confidential_info_redactor_lite 0.0.12 → 0.0.13

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: ad118f207a2c77d6576afe2450015ffb53362817
-  data.tar.gz: 5c62ec610e4ca6361fbf977614eb6a8565424451
+  metadata.gz: 6b37f8797a8ca98088c77462fd3cc34f7bfbb9ef
+  data.tar.gz: ef75c18fada7655ab22d171c1741a9accce73b92
 SHA512:
-  metadata.gz: 4da649dbf21c536a4ba5404636297447db7adcafb78e5cbd7375a5d8bd21ee4d087c192214cfe52167c5a0090fd853fdccbe0d9f9aaf7212bb7d422ceb0348ab
-  data.tar.gz: 05c05072e9ebb34139c959f4e1c2351a36a6e48ea7d8bcd4a853cd75eea3ccc57e8fd4d5095e90a86c1fef8d84eb4657117f654457ed88eb1461fcb1962a6c28
+  metadata.gz: f63e4997217c4e89dd432427d3a3a1d734cf5c2703fbc03343c90444948e41d618b4b4f014c8ce167bec4e5899a70fc20e5adcea14e3eda63f5328dd0c3877b9
+  data.tar.gz: 110de24454372d0572f6a411ca4fd14a9471fb152509d9aecc6707a071c392307bda310ed058b82535755a422e9e59ea15761ca4662f259206ddd9ddea795156

data/lib/confidential_info_redactor_lite/hyperlink.rb

@@ -20,9 +20,9 @@ module ConfidentialInfoRedactorLite
       new_string = string.dup
       string.split(/\s+/).each do |token|
         if !(token !~ URI.regexp) && token !~ NON_HYPERLINK_REGEX && !(token !~ HYPERLINK_REGEX) && token.include?('">')
-          new_string = new_string.gsub(/#{Regexp.escape(token.split('">')[0].gsub(/\.\z/, ''))}/, ' <redacted> ')
+          new_string = new_string.gsub(/#{Regexp.escape(token.split('">')[0].gsub(/\.\z/, ''))}/, ' <redacted hyperlink> ')
         elsif !(token !~ URI.regexp) && token !~ NON_HYPERLINK_REGEX && !(token !~ HYPERLINK_REGEX)
-          new_string = new_string.gsub(/#{Regexp.escape(token.gsub(/\.\z/, ''))}/, ' <redacted> ')
+          new_string = new_string.gsub(/#{Regexp.escape(token.gsub(/\.\z/, ''))}/, ' <redacted hyperlink> ')
         end
       end
       new_string

data/lib/confidential_info_redactor_lite/redactor.rb

@@ -9,7 +9,7 @@ module ConfidentialInfoRedactorLite
     # Rubular: http://rubular.com/r/mxcj2G0Jfa
     EMAIL_REGEX = /(?<=\A|\s|\()[\w+\-.]+@[a-z\d\-]+(\.[a-z]+)*\.[a-z]+(?=\z|\s|\.|\))/i
 
-    attr_reader :text, :language, :number_text, :date_text, :token_text, :tokens, :ignore_emails, :ignore_dates, :ignore_numbers, :ignore_hyperlinks, :dow, :dow_abbr, :months, :months_abbr
+    attr_reader :text, :language, :email_text, :hyperlink_text, :number_text, :date_text, :token_text, :tokens, :ignore_emails, :ignore_dates, :ignore_numbers, :ignore_hyperlinks, :dow, :dow_abbr, :months, :months_abbr
     def initialize(text:, dow:, dow_abbr:, months:, months_abbr:, **args)
       @text = text
       @language = args[:language] || 'en'
@@ -17,6 +17,8 @@ module ConfidentialInfoRedactorLite
       @number_text = args[:number_text] || '<redacted number>'
       @date_text = args[:date_text] || '<redacted date>'
       @token_text = args[:token_text] || '<redacted>'
+      @email_text = args[:email_text] || '<redacted email>'
+      @hyperlink_text = args[:hyperlink_text] || '<redacted hyperlink>'
       @ignore_emails = args[:ignore_emails]
       @ignore_dates = args[:ignore_dates]
       @ignore_numbers = args[:ignore_numbers]
@@ -85,16 +87,16 @@ module ConfidentialInfoRedactorLite
     private
 
     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}<")
+      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 }
-      [redacted_text.gsub(/(?<=[^\>])#{Regexp.escape(token_text)}/, "<span class='confidentialHyperlinks'>#{token_text}</span>"), final_hyperlinks_tokens]
+      [redacted_text.gsub(/(?<=[^\>])#{Regexp.escape(hyperlink_text)}/, "<span class='confidentialHyperlinks'>#{hyperlink_text}</span>"), final_hyperlinks_tokens]
     end
 
     def redact_numbers_html(txt)
-      redacted_text = redact_numbers(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}<")
+      redacted_text = redact_numbers(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
@@ -103,12 +105,12 @@ module ConfidentialInfoRedactorLite
     end
 
     def redact_emails_html(txt)
-      redacted_text = redact_emails(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}<")
+      redacted_text = redact_emails(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_email_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 }
-      [redacted_text.gsub(/(?<=[^\>])#{Regexp.escape(token_text)}/, "<span class='confidentialEmail'>#{token_text}</span>"), final_email_tokens]
+      [redacted_text.gsub(/(?<=[^\>])#{Regexp.escape(email_text)}/, "<span class='confidentialEmail'>#{email_text}</span>"), final_email_tokens]
     end
 
     def redact_dates_html(txt)
@@ -155,7 +157,7 @@ module ConfidentialInfoRedactorLite
     end
 
     def redact_hyperlinks(txt)
-      ConfidentialInfoRedactorLite::Hyperlink.new(string: txt).replace.gsub(/<redacted>/, "#{token_text}").gsub(/\s*#{Regexp.escape(token_text)}\s*/, " #{token_text} ").gsub(/#{Regexp.escape(token_text)}\s{1}\.{1}/, "#{token_text}.").gsub(/#{Regexp.escape(token_text)}\s{1}\,{1}/, "#{token_text},")
+      ConfidentialInfoRedactorLite::Hyperlink.new(string: txt).replace.gsub(/<redacted hyperlink>/, "#{hyperlink_text}").gsub(/\s*#{Regexp.escape(hyperlink_text)}\s*/, " #{hyperlink_text} ").gsub(/#{Regexp.escape(hyperlink_text)}\s{1}\.{1}/, "#{hyperlink_text}.").gsub(/#{Regexp.escape(hyperlink_text)}\s{1}\,{1}/, "#{hyperlink_text},")
     end
 
     def redact_dates(txt)
@@ -167,7 +169,7 @@ module ConfidentialInfoRedactorLite
     end
 
     def redact_emails(txt)
-      txt.gsub(EMAIL_REGEX, "#{token_text}")
+      txt.gsub(EMAIL_REGEX, "#{email_text}")
     end
 
     def redact_tokens(txt)

data/lib/confidential_info_redactor_lite/version.rb

@@ -1,3 +1,3 @@
 module ConfidentialInfoRedactorLite
-  VERSION = "0.0.12"
+  VERSION = "0.0.13"
 end

data/spec/confidential_info_redactor_lite/hyperlink_spec.rb

@@ -49,7 +49,7 @@ RSpec.describe ConfidentialInfoRedactorLite::Hyperlink do
     it 'replaces the hyperlinks in a string with regular tokens #001' do
       string = "Today the date is: Jan 1. Visit https://www.example.com/hello or http://www.google.co.uk"
       ws = described_class.new(string: string)
-      expect(ws.replace).to eq("Today the date is: Jan 1. Visit  <redacted>  or  <redacted> ")
+      expect(ws.replace).to eq("Today the date is: Jan 1. Visit  <redacted hyperlink>  or  <redacted hyperlink> ")
     end
 
     it 'replaces the hyperlinks in a string with regular tokens #002' do

data/spec/confidential_info_redactor_lite/redactor_spec.rb

@@ -88,33 +88,33 @@ RSpec.describe ConfidentialInfoRedactorLite::Redactor do
   describe '#emails' do
     it 'redacts email addresses from a text #001' do
       text = 'His email is john@gmail.com or you can try k.light@tuv.eu.us.'
-      expect(described_class.new(text: text, language: 'en', dow: en_dow, dow_abbr: en_dow_abbr, months: en_months, months_abbr: en_month_abbr).emails).to eq('His email is <redacted> or you can try <redacted>.')
+      expect(described_class.new(text: text, language: 'en', dow: en_dow, dow_abbr: en_dow_abbr, months: en_months, months_abbr: en_month_abbr).emails).to eq('His email is <redacted email> or you can try <redacted email>.')
     end
 
     it 'redacts email addresses from a text #002' do
       text = 'His email is (john@gmail.com) or you can try (k.light@tuv.eu.us).'
-      expect(described_class.new(text: text, language: 'en', dow: en_dow, dow_abbr: en_dow_abbr, months: en_months, months_abbr: en_month_abbr).emails).to eq('His email is (<redacted>) or you can try (<redacted>).')
+      expect(described_class.new(text: text, language: 'en', dow: en_dow, dow_abbr: en_dow_abbr, months: en_months, months_abbr: en_month_abbr).emails).to eq('His email is (<redacted email>) or you can try (<redacted email>).')
     end
   end
 
   describe '#emails_html' do
     it 'surrounds the redacted emails in spans and return the redacted emails from a text #001' do
       text = 'His email is (john@gmail.com) or you can try (k.light@tuv.eu.us).'
-      expect(described_class.new(text: text, language: 'en', dow: en_dow, dow_abbr: en_dow_abbr, months: en_months, months_abbr: en_month_abbr, token_text: "*****").emails_html).to eq(["His email is (<span class='confidentialEmail'>*****</span>) or you can try (<span class='confidentialEmail'>*****</span>).", ["john@gmail.com", "k.light@tuv.eu.us"]])
+      expect(described_class.new(text: text, language: 'en', dow: en_dow, dow_abbr: en_dow_abbr, months: en_months, months_abbr: en_month_abbr, token_text: "*****").emails_html).to eq(["His email is (<span class='confidentialEmail'><redacted email></span>) or you can try (<span class='confidentialEmail'><redacted email></span>).", ["john@gmail.com", "k.light@tuv.eu.us"]])
     end
   end
 
   describe '#hyperlinks' do
     it 'redacts hyperlinks from a text #001' do
       text = 'Visit https://www.tm-town.com for more info.'
-      expect(described_class.new(text: text, language: 'en', dow: en_dow, dow_abbr: en_dow_abbr, months: en_months, months_abbr: en_month_abbr).hyperlinks).to eq('Visit <redacted> for more info.')
+      expect(described_class.new(text: text, language: 'en', dow: en_dow, dow_abbr: en_dow_abbr, months: en_months, months_abbr: en_month_abbr).hyperlinks).to eq('Visit <redacted hyperlink> for more info.')
     end
   end
 
   describe '#hyperlinks_html' do
     it 'surrounds the redacted hyperlinks in spans and return the redacted hyperlinks from a text #001' do
       text = 'Visit https://www.tm-town.com for more info or https://www.google.com.'
-      expect(described_class.new(text: text, language: 'en', dow: en_dow, dow_abbr: en_dow_abbr, months: en_months, months_abbr: en_month_abbr, token_text: "*****").hyperlinks_html).to eq(["Visit <span class='confidentialHyperlinks'>*****</span> for more info or <span class='confidentialHyperlinks'>*****</span>.", ["https://www.tm-town.com", "https://www.google.com"]])
+      expect(described_class.new(text: text, language: 'en', dow: en_dow, dow_abbr: en_dow_abbr, months: en_months, months_abbr: en_month_abbr, token_text: "*****", hyperlink_text: "*****", email_text: "*****").hyperlinks_html).to eq(["Visit <span class='confidentialHyperlinks'>*****</span> for more info or <span class='confidentialHyperlinks'>*****</span>.", ["https://www.tm-town.com", "https://www.google.com"]])
     end
   end
 
@@ -204,19 +204,19 @@ RSpec.describe ConfidentialInfoRedactorLite::Redactor do
     it 'redacts all confidential information from a text #003' do
       tokens = ['Coca-Cola', 'Pepsi', 'John Smith']
       text = 'Coca-Cola announced a merger with Pepsi that will happen on December 15th, 2020 for $200,000,000,000. Please contact John Smith at j.smith@example.com or visit http://www.super-fake-merger.com.'
-      expect(described_class.new(text: text, language: 'en', tokens: tokens, dow: en_dow, dow_abbr: en_dow_abbr, months: en_months, months_abbr: en_month_abbr).redact).to eq('<redacted> announced a merger with <redacted> that will happen on <redacted date> for <redacted number>. Please contact <redacted> at <redacted> or visit <redacted>.')
+      expect(described_class.new(text: text, language: 'en', tokens: tokens, dow: en_dow, dow_abbr: en_dow_abbr, months: en_months, months_abbr: en_month_abbr).redact).to eq('<redacted> announced a merger with <redacted> that will happen on <redacted date> for <redacted number>. Please contact <redacted> at <redacted email> or visit <redacted hyperlink>.')
     end
 
     it 'redacts all confidential information from a text #004' do
       tokens = ['Coca-Cola', 'Pepsi', 'John Smith']
       text = 'Coca-Cola announced a merger with Pepsi that will happen on December 15th, 2020 for $200,000,000,000. Please contact John Smith at j.smith@example.com or visit http://www.super-fake-merger.com.'
-      expect(described_class.new(text: text, language: 'en', tokens: tokens, ignore_numbers: true, dow: en_dow, dow_abbr: en_dow_abbr, months: en_months, months_abbr: en_month_abbr).redact).to eq('<redacted> announced a merger with <redacted> that will happen on <redacted date> for $200,000,000,000. Please contact <redacted> at <redacted> or visit <redacted>.')
+      expect(described_class.new(text: text, language: 'en', tokens: tokens, ignore_numbers: true, dow: en_dow, dow_abbr: en_dow_abbr, months: en_months, months_abbr: en_month_abbr).redact).to eq('<redacted> announced a merger with <redacted> that will happen on <redacted date> for $200,000,000,000. Please contact <redacted> at <redacted email> or visit <redacted hyperlink>.')
     end
 
     it 'redacts all confidential information from a text #005' do
       tokens = ['Coca-Cola', 'Pepsi', 'John Smith']
       text = 'Coca-Cola announced a merger with Pepsi that will happen on December 15th, 2020 for $200,000,000,000. Please contact John Smith at j.smith@example.com or visit http://www.super-fake-merger.com.'
-      expect(described_class.new(text: text, language: 'en', tokens: tokens, number_text: '**redacted number**', date_text: '^^redacted date^^', token_text: '*****', dow: en_dow, dow_abbr: en_dow_abbr, months: en_months, months_abbr: en_month_abbr).redact).to eq('***** announced a merger with ***** that will happen on ^^redacted date^^ for **redacted number**. Please contact ***** at ***** or visit *****.')
+      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('***** announced a merger with ***** that will happen on ^^redacted date^^ for **redacted number**. Please contact ***** at ***** or visit *****.')
     end
   end
 
@@ -224,7 +224,13 @@ RSpec.describe ConfidentialInfoRedactorLite::Redactor do
     it 'redacts all confidential information from a text #001' do
       tokens = ['Coca-Cola', 'Pepsi']
       text = 'Coca-Cola announced a merger with Pepsi that will happen on on December 15th, 2020 for $200,000,000,000. Find out more at https://www.merger.com or contact john@merger.com.'
-      expect(described_class.new(text: text, language: 'en', tokens: tokens, dow: en_dow, dow_abbr: en_dow_abbr, months: en_months, months_abbr: en_month_abbr, number_text: '*****', date_text: '*****', token_text: '*****').redact_html).to eq("Coca-Cola announced a merger with Pepsi that will happen on on <span class='confidentialDate'>*****</span> for <span class='confidentialNumber'>*****</span>. Find out more at <span class='confidentialHyperlinks'>*****</span> or contact <span class='confidentialEmail'>*****</span>.")
+      expect(described_class.new(text: text, language: 'en', tokens: tokens, dow: en_dow, dow_abbr: en_dow_abbr, months: en_months, months_abbr: en_month_abbr, number_text: '*****', hyperlink_text: '*****', email_text: '*****', date_text: '*****', token_text: '*****').redact_html).to eq("Coca-Cola announced a merger with Pepsi that will happen on on <span class='confidentialDate'>*****</span> for <span class='confidentialNumber'>*****</span>. Find out more at <span class='confidentialHyperlinks'>*****</span> or contact <span class='confidentialEmail'>*****</span>.")
+    end
+
+    it 'redacts all confidential information from a text #002' do
+      tokens = ['Coca-Cola', 'Pepsi']
+      text = 'Coca-Cola announced a merger with Pepsi that will happen on on December 15th, 2020 for $200,000,000,000. Find out more at https://www.merger.com or contact john@merger.com.'
+      expect(described_class.new(text: text, language: 'en', tokens: tokens, dow: en_dow, dow_abbr: en_dow_abbr, months: en_months, months_abbr: en_month_abbr, email_text: '**email**', number_text: '**number**', date_text: '**date**', hyperlink_text: '**url**', token_text: '*****').redact).to eq("***** announced a merger with ***** that will happen on on **date** for **number**. Find out more at **url** or contact **email**.")
     end
   end
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: confidential_info_redactor_lite
 version: !ruby/object:Gem::Version
-  version: 0.0.12
+  version: 0.0.13
 platform: ruby
 authors:
 - Kevin S. Dias