confidential_info_redactor_lite 0.0.13 → 0.0.14
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: 7d546836b7298bd773fad876c9af181000f3867b
|
|
4
|
+
data.tar.gz: b66109b97cf689dabf3f92fa4445969aa0b24f70
|
|
5
5
|
SHA512:
|
|
6
|
-
metadata.gz:
|
|
7
|
-
data.tar.gz:
|
|
6
|
+
metadata.gz: 4c986381225e75100ea16ac1c8c53fc9de21cdfcf0302adb0f3cc55c36a63e6d35b5474e3990f92495b7977cbd3618383517d876dfc11431c25ee178f7aa34ae
|
|
7
|
+
data.tar.gz: 5084bd86c4c02ae26a7be74850d9c7431c99deb9373c71f0904afcfa63148eaf6bd1fc8f55636d73347f67ae8c3c081d96b6e1340d7f9fe076d0a84b516bc1a2
|
|
@@ -19,7 +19,13 @@ module ConfidentialInfoRedactorLite
|
|
|
19
19
|
if corpus.include?(t.downcase.gsub(/[\?\)\(\!\\\/\"\:\;\,]/, '').gsub(/\'$/, '').gsub(/\.\z/, '').strip.split(' ')[0]) && t.downcase.gsub(/[\?\)\(\!\\\/\"\:\;\,]/, '').gsub(/\'$/, '').gsub(/\.\z/, '').strip.split(' ')[0] != 'the' && t.downcase.gsub(/[\?\)\(\!\\\/\"\:\;\,]/, '').gsub(/\'$/, '').gsub(/\.\z/, '').strip.split(' ')[0] != 'deutsche' && t.downcase.gsub(/[\?\)\(\!\\\/\"\:\;\,]/, '').gsub(/\'$/, '').gsub(/\.\z/, '').strip.split(' ').length.eql?(2)
|
|
20
20
|
extracted_terms << t.gsub(/[\?\)\(\!\\\/\"\:\;\,]/, '').gsub(/\'$/, '').gsub(/\.\z/, '').strip.split(' ')[1] unless corpus.include?(t.downcase.gsub(/[\?\.\)\(\!\\\/\"\:\;]/, '').gsub(/\'$/, '').strip.split(' ')[1])
|
|
21
21
|
else
|
|
22
|
-
|
|
22
|
+
tracker = true
|
|
23
|
+
unless t.gsub(/[\?\)\(\!\\\/\"\:\;\,]/, '').gsub(/\'$/, '').gsub(/\.\z/, '').strip.split(' ').length.eql?(2) && t.gsub(/[\?\)\(\!\\\/\"\:\;\,]/, '').gsub(/\'$/, '').gsub(/\.\z/, '').strip.split(' ')[1].downcase.eql?('bank')
|
|
24
|
+
t.gsub(/[\?\)\(\!\\\/\"\:\;\,]/, '').gsub(/\'$/, '').gsub(/\.\z/, '').strip.split(' ').each do |token|
|
|
25
|
+
tracker = false if corpus.include?(token.downcase)
|
|
26
|
+
end
|
|
27
|
+
end
|
|
28
|
+
extracted_terms << t.gsub(/[\?\)\(\!\\\/\"\:\;\,]/, '').gsub(/\'$/, '').gsub(/\.\z/, '').strip unless corpus.include?(t.downcase.gsub(/[\?\.\)\(\!\\\/\"\:\;]/, '').gsub(/\'$/, '').strip) || !tracker
|
|
23
29
|
end
|
|
24
30
|
end
|
|
25
31
|
end
|
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
require 'spec_helper'
|
|
2
2
|
|
|
3
3
|
RSpec.describe ConfidentialInfoRedactorLite::Extractor do
|
|
4
|
-
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'] }
|
|
4
|
+
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'] }
|
|
5
5
|
describe '#extract' do
|
|
6
6
|
context 'English (en)' do
|
|
7
7
|
it 'extracts the proper nouns from a text #001' do
|
|
@@ -87,7 +87,7 @@ RSpec.describe ConfidentialInfoRedactorLite::Extractor do
|
|
|
87
87
|
|
|
88
88
|
Don’t forget to use your imagination and creativity!
|
|
89
89
|
EOF
|
|
90
|
-
expect(described_class.new(text: text, corpus: corpus).extract).to eq(["
|
|
90
|
+
expect(described_class.new(text: text, corpus: corpus).extract).to eq(["PGA", "iTunes", "YouTube", "Flickr", "Picasa", "Photobucket"])
|
|
91
91
|
end
|
|
92
92
|
|
|
93
93
|
it 'extracts the proper nouns from a text #007' do
|
|
@@ -104,6 +104,21 @@ RSpec.describe ConfidentialInfoRedactorLite::Extractor do
|
|
|
104
104
|
text = 'Then Peter went to the store.'
|
|
105
105
|
expect(described_class.new(text: text, corpus: corpus, language: 'en').extract).to eq(["Peter"])
|
|
106
106
|
end
|
|
107
|
+
|
|
108
|
+
it 'extracts the proper nouns from a text #010' do
|
|
109
|
+
text = 'HOW TO COOK VEGETABLES'
|
|
110
|
+
expect(described_class.new(text: text, corpus: corpus, language: 'en').extract).to eq([])
|
|
111
|
+
end
|
|
112
|
+
|
|
113
|
+
it 'extracts the proper nouns from a text #011' do
|
|
114
|
+
text = 'All Natural Peanut Butter'
|
|
115
|
+
expect(described_class.new(text: text, corpus: corpus, language: 'en').extract).to eq([])
|
|
116
|
+
end
|
|
117
|
+
|
|
118
|
+
it 'extracts the proper nouns from a text #012' do
|
|
119
|
+
text = 'GOOD CARBS VS. BAD CARBS'
|
|
120
|
+
expect(described_class.new(text: text, corpus: corpus, language: 'en').extract).to eq([])
|
|
121
|
+
end
|
|
107
122
|
end
|
|
108
123
|
|
|
109
124
|
context 'German (de)' do
|
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: 0.0.14
|
|
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: 2015-04-23 00:00:00.000000000 Z
|
|
12
12
|
dependencies:
|
|
13
13
|
- !ruby/object:Gem::Dependency
|
|
14
14
|
name: bundler
|