html-pipeline 2.13.0 → 2.13.1
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/README.md +4 -4
- data/lib/html/pipeline/autolink_filter.rb +6 -1
- data/lib/html/pipeline/camo_filter.rb +14 -4
- data/lib/html/pipeline/sanitization_filter.rb +23 -18
- data/lib/html/pipeline/version.rb +1 -1
- metadata +4 -4
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA256:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 98e2f770a5c65764d3f1876186ada3b9f3566997ec706c11a835216b9a5f2cb6
|
4
|
+
data.tar.gz: 7a839e8ec04a801868674916f2521d3d098dbace80e57b4f3ce3bc9997592b7b
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 63e9bd15cf65b8765d1046d77f7a675d3dc44d8c82a717bec18722b38275753010c9793f3dec3fcf46f7ad5e4021e33b96280efa6324a3cb37092606c5c37f50
|
7
|
+
data.tar.gz: df99642a2bc048ce6d5f7e52dc1816c5589af7a7503b7f69f842fbc361d70e57601376b437cd56b40161d131d27eddc31b62230f6d7672ccfba3666afef6e1df
|
data/README.md
CHANGED
@@ -33,7 +33,7 @@ And then execute:
|
|
33
33
|
$ bundle
|
34
34
|
```
|
35
35
|
|
36
|
-
Or install it yourself as:
|
36
|
+
Or install it by yourself as:
|
37
37
|
|
38
38
|
```sh
|
39
39
|
$ gem install html-pipeline
|
@@ -164,7 +164,7 @@ EmojiPipeline = Pipeline.new [
|
|
164
164
|
* `ImageMaxWidthFilter` - link to full size image for large images
|
165
165
|
* `MarkdownFilter` - convert markdown to html
|
166
166
|
* `PlainTextInputFilter` - html escape text and wrap the result in a div
|
167
|
-
* `SanitizationFilter` -
|
167
|
+
* `SanitizationFilter` - allow sanitize user markup
|
168
168
|
* `SyntaxHighlightFilter` - code syntax highlighter
|
169
169
|
* `TextileFilter` - convert textile to html
|
170
170
|
* `TableOfContentsFilter` - anchor headings with name attributes and generate Table of Contents html unordered list linking headings
|
@@ -330,9 +330,9 @@ html_fragment = "This is outside of an html element, but <strong>this isn't. :+1
|
|
330
330
|
EmojiPipeline.call("<div>#{html_fragment}</div>") # <- Wrap your own html fragments to avoid escaping
|
331
331
|
```
|
332
332
|
|
333
|
-
### 2. How do I customize
|
333
|
+
### 2. How do I customize an allowlist for `SanitizationFilter`s?
|
334
334
|
|
335
|
-
`SanitizationFilter::
|
335
|
+
`SanitizationFilter::ALLOWLIST` is the default allowlist used if no `:allowlist`
|
336
336
|
argument is given in the context. The default is a good starting template for
|
337
337
|
you to add additional elements. You can either modify the constant's value, or
|
338
338
|
re-define your own constant and pass that in via the context.
|
@@ -8,6 +8,7 @@ module HTML
|
|
8
8
|
#
|
9
9
|
# Context options:
|
10
10
|
# :autolink - boolean whether to autolink urls
|
11
|
+
# :link_mode - :all, :urls or :email_addresses
|
11
12
|
# :link_attr - HTML attributes for the link that will be generated
|
12
13
|
# :skip_tags - HTML tags inside which autolinking will be skipped.
|
13
14
|
# See Rinku.skip_tags
|
@@ -22,7 +23,11 @@ module HTML
|
|
22
23
|
flags = 0
|
23
24
|
flags |= context[:flags] if context[:flags]
|
24
25
|
|
25
|
-
Rinku.auto_link(html,
|
26
|
+
Rinku.auto_link(html, link_mode, context[:link_attr], skip_tags, flags)
|
27
|
+
end
|
28
|
+
|
29
|
+
def link_mode
|
30
|
+
context[:link_mode] || :urls
|
26
31
|
end
|
27
32
|
end
|
28
33
|
end
|
@@ -16,7 +16,7 @@ module HTML
|
|
16
16
|
# Context options:
|
17
17
|
# :asset_proxy (required) - Base URL for constructed asset proxy URLs.
|
18
18
|
# :asset_proxy_secret_key (required) - The shared secret used to encode URLs.
|
19
|
-
# :
|
19
|
+
# :asset_proxy_allowlist - Array of host Strings or Regexps to skip
|
20
20
|
# src rewriting.
|
21
21
|
#
|
22
22
|
# This filter does not write additional information to the context.
|
@@ -37,7 +37,7 @@ module HTML
|
|
37
37
|
end
|
38
38
|
|
39
39
|
next if uri.host.nil?
|
40
|
-
next if
|
40
|
+
next if asset_host_allowed?(uri.host)
|
41
41
|
|
42
42
|
element['src'] = asset_proxy_url(original_src)
|
43
43
|
element['data-canonical-src'] = original_src
|
@@ -76,11 +76,21 @@ module HTML
|
|
76
76
|
end
|
77
77
|
|
78
78
|
def asset_proxy_whitelist
|
79
|
-
|
79
|
+
warn "[DEPRECATION] 'asset_proxy_whitelist' is deprecated. Please use 'asset_proxy_allowlist' instead."
|
80
|
+
asset_proxy_allowlist
|
81
|
+
end
|
82
|
+
|
83
|
+
def asset_proxy_allowlist
|
84
|
+
context[:asset_proxy_allowlist] || context[:asset_proxy_whitelist] || []
|
80
85
|
end
|
81
86
|
|
82
87
|
def asset_host_whitelisted?(host)
|
83
|
-
|
88
|
+
warn "[DEPRECATION] 'asset_host_whitelisted?' is deprecated. Please use 'asset_host_allowed?' instead."
|
89
|
+
asset_host_allowed?(host)
|
90
|
+
end
|
91
|
+
|
92
|
+
def asset_host_allowed?(host)
|
93
|
+
asset_proxy_allowlist.any? do |test|
|
84
94
|
test.is_a?(String) ? host == test : test.match(host)
|
85
95
|
end
|
86
96
|
end
|
@@ -4,7 +4,7 @@ HTML::Pipeline.require_dependency('sanitize', 'SanitizationFilter')
|
|
4
4
|
|
5
5
|
module HTML
|
6
6
|
class Pipeline
|
7
|
-
# HTML filter with sanization routines and
|
7
|
+
# HTML filter with sanization routines and allowlists. This module defines
|
8
8
|
# what HTML is allowed in user provided content and fixes up issues with
|
9
9
|
# unbalanced tags and whatnot.
|
10
10
|
#
|
@@ -13,13 +13,13 @@ module HTML
|
|
13
13
|
# https://github.com/rgrove/sanitize/#readme
|
14
14
|
#
|
15
15
|
# Context options:
|
16
|
-
# :
|
16
|
+
# :allowlist - The sanitizer allowlist configuration to use. This
|
17
17
|
# can be one of the options constants defined in this
|
18
18
|
# class or a custom sanitize options hash.
|
19
19
|
# :anchor_schemes - The URL schemes to allow in <a href> attributes. The
|
20
20
|
# default set is provided in the ANCHOR_SCHEMES
|
21
21
|
# constant in this class. If passed, this overrides any
|
22
|
-
# schemes specified in the
|
22
|
+
# schemes specified in the allowlist configuration.
|
23
23
|
#
|
24
24
|
# This filter does not write additional information to the context.
|
25
25
|
class SanitizationFilter < Filter
|
@@ -37,9 +37,9 @@ module HTML
|
|
37
37
|
# These schemes are the only ones allowed in <a href> attributes by default.
|
38
38
|
ANCHOR_SCHEMES = ['http', 'https', 'mailto', 'xmpp', :relative, 'github-windows', 'github-mac', 'irc', 'ircs'].freeze
|
39
39
|
|
40
|
-
# The main sanitization
|
40
|
+
# The main sanitization allowlist. Only these elements and attributes are
|
41
41
|
# allowed through by default.
|
42
|
-
|
42
|
+
ALLOWLIST = {
|
43
43
|
elements: %w[
|
44
44
|
h1 h2 h3 h4 h5 h6 h7 h8 br b i strong em a pre code img tt
|
45
45
|
div ins del sup sub p ol ul table thead tbody tfoot blockquote
|
@@ -68,7 +68,7 @@ module HTML
|
|
68
68
|
hspace ismap label lang
|
69
69
|
maxlength media method
|
70
70
|
multiple name nohref noshade
|
71
|
-
nowrap open prompt readonly rel rev
|
71
|
+
nowrap open progress prompt readonly rel rev
|
72
72
|
role rows rowspan rules scope
|
73
73
|
selected shape size span
|
74
74
|
start summary tabindex target
|
@@ -108,10 +108,10 @@ module HTML
|
|
108
108
|
].freeze
|
109
109
|
}.freeze
|
110
110
|
|
111
|
-
# A more limited sanitization
|
112
|
-
# protocols, and transformers from
|
111
|
+
# A more limited sanitization allowlist. This includes all attributes,
|
112
|
+
# protocols, and transformers from ALLOWLIST but with a more locked down
|
113
113
|
# set of allowed elements.
|
114
|
-
LIMITED =
|
114
|
+
LIMITED = ALLOWLIST.merge(
|
115
115
|
elements: %w[b i strong em a pre code img ins del sup sub mark abbr p ol ul li]
|
116
116
|
)
|
117
117
|
|
@@ -120,19 +120,24 @@ module HTML
|
|
120
120
|
|
121
121
|
# Sanitize markup using the Sanitize library.
|
122
122
|
def call
|
123
|
-
Sanitize.clean_node!(doc,
|
123
|
+
Sanitize.clean_node!(doc, allowlist)
|
124
124
|
end
|
125
125
|
|
126
|
-
# The whitelist to use when sanitizing. This can be passed in the context
|
127
|
-
# hash to the filter but defaults to WHITELIST constant value above.
|
128
126
|
def whitelist
|
129
|
-
|
127
|
+
warn "[DEPRECATION] 'whitelist' is deprecated. Please use 'allowlist' instead."
|
128
|
+
allowlist
|
129
|
+
end
|
130
|
+
|
131
|
+
# The allowlist to use when sanitizing. This can be passed in the context
|
132
|
+
# hash to the filter but defaults to ALLOWLIST constant value above.
|
133
|
+
def allowlist
|
134
|
+
allowlist = context[:allowlist] || context[:whitelist] || ALLOWLIST
|
130
135
|
anchor_schemes = context[:anchor_schemes]
|
131
|
-
return
|
132
|
-
|
133
|
-
|
134
|
-
|
135
|
-
|
136
|
+
return allowlist unless anchor_schemes
|
137
|
+
allowlist = allowlist.dup
|
138
|
+
allowlist[:protocols] = (allowlist[:protocols] || {}).dup
|
139
|
+
allowlist[:protocols]['a'] = (allowlist[:protocols]['a'] || {}).merge('href' => anchor_schemes)
|
140
|
+
allowlist
|
136
141
|
end
|
137
142
|
end
|
138
143
|
end
|
metadata
CHANGED
@@ -1,16 +1,16 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: html-pipeline
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 2.13.
|
4
|
+
version: 2.13.1
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Ryan Tomayko
|
8
8
|
- Jerry Cheung
|
9
9
|
- Garen J. Torikian
|
10
|
-
autorequire:
|
10
|
+
autorequire:
|
11
11
|
bindir: bin
|
12
12
|
cert_chain: []
|
13
|
-
date: 2020-
|
13
|
+
date: 2020-12-02 00:00:00.000000000 Z
|
14
14
|
dependencies:
|
15
15
|
- !ruby/object:Gem::Dependency
|
16
16
|
name: activesupport
|
@@ -108,7 +108,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
|
|
108
108
|
version: '0'
|
109
109
|
requirements: []
|
110
110
|
rubygems_version: 3.1.2
|
111
|
-
signing_key:
|
111
|
+
signing_key:
|
112
112
|
specification_version: 4
|
113
113
|
summary: Helpers for processing content through a chain of filters
|
114
114
|
test_files: []
|