confidential_info_redactor_lite 0.0.26 → 0.0.27

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: e5acaf81f53e7390182f433c0904c0046cd6b887
-  data.tar.gz: 7463858f0d108d8cfb4bfe5c4794ccf9c2dceb03
+  metadata.gz: 0ceeb1140b59f594ab6600ed27b362721f7626cb
+  data.tar.gz: b8daee381620d1fdd3e3883c1ea9d0702ceb2c6f
 SHA512:
-  metadata.gz: b688792d2d55b1b09b13e41b77e0a3b45571632ea78d371373025a2c6f8a805a622f4f322610a4ef1a0ac6a260a6c8630e539220f1b384115b2f24d98e7eb5f2
-  data.tar.gz: a2b71134454512b86b6388ab1f06cd75dc736fa9c8778501aeca2eee87bdccd95ac1b0646d57674359be9f667533c52cee28f8e91766217e588a86fa0c6eca0b
+  metadata.gz: 7c8dbb77b0779043b8fcdc501730624f7827d0e54d1a81cdaaf33e677ef9b2242854c323b0eeb535eb97096cb0e97a3a225ab2642058de2f24c36ac473c983dc
+  data.tar.gz: 6b426392130a87db3b65a320a74f77911f2db7491e80f7becf793d216f9a5d538ad76a41c79980e389285d10fa74ee383ba5fb9f381a4f14f5cc29b80a3f5411

data/lib/confidential_info_redactor_lite/redactor.rb

@@ -88,10 +88,14 @@ module ConfidentialInfoRedactorLite
 
     def redact_hyperlinks_html(txt)
       redacted_text = redact_hyperlinks(txt).gsub(/\>\s#{Regexp.escape(token_text)}\s\</, ">#{token_text}<").gsub(/\>\s#{Regexp.escape(number_text)}\s\</, ">#{number_text}<").gsub(/\>\s#{Regexp.escape(date_text)}\s\</, ">#{date_text}<").gsub(/\>\s#{Regexp.escape(email_text)}\s\</, ">#{email_text}<").gsub(/\>\s#{Regexp.escape(hyperlink_text)}\s\</, ">#{hyperlink_text}<")
-      original_sentence_array = txt.split(' ')
-      redacted_sentence_array = redacted_text.split(' ')
-      diff = original_sentence_array - redacted_sentence_array
-      final_hyperlinks_tokens = diff.map { |token| token[-1].eql?('.') ? token[0...-1] : token }.map { |token| token[-1].eql?(')') ? token[0...-1] : token }.map { |token| token[0].eql?('(') ? token[1..token.length] : token }
+      if language.eql?('ja')
+        final_hyperlinks_tokens = txt.scan(/http[a-zA-Z\/\:\.\-]+|www[a-zA-Z\/\:\.\-]+/)
+      else
+        original_sentence_array = txt.split(' ')
+        redacted_sentence_array = redacted_text.split(' ')
+        diff = original_sentence_array - redacted_sentence_array
+        final_hyperlinks_tokens = diff.map { |token| token[-1].eql?('.') ? token[0...-1] : token }.map { |token| token[-1].eql?(')') ? token[0...-1] : token }.map { |token| token[0].eql?('(') ? token[1..token.length] : token }
+      end
       [redacted_text.gsub(/(?<=[^\>])#{Regexp.escape(hyperlink_text)}/, "<span class='confidentialHyperlinks'>#{hyperlink_text}</span>"), final_hyperlinks_tokens]
     end
 

data/lib/confidential_info_redactor_lite/version.rb

@@ -1,3 +1,3 @@
 module ConfidentialInfoRedactorLite
-  VERSION = "0.0.26"
+  VERSION = "0.0.27"
 end

data/spec/confidential_info_redactor_lite/redactor_spec.rb

@@ -239,6 +239,11 @@ RSpec.describe ConfidentialInfoRedactorLite::Redactor do
       text = 'My Transformation - avoid Trans.'
       expect(described_class.new(text: text, language: 'en', tokens: tokens, number_text: '**redacted number**', date_text: '^^redacted date^^', token_text: '*****', hyperlink_text: '*****', email_text: '*****', dow: en_dow, dow_abbr: en_dow_abbr, months: en_months, months_abbr: en_month_abbr).redact).to eq('My Transformation - avoid *****.')
     end
+
+    it 'redacts all confidential information from a text #007' do
+      text = 'これはjohn@gmail.comかk.light@tuv.eu.usかhttps://www.tm-town.comです.'
+      expect(described_class.new(text: text, language: 'ja', tokens: nil, number_text: '**redacted number**', date_text: '^^redacted date^^', token_text: '*****', hyperlink_text: '*****', email_text: '*****', dow: en_dow, dow_abbr: en_dow_abbr, months: en_months, months_abbr: en_month_abbr).hyperlinks_html[1]).to eq(["https://www.tm-town.com"])
+    end
   end
 
   describe '#redact_html' do

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: confidential_info_redactor_lite
 version: !ruby/object:Gem::Version
-  version: 0.0.26
+  version: 0.0.27
 platform: ruby
 authors:
 - Kevin S. Dias