identifiers 0.12.1 → 0.13.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 423438daad2350706eced26425401a5d97ae715095b54853fe55ba4f8dbbaf2d
-  data.tar.gz: 2776accbdccfc17965dd69507a0b326b2a57e275811828b05e76b47c0f54bb28
+  metadata.gz: a4546231ed2288fa0d807ac0fc71f268f92de75dbc38fb057410441b3b77ca4c
+  data.tar.gz: b55eaf0b183185203c0957faf86335ac3b1996ed7312692d92daf013162798ff
 SHA512:
-  metadata.gz: e319511db960df762b3a646239edf45ff683bef6227736c673072de6ef5d1649dd300232f93c0af0be1d7744308de4f07ebfd53582add6069c6b3f425249722b
-  data.tar.gz: 1ebd31499facbc5a51ec0dcf30fadb920e86ad6e53c20f4bb5dd66fa11c9f9cc7842a8b703348f13aac2675c0415c2c0f9464c42baafd055669c881342c33217
+  metadata.gz: 81cfdbbd15e12d7394deeaf45463837ecb01a995fe9bc713736578153f1725d0a6cb71913453d918ad2a1d2cd5970caa6d18656df70f3b175628c4f753f07c37
+  data.tar.gz: 5472c1c3f7b4c04d6a51f4d6fddfd476d3c8823d6c98a74de295cc730fe72bfb637b88e9c9f606d0144418a3d2b7828faf5ca145c1b53b19d8691c937fcc600f

data/CHANGELOG.md

@@ -2,6 +2,11 @@
 All notable changes to this project will be documented in this file. This
 project adheres to [Semantic Versioning](http://semver.org/).
 
+## [0.13.0] - 2019-09-04
+### Added
+- Added new mode to the DOI extraction, so that it doesn't strip trailing
+  periods when in `strict` mode
+
 ## [0.12.1] - 2018-04-09
 ### Fixed
 - Restored support for extracting hyphenated ISBN-10s with registration group
@@ -88,3 +93,4 @@ project adheres to [Semantic Versioning](http://semver.org/).
 [0.11.0]: https://github.com/altmetric/identifiers/releases/tag/v0.11.0
 [0.12.0]: https://github.com/altmetric/identifiers/releases/tag/v0.12.0
 [0.12.1]: https://github.com/altmetric/identifiers/releases/tag/v0.12.1
+[0.13.0]: https://github.com/altmetric/identifiers/releases/tag/v0.13.0

data/README.md

@@ -32,18 +32,34 @@ Or install it yourself as:
 ## Usage
 
 ```ruby
-Identifiers::DOI.extract('example: 10.123/abcd.efghi')
-# => ["10.123/abcd.efghi"]
+Identifiers::DOI.extract('example: 10.1234/5678.ABC')
+# => ["10.1234/5678.abc"]
 
 Identifiers::DOI.extract('no DOIs here')
 # => []
 
 Identifiers::URN.new('urn:abc:123')
 # => #<URN:0x007ff11c13d930 @urn="urn:abc:123", @nid="abc", @nss="123">
+
 Identifiers::URN('urn:abc:123')
 # => #<URN:0x007ff11c0ff568 @urn="urn:abc:123", @nid="abc", @nss="123">
 ```
 
+A small percentage of DOIs end in trailing `.`. However, having trailing periods
+being returned by the default extraction method would possibly return quite a few
+false positives.
+`DOI.extract` accepts a `strict` option, which can be set to true if we prefer to
+return DOIs ending in `.`. By default, this option is set to `false`, which strips
+any trailing `.`:
+
+```ruby
+Identifiers::DOI.extract('example: 10.1234/5678.abc.', strict: true)
+# => ["10.1234/5678.abc."]
+
+Identifiers::DOI.extract('example: 10.1234/5678.abc.')
+# => ["10.1234/5678.abc"]
+```
+
 ## By identifier
 
 `.extract` is a common method that works across all the supported identifiers.

data/lib/identifiers/doi.rb

@@ -24,11 +24,17 @@ module Identifiers
           |
           [^[:space:]]+(?![[:space:]])\p{^P}    # Suffix ending in non-punctuation
         )
+        \.{0,3}                                 # Allow a DOI to end with up to 3 .
       )
     }x
 
-    def self.extract(str)
-      str.to_s.downcase.scan(REGEXP)
+    def self.extract(str, options = {})
+      strict = options.fetch(:strict, false)
+
+      dois = str.to_s.downcase.scan(REGEXP)
+      dois = dois.map { |doi| doi.gsub(/\.+$/, '') } unless strict
+
+      dois
     end
   end
 end

data/spec/identifiers/doi_spec.rb

@@ -1,151 +1,195 @@
 require 'identifiers/doi'
 
 RSpec.describe Identifiers::DOI do
-  it 'extracts DOIs from a string' do
-    str = 'This is an example of a DOI: 10.1049/el.2013.3006'
+  OPTIONS = [{ strict: false }, { strict: true }].freeze
 
-    expect(described_class.extract(str)).to contain_exactly('10.1049/el.2013.3006')
+  def each_doi(file)
+    Pathname.new(__FILE__).join('..', '..', 'fixtures', file).each_line do |doi|
+      yield(doi.chomp!)
+    end
   end
 
-  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'
+  OPTIONS.each do |options|
+    context "when extracting with options set to #{options.inspect}" do
+      it 'extracts DOIs from a string' do
+        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
+        expect(described_class.extract(str, options)).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'
+      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('10.1097/01.asw.0000443266.17665.19')
-  end
+        expect(described_class.extract(str, options)).to contain_exactly('10.1049/el.2013.3006')
+      end
 
-  it 'does not extract a PubMed ID' do
-    str = 'This is NOT a DOI: 123456'
+      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 be_empty
-  end
+        expect(described_class.extract(str, options)).to contain_exactly('10.1097/01.asw.0000443266.17665.19')
+      end
 
-  it 'returns no DOIs if given nothing' do
-    expect(described_class.extract(nil)).to be_empty
-  end
+      it 'does not extract a PubMed ID' do
+        str = 'This is NOT a DOI: 123456'
 
-  it 'extracts ISBN-As' do
-    str = 'This is an ISBN-A: 10.978.8898392/315'
+        expect(described_class.extract(str, options)).to be_empty
+      end
 
-    expect(described_class.extract(str)).to contain_exactly('10.978.8898392/315')
-  end
+      it 'returns no DOIs if given nothing' do
+        expect(described_class.extract(nil)).to be_empty
+      end
 
-  it 'does not extract invalid ISBN-As' do
-    str = 'This is not an ISBN-A: 10.978.8898392/NotARealIsbnA'
+      it 'extracts ISBN-As' do
+        str = 'This is an ISBN-A: 10.978.8898392/315'
 
-    expect(described_class.extract(str)).to be_empty
-  end
+        expect(described_class.extract(str, options)).to contain_exactly('10.978.8898392/315')
+      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)'
+      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 contain_exactly('10.1130/2013.2502(04)')
-  end
+        expect(described_class.extract(str, options)).to be_empty
+      end
 
-  it 'discards trailing punctuation' do
-    str = 'This is an example of a DOI: 10.1130/2013.2502.'
+      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')
-  end
+        expect(described_class.extract(str, options)).to contain_exactly('10.1130/2013.2502(04)')
+      end
 
-  it 'discards multiple contiguous trailing punctuation' do
-    str = 'This is an example of a DOI: 10.1130/2013.2502...",'
+      it 'discards ellipses' 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
+        expect(described_class.extract(str, options)).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…'
+      it 'extracts old Wiley DOIs' do
+        str = 'This is an example of an old Wiley DOI: 10.1002/(SICI)1096-8644(199601)99:1<135::AID-AJPA8>3.0.CO;2-# 10.1002/(sici)1099-0690(199806)1998:6<1071::aid-ejoc1071>3.0.co;2-5'
 
-    expect(described_class.extract(str)).to contain_exactly('10.1130/2013.2502')
-  end
+        expect(described_class.extract(str, options)).to contain_exactly('10.1002/(sici)1096-8644(199601)99:1<135::aid-ajpa8>3.0.co;2-#', '10.1002/(sici)1099-0690(199806)1998:6<1071::aid-ejoc1071>3.0.co;2-5')
+      end
 
-  it 'extracts old Wiley DOIs' do
-    str = 'This is an example of an old Wiley DOI: 10.1002/(SICI)1096-8644(199601)99:1<135::AID-AJPA8>3.0.CO;2-# 10.1002/(sici)1099-0690(199806)1998:6<1071::aid-ejoc1071>3.0.co;2-5'
+      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('10.1002/(sici)1096-8644(199601)99:1<135::aid-ajpa8>3.0.co;2-#', '10.1002/(sici)1099-0690(199806)1998:6<1071::aid-ejoc1071>3.0.co;2-5')
-  end
+        expect(described_class.extract(str, options)).to contain_exactly('10.1130/2013.2502')
+      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)'
+      it 'discards trailing punctuation from old Wiley DOIs' do
+        str = 'This is an example of an old Wiley DOI: 10.1002/(SICI)1096-8644(199601)99:1<135::AID-AJPA8>3.0.CO;2-#",'
 
-    expect(described_class.extract(str)).to contain_exactly('10.1130/2013.2502')
-  end
+        expect(described_class.extract(str, options)).to contain_exactly('10.1002/(sici)1096-8644(199601)99:1<135::aid-ajpa8>3.0.co;2-#')
+      end
 
-  it 'discards trailing punctuation from old Wiley DOIs' do
-    str = 'This is an example of an old Wiley DOI: 10.1002/(SICI)1096-8644(199601)99:1<135::AID-AJPA8>3.0.CO;2-#",'
+      it 'discards trailing Unicode punctuation after balanced parentheses' do
+        str = 'This is an example of a DOI: 10.1130/2013.2502(04)…",'
 
-    expect(described_class.extract(str)).to contain_exactly('10.1002/(sici)1096-8644(199601)99:1<135::aid-ajpa8>3.0.co;2-#')
-  end
+        expect(described_class.extract(str, options)).to contain_exactly('10.1130/2013.2502(04)')
+      end
 
-  it 'discards trailing punctuation after balanced parentheses' do
-    str = 'This is an example of a DOI: This is an example of a DOI: 10.1130/2013.2502(04).'
+      it 'discards contiguous trailing punctuation after unbalanced parentheses' 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(04)')
-  end
+        expect(described_class.extract(str, options)).to contain_exactly('10.1130/2013.2502')
+      end
 
-  it 'discards contiguous trailing punctuation after balanced parentheses' do
-    str = 'This is an example of a DOI: This is an example of a DOI: 10.1130/2013.2502(04).",'
+      it 'does not extract DOIs with purely punctuation suffixes' do
+        expect(described_class.extract('10.1130/!).",', options)).to be_empty
+      end
 
-    expect(described_class.extract(str)).to contain_exactly('10.1130/2013.2502(04)')
-  end
+      it 'extracts DOIs with emoji in them' do
+        expect(described_class.extract('10.1234/🐔💩123🐔🐔🐔123', options)).to contain_exactly('10.1234/🐔💩123🐔🐔🐔123')
+      end
 
-  it 'discards trailing Unicode punctuation after balanced parentheses' do
-    str = 'This is an example of a DOI: 10.1130/2013.2502(04)…",'
+      it 'extracts DOIs separated by Unicode whitespace' do
+        expect(described_class.extract('10.1234/foo  10.1234/bar', options)).to contain_exactly('10.1234/foo', '10.1234/bar')
+      end
 
-    expect(described_class.extract(str)).to contain_exactly('10.1130/2013.2502(04)')
-  end
+      it 'does not extract DOIs with extra digits prefixed' do
+        expect(described_class.extract('110.1234/foo', options)).to be_empty
+      end
 
-  it 'discards contiguous trailing punctuation after unbalanced parentheses' do
-    str = '(This is an example of a DOI: 10.1130/2013.2502).",'
+      it 'extracts DOIs from a string with trailing closing parentheses' do
+        expect(described_class.extract('(10.1130/2013.2502(04))', options)).to contain_exactly('10.1130/2013.2502(04)')
+      end
 
-    expect(described_class.extract(str)).to contain_exactly('10.1130/2013.2502')
-  end
+      it 'extracts DOIs from a string with multiple trailing closing parentheses' do
+        expect(described_class.extract('10.1130/2013.2502(04))))', options)).to contain_exactly('10.1130/2013.2502(04)')
+      end
 
-  it 'does not overflow when given lots of trailing punctuation' do
-    str = '10.1130/2013.2502' + ('.' * 10000)
+      it 'extracts DOIs with parentheses within the suffix' do
+        expect(described_class.extract('10.1016/0005-2744(70)90072-0', options)).to contain_exactly('10.1016/0005-2744(70)90072-0')
+      end
 
-    expect(described_class.extract(str)).to contain_exactly('10.1130/2013.2502')
+      it 'extracts all DOIs from a Crossref sample' do
+        each_doi('dois.txt') { |doi|
+          expect(described_class.extract(doi, options)).to contain_exactly(doi)
+        }
+      end
+    end
   end
 
-  it 'does not extract DOIs with purely punctuation suffixes' do
-    expect(described_class.extract('10.1130/!).",')).to be_empty
-  end
+  context 'when no options are provided' do
+    it 'discards trailing punctuation' do
+      str = 'This is an example of a DOI: 10.1130/2013.2502.'
 
-  it 'extracts DOIs with emoji in them' do
-    expect(described_class.extract('10.1234/🐔💩123🐔🐔🐔123')).to contain_exactly('10.1234/🐔💩123🐔🐔🐔123')
-  end
+      expect(described_class.extract(str)).to contain_exactly('10.1130/2013.2502')
+    end
 
-  it 'extracts DOIs separated by Unicode whitespace' do
-    expect(described_class.extract('10.1234/foo  10.1234/bar')).to contain_exactly('10.1234/foo', '10.1234/bar')
-  end
+    it 'discards multiple contiguous trailing punctuation' do
+      str = 'This is an example of a DOI: 10.1130/2013.2502...",'
 
-  it 'does not extract DOIs with extra digits prefixed' do
-    expect(described_class.extract('110.1234/foo')).to be_empty
-  end
+      expect(described_class.extract(str)).to contain_exactly('10.1130/2013.2502')
+    end
 
-  it 'extracts DOIs from a string with trailing closing parentheses' do
-    expect(described_class.extract('10.1130/2013.2502(04))')).to contain_exactly('10.1130/2013.2502(04)')
-  end
+    it 'discards trailing punctuation after balanced parentheses' do
+      str = 'This is an example of a DOI: This is an example of a DOI: 10.1130/2013.2502(04).'
 
-  it 'extracts DOIs from a string with multiple trailing closing parentheses' do
-    expect(described_class.extract('10.1130/2013.2502(04))))')).to contain_exactly('10.1130/2013.2502(04)')
-  end
+      expect(described_class.extract(str)).to contain_exactly('10.1130/2013.2502(04)')
+    end
 
-  it 'extracts DOIs with parentheses within the suffix' do
-    expect(described_class.extract('10.1016/0005-2744(70)90072-0')).to contain_exactly('10.1016/0005-2744(70)90072-0')
+    it 'discards contiguous trailing punctuation after balanced parentheses' do
+      str = 'This is an example of a DOI: 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 'does not overflow when given lots of trailing punctuation' do
+      str = '10.1130/2013.2502' + ('.' * 10000)
+
+      expect(described_class.extract(str)).to contain_exactly('10.1130/2013.2502')
+    end
   end
 
-  it 'extracts all DOIs from a Crossref sample' do
-    Pathname.new(__FILE__).join('..', '..', 'fixtures', 'dois.txt').each_line do |doi|
-      doi.chomp!
+  context 'with strict mode on' do
+    it 'extracts DOIs ending with trailing periods' do
+      str = 'This is an example of a DOI: 10.1130/2013.2502...",'
+
+      expect(described_class.extract(str, strict: true)).to contain_exactly('10.1130/2013.2502...')
+    end
+
+    it 'keeps trailing punctuation after balanced parentheses' do
+      str = 'This is an example of a DOI: This is an example of a DOI: 10.1130/2013.2502(04).'
+
+      expect(described_class.extract(str, strict: true)).to contain_exactly('10.1130/2013.2502(04).')
+    end
+
+    it 'discards contiguous trailing punctuation after balanced parentheses' do
+      str = 'This is an example of a DOI: This is an example of a DOI: 10.1130/2013.2502(04).",'
+
+      expect(described_class.extract(str, strict: true)).to contain_exactly('10.1130/2013.2502(04).')
+    end
+
+    it 'limits the trailing periods to 3' do
+      str = 'This is an example of a DOI: 10.1130/2013.2502.......'
+
+      expect(described_class.extract(str, strict: true)).to contain_exactly('10.1130/2013.2502...')
+    end
 
-      expect(described_class.extract(doi)).to contain_exactly(doi)
+    it 'extracts all DOIs from a Crossref sample, keeping the trailing periods' do
+      each_doi('strict_mode_dois.txt') { |doi|
+        expect(described_class.extract(doi, strict: true)).to contain_exactly(doi)
+      }
     end
   end
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: identifiers
 version: !ruby/object:Gem::Version
-  version: 0.12.1
+  version: 0.13.0
 platform: ruby
 authors:
 - Jonathan Hernandez
@@ -9,7 +9,7 @@ authors:
 autorequire: 
 bindir: exe
 cert_chain: []
-date: 2018-04-09 00:00:00.000000000 Z
+date: 2019-09-04 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: urn
@@ -25,20 +25,6 @@ dependencies:
     - - "~>"
       - !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
@@ -118,8 +104,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubyforge_project: 
-rubygems_version: 2.7.3
+rubygems_version: 3.0.3
 signing_key: 
 specification_version: 4
 summary: Utilities library for various scholarly identifiers used by Altmetric