identifiers 0.5.0 → 0.6.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 036d129df184be8b4e577950bbe37c10455a2d6d
-  data.tar.gz: b35262b8180a444476fd45124ddffd5086ee3af3
+  metadata.gz: 20bb1b38cae83fa5173c1c5a955aa799ccb1dee1
+  data.tar.gz: 5885f3af6e8c0c5fef3b0418105602bdf721a0ee
 SHA512:
-  metadata.gz: 5e1ed385ed71f64287445b99452d8905d597f097be0e235e5057d443de98a0f2762f6e624633814a7fa1d2eb7973750d7439ed7a57fa94f2bc4a9d3eb0d4f09a
-  data.tar.gz: f2f32ba1157949782ed5db1d3cdbe28004d76b0743ecf1737719790e872dea024b63fc008b3c6d65873ea407f4ff8be3407856cb4b702f27ad5d57ecfa0ca41b
+  metadata.gz: 7ccfe0444e88dcc61b51c17d8ce431318c7854936604843d50fd56a96da88536ca15da90572af3352b853e9506e1c40638418d187fe359b2c8bc5ec6ab2eaa34
+  data.tar.gz: be40a3196e1c7e8f17786b53df685e7b6c4f70a182ad8363d4a1efb5e6d5471d939c2e44e89e7181a6781fab35a928ad874f086585bfa9317491cfbd7518fce8

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/).
 
+## [0.6.0] - 2017-04-08
+### Added
+- Added support for valid DOIs ending in punctuation
+
 ## [0.5.0] - 2017-01-27
 ### Added
 - Added support for ISBN-As when extracting DOIs and ISBNs
@@ -32,3 +36,4 @@ project adheres to [Semantic Versioning](http://semver.org/).
 [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
+[0.6.0]: https://github.com/altmetric/identifiers/releases/tag/v0.6.0

