cacofonix 0.10.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA256:
+  metadata.gz: 7d71358bce0d5d281f6d8ea181ea0a8b50ea74acd5b5df2e6079d2ab4d98a6fe
+  data.tar.gz: b1802248185109acad0b4cf4951fc701bbb841fc38dc3935da5e519e5db70148
+SHA512:
+  metadata.gz: 335a075c708ad440c71554dc03ef92201dd797dad92ef9d6ac29f729ebdfc4ca46022b6111a325834acecc69d169645b2f512c86a7b1cd9f465b15ab98a32eb4
+  data.tar.gz: aae5a765f88eaa478b7bce6c9590f4900922f778d298ab8de47c605f8225cd74cf7ddfd6f1e29dcc6ca1ddb5719dd3351ddbcda3cd52dd2e011da67f2670f644

data/.gitignore

@@ -0,0 +1,2 @@
+pkg
+Gemfile.lock

data/.rvmrc

@@ -0,0 +1 @@
+rvm use ree@onix

data/.travis.yml

@@ -0,0 +1,10 @@
+---
+sudo: false
+language: ruby
+cache: bundler
+rvm:
+  - 2.6.3
+  - 2.5.5
+before_install:
+  - sudo apt-get install -y xsltproc
+  - gem install bundler -v 2.0.2

data/CHANGELOG.md

@@ -0,0 +1,205 @@
+# Changelog
+
+## [0.10.0] - 2019-07-08
+
+### Changed
+
+- Rename gem from onix to cacofonix
+- Rename primary module namespace from `ONIX` to `Cacofonix`
+- Use Cacofonix::DTDs to set appropriate env vars before XML parsing; required for ONIX 2.1 DTDs to be properly loaded and related entities in source XML files to be respected
+- Address Fixnum->Integer and BigDecimal.new->BigDecimal deprecations
+- Require Ruby 2.5 or newer
+
+# Previous releases (as onix gem)
+
+v0.9.1 (5th September 2011)
+- relax activesupport dependency to work with rails 3 or 3.1
+
+v0.9.0 (14th April 2011)
+- switch back to the vanilla roxml gem. Ben is maintaining it again and
+  he has merged in my bug fixes
+- clarify comments explaining encoding behaviour
+- Add options hash to ONIX::Reader. Only option at this stage is :encoding,
+  which allows the user to override the assumed encoding of the input XML
+- API change, so new minor version
+
+v0.8.5 (21st December 2010)
+- update packaging - use bundler and rspec 2.x
+- support normalising short tag files that include HTML tags
+
+v0.8.4 (18th October 2010)
+- some small fixes to xml names from Tim
+- make all code lists available via the ONIX::Lists class
+
+v0.8.3 (9th September 2010)
+- Fix for race condition in ONIX::Normaliser
+  - thanks to pixelvixen for reporting
+- force roxml to be 3.1.6 or higher. Earlier versions misbehaved when monkey
+  patching nokogiri
+
+v0.8.2 (6th May 2010)
+- fix APAProduct#series and APAProduct#series=
+
+v0.8.1 (5th January 2010)
+- Use nokogiri's support for transparent entity conversion when reading an ONIX file
+- Removed entity replacement from ONIX::Normaliser
+  - the external dependency on sed made me uncomfortable, and it wasn't really
+    necessary now that nokogiri can do it for us
+- Removed utf-8 normalisation from ONIX::Normaliser
+  - nokogiri also handles this really cleanly and transparently. Regardless of
+    the source file encoding, Nokogiri::Reader returns utf-8 encoded data
+- Add the release attribute to files we generate
+  - it's optional in 2.1, but mandatory in 3.0. As we start to see 3.0 files in the
+    wild it will help to have a rapid way to distinguish between them
+- Add ONIX::Reader#release - to detect the release version of files we read in
+
+v0.8.0 (31st October 2009)
+- Replace LibXML dependency with Nokogiri. Nokogiri is under active development, has
+  a responsive maintainer and is significantly more stable
+- Switch to ROXML 3.x
+  - roxml also switched from libxml to nokogiri
+  - roxml removed deprecated parts of it's API
+  - should now avoid various conflicts with mongrel
+- Ensure APAProduct#price returns the first product price and ignores
+  the price type
+
+v0.7.8 (19th October 2009)
+- add support for additional elements (mostly series and audience related)
+  - thanks tim
+
+v0.7.7 (1st October 2009)
+- optimise sed usage in ONIX::Normaliser. *huge* speed improvement on
+  large files.
+
+v0.7.6 (21st September 2009)
+- provide access to the PackQuantity element
+
+v0.7.5 (8th September 2009)
+- Don't raise an exception on malformed dates when reading files
+
+v0.7.4 (2nd September 2009)
+- Expand ONIX::Normaliser
+  - strip control chars
+  - add encoding declaration to valid utf-8 files that aren't declared
+    as such
+
+v0.7.3 (19th August 2009)
+- Switch from java to xsltproc to convert short tag ONIX files
+  to reference tags
+
+v0.7.2 (19th August 2009)
+- Added ONIX::Normaliser class
+  - for normalising various ONIX files into a form that makes them easy
+    to process. Shouldn't be necesary to pre-process files like this, but
+    I'm sick of trying to wrestle the libxml ruby bindings
+
+v0.7.1 (24th June 2009)
+- Small tweak to ordering of elements in the Product group
+
+v0.7.0 (17th June 2009)
+- try using LibXML for reader again
+  - retrieving the ONIX version of the input file is currently disabled, as
+    that seems to be the source of our instability
+- Various Ruby 1.9 compatability tweaks
+  - add source file coding declarations. All source files are UTF-8
+  - ONIX::Reader ensures all input data is converted to UTF-8
+  - the ROXML based objects seem to forget the encoding when they're marshalled,
+    so force string based attributes *back* to UTF-8
+
+v0.6.7 (Unreleased)
+- add some accessors to the Title composite
+
+v0.6.6 (Unreleased)
+- Forget the S on an element name
+
+v0.6.5 (Unreleased)
+- Ruby 1.9 compat
+
+v0.6.4 (Unreleased)
+- Add APAProduct#price
+
+v0.6.3(Unreleased)
+- Bump ROXML dependency to 2.5.3 to get libxml-ruby 1.1.3 compatibility
+
+v0.6.2 (Unreleased)
+- Fix a small typo in APAProduct
+
+v0.6.1 (Unreleased)
+- Stopped using LibXMLs Reader class as the basis for our reader.
+  - We were getting too many segfaults (even 1 is too many!)
+  - until we resolve it, reverted to manual string parsing
+  - This is a fairly major regression of functionality. For 99% of files
+    it won't matter, but for some corner cases it will. ie UTF-16 encoded
+    files
+  - Will also be noticeably slower
+  - Hopefully only a short term fix, until I work out what is going on with
+    libxml
+
+v0.6.0 (18th March 2009)
+- remove use of threads in ONIX::Reader
+  - a producer/consumer pattern was useful in the REXML stream parsing days, but
+    now LibXML's Reader binding provides a better alternative
+  - API left unchanged, this was all under the hood
+- bump required ROXML version to 2.5.2
+
+v0.5.1 (4th March 2009)
+- Fix a single letter typo
+
+v0.5 (2nd March 2009)
+- Switch ROXML dependency from a patched version to vanilla
+  - Vanilla ROXML now has all the features we need
+  - This change should be transparent to ONIX gem users
+
+v0.4.7 (9th December 2008)
+- Contributor sub elements should match the order specified in the DTD
+
+v0.4.6 (2nd December 2008)
+- 2 new accessors on the contributor class - bio and corporate name
+
+v0.4.5 (21st November 2008)
+- APAProduct wrapper should generate valid MediaFile composites
+
+v0.4.4 (19th November 2008)
+- Added support for more elements from MarketRepresentation
+
+v0.4.3 (11th November 2008)
+- Added support for AgentName and MarketPublishingStatus
+
+v0.4.2 (1st November 2008)
+- Remove final remnants of REXML code
+- Minor reordering of elements to match DTD
+
+v0.4.1 (UNRELEASED)
+- Added accessors to various product measurements. Height, weight, etc.
+- Reduced time for an ONIX::Reader class to initialise
+
+v0.4.0 (28th October 2008)
+- Major rework: now based on ROXML instead of xml-mapping
+  - Mostly API Compatible
+  - StreamReader and StreamWriter renamed to Reader and Writer
+  - ROXML is based on libxml, so things should be significantly faster
+
+v0.2.7 (Unreleased)
+- Add line breaks after each product
+
+v0.2.5 (Unreleased)
+- Make PublishingStatus a two_digit_node
+
+v0.2.4 (Unreleased)
+- Initialise the media files array of a new product correctly
+
+v0.2.3 (Unreleased)
+- Switch a few more fields over to TwoDigitNodes
+- Make the product availability field accessible from APAProduct
+
+v0.2.2 (Unreleased)
+- Add a new nodetype (DateNode) for YYYYMMDD fields
+
+v0.2.1 (Unreleased)
+- Add a new nodetype (TwoDigitNode) for two digit codes
+
+v0.2.0 (16th July 2008)
+- Add support for reading and storing subject codes (BIC, BISAC, etc)
+
+v0.1.0 (12th June 2008)
+- Initial Release

data/CODE_OF_CONDUCT.md

@@ -0,0 +1,74 @@
+# Contributor Covenant Code of Conduct
+
+## Our Pledge
+
+In the interest of fostering an open and welcoming environment, we as
+contributors and maintainers pledge to making participation in our project and
+our community a harassment-free experience for everyone, regardless of age, body
+size, disability, ethnicity, gender identity and expression, level of experience,
+nationality, personal appearance, race, religion, or sexual identity and
+orientation.
+
+## Our Standards
+
+Examples of behavior that contributes to creating a positive environment
+include:
+
+* Using welcoming and inclusive language
+* Being respectful of differing viewpoints and experiences
+* Gracefully accepting constructive criticism
+* Focusing on what is best for the community
+* Showing empathy towards other community members
+
+Examples of unacceptable behavior by participants include:
+
+* The use of sexualized language or imagery and unwelcome sexual attention or
+advances
+* Trolling, insulting/derogatory comments, and personal or political attacks
+* Public or private harassment
+* Publishing others' private information, such as a physical or electronic
+  address, without explicit permission
+* Other conduct which could reasonably be considered inappropriate in a
+  professional setting
+
+## Our Responsibilities
+
+Project maintainers are responsible for clarifying the standards of acceptable
+behavior and are expected to take appropriate and fair corrective action in
+response to any instances of unacceptable behavior.
+
+Project maintainers have the right and responsibility to remove, edit, or
+reject comments, commits, code, wiki edits, issues, and other contributions
+that are not aligned to this Code of Conduct, or to ban temporarily or
+permanently any contributor for other behaviors that they deem inappropriate,
+threatening, offensive, or harmful.
+
+## Scope
+
+This Code of Conduct applies both within project spaces and in public spaces
+when an individual is representing the project or its community. Examples of
+representing a project or community include using an official project e-mail
+address, posting via an official social media account, or acting as an appointed
+representative at an online or offline event. Representation of a project may be
+further defined and clarified by project maintainers.
+
+## Enforcement
+
+Instances of abusive, harassing, or otherwise unacceptable behavior may be
+reported by contacting the project team at tim(at)icelab.com.au. All
+complaints will be reviewed and investigated and will result in a response that
+is deemed necessary and appropriate to the circumstances. The project team is
+obligated to maintain confidentiality with regard to the reporter of an incident.
+Further details of specific enforcement policies may be posted separately.
+
+Project maintainers who do not follow or enforce the Code of Conduct in good
+faith may face temporary or permanent repercussions as determined by other
+members of the project's leadership.
+
+## Attribution
+
+This Code of Conduct is adapted from the [Contributor Covenant][homepage], version 1.4,
+available at [http://contributor-covenant.org/version/1/4][version]
+
+[homepage]: http://contributor-covenant.org
+[version]: http://contributor-covenant.org/version/1/4/

data/Gemfile

@@ -0,0 +1,5 @@
+source "https://rubygems.org"
+
+gemspec
+
+gem "pry-byebug", platform: :mri

data/LICENSE.txt

@@ -0,0 +1,22 @@
+Copyright (c)
+  2008-2011 James Healy
+  2011-2012 Joseph Pearson
+  2019 Icelab
+
+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.

data/README.md

@@ -0,0 +1,76 @@
+# Cacofonix
+
+Cacofonix helps you work with ONIX data in your Ruby applications. ONIX is a set
+of (XML-based) standards for published products. Cacofonix focuses on the _[ONIX
+for Books][onix_standard]_ standard, and currently supports ONIX 2.1 (all
+revisions).
+
+With Cacofonix, you can:
+
+- Efficiently read ONIX files
+- Map records in ONIX files to Ruby objects
+- Write ONIX files
+
+Cacofonix is an updated, maintained fork of James Healy's original [onix
+gem][gem_original], also incorporating Joseph Pearson's [major
+refactorings][gem_joseph] and expanded support for the standard.
+
+[onix_standard]: https://www.editeur.org/11/Books/
+[gem_original]: https://github.com/yob/onix
+[gem_joseph]: https://github.com/yob/onix/pull/3
+
+## Installation
+
+Add this line to your application's `Gemfile`:
+
+```ruby
+gem "cacofonix"
+```
+
+And then execute:
+
+```shell
+$ bundle
+```
+
+Or install it yourself as:
+
+```shell
+$ gem install cacofonix
+```
+
+## Usage
+
+See the files in the [examples/][examples] directory to get started quickly.
+
+For more detail, view the comments in the following classes:
+
+* [`Cacofonix::Reader`][reader] - For reading ONIX files
+* [`Cacofonix::Writer`][writer] - For writing ONIX files
+* [`Cacofonix::Normaliser`][normaliser] - For normalising ONIX files before
+  reading (Fixes encoding issues, etc.)
+* [`Cacofonix::Lists`][lists] - For building hashes of code lists from the ONIX
+  spec
+
+[examples]: examples
+[reader]: lib/cacofonix/core/reader.rb
+[writer]: lib/cacofonix/core/writer.rb
+[normaliser]: lib/cacofonix/utils/normaliser.rb
+[lists]: lib/cacofonix/core/lists.rb
+
+## ONIX support
+
+`Cacofonix::Reader` only handles the reference tag versions of ONIX 2.1. Use
+`Cacofonix::Normaliser` to convert any short tag files to reference tags.
+
+`Cacofonix::Writer` only generates reference tag ONIX files.
+
+## License
+
+The gem is available as open source under the terms of the [MIT
+License](https://opensource.org/licenses/MIT).
+
+## Code of Conduct
+
+Everyone interacting in the Cacofonix codebase, issue trackers, chat rooms and
+mailing lists is expected to follow the [code of conduct](CODE_OF_CONDUCT.md).

data/Rakefile

@@ -0,0 +1,6 @@
+require "bundler/gem_tasks"
+require "rspec/core/rake_task"
+
+RSpec::Core::RakeTask.new(:spec)
+
+task :default => :spec

data/TODO

@@ -0,0 +1,14 @@
+- finish adding support for all tags in a Product record
+  - contributor still needs some obscure tags added
+- add a new node type for dates that should be in the form YYYYMMDD
+- allow symbols to be used instead of numeric codes
+  - contribution type, id type, etc
+- validations
+  - hard stuff from the spec
+    - 2 digit numbers, 8 digit dates, char limits on text fields
+  - code lists
+    - only values in code lists allowed in relevant fields
+  - regional requirements
+    - titlepage minimum set of tags
+    - APA (if different to titlepage)
+- documentation

data/bin/onix_extract_codelists

@@ -0,0 +1,41 @@
+#!/usr/bin/ruby
+# coding: utf-8
+
+# NB: When testing locally, you can run this as:
+#
+#   ruby -Ilib bin/onix_extract_codelists [options] xsd dir
+
+require 'optparse'
+
+def parse_options
+  options = {}
+  optparse = OptionParser.new do |parser|
+    parser.banner = [
+      "Usage: onix_extract_codelists [options] xsd_path output_dir_path",
+      "",
+      "  eg: onix_extract_codelists ONIX_BookProduct_CodeLists.xsd support/codes"
+    ].join("\n")
+
+    options[:format] = :tsv
+    parser.on("-f", "--format FMT", "Write to format (TSV or Ruby)") do |fmt|
+      options[:format] = fmt.downcase.to_sym
+    end
+
+    parser.on("-h", "--help", "Display this usage information") do
+      puts parser
+      exit
+    end
+  end
+  optparse.parse!
+  unless ARGV.size == 2
+    puts optparse
+    exit(1)
+  end
+  options
+end
+
+options = parse_options
+
+require "cacofonix"
+extractor = Cacofonix::CodeListExtractor.new(ARGV.shift, options[:format])
+extractor.run(ARGV.shift)