trenni-sanitize 0.2.0 → 0.6.1
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 +5 -5
- data/lib/trenni/sanitize.rb +0 -3
- data/lib/trenni/sanitize/filter.rb +12 -8
- data/lib/trenni/sanitize/fragment.rb +9 -2
- data/lib/trenni/sanitize/text.rb +17 -0
- data/lib/trenni/sanitize/version.rb +1 -1
- metadata +30 -51
- data/.gitignore +0 -19
- data/.rspec +0 -5
- data/.simplecov +0 -9
- data/.travis.yml +0 -17
- data/Gemfile +0 -16
- data/README.md +0 -134
- data/Rakefile +0 -19
- data/lib/trenni/sanitize/extensions.rb +0 -14
- data/spec/spec_helper.rb +0 -53
- data/spec/trenni/sanitize/benchmark_spec.rb +0 -36
- data/spec/trenni/sanitize/extensions_spec.rb +0 -26
- data/spec/trenni/sanitize/fragment_spec.rb +0 -66
- data/spec/trenni/sanitize/sample.html +0 -12
- data/spec/trenni/sanitize/text_spec.rb +0 -0
- data/trenni-sanitize.gemspec +0 -25
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
|
-
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
2
|
+
SHA256:
|
3
|
+
metadata.gz: dde3cfd019e5d0032580e229311ea3c7f61d7c06eff3f925f9e675854987be46
|
4
|
+
data.tar.gz: e30d0b421328ab5b6d324a087a42fa82147c069af24800829969b8e810122908
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 8e2b9bf2f46cef2279ca08297317939cd53e98ed1a39b703f4e2d4d6cfe0afbce838bbeed7ad83f497666e2277f9cdbbd242232ac2d7a2d4e66a434b7b2935fc
|
7
|
+
data.tar.gz: 853edec88367727c751000d0aca1ec1c1b63497b6d21077a7fcba2b5378f507b48dd60c1edce04dba784d427e487933b558736873bd5958886efc15fb1eb0c27
|
data/lib/trenni/sanitize.rb
CHANGED
@@ -64,7 +64,11 @@ module Trenni
|
|
64
64
|
end
|
65
65
|
|
66
66
|
def [] key
|
67
|
-
self.tag
|
67
|
+
self.tag&.attributes[key]
|
68
|
+
end
|
69
|
+
|
70
|
+
def limit_attributes(keys)
|
71
|
+
self.tag&.attributes&.select!{|key, value| keys.include?(key)}
|
68
72
|
end
|
69
73
|
end
|
70
74
|
|
@@ -116,11 +120,11 @@ module Trenni
|
|
116
120
|
|
117
121
|
@current = Node.new(name, tag, current.skip)
|
118
122
|
end
|
119
|
-
|
123
|
+
|
120
124
|
def attribute(key, value)
|
121
125
|
@current.tag.attributes[key] = value
|
122
126
|
end
|
123
|
-
|
127
|
+
|
124
128
|
def open_tag_end(self_closing)
|
125
129
|
if self_closing
|
126
130
|
@current.tag.closed = true
|
@@ -135,7 +139,7 @@ module Trenni
|
|
135
139
|
# If the tag was self-closing, it's no longer current at this point, we are back in the context of the parent tag.
|
136
140
|
@current = self.top if self_closing
|
137
141
|
end
|
138
|
-
|
142
|
+
|
139
143
|
def close_tag(name, offset = nil)
|
140
144
|
while node = @stack.pop
|
141
145
|
node.tag.write_closing_tag(@output) unless node.skip? TAG
|
@@ -153,19 +157,19 @@ module Trenni
|
|
153
157
|
def doctype(string)
|
154
158
|
@output << string unless current.skip? DOCTYPE
|
155
159
|
end
|
156
|
-
|
160
|
+
|
157
161
|
def comment(string)
|
158
162
|
@output << string unless current.skip? COMMENT
|
159
163
|
end
|
160
|
-
|
164
|
+
|
161
165
|
def instruction(string)
|
162
166
|
@output << string unless current.skip? INSTRUCTION
|
163
167
|
end
|
164
|
-
|
168
|
+
|
165
169
|
def cdata(string)
|
166
170
|
@output << string unless current.skip? CDATA
|
167
171
|
end
|
168
|
-
|
172
|
+
|
169
173
|
def text(string)
|
170
174
|
Markup.append(@output, string) unless current.skip? TEXT
|
171
175
|
end
|
@@ -20,10 +20,12 @@
|
|
20
20
|
|
21
21
|
require_relative 'filter'
|
22
22
|
|
23
|
+
require 'set'
|
24
|
+
|
23
25
|
module Trenni
|
24
26
|
module Sanitize
|
25
27
|
class Fragment < Filter
|
26
|
-
STANDARD_ATTRIBUTES = ['class', 'style'].freeze
|
28
|
+
STANDARD_ATTRIBUTES = Set.new(['class', 'style']).freeze
|
27
29
|
|
28
30
|
ALLOWED_TAGS = {
|
29
31
|
'div' => STANDARD_ATTRIBUTES,
|
@@ -34,6 +36,11 @@ module Trenni
|
|
34
36
|
'em' => STANDARD_ATTRIBUTES,
|
35
37
|
'strong' => STANDARD_ATTRIBUTES,
|
36
38
|
'ul' => STANDARD_ATTRIBUTES,
|
39
|
+
'ol' => STANDARD_ATTRIBUTES,
|
40
|
+
'li' => STANDARD_ATTRIBUTES,
|
41
|
+
'dl' => STANDARD_ATTRIBUTES,
|
42
|
+
'dt' => STANDARD_ATTRIBUTES,
|
43
|
+
'dd' => STANDARD_ATTRIBUTES,
|
37
44
|
'strike' => STANDARD_ATTRIBUTES,
|
38
45
|
'h1' => STANDARD_ATTRIBUTES,
|
39
46
|
'h2' => STANDARD_ATTRIBUTES,
|
@@ -49,7 +56,7 @@ module Trenni
|
|
49
56
|
|
50
57
|
def filter(node)
|
51
58
|
if attributes = ALLOWED_TAGS[node.name]
|
52
|
-
node.
|
59
|
+
node.limit_attributes(attributes)
|
53
60
|
|
54
61
|
node.accept!
|
55
62
|
else
|
data/lib/trenni/sanitize/text.rb
CHANGED
@@ -23,7 +23,16 @@ require_relative 'filter'
|
|
23
23
|
module Trenni
|
24
24
|
module Sanitize
|
25
25
|
class Text < Filter
|
26
|
+
CLOSING = {
|
27
|
+
"p" => "\n\n",
|
28
|
+
"div" => "\n\n",
|
29
|
+
}
|
30
|
+
|
26
31
|
def filter(node)
|
32
|
+
if node.name == "br"
|
33
|
+
text("\n\n")
|
34
|
+
end
|
35
|
+
|
27
36
|
if node.name == 'script'
|
28
37
|
node.skip!(ALL) # Skip everything including content.
|
29
38
|
else
|
@@ -31,6 +40,14 @@ module Trenni
|
|
31
40
|
end
|
32
41
|
end
|
33
42
|
|
43
|
+
def close_tag(name, offset = nil)
|
44
|
+
super
|
45
|
+
|
46
|
+
if value = CLOSING[name]
|
47
|
+
text(value)
|
48
|
+
end
|
49
|
+
end
|
50
|
+
|
34
51
|
def doctype(string)
|
35
52
|
end
|
36
53
|
|
metadata
CHANGED
@@ -1,14 +1,14 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: trenni-sanitize
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.
|
4
|
+
version: 0.6.1
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Samuel Williams
|
8
|
-
autorequire:
|
8
|
+
autorequire:
|
9
9
|
bindir: bin
|
10
10
|
cert_chain: []
|
11
|
-
date:
|
11
|
+
date: 2020-11-19 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: trenni
|
@@ -16,110 +16,89 @@ dependencies:
|
|
16
16
|
requirements:
|
17
17
|
- - "~>"
|
18
18
|
- !ruby/object:Gem::Version
|
19
|
-
version: 3.5
|
19
|
+
version: '3.5'
|
20
20
|
type: :runtime
|
21
21
|
prerelease: false
|
22
22
|
version_requirements: !ruby/object:Gem::Requirement
|
23
23
|
requirements:
|
24
24
|
- - "~>"
|
25
25
|
- !ruby/object:Gem::Version
|
26
|
-
version: 3.5
|
26
|
+
version: '3.5'
|
27
27
|
- !ruby/object:Gem::Dependency
|
28
28
|
name: bundler
|
29
29
|
requirement: !ruby/object:Gem::Requirement
|
30
30
|
requirements:
|
31
|
-
- - "
|
31
|
+
- - ">="
|
32
32
|
- !ruby/object:Gem::Version
|
33
|
-
version: '
|
33
|
+
version: '0'
|
34
34
|
type: :development
|
35
35
|
prerelease: false
|
36
36
|
version_requirements: !ruby/object:Gem::Requirement
|
37
37
|
requirements:
|
38
|
-
- - "
|
38
|
+
- - ">="
|
39
39
|
- !ruby/object:Gem::Version
|
40
|
-
version: '
|
40
|
+
version: '0'
|
41
41
|
- !ruby/object:Gem::Dependency
|
42
|
-
name:
|
42
|
+
name: covered
|
43
43
|
requirement: !ruby/object:Gem::Requirement
|
44
44
|
requirements:
|
45
|
-
- - "
|
45
|
+
- - ">="
|
46
46
|
- !ruby/object:Gem::Version
|
47
|
-
version: '
|
47
|
+
version: '0'
|
48
48
|
type: :development
|
49
49
|
prerelease: false
|
50
50
|
version_requirements: !ruby/object:Gem::Requirement
|
51
51
|
requirements:
|
52
|
-
- - "
|
52
|
+
- - ">="
|
53
53
|
- !ruby/object:Gem::Version
|
54
|
-
version: '
|
54
|
+
version: '0'
|
55
55
|
- !ruby/object:Gem::Dependency
|
56
|
-
name:
|
56
|
+
name: rspec
|
57
57
|
requirement: !ruby/object:Gem::Requirement
|
58
58
|
requirements:
|
59
|
-
- - "
|
59
|
+
- - "~>"
|
60
60
|
- !ruby/object:Gem::Version
|
61
|
-
version: '
|
61
|
+
version: '3.4'
|
62
62
|
type: :development
|
63
63
|
prerelease: false
|
64
64
|
version_requirements: !ruby/object:Gem::Requirement
|
65
65
|
requirements:
|
66
|
-
- - "
|
66
|
+
- - "~>"
|
67
67
|
- !ruby/object:Gem::Version
|
68
|
-
version: '
|
69
|
-
description:
|
68
|
+
version: '3.4'
|
69
|
+
description:
|
70
70
|
email:
|
71
|
-
- samuel.williams@oriontransfer.co.nz
|
72
71
|
executables: []
|
73
72
|
extensions: []
|
74
73
|
extra_rdoc_files: []
|
75
74
|
files:
|
76
|
-
- ".gitignore"
|
77
|
-
- ".rspec"
|
78
|
-
- ".simplecov"
|
79
|
-
- ".travis.yml"
|
80
|
-
- Gemfile
|
81
|
-
- README.md
|
82
|
-
- Rakefile
|
83
75
|
- lib/trenni/sanitize.rb
|
84
|
-
- lib/trenni/sanitize/extensions.rb
|
85
76
|
- lib/trenni/sanitize/filter.rb
|
86
77
|
- lib/trenni/sanitize/fragment.rb
|
87
78
|
- lib/trenni/sanitize/text.rb
|
88
79
|
- lib/trenni/sanitize/version.rb
|
89
|
-
- spec/spec_helper.rb
|
90
|
-
- spec/trenni/sanitize/benchmark_spec.rb
|
91
|
-
- spec/trenni/sanitize/extensions_spec.rb
|
92
|
-
- spec/trenni/sanitize/fragment_spec.rb
|
93
|
-
- spec/trenni/sanitize/sample.html
|
94
|
-
- spec/trenni/sanitize/text_spec.rb
|
95
|
-
- trenni-sanitize.gemspec
|
96
80
|
homepage: https://github.com/ioquatix/trenni-sanitize
|
97
|
-
licenses:
|
98
|
-
|
99
|
-
|
81
|
+
licenses:
|
82
|
+
- MIT
|
83
|
+
metadata:
|
84
|
+
funding_uri: https://github.com/sponsors/ioquatix/
|
85
|
+
post_install_message:
|
100
86
|
rdoc_options: []
|
101
87
|
require_paths:
|
102
88
|
- lib
|
103
89
|
required_ruby_version: !ruby/object:Gem::Requirement
|
104
90
|
requirements:
|
105
|
-
- - "
|
91
|
+
- - ">="
|
106
92
|
- !ruby/object:Gem::Version
|
107
|
-
version: '2.
|
93
|
+
version: '2.5'
|
108
94
|
required_rubygems_version: !ruby/object:Gem::Requirement
|
109
95
|
requirements:
|
110
96
|
- - ">="
|
111
97
|
- !ruby/object:Gem::Version
|
112
98
|
version: '0'
|
113
99
|
requirements: []
|
114
|
-
|
115
|
-
|
116
|
-
signing_key:
|
100
|
+
rubygems_version: 3.1.2
|
101
|
+
signing_key:
|
117
102
|
specification_version: 4
|
118
103
|
summary: Sanitize markdown according to a set of rules.
|
119
|
-
test_files:
|
120
|
-
- spec/spec_helper.rb
|
121
|
-
- spec/trenni/sanitize/benchmark_spec.rb
|
122
|
-
- spec/trenni/sanitize/extensions_spec.rb
|
123
|
-
- spec/trenni/sanitize/fragment_spec.rb
|
124
|
-
- spec/trenni/sanitize/sample.html
|
125
|
-
- spec/trenni/sanitize/text_spec.rb
|
104
|
+
test_files: []
|
data/.gitignore
DELETED
data/.rspec
DELETED
data/.simplecov
DELETED
data/.travis.yml
DELETED
data/Gemfile
DELETED
@@ -1,16 +0,0 @@
|
|
1
|
-
source 'https://rubygems.org'
|
2
|
-
|
3
|
-
# Specify your gem's dependencies in trenni.gemspec
|
4
|
-
gemspec
|
5
|
-
|
6
|
-
group :development do
|
7
|
-
gem 'pry'
|
8
|
-
end
|
9
|
-
|
10
|
-
group :test do
|
11
|
-
gem 'ruby-prof', platforms: [:mri]
|
12
|
-
gem "benchmark-ips"
|
13
|
-
|
14
|
-
# For comparisons:
|
15
|
-
gem "sanitize"
|
16
|
-
end
|
data/README.md
DELETED
@@ -1,134 +0,0 @@
|
|
1
|
-
# trenni-sanitize::Sanitize
|
2
|
-
|
3
|
-
Sanitize markup by adding, changing or removing tags.
|
4
|
-
|
5
|
-
[](http://travis-ci.org/ioquatix/trenni-sanitize)
|
6
|
-
[](https://codeclimate.com/github/ioquatix/trenni-sanitize)
|
7
|
-
[](https://coveralls.io/r/ioquatix/trenni-sanitize)
|
8
|
-
|
9
|
-
## Motivation
|
10
|
-
|
11
|
-
I use the [sanitize] gem and generally it's great. However, it's performance can be an issue and additionally, it doesn't preserve tag namespaces when parsing fragments due to how Nokogiri works internally.
|
12
|
-
|
13
|
-
[sanitize]: https://github.com/rgrove/sanitize/
|
14
|
-
|
15
|
-
## Is it fast?
|
16
|
-
|
17
|
-
In my informal testing, this gem is about ~50x faster than the [sanitize] gem when generating plain text.
|
18
|
-
|
19
|
-
Warming up --------------------------------------
|
20
|
-
Sanitize 96.000 i/100ms
|
21
|
-
Trenni::Sanitize 4.447k i/100ms
|
22
|
-
Calculating -------------------------------------
|
23
|
-
Sanitize 958.020 (± 4.5%) i/s - 4.800k in 5.020564s
|
24
|
-
Trenni::Sanitize 44.718k (± 4.2%) i/s - 226.797k in 5.080756s
|
25
|
-
|
26
|
-
Comparison:
|
27
|
-
Trenni::Sanitize: 44718.1 i/s
|
28
|
-
Sanitize: 958.0 i/s - 46.68x slower
|
29
|
-
|
30
|
-
## Installation
|
31
|
-
|
32
|
-
Add this line to your application's Gemfile:
|
33
|
-
|
34
|
-
gem 'trenni-sanitize'
|
35
|
-
|
36
|
-
And then execute:
|
37
|
-
|
38
|
-
$ bundle
|
39
|
-
|
40
|
-
Or install it yourself as:
|
41
|
-
|
42
|
-
$ gem install trenni-sanitize
|
43
|
-
|
44
|
-
## Usage
|
45
|
-
|
46
|
-
`Trenni::Sanitize::Delegate` is a stream-based processor. That means it parses the incoming markup and makes decisions about what to keep and what to discard during parsing.
|
47
|
-
|
48
|
-
### Extracting Text
|
49
|
-
|
50
|
-
You can extract text using something similar to the following parser delegate:
|
51
|
-
|
52
|
-
```ruby
|
53
|
-
class Text < Trenni::Sanitize::Filter
|
54
|
-
def filter(node)
|
55
|
-
skip!(TAG)
|
56
|
-
end
|
57
|
-
|
58
|
-
def doctype(string)
|
59
|
-
end
|
60
|
-
|
61
|
-
def instruction(string)
|
62
|
-
end
|
63
|
-
end
|
64
|
-
|
65
|
-
text = Text.parse("<p>Hello World</p>").output
|
66
|
-
# => "Hello World"
|
67
|
-
```
|
68
|
-
|
69
|
-
### Extracting Safe Markup
|
70
|
-
|
71
|
-
Here is a simple filter that only allows a limited set of tags:
|
72
|
-
|
73
|
-
```ruby
|
74
|
-
class Fragment < Trenni::Sanitize::Filter
|
75
|
-
STANDARD_ATTRIBUTES = ['class'].freeze
|
76
|
-
|
77
|
-
ALLOWED_TAGS = {
|
78
|
-
'em' => [],
|
79
|
-
'strong' => [],
|
80
|
-
'p' => [],
|
81
|
-
'img' => [] + ['src', 'alt', 'width', 'height'],
|
82
|
-
'a' => ['href', 'target']
|
83
|
-
}.freeze
|
84
|
-
|
85
|
-
def filter(node)
|
86
|
-
if attributes = ALLOWED_TAGS[node.name]
|
87
|
-
node.tag.attributes.slice!(attributes)
|
88
|
-
else
|
89
|
-
# Skip the tag, and all contents
|
90
|
-
skip!(ALL)
|
91
|
-
end
|
92
|
-
end
|
93
|
-
|
94
|
-
def doctype(string)
|
95
|
-
end
|
96
|
-
|
97
|
-
def instruction(string)
|
98
|
-
end
|
99
|
-
end
|
100
|
-
```
|
101
|
-
|
102
|
-
As you can see, while [sanitize] is driven by configuration, `Trenni::Sanitize::Filter` is driven by code.
|
103
|
-
|
104
|
-
## Contributing
|
105
|
-
|
106
|
-
1. Fork it
|
107
|
-
2. Create your feature branch (`git checkout -b my-new-feature`)
|
108
|
-
3. Commit your changes (`git commit -am 'Add some feature'`)
|
109
|
-
4. Push to the branch (`git push origin my-new-feature`)
|
110
|
-
5. Create new Pull Request
|
111
|
-
|
112
|
-
## License
|
113
|
-
|
114
|
-
Released under the MIT license.
|
115
|
-
|
116
|
-
Copyright, 2018, by [Samuel G. D. Williams](http://www.codeotaku.com/samuel-williams).
|
117
|
-
|
118
|
-
Permission is hereby granted, free of charge, to any person obtaining a copy
|
119
|
-
of this software and associated documentation files (the "Software"), to deal
|
120
|
-
in the Software without restriction, including without limitation the rights
|
121
|
-
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
|
122
|
-
copies of the Software, and to permit persons to whom the Software is
|
123
|
-
furnished to do so, subject to the following conditions:
|
124
|
-
|
125
|
-
The above copyright notice and this permission notice shall be included in
|
126
|
-
all copies or substantial portions of the Software.
|
127
|
-
|
128
|
-
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
|
129
|
-
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
|
130
|
-
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
|
131
|
-
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
|
132
|
-
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
|
133
|
-
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
|
134
|
-
THE SOFTWARE.
|
data/Rakefile
DELETED
@@ -1,19 +0,0 @@
|
|
1
|
-
require "bundler/gem_tasks"
|
2
|
-
require "rspec/core/rake_task"
|
3
|
-
|
4
|
-
# Load all rake tasks:
|
5
|
-
import(*Dir.glob('tasks/**/*.rake'))
|
6
|
-
|
7
|
-
RSpec::Core::RakeTask.new(:test)
|
8
|
-
|
9
|
-
task :environment do
|
10
|
-
$LOAD_PATH.unshift File.expand_path('lib', __dir__)
|
11
|
-
end
|
12
|
-
|
13
|
-
task :console => :environment do
|
14
|
-
require 'pry'
|
15
|
-
|
16
|
-
Pry.start
|
17
|
-
end
|
18
|
-
|
19
|
-
task :default => :test
|
data/spec/spec_helper.rb
DELETED
@@ -1,53 +0,0 @@
|
|
1
|
-
|
2
|
-
if ENV['COVERAGE']
|
3
|
-
begin
|
4
|
-
require 'simplecov'
|
5
|
-
|
6
|
-
SimpleCov.start do
|
7
|
-
add_filter "/spec/"
|
8
|
-
end
|
9
|
-
|
10
|
-
if ENV['TRAVIS']
|
11
|
-
require 'coveralls'
|
12
|
-
Coveralls.wear!
|
13
|
-
end
|
14
|
-
rescue LoadError
|
15
|
-
warn "Could not load simplecov: #{$!}"
|
16
|
-
end
|
17
|
-
end
|
18
|
-
|
19
|
-
require "bundler/setup"
|
20
|
-
require "trenni/sanitize"
|
21
|
-
|
22
|
-
begin
|
23
|
-
require 'ruby-prof'
|
24
|
-
|
25
|
-
RSpec.shared_context "profile" do
|
26
|
-
before(:all) do
|
27
|
-
RubyProf.start
|
28
|
-
end
|
29
|
-
|
30
|
-
after(:all) do
|
31
|
-
result = RubyProf.stop
|
32
|
-
|
33
|
-
# Print a flat profile to text
|
34
|
-
printer = RubyProf::FlatPrinter.new(result)
|
35
|
-
printer.print(STDOUT)
|
36
|
-
end
|
37
|
-
end
|
38
|
-
rescue LoadError
|
39
|
-
RSpec.shared_context "profile" do
|
40
|
-
before(:all) do
|
41
|
-
puts "Profiling not supported on this platform."
|
42
|
-
end
|
43
|
-
end
|
44
|
-
end
|
45
|
-
|
46
|
-
RSpec.configure do |config|
|
47
|
-
# Enable flags like --only-failures and --next-failure
|
48
|
-
config.example_status_persistence_file_path = ".rspec_status"
|
49
|
-
|
50
|
-
config.expect_with :rspec do |c|
|
51
|
-
c.syntax = :expect
|
52
|
-
end
|
53
|
-
end
|
@@ -1,36 +0,0 @@
|
|
1
|
-
|
2
|
-
require 'sanitize'
|
3
|
-
require 'benchmark/ips'
|
4
|
-
|
5
|
-
require 'trenni/sanitize/text'
|
6
|
-
|
7
|
-
RSpec.describe Trenni::Sanitize do
|
8
|
-
let(:buffer) {Trenni::Buffer.load_file(File.join(__dir__, "sample.html"))}
|
9
|
-
|
10
|
-
it "should be faster than alternatives" do
|
11
|
-
config = Sanitize::Config.freeze_config(
|
12
|
-
:elements => %w[b i em strong ul li strike h1 h2 h3 h4 h5 h6 p img image a],
|
13
|
-
:attributes => {
|
14
|
-
'img' => %w[src alt width],
|
15
|
-
'a' => %w[href]
|
16
|
-
},
|
17
|
-
)
|
18
|
-
|
19
|
-
text = buffer.read
|
20
|
-
|
21
|
-
puts Sanitize.fragment(text).inspect
|
22
|
-
puts Trenni::Sanitize::Text.parse(buffer).output.inspect
|
23
|
-
|
24
|
-
Benchmark.ips do |x|
|
25
|
-
x.report("Sanitize") do
|
26
|
-
Sanitize.fragment text
|
27
|
-
end
|
28
|
-
|
29
|
-
x.report("Trenni::Sanitize") do
|
30
|
-
Trenni::Sanitize::Text.parse(buffer)
|
31
|
-
end
|
32
|
-
|
33
|
-
x.compare!
|
34
|
-
end
|
35
|
-
end
|
36
|
-
end
|
@@ -1,26 +0,0 @@
|
|
1
|
-
|
2
|
-
require 'trenni/sanitize/extensions'
|
3
|
-
|
4
|
-
RSpec.describe Hash do
|
5
|
-
let(:hash) {{x: 10, y: 20, z: 30}}
|
6
|
-
|
7
|
-
it "can slice the hash" do
|
8
|
-
result = hash.slice(:x)
|
9
|
-
|
10
|
-
expect(hash.size).to be == 3
|
11
|
-
expect(result.size).to be == 1
|
12
|
-
|
13
|
-
expect(result[:x]).to be == 10
|
14
|
-
expect(result[:y]).to be_nil
|
15
|
-
expect(result[:z]).to be_nil
|
16
|
-
end
|
17
|
-
|
18
|
-
it "can slice! the hash in-place" do
|
19
|
-
hash.slice!(:x)
