identifiers 0.3.1 → 0.4.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 94c2604feed758edf36b8f8f50a2b1538a8c35bc
-  data.tar.gz: 986267a6b22a62017d96f08ebf4dbb02a988c9f0
+  metadata.gz: ab0f2da0f90f2dda268319d5be99dc314bd9b9fe
+  data.tar.gz: 443f4aead25198aa6d267fa9c67a3800739f837c
 SHA512:
-  metadata.gz: 88eba550c8d0b5845a8313287bbbc2c17b6641a4eeb43d3b300f1e9fe7e62edc5fcb688306b2def0a6b31e6d42cc655a83f3f5b21df632ac3997818303cf6ccd
-  data.tar.gz: 2be54f4d562fe47cae613626cc6e4637f08761cfd36430657e94de5667251255dd1e46d14d0062b99cd6227c4874dc1d622e2d8fe2df55c79eb5103e8783bda8
+  metadata.gz: 51dc9476b30151bda26a037ae4dba6e25d59feef23af27bbc7d9ca7ab497221ef4117194a9524a4ba552cf708061bcc80b80b4404735abc08f4bbd38b615f3ad
+  data.tar.gz: 088d481f41064ec32560dea76c25a0ddfdb3f731937bda7c0a0d32b2c2dd3e1d44e96f5e6eea2b4410a7fcb57c47779ca0adb68b5b41806256ef21504bc840d7

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/).
 
+## [0.4.0] - 2017-01-23
+### Changed
+- Extract ISBNs separated by spaces as well as hyphens
+
 ## [0.3.1] - 2016-12-06
 ### Fixed
 - Fix ISBN-10 to 13 conversion when check digit is 10
@@ -17,3 +21,9 @@ project adheres to [Semantic Versioning](http://semver.org/).
 ## [0.1.0] - 2016-10-21
 ### Added
 - Initial release
+
+[0.1.0]: https://github.com/altmetric/identifiers/releases/tag/v0.1.0
+[0.2.0]: https://github.com/altmetric/identifiers/releases/tag/v0.2.0
+[0.3.0]: https://github.com/altmetric/identifiers/releases/tag/v0.2.0
+[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

data/README.md

@@ -1,25 +1,24 @@
-# 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 [![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)
 
 Collection of utilities related to the extraction, validation and normalization of various scholarly identifiers. The supported list is:
+
 - [ADS Bibcodes](http://adsdoc.harvard.edu/abs_doc/help_pages/bibcodes.html)
-- [arXiv](https://arxiv.org/help/arxiv_identifier)
-- [DOI](https://www.doi.org/)
-- [Handle](https://en.wikipedia.org/wiki/Handle_System)
-- [ISBN](https://en.wikipedia.org/wiki/International_Standard_Book_Number)
-- [National Clinic Trials](https://clinicaltrials.gov/)
-- [PubMed](http://www.ncbi.nlm.nih.gov/pubmed)
-- [RePEc](https://en.wikipedia.org/wiki/Research_Papers_in_Economics)
-- [URN](https://en.wikipedia.org/wiki/Uniform_Resource_Name)
-- [ORCID](http://orcid.org/)
+- [arXiv IDs](https://arxiv.org/help/arxiv_identifier)
+- [DOIs](https://www.doi.org/)
+- [Handles](https://en.wikipedia.org/wiki/Handle_System)
+- [ISBNs](https://en.wikipedia.org/wiki/International_Standard_Book_Number)
+- [National Clinical Trial IDs](https://clinicaltrials.gov/)
+- [PubMed IDs](http://www.ncbi.nlm.nih.gov/pubmed)
+- [RePEc IDs](https://en.wikipedia.org/wiki/Research_Papers_in_Economics)
+- [URNs](https://en.wikipedia.org/wiki/Uniform_Resource_Name)
+- [ORCID identifiers](http://orcid.org/)
 
 ## Installation
 
-Add this line to your application's Gemfile:
+Add this line to your application's `Gemfile`:
 
 ```ruby
-gem 'identifiers', '~> 0.3'
+gem 'identifiers', '~> 0.4'
 ```
 
 And then execute:
@@ -34,9 +33,15 @@ Or install it yourself as:
 
 ```ruby
 Identifiers::DOI.extract('example: 10.123/abcd.efghi')
+# => ["10.123/abcd.efghi"]
+
+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">
 ```
 
 ## By identifier
@@ -56,7 +61,7 @@ Identifiers::RepecId.extract('')
 Identifiers::URN.extract('')
 ```
 
-But for some identifiers might have more. Check their implementation to see all the methods available.
+But for some identifiers might have more. Check [their implementation](https://github.com/altmetric/identifiers/tree/master/lib/identifiers) to see all the methods available.
 
 For `URN`s, please check the [URN gem documentation](https://github.com/altmetric/urn) to see all the available options.
 
@@ -64,6 +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.
 
+## PHP version
+
+We also maintain [a version of this library for PHP](https://github.com/altmetric/php-identifiers).
+
 ## License
 
 Copyright © 2016 Altmetric LLP

data/lib/identifiers/isbn.rb

@@ -8,11 +8,11 @@ module Identifiers
     end
 
     def self.extract_thirteen_digit_isbns(str)
-      str.tr('-', '').scan(REGEX_13).select { |isbn| valid_isbn_13?(isbn) }
+      str.gsub(/(?<=\d)[- ](?=\d)/, '').scan(REGEX_13).select { |isbn| valid_isbn_13?(isbn) }
     end
 
     def self.extract_ten_digit_isbns(str)
-      str.tr('-', '').scan(REGEX_10).select { |isbn| valid_isbn_10?(isbn) }.map { |isbn|
+      str.gsub(/(?<=\d)[- ](?=[\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/lib/identifiers/urn.rb

@@ -1,3 +1,4 @@
+# Documentation at https://github.com/altmetric/urn
 require 'urn'
 
 module Identifiers

data/spec/identifiers/isbn_spec.rb

@@ -11,6 +11,14 @@ RSpec.describe Identifiers::ISBN do
     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 spaces' do
+    expect(described_class.extract('ISBN: 978 0 80 506909 9')).to contain_exactly('9780805069099')
+  end
+
   it 'normalizes 10-digit ISBNs' do
     str = "0-8050-6909-7 \n 2-7594-0269-X"
 
@@ -21,6 +29,14 @@ RSpec.describe Identifiers::ISBN 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 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

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: identifiers
 version: !ruby/object:Gem::Version
-  version: 0.3.1
+  version: 0.4.0
 platform: ruby
 authors:
 - Jonathan Hernandez
@@ -9,7 +9,7 @@ authors:
 autorequire: 
 bindir: exe
 cert_chain: []
-date: 2016-12-06 00:00:00.000000000 Z
+date: 2017-01-23 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: urn