html-proofer 3.19.2 → 4.0.0.rc3
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/bin/htmlproofer +31 -57
- data/lib/html-proofer.rb +1 -54
- data/lib/html_proofer/attribute/url.rb +231 -0
- data/lib/html_proofer/attribute.rb +15 -0
- data/lib/html_proofer/cache.rb +236 -0
- data/lib/html_proofer/check/favicon.rb +35 -0
- data/lib/html_proofer/check/images.rb +62 -0
- data/lib/html_proofer/check/links.rb +118 -0
- data/lib/html_proofer/check/open_graph.rb +34 -0
- data/lib/html_proofer/check/scripts.rb +38 -0
- data/lib/html_proofer/check.rb +91 -0
- data/lib/{html-proofer → html_proofer}/configuration.rb +30 -30
- data/lib/html_proofer/element.rb +122 -0
- data/lib/html_proofer/failure.rb +17 -0
- data/lib/{html-proofer → html_proofer}/log.rb +0 -0
- data/lib/html_proofer/reporter/cli.rb +29 -0
- data/lib/html_proofer/reporter.rb +23 -0
- data/lib/html_proofer/runner.rb +245 -0
- data/lib/html_proofer/url_validator/external.rb +189 -0
- data/lib/html_proofer/url_validator/internal.rb +86 -0
- data/lib/html_proofer/url_validator.rb +16 -0
- data/lib/{html-proofer → html_proofer}/utils.rb +6 -9
- data/lib/{html-proofer → html_proofer}/version.rb +1 -1
- data/lib/html_proofer/xpath_functions.rb +10 -0
- data/lib/html_proofer.rb +55 -0
- metadata +51 -30
- data/lib/html-proofer/cache.rb +0 -194
- data/lib/html-proofer/check/favicon.rb +0 -29
- data/lib/html-proofer/check/html.rb +0 -37
- data/lib/html-proofer/check/images.rb +0 -48
- data/lib/html-proofer/check/links.rb +0 -182
- data/lib/html-proofer/check/opengraph.rb +0 -46
- data/lib/html-proofer/check/scripts.rb +0 -42
- data/lib/html-proofer/check.rb +0 -75
- data/lib/html-proofer/element.rb +0 -261
- data/lib/html-proofer/issue.rb +0 -65
- data/lib/html-proofer/middleware.rb +0 -82
- data/lib/html-proofer/runner.rb +0 -248
- data/lib/html-proofer/url_validator.rb +0 -237
@@ -1,42 +0,0 @@
|
|
1
|
-
# frozen_string_literal: true
|
2
|
-
|
3
|
-
class ScriptCheck < ::HTMLProofer::Check
|
4
|
-
attr_reader :src
|
5
|
-
|
6
|
-
def missing_src?
|
7
|
-
!@script.src
|
8
|
-
end
|
9
|
-
|
10
|
-
def run
|
11
|
-
@html.css('script').each do |node|
|
12
|
-
@script = create_element(node)
|
13
|
-
line = node.line
|
14
|
-
content = node.content
|
15
|
-
|
16
|
-
next if @script.ignore?
|
17
|
-
next unless node.text.strip.empty?
|
18
|
-
|
19
|
-
# does the script exist?
|
20
|
-
if missing_src?
|
21
|
-
add_issue('script is empty and has no src attribute', line: line, content: content)
|
22
|
-
elsif @script.remote?
|
23
|
-
add_to_external_urls(@script.src)
|
24
|
-
check_sri(line, content) if @script.check_sri?
|
25
|
-
elsif !@script.exists?
|
26
|
-
add_issue("internal script #{@script.src} does not exist", line: line, content: content)
|
27
|
-
end
|
28
|
-
end
|
29
|
-
|
30
|
-
external_urls
|
31
|
-
end
|
32
|
-
|
33
|
-
def check_sri(line, content)
|
34
|
-
if !defined?(@script.integrity) && !defined?(@script.crossorigin)
|
35
|
-
add_issue("SRI and CORS not provided in: #{@script.src}", line: line, content: content)
|
36
|
-
elsif !defined?(@script.integrity)
|
37
|
-
add_issue("Integrity is missing in: #{@script.src}", line: line, content: content)
|
38
|
-
elsif !defined?(@script.crossorigin)
|
39
|
-
add_issue("CORS not provided for external resource in: #{@script.src}", line: line, content: content)
