confidential_info_redactor 0.0.7 → 0.0.8
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: 618575745203cab096e0fe7c6589ebbaadb45b69
|
4
|
+
data.tar.gz: 6259ad839c30e5abbe079c3ce7affb109ea17367
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 22656a12c77e0b18016e1860104e6c287eb29d2cb0fc431d9edcd851e42bcf1ac2488865d0773f784ceaab2e4b161d49729e0d840cd5239a98e6982069f9d823
|
7
|
+
data.tar.gz: a85abad1e3687888d022cc15e9b47f4e515173824185f26bc21b4ab7449b1fdf2c9ee3e1a01ae32d69c4784e10e492a381b34aaf515ba10b8861c974c4d59b89
|
@@ -4,8 +4,8 @@ require 'confidential_info_redactor/hyperlink'
|
|
4
4
|
module ConfidentialInfoRedactor
|
5
5
|
# This class redacts various tokens from a text
|
6
6
|
class Redactor
|
7
|
-
# Rubular: http://rubular.com/r/
|
8
|
-
NUMBER_REGEX = /(?<=\A|\A\()[^(]?\d+((,|\.)*\d)*(\D?\s|\s|\.?\s|\.$)|(?<=\s|\s\()[^(]?\d+((,|\.)*\d)*(?=(\D?\s|\s|\.?\s|\.$))|(?<=\s)\d+(nd|th|st)|(?<=\s)\d+\/\d+\"*(?=\s)/
|
7
|
+
# Rubular: http://rubular.com/r/OI2wQZ0KSl
|
8
|
+
NUMBER_REGEX = /(?<=\A|\A\()[^(]?\d+((,|\.)*\d)*(\D?\s|\s|\.?\s|\.$)|(?<=\s|\s\()[^(]?\d+((,|\.)*\d)*(?=(\D?\s|\s|\.?\s|\.$))|(?<=\s)\d+(nd|th|st)|(?<=\s)\d+\/\d+\"*(?=\s)|(?<=\()\S{1}\d+(?=\))|(?<=\s{1})\S{1}\d+\z/
|
9
9
|
# Rubular: http://rubular.com/r/mxcj2G0Jfa
|
10
10
|
EMAIL_REGEX = /(?<=\A|\s|\()[\w+\-.]+@[a-z\d\-]+(\.[a-z]+)*\.[a-z]+(?=\z|\s|\.|\))/i
|
11
11
|
|
@@ -66,7 +66,7 @@ module ConfidentialInfoRedactor
|
|
66
66
|
end
|
67
67
|
|
68
68
|
def redact_numbers(txt)
|
69
|
-
txt.gsub(NUMBER_REGEX, " #{number_text} ").gsub(/\s*#{Regexp.escape(number_text)}\s*/, " #{number_text} ").gsub(/\A\s*#{Regexp.escape(number_text)}\s*/, "#{number_text} ").gsub(/#{Regexp.escape(number_text)}\s{1}\.{1}/, "#{number_text}.").gsub(/#{Regexp.escape(number_text)}\s{1}\,{1}/, "#{number_text},").gsub(/#{Regexp.escape(number_text)}\s{1}\){1}/, "#{number_text})").gsub(/\(\s{1}#{Regexp.escape(number_text)}/, "(#{number_text}")
|
69
|
+
txt.gsub(NUMBER_REGEX, " #{number_text} ").gsub(/\s*#{Regexp.escape(number_text)}\s*/, " #{number_text} ").gsub(/\A\s*#{Regexp.escape(number_text)}\s*/, "#{number_text} ").gsub(/#{Regexp.escape(number_text)}\s{1}\.{1}/, "#{number_text}.").gsub(/#{Regexp.escape(number_text)}\s{1}\,{1}/, "#{number_text},").gsub(/#{Regexp.escape(number_text)}\s{1}\){1}/, "#{number_text})").gsub(/\(\s{1}#{Regexp.escape(number_text)}/, "(#{number_text}").gsub(/#{Regexp.escape(number_text)}\s\z/, "#{number_text}")
|
70
70
|
end
|
71
71
|
|
72
72
|
def redact_emails(txt)
|
@@ -38,6 +38,16 @@ RSpec.describe ConfidentialInfoRedactor::Redactor do
|
|
38
38
|
text = 'It was his 1st time, not yet his 10th, not even his 2nd. The wood was 3/4" thick.'
|
39
39
|
expect(described_class.new(text: text, language: 'en').numbers).to eq('It was his <redacted number> time, not yet his <redacted number>, not even his <redacted number>. The wood was <redacted number> thick.')
|
40
40
|
end
|
41
|
+
|
42
|
+
it 'redacts numbers from a text #004' do
|
43
|
+
text = 'Checking file of %2'
|
44
|
+
expect(described_class.new(text: text, language: 'en').numbers).to eq('Checking file of <redacted number>')
|
45
|
+
end
|
46
|
+
|
47
|
+
it 'redacts numbers from a text #005' do
|
48
|
+
text = 'zawiera pliki skompresowane (%2).'
|
49
|
+
expect(described_class.new(text: text, language: 'en').numbers).to eq('zawiera pliki skompresowane (<redacted number>).')
|
50
|
+
end
|
41
51
|
end
|
42
52
|
|
43
53
|
describe '#emails' do
|
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: 0.0.8
|
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: 2015-04-22 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: bundler
|