identifiers 0.14.0 → 0.15.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 911c52af8788814413165b25ec5dfdace4cd213906dd193216c720c31cb6d3de
-  data.tar.gz: fb75b4b356a1e87711f7b0d9a820d938d4dbb2d28730c5c8738d105f947cae00
+  metadata.gz: f0cc5842531ab0baf207b1aba207fa1fc89e338b3bb6a36c689346e7b473fdd6
+  data.tar.gz: bba49e3c29eeb837cf62f0dcc20256d024ee2690e65ce1df36d7f619a4afc25f
 SHA512:
-  metadata.gz: 72881f5981cec05c2273e8c76912a8853edaa5b6a0d0cc69a298daedde4037ee98080903fcf9c80f8290a9fe79d7e0ced24ec680dd9f92c7756c9e76c70e3bbe
-  data.tar.gz: 1255cb693b80e63ccd19e2ed0c2c5962319467c6635e8713cf7185e5e6c91dc7f952e6b614f5c1131cef45586c06fff12c4eb38e7803b8bd0cb1dfec8b0134e0
+  metadata.gz: b629b7898e27360f8b0b45c537b735f9e3a2cfaa37cb0c8a4b00b226af0d16c861fefd00c3d630658c38447d05aa2e25dcd6b4f8a52e257762b3ed3469c53b73
+  data.tar.gz: ea4edebb501806152ac4affc90d766bd31b93526606cbd90c64c1c8fa62722da45ca40514e6ade5229878390ab857390d8f4502cb87b27ab6390561e7ec98a1c

data/CHANGELOG.md

@@ -2,6 +2,14 @@
 All notable changes to this project will be documented in this file. This
 project adheres to [Semantic Versioning](http://semver.org/).
 
+## [0.15.0] - 2026-06-12
+### Added
+- Extract ISBNs that mix different dash characters, including the U+2212 minus
+  sign, within a single ISBN (#31)
+
+### Fixed
+- Stop extracting spurious ISBNs from a long run of digits separated by hyphens (#34)
+
 ## [0.14.0] - 2024-07-30
 ### Added
 - Added optional prefixes argument to ISBNs extraction.

data/README.md

@@ -1,4 +1,4 @@
-# Identifiers [![Build Status](https://travis-ci.org/altmetric/identifiers.svg?branch=master)](https://travis-ci.org/altmetric/identifiers) [![Gem Version](https://badge.fury.io/rb/identifiers.svg)](https://badge.fury.io/rb/identifiers)
+# Identifiers [![Gem Version](https://badge.fury.io/rb/identifiers.svg)](https://badge.fury.io/rb/identifiers)
 
 Collection of utilities related to the extraction, validation and normalization of various scholarly identifiers. The supported list is:
 
@@ -13,6 +13,8 @@ Collection of utilities related to the extraction, validation and normalization
 - [URNs](https://en.wikipedia.org/wiki/Uniform_Resource_Name)
 - [ORCID identifiers](http://orcid.org/)
 
+**Supported Ruby versions**: >= 2.7
+
 ## Installation
 
 Add this line to your application's `Gemfile`:
@@ -106,6 +108,6 @@ We also maintain [a version of this library for PHP](https://github.com/altmetri
 
 ## License
 
-Copyright © 2016-2018 Altmetric LLP
+Copyright © 2016-2024 Altmetric LLP
 
 Distributed under the [MIT License](http://opensource.org/licenses/MIT).

data/lib/identifiers/isbn.rb

@@ -1,6 +1,9 @@
+# frozen_string_literal: true
+
 module Identifiers
   class ISBN
     ISBN_13_REGEXP = /
+      (?<!\p{Pd})         # Not part of a longer hyphen-separated run of digits
       \b
       (
         97[89]            # ISBN (GS1) Bookland prefix
@@ -12,12 +15,14 @@ module Identifiers
         \d                # Check digit
       )
       \b
-    /x
+      (?!\p{Pd})          # Not part of a longer hyphen-separated run of digits
+    /x.freeze
     ISBN_10_REGEXP = /
       (?<!              # Don't match a hyphenated or spaced ISBN-13
         97[89]
         [\p{Pd}\p{Zs}]
       )
+      (?<!\p{Pd})         # Not part of a longer hyphen-separated run of digits
       \b
       (
         \d{1,5}           # Registration group identifier
@@ -29,7 +34,8 @@ module Identifiers
         [\dX]             # Check digit
       )
       \b
-    /x
+      (?!\p{Pd})          # Not part of a longer hyphen-separated run of digits
+    /x.freeze
     ISBN_A_REGEXP = %r{
       \b
       (?<=10\.) # Directory indicator (always 10)
@@ -38,24 +44,26 @@ module Identifiers
       /         # Prefix/suffix divider
       \d{1,7}   # ISBN title enumerator and check digit
       \b
-    }x
-    TEXT_AFTER_PREFIX_REGEXP = ':?\s*(\d.*)$'.freeze
+    }x.freeze
+    # Dashes other than the ASCII hyphen we normalise to, including U+2212
+    # MINUS SIGN, which is not part of \p{Pd}
+    NON_CANONICAL_DASHES_REGEXP = /[[\p{Pd}−]&&[^-]]/.freeze
 
