confidential_info_redactor_lite 1.0.1 → 1.0.2
Sign up to get free protection for your applications and to get access to all the features.
checksums.yaml
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
---
|
|
2
2
|
SHA1:
|
|
3
|
-
metadata.gz:
|
|
4
|
-
data.tar.gz:
|
|
3
|
+
metadata.gz: 5944b7a68fd13e6993315805c0cfdccb59e4fd9d
|
|
4
|
+
data.tar.gz: bb7a44c64076277287649e006002b7cf396e2043
|
|
5
5
|
SHA512:
|
|
6
|
-
metadata.gz:
|
|
7
|
-
data.tar.gz:
|
|
6
|
+
metadata.gz: 0d060ed3456c2c8eaeebf8b486d70a9a15d4f35e9c7b8102ebf72a14ed4e3486cdfc0c40a151733fb6054e052145717806d8e391747e1a95dce425690440b8df
|
|
7
|
+
data.tar.gz: 7d0729c5404c6425f720ef0ba3bd7fe602b35e2e8d94df70be6c27aaf2a93f84f9afc29450ecdfea9d721a9f7b7b152063d0f09fa9e41b818031b6d0185c5cf2
|
|
@@ -18,7 +18,7 @@ module ConfidentialInfoRedactorLite
|
|
|
18
18
|
next if initial_extracted_terms.length.eql?(segment.split(' ').length) && !in_corpus?(initial_extracted_terms)
|
|
19
19
|
search_ngrams(initial_extracted_terms, extracted_terms)
|
|
20
20
|
end
|
|
21
|
-
extracted_terms.uniq.reject(&:empty?)
|
|
21
|
+
extracted_terms.map { |t| t.gsub(/\{\}/, '') }.uniq.reject(&:empty?)
|
|
22
22
|
end
|
|
23
23
|
|
|
24
24
|
private
|
|
@@ -149,6 +149,11 @@ RSpec.describe ConfidentialInfoRedactorLite::Extractor do
|
|
|
149
149
|
text = 'John and Jane Doe'
|
|
150
150
|
expect(described_class.new(corpus: corpus, language: 'en').extract(text)).to eq(["John", "Jane Doe"])
|
|
151
151
|
end
|
|
152
|
+
|
|
153
|
+
it 'extracts the proper nouns from a text #019' do
|
|
154
|
+
text = 'Westin{}'
|
|
155
|
+
expect(described_class.new(corpus: corpus, language: 'en').extract(text)).to eq(["Westin"])
|
|
156
|
+
end
|
|
152
157
|
end
|
|
153
158
|
|
|
154
159
|
context 'German (de)' do
|