research_metadata 0.1.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: 44b8ec73389b2fb8f75aa96fca6213b0fbe7fb1e
+  data.tar.gz: 5dcdf92b3c6437da322181ae345b418e37e0312c
+SHA512:
+  metadata.gz: 95c845a1a08d31f1d63085382598be3011230a400bfd76ce31c5604c0e03bc1678b425974a996e0b014e319d4ec10f42c7895738b406c8ab0e9158b42832a58f
+  data.tar.gz: def6a7e3e6078b1974ed06f8156908316acfdb6a58bdc9164bf49c42bcc8c5598c46bfe335a28652a611f60d23b5e3e12210c4704de126cb8675eab248c7d24b

data/.gitignore

@@ -0,0 +1,18 @@
+*.gem
+*.rbc
+.bundle
+.config
+.yardoc
+Gemfile.lock
+InstalledFiles
+_yardoc
+coverage
+doc/
+lib/bundler/man
+pkg
+rdoc
+spec/reports
+test/tmp
+test/version_tmp
+tmp
+.idea

data/CHANGELOG.md

@@ -0,0 +1,10 @@
+# Change Log
+All notable changes to this project will be documented in this file.
+This project adheres to [Semantic Versioning](http://semver.org/).
+
+## Unreleased
+
+## 0.1.0 - 2017-02-03
+### Added
+- Working product supports datasets.
+- RSpec tests for datasets.

data/Gemfile

@@ -0,0 +1,4 @@
+source 'https://rubygems.org'
+
+# Specify your gem's dependencies in research_metadata.gemspec
+gemspec

data/LICENSE.txt

@@ -0,0 +1,22 @@
+Copyright (c) 2017 Adrian Albin-Clark
+
+MIT License
+
+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 +1,51 @@
+# ResearchMetadata [![Gem Version](https://badge.fury.io/rb/research_metadata.svg)](https://badge.fury.io/rb/research_metadata)
+
+Extraction and Transformation for Loading by DataCite's API.
+
+## Installation
+
+Add this line to your application's Gemfile:
+
+    gem 'research_metadata'
+
+And then execute:
+
+    $ bundle
+
+Or install it yourself as:
+
+    $ gem install research_metadata
+
+## Usage
+
+### Configuration
+Configure Purée.
+
+```ruby
+Puree.base_url   = ENV['PURE_BASE_URL']
+Puree.username   = ENV['PURE_USERNAME']
+Puree.password   = ENV['PURE_PASSWORD']
+Puree.basic_auth = true
+```
+
+### Transformation
+
+Create a metadata transformer for a Pure dataset...
+
+```ruby
+transformer = ResearchMetadata::Transformer::Dataset.new
+```
+
+...and give it a Pure identifier and a DOI...
+
+```ruby
+metadata = transformer.transform uuid: 'xxxxxxxx-xxxx-4xxx-yxxx-xxxxxxxxxxxx',
+                                 doi: '10.1234/foo/bar/1'
+```
+
+...to get DataCite-ready metadata.
+
+## Documentation
+[API in YARD](http://www.rubydoc.info/gems/research_metadata)
+
+[Detailed usage in GitBook](https://aalbinclark.gitbooks.io/research_metadata)

data/Rakefile

@@ -0,0 +1 @@
+require "bundler/gem_tasks"

