.5938C785,-1041.5635 785,-1036.139 785,-1030.7273"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="788.5001,-1030.4427 785,-1020.4427 781.5001,-1030.4428 788.5001,-1030.4427"/>
+</g>
+<!-- t4 -->
+<g id="node5" class="node">
+<title>t4</title>
+<polygon fill="#efa03b" stroke="#000000" points="889.3166,-941.2656 582.6834,-941.2656 578.6834,-937.2656 578.6834,-905.2656 885.3166,-905.2656 889.3166,-909.2656 889.3166,-941.2656"/>
+<polyline fill="none" stroke="#000000" points="885.3166,-937.2656 578.6834,-937.2656 "/>
+<polyline fill="none" stroke="#000000" points="885.3166,-937.2656 885.3166,-905.2656 "/>
+<polyline fill="none" stroke="#000000" points="885.3166,-937.2656 889.3166,-941.2656 "/>
+<text text-anchor="middle" x="734" y="-917.2656" font-family="Times,serif" font-size="20.00" fill="#000000">ocrmypdf.pipeline.rasterize_preview</text>
+</g>
+<!-- t3&#45;&gt;t4 -->
+<g id="edge4" class="edge">
+<title>t3&#45;&gt;t4</title>
+<path fill="none" stroke="#0044a0" d="M767.1627,-967.797C762.8396,-961.9919 758.1927,-955.7519 753.7858,-949.8343"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="756.3465,-947.4129 747.5666,-941.483 750.7323,-951.5939 756.3465,-947.4129"/>
+</g>
+<!-- t5 -->
+<g id="node6" class="node">
+<title>t5</title>
+<polygon fill="#efa03b" stroke="#000000" points="1028.0824,-883.2656 769.9176,-883.2656 765.9176,-879.2656 765.9176,-847.2656 1024.0824,-847.2656 1028.0824,-851.2656 1028.0824,-883.2656"/>
+<polyline fill="none" stroke="#000000" points="1024.0824,-879.2656 765.9176,-879.2656 "/>
+<polyline fill="none" stroke="#000000" points="1024.0824,-879.2656 1024.0824,-847.2656 "/>
+<polyline fill="none" stroke="#000000" points="1024.0824,-879.2656 1028.0824,-883.2656 "/>
+<text text-anchor="middle" x="897" y="-859.2656" font-family="Times,serif" font-size="20.00" fill="#000000">ocrmypdf.pipeline.orient_page</text>
+</g>
+<!-- t3&#45;&gt;t5 -->
+<g id="edge6" class="edge">
+<title>t3&#45;&gt;t5</title>
+<path fill="none" stroke="#0044a0" d="M869.1177,-967.8063C880.553,-961.0264 890.81,-952.3527 898,-941.2656 907.042,-927.3226 906.9457,-908.7053 904.5139,-893.387"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="907.914,-892.5383 902.5408,-883.4071 901.0469,-893.8961 907.914,-892.5383"/>
+</g>
+<!-- t4&#45;&gt;t5 -->
+<g id="edge5" class="edge">
+<title>t4&#45;&gt;t5</title>
+<path fill="none" stroke="#0044a0" d="M784.6807,-905.2319C801.0865,-899.3943 819.4462,-892.8614 836.4913,-886.7963"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="838.1026,-889.938 846.3506,-883.288 835.7559,-883.343 838.1026,-889.938"/>
+</g>
+<!-- t6 -->
+<g id="node7" class="node">
+<title>t6</title>
+<polygon fill="#efa03b" stroke="#000000" points="1064.7325,-825.2656 689.2675,-825.2656 685.2675,-821.2656 685.2675,-789.2656 1060.7325,-789.2656 1064.7325,-793.2656 1064.7325,-825.2656"/>
+<polyline fill="none" stroke="#000000" points="1060.7325,-821.2656 685.2675,-821.2656 "/>
+<polyline fill="none" stroke="#000000" points="1060.7325,-821.2656 1060.7325,-789.2656 "/>
+<polyline fill="none" stroke="#000000" points="1060.7325,-821.2656 1064.7325,-825.2656 "/>
+<text text-anchor="middle" x="875" y="-801.2656" font-family="Times,serif" font-size="20.00" fill="#000000">ocrmypdf.pipeline.rasterize_with_ghostscript</text>
+</g>
+<!-- t5&#45;&gt;t6 -->
+<g id="edge7" class="edge">
+<title>t5&#45;&gt;t6</title>
+<path fill="none" stroke="#0044a0" d="M890.1597,-847.2319C888.6839,-843.3412 887.0909,-839.1417 885.5115,-834.9776"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="888.731,-833.5965 881.9119,-825.4878 882.186,-836.0791 888.731,-833.5965"/>
+</g>
+<!-- t13 -->
+<g id="node16" class="node">
+<title>t13</title>
+<polygon fill="#00cc66" stroke="#000000" points="1077,-515.2656 754.4141,-487.2656 1077,-459.2656 1399.5859,-487.2656 1077,-515.2656"/>
+<text text-anchor="middle" x="1077" y="-481.2656" font-family="Times,serif" font-size="20.00" fill="#000000">ocrmypdf.pipeline.select_image_layer</text>
+</g>
+<!-- t5&#45;&gt;t13 -->
+<g id="edge20" class="edge">
+<title>t5&#45;&gt;t13</title>
+<path fill="none" stroke="#0044a0" d="M1000.2704,-847.241C1031.2359,-840.6873 1060.5415,-832.9862 1074,-825.2656 1114.0954,-802.2644 1145,-795.4899 1145,-749.2656 1145,-749.2656 1145,-749.2656 1145,-633.2656 1145,-590.368 1154.8687,-575.2844 1135,-537.2656 1131.571,-530.7041 1126.8893,-524.6314 1121.6622,-519.1451"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="1123.8989,-516.4405 1114.2626,-512.0367 1119.0494,-521.4885 1123.8989,-516.4405"/>
+</g>
+<!-- t7 -->
+<g id="node8" class="node">
+<title>t7</title>
+<polygon fill="#efa03b" stroke="#000000" points="856.0801,-767.2656 431.9199,-767.2656 427.9199,-763.2656 427.9199,-731.2656 852.0801,-731.2656 856.0801,-735.2656 856.0801,-767.2656"/>
+<polyline fill="none" stroke="#000000" points="852.0801,-763.2656 427.9199,-763.2656 "/>
+<polyline fill="none" stroke="#000000" points="852.0801,-763.2656 852.0801,-731.2656 "/>
+<polyline fill="none" stroke="#000000" points="852.0801,-763.2656 856.0801,-767.2656 "/>
+<text text-anchor="middle" x="642" y="-743.2656" font-family="Times,serif" font-size="20.00" fill="#000000">ocrmypdf.pipeline.preprocess_remove_background</text>
+</g>
+<!-- t6&#45;&gt;t7 -->
+<g id="edge8" class="edge">
+<title>t6&#45;&gt;t7</title>
+<path fill="none" stroke="#0044a0" d="M802.5546,-789.2319C777.7884,-783.067 749.9071,-776.1266 724.4138,-769.7806"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="724.95,-766.3073 714.4006,-767.288 723.259,-773.1 724.95,-766.3073"/>
+</g>
+<!-- t12 -->
+<g id="node15" class="node">
+<title>t12</title>
+<polygon fill="#efa03b" stroke="#000000" points="742,-593.2656 358.1874,-565.2656 742,-537.2656 1125.8126,-565.2656 742,-593.2656"/>
+<text text-anchor="middle" x="742" y="-559.2656" font-family="Times,serif" font-size="20.00" fill="#000000">ocrmypdf.pipeline.select_visible_page_image</text>
+</g>
+<!-- t6&#45;&gt;t12 -->
+<g id="edge18" class="edge">
+<title>t6&#45;&gt;t12</title>
+<path fill="none" stroke="#0044a0" d="M875.1443,-789.1129C874.6867,-773.2956 872.5831,-750.0189 865,-731.2656 844.2991,-680.0716 804.0126,-630.4165 775.1838,-598.9641"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="777.4937,-596.3085 768.1202,-591.3701 772.3682,-601.076 777.4937,-596.3085"/>
+</g>
+<!-- t8 -->
+<g id="node9" class="node">
+<title>t8</title>
+<polygon fill="#efa03b" stroke="#000000" points="732.6759,-709.2656 413.3241,-709.2656 409.3241,-705.2656 409.3241,-673.2656 728.6759,-673.2656 732.6759,-677.2656 732.6759,-709.2656"/>
+<polyline fill="none" stroke="#000000" points="728.6759,-705.2656 409.3241,-705.2656 "/>
+<polyline fill="none" stroke="#000000" points="728.6759,-705.2656 728.6759,-673.2656 "/>
+<polyline fill="none" stroke="#000000" points="728.6759,-705.2656 732.6759,-709.2656 "/>
+<text text-anchor="middle" x="571" y="-685.2656" font-family="Times,serif" font-size="20.00" fill="#000000">ocrmypdf.pipeline.preprocess_deskew</text>
+</g>
+<!-- t7&#45;&gt;t8 -->
+<g id="edge9" class="edge">
+<title>t7&#45;&gt;t8</title>
+<path fill="none" stroke="#0044a0" d="M619.9243,-731.2319C613.9709,-726.3685 607.4267,-721.0226 601.115,-715.8666"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="603.2653,-713.1037 593.3065,-709.4878 598.8367,-718.5248 603.2653,-713.1037"/>
+</g>
+<!-- t7&#45;&gt;t12 -->
+<g id="edge17" class="edge">
+<title>t7&#45;&gt;t12</title>
+<path fill="none" stroke="#0044a0" d="M717.0346,-731.1646C726.8757,-725.6884 735.7103,-718.5557 742,-709.2656 763.0291,-678.205 759.4083,-634.0888 752.8082,-602.8898"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="756.1481,-601.7976 750.487,-592.842 749.3278,-603.3733 756.1481,-601.7976"/>
+</g>
+<!-- t9 -->
+<g id="node10" class="node">
+<title>t9</title>
+<polygon fill="#efa03b" stroke="#000000" points="712.8828,-651.2656 411.1172,-651.2656 407.1172,-647.2656 407.1172,-615.2656 708.8828,-615.2656 712.8828,-619.2656 712.8828,-651.2656"/>
+<polyline fill="none" stroke="#000000" points="708.8828,-647.2656 407.1172,-647.2656 "/>
+<polyline fill="none" stroke="#000000" points="708.8828,-647.2656 708.8828,-615.2656 "/>
+<polyline fill="none" stroke="#000000" points="708.8828,-647.2656 712.8828,-651.2656 "/>
+<text text-anchor="middle" x="560" y="-627.2656" font-family="Times,serif" font-size="20.00" fill="#000000">ocrmypdf.pipeline.preprocess_clean</text>
+</g>
+<!-- t8&#45;&gt;t9 -->
+<g id="edge10" class="edge">
+<title>t8&#45;&gt;t9</title>
+<path fill="none" stroke="#0044a0" d="M567.5798,-673.2319C566.8624,-669.4493 566.0897,-665.3747 565.3216,-661.3247"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="568.7581,-660.6605 563.4559,-651.4878 561.8807,-661.9649 568.7581,-660.6605"/>
+</g>
+<!-- t8&#45;&gt;t12 -->
+<g id="edge16" class="edge">
+<title>t8&#45;&gt;t12</title>
+<path fill="none" stroke="#0044a0" d="M670.0045,-673.2618C693.2528,-667.2338 713.6919,-659.8307 722,-651.2656 734.1971,-638.6912 739.4901,-620.2051 741.6123,-603.5914"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="745.1041,-603.8427 742.5574,-593.5585 738.1349,-603.1862 745.1041,-603.8427"/>
+</g>
+<!-- t10 -->
+<g id="node11" class="node">
+<title>t10</title>
+<polygon fill="#efa03b" stroke="#000000" points="340.1094,-583.2656 35.8906,-583.2656 31.8906,-579.2656 31.8906,-547.2656 336.1094,-547.2656 340.1094,-551.2656 340.1094,-583.2656"/>
+<polyline fill="none" stroke="#000000" points="336.1094,-579.2656 31.8906,-579.2656 "/>
+<polyline fill="none" stroke="#000000" points="336.1094,-579.2656 336.1094,-547.2656 "/>
+<polyline fill="none" stroke="#000000" points="336.1094,-579.2656 340.1094,-583.2656 "/>
+<text text-anchor="middle" x="186" y="-559.2656" font-family="Times,serif" font-size="20.00" fill="#000000">ocrmypdf.pipeline.select_ocr_image</text>
+</g>
+<!-- t9&#45;&gt;t10 -->
+<g id="edge11" class="edge">
+<title>t9&#45;&gt;t10</title>
+<path fill="none" stroke="#0044a0" d="M460.7568,-615.2213C409.7279,-605.9434 347.4237,-594.6153 295.0537,-585.0935"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="295.5223,-581.6214 285.0575,-583.276 294.2701,-588.5085 295.5223,-581.6214"/>
+</g>
+<!-- t9&#45;&gt;t12 -->
+<g id="edge15" class="edge">
+<title>t9&#45;&gt;t12</title>
+<path fill="none" stroke="#0044a0" d="M608.2948,-615.2213C627.0226,-608.2242 648.8712,-600.0609 669.4134,-592.3859"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="670.9148,-595.5613 679.0573,-588.7826 668.4648,-589.004 670.9148,-595.5613"/>
+</g>
+<!-- t11 -->
+<g id="node12" class="node">
+<title>t11</title>
+<polygon fill="#00cc66" stroke="#000000" points="334.0996,-505.2656 19.9004,-505.2656 15.9004,-501.2656 15.9004,-469.2656 330.0996,-469.2656 334.0996,-473.2656 334.0996,-505.2656"/>
+<polyline fill="none" stroke="#000000" points="330.0996,-501.2656 15.9004,-501.2656 "/>
+<polyline fill="none" stroke="#000000" points="330.0996,-501.2656 330.0996,-469.2656 "/>
+<polyline fill="none" stroke="#000000" points="330.0996,-501.2656 334.0996,-505.2656 "/>
+<text text-anchor="middle" x="175" y="-481.2656" font-family="Times,serif" font-size="20.00" fill="#000000">ocrmypdf.pipeline.ocr_tesseract_hocr</text>
+</g>
+<!-- t10&#45;&gt;t11 -->
+<g id="edge12" class="edge">
+<title>t10&#45;&gt;t11</title>
+<path fill="none" stroke="#0044a0" d="M183.4487,-547.1748C182.1254,-537.7914 180.4788,-526.1154 178.9917,-515.5701"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="182.4378,-514.9417 177.5755,-505.5285 175.5064,-515.9193 182.4378,-514.9417"/>
+</g>
+<!-- t15 -->
+<g id="node14" class="node">
+<title>t15</title>
+<polygon fill="#ff69b4" stroke="#000000" points="736.2696,-505.2656 355.7304,-505.2656 351.7304,-501.2656 351.7304,-469.2656 732.2696,-469.2656 736.2696,-473.2656 736.2696,-505.2656"/>
+<polyline fill="none" stroke="#000000" points="732.2696,-501.2656 351.7304,-501.2656 "/>
+<polyline fill="none" stroke="#000000" points="732.2696,-501.2656 732.2696,-469.2656 "/>
+<polyline fill="none" stroke="#000000" points="732.2696,-501.2656 736.2696,-505.2656 "/>
+<text text-anchor="middle" x="544" y="-481.2656" font-family="Times,serif" font-size="20.00" fill="#000000">ocrmypdf.pipeline.ocr_tesseract_textonly_pdf</text>
+</g>
+<!-- t10&#45;&gt;t15 -->
+<g id="edge14" class="edge">
+<title>t10&#45;&gt;t15</title>
+<path fill="none" stroke="#0044a0" d="M269.0322,-547.1748C323.4947,-535.3086 394.7854,-519.776 451.1284,-507.5002"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="452.0829,-510.8744 461.1086,-505.3257 450.5927,-504.0348 452.0829,-510.8744"/>
+</g>
+<!-- t14 -->
+<g id="node13" class="node">
+<title>t14</title>
+<polygon fill="#00cc66" stroke="#000000" points="330.0433,-411.7258 21.9567,-411.7258 17.9567,-407.7258 17.9567,-375.7258 326.0433,-375.7258 330.0433,-379.7258 330.0433,-411.7258"/>
+<polyline fill="none" stroke="#000000" points="326.0433,-407.7258 17.9567,-407.7258 "/>
+<polyline fill="none" stroke="#000000" points="326.0433,-407.7258 326.0433,-375.7258 "/>
+<polyline fill="none" stroke="#000000" points="326.0433,-407.7258 330.0433,-411.7258 "/>
+<text text-anchor="middle" x="174" y="-387.7258" font-family="Times,serif" font-size="20.00" fill="#000000">ocrmypdf.pipeline.render_hocr_page</text>
+</g>
+<!-- t11&#45;&gt;t14 -->
+<g id="edge13" class="edge">
+<title>t11&#45;&gt;t14</title>
+<path fill="none" stroke="#0044a0" d="M174.8072,-469.2302C174.6642,-455.8584 174.4666,-437.3702 174.3027,-422.0357"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="177.8024,-421.987 174.1956,-412.025 170.8028,-422.0619 177.8024,-421.987"/>
+</g>
+<!-- t19 -->
+<g id="node22" class="node">
+<title>t19</title>
+<polygon fill="#efa03b" stroke="#000000" points="351.7205,-381.5085 545,-354.1897 738.2795,-381.5085 738.0991,-425.7112 351.9009,-425.7112 351.7205,-381.5085"/>
+<polygon fill="none" stroke="#000000" points="347.7033,-378.0329 545,-350.1463 742.2967,-378.0329 742.0858,-429.7148 347.9142,-429.7148 347.7033,-378.0329"/>
+<text text-anchor="middle" x="545" y="-387.7258" font-family="Times,serif" font-size="20.00" fill="#000000">ocrmypdf.pipeline.merge_sidecars</text>
+</g>
+<!-- t11&#45;&gt;t19 -->
+<g id="edge32" class="edge">
+<title>t11&#45;&gt;t19</title>
+<path fill="none" stroke="#0044a0" d="M246.3397,-469.2302C287.966,-458.7066 342.1269,-445.0142 392.8772,-432.184"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="393.8058,-435.5594 402.6429,-429.7151 392.0901,-428.773 393.8058,-435.5594"/>
+</g>
+<!-- t14&#45;&gt;t16 -->
+<g id="edge22" class="edge">
+<title>t14&#45;&gt;t16</title>
+<path fill="none" stroke="#0044a0" d="M230.6615,-375.7128C262.2207,-366.4581 302.4172,-355.9425 339,-350.1861 448.3957,-332.9725 745.7869,-320.7866 927.9215,-314.6743"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="928.248,-318.1655 938.1258,-314.3342 928.0148,-311.1693 928.248,-318.1655"/>
+</g>
+<!-- t15&#45;&gt;t16 -->
+<g id="edge21" class="edge">
+<title>t15&#45;&gt;t16</title>
+<path fill="none" stroke="#0044a0" d="M630.0636,-469.2083C667.5329,-460.6467 711.76,-449.5912 751,-437.2656 850.4985,-406.0121 963.1653,-359.5222 1026.586,-332.2894"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="1028.1566,-335.4238 1035.9553,-328.2523 1025.3866,-328.9951 1028.1566,-335.4238"/>
+</g>
+<!-- t15&#45;&gt;t19 -->
+<g id="edge31" class="edge">
+<title>t15&#45;&gt;t19</title>
+<path fill="none" stroke="#0044a0" d="M544.1928,-469.2302C544.2822,-460.8687 544.393,-450.5066 544.5035,-440.166"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="548.006,-439.9443 544.6132,-429.9075 541.0064,-439.8694 548.006,-439.9443"/>
+</g>
+<!-- t12&#45;&gt;t13 -->
+<g id="edge19" class="edge">
+<title>t12&#45;&gt;t13</title>
+<path fill="none" stroke="#0044a0" d="M833.9833,-543.8486C879.0975,-533.3444 933.4556,-520.6879 979.3116,-510.0109"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="980.3156,-513.3709 989.2614,-507.6943 978.7282,-506.5532 980.3156,-513.3709"/>
+</g>
+<!-- t13&#45;&gt;t16 -->
+<g id="edge23" class="edge">
+<title>t13&#45;&gt;t16</title>
+<path fill="none" stroke="#0044a0" d="M1077,-459.2068C1077,-426.2624 1077,-371.9187 1077,-338.7552"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="1080.5001,-338.3818 1077,-328.3819 1073.5001,-338.3819 1080.5001,-338.3818"/>
+</g>
+<!-- t16&#45;&gt;t18 -->
+<g id="edge27" class="edge">
+<title>t16&#45;&gt;t18</title>
+<path fill="none" stroke="#0044a0" d="M1117.3592,-292.0592C1133.8695,-284.6437 1153.6803,-275.7459 1173.2953,-266.9361"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="1174.8979,-270.0531 1182.586,-262.7632 1172.0299,-263.6676 1174.8979,-270.0531"/>
+</g>
+<!-- t17&#45;&gt;t18 -->
+<g id="edge26" class="edge">
+<title>t17&#45;&gt;t18</title>
+<path fill="none" stroke="#0044a0" d="M1326.2292,-973.7283C1377.8362,-955.768 1439,-922.4247 1439,-865.2656 1439,-865.2656 1439,-865.2656 1439,-393.7258 1439,-338.7092 1393.2056,-296.3464 1348.3356,-268.0433"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="1350.0403,-264.9831 1339.6842,-262.7465 1346.3852,-270.9531 1350.0403,-264.9831"/>
+</g>
+<!-- t20 -->
+<g id="node20" class="node">
+<title>t20</title>
+<polygon fill="#efa03b" stroke="#000000" points="1400.3184,-161.1062 1129.6816,-161.1062 1125.6816,-157.1062 1125.6816,-125.1062 1396.3184,-125.1062 1400.3184,-129.1062 1400.3184,-161.1062"/>
+<polyline fill="none" stroke="#000000" points="1396.3184,-157.1062 1125.6816,-157.1062 "/>
+<polyline fill="none" stroke="#000000" points="1396.3184,-157.1062 1396.3184,-125.1062 "/>
+<polyline fill="none" stroke="#000000" points="1396.3184,-157.1062 1400.3184,-161.1062 "/>
+<text text-anchor="middle" x="1263" y="-137.1062" font-family="Times,serif" font-size="20.00" fill="#000000">ocrmypdf.pipeline.optimize_pdf</text>
+</g>
+<!-- t18&#45;&gt;t20 -->
+<g id="edge29" class="edge">
+<title>t18&#45;&gt;t20</title>
+<path fill="none" stroke="#0044a0" d="M1263,-182.9188C1263,-179.129 1263,-175.3607 1263,-171.739"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="1266.5001,-171.4394 1263,-161.4394 1259.5001,-171.4394 1266.5001,-171.4394"/>
+</g>
+<!-- t21 -->
+<g id="node21" class="node">
+<title>t21</title>
+<polygon fill="#efa03b" stroke="#000000" points="1096.0652,-47.332 1263,-20.0049 1429.9348,-47.332 1429.779,-91.5483 1096.221,-91.5483 1096.0652,-47.332"/>
+<polygon fill="none" stroke="#000000" points="1092.0538,-43.9306 1263,-15.9468 1433.9462,-43.9306 1433.7643,-95.5532 1092.2357,-95.5532 1092.0538,-43.9306"/>
+<text text-anchor="middle" x="1263" y="-53.5531" font-family="Times,serif" font-size="20.00" fill="#000000">ocrmypdf.pipeline.copy_final</text>
+</g>
+<!-- t20&#45;&gt;t21 -->
+<g id="edge30" class="edge">
+<title>t20&#45;&gt;t21</title>
+<path fill="none" stroke="#0044a0" d="M1263,-124.9764C1263,-119.37 1263,-112.9163 1263,-106.2938"/>
+<polygon fill="#0044a0" stroke="#0044a0" points="1266.5001,-105.8456 1263,-95.8457 1259.5001,-105.8457 1266.5001,-105.8456"/>
+</g>
+</g>
+</svg>

docs/release_notes.rst

@@ -0,0 +1,864 @@
+Release notes
+=============
+
+OCRmyPDF uses `semantic versioning <http://semver.org/>`_ for its command line interface.
+
+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.
+
+.. Issue regex
+   find:    [^`]\#([0-9]{1,3})[^0-9]
+   replace: `#$1 <https://github.com/jbarlow83/OCRmyPDF/issues/$1>`_
+
+
+v7
+--
+
+-   The core algorithm for combining OCR layers with existing PDF pages has been rewritten and improved considerably.  It works directly with the input file to minimize changes.  The new algorithm uses less temporary disk space and eliminates cost object duplication and deduplication that used to be a requirement.
+
+-   New feature: PDF optimization with ``-O`` or ``--optimize``.  After OCR, OCRmyPDF will automatically performs image optimizations relevant to OCR PDFs.
+
+    +   If a JBIG2 encoder is available, then monochrome images will be converted, with the potential for huge savings on large black and white files, since JBIG2 is far more efficient than any other monochrome format. (All known US patents related to JBIG2 have probably expired, but it remains the responsibility of the user to supply a JBIG2 encoder such as `jbig2enc <https://github.com/agl/jbig2enc>`_. OCRmyPDF does not contain any portion of JBIG2.)
+
+    +   If ``pngquant`` is installed, OCRmyPDF will use to perform lossy compression of PNG images.
+
+    +   The quality of JPEGs can also be lowered, on the assumption that a lower quality image may be suitable for storage after OCR.
+
+    +   It is likely this component will be offered as a separate command line utility.
+
+-   New dependency: `pikepdf <https://github.com/pikepdf>`_. pikepdf is a  powerful new Python PDF library driving the latest OCRmyPDF features, built on the proven and mature libqpdf C++ library.
+
+-   Small amounts of text in the margins of a page, such as watermarks, page numbers, or digital stamps, will no longer prevent the rest of a page from being OCRed when ``--skip-text`` is issued. This behavior is based on a heuristic.
+
+-   Removed features
+
+    +   The deprecated ``tesseract`` PDF renderer was removed, because due to changes in how we construct PDFs.
+
+    +   ``-g``, the option to generate debug text pages, was removed because the extra pages it generates were too much of a maintenance burden and it never worked with the ``sandwich`` renderer (Tesseract) anyway. HOCR pages can still be previewed by running the hocrtransform.py with appropriate settings.
+
+-   The ``sandwich`` PDF renderer can be used with all supported versions of Tesseract, including that those priority to v3.05 which don't support ``-c textonly``
+
+-   ``--pdf-renderer auto`` and the diagnostics regarding the selection of PDF renderer are now more consistent.
+
+
+v6.2.0
+------
+
+-   **Docker**: The Docker image ``ocrmypdf-tess4`` has been removed. The main Docker images, ``ocrmypdf`` and ``ocrmypdf-polyglot`` now use Ubuntu 18.04 as a base image, and as such Tesseract 4.0.0-beta1 is now the Tesseract version they use. There is no Docker image based on Tesseract 3.05 anymore.
+
+-   Creation of PDF/A-3 is now supported. However, there is no ability to attach files to PDF/A-3.
+
+-   List more reasons why the file size might grow.
+
+-   Fix issue `#262 <https://github.com/ppjbarlow83/OCRmyPDF/issues/262>`_, ``--remove-background`` error on PDFs contained colormapped (paletted) images.
+
+-   Fix another XMP metadata validation issue, in cases where the input file's creation date has no timezone and the creation date is not overridden.
+
+
+v6.1.5
+------
+
+-   Fix issue `#253 <https://github.com/jbarlow83/OCRmyPDF/issues/253>`_, a possible division by zero when using the ``hocr`` renderer.
+
+-   Fix incorrectly formatted ``<xmp:ModifyDate>`` field inside XMP metadata for PDF/As.  veraPDF flags this as a PDF/A validation failure. The error is caused the timezone and final digit of the seconds of modified time to be omitted, so at worst the modification time stamp is rounded to the nearest 10 seconds.
+
+
+v6.1.4
+------
+
+-   Fix issue `#248 <https://github.com/jbarlow83/OCRmyPDF/issues/248>`_ ``--clean`` argument may remove OCR from left column of text on certain documents. We now set ``--layout none`` to suppress this.
+
+-   The test cache was updated to reflect the change above.
+
+-   Change test suite to accommodate Ghostscript 9.23's new ability to insert JPEGs into PDFs without transcoding.
+
+-   XMP metadata in PDFs is now examined using ``defusedxml`` for safety.
+
+-   If an external process exits with a signal when asked to report its version, we now print the system error message instead of suppressing it.  This occurred when the required executable was found but was missing a shared library.
+
+-   qpdf 7.0.0 or newer is now required as the test suite can no longer pass without it.
+
+Notes
+~~~~~
+
+-   An apparent `regression in Ghostscript 9.23 <https://bugs.ghostscript.com/show_bug.cgi?id=699216>`_ will cause some ocrmypdf output files to become invalid in rare cases; the workaround for the moment is to set ``--force-ocr``.
+
+
+v6.1.3
+------
+
+-   Fix issue `#247 <https://github.com/jbarlow83/OCRmyPDF/issues/247>`_, ``/CreationDate`` metadata not copied from input to output.
+
+-   A warning is now issued when Python 3.5 is used on files with a large page count, as this case is known to regress to single core performance. The cause of this problem is unknown.
+
+
+v6.1.2
+------
+
+-   Upgrade to PyMuPDF v1.12.5 which includes a more complete fix to `#239 <https://github.com/jbarlow83/OCRmyPDF/issues/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 <https://github.com/jbarlow83/OCRmyPDF/issues/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 <https://github.com/jbarlow83/OCRmyPDF/issues/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 <https://github.com/jbarlow83/OCRmyPDF/issues/233>`_, `#232 <https://github.com/jbarlow83/OCRmyPDF/issues/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 <https://github.com/jbarlow83/OCRmyPDF/issues/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 <https://github.com/jbarlow83/OCRmyPDF/issues/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 <https://github.com/jbarlow83/OCRmyPDF/issues/217>`_)
+
+
+v5.7.0
+------
+
+-   Fixed an issue that caused poor CPU utilization on machines more than 4 cores when running Tesseract 4. (Related to issue `#217 <https://github.com/jbarlow83/OCRmyPDF/issues/217>`_.)
+
+-   The 'hocr' renderer has been improved. The 'sandwich' and 'tesseract' renderers are still better for most use cases, but 'hocr' may be useful for people who work with the PDF.js renderer in English/ASCII languages. (`#225 <https://github.com/jbarlow83/OCRmyPDF/issues/225>`_)
+
+    + It now formats text in a matter that is easier for certain PDF viewers to select and extract copy and paste text. This should help macOS Preview and PDF.js in particular.
+    + The appearance of selected text and behavior of selecting text is improved.
+    + The PDF content stream now uses relative moves, making it more compact and easier for viewers to determine when two words on the same line.
+    + It can now deal with text on a skewed baseline.
+    + Thanks to @cforcey for the pull request, @jbreiden for many helpful suggestions, @ctbarbour for another round of improvements, and @acaloiaro for an independent review.
+
+v5.6.3
+------
+
+-   Suppress two debug messages that were too verbose
+
+
+v5.6.2
+------
+
+-   Development branch accidentally tagged as release. Do not use.
+
+
+v5.6.1
+------
+
+-   Fix issue `#219 <https://github.com/jbarlow83/OCRmyPDF/issues/219>`_: change how the final output file is created to avoid triggering permission errors when the output is a special file such as ``/dev/null``
+-   Fix test suite failures due to a qpdf 8.0.0 regression and Python 3.5's handling of symlink
+-   The "encrypted PDF" error message was different depending on the type of PDF encryption. Now a single clear message appears for all types of PDF encryption.
+-   ocrmypdf is now in Homebrew. Homebrew users are advised to the version of ocrmypdf in the official homebrew-core formulas rather than the private tap.
+-   Some linting
+
+
+v5.6.0
+------
+
+-   Fix issue `#216 <https://github.com/jbarlow83/OCRmyPDF/issues/216>`_: preserve "text as curves" PDFs without rasterizing file
+-   Related to the above, messages about rasterizing are more consistent
+-   For consistency versions minor releases will now get the trailing .0 they always should have had.
+
+
+v5.5
+----
+
+-   Add new argument ``--max-image-mpixels``. Pillow 5.0 now raises an exception when images may be decompression bombs. This argument can be used to override the limit Pillow sets.
+-   Fix output page cropped when using the sandwich renderer and OCR is skipped on a rotated and image-processed page
+-   A warning is now issued when old versions of Ghostscript are used in cases known to cause issues with non-Latin characters
+-   Fix a few parameter validation checks for ``-output-type pdfa-1`` and ``pdfa-2``
+
+
+v5.4.4
+------
+
+-   Fix issue `#181 <https://github.com/jbarlow83/OCRmyPDF/issues/181>`_: fix final merge failure for PDFs with more pages than the system file handle limit (``ulimit -n``)
+-   Fix issue `#200 <https://github.com/jbarlow83/OCRmyPDF/issues/200>`_: an uncommon syntax for formatting decimal numbers in a PDF would cause qpdf to issue a warning, which ocrmypdf treated as an error. Now this the warning is relayed.
+-   Fix an issue where intermediate PDFs would be created at version 1.3 instead of the version of the original file. It's possible but unlikely this had side effects.
+-   A warning is now issued when older versions of qpdf are used since issues like `#200 <https://github.com/jbarlow83/OCRmyPDF/issues/200>`_ cause qpdf to infinite-loop
+-   Address issue `#140 <https://github.com/jbarlow83/OCRmyPDF/issues/140>`_: if Tesseract outputs invalid UTF-8, escape it and print its message instead of aborting with a Unicode error
+-   Adding previously unlisted setup requirement, pytest-runner
+-   Update documentation: fix an error in the example script for Synology with Docker images, improved security guidance, advised ``pip install --user``
+
+
+v5.4.3
+------
+
+-   If a subprocess fails to report its version when queried, exit cleanly with an error instead of throwing an exception
+-   Added test to confirm that the system locale is Unicode-aware and fail early if it's not
+-   Clarified some copyright information
+-   Updated pinned requirements.txt so the homebrew formula captures more recent versions
+
+
+v5.4.2
+------
+
+-   Fixed a regression from v5.4.1 that caused sidecar files to be created as empty files
+
+
+v5.4.1
+------
+
+-   Add workaround for Tesseract v4.00alpha crash when trying to obtain orientation and the latest language packs are installed
+
+
+v5.4
+----
+
+-   Change wording of a deprecation warning to improve clarity
+-   Added option to generate PDF/A-1b output if desired (``--output-type pdfa-1``); default remains PDF/A-2b generation
+-   Update documentation
+
+
+v5.3.3
+------
+
+-   Fixed missing error message that should occur when trying to force ``--pdf-renderer sandwich`` on old versions of Tesseract
+-   Update copyright information in test files
+-   Set system ``LANG`` to UTF-8 in Dockerfiles to avoid UTF-8 encoding errors
+
+
+v5.3.2
+------
+
+-   Fixed a broken test case related to language packs
+
+
+v5.3.1
+------
+
+-   Fixed wrong return code given for missing Tesseract language packs
+-   Fixed "brew audit" crashing on Travis when trying to auto-brew
+
+
+v5.3
+----
+
+-   Added ``--user-words`` and ``--user-patterns`` arguments which are forwarded to Tesseract OCR as words and regular expressions respective to use to guide OCR. Supplying a list of subject-domain words should assist Tesseract with resolving words. (`#165 <https://github.com/jbarlow83/OCRmyPDF/issues/165>`_)
+-   Using a non Latin-1 language with the "hocr" renderer now warns about possible OCR quality and recommends workarounds (`#176 <https://github.com/jbarlow83/OCRmyPDF/issues/176>`_)
+-   Output file path added to error message when that location is not writable (`#175 <https://github.com/jbarlow83/OCRmyPDF/issues/175>`_)
+-   Otherwise valid PDFs with leading whitespace at the beginning of the file are now accepted
+
+
+v5.2
+----
+
+-   When using Tesseract 3.05.01 or newer, OCRmyPDF will select the "sandwich" PDF renderer by default, unless another PDF renderer is specified with the ``--pdf-renderer`` argument. The previous behavior was to select ``--pdf-renderer=hocr``.
+-   The "tesseract" PDF renderer is now deprecated, since it can cause problems with Ghostscript on Tesseract 3.05.00
+-   The "tess4" PDF renderer has been renamed to "sandwich". "tess4" is now a deprecated alias for "sandwich".
+
+
+v5.1
+----
+
+-   Files with pages larger than 200" (5080 mm) in either dimension are now supported with ``--output-type=pdf`` with the page size preserved (in the PDF specification this feature is called UserUnit scaling). Due to Ghostscript limitations this is not available in conjunction with PDF/A output.
+
+
+v5.0.1
+------
+
+-   Fixed issue `#169 <https://github.com/jbarlow83/OCRmyPDF/issues/169>`_, exception due to failure to create sidecar text files on some versions of Tesseract 3.04, including the jbarlow83/ocrmypdf Docker image
+
+
+v5.0
+----
+
+-   Backward incompatible changes
+
+     + Support for Python 3.4 dropped. Python 3.5 is now required.
+     + Support for Tesseract 3.02 and 3.03 dropped. Tesseract 3.04 or newer is required. Tesseract 4.00 (alpha) is supported.
+     + The OCRmyPDF.sh script was removed.
+
+-   Add a new feature, ``--sidecar``, which allows creating "sidecar" text files which contain the OCR results in plain text. These OCR text is more reliable than extracting text from PDFs. Closes `#126 <https://github.com/jbarlow83/OCRmyPDF/issues/126>`_.
+-   New feature: ``--pdfa-image-compression``, which allows overriding Ghostscript's lossy-or-lossless image encoding heuristic and making all images JPEG encoded or lossless encoded as desired. Fixes `#163 <https://github.com/jbarlow83/OCRmyPDF/issues/163>`_.
+-   Fixed issue `#143 <https://github.com/jbarlow83/OCRmyPDF/issues/143>`_, added ``--quiet`` to suppress "INFO" messages
+-   Fixed issue `#164 <https://github.com/jbarlow83/OCRmyPDF/issues/164>`_, a typo
+-   Removed the command line parameters ``-n`` and ``--just-print`` since they have not worked for some time (reported as Ubuntu bug `#1687308 <https://bugs.launchpad.net/ubuntu/+source/ocrmypdf/+bug/1687308>`_)
+
+
+v4.5.6
+------
+
+-   Fixed issue `#156 <https://github.com/jbarlow83/OCRmyPDF/issues/156>`_, 'NoneType' object has no attribute 'getObject' on pages with no optional /Contents record.  This should resolve all issues related to pages with no /Contents record.
+-   Fixed issue `#158 <https://github.com/jbarlow83/OCRmyPDF/issues/158>`_, ocrmypdf now stops and terminates if Ghostscript fails on an intermediate step, as it is not possible to proceed.
+-   Fixed issue `#160 <https://github.com/jbarlow83/OCRmyPDF/issues/160>`_, exception thrown on certain invalid arguments instead of error message
+
+
+v4.5.5
+------
+
+-   Automated update of macOS homebrew tap
+-   Fixed issue `#154 <https://github.com/jbarlow83/OCRmyPDF/issues/154>`_, KeyError '/Contents' when searching for text on blank pages that have no /Contents record.  Note: incomplete fix for this issue.
+
+
+v4.5.4
+------
+
+-   Fix ``--skip-big`` raising an exception if a page contains no images (`#152 <https://github.com/jbarlow83/OCRmyPDF/issues/152>`_) (thanks to @TomRaz)
+-   Fix an issue where pages with no images might trigger "cannot write mode P as JPEG" (`#151 <https://github.com/jbarlow83/OCRmyPDF/issues/151>`_)
+
+
+v4.5.3
+------
+
+-   Added a workaround for Ghostscript 9.21 and probably earlier versions would fail with the error message "VMerror -25", due to a Ghostscript bug in XMP metadata handling
+-   High Unicode characters (U+10000 and up) are no longer accepted for setting metadata on the command line, as Ghostscript may not handle them correctly.
+-   Fixed an issue where the ``tess4`` renderer would duplicate content onto output pages if tesseract failed or timed out
+-   Fixed ``tess4`` renderer not recognized when lossless reconstruction is possible
+
+
+v4.5.2
+------
+
+-   Fix issue `#147 <https://github.com/jbarlow83/OCRmyPDF/issues/147>`_. ``--pdf-renderer tess4 --clean`` will produce an oversized page containing the original image in the bottom left corner, due to loss DPI information.
+-   Make "using Tesseract 4.0" warning less ominous
+-   Set up machinery for homebrew OCRmyPDF tap
+
+
+v4.5.1
+------
+
+-   Fix issue `#137 <https://github.com/jbarlow83/OCRmyPDF/issues/137>`_, proportions of images with a non-square pixel aspect ratio would be distorted in output for ``--force-ocr`` and some other combinations of flags
+
+
+v4.5
+----
+
+-   Exotic PDFs containing "Form XObjects" are now supported (issue `#134 <https://github.com/jbarlow83/OCRmyPDF/issues/134>`_; PDF reference manual 8.10), and images they contain are taken into account when determining the resolution for rasterizing
+-   The Tesseract 4 Docker image no longer includes all languages, because it took so long to build something would tend to fail
+-   OCRmyPDF now warns about using ``--pdf-renderer tesseract`` with Tesseract 3.04 or lower due to issues with Ghostscript corrupting the OCR text in these cases
+
+
+v4.4.2
+------
+
+-   The Docker images (ocrmypdf, ocrmypdf-polyglot, ocrmypdf-tess4) are now based on Ubuntu 16.10 instead of Debian stretch
+
+    + This makes supporting the Tesseract 4 image easier
+    + This could be a disruptive change for any Docker users who built customized these images with their own changes, and made those changes in a way that depends on Debian and not Ubuntu
+
+-   OCRmyPDF now prevents running the Tesseract 4 renderer with Tesseract 3.04, which was permitted in v4.4 and v4.4.1 but will not work
+
+
+v4.4.1
+------
+
+-   To prevent a `TIFF output error <https://github.com/python-pillow/Pillow/issues/2206>`_ caused by img2pdf >= 0.2.1 and Pillow <= 3.4.2, dependencies have been tightened
+-   The Tesseract 4.00 simultaneous process limit was increased from 1 to 2, since it was observed that 1 lowers performance
+-   Documentation improvements to describe the ``--tesseract-config`` feature
+-   Added test cases and fixed error handling for ``--tesseract-config``
+-   Tweaks to setup.py to deal with issues in the v4.4 release
+
+v4.4
+----
+
+-   Tesseract 4.00 is now supported on an experimental basis.
+
+    +  A new rendering option ``--pdf-renderer tess4`` exploits Tesseract 4's new text-only output PDF mode. See the documentation on PDF Renderers for details.
+    +  The ``--tesseract-oem`` argument allows control over the Tesseract 4 OCR engine mode (tesseract's ``--oem``). Use ``--tesseract-oem 2`` to enforce the new LSTM mode.
+    +  Fixed poor performance with Tesseract 4.00 on Linux
+
+-   Fixed an issue that caused corruption of output to stdout in some cases
+-   Removed test for Pillow JPEG and PNG support, as the minimum supported version of Pillow now enforces this
+-   OCRmyPDF now tests that the intended destination file is writable before proceeding
+-   The test suite now requires ``pytest-helpers-namespace`` to run (but not install)
+-   Significant code reorganization to make OCRmyPDF re-entrant and improve performance. All changes should be backward compatible for the v4.x series.
+
+    + However, OCRmyPDF's dependency "ruffus" is not re-entrant, so no Python API is available. Scripts should continue to use the command line interface.
+
+
+v4.3.5
+------
+
+-   Update documentation to confirm Python 3.6.0 compatibility. No code changes were needed, so many earlier versions are likely supported.
+
+
+v4.3.4
+------
+
+-   Fixed "decimal.InvalidOperation: quantize result has too many digits" for high DPI images
+
+
+v4.3.3
+------
+
+-   Fixed PDF/A creation with Ghostscript 9.20 properly
+-   Fixed an exception on inline stencil masks with a missing optional parameter
+
+
+v4.3.2
+------
+
+-   Fixed a PDF/A creation issue with Ghostscript 9.20 (note: this fix did not actually work)
+
+
+v4.3.1
+------
+
+-   Fixed an issue where pages produced by the "hocr" renderer after a Tesseract timeout would be rotated incorrectly if the input page was rotated with a /Rotate marker
+-   Fixed a file handle leak in LeptonicaErrorTrap that would cause a "too many open files" error for files around hundred pages of pages long when ``--deskew`` or ``--remove-background`` or other Leptonica based image processing features were in use, depending on the system value of ``ulimit -n``
+-   Ability to specify multiple languages for multilingual documents is now advertised in documentation
+-   Reduced the file sizes of some test resources
+-   Cleaned up debug output
+-   Tesseract caching in test cases is now more cautious about false cache hits and reproducing exact output, not that any problems were observed
+
+
+v4.3
+----
+
+-   New feature ``--remove-background`` to detect and erase the background of color and grayscale images
+-   Better documentation
+-   Fixed an issue with PDFs that draw images when the raster stack depth is zero
+-   ocrmypdf can now redirect its output to stdout for use in a shell pipeline
+
+    +  This does not improve performance since temporary files are still used for buffering
+    +  Some output validation is disabled in this mode
+
+v4.2.5
+------
+
+-   Fixed an issue (`#100 <https://github.com/jbarlow83/OCRmyPDF/issues/100>`_) with PDFs that omit the optional /BitsPerComponent parameter on images
+-   Removed non-free file milk.pdf
+
+
+v4.2.4
+------
+
+-   Fixed an error (`#90 <https://github.com/jbarlow83/OCRmyPDF/issues/90>`_) caused by PDFs that use stencil masks properly
+-   Fixed handling of PDFs that try to draw images or stencil masks without properly setting up the graphics state (such images are now ignored for the purposes of calculating DPI)
+
+v4.2.3
+------
+
+-   Fixed an issue with PDFs that store page rotation (/Rotate) in an indirect object
+-   Integrated a few fixes to simplify downstream packaging (Debian)
+
+    +  The test suite no longer assumes it is installed
+    +  If running Linux, skip a test that passes Unicode on the command line
+
+-   Added a test case to check explicit masks and stencil masks
+-   Added a test case for indirect objects and linearized PDFs
+-   Deprecated the OCRmyPDF.sh shell script
+
+
+v4.2.2
+------
+
+-   Improvements to documentation
+
+
+v4.2.1
+------
+
+-   Fixed an issue where PDF pages that contained stencil masks would report an incorrect DPI and cause Ghostscript to abort
+-   Implemented stdin streaming
+
+
+v4.2
+----
+
+-   ocrmypdf will now try to convert single image files to PDFs if they are provided as input (`#15 <https://github.com/jbarlow83/OCRmyPDF/issues/15>`_)
+
+    +  This is a basic convenience feature. It only supports a single image and always makes the image fill the whole page.
+    +  For better control over image to PDF conversion, use ``img2pdf`` (one of ocrmypdf's dependencies)
+
+-   New argument ``--output-type {pdf|pdfa}`` allows disabling Ghostscript PDF/A generation
+
+    +  ``pdfa`` is the default, consistent with past behavior
+    +  ``pdf`` provides a workaround for users concerned about the increase in file size from Ghostscript forcing JBIG2 images to CCITT and transcoding JPEGs
+    +  ``pdf`` preserves as much as it can about the original file, including problems that PDF/A conversion fixes
+
+-   PDFs containing images with "non-square" pixel aspect ratios, such as 200x100 DPI, are now handled and converted properly (fixing a bug that caused to be cropped)
+-   ``--force-ocr`` rasterizes pages even if they contain no images
+
+    +  supports users who want to use OCRmyPDF to reconstruct text information in PDFs with damaged Unicode maps (copy and paste text does not match displayed text)
+    +  supports reinterpreting PDFs where text was rendered as curves for printing, and text needs to be recovered
+    +  fixes issue `#82 <https://github.com/jbarlow83/OCRmyPDF/issues/82>`_
+
+-   Fixes an issue where, with certain settings, monochrome images in PDFs would be converted to 8-bit grayscale, increasing file size (`#79 <https://github.com/jbarlow83/OCRmyPDF/issues/79>`_)
+-   Support for Ubuntu 12.04 LTS "precise" has been dropped in favor of (roughly) Ubuntu 14.04 LTS "trusty"
+
+    +  Some Ubuntu "PPAs" (backports) are needed to make it work
+
+-   Support for some older dependencies dropped
+
+    +  Ghostscript 9.15 or later is now required (available in Ubuntu trusty with backports)
+    +  Tesseract 3.03 or later is now required (available in Ubuntu trusty)
+
+-   Ghostscript now runs in "safer" mode where possible
+
+v4.1.4
+------
+
+-   Bug fix: monochrome images with an ICC profile attached were incorrectly converted to full color images if lossless reconstruction was not possible due to other settings; consequence was increased file size for these images
+
+
+v4.1.3
+------
+
+-   More helpful error message for PDFs with version 4 security handler
+-   Update usage instructions for Windows/Docker users
+-   Fix order of operations for matrix multiplication (no effect on most users)
+-   Add a few leptonica wrapper functions (no effect on most users)
+
+
+v4.1.2
+------
+
+-   Replace IEC sRGB ICC profile with Debian's sRGB (from icc-profiles-free) which is more compatible with the MIT license
+-   More helpful error message for an error related to certain types of malformed PDFs
+
+
+v4.1
+----
+
+-   ``--rotate-pages`` now only rotates pages when reasonably confidence in the orientation. This behavior can be adjusted with the new argument ``--rotate-pages-threshold``
+-   Fixed problems in error checking if ``unpaper`` is uninstalled or missing at run-time
+-   Fixed problems with "RethrownJobError" errors during error handling that suppressed the useful error messages
+
+
+v4.0.7
+------
+
+-   Minor correction to Ghostscript output settings
+
+
+v4.0.6
+------
+
+-   Update install instructions
+-   Provide a sRGB profile instead of using Ghostscript's
+
+
+v4.0.5
+------
+
+-   Remove some verbose debug messages from v4.0.4
+-   Fixed temporary that wasn't being deleted
+-   DPI is now calculated correctly for cropped images, along with other image transformations
+-   Inline images are now checked during DPI calculation instead of rejecting the image
+
+v4.0.4
+------
+
+Released with verbose debug message turned on. Do not use. Skip to v4.0.5.
+
+
+v4.0.3
+------
+
+New features
+^^^^^^^^^^^^
+
+-   Page orientations detected are now reported in a summary comment
+
+
+Fixes
+^^^^^
+
+-   Show stack trace if unexpected errors occur
+-   Treat "too few characters" error message from Tesseract as a reason to skip that page rather than
+    abort the file
+-   Docker: fix blank JPEG2000 issue by insisting on Ghostscript versions that have this fixed
+
+
+v4.0.2
+------
+
+Fixes
+^^^^^
+
+-   Fixed compatibility with Tesseract 3.04.01 release, particularly its different way of outputting
+    orientation information
+-   Improved handling of Tesseract errors and crashes
+-   Fixed use of chmod on Docker that broke most test cases
+
+
+v4.0.1
+------
+
+Fixes
+^^^^^
+
+-   Fixed a KeyError if tesseract fails to find page orientation information
+
+
+v4.0
+----
+
+New features
+^^^^^^^^^^^^
+
+-   Automatic page rotation (``-r``) is now available. It uses ignores any prior rotation information
+    on PDFs and sets rotation based on the dominant orientation of detectable text. This feature is
+    fairly reliable but some false positives occur especially if there is not much text to work with. (`#4 <https://github.com/jbarlow83/OCRmyPDF/issues/4>`_)
+-   Deskewing is now performed using Leptonica instead of unpaper. Leptonica is faster and more reliable
+    at image deskewing than unpaper.
+
+
+Fixes
+^^^^^
+
+-   Fixed an issue where lossless reconstruction could cause some pages to be appear incorrectly
+    if the page was rotated by the user in Acrobat after being scanned (specifically if it a /Rotate tag)
+-   Fixed an issue where lossless reconstruction could misalign the graphics layer with respect to
+    text layer if the page had been cropped such that its origin is not (0, 0) (`#49 <https://github.com/jbarlow83/OCRmyPDF/issues/49>`_)
+
+
+Changes
+^^^^^^^
+
+-   Logging output is now much easier to read
+-   ``--deskew`` is now performed by Leptonica instead of unpaper (`#25 <https://github.com/jbarlow83/OCRmyPDF/issues/25>`_)
+-   libffi is now required
+-   Some changes were made to the Docker and Travis build environments to support libffi
+-   ``--pdf-renderer=tesseract`` now displays a warning if the Tesseract version is less than 3.04.01,
+    the planned release that will include fixes to an important OCR text rendering bug in Tesseract 3.04.00.
+    You can also manually install ./share/sharp2.ttf on top of pdf.ttf in your Tesseract tessdata folder
+    to correct the problem.
+
+
+v3.2.1
+------
+
+Changes
+^^^^^^^
+
+-   Fixed issue `#47 <https://github.com/jbarlow83/OCRmyPDF/issues/47>`_ "convert() got and unexpected keyword argument 'dpi'" by upgrading to img2pdf 0.2
+-   Tweaked the Dockerfiles
+
+
+v3.2
+----
+
+New features
+^^^^^^^^^^^^
+
+-   Lossless reconstruction: when possible, OCRmyPDF will inject text layers without
+    otherwise manipulating the content and layout of a PDF page. For example, a PDF containing a mix
+    of vector and raster content would see the vector content preserved. Images may still be transcoded
+    during PDF/A conversion.  (``--deskew`` and ``--clean-final`` disable this mode, necessarily.)
+-   New argument ``--tesseract-pagesegmode`` allows you to pass page segmentation arguments to Tesseract OCR.
+    This helps for two column text and other situations that confuse Tesseract.
+-   Added a new "polyglot" version of the Docker image, that generates Tesseract with all languages packs installed,
+    for the polyglots among us. It is much larger.
+
+Changes
+^^^^^^^
+
+-   JPEG transcoding quality is now 95 instead of the default 75. Bigger file sizes for less degradation.
+
+
+
+v3.1.1
+------
+
+Changes
+^^^^^^^
+
+-   Fixed bug that caused incorrect page size and DPI calculations on documents with mixed page sizes
+
+v3.1
+----
+
+Changes
+^^^^^^^
+
+-   Default output format is now PDF/A-2b instead of PDF/A-1b
+-   Python 3.5 and macOS El Capitan are now supported platforms - no changes were
+    needed to implement support
+-   Improved some error messages related to missing input files
+-   Fixed issue `#20 <https://github.com/jbarlow83/OCRmyPDF/issues/20>`_ - uppercase .PDF extension not accepted
+-   Fixed an issue where OCRmyPDF failed to text that certain pages contained previously OCR'ed text,
+    such as OCR text produced by Tesseract 3.04
+-   Inserts /Creator tag into PDFs so that errors can be traced back to this project
+-   Added new option ``--pdf-renderer=auto``, to let OCRmyPDF pick the best PDF renderer.
+    Currently it always chooses the 'hocrtransform' renderer but that behavior may change.
+-   Set up Travis CI automatic integration testing
+
+v3.0
+----
+
+New features
+^^^^^^^^^^^^
+
+-   Easier installation with a Docker container or Python's ``pip`` package manager
+-   Eliminated many external dependencies, so it's easier to setup
+-   Now installs ``ocrmypdf`` to ``/usr/local/bin`` or equivalent for system-wide
+    access and easier typing
+-   Improved command line syntax and usage help (``--help``)
+-   Tesseract 3.03+ PDF page rendering can be used instead for better positioning
+    of recognized text (``--pdf-renderer tesseract``)
+-   PDF metadata (title, author, keywords) are now transferred to the
+    output PDF
+-   PDF metadata can also be set from the command line (``--title``, etc.)
+-   Automatic repairs malformed input PDFs if possible
+-   Added test cases to confirm everything is working
+-   Added option to skip extremely large pages that take too long to OCR and are
+    often not OCRable (e.g. large scanned maps or diagrams); other pages are still
+    processed (``--skip-big``)
+-   Added option to kill Tesseract OCR process if it seems to be taking too long on
+    a page, while still processing other pages (``--tesseract-timeout``)
+-   Less common colorspaces (CMYK, palette) are now supported by conversion to RGB
+-   Multiple images on the same PDF page are now supported
+
+Changes
+^^^^^^^
+
+-   New, robust rewrite in Python 3.4+ with ruffus_ pipelines
+-   Now uses Ghostscript 9.14's improved color conversion model to preserve PDF colors
+-   OCR text is now rendered in the PDF as invisible text. Previous versions of OCRmyPDF
+    incorrectly rendered visible text with an image on top.
+-   All "tasks" in the pipeline can be executed in parallel on any
+    available CPUs, increasing performance
+-   The ``-o DPI`` argument has been phased out, in favor of ``--oversample DPI``, in
+    case we need ``-o OUTPUTFILE`` in the future
+-   Removed several dependencies, so it's easier to install.  We no
+    longer use:
+
+    - GNU parallel_
+    - ImageMagick_
+    - Python 2.7
+    - Poppler
+    - MuPDF_ tools
+    - shell scripts
+    - Java and JHOVE_
+    - libxml2
+
+-   Some new external dependencies are required or optional, compared to v2.x:
+
+    - Ghostscript 9.14+
+    - qpdf_ 5.0.0+
+    - Unpaper_ 6.1 (optional)
+    - some automatically managed Python packages
+
+.. _ruffus: http://www.ruffus.org.uk/index.html
+.. _parallel: https://www.gnu.org/software/parallel/
+.. _ImageMagick: http://www.imagemagick.org/script/index.php
+.. _MuPDF: http://mupdf.com/docs/
+.. _qpdf: http://qpdf.sourceforge.net/
+.. _Unpaper: https://github.com/Flameeyes/unpaper
+.. _JHOVE: http://jhove.sourceforge.net/
+
+Release candidates
+^^^^^^^^^^^^^^^^^^
+
+-   rc9:
+
+    - fix issue `#118 <https://github.com/jbarlow83/OCRmyPDF/issues/118>`_: report error if ghostscript iccprofiles are missing
+    - fixed another issue related to `#111 <https://github.com/jbarlow83/OCRmyPDF/issues/111>`_: PDF rasterized to palette file
+    - add support image files with a palette
+    - don't try to validate PDF file after an exception occurs
+
+-   rc8:
+
+    - fix issue `#111 <https://github.com/jbarlow83/OCRmyPDF/issues/111>`_: exception thrown if PDF is missing DocumentInfo dictionary
+
+-   rc7:
+
+    - fix error when installing direct from pip, "no such file 'requirements.txt'"
+
+-   rc6:
+
+    - dropped libxml2 (Python lxml) since Python 3's internal XML parser is sufficient
+    - set up Docker container
+    - fix Unicode errors if recognized text contains Unicode characters and system locale is not UTF-8
+
+-   rc5:
+
+    - dropped Java and JHOVE in favour of qpdf
+    - improved command line error output
+    - additional tests and bug fixes
+    - tested on Ubuntu 14.04 LTS
+
+-   rc4:
+
+    - dropped MuPDF in favour of qpdf
+    - fixed some installer issues and errors in installation instructions
+    - improve performance: run Ghostscript with multithreaded rendering
+    - improve performance: use multiple cores by default
+    - bug fix: checking for wrong exception on process timeout
+
+-   rc3: skipping version number intentionally to avoid confusion with Tesseract
+-   rc2: first release for public testing to test-PyPI, Github
+-   rc1: testing release process
+
+Compatibility notes
+-------------------
+
+-   ``./OCRmyPDF.sh`` script is still available for now
+-   Stacking the verbosity option like ``-vvv`` is no longer supported
+
+-   The configuration file ``config.sh`` has been removed.  Instead, you can
+    feed a file to the arguments for common settings:
+
+::
+
+    ocrmypdf input.pdf output.pdf @settings.txt
+
+where ``settings.txt`` contains *one argument per line*, for example:
+
+::
+
+    -l
+    deu
+    --author
+    A. Merkel
+    --pdf-renderer
+    tesseract
+
+
+Fixes
+^^^^^
+
+-   Handling of filenames containing spaces: fixed
+
+Notes and known issues
+^^^^^^^^^^^^^^^^^^^^^^
+
+-   Some dependencies may work with lower versions than tested, so try
+    overriding dependencies if they are "in the way" to see if they work.
+
+-   ``--pdf-renderer tesseract`` will output files with an incorrect page size in Tesseract 3.03,
+    due to a bug in Tesseract.
+
+-   PDF files containing "inline images" are not supported and won't be for the 3.0 release. Scanned
+    images almost never contain inline images.
+
+
+v2.2-stable (2014-09-29)
+------------------------
+
+OCRmyPDF versions 1 and 2 were implemented as shell scripts. OCRmyPDF 3.0+ is a fork that gradually replaced all shell scripts with Python while maintaining the existing command line arguments. No one is maintaining old versions.
+
+For details on older versions, see the `final version of its release notes <https://github.com/fritz-hh/OCRmyPDF/blob/7fd3dbdf42ca53a619412ce8add7532c5e81a9d1/RELEASE_NOTES.md>`_.

docs/security.rst

@@ -0,0 +1,77 @@
+PDF security issues
+===================
+
+	OCRmyPDF should only be used on PDFs you trust. It is not designed to protect you against malware.
+
+Recognizing that many users have an interest in handling PDFs and applying OCR to PDFs they did not generate themselves, this article discusses the security implications of PDFs and how users can protect themselves.
+
+The disclaimer applies: this software has no warranties of any kind.
+
+PDFs may contain malware
+------------------------
+
+PDF is a rich, complex file format. The official PDF 1.7 specification, ISO 32000:2008, is hundreds of pages long and references several annexes each of which are similar in length. PDFs can contain video, audio, XML, JavaScript and other programming, and forms. In some cases, they can open internet connections to pre-selected URLs. All of these possible attack vectors.
+
+In short, PDFs `may contain viruses <https://security.stackexchange.com/questions/64052/can-a-pdf-file-contain-a-virus>`_.
+
+This `article <https://theinvisiblethings.blogspot.ca/2013/02/converting-untrusted-pdfs-into-trusted.html>`_ describes a high-paranoia method which allows potentially hostile PDFs to be viewed and rasterized safely in a disposable virtual machine. A trusted PDF created in this manner is converted to images and loses all information making it searchable and losing all compression. OCRmyPDF could be used restore searchability.
+
+How OCRmyPDF processes PDFs
+---------------------------
+
+OCRmyPDF must open and interpret your PDF in order to insert an OCR layer. First, it runs all PDFs through `pikepdf <https://github.com/pikepdf/pikepdf>`_, a library based on `qpdf <https://github.com/qpdf/qpdf>`_, a program that repairs PDFs with syntax errors. This is done because, in the author's experience, a significant number of PDFs in the wild especially those created by scanners are not well-formed files. qpdf makes it more likely that OCRmyPDF will succeed, but offers no security guarantees. qpdf is also used to split the PDF into single page PDFs.
+
+Finally, OCRmyPDF rasterizes each page of the PDF using `Ghostscript <http://ghostscript.com/>`_ in ``-dSAFER`` mode.
+
+Depending on the options specified, OCRmyPDF may graft the OCR layer into the existing PDF or it may essentially reconstruct ("re-fry") a visually identical PDF that may be quite different at the binary level. That said, OCRmyPDF is not a tool designed for sanitizing PDFs.
+
+Using OCRmyPDF online or as a service
+-------------------------------------
+
+OCRmyPDF should not be deployed as a public-facing service, such as a website where a potential attacker could upload a PDF of their choice for OCR. OCRmyPDF is not designed to be secure against PDF malware. Another concern is PDFs specifically designed to be a denial of service attack: PDFs can contain recursive data structures that sometimes send parsers into infinite loops, and issue complex graphics drawing commands.
+
+Setting aside these concerns, a side effect of OCRmyPDF is it may incidentally sanitize PDFs that contain malware. It runs ``qpdf`` to repair the PDF, which could correct malformed PDF structures that are part of an attack. When PDF/A output is selected (the default), the input PDF is partially reconstructed by Ghostscript. When ``--force-ocr`` is used, all pages are rasterized and reconverted to PDF, which could remove malware in embedded images. No guarantees.
+
+OCRmyPDF should be relatively safe to use in a trusted intranet, with some considerations:
+
+Limiting CPU usage
+^^^^^^^^^^^^^^^^^^
+
+OCRmyPDF will attempt to use all available CPUs and storage, so executing ``nice ocrmypdf`` or limiting the number of jobs with the ``-j`` argument may ensure the server remains available. Another option would be run OCRmyPDF jobs inside a Docker container, a virtual machine, or a cloud instance, which can impose its own limits on CPU usage and be terminated "from orbit" if it fails to complete.
+
+Temporary storage requirements
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+OCRmyPDF will use a large amount of temporary storage for its work, proportional to the total number of pixels needed to rasterize the PDF. The raster image of a 8.5×11" color page at 300 DPI takes 25 MB uncompressed; OCRmyPDF saves its intermediates as PNG, but that still means it requires about 9 MB per intermediate based on average compression ratios. Multiple intermediates per page are also required, depending on the command line given. A rule of thumb would be to allow 100 MB of temporary storage per page in a file – meaning that a small cloud servers or small VM partitions should be provisioned with plenty of extra space, if say, a 500 page file might be sent.
+
+To check temporary storage usage on actual files, run ``ocrmypdf -k ...`` which will preserve and print the path to temporary storage when the job is done.
+
+To change where temporary files are stored, change the ``TMPDIR`` environment variable for ocrmypdf's environment. (Python's ``tempfile.gettempdir()`` returns the root directory in which temporary files will be stored.) For example, one could redirect ``TMPDIR`` to a large RAM disk to avoid wear on HDD/SSD and potentially improve performance. On Amazon Web Services, ``TMPDIR`` can be set to `empheral storage <https://docs.aws.amazon.com/AWSEC2/latest/UserGuide/InstanceStorage.html>`_.
+
+Timeouts
+^^^^^^^^
+
+To prevent excessively long OCR jobs consider setting ``--tesseract-timeout`` and/or ``--skip-big`` arguments. ``--skip-big`` is particularly helpful if your PDFs include documents such as reports on standard page sizes with large images attached - often large images are not worth OCR'ing anyway.
+
+Commercial alternatives
+^^^^^^^^^^^^^^^^^^^^^^^
+
+The author also provides professional services that include OCR and building databases around PDFs, and is happy to provide consultation.
+
+Abbyy Cloud OCR is a viable commercial alternative with a web services API.
+
+
+Password protection, digital signatures and certification
+---------------------------------------------------------
+
+Password protected PDFs usually have two passwords, and owner and user password. When the user password is set to empty, PDF readers will open the file automatically and marked it as "(SECURED)". While not as reliable as a digital signature, this indicates that whoever set the password approved of the file at that time. When the user password is set, the document cannot be viewed without the password.
+
+Either way, OCRmyPDF does not remove passwords from PDFs and exits with an error on encountering them.
+
+``qpdf``, one of OCRmyPDF's dependencies, can remove passwords. If the owner and user password are set, a password is required for ``qpdf``. If only the owner password is set, then the password can be stripped, even if one does not have the owner password.
+
+After OCR is applied, password protection is not permitted on PDF/A documents but the file can be converted to regular PDF.
+
+Many programs exist which are capable of inserting an image of someone's signature. On its own, this offers no security guarantees. It is trivial to remove the signature image and apply it to other files. This practice offers no real security.
+
+Important documents can be digitally signed and certified to attest to their authorship. OCRmyPDF cannot do this. Open source tools such as pdfbox (Java) have this capability as does Adobe Acrobat.

jhove/COPYING

@@ -1,502 +0,0 @@
-		  GNU LESSER GENERAL PUBLIC LICENSE
-		       Version 2.1, February 1999
-
- Copyright (C) 1991, 1999 Free Software Foundation, Inc.
-     59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
- Everyone is permitted to copy and distribute verbatim copies
- of this license document, but changing it is not allowed.
-
-[This is the first released version of the Lesser GPL.  It also counts
- as the successor of the GNU Library Public License, version 2, hence
- the version number 2.1.]
-
-			    Preamble
-
-  The licenses for most software are designed to take away your
-freedom to share and change it.  By contrast, the GNU General Public
-Licenses are intended to guarantee your freedom to share and change
-free software--to make sure the software is free for all its users.
-
-  This license, the Lesser General Public License, applies to some
-specially designated software packages--typically libraries--of the
-Free Software Foundation and other authors who decide to use it.  You
-can use it too, but we suggest you first think carefully about whether
-this license or the ordinary General Public License is the better
-strategy to use in any particular case, based on the explanations below.
-
-  When we speak of free software, we are referring to freedom of use,
-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 this service if you wish); that you receive source code or can get
-it if you want it; that you can change the software and use pieces of
-it in new free programs; and that you are informed that you can do
-these things.
-
-  To protect your rights, we need to make restrictions that forbid
-distributors to deny you these rights or to ask you to surrender these
-rights.  These restrictions translate to certain responsibilities for
-you if you distribute copies of the library or if you modify it.
-
-  For example, if you distribute copies of the library, whether gratis
-or for a fee, you must give the recipients all the rights that we gave
-you.  You must make sure that they, too, receive or can get the source
-code.  If you link other code with the library, you must provide
-complete object files to the recipients, so that they can relink them
-with the library after making changes to the library and recompiling
-it.  And you must show them these terms so they know their rights.
-
-  We protect your rights with a two-step method: (1) we copyright the
-library, and (2) we offer you this license, which gives you legal
-permission to copy, distribute and/or modify the library.
-
-  To protect each distributor, we want to make it very clear that
-there is no warranty for the free library.  Also, if the library is
-modified by someone else and passed on, the recipients should know
-that what they have is not the original version, so that the original
-author's reputation will not be affected by problems that might be
-introduced by others.
-
-  Finally, software patents pose a constant threat to the existence of
-any free program.  We wish to make sure that a company cannot
-effectively restrict the users of a free program by obtaining a
-restrictive license from a patent holder.  Therefore, we insist that
-any patent license obtained for a version of the library must be
-consistent with the full freedom of use specified in this license.
-
-  Most GNU software, including some libraries, is covered by the
-ordinary GNU General Public License.  This license, the GNU Lesser
-General Public License, applies to certain designated libraries, and
-is quite different from the ordinary General Public License.  We use
-this license for certain libraries in order to permit linking those
-libraries into non-free programs.
-
-  When a program is linked with a library, whether statically or using
-a shared library, the combination of the two is legally speaking a
-combined work, a derivative of the original library.  The ordinary
-General Public License therefore permits such linking only if the
-entire combination fits its criteria of freedom.  The Lesser General
-Public License permits more lax criteria for linking other code with
-the library.
-
-  We call this license the "Lesser" General Public License because it
-does Less to protect the user's freedom than the ordinary General
-Public License.  It also provides other free software developers Less
-of an advantage over competing non-free programs.  These disadvantages
-are the reason we use the ordinary General Public License for many
-libraries.  However, the Lesser license provides advantages in certain
-special circumstances.
-
-  For example, on rare occasions, there may be a special need to
-encourage the widest possible use of a certain library, so that it becomes
-a de-facto standard.  To achieve this, non-free programs must be
-allowed to use the library.  A more frequent case is that a free
-library does the same job as widely used non-free libraries.  In this
-case, there is little to gain by limiting the free library to free
-software only, so we use the Lesser General Public License.
-
-  In other cases, permission to use a particular library in non-free
-programs enables a greater number of people to use a large body of
-free software.  For example, permission to use the GNU C Library in
-non-free programs enables many more people to use the whole GNU
-operating system, as well as its variant, the GNU/Linux operating
-system.
-
-  Although the Lesser General Public License is Less protective of the
-users' freedom, it does ensure that the user of a program that is
-linked with the Library has the freedom and the wherewithal to run
-that program using a modified version of the Library.
-
-  The precise terms and conditions for copying, distribution and
-modification follow.  Pay close attention to the difference between a
-"work based on the library" and a "work that uses the library".  The
-former contains code derived from the library, whereas the latter must
-be combined with the library in order to run.
-
-		  GNU LESSER GENERAL PUBLIC LICENSE
-   TERMS AND CONDITIONS FOR COPYING, DISTRIBUTION AND MODIFICATION
-
-  0. This License Agreement applies to any software library or other
-program which contains a notice placed by the copyright holder or
-other authorized party saying it may be distributed under the terms of
-this Lesser General Public License (also called "this License").
-Each licensee is addressed as "you".
-
-  A "library" means a collection of software functions and/or data
-prepared so as to be conveniently linked with application programs
-(which use some of those functions and data) to form executables.
-
-  The "Library", below, refers to any such software library or work
-which has been distributed under these terms.  A "work based on the
-Library" means either the Library or any derivative work under
-copyright law: that is to say, a work containing the Library or a
-portion of it, either verbatim or with modifications and/or translated
-straightforwardly into another language.  (Hereinafter, translation is
-included without limitation in the term "modification".)
-
-  "Source code" for a work means the preferred form of the work for
-making modifications to it.  For a library, complete source code means
-all the source code for all modules it contains, plus any associated
-interface definition files, plus the scripts used to control compilation
-and installation of the library.
-
-  Activities other than copying, distribution and modification are not
-covered by this License; they are outside its scope.  The act of
-running a program using the Library is not restricted, and output from
-such a program is covered only if its contents constitute a work based
-on the Library (independent of the use of the Library in a tool for
-writing it).  Whether that is true depends on what the Library does
-and what the program that uses the Library does.
-  
-  1. You may copy and distribute verbatim copies of the Library's
-complete source code as you receive it, in any medium, provided that
-you conspicuously and appropriately publish on each copy an
-appropriate copyright notice and disclaimer of warranty; keep intact
-all the notices that refer to this License and to the absence of any
-warranty; and distribute a copy of this License along with the
-Library.
-
-  You may charge a fee for the physical act of transferring a copy,
-and you may at your option offer warranty protection in exchange for a
-fee.
-
-  2. You may modify your copy or copies of the Library or any portion
-of it, thus forming a work based on the Library, and copy and
-distribute such modifications or work under the terms of Section 1
-above, provided that you also meet all of these conditions:
-
-    a) The modified work must itself be a software library.
-
-    b) You must cause the files modified to carry prominent notices
-    stating that you changed the files and the date of any change.
-
-    c) You must cause the whole of the work to be licensed at no
-    charge to all third parties under the terms of this License.
-
-    d) If a facility in the modified Library refers to a function or a
-    table of data to be supplied by an application program that uses
-    the facility, other than as an argument passed when the facility
-    is invoked, then you must make a good faith effort to ensure that,
-    in the event an application does not supply such function or
-    table, the facility still operates, and performs whatever part of
-    its purpose remains meaningful.
-
-    (For example, a function in a library to compute square roots has
-    a purpose that is entirely well-defined independent of the
-    application.  Therefore, Subsection 2d requires that any
-    application-supplied function or table used by this function must
-    be optional: if the application does not supply it, the square
-    root function must still compute square roots.)
-
-These requirements apply to the modified work as a whole.  If
-identifiable sections of that work are not derived from the Library,
-and can be reasonably considered independent and separate works in
-themselves, then this License, and its terms, do not apply to those
-sections when you distribute them as separate works.  But when you
-distribute the same sections as part of a whole which is a work based
-on the Library, the distribution of the whole must be on the terms of
-this License, whose permissions for other licensees extend to the
-entire whole, and thus to each and every part regardless of who wrote
-it.
-
-Thus, it is not the intent of this section to claim rights or contest
-your rights to work written entirely by you; rather, the intent is to
-exercise the right to control the distribution of derivative or
-collective works based on the Library.
-
-In addition, mere aggregation of another work not based on the Library
-with the Library (or with a work based on the Library) on a volume of
-a storage or distribution medium does not bring the other work under
-the scope of this License.
-
-  3. You may opt to apply the terms of the ordinary GNU General Public
-License instead of this License to a given copy of the Library.  To do
-this, you must alter all the notices that refer to this License, so
-that they refer to the ordinary GNU General Public License, version 2,
-instead of to this License.  (If a newer version than version 2 of the
-ordinary GNU General Public License has appeared, then you can specify
-that version instead if you wish.)  Do not make any other change in
-these notices.
-
-  Once this change is made in a given copy, it is irreversible for
-that copy, so the ordinary GNU General Public License applies to all
-subsequent copies and derivative works made from that copy.
-
-  This option is useful when you wish to copy part of the code of
-the Library into a program that is not a library.
-
-  4. You may copy and distribute the Library (or a portion or
-derivative of it, under Section 2) in object code or executable form
-under the terms of Sections 1 and 2 above provided that you accompany
-it with the complete corresponding machine-readable source code, which
-must be distributed under the terms of Sections 1 and 2 above on a
-medium customarily used for software interchange.
-
-  If distribution of object code is made by offering access to copy
-from a designated place, then offering equivalent access to copy the
-source code from the same place satisfies the requirement to
-distribute the source code, even though third parties are not
-compelled to copy the source along with the object code.
-
-  5. A program that contains no derivative of any portion of the
-Library, but is designed to work with the Library by being compiled or
-linked with it, is called a "work that uses the Library".  Such a
-work, in isolation, is not a derivative work of the Library, and
-therefore falls outside the scope of this License.
-
-  However, linking a "work that uses the Library" with the Library
-creates an executable that is a derivative of the Library (because it
-contains portions of the Library), rather than a "work that uses the
-library".  The executable is therefore covered by this License.
-Section 6 states terms for distribution of such executables.
-
-  When a "work that uses the Library" uses material from a header file
-that is part of the Library, the object code for the work may be a
-derivative work of the Library even though the source code is not.
-Whether this is true is especially significant if the work can be
-linked without the Library, or if the work is itself a library.  The
-threshold for this to be true is not precisely defined by law.
-
-  If such an object file uses only numerical parameters, data
-structure layouts and accessors, and small macros and small inline
-functions (ten lines or less in length), then the use of the object
-file is unrestricted, regardless of whether it is legally a derivative
-work.  (Executables containing this object code plus portions of the
-Library will still fall under Section 6.)
-
-  Otherwise, if the work is a derivative of the Library, you may
-distribute the object code for the work under the terms of Section 6.
-Any executables containing that work also fall under Section 6,
-whether or not they are linked directly with the Library itself.
-
-  6. As an exception to the Sections above, you may also combine or
-link a "work that uses the Library" with the Library to produce a
-work containing portions of the Library, and distribute that work
-under terms of your choice, provided that the terms permit
-modification of the work for the customer's own use and reverse
-engineering for debugging such modifications.
-
-  You must give prominent notice with each copy of the work that the
-Library is used in it and that the Library and its use are covered by
-this License.  You must supply a copy of this License.  If the work
-during execution displays copyright notices, you must include the
-copyright notice for the Library among them, as well as a reference
-directing the user to the copy of this License.  Also, you must do one
-of these things:
-
-    a) Accompany the work with the complete corresponding
-    machine-readable source code for the Library including whatever
-    changes were used in the work (which must be distributed under
-    Sections 1 and 2 above); and, if the work is an executable linked
-    with the Library, with the complete machine-readable "work that
-    uses the Library", as object code and/or source code, so that the
-    user can modify the Library and then relink to produce a modified
-    executable containing the modified Library.  (It is understood
-    that the user who changes the contents of definitions files in the
-    Library will not necessarily be able to recompile the application
-    to use the modified definitions.)
-
-    b) Use a suitable shared library mechanism for linking with the
-    Library.  A suitable mechanism is one that (1) uses at run time a
-    copy of the library already present on the user's computer system,
-    rather than copying library functions into the executable, and (2)
-    will operate properly with a modified version of the library, if
-    the user installs one, as long as the modified version is
-    interface-compatible with the version that the work was made with.
-
-    c) Accompany the work with a written offer, valid for at
-    least three years, to give the same user the materials
-    specified in Subsection 6a, above, for a charge no more
-    than the cost of performing this distribution.
-
-    d) If distribution of the work is made by offering access to copy
-    from a designated place, offer equivalent access to copy the above
-    specified materials from the same place.
-
-    e) Verify that the user has already received a copy of these
-    materials or that you have already sent this user a copy.
-
-  For an executable, the required form of the "work that uses the
-Library" must include any data and utility programs needed for
-reproducing the executable from it.  However, as a special exception,
-the materials to be distributed need not include anything that is
-normally distributed (in either source or binary form) with the major
-components (compiler, kernel, and so on) of the operating system on
-which the executable runs, unless that component itself accompanies
-the executable.
-
-  It may happen that this requirement contradicts the license
-restrictions of other proprietary libraries that do not normally
-accompany the operating system.  Such a contradiction means you cannot
-use both them and the Library together in an executable that you
-distribute.
-
-  7. You may place library facilities that are a work based on the
-Library side-by-side in a single library together with other library
-facilities not covered by this License, and distribute such a combined
-library, provided that the separate distribution of the work based on
-the Library and of the other library facilities is otherwise
-permitted, and provided that you do these two things:
-
-    a) Accompany the combined library with a copy of the same work
-    based on the Library, uncombined with any other library
-    facilities.  This must be distributed under the terms of the
-    Sections above.
-
-    b) Give prominent notice with the combined library of the fact
-    that part of it is a work based on the Library, and explaining
-    where to find the accompanying uncombined form of the same work.
-
-  8. You may not copy, modify, sublicense, link with, or distribute
-the Library except as expressly provided under this License.  Any
-attempt otherwise to copy, modify, sublicense, link with, or
-distribute the Library is void, and will automatically terminate your
-rights under this License.  However, parties who have received copies,
-or rights, from you under this License will not have their licenses
-terminated so long as such parties remain in full compliance.
-
-  9. You are not required to accept this License, since you have not
-signed it.  However, nothing else grants you permission to modify or
-distribute the Library or its derivative works.  These actions are
-prohibited by law if you do not accept this License.  Therefore, by
-modifying or distributing the Library (or any work based on the
-Library), you indicate your acceptance of this License to do so, and
-all its terms and conditions for copying, distributing or modifying
-the Library or works based on it.
-
-  10. Each time you redistribute the Library (or any work based on the
-Library), the recipient automatically receives a license from the
-original licensor to copy, distribute, link with or modify the Library
-subject to these terms and conditions.  You may not impose any further
-restrictions on the recipients' exercise of the rights granted herein.
-You are not responsible for enforcing compliance by third parties with
-this License.
-
-  11. If, as a consequence of a court judgment or allegation of patent
-infringement or for any other reason (not limited to patent issues),
-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
-distribute so as to satisfy simultaneously your obligations under this
-License and any other pertinent obligations, then as a consequence you
-may not distribute the Library at all.  For example, if a patent
-license would not permit royalty-free redistribution of the Library by
-all those who receive copies directly or indirectly through you, then
-the only way you could satisfy both it and this License would be to
-refrain entirely from distribution of the Library.
-
-If any portion of this section is held invalid or unenforceable under any
-particular circumstance, the balance of the section is intended to apply,
-and the section as a whole is intended to apply in other circumstances.
-
-It is not the purpose of this section to induce you to infringe any
-patents or other property right claims or to contest validity of any
-such claims; this section has the sole purpose of protecting the
-integrity of the free software distribution system which is
-implemented by public license practices.  Many people have made
-generous contributions to the wide range of software distributed
-through that system in reliance on consistent application of that
-system; it is up to the author/donor to decide if he or she is willing
-to distribute software through any other system and a licensee cannot
-impose that choice.
-
-This section is intended to make thoroughly clear what is believed to
-be a consequence of the rest of this License.
-
-  12. If the distribution and/or use of the Library is restricted in
-certain countries either by patents or by copyrighted interfaces, the
-original copyright holder who places the Library under this License may add
-an explicit geographical distribution limitation excluding those countries,
-so that distribution is permitted only in or among countries not thus
-excluded.  In such case, this License incorporates the limitation as if
-written in the body of this License.
-
-  13. The Free Software Foundation may publish revised and/or new
-versions of the Lesser 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 Library
-specifies a version number of this License which applies to it and
-"any later version", you have the option of following the terms and
-conditions either of that version or of any later version published by
-the Free Software Foundation.  If the Library does not specify a
-license version number, you may choose any version ever published by
-the Free Software Foundation.
-
-  14. If you wish to incorporate parts of the Library into other free
-programs whose distribution conditions are incompatible with these,
-write to the author to ask for permission.  For software which is
-copyrighted by the Free Software Foundation, write to the Free
-Software Foundation; we sometimes make exceptions for this.  Our
-decision will be guided by the two goals of preserving the free status
-of all derivatives of our free software and of promoting the sharing
-and reuse of software generally.
-
-			    NO WARRANTY
-
-  15. BECAUSE THE LIBRARY IS LICENSED FREE OF CHARGE, THERE IS NO
-WARRANTY FOR THE LIBRARY, TO THE EXTENT PERMITTED BY APPLICABLE LAW.
-EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT HOLDERS AND/OR
-OTHER PARTIES PROVIDE THE LIBRARY "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
-LIBRARY IS WITH YOU.  SHOULD THE LIBRARY PROVE DEFECTIVE, YOU ASSUME
-THE COST OF ALL NECESSARY SERVICING, REPAIR OR CORRECTION.
-
-  16. IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN
-WRITING WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MAY MODIFY
-AND/OR REDISTRIBUTE THE LIBRARY 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
-LIBRARY (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 LIBRARY TO OPERATE WITH ANY OTHER SOFTWARE), EVEN IF
-SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF SUCH
-DAMAGES.
-
-		     END OF TERMS AND CONDITIONS
-
-           How to Apply These Terms to Your New Libraries
-
-  If you develop a new library, and you want it to be of the greatest
-possible use to the public, we recommend making it free software that
-everyone can redistribute and change.  You can do so by permitting
-redistribution under these terms (or, alternatively, under the terms of the
-ordinary General Public License).
-
-  To apply these terms, attach the following notices to the library.  It is
-safest to attach them to the start of each source file to most effectively
-convey 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 library's name and a brief idea of what it does.>
-    Copyright (C) <year>  <name of author>
-
-    This library is free software; you can redistribute it and/or
-    modify it under the terms of the GNU Lesser General Public
-    License as published by the Free Software Foundation; either
-    version 2.1 of the License, or (at your option) any later version.
-
-    This library 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
-    Lesser General Public License for more details.
-
-    You should have received a copy of the GNU Lesser General Public
-    License along with this library; if not, write to the Free Software
-    Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
-
-Also add information on how to contact you by electronic and paper mail.
-
-You should also get your employer (if you work as a programmer) or your
-school, if any, to sign a "copyright disclaimer" for the library, if
-necessary.  Here is a sample; alter the names:
-
-  Yoyodyne, Inc., hereby disclaims all copyright interest in the
-  library `Frob' (a library for tweaking knobs) written by James Random Hacker.
-
-  <signature of Ty Coon>, 1 April 1990
-  Ty Coon, President of Vice
-
-That's all there is to it!

jhove/LICENSE

@@ -1,17 +0,0 @@
-JHOVE - JSTOR/Harvard Object Validation Environment
-Copyright 2003-2008 by JSTOR and the President and Fellows of Harvard College
-
-This program is free software; you can redistribute it and/or modify
-it under the terms of the GNU Lessor General Public License as
-published by the Free Software Foundation; either version 2.1 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
-Lesser General Public License for more details.
-
-You should have received a copy of the GNU Lesser General Public
-License along with this program; if not, write to the Free Software
-Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307
-USA

jhove/README

@@ -1,227 +0,0 @@
-JHOVE - JSTOR/Harvard Object Validation Environment
-Copyright 2003-2012 by JSTOR and the President and Fellows of Harvard College
-JHOVE is made available under the GNU Lesser General Public License (LGPL;
-see the file LICENSE for details)
-
-Rev. 1.9, 2012-12-17
-
-JHOVE (the JSTOR/Harvard Object Validation Environment, pronounced "jhove")
-is an extensible software framework for performing format identification,
-validation, and characterization of digital objects.
-
-o Format identification is the process of determining the format to which a
-  digital object conforms: "I have a digital object; what format is it?"
-o Format validation is the process of determining the level of compliance of a
-  digital object to the specification for its purported format: "I have an
-  object purportedly of format F; is it?"
-o Format characterization is the process of determing the format-specific
-  significant properties of an object of a given format: "I have an object of
-  format F; what are its salient properties?"
-
-These actions are frequently necessary during routine operation of digital
-repositories and for digital preservation activities.
-
-The output from JHOVE is controlled by output handlers. JHOVE uses an
-extensible plug-in architecture; it can be configured at the time of its
-invocation to include whatever specific format modules and output handlers
-that are desired. The initial release of JHOVE includes modules for
-arbitrary byte streams, ASCII and UTF-8 encoded text, AIFF and WAVE audio,
-GIF, JPEG, JPEG 2000, TIFF, and PDF; and text and XML output handlers.
-
-The JHOVE project is a collaboration of JSTOR and the Harvard University
-Library.  Development of JHOVE was funded in part by the Andrew W. Mellon
-Foundation.  JHOVE is made available under the GNU Lesser General Public
-License (LGPL; see the file LICENSE for details).
-
-JHOVE is currently being maintained by indpendent developers.
-
-REQUIREMENTS
-
-1. Java J2SE 1.5
-(JHOVE was originally implemented using the Sun J2SE SDK 1.4.1 and has
-been tested to work with 1.5)
-
-2. If you would like to compile the JHOVE source code, then
-Apache Ant, a Java-based build tool <http://ant.apache.org/> is necessary.
-Note that the JAVA_HOME environment variable must be set appropriately for
-Ant to work properly.
-(JHOVE was implemented and tested using Ant 1.5.1.)
-
-DISTRIBUTION
-
-The JHOVE distribution package includes:
-
-    jhove/                                 # JHOVE home directory
-          COPYING                          # GNU Lesser General Public License
-          LICENSE                          # JHOVE license information
-          README
-          RELEASENOTES                     # JHOVE release notes
-          bin/
-                    jhove.jar              # JHOVE API package
-                    jhove-handler.jar      # Standard output handler package
-                    jhove-module.jar       # Standard module package
-                    JhoveApp.jar           # JHOVE command line application
-                    JhoveView.jar          # JHOVE with Swing GUI front-end
-          build.xml                        # Ant configuration file
-          classes/
-                    build.xml              # Ant configuration file
-                    edu/ ...               # JHOVE API packages
-                    ADump.*                # AIFF dump utility class
-                    GDump.*                # GIF dump utility class
-                    Jhove.*                # JHOVE main class
-                    JDump.*                # JPEG dump utility class
-                    J2Dump.*               # JPEG 2000 dump utility class
-                    PDump.*                # PDF dump utility class
-                    TDump.*                # TIFF dump utility class
-                    UserHome.*             # user.home property utility class
-                    WDump.*                # WAVE dump utility class
-          conf/
-                   jhove.conf              # JHOVE configuration file
-                   jhove.xsd               # JHOVE output schema
-                   jhoveConfig.xsd         # JHOVE configuration file schema
-          doc/
-                   *.html                  # API documentation
-                   ...
-          examples/                        # Sample files
-                   ascii/ ...
-                   gif/   ...
-                   jpeg/  ...
-                   jpeg2000/ ...
-                   pdf/   ...
-                   tiff/  ...
-                   utf-8/ ...
-          adump*                           # AIFF dump Bourne shell driver
-          adump.bat*                       # AIFF dump DOS shell driver script
-          gdump*                           # GIF dump Bourne shell driver
-          gdump.bat*                       # GIF dump DOS shell driver script
-          jdump*                           # JPEG dump Bourne shell driver
-          jdump.bat*                       # JPEG dump DOS shell driver script
-          j2dump*                          # JPEG 2000 dump Bourne shell driver
-          j2dump.bat*                      # JPEG 2000 dump DOS shell driver
-          jhove.tmpl*                      # Template for JHOVE Bourne shell driver script
-          jhove_bat.tmpl*                  # Template for JHOVE DOS shell driver script
-          pdump*                           # PDF dump Bourne shell driver
-          pdump.bat*                       # PDF dump DOS shell driver script
-          tdump*                           # TIFF dump Bourne shell driver
-          tdump.bat*                       # TIFF dump DOS shell driver script
-          userhome*                        # user.home Bourne shell driver
-          userhome.bat*                    # user.home DOS shell driver script
-          wdump*                           # WAVE dump Bourne shell driver
-          wdump.bat*                       # WAVE dump DOS shell driver script
-
-INSTALLATION
-
-Edit the configuration file, jhove/conf/jhove.conf, and set the absolute
-pathname of the JHOVE home directory and the temporary directory (in which
-temporary files are created):
-
-    <jhoveHome>jhove-home-directory</jhoveHome>
-    <tempDirectory>temporary-directory</tempDirectory>
-
-The JHOVE home directory is the top-most directory in the distribution TAR
-or ZIP file.  On Unix systems, "/var/tmp" is an appropriate temporary
-directory; on Windows, "C:\Temp".  For example, if the distribution TAR
-file is disaggregated on a Unix system in the directory "/users/stephen/
-projects", then the configuration file should read:
-
-    <jhoveHome>/users/stephen/projects/jhove</jhoveHome>
-    <tempDirectory>/var/tmp</jhoveHome>
-
-In the JHOVE home directory, copy the JHOVE Bourne shell driver script
-template, "jhove.tmpl", to "jhove" (or the equivalent Windows shell 
-script, "jhove_bat.tmpl" to "jhove.bat"), and set the
-JHOVE home directory, Java home directory, and Java interpreter:
-
-    JHOVE_HOME=jhove-home-directory
-    JAVA_HOME=java-home-directory
-    JAVA=java-interpreter
-
-The JAVA_HOME property should provide the absolute pathname of the Java
-runtime or SDK installation; JAVA should provide the absolute pathname of the
-Java interpreter.  For example:
-
-    JHOVE_HOME=/users/stephen/projects/jhove
-    JAVA_HOME=/usr/local/j2re1.4.1_02
-    JAVA=$JAVA_HOME/bin/java
-
-In the DOS shell driver script, jhove.bat, the equivalent three
-variables are:
-
-    SET JHOVE_HOME=jhove-home-directory
-    SET JAVA_HOME=java-home-directory
-    SET JAVA=%JAVA_HOME%\bin\java
-
-For example:
-
-    SET JHOVE_HOME="C:\Program Files\jhove"
-    SET JAVA_HOME="C:\Program Files\java\j2re1.4.1_02"
-    SET JAVA=%JAVA_HOME%\bin\java
-
-The quotation marks are necessary because of the embedded space characters.
-On Windows platforms it may also be necessary to add the Java bin subdirectory
-to the System PATH environment variable:
-
-    PATH=C:\Program Files\java\j2re1.4.1_02\bin;...
-
-(For information on setting a Windows environment variable, consult your local
-documentation or system administrator.)
-
-USAGE
-
-    java Jhove [-c config] [-m module] [-h handler] [-e encoding] [-H handler]
-               [-o output] [-x saxclass] [-t tempdir] [-b bufsize]
-               [-l loglevel] [[-krs] dir-file-or-uri [...]]
-
-where -c config   Configuration file pathname
-      -m module   Module name
-      -h handler  Output handler name (defaults to TEXT)
-      -e encoding Character encoding used by output handler (defaults to UTF-8)
-      -H handler  About handler name
-      -o output   Output file pathname (defaults to standard output)
-      -x saxclass SAX parser class (defaults to J2SE default)
-      -t tempdir  Temporary directory in which to create temporary files
-      -b bufsize  Buffer size for buffered I/O (defaults to J2SE 1.4 default)
-      -l loglevel Logging level
-      -k          Calculate CRC32, MD5, and SHA-1 checksums
-      -r          Display raw data flags, not textual equivalents
-      -s          Format identification based on internal signatures only
-      dir-file-or-uri Directory or file pathname or URI of formated content
-                      stream
-
-All named modules and output handlers must be found on the Java CLASSPATH at
-the time of invocation.  The JHOVE driver script, jhove/jhove, automatically
-sets the CLASSPATH and invokes the Jhove main class:
-
-    jhove [-c config] [-m module] [-h handler] [-e encoding] [-H handler]
-          [-o output] [-x saxclass] [-t tempdir] [-b bufsize] [-l loglevel]
-          [[-krs] dir-file-or-uri [...]]
-
-The following additional programs are available, primarily for testing
-and debugging purposes.  They display a minimally processed, human-readable
-version of the contents of AIFF, GIF, JPEG, JPEG 2000, PDF, TIFF, and WAVE
-files:
-
-    java ADump  aiff-file
-    java GDump  gif-file
-    java JDump  jpeg-file
-    java J2Dump jpeg2000-file
-    java PDump  pdf-file
-    java TDump  tiff-file
-    java WDump  wave-file
-
-For convenience, the following driver scripts are also available:
-
-    adump  aiff-file
-    gdump  gif-file
-    jdump  jpeg-file
-    j2dump jpeg2000-file
-    pdump  pdf-file
-    tdump  tiff-file
-    wdump  wave-file
-
-The JHOVE Swing-based GUI interface can be invoked from a command shell from
-the jhove/bin sub-directory:
-
-    java -jar JhoveView.jar -c <configFile>
-
-where <configFile> is the pathname of the JHOVE configuration file.

jhove/build.xml

@@ -1,78 +0,0 @@
-<project name="Jhove" default="dist" basedir=".">
-  <description>Project build file
-    Jhove - JSTOR/Harvard Object Validation Environment
-    Version 1.0 2004-09-10
-    Copyright 2004 by JSTOR and the President and Fellows of Harvard College
-  </description>
-
-  <!-- ant (or ant dist) Build everything
-       ant debug         Build everything with debug enabled
-       ant clean         Delete backup files
-       ant cleanclass    Delete backup and class files
-       ant cleandist     Delete backup, class, and jar files
-       ant javadoc       Build javadocs
-    -->
-
-  <!-- set global properties for this build -->
-  <property name="bin"     location="bin"/>
-  <property name="classes" location="classes"/>
-  <property name="doc"     location="doc"/>
-
-  <target name="dist" description="Create distribution">
-    <ant dir="${classes}" inheritAll="false">
-      <property name="dbg" value="off"/>
-    </ant>
-  	<chmod file="jhove" perm="ugo+x"/>
-  	<chmod file="${bin}/JhoveView.jar" perm="ugo+x"/>
-  </target>
-
-  <target name="debug" description="Create distribution with debug enabled">
-    <ant dir="${classes}" inheritAll="false">
-      <property name="dbg" value="on"/>
-    </ant>
-  </target>
-
-  <target name="view" description="Create JhoveView application">
-    <ant dir="${classes}" target="view" inheritAll="false">
-      <property name="dbs" value="on"/>
-    </ant>
-  </target>
-
-  <target name="clean" description="Delete backup files">
-    <ant dir="${classes}" target="main-clean" inheritAll="false"/>
-  </target>
-
-  <target name="cleanclass" depends="clean">
-    <ant dir="${classes}" target="main-cleanclass" inheritAll="false"/>
-  </target>
-
-  <target name="cleandist" depends="cleanclass">
-    <delete file="${bin}/jhove.jar"/>
-    <delete file="${bin}/jhove-handler.jar"/>
-    <delete file="${bin}/jhove-module.jar"/>
-    <delete file="${bin}/JhoveApp.jar"/>
-    <delete file="${bin}/JhoveView.jar"/>
-  </target>
-
-  <target name="javadoc">
-    <javadoc sourcepath="${classes}" destdir="${doc}"
-             windowtitle="JHOVE Documentation"
-             Overview="${classes}/overview.html">
-      <package name="edu.harvard.hul.ois.jhove"/>
-      <package name="edu.harvard.hul.ois.jhove.handler"/>
-      <package name="edu.harvard.hul.ois.jhove.handler.audit"/>
-      <package name="edu.harvard.hul.ois.jhove.module"/>
-      <package name="edu.harvard.hul.ois.jhove.module.aiff"/>
-      <package name="edu.harvard.hul.ois.jhove.module.gif"/>
-      <package name="edu.harvard.hul.ois.jhove.module.html"/>
-      <package name="edu.harvard.hul.ois.jhove.module.iff"/>
-      <package name="edu.harvard.hul.ois.jhove.module.jpeg"/>
-      <package name="edu.harvard.hul.ois.jhove.module.jpeg2000"/>
-      <package name="edu.harvard.hul.ois.jhove.module.pdf"/>
-      <package name="edu.harvard.hul.ois.jhove.module.tiff"/>
-      <package name="edu.harvard.hul.ois.jhove.module.wave"/>
-      <package name="edu.harvard.hul.ois.jhove.module.xml"/>
-      <package name="edu.harvard.hul.ois.jhove.viewer"/>
-    </javadoc>
-  </target>
-</project>

jhove/classes/ADump.java

@@ -1,235 +0,0 @@
-/**********************************************************************
- * JDump - JSTOR/Harvard Object Validation Environment
- * Copyright 2004-2005 by the President and Fellows of Harvard College
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU Lesser General Public License as published by
- * the Free Software Foundation; either version 2 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
- * Lesser General Public License for more details.
- * 
- * You should have received a copy of the GNU Lesser General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307
- * USA
- **********************************************************************/
-
-import edu.harvard.hul.ois.jhove.*;
-import edu.harvard.hul.ois.jhove.module.aiff.*;
-import java.io.*;
-
-/**
- * Dump contents of AIFF file in human-readable format.
- * @author Gary McGath
- */
-public class ADump extends Dump {
-
-    /* Fixed value for first 4 bytes */
-    private static final int[] sigByte =
-       { 0X46, 0X4F, 0X52, 0X4D };
-    private static final boolean ENDIAN = true;     /* bigEndian */
-
-    /******************************************************************
-     * MAIN ENTRY POINT.
-     ******************************************************************/
-
-    /**
-     * Main entry point.
-     * @param args Command line arguments
-     */
-    public static void main (String [] args)
-    {
-        if (args.length < 1) {
-            System.err.println ("usage: java ADump file");
-            System.exit (-1);
-        }
-        try {
-            FileInputStream file = new FileInputStream (args[0]);
-            BufferedInputStream buffer = new BufferedInputStream (file);
-            DataInputStream stream = new DataInputStream (buffer);
-            ADump dump = new ADump ();   // Just to access contained classes
-            long os = 0;
-            for (int i=0; i<4; i++) {
-                int ch;
-                ch = stream.readUnsignedByte();
-                if (ch != sigByte[i]) {
-                    System.out.println ("No AIFF FORM header");
-                    System.exit (-2);
-                }
-            }
-            os += 4;
-            long ckSize = ModuleBase.readUnsignedInt (stream, ENDIAN);
-            
-            // Read the file type
-            StringBuffer formType = new StringBuffer (4);
-            for (int i=0; i<4; i++) {
-                int ch = ModuleBase.readUnsignedByte(stream);
-                formType.append((char) ch);
-            }
-	    System.out.println ("00000000: FORM " + ckSize + ": " + formType);
-
-	    boolean aiff_c = false;
-	    if (formType.toString ().equals ("AIFC")) {
-		aiff_c = true;
-	    }
-
-            StringBuffer sbuf = new StringBuffer ();
-            boolean endOfFile = false;
-            while (!endOfFile) {
-                // Read chunks
-                try {
-                    sbuf.setLength(0);
-                    // Read chunk name.
-                    for (int i=0; i<4; i++) {
-                        int ch = ModuleBase.readUnsignedByte(stream);
-                        sbuf.append((char) ch);
-                    }
-                    String ckID = sbuf.toString ();
-                    // Read size (excluding chunk name and size fields)
-		    ckSize = ModuleBase.readUnsignedInt (stream, ENDIAN);
-                    System.out.print (leading (os, 8) + os + ": " + ckID +
-				      " " + ckSize);
-		    long alreadyRead = 0;
-		    if (ckID.equals ("AESD")) {
-			int [] aes = new int[24];
-			for (int i=0; i<24; i++) {
-			    aes[i] = ModuleBase.readUnsignedByte (stream);
-			    
-			}
-			System.out.print (": " + aes[0]);
-			for (int i=1; i<24; i++) {
-			    System.out.print ("," + aes[i]);
-			}
-			alreadyRead = 24;
-		    }
-		    else if (ckID.equals ("ANNO") ||
-			     ckID.equals ("AUTH") ||
-			     ckID.equals ("(c) ") ||
-			     ckID.equals ("NAME")) {
-			sbuf.setLength (0);
-			for (int i=0; i<ckSize; i++) {
-			    int ch = ModuleBase.readUnsignedByte (stream);
-			    sbuf.append ((char) ch);
-			}
-			System.out.print (": \"" + sbuf.toString () + "\"");
-			alreadyRead = ckSize;
-		    }
-		    else if (ckID.equals ("APPL")) {
-			sbuf.setLength (0);
-			for (int i=0; i<4; i++) {
-			    int ch = ModuleBase.readUnsignedByte (stream);
-			    sbuf.append ((char) ch);
-			}
-			System.out.print (": " + sbuf.toString ());
-			alreadyRead = 4;
-		    }
-		    else if (ckID.equals ("COMM")) {
-			int numChannels = ModuleBase.readSignedShort (stream,
-								      ENDIAN);
-			long numSampleFrames =
-			    ModuleBase.readUnsignedInt (stream, ENDIAN);
-			int sampleSize = ModuleBase.readSignedShort (stream,
-								     ENDIAN);
-			byte [] buf = new byte[10];
-			for (int i=0; i<10; i++) {
-			    buf[i] = (byte) ModuleBase.readSignedByte (stream);
-			}
-			ExtDouble xd = new ExtDouble (buf);
-			double sampleRate = xd.toDouble ();
-
-			System.out.print (": " + numChannels + " " +
-					  numSampleFrames + " " + sampleSize +
-					  " " + sampleRate);
-			alreadyRead = 18;
-
-			if (aiff_c) {
-			    sbuf.setLength (0);
-			    for (int i=0; i<4; i++) {
-				int ch = ModuleBase.readUnsignedByte (stream,
-								      null);
-				sbuf.append ((char) ch);
-			    }
-			    System.out.print (" " + sbuf.toString ());
-
-			    int count = ModuleBase.readUnsignedByte (stream,
-								     null);
-			    alreadyRead = 23;
-			    sbuf.setLength (0);
-			    for (int i=0; i<count; i++) {
-				int ch = ModuleBase.readUnsignedByte (stream,
-								      null);
-				sbuf.append ((char) ch);
-
-				alreadyRead++;
-			    }
-			    System.out.print (" \"" + sbuf.toString () + "\"");
-			}
-
-		    }
-		    else if (ckID.equals ("COMT")) {
-			int numComments = ModuleBase.readUnsignedShort (stream,
-									ENDIAN,
-									null);
-			System.out.print (": " + numComments);
-			alreadyRead = 2;
-		    }
-		    else if (ckID.equals ("FVER")) {
-			long timestamp = ModuleBase.readUnsignedInt (stream,
-								     ENDIAN,
-								     null);
-			System.out.print (": " + timestamp);
-			alreadyRead = 4;
-		    }
-		    else if (ckID.equals ("INST")) {
-			int baseNote = ModuleBase.readSignedByte (stream);
-			int detune = ModuleBase.readSignedByte (stream);
-			int lowNote = ModuleBase.readSignedByte (stream);
-			int highNote = ModuleBase.readSignedByte (stream);
-			int lowVelocity = ModuleBase.readSignedByte (stream);
-			int highVelocity = ModuleBase.readSignedByte (stream);
-			int gain = ModuleBase.readSignedShort (stream, ENDIAN);
-
-			System.out.print (": " + baseNote + " " + detune +
-					  " " + lowNote + "," + highNote +
-					  " " + lowVelocity + "," +
-					  highVelocity + " " + gain);
-			alreadyRead = 8;
-		    }
-		    else if (ckID.equals ("MARK")) {
-			int numMarkers = ModuleBase.readUnsignedShort (stream,
-								       ENDIAN);
-			System.out.print (": " + numMarkers);
-			alreadyRead = 2;
-		    }
-		    else if (ckID.equals ("SSND")) {
-			long offset = ModuleBase.readUnsignedInt (stream,
-								  ENDIAN);
-			long blockSize = ModuleBase.readUnsignedInt (stream,
-								     ENDIAN);
-			System.out.print (": " + offset + " " + blockSize);
-			alreadyRead = 8;
-		    }
-		    System.out.println ();
-
-                    // Actual number of bytes to skip must be even.
-                    long actSize = ckSize;
-                    if ((actSize & 1) != 0) {
-                        actSize++;
-                    }
-		    actSize -= alreadyRead;
-                    stream.skipBytes ((int) actSize);
-                    os += ckSize + 8;
-                }
-                catch (EOFException e) {
-                    endOfFile = true;
-                }
-            }
-        }
-        catch (Exception e) {
-        }
-    }
-}

jhove/classes/GDump.java

@@ -1,264 +0,0 @@
-/**********************************************************************
- * GDump - JSTOR/Harvard Object Validation Environment
- * Copyright 2004 by the President and Fellows of Harvard College
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU Lesser General Public License as published by
- * the Free Software Foundation; either version 2 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
- * Lesser General Public License for more details.
- * 
- * You should have received a copy of the GNU Lesser General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307
- * USA
- **********************************************************************/
-
-import edu.harvard.hul.ois.jhove.*;
-import java.io.*;
-//import java.util.*;
-
-/**
- * Dump contents of GIF file in human-readable format.
- */
-public class GDump
-    extends Dump
-{
-    /******************************************************************
-     * MAIN ENTRY POINT.
-     ******************************************************************/
-
-    /**
-     * Main entry point.
-     * @param args Command line arguments
-     */
-    public static void main (String [] args)
-    {
-	if (args.length < 1) {
-	    System.err.println ("usage: java GDump file");
-	    System.exit (-1);
-	}
-
-	try {
-	    FileInputStream file = new FileInputStream (args[0]);
-	    BufferedInputStream buffer = new BufferedInputStream (file);
-	    DataInputStream stream = new DataInputStream (buffer);
-	    boolean bigEndian = false;
-
-	    String signature = readChars (stream, 3);
-	    String version   = readChars (stream, 3);
-	    System.out.println ("00000000: \"" + signature + version + "\"");
-
-	    int width  = ModuleBase.readUnsignedShort(stream, bigEndian, null);
-	    int height = ModuleBase.readUnsignedShort(stream, bigEndian, null);
-	    int packedFields    = stream.readUnsignedByte ();
-	    int backgroundColor = stream.readUnsignedByte ();
-	    int aspectRatio     = stream.readUnsignedByte ();
-	    System.out.println ("00000006: LogicalScreenDescriptor: " +
-				width + "x" + height + " 0x" +
-				leading (packedFields, 2) +
-				Integer.toHexString (packedFields) + " " +
-				backgroundColor + " " + aspectRatio);
-	    long os = 13;
-
-	    boolean globalColorTable     = (packedFields & 0x80) != 0;
-	    int     globalColorTableSize =  packedFields & 0x07;
-
-	    if (globalColorTable) {
-		System.out.println (leading (os, 8) + os +
-				    ": GlobalColorTable:");
-		os = colorTable (stream, os, globalColorTableSize);
-	    }
-
-	    for (int op = 0; (op = stream.readUnsignedByte ()) != -1;) {
-		if (op == 0x00) {
-		    System.out.println (leading (os, 8) + os + 
-					": BlockTerminator");
-		    os++;
-		}
-		else if (op == 0x2c) {
-		    int imageLeft   = ModuleBase.readUnsignedShort (stream,
-								    bigEndian,
-								    null);
-		    int imageTop    = ModuleBase.readUnsignedShort (stream,
-								    bigEndian,
-								    null);
-		    int imageWidth  = ModuleBase.readUnsignedShort (stream,
-								    bigEndian,
-								    null);
-		    int imageHeight = ModuleBase.readUnsignedShort (stream,
-								    bigEndian,
-								    null);
-		    packedFields = stream.readUnsignedByte ();
-		    System.out.println (leading (os, 8) + os +
-					": ImageDescriptor: " + imageLeft +
-					"," + imageTop + " " + imageWidth +
-					"x" + imageHeight + " 0x" +
-					leading (packedFields, 2) +
-					Integer.toHexString (packedFields));
-		    os += 10;
-
-		    boolean localColorTable     = (packedFields & 0x80) != 0;
-		    int     localColorTableSize =  packedFields & 0x07;
-
-		    if (localColorTable) {
-			System.out.println (leading (os, 8) + os +
-					    ": LocalColorTable:");
-			os = colorTable (stream, os, localColorTableSize);
-		    }
-
-		    int size = stream.readUnsignedByte ();
-		    System.out.println (leading (os, 8) + os +
-					": ImageData: " + size);
-		    os = subBlocks (stream, ++os);
-		}
-		else if (op == 0x21) {
-		    int label = stream.readUnsignedByte ();
-
-		    if (label == 0x01) {
-			int blockSize = stream.readUnsignedByte ();
-			int gridLeft  = ModuleBase.readUnsignedShort(stream,
-								     bigEndian,
-								     null);
-			int gridTop   = ModuleBase.readUnsignedShort(stream,
-								     bigEndian,
-								     null);
-			int gridWidth = ModuleBase.readUnsignedShort(stream,
-								     bigEndian,
-								     null);
-			int gridHeight= ModuleBase.readUnsignedShort(stream,
-								     bigEndian,
-								     null);
-			int cellWidth  = stream.readUnsignedByte ();
-			int cellHeight = stream.readUnsignedByte ();
-			int foreground = stream.readUnsignedByte ();
-			int background = stream.readUnsignedByte ();
-			System.out.println (leading (os, 8) + os + 
-					    ": PlainTextExtension: " +
-					    blockSize + " " + gridLeft + "," +
-					    gridTop + " " + gridWidth + "x" +
-					    gridHeight + " " + cellWidth +
-					    "x" + cellHeight + " " +
-					    foreground + "," + background);
-			os += 15;
-			os = subBlocks (stream, os);
-		    }
-		    else if (label == 0xf9) {
-			int blockSize = stream.readUnsignedByte ();
-			packedFields  = stream.readUnsignedByte ();
-			int delayTime = ModuleBase.readUnsignedShort(stream,
-								     bigEndian,
-								     null);
-			int colorIndex= stream.readUnsignedByte ();
-			System.out.println (leading (os, 8) + os +
-					    ": GraphicControlExtension: " +
-					    blockSize + " 0x" +
-					    leading (packedFields, 2) +
-					    packedFields + " " + delayTime +
-					    " " + colorIndex);
-			os += 7;
-		    }
-		    else if (label == 0xfe) {
-			System.out.println (leading (os, 8) + os + 
-					    ": CommentExtension: \"" +
-					    "\"");
-			os += 2;
-			os = subBlocks (stream, os);
-		    }
-		    else if (label == 0xff) {
-			int blockSize = stream.readUnsignedByte ();
-			String appId  = readChars (stream, 8);
-			int [] authCode = new int [3];
-			authCode[0]   = stream.readUnsignedByte ();
-			authCode[1]   = stream.readUnsignedByte ();
-			authCode[2]   = stream.readUnsignedByte ();
-			System.out.println (leading (os, 8) + os + 
-					    ": ApplicationExtension: " +
-					    blockSize + " \"" + appId +
-					    "\" " + authCode[0] + "," +
-					    authCode[1] + "," + authCode[2]);
-			os += 14;
-			os = subBlocks (stream, os);
-		    }
-		    else {
-			String hex = Integer.toHexString (label);
-			System.out.println (leading (os-1, 8) + (os-1) +
-					    ": Unknown extension block: 0x" +
-					    leading (hex, 2) + hex);
-			os += 2;
-		    }
-		}
-		else if (op == 0x3b) {
-		    System.out.println (leading (os, 8) + os +
-					": Trailer: 0x3b");
-		    os++;
-		    break;
-		}
-		else {
-		    String hex = Integer.toHexString (op);
-		    System.out.println (leading (os, 8) + os +
-					": Unknown block: 0x" +
-					leading (hex, 2) +  hex);
-		    os++;
-		}
-	    }
-	    stream.close ();
-	}
-	catch (Exception e) {
-	    e.printStackTrace (System.err);
-	    System.exit (-2);
-	}
-    }
-
-    /**
-     * Read and display a color table.
-     * @param stream Data input stream
-     * @param os     Current byte offset
-     * @param size   Color table size
-     * @return Updated byte offset
-     */
-    private static long colorTable (DataInputStream stream, long os, int size)
-	throws IOException
-    {
-	int n = 2<<size;
-	for (int i=0; i<n; i++) {
-	    long r = stream.readUnsignedByte ();
-	    long g = stream.readUnsignedByte ();
-	    long b = stream.readUnsignedByte ();
-	    System.out.println (leading (os, 8) + os + ": " +
-				leading (i, 3, ' ') + i + ": " +
-				leading (r, 3, ' ') + r + "," +
-				leading (g, 3, ' ') + g + "," +
-				leading (b, 3, ' ') + b);
-	    os += 3;
-	}
-	return os;
-    }
-
-    /**
-     * Read and display a sequence of sub-blocks.
-     * @param stream Data input stream
-     * @param os     Current byte offset
-     * @return Updated byte offset
-     */
-    private static long subBlocks (DataInputStream stream, long os)
-	throws IOException
-    {
-	int size;
-
-	while ((size = stream.readUnsignedByte ()) != 0) {
-	    System.out.println (leading (os, 8) + os + ": SubBlock: " + size);
-	    os += 1;
-	    for (int i=0; i<size; i++) {
-		stream.readUnsignedByte ();
-		os += 1;
-	    }
-	}
-	System.out.println (leading (os, 8) + os +  ": BlockTerminator");
-	return os + 1;
-    }
-}

jhove/classes/J2Dump.java

@@ -1,216 +0,0 @@
-/**********************************************************************
- * JDump - JSTOR/Harvard Object Validation Environment
- * Copyright 2004 by the President and Fellows of Harvard College
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU Lesser General Public License as published by
- * the Free Software Foundation; either version 2 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
- * Lesser General Public License for more details.
- * 
- * You should have received a copy of the GNU Lesser General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307
- * USA
- **********************************************************************/
-
-import edu.harvard.hul.ois.jhove.*;
-import java.io.*;
-import java.util.*;
-
-/**
- * Dump contents of JPEG2000 file in human-readable format.
- */
-public class J2Dump extends Dump {
-
-    /* Fixed value for first 12 bytes */
-    private static final int[] sigByte =
-        {
-            0X00,
-            0X00,
-            0X00,
-            0X0C,
-            0X6A,
-            0X50,
-            0X20,
-            0X20,
-            0X0D,
-            0X0A,
-            0X87,
-            0X0A };
-
-    private static final boolean ENDIAN = true;     /* bigEndian */
-    
-    /******************************************************************
-     * MAIN ENTRY POINT.
-     ******************************************************************/
-
-    /**
-     * Main entry point.
-     * @param args Command line arguments
-     */
-    public static void main (String [] args)
-    {
-        if (args.length < 1) {
-            System.err.println ("usage: java J2Dump file");
-            System.exit (-1);
-        }
-        try {
-            FileInputStream file = new FileInputStream (args[0]);
-            BufferedInputStream buffer = new BufferedInputStream (file);
-            DataInputStream stream = new DataInputStream (buffer);
-            J2Dump dump = new J2Dump ();   // Just to access contained classes
-            long os = 0;
-            boolean bigEndian = true;
-            int i;
-            for (i = 0; i < 12; i++) {
-                int ch;
-                ch = stream.readUnsignedByte();
-                if (ch != sigByte[i]) {
-                    System.out.println ("No JPEG 2000 header");
-                    System.exit (-2);
-                }
-            }
-            os += 12;
-            
-            boolean endOfFile = false;
-            Stack boxStack = new Stack ();
-            while (!endOfFile) {
-                //If there are boxes on the stack, see if there's space
-                //left in the top one.
-                Box boxtop;
-                for (;;) {
-                    boxtop = null;
-                    if (boxStack.isEmpty ()) {
-                        break;
-                    }
-                    boxtop = (Box) boxStack.peek ();
-                    if (boxtop.bytesLeft > 0) {
-                        break;
-                    }
-                    else {
-                        boxStack.pop ();
-                    }
-                }
-                
-                // Read the header of a JP2 box
-                Box box = dump.new Box (stream);
-                try {
-                    box.read ();
-                }
-                catch (EOFException e) {
-                    endOfFile = true;
-                    break;
-                }
-                os += box.length - box.bytesLeft;
-                
-                // If it's contained in a superbox, subtract
-                // this box from its remaining length
-                if (boxtop != null) {
-                    boxtop.bytesLeft -= box.length;
-                }
-                System.out.println (leading (os, 8) + os + ": " + 
-                    stackPrefix (boxStack) + box.type + " " + box.length);
-                if (box.isSuperbox ()) {
-                    boxStack.push (box);
-                }
-                else {
-                    os += box.bytesLeft;
-                    stream.skipBytes((int) box.bytesLeft);
-                }
-                
-                // A "length" of 0 means the box occupies the rest of the file.
-                if (box.length == 0) {
-                    endOfFile = true;
-                }
-            }
-        }
-        catch (Exception e) {
-            e.printStackTrace (System.err);
-            System.exit (-2);
-        }
-    }
-
-
-    /* Constructs a qualifying prefix to indicate nested boxes. */
-    private static String stackPrefix (Stack boxStack)
-    {
-        StringBuffer retval = new StringBuffer ();
-        // In defiance of gravity, we rummage through the stack
-        // of boxes starting at the bottom.
-        for (int i = 0; i < boxStack.size(); i++) {
-            Box box = (Box) boxStack.elementAt (i);
-            // Remove trailing spaces from types for better readability
-            retval.append (box.type.trim() + "/");
-        }
-        return retval.toString ();
-    }
-
-
-
-    /** Local class for defining JPEG2000 boxes. */
-    class Box {
-        public String type;
-        public long length;
-        public long bytesLeft;
-        public boolean hasBoxes;
-        DataInputStream dstream;
-        
-        public Box (DataInputStream stream)
-        {
-            this.dstream = stream;
-        }
-        
-        
-        /** Reads a box header and sets up for reading contents. */
-        public void read () throws IOException
-        {
-            length = ModuleBase.readUnsignedInt (dstream, ENDIAN, null);
-            long headerLength = 8;
-            type = read4Chars ();
-            // If the length field is 1, there is an 8-byte extended
-            // length field.
-            if (length == 1) {
-                length = ModuleBase.readSignedLong(dstream, true, null);
-                headerLength = 16;
-            }
-            bytesLeft = length - headerLength;
-        }
-
-
-        /* Reads a 4-character name */
-        private String read4Chars() throws IOException {
-            StringBuffer sbuf = new StringBuffer(4);
-            for (int i = 0; i < 4; i++) {
-                int ch = ModuleBase.readUnsignedByte(dstream, null);
-                sbuf.append((char) ch);
-            }
-            return sbuf.toString();
-        }
-
-        /** Returns true if this box contains other boxes.
-         *  At present, we don't deal with the insides of boxes
-         *  that contain both data and boxes (e.g., cref). */
-        public boolean isSuperbox ()
-        {
-            // If it's a known superbox type, we return true.
-            // If we've left any out, that will merely make us
-            // lose the subboxes of that type.
-            String [] supertypes = { "asoc", "cgrp", "comp", "drep",
-                "ftbl", "jp2h", "jpch",
-                "jplh", "res ", "uuid" };
-            for (int i = 0; i < supertypes.length; i++) {
-                if (supertypes[i].equals (type)) {
-                    return true;
-                }
-            }
-            return false;
-        }
-    }
-
-
-}

jhove/classes/JDump.java

@@ -1,404 +0,0 @@
-/**********************************************************************
- * JDump - JSTOR/Harvard Object Validation Environment
- * Copyright 2004 by the President and Fellows of Harvard College
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU Lesser General Public License as published by
- * the Free Software Foundation; either version 2 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
- * Lesser General Public License for more details.
- * 
- * You should have received a copy of the GNU Lesser General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307
- * USA
- **********************************************************************/
-
-import edu.harvard.hul.ois.jhove.*;
-import java.io.*;
-//import java.util.*;
-
-/**
- * Dump contents of JPEG file in human-readable format.
- */
-public class JDump
-    extends Dump
-{
-    /******************************************************************
-     * MAIN ENTRY POINT.
-     ******************************************************************/
-
-    /**
-     * Main entry point.
-     * @param args Command line arguments
-     */
-    public static void main (String [] args)
-    {
-	if (args.length < 1) {
-	    System.err.println ("usage: java JDump file");
-	    System.exit (-1);
-	}
-
-	try {
-	    FileInputStream file = new FileInputStream (args[0]);
-	    BufferedInputStream buffer = new BufferedInputStream (file);
-	    DataInputStream stream = new DataInputStream (buffer);
-	    boolean bigEndian = true;
-
-	    long os = 0;
-
-	    boolean endOfImage = false;
-	    boolean readingECS = false;
-	    boolean haveCode   = false;;
-	    int nECS = 0;
-	    int code = 0;
-	    while (!endOfImage) {
-		if (!readingECS) {
-		    if (!haveCode) {
-			code = stream.readUnsignedByte ();
-			for (int i=0;
-			     (code = stream.readUnsignedByte ()) == 0xff;
-			     i++) {
-			    System.out.println (leading (os, 8) + os +
-						": fill 0xff");
-			    os++;
-			}
-		    }
-		}
-		else {
-		    boolean ff = false;
-		    int length = 0;
-		    while (true) {
-			code = stream.readUnsignedByte ();
-			length++;
-			if (code == 0xff) {
-			    ff = true;
-			}
-			else if (ff) {
-			    if (code != 0x00) {
-				length -= 2;
-				break;
-			    }
-			    else {
-				ff = false;
-			    }
-			}
-		    }
-		    System.out.println (leading (os, 8) + os + ": ECS" +
-					nECS + " " + length + " ...");
-		    os += length;
-		    nECS++;
-		    readingECS = false;
-		    haveCode   = true;
-		    continue;
-		}
-
-		if (code == 0x01) {
-		    System.out.println (leading (os, 8) + os + ": TEM");
-		}
-		else if ((code >= 0xc0 && code <= 0xc3) ||
-			 (code >= 0xc5 && code <= 0xc7) ||
-			 (code >= 0xc9 && code <= 0xcb) ||
-			 (code >= 0xcd && code <= 0xcf)) {
-		    int n = code - 0xc0;
-/****************** int length = markerSegment (stream, bigEndian); */
-		    int length = ModuleBase.readUnsignedShort (stream,
-							       bigEndian,
-							       null);
-		    int P  = stream.readUnsignedByte ();
-		    int Y  = ModuleBase.readUnsignedShort (stream, bigEndian,
-							  null);
-		    int X  = ModuleBase.readUnsignedShort (stream, bigEndian,
-							   null);
-		    int Nf = stream.readUnsignedByte ();
-		    int [] Ci  = new int [Nf];
-		    int [] Hi  = new int [Nf];
-		    int [] Vi  = new int [Nf];
-		    int [] Tqi = new int [Nf];
-		    for (int i=0; i<Nf; i++) {
-			Ci[i]  = stream.readUnsignedByte ();
-			Hi[i]  = stream.readUnsignedByte ();
-			Tqi[i] = stream.readUnsignedByte ();
-		    }
-		    System.out.print (leading (os, 8) + os + ": SOF" + n +
-				      " " + length + ": " + P + " " + X +
-				      "x" + Y + " " + Nf + ":");
-		    for (int i=0; i<Nf; i++) {
-			System.out.print (" " + Ci[i] + "," + Hi[i] + "," +
-					  Tqi[i]);
-		    }
-		    System.out.println ();
-		    os += length;
-		}
-		else if (code == 0xc4) {
-		    int length = markerSegment (stream, bigEndian);
-		    System.out.println (leading (os, 8) + os + ": DHT" + " " +
-					length + " ...");
-		    os += length;
-		}
-		else if (code == 0xc8) {
-		    int length = markerSegment (stream, bigEndian);
-		    System.out.println (leading (os, 8) + os + ": JPG" + " " +
-					length + " ...");
-		    os += length;
-		}
-		else if (code == 0xcc) {
-		    int length = markerSegment (stream, bigEndian);
-		    System.out.println (leading (os, 8) + os + ": DAC" + " " +
-					length + " ...");
-		    os += length;
-		}
-		else if (code >= 0xd0 && code <= 0xd7) {
-		    int m = code - 0xd0;
-		    System.out.println (leading (os, 8) + os + ": RST" + m);
-
-		    readingECS = true;
-		}
-		else if (code == 0xd8) {
-		    System.out.println (leading (os, 8) + os + ": SOI");
-		}
-		else if (code == 0xd9) {
-		    System.out.println (leading (os, 8) + os + ": EOI");
-		    endOfImage = true;
-		    break;
-		}
-		else if (code == 0xda) {
-		    int length = markerSegment (stream, bigEndian);
-		    System.out.println (leading (os, 8) + os + ": SOS" + " " +
-					length + " ...");
-		    os += length;
-
-		    readingECS = true;
-		}
-		else if (code == 0xdb) {
-		    int length = markerSegment (stream, bigEndian);
-		    System.out.println (leading (os, 8) + os + ": DQT" + " " +
-					length + " ...");
-		    os += length;
-		}
-		else if (code == 0xdc) {
-		    int length = markerSegment (stream, bigEndian);
-		    System.out.println (leading (os, 8) + os + ": DNL" + " " +
-					length + " ...");
-		    os += length;
-		}
-		else if (code == 0xdd) {
-		    int length = markerSegment (stream, bigEndian);
-		    System.out.println (leading (os, 8) + os + ": DRI" + " " +
-					length + " ...");
-		    os += length;
-		}
-		else if (code == 0xde) {
-		    int length = markerSegment (stream, bigEndian);
-		    System.out.println (leading (os, 8) + os + ": DHP" + " " +
-					length + " ...");
-		    os += length;
-		}
-		else if (code == 0xdf) {
-		    int length = markerSegment (stream, bigEndian);
-		    System.out.println (leading (os, 8) + os + ": EXP" + " " +
-					length + " ...");
-		    os += length;
-		}
-		else if (code == 0xe0) {
-		    int length = ModuleBase.readUnsignedShort (stream,
-							       bigEndian,
-							       null);
-		    String id  = readChars (stream, 5);
-		    if (id.equals ("JFIF\0")) {
-			int major  = stream.readUnsignedByte ();
-			int minor  = stream.readUnsignedByte ();
-			int units  = stream.readUnsignedByte ();
-			int xDensity = ModuleBase.readUnsignedShort (stream,
-								     bigEndian,
-								     null);
-			int yDensity = ModuleBase.readUnsignedShort (stream,
-								     bigEndian,
-								     null);
-			int xThumbnail = stream.readUnsignedByte ();
-			int yThumbnail = stream.readUnsignedByte ();
-			System.out.print (leading (os, 8) + os + ": APP0 " +
-					  "\"" + id + "\" " + major + "." +
-					  minor + " " + units + " " +
-					  xDensity + "x" + yDensity + " "
-					  + xThumbnail + "x" + yThumbnail);
-			int n = length - 16;
-			if (n > 0) {
-			    for (int i=0; i<n; i++) {
-				stream.readUnsignedByte ();
-			    }
-			    System.out.print (" " + n + " ...");
-			}
-			System.out.println ();
-		    }
-		    else if (id.equals ("JFXX\0")) {
-			int ext = stream.readUnsignedByte ();
-			String hex = Integer.toHexString (ext);
-			System.out.print (leading (os, 8) + os + ": APP0 " +
-					  "0x" + leading (hex, 2) + hex);
-			int n = length-3;
-			if (n > 0) {
-			    for (int i=0; i<n; i++) {
-				stream.readUnsignedByte ();
-			    }
-			    System.out.print (" " + n + " ...");
-			}
-			System.out.println ();
-		    }
-		    else {
-			System.out.println (leading (os, 8) + os + ": APP0 " +
-					    length + " ...");
-			for (int i=2; i<length; i++) {
-			    stream.readUnsignedByte ();
-			}
-		    }
-		    os += length;
-		}
-		else if (code >= 0xe1 && code <= 0xef) {
-		    int n = code - 0xe0;
-		    /*
-    		    int length = markerSegment (stream, bigEndian);
-		    */
-		    int length = ModuleBase.readUnsignedShort (stream,
-							       bigEndian,
-							       null);
-		    if ((n == 1 || n == 2) && length >= 8) {
-			String id = readChars (stream, 4);
-			int NULL    = stream.readUnsignedByte ();
-			int padding = stream.readUnsignedByte ();
-			if (id.equals ("Exif") || id.equals ("FPXR")) {
-			    System.out.println (leading (os, 8) + os +
-						": APP" + n + " \"" + id +
-						"\" " + NULL + " " + padding +
-						" " + (length-8) + ": ...");
-			}
-			else {
-			    System.out.println (leading (os, 8) + os +
-						": APP" + n + " " + length +
-						" ...");
-			}
-			for (int i=8; i<length; i++) {
-			    stream.readUnsignedByte ();
-			}
-		    }
-		    else {
-			System.out.println (leading (os, 8) + os + ": APP" +
-					    n +	" " + length + " ...");
-			for (int i=2; i<length; i++) {
-			    stream.readUnsignedByte ();
-			}
-		    }
-		    os += length;
-		}
-		else if (code == 0xf0) {
-		    int length = ModuleBase.readUnsignedShort (stream,
-							       bigEndian,
-							       null);
-		    int v   = stream.readUnsignedByte ();
-		    int rev = stream.readUnsignedByte ();
-		    System.out.print (leading (os, 8) + os + ": VER " + 
-					v + "." + rev);
-		    int n = length - 4;
-		    if (n > 0) {
-			int [] cap = new int [n];
-			for (int i=0; i<n; i++) {
-			    cap[i] = stream.readUnsignedByte ();
-			    System.out.print (((i==0) ? " " : ",") + cap[i]);
-			}
-		    }
-		    System.out.println ();
-		    os += length;
-		}
-		else if (code == 0xf1) {
-		    int length = markerSegment (stream, bigEndian);
-		    System.out.println (leading (os, 8) + os + ": DTI " +
-					length + " ...");
-		    os += length;
-		}
-		else if (code == 0xf2) {
-		    int length = markerSegment (stream, bigEndian);
-		    System.out.println (leading (os, 8) + os + ": DTT " +
-					length + " ...");
-		    os += length;
-		}
-		else if (code == 0xf3) {
-		    int length = markerSegment (stream, bigEndian);
-		    System.out.println (leading (os, 8) + os + ": SRF " +
-					length + " ...");
-		    os += length;
-		}
-		else if (code == 0xf4) {
-		    int length = markerSegment (stream, bigEndian);
-		    System.out.println (leading (os, 8) + os + ": SRS " +
-					length + " ...");
-		    os += length;
-		}
-		else if (code == 0xf5) {
-		    int length = markerSegment (stream, bigEndian);
-		    System.out.println (leading (os, 8) + os + ": DCR " +
-					length + " ...");
-		    os += length;
-		}
-		else if (code == 0xf6) {
-		    int length = markerSegment (stream, bigEndian);
-		    System.out.println (leading (os, 8) + os + ": DQS " +
-					length + " ...");
-		    os += length;
-		}
-		else if (code >= 0xf7 && code <= 0xfd) {
-		    int n = code - 0xf0;
-		    int length = markerSegment (stream, bigEndian);
-		    System.out.println (leading (os, 8) + os + ": JPG" + n +
-					" " + length + " ...");
-		    os += length;
-		}
-		else if (code == 0xfe) {
-		    int length = ModuleBase.readUnsignedShort (stream,
-							       bigEndian,
-							       null);
-		    String comment = readChars (stream, length-2);
-		    System.out.println (leading (os, 8) + os + ": COM \"" +
-					comment + "\"");
-		    os += length;
-		}
-		else {
-		    int length = markerSegment (stream, bigEndian);
-		    String hex = Integer.toHexString (code);
-		    System.out.println (leading (os, 8) + os + ": RES (0x" +
-					leading (hex, 2) + hex + ") " +
-					length + " ...");
-		}
-		os += 2;
-	    }
-
-	    stream.close ();
-	}
-	catch (Exception e) {
-	    e.printStackTrace (System.err);
-	    System.exit (-2);
-	}
-    }
-
-    /**
-     * Read marker segment data
-     * @param stream    Data input stream
-     * @param bigEndian True if big-endian
-     * @return Length of marker segment
-     */
-    private static int markerSegment (DataInputStream stream,
-				      boolean bigEndian)
-	throws IOException
-    {
-	int length = ModuleBase.readUnsignedShort (stream,
-						   bigEndian,
-						   null);
-	for (int i=2; i<length; i++) {
-	    stream.readUnsignedByte ();
-	}
-	return length;
-    }
-}

jhove/classes/Jhove.java

@@ -1,313 +0,0 @@
-/**********************************************************************
- * Jhove - JSTOR/Harvard Object Validation Environment
- * Copyright 2004-2007 by the President and Fellows of Harvard College
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU Lesser General Public License as published by
- * the Free Software Foundation; either version 2 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
- * Lesser General Public License for more details.
- * 
- * You should have received a copy of the GNU Lesser General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307
- * USA
- **********************************************************************/
-
-import edu.harvard.hul.ois.jhove.*;
-//import java.io.*;
-import java.util.*;
-
-public class Jhove
-{
-    /******************************************************************
-     * PRIVATE CLASS FIELDS.
-     ******************************************************************/
-
-    /** Application name. */
-    private static final String NAME = "Jhove";
-
-    /** Application build date, YYYY, MM, DD. */
-    private static int [] DATE;
-
-    /** Application release number. */
-    private static String RELEASE;
-
-    /** Application invocation syntax. */
-    private static final String USAGE = "java " + NAME + " [-c config] " +
-        "[-m module] [-h handler] [-e encoding] [-H handler] [-o output] " +
-	"[-x saxclass] [-t tempdir] [-b bufsize] [-l loglevel] [[-krs] " +
-	"dir-file-or-uri [...]]";
-
-    /** Copyright information. */
-    private static final String RIGHTS =
-	"Derived from software Copyright 2004-2011 " +
-    "by the President and Fellows of Harvard College. " +
-    "Version 1.7 and higher independently released. " +
-	"Released under the GNU Lesser General Public License.";
-
-    /******************************************************************
-     * MAIN ENTRY POINT.
-     ******************************************************************/
-
-    public static void main (String [] args)
-    {
-        RELEASE = JhoveBase._release;      // possibly safer than final static init
-        DATE = JhoveBase.DATE;
-        /* Make sure we have a satisfactory version of Java. */
-        String version = System.getProperty ("java.vm.version");
-        if (version.compareTo ("1.5.0") < 0) {
-            //System.err.println (NAME + ": Java 1.4 or higher is required");
-            System.out.println ("Java 1.5 or higher is required");
-            System.exit (-1);
-        }
-
-        try {
-    
-    	    /**********************************************************
-    	     * Initialize the application state object.
-    	     **********************************************************/
-    
-    	    App app = new App (NAME, RELEASE, DATE, USAGE, RIGHTS);
-    
-    	    /**********************************************************
-    	     * Retrieve the configuration file.
-    	     **********************************************************/
-    
-    	    String configFile = JhoveBase.getConfigFileFromProperties ();
-    	    String saxClass   = JhoveBase.getSaxClassFromProperties ();
-    
-    	    /* Pre-parse the command line for -c and -x config options. 
-    	     * With Windows, we have to deal with quote marks on our own. With Unix,
-    	     * the shell takes care of quotes for us. */
-    	    boolean quoted = false;
-    	    for (int i=0; i<args.length; i++) {
-    		if (quoted) {
-    		    int len = args[i].length ();
-                if (args[i].charAt (len-1) == '"') {
-                    quoted = false;
-                }
-    		}
-    		else {
-    		    if (args[i].equals ("-c")) {
-                    if (i < args.length-1) {
-                        configFile = args[++i];
-                    }
-                }
-    		    else if (args[i].equals ("-x")) {
-                    if (i <args.length-1) {
-                        saxClass = args[++i];
-                    }
-                }
-    		    else if (args[i].charAt (0) == '"') {
-                    quoted = true;
-                }
-    		}
-        }
-    
-    	    /**********************************************************
-    	     * Initialize the JHOVE engine.
-    	     **********************************************************/
-    
-    	    String encoding     = null;
-    	    String tempDir      = null;
-    	    int    bufferSize   = -1;
-    
-            String moduleName   = null;
-            String handlerName  = null;
-            String aboutHandler = null;
-            String logLevel     = "SEVERE";
-            String outputFile   = null;
-            boolean checksum    = false;
-            boolean showRaw     = false;
-            boolean signature   = false;
-            List<String> list   = new ArrayList<String> ();
-    
-    	 
-                /**********************************************************
-                 * Parse command line arguments:
-                 *  -m module    Module name
-                 *  -h handler   Output handler
-    	     *  -e encoding  Output encoding
-                 *  -H handler   About handler
-                 *  -o output    Output file pathname
-                 *  -t tempdir   Directory for temp files
-                 *  -b bufsize   Buffer size for buffered I/O
-                 *  -k           Calculate checksums
-                 *  -r           Display raw numeric flags 
-                 *  -s           Check internal signatures only
-                 *  dirFileOrUri Directories, file pathnames, or URIs
-    	     *
-    	     * The following arguments were defined in previous
-    	     * versions, but are now obsolete
-                 *  -p param     OBSOLETE
-                 *  -P param     OBSOLETE
-    	     **********************************************************/
-    
-    	    quoted = false;
-    	    StringBuffer filename = null;
-    
-            for (int i=0; i<args.length; i++) {
-                if (quoted) {
-                    int len = args[i].length ();
-                    if (args[i].charAt (len-1) == '"') {
-                        filename.append (" " + args[i].substring (0, len-1));
-                        list.add (filename.toString ());
-                        quoted = false;
-                    }
-                    else {
-                        filename.append (" " + args[i]);
-                    }
-                }
-                else {
-        		    if (args[i].equals ("-c")) {
-                        i++;
-        		    }
-        		    else if (args[i].equals ("-m")) {
-                        if (i < args.length-1) {
-                            moduleName = args[++i];
-                        }
-        		    }
-        		    else if (args[i].equals ("-p")) {
-                        // Obsolete -- but eat the next arg for compatibility
-                        if (i <args.length-1) {
-                            @SuppressWarnings("unused")
-                            String moduleParam = args[++i];
-                        }
-                    }
-        		    else if (args[i].equals ("-h")) {
-                        if (i < args.length-1) {
-                            handlerName = args[++i];
-                        }
-                    }
-        		    else if (args[i].equals ("-P")) {
-                        // Obsolete -- but eat the next arg for compatibility
-                        if (i <args.length-1) {
-                            @SuppressWarnings("unused")
-                            String handlerParam = args[++i];
-                        }
-        		    }
-        		    else if (args[i].equals ("-e")) {
-                        if (i < args.length-1) {
-                            encoding = args[++i];
-                        }
-        		    }
-        		    else if (args[i].equals ("-H")) {
-                        if (i < args.length-1) {
-                            aboutHandler = args[++i];
-                        }
-                    }
-        		    else if (args[i].equals ("-l")) {
-                        if (i < args.length-1) {
-                            logLevel = args[++i];
-                        }
-        		    }
-        		    else if (args[i].equals ("-o")) {
-                        if (i < args.length-1) {
-                            outputFile = args[++i];
-                        }
-                    }
-        		    else if (args[i].equals ("-x")) {
-                        i++;
-        		    }
-        		    else if (args[i].equals ("-t")) {
-                        if (i <args.length-1) {
-                            tempDir = args[++i];
-                        }
-                    }
-        		    else if (args[i].equals ("-b")) {
-                        if (i <args.length-1) {
-                            try {
-                                bufferSize = Integer.parseInt (args[++i]);
-                            }
-                            catch (NumberFormatException e) {
-                                System.err.println ("Invalid buffer size, using default.");
-                            }
-                        }
-        		    }
-        		    else if (args[i].equals ("-k")) {
-                        checksum = true;
-        		    }
-        		    else if (args[i].equals ("-r")) {
-                        showRaw = true;
-        		    }
-        		    else if (args[i].equals ("-s")) {
-                        signature = true;
-                    }
-        		    else if (args[i].charAt (0) != '-') {
-                        if (args[i].charAt (0) == '"') {
-                            filename = new StringBuffer ();
-                            filename.append (args[i].substring (1));
-                            quoted = true;
-                        }
-                        else {
-                            list.add (args[i]);
-                        }
-        		    }
-        		}
-            }
-            if (quoted) {
-                list.add (filename.toString ());
-    	    }
-    
-            JhoveBase je = new JhoveBase ();
-            je.setLogLevel (logLevel);
-            je.init (configFile, saxClass);
-            if (encoding == null) {
-                encoding = je.getEncoding ();
-            }
-            if (tempDir == null) {
-                tempDir = je.getTempDirectory ();
-            }
-            if (bufferSize < 0) {
-                bufferSize = je.getBufferSize ();
-            }
-            Module module = je.getModule  (moduleName);
-            if (module == null && moduleName != null) {
-                System.out.println ("Module '" + moduleName + "' not found");
-                System.exit (-1);
-            }
-            OutputHandler about   = je.getHandler (aboutHandler);
-            if (about == null && aboutHandler != null) {
-                System.out.println ("Handler '" + aboutHandler + "' not found");
-                System.exit (-1);
-            }
-    	    OutputHandler handler = je.getHandler (handlerName);
-            if (handler == null && handlerName != null) {
-                System.out.println ("Handler '" + handlerName + "' not found");
-                System.exit (-1);
-            }
-    	    String [] dirFileOrUri = null;
-    	    int len = list.size ();
-            if (len > 0) {
-        		dirFileOrUri = new String [len];
-        		for (int i=0; i<len; i++) {
-        		    dirFileOrUri[i] = (String) list.get (i);
-        		}
-            }
-    
-    	    /**********************************************************
-    	     * Invoke the JHOVE engine.
-    	     **********************************************************/
-                
-            je.setEncoding (encoding);
-            je.setTempDirectory (tempDir);
-            je.setBufferSize (bufferSize);
-            je.setChecksumFlag (checksum);
-            je.setShowRawFlag (showRaw);
-            je.setSignatureFlag (signature);
-    	    je.dispatch (app, module, about, handler, outputFile, 
-    			 dirFileOrUri);
-    	}
-        catch (Exception e) {
-            e.printStackTrace (System.err);
-            System.exit (-1);
-        }
-    }
-    
-
-}

jhove/classes/JhoveView.java

@@ -1,229 +0,0 @@
-/**********************************************************************
- * Jhove - JSTOR/Harvard Object Validation Environment
- * Copyright 2004-2008 by JSTOR and the President and Fellows of Harvard College
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU Lesser General Public License as published by
- * the Free Software Foundation; either version 2 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
- * Lesser General Public License for more details.
- * 
- * You should have received a copy of the GNU Lesser General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307
- * USA
- **********************************************************************/
-
-import edu.harvard.hul.ois.jhove.*;
-import edu.harvard.hul.ois.jhove.viewer.*;
-import javax.swing.*;
-
-/**
- * JhoveView - JSTOR/Harvard Object Validation Environment.
- */
-public class JhoveView
-{
-    /******************************************************************
-     * PRIVATE CLASS FIELDS.
-     *
-     * Application constants.
-     ******************************************************************/
-
-    /** Application name. */
-    private static final String NAME = "JhoveView";
-
-    /** Application build date, YYYY, MM, DD. */
-    private static int [] _date;
-
-    /** Usage string is meaningless here. */
-    private static final String USAGE = null;
-    
-    /** Application release number. */
-    private static String _release;
-
-    /** Default character encoding */
-    //private static final String DEFAULT_ENCODING = "UTF-8";
-
-    /** Copyright information. */
-    private static final String RIGHTS = 
-        "Derived from software Copyright 2004-2011 " +
-        "by the President and Fellows of Harvard College. " +
-        "Version 1.7 and higher independently released. " +
-    	"Released under the GNU Lesser General Public License.";
-
-    /******************************************************************
-     * Configuration constants.
-     ******************************************************************/
-
-    /** Configuration file property. */
-//    private static final String CONFIG_PROPERTY = "edu.harvard.hul.ois." +
-//                                                  "jhove.config";
-    /** Jhove directory */
-//    private static final String JHOVE_DIR = "jhove";
-
-    /** Config directory */
-//    private static final String CONFIG_DIR = "conf";
-
-    /** SAX parser class property. */
-//    private static final String SAX_PROPERTY = "edu.harvard.hul.ois.jhove." +
-//                                               "saxClass";
-
-    /******************************************************************
-     * Action constants.
-     ******************************************************************/
-
-    /******************************************************************
-     * Exit code constants.
-     ******************************************************************/
-
-    /** General error. */
-    private static final int ERROR = -1;
-
-    /** Incompatible Java VM. */
-    private static final int INCOMPATIBLE_VM = -2;
-
-    /** File not writable. */
-    //private static final int FILE_NOT_WRITABLE = -11;
-
-    /** No module specified. */
-    //private static final int NO_MODULE = -21;
-
-    /** Module not found. */
-    //private static final int MODULE_NOT_FOUND = -22;
-
-    /** Output handler not found. */
-    //private static final int HANDLER_NOT_FOUND = -31;
-
-    /** No object specified. */
-    //private static final int NO_OBJECT = -41;
-
-    /** URL not accessible. */
-    //private static final int URL_NOT_ACCESSIBLE = -42;
-
-    /** File not found. */
-    //private static final int FILE_NOT_FOUND = -43;
-
-    /** File not readable. */
-    //private static final int FILE_NOT_READABLE = -44;
-
-    /** SAX parser not found. */
-    //private static final int PARSER_NOT_FOUND = -51;
-    
-
-    /******************************************************************
-     * PUBLIC CLASS METHODS.
-     ******************************************************************/
-
-    /**
-     *  Stub constructor.
-     */
-
-    private JhoveView ()
-    {
-    }
-
-    /**
-     * Application main entry point.
-     * @parm args Command line arguments
-     */
-    public static void main (String [] args)
-    {
-        _release = JhoveBase._release;     // Seems safer than final init
-        _date = JhoveBase.DATE;
-        /* Make sure we have a satisfactory version of Java. */
-        String version = System.getProperty ("java.vm.version");
-        if (version.compareTo ("1.4.0") < 0) {
-            //System.err.println (NAME + ": Java 1.4 or higher is required");
-            errorAlert ("Java 1.4 or higher is required");
-            System.exit (INCOMPATIBLE_VM);
-        }
-
-        // If we're running on a Macintosh, put the menubar at the top
-        // of the screen where it belongs.
-        System.setProperty ("apple.laf.useScreenMenuBar", "true");
-
-        App app = new App (NAME, _release, _date, USAGE, RIGHTS);
-        try {
-
-            /**********************************************************
-             * Retrieve the configuration file.
-             **********************************************************/
-    
-            String configFile = JhoveBase.getConfigFileFromProperties ();
-            String saxClass   = JhoveBase.getSaxClassFromProperties ();
-
-            /**********************************************************
-             * Initialization:
-             *  configFile  Configuration file pathname
-             *  saxClass    SAX parser class
-             **********************************************************/
-
-	    /* Pre-parse the command line for -c and -x config options. */
-	    boolean quoted = false;
-	    for (int i=0; i<args.length; i++) {
-		if (quoted) {
-		    int len = args[i].length ();
-		    if (args[i].charAt (len-1) == '"') {
-			quoted = false;
-		    }
-		}
-		else {
-		    if (args[i].equals ("-c")) {
-			if (i < args.length-1) {
-			    configFile = args[++i];
-			}
-		    }
-		    else if (args[i].equals ("-x")) {
-			if (i <args.length-1) {
-			    saxClass = args[++i];
-			}
-		    }
-		    else if (args[i].charAt (0) == '"') {
-			quoted = true;
-		    }
-		}
-	    }
-
-            
-            /**********************************************************
-             * Initialize the JHOVE engine.
-             **********************************************************/
-    
-            JhoveBase je = new JhoveBase ();
-            try {
-                je.init (configFile, saxClass);
-            }
-            catch (JhoveException e) {
-                errorAlert (e.getMessage ());
-                // Keep going, so user can correct in editor
-            }
-
-            // Create the main window to select a file.
-            
-            JhoveWindow jwin = new JhoveWindow (app, je);
-            jwin.setVisible (true);
-
-        }
-        catch (Exception e) {
-            e.printStackTrace (System.err);
-            System.exit (ERROR);
-        }
-    }
-    
-    /* Displays an error alert. */
-    private static void errorAlert (String msg)
-    {
-        JFrame hiddenFrame = new JFrame ();
-        // Truncate long messages so the alert isn't wider
-        // than the screen
-        if (msg.length() > 80) {
-            msg = msg.substring (0, 79) + "...";
-        }
-        JOptionPane.showMessageDialog (hiddenFrame, 
-            msg, "Jhove Error", JOptionPane.ERROR_MESSAGE);
-    }
-}

jhove/classes/PDump.java

@@ -1,115 +0,0 @@
-/**********************************************************************
- * PDump - JSTOR/Harvard Object Validation Environment
- * Copyright 2003 by JSTOR and the President and Fellows of Harvard College
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU Lesser General Public License as published by
- * the Free Software Foundation; either version 2 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
- * Lesser General Public License for more details.
- * 
- * You should have received a copy of the GNU Lesser General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307
- * USA
- **********************************************************************/
-
-import edu.harvard.hul.ois.jhove.*;
-import edu.harvard.hul.ois.jhove.module.pdf.*;
-import java.io.*;
-
-/**
- * Dump contents of PDF file in human-readable format.
- */
-public class PDump
-    extends Dump
-{
-    /******************************************************************
-     * MAIN ENTRY POINT.
-     ******************************************************************/
-
-    /**
-     * Main entry point.
-     * @param args Command line arguments
-     */
-    public static void main (String [] args)
-    {
-	if (args.length < 1) {
-	    System.err.println ("usage: java PDump file");
-	    System.exit (-1);
-	}
-
-	try {
-	    RandomAccessFile file = new RandomAccessFile (args[0], "r");
-	    Tokenizer tokenizer = new FileTokenizer (file);
-	    Token token = null;
-	    long offset = 0;
-	    while ((token = tokenizer.getNext ()) != null) {
-		System.out.print (leading (offset, 8) + offset + ": ");
-		if (token instanceof ArrayEnd) {
-		    System.out.println ("ArrayEnd");
-		}
-		else if (token instanceof ArrayStart) {
-		    System.out.println ("ArrayStart");
-		}
-		else if (token instanceof Comment) {
-		    System.out.println ("Comment \"" +
-					((Comment) token).getValue () + "\"");
-		}
-		else if (token instanceof DictionaryEnd) {
-		    System.out.println ("DictionaryEnd");
-		}
-		else if (token instanceof DictionaryStart) {
-		    System.out.println ("DictionaryStart");
-		}
-//		else if (token instanceof Hexadecimal) {
-//		    System.out.println ("Hexadecimal[" +
-//					(((Hexadecimal) token).isPDFDocEncoding () ?
-//					  "PDF" : "UTF-16") + "] \"" +
-//					((Hexadecimal) token).getValue () +
-//					"\"");
-//		}
-		else if (token instanceof Keyword) {
-		    System.out.println ("Keyword \"" +
-					((Keyword) token).getValue () + "\"");
-		}
-		else if (token instanceof Literal) {
-		    System.out.println ("Literal[" +
-					(((Literal)token).isPDFDocEncoding () ?
-					 "PDF" : "UTF-16") + "] \"" +
-					((Literal) token).getValue () + "\"");
-		}
-		else if (token instanceof Name) {
-		    System.out.println ("Name \"" +
-					((Name) token).getValue () + "\"");
-		}
-		else if (token instanceof Numeric) {
-		    Numeric numeric = (Numeric) token;
-		    if (numeric.isReal ()) {
-			System.out.println ("Numeric " + numeric.getValue ());
-		    }
-		    else {
-			System.out.println ("Numeric " +
-					    numeric.getIntegerValue ());
-		    }
-		}
-		else if (token instanceof Stream) {
-		    System.out.println ("Stream " +
-					((Stream) token).getLength ());
-		}
-		else {
-		    System.out.println (token);
-		}
-		offset = tokenizer.getOffset ();
-	    }
-	}
-	catch (Exception e) {
-	    e.printStackTrace (System.err);
-	    System.exit (-2);
-	}
-    }
-}

jhove/classes/TDump.java

@@ -1,361 +0,0 @@
-/**********************************************************************
- * TDump - JSTOR/Harvard Object Validation Environment
- * Copyright 2003-2004 by JSTOR and the President and Fellows of Harvard College
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU Lesser General Public License as published by
- * the Free Software Foundation; either version 2 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
- * Lesser General Public License for more details.
- * 
- * You should have received a copy of the GNU Lesser General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307
- * USA
- **********************************************************************/
-
-import edu.harvard.hul.ois.jhove.*;
-import edu.harvard.hul.ois.jhove.module.tiff.*;
-import java.io.*;
-import java.util.*;
-
-/**
- * Dump contents of TIFF file in human-readable format.
- */
-public class TDump
-    extends Dump
-{
-    /******************************************************************
-     * PRIVATE CLASS FIELDS.
-     ******************************************************************/
-
-    /** Count of IFDs. */
-    private static int _nIFDs;
-    /** Sorted associative map of tags. */
-    private static Map _tags;
-
-    /******************************************************************
-     * MAIN ENTRY POINT.
-     ******************************************************************/
-
-    /**
-     * Main entry point.
-     * @param args Command line arguments
-     */
-    public static void main (String [] args)
-    {
-	if (args.length < 1) {
-	    System.err.println ("usage: java TDump [-bs] file");
-	    System.exit (-1);
-	}
-
-	String tiff = null;
-	boolean nobyte = false;
-	boolean nosub  = false;
-	for (int i=0; i<args.length; i++) {
-	    if (args[i].equals ("-b")) {
-		nobyte = true;
-	    }
-	    else if (args[i].equals ("-s")) {
-		nosub = true;
-	    }
-	    else if (tiff == null) {
-		tiff = args[i];
-	    }
-	}
-
-	/* Accumlate all tag definitions in a sorted map. */
-
-	_tags = new TreeMap ();
-
-	int err = 0;
-	try {
-
-	    /* Read TIFF header. */
-
-	    RandomAccessFile file = new RandomAccessFile (tiff, "r");
-	    boolean bigEndian = true;
-	    int b1 = ModuleBase.readUnsignedByte (file);
-	    int b2 = ModuleBase.readUnsignedByte (file);
-	    if (b1 == 0x49 && b2 == b1) {
-		bigEndian = false;
-	    }
-	    int magic = ModuleBase.readUnsignedShort (file, bigEndian);
-	    long offset = ModuleBase.readUnsignedInt (file, bigEndian);
-	    _tags.put ("00000000", "\"" + ((char) b1) + ((char) b2) + "\" (" +
-		       (bigEndian ? "big" : "little") + " endian) " + magic +
-		       " LONG @" + offset);
-
-	    /* Read IFDs. */
-
-	    _nIFDs = 0;
-	    while ((offset = readIFD (file, bigEndian, offset, nobyte,
-				      nosub)) > 0) {
-	    }
-	    file.close ();
-	}
-	catch (Exception e) {
-	    e.printStackTrace (System.out);
-	    err = -2;
-	}
-	finally {
-
-	    /* Display all tags in offset-sorted order. */
-
-	    Iterator iter = _tags.keySet ().iterator ();
-	    while (iter.hasNext ()) {
-		String os = (String) iter.next ();
-		System.out.println (os + ": " + (String) _tags.get (os));
-	    }
-	    if (err != 0) {
-		System.exit (err);
-	    }
-	}
-    }
-
-    /**
-     * Read IFDs.
-     * @param file      Open TIFF file
-     * @param bigEndian True if big-endian
-     * @param offset    Byte offset of IFD
-     * @param nobyte    If true, only display the first 8 bytes of data of
-     *                  type BYTE
-     * @param nosub     If true, do not parse subIFDs
-     */
-    private static long readIFD (RandomAccessFile file, boolean bigEndian,
-				 long offset, boolean nobyte, boolean nosub)
-	throws Exception
-    {
-	int nIFD = ++_nIFDs;
-	List subIFDs = new ArrayList ();
-	List stripByteCounts = new ArrayList ();
-	List stripOffsets    = new ArrayList ();
-
-	file.seek (offset);
-	int nEntries = ModuleBase.readUnsignedShort (file, bigEndian);
-	_tags.put (leading (offset, 8) + offset, "IFD " + nIFD + " with " +
-	       nEntries + " entries");
-
-	String name = null;
-	for (int i=0; i<nEntries; i++) {
-	    long os = offset + 2 + i*12;
-	    file.seek (os);
-	    int  tag   = ModuleBase.readUnsignedShort (file, bigEndian);
-	    int  type  = ModuleBase.readUnsignedShort (file, bigEndian);
-	    long count = ModuleBase.readUnsignedInt   (file, bigEndian);
-
-	    StringBuffer buffer = new StringBuffer (tag + " (" +
-						    TiffTags.tagName(tag) +
-						    ") " + IFD.TYPE[type] +
-						    " " + count);
-	    if (type == IFD.ASCII) {
-		if (count > 4) {
-		    long vo = ModuleBase.readUnsignedInt (file, bigEndian);
-		    file.seek (vo);
-
-		    buffer.append (" @" + vo);
-		}
-		StringBuffer ascii = new StringBuffer ();
-		for (int j=0; j<count-1; j++) {
-		    ascii.append ((char) ModuleBase.readUnsignedByte (file));
-		}
-		buffer.append (" = \"" + ascii.toString () + "\"");
-	    }
-	    else if (type == IFD.BYTE ||
-		     type == IFD.UNDEFINED) {
-		if (count > 4) {
-		    long vo = ModuleBase.readUnsignedInt (file, bigEndian);
-		    file.seek (vo);
-
-		    buffer.append (" @" + vo);
-		}
-		buffer.append (" =");
-		long ct = count;
-		if (nobyte && count > 8) {
-		    ct = 8;
-		}
-		for (int j=0; j<ct; j++) {
-		    long by = ModuleBase.readUnsignedByte (file);
-		    buffer.append (" " + by);
-		}
-		if (nobyte && count > 8) {
-		    buffer.append (" ...");
-		}
-	    }
-	    else if (type == IFD.DOUBLE) {
-		long vo = ModuleBase.readUnsignedInt (file, bigEndian);
-		file.seek (vo);
-
-		buffer.append (" @" + vo + " =");
-		for (int j=0; j<count; j++) {
-		    double db = ModuleBase.readDouble (file, bigEndian);
-		    buffer.append (" " + db);
-		}
-	    }
-	    else if (type == IFD.FLOAT) {
-		if (count > 1) {
-		    long vo = ModuleBase.readUnsignedInt (file, bigEndian);
-		    file.seek (vo);
-
-		    buffer.append (" @" + vo);
-		}
-		buffer.append (" =");
-		for (int j=0; j<count; j++) {
-		    float fl = ModuleBase.readFloat (file, bigEndian);
-		    buffer.append (" " + fl);
-		}
-	    }
-	    else if (type == IFD.LONG || type == IFD.IFD) {
-		if (count > 1) {
-		    long vo = ModuleBase.readUnsignedInt (file, bigEndian);
-		    file.seek (vo);
-
-		    buffer.append (" @" + vo + " = ");
-		}
-		else if (tag == 330   ||   /* Sub IFD */
-			 tag == 34665 ||   /* EXIF IFD */
-			 tag == 34853 ||   /* EXIF GPS IFD */
-			 tag == 40965) {   /* EXIF Interoperability IFD */
-		    buffer.append (" @");
-		}
-		else {
-		    buffer.append (" = ");
-		}
-		for (int j=0; j<count; j++) {
-		    long in = ModuleBase.readUnsignedInt (file, bigEndian);
-		    if (j > 0) {
-			buffer.append (" ");
-		    }
-		    buffer.append (in);
-
-		    if (tag == 330   ||   /* Sub IFD */
-			tag == 34665 ||   /* EXIF IFD */
-			tag == 34853 ||   /* EXIF GPS IFD */
-			tag == 40965) {   /* EXIF Interoperability IFD */
-			subIFDs.add (new Long (in));
-		    }
-		    else if (tag == 273) {
-			stripOffsets.add (new Long (in));
-		    }
-		    else if (tag == 279) {
-			stripByteCounts.add (new Long (in));
-		    }
-		}
-	    }
-	    else if (type == IFD.RATIONAL) {
-		long vo = ModuleBase.readUnsignedInt (file, bigEndian);
-		file.seek (vo);
-
-		buffer.append (" @" + vo + " =");
-		for (int j=0; j<count; j++) {
-		    long numer = ModuleBase.readUnsignedInt (file, bigEndian);
-		    long denom = ModuleBase.readUnsignedInt (file, bigEndian);
-		    buffer.append (" " + numer + "/" + denom);
-		}
-	    }
-	    else if (type == IFD.SBYTE) {
-		if (count > 4) {
-		    long vo = ModuleBase.readUnsignedInt (file, bigEndian);
-		    file.seek (vo);
-
-		    buffer.append (" @" + vo);
-		}
-		buffer.append (" =");
-		for (int j=0; j<count; j++) {
-		    long by = ModuleBase.readSignedByte (file);
-		    buffer.append (" " + by);
-		}
-	    }
-	    else if (type == IFD.SHORT) {
-		if (count > 2) {
-		    long vo = ModuleBase.readUnsignedInt (file, bigEndian);
-		    file.seek (vo);
-
-		    buffer.append (" @" + vo);
-		}
-		buffer.append (" =");
-		for (int j=0; j<count; j++) {
-		    int sh = ModuleBase.readUnsignedShort (file, bigEndian);
-		    buffer.append (" " + sh);
-
-		    if (tag == 273) {
-			stripOffsets.add (new Long ((long) sh));
-		    }
-		    else if (tag == 279) {
-			stripByteCounts.add (new Long ((long) sh));
-		    }
-
-		}
-	    }
-	    else if (type == IFD.SLONG) {
-		if (count > 1) {
-		    long vo = ModuleBase.readUnsignedInt (file, bigEndian);
-		    file.seek (vo);
-
-		    buffer.append (" @" + vo);
-		}
-		buffer.append (" =");
-		for (int j=0; j<count; j++) {
-		    int in = ModuleBase.readSignedInt (file, bigEndian);
-		    buffer.append (" " + in);
-		}
-	    }
-	    else if (type == IFD.SRATIONAL) {
-		long vo = ModuleBase.readUnsignedInt (file, bigEndian);
-		file.seek (vo);
-
-		buffer.append (" @" + vo + " =");
-		for (int j=0; j<count; j++) {
-		    long numer = ModuleBase.readSignedInt (file, bigEndian);
-		    long denom = ModuleBase.readSignedInt (file, bigEndian);
-		    buffer.append (" " + numer + "/" + denom);
-		}
-	    }
-	    else if (type == IFD.SSHORT) {
-		if (count > 2) {
-		    long vo = ModuleBase.readUnsignedInt (file, bigEndian);
-		    file.seek (vo);
-
-		    buffer.append (" @" + vo);
-		}
-		buffer.append (" =");
-		for (int j=0; j<count; j++) {
-		    int sh = ModuleBase.readSignedShort (file, bigEndian);
-		    buffer.append (" " + sh);
-		}
-	    }
-	    _tags.put (leading (os, 8) + os, buffer.toString ());
-	}
-
-	if (!nosub) {
-	    for (int i=0; i<subIFDs.size (); i++) {
-		long os = ((Long) subIFDs.get (i)).longValue ();
-		while ((os = readIFD (file, bigEndian, os, nobyte, nosub)) > 0) {
-		}
-	    }
-	}
-
-	long os = offset + 2 + nEntries*12;
-	file.seek (os);
-	long next = ModuleBase.readUnsignedInt (file, bigEndian);
-	_tags.put (leading (os, 8) + os, "NextIFDOffset LONG @" + next);
-
-	int len = stripOffsets.size ();
-	if (len > 0) {
-	    for (int j=0; j<len; j++) {
-		long start = ((Long) stripOffsets.get (j)).longValue ();
-		long count = ((Long) stripByteCounts.get (j)).longValue ();
-		long finish= start + count - 1;
-		_tags.put (leading (start, 8) + start, "(Image " + nIFD +
-			   ",strip " + (j+1) + ") IMAGEDATA " + count +
-			   ": ... " + leading (finish, 8) + finish);
-	    }
-	}
-
-	return next;
-    }
-}

jhove/classes/UserHome.java

@@ -1,33 +0,0 @@
-/**********************************************************************
- * UserHome - JSTOR/Harvard Object Validation Environment
- * Copyright 2006 by the President and Fellows of Harvard College
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU Lesser General Public License as published by
- * the Free Software Foundation; either version 2 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
- * Lesser General Public License for more details.
- * 
- * You should have received a copy of the GNU Lesser General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307
- * USA
- **********************************************************************/
-
-import java.io.*;
-
-/**
- * Determine the default value of the Java user.home property.
- */
-public class UserHome
-{
-    public static void main (String [] args)
-    {
-	System.out.println ("Default user.home is \"" +
-			    System.getProperty ("user.home") + "\"");
-    }
-}

jhove/classes/WDump.java

@@ -1,196 +0,0 @@
-/**********************************************************************
- * JDump - JSTOR/Harvard Object Validation Environment
- * Copyright 2004-2005 by the President and Fellows of Harvard College
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU Lesser General Public License as published by
- * the Free Software Foundation; either version 2 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
- * Lesser General Public License for more details.
- * 
- * You should have received a copy of the GNU Lesser General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307
- * USA
- **********************************************************************/
-
-import edu.harvard.hul.ois.jhove.*;
-import java.io.*;
-
-/**
- * Dump contents of WAVE file in human-readable format.
- *
- * @author Gary McGath
- *
- */
-public class WDump extends Dump {
-
-    /* Fixed value for first 4 bytes */
-    private static final int[] sigByte =
-       { 0X52, 0X49, 0X46, 0X46 };
-
-    private static final boolean ENDIAN = false;     /* little endian */
-
-    /******************************************************************
-     * MAIN ENTRY POINT.
-     ******************************************************************/
-
-    /**
-     * Main entry point.
-     * @param args Command line arguments
-     */
-    public static void main (String [] args)
-    {
-        if (args.length < 1) {
-            System.err.println ("usage: java WDump file");
-            System.exit (-1);
-        }
-        try {
-            FileInputStream file = new FileInputStream (args[0]);
-            BufferedInputStream buffer = new BufferedInputStream (file);
-            DataInputStream stream = new DataInputStream (buffer);
-            ADump dump = new ADump ();   // Just to access contained classes
-            long os = 0;
-            for (int i=0; i<4; i++) {
-                int ch;
-                ch = stream.readUnsignedByte();
-                if (ch != sigByte[i]) {
-                    System.out.println ("No AIFF FORM header");
-                    System.exit (-2);
-                }
-		os++;
-            }
-            long ckSize = ModuleBase.readUnsignedInt (stream, ENDIAN);
-	    os += 4;
-            
-            // Read the file type
-            String formType = read4Chars (stream);
-	    os += 4;
-
-	    System.out.println ("00000000: RIFF " + ckSize + ": " + formType);
-
-            boolean endOfFile = false;
-            while (!endOfFile) {
-                // Read chunks
-                try {
-                    // Read chunk name.
-                    String ckID = read4Chars (stream);
-                    // Read size (excluding chunk name and size fields)
-		    ckSize = ModuleBase.readUnsignedInt (stream, ENDIAN);
-                    System.out.print (leading (os, 8) + os + ": " + ckID +
-				      " " + ckSize);
-		    long alreadyRead = 0;
-		    if (ckID.equals ("fact")) {
-			long sampleLength =
-			    ModuleBase.readUnsignedInt (stream, ENDIAN);
-			System.out.print (": " + sampleLength);
-			alreadyRead = 4;
-		    }
-		    else if (ckID.equals ("fmt ")) {
-			int formatTag = ModuleBase.readUnsignedShort (stream,
-								      ENDIAN);
-			int channels = ModuleBase.readUnsignedShort (stream,
-								     ENDIAN);
-			long samplesPerSec =
-			    ModuleBase.readUnsignedInt (stream, ENDIAN);
-			long avgBytesPerSec =
-			    ModuleBase.readUnsignedInt (stream, ENDIAN);
-			int blockAlign = ModuleBase.readUnsignedShort (stream,
-								       ENDIAN);
-			String hex = Integer.toHexString (formatTag);
-			System.out.print (": 0x" + leading (hex, 4) + hex +
-					  " " + channels + " " +
-					  samplesPerSec + " " +
-					  avgBytesPerSec + " " + blockAlign);
-			alreadyRead = 14;
-			if (ckSize > 14) {
-			    int bitsPerSample =
-				ModuleBase.readUnsignedShort (stream, ENDIAN);
-			    System.out.print (" " + bitsPerSample);
-			    alreadyRead = 16;
-			    if (ckSize > 16) {
-				int size =
-				    ModuleBase.readUnsignedShort (stream,
-								  ENDIAN);
-				System.out.print (" " + size);
-				alreadyRead = 18;
-				if (size == 22) {
-				    int validBitsPerSample =
-					ModuleBase.readUnsignedShort (stream,
-								      ENDIAN);
-				    long channelMask =
-					ModuleBase.readUnsignedInt (stream,
-								    ENDIAN);
-				    hex = Long.toHexString (channelMask);
-				    System.out.print (" " +
-						      validBitsPerSample +
-						      " 0x" +
-						      leading (hex, 8) + hex +
-						      " 0x");
-				    for (int i=0; i<4; i++) {
-					long guid =
-					    ModuleBase.readUnsignedInt (
-								  stream,
-								  ENDIAN);
-					hex = Long.toHexString (guid);
-					System.out.print (leading (hex, 8) +
-							  hex);
-				    }
-				    alreadyRead = 40;
-				}
-			    }
-			}
-		    }
-		    System.out.println ();
-
-                    if (ckID.equals ("list") || ckID.equals ("LIST")) {
-                        readNestedChunks (ckID, stream, ckSize, os + 8);
-                    }
-                    else {
-                        stream.skipBytes ((int) (ckSize - alreadyRead));
-                    }
-                    os += ckSize + 8;
-                }
-                catch (EOFException e) {
-                    endOfFile = true;
-                }
-            }
-        }
-        catch (Exception e) {
-        }
-    }
-    
-    /* The "list" and "LIST" chunks (which are two distinct chunk types)
-       hold nested chunks. */
-    private static void readNestedChunks 
-            (String ckID, DataInputStream stream, long ckSize, long os)
-            throws IOException
-    {
-        String listType = read4Chars (stream);
-        System.out.println ("List type = " + listType);
-        while (ckSize > 0) {
-            String subCkID = read4Chars (stream);
-            long subCkSize = ModuleBase.readUnsignedInt (stream, ENDIAN, null);
-            System.out.println (leading (os, 8) + os + ": " +
-                    ckID + "/" + subCkID + " " + subCkSize);
-            stream.skipBytes ((int) subCkSize);
-            os += subCkSize + 8;
-            ckSize -= subCkSize + 8;
-        }
-    }
-    
-    private static String read4Chars (DataInputStream stream) 
-            throws IOException
-    {
-        StringBuffer sbuf = new StringBuffer(4);
-        for (int i = 0; i < 4; i++) {
-            int ch = ModuleBase.readUnsignedByte(stream, null);
-            sbuf.append((char) ch);
-        }
-        return sbuf.toString ();
-    }
-}

jhove/classes/build.xml

@@ -1,128 +0,0 @@
-<project name="Jhove" default="main-dist" basedir=".">
-  <description>Main build file
-    Jhove - JSTOR/Harvard Object Validation Environment
-    Version 1.1 2006-02-13
-    Copyright 2004-2006 by JSTOR and the President and Fellows of Harvard College
-  </description>
-
-  <!-- set global properties for this build -->
-  <property name="classpath" value=".:../bin/jhove.jar"/>
-  <property name="api" location="edu/harvard/hul/ois/jhove"/>
-  <property name="viewer" location="edu/harvard/hul/ois/jhove/viewer"/>
-  <property name="root" location=".."/>
-  <property name="manifest" location="${viewer}/META-INF"/>
-
-  <target name="main-init" description="Create the time stamp">
-    <tstamp>
-      <format property="timestamp.isoformat" pattern="yyyy-MM-dd'T'HH:mm:ss"/>
-    </tstamp>
-  </target>
-
-  <target name="main-dist" depends="api,main,view"/>
-
-  <target name="api" description="Compile the API">
-    <ant dir="${api}" inheritAll="false">
-      <property name="dbg" value="${dbg}"/>
-    </ant>
-  </target>
-
-  <target name="main-compile" depends="main-init"
-          description="Compile the main file">
-    <javac compiler="javac1.5" target="1.5" srcdir="." debug="${dbg}" classpath="${classpath}"/>
-  </target>
-
-  <target name="main" depends="main-compile, app-manifest"
-          description="Build the app jar">
-    <jar destfile="${root}/bin/JhoveApp.jar" basedir="." index="true"
-         manifest="./META-INF/MANIFEST.MF"
-         includes="Jhove.class,
-              GDump.class, JDump.class, PDump.class, TDump.class,
-              J2Dump.class,J2Dump$Box.class,
-              ADump.class,
-              WDump.class, UserHome.class,
-              edu/harvard/hul/ois/jhove/*.class,
-              edu/harvard/hul/ois/jhove/*.xsd,
-              edu/harvard/hul/ois/jhove/handler/*.class,
-              edu/harvard/hul/ois/jhove/handler/audit/*.class,
-              edu/harvard/hul/ois/jhove/module/*.class,
-              edu/harvard/hul/ois/jhove/module/aiff/*.class,
-              edu/harvard/hul/ois/jhove/module/gif/*.class,
-              edu/harvard/hul/ois/jhove/module/html/*.class,
-              edu/harvard/hul/ois/jhove/module/html/*.dtd,
-              edu/harvard/hul/ois/jhove/module/html/*.ent,
-              edu/harvard/hul/ois/jhove/module/iff/*.class,
-              edu/harvard/hul/ois/jhove/module/jpeg/*.class,
-              edu/harvard/hul/ois/jhove/module/jpeg2000/*.class,
-              edu/harvard/hul/ois/jhove/module/pdf/*.class,
-              edu/harvard/hul/ois/jhove/module/tiff/*.class,
-              edu/harvard/hul/ois/jhove/module/wave/*.class,
-	      edu/harvard/hul/ois/jhove/module/xml/*.class"/>
-  </target>
-
-  <target name="app-manifest" depends="main-init">
-    <mkdir dir="${manifest}"/>
-    <manifest file="./META-INF/MANIFEST.MF">
-      <attribute name="Built-By" value="${user.name}"/>
-      <attribute name="Built-On" value="${timestamp.isoformat}"/>
-      <attribute name="Main-Class" value="Jhove"/>
-      <section name="JHOVE">
-        <attribute name="Version" value="1.0"/>
-        <attribute name="Package" value="Jhove app"/>
-        <attribute name="Rights"  value="Copyright 2004-2006 by JSTOR and the President and Fellows of Harvard College"/>
-      </section>
-    </manifest>
-  </target>
-
-  <target name="view-manifest" depends="main-init">
-    <mkdir dir="${manifest}"/>
-    <manifest file="${manifest}/MANIFEST.MF">
-      <attribute name="Built-By" value="${user.name}"/>
-      <attribute name="Built-On" value="${timestamp.isoformat}"/>
-      <attribute name="Main-Class" value="JhoveView"/>
-      <section name="JHOVE">
-        <attribute name="Version" value="1.0"/>
-        <attribute name="Package" value="Swing Viewer"/>
-        <attribute name="Rights"  value="Copyright 2004-2006 by JSTOR and the President and Fellows of Harvard College"/>
-      </section>
-    </manifest>
-  </target>
-
-  <target name="view" description="Compile the viewer application" 
-             depends="api,main,view-manifest">
-    <jar destfile="${root}/bin/JhoveView.jar" basedir="." index="true"
-         manifest="${manifest}/MANIFEST.MF"
-         includes="JhoveView.class,
-              edu/harvard/hul/ois/jhove/*.class,
-              edu/harvard/hul/ois/jhove/handler/*.class,
-              edu/harvard/hul/ois/jhove/handler/audit/*.class,
-              edu/harvard/hul/ois/jhove/module/*.class,
-              edu/harvard/hul/ois/jhove/module/aiff/*.class,
-              edu/harvard/hul/ois/jhove/module/gif/*.class,
-              edu/harvard/hul/ois/jhove/module/html/*.class,
-              edu/harvard/hul/ois/jhove/module/html/*.dtd,
-              edu/harvard/hul/ois/jhove/module/html/*.ent,
-              edu/harvard/hul/ois/jhove/module/iff/*.class,
-              edu/harvard/hul/ois/jhove/module/jpeg/*.class,
-              edu/harvard/hul/ois/jhove/module/jpeg2000/*.class,
-              edu/harvard/hul/ois/jhove/module/pdf/*.class,
-              edu/harvard/hul/ois/jhove/module/tiff/*.class,
-              edu/harvard/hul/ois/jhove/module/wave/*.class,
-              edu/harvard/hul/ois/jhove/module/xml/*.class,
-              edu/harvard/hul/ois/jhove/viewer/*.gif,
-              edu/harvard/hul/ois/jhove/viewer/*.class"/>
-  </target>
-
-  <target name="main-clean">
-    <delete>
-      <fileset dir="." includes="*~ \#*"/>
-    </delete>
-    <ant dir="${api}" target="api-clean" inheritAll="false"/>
-  </target>
-
-  <target name="main-cleanclass">
-    <delete>
-      <fileset dir="." includes="*.class*"/>
-    </delete>
-    <ant dir="${api}" target="api-cleanclass" inheritAll="false"/>
-  </target>
-</project>

jhove/classes/edu/harvard/hul/ois/jhove/AESAudioMetadata.java

@@ -1,940 +0,0 @@
-/**********************************************************************
- * Jhove - JSTOR/Harvard Object Validation Environment
- * Copyright 2004-2005 by JSTOR and the President and Fellows of Harvard College
- *
- **********************************************************************/
-
-package edu.harvard.hul.ois.jhove;
-
-import java.util.*;
-
-/**
- * Encapsulation of the AES Metadata for Audio documents
- *
- * @author Gary McGath
- *
- */
-public class AESAudioMetadata 
-{
-    /******************************************************************
-     * PUBLIC CLASS FIELDS.
-     ******************************************************************/
-
-    /** Big-endian constant. */
-    public static final int BIG_ENDIAN = 0;
-
-    /** Little-endian constant. */
-    public static final int LITTLE_ENDIAN = 1;
-
-    /** Analog / digital labels. */
-    public static final String [] A_D = {
-    "ANALOG", "PHYS_DIGITAL", "FILE_DIGITAL"
-    };
-    
-    /** Values for primary identifier type */
-    public static final String
-        FILE_NAME = "FILE_NAME",
-        OTHER = "OTHER";
-
-    /** Constant for an undefined integer value. */
-    public static final int NULL = -1;
-    /** Constant for an undefined floating-point value. */
-    public static final double NILL = -1.0;
-
-    /******************************************************************
-     * PRIVATE INSTANCE FIELDS.
-     *
-     ******************************************************************/
-
-    /** Constant value for the SchemaVersion field */
-    public static final String SCHEMA_VERSION = "1.02b";
-    
-    /** Constant value for the disposition field */
-    private static final String DEFAULT_DISPOSITION = "validation";
-
-    private String _analogDigitalFlag;
-    private String _appSpecificData;
-    private String _audioDataEncoding;
-    private int _byteOrder;
-    private String _disposition;
-    private List _faceList;
-    private long _firstSampleOffset;
-    private String _format;
-    private List _formatList;
-    private int _numChannels;
-    private String _primaryIdentifier;
-    private String _primaryIdentifierType;
-    private String _primaryIdentifierOtherType;
-    private String _schemaVersion;
-    private String _specificationVersion;
-    private String[] _use;
-
-    /* Most recently added FormatRegion */
-    private FormatRegion _curFormatRegion;
-    /* Most recently added Face */
-    private Face _curFace;
-
-    /******************************************************************
-     * CLASS CONSTRUCTOR.
-     ******************************************************************/
-
-    /** Instantiate a <code>NisoImageMetadata</code> object.
-     */
-    public AESAudioMetadata ()
-    {
-        _schemaVersion = SCHEMA_VERSION;
-        _disposition = DEFAULT_DISPOSITION;
-        _analogDigitalFlag = null;
-        _format = null;
-        _specificationVersion = null;
-        _audioDataEncoding = null;
-        _primaryIdentifier = null;
-        _primaryIdentifierType = null;
-        _use = null;
-
-        // We add one format region to get started.  In practice,
-        // that one is all we're likely to need. but more can be
-        // added if necessary.
-        _formatList = new LinkedList ();
-        _faceList = new LinkedList ();
-        addFormatRegion ();
-        addFace ();
-        _numChannels = NULL;
-        _byteOrder = NULL;
-        _firstSampleOffset = NULL;
-    }
-    
-    /******************************************************************
-     * PUBLIC STATIC INTERFACES.
-     * 
-     ******************************************************************/
-    /**
-     *  Public interface to the nested FormatRegion object.  Instances
-     *  of this should be created only by addFormatRegion, but can be
-     *  accessed through the public methods of this interface.
-     */
-    public static interface FormatRegion {
-        /** Returns the bit depth. */
-        public int getBitDepth ();
-        /** Returns the bitrate reduction (compression information).
-         *  This will be an array of seven strings (which may be
-         *  empty, but should never be null) interpreted as follows:
-         *  <ul>
-         *  <li>0: codecName
-         *  <li>1: codecNameVersion
-         *  <li>2: codecCreatorApplication
-         *  <li>3: codecCreatorApplicationVersion
-         *  <li>4: codecQuality
-         *  <li>5: dataRate
-         *  <li>6: dataRateMode
-         *  </ul> 
-         */
-        public String[] getBitrateReduction ();
-        /** Returns the sample rate. */
-        public double getSampleRate ();
-        /** Returns the word size. */
-        int getWordSize ();
-        /** Returns <code>true</code> if the region is empty. */
-        public boolean isEmpty ();
-        /** Sets the bit depth value. */
-        public void setBitDepth (int bitDepth);
-        /** Sets the bitrate reduction information to null (no compression). */
-        public void clearBitrateReduction ();
-        /** Sets the bitrate reduction (aka compression type). */
-        public void setBitrateReduction (String codecName,
-                String codecNameVersion,
-                String codecCreatorApplication,
-                String codecCreatorApplicationVersion,
-                String codecQuality,
-                String dataRate,
-                String dataRateMode);
-        /** Sets the sample rate. */
-        public void setSampleRate (double sampleRate);
-        /** Sets the word size. */
-        public void setWordSize (int wordSize);
-    }
-
-    /**
-     *  Public interface to the nested TimeDesc object.  Instances
-     *  of this should be created only by appropriate methods, but can be
-     *  accessed through the public methods of this interface.
-     */
-    public static interface TimeDesc {
-        /** Returns the hours component. */
-        public int getHours ();
-        /** Returns the minutes component. */
-        public int getMinutes ();
-        /** Returns the seconds component. */
-        public int getSeconds ();
-        /** Returns the frames component of the fraction of a second.
-         *  We always consider frames to be thirtieths of a second. */
-        public int getFrames ();
-        /** Returns the samples remaining after the frames part of
-         *  the fractional second. */
-        public int getSamples ();
-        /** Returns the sample rate on which the samples remainder
-         *  is based. */
-        public double getSampleRate ();
-    }
-    
-    /** Public interface to the nested Face object. Instances
-     *  of this should be created only by appropriate methods, but can be
-     *  accessed through the public methods of this interface. */
-    public static interface Face {
-        /** Returns an indexed FaceRegion. */
-        public FaceRegion getFaceRegion (int i);
-        
-        /** Adds a FaceRegion. This may be called repeatedly to
-         *  add multiple FaceRegions. */
-        public void addFaceRegion ();
-        
-        /** Returns the starting time. */
-        public TimeDesc getStartTime ();
-        
-        /** Returns the duration. */
-        public TimeDesc getDuration ();
-        
-        /** Returns the direction. */
-        public String getDirection ();
-        
-        /** Sets the starting time.  This will be converted
-         *  into a TimeDesc. */
-        public void setStartTime (long samples);
-        
-        /** Sets the duration. This will be converted
-         *  into a TimeDesc. */
-        public void setDuration (long samples);
-        
-        /** Sets the direction.  This must be one of the
-         *  directionTypes.  FORWARD is recommended for most
-         *  or all cases. 
-         */
-        public void setDirection (String direction);
-
-        /* End of interface Face */
-    }
-    
-    /** Public interface to the nested FaceRegion object. Instances
-     *  of this should be created only by appropriate methods, but can be
-     *  accessed through the public methods of this interface. */
-    public static interface FaceRegion {
-        /** Returns the starting time. */
-        public TimeDesc getStartTime ();
-        
-        /** Returns the duration. */
-        public TimeDesc getDuration ();
-
-        /** Returns the channel map locations.  The array length must
-         *  equal the number of channels. */
-        public String[] getMapLocations ();
-
-        /** Sets the starting time. */
-        public void setStartTime (long samples);
-        
-        /** Sets the duration. */
-        public void setDuration (long samples);
-        
-        /** Sets the channel map locations.  The array length must
-         *  equal the number of channels. */
-        public void setMapLocations (String[] locations);
-
-        /* End of interface FaceRegion */
-    }
-
-    /******************************************************************
-     * STATIC MEMBER CLASSES.
-     * 
-     ******************************************************************/
-    /** The implementation of the FormatRegion interface.  The combination
-     *  of a public interface and a private implementation is suggested
-     *  in _Java in a Nutshell_.
-     */
-    class FormatRegionImpl implements FormatRegion {
-        
-        private int _bitDepth;
-        private double _sampleRate;
-        private int _wordSize;
-        private String[] _bitrateReduction;
-
-        public FormatRegionImpl () {
-            _bitDepth = NULL;
-            _sampleRate = NILL;
-            _wordSize = NULL;
-            _bitrateReduction = null;
-        }
-        
-        /** Returns bit depth. */
-        public int getBitDepth ()
-        {
-            return _bitDepth;
-        }
-        
-        /** Returns the bitrate reduction (compression information).
-         *  This will be an array of seven strings (which may be
-         *  empty but not null) interpreted respectively as follows:
-         *  <ul>
-         *  <li>0: codecName
-         *  <li>1: codecNameVersion
-         *  <li>2: codecCreatorApplication
-         *  <li>3: codecCreatorApplicationVersion
-         *  <li>4: codecQuality
-         *  <li>5: dataRate
-         *  <li>6: dataRateMode
-         *  </ul> 
-         */
-        public String[] getBitrateReduction ()
-        {
-            return _bitrateReduction;
-        }
-        
-        /** Returns sample rate. */
-        public double getSampleRate ()
-        {
-            return _sampleRate;
-        }
-        
-        /** Returns word size. */
-        public int getWordSize ()
-        {
-            return _wordSize;
-        }
-        
-        /** Returns true if the FormatRegion contains only
-         *  default values. */
-        public boolean isEmpty ()
-        {
-            return _bitDepth == NULL &&
-                   _sampleRate == NILL &&
-                   _wordSize == NULL;
-        }
-
-        /** Sets bit depth. */
-        public void setBitDepth (int bitDepth)
-        {
-            _bitDepth = bitDepth;
-        }
-
-        /** Sets the bitrate reduction information to null (no compression). */
-        public void clearBitrateReduction ()
-        {
-            _bitrateReduction = null;
-        }
-
-        /** Sets the bitrate reduction (compression type). */
-        public void setBitrateReduction (String codecName,
-                String codecNameVersion,
-                String codecCreatorApplication,
-                String codecCreatorApplicationVersion,
-                String codecQuality,
-                String dataRate,
-                String dataRateMode)
-        {
-            _bitrateReduction = new String[7];
-            _bitrateReduction[0] = codecName;
-            _bitrateReduction[1] = codecNameVersion;  
-            _bitrateReduction[2] = codecCreatorApplication;
-            _bitrateReduction[3] = codecCreatorApplicationVersion;
-            _bitrateReduction[4] = codecQuality;
-            _bitrateReduction[5] = dataRate;
-            _bitrateReduction[6] = dataRateMode;
-        }
-
-        /** Sets sample rate. */
-        public void setSampleRate (double sampleRate)
-        {
-            _sampleRate = sampleRate;
-        }
-        
-        
-        /** Sets word size. */
-        public void setWordSize (int wordSize)
-        {
-            _wordSize = wordSize;
-        }
-        
-        /* End of FormatRegionImpl */
-    }
-
-    /** The implementation of the TimeDesc interface.  The combination
-     *  of a public interface and a private implementation is suggested
-     *  in _Java in a Nutshell_.
-     */
-    class TimeDescImpl implements TimeDesc
-    {
-        private int _hours;
-        private int _minutes;
-        private int _seconds;
-        private int _frames;
-        private int _samples;
-        private double _sampleRate;
-	private int _frameCount;
-        
-	/* Constructor rewritten to avoid rounding errors when converting to
-	 * TCF. Now uses integer remainder math instead of floating point.
-	 * Changed the base unit from a double representing seconds to a long
-	 * representing samples. Changed all existing calls (that I could find)
-	 * to this method to accomodate this change.
-	 *
-	 * @author David Ackerman
-	 */
-        public TimeDescImpl (long samples)
-	{
-	    long _sample_count = samples;
-	    _frameCount = 30;
-	    _sampleRate = _curFormatRegion.getSampleRate ();
-			
-	    /* It seems that this method is initially called before a valid
-	     * sample rate has been established, causing a divide by zero
-	     * error.
-	     */
-	    if (_sampleRate < 0) {
-                _sampleRate = 44100.0; //reasonable default value 
-            }
-
-	    long sample_in_1_frame = (long)(_sampleRate/_frameCount);
-	    long sample_in_1_second = sample_in_1_frame * _frameCount;
-	    long sample_in_1_minute = sample_in_1_frame * _frameCount * 60;
-	    long sample_in_1_hour = sample_in_1_frame * _frameCount * 60 * 60;
-	    long sample_in_1_day = sample_in_1_frame * _frameCount * 60 * 60 * 24;
-			
-	    // BWF allows for a negative timestamp but tcf does not, so adjust
-	    // time accordingly
-	    // this might be a good place to report a warning during validation
-	    if (_sample_count < 0) {
-		_sample_count += sample_in_1_day;
-		_sample_count = (_sample_count % sample_in_1_day);
-	    }
-		
-	    _hours = (int)(_sample_count / sample_in_1_hour);
-	    _sample_count -= (_hours * sample_in_1_hour);
-	    _minutes = (int)(_sample_count / sample_in_1_minute);
-	    _sample_count -= (_minutes * sample_in_1_minute);
-	    _seconds = (int)(_sample_count / sample_in_1_second);
-	    _sample_count -= (_seconds * sample_in_1_second);
-	    _frames = (int)(_sample_count / sample_in_1_frame);
-	    _sample_count -= (_frames * sample_in_1_frame);
-	    _samples = (int)_sample_count;
-			
-	    /* At present TCF does not have the ability to handle time stamps
-	     * > midnight. Industry practice is to roll the clock forward to
-	     * zero or back to 23:59:59:29... when crossing this boundary
-	     * condition.
-	     */
-	    _hours = _hours % 24;	
-        }
-        
-        /** Returns the hours component. */
-        public int getHours () {
-            return _hours;
-        }
-
-        /** Returns the minutes component. */
-        public int getMinutes () {
-            return _minutes;
-        }
-
-        /** Returns the seconds component. */
-        public int getSeconds () {
-            return _seconds;
-        }
-
-        /** Returns the frames component of the fraction of a second.
-         *  We always consider frames to be thirtieths of a second. */
-        public int getFrames () {
-            return _frames;
-        }
-
-        /** Returns the samples remaining after the frames part of
-         *  the fractional second. */
-        public int getSamples () {
-            return _samples;
-        }
-        
-        /** Returns the sample rate on which the samples remainder
-         *  is based. */
-        public double getSampleRate () {
-            return _sampleRate;
-        }
-    } /* End of TimeDescImpl */
-
-    /** The implementation of the Face interface.  The combination
-     *  of a public interface and a private implementation is suggested
-     *  in _Java in a Nutshell_.
-     */
-    class FaceImpl implements Face {
-        List _regionList;
-        TimeDesc _startTime;
-        TimeDesc _duration;
-        String _direction;
-        
-        
-        /** Constructor.  Initially the duration is set
-         *  to null, indicating unknown value. */
-        public FaceImpl ()
-        {
-            _regionList = new ArrayList ();
-            _startTime = new TimeDescImpl (0);
-            _duration = null;
-        }
-
-
-        /** Returns an indexed FaceRegion. */
-        public FaceRegion getFaceRegion (int i) {
-            return (FaceRegion) _regionList.get (i);
-        }
-        
-        /** Adds a FaceRegion. This may be called repeatedly to
-         *  add multiple FaceRegions. */
-        public void addFaceRegion () {
-            _regionList.add (new FaceRegionImpl ());
-        }
-        
-        /** Returns the starting time. Will be zero if not
-         *  explicitly specified. */
-        public TimeDesc getStartTime () {
-            return _startTime;
-        }
-        
-        /** Returns the duration. May be null if the duration
-         *  is unspecified. */
-        public TimeDesc getDuration () {
-            return _duration;
-        }
-
-        /** Returns the direction. */
-        public String getDirection ()
-        {
-            return _direction;
-        }
-
-        /** Sets the starting time.  This will be converted
-         *  into a TimeDesc. */
-        public void setStartTime (long samples)
-        {
-            _startTime = new TimeDescImpl (samples);
-        }
-        
-        /** Sets the duration. This will be converted
-         *  into a TimeDesc. */
-        public void setDuration (long samples)
-        {
-            _duration = new TimeDescImpl (samples);
-        }
-
-        /** Sets the direction.  This must be one of the
-         *  directionTypes.  FORWARD is recommended for most
-         *  or all cases. 
-         */
-        public void setDirection (String direction)
-        {
-            _direction = direction;
-        }
-
-        /* End of FaceImpl */
-    }
-
-
-    /** The implementation of the Face interface.  The combination
-     *  of a public interface and a private implementation is suggested
-     *  in _Java in a Nutshell_.
-     */
-    class FaceRegionImpl implements FaceRegion {
-        private TimeDesc _startTime;
-        private TimeDesc _duration;
-        private String[] _mapLocations;
-        
-        public FaceRegionImpl ()
-        {
-            _startTime = new TimeDescImpl (0);
-            _duration = null;
-        }
-        
-        /** Returns the starting time. */
-        public TimeDesc getStartTime () {
-            return _startTime;
-        }
-        
-        /** Returns the duration. */
-        public TimeDesc getDuration () {
-            return _duration;
-        }
-        
-        /** Returns the channel map locations.  The array length
-         *  will equal the number of channels. */
-        public String[] getMapLocations ()
-        {
-            return _mapLocations;
-        }
-
-        /** Sets the duration. This will be converted
-         *  into a TimeDesc. */
-        public void setStartTime (long samples) {
-            _startTime = new TimeDescImpl (samples);
-        }
-        
-        /** Sets the duration. This will be converted
-         *  into a TimeDesc. */
-        public void setDuration (long samples)
-        {
-            _duration = new TimeDescImpl (samples);
-        }
-
-        /** Sets the channel map locations.  The array length must
-         *  equal the number of channels. */
-        public void setMapLocations (String[] locations)
-        {
-            _mapLocations = locations;
-        }        
-        /* End of FaceRegionImpl */
-    }
-   
-    /* End of inner classes */
-
-    /******************************************************************
-     * PUBLIC INSTANCE METHODS.
-     * 
-     * Accessor methods.
-     ******************************************************************/
-
-    /** Returns analog/digital flag.  Value will always be
-     *  "FILE_DIGITAL" in practice. */
-    public String getAnalogDigitalFlag ()
-    {
-        return _analogDigitalFlag;
-    }
-    
-    /** Returns application-specific data.  We assume this is
-     *  representable in String format. 
-     */
-    public String getAppSpecificData ()
-    {
-        return _appSpecificData;
-    }
-    
-    /** Returns audio data encoding. */
-    public String getAudioDataEncoding ()
-    {
-        return _audioDataEncoding;
-    }
-
-    /** Returns the bitrate reduction (compression information).
-     *  This will be an array of seven strings (which may be
-     *  empty, but should never be null) interpreted as follows:
-     *  <ul>
-     *  <li>0: codecName
-     *  <li>1: codecNameVersion
-     *  <li>2: codecCreatorApplication
-     *  <li>3: codecCreatorApplicationVersion
-     *  <li>4: codecQuality
-     *  <li>5: dataRate
-     *  <li>6: dataRateMode
-     *  </ul> 
-     */
-    public String[] getBitrateReduction ()
-    {
-        return _curFormatRegion.getBitrateReduction();
-    }
-
-    /* Returns the sample rate. */
-    public double getSampleRate ()
-    {
-	return _curFormatRegion.getSampleRate ();
-    }
-
-    /** Return the byte order: 0 = big-endian; 1 = little-endian. */
-    public int getByteOrder ()
-    {
-        return _byteOrder;
-    }
-    
-    /** Returns disposition. */
-    public String getDisposition ()
-    {
-        return _disposition;
-    }
-    
-    /** Gets the list of Faces. Normally there will be only one face
-     *  in a digital file. */
-    public List getFaceList ()
-    {
-        return _faceList;
-    }
-    
-    /** Return the offset of the first byte of sample data. */
-    public long getFirstSampleOffset ()
-    {
-        return _firstSampleOffset;
-    }
-
-    /** Returns format name. */
-    public String getFormat ()
-    {
-        return _format;
-    }
-    
-    /** Gets the list of Format Regions.  Since one is created
-     *  automatically on initialization, it's possible that the
-     *  list will contain a Format Region with only default values.
-     *  This should be checked with isEmpty ().
-     */
-    public List getFormatList ()
-    {
-        return _formatList;
-    }
-    
-    /** Returns the names of the map locations.
-     *  The returned
-     *  value is an array whose length equals the number of
-     *  channels and whose elements correspond to channels 0, 1,
-     *  etc. 
-     */
-    public String[] getMapLocations() {
-        return _curFace.getFaceRegion(0).getMapLocations();
-    }
-    
-    /** Returns number of channels. */
-    public int getNumChannels ()
-    {
-        return _numChannels;
-    }
-
-    /** Returns primary identifier. */
-    public String getPrimaryIdentifier ()
-    {
-        return _primaryIdentifier;
-    }
-
-    /** Returns primary identifier type. */
-    public String getPrimaryIdentifierType ()
-    {
-        return _primaryIdentifierType;
-    }
-
-    /** Returns schema version. */
-    public String getSchemaVersion ()
-    {
-        return _schemaVersion;
-    }
-    
-    /** Returns specification version of the document format. */
-    public String getSpecificationVersion ()
-    {
-        return _specificationVersion;
-    }
-    
-    /** Returns the use (role of the document).
-     *  The value returned is an array of two strings,
-     *  the useType and the otherType. */
-    public String[] getUse ()
-    {
-        return _use;
-    }
-    
-
-    
-
-
-    /******************************************************************
-     * Mutator methods.
-     ******************************************************************/
-    
-    /** Sets the analog/digital flag.  The value set should always
-     *  be "FILE_DIGITAL". */
-    public void  setAnalogDigitalFlag (String flagType)
-    {
-        _analogDigitalFlag = flagType;
-    }
-
-    /** Sets the bitrate reduction (compression type). */
-    public void setBitrateReduction (String codecName,
-            String codecNameVersion,
-            String codecCreatorApplication,
-            String codecCreatorApplicationVersion,
-            String codecQuality,
-            String dataRate,
-            String dataRateMode)
-    {
-        _curFormatRegion.setBitrateReduction (codecName,
-                codecNameVersion, codecCreatorApplication,
-                codecCreatorApplicationVersion,
-                codecQuality, dataRate, dataRateMode);
-    }
-    
-    /** Set the bitrate reduction information to null (no compression). */
-    public void clearBitrateReduction ()
-    {
-        _curFormatRegion.clearBitrateReduction ();
-    }
-
-    /** Sets the byte order.
-     * @param order Byte order: 0 = big-endian, 1 = little-endian
-     */
-    public void setByteOrder (int order)
-    {
-	   _byteOrder = order;
-    }
-
-    /** Sets the byte order.
-     */
-    public void setByteOrder (String order)
-    {
-    	if (order.substring (0, 3).toLowerCase ().equals ("big")) {
-    	    _byteOrder = BIG_ENDIAN;
-    	}
-    	else if (order.substring (0, 6).toLowerCase ().equals ("little")) {
-    	    _byteOrder = LITTLE_ENDIAN;
-    	}
-    }
-
-    /** Sets the audio data encoding. */
-    public void setAudioDataEncoding (String audioDataEncoding)
-    {
-        _audioDataEncoding = audioDataEncoding;
-    }
-    
-    /** Set the application-specific data.  For present purposes,
-     *  we assume this is representable as a text string. */
-    public void setAppSpecificData (String data)
-    {
-        _appSpecificData = data;
-    }
-    
-    /** Sets the bit depth. */
-    public void setBitDepth (int bitDepth)
-    {
-        _curFormatRegion.setBitDepth (bitDepth);
-    }
-    
-    /** Sets the disposition. */
-    public void setDisposition (String disposition)
-    {
-        _disposition = disposition;
-    }
-
-    /** Sets the direction.  
-     *  This must be one of the values 
-     *  FORWARD, REVERSE, A_WIND, B_WIND, C_WIND, D_WIND,
-     *  FRONT, BACK.  FORWARD may be the only one that
-     *  makes sense for digital formats.
-     */
-    public void setDirection (String direction)
-    {
-        _curFace.setDirection (direction);
-    }
-    
-    /** Sets the duration in samples. 
-     * This affects the current face and its first FaceRegion.
-     */
-    public void setDuration (long duration)
-    {
-	_curFace.setDuration (duration);
-	_curFace.getFaceRegion(0).setDuration (duration);
-    }
-
-    /** Sets the offset of the first byte of sample data. */
-    public void setFirstSampleOffset (long offset)
-    {
-        _firstSampleOffset = offset;
-    }
-
-    /** Sets the format name. */
-    public void setFormat (String format)
-    {
-        _format = format;
-    }
-    
-    /** Sets the array of channel map locations. The length
-     *  of the array must equal the number of channels. */
-    public void setMapLocations (String[] locations) {
-        _curFace.getFaceRegion(0).setMapLocations (locations);
-    }
-
-    /** Sets the number of channels. */
-    public void setNumChannels (int numChannels)
-    {
-        _numChannels = numChannels;
-    }
-
-    /** Sets the primary identifier. */
-    public void setPrimaryIdentifier (String primaryIdentifier)
-    {
-        _primaryIdentifier = primaryIdentifier;
-    }
-    
-    /** Sets the primary identifier type. If the primary identifier
-     *  type is OTHER, use setOtherPrimaryIdentifierType instead.
-     */
-    public void setPrimaryIdentifierType (String primaryIdentifierType)
-    {
-        _primaryIdentifierType = primaryIdentifierType;
-    }
-
-    /** Sets the primary identifier type as "OTHER", and
-     *  set the otherType.
-     */
-    public void setOtherPrimaryIdentifierType (String otherType)
-    {
-        _primaryIdentifierType = "OTHER";
-        _primaryIdentifierOtherType = otherType;
-    }
-    
-    /** Sets the sample rate. */
-    public void setSampleRate (double sampleRate)
-    {
-        _curFormatRegion.setSampleRate (sampleRate);
-    }
-    
-    /** Sets the specification version of the document format.*/
-    public void setSpecificationVersion (String specificationVersion)
-    {
-        _specificationVersion = specificationVersion;
-    }
-
-    /** Sets the start time in samples. 
-     * This affects the current face and its first FaceRegion.
-     */
-    public void setStartTime (long samples)
-    {
-	_curFace.setStartTime (samples);
-	_curFace.getFaceRegion(0).setStartTime (samples);
-    }
-    
-    /** Sets the role of the document. Permitted values are
-     *  ORIGINAL_MASTER, PRESERVATION_MASTER, PRODUCTION_MASTER, 
-     *  SERVICE, PREVIEW, or OTHER.
-     *  If useType is "OTHER", then otherType
-     *  is significant.  Since OTHER is the only meaningful
-     *  value for a digital document, the code assumes this will always
-     *  be the case and uses otherType. */
-    public void setUse (String useType, String otherType)
-    {
-        _use = new String[] {useType, otherType};
-    }
-    
-    /** Sets the word size. */
-    public void setWordSize (int wordSize)
-    {
-        _curFormatRegion.setWordSize (wordSize);
-    }
-    
-    /** Adds a FormatRegion object to a FormatSize list.
-     *  The most recently added FormatRegion object will
-     *  be filled in by setBitDepth, setSampleRate, and
-     *  setWordSize.
-     */
-    public void addFormatRegion ()
-    {
-        _curFormatRegion = new FormatRegionImpl ();
-        _formatList.add (_curFormatRegion);
-    }
-    
-    /** Adds a Face.  
-     */
-    public void addFace ()
-    {
-        _curFace = new FaceImpl ();
-        _faceList.add (_curFace);
-        _curFace.addFaceRegion();
-    }
-    
-}

jhove/classes/edu/harvard/hul/ois/jhove/Agent.java

@@ -1,167 +0,0 @@
-/**********************************************************************
- * Jhove - JSTOR/Harvard Object Validation Environment
- * Copyright 2003 by JSTOR and the President and Fellows of Harvard College
- **********************************************************************/
-
-package edu.harvard.hul.ois.jhove;
-
-/**
- *  Encapsulates information about agents, either individual 
- *  persons or corporate bodies.
- */
-public class Agent
-{
-    /******************************************************************
-     * PRIVATE INSTANCE FIELDS.
-     ******************************************************************/
-
-    private String _name;
-    private AgentType _type;
-    private String _address;
-    private String _telephone;
-    private String _fax;
-    private String _email;
-    private String _web;
-    private String _note;
-
-    /******************************************************************
-     * CLASS CONSTRUCTOR.
-     ******************************************************************/
-
-    /**
-     *  Creates an Agent given a name and an AgentType.
-     */
-    public Agent (String name, AgentType type)
-    {
-	_name = name;
-	_type = type;
-    }
-
-    /******************************************************************
-     * PUBLIC INSTANCE METHODS.
-     ******************************************************************/
-
-    /**
-     *  Returns the value of the address property.
-     */
-    public String getAddress ()
-    {
-	return _address;
-    }
-
-    /**
-     *  Returns the value of the email property.
-     */
-    public String getEmail ()
-    {
-	return _email;
-    }
-
-    /**
-     *  Returns the value of the fax property.
-     */
-    public String getFax ()
-    {
-	return _fax;
-    }
-
-    /**
-     *  Returns the value of the name property.
-     */
-    public String getName ()
-    {
-	return _name;
-    }
-
-    /**
-     *  Returns the value of the note property.
-     */
-    public String getNote ()
-    {
-	return _note;
-    }
-
-    /**
-     *  Returns the value of the telephone property.
-     */
-    public String getTelephone ()
-    {
-	return _telephone;
-    }
-
-    /**
-     *  Returns the value of the type property.
-     */
-    public AgentType getType ()
-    {
-	return _type;
-    }
-
-    /**
-     *  Returns the value of the web property.
-     */
-    public String getWeb ()
-    {
-	return _web;
-    }
-
-    /******************************************************************
-     * Mutator methods.
-     ******************************************************************/
-
-    /**
-     *  Sets the value of the address property.
-     */
-    public void setAddress (String address)
-    {
-	_address = address;
-    }
-
-    /**
-     *  Sets the value of the email property.
-     */
-    public void setEmail (String email)
-    {
-	_email = email;
-    }
-
-    /**
-     *  Sets the value of the fax property.
-     */
-    public void setFax (String fax)
-    {
-	_fax = fax;
-    }
-
-    /**
-     *  Sets the value of the name property.
-     */
-    public void setName (String name)
-    {
-	_name = name;
-    }
-
-    /**
-     *  Sets the value of the note property.
-     */
-    public void setNote (String note)
-    {
-	_note = note;
-    }
-
-    /**
-     *  Sets the value of the telephone property.
-     */
-    public void setTelephone (String telephone)
-    {
-	_telephone = telephone;
-    }
-
-    /**
-     *  Sets the value of the web property.
-     */
-    public void setWeb (String web)
-    {
-	_web = web;
-    }
-}

jhove/classes/edu/harvard/hul/ois/jhove/AgentType.java

@@ -1,60 +0,0 @@
-/**********************************************************************
- * Jhove - JSTOR/Harvard Object Validation Environment
- * Copyright 2003 by JSTOR and the President and Fellows of Harvard College
- **********************************************************************/
-
-package edu.harvard.hul.ois.jhove;
-
-
-/**
- *  This class defines enumerated types for an Agent. 
- *  Applications will not create or modify AgentTypes, but will
- *  use one of the predefined AgentType instances COMMERCIAL, GOVERNMENT,
- *  EDUCATIONAL, NONPROFIT, STANDARD, or OTHER.
- *
- *  @see Agent
- */
-public final class AgentType
-    extends EnumerationType
-{
-    /******************************************************************
-     * PUBLIC STATIC INSTANCES.
-     ******************************************************************/
-
-    /**
-     *  Agent type for a commercial entity.
-     */
-    public static final AgentType COMMERCIAL = new AgentType ("Commercial");
-    /**
-     *  Agent type for a governmental body.
-     */
-    public static final AgentType GOVERNMENT = new AgentType ("Government");
-    /**
-     *  Agent type for an educational institution.
-     */
-    public static final AgentType EDUCATIONAL = new AgentType ("Educational");
-    /**
-     *  Agent type for a non-profit organization.
-     */
-    public static final AgentType NONPROFIT = new AgentType ("Non-profit");
-    /**
-     *  Agent type for a standards body.
-     */
-    public static final AgentType STANDARD = new AgentType ("Standards body");
-    /**
-     *  Agent type that doesn't fit the other categories.
-     */
-    public static final AgentType OTHER = new AgentType ("Other");
-
-    /******************************************************************
-     * CLASS CONSTRUCTOR.
-     ******************************************************************/
-
-    /** 
-     *  Applications will never create AgentTypes directly.
-     **/
-    private AgentType (String value)
-    {
-	super (value);
-    }
-}

jhove/classes/edu/harvard/hul/ois/jhove/AnalogDigitalFlagType.java

@@ -1,40 +0,0 @@
-/**********************************************************************
- * Jhove - JSTOR/Harvard Object Validation Environment
- * Copyright 2004 by JSTOR and the President and Fellows of Harvard College
- *
- **********************************************************************/
-
-package edu.harvard.hul.ois.jhove;
-
-/**
- *  This class defines enumerated types for the analog/digital
- *  flag of AESAudioMetadata. 
- *  Applications will not create or modify instances of this class, but will
- *  use one of the predefined AnalogDigitalFlagType instances.
- * 
- * @author Gary McGath
- *
- */
-public class AnalogDigitalFlagType extends EnumerationType {
-
-    /** Enumeration instance for analog data */
-    public static final AnalogDigitalFlagType ANALOG = 
-        new AnalogDigitalFlagType ("ANALOG");
-
-    /** Enumeration instance for physical digital data */
-    public static final AnalogDigitalFlagType PHYS_DIGITAL = 
-        new AnalogDigitalFlagType ("PHYS_DIGITAL");
-
-    /** Enumeration instance for FILE digital data */
-    public static final AnalogDigitalFlagType FILE_DIGITAL = 
-        new AnalogDigitalFlagType ("FILE_DIGITAL");
-
-    /** 
-     *  Applications will never create PropertyTypes directly.
-     **/
-    private AnalogDigitalFlagType (String value)
-    {
-        super (value);
-    }
-
-}

jhove/classes/edu/harvard/hul/ois/jhove/App.java

@@ -1,128 +0,0 @@
-/**********************************************************************
- * Jhove - JSTOR/Harvard Object Validation Environment
- * Copyright 2003 by JSTOR and the President and Fellows of Harvard College
- **********************************************************************/
-
-package edu.harvard.hul.ois.jhove;
-
-//import java.io.*;
-import java.util.*;
-
-/**
- *  The application class for JHOVE. One instance of this class is
- *  generated by the application.  Various utility and informational
- *  methods are contained here.
- */
-public class App
-{
-    /******************************************************************
-     * PRIVATE INSTANCE FIELDS.
-     ******************************************************************/
-
-    /** Application build date. */
-    private Date _date;
-
-    /** Application name. */
-    private String _name;
-
-    /** Application release identifier. */
-    private String _release;
-
-    /** Application rights statement. */
-    private String _rights;
-
-    /** Application invocation syntax. */
-    private String _usage;
-
-    /******************************************************************
-     * CLASS CONSTRUCTOR.
-     ******************************************************************/
-
-    /**
-     *   Creates an App object.
-     *   @param name            Name of the application.
-     *   @param release         Release identifier.
-     *   @param date            Last modification date of the application code,
-     *                          in the form of an array of three numbers.
-     *                          <code>date[0]</code> is the year, 
-     *                          <code>date[1]</code> the month, and
-     *                          <code>date[2]</code> the day.
-     *   @param usage           String summarizing command line usage, to
-     *                          output when app name is typed with no
-     *                          arguments or flags.
-     *   @param rights            Copyright or other rights statement.
-     */
-    public App (String name, String release, int [] date, String usage,
-                String rights)
-    {
-        Calendar calendar = new GregorianCalendar ();
-        calendar.set (date[0], date[1]-1, date[2]);
-
-        _name    = name;
-        _release = release;
-        _date    = calendar.getTime ();
-        _usage   = usage;
-        _rights  = rights;
-    }
-
-    /******************************************************************
-     * PUBLIC INSTANCE METHODS.
-     *
-     * Accessor methods.
-     ******************************************************************/
-
-    /**
-     *  Returns application code creation date
-     */
-    public Date getDate ()
-    {
-        return _date;
-    }
-
-    /**
-     *  Returns the name of this application
-     */
-    public String getName ()
-    {
-        return _name;
-    }
-
-    /**
-     *  Returns the release identifier for this application.
-     */
-    public String getRelease ()
-    {
-        return _release;
-    }
-
-    /**
-     *  Returns the rights string.
-     */
-    public String getRights ()
-    {
-        return _rights;    
-    }
-    
-    /**
-     *  Returns the usage string, which should be output when the user
-     *  enters a command line with only the application name.
-     */
-    public String getUsage ()
-    {
-        return _usage;
-    }
-
-    /******************************************************************
-     * Serialization methods.
-     ******************************************************************/
-
-    /**
-     *  Outputs detailed information about the application,
-     *  including configuration, available modules and handlers,
-     *  etc.
-     */
-    public void show (OutputHandler handler)
-    {
-        handler.show (this);
-    }
-}

jhove/classes/edu/harvard/hul/ois/jhove/ByteArrayXMPSource.java

@@ -1,66 +0,0 @@
-/**********************************************************************
- * Jhove - JSTOR/Harvard Object Validation Environment
- * Copyright 2003 by JSTOR and the President and Fellows of Harvard College
- *
- **********************************************************************/
-
-package edu.harvard.hul.ois.jhove;
-
-import java.io.*;
-
-/**
- * Class for providing an InputSource to XMPHandler,
- * with a ByteArrayInputStream as the basis of the
- * InputSource.  This is suitable for a number of modules.
- *
- *  @author Gary McGath
- *
- */
-public class ByteArrayXMPSource extends XMPSource {
-
-    /* The underlying ByteArrayInputStream. */
-    ByteArrayInputStream _instrm;
-
-    /**
-     * Constructor based on ByteArrayInputStream. 
-     * 
-     * @param instrm   ByteArrayInputStream containing the XMP
-     */
-    public ByteArrayXMPSource (ByteArrayInputStream instrm)
-            throws IOException
-    {
-        super (new InputStreamReader
-               (new XMLWrapperStream (instrm)));
-        _instrm = instrm;
-        // Prepare for resetting.
-        instrm.mark (instrm.available ());
-    }
-
-
-    /**
-     * Constructor based on ByteArrayInputStream with encoding. 
-     * 
-     * @param instrm   ByteArrayInputStream containing the XMP
-     */
-    public ByteArrayXMPSource (ByteArrayInputStream instrm,
-                    String encoding)
-            throws IOException
-    {
-        super (new InputStreamReader
-               (new XMLWrapperStream (instrm), encoding));
-        _instrm = instrm;
-        // Prepare for resetting.
-        instrm.mark (instrm.available ());
-    }
-
-
-
-    /* (non-Javadoc)
-     * @see edu.harvard.hul.ois.jhove.XMPSource#resetReader()
-     */
-    protected void resetReader() {
-        _instrm.reset ();
-        _reader = new InputStreamReader (_instrm);
-    }
-
-}

jhove/classes/edu/harvard/hul/ois/jhove/Callback.java

@@ -1,25 +0,0 @@
-/**********************************************************************
- * Jhove - JSTOR/Harvard Object Validation Environment
- * Copyright 2003 by JSTOR and the President and Fellows of Harvard College
- **********************************************************************/
-
-package edu.harvard.hul.ois.jhove;
-
-/**
- *  An interface for supporting a general, simple callback function.
- */
-public interface Callback 
-{
-    /**
-     *  A generic callback function.  Any class which needs to support
-     *  callback can implement callback and pass a reference to itself
-     *  to the function that does the callback.
-     *
-     *  @param  selector  An indicator of the function to be performed.
-     *                    Interpretation is determined by the implementing class.
-     *  @param  parm      Whatever data may be appropriate to the callback.
-     *
-     *  @return          As specified by the implementing class.
-     */
-    public int callback (int selector, Object parm);
-}

jhove/classes/edu/harvard/hul/ois/jhove/Checksum.java

@@ -1,93 +0,0 @@
-/**********************************************************************
- * Jhove - JSTOR/Harvard Object Validation Environment
- * Copyright 2003 by JSTOR and the President and Fellows of Harvard College
- **********************************************************************/
-
-package edu.harvard.hul.ois.jhove;
-
-
-/**
- *  This class encapsulates the result of calculations which provide a greater
- *  or lesser degree of confirmation of the integrity of a digital
- *  object's content, including checksums, CRC's, message digests,
- *  etc.
- *
- *  @see ChecksumType
- *  @see Checksummer
- */
-public class Checksum
-{
-    /******************************************************************
-     * PRIVATE INSTANCE FIELDS.
-     ******************************************************************/
-
-    private ChecksumType _type;
-    private String _value;
-
-    /******************************************************************
-     * CLASS CONSTRUCTOR.
-     ******************************************************************/
-
-    /**
-     *  Creates a Checksum with a given value and type
-     */
-    public Checksum (String value, ChecksumType type)
-    {
-	_value = value;
-	_type  = type;
-    }
-
-
-    /******************************************************************
-     * PUBLIC INSTANCE METHODS.
-     *
-     * Accessor methods.
-     ******************************************************************/
-
-    /** 
-     *  Returns this Checksum's type
-     */
-    public ChecksumType getType ()
-    {
-	return _type;
-    }
-
-    /** 
-     *  Returns this Checksum's value
-     */
-    public String getValue ()
-    {
-	return _value;
-    }
-
-    /******************************************************************
-     * Mutator methods.
-     ******************************************************************/
-
-    /**
-     *  Sets the type of this Checksum
-     */
-    public void setType (ChecksumType type)
-    {
-	_type = type;
-    }
-
-    /**
-     *  Sets the value of this Checksum
-     */
-    public void setValue (String value)
-    {
-	_value = value;
-    }
-
-    /******************************************************************
-     *  Put here as a convenience for checksum calculators
-     *****************************************************************/
-    /**
-     * Maps unsigned byte value (0 to 256) to signed byte value (-128 to 127).
-     */
-    public static byte unsignedByteToByte (int value)
-    {
-	return (byte) ((value < 127) ? value : value - 256);
-    }
-}

jhove/classes/edu/harvard/hul/ois/jhove/ChecksumInputStream.java

@@ -1,145 +0,0 @@
-/**********************************************************************
- * Jhove - JSTOR/Harvard Object Validation Environment
- * Copyright 2003-2006 by JSTOR and the President and Fellows of Harvard College
- **********************************************************************/
-
-package edu.harvard.hul.ois.jhove;
-
-import java.io.IOException;
-import java.io.*;
-
-/**
- * A ChecksumInputStream is a FilterInputStream with the added
- * functionality of calculating checksums as it goes.  
- * 
- * The idea of replacing this with java.util.zip.CheckedInputStream
- * looks very tempting, but we need the byte count, which
- * CheckedInputStream doesn't provide.
- * 
- * @author Gary McGath
- *
- */
-public class ChecksumInputStream extends FilterInputStream {
-
-    private InputStream subsumedStream;
-    private Checksummer _cksummer;
-    private long _nBytes;
-    
-    /**
-     *  Constructor.
-     * 
-     *  @param stream   Stream to be filtered
-     *  @param cksummer Object to calculate checksum on the bytes
-     *                  as they are read
-     */
-    public ChecksumInputStream(InputStream stream, Checksummer cksummer) {
-        super (stream);
-        subsumedStream = stream;
-        _cksummer = cksummer;
-        _nBytes = 0;
-    }
-
-    /**
-     *  Reads a byte from the subsumed stream, updating
-     *  the byte count and the checksums.
-     */
-    public int read() throws IOException {
-        int ch = subsumedStream.read ();
-        if (ch >= 0) {
-            _nBytes++;
-            if (_cksummer != null) {
-                _cksummer.update (ch);
-            }
-        }
-        return ch;
-    }
-
-    /**
-     * Reads some number of bytes from the input stream and
-     * stores them into the buffer array b. The number of
-     * bytes actually read is returned as an integer.
-     * 
-     * All bytes read are fed through the checksummer.
-     */
-    public int read(byte[] b) throws IOException 
-    {
-        int len = subsumedStream.read (b);
-        // Careful here -- don't want to add -1 bytes at EOF
-        if (len > 0) {
-	    if (_cksummer != null) {
-		_cksummer.update (b);
-	    }
-            _nBytes += len;
-        }
-        return len;
-    }
-    
-    /**
-     * Reads up to len bytes of data from the input stream 
-     * into an array of bytes. An attempt is made to read as 
-     * many as len bytes, but a smaller number may be read, 
-     * possibly zero. The number of bytes actually read is
-     * returned as an integer.
-     * 
-     * All bytes read are fed through the checksummer.
-     */
-    public int read(byte[] b, int off, int len) throws IOException 
-    {
-        len = subsumedStream.read (b, off, len);
-        // Careful here -- don't want to add -1 bytes at EOF
-        if (len > 0) {
-            if (_cksummer != null) {
-		_cksummer.update (b, off, len);
-            }
-            _nBytes += len;
-        }
-        return len;
-    }
-    
-    /**
-     *  Skips n bytes.
-     *  Reads them and feeds them through the checksummer.
-     */
-    public long skip (long n) throws IOException {
-        long nret = 0;
-        while (n > 0) {
-            // grab the data in reasonable buffer-sized chunks.
-            int bufsize = (int) (n > 8192 ? 8192 : n);
-            byte[] buf = new byte[bufsize];
-            int nread = read (buf);
-            if (nread <= 0) {
-                break;
-            }
-            nret += nread;
-            n -= nread;
-        }
-        return nret;
-    }
-    
-    /**
-     *  Closes the subsumed stream.
-     */
-    public void close () throws IOException
-    {
-        subsumedStream.close();
-    }
-    
-    /**
-     *  Returns the byte count to date on the stream.
-     *  This returns the number of bytes read.
-     *  Because of buffering, this is not a reliable
-     *  indicator of how many bytes have actually been processed.
-     */
-    public long getNBytes ()
-    {
-        return _nBytes;
-    }
-    
-    /**
-     *  Returns the Checksummer object.
-     */
-    public Checksummer getChecksummer ()
-    {
-        return _cksummer;
-    }
-}

jhove/classes/edu/harvard/hul/ois/jhove/ChecksumType.java

@@ -1,37 +0,0 @@
-/**********************************************************************
- * Jhove - JSTOR/Harvard Object Validation Environment
- * Copyright 2003 by JSTOR and the President and Fellows of Harvard College
- **********************************************************************/
-
-package edu.harvard.hul.ois.jhove;
-
-
-/**
- *  This class defines enumerated types for a Checksum on a content
- *  stream or file. 
- *  Applications will not create or modify ChecksumTypes, but will
- *  use one of the predefined ChecksumType instances 
- *  CRC32, MD5, or SHA1.
- *
- *  @see Checksum
- */
-public final class ChecksumType
-    extends EnumerationType
-{
-    /** 32-bit Cyclical Redundancy Checksum. */
-    public static final ChecksumType CRC32 = new ChecksumType ("CRC32");
-
-    /** 128-bit Message Digest 5. */
-    public static final ChecksumType MD5 = new ChecksumType ("MD5");
-
-    /** 160-bit Secure Hash Algorithm. */
-    public static final ChecksumType SHA1 = new ChecksumType ("SHA-1");
-
-    /** 
-     *  Applications will never create ChecksumTypes directly.
-     **/
-    private ChecksumType (String value)
-    {
-	super (value);
-    }
-}

jhove/classes/edu/harvard/hul/ois/jhove/Checksummer.java

@@ -1,193 +0,0 @@
-/**********************************************************************
- * Jhove - JSTOR/Harvard Object Validation Environment
- * Copyright 2003-2006 by JSTOR and the President and Fellows of Harvard College
- **********************************************************************/
-
-package edu.harvard.hul.ois.jhove;
-import java.security.*;
-import java.util.zip.*;
-
-/**
- *  The Checksummer class encapsulates the calculation of the 
- *  CRC32, MD5, and SHA-1 checksums. 
- */
-public class Checksummer implements java.util.zip.Checksum
-{
-    /******************************************************************
-     * PRIVATE INSTANCE FIELDS.
-     ******************************************************************/
-
-    /** Byte count. */
-    protected long _nByte;
-    /** CRC32 object. */
-    private CRC32 _crc32;
-    /** MD5 message digest. */
-    private MessageDigest _md5;
-    /** SHA-1 message digest. */
-    private MessageDigest _sha1;
-
-    /**
-     *  Creates a Checksummer, with instances of each of 
-     *  CRC32, MD5 MessageDigest, and SHA-1 MessageDigest.
-     *  If one or both of the MessageDigests aren't supported
-     *  on the current platform, they are left as null.
-     *
-     *  @see CRC32
-     *  @see MessageDigest
-     */
-    public Checksummer ()
-    {
-	reset ();
-    }
-    
-    /** Resets all checksums and the byte count to their
-     *  initial values.
-     */
-    public void reset ()
-    {
-        _nByte = 0;
-        _crc32 = new CRC32 ();
-        try {
-            _md5  = MessageDigest.getInstance ("MD5");
-            _sha1 = MessageDigest.getInstance ("SHA-1");
-        }
-        catch (NoSuchAlgorithmException e) {
-        }
-    }
-    
-    /** getValue is required by the Checksum interface, but
-     *  we can return only one of the three values.  We 
-     *  return the CRC32 value, since that's the one which
-     *  is guaranteed to be available.
-     */
-    public long getValue ()
-    {
-        return _crc32.getValue ();
-    }
-    
-    /**
-     *  Updates the checksum with the argument.
-     *  Called when a signed byte is available.
-     */
-    public void update (byte b)
-    {
-	_crc32.update (b);
-	if (_md5 != null) {
-	    _md5.update (b);
-	}
-	if (_sha1 != null) {
-       	    _sha1.update (b);
-	}
-    }
-
-    /**
-     *  Updates the checksum with the argument.
-     *  Called when an unsigned byte is available.
-     */
-    public void update (int b)
-    {
-	byte sb;
-	if (b > 127) {
-	    sb = (byte) (b - 256);
-	}
-	else {
-	    sb = (byte) b;
-	}
-	update (sb);
-    }
-    
-    /**
-     *  Updates the checksum with the argument.
-     *  Called when a byte array is available.
-     */
-    public void update (byte[] b)
-    {
-	_crc32.update (b);
-	if (_md5 != null) {
-	    _md5.update (b);
-	}
-	if (_sha1 != null) {
-	    _sha1.update (b);
-	}
-    }
-    
-    /**
-     *  Updates the checksum with the argument.
-     *  Called when a byte array is available.
-     */
-    public void update (byte[] b, int off, int len)
-    {
-	_crc32.update (b, off, len);
-	if (_md5 != null) {
-	    _md5.update (b, off, len);
-	}
-	if (_sha1 != null) {
-	    _sha1.update (b, off, len);
-	}
-    }
-
-    /**
-     *  Returns the value of the CRC32 as a hex string.
-     */
-    public String getCRC32 ()
-    {
-	return padLeadingZeroes 
-            (Long.toHexString (_crc32.getValue ()), 8);
-    }
-
-    /**
-     *  Returns the value of the MD5 digest as a hex string.
-     *  Returns null if the digest is not available.
-     */
-    public String getMD5 ()
-    {
-	String value = null;
-
-	if (_md5 != null) {
-	    StringBuffer buffer = new StringBuffer ();
-	    byte [] digest = _md5.digest ();
-	    for (int i=0; i<digest.length; i++) {
-		int un = (digest[i] >= 0) ? digest[i] : 256+digest[i];
-                buffer.append (padLeadingZeroes 
-                                (Integer.toHexString (un), 2));
-	    }
-	    value = buffer.toString ();
-	}
-
-	return value;
-    }
-
-    /**
-     *  Returns the value of the SHA-1 digest as a hex string.
-     *  Returns null if the digest is not available.
-     */
-    public String getSHA1 ()
-    {
-	String value = null;
-
-	if (_sha1 != null) {
-	    StringBuffer buffer = new StringBuffer ();
-	    byte [] digest = _sha1.digest ();
-	    for (int i=0; i<digest.length; i++) {
-		int un = (digest[i] >= 0) ? digest[i] : 256+digest[i];
-		buffer.append (padLeadingZeroes 
-                                (Integer.toHexString (un), 2));
-	    }
-	    value = buffer.toString ();
-	}
-
-	return value;
-    }
-    
-    /** Pad a hexadecimal (or other numeric) string out to
-     *  the specified length with leading zeroes. */
-    private String padLeadingZeroes (String str, int len)
-    {
-        // This is optimized for adding just one leading zero
-        // or none, which will be the usual case.
-        while (str.length () < len) {
-            str = "0" + str;
-        }
-        return str;
-    }
-}

jhove/classes/edu/harvard/hul/ois/jhove/ConfigHandler.java

@@ -1,395 +0,0 @@
-/**********************************************************************
- * Jhove - JSTOR/Harvard Object Validation Environment
- * Copyright 2003 by JSTOR and the President and Fellows of Harvard College
- **********************************************************************/
-
-package edu.harvard.hul.ois.jhove;
-
-import java.io.IOException;
-import java.io.InputStream;
-import java.net.URL;
-import java.util.*;
-import org.xml.sax.*;
-
-/**
- *  SAX Parser for the configuration file.
- */
-public class ConfigHandler
-    extends org.xml.sax.helpers.DefaultHandler
-{
-    /******************************************************************
-     * PRIVATE INSTANCE FIELDS.
-     ******************************************************************/
-
-    private String _class;
-    protected StringBuffer _content;
-    private Map<String, String> _extension;
-
-    /** The schema name */
-    private final static String configSchemaName =
-        "jhoveConfig.xsd";
-    
-    /** The list of handlers.  Each element in the List is an
-     *  array of two Strings representing the class and the initialization
-     *  string. */
-    private List<String[]> _handler;
-
-    /** The list of handler parameters.  Each element in the List is
-     *  a List of Strings (which may be empty but not null) representing 
-     *  parameters to be passed to the module.  List elements are in
-     *  one-to-one correspondence with _handler.
-     */
-    protected List<List<String>> _handlerParams;
-    private String _init;
-    private List<String> _param;
-    private String _tempDir;
-    private String _mixVsn;
-    private String _encoding;
-    private String _logLevel;
-    private int _bufferSize;
-    private String _jhoveHome;
-    private int _sigBytes;
-    
-    protected boolean _isHandler;
-    
-    /* _isModule is protected rather than private so that subclasses
-     * can add elements to the module element. */
-    protected boolean _isModule;
-    
-    private boolean _isTempDir;
-    private boolean _isMixVsn;
-    private boolean _isEncoding;
-    private boolean _isBufferSize;
-    private boolean _isJhoveHome;
-    private boolean _isLogLevel;
-    private boolean _isSigBytes;
-
-    /** The list of modules.  Each element in the List is an
-     *  array of two Strings representing the class and the initialization
-     *  string. */
-    protected List<ModuleInfo> _module;
-    
-    /** The list of module parameters.  Each element in the List is
-     *  a List of Strings (which may be empty but not null) representing 
-     *  parameters to be passed to the module.  List elements are in
-     *  one-to-one correspondence with _module.
-     */
-    protected List<List<String>> _modParams;
-
-    /******************************************************************
-     * CLASS CONSTRUCTOR.
-     ******************************************************************/
-
-    /** 
-     *  Creates a ConfigHandler.
-     */
-    public ConfigHandler ()
-    {
-        _module  = new ArrayList<ModuleInfo> ();
-        _handler = new ArrayList<String[]> ();
-        _modParams = new ArrayList<List<String>> ();
-        _handlerParams = new ArrayList<List<String>> ();
-
-        _isModule  = false;
-        _isHandler = false;
-        _isTempDir = false;
-        _isEncoding = false;
-        _isBufferSize = false;
-        _isJhoveHome = false;
-        _isLogLevel = false;
-
-        _bufferSize = -1;
-        _encoding   = null;
-        _extension  = new Hashtable<String, String> ();
-        _tempDir    = null;
-        _mixVsn     = null;
-        _sigBytes   = 1024;
-        _logLevel = null;
-    }
-
-    /******************************************************************
-     * PUBLIC INSTANCE METHODS.
-     *
-     * Accessor methods.
-     ******************************************************************/
-
-    /**
-     *  Returns the List of Modules specified by the config file.
-     *  Each element of the List is a String[2] whose elements are
-     *  the module class name and initialization value.
-     *
-     *  @see Module
-     */
-    public List<ModuleInfo> getModule ()
-    {
-        return _module;
-    }
-    
-    /**
-     *  Returns the List of module parameters specified by the config file.
-     *  Each element of the List is a List (possibly empty) of Strings
-     *  whose elements are parameters to pass to the module.  The
-     *  values returned by <code>getModuleParams()</code> are in 
-     *  one-to-one correspondence with those return by <code>getModule()</code>.
-     */
-    public List<List<String>> getModuleParams ()
-    {
-        return _modParams;
-    }
-
-    /**
-     *  Returns the List of handler parameters specified by the config file.
-     *  Each element of the List is a List (possibly empty) of Strings
-     *  whose elements are parameters to pass to the output handler.  The
-     *  values returned by <code>getHandlerParams()</code> are in 
-     *  one-to-one correspondence with those return by <code>getHandler()</code>.
-     */
-    public List<List<String>> getHandlerParams ()
-    {
-        return _handlerParams;
-    }
-
-    /**
-     *  Returns the List of OutputHandlers specified by the config file.
-     *
-     *  @see OutputHandler
-     */
-    public List<String[]> getHandler ()
-    {
-        return _handler;
-    }
-
-    /**
-     *  Returns the temporary directory path specified by the config file,
-     *  with final path separator.
-     */
-    public String getTempDir ()
-    {
-        return _tempDir;
-    }
-    
-    /** Returns the MIX schema version specified by the config file.
-     *  Acceptable values are "0.2" and "1.0" and "2.0".
-     */
-    public String getMixVsn () 
-    {
-        return _mixVsn;
-    }
-    
-    /** Returns the number of bytes to examine when looking for an
-     *  indefinitely positioned signature, or checking the first
-     *  sigBytes bytes of a file in lieu of a signature.
-     */
-    public int getSigBytes ()
-    {
-        return _sigBytes;
-    }
-
-    /**
-     *  Returns the character encoding specified by the config file.
-     */
-    public String getEncoding ()
-    {
-        return _encoding;
-    }
-
-    /**
-     *           Returns the buffer size specified in the config file.
-     *
-     * @return   the buffer size, or -1 if none specified
-     */
-    public int getBufferSize ()
-    {
-	return _bufferSize;
-    }
-
-    /**
-     * Return an associative map of configuration extensions.
-     */
-    public Map<String, String> getExtensions ()
-    {
-        return _extension;
-    }
-
-    /**
-     *  Returns the path to the application's home directory,
-     *  with final path separator.
-     */
-    public String getJhoveHome ()
-    {
-        return _jhoveHome;
-    }
-    
-    /**
-     *  Returns the name of the desired log level.  This should be the
-     *  name of one of the predefined values of java.util.logging.Level,
-     *  e.g., "WARNING", "INFO", "ALL".  The default level is SEVERE. 
-     */
-    public String getLogLevel ()
-    {
-        return _logLevel;
-    }
-
-
-    /******************************************************************
-     * SAX parser methods.
-     ******************************************************************/
-
-    /** 
-     *  SAX parser callback method.
-     */
-    public void startElement (String namespaceURI, String localName,
-			      String rawName, Attributes atts)
-	throws SAXException
-    {
-        _content = new StringBuffer ();
-        
-        if (rawName.equals ("module")) {
-            _isModule  = true;
-            _init = null;
-            _param = new ArrayList<String> (1);
-            _class = null;
-        }
-        else if (rawName.equals ("outputHandler")) {
-            _isHandler = true;
-            _init = null;
-            _param = new ArrayList<String> (1);
-            _class = null;
-        }
-        else if (rawName.equals ("tempDirectory")) {
-            _isTempDir = true;
-        }
-        else if (rawName.equals ("mixVersion")) {
-            _isMixVsn = true;
-        }
-        else if (rawName.equals ("defaultEncoding")) {
-            _isEncoding = true;
-        }
-        else if (rawName.equals ("bufferSize")) {
-            _isBufferSize = true;
-        }
-        else if (rawName.equals ("jhoveHome")) {
-            _isJhoveHome = true;
-        }
-        else if (rawName.equals ("logLevel")) {
-            _isLogLevel = true;
-        }
-        else if (rawName.equals ("sigBytes")) {
-            _isSigBytes = true;
-        }
-    }
-
-    /** 
-     *  SAX parser callback method.
-     */
-    public void characters (char [] ch, int start, int length)
-	throws SAXException
-    {
-	_content.append (ch, start, length);
-    }
-
-    /** 
-     *  SAX parser callback method.
-     */
-    public void endElement (String namespaceURI, String localName,
-			    String rawName)
-	throws SAXException
-    {
-        if (_isModule) {
-            if (rawName.equals ("class")) {
-                _class = _content.toString ();
-        }
-        else if (rawName.equals ("init")) {
-            _init = _content.toString ();
-        }
-        else if (rawName.equals ("param")) {
-            _param.add (_content.toString ());
-        }
-	    else if (rawName.equals ("module")) {
-            ModuleInfo modInfo = new ModuleInfo( _class, _init);
-            _module.add (modInfo);
-            _modParams.add (_param);
-            _isModule = false;
-	    }
-	}
-	else if (_isHandler) {
-	    if (rawName.equals ("class")) {
-		_class = _content.toString ();
-	    }
-	    else if (rawName.equals ("init")) {
-		_init = _content.toString ();
-	    }
-            else if (rawName.equals ("param")) {
-                _param.add (_content.toString ());
-            }
-	    else if (rawName.equals ("outputHandler")) {
-		String [] tuple = { _class, _init };
-		_handler.add (tuple);
-                _handlerParams.add (_param);
-		_isHandler = false;
-	    }
-	}
-        else if (_isTempDir) {
-            _tempDir = _content.toString ().trim ();
-            _isTempDir = false;
-        }
-        else if (_isMixVsn) {
-            _mixVsn =  _content.toString ().trim ();
-            _isMixVsn = false;
-        }
-        else if (_isSigBytes) {
-            try {
-                _sigBytes = Integer.parseInt (_content.toString ().trim ());
-            }
-            catch (NumberFormatException e) {}
-            _isSigBytes = false;
-        }
-        else if (_isEncoding) {
-            _encoding = _content.toString ().trim ();
-            _isEncoding = false;
-        }
-        else if (_isJhoveHome) {
-            _jhoveHome = _content.toString ().trim ();
-            _isJhoveHome = false;
-        }
-        else if (_isLogLevel) {
-            _logLevel = _content.toString ().trim ();
-            _isLogLevel = false;
-        }
-	else if (_isBufferSize) {
-	    try {
-		_bufferSize = Integer.parseInt (_content.toString ().trim ());
-	    }
-	    catch (NumberFormatException e) {
-		/* Just ignore a malformed number */
-	    }
-	    _isBufferSize = false;
-	}
-	else if (!rawName.equals ("jhoveConfig")) {
-	    _extension.put (rawName, _content.toString ().trim ());
-	}
-    }
-    
-    /** EntityResolver designed to locate the config schema. It tries to find it
-     *  as a local resource.
-     *  
-     *  It appears that not all SAX implementations will actually call this
-     *  function for schema resolution, so this isn't a guarantee that the
-     *  schema in the config file won't be called directly. But hopefully
-     *  it will cut down on the burden on the server with the official
-     *  schema copy.
-     */
-    public InputSource resolveEntity (String publicId, String systemId)
-                    throws SAXException, IOException {
-        if (systemId.endsWith (configSchemaName)) {
-            try {
-                URL resURL = this.getClass().getResource("jhoveConfig.xsd");
-                InputStream strm = resURL.openStream ();
-                return new InputSource (strm);
-            }
-            catch (Exception e) {}
-        }
-        // If we couldn't get the local resource, use default location methods
-        return super.resolveEntity (publicId, systemId);
-    }
-}

jhove/classes/edu/harvard/hul/ois/jhove/ConfigWriter.java

@@ -1,212 +0,0 @@
-/**********************************************************************
- * Jhove - JSTOR/Harvard Object Validation Environment
- * Copyright 2003 by JSTOR and the President and Fellows of Harvard College
- *
- **********************************************************************/
-
-package edu.harvard.hul.ois.jhove;
-
-import java.io.*;
-import java.util.*;
-import javax.swing.*;
-
-import edu.harvard.hul.ois.jhove.viewer.ConfigWindow;
-
-/**
- * 
- * Class to write out configuration information to the configuration file.
- * To minimize the chance of getting into a bad state, it writes to a
- * temporary file, then replaces the old config file with that file,
- * rather than directly overwriting the existing file.
- * 
- * @author Gary McGath
- *
- */
-public class ConfigWriter {
-
-    
-    private PrintWriter _confOut;
-    private File _tempFile;
-    private File _confFile;
-    ConfigWindow _parent;
-
-    /**
-     *  Constructor.
-     *  Creates a temporary file for writing and creates an OutputStreamWriter
-     *  to write to it.  If there is already a file located by
-     *  <code>file</code>, it will not be replaced or overwritten
-     *  until <code>writeFile</code> has successfully written out
-     *  the temporary file.
-     * 
-     *  @param  file    Location of the configuration file
-     * 
-     *  @param  parent  The ConfigWindow which invoked this instance.
-     *                  May be null if invoked to write a default config file.
-     */
-    public ConfigWriter (File file, ConfigWindow parent) throws IOException
-    {
-        _confFile = file;
-        _parent = parent;
-        // Set up a temporary file to write to. 
-        String path = file.getParent();
-        file.getParentFile().mkdirs();        // Make sure the directory exists
-        _tempFile = File.createTempFile ("jho", ".conf", new File (path));
-        //_tempFile.createNewFile();   
-        FileOutputStream ostrm = new FileOutputStream (_tempFile);
-        OutputStreamWriter osw = new OutputStreamWriter (ostrm, "UTF-8");
-        _confOut = new PrintWriter (osw);
-    }
-    
-
-    /**
-     *   Writes out the content of the file to the temporary file,
-     *   then deletes the existing configuration file (as specified 
-     *   by the constructor parameter) and renames the temporary file 
-     *   to the configuration file.
-     * 
-     *   If the temporary file can't be written, or the configuration
-     *   file can't be replaced, a warning dialog is put up and the
-     *   configuration file remains unchanged.
-     */
-    public void writeFile (List<ModuleInfo> modules,
-            List<String[]> handlers,
-            File homeDir,
-            File tempDir,
-            String encoding,
-            int bufferSize) throws IOException
-    {
-        writeHead ();
-        
-        // Write the home and temp directories.  Home must always be valid.
-        _confOut.println (" <jhoveHome>" + 
-                    encodeContent (homeDir.getPath ()) + 
-                    "</jhoveHome>");
-
-        // Write out the encoding
-        if (encoding != null && encoding.length() > 0) {
-            _confOut.println (" <defaultEncoding>" +
-                    encodeContent (encoding) + "</defaultEncoding>");
-        }
-        
-
-        if (tempDir != null) {
-            _confOut.println (" <tempDirectory>" + 
-                    encodeContent (tempDir.getPath ()) + 
-                    "</tempDirectory>");
-        }
-        
-        // Write the buffer size if not default
-        if (bufferSize > 0) {
-            _confOut.println (" <bufferSize>" + bufferSize + 
-                    "</bufferSize>");
-        }
-        
-        // Write out the modules
-        ListIterator<ModuleInfo> iter = modules.listIterator ();
-        while (iter.hasNext ()) {
-            ModuleInfo minfo = iter.next ();
-            // The class must be non-null, but init may be null.
-            // If the class is empty, it's a user error (probably
-            // clicked "Add" and then lost track of it).  Don't
-            // write it out.
-            if (!"".equals (minfo.clas)) {
-                _confOut.println (" <module>");
-                _confOut.println ("   <class>" + encodeContent (minfo.clas) +
-                         "</class>");
-                if (minfo.init != null && minfo.init.length () > 0) {
-                    _confOut.println ("   <init>" + encodeContent (minfo.init) +
-                         "</init>");
-                }
-                /** tuple[2] and beyond are parameters */
-                if (minfo.params != null) {
-                    for (int i = 0; i < minfo.params.length; i++) {
-                        _confOut.println ("   <param>" + encodeContent(minfo.params[i]) +
-                             "</param>");
-                    }
-                }
-                _confOut.println (" </module>");
-            }
-        }
-        
-        // Write out the handlers
-        ListIterator<String[]> hiter = handlers.listIterator ();
-        while (hiter.hasNext ()) {
-            String handler = hiter.next ()[0];
-            if (handler.length() > 0) {          // Don't write out blank handler names
-                _confOut.println (" <outputHandler>");
-                _confOut.println ("   <class>" + encodeContent (handler) +
-                         "</class>");
-                _confOut.println (" </outputHandler>");
-            }
-        }
-
-        writeTail ();
-        _confOut.close ();
-        
-        // Replace the old file with the new.
-        if (_confFile.exists () && !_confFile.delete ()) {
-            if (_parent != null) {
-                JOptionPane.showMessageDialog(_parent, 
-                        "Can't replace old config file", 
-                        "Error", 
-                        JOptionPane.ERROR_MESSAGE);
-            }
-            _tempFile.delete ();
-        }
-        else {
-            _tempFile.renameTo (_confFile);
-        }
-    }
-    
-    /* Write the fixed lines which begin the config file */
-    private void writeHead () throws IOException
-    {
-        _confOut.println("<?xml version=\"1.0\" encoding=\"UTF-8\"?>");
-        _confOut.println("<jhoveConfig version=\"1.0\"");
-        _confOut.println("             xmlns:xsi=\"http://www.w3.org/2001/XMLSchema-instance\"");
-        _confOut.println("             xmlns=\"http://hul.harvard.edu/ois/xml/ns/jhove/jhoveConfig\"");
-
-        // Note that the open quote of this line isn't closed till the next line; that's intentional.
-        _confOut.println("xsi:schemaLocation=\"http://hul.harvard.edu/ois/xml/ns/jhove/jhoveConfig");
-
-        _confOut.println("             http://hul.harvard.edu/ois/xml/xsd/jhove/jhoveConfig.xsd\">");
-    }
-    
-    /* Write out the fixed end of the config file */
-    private void writeTail () throws IOException
-    {
-        _confOut.println("</jhoveConfig>");
-    }
-    
-    
-        /**
-     *   Encodes a content String in XML-clean form, converting characters
-     *   to entities as necessary.  The null string will be
-     *   converted to an empty string.
-     */
-    private static String encodeContent (String content)
-    {
-        if (content == null) {
-            content = "";
-        }
-        StringBuffer buffer = new StringBuffer (content);
-
-        int n = 0;
-        while ((n = buffer.indexOf ("&", n)) > -1) {
-            buffer.insert (n+1, "amp;");
-            n +=5;
-        }
-        n = 0;
-        while ((n = buffer.indexOf ("<", n)) > -1) {
-            buffer.replace (n, n+1, "&lt;");
-            n += 4;
-        }
-        n = 0;
-        while ((n = buffer.indexOf (">", n)) > -1) {
-            buffer.replace (n, n+1, "&gt;");
-            n += 4;
-        }
-
-        return buffer.toString ();
-    }
-}

jhove/classes/edu/harvard/hul/ois/jhove/CountedInputStream.java

@@ -1,114 +0,0 @@
-/**********************************************************************
- * Jhove - JSTOR/Harvard Object Validation Environment
- * Copyright 2004 by JSTOR and the President and Fellows of Harvard College
- **********************************************************************/
-
-package edu.harvard.hul.ois.jhove;
-
-import java.io.*;
-
-/**
- * A FilterInputStream which passes only a specified
- * number of bytes, then returns an EOF condition.
- *
- * @author Gary McGath
- *
- */
-public class CountedInputStream extends FilterInputStream {
-
-    private int bytesLeft;
-    
-    /**
-     * @param instrm       The InputStream being counted
-     * @param count        The number of bytes to be allowed
-     */
-    public CountedInputStream(InputStream instrm, int count) {
-        super(instrm);
-        bytesLeft = count;
-    }
-
-
-    /** Reads a single byte from the stream and decrements
-     *  the count of remaining bytes.  If the count
-     *  is exhausted, returns -1 to signify end of file. */
-    public int read() throws IOException {
-        if (bytesLeft <= 0) {
-            return -1;
-        }
-        else {
-            int ch = super.read ();
-            if (ch != -1) {
-                --bytesLeft;
-            }
-            return ch;
-        }
-    }
-
-
-    /**
-     * Reads some number of bytes from the input stream and
-     * stores them into the buffer array b. The number of
-     * bytes actually read is returned as an integer.
-     * 
-     * The number of bytes read will not exceed the number
-     * of bytes remaining in the count.  The count is
-     * decremented by the number of bytes actually read.
-     */
-    public int read(byte[] b) throws IOException 
-    {
-        int len = b.length;
-        int bytesRead;
-        if (len <= bytesLeft) {
-            // Limit doesn't affect us, do normal read
-            bytesRead = super.read (b);
-        }
-        else {
-            // Limit the read to bytesLeft
-            bytesRead = super.read (b, 0, bytesLeft);
-        }
-        bytesLeft -= bytesRead;
-        return bytesRead;
-    }
-
-
-    /**
-     * Reads up to len bytes of data from the input stream 
-     * into an array of bytes. An attempt is made to read as 
-     * many as len bytes, but a smaller number may be read, 
-     * possibly zero. The number of bytes actually read is
-     * returned as an integer.
-     * 
-     * The number of bytes read will not exceed the number
-     * of bytes remaining in the count.  The count is
-     * decremented by the number of bytes actually read.
-     */
-    public int read(byte[] b, int off, int len) throws IOException 
-    {
-        int bytesRead;
-        if (len <= bytesLeft) {
-            // Limit doesn't affect us, do normal read
-            bytesRead = super.read (b, off, len);
-        }
-        else {
-            bytesRead = super.read (b, off, bytesLeft);
-        }
-        bytesLeft -= bytesRead;
-        return bytesRead;
-    }
-
-    /**
-     *  Skips n bytes.
-     *  Decrements the count by the number of bytes
-     *  actually skipped.
-     */
-    public long skip (long n) throws IOException {
-        long bytesRead = super.skip (n);
-        if (bytesLeft < bytesRead) {
-            bytesLeft = 0;
-        }
-        else {
-            bytesLeft -= bytesRead;
-        }
-        return bytesRead;
-    }
-}

jhove/classes/edu/harvard/hul/ois/jhove/DefaultConfigurationBuilder.java

@@ -1,128 +0,0 @@
-package edu.harvard.hul.ois.jhove;
-
-import java.io.File;
-import java.io.IOException;
-import java.lang.reflect.Field;
-import java.util.ArrayList;
-import java.util.List;
-
-import edu.harvard.hul.ois.jhove.module.*;
-
-/** This class creates a default configuration if no valid configuration file
- *  is found. */
-public class DefaultConfigurationBuilder {
-
-    private final static String FILE_SEP = System.getProperty ("file.separator");
-    private final static String HOME_DIR = System.getProperty ("user.home");
-    private final static String JHOVE_DIR = HOME_DIR + FILE_SEP + "jhove";
-    private final static String TEMP_DIR = System.getProperty("java.io.tmpdir");
-    private final static String DEFAULT_ENCODING = "utf-8";
-    private final static int DEFAULT_BUFFER_SIZE = 131072;
-    
-    private File configFile;
-    
-    
-    /** Constructor. A location for the file may be specified or
-     *  left null, */
-    public DefaultConfigurationBuilder (File location) {
-        if (location != null) {
-            configFile = location;
-        }
-        else {
-            configFile = new File (JHOVE_DIR +
-                      FILE_SEP + "conf" +
-                      FILE_SEP + "jhove.conf");
-        }
-    }
-    
-    
-    public void writeDefaultConfigFile () throws IOException {
-//        if (TEMP_DEBUG) {
-//            String configFileName = "null";
-//            if (configFile != null) 
-//                configFileName = configFile.getAbsolutePath();
-//            System.out.println ("writeDefaultConfigFile: path is " + configFileName);
-//        }
-        ConfigWriter cw = new ConfigWriter (configFile, null);
-        List<ModuleInfo> modules = getModules();
-        // TextHandler, XmlHandler, and AuditHandler are loaded by
-        // default, so there are no handlers to put in the config file.
-        List<String[]> handlers = new ArrayList<String[]> ();
-        File homeDir = new File (JHOVE_DIR);
-        File tempDir = new File (TEMP_DIR);
-        try {
-            cw.writeFile(modules, handlers, homeDir, tempDir, 
-                DEFAULT_ENCODING, DEFAULT_BUFFER_SIZE);
-        }
-        catch (IOException e) {
-//            if (TEMP_DEBUG)
-//                e.printStackTrace();
-            throw e;
-        }
-    }
-
-//    public void writeDefaultConfigFile () throws IOException {
-//        ConfigWriter cw = new ConfigWriter (configFile, null);
-//        List<ConfigWriter.ModuleInfo> modules = getModules();
-//        // TextHandler, XmlHandler, and AuditHandler are loaded by
-//        // default, so there are no handlers to put in the config file.
-//        List<String> handlers = new ArrayList<String> ();
-//        File homeDir = new File (JHOVE_DIR);
-//        File tempDir = new File (TEMP_DIR);
-//        cw.writeFile(modules, handlers, homeDir, tempDir, 
-//                DEFAULT_ENCODING, DEFAULT_BUFFER_SIZE);
-//    }
-
-    public File getConfigFile () {
-        return configFile;
-    }
-    
-    
-    protected List<ModuleInfo> getModules () {
-        int nModules = builtInModules.length;
-        ArrayList<ModuleInfo> mods = new ArrayList<ModuleInfo> (nModules);
-        try {
-            for (int i = 0; i < nModules; i++) {
-                Class<?> cls = builtInModules[i];
-                ModuleInfo minfo = new ModuleInfo(cls.getName());
-                minfo.init = null;       // Never used at present
-                minfo.params = getDefaultConfigParameters (cls);
-                mods.add(minfo);
-            }
-        }
-        catch (Exception e) {}
-        return mods;
-    }
-    
-    
-    /** We can't have a static method in an Interface and override it, so we
-     *  have to get a bit ugly to fake static inheritance. The advantage of
-     *  this is that only the Modules with non-null default config file
-     *  parameters have to implement the defaultConfigParams static field. */
-    protected String[] getDefaultConfigParameters (Class<?> c) {
-        try {
-            Field dcpField = c.getField("defaultConfigParams");
-            return (String[]) dcpField.get(null);
-        }
-        catch (Exception e) {
-            return new String [] {};
-        }
-    }
-    
-    /** The array of build-in modules. If a module is added to or removed from
-     *  the build, this array must be changed. The Bytestream module is
-     *  loaded by default and so is not listed here. */
-    private Class<?>[] builtInModules = {
-        AiffModule.class,
-        AsciiModule.class,
-        GifModule.class,
-        HtmlModule.class,
-        Jpeg2000Module.class,
-        JpegModule.class,
-        PdfModule.class,
-        TiffModule.class,
-        Utf8Module.class,
-        WaveModule.class,
-        XmlModule.class
-    };
-}

jhove/classes/edu/harvard/hul/ois/jhove/Document.java

@@ -1,194 +0,0 @@
-/**********************************************************************
- * Jhove - JSTOR/Harvard Object Validation Environment
- * Copyright 2003 by JSTOR and the President and Fellows of Harvard College
- **********************************************************************/
-
-package edu.harvard.hul.ois.jhove;
-
-import java.util.*;
-
-/** 
- *  This class encapsulates information about format specification documents.
- *
- *  @see  DocumentType
- */
-public class Document
-{
-    private List _author;
-    private String _date;
-    private String _edition;
-    private String _enum;
-    private List _identifier;
-    private String _note;
-    private String _pages;
-    private List _publisher;
-    private String _title;
-    private DocumentType _type;
-
-    /**
-     *  Creates a Document with a given title and one of the predefined
-     *  DocumentTypes.
-     */
-    public Document (String title, DocumentType type)
-    {
-    _title = title;
-    _type  = type;
-
-    _author     = new ArrayList ();
-    _identifier = new ArrayList ();
-    _publisher  = new ArrayList ();
-    }
-
-    /**
-     *  Returns a List of Agents, each representing an author of this
-     *  Document.
-     *  Returns an empty list if no authors have been listed.
-     *
-     *  @see Agent
-     */
-    public List getAuthor ()
-    {
-    return _author;
-    }
-    
-    /**
-     *  Returns the date of this Document
-     */
-    public String getDate ()
-    {
-    return _date;
-    }
-
-    /**
-     *   Returns informaton on the edition of this Document
-     */
-    public String getEdition ()
-    {
-    return _edition;
-    }
-
-    /**
-     *  Returns the enumeration (e.g., serial volume and number)
-     *  of this Document
-     */
-    public String getEnumeration ()
-    {
-    return _enum;
-    }
-
-    /**
-     *  Returns the list of formal Identifiers for this Document.
-     *  If no Identifiers are given, returns an empty list.
-     */
-    public List getIdentifier ()
-    {
-    return _identifier;
-    }
-
-    /**
-     *  Returns the note associated with this Document
-     */
-    public String getNote ()
-    {
-    return _note;
-    }
-
-    /**
-     *  Returns pagination information for this Document
-     */
-    public String getPages ()
-    {
-    return _pages;
-    }
-
-    /**
-     *  Returns a List of Agents, each representing a publisher of this
-     *  Document.  If no publishers are listed, returns an empty list.
-     */
-    public List getPublisher ()
-    {
-    return _publisher;
-    }
-
-    /**
-     *  Returns the title of this Document 
-     */
-    public String getTitle ()
-    {
-    return _title;
-    }
-
-    /**
-     *  Returns one of the predefined DocumentTypes as the type of
-     *  this Document
-     */
-    public DocumentType getType ()
-    {
-    return _type;
-    }
-
-    /**
-     *  Adds an author to the list of authors
-     */
-    public void setAuthor (Agent author)
-    {
-    _author.add (author);
-    }
-
-    /**
-     *  Sets the date of this Document
-     */
-    public void setDate (String date)
-    {
-    _date = date;
-    }
-
-    /**
-     *  Sets edition information for this Document
-     */
-    public void setEdition (String edition)
-    {
-    _edition = edition;
-    }
-
-    /**
-     *  Sets enumeration information (e.g., serial volume and number)
-     *  for this Document
-     */
-    public void setEnumeration (String enm)
-    {
-    _enum = enm;
-    }
-
-    /**
-     *  Adds an Identifier to the list of identifiers
-     */
-    public void setIdentifier (Identifier identifier)
-    {
-    _identifier.add (identifier);
-    }
-
-    /**
-     *  Sets a note giving additional information about this Document
-     */
-    public void setNote (String note)
-    {
-    _note = note;
-    }
-
-    /**
-     *  Sets pagination information for this Document
-     */
-    public void setPages (String pages)
-    {
-    _pages = pages;
-    }
-
-    /**
-     *  Adds a publisher to the list of publishers
-     */
-    public void setPublisher (Agent publisher)
-    {
-    _publisher.add (publisher);
-    }
-}

jhove/classes/edu/harvard/hul/ois/jhove/DocumentType.java

@@ -1,61 +0,0 @@
-/**********************************************************************
- * Jhove - JSTOR/Harvard Object Validation Environment
- * Copyright 2003 by JSTOR and the President and Fellows of Harvard College
- **********************************************************************/
-
-package edu.harvard.hul.ois.jhove;
-
-
-/**
- *  This class defines enumerated types for a Document.
- *  Applications will not create or modify DocumentTypes, but will
- *  use one of the predefined DocumentType instances 
- *  ARTICLE, BOOK, REPORT, RFC, STANDARD, WEB, or OTHER.
- *
- *  @see Document
- *  
- */
-public final class DocumentType
-    extends EnumerationType
-{
-    /**
-     *  Document type for a printed article.
-     */
-    public static final DocumentType ARTICLE = new DocumentType ("Article");
-    /**
-     *  Document type for an book.
-     */
-    public static final DocumentType BOOK = new DocumentType ("Book");
-    /**
-     *  Document type for a report.
-     */
-    public static final DocumentType REPORT = new DocumentType ("Report");
-    /**
-     *  Document type for an IETF Request for Comment.
-     */
-    public static final DocumentType RFC = new DocumentType ("RFC");
-    /**
-     *  Document type for a standards body publication.
-     */
-    public static final DocumentType STANDARD = new DocumentType ("Standard");
-    /**
-     *  Document type for a Web page.
-     */
-    public static final DocumentType WEB = new DocumentType ("Web");
-    /**
-     *  Document type that doesn't fit the other categories.
-     */
-    public static final DocumentType OTHER = new DocumentType ("Other");
-
-    /******************************************************************
-     * CLASS CONSTRUCTOR.
-     ******************************************************************/
-
-    /** 
-     *  Applications will never create DocumentTypes directly.
-     **/
-    private DocumentType (String value)
-    {
-	super (value);
-    }
-}

jhove/classes/edu/harvard/hul/ois/jhove/Dump.java

@@ -1,134 +0,0 @@
-/**********************************************************************
- * JHOVE - JSTOR/Harvard Object Validation Environment
- * Copyright 2004 by the President and Fellows of Harvard College
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU Lesser General Public License as published by
- * the Free Software Foundation; either version 2 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
- * Lesser General Public License for more details.
- * 
- * You should have received a copy of the GNU Lesser General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307
- * USA
- **********************************************************************/
-
-package edu.harvard.hul.ois.jhove;
-
-import java.io.*;
-
-/**
- * Common methods for dump utilities.
- */
-public class Dump
-{
-    /******************************************************************
-     * CLASS CONSTRUCTOR.
-     ******************************************************************/
-    public Dump ()
-    {
-    }
-
-    /******************************************************************
-     * PUBLIC CLASS METHODS.
-     ******************************************************************/
-
-    /**
-     * Return leading characters to pad out the byte offset to field width.
-     * @param os Byte offset
-     * @param width Field width
-     * @return String of leading zeros 
-     */
-    protected static String leading (int os, int width)
-    {
-	return leading (os, width, '0');
-    }
-
-    /**
-     * Return leading characters to pad out the byte offset to field width.
-     * @param os Byte offset
-     * @param width Field width
-     * @return String of leading zeros 
-     */
-    protected static String leading (long os, int width)
-    {
-	return leading (os, width, '0');
-    }
-
-    /**
-     * Return leading characters to pad out the byte offset to field width.
-     * @param os    Byte offset
-     * @param width Field width
-     * @param pad   Padding character
-     * @return String of leading characters 
-     */
-    protected static String leading (int os, int width, char pad)
-    {
-	return leading ((long) os, width, pad);
-    }
-
-    /**
-     * Return leading characters to pad out the byte offset to field width.
-     * @param os    Byte offset
-     * @param width Field width
-     * @param pad   Padding character
-     * @return String of leading characters 
-     */
-    protected static String leading (long os, int width, char pad)
-    {
-	String ss = Long.toString (os);
-	StringBuffer buffer = new StringBuffer ();
-	for (int j=0; j<width-ss.length (); j++) {
-	    buffer.append (pad);
-	}
-	return buffer.toString ();
-    }
-
-    /**
-     * Return leading characters to pad out the string to field width.
-     * @param s     String
-     * @param width Field width
-     * @return String of leading characters 
-     */
-    protected static String leading (String s, int width)
-    {
-	return leading (s, width, '0');
-    }
-
-    /**
-     * Return leading characters to pad out the string to field width.
-     * @param s     String
-     * @param width Field width
-     * @param pad   Padding character
-     * @return String of leading characters 
-     */
-    protected static String leading (String s, int width, char pad)
-    {
-	StringBuffer buffer = new StringBuffer ();
-	for (int j=0; j<width-s.length (); j++) {
-	    buffer.append (pad);
-	}
-	return buffer.toString ();
-    }
-
-    /**
-     * Read and display a sequence of characters.
-     * @param stream Data input stream
-     * @param length Number of characters
-     * @return Character string
-     */
-    protected static String readChars (DataInputStream stream, int length)
-	throws IOException
-    {
-	byte [] buffer = new byte [length];
-	for (int i=0; i<length; i++) {
-	    buffer[i] = stream.readByte ();
-	}
-	return new String (buffer);
-    }
-}

jhove/classes/edu/harvard/hul/ois/jhove/EnumerationType.java

@@ -1,70 +0,0 @@
-/**********************************************************************
- * Jhove - JSTOR/Harvard Object Validation Environment
- * Copyright 2003 by JSTOR and the President and Fellows of Harvard College
- **********************************************************************/
-
-package edu.harvard.hul.ois.jhove;
-
-/**
- * Enumerated data type.  To create an emumeration, define a subclass
- * of EnumerationType with a private constructor, and define as
- * many <code>public final static</code> instances of the subclass,
- * within the subclass definition, as there are enumeration cases.
- * No other instances of an EnumerationType should ever be created,
- * and the only operations which should ever be performed on an
- * EnumerationType are assignment and equality testing.
- * 
- */
-public abstract class EnumerationType
-{
-    /******************************************************************
-     * PRIVATE INSTANCE FIELDS.
-     ******************************************************************/
-
-    /** Enumeration value. */
-    private String _value;
-
-    /******************************************************************
-     * CLASS CONSTRUCTOR.
-     ******************************************************************/
-
-    /**
-     * Instantiate an <tt>EnumerationType</tt> object.
-     * @param value Enumeration value
-     */
-    protected EnumerationType (String value)
-    {
-    _value = value;
-    }
-
-    /**
-     *  Private no-argument constructor to close off the default
-     *  constructor.
-     */
-    private EnumerationType ()
-    {
-    }
-     
-    /******************************************************************
-     * PUBLIC INSTANCE METHODS.
-     ******************************************************************/
-
-    /**
-     * Type equality test.
-     * @param enm Enumerated type
-     * @return True, if equal
-     */
-    public boolean equals (EnumerationType enm)
-    {
-    return this == enm;
-    }
-
-    /**
-     * Return enumeration value.
-     * @return Value
-     */
-    public String toString ()
-    {
-    return _value;
-    }
-}

jhove/classes/edu/harvard/hul/ois/jhove/ErrorMessage.java

@@ -1,58 +0,0 @@
-/**********************************************************************
- * Jhove - JSTOR/Harvard Object Validation Environment
- * Copyright 2003 by JSTOR and the President and Fellows of Harvard College
- **********************************************************************/
-
-package edu.harvard.hul.ois.jhove;
-
-/**
- *  This class encapsulates an error message from a Module, representing
- *  a problem in the content being analyzed. 
- */
-public class ErrorMessage
-    extends Message
-{
-    /******************************************************************
-     * CLASS CONSTRUCTOR.
-     ******************************************************************/
-
-    /** 
-     *  Create an ErrorMessage.
-     *  @param  message   Human-readable string describing the problem.
-     */
-    public ErrorMessage (String message)
-    {
-	super (message);
-    }
-
-    /** 
-     *  Create an ErrorMessage.
-     *  @param  message   Human-readable string describing the problem.
-     *  @param  offset    The offset in the file at which the problem
-     *                    was detected.
-     */
-    public ErrorMessage (String message, long offset)
-    {
-	super (message, offset);
-    }
-    /** 
-     *  Create an ErrorMessage.
-     *  @param  message   Human-readable string describing the problem.
-     */
-    public ErrorMessage (String message, String subMessage)
-    {
-        super (message, subMessage);
-    }
-
-    /** 
-     *  Create an ErrorMessage.
-     *  @param  message   Human-readable string describing the problem.
-     *  @param  subMessage Human-readable additional information.
-     *  @param  offset    The offset in the file at which the problem
-     *                    was detected.
-     */
-    public ErrorMessage (String message, String subMessage, long offset)
-    {
-        super (message, subMessage, offset);
-    }
-}

jhove/classes/edu/harvard/hul/ois/jhove/ExternalSignature.java

@@ -1,60 +0,0 @@
-/**********************************************************************
- * Jhove - JSTOR/Harvard Object Validation Environment
- * Copyright 2003-4 by JSTOR and the President and Fellows of Harvard College
- **********************************************************************/
-
-package edu.harvard.hul.ois.jhove;
-
-/**
- *  This class encapsulates information about external format signatures.
- *   The value of a Signature may be either a String or a byte array
- *   (stored as an int array to avoid signed byte problems).
- */
-public class ExternalSignature
-    extends Signature
-{
-    /**
-     *  Creates an ExternalSignature given a string value, a type,
-     *  and a use requirement.  
-     */
-    public ExternalSignature (String value, SignatureType type,
-			      SignatureUseType use)
-    {
-	super (value, type, use);
-    }
-
-    /**
-     *  Creates an ExternalSignature given a byte array, a type,
-     *  and a use requirement.
-     */
-    public ExternalSignature (int[] value, SignatureType type,
-			      SignatureUseType use)
-    {
-	super (value, type, use);
-    }
-
-    /**
-     *  Creates an ExternalSignature given a string value, a type,
-     *  a use requirement, and a note.  
-     */
-    public ExternalSignature (String value, SignatureType type,
-                  SignatureUseType use,
-                  String note)
-    {
-        super (value, type, use, note);
-    }
-
-
-    /**
-     *  Creates an ExternalSignature given a byte array, a type,
-     *  a use requirement, and a note.
-     */
-    public ExternalSignature (int[] value, SignatureType type,
-                  SignatureUseType use,
-                  String note)
-    {
-        super (value, type, use, note);
-    }
-
-
-}

jhove/classes/edu/harvard/hul/ois/jhove/HandlerBase.java

@@ -1,812 +0,0 @@
-/**********************************************************************
- * Jhove - JSTOR/Harvard Object Validation Environment
- * Copyright 2003 by JSTOR and the President and Fellows of Harvard College
- **********************************************************************/
-
-package edu.harvard.hul.ois.jhove;
-
-import java.io.*;
-import java.text.*;
-import java.util.*;
-import java.util.logging.*;
-
-/**
- *  Abstract base class for Jhove output handlers.
- *  Output handlers should normally subclass HandlerBase.
- */
-public abstract class HandlerBase
-    implements OutputHandler
-{
-    /******************************************************************
-     * PUBLIC CLASS FIELDS.
-     ******************************************************************/
-
-    /**
-     *  A DateFormat for representing a Date in yyyy-MM-dd 
-     *  (e.g., 2003-07-31) format.
-     */
-    public static SynchronizedDateFormat date =
-              new SynchronizedDateFormat ("yyyy-MM-dd");
-    
-    /**
-     *  A DateFormat for representing a Date in yyyy-MM-dd HH:mm:ss z
-     *  (e.g., 2003-07-31 15:31:12 EDT) format.
-     */
-    public static SynchronizedDateFormat dateTime =
-              new SynchronizedDateFormat ("yyyy-MM-dd HH:mm:ss z");
-
-    /**
-     *  A DateFormat for representing a Date in ISO 8601
-     *  (e.g., 2003-07-31T15:31:12-0400) format.
-     *  We subclass SimpleDateFormat to make it thread-safe.
-     */
-    public static SynchronizedDateFormat iso8601 =
-              new SynchronizedDateFormat ("yyyy-MM-dd'T'HH:mm:ssZ");
-
-    /******************************************************************
-     * PRIVATE INSTANCE FIELDS.
-     ******************************************************************/
-
-    /**  The application object */
-    protected App _app;
-    /**  The Jhove engine */
-    protected JhoveBase _base;
-    /**  Handler last modification date */
-    protected Date _date;
-    /**  Character encoding for writer */
-    protected String _encoding;
-    /** Initialization value. */
-    protected String _init;
-    /** List of default parameters. */
-    protected List<String> _defaultParams;
-    /**  JHOVE engine. */
-    protected JhoveBase _je;
-    /**  Indentation level */
-    protected int _level;
-    /**  Handler name */
-    protected String _name;
-    /**  Handler note */
-    protected String _note;
-    /**  Handler release description. */
-    protected String _release;
-    /** Handler-specific parameter. */
-    protected String _param;
-    /**  Copyright notice */
-    protected String _rights;
-    /**  Handler specification document list */
-    protected List<Document> _specification;
-    /**  Handler vendor */
-    protected Agent _vendor;
-    /**  Writer for doing output */
-    protected PrintWriter _writer;
-    /** Logger for a handler class. */
-    protected Logger _logger;
-
-    /******************************************************************
-     * CLASS CONSTRUCTOR.
-     ******************************************************************/
-
-    /**
-     *   Constructors of all subclasses of HandlerBase should call
-     *   this as a <code>super</code> constructor.
-     *
-     *   @param name            Name of the handler
-     *   @param release         Release identifier
-     *   @param date            Last modification date of the handler code,
-     *                          in the form of an array of three numbers.
-     *                          <code>date[0]</code> is the year, 
-     *                          <code>date[1]</code> the month, and
-     *                          <code>date[2]</code> the day.
-     *   @param note            Additional information about the handler
-     *                          (may be null)
-     *   @param rights          Copyright notice for the handler
-     */
-    protected HandlerBase (String name, String release, int [] date,
-                           String note, String rights)
-    {
-        // Though we're actually in the jhove package, all the related
-        // action logically belongs in the handler package, so we name
-        // this logger accordingly.
-        _logger = Logger.getLogger ("edu.harvard.hul.ois.jhove.handler");
-        _logger.info ("Initializing " + name);
-        _name    = name;
-        _release = release;
-	_encoding = "UTF-8";
-
-        Calendar calendar = new GregorianCalendar ();
-        calendar.set (date[0], date[1]-1, date[2]);
-        _date = calendar.getTime ();
-
-        _note   = note;
-        _rights = rights;
-        _specification = new ArrayList<Document> ();
-
-        _level = -1;
-    }
-
-    /******************************************************************
-     * PUBLIC INSTANCE METHODS.
-     *
-     * Initialization methods.
-     ******************************************************************/
-
-    /**
-     * Reset the handler. This needs to be called before each invocation.
-     */
-    public void reset () {
-        _level = -1;
-    }
-    
-    /**
-     * Set a a List of default parameters for the module.
-     * 
-     * @param   params     A List whose elements are Strings.
-     *                     May be empty.
-     */
-    public void setDefaultParams (List<String> params)
-    {
-        _defaultParams = params;
-    }
-
-    /**
-     *  Applies the default parameters.
-     *  Calling this clears any prior parameters.
-     */
-    public void applyDefaultParams ()
-        throws Exception
-    {
-        resetParams ();
-        Iterator<String> iter = _defaultParams.iterator ();
-        while (iter.hasNext ()) {
-            String parm =  iter.next ();
-            param (parm);
-        }
-    }
-
-    /** Reset parameter settings.
-     *  Returns to a default state without any parameters.
-     *  The default method clears the saved parameter.
-     */
-    public void resetParams ()
-        throws Exception
-    {
-        _param = null;
-    }
-
-
-    /**
-     * Per-instantiation initialization.
-     * The default method does nothing.
-     */
-    public void init (String init)
-        throws Exception
-    {
-	_init = init;
-    }
-
-    /**
-     * Per-action initialization.
-     * The default method does nothing.
-     */
-    public void param (String param)
-        throws Exception
-    {
-	_param = param;
-    }
-
-    /******************************************************************
-     * Accessor methods.
-     ******************************************************************/
-
-    /**
-     *  Return the last modification date of this OutputHandler, as a
-     *  Java Date object
-     */
-    public final Date getDate ()
-    {
-        return _date;
-    }
-
-    /**
-     *  Return the OutputHandler name
-     */
-    public final String getName ()
-    {
-        return _name;
-    }
-
-    /**
-     *  Return the OutputHandler note
-     */
-    public final String getNote ()
-    {
-        return _note;
-    }
-
-    /**
-     *   Return the release identifier
-     */
-    public final String getRelease ()
-    {
-        return _release;
-    }
-
-    /**
-     *   Return the copyright information string
-     */
-    public final String getRights ()
-    {
-        return _rights;
-    }
-
-    /**
-     *  Returns a list of <code>Document</code> objects (one for each 
-     *  specification document).  The specification
-     *  list is generated by the OutputHandler, and specifications cannot
-     *  be added by callers.
-     *
-     *  @see Document
-     */
-    public final List<Document> getSpecification ()
-    {
-        return _specification;
-    }
-
-    /**
-     *  Return the vendor information
-     */
-    public final Agent getVendor ()
-    {
-        return _vendor;
-    }
-
-    /**
-     *  Returns this handler's encoding.
-     */
-    public String getEncoding ()
-    {
-	return _encoding;
-    }
-
-    /******************************************************************
-     * Mutator methods.
-     ******************************************************************/
-
-    /**
-     *  Pass the associated App object to this Module.
-     *  The App makes various services available.
-     */
-    public final void setApp (App app)
-    {
-        _app = app;
-    }
-
-    /**
-     *  Assigns the JHOVE engine object to provide services to this handler
-     */
-    public final void setBase (JhoveBase je)
-    {
-        _je = je;
-    }
-
-    /**
-     *  Assigns the encoding to be used by this OutputHandler
-     */
-    public void setEncoding (String encoding)
-    {
-	_encoding = encoding;
-    }
-
-    /**
-     *  Assigns a PrintWriter to do output for this OutputHandler
-     */
-    public final void setWriter (PrintWriter writer)
-    {
-        _writer = writer;
-    }
-
-    /******************************************************************
-     * Serialization methods.
-     ******************************************************************/
-
-    /**
-     * Callback allowing post-parse, pre-show analysis of object
-     * representation information.
-     * @param info Object representation information
-     */
-    public void analyze (RepInfo info)
-    {
-	/* Do nothing, which is sufficient for most handlers. */
-    }
-
-    /**
-     * Callback indicating a directory is finished being processed.
-     */
-    public void endDirectory ()
-    {
-	/* Do nothing, which is sufficient for most handlers. */
-    }
-
-    /**
-     * Callback to give the handler the opportunity to decide whether or
-     * not to process a file.  Most handlers will always return true.
-     * @param filepath File pathname
-     */
-    public boolean okToProcess (String filepath)
-    {
-	return true;
-    }
-
-    /**
-     *  Outputs information about a Module
-     */
-    public abstract void show (Module module);
-
-    /**
-     *  Outputs the information contained in a RepInfo object
-     */
-    public abstract void show (RepInfo info);
-
-    /**
-     *  Outputs information about the OutputHandler specified
-     *  in the parameter 
-     */
-    public abstract void show (OutputHandler handler);
-
-    /**
-     *  Outputs minimal information about the application
-     */
-    public abstract void show ();
-
-    /**
-     *  Outputs detailed information about the application,
-     *  including configuration, available modules and handlers,
-     *  etc.
-     */
-    public abstract void show (App app);
-
-    /**
-     *  Do the initial output.  This should be in a suitable format
-     *  for including multiple files between the header and the footer. 
-     */
-    public abstract void showHeader ();
-
-    /**
-     *  Do the final output.  This should be in a suitable format
-     *  for including multiple files between the header and the footer. 
-     */
-    public abstract void showFooter ();
-    
-    /**
-     *  Close the writer after all output has been done.
-     */
-    public void close ()
-    {
-        _writer.close ();
-    }
-
-    /**
-     * Callback indicating a new directory is being processed.
-     * @param directory Directory path
-     */
-    public void startDirectory (String directory)
-    {
-	/* Do nothing, which is sufficient for most handlers. */
-    }
-
-    /******************************************************************
-     * PRIVATE CLASS METHODS.
-     *
-     * XML methods.
-     ******************************************************************/
-
-    /**
-     * Return the XML DOCTYPE instruction.
-     * @param root Root element of the DTD
-     * @param uri  URI of the DTD
-     */
-    protected static String doctype (String root, String uri)
-    {
-	return doctype (root, null, uri);
-    }
-
-    /**
-     * Return the XML DOCTYPE instruction.
-     * @param root Root element of the DTD
-     * @param name Public name of the DTD
-     * @param uri  URI of the DTD
-     */
-    protected static String doctype (String root, String name, String uri)
-    {
-	StringBuffer s = new StringBuffer ("<!DOCTYPE " + root);
-	if (name != null) {
-	    s.append (" PUBLIC \"" + name + "\" \"");
-	}
-	else {
-	    s.append (" SYSTEM \"");
-	}
-	s.append (uri + "\">");
-
-	return s.toString ();
-    }
-
-    /**
-     * Returns, as a String, an empty XML.
-     *
-     * @param tag XML tag
-     */
-    protected static String element (String tag)
-    {
-        return "<" + tag + "/>";
-    }
-
-    /**
-     *  Returns, as a String, an XML element with a given tag and content
-     *
-     *  @param tag      An XML tag
-     *  @param content  Content string.  Characters requiring
-     *                  conversion to entitites will be converted.
-     */
-    protected static String element (String tag, String content)
-    {
-        return elementStart (tag) + encodeContent (content) + elementEnd (tag);
-    }
-
-    /**
-     *  Returns, as a String,
-     *  an XML element with a given tag and attributes
-     *
-     *  @param tag      An XML tag
-     *  @param attrs    An array of String[2] elements, where for each
-     *                  element, attrs[i][0] is the attribute key and
-     *                  attrs[i][1] is the attribute value.
-     *                  Null values are skipped.
-     */
-    protected static String element (String tag, String [][] attrs)
-    {
-        StringBuffer buffer = new StringBuffer ("<");
-        buffer.append (tag);
-        for (int i=0; i<attrs.length; i++) {
-			if (attrs[i][0] != null && attrs[i][1] != null) {
-				buffer.append (" ");
-				buffer.append (attrs[i][0]);
-				buffer.append ("=\"");
-				buffer.append (encodeValue (attrs[i][1]));
-				buffer.append ("\"");
-			}
-        }
-        buffer.append ("/>");
-
-        return buffer.toString ();
-    }
-
-    /**
-     *  Returns, as a String,
-     *  an XML element with a given tag, content and attributes
-     *
-     *  @param tag      An XML tag
-     *  @param content  Content string.  Characters requiring
-     *                  conversion to entitites will be converted.
-     *  @param attrs    An array of String[2] elements, where for each
-     *                  element, attrs[i][0] is the attribute key and
-     *                  attrs[i][1] is the attribute value.
-     *                  Null values are skipped.
-     *
-     */
-    protected static String element (String tag, String [][] attrs,
-                                     String content)
-    {
-        StringBuffer buffer = new StringBuffer ("<");
-        buffer.append (tag);
-        for (int i=0; i<attrs.length; i++) {
-			if (attrs[i][0] != null && attrs[i][1] != null) {
-				buffer.append (" ");
-				buffer.append (attrs[i][0]);
-				buffer.append ("=\"");
-				buffer.append (encodeValue (attrs[i][1]));
-				buffer.append ("\"");
-			}
-        }
-        buffer.append (">");
-        buffer.append (encodeContent (content));
-        buffer.append (elementEnd (tag));
-
-        return buffer.toString ();
-    }
-
-    /**
-     *   Returns, as a String, the closing tag of an element.  
-     *   No checking is done that opening and closing tags match.
-     *
-     *  @param tag      An XML tag
-     */
-    protected static String elementEnd (String tag)
-    {
-        return "</" + tag + ">";
-    }
-
-    /**
-     *  Returns, as a String, the opening tag of an element.
-     *
-     *  @param tag      An XML tag
-     */
-    protected static String elementStart (String tag)
-    {
-        return "<" + tag + ">";
-    }
-
-    /**
-     *   Returns, as a String, the opening tag of an element with
-     *   specified attributes.
-     *
-     *  @param tag      An XML tag
-     *  @param attrs    An array of String[2] elements, where for each
-     *                  element, attrs[i][0] is the attribute key and
-     *                  attrs[i][1] is the attribute value.
-     */
-    protected static String elementStart (String tag, String [][] attrs)
-    {
-        StringBuffer buffer = new StringBuffer ("<");
-        buffer.append (tag);
-        for (int i=0; i<attrs.length; i++) {
-            buffer.append (" ");
-            buffer.append (attrs[i][0]);
-            buffer.append ("=\"");
-            buffer.append (encodeValue (attrs[i][1]));
-            buffer.append ("\"");
-        }
-        buffer.append (">");
-
-        return buffer.toString ();
-    }
-
-    /**
-     *   Encodes a content String in XML-clean form, converting characters
-     *   to entities as necessary and removing control characters disallowed
-     *   by XML.  The null string will be converted to an empty string.
-     */
-    private static String encodeContent (String content)
-    {
-        if (content == null) {
-            content = "";
-        }
-        StringBuffer buffer = new StringBuffer (content);
-
-	/* Remove disallowed control characters from the content string. */
-        int n = buffer.length ();
-	for (int i=0; i<n; i++) {
-	    char ch = buffer.charAt (i);
-	    if ((0x00 <= ch && ch <= 0x08) || (0x0b <= ch && ch <= 0x0c) ||
-		(0x0e <= ch && ch <= 0x1f) ||  0x7f == ch) {
-		buffer.deleteCharAt (i--);
-		n--;
-	    }
-	}
-	n = 0;
-        while ((n = buffer.indexOf ("&", n)) > -1) {
-            buffer.insert (n+1, "amp;");
-            n +=5;
-        }
-        n = 0;
-        while ((n = buffer.indexOf ("<", n)) > -1) {
-            buffer.replace (n, n+1, "&lt;");
-            n += 4;
-        }
-        n = 0;
-        while ((n = buffer.indexOf (">", n)) > -1) {
-            buffer.replace (n, n+1, "&gt;");
-            n += 4;
-        }
-
-        return buffer.toString ();
-    }
-
-    /**
-     *   Encodes an attribute value String in XML-clean form, 
-     *   converting quote characters to entities and removing control
-     *   characters disallowed by XML.
-     */
-    private static String encodeValue (String value)
-    {
-        StringBuffer buffer = new StringBuffer (value);
-
-	/* Remove disallowed control characters from the value string. */
-        int n = buffer.length ();
-	for (int i=0; i<n; i++) {
-	    char ch = buffer.charAt (i);
-	    if ((0x00 <= ch && ch <= 0x08) || (0x0b <= ch && ch <= 0x0c) ||
-		(0x0e <= ch && ch <= 0x1f) ||  0x7f == ch) {
-		buffer.deleteCharAt (i--);
-		n--;
-	    }
-	}
-	    // [CC], escape &, < and > characters which are disallowed in xml
-        n = 0;
-        while ((n = buffer.indexOf ("&", n)) > -1) {
-            buffer.insert (n+1, "amp;");
-            n +=5;
-        }
-     	n = 0;
-        while ((n = buffer.indexOf ("<", n)) > -1) {
-            buffer.replace (n, n+1, "&lt;");
-            n += 4;
-        }
-        n = 0;
-        while ((n = buffer.indexOf (">", n)) > -1) {
-            buffer.replace (n, n+1, "&gt;");
-            n += 4;
-        }
-		n = 0;
-        while ((n = buffer.indexOf ("\"", n)) > -1) {
-            // [LP] fix for invalid escaping, "" quotes were accidentally left in place.
-            buffer.replace (n, n+1, "&quot;");
-            n +=7;
-        }
-
-        return buffer.toString ();
-    }
-
-    /**
-     *  Return a canonical XML declaration with default encoding.
-     */
-    protected static String xmlDecl ()
-    {
-        return "<?xml version=\"1.0\"?>";
-    }
-
-    /**
-     *  Return a canonical XML declaration with specified encoding.
-     */
-    protected static String xmlDecl (String encoding)
-    {
-        return "<?xml version=\"1.0\" encoding=\"" +
-                encoding +
-                "\"?>";
-    }
-
-    /******************************************************************
-     * Nesting level methods.
-     ******************************************************************/
-
-    /**
-     *   Returns a String containing a number of spaces equal
-     *   to the current indent level.
-     */
-    protected static String getIndent (int level)
-    {
-        StringBuffer s = new StringBuffer ();
-        for (int i=0; i<level; i++) {
-            s.append (" ");
-        }
-
-        return s.toString ();
-    }
-
-    /******************************************************************
-     * Array methods.
-     ******************************************************************/
-
-    /**
-     * Return String representation of an integer array.
-     */
-    protected static String integerArray (int [] iarray)
-    {
-    	return integerArray (iarray, ' ');
-    }
-    
-    /**
-     * Return String representation of an integer array with
-     * specified separator.
-     */
-    protected static String integerArray (int [] iarray, char separator)
-    {
-        StringBuffer buffer = new StringBuffer ();
-        for (int i=0; i<iarray.length; i++) {
-            if (i > 0) {
-                buffer.append (separator);
-            }
-            buffer.append (Integer.toString (iarray[i]));
-        }
-        return buffer.toString ();
-    }
-
-    /**
-     * Return String representation of an array of long with
-     * space separator.
-     */
-    protected static String longArray (long [] larray)
-    {
-        StringBuffer buffer = new StringBuffer ();
-        for (int i=0; i<larray.length; i++) {
-            if (i > 0) {
-                buffer.append (" ");
-            }
-            buffer.append (Long.toString (larray[i]));
-        }
-        return buffer.toString ();
-    }
-
-    /**
-     * Return String representation of an array of Rational, each evaluated
-     * as a double, with space separator.
-     */
-    protected static String rationalArray (Rational [] rarray)
-    {
-        StringBuffer buffer = new StringBuffer ();
-        for (int i=0; i<rarray.length; i++) {
-            if (i > 0) {
-                buffer.append (" ");
-            }
-            buffer.append (rarray[i].toDouble ());
-        }
-        return buffer.toString ();
-    }
-
-
-    /**
-     * Return String representation of an array of Rational, each as
-     * two integers, with space separator.
-     */
-    protected static String rationalArray10 (Rational [] rarray)
-    {
-	StringBuffer buffer = new StringBuffer ();
-	for (int i=0; i<rarray.length; i++) {
-	    if (i > 0) {
-		buffer.append (" ");
-	    }
-	    buffer.append (rarray[i].getNumerator ());
-	    buffer.append (" ");
-	    buffer.append (rarray[i].getNumerator ());
-	}
-	return buffer.toString ();
-    }
-
-    /**
-     * Return String representation of an array of double.
-     */
-    protected static String doubleArray (double [] darray)
-    {
-        StringBuffer buffer = new StringBuffer ();
-        for (int i=0; i<darray.length; i++) {
-            if (i > 0) {
-                buffer.append (" ");
-            }
-            buffer.append (Double.toString (darray[i]));
-        }
-        return buffer.toString ();
-    }
-
-
-    /* Text formatting methods. */
-    /* Convert a date to the dateTime format used by the
-     * XML schema.  This is ISO 8610 with a colon between
-     * the hour and minute fields of the time zone.  Unfortunately,
-     * SimpleDateFormat generates the time zone without the
-     * colon; this also conforms to 8601, but doesn't conform
-     * to the schema, so we have to diddle it.
-     */
-    protected String toDateTime (Date date)
-    {
-        String isoStr = iso8601.format (date);
-	// We can't directly use a SimpleDateFormat, because
-	// the 'z' field gives us the colonless time zone.
-        int len = isoStr.length ();
-	// Add the colon before the last two characters.
-        return isoStr.substring (0, len - 2) +
-		":" +
-		isoStr.substring (len - 2);
-    }
-    
-    /** A DateFormat class to address an issue of thread safety. */
-    public static class SynchronizedDateFormat extends SimpleDateFormat
-        {
-            public SynchronizedDateFormat(String pattern) {
-                super(pattern);
-            }
-            public synchronized StringBuffer format(Date date,
-                                    StringBuffer toAppendTo, FieldPosition pos) {
-                return super.format(date, toAppendTo, pos);
-            }
-      }
-
-}

jhove/classes/edu/harvard/hul/ois/jhove/Identifier.java

@@ -1,64 +0,0 @@
-/**********************************************************************
- * Jhove - JSTOR/Harvard Object Validation Environment
- * Copyright 2003 by JSTOR and the President and Fellows of Harvard College
- **********************************************************************/
-
-package edu.harvard.hul.ois.jhove;
-
-/**
- *  This class encapsulates information about an identifier
- *  for a specification document.
- */
-public class Identifier
-{
-    private IdentifierType _type;
-    private String _value;
-    private String _note;
-
-	/**
-	 *  Create an Identifier.
-	 *  @param  value  The text displayed for this Identifier.
-	 *  @param  type   The type of identification.
-	 */
-    public Identifier (String value, IdentifierType type)
-    {
-	_value = value;
-	_type  = type;
-    }
-
-	/**
-	 *  Create an Identifier.
-	 *  @param  value  The text displayed for this Identifier.
-	 *  @param  type   The type of identification.
-	 *  @param  note   A note giving supplementary information.
-	 */
-    public Identifier (String value, IdentifierType type, String note)
-    {
-	this (value, type);
-	_note = note;
-    }
-
-	/**
-	 *  Return the identifier type.
-	 */
-    public IdentifierType getType ()
-    {
-	return _type;
-    }
-
-	/**
-	 *  Return the displayable string.
-	 */
-    public String getValue ()
-    {
-	return _value;
-    }
-
-	/**
-	 *  Return the note, which will be null if none was specified.
-	 */
-    public String getNote()
-    {
-	return _note;
-    }
-}

jhove/classes/edu/harvard/hul/ois/jhove/IdentifierType.java

@@ -1,115 +0,0 @@
-/**********************************************************************
- * Jhove - JSTOR/Harvard Object Validation Environment
- * Copyright 2003 by JSTOR and the President and Fellows of Harvard College
- **********************************************************************/
-
-package edu.harvard.hul.ois.jhove;
-
-
-/**
- *  This class defines enumerated types for an Identifier of a
- *  format specification document. 
- *  Applications will not create or modify IdentifierTypes, but will
- *  use one of the predefined IdentifierType instances 
- *  ANSI, DDC, DOI, ECMA, HANDLE, ISO, ISBN, LC, LCCN,
- *  NISO, PII, RFC, SICI, URI, URL, URN, or OTHER.
- *
- *  @see  Identifier
- */
-public final class IdentifierType
-    extends EnumerationType
-{
-    /**
-     *  Identifier type for American National Standards Institute.
-     */
-    public static final IdentifierType ANSI = new IdentifierType ("ANSI");
-    /**
-     *  Identifier type for Dewey Decimal Classification.
-     */
-    public static final IdentifierType DDC = new IdentifierType ("DDC");
-    /**
-     *  Identifier type for Digital Object Identifier.
-     */
-    public static final IdentifierType DOI = new IdentifierType ("DOI");
-    /**
-     *  Identifier type for ECMA.
-     */
-    public static final IdentifierType ECMA = new IdentifierType ("ECMA");
-    /**
-     *  Identifier type for CNRI Handle.
-     */
-    public static final IdentifierType HANDLE = new IdentifierType ("Handle");
-    /**
-     *  Identifier type for International Standards Organization.
-     */
-    public static final IdentifierType ISO = new IdentifierType ("ISO");
-    /**
-     *  Identifier type for International Standard Book Number.
-     */
-    public static final IdentifierType ISBN = new IdentifierType ("ISBN");
-    /**
-     *  Identifier type for Library of Congress classification.
-     */
-    public static final IdentifierType LC = new IdentifierType ("LC");
-    /**
-     *  Identifier type for Library of Congress catalogue number.
-     */
-    public static final IdentifierType LCCN = new IdentifierType ("LCCN");
-    /**
-     *  Identifier type for NISO standard number.
-     */
-    public static final IdentifierType NISO = new IdentifierType ("NISO");
-    /**
-     *  Identifier type for Publisher Item Identifier.
-     */
-    public static final IdentifierType PII = new IdentifierType ("PII");
-    /**
-     *  Identifier type for IETF Request for Comment.
-     */
-    public static final IdentifierType RFC = new IdentifierType ("RFC");
-    /**
-     *  Identifier type for Serial Item and Contribution Identifier.
-     */
-    public static final IdentifierType SICI = new IdentifierType ("SICI");
-    /**
-     *  Identifier type for Uniform Resource Identifier.
-     */
-    public static final IdentifierType URI = new IdentifierType ("URI");
-    /**
-     *  Identifier type for Uniform Resource Locator.
-     */
-    public static final IdentifierType URL = new IdentifierType ("URL");
-    /**
-     *  Identifier type for Uniform Resource Name.
-     */
-    public static final IdentifierType URN = new IdentifierType ("URN");
-    /**
-     *  Identifier type for CCITT.
-     */
-    public static final IdentifierType CCITT = new IdentifierType ("CCITT");
-    /**
-     *  Identifier type for International Telecommunication Union.
-     */
-    public static final IdentifierType ITU = new IdentifierType ("ITU");
-    /**
-     *  Identifier type for Japan Electronics and Information Technology
-     *  Industries Association.
-     */
-    public static final IdentifierType JEITA = new IdentifierType ("JEITA");
-    /**
-     *  Identifier type for whatever doesn't fit other categories.
-     */
-    public static final IdentifierType OTHER = new IdentifierType ("Other");
-
-    /******************************************************************
-     * CLASS CONSTRUCTOR.
-     ******************************************************************/
-
-    /** 
-     *  Applications will never create SignatureTypes directly.
-     **/
-    private IdentifierType (String value)
-    {
-	super (value);
-    }
-}

jhove/classes/edu/harvard/hul/ois/jhove/InfoMessage.java

@@ -1,62 +0,0 @@
-/**********************************************************************
- * Jhove - JSTOR/Harvard Object Validation Environment
- * Copyright 2003 by JSTOR and the President and Fellows of Harvard College
- **********************************************************************/
-
-package edu.harvard.hul.ois.jhove;
-
-/**
- *  This class encapsulates an informational message from a Module, giving
- *  information (not necessarily a problem)
- *  about the content being analyzed or the way that Jhove
- *  deals with it. 
- */
-public class InfoMessage
-    extends Message
-{
-    /******************************************************************
-     * CLASS CONSTRUCTOR.
-     ******************************************************************/
-
-    /** 
-     *  Create an InfoMessage.
-     *  @param  message   Human-readable string giving the information.
-     */
-    public InfoMessage (String message)
-    {
-	super (message);
-    }
-
-    /** 
-     *  Create an InfoMessage.
-     *  @param  message   Human-readable string giving the information.
-     *  @param  offset    The offset in the file relevant to the
-     *                    situation being described
-     */
-    public InfoMessage (String message, long offset)
-    {
-	super (message, offset);
-    }
-
-    /** 
-     *  Create an InfoMessage.
-     *  @param  message   Human-readable string giving the information.
-     *  @param  subMessage Human-readable additional information.
-     */
-    public InfoMessage (String message, String subMessage)
-    {
-        super (message, subMessage);
-    }
-
-    /** 
-     *  Create an InfoMessage.
-     *  @param  message   Human-readable string giving the information.
-     *  @param  subMessage Human-readable additional information.
-     *  @param  offset    The offset in the file relevant to the
-     *                    situation being described
-     */
-    public InfoMessage (String message, String subMessage, long offset)
-    {
-        super (message, subMessage, offset);
-    }
-}

jhove/classes/edu/harvard/hul/ois/jhove/InternalSignature.java

@@ -1,140 +0,0 @@
-/**********************************************************************
- * Jhove - JSTOR/Harvard Object Validation Environment
- * Copyright 2003 by JSTOR and the President and Fellows of Harvard College
- **********************************************************************/
-
-package edu.harvard.hul.ois.jhove;
-
-/**
- *  This class encapsulates information about internal format signatures.
- *   The value of a Signature may be either a String or a byte array
- *   (stored as an int array to avoid signed byte problems).
- */
-public class InternalSignature
-    extends Signature
-{
-    private boolean _hasFixedOffset;
-    private int _offset;
-
-    /**
-     *  Creates an InternalSignature given a string value, a type,
-     *  and a use requirement.  An InternalSignature created with
-     *  this constructor does not have a fixed byte offset.
-     */
-    public InternalSignature (String value, SignatureType type,
-			      SignatureUseType use)
-    {
-	super (value, type, use);
-	_hasFixedOffset = false;
-    }
-
-    /**
-     *  Creates an InternalSignature given a byte array, a type,
-     *  and a use requirement.  An InternalSignature created with
-     *  this constructor does not have a fixed byte offset.
-     */
-    public InternalSignature (int[] value, SignatureType type,
-			      SignatureUseType use)
-    {
-	super (value, type, use);
-	_hasFixedOffset = false;
-    }
-
-    /**
-     *  Creates an InternalSignature given a string value, a type,
-     *  a use requirement, and a byte offset.  An InternalSignature 
-     *  created with this constructor has a fixed byte offset.
-     */
-    public InternalSignature (String value, SignatureType type,
-			      SignatureUseType use, int offset)
-    {
-	super (value, type, use);
-	_offset = offset;
-	_hasFixedOffset = true;
-    }
-
-    /**
-     *  Creates an InternalSignature given a byte array, a type,
-     *  a use requirement, and a byte offset.  An InternalSignature 
-     *  created with this constructor has a fixed byte offset.
-     */
-    public InternalSignature (int[] value, SignatureType type,
-			      SignatureUseType use, int offset)
-    {
-	super (value, type, use);
-	_offset = offset;
-	_hasFixedOffset = true;
-    }
-
-    /**
-     *  Creates an InternalSignature given a string value, a type,
-     *  a use requirement, and a note.  An InternalSignature created with
-     *  this constructor does not have a fixed byte offset.
-     */
-    public InternalSignature (String value, SignatureType type,
-			      SignatureUseType use, String note)
-    {
-	super (value, type, use, note);
-	_hasFixedOffset = false;
-    }
-
-    /**
-     *  Creates an InternalSignature given a byte array, a type,
-     *  a use requirement, and a note.  An InternalSignature created with
-     *  this constructor does not have a fixed byte offset.
-     */
-    public InternalSignature (int[] value, SignatureType type,
-			      SignatureUseType use, String note)
-    {
-	super (value, type, use, note);
-	_hasFixedOffset = false;
-    }
-
-    /**
-     *  Creates an InternalSignature given a string value, a type,
-     *  a use requirement, a byte offset, and a note.
-     *  An InternalSignature created with
-     *  this constructor has a fixed byte offset.
-     */
-    public InternalSignature (String value, SignatureType type,
-			      SignatureUseType use, int offset,
-			      String note)
-    {
-	super (value, type, use, note);
-	_offset = offset;
-	_hasFixedOffset = true;
-    }
-
-    /**
-     *  Creates an InternalSignature given a string value, a type,
-     *  a use requirement, a byte offset, and a note.
-     *  An InternalSignature created with
-     *  this constructor has a fixed byte offset.
-     */
-    public InternalSignature (int[] value, SignatureType type,
-			      SignatureUseType use, int offset,
-			      String note)
-    {
-	super (value, type, use, note);
-	_offset = offset;
-	_hasFixedOffset = true;
-    }
-
-    /**
-     *  Returns the byte offset.  This value is meaningful only
-     *  if this InternalSignature has a fixed byte offset.
-     */
-    public int getOffset ()
-    {
-	return _offset;
-    }
-
-    /**
-     *  Returns <code>true</code> if this InternalSignature
-     *  has a fixed byte offset.
-     */
-    public boolean hasFixedOffset ()
-    {
-	return _hasFixedOffset;
-    }
-}

jhove/classes/edu/harvard/hul/ois/jhove/JhoveException.java

@@ -1,19 +0,0 @@
-/**********************************************************************
- * Jhove - JSTOR/Harvard Object Validation Environment
- * Copyright 2004 by JSTOR and the President and Fellows of Harvard College
- **********************************************************************/
-
-package edu.harvard.hul.ois.jhove;
-
-public class JhoveException
-    extends Exception
-{
-    public JhoveException ()
-    {
-	super ();
-    }
-    public JhoveException (String message)
-    {
-	super (message);
-    }
-}

jhove/classes/edu/harvard/hul/ois/jhove/MacStuff.java

@@ -1,96 +0,0 @@
-/**********************************************************************
- * Jhove - JSTOR/Harvard Object Validation Environment
- * Copyright 2003 by JSTOR and the President and Fellows of Harvard College
- **********************************************************************/
-
-package edu.harvard.hul.ois.jhove;
-
-import java.io.*;
-import java.lang.reflect.*;
-//import com.apple.eio.FileManager;
-
-
-/**
- * Code specific to Macintosh Java. This class consists of static
- * methods, and should not be instantiated.  Its methods should be
- * called only on the Macintosh OS X platform.  It requires the 
- * package com.apple.eio.FileManager.
- * 
- * @author Gary McGath
- *
- */
-public class MacStuff {
-    
-    /** Private constructor to prevent instantiation.*/
-    private MacStuff ()
-    {
-    }
-    
-    
-    /**
-     * Determines if we're running on a Macintosh,
-     * so appropriate UI adjustments can be made.  In accordance
-     * with Apple's recommendations, this checks for the existence
-     * of the mrj.version property rather than checking the os.name
-     * property.
-     */
-    public static boolean isMacintosh ()
-    {
-        return (System.getProperty ("mrj.version") != null);
-
-    }
-    
-    
-
-    /**
-     * Returns true if a file has the given file type.
-     * This method uses FileManager in a dynamic way, so 
-     * that it will merely throw a ClassNotFound exception
-     * if it fails.
-     * 
-     * Currently this code isn't actually used, since the
-     * Jhove application is specified as checking only internal
-     * signatures.  Should some future version or add-on
-     * code wish to use it, the code should
-     * look something like this:
-     * 
-     * <code><pre>
-     *           try {
-     *               if (sig.getType() == SignatureType.FILETYPE &&
-     *                       MacStuff.isMacintosh ()) {
-     *                   if (!MacStuff.fileHasType(file, sig.getValueString())) {
-     *                       info.setConsistent (false);
-     *                   }    
-     *               }
-     *           }
-     *           catch (ClassNotFoundException e) {
-     *               // Mac classes missing -- can't check filetype.
-     *           }
-     * </pre></code>
-     */
-    public static boolean fileHasType(File file, String type)
-            throws ClassNotFoundException
-    {
-        // Need to make this completely dynamic.
-        //return type.equals (FileManager.getFileType (file));
-        try {
-            if (type == null) {
-                return false;
-            }
-            Class fmclass = Class.forName ("com.apple.eio.FileManager");
-            Class[] params = new Class[1];
-            params[0] = Class.forName ("java.io.File");
-            Object[] args = new Object[1];
-            args[0] = file; 
-            Method method = fmclass.getMethod ("getFileType", params);
-            String ftype = (String) method.invoke (null, args); 
-            return (type.equals (ftype));
-        }
-        catch (ClassNotFoundException e) {
-            throw e;
-        }
-        catch (Exception f) {
-            return false;
-        }
-    }
-}

jhove/classes/edu/harvard/hul/ois/jhove/Message.java

@@ -1,131 +0,0 @@
-/**********************************************************************
- * Jhove - JSTOR/Harvard Object Validation Environment
- * Copyright 2003 by JSTOR and the President and Fellows of Harvard College
- **********************************************************************/
-
-package edu.harvard.hul.ois.jhove;
-
-/**
- *  This class encapsulates a String to be displayed. 
- */
-public abstract class Message
-{
-    /******************************************************************
-     * PUBLIC CLASS FIELDS.
-     ******************************************************************/
-
-    /** Value indicating a null offset. */
-    public static final long NULL = -1;
-
-    /******************************************************************
-     * PRIVATE INSTANCE FIELDS.
-     ******************************************************************/
-
-    /** Message text. */
-    protected String _message;
-    
-    /** Additional information. */
-    protected String _subMessage;
-    
-    /** Byte offset to which message applies. */
-    protected long _offset;
-
-    /******************************************************************
-     * CLASS CONSTRUCTOR.
-     ******************************************************************/
-
-    /**
-     *  Create a Message.  This constructor cannot be invoked directly,
-     *                     since Message is abstract.
-     *  @param  message   Human-readable string.
-     */
-    protected Message (String message)
-    {
-	init (message, null, NULL);
-    }
-
-    /**
-     *  Create a Message.  This constructor cannot be invoked directly,
-     *                     since Message is abstract.  The second argument
-     *                     adds secondary details to the primary message;
-     *                     the message will typically be displayed in the
-     *                     form "message:subMessage".
-     *  @param  message    Human-readable string.
-     *  @param  subMessage Human-readable additional information.
-     */
-    protected Message (String message, String subMessage)
-    {
-	init (message, subMessage, NULL);
-    }
-
-    /**
-     *  Create a Message.  This constructor cannot be invoked directly,
-     *                     since Message is abstract.  The second argument
-     *                     adds secondary details to the primary message;
-     *                     the message will typically be displayed in the
-     *                     form "message:subMessage".
-     *  @param  message    Human-readable string.
-     *  @param  offset     Byte offset associated with the message.
-     */
-    protected Message (String message, long offset)
-    {
-	init (message, null, offset);
-    }
-
-    /**
-     *  Create a Message.  This constructor cannot be invoked directly,
-     *                     since Message is abstract.  The second argument
-     *                     adds secondary details to the primary message;
-     *                     the message will typically be displayed in the
-     *                     form "message:subMessage".
-     *  @param  message    Human-readable string.
-     *  @param  subMessage Human-readable additional information.
-     *  @param  offset     Byte offset associated with the message.
-     */
-    protected Message (String message, String subMessage, long offset)
-    {
-	init (message, subMessage, offset);
-    }
-
-    /**
-     * Initialize the <tt>Message</tt> object.
-     *  @param  message    Human-readable string.
-     *  @param  subMessage Human-readable additional information.
-     */
-    private void init (String message, String subMessage, long offset)
-    {
-        _message    = message;
-        _subMessage = subMessage;
-	_offset     = offset;
-    }
-
-    /******************************************************************
-     * PUBLIC INSTANCE METHODS.
-     *
-     * Accessor methods.
-     ******************************************************************/
-
-    /**
-     *  Get the message string.
-     */
-    public String getMessage ()
-    {
-        return _message;
-    }
-
-    /**
-     *  Get the submessage string.
-     */
-    public String getSubMessage ()
-    {
-        return _subMessage;
-    }
-
-    /**
-     *  Return the offset to which the information is related.
-     */
-    public long getOffset ()
-    {
-	return _offset;
-    }
-}

jhove/classes/edu/harvard/hul/ois/jhove/Module.java

@@ -1,264 +0,0 @@
-/**********************************************************************
- * Jhove - JSTOR/Harvard Object Validation Environment
- * Copyright 2003-4 by JSTOR and the President and Fellows of Harvard College
- **********************************************************************/
-
-package edu.harvard.hul.ois.jhove;
-
-import java.io.*;
-import java.util.*;
-
-/**
- * Public interface for Jhove format-specific plug-in modules.
- * 
- * All format modules must implement the Module interface; 
- * usually the best way to do this will be to subclass ModuleBase.
- * Modules must be declared in the configuration file and present
- * in the Classpath to be recognized by Jhove.  
- *
- * @see  ModuleBase
- */
-public interface Module
-{
-    public static final int
-	MAXIMUM_VERBOSITY = 1,
-	MINIMUM_VERBOSITY = 2;
-
-    /**
-     * Per-instantiation initialization.
-     *
-     * @param init    Initialization parameter.  This is typically obtained
-     *                from the configuration file.
-     */
-    public void init (String init)
-	throws Exception;
-
-    /**
-     * Sets list of default parameters.
-     * 
-     * @param   params     A List whose elements are Strings.
-     *                     May be empty.
-     */
-    public void setDefaultParams (List<String> params);
-
-
-    /**
-     *  Applies the default parameters.
-     */
-    public void applyDefaultParams ()
-        throws Exception;
-    
-    /** Reset parameter settings.
-     *  Returns to a default state without any parameters.
-     */
-    public void resetParams ()
-        throws Exception;
-
-    /**
-     * Per-action initialization.
-     * May be called multiple times.
-     *
-     * @param param   Initialization parameter.
-     */
-    public void param (String param)
-	throws Exception;
-
-    /**
-     *  Pass the associated App object to this Module.
-     *  The App makes various services available.
-     */
-    public void setApp (App app);
-
-    /**
-     *  Pass the JHOVE engine object to this Module.
-     */
-    public void setBase (JhoveBase je);
-
-    /**
-     *  Set the degree of verbosity desired from the module.  
-     *
-     *  @param  verbosity  The requested verbosity value.  
-     */
-    public void setVerbosity (int verbosity);
-
-    /**
-     *  Return the name of this Module.
-     */
-    public String getName ();
-    
-    /**
-     *   Return the release identifier
-     */    
-    public String getRelease ();
-
-    /**
-     *  Return the last modification date of the Module, as a
-     *  Java Date object
-     */
-    public Date getDate ();
-
-    /**
-     *  Return the vendor information
-     */
-    public Agent  getVendor ();
-
-    /**
-     *   Return the copyright information string
-     */
-    public String getRights ();
-
-    /**
-     *   Return the Module note
-     */
-    public String getNote ();
-
-    /**
-     *   Return the array of format names supported by this Module
-     */
-    public String [] getFormat ();
-
-    /**
-     *   Return the array of MIME type strings for formats supported
-     *   by this Module
-     */
-    public String [] getMimeType ();
-
-    /**
-     *  Return details as to the specific format versions or 
-     *  variants that are supported by this Module
-     */
-    public String getCoverage ();
-
-    /**
-     *   Return the List of Signatures recognized by this Module
-     */
-    public List<Signature> getSignature ();
-
-    /**
-     *  Returns a list of <code>Document</code> objects (one for each 
-     *  specification document of the format).  The specification
-     *  list is generated by the Module, and specifications cannot
-     *  be added by callers.
-     *
-     *  @see Document
-     */
-    public List<Document> getSpecification ();
-
-    /**
-     *   Return the string describing well-formedness criteria
-     */
-    public String getWellFormedNote ();
-
-    /**
-     *   Returns the RepInfo note
-     */
-    public String getRepInfoNote ();
-
-    /**
-     *   Returns the string describing validity criteria
-     */
-    public String getValidityNote ();
-
-    /**
-     *  Returns the random access flag (true if the module operates
-     *  on random access files, false if it operates on streams)
-     */
-    public boolean isRandomAccess ();
-    
-    /**
-     *  Returns <code>true</code> if the module supports a given
-     *  named feature, and <code>false</code> if the feature is
-     *  unsupported or unknown.
-     */
-    public boolean hasFeature (String feature);
-
-    /**
-     *  Returns the full list of features. 
-     */
-    public List<String> getFeatures ();
-    
-    /**
-     *  Returns the list of default parameters. 
-     */
-    public List<String> getDefaultParams ();
-
-
-
-    /**
-     *   Parse the content of a stream digital object and store the
-     *   results in RepInfo.
-     *   A given Module will normally implement only one of the two
-     *   parse methods, leaving the other as a stub.
-     *
-     *   @param stream    An InputStream, positioned at its beginning,
-     *                    which is generated from the object to be parsed.
-     *                    If multiple calls to <code>parse</code> are made 
-     *                    on the basis of a nonzero value being returned,
-     *                    a new InputStream must be provided each time.
-     * 
-     *   @param info      A fresh (on the first call) RepInfo object 
-     *                    which will be modified
-     *                    to reflect the results of the parsing
-     *                    If multiple calls to <code>parse</code> are made 
-     *                    on the basis of a nonzero value being returned, 
-     *                    the same RepInfo object should be passed with each
-     *                    call.
-     *
-     *   @param parseIndex  Must be 0 in first call to <code>parse</code>.  If
-     *                    <code>parse</code> returns a nonzero value, it must be
-     *                    called again with <code>parseIndex</code> 
-     *                    equal to that return value.
-     */
-    public int parse (InputStream stream, RepInfo info, int parseIndex)
-    throws IOException;
-
-    /**
-     *   Parse the content of a random access digital object and store the
-     *   results in RepInfo.
-     *   A given Module will normally implement only one of the two
-     *   parse methods, leaving the other as a stub.
-     *
-     *   @param file      A RandomAccessFile, positioned at its beginning,
-     *                    which is generated from the object to be parsed
-     *   @param info      A fresh RepInfo object which will be modified
-     *                    to reflect the results of the parsing
-     */
-    public void parse (RandomAccessFile file, RepInfo info)
-        throws IOException;
-
-    /**
-     *  Check if the digital object conforms to this Module's
-     *  internal signature information.
-     *
-     *   @param file      A File object for the object being parsed
-     *   @param stream    An InputStream, positioned at its beginning,
-     *                    which is generated from the object to be parsed
-     *   @param info      A fresh RepInfo object which will be modified
-     *                    to reflect the results of the test
-     */
-    public void checkSignatures (File file,
-                InputStream stream, 
-                RepInfo info)
-        throws IOException;
-
-    /**
-     *  Check if the digital object conforms to this Module's
-     *  internal signature information.
-     *
-     *   @param file      A File object for the object being parsed
-     *   @param raf       A RandomAccessFile, positioned at its beginning,
-     *                    which is generated from the object to be parsed
-     *   @param info      A fresh RepInfo object which will be modified
-     *                    to reflect the results of the test
-     */
-    public void checkSignatures (File file, 
-            RandomAccessFile raf, 
-            RepInfo info)
-        throws IOException;
-
-	/**
-	 *  Generates information about this Module.
-	 *  The format of the output depends on the OutputHandler.
-	 */
-    public void show (OutputHandler handler);
-}

jhove/classes/edu/harvard/hul/ois/jhove/ModuleInfo.java

@@ -1,17 +0,0 @@
-package edu.harvard.hul.ois.jhove;
-
-/** A small class to hold information about a module. */
-public class ModuleInfo {
-    public String clas;
-    public String init;
-    public String[] params;
-    
-    public ModuleInfo (String className) {
-        clas = className;
-    }
-    
-    public ModuleInfo (String className, String init) {
-        clas = className;
-        this.init =  init;
-    }
-}

jhove/classes/edu/harvard/hul/ois/jhove/ObjectIdentifier.java

@@ -1,118 +0,0 @@
-/**********************************************************************
- * Jhove - JSTOR/Harvard Object Validation Environment
- * Copyright 2003-4 by JSTOR and the President and Fellows of Harvard College
- **********************************************************************/
-
-package edu.harvard.hul.ois.jhove;
-
-import java.io.*;
-import java.util.*;
-
-/**
- *  Module for identification of a document.  "Identification"
- *  means determining, by querying modules successively, what the format
- *  of a document is.  The Bytestream module is always queried last,
- *  so a document will by identified as a Bytestream if all else fails.
- */
-public class ObjectIdentifier
-{
-    /******************************************************************
-     * PRIVATE INSTANCE FIELDS.
-     ******************************************************************/
-
-    private List _moduleList;
-
-    /******************************************************************
-     * CLASS CONSTRUCTOR.
-     ******************************************************************/
-    public ObjectIdentifier (List moduleList) 
-    {
-	_moduleList = moduleList;
-    }
-
-
-    /******************************************************************
-     * PUBLIC INSTANCE METHODS.
-     *
-     * Processing methods.
-     *
-     ******************************************************************/
-
-    /**
-     *  Perform identification on a file.  The file is parsed by
-     *  each of the modules in the module list until one
-     *  declares that the file is well-formed. It is assumed
-     *  that there is a module in the list (normally Bytestream
-     *  at the end) which will always consider a file well-formed.
-     */
-    public void identify (File file, RepInfo info, 
-			  String parm, boolean verbose,
-			  boolean shortCheck) 
-	                 throws IOException 
-    {
-	/******************************************************
-	 *  Go through all modules, in the order in the config
-	 *  file, calling the parse method till we find one 
-         *  which matches.
-	 ******************************************************/
-
-	ListIterator modIter = _moduleList.listIterator();
-	while (modIter.hasNext ()) {
-	    /* We need clean RepInfo for each run */
-	    RepInfo info1;
-	    info1 = (RepInfo) info.clone ();
-
-	    Module mod = (Module) modIter.next ();
-	    try {
-                if (!mod.hasFeature("edu.harvard.hul.ois.jhove.canValidate")) {
-                    continue;
-                }
-		if (mod.isRandomAccess ()) {
-                    RandomAccessFile raf = 
-                        new RandomAccessFile (file, "r");
-                    mod.param (parm);
-                    if (verbose) {
-                        mod.setVerbosity (Module.MAXIMUM_VERBOSITY);
-                    }
-                    if (shortCheck) {
-                        mod.checkSignatures (file, raf, info1);
-                    }
-                    else {
-                        mod.parse (raf, info1);
-                    }
-                    raf.close ();
-                }
-		else {
-		    InputStream stream = new FileInputStream (file);
-		    mod.param (parm);
-		    if (shortCheck) {
-		        mod.checkSignatures (file, stream, info1);
-		    }
-		    else {
-                        int parseIndex = mod.parse (stream, info1, 0);
-                        while (parseIndex != 0) {
-                            stream.close ();
-                            stream = new FileInputStream (file);
-                            parseIndex = mod.parse (stream, info1, parseIndex);
-                        }
-		    }
-		    stream.close ();
-		}
-	    }
-            catch (Exception e) {
-		/*  The assumption is that in trying to analyze
-		    the wrong type of file, the module may go
-		    off its track and throw an exception, so we
-		    just continue on to the next module.
-		*/
-            continue;
-	    }
-	    if (info1.getWellFormed () == RepInfo.TRUE) {
-               info.copy (info1);
-               break;
-	    }
-	}
-    }
-
-    
-}

jhove/classes/edu/harvard/hul/ois/jhove/OutputHandler.java

@@ -1,196 +0,0 @@
-/**********************************************************************
- * Jhove - JSTOR/Harvard Object Validation Environment
- * Copyright 2003 by JSTOR and the President and Fellows of Harvard College
- **********************************************************************/
-
-package edu.harvard.hul.ois.jhove;
-
-import java.io.*;
-import java.util.*;
-
-/**
- * Public interface for Jhove output handlers.
- * All output handlers must implement OutputHandler, and in 
- * normal cases should subclass HandlerBase.
- */
-public interface OutputHandler
-{
-    
-    /**
-     * Reset the handler. This needs to be called before each invocation.
-     */
-    public void reset ();
-
-    /**
-     * Callback allowing post-parse, pre-show analysis of object
-     * representation information.
-     * @param info Object representation information
-     */
-    public void analyze (RepInfo info);
-
-    /**
-     * Callback indicating a directory is finished being processed.
-     * Most handlers will do nothing.
-     */
-    public void endDirectory ();
-
-    /**
-     *  Returns the name of this handler
-     */
-    public String getName ();
-    /**
-     *  Returns release information for this handler
-     */
-    public String getRelease ();
-
-    /**
-     *  Returns the last modification date of this handler
-     */
-    public Date getDate ();
-
-    /**
-     *  Returns a List of Document objects giving the format
-     *  specification documentation
-     *
-     *  @see Document
-     */
-    public List<Document> getSpecification ();
-
-    /**
-     *  Returns a List of Agent objects giving the vendor(s)
-     *  of this handler.
-     */
-    public Agent getVendor ();
-
-    /**
-     *  Returns this handler's note
-     */
-    public String getNote ();
-
-    /**
-     *  Returns this handler's copyright information
-     */
-    public String getRights ();
-
-    /**
-     *  Returns this handler's encoding.
-     */
-    public String getEncoding ();
-
-    /**
-     * Per-instantiation initialization.
-     *
-     * @param init    Initialization parameter.  This is typically obtained
-     *                from the configuration file.
-     */
-    public void init (String init)
-	throws Exception;
-
-    /**
-     * Callback to give the handler the opportunity to decide whether or
-     * not to process a file.  Most handlers will always return true.
-     * @param filepath File pathname
-     */
-    public boolean okToProcess (String filepath);
-
-    /**
-     * Sets list of default parameters.
-     * 
-     * @param   params     A List whose elements are Strings.
-     *                     May be empty.
-     */
-    public void setDefaultParams (List<String> params);
-
-
-    /**
-     *  Applies the default parameters.
-     */
-    public void applyDefaultParams ()
-        throws Exception;
-    
-    /** Reset parameter settings.
-     *  Returns to a default state without any parameters.
-     */
-    public void resetParams ()
-        throws Exception;
-
-    /**
-     * Per-action initialization.
-     *
-     * @param param   Initialization parameter.
-     */
-    public void param (String param)
-	throws Exception;
-
-    /**
-     *  Assigns an application object to provide services to this handler
-     */
-    public void setApp (App app);
-
-    /**
-     *  Assigns the JHOVE engine object to provide services to this handler
-     */
-    public void setBase (JhoveBase je);
-
-    /**
-     *  Assigns the encoding to be used by this OutputHandler
-     */
-    public void setEncoding (String encoding);
-
-    /**
-     *  Assigns a PrintWriter to do output for this OutputHandler
-     */
-    public void setWriter (PrintWriter output);
-
-    /**
-     *  Outputs information about a Module
-     */
-    public void show (Module module);
-
-    /**
-     *  Outputs the information contained in a RepInfo object
-     */
-    public void show (RepInfo info);
-
-    /**
-     *  Outputs information about the OutputHandler specified
-     *  in the parameter 
-     */
-    public void show (OutputHandler handler);
-
-    /**
-     *  Outputs minimal information about the application
-     */
-    public void show ();
-
-    /**
-     *  Outputs detailed information about the application,
-     *  including configuration, available modules and handlers,
-     *  etc.
-     */
-    public void show (App app);
-
-    /**
-     *  Do the initial output.  This should be in a suitable format
-     *  for including multiple files between the header and the footer. 
-     */
-    public void showHeader ();
-
-    /**
-     *  Do the final output.  This should be in a suitable format
-     *  for including multiple files between the header and the footer. 
-     */
-    public void showFooter ();
-
-    /**
-     *  Do appropriate finalization after all output is complete.
-     */
-    public void close ();
-
-    /**
-     * Callback indicating a new directory is being processed.
-     * Most handlers will do nothing.
-     * @param directory Directory path
-     */
-    public void startDirectory (String directory);
-}

jhove/classes/edu/harvard/hul/ois/jhove/Property.java

@@ -1,214 +0,0 @@
-/**********************************************************************
- * Jhove - JSTOR/Harvard Object Validation Environment
- * Copyright 2003 by JSTOR and the President and Fellows of Harvard College
- **********************************************************************/
-
-package edu.harvard.hul.ois.jhove;
-
-import java.util.*;
-
-/**
- *  This class encapsulates arbitrary format-specific properties.
- *  A Property's value can be a simple object or a structure.
- *  If it is a simple object, it has arity SCALAR.  If it is
- *  a structure, its must be a Map, a List, a Set, or an array,
- *  with corresponding Arity.  The simple object (in the case of
- *  arity SCALAR) or the components of the structure must have a
- *  type corresponding to one of the enumerations given by
- *  <code>PropertyType</code>.
- *
- *  The components of a Property may themselves be Property 
- *  objects, allowing nested structures.
- *
- *  @see PropertyType
- *  @see PropertyArity
- */
-public class Property
-{
-    /******************************************************************
-     * PRIVATE INSTANCE FIELDS.
-     ******************************************************************/
-
-    private String _name;
-    private PropertyType _type;
-    private PropertyArity _arity;
-    private Object _value;
-
-
-    /******************************************************************
-     * CLASS CONSTRUCTOR.
-     ******************************************************************/
-
-	/**
-	 *  Creates a Property with arity SCALAR.
-	 *
-	 *  @param   name   The displayable name of the property
-	 *  @param   type   The type of property
-	 *  @param   value  The value of the property.  The type of the
-	 *                  parameter must agree with <code>type</code>.
-	 */
-    public Property (String name, PropertyType type, Object value)
-    {
-	init (name, type, PropertyArity.SCALAR, value);
-    }
-
-	/**
-	 *  Creates a Property with a given name, type, arity and value.
-	 *
-	 *  @param   name   The displayable name of the property.
-	 *  @param   type   The type of property.
-	 *  @param   arity  The arity of the property.
-	 *  @param   value  The value of the property.  If the arity is
-	 *		SCALAR, the type of this parameter must agree
-	 *		with <code>type</code>.  Otherwise, the arity
-	 *              must agree with <code>arity</code>, and its
-	 *              components must agree with <code>type</code>.
-	 */
-    public Property (String name, PropertyType type, PropertyArity arity,
-		     Object value)
-    {
-	init (name, type, arity, value);
-    }
-
-    private void init (String name, PropertyType type, PropertyArity arity,
-		       Object value)
-    {
-	/* Some limited type checking. Checking for mismatched
-           types here may help avoid difficult chasing down
-           of the bugs such mismatches cause. */
-	if (value == null) {
-	    throw new NullPointerException ("Null value for Property not permitted");
-	}
-	if (arity == PropertyArity.SCALAR) {
-	    if (value instanceof List ||
-		    value instanceof Map ||
-		    value instanceof Set) {
-		throw new IncompatibleClassChangeError
-			("Wrong class for Scalar Property");
-	    }
-	}
-	else if (arity == PropertyArity.MAP) {
-	    if (!(value instanceof Map)) {
-		throw new IncompatibleClassChangeError
-			("Wrong class for Map Property");
-	    }
-
-	}
-	else if (arity == PropertyArity.SET) {
-	    if (!(value instanceof Set)) {
-		throw new IncompatibleClassChangeError
-			("Wrong class for Set Property");
-	    }
-
-	}
-	else if (arity == PropertyArity.LIST) {
-	    if (!(value instanceof List)) {
-		throw new IncompatibleClassChangeError
-			("Wrong class for List Property");
-	    }
-
-	}
-
-	_name  = name;
-	_type  = type;
-	_arity = arity;
-	_value = value;
-    }
-
-    /******************************************************************
-     * PUBLIC INSTANCE METHODS.
-     *
-     * Accessor methods.
-     ******************************************************************/
-
-	/**
-	 *   Returns the arity (type of structure) of this Property.
-	 */
-    public PropertyArity getArity ()
-    {
-	return _arity;
-    }
-
-    /**
-     * Return a property by its name, regardless of its position in the
-     * structural hierarchy of properties.
-     * @param name Property name
-     * @return Named property (or null)
-     */
-    public Property getByName (String name)
-    {
-	if (_name.equals (name)) {
-	    return this;
-	}
-
-	if (!_arity.equals (PropertyArity.SCALAR) &&
-	    _type.equals (PropertyType.PROPERTY)) {
-	    if (_arity.equals (PropertyArity.ARRAY)) {
-		Property [] array = (Property []) _value;
-		for (int i=0; i<array.length; i++) {
-		    Property prop = array[i].getByName (name);
-		    if (prop != null) {
-			return prop;
-		    }
-		}
-	    }
-	    else if (_arity.equals (PropertyArity.LIST)) {
-		List list = (List) _value;
-		int len = list.size ();
-		for (int i=0; i<len; i++) {
-		    Property prop = ((Property) list.get (i)).getByName (name);
-		    if (prop != null) {
-			return prop;
-		    }
-		}
-	    }
-	    else if (_arity.equals (PropertyArity.MAP)) {
-		Collection coll = ((Map) _value).values ();
-		Iterator iter = coll.iterator ();
-		while (iter.hasNext ()) {
-		    Property prop = ((Property) iter.next ()).getByName (name);
-		    if (prop != null) {
-			return prop;
-		    }
-		}
-	    }
-	    else if (_arity.equals (PropertyArity.SET)) {
-		Iterator iter = ((Set) _value).iterator ();
-		while (iter.hasNext ()) {
-		    Property prop = ((Property) iter.next ()).getByName (name);
-		    if (prop != null) {
-			return prop;
-		    }
-		}
-	    }
-	}
-
-	return null;
-    }
-
-	/**
-	 *   Returns the displayable name of this Property.
-	 */
-    public String getName ()
-    {
-	return _name;
-    }
-
-	/**
-	 *  Returns the type of this Property.
-	 *  If the arity is other than SCALAR, the type refers to the
-	 *  compononents of the Property structure.
-	 */
-    public PropertyType getType ()
-    {
-	return _type;
-    }
-
-	/**
-	 *  Returns the Object which is the Property's value.
-	 */
-    public Object getValue ()
-    {
-	return _value;
-    }
-}

jhove/classes/edu/harvard/hul/ois/jhove/PropertyArity.java

@@ -1,60 +0,0 @@
-/**********************************************************************
- * Jhove - JSTOR/Harvard Object Validation Environment
- * Copyright 2003 by JSTOR and the President and Fellows of Harvard College
- **********************************************************************/
-
-package edu.harvard.hul.ois.jhove;
-
-
-/**
- *  This class represents the arity (structure type) of a Property.
- *  Applications will not create or modify PropertyArities, but will
- *  use one of the predefined PropertyArity instances 
- *  ARRAY, LIST, MAP, SCALAR, or SET.
- *
- *   @see Property
- */
-public final class PropertyArity
-    extends EnumerationType
-{
-	/**
-	 *  An Arity corresponding to a Java array.  For the Java types
-	 *  <code>Integer</code>, <code>Boolean</code>, <code>Byte</code>, 
-	 *  <code>Character</code>, <code>Double</code>, 
-	 *  <code>Float</code>, <code>Long</code>, and
-	 *  <code>Short</code>, a Property with arity ARRAY is an array of primitive
-	 *  Java types rather than Objects (e.g., <code>int</code> 
-	 *  rather than <code>Integer</code>).
-	 */
-    public static final PropertyArity ARRAY = new PropertyArity ("Array");
-    
-    /**
-     *  An Arity corresponding to java.util.List or any of its derived classes.
-     */
-    public static final PropertyArity LIST = new PropertyArity ("List");
-
-    /**
-     *  An Arity corresponding to java.util.Map or any of its derived classes.
-     */
-    public static final PropertyArity MAP = new PropertyArity ("Map");
-
-    /**
-     *  An Arity corresponding to a simple object, which must be of a
-     *  type corresponding to one of the instances of 
-     *  <code>PropertyType</code>.
-     */
-    public static final PropertyArity SCALAR = new PropertyArity ("Scalar");
-
-    /**
-     *  An Arity corresponding to java.util.Set or any of its derived classes.
-     */
-    public static final PropertyArity SET = new PropertyArity ("Set");
-
-    /** 
-     *  Applications will never create PropertyArities directly.
-     **/
-    private PropertyArity (String value)
-    {
-	super (value);
-    }
-}

jhove/classes/edu/harvard/hul/ois/jhove/PropertyPath.java

@@ -1,278 +0,0 @@
-/**********************************************************************
- * Jhove - JSTOR/Harvard Object Validation Environment
- * Copyright 2004 by JSTOR and the President and Fellows of Harvard College
- **********************************************************************/
-
-package edu.harvard.hul.ois.jhove;
-
-
-import java.util.*;
-
-/**
- * A description of the location of a Property in a
- * RepInfo object.  Properties can be nested under other
- * properties, in lists, maps, or subproperties. This class
- * provides a general way to specify their location.
- * 
- * For the moment, only paths by name are fully supported. 
- *
- * @author Gary McGath
- *
- */
-public class PropertyPath {
-
-    private List pathInfo;
-    
-    /**
-     * No-argument constructor.
-     * Creates an empty path.
-     */
-    public PropertyPath ()
-    {
-        pathInfo = new LinkedList ();
-    }
-    
-    /**
-     *  Cloning constructor.
-     *  This creates a new pathInfo list, whose elements
-     *  are shared with the original PropertyPath's list.
-     */
-    public PropertyPath (PropertyPath path) 
-    {
-        pathInfo = new LinkedList ();
-        pathInfo.addAll (path.pathInfo);
-    }
-    
-    /**
-     *  String array constructor.
-     *  This allows creation of a path in a common and simple
-     *  case:  a hierarchy of named subproperties. It's the
-     *  equivalent of creating an empty PropertyPath and then
-     *  calling addElement successively with each of the strings
-     *  in the array.
-     */
-    public PropertyPath (String[] pathArray)
-    {
-        pathInfo = new LinkedList ();
-        for (int i = 0; i < pathArray.length; i++) {
-            pathInfo.add (pathArray[i]);
-        }
-    }
-
-    /**
-     *  Adds a property name to the path.
-     */
-    public void addPropertyName (String str)
-    {
-        pathInfo.add (str);
-        // Now -- how do we add a key and distinguish it from a 
-        // property name?  We could define an internal type for
-        // keys.  Do that for the moment and see what that leads
-        // to in retrieval.  Alternatively, it isn't needed because
-        // we can see that a property has arity Map.
-    }
-    
-    /**
-     *  Adds a key to the path, for a property map.
-     */
-    public void addPropertyKey (Object obj)
-    {
-        pathInfo.add (new PropertyKey (obj));
-    }
-    
-    /**
-     *  Adds an index to the path, for an indexed property.
-     */
-    public void addPropertyIndex (int idx)
-    {
-        pathInfo.add (new Integer (idx));
-    }
-    
-    /**
-     *   Walk down the path and return the specified Property.
-     *   
-     *   @param   info   The RepInfo object to search
-     * 
-     *   @return  The specified Property if found, otherwise null.
-     */
-    public Property locateProperty (RepInfo info)
-    {
-        return locateProperty (info, false);
-    }
-    
-
-    /**
-     *   Walk down the path and return the specified Property.
-     *   
-     *   @param   info   The RepInfo object to search
-     *   @param   trace  If <code>true</code>, write debugging information
-     *                   to standard output.
-     * 
-     *   @return  The specified Property if found, otherwise null.
-     */
-    public Property locateProperty (RepInfo info, boolean trace)
-    {
-        if (pathInfo.isEmpty ()) {
-            // An empty path can't reach any property
-            if (trace) {
-                System.out.println ("Empty property path");
-            }
-            return null;
-        }
-        Object obj = pathInfo.get(0);
-        if (!(obj instanceof String)) {
-            // The initial qualifier must be a property name
-            if (trace) {
-                System.out.println ("Not a property name");
-            }
-            return null;
-        }
-        String top = (String) obj;
-        if (trace) {
-            System.out.println ("Getting proprerty " + top);
-        }
-        Property prop = info.getProperty (top);
-        if (prop == null) {
-            // No property of that name in RepInfo
-            if (trace) {
-                System.out.println ("Property is null");
-            }
-            return null;
-        }
-        int pathLen = pathInfo.size ();
-        // Pass the CDR of the list to locateSubProperty.
-        return locateSubProperty (prop, pathInfo.subList (1, pathLen), trace);
-    }
-    
-    /* Recursive function for extracting a subproperty of a property. */
-    private Property locateSubProperty (Property property, List path, boolean trace)
-    {
-        // If there's nothing left of the path, we're done.
-        if (path.isEmpty ()) {
-            return property;
-        }
-        List cdr = path.subList (1, path.size());
-        PropertyArity arity = property.getArity ();
-        PropertyType type = property.getType ();
-        Object val = property.getValue ();
-        if (trace) {
-            System.out.println ("Property arity = " + arity + ", type = " + type);
-        }
-        // If the type isn't PROPERTY, then there are no subproperties.
-        if (type != PropertyType.PROPERTY) {
-            if (trace) {
-                System.out.println ("Not a property, type is " + type.toString ());
-            }
-            return null;
-        }
-        Object obj = path.get (0);
-
-        if (obj instanceof String) {
-            Iterator iter;
-            // Iterate through the property and see if any of the elements
-            // are Properties that match the name.  
-            String name = (String) obj;
-            if (trace) {
-                System.out.println ("Looking for subproperty " + name + 
-                    " arity= " + arity.toString ());
-            }
-            if (arity.equals (PropertyArity.SCALAR)) {
-                // There's just one shot at matching a scalar.
-                Property p = (Property) property.getValue ();
-                if (p.getName().equals (name)) {
-                    return locateSubProperty (p, cdr, trace);
-                }
-                else {
-                    return null;
-                }
-            }
-            else if (arity.equals (PropertyArity.ARRAY)) {
-                // We know it's an array of Properties, which saves much
-                // hair-tearing.
-                Property[] parray = (Property []) val;
-                for (int i = 0; i < parray.length; i++) {
-                    Property p = parray[i];
-                    if (p.getName ().equals (name)) {
-                        return locateSubProperty (p, cdr, trace);
-                    }
-                }
-                return null;
-            }
-            else if (arity.equals (PropertyArity.LIST)) {
-                iter = ((List) val).listIterator ();
-                return getIteratedSubProperty (iter, name, cdr, trace);
-            }
-            else if (arity.equals (PropertyArity.SET)) {
-                iter = ((Set) val).iterator ();
-                return getIteratedSubProperty (iter, name, cdr, trace);
-            }
-            else if (arity.equals (PropertyArity.MAP)) {
-                iter = ((Map) val).values().iterator();
-                return getIteratedSubProperty (iter, name, cdr, trace);
-            }
-            else {
-                // Should never happen, but keep compiler happy
-                //System.out.println ("Unknown arity");
-                return null;
-            }
-        }
-        else if (obj instanceof Integer) {
-            int idx = ((Integer) obj).intValue();
-            //System.out.println ("Property index = " + idx + ", arity= " + arity.toString ());
-            if (arity.equals (PropertyArity.LIST)) {
-                List propList = (List) val;
-                return locateSubProperty 
-                    ((Property) propList.get (idx), cdr, trace);
-            }
-            else if (arity.equals (PropertyArity.ARRAY)) {
-                Property[] propArr = (Property []) val;
-                return locateSubProperty (propArr[idx], cdr, trace);
-            }
-            else {
-                // Other arities are not indexable
-                return null;
-            }
-        }
-        else if (obj instanceof PropertyKey) {
-            // This is applicable only to a Map.
-            if (arity != PropertyArity.MAP) {
-                return null;
-            }
-            return null;   // I'm not sure this case is even meaningful
-        }
-        else {
-            // We should never get here
-            return null;
-        }
-    }
-    
-    /* Walk through an Iterator, whose elements are Properties,
-     * and return the subproperty by <code>path</code> of the first element
-     * whose name matches <code>name</code>.
-     */
-    private Property getIteratedSubProperty (Iterator iter, 
-                    String name, 
-                    List path,
-                    boolean trace)
-    {
-        while (iter.hasNext ()) {
-            Property p = (Property) iter.next ();
-            if (p.getName ().equals (name)) {
-                return locateSubProperty (p, path, trace);
-            }
-        }
-        return null;
-    }
-    
-    
-        
-    private class PropertyKey
-    {
-        public Object key;
-        
-        public PropertyKey (Object obj)
-        {
-            key = obj;
-        }
-    }
-}

jhove/classes/edu/harvard/hul/ois/jhove/PropertyType.java

@@ -1,110 +0,0 @@
-/**********************************************************************
- * Jhove - JSTOR/Harvard Object Validation Environment
- * Copyright 2003-2009 by JSTOR and the President and Fellows of Harvard College
- **********************************************************************/
-
-package edu.harvard.hul.ois.jhove;
-
-
-/**
- *  This class defines enumerated types for an Property of 
- *  some given content. 
- *  Applications will not create or modify PropertyTypes, but will
- *  use one of the predefined PropertyType instances 
- *  BOOLEAN, BYTE, CHARACTER, DATE, DOUBLE, FLOAT, INTEGER,
- *  LONG, OBJECT, PROPERTY, SHORT, STRING, RATIONAL, or
- *  NISOIMAGEMETADATA.
- *
- *  @see Property
- */
-public final class PropertyType
-    extends EnumerationType
-{
-    /**
-     *  Property type for a <code>Boolean</code> object, or a
-     *  <code>boolean</code> if the Arity is Array.
-     */
-    public static final PropertyType BOOLEAN = new PropertyType ("Boolean");
-    /**
-     *  Property type for a <code>Byte</code> object, or a <code>byte</code>
-     *  if the Arity is Array.
-     */
-    public static final PropertyType BYTE = new PropertyType ("Byte");
-    /**
-     *  Property type for a <code>Character</code> object, or a
-     *  <code>char</code> if the Arity is Array.
-     */
-    public static final PropertyType CHARACTER = new PropertyType("Character");
-    /**
-     *  Property type for a <code>Date</code> object.
-     */
-    public static final PropertyType DATE = new PropertyType ("Date");
-    /**
-     *  Property type for a <code>Double</code> object, or 
-     *a <code>double</code> if the Arity is Array.
-     */
-    public static final PropertyType DOUBLE = new PropertyType ("Double");
-    /**
-     *  Property type for a <code>Float</code> object, or a
-     *  <code>float</code> if the Arity is Array.
-     */
-    public static final PropertyType FLOAT = new PropertyType ("Float");
-    /**
-     *  Property type for an <code>Integer</code> object, or an
-     *  <code>integer</code> if the Arity is Array.
-     */
-    public static final PropertyType INTEGER = new PropertyType ("Integer");
-    /**
-     *  Property type for a <code>Long</code> object, or a
-     *  <code>long</code> if the Arity is Array.
-     */
-    public static final PropertyType LONG = new PropertyType ("Long");
-    /**
-     *  Property type for an <code>Object</code>.
-     */
-    public static final PropertyType OBJECT = new PropertyType ("Object");
-    /**
-     *  Property type for an <code>AESAudioMetadata</code>.
-     */
-    public static final PropertyType AESAUDIOMETADATA =
-	new PropertyType ("AESAudioMetadata");
-    /**
-     *  Property type for a <code>NisoImageMetadata</code>.
-     */
-    public static final PropertyType NISOIMAGEMETADATA =
-    new PropertyType ("NISOImageMetadata");
-    /**
-     *  Property type for a <code>TextMDMetadata</code>.
-     */
-    public static final PropertyType TEXTMDMETADATA =
-    new PropertyType ("TextMDMetadata");
-    /**
-     *  Property type for a <code>Property</code> object.
-     */
-    public static final PropertyType PROPERTY = new PropertyType ("Property");
-    /**
-     *  Property type for a <code>Short</code> object, or a
-     *  <code>short</code> if the Arity is Array.
-     */
-    public static final PropertyType SHORT = new PropertyType ("Short");
-    /**
-     *  Property type for a <code>String</code> object.
-     */
-    public static final PropertyType STRING = new PropertyType ("String");
-    /**
-     *  Property type for a <code>Rational</code> object.
-     */
-    public static final PropertyType RATIONAL = new PropertyType ("Rational");
-
-    /******************************************************************
-     * CLASS CONSTRUCTOR.
-     ******************************************************************/
-
-    /** 
-     *  Applications will never create PropertyTypes directly.
-     **/
-    private PropertyType (String value)
-    {
-	super (value);
-    }
-}

jhove/classes/edu/harvard/hul/ois/jhove/RAFInputStream.java

@@ -1,261 +0,0 @@
-/**********************************************************************
- * Jhove - JSTOR/Harvard Object Validation Environment
- * Copyright 2004 by JSTOR and the President and Fellows of Harvard College
- **********************************************************************/
-
-package edu.harvard.hul.ois.jhove;
-
-import java.io.*;
-
-/**
- * An InputStream layered on top of a RandomAccessFile.
- * This is useful for a Module which has requirements that
- * force it to use a RandomAccessFile, but is usually
- * accessed sequentially.
- * 
- * An RAFInputStream maintains its own position information
- * in the file, so multiple RAFInputStreams in the same file
- * will work without interference.  However, this class is
- * not thread-safe.
- * 
- * @author Gary McGath
- *
- */
-public class RAFInputStream extends InputStream {
-
-    /* The file on which the stream is based */
-    private RandomAccessFile _raf;
-    
-    /* Size of fileBuf */
-    private int fileBufSize;
-    
-    /* Buffer for reading from the file */
-    private byte[] fileBuf;
-    
-    /* Offset for reading next byte from filebuf */
-    private int fileBufPos;
-    
-    /* Number of valid bytes in fileBuf */
-    private int fileBufBytes;
-    
-    /* Position in file for next read from RandomAccessFile */
-    private long fileOffset;
-    
-    /* EOF flag */
-    boolean eof;
-    
-    /**
-     *  Constructor with default buffer size.
-     *  The stream starts at the current position of the
-     *  RandomAccessFile.
-     * 
-     *  @param   raf   The file on which the
-     *                 stream is to be based.
-     */
-    public RAFInputStream(RandomAccessFile raf) {
-        super();
-        _raf = raf;
-        fileBufSize = 65536;  // pick a size, any size
-        init ();
-    }
-
-
-    /**
-     *  Constructor with buffer size.
-     *  The stream starts at the current position of the
-     *  RandomAccessFile.
-     * 
-     *  @param   raf         The file on which the
-     *                       stream is to be based.
-     * 
-     *  @param   bufferSize  The buffer size to be used.
-     *                       If less than or equal to 0, the
-     *                       default buffer size is used.
-     */
-    public RAFInputStream(RandomAccessFile raf, int bufferSize) {
-        super();
-        _raf = raf;
-        fileBufSize = (bufferSize <= 0 ? 65536 : bufferSize);
-        init ();
-    }
-
-    private void init ()
-    {
-        fileBufBytes = 0;
-        fileBufPos = 0;
-        fileBuf = new byte[fileBufSize];
-        try {
-            fileOffset = _raf.getFilePointer ();
-        }
-        catch (IOException e) {}
-        eof = false;
-        
-    }
-    /**
-     *  Reads a single byte from the file.
-     */
-    public int read() throws IOException {
-        if (eof) {
-            return -1;
-        }
-        if (fileBufPos >= fileBufBytes) {
-            // Need to read another bufferful
-            _raf.seek (fileOffset);
-            fileBufBytes = _raf.read (fileBuf);
-            fileBufPos = 0;
-            if (fileBufBytes <= 0) {
-                // No more in file
-                eof = true;
-                return -1;
-            }
-            else {
-                fileOffset += fileBufBytes;
-            }
-        }
-        return ((int) fileBuf[fileBufPos++] & 0XFF);
-    }
-    
-    /**
-     * Reads some number of bytes from the input stream and
-     * stores them into the buffer array b. The number of
-     * bytes actually read is returned as an integer.
-     */
-    public int read (byte[] b) throws IOException
-    {
-        int bytesToRead = b.length;
-        int bytesRead = 0;
-        for (;;) {
-            // See how many bytes are available in fileBuf.
-            int fbAvail = fileBufBytes - fileBufPos;
-            if (fbAvail <= 0) {
-                // Need to read another bufferful
-                _raf.seek (fileOffset);
-                fileBufBytes = _raf.read (fileBuf);
-                fileBufPos = 0;
-                if (fileBufBytes <= 0) {
-                    // No more in file -- return what we have
-                    eof = true;
-                    return bytesRead;
-                }
-                fbAvail = fileBufBytes;
-                fileOffset += fileBufBytes;
-            }
-            if (fbAvail > bytesToRead) {
-                // We have more than enough bytes.
-                fbAvail = bytesToRead;
-            }
-            for (int i = 0; i < fbAvail; i++) {
-                b[bytesRead++] = fileBuf[fileBufPos++];
-                bytesToRead--;
-            }
-            if (bytesToRead == 0) {
-                return bytesRead;
-            }
-        }
-    }
-
-    /**
-     * Reads up to len bytes of data from the input stream 
-     * into an array of bytes. An attempt is made to read as 
-     * many as len bytes, but a smaller number may be read, 
-     * possibly zero. The number of bytes actually read is
-     * returned as an integer.
-     * 
-     */
-    public int read(byte[] b, int off, int len) throws IOException 
-    {
-        int bytesToRead = len;
-        int bytesRead = 0;
-        for (;;) {
-            // See how many bytes are available in fileBuf.
-            int fbAvail = fileBufBytes - fileBufPos;
-            if (fbAvail <= 0) {
-                // Need to read another bufferful
-                _raf.seek (fileOffset);
-                fileBufBytes = _raf.read (fileBuf);
-                fileBufPos = 0;
-                if (fileBufBytes <= 0) {
-                    // No more in file -- return what we have
-                    eof = true;
-                    return bytesRead;
-                }
-                fbAvail = fileBufBytes;
-                fileOffset += fileBufBytes;
-            }
-            if (fbAvail > bytesToRead) {
-                // We have more than enough bytes.
-                fbAvail = bytesToRead;
-            }
-            for (int i = 0; i < fbAvail; i++) {
-                b[off + bytesRead++] = fileBuf[fileBufPos++];
-                bytesToRead--;
-            }
-            if (bytesToRead == 0) {
-                return bytesRead;
-            }
-        }
-    }
-
-
-    /** Skips some number of bytes.
-     * 
-     *  @return  The number of bytes actually skipped.
-     */
-    public long skip (long n) throws IOException 
-    {
-        // If the range of the skip lies
-        // within the current buffer, we just adjust
-        // the buffer offset.
-        int bytesLeft = fileBufBytes - fileBufPos;
-        if (bytesLeft > n) {
-            fileBufPos += (int) n;
-        }
-        else {
-            // doesn't fit within the buffer.            
-            // Set up to seek to the new position.
-            //long curPos = _raf.getFilePointer ();
-            if (fileOffset + n - bytesLeft  > _raf.length ()) {
-                fileOffset = _raf.length ();
-            }
-            //seek (curPos + n - bytesLeft);
-            else {
-                fileOffset += n - bytesLeft;
-            }
-            fileBufBytes = 0;   // Invalidate current buffer
-        }
-        return n;
-    }
-    
-    
-    
-    /**
-     *  Returns the RandomAccessFile object.
-     */
-    public RandomAccessFile getRAF ()
-    {
-        return _raf;
-    }
-
-
-    /**  Positions the stream to a different point in the file.
-     *   This invalidates the buffer.
-     */
-    public void seek (long offset) throws IOException
-    {
-        _raf.seek (offset);
-        fileBufBytes = 0;
-        fileBufPos = 0;
-        eof = false;
-    }
-    
-    /**  Returns the current position in the file.  
-     *   What is reported is the position of the byte
-     *   in the file which was last extracted from
-     *   the buffer.
-     */
-    public long getFilePos () throws IOException
-    {
-        return _raf.getFilePointer() -
-                (fileBufBytes - fileBufPos);
-    }
-}

