charazard 0.0.1

Sign up to get free protection for your applications and to get access to all the features.
checksums.yaml ADDED
@@ -0,0 +1,7 @@
1
+ ---
2
+ SHA1:
3
+ metadata.gz: 34b9d5367e647921915519d5a3a252f683ddf91b
4
+ data.tar.gz: b762b59f2e9ddeeefb4ade4afe6511a6756d1074
5
+ SHA512:
6
+ metadata.gz: 887e42a951e9fcb07146bcf9f7adc7dbde56f706dd6d964d32d345112bc27508a38d6210430218e2165ca785d07f1c5e37d840e74198938dc3a35c58f8b19a81
7
+ data.tar.gz: dd537a7e4d2ae0d675f06731a3aac65e729a0b28f341d6c4adcc8ec60073ab312aefa605722b03b3b093d76e5470af79bf430dc3d38b5e683a24390399334e1e
data/.gitignore ADDED
@@ -0,0 +1,3 @@
1
+ Gemfile.lock
2
+ pkg
3
+ .bundle
data/Gemfile ADDED
@@ -0,0 +1,3 @@
1
+ source 'https://rubygems.org'
2
+
3
+ gemspec
data/LICENSE.txt ADDED
@@ -0,0 +1,22 @@
1
+ Copyright (c) 2014 Jason Weathered
2
+
3
+ MIT License
4
+
5
+ Permission is hereby granted, free of charge, to any person obtaining
6
+ a copy of this software and associated documentation files (the
7
+ "Software"), to deal in the Software without restriction, including
8
+ without limitation the rights to use, copy, modify, merge, publish,
9
+ distribute, sublicense, and/or sell copies of the Software, and to
10
+ permit persons to whom the Software is furnished to do so, subject to
11
+ the following conditions:
12
+
13
+ The above copyright notice and this permission notice shall be
14
+ included in all copies or substantial portions of the Software.
15
+
16
+ THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
17
+ EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
18
+ MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
19
+ NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
20
+ LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
21
+ OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
22
+ WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
data/README.markdown ADDED
@@ -0,0 +1,64 @@
1
+ # Charazard
2
+
3
+ Cleans up bad character encodings with liberal application of fire.
4
+
5
+ ## Usage
6
+
7
+ ### Converting Windows-1252 (ISO 8859-1) to UTF-8
8
+
9
+ CSV files saved by Excel on Windows are by default encoded in Windows-1252 (which is close to but not quite ISO 8859-1 or ISO Latin 1).
10
+ `Charazard.fix_invalid_unicode_literals` can be used to convert these characters into valid UTF-8 without breaking existing UTF-8 strings.
11
+
12
+ ```ruby
13
+ Charazard.fix_invalid_unicode_literals("\x93Smart quotes\x94 \xC3\x9Cber Unicode")
14
+ # => "“Smart quotes” Über Unicode"
15
+ ```
16
+
17
+ `Charazard.fix_invalid_unicode_literals` can be used in combination with
18
+ [`filter_io`](https://github.com/jasoncodes/filter_io) to filter CSV streams.
19
+ Here’s an example that handles UTF-8/ISO-8859-1 with mixed line endings:
20
+
21
+ ``` ruby
22
+ require 'filter_io'
23
+ require 'charazard'
24
+ require 'csv'
25
+
26
+ File.open(filename, external_encoding: 'UTF-8') do |io|
27
+ io = FilterIO.new(io) do |data, state|
28
+ # fix invalid UTF-8 literals
29
+ data = Charazard.fix_invalid_unicode_literals(data)
30
+
31
+ # grab another chunk if the last character is a delimiter
32
+ raise FilterIO::NeedMoreData if data =~ /[\r\n]\z/ && !state.eof?
33
+ # normalise line endings to LF
34
+ data = data.gsub /\r\n|\r|\n/, "\n"
35
+
36
+ data
37
+ end
38
+
39
+ CSV.parse(io, row_sep: "\n") do |row|
40
+ p row
41
+ end
42
+ end
43
+ ```
44
+
45
+ ### Converting HTML to plain text
46
+
47
+ Feeds (RSS, product lists, etc.) often contain HTML which you may want to sanitize into plain text.
48
+ Charazard recognises basic formatting such as paragraphs and lists.
49
+
50
+ ```html
51
+ <p>First sentence.</p><p>Second sentenence.</p>
52
+ <ul><li>foo</li><li>bar</li></ul>
53
+ ```
54
+
55
+ ```ruby
56
+ text = Charazard.html_to_plain(html)
57
+ ```
58
+
59
+ ```markdown
60
+ First sentence.
61
+ Second sentenence.
62
+ * foo
63
+ * bar
64
+ ```
data/Rakefile ADDED
@@ -0,0 +1,17 @@
1
+ require 'bundler/gem_tasks'
2
+ require 'rake/testtask'
3
+
4
+ task :default => :test
5
+
6
+ desc 'Run the tests'
7
+ Rake::TestTask.new do |t|
8
+ t.libs.push 'lib'
9
+ t.libs.push 'test'
10
+ t.test_files = FileList['test/*_test.rb']
11
+ t.verbose = true
12
+ end
13
+
14
+ desc 'Open a Pry console with environment'
15
+ task :console do
16
+ exec "pry -Ilib -rcharazard"
17
+ end
data/charazard.gemspec ADDED
@@ -0,0 +1,25 @@
1
+ # coding: utf-8
2
+ lib = File.expand_path('../lib', __FILE__)
3
+ $LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
4
+ require 'charazard/version'
5
+
6
+ Gem::Specification.new do |spec|
7
+ spec.name = 'charazard'
8
+ spec.version = Charazard::VERSION
9
+ spec.authors = ['Jason Weathered']
10
+ spec.email = ['jason@jasoncodes.com']
11
+ spec.summary = %q{Cleans up bad character encodings with liberal application of fire.}
12
+ spec.homepage = 'https://github.com/jasoncodes/charazard'
13
+ spec.license = 'MIT'
14
+
15
+ spec.files = `git ls-files -z`.split("\x0")
16
+ spec.executables = spec.files.grep(%r{^bin/}) { |f| File.basename(f) }
17
+ spec.test_files = spec.files.grep(%r{^(test|spec|features)/})
18
+ spec.require_paths = ['lib']
19
+
20
+ spec.add_dependency 'nokogiri', '~> 1.5'
21
+
22
+ spec.add_development_dependency 'bundler', '~> 1.6'
23
+ spec.add_development_dependency 'rake'
24
+ spec.add_development_dependency 'pry'
25
+ end
@@ -0,0 +1,3 @@
1
+ module Charazard
2
+ VERSION = '0.0.1'
3
+ end
data/lib/charazard.rb ADDED
@@ -0,0 +1,107 @@
1
+ # coding: utf-8
2
+
3
+ require 'charazard/version'
4
+ require 'nokogiri'
5
+
6
+ module Charazard
7
+ extend self
8
+
9
+ CP1252_TABLE = {
10
+ 128 => 0x20AC, 130 => 0x201A, 131 => 0x0192, 132 => 0x201E, 133 => 0x2026, 134 => 0x2020, 135 => 0x2021,
11
+ 136 => 0x02C6, 137 => 0x2030, 138 => 0x0160, 139 => 0x2039, 140 => 0x0152, 142 => 0x017D, 145 => 0x2018,
12
+ 146 => 0x2019, 147 => 0x201C, 148 => 0x201D, 149 => 0x2022, 150 => 0x2013, 151 => 0x2014, 152 => 0x02DC,
13
+ 153 => 0x2122, 154 => 0x0161, 155 => 0x203A, 156 => 0x0153, 158 => 0x017E, 159 => 0x0178
14
+ }
15
+
16
+ UTF8_REGEX_PREFIX = /\A(
17
+ [\x09\x0A\x0D\x20-\x7E] # ASCII
18
+ | [\xC2-\xDF][\x80-\xBF] # non-overlong 2-byte
19
+ | \xE0[\xA0-\xBF][\x80-\xBF] # excluding overlongs
20
+ | [\xE1-\xEC\xEE][\x80-\xBF]{2} # straight 3-byte
21
+ | \xEF[\x80-\xBE]{2} #
22
+ | \xEF\xBF[\x80-\xBD] # excluding U+fffe and U+ffff
23
+ | \xED[\x80-\x9F][\x80-\xBF] # excluding surrogates
24
+ | \xF0[\x90-\xBF][\x80-\xBF]{2} # planes 1-3
25
+ | [\xF1-\xF3][\x80-\xBF]{3} # planes 4-15
26
+ | \xF4[\x80-\x8F][\x80-\xBF]{2} # plane 16
27
+ )*/nx;
28
+
29
+ def fix_invalid_unicode_literals(str)
30
+ input = str.dup.force_encoding('ASCII-8BIT')
31
+ input.gsub!(/\xef\xbb\xbf/n, '') # byte order marker
32
+ input.gsub!(/\xef\xbf\xbd/n, '') # replacement character
33
+ if input =~ /[\x80-\xFF]/n
34
+ output = input.slice! 0, 0
35
+ until input.empty?
36
+ input =~ UTF8_REGEX_PREFIX or raise "UTF8 match failed"
37
+ input = $'
38
+ output << $&
39
+ unless input.empty?
40
+ byte = input.slice!(0,1).ord
41
+ char = if CP1252_TABLE[byte]
42
+ [CP1252_TABLE[byte]].pack 'U'
43
+ else
44
+ [byte].pack 'U'
45
+ end
46
+ output << char.force_encoding('ASCII-8BIT')
47
+ end
48
+ end
49
+ output.force_encoding('UTF-8')
50
+ else
51
+ input.force_encoding('UTF-8')
52
+ end
53
+ end
54
+
55
+ def strip_dom(str, keep_newline = false)
56
+ str = str.gsub(/\v/, '') # remove vertical tabs
57
+ str = str.gsub(/(?:\s|\xC2\xA0|\xEF\xBF\xBD)+/) do |match|
58
+ if keep_newline && match =~ /(?:\r|\n)/
59
+ "\n"
60
+ else
61
+ " "
62
+ end
63
+ end
64
+ str = str.gsub(/[\x00-\x09\x0b-\x1f]/, '') # remove all chars < 0x20 except 0x10 (LF)
65
+ str.strip
66
+ end
67
+
68
+ def fix_cp1252_entities(str)
69
+ if str =~ /&#1[345][0-9];/
70
+ CP1252_TABLE.each do |from,to|
71
+ str = str.gsub "&##{from};", "&##{to};"
72
+ end
73
+ end
74
+ str
75
+ end
76
+
77
+ def html_to_plain(str, keep_newline = true)
78
+ str = fix_invalid_unicode_literals(str)
79
+
80
+ if str.include? '<' or str.include? '&'
81
+ str = fix_cp1252_entities(strip_dom(str))
82
+ str.gsub!(/-<-/, '-&lt;-')
83
+ doc = Nokogiri::HTML.fragment(str)
84
+ doc.search('style,script').each(&:remove)
85
+ doc.search('br').each do |br|
86
+ br.replace(Nokogiri::XML::Text.new("\n", doc))
87
+ end
88
+ doc.search('p,div').each do |p|
89
+ p.add_next_sibling(Nokogiri::XML::Text.new("\n", doc))
90
+ p.add_previous_sibling(Nokogiri::XML::Text.new("\n", doc))
91
+ end
92
+ doc.search('ul,ol').each do |list|
93
+ is_ordered = list.node_name.downcase == 'ol'
94
+ start = list[:start] =~ /\A(\d+)\z/ ? $1.to_i : 1
95
+ list.add_next_sibling Nokogiri::XML::Text.new("\n", doc)
96
+ list.add_previous_sibling Nokogiri::XML::Text.new("\n", doc)
97
+ list.css('li').each_with_index do |item,index|
98
+ item_prefix_text = is_ordered ? "\n#{start+index}. " : "\n* "
99
+ item.add_previous_sibling Nokogiri::XML::Text.new(item_prefix_text, doc)
100
+ end
101
+ end
102
+ str = doc.inner_text
103
+ end
104
+
105
+ return strip_dom(str, keep_newline)
106
+ end
107
+ end
@@ -0,0 +1,167 @@
1
+ # -*- coding: utf-8 -*-
2
+
3
+ require 'test_helper'
4
+
5
+ describe Charazard do
6
+ describe 'fix_invalid_unicode_literals' do
7
+ test "Test ISO-8859-1 literal conversion is idempotent" do
8
+ assert_equal Charazard.html_to_plain("&trade; &copy; &reg;"), Charazard.fix_invalid_unicode_literals(Charazard.fix_invalid_unicode_literals("\231 \251 \256"))
9
+ end
10
+
11
+ test "ISO-8859-1 characters within words" do
12
+ assert_equal "M\xc3\xa9nage \xc3\xa0 Trois for", Charazard.fix_invalid_unicode_literals("M\xe9nage \xe0 Trois for")
13
+ end
14
+
15
+ test "should fix literals in ASCII-8BIT without breaking correct UTF-8" do
16
+ input = "r\xc3\xa9sum\xe9"
17
+ input.force_encoding 'ASCII-8BIT'
18
+ expected = "r\xc3\xa9sum\xc3\xa9"
19
+ output = Charazard.fix_invalid_unicode_literals(input)
20
+ assert_equal expected, output
21
+ end
22
+
23
+ test "replacement character (U+FFFD, UTF-8 EF BF BD) as invalid literal" do
24
+ assert_equal "foo bar", Charazard.fix_invalid_unicode_literals("foo \xef\xbf\xbdbar")
25
+ end
26
+
27
+ test "byte order marker (U+FEFF, UTF-8 EF BB BF) as invalid literal" do
28
+ assert_equal "foo bar", Charazard.fix_invalid_unicode_literals("foo \xef\xbb\xbfbar")
29
+ end
30
+ end
31
+
32
+ describe 'strip_dom' do
33
+ test "whitespace normalisation removing newlines" do
34
+ assert_equal "foo bar", Charazard.strip_dom(" foo \n\t\tbar \n ")
35
+ end
36
+
37
+ test "whitespace normalisation keeping newlines" do
38
+ assert_equal "foo\nbar", Charazard.strip_dom(" foo \n\t\tbar \n ", true)
39
+ end
40
+
41
+ test "newline preservation with multiple newlines together" do
42
+ assert_equal "foo\nbar\nbaz", Charazard.strip_dom("foo\n\n\n\nbar\t\n\t\n\tbaz", true)
43
+ end
44
+
45
+ test "non-breaking space (UTF-8 C2 A0)" do
46
+ assert_equal "foo bar", Charazard.strip_dom("foo\xc2\xa0bar")
47
+ end
48
+
49
+ test "replacement character (U+FFFD, UTF-8 EF BF BD)" do
50
+ assert_equal "foo bar", Charazard.strip_dom("foo\xef\xbf\xbdbar")
51
+ end
52
+
53
+ test "CR in newline removal" do
54
+ assert_equal "foo bar", Charazard.strip_dom("foo\rbar", false)
55
+ end
56
+
57
+ test "CR in newline preservation" do
58
+ assert_equal "foo\nbar", Charazard.strip_dom("foo\rbar", true)
59
+ end
60
+
61
+ test "invalid Unicode code points below 0x20" do
62
+ assert_equal "foobar", Charazard.strip_dom("foo\006bar")
63
+ assert_equal "foobar\nbaz", Charazard.strip_dom("foo\006bar\n baz", true)
64
+ assert_equal "shes", Charazard.strip_dom("\x73\x68\x65\x1a\x73")
65
+ end
66
+ end
67
+
68
+ describe 'html_to_plain' do
69
+ test "html basic entities" do
70
+ assert_equal "foo & \"bar\" <baz>", Charazard.html_to_plain("foo &amp; &quot;bar\" &lt;baz&gt;")
71
+ assert_equal "foo\xc2\xae bar \xe2\x82\xac123!", Charazard.html_to_plain("foo&reg; bar &euro;12&#51;&#33;")
72
+ end
73
+
74
+ test "html basic pass through" do
75
+ assert_equal "foo bar", Charazard.html_to_plain("foo bar")
76
+ end
77
+
78
+ test "html basic whitespace" do
79
+ assert_equal "foo bar baz. Hello world. 1 2 3.", Charazard.html_to_plain("foo&nbsp;bar baz.&nbsp; Hello world. 1 2 3.")
80
+ end
81
+
82
+ test "html basic elements" do
83
+ assert_equal "This is a test.", Charazard.html_to_plain("<strong>This</strong> <em>is <span style='text-decoration: underline'>a</span></em> <a href='http://www.example.com/' title=\"Testing\">test</a>.")
84
+ end
85
+
86
+ test "html block entities" do
87
+ assert_equal "Foo\nBar\nabc\ndef\nghi", Charazard.html_to_plain("<p>Foo</p><p>Bar</p><p>abc<p>def<br />ghi")
88
+ end
89
+
90
+ test "invalid Unicode code points in numeric entities from CP1252" do
91
+ assert_equal "that\xe2\x80\x99s \xe2\x80\x93 a test", Charazard.html_to_plain("that&#146;s &#150; a test")
92
+ end
93
+
94
+ test "Test common ISO-8859-1 literals" do
95
+ assert_equal Charazard.html_to_plain("Foo&reg; Bar&trade; &copy;2010"), Charazard.html_to_plain("Foo\256 Bar\231 \2512010")
96
+ end
97
+
98
+ test "ISO-8859-1 capital A grave accent literal" do
99
+ assert_equal "\xc3\x82", Charazard.html_to_plain(Charazard.html_to_plain("\xc2"))
100
+ end
101
+
102
+ test "Line tabulation character U+000B in HTML should be stripped" do
103
+ assert_equal 'foobar', Charazard.html_to_plain("foo\x0bbar")
104
+ end
105
+
106
+ test "Newline U+000A in HTML should be preserved" do
107
+ assert_equal "foo\nbar", Charazard.html_to_plain("foo\nbar")
108
+ end
109
+
110
+ test "Tab U+0009 in HTML should be normalised to space" do
111
+ assert_equal "foo bar", Charazard.html_to_plain("foo\tbar")
112
+ end
113
+
114
+ test "Combination of different conversion cases in HTML to plain" do
115
+ assert_equal "A\nB\xc3\x82CD", Charazard.html_to_plain(Charazard.html_to_plain("A\nB\xc2C\x0bD"))
116
+ end
117
+
118
+ test "stylesheet and script blocks should be stripped" do
119
+ html = <<-HTML
120
+ foo
121
+ <script>alert('hi');</script><strong>bar</strong>
122
+ <style type="text/css">
123
+ body
124
+ {
125
+ font-face: Helvetica;
126
+ }
127
+ </style>
128
+ baz
129
+ HTML
130
+ plain = "foo bar baz"
131
+ assert_equal plain, Charazard.html_to_plain(html)
132
+ end
133
+
134
+ test "unordered lists should format as lines" do
135
+ html = "foo<ul><li>one</li><li>two</li><li>three</li></ul>bar"
136
+ plain = "foo\n* one\n* two\n* three\nbar"
137
+ assert_equal plain, Charazard.html_to_plain(html)
138
+ end
139
+
140
+ test "ordered lists should format as lines" do
141
+ html = "foo<ol><li>one</li><li>two</li><li>three</li></ol>bar"
142
+ plain = "foo\n1. one\n2. two\n3. three\nbar"
143
+ assert_equal plain, Charazard.html_to_plain(html)
144
+ end
145
+
146
+ test "ordered list with start offset" do
147
+ html = "<ol start=3><li>three</li><li>four</li></ol>"
148
+ plain = "3. three\n4. four"
149
+ assert_equal plain, Charazard.html_to_plain(html)
150
+ end
151
+
152
+ test "should be converted to UTF-8" do
153
+ input = "Foo\nBar\x99".force_encoding('ASCII-8BIT').split("\n").to_a
154
+ expected = ["Foo", "Bar\xE2\x84\xA2"]
155
+ actual = input.map { |str| Charazard.html_to_plain(str) }
156
+ assert_equal expected, actual
157
+ expected.zip(actual).each do |expected_line, actual_line|
158
+ assert_equal expected_line.encoding, actual_line.encoding
159
+ end
160
+ end
161
+
162
+ test "URL containing hyphen-less-than-hyphen passes through" do
163
+ str = "http://example.com/age-<-5-years"
164
+ assert_equal str, Charazard.html_to_plain(str)
165
+ end
166
+ end
167
+ end
@@ -0,0 +1,8 @@
1
+ require 'minitest/spec'
2
+ require 'minitest/autorun'
3
+
4
+ MiniTest::Spec::DSL.class_eval do
5
+ alias_method :test, :it
6
+ end
7
+
8
+ require 'charazard'
metadata ADDED
@@ -0,0 +1,112 @@
1
+ --- !ruby/object:Gem::Specification
2
+ name: charazard
3
+ version: !ruby/object:Gem::Version
4
+ version: 0.0.1
5
+ platform: ruby
6
+ authors:
7
+ - Jason Weathered
8
+ autorequire:
9
+ bindir: bin
10
+ cert_chain: []
11
+ date: 2014-06-11 00:00:00.000000000 Z
12
+ dependencies:
13
+ - !ruby/object:Gem::Dependency
14
+ name: nokogiri
15
+ requirement: !ruby/object:Gem::Requirement
16
+ requirements:
17
+ - - "~>"
18
+ - !ruby/object:Gem::Version
19
+ version: '1.5'
20
+ type: :runtime
21
+ prerelease: false
22
+ version_requirements: !ruby/object:Gem::Requirement
23
+ requirements:
24
+ - - "~>"
25
+ - !ruby/object:Gem::Version
26
+ version: '1.5'
27
+ - !ruby/object:Gem::Dependency
28
+ name: bundler
29
+ requirement: !ruby/object:Gem::Requirement
30
+ requirements:
31
+ - - "~>"
32
+ - !ruby/object:Gem::Version
33
+ version: '1.6'
34
+ type: :development
35
+ prerelease: false
36
+ version_requirements: !ruby/object:Gem::Requirement
37
+ requirements:
38
+ - - "~>"
39
+ - !ruby/object:Gem::Version
40
+ version: '1.6'
41
+ - !ruby/object:Gem::Dependency
42
+ name: rake
43
+ requirement: !ruby/object:Gem::Requirement
44
+ requirements:
45
+ - - ">="
46
+ - !ruby/object:Gem::Version
47
+ version: '0'
48
+ type: :development
49
+ prerelease: false
50
+ version_requirements: !ruby/object:Gem::Requirement
51
+ requirements:
52
+ - - ">="
53
+ - !ruby/object:Gem::Version
54
+ version: '0'
55
+ - !ruby/object:Gem::Dependency
56
+ name: pry
57
+ requirement: !ruby/object:Gem::Requirement
58
+ requirements:
59
+ - - ">="
60
+ - !ruby/object:Gem::Version
61
+ version: '0'
62
+ type: :development
63
+ prerelease: false
64
+ version_requirements: !ruby/object:Gem::Requirement
65
+ requirements:
66
+ - - ">="
67
+ - !ruby/object:Gem::Version
68
+ version: '0'
69
+ description:
70
+ email:
71
+ - jason@jasoncodes.com
72
+ executables: []
73
+ extensions: []
74
+ extra_rdoc_files: []
75
+ files:
76
+ - ".gitignore"
77
+ - Gemfile
78
+ - LICENSE.txt
79
+ - README.markdown
80
+ - Rakefile
81
+ - charazard.gemspec
82
+ - lib/charazard.rb
83
+ - lib/charazard/version.rb
84
+ - test/charazard_test.rb
85
+ - test/test_helper.rb
86
+ homepage: https://github.com/jasoncodes/charazard
87
+ licenses:
88
+ - MIT
89
+ metadata: {}
90
+ post_install_message:
91
+ rdoc_options: []
92
+ require_paths:
93
+ - lib
94
+ required_ruby_version: !ruby/object:Gem::Requirement
95
+ requirements:
96
+ - - ">="
97
+ - !ruby/object:Gem::Version
98
+ version: '0'
99
+ required_rubygems_version: !ruby/object:Gem::Requirement
100
+ requirements:
101
+ - - ">="
102
+ - !ruby/object:Gem::Version
103
+ version: '0'
104
+ requirements: []
105
+ rubyforge_project:
106
+ rubygems_version: 2.2.2
107
+ signing_key:
108
+ specification_version: 4
109
+ summary: Cleans up bad character encodings with liberal application of fire.
110
+ test_files:
111
+ - test/charazard_test.rb
112
+ - test/test_helper.rb