confidential_info_redactor 0.0.12 → 0.0.13
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
checksums.yaml
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
---
|
|
2
2
|
SHA1:
|
|
3
|
-
metadata.gz:
|
|
4
|
-
data.tar.gz:
|
|
3
|
+
metadata.gz: d698521a92a28fa94c1cd8f2c6317b4249a0a19d
|
|
4
|
+
data.tar.gz: ab825e72bb74de93b72efaac0364f4b01ba7b3fb
|
|
5
5
|
SHA512:
|
|
6
|
-
metadata.gz:
|
|
7
|
-
data.tar.gz:
|
|
6
|
+
metadata.gz: b91adab393e7137f24f9255a20b9d35cb812fbbb0513b0a3daf01944065d3659ef40864bc8013c7291d210593a60341e1dae898d6c5c97262029d7f0fefc8a5f
|
|
7
|
+
data.tar.gz: c554f97b0ce9fe0341ab983641bc347c415d770561acb150ce810236271c485cd0b395d8ebf8eef333372ebbb6719a703adca82cef36855022b8d565c1d196e1
|
|
@@ -34,7 +34,7 @@ module ConfidentialInfoRedactor
|
|
|
34
34
|
tracker = false if corpus.include?(token.downcase)
|
|
35
35
|
end
|
|
36
36
|
end
|
|
37
|
-
extracted_terms << t.gsub(/[\?\)\(\!\\\/\"\:\;\,]/, '').gsub(/\'$/, '').gsub(/”/,'').gsub(/\.\z/, '').strip unless corpus.include?(t.downcase.gsub(/[\?\.\)\(\!\\\/\"\:\;]/, '').gsub(/”/,'').gsub(/\'$/, '').strip) || !tracker
|
|
37
|
+
extracted_terms << t.gsub(/[\?\)\(\!\\\/\"\:\;\,]/, '').gsub(/\'$/, '').gsub(/”/,'').gsub(/\.\z/, '').strip unless corpus.include?(t.downcase.gsub(/[\?\.\)\(\!\\\/\"\:\;]/, '').gsub(/”/,'').gsub(/\'$/, '').strip) || !tracker || (corpus.include?(t.downcase.gsub(/[\?\.\)\(\!\\\/\"\:\;]/, '').gsub(/”/,'').gsub(/\'$/, '').strip[0...-2]) && t.downcase.gsub(/[\?\.\)\(\!\\\/\"\:\;]/, '').gsub(/”/,'').gsub(/\'$/, '').strip[-2..-1].eql?('en')) || (corpus.include?(t.downcase.gsub(/[\?\.\)\(\!\\\/\"\:\;]/, '').gsub(/”/,'').gsub(/\'$/, '').strip[0...-2]) && t.downcase.gsub(/[\?\.\)\(\!\\\/\"\:\;]/, '').gsub(/”/,'').gsub(/\'$/, '').strip[-2..-1].eql?('es')) || (corpus.include?(t.downcase.gsub(/[\?\.\)\(\!\\\/\"\:\;]/, '').gsub(/”/,'').gsub(/\'$/, '').strip[0...-2]) && t.downcase.gsub(/[\?\.\)\(\!\\\/\"\:\;]/, '').gsub(/”/,'').gsub(/\'$/, '').strip[-2..-1].eql?('er')) || (corpus.include?(t.downcase.gsub(/[\?\.\)\(\!\\\/\"\:\;]/, '').gsub(/”/,'').gsub(/\'$/, '').strip[0...-1]) && t.downcase.gsub(/[\?\.\)\(\!\\\/\"\:\;]/, '').gsub(/”/,'').gsub(/\'$/, '').strip[-1].eql?('s'))
|
|
38
38
|
end
|
|
39
39
|
end
|
|
40
40
|
end
|
|
@@ -141,10 +141,15 @@ RSpec.describe ConfidentialInfoRedactor::Extractor do
|
|
|
141
141
|
expect(described_class.new(text: text, language: 'de').extract).to eq(['Deutschen Bank'])
|
|
142
142
|
end
|
|
143
143
|
|
|
144
|
-
it 'extracts the proper nouns from a text #
|
|
144
|
+
it 'extracts the proper nouns from a text #002' do
|
|
145
145
|
text = 'Viele Mitarbeiter der Deutsche Bank suchen eine andere Arbeitsstelle.'
|
|
146
146
|
expect(described_class.new(text: text, language: 'de').extract).to eq(['Deutsche Bank'])
|
|
147
147
|
end
|
|
148
|
+
|
|
149
|
+
it 'extracts the proper nouns from a text #003' do
|
|
150
|
+
text = 'Ich behielt diese Routine während und sogar während des Studiums an der Uni bei, und ich war damals froh, wenn ich pro Tag zwei ganze Mahlzeiten zu mir nahm.'
|
|
151
|
+
expect(described_class.new(text: text, language: 'de').extract).to eq([])
|
|
152
|
+
end
|
|
148
153
|
end
|
|
149
154
|
end
|
|
150
155
|
end
|
metadata
CHANGED
|
@@ -1,14 +1,14 @@
|
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
|
2
2
|
name: confidential_info_redactor
|
|
3
3
|
version: !ruby/object:Gem::Version
|
|
4
|
-
version: 0.0.
|
|
4
|
+
version: 0.0.13
|
|
5
5
|
platform: ruby
|
|
6
6
|
authors:
|
|
7
7
|
- Kevin S. Dias
|
|
8
8
|
autorequire:
|
|
9
9
|
bindir: bin
|
|
10
10
|
cert_chain: []
|
|
11
|
-
date: 2015-04-
|
|
11
|
+
date: 2015-04-24 00:00:00.000000000 Z
|
|
12
12
|
dependencies:
|
|
13
13
|
- !ruby/object:Gem::Dependency
|
|
14
14
|
name: bundler
|