identifiers 0.13.0 → 0.14.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: a4546231ed2288fa0d807ac0fc71f268f92de75dbc38fb057410441b3b77ca4c
-  data.tar.gz: b55eaf0b183185203c0957faf86335ac3b1996ed7312692d92daf013162798ff
+  metadata.gz: 911c52af8788814413165b25ec5dfdace4cd213906dd193216c720c31cb6d3de
+  data.tar.gz: fb75b4b356a1e87711f7b0d9a820d938d4dbb2d28730c5c8738d105f947cae00
 SHA512:
-  metadata.gz: 81cfdbbd15e12d7394deeaf45463837ecb01a995fe9bc713736578153f1725d0a6cb71913453d918ad2a1d2cd5970caa6d18656df70f3b175628c4f753f07c37
-  data.tar.gz: 5472c1c3f7b4c04d6a51f4d6fddfd476d3c8823d6c98a74de295cc730fe72bfb637b88e9c9f606d0144418a3d2b7828faf5ca145c1b53b19d8691c937fcc600f
+  metadata.gz: 72881f5981cec05c2273e8c76912a8853edaa5b6a0d0cc69a298daedde4037ee98080903fcf9c80f8290a9fe79d7e0ced24ec680dd9f92c7756c9e76c70e3bbe
+  data.tar.gz: 1255cb693b80e63ccd19e2ed0c2c5962319467c6635e8713cf7185e5e6c91dc7f952e6b614f5c1131cef45586c06fff12c4eb38e7803b8bd0cb1dfec8b0134e0

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/).
 
+## [0.14.0] - 2024-07-30
+### Added
+- Added optional prefixes argument to ISBNs extraction.
+  If passed `.extract` will only match series of numbers that are preceded by any of the passed prefixes
+
 ## [0.13.0] - 2019-09-04
 ### Added
 - Added new mode to the DOI extraction, so that it doesn't strip trailing

data/README.md

@@ -77,6 +77,17 @@ Identifiers::RepecId.extract('')
 Identifiers::URN.extract('')
 ```
 
+For `ISBN`s `.extract`, you can pass an array of prefixes as an optional parameter when you want to exclude matches that are not preceded by those prefixes (it is case insensitive and ignores ':' and extra whitespaces):
+
+```ruby
+Identifiers::ISBN.extract(
+  "IsBN:9789992158104  \n isbn-10 9789971502102 \n ISBN-13: 9789604250592 \n 9788090273412",
+  ["ISBN", "ISBN-10"]
+)
+# => ["9789992158104", "9789971502102"]
+```
+
+
 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.

data/lib/identifiers/isbn.rb

@@ -39,11 +39,25 @@ module Identifiers
       \d{1,7}   # ISBN title enumerator and check digit
       \b
     }x
+    TEXT_AFTER_PREFIX_REGEXP = ':?\s*(\d.*)$'.freeze
+
+    def self.extract(str , prefixes = [])
+      str = match_strings_with_prefix(str , prefixes) if prefixes.any?
 
-    def self.extract(str)
       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('|')
+
+      str
+        .to_s
+        .scan(/(#{prefix_regexp})#{TEXT_AFTER_PREFIX_REGEXP}/i)
+        .inject('') do |acum, (_prefix, match)|
+          acum + "#{match} \n "
+        end
+    end
+
     def self.extract_isbn_as(str)
       extract_thirteen_digit_isbns(str.to_s.scan(ISBN_A_REGEXP).join("\n").tr('/.', ''))
     end

data/spec/identifiers/isbn_spec.rb

@@ -123,4 +123,29 @@ RSpec.describe Identifiers::ISBN 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')
   end
+
+  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']
+
+      expect(described_class.extract(text, prefixes))
+        .to contain_exactly('9789992158104', '9789971502102', '9789604250592')
+    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']
+
+      expect(described_class.extract(text, prefixes))
+        .to contain_exactly('9789992158104', '9789971502102')
+    end
+
+    it 'does not extract ISBNs without prefixes' do
+      text = "9789992158104 9789971502102 9789604250592 \n 9788090273412"
+      prefixes = ['IsBn', 'ISBN-10', 'ISBN-13']
+
+      expect(described_class.extract(text, prefixes)).to be_empty
+    end
+  end
 end

metadata

@@ -1,15 +1,16 @@
 --- !ruby/object:Gem::Specification
 name: identifiers
 version: !ruby/object:Gem::Version
-  version: 0.13.0
+  version: 0.14.0
 platform: ruby
 authors:
 - Jonathan Hernandez
 - Paul Mucur
-autorequire: 
+- PatoSoft
+autorequire:
 bindir: exe
 cert_chain: []
-date: 2019-09-04 00:00:00.000000000 Z
+date: 2024-08-01 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: urn
@@ -53,7 +54,7 @@ dependencies:
     - - "~>"
       - !ruby/object:Gem::Version
         version: '3.4'
-description: 
+description:
 email:
 - support@altmetric.com
 executables: []
@@ -89,7 +90,7 @@ homepage: https://github.com/altmetric/identifiers
 licenses:
 - MIT
 metadata: {}
-post_install_message: 
+post_install_message:
 rdoc_options: []
 require_paths:
 - lib
@@ -104,19 +105,19 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.0.3
-signing_key: 
+rubygems_version: 3.3.27
+signing_key:
 specification_version: 4
 summary: Utilities library for various scholarly identifiers used by Altmetric
 test_files:
-- spec/spec_helper.rb
-- spec/identifiers/repec_id_spec.rb
-- spec/identifiers/pubmed_id_spec.rb
+- spec/identifiers/ads_bibcode_spec.rb
 - spec/identifiers/arxiv_id_spec.rb
-- spec/identifiers/urn_spec.rb
+- spec/identifiers/doi_spec.rb
 - spec/identifiers/handle_spec.rb
-- spec/identifiers/ads_bibcode_spec.rb
 - spec/identifiers/isbn_spec.rb
-- spec/identifiers/doi_spec.rb
 - spec/identifiers/national_clinical_trial_id_spec.rb
 - spec/identifiers/orcid_spec.rb
+- spec/identifiers/pubmed_id_spec.rb
+- spec/identifiers/repec_id_spec.rb
+- spec/identifiers/urn_spec.rb
+- spec/spec_helper.rb