confidential_info_redactor 0.0.2 → 0.0.3
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: 53df3b59f337fc1c1975f4cc37701bce82867bea
|
4
|
+
data.tar.gz: 48619c48b24dcc0fdfc6b407f911045f4c5286c7
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: b63e2e817891fe6fe20664f7b0dd279193015ad6b491303914593f2955c1941e1277e3f58b4eff7e9d166378f7b4455cb8143b0df51413bdbe068a01df295d9f
|
7
|
+
data.tar.gz: 66af11baec2a927039becc83da9366d5beea1c8fcb263ec15c78af4b6f3ac5558566fb18e624e4f9e0a530598d4834d47998ab8ee97bb18f52b4ff6327ec7ac6
|
data/README.md
CHANGED
@@ -74,7 +74,8 @@ ConfidentialInfoRedactor::Redactor.new(text: text, language: 'de', tokens: token
|
|
74
74
|
# => 'Viele Mitarbeiter der <redacted> suchen eine andere Arbeitsstelle.'
|
75
75
|
|
76
76
|
# It is also possible to change the redaction text
|
77
|
-
|
77
|
+
text = 'Coca-Cola announced a merger with Pepsi that will happen on December 15th, 2020 for $200,000,000,000. Please contact John Smith at j.smith@example.com or visit http://www.super-fake-merger.com.'
|
78
|
+
tokens = ['Coca-Cola', 'Pepsi', 'John Smith']
|
78
79
|
ConfidentialInfoRedactor::Redactor.new(text: text, tokens: tokens, number_text: '**redacted number**', date_text: '^^redacted date^^', token_text: '*****').redact
|
79
80
|
# => '***** announced a merger with ***** that will happen on ^^redacted date^^ for **redacted number**. Please contact ***** at ***** or visit *****.'
|
80
81
|
```
|
@@ -62,7 +62,7 @@ module ConfidentialInfoRedactor
|
|
62
62
|
end
|
63
63
|
|
64
64
|
def redact_dates(txt)
|
65
|
-
ConfidentialInfoRedactor::Date.new(string: txt, language: language).replace.gsub(/\s*#{Regexp.escape(date_text)}\s*/, " #{date_text} ").gsub(/\A\s*#{Regexp.escape(date_text)}\s*/, "#{date_text} ").gsub(/#{Regexp.escape(date_text)}\s{1}\.{1}/, "#{date_text}.")
|
65
|
+
ConfidentialInfoRedactor::Date.new(string: txt, language: language).replace.gsub(/<redacted date>/, "#{date_text}").gsub(/\s*#{Regexp.escape(date_text)}\s*/, " #{date_text} ").gsub(/\A\s*#{Regexp.escape(date_text)}\s*/, "#{date_text} ").gsub(/#{Regexp.escape(date_text)}\s{1}\.{1}/, "#{date_text}.")
|
66
66
|
end
|
67
67
|
|
68
68
|
def redact_numbers(txt)
|
@@ -148,5 +148,11 @@ RSpec.describe ConfidentialInfoRedactor::Redactor do
|
|
148
148
|
text = 'Coca-Cola announced a merger with Pepsi that will happen on December 15th, 2020 for $200,000,000,000. Please contact John Smith at j.smith@example.com or visit http://www.super-fake-merger.com.'
|
149
149
|
expect(described_class.new(text: text, language: 'en', tokens: tokens, ignore_numbers: true).redact).to eq('<redacted> announced a merger with <redacted> that will happen on <redacted date> for $200,000,000,000. Please contact <redacted> at <redacted> or visit <redacted>.')
|
150
150
|
end
|
151
|
+
|
152
|
+
it 'redacts all confidential information from a text #005' do
|
153
|
+
tokens = ['Coca-Cola', 'Pepsi', 'John Smith']
|
154
|
+
text = 'Coca-Cola announced a merger with Pepsi that will happen on December 15th, 2020 for $200,000,000,000. Please contact John Smith at j.smith@example.com or visit http://www.super-fake-merger.com.'
|
155
|
+
expect(described_class.new(text: text, language: 'en', tokens: tokens, number_text: '**redacted number**', date_text: '^^redacted date^^', token_text: '*****').redact).to eq('***** announced a merger with ***** that will happen on ^^redacted date^^ for **redacted number**. Please contact ***** at ***** or visit *****.')
|
156
|
+
end
|
151
157
|
end
|
152
158
|
end
|