sitediff 0.0.6 → 1.0.0

Sign up to get free protection for your applications and to get access to all the features.
Files changed (30) hide show
  1. checksums.yaml +5 -5
  2. data/bin/sitediff +9 -2
  3. data/lib/sitediff.rb +126 -81
  4. data/lib/sitediff/cache.rb +35 -6
  5. data/lib/sitediff/cli.rb +254 -119
  6. data/lib/sitediff/config.rb +362 -29
  7. data/lib/sitediff/config/creator.rb +53 -71
  8. data/lib/sitediff/config/preset.rb +75 -0
  9. data/lib/sitediff/crawler.rb +11 -15
  10. data/lib/sitediff/diff.rb +28 -9
  11. data/lib/sitediff/fetch.rb +9 -2
  12. data/lib/sitediff/files/diff.html.erb +20 -2
  13. data/lib/sitediff/files/jquery.min.js +2 -0
  14. data/lib/sitediff/files/normalize.css +349 -0
  15. data/lib/sitediff/files/report.html.erb +144 -0
  16. data/lib/sitediff/files/sidebyside.html.erb +5 -2
  17. data/lib/sitediff/files/sitediff.css +226 -30
  18. data/lib/sitediff/files/sitediff.js +176 -0
  19. data/lib/sitediff/report.rb +238 -0
  20. data/lib/sitediff/result.rb +47 -19
  21. data/lib/sitediff/sanitize.rb +29 -8
  22. data/lib/sitediff/sanitize/dom_transform.rb +45 -6
  23. data/lib/sitediff/sanitize/regexp.rb +23 -2
  24. data/lib/sitediff/uriwrapper.rb +56 -15
  25. data/lib/sitediff/webserver.rb +12 -3
  26. data/lib/sitediff/webserver/resultserver.rb +28 -33
  27. metadata +33 -16
  28. data/lib/sitediff/files/html_report.html.erb +0 -66
  29. data/lib/sitediff/files/rules/drupal.yaml +0 -63
  30. data/lib/sitediff/rules.rb +0 -65
data/lib/sitediff/files/html_report.html.erb DELETED
@@ -1,66 +0,0 @@
1
- <!DOCTYPE html>
2
- <html>
3
- <head>
4
- <!-- important: otherwise chrome will choke on non-ascii characters -->
5
- <meta charset="utf-8" />
6
- <style>
7
- <%= SiteDiff::Diff.css %>
8
- </style>
9
- <title> SiteDiff Report </title>
10
- </head>
11
- <body>
12
- <div class="sitediff">
13
- <div class="legend">
14
- <%
15
- tags = %w[before after]
16
- tags.each do |tag| %>
17
- <% if tags.first != tag %> | <% end %>
18
- <% notes = ['base url']
19
- notes << 'cached' if cache.read_tags.include?(tag.to_sym) %>
20
- <strong><%= tag %></strong> (<%= notes.join(', ') %>):
21
- <a href="<%= eval(tag) %>"><%= eval(tag) %></a>
22
- <% end %>
23
- </div>
24
- <div class="run">
25
- <a href="../run/diff">Rerun diff</a>
26
- </div>
27
- <table class="results">
28
-
29
- <colgroup>
30
- <col class="before-col">
31
- <col class="after-col">
32
- <col class="both-col">
33
- <col class="path-col">
34
- <col class="diff-stat-col">
35
- </colgroup>
36
-
37
- <thead>
38
- <tr>
39
- <th> Before </th>
40
- <th> After </th>
41
- <th> Both </th>
42
- <th> Path </th>
43
- <th> Status </th>
44
- </tr>
45
- </thead>
46
-
47
- <% results.each do |result| %>
48
- <tr class="<%= result.status_text %>">
49
- <td class="before">
50
- <a href="<%= result.url(:before, before, cache) %>">[before]</a>
51
- </td>
52
- <td class="after">
53
- <a href="<%= result.url(:after, after, cache) %>">[after]</a>
54
- </td>
55
- <td class="both">
56
- <a href="/sidebyside<%= result.path %>">[both]</a>
57
- </td>
58
- <td class="path"><%= result.path %></td>
59
- <td class="status"><%= result.link %></td>
60
- </tr>
61
- <% end %>
62
-
63
- </table>
64
- </div>
65
- </body>
66
- </html>
data/lib/sitediff/files/rules/drupal.yaml DELETED
@@ -1,63 +0,0 @@
1
- sanitization:
2
- - title: Strip Drupal.settings
3
- selector: script
4
- pattern: '^(<script>)?jQuery.extend\(Drupal.settings.*$'
5
- - title: Strip IE CSS/JS cache IDs
6
- pattern: '("[^"]*ie\d?\.(js|css))\?[a-z0-9]{6}"'
7
- substitute: '\1'
8
- - title: Strip form build ID
9
- selector: input
10
- pattern: 'name="form_build_id" value="form-[-\w]{40,43}"'
11
- substitute: 'name="form_build_id" value="form-DRUPAL_FORM_BUILD_ID"'
12
- - title: Strip view DOM ID
13
- pattern: '(class="view .*) view-dom-id-[a-f0-9]{32}"'
14
- substitute: '\1 view-dom-id-DRUPAL_VIEW_DOM_ID"'
15
- - title: Strip CSS aggregation filenames
16
- selector: link[rel=stylesheet]
17
- pattern: '(href="[^"]*/files/css/css_)[-\w]{40,43}\.css"'
18
- substitute: '\1DRUPAL_AGGREGATED_CSS.css"'
19
- - title: Strip JS aggregation filenames
20
- selector: script
21
- pattern: '(src="[^"]*/files/js/js_)[-\w]{40,43}\.js"'
22
- substitute: '\1DRUPAL_AGGREGATED_JS.js"'
23
- - title: Strip CSS/JS cache IDs
24
- selector: style, script
25
- pattern: '("[^"]*\.(js|css))\?[a-z0-9]{6}"'
26
- substitute: '\1'
27
- - title: Strip Drupal JS version tags
28
- selector: script
29
- pattern: '(src="[^"]*/misc/\w+\.js)?v=\d+\.\d+"'
30
- substitute: '\1'
31
- - title: Strip domain names from absolute URLs
32
- pattern: 'http:\/\/[a-zA-Z0-9.:-]+'
33
- substitute: '__domain__'
34
- - title: Strip form build ID
35
- selector: input
36
- pattern: 'autocomplete="off" data-drupal-selector="form-[-\w]{40,43}"'
37
- substitute: 'autocomplete="off" data-drupal-selector="form-DRUPAL_FORM_BUILD_ID"'
38
- - title: Strip form build ID 2
39
- selector: input
40
- pattern: 'name="form_build_id" value="form-[-\w]{40,43}"'
41
- substitute: 'name="form_build_id" value="form-DRUPAL_FORM_BUILD_ID"'
42
- - title: Strip Drupal CSS link queries
43
- selector: link
44
- pattern: '\.css\?(\w*)'
45
- substitute: '\.css'
46
- - title: Strip Drupal JS link queries
47
- selector: script
48
- pattern: '\.js\?(\w*)'
49
- substitute: '\.js'
50
- - title: Strip Drupal View-DOM ID
51
- pattern: 'view-dom-id-\w*'
52
- substitute: 'view-dom-id-_ID_'
53
- - title: Strip Drupal View-DOM ID 2
54
- pattern: '(views?_dom_id"?:"?)\w*'
55
- substitute: '\1_ID_'
56
- - title: Ignore Drupal CSS file names
57
- selector: link
58
- pattern: 'css_[-\w]{40,43}(\\|%5C)?\.css'
59
- substitute: 'css__ID__.css'
60
- - title: Ignore Drupal JS file names
61
- selector: script
62
- pattern: 'js_[-\w]{40,43}\\?\.js'
63
- substitute: 'js__ID__.js'
data/lib/sitediff/rules.rb DELETED
@@ -1,65 +0,0 @@
1
- # frozen_string_literal: true
2
-
3
- require 'sitediff/sanitize/regexp'
4
- require 'pathname'
5
- require 'set'
6
-
7
- class SiteDiff
8
- # Find appropriate rules for a given site
9
- class Rules
10
- def initialize(config, disabled = false)
11
- @disabled = disabled
12
- @config = config
13
- find_sanitization_candidates
14
- @rules = Hash.new { |h, k| h[k] = Set.new }
15
- end
16
-
17
- def find_sanitization_candidates
18
- @candidates = Set.new
19
-
20
- rules_dir = Pathname.new(__FILE__).dirname + 'files' + 'rules'
21
- rules_dir.children.each do |f|
22
- next unless f.file? && f.extname == '.yaml'
23
-
24
- conf = YAML.load_file(f)
25
- @candidates.merge(conf['sanitization'])
26
- end
27
- end
28
-
29
- def handle_page(tag, html, doc)
30
- found = find_rules(html, doc)
31
- @rules[tag].merge(found)
32
- end
33
-
34
- # Yield a set of rules that seem reasonable for this HTML
35
- # assumption: the YAML file is a list of regexp rules only
36
- def find_rules(html, doc)
37
- @candidates.select do |rule|
38
- re = SiteDiff::Sanitizer::Regexp.create(rule)
39
- re.applies?(html, doc)
40
- end
41
- end
42
-
43
- # Find all rules from all rulesets that apply for all pages
44
- def add_config
45
- have_both = @rules.include?(:before)
46
-
47
- r1, r2 = *@rules.values_at(:before, :after)
48
- if have_both
49
- add_section('before', r1 - r2)
50
- add_section('after', r2 - r1)
51
- add_section(nil, r1 & r2)
52
- else
53
- add_section(nil, r2)
54
- end
55
- end
56
-
57
- def add_section(name, rules)
58
- return if rules.empty?
59
-
60
- conf = name ? @config[name] : @config
61
- rules.each { |r| r['disabled'] = true } if @disabled
62
- conf['sanitization'] = rules.to_a.sort_by { |r| r['title'] }
63
- end
64
- end
65
- end