confidential_info_redactor_lite 0.0.17 → 0.0.18
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: 52f6dc75062fd5b96bf6ebddda6091ece0984a5f
|
|
4
|
+
data.tar.gz: f1e59cf4d26237d79076474ca22ee5eaeb27ae41
|
|
5
5
|
SHA512:
|
|
6
|
-
metadata.gz:
|
|
7
|
-
data.tar.gz:
|
|
6
|
+
metadata.gz: 9295558573274c81494ad53a53f61da538cba25a8bf5b32035a0af7baa78f8e2b83b63ecd3516902fc2457acfda037e5a45bf9106a4976d8c7489554182ebb34
|
|
7
|
+
data.tar.gz: 3b881aef75c2df2c7507034feb57ab02deba5ba4735bf50ca00c63d83eee034fd0c92a53b80a0fdf77203a8a19434c70850847cf08b9b3adc1b9796acd0e21af
|
|
@@ -25,7 +25,7 @@ module ConfidentialInfoRedactorLite
|
|
|
25
25
|
tracker = false if corpus.include?(token.downcase)
|
|
26
26
|
end
|
|
27
27
|
end
|
|
28
|
-
extracted_terms << t.gsub(/[\?\)\(\!\\\/\"\:\;\,]/, '').gsub(/\'$/, '').gsub(/”/,'').gsub(/\.\z/, '').strip unless corpus.include?(t.downcase.gsub(/[\?\.\)\(\!\\\/\"\:\;]/, '').gsub(/”/,'').gsub(/\'$/, '').strip) || !tracker
|
|
28
|
+
extracted_terms << t.gsub(/[\?\)\(\!\\\/\"\:\;\,]/, '').gsub(/\'$/, '').gsub(/”/,'').gsub(/\.\z/, '').strip unless corpus.include?(t.downcase.gsub(/[\?\.\)\(\!\\\/\"\:\;]/, '').gsub(/”/,'').gsub(/\'$/, '').strip) || !tracker || (corpus.include?(t.downcase.gsub(/[\?\.\)\(\!\\\/\"\:\;]/, '').gsub(/”/,'').gsub(/\'$/, '').strip[0...-2]) && t.downcase.gsub(/[\?\.\)\(\!\\\/\"\:\;]/, '').gsub(/”/,'').gsub(/\'$/, '').strip[-2..-1].eql?('en')) || (corpus.include?(t.downcase.gsub(/[\?\.\)\(\!\\\/\"\:\;]/, '').gsub(/”/,'').gsub(/\'$/, '').strip[0...-2]) && t.downcase.gsub(/[\?\.\)\(\!\\\/\"\:\;]/, '').gsub(/”/,'').gsub(/\'$/, '').strip[-2..-1].eql?('es')) || (corpus.include?(t.downcase.gsub(/[\?\.\)\(\!\\\/\"\:\;]/, '').gsub(/”/,'').gsub(/\'$/, '').strip[0...-2]) && t.downcase.gsub(/[\?\.\)\(\!\\\/\"\:\;]/, '').gsub(/”/,'').gsub(/\'$/, '').strip[-2..-1].eql?('er')) || (corpus.include?(t.downcase.gsub(/[\?\.\)\(\!\\\/\"\:\;]/, '').gsub(/”/,'').gsub(/\'$/, '').strip[0...-1]) && t.downcase.gsub(/[\?\.\)\(\!\\\/\"\:\;]/, '').gsub(/”/,'').gsub(/\'$/, '').strip[-1].eql?('s'))
|
|
29
29
|
end
|
|
30
30
|
end
|
|
31
31
|
end
|
|
@@ -142,10 +142,15 @@ RSpec.describe ConfidentialInfoRedactorLite::Extractor do
|
|
|
142
142
|
expect(described_class.new(text: text, corpus: corpus, language: 'de').extract).to eq(['Deutschen Bank'])
|
|
143
143
|
end
|
|
144
144
|
|
|
145
|
-
it 'extracts the proper nouns from a text #
|
|
145
|
+
it 'extracts the proper nouns from a text #002' do
|
|
146
146
|
text = 'Viele Mitarbeiter der Deutsche Bank suchen eine andere Arbeitsstelle.'
|
|
147
147
|
expect(described_class.new(text: text, corpus: corpus, language: 'de').extract).to eq(['Deutsche Bank'])
|
|
148
148
|
end
|
|
149
|
+
|
|
150
|
+
it 'extracts the proper nouns from a text #003' do
|
|
151
|
+
text = 'Viele de Mitarbeiters der Deutsche Bank suchen eine andere Arbeitsstelle.'
|
|
152
|
+
expect(described_class.new(text: text, corpus: corpus, language: 'de').extract).to eq(['Deutsche Bank'])
|
|
153
|
+
end
|
|
149
154
|
end
|
|
150
155
|
end
|
|
151
156
|
end
|
metadata
CHANGED
|
@@ -1,14 +1,14 @@
|
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
|
2
2
|
name: confidential_info_redactor_lite
|
|
3
3
|
version: !ruby/object:Gem::Version
|
|
4
|
-
version: 0.0.
|
|
4
|
+
version: 0.0.18
|
|
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
|