confidential_info_redactor_lite 1.0.11 → 1.0.12

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 6a5ec9e9eeb82984f87cba0c612404b7a6e9f4b4
-  data.tar.gz: 5e410055fe45224d70930f7e6c8f2858eeda4bc0
+  metadata.gz: 96535d227ea64669725219062661210c94bdb9dc
+  data.tar.gz: 4090e57ce0c991d4d33d1dc37207d0e016410de5
 SHA512:
-  metadata.gz: 5e3c14787d5013846629bbab16ef5117fe96a0e8d1193be266e1325f7d21ff978100f4af666289d933869f744d7bd0383e7c136f81d6bac733e72dabde40f766
-  data.tar.gz: ef113dda2f3a5928f1281d0fb96fd9d99bc8d4d8d7bc0c5aa5d227b77e3182b05934e498aa8c7481bb1c80ee51be7a1132c3740207b33e19264c9005bf8d5b77
+  metadata.gz: d118b2bf42e77d568d548ff9757a5a009a88d57ce5b1a510143723fe030a8a5f034703ebbfa638bb348aa1f54d3c97c836aaea077ff9f355be19a6418131c607
+  data.tar.gz: eac920b4c54966f04f39116790eb974d7b700eb423737546c1cb30c8b25b38e4d0f530825ed446160e81e4b6ea0a52e5b329041c82f9ac8bb0d6e7e0081ec5f4

data/lib/confidential_info_redactor_lite/extractor.rb

@@ -2,7 +2,7 @@ module ConfidentialInfoRedactorLite
   # This class extracts proper nouns from a text
   class Extractor
     # Rubular: http://rubular.com/r/qE0g4r9zR7
-    EXTRACT_REGEX = /(?<=\s|^|\s\"|\s\“|\s\«|\s\‹|\s\”|\s\»|\s\›)([A-Z]\S*\s)*[A-Z]\S*(?=(\s|\.|\z))|(?<=\s|^|\s\"|\s\”|\s\»|\s\›|\s\“|\s\«|\s\‹)[i][A-Z][a-z]+/
+    EXTRACT_REGEX = /(?<=\s|^|\s\"|\s\“|\s\«|\s\‹|\s\”|\s\»|\s\›)(\p{Lu}\S*\s)*\p{Lu}\S*(?=(\s|\.|\z))|(?<=\s|^|\s\"|\s\”|\s\»|\s\›|\s\“|\s\«|\s\‹)[i][A-Z][a-z]+/
 
     PUNCTUATION_REGEX = /[\?\)\(\!\\\/\"\:\;\,\”\“\«\»\‹\›]/
     attr_reader :language, :corpus

data/lib/confidential_info_redactor_lite/version.rb

@@ -1,3 +1,3 @@
 module ConfidentialInfoRedactorLite
-  VERSION = "1.0.11"
+  VERSION = "1.0.12"
 end

data/spec/confidential_info_redactor_lite/extractor_spec.rb

@@ -159,6 +159,11 @@ RSpec.describe ConfidentialInfoRedactorLite::Extractor do
         text = 'Document No:-'
         expect(described_class.new(corpus: corpus, language: 'en').extract(text)).to eq(["Document No"])
       end
+
+      it 'extracts the proper nouns from a text #021' do
+        text = 'Óscar is the best.'
+        expect(described_class.new(corpus: corpus, language: 'en').extract(text)).to eq(["Óscar"])
+      end
     end
 
     context 'German (de)' do

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: confidential_info_redactor_lite
 version: !ruby/object:Gem::Version
-  version: 1.0.11
+  version: 1.0.12
 platform: ruby
 authors:
 - Kevin S. Dias
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2016-03-07 00:00:00.000000000 Z
+date: 2016-07-26 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler