identifiers 0.10.0 → 0.11.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 612736c08372d3108c5b62dbab508417c3b67a73
-  data.tar.gz: a693d991efe3c913cce2fe6fc4496999c0883103
+  metadata.gz: ab7d56e3e6048da713104ab263f36bdd96a9da98
+  data.tar.gz: 4d2636ffdeeb7b3a1e563b36c761e39dc81f488e
 SHA512:
-  metadata.gz: 19ca1c46ff464e700b3158794edbcdb677d25fa2e3b7f557595d897e430a84e725d0d2a0ce0e8904af713c9adead71d26ff0dd7c72b788a033c451fec31ba73b
-  data.tar.gz: cfcfc156b3ca04b2becf36f810a0a6b3ad4e402a3eb6d1b2ad4642091b91c20cd64e5e739d30f2e4fb35b849c583e08cab5d4a8e06996ced17db3a593b6c61a8
+  metadata.gz: 3a62e98dcf6f35c180e1dd2c2e574f8993c6123a182e6fee782a96bc85e342de5b3894455f8fa99325100edcb8f3a9f0fa33d3135040b775bbf6e0b442bc1992
+  data.tar.gz: fcc0d3d178e49ee0eefed149200f4f8489d58c4cb953b21a0cab63067ae237432eee607e8e81460f70cbdba9ebb8d1d44c6f3d01fe82f16c9038a12f31aba609

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/).
 
+## [0.11.0] - 2018-03-12
+## Fixed
+- Stricter ISBN extraction: consistent hyphenation (#27) and correct number of groups (#28)
+- Prevent stack overflow when extracting DOIS (#25)
+
 ## [0.10.0] - 2017-12-20
 ### Added
 - Extract PubMed IDs from URLs (e.g https://www.ncbi.nlm.nih.gov/pubmed/123456) and URIs with schemes `pmid:` and `info:pmid`
@@ -68,3 +73,4 @@ project adheres to [Semantic Versioning](http://semver.org/).
 [0.9.0]: https://github.com/altmetric/identifiers/releases/tag/v0.9.0
 [0.9.1]: https://github.com/altmetric/identifiers/releases/tag/v0.9.1
 [0.10.0]: https://github.com/altmetric/identifiers/releases/tag/v0.10.0
+[0.11.0]: https://github.com/altmetric/identifiers/releases/tag/v0.11.0

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', '~> 0.9'
+gem 'identifiers', '~> 0.11'
 ```
 
 And then execute:
@@ -79,6 +79,6 @@ We also maintain [a version of this library for PHP](https://github.com/altmetri
 
 ## License
 
-Copyright © 2016-2017 Altmetric LLP
+Copyright © 2016-2018 Altmetric LLP
 
 Distributed under the [MIT License](http://opensource.org/licenses/MIT).

data/lib/identifiers/doi.rb

@@ -29,20 +29,15 @@ module Identifiers
     /x
 
     def self.extract(str)
-      str.to_s.downcase.scan(REGEXP).map { |doi| strip_punctuation(doi) }.compact
+      str.to_s.downcase.scan(REGEXP).map { |doi| extract_one(doi) }.compact
     end
 
     def self.extract_one(str)
-      match = str.to_s.downcase[REGEXP]
-      return unless match
+      while (match = str.to_s.downcase[REGEXP])
+        break match if match =~ VALID_ENDING
 
-      strip_punctuation(match)
-    end
-
-    def self.strip_punctuation(doi)
-      return doi if doi =~ VALID_ENDING
-
-      extract_one(doi.sub(/\p{Punct}\z/, ''))
+        str = match.sub(/\p{Punct}\z/, '')
+      end
     end
   end
 end

data/lib/identifiers/isbn.rb

@@ -1,99 +1,107 @@
-module Identifiers
-  class ISBN
-    ISBN_13_REGEXP = /
-      \b
-      97[89]            # ISBN (GS1) Bookland prefix
-      [\p{Pd}\p{Zs}]?   # Optional hyphenation
-      (?:
-        \d              # Digit
-        [\p{Pd}\p{Zs}]? # Optional hyphenation
-      ){9}
-      \d                # Check digit
-      \b
-    /x
-    ISBN_10_REGEXP = /
-      (?<!              # Don't match a hyphenated or spaced ISBN-13
-        97[89]
-        [\p{Pd}\p{Zs}]
-      )
-      \b
-      (?:
-        \d              # Digit
-        [\p{Pd}\p{Zs}]? # Optional hyphenation
-      ){9}
-      [\dX]             # Check digit
-      \b
-    /x
-    ISBN_A_REGEXP = %r{
-      \b
-      (?<=10\.) # Directory indicator (always 10)
-      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
-      \b
-    }x
-
-    def self.extract(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.to_s.scan(ISBN_A_REGEXP).join("\n").tr('/.', ''))
-    end
-
-    def self.extract_thirteen_digit_isbns(str)
-      str
-        .to_s
-        .scan(ISBN_13_REGEXP)
-        .map { |isbn| isbn.gsub(/[\p{Pd}\p{Zs}]/, '') }
-        .select { |isbn| valid_isbn_13?(isbn) }
-    end
-
-    def self.extract_ten_digit_isbns(str)
-      str
-        .to_s
-        .scan(ISBN_10_REGEXP)
-        .map { |isbn| isbn.gsub(/[\p{Pd}\p{Zs}]/, '') }
-        .select { |isbn| valid_isbn_10?(isbn) }
-        .map { |isbn|
-          isbn.chop!
-          isbn.prepend('978')
-          isbn << isbn_13_check_digit(isbn).to_s
-
-          isbn
-        }
-    end
-
-    def self.isbn_13_check_digit(isbn)
-      sum = digits_of(isbn).zip([1, 3].cycle).map { |digit, weight| digit * weight }.reduce(:+)
-      check_digit = 10 - (sum % 10)
-
-      if check_digit == 10
-        0
-      else
-        check_digit
-      end
-    end
-
-    def self.valid_isbn_13?(isbn)
-      return false unless isbn =~ ISBN_13_REGEXP
-
-      result = digits_of(isbn).zip([1, 3].cycle).map { |digit, weight| digit * weight }.reduce(:+)
-
-      (result % 10).zero?
-    end
-
-    def self.valid_isbn_10?(isbn)
-      return false unless isbn =~ ISBN_10_REGEXP
-
-      result = digits_of(isbn).with_index.map { |digit, weight| digit * weight.succ }.reduce(:+)
-
-      (result % 11).zero?
-    end
-
-    def self.digits_of(isbn)
-      isbn.to_s.each_char.map { |char| char == 'X' ? 10 : Integer(char) }.to_enum
-    end
-  end
-end
+module Identifiers
+  class ISBN
+    ISBN_13_REGEXP = /
+      \b
+      (
+        97[89]            # ISBN (GS1) Bookland prefix
+        ([\p{Pd}\p{Zs}])? # Optional hyphenation
+        (?:
+          \d              # Digit
+          \2?             # Optional hyphenation
+        ){9}
+        \d                # Check digit
+      )
+      \b
+    /x
+    ISBN_10_REGEXP = /
+      (?<!              # Don't match a hyphenated or spaced ISBN-13
+        97[89]
+        [\p{Pd}\p{Zs}]
+      )
+      \b
+      (
+        \d                # Digit
+        ([\p{Pd}\p{Zs}])? # Optional hyphenation
+        (?:
+          \d              # Digit
+          \2?             # Optional hyphenation
+        ){8}
+        [\dX]             # Check digit
+      )
+      \b
+    /x
+    ISBN_A_REGEXP = %r{
+      \b
+      (?<=10\.) # Directory indicator (always 10)
+      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
+      \b
+    }x
+
+    def self.extract(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.to_s.scan(ISBN_A_REGEXP).join("\n").tr('/.', ''))
+    end
+
+    def self.extract_thirteen_digit_isbns(str)
+      str
+        .to_s
+        .scan(ISBN_13_REGEXP)
+        .select { |isbn, hyphen| !hyphen || isbn.count(hyphen) == 4 }
+        .map { |isbn, hyphen| isbn.delete(hyphen.to_s) }
+        .select { |isbn| valid_isbn_13?(isbn) }
+    end
+
+    def self.extract_ten_digit_isbns(str)
+      str
+        .to_s
+        .scan(ISBN_10_REGEXP)
+        .select { |isbn, hyphen| !hyphen || isbn.count(hyphen) == 3 }
+        .map { |isbn, hyphen| isbn.delete(hyphen.to_s) }
+        .select { |isbn| valid_isbn_10?(isbn) }
+        .map { |isbn|
+          isbn.chop!
+          isbn.prepend('978')
+          isbn << isbn_13_check_digit(isbn).to_s
+
+          isbn
+        }
+    end
+
+    def self.isbn_13_check_digit(isbn)
+      sum = digits_of(isbn).zip([1, 3].cycle).map { |digit, weight| digit * weight }.reduce(:+)
+      check_digit = 10 - (sum % 10)
+
+      if check_digit == 10
+        0
+      else
+        check_digit
+      end
+    end
+
+    def self.valid_isbn_13?(isbn)
+      return false unless isbn =~ ISBN_13_REGEXP
+
+      result = digits_of(isbn).zip([1, 3].cycle).map { |digit, weight| digit * weight }.reduce(:+)
+
+      (result % 10).zero?
+    end
+
+    def self.valid_isbn_10?(isbn)
+      return false unless isbn =~ ISBN_10_REGEXP
+
+      result = digits_of(isbn).with_index.map { |digit, weight| digit * weight.succ }.reduce(:+)
+
+      (result % 11).zero?
+    end
+
+    def self.digits_of(isbn)
+      isbn.to_s.each_char.map { |char| char == 'X' ? 10 : Integer(char) }.to_enum
+    end
+  end
+end

data/spec/identifiers/doi_spec.rb

@@ -107,6 +107,12 @@ RSpec.describe Identifiers::DOI do
     expect(described_class.extract(str)).to contain_exactly('10.1130/2013.2502')
   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
+
   it 'does not extract DOIs with purely punctuation suffixes' do
     expect(described_class.extract('10.1130/!).",')).to be_empty
   end

data/spec/identifiers/isbn_spec.rb

@@ -1,97 +1,121 @@
-require 'identifiers/isbn'
-
-RSpec.describe Identifiers::ISBN do
-  it 'extracts a ISBN' do
-    expect(described_class.extract('ISBN: 9780805069099')).to contain_exactly('9780805069099')
-  end
-
-  it 'extracts ISBNs when given as a number' do
-    isbn = 9780805069099
-
-    expect(described_class.extract(isbn)).to contain_exactly('9780805069099')
-  end
-
-  it 'normalizes 13-digit ISBNs' do
-    str = "978-0-80-506909-9\n978-0-67-187919-8"
-
-    expect(described_class.extract(str)).to contain_exactly('9780805069099', '9780671879198')
-  end
-
-  it 'extracts multiple ISBN-13s separated by a space' do
-    str = '978-0-80-506909-9 978-0-67-187919-8'
-
-    expect(described_class.extract(str)).to contain_exactly('9780805069099', '9780671879198')
-  end
-
-  it 'extracts ISBNs with hyphens' 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
-
-  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"
-
-    expect(described_class.extract(str)).to contain_exactly('9780805069099', '9782759402694')
-  end
-
-  it 'extracts multiple 10-digit ISBNs separated by a space' do
-    str = '0-8050-6909-7 2-7594-0269-X'
-
-    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
-
-  it 'normalizes 10-digit ISBNs with spaces' 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
-
-  it 'does not extract invalid 13-digit ISBNs' do
-    expect(described_class.extract('9783319217280')).to be_empty
-  end
-
-  it 'does not extract invalid 10-digit ISBNs' do
-    expect(described_class.extract('3319217280')).to be_empty
-  end
-
-  it 'does not extract ISBN-10s from hyphenated ISBN-13s' do
-    expect(described_class.extract('978-0-309-57079-4')).to contain_exactly('9780309570794')
-  end
-
-  it 'does not extract ISBN-10s from space-separated ISBN-13s' do
-    expect(described_class.extract('978 0 309 57079 4')).to contain_exactly('9780309570794')
-  end
-end
+require 'identifiers/isbn'
+
+RSpec.describe Identifiers::ISBN do
+  it 'extracts a ISBN' do
+    expect(described_class.extract('ISBN: 9780805069099')).to contain_exactly('9780805069099')
+  end
+
+  it 'extracts ISBNs when given as a number' do
+    isbn = 9780805069099
+
+    expect(described_class.extract(isbn)).to contain_exactly('9780805069099')
+  end
+
+  it 'normalizes 13-digit ISBNs' do
+    str = "978-0-80-506909-9\n978-0-67-187919-8"
+
+    expect(described_class.extract(str)).to contain_exactly('9780805069099', '9780671879198')
+  end
+
+  it 'extracts multiple ISBN-13s separated by a space' do
+    str = '978-0-80-506909-9 978-0-67-187919-8'
+
+    expect(described_class.extract(str)).to contain_exactly('9780805069099', '9780671879198')
+  end
+
+  it 'extracts ISBNs with hyphens' 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
+
+  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"
+
+    expect(described_class.extract(str)).to contain_exactly('9780805069099', '9782759402694')
+  end
+
+  it 'extracts multiple 10-digit ISBNs separated by a space' do
+    str = '0-8050-6909-7 2-7594-0269-X'
+
+    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
+
+  it 'normalizes 10-digit ISBNs with spaces' 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
+
+  it 'does not extract invalid 13-digit ISBNs' do
+    expect(described_class.extract('9783319217280')).to be_empty
+  end
+
+  it 'does not extract invalid 10-digit ISBNs' do
+    expect(described_class.extract('3319217280')).to be_empty
+  end
+
+  it 'does not extract ISBN-10s from hyphenated ISBN-13s' do
+    expect(described_class.extract('978-0-309-57079-4')).to contain_exactly('9780309570794')
+  end
+
+  it 'does not extract ISBN-10s from space-separated ISBN-13s' do
+    expect(described_class.extract('978 0 309 57079 4')).to contain_exactly('9780309570794')
+  end
+
+  it 'does not extract ISBN-13s from strings with inconsistent hyphenation' do
+    expect(described_class.extract('978-0 80-506909 9')).to be_empty
+  end
+
+  it 'does not extract ISBN-10s from strings with inconsistent hyphenation' do
+    expect(described_class.extract('0-8050 6909-7')).to be_empty
+  end
+
+  it 'does not extract ISBN-13s if they have more than five groups' do
+    expect(described_class.extract('978-0-80-506-909-9')).to be_empty
+  end
+
+  it 'does not extract ISBN-13s if they have less than five groups' do
+    expect(described_class.extract('978-0-80506909-9')).to be_empty
+  end
+
+  it 'does not extract ISBN-10s if they have more than four groups' do
+    expect(described_class.extract('0-8050-69-09-7')).to be_empty
+  end
+
+  it 'does not extract ISBN-10s if they have less than four groups' do
+    expect(described_class.extract('0-80506909-7')).to be_empty
+  end
+end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: identifiers
 version: !ruby/object:Gem::Version
-  version: 0.10.0
+  version: 0.11.0
 platform: ruby
 authors:
 - Jonathan Hernandez
@@ -9,7 +9,7 @@ authors:
 autorequire: 
 bindir: exe
 cert_chain: []
-date: 2017-12-20 00:00:00.000000000 Z
+date: 2018-03-12 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: urn