|
40
|
-
end
|
41
|
-
end
|
42
|
-
end
|
data/lib/html-proofer/check.rb
DELETED
@@ -1,75 +0,0 @@
|
|
1
|
-
# frozen_string_literal: true
|
2
|
-
|
3
|
-
module HTMLProofer
|
4
|
-
# Mostly handles issue management and collecting of external URLs.
|
5
|
-
class Check
|
6
|
-
attr_reader :node, :html, :element, :src, :path, :options, :issues, :internal_urls, :external_urls
|
7
|
-
|
8
|
-
def initialize(src, path, html, logger, cache, options)
|
9
|
-
@src = src
|
10
|
-
@path = path
|
11
|
-
@html = remove_ignored(html)
|
12
|
-
@logger = logger
|
13
|
-
@cache = cache
|
14
|
-
@options = options
|
15
|
-
@issues = []
|
16
|
-
@internal_urls = {}
|
17
|
-
@external_urls = {}
|
18
|
-
end
|
19
|
-
|
20
|
-
def create_element(node)
|
21
|
-
@node = node
|
22
|
-
Element.new(node, self, @logger)
|
23
|
-
end
|
24
|
-
|
25
|
-
def run
|
26
|
-
raise NotImplementedError, 'HTMLProofer::Check subclasses must implement #run'
|
27
|
-
end
|
28
|
-
|
29
|
-
def add_issue(desc, line: nil, path: nil, status: -1, content: nil)
|
30
|
-
@issues << Issue.new(path || @path, desc, line: line, status: status, content: content)
|
31
|
-
false
|
32
|
-
end
|
33
|
-
|
34
|
-
def add_to_internal_urls(url, internal_url)
|
35
|
-
if @internal_urls[url]
|
36
|
-
@internal_urls[url] << internal_url
|
37
|
-
else
|
38
|
-
@internal_urls[url] = [internal_url]
|
39
|
-
end
|
40
|
-
end
|
41
|
-
|
42
|
-
def add_to_external_urls(url)
|
43
|
-
return if @external_urls[url]
|
44
|
-
|
45
|
-
if @external_urls[url]
|
46
|
-
@external_urls[url] << @path
|
47
|
-
else
|
48
|
-
@external_urls[url] = [@path]
|
49
|
-
end
|
50
|
-
end
|
51
|
-
|
52
|
-
def self.subchecks
|
53
|
-
classes = []
|
54
|
-
|
55
|
-
ObjectSpace.each_object(Class) do |c|
|
56
|
-
next unless c.superclass == self
|
57
|
-
|
58
|
-
classes << c
|
59
|
-
end
|
60
|
-
|
61
|
-
classes
|
62
|
-
end
|
63
|
-
|
64
|
-
def blank?(attr)
|
65
|
-
attr.nil? || attr.empty?
|
66
|
-
end
|
67
|
-
|
68
|
-
private
|
69
|
-
|
70
|
-
def remove_ignored(html)
|
71
|
-
html.css('code, pre, tt').each(&:unlink)
|
72
|
-
html
|
73
|
-
end
|
74
|
-
end
|
75
|
-
end
|
data/lib/html-proofer/element.rb
DELETED
@@ -1,261 +0,0 @@
|
|
1
|
-
# frozen_string_literal: true
|
2
|
-
|
3
|
-
require 'addressable/uri'
|
4
|
-
require_relative './utils'
|
5
|
-
|
6
|
-
module HTMLProofer
|
7
|
-
# Represents the element currently being processed
|
8
|
-
class Element
|
9
|
-
include HTMLProofer::Utils
|
10
|
-
|
11
|
-
attr_reader :id, :name, :alt, :href, :link, :src, :line, :data_proofer_ignore
|
12
|
-
|
13
|
-
def initialize(obj, check, logger)
|
14
|
-
@logger = logger
|
15
|
-
# Construct readable ivars for every element
|
16
|
-
begin
|
17
|
-
obj.attributes.each_pair do |attribute, value|
|
18
|
-
name = attribute.tr('-:.;@', '_').to_s.to_sym
|
19
|
-
(class << self; self; end).send(:attr_reader, name)
|
20
|
-
instance_variable_set("@#{name}", value.value)
|
21
|
-
end
|
22
|
-
rescue NameError => e
|
23
|
-
@logger.log :error, "Attribute set `#{obj}` contains an error!"
|
24
|
-
raise e
|
25
|
-
end
|
26
|
-
|
27
|
-
@aria_hidden = defined?(@aria_hidden) && @aria_hidden == 'true'
|
28
|
-
|
29
|
-
@data_proofer_ignore = defined?(@data_proofer_ignore)
|
30
|
-
|
31
|
-
@text = obj.content
|
32
|
-
@check = check
|
33
|
-
@checked_paths = {}
|
34
|
-
@type = check.class.name
|
35
|
-
@line = obj.line
|
36
|
-
|
37
|
-
@html = check.html
|
38
|
-
|
39
|
-
parent_attributes = obj.ancestors.map { |a| a.respond_to?(:attributes) && a.attributes }
|
40
|
-
parent_attributes.pop # remove document at the end
|
41
|
-
@parent_ignorable = parent_attributes.any? { |a| !a['data-proofer-ignore'].nil? }
|
42
|
-
|
43
|
-
# fix up missing protocols
|
44
|
-
if defined?(@href)
|
45
|
-
@href.insert(0, 'http:') if %r{^//}.match?(@href)
|
46
|
-
else
|
47
|
-
@href = nil
|
48
|
-
end
|
49
|
-
|
50
|
-
if defined?(@src)
|
51
|
-
@src.insert(0, 'http:') if %r{^//}.match?(@src)
|
52
|
-
else
|
53
|
-
@src = nil
|
54
|
-
end
|
55
|
-
|
56
|
-
if defined?(@srcset)
|
57
|
-
@srcset.insert(0, 'http:') if %r{^//}.match?(@srcset)
|
58
|
-
else
|
59
|
-
@srcset = nil
|
60
|
-
end
|
61
|
-
end
|
62
|
-
|
63
|
-
def url
|
64
|
-
return @url if defined?(@url)
|
65
|
-
|
66
|
-
@url = (@src || @srcset || @href || '').delete("\u200b").strip
|
67
|
-
@url = Addressable::URI.join(base.attr('href') || '', url).to_s if base
|
68
|
-
return @url if @check.options[:url_swap].empty?
|
69
|
-
|
70
|
-
@url = swap(@url, @check.options[:url_swap])
|
71
|
-
end
|
72
|
-
|
73
|
-
def valid?
|
74
|
-
!parts.nil?
|
75
|
-
end
|
76
|
-
|
77
|
-
def path?
|
78
|
-
!parts.host.nil? && !parts.path.nil?
|
79
|
-
end
|
80
|
-
|
81
|
-
def parts
|
82
|
-
@parts ||= Addressable::URI.parse url
|
83
|
-
rescue URI::Error, Addressable::URI::InvalidURIError
|
84
|
-
@parts = nil
|
85
|
-
end
|
86
|
-
|
87
|
-
def path
|
88
|
-
Addressable::URI.unencode parts.path unless parts.nil?
|
89
|
-
end
|
90
|
-
|
91
|
-
def hash
|
92
|
-
parts&.fragment
|
93
|
-
end
|
94
|
-
|
95
|
-
def scheme
|
96
|
-
parts&.scheme
|
97
|
-
end
|
98
|
-
|
99
|
-
# path is to an external server
|
100
|
-
def remote?
|
101
|
-
%w[http https].include? scheme
|
102
|
-
end
|
103
|
-
|
104
|
-
def non_http_remote?
|
105
|
-
!scheme.nil? && !remote?
|
106
|
-
end
|
107
|
-
|
108
|
-
def ignore?
|
109
|
-
return true if @data_proofer_ignore
|
110
|
-
return true if @parent_ignorable
|
111
|
-
|
112
|
-
return true if /^javascript:/.match?(url)
|
113
|
-
|
114
|
-
# ignore base64 encoded images
|
115
|
-
return true if %w[ImageCheck FaviconCheck].include?(@type) && /^data:image/.match?(url)
|
116
|
-
|
117
|
-
# ignore user defined URLs
|
118
|
-
return true if ignores_pattern_check(@check.options[:url_ignore])
|
119
|
-
end
|
120
|
-
|
121
|
-
def ignore_alt?
|
122
|
-
return true if ignores_pattern_check(@check.options[:alt_ignore]) || @aria_hidden
|
123
|
-
end
|
124
|
-
|
125
|
-
def ignore_empty_alt?
|
126
|
-
@check.options[:empty_alt_ignore]
|
127
|
-
end
|
128
|
-
|
129
|
-
def allow_missing_href?
|
130
|
-
@check.options[:allow_missing_href]
|
131
|
-
end
|
132
|
-
|
133
|
-
def allow_hash_href?
|
134
|
-
@check.options[:allow_hash_href]
|
135
|
-
end
|
136
|
-
|
137
|
-
def check_img_http?
|
138
|
-
@check.options[:check_img_http]
|
139
|
-
end
|
140
|
-
|
141
|
-
def check_sri?
|
142
|
-
@check.options[:check_sri]
|
143
|
-
end
|
144
|
-
|
145
|
-
# path is external to the file
|
146
|
-
def external?
|
147
|
-
!internal?
|
148
|
-
end
|
149
|
-
|
150
|
-
def internal?
|
151
|
-
relative_link? || internal_absolute_link?
|
152
|
-
end
|
153
|
-
|
154
|
-
def internal_absolute_link?
|
155
|
-
url.start_with?('/')
|
156
|
-
end
|
157
|
-
|
158
|
-
def relative_link?
|
159
|
-
return false if remote?
|
160
|
-
|
161
|
-
hash_link || param_link || url.start_with?('.') || url =~ /^\S/
|
162
|
-
end
|
163
|
-
|
164
|
-
def link_points_to_same_page?
|
165
|
-
hash_link || param_link
|
166
|
-
end
|
167
|
-
|
168
|
-
def hash_link
|
169
|
-
url.start_with?('#')
|
170
|
-
end
|
171
|
-
|
172
|
-
def param_link
|
173
|
-
url.start_with?('?')
|
174
|
-
end
|
175
|
-
|
176
|
-
def absolute_path?(path)
|
177
|
-
path.start_with?('/')
|
178
|
-
end
|
179
|
-
|
180
|
-
def file_path
|
181
|
-
return if path.nil? || path.empty?
|
182
|
-
|
183
|
-
path_dot_ext = ''
|
184
|
-
|
185
|
-
path_dot_ext = path + @check.options[:extension] if @check.options[:assume_extension]
|
186
|
-
|
187
|
-
base = if absolute_path?(path) # path relative to root
|
188
|
-
# either overwrite with root_dir; or, if source is directory, use that; or, just get the current file's dirname
|
189
|
-
@check.options[:root_dir] || (File.directory?(@check.src) ? @check.src : File.dirname(@check.src))
|
190
|
-
elsif File.exist?(File.expand_path(path, @check.src)) || File.exist?(File.expand_path(path_dot_ext, @check.src)) # relative links, path is a file
|
191
|
-
File.dirname(@check.path)
|
192
|
-
elsif File.exist?(File.join(File.dirname(@check.path), path)) || File.exist?(File.join(File.dirname(@check.path), path_dot_ext)) # rubocop:disable Lint/DuplicateBranch; relative links in nested dir, path is a file
|
193
|
-
File.dirname(@check.path)
|
194
|
-
else # relative link, path is a directory
|
195
|
-
@check.path
|
196
|
-
end
|
197
|
-
|
198
|
-
file = File.join(base, path)
|
199
|
-
|
200
|
-
if @check.options[:assume_extension] && File.file?("#{file}#{@check.options[:extension]}")
|
201
|
-
file = "#{file}#{@check.options[:extension]}"
|
202
|
-
elsif File.directory?(file) && !unslashed_directory?(file) # implicit index support
|
203
|
-
file = File.join file, @check.options[:directory_index_file]
|
204
|
-
end
|
205
|
-
|
206
|
-
file
|
207
|
-
end
|
208
|
-
|
209
|
-
# checks if a file exists relative to the current pwd
|
210
|
-
def exists?
|
211
|
-
return @checked_paths[absolute_path] if @checked_paths.key?(absolute_path)
|
212
|
-
|
213
|
-
@checked_paths[absolute_path] = File.exist?(absolute_path)
|
214
|
-
end
|
215
|
-
|
216
|
-
def absolute_path
|
217
|
-
path = file_path || @check.path
|
218
|
-
|
219
|
-
File.expand_path(path, Dir.pwd)
|
220
|
-
end
|
221
|
-
|
222
|
-
def ignores_pattern_check(links)
|
223
|
-
return false unless links.is_a?(Array)
|
224
|
-
|
225
|
-
links.each do |ignore|
|
226
|
-
case ignore
|
227
|
-
when String
|
228
|
-
return true if ignore == url
|
229
|
-
when Regexp
|
230
|
-
return true if ignore&.match?(url)
|
231
|
-
end
|
232
|
-
end
|
233
|
-
|
234
|
-
false
|
235
|
-
end
|
236
|
-
|
237
|
-
def unslashed_directory?(file)
|
238
|
-
File.directory?(file) && !file.end_with?(File::SEPARATOR) && !follow_location?
|
239
|
-
end
|
240
|
-
|
241
|
-
def follow_location?
|
242
|
-
@check.options[:typhoeus] && @check.options[:typhoeus][:followlocation]
|
243
|
-
end
|
244
|
-
|
245
|
-
def base
|
246
|
-
@base ||= @html.at_css('base')
|
247
|
-
end
|
248
|
-
|
249
|
-
def html
|
250
|
-
# If link is on the same page, then URL is on the current page. use the same HTML as for current page
|
251
|
-
if link_points_to_same_page?
|
252
|
-
@html
|
253
|
-
elsif internal?
|
254
|
-
# link on another page, e.g. /about#Team - need to get HTML from the other page
|
255
|
-
create_nokogiri(absolute_path)
|
256
|
-
else
|
257
|
-
raise NotImplementedError, 'HTMLProofer should not have gotten here. Please report this as a bug.'
|
258
|
-
end
|
259
|
-
end
|
260
|
-
end
|
261
|
-
end
|
data/lib/html-proofer/issue.rb
DELETED
@@ -1,65 +0,0 @@
|
|
1
|
-
# frozen_string_literal: true
|
2
|
-
|
3
|
-
module HTMLProofer
|
4
|
-
class Issue
|
5
|
-
attr_reader :path, :desc, :status, :line, :content
|
6
|
-
|
7
|
-
def initialize(path, desc, line: nil, status: -1, content: nil)
|
8
|
-
@line = line.nil? ? '' : " (line #{line})"
|
9
|
-
@path = path
|
10
|
-
@desc = desc
|
11
|
-
@status = status
|
12
|
-
@content = content
|
13
|
-
end
|
14
|
-
|
15
|
-
def to_s
|
16
|
-
"#{@path}: #{@desc}#{@line}"
|
17
|
-
end
|
18
|
-
end
|
19
|
-
|
20
|
-
class SortedIssues
|
21
|
-
attr_reader :issues
|
22
|
-
|
23
|
-
def initialize(issues, error_sort, logger)
|
24
|
-
@issues = issues
|
25
|
-
@error_sort = error_sort
|
26
|
-
@logger = logger
|
27
|
-
end
|
28
|
-
|
29
|
-
def sort_and_report
|
30
|
-
case @error_sort
|
31
|
-
when :path
|
32
|
-
sorted_issues = sort(:path, :desc)
|
33
|
-
report(sorted_issues, :path, :desc)
|
34
|
-
when :desc
|
35
|
-
sorted_issues = sort(:desc, :path)
|
36
|
-
report(sorted_issues, :desc, :path)
|
37
|
-
when :status
|
38
|
-
sorted_issues = sort(:status, :path)
|
39
|
-
report(sorted_issues, :status, :path)
|
40
|
-
end
|
41
|
-
end
|
42
|
-
|
43
|
-
def sort(first_sort, second_sort)
|
44
|
-
issues.sort_by { |t| [t.send(first_sort), t.send(second_sort)] }
|
45
|
-
end
|
46
|
-
|
47
|
-
def report(sorted_issues, first_report, second_report)
|
48
|
-
matcher = nil
|
49
|
-
|
50
|
-
sorted_issues.each do |issue|
|
51
|
-
if matcher != issue.send(first_report)
|
52
|
-
@logger.log :error, "- #{issue.send(first_report)}"
|
53
|
-
matcher = issue.send(first_report)
|
54
|
-
end
|
55
|
-
if first_report == :status
|
56
|
-
@logger.log :error, " * #{issue}"
|
57
|
-
else
|
58
|
-
msg = " * #{issue.send(second_report)}#{issue.line}"
|
59
|
-
msg = "#{msg}\n #{issue.content}" if !issue.content.nil? && !issue.content.empty?
|
60
|
-
@logger.log(:error, msg)
|
61
|
-
end
|
62
|
-
end
|
63
|
-
end
|
64
|
-
end
|
65
|
-
end
|
@@ -1,82 +0,0 @@
|
|
1
|
-
# frozen_string_literal: true
|
2
|
-
|
3
|
-
module HTMLProofer
|
4
|
-
class Middleware
|
5
|
-
include HTMLProofer::Utils
|
6
|
-
|
7
|
-
class InvalidHtmlError < StandardError
|
8
|
-
def initialize(failures)
|
9
|
-
super
|
10
|
-
@failures = failures
|
11
|
-
end
|
12
|
-
|
13
|
-
def message
|
14
|
-
"HTML Validation errors (skip by adding `?proofer-ignore` to URL): \n#{@failures.join("\n")}"
|
15
|
-
end
|
16
|
-
end
|
17
|
-
|
18
|
-
def self.options
|
19
|
-
@options ||= {
|
20
|
-
type: :file,
|
21
|
-
allow_missing_href: true, # Permitted in html5
|
22
|
-
allow_hash_href: true,
|
23
|
-
check_external_hash: true,
|
24
|
-
check_html: true,
|
25
|
-
url_ignore: [%r{^/}], # Don't try to check if local files exist
|
26
|
-
validation: { report_eof_tags: true }
|
27
|
-
}
|
28
|
-
end
|
29
|
-
|
30
|
-
def initialize(app)
|
31
|
-
@app = app
|
32
|
-
end
|
33
|
-
|
34
|
-
HTML_SIGNATURE = [
|
35
|
-
'<!DOCTYPE HTML',
|
36
|
-
'<HTML',
|
37
|
-
'<HEAD',
|
38
|
-
'<SCRIPT',
|
39
|
-
'<IFRAME',
|
40
|
-
'<H1',
|
41
|
-
'<DIV',
|
42
|
-
'<FONT',
|
43
|
-
'<TABLE',
|
44
|
-
'<A',
|
45
|
-
'<STYLE',
|
46
|
-
'<TITLE',
|
47
|
-
'<B',
|
48
|
-
'<BODY',
|
49
|
-
'<BR',
|
50
|
-
'<P',
|
51
|
-
'<!--'
|
52
|
-
].freeze
|
53
|
-
|
54
|
-
def call(env)
|
55
|
-
result = @app.call(env)
|
56
|
-
return result if env['REQUEST_METHOD'] != 'GET'
|
57
|
-
return result if /proofer-ignore/.match?(env['QUERY_STRING'])
|
58
|
-
return result if result.first != 200
|
59
|
-
|
60
|
-
body = []
|
61
|
-
result.last.each { |e| body << e }
|
62
|
-
|
63
|
-
body = body.join
|
64
|
-
begin
|
65
|
-
html = body.lstrip
|
66
|
-
rescue StandardError
|
67
|
-
return result # Invalid encoding; it's not gonna be html.
|
68
|
-
end
|
69
|
-
if HTML_SIGNATURE.any? { |sig| html.upcase.start_with? sig }
|
70
|
-
parsed = HTMLProofer::Runner.new(
|
71
|
-
'response',
|
72
|
-
Middleware.options
|
73
|
-
).check_parsed(
|
74
|
-
Nokogiri::HTML5(html, max_errors: -1), 'response'
|
75
|
-
)
|
76
|
-
|
77
|
-
raise InvalidHtmlError, parsed[:failures] unless parsed[:failures].empty?
|
78
|
-
end
|
79
|
-
result
|
80
|
-
end
|
81
|
-
end
|
82
|
-
end
|