identifiers 0.2.0 → 0.3.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: cfc37db391d8a0cd5bd16a6cc9b16f7e3a5f224f
-  data.tar.gz: 0d31d7feff4d516d95e9ce2fbbb3fdd576c6ac35
+  metadata.gz: 19a6b42db016b656d1c1114ae8e0dee77c69f5e1
+  data.tar.gz: a954deca478c665226f8073cc9837a4c64ad2e88
 SHA512:
-  metadata.gz: 1afa5cfa7a7f74b1e742de7e184b2070a4378e62e7feac8f6eef77cc7607165bb4bf6c50c207dbb67cb9736e05c8e8bcae83b6692f148a0d844c0b627036a996
-  data.tar.gz: 413911a758a18ee91ba69337ed799ac9e8d7a7a98db1cce57c3a4baba05786431c9806c77aa5702dea30a6dd25358f36497965df3677e0dfe224ba0ed4dd47c0
+  metadata.gz: 22c9cc78407e5561a3122a766368278eb0258cc71d61e715411fd6c9a2224a573c5818d782fe2167d79b4aad367dfa310b062d497d5b529e4fd3bf801e4ffccd
+  data.tar.gz: 80b229ac1c454db783a6b200d2ca225c603aaa5d5adb9a5009b31752c7358f9442d164e430c2f400bdcdbaa8c79e60f1582ee4a95615b18110307814f751d0ec

data/CHANGELOG.md

@@ -2,6 +2,10 @@
 All notable changes to this project will be documented in this file. This
 project adheres to [Semantic Versioning](http://semver.org/).
 
+## [0.3.0] - 2016-11-03
+### Added
+- Support for ORCID
+
 ## [0.2.0] - 2016-11-01
 ### Changed
 - Strip leading 0s from Pubmed IDs. 0 is no longer a valid Pubmed ID.

data/README.md

@@ -10,13 +10,14 @@ Collection of utilities related to the extraction, validation and normalization
 - [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)
+- [ORCID](http://orcid.org/)
 
 ## Installation
 
 Add this line to your application's Gemfile:
 
 ```ruby
-gem 'identifiers', '~> 0.2'
+gem 'identifiers', '~> 0.3'
 ```
 
 And then execute:
@@ -36,6 +37,27 @@ Identifiers::URN.new('urn:abc:123')
 Identifiers::URN('urn:abc:123')
 ```
 
+## By identifier
+
+`.extract` is a common method that works across all the supported identifiers.
+
+```ruby
+Identifiers::AdsBibcode.extract('')
+Identifiers::ArxivId.extract('')
+Identifiers::DOI.extract('')
+Identifiers::Handle.extract('')
+Identifiers::ISBN.extract('')
+Identifiers::NationalClinicalTrialId.extract('')
+Identifiers::ORCID.extract('')
+Identifiers::PubmedId.extract('')
+Identifiers::RepecId.extract('')
+Identifiers::URN.extract('')
+```
+
+But for some identifiers might have more. Check their implementation to see all the methods available.
+
+For `URN`s, please check the [URN gem documentation](https://github.com/altmetric/urn) to see all the available options.
+
 ## Contributing
 
 Bug reports and pull requests are welcome on GitHub at https://github.com/altmetric/identifiers.

data/lib/identifiers.rb

@@ -7,6 +7,7 @@ require 'identifiers/national_clinical_trial_id'
 require 'identifiers/pubmed_id'
 require 'identifiers/repec_id'
 require 'identifiers/urn'
+require 'identifiers/orcid'
 
 module Identifiers
 end

data/lib/identifiers/orcid.rb

@@ -0,0 +1,27 @@
+module Identifiers
+  class ORCID
+    REGEX = /\b(?:\d{4}-){3}\d{3}[\dx]\b/i
+
+    def self.extract(str)
+      str.scan(REGEX).select { |orcid| valid?(orcid) }.map(&:upcase)
+    end
+
+    def self.valid?(str)
+      digit = calculate_digit(str)
+      return false unless digit
+
+      digit == str[-1].upcase
+    end
+
+    def self.calculate_digit(str)
+      return unless str =~ REGEX
+
+      base_digits = str.chop.tr('-', '')
+      total = 0
+      base_digits.each_char { |c| total = (total + Integer(c)) * 2 }
+      remainder = total % 11
+      result = (12 - remainder) % 11
+      result == 10 ? 'X' : result.to_s
+    end
+  end
+end

data/spec/identifiers/orcid_spec.rb

@@ -0,0 +1,39 @@
+require 'identifiers/orcid'
+
+RSpec.describe Identifiers::ORCID do
+  describe '.extract' do
+    it 'extracts ORCIDs from a string' do
+      str = "orcid.org/0000-0002-0088-0058\n0000-0002-0488-8591"
+
+      expect(described_class.extract(str)).to contain_exactly('0000-0002-0088-0058', '0000-0002-0488-8591')
+    end
+
+    it 'normalizes the ORCID extracted' do
+      str = 'orcid.org/0000-0003-0166-248x'
+
+      expect(described_class.extract(str)).to contain_exactly('0000-0003-0166-248X')
+    end
+  end
+
+  describe '.valid?' do
+    it 'returns true if the ORCID is valid' do
+      str = '0000-0002-0088-0058'
+
+      expect(described_class.valid?(str)).to eq(true)
+    end
+
+    it 'returns false if the ORCID is not valid' do
+      str = '0000-0002-0088-005X'
+
+      expect(described_class.valid?(str)).to eq(false)
+    end
+  end
+
+  describe '.calculate_digit' do
+    it 'calculates the digit of an ORCID' do
+      str = '0000-0002-0088-0058'
+
+      expect(described_class.calculate_digit(str)).to eq('8')
+    end
+  end
+end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: identifiers
 version: !ruby/object:Gem::Version
-  version: 0.2.0
+  version: 0.3.0
 platform: ruby
 authors:
 - Jonathan Hernandez
 autorequire: 
 bindir: exe
 cert_chain: []
-date: 2016-11-01 00:00:00.000000000 Z
+date: 2016-11-03 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: urn
@@ -83,6 +83,7 @@ files:
 - lib/identifiers/handle.rb
 - lib/identifiers/isbn.rb
 - lib/identifiers/national_clinical_trial_id.rb
+- lib/identifiers/orcid.rb
 - lib/identifiers/pubmed_id.rb
 - lib/identifiers/repec_id.rb
 - lib/identifiers/urn.rb
@@ -92,6 +93,7 @@ files:
 - spec/identifiers/handle_spec.rb
 - spec/identifiers/isbn_spec.rb
 - spec/identifiers/national_clinical_trial_id_spec.rb
+- spec/identifiers/orcid_spec.rb
 - spec/identifiers/pubmed_id_spec.rb
 - spec/identifiers/repec_id_spec.rb
 - spec/identifiers/urn_spec.rb
@@ -127,6 +129,7 @@ test_files:
 - spec/identifiers/handle_spec.rb
 - spec/identifiers/isbn_spec.rb
 - spec/identifiers/national_clinical_trial_id_spec.rb
+- spec/identifiers/orcid_spec.rb
 - spec/identifiers/pubmed_id_spec.rb
 - spec/identifiers/repec_id_spec.rb
 - spec/identifiers/urn_spec.rb