jhove/classes/edu/harvard/hul/ois/jhove/RFC1766Lang.java

@@ -1,92 +0,0 @@
-
-/**********************************************************************
- * Jhove - JSTOR/Harvard Object Validation Environment
- * Copyright 2003 by JSTOR and the President and Fellows of Harvard College
- **********************************************************************/
-
-
-package edu.harvard.hul.ois.jhove;
-
-
-/**
- *  Class encapsulating RFC-1766 language codes.
- */
-public final class RFC1766Lang 
-{
-
-    String _langCode;
-
-    /**
-     * Constructor. 
-     *
-     * @param   str	The ASCII string for the language code.
-     */
-    public RFC1766Lang (String str) 
-    {
-	_langCode = str;
-    }
-
-    /**
-     *  Returns the language code string. 
-     */
-    public String getLangCode () 
-    {
-	return _langCode;
-    }
-
-    /**
-     *  Returns <code>true</code> if the language code
-     *  string is syntactically compliant.
-     *  The primary tag must be either a two-letter code,
-     *  the letter i, or the letter x (case insensitive);
-     *  no checking is done against registry lists.
-     */
-    public boolean isSyntaxCorrect ()
-    {
-	int i;
-	if (_langCode == null) {
-	    return false;
-	}
-	char[] chrs = _langCode.toLowerCase().toCharArray();
-	char firstChar = '\0';
-
-	int ntags = 0;
-	int taglength = 0;
-	for (i = 0; i < chrs.length; i++) {
-	    char ch = chrs[i];
-	    if (i == 0) {
-		firstChar = ch;
-	    }
-	    if (!Character.isLetter (ch) && ch != '-') {
-		return false;
-	    }
-	    if (ch == '-') {
-		taglength = 0;
-
-		// If this is the primary tag, do some checks
-		if (ntags++ == 0) {
-		    if (taglength == 1) {
-			if (firstChar != 'i' && firstChar != 'x') {
-			    return false;
-			}
-			else if (taglength != 2) {
-			    return false;
-			}
-		    }
-		}
-	    }
-	    else {
-		taglength++;
-		if (taglength > 8) {
-		    return false;
-		}
-	    }
-	}
-	// A dangling hyphen at the end isn't allowed.
-	if (taglength == 0) {
-	    return false;
-	}
-
-	return true;
-    }
-}

jhove/classes/edu/harvard/hul/ois/jhove/Rational.java

@@ -1,100 +0,0 @@
-/**********************************************************************
- * Jhove - JSTOR/Harvard Object Validation Environment
- * Copyright 2003 by JSTOR and the President and Fellows of Harvard College
- **********************************************************************/
-
-package edu.harvard.hul.ois.jhove;
-
-/**
- *  This class encapsulates a number which is defined as the ratio
- *  of two 32-bit unsigned integers, in accordance with the TIFF
- *  specification.  
- */
-public class Rational
-{
-    /******************************************************************
-     * PRIVATE INSTANCE FIELDS.
-     ******************************************************************/
-
-    /** Numerator of ratio. */
-    private long _numerator;
-    /** Denominator of ratio. */
-    private long _denominator;
-
-    /******************************************************************
-     * CLASS CONSTRUCTOR.
-     ******************************************************************/
-	
-    /**
-     *  The arguments to this constructor are long in order to
-     *  represent all possible 32-bit unsigned integers.  Parameters
-     *  greater than 2 ^ 32 - 1 are not meaningful. 
-     *  @param numerator     numerator of the Rational value
-     *  @param denominator   denominator of the Rational value
-     */
-    public Rational (long numerator, long denominator)
-    {
-	_numerator = numerator;
-	_denominator = denominator;
-    }
-    
-    /**
-     *  The arguments to the int constructor are treated as
-     *  32-bit unsigned integers.   
-     *  @param numerator     numerator of the Rational value
-     *  @param denominator   denominator of the Rational value
-     */
-    public Rational (int numerator, int denominator)
-    {
-	_numerator = (long) numerator & 0XFFFFFFFF;
-	_denominator = (long) denominator & 0XFFFFFFFF;
-    }
-
-    /******************************************************************
-     * PUBLIC INSTANCE METHODS.
-     ******************************************************************/
-	
-    /**
-     *  Returns the Numerator property.
-     */
-    public long getNumerator ()
-    {
-	return _numerator;
-    }
-	
-    /**
-     *  Returns the Denominator property.
-     */
-    public long getDenominator()
-    {
-	return _denominator;
-    }
-
-    /**
-     *  Converts to a floating-point value (numerator/denominator).
-     *  May throw an ArithmeticException.
-     **/
-    public double toDouble ()
-    {
-	return ((double) _numerator / (double) _denominator);
-    }
-
-    /**
-     *  Converts to a long value (numerator/denominator).
-     *  May throw an ArithmeticException.
-     **/
-    public long toLong ()
-    {
-	return (long) ((double) _numerator / (double) _denominator);
-    }
-
-    /**
-     *	Represents the Rational as a String in the form of 
-     *  "numerator/denominator".
-     */	
-    public String toString ()
-    {
-	return Long.toString (_numerator) + "/" +
-	       Long.toString (_denominator);
-    }
-}

jhove/classes/edu/harvard/hul/ois/jhove/RepInfo.java

@@ -1,599 +0,0 @@
-/**********************************************************************
- * Jhove - JSTOR/Harvard Object Validation Environment
- * Copyright 2003-2005 by JSTOR and the President and Fellows of Harvard College
- **********************************************************************/
-
-package edu.harvard.hul.ois.jhove;
-
-import java.util.*;
-
-/**
- *  This class encapsulates representation information, as defined 
- *  by ISO/IEC 14721, about a content stream.
- *
- *  @see <a href="http://wwwclassic.ccsds.org/documents/pdf/CCSDS-650.0-B-1.pdf">ISO/IEC
- *       14721 (PDF)</a>
- */
-public class RepInfo implements Cloneable
-{
-    /******************************************************************
-     * PRIVATE INSTANCE FIELDS.
-     ******************************************************************/
-
-    /** List of checksums. */
-    private List<Checksum> _checksum;
-
-    /** Consistency flag. */
-    private boolean _consistent;
-
-    /** Validity flag.  A ternary variable which can have a value
-     *  of TRUE, FALSE, or UNDETERMINED. */
-    private int _valid;
-    
-    /** Values for _valid */
-    public final static int
-        TRUE = 1,
-        FALSE = 0,
-        UNDETERMINED = -1;
-
-    /** Creation date. */
-    private Date _created;
-
-    /** External representation information. */
-    private RepInfo _external;
-
-    /** Format identifier. */
-    private String _format;
-
-    /** Modification date. */
-    private Date _lastModified;
-
-    /** List of diagnostic and informative messages. */
-    private List<Message> _message;
-
-    /** MIME media type. */
-    private String _mimeType;
-
-    /** The module used to populate this representation information. */
-    private Module _module;
-
-    /** List of conforming format profiles. */
-    private List<String> _profile;
-    
-    /** List of modules for which signature matches. */
-    private List<String> _sigMatch;
-
-    /** Associative map of module-specific representation information. */
-    private Map<String, Property> _property;
-
-    /** Object size. */
-    private long _size;
-
-    /** Object file pathname or URI. */
-    private String _uri;
-    
-    /** Flag indicating _uri is a URL if true. */
-    private boolean _urlFlag;
-
-    /** Well-formed flag. A ternary variable which can have a value
-     *  of TRUE, FALSE, or UNDETERMINED. */
-    private int _wellFormed;
-
-    /** Version of format which applies. */
-    private String _version;
-
-    /** Note. */
-    private String _note;
-
-    /******************************************************************
-     * CLASS CONSTRUCTOR.
-     ******************************************************************/
-
-    /**
-     *  Creates a RepInfo with a URI reference
-     *
-     *  @param uri   Object file pathname or URI
-     */
-    public RepInfo (String uri)
-    {
-	init (uri);
-    }
-
-    /**
-     *  Creates a RepInfo with a URI reference and an external RepInfo.
-     * 
-     *  By default, urlFlag is <code>false</code>.
-     *
-     *  @param uri       Object file pathname or URI
-     *  @param external  External representation information
-     */
-    public RepInfo (String uri, RepInfo external)
-    {
-	init (uri);
-	_external = external;
-    }
-
-    private void init (String uri)
-    {
-        _uri = uri;
-        _size = -1;
-        _wellFormed = TRUE;
-        _consistent = true;
-        _urlFlag = false;
-        _valid = TRUE;
-        
-        _checksum = new ArrayList<Checksum> ();
-        _message  = new ArrayList<Message> ();
-        _profile  = new ArrayList<String> ();
-        _property = new TreeMap<String, Property> ();
-        _sigMatch = new ArrayList<String> ();
-    }
-
-    /******************************************************************
-     * PUBLIC INSTANCE METHODS.
-     ******************************************************************/
-
-    /**
-     *  Clones the RepInfo one level deep, making fresh copies
-     *  of the checksum, message, profile, signature match, 
-     *  and property fields.
-     *  The external RepInfo (if any) is not cloned, but
-     *  is attached directly to the clone.
-     */
-    public Object clone () 
-    {
-	RepInfo newri;
-	try {
-	    newri = (RepInfo) super.clone ();
-	}
-	catch (CloneNotSupportedException e) {
-	    return null;   // should never happen
-	}
-
-        newri._checksum = new ArrayList<Checksum> (_checksum);
-        newri._message = new ArrayList<Message>(_message);
-        newri._profile = new ArrayList<String> (_profile);
-        newri._sigMatch = new ArrayList<String> (_sigMatch);
-        newri._property = new TreeMap<String, Property> (_property);
-        
-        return (Object) newri;
-    }
-
-    /**
-     *  Copies all the information out of the parameter object.
-     *  This is a "shallow" copy; it is assumed that the parameter
-     *  object is a temporary one that will not be further modified.
-     */
-    public void copy (RepInfo info)
-    {
-        _checksum = info._checksum;
-        _consistent = info._consistent;
-        _created = info._created;
-        _external = info._external;
-        _format = info._format;
-        _lastModified = info._lastModified;
-        _message = info._message;
-        _mimeType = info._mimeType;
-        _profile = info._profile;
-        _property = info._property;
-        _size = info._size;
-        _uri = info._uri;
-        _urlFlag = info._urlFlag;
-        _wellFormed = info._wellFormed;
-        _valid = info._valid;
-        _version = info._version;
-        _note = info._note;
-        _module = info._module;
-        _sigMatch = info._sigMatch;
-    }
-
-    /******************************************************************
-     *
-     * Accessor methods.
-     ******************************************************************/
-
-    /**
-     *   Returns this object's list of Checksums
-     */
-    public List<Checksum> getChecksum ()
-    {
-        return _checksum;
-    }
-
-    /**
-     *   Returns the creation date stored in this object. A creation
-     *   date is not automatically generated, but must be explicitly
-     *   stored.
-     **/
-    public Date getCreated ()
-    {
-        return _created;
-    }
-
-    /**
-     *   Return the format identifier
-     */
-    public String getFormat ()
-    {
-        return _format;
-    }
-
-    /**
-     *   Returns the last modified date stored in this object. A
-     *   date is not automatically generated, but must be explicitly
-     *   stored.
-     **/
-    public Date getLastModified ()
-    {
-        return _lastModified;
-    }
-
-    /**
-     *  Returns the message list stored in this object
-     */
-    public List<Message> getMessage ()
-    {
-        return _message;
-    }
-
-    /**
-     *  Returns the MIME type string stored in this object
-     */
-    public String getMimeType ()
-    {
-        return _mimeType;
-    }
-
-    /**
-     * Return the module.
-     */
-    public Module getModule ()
-    {
-        return _module;
-    }
-
-    /**
-     *  Returns the list of profiles (Strings) stored in this object
-     */
-    public List<String> getProfile ()
-    {
-        return _profile;
-    }
-
-    /**
-     *  Returns the Property map stored in this object.  The
-     *  Property map contains key-value pairs whose key is a 
-     *  <code>String</code> and whose value is a <code>Property</code>.
-     */
-    public Map<String, Property> getProperty ()
-    {
-        return _property;
-    }
-
-    /**
-     *  Returns a named Property from the Property map
-     *
-     *  @param name  The name of the Property.
-     */
-    public Property getProperty (String name)
-    {
-        Property property = null;
-        if (_property.size () > 0) {
-            property = (Property) _property.get (name);
-        }
-
-	return property;
-    }
-
-    /**
-     *  Returns the size property stored in this object.
-     */
-    public long getSize ()
-    {
-        return _size;
-    }
-
-    /**
-     *  Returns the URI property stored in this object.
-     */
-    public String getUri ()
-    {
-        return _uri;
-    }
-
-    /**
-     *  Returns a flag which, if <code>true</code>, indicates
-     *  the object is a URL.
-     */
-    public boolean getURLFlag ()
-    {
-        return _urlFlag;
-    }
-
-    /**
-     *  Returns the value of the consistency flag.
-     */
-    public boolean isConsistent ()
-    {
-        return _consistent;
-    }
-
-    /**
-     *  Returns the value of the well-formed flag.
-     *  Can return TRUE, FALSE, or UNDETERMINED.
-     */
-    public int getWellFormed ()
-    {
-        return _wellFormed;
-    }
-
-    /**
-     *  Returns the value of the validity flag.
-     *  Can return TRUE, FALSE, or UNDETERMINED.
-     */
-    public int getValid ()
-    {
-        return _valid;
-    }
-
-    /**
-     *  Returns the version property stored in this object
-     */
-    public String getVersion ()
-    {
-	return _version;
-    }
-
-    /**
-     *  Returns the note property stored in this object
-     */
-    public String getNote ()
-    {
-	return _note;
-    }
-    
-    /**
-     *  Returns the list of matching signatures.  
-     *  JhoveBase will make this value persistent across
-     *  module invocations for a given document, so the list
-     *  returned will reflect all modules that have looked
-     *  at the document so far.
-     */
-    public List<String> getSigMatch ()
-    {
-        return _sigMatch;
-    }
-
-    /**
-     * Return property by name, regardless of its position in the
-     * property hierarchy.
-     * @param name Property name
-     * @return Named property (or null)
-     */
-    public Property getByName (String name)
-    {
-        Property prop = null;
-
-        Collection<Property> coll = _property.values ();
-        Iterator<Property> iter = coll.iterator ();
-        while (iter.hasNext ()) {
-            prop = (Property) iter.next ();
-            if ((prop = prop.getByName (name)) != null) {
-                break;
-            }
-        }
-
-        return prop;
-    }
-
-    /******************************************************************
-     * Mutator methods.
-     ******************************************************************/
-
-    /**
-     *  Append a Checksum object to the checksum list.
-     */
-    public void setChecksum (Checksum checksum)
-    {
-        _checksum.add (checksum);
-    }
-
-    /**
-     *  Set the value of the consistency flag
-     */
-    public void setConsistent (boolean consistent)
-    {
-	_consistent = consistent;
-    }
-
-    /**
-     *  Set the creation date
-     */
-    public void setCreated (Date created)
-    {
-	_created = created;
-    }
-
-    /**
-     *  Set the format identifier
-     */
-    public void setFormat (String format)
-    {
-	_format = format;
-    }
-
-    /**
-     *  Set the last modified date
-     */
-    public void setLastModified (Date lastModified)
-    {
-        _lastModified = lastModified;
-    }
-
-    /**
-     *  Append a Message object to the message list
-     */
-    public void setMessage (Message message)
-    {
-        _message.add (message);
-    }
-
-    /**
-     *  Set the MIME type string
-     */
-    public void setMimeType (String mimeType)
-    {
-        _mimeType = mimeType;
-    }
-
-    /**
-     * Add the module.
-     */
-    public void setModule (Module module)
-    {
-        _module = module;
-    }
-
-    /**
-     *  Append a profile String to the profile list
-     */
-    public void setProfile (String profile)
-    {
-        _profile.add (profile);
-    }
-
-    /**
-     *   Add a Property to the property map.  The name of the Property
-     *   becomes its key in the map.
-     */
-    public void setProperty (Property property)
-    {
-        _property.put (property.getName (), property);
-    }
-
-    /**
-     *  Set the size property
-     */
-    public void setSize (long size)
-    {
-        _size = size;
-    }
-    
-    /**
-     *  Set the flag to indicate whether this is a URL (true)
-     *  or a file (false)
-     */
-    public void setURLFlag (boolean flag)
-    {
-        _urlFlag = flag;
-    }
-
-    /**
-     *  Set the well-formed flag
-     * 
-     *  @param wellFormed    Boolean argument that maps to
-     *                  an integer value:
-     *                  true maps to TRUE, and false to FALSE.
-     */
-    public void setWellFormed (boolean wellFormed) 
-    {
-        _wellFormed = wellFormed ? TRUE : FALSE;
-        if (!wellFormed) {
-            _consistent = false;
-            _valid = FALSE;
-        }
-    }
-
-    /**
-     *  Set the wellFormed flag.
-     *  Setting wellFormed to false forces the consistent and
-     *  valid flags to be false as well.
-     */
-    public void setWellFormed (int wellFormed)
-    {
-        _wellFormed = wellFormed;
-	if (wellFormed == FALSE) {
-	    _consistent = false;
-	    _valid = FALSE;
-	}
-        if (wellFormed == UNDETERMINED) {
-            _valid = UNDETERMINED;
-        }
-    }
-
-    /**
-     *  Set the validity flag
-     * 
-     *  @param valid    Boolean argument that maps to
-     *                  an integer value:
-     *                  true maps to TRUE, and false to FALSE.
-     */
-    public void setValid (boolean valid) 
-    {
-        _valid = valid ? TRUE : FALSE;
-    }
-
-    /**
-     *  Set the validity flag
-     * 
-     *  @param valid    Permitted values are TRUE, FALSE, AND
-     *                  UNDETERMINED.  The effect of using 
-     *                  other values is undefined.
-     */
-    public void setValid (int valid) 
-    {
-        _valid = valid;
-    }
-
-    /**
-     *  Set the version string
-     */
-    public void setVersion (String version) 
-    {
-        _version = version;
-    }
-
-    /**
-     *  Set the note string
-     */
-    public void setNote (String note)
-    {
-	_note = note;
-    }
-    
-    /** Adds the name of a module, signifying that the document
-     *  signature matched the module's requirements.
-     *  JhoveBase will make this value persistent across
-     *  module invocations for a given document.
-     */
-    public void setSigMatch (String modname)
-    {
-        _sigMatch.add (modname);
-    }
-    
-    /** Adds a list of module names, signifying that the document
-     *  signature matched the module's requirements.
-     *  Any previous list is lost.
-     *  JhoveBase will make this value persistent across
-     *  module invocations for a given document.
-     */
-    public void setSigMatch (List<String> modnames)
-    {
-        _sigMatch = modnames;
-    }
-
-    /******************************************************************
-     * Serialization methods.
-     ******************************************************************/
-
-    /**
-     *  Output the information in this object.  The format and 
-     *  destination of the output are determined by the
-     *  OutputHandler.
-     */
-    public void show (OutputHandler handler)
-    {
-	handler.analyze (this);
-	handler.show    (this);
-    }
-}

jhove/classes/edu/harvard/hul/ois/jhove/Signature.java

@@ -1,157 +0,0 @@
-/**********************************************************************
- * Jhove - JSTOR/Harvard Object Validation Environment
- * Copyright 2003 by JSTOR and the President and Fellows of Harvard College
- **********************************************************************/
-
-package edu.harvard.hul.ois.jhove;
-
-/**
- *  This class encapsulates information about format signatures,
- *   both internal and external.
- *   The value of a Signature may be either a String or a byte array
- *   (stored as an int array to avoid signed byte problems).
- */
-public abstract class Signature
-{
-    private int[] _value;
-    private String _stringValue;
-    private SignatureType _type;
-    private SignatureUseType _use;
-    private String _note;
-
-    /**
-     *  A Signature cannot be created directly; this constructor
-     *  can be called as the superclass constructor from a subclass.
-     *  This constructor uses a String value.
-     */
-    protected Signature (String value, SignatureType type,
-             SignatureUseType use)
-    {
-    this (new int[value.length ()], type, use);
-    int len = value.length ();
-    _stringValue = value;
-    for (int i = 0; i < len; i++) {
-        _value[i] = value.charAt(i);
-    }
-    }
-
-    /**
-     *  A Signature cannot be created directly; this constructor
-     *  can be called as the superclass constructor from a subclass.
-     *  This constructor uses a byte array (stored as an int array) value.
-     */
-    protected Signature (int[] value, SignatureType type,
-             SignatureUseType use)
-    {
-    _value = value;
-    _type  = type;
-    _use   = use;
-    _stringValue = null;
-    }
-
-    /**
-     *  A Signature cannot be created directly; this constructor
-     *  can be called as the superclass constructor from a subclass.
-     *  This constructor uses a String value and allows specification
-     *  of a note.
-     */
-    protected Signature (String value, SignatureType type,
-             SignatureUseType use,
-             String note)
-    {
-    this (new int[value.length ()], type, use, note);
-    int len = value.length ();
-    for (int i = 0; i < len; i++) {
-        _value[i] = value.charAt(i);
-    }
-    _stringValue = value;
-    }
-
-    /**
-     *  A Signature cannot be created directly; this constructor
-     *  can be called as the superclass constructor from a subclass.
-     *  This constructor uses a byte array (stored as an int array) value
-     *  and allows specification of a note.
-     */
-    protected Signature (int[] value, SignatureType type,
-             SignatureUseType use,
-             String note)
-    {
-    this (value, type, use);
-    _note = note;
-    }
-
-    /**
-     *  Returns the type of this Signature
-     */
-    public SignatureType getType ()
-    {
-    return _type;
-    }
-
-    /**
-     *  Returns the use requirement for this Signature
-     */
-    public SignatureUseType getUse ()
-    {
-    return _use;
-    }
-
-    /**
-     *  Returns the byte array value for this Signature.
-     *  If this Signature was constructed from a String, it
-     *  returns the characters of the String as the bytes of
-     *  the array.
-     */
-    public int[] getValue ()
-    {
-    return _value;
-    }
-
-    /**
-     *  Returns the note specified for this Signature, or null
-     *  if no note was specified.
-     */
-    public String getNote ()
-    {
-    return _note;
-    }
-
-    /**
-     *  Returns true if this Signature's value was provided as a
-     *  String, false if as an array.
-     */
-    public boolean isStringValue ()
-    {
-    return (_stringValue != null);
-    }
-
-    /**
-     *  Returns the string value of this Signature.  Returns null
-     *  if this Signature was constructed with an array.
-     */
-    public String getValueString ()
-    {
-    return _stringValue;
-    }
-
-    /**
-     *  Returns the value of this Signature as a hexadecimal string.
-     *  The length of the string is twice the length of the array
-     *  or string from which this Signature was created, and all
-     *  alphabetic characters are lower case.  
-     */
-    public String getValueHexString ()
-    {
-    StringBuffer valBuf = new StringBuffer ("0x");
-    for (int i = 0; i < _value.length; i++) {
-        /* Make each byte exactly two digits */
-        int b = _value[i];
-        if (b < 16) {
-        valBuf.append ('0');
-        }
-        valBuf.append (Integer.toHexString (b));
-    }
-    return valBuf.toString ();
-    }
-}

jhove/classes/edu/harvard/hul/ois/jhove/SignatureType.java

@@ -1,54 +0,0 @@
-/**********************************************************************
- * Jhove - JSTOR/Harvard Object Validation Environment
- * Copyright 2003 by JSTOR and the President and Fellows of Harvard College
- **********************************************************************/
-
-package edu.harvard.hul.ois.jhove;
-
-
-/**
- *  This class defines enumerated types for a Signature in a module. 
- *  Applications will not create or modify SignatureTypes, but will
- *  use one of the predefined SignatureType instances 
- *  EXTENSION, FILETYPE, or MAGIC.
- *
- *  @see Signature
- */
-public final class SignatureType
-    extends EnumerationType
-{
-    /******************************************************************
-     * PUBLIC STATIC INSTANCES.
-     ******************************************************************/
-
-    /** 
-     *  Signature type for a file extension, i.e., a sequence of
-     *  characters following a period character in a file name.
-     */
-    public static final SignatureType EXTENSION =
-	            new SignatureType ("File extension");
-
-    /** 
-     *  Signature type for a Macintosh OS file type. This applies
-     *  only to Mac OS files, and is always a four-character code.
-     */
-    public static final SignatureType FILETYPE =
-	            new SignatureType ("Mac OS file type");
-    /** 
-     *  Signature type for a "magic number" stored in the file.
-     */
-    public static final SignatureType MAGIC =
-	            new SignatureType ("Magic number");
-
-    /******************************************************************
-     * CLASS CONSTRUCTOR.
-     ******************************************************************/
-
-    /** 
-     *  Applications will never create SignatureTypes directly.
-     **/
-    private SignatureType (String value)
-    {
-	super (value);
-    }
-}

jhove/classes/edu/harvard/hul/ois/jhove/SignatureUseType.java

@@ -1,55 +0,0 @@
-/**********************************************************************
- * Jhove - JSTOR/Harvard Object Validation Environment
- * Copyright 2003 by JSTOR and the President and Fellows of Harvard College
- **********************************************************************/
-
-package edu.harvard.hul.ois.jhove;
-
-
-/**
- *  This class defines enumerated use types for a Signature in a module. 
- *  These give information on whether a signature is required in
- *  valid content.
- *  Applications will not create or modify SignatureUseTypes, but will
- *  use one of the predefined SignatureUseType instances 
- *  MANDATORY, MANDATORY_IF_APPLICABLE, or OPTIONAL.
- *
- *  @see Signature
- */
-public final class SignatureUseType
-    extends EnumerationType
-{
-    /******************************************************************
-     * PRIVATE CLASS FIELDS.
-     ******************************************************************/
-
-    /** 
-     *  Use type for a required signature.
-     */
-    public static final SignatureUseType MANDATORY =
-	            new SignatureUseType ("Mandatory");
-
-
-    /** 
-     *  Use type for a conditionally required signature.
-     */
-    public static final SignatureUseType MANDATORY_IF_APPLICABLE =
-	            new SignatureUseType ("Mandatory if applicable");
-    /**
-     *  Use type for an optional signature.
-     */
-    public static final SignatureUseType OPTIONAL =
-	            new SignatureUseType ("Optional");
-
-    /******************************************************************
-     * CLASS CONSTRUCTOR.
-     ******************************************************************/
-
-    /** 
-     *  Applications will never create SignatureUseTypes directly.
-     **/
-    private SignatureUseType (String value)
-    {
-	super (value);
-    }
-}

jhove/classes/edu/harvard/hul/ois/jhove/TextMDMetadata.java

@@ -1,438 +0,0 @@
-package edu.harvard.hul.ois.jhove;
-
-import java.nio.charset.Charset;
-import java.util.Arrays;
-import java.util.HashMap;
-import java.util.HashSet;
-import java.util.Locale;
-import java.util.Map;
-import java.util.Set;
-
-/**
- * Encapsulation of the textMD metadata for text files.
- * See http://www.loc.gov/standards/textMd for more information.
- *
- * @author Thomas Ledoux
- *
- */
-public class TextMDMetadata {
-	/**
-	 * textMD namespace and version
-	 */
-	public static final String NAMESPACE = "info:lc/xmlns/textMD-v3";
-    public static final String DEFAULT_LOCATION = 
-        "http://www.loc.gov/standards/textMD/textMD-v3.01a.xsd";
-	public static final String VERSION = "3.0";
-	
-	/**
-     *  Uses enumerated values of 'big', 'little', and 'middle' endian. 
-     */
-	public static final String[] BYTE_ORDER = { 
-		"big", "little", "middle" 
-	};
-    public static final int BYTE_ORDER_BIG = 0;
-    public static final int BYTE_ORDER_LITTLE = 1;
-    public static final int BYTE_ORDER_MIDDLE= 2;
-    
-    /**
-     *  Uses enumerated values of 'CR', 'LF' and 'CR/LF' for the idenntification of the linebreak. 
-     */
-	public static final String[] LINEBREAK = { 
-		"CR", "LF", "CR/LF" 
-	};
-    public static final int LINEBREAK_CR = 0;
-    public static final int LINEBREAK_LF = 1;
-    public static final int LINEBREAK_CRLF = 2;
-   
-    /**
-     * Array of textMD charsets unknown by java.nio.charset.Charsets
-     */
-    protected static final String[] UNKNOWN_JAVA_CHARSET =
-            new String[] { 
-                    "ISO-10646-UTF-1", "ISO_646.basic:1983", "INVARIANT", "BS_4730", "NATS-SEFI",
-                    "NATS-SEFI-ADD", "NATS-DANO", "NATS-DANO-ADD", "SEN_850200_B", "SEN_850200_C", "ISO-2022-CN-EXT",
-                    "JIS_C6220-1969-jp", "JIS_C6220-1969-ro", "IT", "PT", "ES", "greek7-old", "latin-greek",
-                    "DIN_66003", "NF_Z_62-010_(1973)", "latin-greek-1", "ISO_5427", "JIS_C6226-1978", "BS_viewdata",
-                    "INIS", "INIS-8", "INIS-cyrillic", "ISO_5427:1981", "ISO_5428:1980", "GB_1988-80", "GB_2312-80",
-                    "NS_4551-1", "NS_4551-2", "NF_Z_62-010", "videotex-suppl", "PT2", "ES2", "MSZ_7795.3", "greek7",
-                    "ASMO_449", "iso-ir-90", "JIS_C6229-1984-a", "JIS_C6229-1984-b", "JIS_C6229-1984-b-add",
-                    "JIS_C6229-1984-hand", "JIS_C6229-1984-hand-add", "JIS_C6229-1984-kana", "ISO_2033-1983",
-                    "ANSI_X3.110-1983", "T.61-7bit", "ECMA-cyrillic", "CSA_Z243.4-1985-1", "CSA_Z243.4-1985-2",
-                    "CSA_Z243.4-1985-gr", "ISO_8859-6-E", "ISO_8859-6-I", "T.101-G2", "ISO_8859-8-E", "ISO_8859-8-I",
-                    "CSN_369103", "JUS_I.B1.002", "ISO_6937-2-add", "IEC_P27-1", "JUS_I.B1.003-serb",
-                    "JUS_I.B1.003-mac", "greek-ccitt", "NC_NC00-10:81", "ISO_6937-2-25", "GOST_19768-74",
-                    "ISO_8859-supp", "ISO_10367-box", "ISO-8859-10", "latin-lap", "DS_2089", "us-dk", "dk-us",
-                    "KSC5636", "ISO-10646-UCS-4", "DEC-MCS", "hp-roman8", "macintosh", "IBM038", "IBM274", "IBM275",
-                    "IBM281", "IBM290", "IBM423", "IBM851", "IBM880", "IBM891", "IBM903", "IBM904", "IBM905",
-                    "EBCDIC-AT-DE", "EBCDIC-AT-DE-A", "EBCDIC-CA-FR", "EBCDIC-DK-NO", "EBCDIC-DK-NO-A", "EBCDIC-FI-SE",
-                    "EBCDIC-FI-SE-A", "EBCDIC-FR", "EBCDIC-IT", "EBCDIC-PT", "EBCDIC-ES", "EBCDIC-ES-A", "EBCDIC-ES-S",
-                    "EBCDIC-UK", "EBCDIC-US", "UNKNOWN-8BIT", "MNEMONIC", "MNEM", "VISCII", "VIQR", "IBM00924",
-                    "UNICODE-1-1", "SCSU", "UTF-7", "CESU-8", "UNICODE-1-1-UTF-7", "ISO-8859-14", "ISO-8859-16",
-                    "Extended_UNIX_Code_Fixed_Width_for_Japanese", "ISO-10646-UCS-Basic", "ISO-10646-Unicode-Latin1",
-                    "ISO-10646-J-1", "ISO-Unicode-IBM-1268", "ISO-Unicode-IBM-1276", "ISO-Unicode-IBM-1264",
-                    "ISO-Unicode-IBM-1265", "ISO-8859-1-Windows-3.0-Latin-1", "ISO-8859-1-Windows-3.1-Latin-1",
-                    "ISO-8859-2-Windows-Latin-2", "ISO-8859-9-Windows-Latin-5", "Adobe-Standard-Encoding",
-                    "Ventura-US", "Ventura-International", "PC8-Danish-Norwegian", "PC8-Turkish", "IBM-Symbols",
-                    "HP-Legal", "HP-Pi-font", "HP-Math8", "Adobe-Symbol-Encoding", "HP-DeskTop", "Ventura-Math",
-                    "Microsoft-Publishing", "HZ-GB-2312", };
-    /**
-     * Set of unknown charsets in Java
-     */
-    protected static Set setOfUnknownJavaCharset;
-    
-    /**
-     * Map from ISO 639/2 T to ISO 639/2 B
-     */
-    protected static Map<String, String> fromISO_639_2_T2B;
-    
-	public static final String CHARSET_ASCII = "US-ASCII";
-	public static final String CHARSET_UTF8 = "UTF-8";
-	public static final String CHARSET_ISO8859_1 = "ISO-8859-1";
-
-	/**
-     * To represent the unknown
-	 */ 
-	public static final int NILL = -1;
-	
-    static {
-        setOfUnknownJavaCharset = new HashSet(Arrays.asList(UNKNOWN_JAVA_CHARSET));
-        
-        // Map to transform from the terminology code to the bibliographic one 
-        fromISO_639_2_T2B = new HashMap<String, String>();
-        fromISO_639_2_T2B.put("sqi", "alb");
-        fromISO_639_2_T2B.put("hye", "arm");
-        fromISO_639_2_T2B.put("eus", "baq");
-        fromISO_639_2_T2B.put("mya", "bur");
-        fromISO_639_2_T2B.put("zho", "chi");
-        fromISO_639_2_T2B.put("ces", "cze");
-        fromISO_639_2_T2B.put("nld", "dut");
-        fromISO_639_2_T2B.put("fra", "fre");
-        fromISO_639_2_T2B.put("kat", "geo");
-        fromISO_639_2_T2B.put("deu", "ger");
-        fromISO_639_2_T2B.put("ell", "gre");
-        fromISO_639_2_T2B.put("isl", "ice");
-        fromISO_639_2_T2B.put("mkd", "mac");
-        fromISO_639_2_T2B.put("mri", "mao");
-        fromISO_639_2_T2B.put("msa", "may");
-        fromISO_639_2_T2B.put("fas", "per");
-        fromISO_639_2_T2B.put("ron", "rum");
-        fromISO_639_2_T2B.put("slk", "slo");
-        fromISO_639_2_T2B.put("bod", "tib");
-        fromISO_639_2_T2B.put("cym", "wel");
-    }
-    
-	/**
-	charset
-	    Usage: The character set employed by the text. Controlled vocab using IANA names for character sets.
-	    Attributes: none.
-	    Contains: none.
-	    Contained by: character_info.
-   */
-	private String charset;
-
-	/**
- 	byte_order
-	    Usage: Byte order, primarily useful for cases where it's not clear just by specifying an IANA character set. 
-	    Uses enumerated values of big, little, and middle' endian.
-	    Attributes: none.
-	    Contains: none.
-	    Contained by: character_info.
-	*/
-	private int byte_order = NILL;
-
-	/**
-	byte_size
-	    Usage: The size of an individual byte within the expressed as a number of bits (as integer). This does not necessarily equal the character size, as a character may have more than one, or a variable number of bytes per character.
-	    Attributes: none.
-	    Contains: none.
-	    Contained by: character_info.
-	*/
-	private String byte_size;
-    
-	/**
-	character_size
-	    Usage: The size of an individual character within the character set as a number of bytes of the size expressed in the byte_size. In the case of variable encodings, such as UTF-8 for Unicode, the character_size element should state "variable" and also identify the specific variable character set encoding in the encoding attribute.
-	    Attributes: encoding.
-	    Contains: none.
-	    Contained by: character_info.
-	 */
-	private String character_size;
-    
-	/**
-	linebreak
-	    Usage: How line breaks are represented in current file (which may differ from how they were originally encoded). Either carriage return, line feed, or carriage return/line feed.
-	    Attributes: none.
-	    Contains: none.
-	    Contained by: character_info. 
-	 */
-	private int linebreak = NILL;
-	
-	/**
-    language
-        Usage: Language(s) used in work. Use ISO 639-2 codes, which are enumerated in the schema as valid text values.
-        Attributes: none.
-        Contains: none.
-        Contained by: textMD.
-	 */
-	private String language;
-	
-	/**
-	markup_basis
-	    Usage: The metalanguage used to create the markup language, such as SGML, XML, GML, etc.
-	    Attributes: version.
-	    Contains: none.
-	    Contained by: textMD.
-	*/
-	private String markup_basis;
-	/**	
-	 version
-	    Usage: Used to record the version number (as a string) for a given piece of software, a markup language, or a schema version.
-	*/	
-	private String markup_basis_version;
-	
-	/**
-	markup_language
-	    Usage: Markup language employed on the text (i.e., the specific schema or dtd). May be a URI for schema or dtd, but not mandatory.
-	    Attributes: version.
-	    Contains: none.
-	    Contained by: textMD. 	
-	*/
-	private String markup_language;
-    
-	/**	
-	 version
-	    Usage: Used to record the version number (as a string) for a given piece of software, a markup language, or a schema version.
-	*/	
-	private String markup_language_version;
-    
-	/**
-	 * @return the charset
-	 */
-	public String getCharset() {
-		return charset;
-	}
-    
-	/**
-	 * @param charset the charset to set
-	 */
-	public void setCharset(String charset) {
-		this.charset = toTextMDCharset(charset);
-	}
-    
-	/**
-	 * @return the byte_order
-	 */
-	public int getByte_order() {
-		return byte_order;
-	}
-        public String getByte_orderString() {
-            if (byte_order == NILL) {
-                return BYTE_ORDER[BYTE_ORDER_BIG]; // default !!!
-            }
-            return BYTE_ORDER[byte_order];
-    }
-	
-	/**
-	 * @param byte_order the byte_order to set
-	 */
-	public void setByte_order(int byte_order) {
-		this.byte_order = byte_order;
-	}
-    
-	/**
-	 * @return the byte_size
-	 */
-	public String getByte_size() {
-		return byte_size;
-	}
-    
-	/**
-	 * @param byte_size the byte_size to set
-	 */
-	public void setByte_size(String byte_size) {
-		this.byte_size = byte_size;
-	}
-    
-	/**
-	 * @return the character_size
-	 */
-	public String getCharacter_size() {
-		return character_size;
-	}
-    
-	/**
-	 * @param character_size the character_size to set
-	 */
-	public void setCharacter_size(String character_size) {
-		this.character_size = character_size;
-	}
-    
-	/**
-	 * @return the linebreak
-	 */
-	public int getLinebreak() {
-		return linebreak;
-	}
-    
-    /**
-     * @return the linebreak in String form
-     */
-    public String getLinebreakString() {
-        if (linebreak == NILL) {
-            return LINEBREAK[LINEBREAK_CRLF]; // default !!!
-        }
-        return LINEBREAK[linebreak];
-    }
-    
-	/**
-	 * @param linebreak the linebreak to set
-	 */
-	public void setLinebreak(int linebreak) {
-		this.linebreak = linebreak;
-	}
-    
-	/**
-	 * @return the language
-	 */
-	public String getLanguage() {
-		return language;
-	}
-    
-	/**
-	 * @param language the language to set
-	 */
-	public void setLanguage(String language) {
-        this.language = toISO_639_2(language);
-	}
-    
-	/**
-	 * @return the markup_basis
-	 */
-	public String getMarkup_basis() {
-		return markup_basis;
-	}
-    
-	/**
-	 * @param markup_basis the markup_basis to set
-	 */
-	public void setMarkup_basis(String markup_basis) {
-		this.markup_basis = markup_basis;
-	}
-    
-	/**
-	 * @return the markup_basis_version
-	 */
-	public String getMarkup_basis_version() {
-		return markup_basis_version;
-	}
-    
-	/**
-	 * @param markup_basis_version the markup_basis_version to set
-	 */
-	public void setMarkup_basis_version(String markup_basis_version) {
-		this.markup_basis_version = markup_basis_version;
-	}
-    
-	/**
-	 * @return the markup_language
-	 */
-	public String getMarkup_language() {
-		return markup_language;
-	}
-    
-	/**
-	 * @param markup_language the markup_language to set
-	 */
-	public void setMarkup_language(String markup_language) {
-		this.markup_language = markup_language;
-	}
-    
-	/**
-	 * @return the markup_language_version
-	 */
-	public String getMarkup_language_version() {
-		return markup_language_version;
-	}
-    
-	/**
-	 * @param markup_language_version the markup_language_version to set
-	 */
-	public void setMarkup_language_version(String markup_language_version) {
-		this.markup_language_version = markup_language_version;
-	}
-    
-    /**
-     * Transform a given charset in the "authorized" list given in the textMD schema enumeration.
-     * From the schema documentation on charset (http://www.loc.gov/standards/textMD/elementSet/index.html#element_charset).
-     * The character set employed by the text. Controlled vocab using IANA names for character sets:
-     * http://www.iana.org/assignments/character-sets.
-     * The problem arises because the java Charset uses the (preferred MIME name) where textMD uses the Name ...
-     * @param srcCharset charset from the file
-     * @return normalized charset
-     */
-    public static String toTextMDCharset(String srcCharset) {
-        if (srcCharset == null) return null;
-        
-        Charset cs = null;
-        String textMDCharset = null;
-        try {
-            cs = Charset.forName(srcCharset);
-            textMDCharset = cs.name();
-        } catch (Exception e) {
-            // Try a unknown one
-            if (setOfUnknownJavaCharset.contains(srcCharset)) {
-                textMDCharset = srcCharset;
-            } else {
-                // Downgrade to default
-                textMDCharset = CHARSET_ISO8859_1;
-            }
-        }
-        if (textMDCharset != null) {
-            return textMDCharset;
-        } else {
-            // Downgrade to default
-            return CHARSET_ISO8859_1;
-        }
-    }
-    
-    /**
-     * Transform a language to the ISO_639-2 language (only enumeration allowed in textMD schema).
-     * @param srcLang language in the file
-     * @return normalized language in 3 letters (except qaa-qtz)
-     */
-    public static String toISO_639_2(String srcLang) {
-        if (srcLang == null) return null;
-        if ("qaa-qtz".equals(srcLang)) return srcLang;
-        
-        String textMDLang = null;
-        if (srcLang.length() == 3) {
-            textMDLang = srcLang;
-        }
-        else if (srcLang.length() == 2) {
-            try {
-                Locale loc = new Locale(srcLang);
-                textMDLang = loc.getISO3Language();
-            } catch (Exception e) {
-                // Unknown language
-            }
-        }
-        else if (srcLang.length() > 3) {
-            // Just try with the first 2 characters
-            try {
-                Locale loc = new Locale(srcLang.substring(0, 2));
-                srcLang = loc.getISO3Language();
-            } catch (Exception e) {
-                // Unknown language
-            }
-        }
-        if (textMDLang != null && textMDLang.length() == 3) {
-            // From ISO 639-2/T to ISO 639-2/B
-            if (fromISO_639_2_T2B.containsKey(textMDLang)) {
-                textMDLang = (String)fromISO_639_2_T2B.get(textMDLang);
-            }
-            return textMDLang;
-        }
-        return null;
-
-    }
-}

jhove/classes/edu/harvard/hul/ois/jhove/Utf8BlockMarker.java

@@ -1,62 +0,0 @@
-/**********************************************************************
- * Jhove - JSTOR/Harvard Object Validation Environment
- * Copyright 2004 by JSTOR and the President and Fellows of Harvard College
- **********************************************************************/
-
-package edu.harvard.hul.ois.jhove;
-
-import edu.harvard.hul.ois.jhove.module.Utf8Block;
-import java.util.*;
-
-/**
- *
- * @author Gary McGath
- *
- */
-public class Utf8BlockMarker {
-    private boolean[] blocksUsed;
-
-    public Utf8BlockMarker () {
-        blocksUsed = new boolean [Utf8Block.unicodeBlock.length];
-    }
-
-    public void markBlock (int code) {
-        for (int i=0; i<Utf8Block.unicodeBlock.length; i++) {
-            if (Utf8Block.unicodeBlock[i].getStart () <= code &&
-            Utf8Block.unicodeBlock[i].getEnd   () >= code) {
-                blocksUsed[i] = true;
-                break;
-            }
-        }
-    }
-
-    /** Returns a Property listing the blocks that have been 
-     *  marked as used.  If no blocks have been marked,
-     *  returns null. */
-    public Property getBlocksUsedProperty (String name)
-    {  
-        List<String> block = new ArrayList<String> (blocksUsed.length);
-        for (int i=0; i<blocksUsed.length; i++) {
-            if (blocksUsed[i]) {
-            block.add (Utf8Block.unicodeBlock[i].getName ());
-            }
-        }
-        if (block.isEmpty ()) {
-            return null;
-        }
-        else {
-            return new Property (name,
-                PropertyType.STRING,
-                PropertyArity.LIST,
-                block);
-        }
-    }
-
-    /** Clears all marked blocks. */
-    public void reset ()
-    {
-        for (int i=0; i<Utf8Block.unicodeBlock.length; i++) {
-            blocksUsed[i] = false;
-        }
-    }
-}

jhove/classes/edu/harvard/hul/ois/jhove/XMLWrapperStream.java

@@ -1,161 +0,0 @@
-/**********************************************************************
- * Jhove - JSTOR/Harvard Object Validation Environment
- * Copyright 2003 by JSTOR and the President and Fellows of Harvard College
- *
- **********************************************************************/
-
-package edu.harvard.hul.ois.jhove;
-
-import java.io.IOException;
-import java.io.InputStream;
-
-/**
- * This class serves to provide an InputStream for an XML
- * fragment (e.g., embedded XMP metadata).  
- * 
- * @author Gary McGath
- */
-public class XMLWrapperStream extends InputStream 
-{
-    
-    private String xmlDecl;
-    private String rootStart;
-    private String rootEnd;
-    private int strIndex;
-    private int state;
-
-    /* Values for state */    
-    private final static int DECL = 0,
-        ROOT_START = 1,
-        CONTENT = 2,
-        ROOT_END = 3;
-
-    private InputStream _wrappedStream;
-
-    /**
-     *  Constructor.
-     *  
-     *  @param wrappedStream       The stream which this stream will subsume.
-     *  @param rootName            The name of the root element.  May be null 
-     *                             if <code>wrappedStream</code> already contains a root element.
-     *  @param version             The XML version.  Should be null or "1.0" unless 
-     *                             there's a really good reason.
-     *  @param encoding            The name of the character encoding. May be null.
-     *  @param standalone          The value of the <code>standalone</code> attribute.  May be null.
-     */
-    public XMLWrapperStream (InputStream wrappedStream, 
-            String rootName,
-            String version,
-            String encoding,
-            String standalone) 
-    {
-        _wrappedStream = wrappedStream;
-        xmlDecl = "<?xml version='";
-        if (version == null) {
-            xmlDecl += "1.0'";   
-        }
-        else {
-            xmlDecl += version + "'";
-        }
-        if (encoding != null) {
-            xmlDecl += " encoding='" + encoding + "' ";   
-        }
-        if (standalone != null) {
-            xmlDecl += " standalone='" + standalone + "' ";
-        }
-        xmlDecl += "?>";
-        state = DECL;
-        strIndex = 0;
-        
-        if (rootName != null) {
-            rootStart = "<" + rootName + ">";
-            rootEnd = "</" + rootName + ">";
-        }
-        else {
-            rootStart = "";
-            rootEnd = "";
-        }
-    }
-    
-    /**
-     *  Constructor.  Equivalent to 
-     *                <code>XMLWrapperStream (wrappedStream, null, null, null, null)</code>
-     *  
-     *  @param wrappedStream       The stream which this stream will subsume.
-     */
-    public XMLWrapperStream (InputStream wrappedStream)
-    {
-        this (wrappedStream, null, null, null, null);
-    }
-
-    /**
-     *  Constructor.  Equivalent to 
-     *                <code>XMLWrapperStream (wrappedStream, rootName, null, null, null)</code>
-     *  
-     *  @param wrappedStream       The stream which this stream will subsume.
-     *  @param rootName            The name of the root element.  May be null.
-     */
-    public XMLWrapperStream (InputStream wrappedStream, String rootName)
-    {
-        this (wrappedStream, rootName, null, null, null);
-    }
-    
-    
-    /** 
-     * Get a byte.  Successive calls will return the
-     * XML declaration, then the wrapped stream.
-     * 
-     * @see java.io.InputStream#read()
-     */
-    public int read() throws IOException 
-    {
-        int retval;
-        if (state == DECL) { 
-            if (strIndex >= xmlDecl.length()) {
-                // We have finished the declaration string now.
-                state = ROOT_START;
-                strIndex = 0;
-            }
-            else {
-                // We haven't finished returning the declaration string.
-                return (int) xmlDecl.charAt(strIndex++);
-            }
-        }
-        
-        // Each state can fall through to the next
-        
-        if (state == ROOT_START) {
-            if (strIndex >= rootStart.length()) {
-                // We have finished the root element start now.
-                state = CONTENT;
-            }
-            else {
-            return (int) rootStart.charAt(strIndex++);
-            }
-        }
-             
-        if (state == CONTENT) {
-            // Metadata alleged stream doesn't look remotely like metadata --
-            // probably looking at wrong part of file!
-            retval = _wrappedStream.read ();
-            if (retval == -1) {
-                state = ROOT_END;
-                strIndex = 0;
-            }
-            else {
-                return retval;
-            }
-        }
-            
-        // Must be ROOT_END if it gets here
-        if (strIndex >= rootEnd.length()) {
-            // We have finished the root element end and the document now.
-            return -1;
-        }
-        else {
-            return (int) rootEnd.charAt(strIndex++);
-        }
-        
-     }
-
-}