data/lib/research_metadata/transformer/dataset.rb

@@ -0,0 +1,233 @@
+# Extraction (from Pure) and Transformation for Loading by DataCite's API
+#
+module ResearchMetadata
+
+  # Transformer
+  #
+  module Transformer
+
+    # Dataset
+    #
+    class Dataset
+
+      # Dataset transformation
+      #
+      # @param id [String]
+      # @param uuid [String]
+      # @param doi [String]
+      # @return [String]
+      def transform(id: nil, uuid: nil, doi: nil)
+        @dataset = extract uuid: uuid, id: id
+        raise 'No metadata to transform' if @dataset.metadata.empty?
+        person_o = person
+        file_o = file
+        resource = ::Datacite::Mapping::Resource.new(
+            identifier: identifier(doi),
+            creators: person_o['creator'],
+            titles: [ title ],
+            publisher: publisher,
+            publication_year: publication_year,
+            subjects: subjects,
+            contributors: person_o['contributor'],
+            dates: dates,
+            language: language,
+            resource_type: resource_type,
+            related_identifiers: related_identifiers,
+            sizes: file_o.map { |i| i['size'] },
+            formats: file_o.map { |i| i['mime'] },
+            rights_list: file_o.map { |i| i['license']['name'] },
+            descriptions: description,
+            geo_locations: spatial
+        )
+        resource.write_xml
+      end
+
+      private
+
+      def affiliations(person)
+        person.affiliation.map { |i| i['name'] }
+      end
+
+      def dates
+        a = []
+        available = ::Datacite::Mapping::Date.new value: Puree::Date.iso(@dataset.available),
+                                                  type: ::Datacite::Mapping::DateType::AVAILABLE
+        a << available
+
+        temporal = @dataset.temporal
+        temporal_range = ''
+        if !temporal['start']['year'].empty?
+          temporal_range << Puree::Date.iso(temporal['start'])
+          if !temporal['end']['year'].empty?
+            temporal_range << '/'
+            temporal_range << Puree::Date.iso(temporal['end'])
+          end
+          if !temporal_range.empty?
+            collected = ::Datacite::Mapping::Date.new value: temporal_range,
+                                                      type: ::Datacite::Mapping::DateType::COLLECTED
+            a << collected
+          end
+        end
+
+        a
+      end
+
+      def description
+        desc = @dataset.description
+        if !desc.empty?
+          d = ::Datacite::Mapping::Description.new value: desc,
+                                             type: ::Datacite::Mapping::DescriptionType::ABSTRACT
+          [d]
+        else
+          []
+        end
+      end
+
+      def extract(uuid: nil, id: nil)
+        d = Puree::Dataset.new
+        if !uuid.nil?
+          d.find uuid: uuid
+        else
+          d.find id: id
+        end
+        d
+      end
+
+      def file
+        @dataset.file
+      end
+
+      def identifier(doi)
+        ::Datacite::Mapping::Identifier.new(value: doi)
+      end
+
+      def language
+        @dataset.locale
+      end
+
+      def name_identifier_orcid(person)
+        name_identifier = nil
+        if !person.orcid.empty?
+          name_identifier = ::Datacite::Mapping::NameIdentifier.new  scheme: 'ORCID',
+                                                                   scheme_uri: URI('http://orcid.org/'),
+                                                                   value: person.orcid
+        end
+        name_identifier
+      end
+
+      def person
+        o = {}
+        o['creator'] = []
+        o['contributor'] = []
+        person_types = %w(internal external other)
+        person_types.each do |person_type|
+          @dataset.person[person_type].each do |dataset_person|
+            pure_role = dataset_person['role'].gsub(/\s+/, '')
+              name = "#{dataset_person['name']['last']}, #{dataset_person['name']['first']}"
+              if pure_role == 'Creator'
+                human = ::Datacite::Mapping::Creator.new name: name
+              else
+                pure_role = 'Other' if pure_role === 'Contributor'
+                contributor_type = ::Datacite::Mapping::ContributorType.find_by_value pure_role
+                if contributor_type
+                  human = ::Datacite::Mapping::Contributor.new  name: name,
+                                                                type: contributor_type
+                end
+              end
+              if human
+                if !dataset_person['uuid'].empty?
+                  person = Puree::Person.new
+                  person.find uuid: dataset_person['uuid']
+                  if !person.metadata.empty?
+                    identifier = name_identifier_orcid(person)
+                    human.identifier = identifier if !identifier.nil?
+
+                    affiliation = affiliations(person)
+                    human.affiliations = affiliation if !affiliation.empty?
+                  end
+                end
+                if dataset_person['role'] == 'Creator'
+                  o['creator'] << human
+                else
+                  o['contributor'] << human
+                end
+              end
+          end
+        end
+        o
+      end
+
+      def publication_year
+        @dataset.available['year']
+      end
+
+      def publisher
+        @dataset.publisher
+      end
+
+      def related_identifiers
+        publications = @dataset.publication
+        data = []
+        publications.each do |i|
+          if i['type'] === 'Dataset'
+            # Do nothing as the relationship cannot currently be determined
+            # pub = Puree::Dataset.new
+            next
+          else
+            pub = Puree::Publication.new
+          end
+          pub.find uuid: i['uuid']
+          doi = pub.doi
+          if doi && !doi.empty?
+            doi_part_to_remove = 'http://dx.doi.org/'
+            doi_short = doi.gsub(doi_part_to_remove, '')
+            doi_short.gsub!('/', '-')
+            related_identifier =
+                ::Datacite::Mapping::RelatedIdentifier.new(
+                    value: doi_short,
+                    identifier_type: ::Datacite::Mapping::RelatedIdentifierType::DOI,
+                    relation_type: ::Datacite::Mapping::RelationType::IS_REFERENCED_BY)
+            data << related_identifier
+          end
+        end
+        data
+      end
+
+      def resource_type
+        ::Datacite::Mapping::ResourceType.new(
+            resource_type_general: ::Datacite::Mapping::ResourceTypeGeneral::DATASET,
+            value: 'Dataset'
+        )
+      end
+
+      def spatial
+        # Pure has free text to list place names and does not allow a point to
+        # be associated with a specific place
+
+        # Place names
+        arr = @dataset.spatial.map { |i| ::Datacite::Mapping::GeoLocation.new place: i }
+
+        # Lat Long point
+        spatial_point = @dataset.spatial_point
+        if !spatial_point.empty?
+          point = ::Datacite::Mapping::GeoLocationPoint.new latitude:  spatial_point['latitude'],
+                                                            longitude: spatial_point['longitude']
+          geolocation = ::Datacite::Mapping::GeoLocation.new point: point
+          arr << geolocation
+        end
+        arr
+      end
+
+      def subjects
+        @dataset.keyword.map { |i| ::Datacite::Mapping::Subject.new value: i }
+      end
+
+      def title
+        ::Datacite::Mapping::Title.new value: @dataset.title
+      end
+
+    end
+
+  end
+
+end

data/lib/research_metadata/version.rb

@@ -0,0 +1,5 @@
+module ResearchMetadata
+  # Semantic version number
+  #
+  VERSION = "0.1.0"
+end

data/lib/research_metadata.rb

@@ -0,0 +1,4 @@
+require 'puree'
+require 'datacite/mapping'
+require 'research_metadata/transformer/dataset'
+require 'research_metadata/version'

data/research_metadata.gemspec

@@ -0,0 +1,23 @@
+# coding: utf-8
+lib = File.expand_path('../lib', __FILE__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+require 'research_metadata/version'
+
+Gem::Specification.new do |spec|
+  spec.name          = "research_metadata"
+  spec.version       = ResearchMetadata::VERSION
+  spec.authors       = ["Adrian Albin-Clark"]
+  spec.email         = ["a.albin-clark@lancaster.ac.uk"]
+  spec.summary       = %q{Extraction and Transformation for Loading by the DataCite API.}
+  spec.description   = %q{Extraction and Transformation for Loading by the DataCite API.}
+  spec.homepage      = "https://aalbinclark.gitbooks.io/research_metadata"
+  spec.license       = "MIT"
+
+  spec.files         = `git ls-files -z`.split("\x0")
+  spec.executables   = spec.files.grep(%r{^bin/}) { |f| File.basename(f) }
+  spec.test_files    = spec.files.grep(%r{^(test|spec|features)/})
+  spec.require_paths = ["lib"]
+
+  spec.add_runtime_dependency "puree", "~> 0.20"
+  spec.add_runtime_dependency "datacite-mapping", "~> 0.2"
+end

data/spec/spec_helper.rb

@@ -0,0 +1,4 @@
+require 'puree'
+require 'datacite/mapping'
+require 'research_metadata/transformer/dataset'
+require 'research_metadata/version'

data/spec/transformer/dataset_spec.rb

@@ -0,0 +1,39 @@
+require 'spec_helper'
+
+describe 'Dataset' do
+
+  def setup
+    Puree.base_url   = ENV['PURE_BASE_URL']
+    Puree.username   = ENV['PURE_USERNAME']
+    Puree.password   = ENV['PURE_PASSWORD']
+    Puree.basic_auth = true
+    @t = ResearchMetadata::Transformer::Dataset.new
+  end
+
+  it '#new' do
+    t = ResearchMetadata::Transformer::Dataset.new
+    expect(t).to be_an_instance_of ResearchMetadata::Transformer::Dataset
+  end
+
+  describe 'data transformation' do
+    before(:all) do
+      setup
+    end
+
+    it '#transform with valid UUID' do
+      metadata = @t.transform uuid: ENV['PURE_DATASET_UUID'],
+                              doi:  '10.1234/foo/bar/1'
+      is_xml = metadata.downcase.start_with?('<resource')
+      expect(is_xml).to match(true)
+    end
+
+    it '#transform with valid ID' do
+      metadata = @t.transform id:  ENV['PURE_DATASET_ID'],
+                              doi: '10.1234/foo/bar/1'
+      is_xml = metadata.downcase.start_with?('<resource')
+      expect(is_xml).to match(true)
+    end
+
+  end
+
+end

metadata

@@ -0,0 +1,87 @@
+--- !ruby/object:Gem::Specification
+name: research_metadata
+version: !ruby/object:Gem::Version
+  version: 0.1.0
+platform: ruby
+authors:
+- Adrian Albin-Clark
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2017-02-06 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: puree
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '0.20'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '0.20'
+- !ruby/object:Gem::Dependency
+  name: datacite-mapping
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '0.2'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '0.2'
+description: Extraction and Transformation for Loading by the DataCite API.
+email:
+- a.albin-clark@lancaster.ac.uk
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- ".gitignore"
+- CHANGELOG.md
+- Gemfile
+- LICENSE.txt
+- README.md
+- Rakefile
+- lib/research_metadata.rb
+- lib/research_metadata/transformer/dataset.rb
+- lib/research_metadata/version.rb
+- research_metadata.gemspec
+- spec/spec_helper.rb
+- spec/transformer/dataset_spec.rb
+homepage: https://aalbinclark.gitbooks.io/research_metadata
+licenses:
+- MIT
+metadata: {}
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project: 
+rubygems_version: 2.2.2
+signing_key: 
+specification_version: 4
+summary: Extraction and Transformation for Loading by the DataCite API.
+test_files:
+- spec/spec_helper.rb
+- spec/transformer/dataset_spec.rb
+has_rdoc: