confidential_info_redactor_lite 0.0.13 → 0.0.14

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 6b37f8797a8ca98088c77462fd3cc34f7bfbb9ef
-  data.tar.gz: ef75c18fada7655ab22d171c1741a9accce73b92
+  metadata.gz: 7d546836b7298bd773fad876c9af181000f3867b
+  data.tar.gz: b66109b97cf689dabf3f92fa4445969aa0b24f70
 SHA512:
-  metadata.gz: f63e4997217c4e89dd432427d3a3a1d734cf5c2703fbc03343c90444948e41d618b4b4f014c8ce167bec4e5899a70fc20e5adcea14e3eda63f5328dd0c3877b9
-  data.tar.gz: 110de24454372d0572f6a411ca4fd14a9471fb152509d9aecc6707a071c392307bda310ed058b82535755a422e9e59ea15761ca4662f259206ddd9ddea795156
+  metadata.gz: 4c986381225e75100ea16ac1c8c53fc9de21cdfcf0302adb0f3cc55c36a63e6d35b5474e3990f92495b7977cbd3618383517d876dfc11431c25ee178f7aa34ae
+  data.tar.gz: 5084bd86c4c02ae26a7be74850d9c7431c99deb9373c71f0904afcfa63148eaf6bd1fc8f55636d73347f67ae8c3c081d96b6e1340d7f9fe076d0a84b516bc1a2

data/lib/confidential_info_redactor_lite/extractor.rb

@@ -19,7 +19,13 @@ module ConfidentialInfoRedactorLite
             if corpus.include?(t.downcase.gsub(/[\?\)\(\!\\\/\"\:\;\,]/, '').gsub(/\'$/, '').gsub(/\.\z/, '').strip.split(' ')[0]) && t.downcase.gsub(/[\?\)\(\!\\\/\"\:\;\,]/, '').gsub(/\'$/, '').gsub(/\.\z/, '').strip.split(' ')[0] != 'the' && t.downcase.gsub(/[\?\)\(\!\\\/\"\:\;\,]/, '').gsub(/\'$/, '').gsub(/\.\z/, '').strip.split(' ')[0] != 'deutsche' && t.downcase.gsub(/[\?\)\(\!\\\/\"\:\;\,]/, '').gsub(/\'$/, '').gsub(/\.\z/, '').strip.split(' ').length.eql?(2)
               extracted_terms << t.gsub(/[\?\)\(\!\\\/\"\:\;\,]/, '').gsub(/\'$/, '').gsub(/\.\z/, '').strip.split(' ')[1] unless corpus.include?(t.downcase.gsub(/[\?\.\)\(\!\\\/\"\:\;]/, '').gsub(/\'$/, '').strip.split(' ')[1])
             else
-              extracted_terms << t.gsub(/[\?\)\(\!\\\/\"\:\;\,]/, '').gsub(/\'$/, '').gsub(/\.\z/, '').strip unless corpus.include?(t.downcase.gsub(/[\?\.\)\(\!\\\/\"\:\;]/, '').gsub(/\'$/, '').strip)
+              tracker = true
+              unless t.gsub(/[\?\)\(\!\\\/\"\:\;\,]/, '').gsub(/\'$/, '').gsub(/\.\z/, '').strip.split(' ').length.eql?(2) && t.gsub(/[\?\)\(\!\\\/\"\:\;\,]/, '').gsub(/\'$/, '').gsub(/\.\z/, '').strip.split(' ')[1].downcase.eql?('bank')
+                t.gsub(/[\?\)\(\!\\\/\"\:\;\,]/, '').gsub(/\'$/, '').gsub(/\.\z/, '').strip.split(' ').each do |token|
+                  tracker = false if corpus.include?(token.downcase)
+                end
+              end
+              extracted_terms << t.gsub(/[\?\)\(\!\\\/\"\:\;\,]/, '').gsub(/\'$/, '').gsub(/\.\z/, '').strip unless corpus.include?(t.downcase.gsub(/[\?\.\)\(\!\\\/\"\:\;]/, '').gsub(/\'$/, '').strip) || !tracker
             end
           end
         end

data/lib/confidential_info_redactor_lite/version.rb

@@ -1,3 +1,3 @@
 module ConfidentialInfoRedactorLite
-  VERSION = "0.0.13"
+  VERSION = "0.0.14"
 end

data/spec/confidential_info_redactor_lite/extractor_spec.rb

@@ -1,7 +1,7 @@
 require 'spec_helper'
 
 RSpec.describe ConfidentialInfoRedactorLite::Extractor do
-  let(:corpus) { ['i', 'in', 'you', 'top', 'so', 'are', 'december', 'please', 'viele', 'mitarbeiter', 'arbeitsstelle', 'some', 'there', 'king', 'by', "don't", 'dec', 'at', 'dot', 'and', 'project', 'activity', 'complete', 'prizes', 'build', 'video', 'many', 'autographs', 'picture', 'the', 'each', 'submit', 'to', 'then', 'coming', 'screenshot'] }
+  let(:corpus) { ['i', 'in', 'you', 'top', 'so', 'are', 'december', 'please', 'viele', 'mitarbeiter', 'arbeitsstelle', 'some', 'there', 'king', 'by', "don't", 'dec', 'at', 'dot', 'and', 'project', 'activity', 'complete', 'prizes', 'build', 'video', 'many', 'autographs', 'picture', 'the', 'each', 'submit', 'to', 'then', 'coming', 'screenshot', 'putter', 'king', 'miniature', 'good', 'bad', 'vs.', 'carbs', 'all', 'natural', 'peanut', 'butter', 'world', 'heritage', 'site', 'gift', 'card', 'engraved', 'crystal', 'trophy'] }
   describe '#extract' do
     context 'English (en)' do
       it 'extracts the proper nouns from a text #001' do
@@ -87,7 +87,7 @@ RSpec.describe ConfidentialInfoRedactorLite::Extractor do
 
           Don’t forget to use your imagination and creativity!
         EOF
-        expect(described_class.new(text: text, corpus: corpus).extract).to eq(["Putter King Miniature Golf Scavenger Hunt", "Putter King", "Annual Miniature Golf Scavenger Hunt", "The Official List", "Nostalgic Miniature Golf Obstacles", "Putter King Hole Design Contest", "World Heritage Site", "PGA", "iTunes", "Gift Card", "Putter King Scavenger Hunt Trophy", "Engraved Crystal Trophy", "Picture Coming Soon", "The Putter King", "The U.S. Government", "Putter King Scavenger Hunt Submission", "YouTube", "Flickr", "Picasa", "Photobucket"])
+        expect(described_class.new(text: text, corpus: corpus).extract).to eq(["PGA", "iTunes", "YouTube", "Flickr", "Picasa", "Photobucket"])
       end
 
       it 'extracts the proper nouns from a text #007' do
@@ -104,6 +104,21 @@ RSpec.describe ConfidentialInfoRedactorLite::Extractor do
         text = 'Then Peter went to the store.'
         expect(described_class.new(text: text, corpus: corpus, language: 'en').extract).to eq(["Peter"])
       end
+
+      it 'extracts the proper nouns from a text #010' do
+        text = 'HOW TO COOK VEGETABLES'
+        expect(described_class.new(text: text, corpus: corpus, language: 'en').extract).to eq([])
+      end
+
+      it 'extracts the proper nouns from a text #011' do
+        text = 'All Natural Peanut Butter'
+        expect(described_class.new(text: text, corpus: corpus, language: 'en').extract).to eq([])
+      end
+
+      it 'extracts the proper nouns from a text #012' do
+        text = 'GOOD CARBS VS. BAD CARBS'
+        expect(described_class.new(text: text, corpus: corpus, language: 'en').extract).to eq([])
+      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: 0.0.13
+  version: 0.0.14
 platform: ruby
 authors:
 - Kevin S. Dias
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2015-04-22 00:00:00.000000000 Z
+date: 2015-04-23 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler