confidential_info_redactor_lite 0.0.8 → 0.0.9

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: a00a35159e096f07346d94b3ffd1ebf139ef9561
-  data.tar.gz: adacee6c75993572f2343bfef71fa94b70ab885a
+  metadata.gz: 216e96faca24f56d0c98efd9fe537d443ebf99ee
+  data.tar.gz: 79fd2f8c443c6d3875298b860a81ba84b4d68113
 SHA512:
-  metadata.gz: 8958fef084a98d839334725773f4fa1a5a4ec0de746d0826a02902398ac83184052b9cc12bd9e22bfc819133a33d12b1f8891731801fcc3d49a717cac605711b
-  data.tar.gz: eb78915b7d9f8ccdb57d377b1af1be2afa754a91f12a222a7946b532b590212dd788eefcc3e8f0a808eebd8a63f5017f1df79bbac23c293c51ade05143e82c7e
+  metadata.gz: f82751b04aa5c32af2de0fc4048a3fa79a82dbf0a9fdbe63b8118371172c62fc0b0d9cffa9eb036e1529e2b66b1ff37ce77e1cb4ee849fe45cff55cfd0b5ab5d
+  data.tar.gz: 7b2e643f54eb7bcfd624f16fc64ea2301f99cbad9c19a8b11c10faa1a3bd9282a319fbbd506ece94a3ea42246e8f310337a73ff2a5611632b8d0e9f04aab83e6

data/lib/confidential_info_redactor_lite/extractor.rb

@@ -16,7 +16,7 @@ module ConfidentialInfoRedactorLite
         initial_extracted_terms = segment.gsub(EXTRACT_REGEX).map { |match| match unless corpus.include?(match.downcase.gsub(/[\?\.\)\(\!\\\/\"\:\;]/, '').gsub(/\'$/, '')) }.compact
         initial_extracted_terms.each do |ngram|
           ngram.split(/[\?\)\(\!\\\/\"\:\;\,]/).each do |t|
-            if corpus.include?(t.downcase.gsub(/[\?\)\(\!\\\/\"\:\;\,]/, '').gsub(/\'$/, '').gsub(/\.\z/, '').strip.split(' ')[0]) && t.downcase.gsub(/[\?\)\(\!\\\/\"\:\;\,]/, '').gsub(/\'$/, '').gsub(/\.\z/, '').strip.split(' ')[0] != 'the'
+            if corpus.include?(t.downcase.gsub(/[\?\)\(\!\\\/\"\:\;\,]/, '').gsub(/\'$/, '').gsub(/\.\z/, '').strip.split(' ')[0]) && t.downcase.gsub(/[\?\)\(\!\\\/\"\:\;\,]/, '').gsub(/\'$/, '').gsub(/\.\z/, '').strip.split(' ')[0] != 'the' && t.downcase.gsub(/[\?\)\(\!\\\/\"\:\;\,]/, '').gsub(/\'$/, '').gsub(/\.\z/, '').strip.split(' ')[0] != 'deutsche' && t.downcase.gsub(/[\?\)\(\!\\\/\"\:\;\,]/, '').gsub(/\'$/, '').gsub(/\.\z/, '').strip.split(' ').length.eql?(2)
               extracted_terms << t.gsub(/[\?\)\(\!\\\/\"\:\;\,]/, '').gsub(/\'$/, '').gsub(/\.\z/, '').strip.split(' ')[1] unless corpus.include?(t.downcase.gsub(/[\?\.\)\(\!\\\/\"\:\;]/, '').gsub(/\'$/, '').strip.split(' ')[1])
             else
               extracted_terms << t.gsub(/[\?\)\(\!\\\/\"\:\;\,]/, '').gsub(/\'$/, '').gsub(/\.\z/, '').strip unless corpus.include?(t.downcase.gsub(/[\?\.\)\(\!\\\/\"\:\;]/, '').gsub(/\'$/, '').strip)
@@ -25,14 +25,7 @@ module ConfidentialInfoRedactorLite
         end
       end
 
-      if language.eql?('de')
-        extracted_terms.delete_if do |token|
-          corpus.include?(token.split(' ')[0].downcase.strip) &&
-            token.split(' ')[0].downcase.strip != 'deutsche'
-        end.uniq.reject(&:empty?)
-      else
-        extracted_terms.uniq.reject(&:empty?)
-      end
+      extracted_terms.uniq.reject(&:empty?)
     end
   end
 end

data/lib/confidential_info_redactor_lite/version.rb

@@ -1,3 +1,3 @@
 module ConfidentialInfoRedactorLite
-  VERSION = "0.0.8"
+  VERSION = "0.0.9"
 end

data/spec/confidential_info_redactor_lite/extractor_spec.rb

@@ -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", "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(["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"])
       end
 
       it 'extracts the proper nouns from a text #007' do

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: confidential_info_redactor_lite
 version: !ruby/object:Gem::Version
-  version: 0.0.8
+  version: 0.0.9
 platform: ruby
 authors:
 - Kevin S. Dias