identifiers 0.4.0 → 0.5.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: ab0f2da0f90f2dda268319d5be99dc314bd9b9fe
-  data.tar.gz: 443f4aead25198aa6d267fa9c67a3800739f837c
+  metadata.gz: 036d129df184be8b4e577950bbe37c10455a2d6d
+  data.tar.gz: b35262b8180a444476fd45124ddffd5086ee3af3
 SHA512:
-  metadata.gz: 51dc9476b30151bda26a037ae4dba6e25d59feef23af27bbc7d9ca7ab497221ef4117194a9524a4ba552cf708061bcc80b80b4404735abc08f4bbd38b615f3ad
-  data.tar.gz: 088d481f41064ec32560dea76c25a0ddfdb3f731937bda7c0a0d32b2c2dd3e1d44e96f5e6eea2b4410a7fcb57c47779ca0adb68b5b41806256ef21504bc840d7
+  metadata.gz: 5e1ed385ed71f64287445b99452d8905d597f097be0e235e5057d443de98a0f2762f6e624633814a7fa1d2eb7973750d7439ed7a57fa94f2bc4a9d3eb0d4f09a
+  data.tar.gz: f2f32ba1157949782ed5db1d3cdbe28004d76b0743ecf1737719790e872dea024b63fc008b3c6d65873ea407f4ff8be3407856cb4b702f27ad5d57ecfa0ca41b

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/).
 
+## [0.5.0] - 2017-01-27
+### Added
+- Added support for ISBN-As when extracting DOIs and ISBNs
+
 ## [0.4.0] - 2017-01-23
 ### Changed
 - Extract ISBNs separated by spaces as well as hyphens
@@ -27,3 +31,4 @@ project adheres to [Semantic Versioning](http://semver.org/).
 [0.3.0]: https://github.com/altmetric/identifiers/releases/tag/v0.2.0
 [0.3.1]: https://github.com/altmetric/identifiers/releases/tag/v0.3.1
 [0.4.0]: https://github.com/altmetric/identifiers/releases/tag/v0.4.0
+[0.5.0]: https://github.com/altmetric/identifiers/releases/tag/v0.5.0

data/README.md

@@ -4,7 +4,7 @@ Collection of utilities related to the extraction, validation and normalization
 
 - [ADS Bibcodes](http://adsdoc.harvard.edu/abs_doc/help_pages/bibcodes.html)
 - [arXiv IDs](https://arxiv.org/help/arxiv_identifier)
-- [DOIs](https://www.doi.org/)
+- [DOIs](https://www.doi.org/) (including [ISBN-As](https://www.doi.org/factsheets/ISBN-A.html))
 - [Handles](https://en.wikipedia.org/wiki/Handle_System)
 - [ISBNs](https://en.wikipedia.org/wiki/International_Standard_Book_Number)
 - [National Clinical Trial IDs](https://clinicaltrials.gov/)
@@ -18,7 +18,7 @@ Collection of utilities related to the extraction, validation and normalization
 Add this line to your application's `Gemfile`:
 
 ```ruby
-gem 'identifiers', '~> 0.4'
+gem 'identifiers', '~> 0.5'
 ```
 
 And then execute:

data/lib/identifiers/doi.rb

@@ -1,7 +1,7 @@
 module Identifiers
   class DOI
     def self.extract(str)
-      str.scan(%r{\b10\.\d{3,}/\S+\b}).map(&:downcase)
+      str.scan(%r{\b10\.(?:97[89]\.\d{2,8}/\d{1,7}|\d{4,9}/\S+)\b}).map(&:downcase)
     end
   end
 end

data/lib/identifiers/isbn.rb

@@ -2,9 +2,14 @@ module Identifiers
   class ISBN
     REGEX_13 = /\b97[89]\d{10}\b/
     REGEX_10 = /\b\d{9}(?:\d|X)\b/
+    REGEX_A = %r{\b(?<=10\.)97[89]\.\d{2,8}/\d{1,7}\b}
 
     def self.extract(str)
-      extract_thirteen_digit_isbns(str) + extract_ten_digit_isbns(str)
+      extract_isbn_as(str) + extract_thirteen_digit_isbns(str) + extract_ten_digit_isbns(str)
+    end
+
+    def self.extract_isbn_as(str)
+      extract_thirteen_digit_isbns(str.scan(REGEX_A).join("\n").tr('/.', ''))
     end
 
     def self.extract_thirteen_digit_isbns(str)

data/spec/identifiers/doi_spec.rb

@@ -13,9 +13,21 @@ RSpec.describe Identifiers::DOI do
     expect(described_class.extract(str)).to contain_exactly('10.1097/01.asw.0000443266.17665.19')
   end
 
-  it 'does not extract a PUBMED ID' do
+  it 'does not extract a PubMed ID' do
     str = 'This is NOT a DOI: 123456'
 
     expect(described_class.extract(str)).to be_empty
   end
+
+  it 'extracts ISBN-As' do
+    str = 'This is an ISBN-A: 10.978.8898392/315'
+
+    expect(described_class.extract(str)).to contain_exactly('10.978.8898392/315')
+  end
+
+  it 'does not extract invalid ISBN-As' do
+    str = 'This is not an ISBN-A: 10.978.8898392/NotARealIsbnA'
+
+    expect(described_class.extract(str)).to be_empty
+  end
 end

data/spec/identifiers/isbn_spec.rb

@@ -19,6 +19,14 @@ RSpec.describe Identifiers::ISBN do
     expect(described_class.extract('ISBN: 978 0 80 506909 9')).to contain_exactly('9780805069099')
   end
 
+  it 'extracts ISBN-13s from ISBN-As' do
+    expect(described_class.extract('10.978.8898392/315')).to contain_exactly('9788898392315')
+  end
+
+  it 'does not extract invalid ISBNs from ISBN-As' do
+    expect(described_class.extract('10.978.8898392/316')).to be_empty
+  end
+
   it 'normalizes 10-digit ISBNs' do
     str = "0-8050-6909-7 \n 2-7594-0269-X"
 

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: identifiers
 version: !ruby/object:Gem::Version
-  version: 0.4.0
+  version: 0.5.0
 platform: ruby
 authors:
 - Jonathan Hernandez
@@ -9,7 +9,7 @@ authors:
 autorequire: 
 bindir: exe
 cert_chain: []
-date: 2017-01-23 00:00:00.000000000 Z
+date: 2017-01-27 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: urn