identifiers 0.7.0 → 0.8.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: d5c6a569245a2c9931eb0fd3a4f4e5e234254c6d
-  data.tar.gz: 41d5ea41e4fbf1bc967d27f671e3777991907d3a
+  metadata.gz: 1d323ecfde9659ed9a795b2b2519450d33ec77c6
+  data.tar.gz: 391573ad4170738967c32597eee590554f47d59a
 SHA512:
-  metadata.gz: 08707a69b6d6143e13db5f8b3a4d8e58f54089fd37a7382296898ce4f5ac6b6dcb8ccd7a99535009074ce679d47f85fe0c51737cfb7f3b019b39b3855e000716
-  data.tar.gz: 03d64f650ebe7e4c411ad77c98d83c1a58be7eb3a034183d158cd615584a4d7fd5beb2a7197cdf39ee64450cc9e09c06162f526bef7238b92c811e6704e2dffd
+  metadata.gz: b50b32b55b82b97b3d07bc6613c064ffadf59c760f51ba9b26b1e200c4efe883747bb47b89e889597da2f56e426138412acb21797eddc9da699f94829d65bf17
+  data.tar.gz: 509003d4b24d3cde4b350b5198384d42c5232ac3417007bdc9a8823e07f1551a61ba6c08553fea19f731dd319723d9c7c590d003d31152b5389aa9cb356587b7

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/).
 
+## [0.8.0] - 2017-04-10
+### Added
+- Added support for ISBNs with digits separated by Unicode whitespace and dashes
+
 ## [0.7.0] - 2017-04-10
 ### Added
 - Added support for cleaning trailing punctuation from DOIs that also end in punctuation
@@ -42,3 +46,4 @@ project adheres to [Semantic Versioning](http://semver.org/).
 [0.5.0]: https://github.com/altmetric/identifiers/releases/tag/v0.5.0
 [0.6.0]: https://github.com/altmetric/identifiers/releases/tag/v0.6.0
 [0.7.0]: https://github.com/altmetric/identifiers/releases/tag/v0.7.0
+[0.8.0]: https://github.com/altmetric/identifiers/releases/tag/v0.8.0

data/README.md

@@ -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', '~> 0.7'
+gem 'identifiers', '~> 0.8'
 ```
 
 And then execute:

data/lib/identifiers/isbn.rb

@@ -13,11 +13,11 @@ module Identifiers
     end
 
     def self.extract_thirteen_digit_isbns(str)
-      str.gsub(/(?<=\d)[- ](?=\d)/, '').scan(REGEX_13).select { |isbn| valid_isbn_13?(isbn) }
+      str.gsub(/(?<=\d)[\p{Pd}\p{Zs}](?=\d)/, '').scan(REGEX_13).select { |isbn| valid_isbn_13?(isbn) }
     end
 
     def self.extract_ten_digit_isbns(str)
-      str.gsub(/(?<=\d)[- ](?=[\dX])/i, '').scan(REGEX_10).select { |isbn| valid_isbn_10?(isbn) }.map { |isbn|
+      str.gsub(/(?<=\d)[\p{Pd}\p{Zs}](?=[\dX])/i, '').scan(REGEX_10).select { |isbn| valid_isbn_10?(isbn) }.map { |isbn|
         isbn.chop!
         isbn.prepend('978')
         isbn << isbn_13_check_digit(isbn).to_s

data/spec/identifiers/isbn_spec.rb

@@ -15,10 +15,18 @@ RSpec.describe Identifiers::ISBN do
     expect(described_class.extract('ISBN: 978-0-80-506909-9')).to contain_exactly('9780805069099')
   end
 
+  it 'extracts ISBNs with Unicode dashes' do
+    expect(described_class.extract('ISBN: 978–0–80–506909–9')).to contain_exactly('9780805069099')
+  end
+
   it 'extracts ISBNs with spaces' do
     expect(described_class.extract('ISBN: 978 0 80 506909 9')).to contain_exactly('9780805069099')
   end
 
+  it 'extracts ISBNs with Unicode spaces' 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
@@ -33,6 +41,10 @@ RSpec.describe Identifiers::ISBN do
     expect(described_class.extract(str)).to contain_exactly('9780805069099', '9782759402694')
   end
 
+  it 'normalizes 10-digit ISBNs with Unicode dashes' do
+    expect(described_class.extract('0–8050–6909–7')).to contain_exactly('9780805069099')
+  end
+
   it 'normalizes 10-digit ISBNs with a check digit of 10' do
     expect(described_class.extract('4423272350')).to contain_exactly('9784423272350')
   end
@@ -41,6 +53,10 @@ RSpec.describe Identifiers::ISBN do
     expect(described_class.extract('0 8050 6909 7')).to contain_exactly('9780805069099')
   end
 
+  it 'normalizes 10-digit ISBNs with Unicode spaces' do
+    expect(described_class.extract('0 8050 6909 7')).to contain_exactly('9780805069099')
+  end
+
   it 'normalizes 10-digit ISBNs with spaces and a check digit of X' do
     expect(described_class.extract('2 7594 0269 X')).to contain_exactly('9782759402694')
   end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: identifiers
 version: !ruby/object:Gem::Version
-  version: 0.7.0
+  version: 0.8.0
 platform: ruby
 authors:
 - Jonathan Hernandez