identifiers 0.1.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: 64dea49b2835751962c267670fdef1c57696eceb
+  data.tar.gz: 5d4bfc54e1a55194e2286c80bd24cb7fa255aeb3
+SHA512:
+  metadata.gz: b0dd1c0a6b57d8e3a4066487e79b8fda6552c2e443ae58869d1271abe8ed526ba8aaf3a4a9a1ec833df547934d4f4fcbce5e61858956b035af69bd868b95b23d
+  data.tar.gz: 93b41b272316d5cfe8ce134f9f2e09714c7723ed33ab1186e6b13d17409ca3fd00574d5bf26a0f68ed536e2a4db7db68536f983a191f9a3d193038650262d31b

data/CHANGELOG.md

@@ -0,0 +1,7 @@
+# Change Log
+All notable changes to this project will be documented in this file. This
+project adheres to [Semantic Versioning](http://semver.org/).
+
+## [0.1.0] - 2016-10-21
+### Added
+- Initial release

data/LICENSE.txt

@@ -0,0 +1,21 @@
+The MIT License (MIT)
+
+Copyright (c) 2016 Altmetric LLP
+
+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 +1,47 @@
+# Identifiers
+
+Collection of utilities related to the extraction, validation and normalization of various scholarly identifiers. The supported list is:
+- [ADS Bibcodes](http://adsdoc.harvard.edu/abs_doc/help_pages/bibcodes.html)
+- [arXiv](https://arxiv.org/help/arxiv_identifier)
+- [DOI](https://www.doi.org/)
+- [Handle](https://en.wikipedia.org/wiki/Handle_System)
+- [ISBN](https://en.wikipedia.org/wiki/International_Standard_Book_Number)
+- [National Clinic Trials](https://clinicaltrials.gov/)
+- [PubMed](http://www.ncbi.nlm.nih.gov/pubmed)
+- [RePEc](https://en.wikipedia.org/wiki/Research_Papers_in_Economics)
+- [URN](https://en.wikipedia.org/wiki/Uniform_Resource_Name)
+
+## Installation
+
+Add this line to your application's Gemfile:
+
+```ruby
+gem 'identifiers', '~> 0.1'
+```
+
+And then execute:
+
+    $ bundle
+
+Or install it yourself as:
+
+    $ gem install identifiers
+
+## Usage
+
+```ruby
+Identifiers::DOI.extract('example: 10.123/abcd.efghi')
+
+Identifiers::URN.new('urn:abc:123')
+Identifiers::URN('urn:abc:123')
+```
+
+## Contributing
+
+Bug reports and pull requests are welcome on GitHub at https://github.com/altmetric/identifiers.
+
+## License
+
+Copyright © 2016 Altmetric LLP
+
+Distributed under the [MIT License](http://opensource.org/licenses/MIT).

data/lib/identifiers.rb

@@ -0,0 +1,12 @@
+require 'identifiers/ads_bibcode'
+require 'identifiers/arxiv_id'
+require 'identifiers/doi'
+require 'identifiers/handle'
+require 'identifiers/isbn'
+require 'identifiers/national_clinical_trial_id'
+require 'identifiers/pubmed_id'
+require 'identifiers/repec_id'
+require 'identifiers/urn'
+
+module Identifiers
+end

data/lib/identifiers/ads_bibcode.rb

@@ -0,0 +1,7 @@
+module Identifiers
+  class AdsBibcode
+    def self.extract(str)
+      str.scan(/\b\d{4}[a-z][0-9a-z&.]{14}\b/i)
+    end
+  end
+end

data/lib/identifiers/arxiv_id.rb

@@ -0,0 +1,19 @@
+module Identifiers
+  class ArxivId
+    def self.extract(str)
+      extract_pre_2007_arxiv_ids(str) + extract_post_2007_arxiv_ids(str)
+    end
+
+    def self.extract_post_2007_arxiv_ids(str)
+      str
+        .scan(%r{(?<=^|\s|/)(?:arXiv:)?\d{4}\.\d{4,5}(?:v\d+)?(?=$|\s)}i)
+        .map { |arxiv_id| arxiv_id.sub(/\AarXiv:/i, '') }
+    end
+
+    def self.extract_pre_2007_arxiv_ids(str)
+      str
+        .scan(%r{(?<=^|\s|/)(?:arXiv:)?[a-z-]+(?:\.[A-Z]{2})?/\d{2}(?:0[1-9]|1[012])\d{3}(?:v\d+)?(?=$|\s)}i)
+        .map { |arxiv_id| arxiv_id.sub(/\AarXiv:/i, '') }
+    end
+  end
+end

data/lib/identifiers/doi.rb

@@ -0,0 +1,7 @@
+module Identifiers
+  class DOI
+    def self.extract(str)
+      str.scan(%r{\b10\.\d{3,}/\S+\b}).map(&:downcase)
+    end
+  end
+end

data/lib/identifiers/handle.rb

@@ -0,0 +1,7 @@
+module Identifiers
+  class Handle
+    def self.extract(str)
+      str.scan(%r{\b[0-9.]+/\S+\b}i)
+    end
+  end
+end

data/lib/identifiers/isbn.rb

@@ -0,0 +1,46 @@
+module Identifiers
+  class ISBN
+    REGEX_13 = /\b97[89]\d{10}\b/
+    REGEX_10 = /\b\d{9}(?:\d|X)\b/
+
+    def self.extract(str)
+      extract_thirteen_digit_isbns(str) + extract_ten_digit_isbns(str)
+    end
+
+    def self.extract_thirteen_digit_isbns(str)
+      str.tr('-', '').scan(REGEX_13).select { |isbn| valid_isbn_13?(isbn) }
+    end
+
+    def self.extract_ten_digit_isbns(str)
+      str.tr('-', '').scan(REGEX_10).select { |isbn| valid_isbn_10?(isbn) }.map { |isbn|
+        isbn.chop!
+        isbn.prepend('978')
+        isbn << isbn_13_check_digit(isbn).to_s
+
+        isbn
+      }
+    end
+
+    def self.isbn_13_check_digit(isbn)
+      10 - isbn.each_char.zip([1, 3].cycle).reduce(0) { |sum, values| sum + (Integer(values[0]) * values[1]) } % 10
+    end
+
+    def self.valid_isbn_13?(isbn)
+      return false unless isbn =~ REGEX_13
+
+      result = isbn.each_char.zip([1, 3].cycle).reduce(0) { |sum, values| sum + (Integer(values[0]) * values[1]) }
+
+      (result % 10).zero?
+    end
+
+    def self.valid_isbn_10?(isbn)
+      return false unless isbn =~ REGEX_10
+
+      result = isbn.each_char.with_index.reduce(0) { |sum, values|
+        sum + (Integer(values[0].sub('X', '10')) * values[1].succ)
+      }
+
+      (result % 11).zero?
+    end
+  end
+end

data/lib/identifiers/national_clinical_trial_id.rb

@@ -0,0 +1,7 @@
+module Identifiers
+  class NationalClinicalTrialId
+    def self.extract(str)
+      str.scan(/\bNCT\d+\b/i).map(&:upcase)
+    end
+  end
+end

data/lib/identifiers/pubmed_id.rb

@@ -0,0 +1,7 @@
+module Identifiers
+  class PubmedId
+    def self.extract(str)
+      str.scan(/(?<=^|\s)\d+(?=$|\s)/)
+    end
+  end
+end

data/lib/identifiers/repec_id.rb

@@ -0,0 +1,7 @@
+module Identifiers
+  class RepecId
+    def self.extract(str)
+      str.scan(/\brepec:\S+\b/i).map { |repec| "RePEc:#{repec.split(':', 2).last}" }
+    end
+  end
+end

data/lib/identifiers/urn.rb

@@ -0,0 +1,5 @@
+require 'urn'
+
+module Identifiers
+  URN = ::URN
+end

data/spec/identifiers/ads_bibcode_spec.rb

@@ -0,0 +1,19 @@
+require 'identifiers/ads_bibcode'
+
+RSpec.describe Identifiers::AdsBibcode do
+  describe '#extract' do
+    it 'does extract a bibcode' do
+      str = 'This is a Bibcode: 1974AJ.....79..819H'
+
+      expect(described_class.extract(str)).to contain_exactly('1974AJ.....79..819H')
+    end
+
+    it 'does extract a PhD Thesis Bibcode' do
+      expect(described_class.extract('2004PhRvL..93o0801M')).to contain_exactly('2004PhRvL..93o0801M')
+    end
+
+    it 'does not extract Bibcodes from DOIs' do
+      expect(described_class.extract('10.1097/01.ASW.0000443266.17665.19')).to be_empty
+    end
+  end
+end

data/spec/identifiers/arxiv_id_spec.rb

@@ -0,0 +1,25 @@
+require 'identifiers/arxiv_id'
+
+RSpec.describe Identifiers::ArxivId do
+  describe '#extract' do
+    it 'does extract a pre 2007 arXiv ID' do
+      expect(described_class.extract('Example: math.GT/0309136')).to contain_exactly('math.GT/0309136')
+    end
+
+    it 'does extract a post 2007 unversioned arXiv ID' do
+      expect(described_class.extract('Example: arXiv:0706.0001')).to contain_exactly('0706.0001')
+    end
+
+    it 'does extract a post 2007 versioned arXiv ID' do
+      expect(described_class.extract('Example: arXiv:1501.00001v2')).to contain_exactly('1501.00001v2')
+    end
+
+    it 'does not extract IDs from DOIs that end in a valid arXiv ID' do
+      expect(described_class.extract('10.1049/el.2013.3006')).to be_empty
+    end
+
+    it 'does not extract IDs from DOIs that contain a valid arXiv ID' do
+      expect(described_class.extract('10.2310/7290.2014.00033')).to be_empty
+    end
+  end
+end

data/spec/identifiers/doi_spec.rb

@@ -0,0 +1,21 @@
+require 'identifiers/doi'
+
+RSpec.describe Identifiers::DOI do
+  it 'extracts DOIs from a string' do
+    str = 'This is an example of DOI: 10.1049/el.2013.3006'
+
+    expect(described_class.extract(str)).to contain_exactly('10.1049/el.2013.3006')
+  end
+
+  it 'downcase the DOIs extracted' do
+    str = 'This is an example of DOI: 10.1097/01.ASW.0000443266.17665.19'
+
+    expect(described_class.extract(str)).to contain_exactly('10.1097/01.asw.0000443266.17665.19')
+  end
+
+  it 'does not extract a PUBMED ID' do
+    str = 'This is NOT a DOI: 123456'
+
+    expect(described_class.extract(str)).to be_empty
+  end
+end

data/spec/identifiers/handle_spec.rb

@@ -0,0 +1,15 @@
+require 'identifiers/handle'
+
+RSpec.describe Identifiers::Handle do
+  it 'extracts a Handle' do
+    str = 'http://hdl.handle.net/10149/596901'
+
+    expect(described_class.extract(str)).to contain_exactly('10149/596901')
+  end
+
+  it 'extracts another Handle' do
+    str = 'http://hdl.handle.net/2117/83545it.ly/1UtXnTW'
+
+    expect(described_class.extract(str)).to contain_exactly('2117/83545it.ly/1UtXnTW')
+  end
+end

data/spec/identifiers/isbn_spec.rb

@@ -0,0 +1,26 @@
+require 'identifiers/isbn'
+
+RSpec.describe Identifiers::ISBN do
+  it 'extracts a ISBN' do
+    expect(described_class.extract('ISBN: 9780805069099')).to contain_exactly('9780805069099')
+  end
+
+  it 'normalizes 13-digit ISBNs' do
+    str = "978-0-80-506909-9\n978-0-67-187919-8"
+
+    expect(described_class.extract(str)).to contain_exactly('9780805069099', '9780671879198')
+  end
+
+  it 'normalizes 10-digit ISBNs' do
+    str = "0-8050-6909-7 \n 2-7594-0269-X"
+    expect(described_class.extract(str)).to contain_exactly('9780805069099', '9782759402694')
+  end
+
+  it 'does not extract invalid 13-digit ISBNs' do
+    expect(described_class.extract('9783319217280')).to be_empty
+  end
+
+  it 'does not extract invalid 10-digit ISBNs' do
+    expect(described_class.extract('3319217280')).to be_empty
+  end
+end

data/spec/identifiers/national_clinical_trial_id_spec.rb

@@ -0,0 +1,11 @@
+require 'identifiers/national_clinical_trial_id'
+
+RSpec.describe Identifiers::NationalClinicalTrialId do
+  it 'extract NCT IDs' do
+    expect(described_class.extract("NCT00000106\nNCT00000107")).to contain_exactly('NCT00000106', 'NCT00000107')
+  end
+
+  it 'normalizes NCT IDs' do
+    expect(described_class.extract("nct00000106\nnCt00000107")).to contain_exactly('NCT00000106', 'NCT00000107')
+  end
+end

data/spec/identifiers/pubmed_id_spec.rb

@@ -0,0 +1,13 @@
+require 'identifiers/pubmed_id'
+
+RSpec.describe Identifiers::PubmedId do
+  it 'extracts PubMed IDs' do
+    expect(described_class.extract("123\n456")).to contain_exactly('123', '456')
+  end
+
+  it 'does not return outputs with PubMed IDs in DOIs' do
+    str = "10.1038/nplants.2015.3\n10.1126/science.286.5445.1679e"
+
+    expect(described_class.extract(str)).to be_empty
+  end
+end

data/spec/identifiers/repec_id_spec.rb

@@ -0,0 +1,15 @@
+require 'identifiers/repec_id'
+
+RSpec.describe Identifiers::RepecId do
+  it 'extracts RePEc IDs' do
+    str = "RePEc:wbk:wbpubs:2266\nRePEc:inn:wpaper:2016-03"
+
+    expect(described_class.extract(str)).to contain_exactly('RePEc:wbk:wbpubs:2266', 'RePEc:inn:wpaper:2016-03')
+  end
+
+  it 'normalizes RePec IDs' do
+    str = "REPEC:wbk:wbpubs:2266\nrepec:inn:wpaper:2016-03"
+
+    expect(described_class.extract(str)).to contain_exactly('RePEc:wbk:wbpubs:2266', 'RePEc:inn:wpaper:2016-03')
+  end
+end

data/spec/identifiers/urn_spec.rb

@@ -0,0 +1,9 @@
+require 'identifiers/urn'
+
+RSpec.describe Identifiers::URN do
+  it 'extracts URNs' do
+    str = 'En un pueblo italiano urn:1234:abc al pie de la montaña URN:foo:bar%23.\\'
+
+    expect(described_class.extract(str)).to contain_exactly('urn:1234:abc', 'URN:foo:bar%23.')
+  end
+end

data/spec/spec_helper.rb

@@ -0,0 +1,18 @@
+RSpec.configure do |config|
+  config.filter_run :focus
+  config.run_all_when_everything_filtered = true
+  config.example_status_persistence_file_path = "spec/examples.txt"
+  config.disable_monkey_patching!
+  config.warnings = true
+  config.order = :random
+  config.default_formatter = 'doc' if config.files_to_run.one?
+  Kernel.srand config.seed
+
+  config.expect_with :rspec do |expectations|
+    expectations.include_chain_clauses_in_custom_matcher_descriptions = true
+  end
+
+  config.mock_with :rspec do |mocks|
+    mocks.verify_partial_doubles = true
+  end
+end

metadata

@@ -0,0 +1,133 @@
+--- !ruby/object:Gem::Specification
+name: identifiers
+version: !ruby/object:Gem::Version
+  version: 0.1.0
+platform: ruby
+authors:
+- Jonathan Hernandez
+autorequire: 
+bindir: exe
+cert_chain: []
+date: 2016-10-21 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: urn
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '2.0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '2.0'
+- !ruby/object:Gem::Dependency
+  name: bundler
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.10'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.10'
+- !ruby/object:Gem::Dependency
+  name: rake
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '10.0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '10.0'
+- !ruby/object:Gem::Dependency
+  name: rspec
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.4'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.4'
+description: 
+email:
+- support@altmetric.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- CHANGELOG.md
+- LICENSE.txt
+- README.md
+- lib/identifiers.rb
+- lib/identifiers/ads_bibcode.rb
+- lib/identifiers/arxiv_id.rb
+- lib/identifiers/doi.rb
+- lib/identifiers/handle.rb
+- lib/identifiers/isbn.rb
+- lib/identifiers/national_clinical_trial_id.rb
+- lib/identifiers/pubmed_id.rb
+- lib/identifiers/repec_id.rb
+- lib/identifiers/urn.rb
+- spec/identifiers/ads_bibcode_spec.rb
+- spec/identifiers/arxiv_id_spec.rb
+- spec/identifiers/doi_spec.rb
+- spec/identifiers/handle_spec.rb
+- spec/identifiers/isbn_spec.rb
+- spec/identifiers/national_clinical_trial_id_spec.rb
+- spec/identifiers/pubmed_id_spec.rb
+- spec/identifiers/repec_id_spec.rb
+- spec/identifiers/urn_spec.rb
+- spec/spec_helper.rb
+homepage: https://github.com/altmetric/identifiers
+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: 2.5.1
+signing_key: 
+specification_version: 4
+summary: Utilities library for various scholarly identifiers used by Altmetric
+test_files:
+- spec/identifiers/ads_bibcode_spec.rb
+- spec/identifiers/arxiv_id_spec.rb
+- spec/identifiers/doi_spec.rb
+- spec/identifiers/handle_spec.rb
+- spec/identifiers/isbn_spec.rb
+- spec/identifiers/national_clinical_trial_id_spec.rb
+- spec/identifiers/pubmed_id_spec.rb
+- spec/identifiers/repec_id_spec.rb
+- spec/identifiers/urn_spec.rb
+- spec/spec_helper.rb