|
20
|
-
|
21
|
-
expect(hash.size).to be == 1
|
22
|
-
expect(hash[:x]).to be == 10
|
23
|
-
expect(hash[:y]).to be_nil
|
24
|
-
expect(hash[:z]).to be_nil
|
25
|
-
end
|
26
|
-
end
|
@@ -1,66 +0,0 @@
|
|
1
|
-
# Copyright, 2018, by Samuel G. D. Williams. <http://www.codeotaku.com>
|
2
|
-
#
|
3
|
-
# Permission is hereby granted, free of charge, to any person obtaining a copy
|
4
|
-
# of this software and associated documentation files (the "Software"), to deal
|
5
|
-
# in the Software without restriction, including without limitation the rights
|
6
|
-
# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
|
7
|
-
# copies of the Software, and to permit persons to whom the Software is
|
8
|
-
# furnished to do so, subject to the following conditions:
|
9
|
-
#
|
10
|
-
# The above copyright notice and this permission notice shall be included in
|
11
|
-
# all copies or substantial portions of the Software.
|
12
|
-
#
|
13
|
-
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
|
14
|
-
# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
|
15
|
-
# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
|
16
|
-
# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
|
17
|
-
# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
|
18
|
-
# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
|
19
|
-
# THE SOFTWARE.
|
20
|
-
|
21
|
-
require 'trenni/sanitize/fragment'
|
22
|
-
|
23
|
-
RSpec.describe Trenni::Sanitize::Fragment do
|
24
|
-
it "should filter out script tags" do
|
25
|
-
fragment = described_class.parse("<p onclick='malicious()'>Hello World</p><script>doot()</script>")
|
26
|
-
|
27
|
-
expect(fragment.output).to be == "<p>Hello World</p>"
|
28
|
-
end
|
29
|
-
|
30
|
-
it "should filter out nested script tags" do
|
31
|
-
fragment = described_class.parse("<div><p>Hello World</p><script>doot()</script></div>")
|
32
|
-
|
33
|
-
expect(fragment.output).to be == "<div><p>Hello World</p></div>"
|
34
|
-
end
|
35
|
-
|
36
|
-
it "should filter out tags" do
|
37
|
-
fragment = described_class.parse("<p onclick='malicious()'>Hello World</p><script>script</script>")
|
38
|
-
|
39
|
-
expect(fragment.output).to be == "<p>Hello World</p>"
|
40
|
-
end
|
41
|
-
|
42
|
-
it "should ignore unbalanced closing tags" do
|
43
|
-
fragment = described_class.parse("<p>Hello World</a></p>")
|
44
|
-
|
45
|
-
expect(fragment.output).to be == "<p>Hello World</p>"
|
46
|
-
end
|
47
|
-
|
48
|
-
it "should include trailing text" do
|
49
|
-
fragment = described_class.parse("Hello<script/>World")
|
50
|
-
|
51
|
-
expect(fragment.output).to be == "HelloWorld"
|
52
|
-
end
|
53
|
-
|
54
|
-
it "should escape text" do
|
55
|
-
fragment = described_class.parse("x&y")
|
56
|
-
|
57
|
-
expect(fragment.output).to be == "x&y"
|
58
|
-
end
|
59
|
-
|
60
|
-
it "should include nested img" do
|
61
|
-
fragment = described_class.parse("<table><img src='foo'/></table>")
|
62
|
-
|
63
|
-
expect(fragment.output).to be == "<img src=\"foo\"/>"
|
64
|
-
end
|
65
|
-
end
|
66
|
-
|
@@ -1,12 +0,0 @@
|
|
1
|
-
<hr>
|
2
|
-
<a href="http://somegreatsite.com">Link Name</a>
|
3
|
-
is a link to another nifty site
|
4
|
-
<h1>This is a Header</h1>
|
5
|
-
<h1>This is a Medium Header</h2>
|
6
|
-
Send me mail at <a href="mailto:support@yourcompany.com">
|
7
|
-
support@yourcompany.com</a>.
|
8
|
-
<hr>
|
9
|
-
<p>This is a new paragraph!</p>
|
10
|
-
<p><b>This is a new paragraph!</b></p>
|
11
|
-
<br/><b><i>This is a new sentence without a paragraph break, in bold italics.</i></b>
|
12
|
-
<hr>
|
File without changes
|
data/trenni-sanitize.gemspec
DELETED
@@ -1,25 +0,0 @@
|
|
1
|
-
|
2
|
-
require_relative 'lib/trenni/sanitize/version'
|
3
|
-
|
4
|
-
Gem::Specification.new do |spec|
|
5
|
-
spec.name = "trenni-sanitize"
|
6
|
-
spec.platform = Gem::Platform::RUBY
|
7
|
-
spec.version = Trenni::Sanitize::VERSION
|
8
|
-
spec.authors = ["Samuel Williams"]
|
9
|
-
spec.email = ["samuel.williams@oriontransfer.co.nz"]
|
10
|
-
spec.summary = %q{Sanitize markdown according to a set of rules.}
|
11
|
-
spec.homepage = "https://github.com/ioquatix/trenni-sanitize"
|
12
|
-
|
13
|
-
spec.files = `git ls-files`.split($/)
|
14
|
-
spec.executables = spec.files.grep(%r{^bin/}).map{ |f| File.basename(f) }
|
15
|
-
spec.test_files = spec.files.grep(%r{^(test|spec|features)/})
|
16
|
-
spec.require_paths = ["lib"]
|
17
|
-
|
18
|
-
spec.required_ruby_version = '~> 2.1'
|
19
|
-
|
20
|
-
spec.add_dependency "trenni", '~> 3.5.0'
|
21
|
-
|
22
|
-
spec.add_development_dependency "bundler", "~> 1.3"
|
23
|
-
spec.add_development_dependency "rspec", "~> 3.4"
|
24
|
-
spec.add_development_dependency "rake"
|
25
|
-
end
|