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', '~> 0.5'
+gem 'identifiers', '~> 0.6'
 ```
 
 And then execute:
@@ -69,6 +69,10 @@ For `URN`s, please check the [URN gem documentation](https://github.com/altmetri
 
 Bug reports and pull requests are welcome on GitHub at https://github.com/altmetric/identifiers.
 
+## Contributions
+
+* Thanks to [Tom Stuart](https://github.com/tomstuart) for [cleaning up the ISBN check digit code](https://github.com/altmetric/identifiers/pull/10).
+
 ## PHP version
 
 We also maintain [a version of this library for PHP](https://github.com/altmetric/php-identifiers).

data/lib/identifiers/doi.rb

@@ -1,7 +1,43 @@
 module Identifiers
   class DOI
+    PATTERN = %r{
+      \b
+      10 # Directory indicator (always 10)
+      \.
+      (?:
+        # ISBN-A
+        97[89]\. # ISBN (GS1) Bookland prefix
+        \d{2,8}  # ISBN registration group element and publisher prefix
+        /        # Prefix/suffix divider
+        \d{1,7}  # ISBN title enumerator and check digit
+        |
+        # DOI
+        \d{4,9} # Registrant code
+        /       # Prefix/suffix divider
+        \S+     # DOI suffix
+      )
+    }x
+    VALID_ENDING = /
+      (?:
+        \p{^Punct}  # Non-punctuation character
+        |
+        \(.+\)      # Balanced parentheses
+        |
+        2-\#        # Early Wiley DOI suffix
+      )
+      \z
+    /x
+
     def self.extract(str)
-      str.scan(%r{\b10\.(?:97[89]\.\d{2,8}/\d{1,7}|\d{4,9}/\S+)\b}).map(&:downcase)
+      str
+        .to_s
+        .downcase
+        .scan(PATTERN)
+        .map { |doi|
+          next doi if doi =~ VALID_ENDING
+
+          doi.sub(/\p{Punct}+\z/, '')
+        }
     end
   end
 end

data/lib/identifiers/isbn.rb

@@ -27,7 +27,7 @@ module Identifiers
     end
 
     def self.isbn_13_check_digit(isbn)
-      sum = isbn.each_char.zip([1, 3].cycle).reduce(0) { |sum, values| sum + (Integer(values[0]) * values[1]) }
+      sum = digits_of(isbn).zip([1, 3].cycle).map { |digit, weight| digit * weight }.reduce(:+)
       check_digit = 10 - (sum % 10)
 
       if check_digit == 10
@@ -40,7 +40,7 @@ module Identifiers
     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 = digits_of(isbn).zip([1, 3].cycle).map { |digit, weight| digit * weight }.reduce(:+)
 
       (result % 10).zero?
     end
@@ -48,11 +48,13 @@ module Identifiers
     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 = digits_of(isbn).with_index.map { |digit, weight| digit * weight.succ }.reduce(:+)
 
       (result % 11).zero?
     end
+
+    def self.digits_of(isbn)
+      isbn.each_char.map { |char| char == 'X' ? 10 : Integer(char) }.to_enum
+    end
   end
 end

data/spec/identifiers/doi_spec.rb

@@ -2,13 +2,19 @@ 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'
+    str = 'This is an example of a 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'
+  it 'extracts DOIs from anywhere in a string' do
+    str = 'This is an example of a DOI - 10.1049/el.2013.3006 - which is entirely valid'
+
+    expect(described_class.extract(str)).to contain_exactly('10.1049/el.2013.3006')
+  end
+
+  it 'downcases the DOIs extracted' do
+    str = 'This is an example of a DOI: 10.1097/01.ASW.0000443266.17665.19'
 
     expect(described_class.extract(str)).to contain_exactly('10.1097/01.asw.0000443266.17665.19')
   end
@@ -19,6 +25,10 @@ RSpec.describe Identifiers::DOI do
     expect(described_class.extract(str)).to be_empty
   end
 
+  it 'returns no DOIs if given nothing' do
+    expect(described_class.extract(nil)).to be_empty
+  end
+
   it 'extracts ISBN-As' do
     str = 'This is an ISBN-A: 10.978.8898392/315'
 
@@ -30,4 +40,40 @@ RSpec.describe Identifiers::DOI do
 
     expect(described_class.extract(str)).to be_empty
   end
+
+  it 'retains closing parentheses that are part of the DOI' do
+    str = 'This is an example of a DOI: 10.1130/2013.2502(04)'
+
+    expect(described_class.extract(str)).to contain_exactly('10.1130/2013.2502(04)')
+  end
+
+  it 'discards trailing punctuation' do
+    str = 'This is an example of a DOI: 10.1130/2013.2502.'
+
+    expect(described_class.extract(str)).to contain_exactly('10.1130/2013.2502')
+  end
+
+  it 'discards multiple contiguous trailing punctuation' do
+    str = 'This is an example of a DOI: 10.1130/2013.2502...",'
+
+    expect(described_class.extract(str)).to contain_exactly('10.1130/2013.2502')
+  end
+
+  it 'discards trailing Unicode punctuation' do
+    str = 'This is an example of a DOI: 10.1130/2013.2502…'
+
+    expect(described_class.extract(str)).to contain_exactly('10.1130/2013.2502')
+  end
+
+  it 'extracts particularly exotic DOIs' do
+    str = 'This is an example of an exotic DOI: 10.1002/(SICI)1096-8644(199601)99:1<135::AID-AJPA8>3.0.CO;2-#'
+
+    expect(described_class.extract(str)).to contain_exactly('10.1002/(sici)1096-8644(199601)99:1<135::aid-ajpa8>3.0.co;2-#')
+  end
+
+  it 'does not extract a closing parenthesis if not part of the DOI' do
+    str = '(This is an example of a DOI: 10.1130/2013.2502)'
+
+    expect(described_class.extract(str)).to contain_exactly('10.1130/2013.2502')
+  end
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: identifiers
 version: !ruby/object:Gem::Version
-  version: 0.5.0
+  version: 0.6.0
 platform: ruby
 authors:
 - Jonathan Hernandez
@@ -9,7 +9,7 @@ authors:
 autorequire: 
 bindir: exe
 cert_chain: []
-date: 2017-01-27 00:00:00.000000000 Z
+date: 2017-04-08 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: urn