-    def self.extract(str , prefixes = [])
-      str = match_strings_with_prefix(str , prefixes) if prefixes.any?
+    def self.extract(str, prefixes = [])
+      str = str.to_s
+      # Normalise dashes to a single ASCII hyphen so one ISBN can mix them
+      str = str.gsub(NON_CANONICAL_DASHES_REGEXP, '-') if str.match?(NON_CANONICAL_DASHES_REGEXP)
+      return extract_with_prefix(str, prefixes) if prefixes.any?
 
       extract_isbn_as(str) + extract_thirteen_digit_isbns(str) + extract_ten_digit_isbns(str)
     end
 
-    def self.match_strings_with_prefix(str, prefixes)
-      prefix_regexp = prefixes.join('|')
+    def self.extract_with_prefix(str, prefixes)
+      prefix_regexp = generate_prefix_regexp(prefixes)
 
-      str
-        .to_s
-        .scan(/(#{prefix_regexp})#{TEXT_AFTER_PREFIX_REGEXP}/i)
-        .inject('') do |acum, (_prefix, match)|
-          acum + "#{match} \n "
-        end
+      [isbn_a_candidate_matcher, ISBN_13_REGEXP, ISBN_10_REGEXP].inject([]) do |matches, isbn_regexp|
+        matches | isbn_with_prefix_candidates(str, prefix_regexp, isbn_regexp)
+      end
     end
 
     def self.extract_isbn_as(str)
@@ -78,13 +86,13 @@ module Identifiers
         .select { |isbn, hyphen| !hyphen || isbn.count(hyphen) == 3 }
         .map { |isbn, hyphen| isbn.delete(hyphen.to_s) }
         .select { |isbn| valid_isbn_10?(isbn) }
-        .map { |isbn|
+        .map do |isbn|
           isbn.chop!
           isbn.prepend('978')
           isbn << isbn_13_check_digit(isbn).to_s
 
           isbn
-        }
+        end
     end
 
     def self.isbn_13_check_digit(isbn)
@@ -117,5 +125,34 @@ module Identifiers
     def self.digits_of(isbn)
       isbn.to_s.each_char.map { |char| char == 'X' ? 10 : Integer(char) }.to_enum
     end
+
+    def self.isbn_with_prefix_candidates(str, prefix_regexp, isbn_regexp)
+      regexp = Regexp.new("#{prefix_regexp}#{isbn_regexp}", Regexp::IGNORECASE | Regexp::EXTENDED)
+
+      str
+        .to_s
+        .scan(regexp)
+        .filter_map do |match|
+          extract(Array(match).first)&.first
+        end
+    end
+
+    def self.generate_prefix_regexp(prefixes)
+      joined_prefixes = Regexp.union(prefixes).source
+
+      Regexp.new(
+        "(?<=                 # Lookbehind for a prefix
+           #{joined_prefixes} # ie:p1|p2|p3
+         )
+         :?                   # Optional colon. If you want to use a different separator, you can add it as a prefix
+         \\s*                 # Optional whitespaces
+         ", Regexp::IGNORECASE | Regexp::EXTENDED
+      )
+    end
+
+    def self.isbn_a_candidate_matcher
+      # We capture the ISBN-A prefix for the ISBN-A regexp to work correctly when extracting ISBN-As
+      Regexp.new(ISBN_A_REGEXP.source.gsub('(?<=10\\.)', '10\.'), Regexp::IGNORECASE | Regexp::EXTENDED)
+    end
   end
 end

data/spec/identifiers/isbn_spec.rb

@@ -1,3 +1,5 @@
+# frozen_string_literal: true
+
 require 'identifiers/isbn'
 
 RSpec.describe Identifiers::ISBN do
@@ -31,6 +33,10 @@ RSpec.describe Identifiers::ISBN do
     expect(described_class.extract('ISBN: 978–0–80–506909–9')).to contain_exactly('9780805069099')
   end
 
+  it 'extracts ISBNs that mix different dash characters' do
+    expect(described_class.extract('978–3−200–01908–9')).to contain_exactly('9783200019089')
+  end
+
   it 'extracts ISBNs with spaces' do
     expect(described_class.extract('ISBN: 978 0 80 506909 9')).to contain_exactly('9780805069099')
   end
@@ -119,6 +125,14 @@ RSpec.describe Identifiers::ISBN do
     expect(described_class.extract('0-80506909-7')).to be_empty
   end
 
+  it 'does not extract ISBNs from a long run of digits separated by hyphens' do
+    expect(described_class.extract('0-1884-0-3140-0-4396-0-5652-0-4396-0-2826')).to be_empty
+  end
+
+  it 'does not extract ISBNs joined to other digits by a hyphen' do
+    expect(described_class.extract('9780805069099-9780671879198')).to be_empty
+  end
+
   it 'extracts ISBN-10s with variable width registration group identifiers' do
     expect(described_class.extract('99921-58-10-7 9971-5-0210-0 960-425-059-0 80-902734-1-6'))
       .to contain_exactly('9789992158104', '9789971502102', '9789604250592', '9788090273412')
@@ -126,16 +140,57 @@ RSpec.describe Identifiers::ISBN do
 
   context 'when passing prefixes' do
     it 'extracts only prefixed ISBNs' do
-      text = "ISBN:9789992158104  \n ISBN-10 9789971502102 \n IsbN-13: 9789604250592 \n 9788090273412"
-      prefixes = ['IsBn', 'ISBN-10', 'ISBN-13']
+      text = "ISBN:9789992158104  ISBN-10 9789971502102 \n IsbN-13: 9789604250592 \n 9788090273412"
+      prefixes = %w[IsBn ISBN-10 ISBN-13]
 
       expect(described_class.extract(text, prefixes))
         .to contain_exactly('9789992158104', '9789971502102', '9789604250592')
     end
 
+    it 'extracts ISBNs with special characters in the prefixes' do
+      text = 'ISB*N:99921-58-10-7 IS?BN-10 9971-5-0210-0 Is$bN-13: 978-0-80-506909-9 80-902734-1-6'
+      prefixes = ['IsB*n', 'IS?BN-10', 'IS$BN-13']
+
+      expect(described_class.extract(text, prefixes))
+        .to contain_exactly('9789992158104', '9789971502102', '9780805069099')
+    end
+
+    it 'extracts ISBNs with Unicode dashes' do
+      text = 'ISB*N:99921-58-10-7 IS?BN-10 9971-5-0210-0 Is$bN-13: 978–0–80–506909–9 80-902734-1-6'
+      prefixes = ['IsB*n', 'IS?BN-10', 'IS$BN-13']
+
+      expect(described_class.extract(text, prefixes))
+        .to contain_exactly('9789992158104', '9789971502102', '9780805069099')
+    end
+
+    it 'extracts ISBNs with Unicode spaces' do
+      text = 'ISBN-13: 978 0 80 506909 9'
+      prefixes = ['ISBN-13']
+
+      expect(described_class.extract(text, prefixes)).to contain_exactly('9780805069099')
+    end
+
+    it 'normalizes 10-digit ISBNs with hyphens and a check digit of X' do
+      expect(described_class.extract('ISBN:2-7594-0269-X', ['ISBN'])).to contain_exactly('9782759402694')
+    end
+
+    it 'normalizes 10-digit ISBNs with spaces and a check digit of X' do
+      text = 'ISBN-10 2 7594 0269 X'
+      prefixes = ['ISBN-10']
+
+      expect(described_class.extract(text, prefixes)).to contain_exactly('9782759402694')
+    end
+
+    it 'extracts ISBN-13s from ISBN-As' do
+      text = 'ISBN 10.978.8898392/315'
+      prefixes = %w[ISBN ISBN-10]
+
+      expect(described_class.extract(text, prefixes)).to contain_exactly('9788898392315')
+    end
+
     it 'does not extract ISBNs with different prefixes' do
-      text = "ISBN:9789992158104 \n ISBN-10 9789971502102  \n IsbN-13: 9789604250592 \n 9788090273412"
-      prefixes = ['IsBn', 'ISBN-10']
+      text = "ISBN:9789992158104 \n ISBN-10 9789971502102  IsbN-13: 9789604250592  9788090273412"
+      prefixes = %w[IsBn ISBN-10]
 
       expect(described_class.extract(text, prefixes))
         .to contain_exactly('9789992158104', '9789971502102')
@@ -143,7 +198,7 @@ RSpec.describe Identifiers::ISBN do
 
     it 'does not extract ISBNs without prefixes' do
       text = "9789992158104 9789971502102 9789604250592 \n 9788090273412"
-      prefixes = ['IsBn', 'ISBN-10', 'ISBN-13']
+      prefixes = %w[IsBn ISBN-10 ISBN-13]
 
       expect(described_class.extract(text, prefixes)).to be_empty
     end

metadata

@@ -1,16 +1,15 @@
 --- !ruby/object:Gem::Specification
 name: identifiers
 version: !ruby/object:Gem::Version
-  version: 0.14.0
+  version: 0.15.0
 platform: ruby
 authors:
 - Jonathan Hernandez
 - Paul Mucur
 - PatoSoft
-autorequire:
 bindir: exe
 cert_chain: []
-date: 2024-08-01 00:00:00.000000000 Z
+date: 1980-01-02 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: urn
@@ -32,29 +31,28 @@ dependencies:
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '10.0'
+        version: '13.2'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '10.0'
+        version: '13.2'
 - !ruby/object:Gem::Dependency
   name: rspec
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '3.4'
+        version: '3.13'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '3.4'
-description:
+        version: '3.13'
 email:
 - support@altmetric.com
 executables: []
@@ -90,7 +88,6 @@ homepage: https://github.com/altmetric/identifiers
 licenses:
 - MIT
 metadata: {}
-post_install_message:
 rdoc_options: []
 require_paths:
 - lib
@@ -105,8 +102,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.3.27
-signing_key:
+rubygems_version: 3.6.9
 specification_version: 4
 summary: Utilities library for various scholarly identifiers used by Altmetric
 test_files: