sitediff 1.2.8 → 1.2.11

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: d8ada20fc6a7f1adad1a21601dd0ffb9d8391f6a939296339cec3eb1b0104aba
-  data.tar.gz: 899e79721748ec176b0ce6bd602c521cd94689ce0d28806f77d495effa92f57e
+  metadata.gz: 0d72ceb59ad0298c164aa50f19bf0d374b77936f5fdbb26f6f0d3934c77eb94f
+  data.tar.gz: 1ec3ab62b35e6013a1562ec4d5cd7eb484c49b634db4fd15755e6ef7d4038adb
 SHA512:
-  metadata.gz: 70cff17823e4244a3ce2d148b8ebbc707ae7b38d1a9ea7c90ea622520d730d13fd0b4efd2733784e0fd806f39afee835c4536b0c6fc2bf749aa9a3ab77c6afa0
-  data.tar.gz: da2a6294e02c1a1badb93c04af8d5bf7f21f05c976e902463f2d8ffe3bad53ef6aae79e5ee9373ae949f35cce883098b7081b5d482dc78dab1b929665c4968f6
+  metadata.gz: bec37fcb8498819a817bfa7670b247c335a942b5eac1ed9fbef363d0cfb9e70c4e43313a36ef501e3fcff093692f37c8f3f18f0bcc3938f0098693c6c233cd4c
+  data.tar.gz: 13c951e3f4973278cd5f7a1d48b7aff57ec54b6a72af8830fa7d6eeefc190dfc91b3bdc5500e96890a7af11a2ff48ceb0431c1213f88f4a213c7a144f9d95a7b

data/CHANGELOG.md

@@ -1,6 +1,18 @@
 # SiteDiff Change Log
 
 Contains noteworthy changes made to SiteDiff.
+
+## Version 1.2.11
+- Change to the Drupal preset for absolute links.  It no longer changes __domain__ to an empty string.
+- Added an option to the 'diff' command to remove HTML comments from pages.
+
+## Version 1.2.10
+- Updated deployment to get Docker build.
+- Removed some debug code.
+
+## Version 1.2.9
+- Fixing bug with version command within the Docker image.
+
 ## Version 1.2.8
 - Dependency updates.
 

data/Gemfile.lock

@@ -1,7 +1,7 @@
 PATH
   remote: .
   specs:
-    sitediff (1.2.7)
+    sitediff (1.2.10)
       addressable (>= 2.5.2, < 2.9.0)
       diffy (~> 3.4.0)
       minitar (~> 0.9)
@@ -15,7 +15,7 @@ PATH
 GEM
   remote: https://rubygems.org/
   specs:
-    addressable (2.8.1)
+    addressable (2.8.5)
       public_suffix (>= 2.0.2, < 6.0)
     ast (2.4.2)
     diff-lcs (1.5.0)
@@ -26,19 +26,20 @@ GEM
     fileutils (1.1.0)
     json (2.6.2)
     minitar (0.9)
-    nokogiri (1.15.2-aarch64-linux)
+    nokogiri (1.16.5-arm64-darwin)
       racc (~> 1.4)
-    nokogiri (1.15.2-x86_64-linux)
+    nokogiri (1.16.5-x86_64-linux)
       racc (~> 1.4)
     parallel (1.22.1)
     parser (3.1.2.0)
       ast (~> 2.4.1)
-    pkg-config (1.5.1)
-    public_suffix (5.0.1)
-    racc (1.6.2)
+    pkg-config (1.5.5)
+    public_suffix (5.0.3)
+    racc (1.7.3)
     rainbow (3.1.1)
     regexp_parser (2.5.0)
-    rexml (3.2.5)
+    rexml (3.3.6)
+      strscan
     rspec (3.11.0)
       rspec-core (~> 3.11.0)
       rspec-expectations (~> 3.11.0)
@@ -65,6 +66,7 @@ GEM
     rubocop-ast (1.18.0)
       parser (>= 3.1.1.0)
     ruby-progressbar (1.11.0)
+    strscan (3.1.0)
     thor (1.2.1)
     typhoeus (1.4.0)
       ethon (>= 0.9.0)
@@ -72,6 +74,7 @@ GEM
     webrick (1.8.1)
 
 PLATFORMS
+  arm64-darwin-22
   x86_64-linux
 
 DEPENDENCIES

data/README.md

@@ -28,8 +28,9 @@
     - [selector](#selector)
     - [sanitization](#sanitization)
     - [ignore_whitespace](#ignore_whitespace)
+    - [remove_html_comments](#remove_html_comments)
     - [before / after](#before--after)
-    - [includes](#incudes) 
+    - [includes](#incudes)
     - [dom_transform](#dom_transform)
         - [remove](#remove)
         - [strip](#strip)
@@ -61,7 +62,7 @@
     - [Empty Attributes](#empty-attributes)
 - [Acknowledgements](#acknowledgements)
 
-## Introduction 
+## Introduction
 SiteDiff makes it easy to see how a website changes. It can compare two similar
 sites or it can show how a single site changed over time. It helps identify
 undesirable changes to the site's HTML and it's a useful tool for conducting QA
@@ -393,6 +394,15 @@ On the command line, use `-w` or `--ignore-whitespace`.
 sitediff diff -w
 ```
 
+### remove_html_comments
+Remove HTML comments from a page.  Useful for Drupal sites with the theme debugging enabled.
+
+On the command line, use `-c` or `--remove-html-comments`.
+
+```bash
+sitediff diff -c
+```
+
 ### before / after
 
 Applies rules to just one side of the comparison.
@@ -791,7 +801,7 @@ If you have an empty `<p/>` tag appearing in the diff, you can write the followi
 
 ### HTML Tag Formatting
 
-There are times when the HTML tags do not have newlines between them on one of the sites you wish to compare.  In this 
+There are times when the HTML tags do not have newlines between them on one of the sites you wish to compare.  In this
 case, these sanitzation rules are useful:
 ```yaml
   - name: remove_space_before

data/lib/sitediff/api.rb

@@ -82,6 +82,8 @@ class SiteDiff
     def diff(options)
       @config.ignore_whitespace = options[:ignore_whitespace]
       @config.export = options[:export]
+      @config.remove_html_comments = options[:remove_html_comments]
+
       # Apply "paths" override, if any.
       if options[:paths]
         @config.paths = options[:paths]

data/lib/sitediff/cli.rb

@@ -1,5 +1,6 @@
 # frozen_string_literal: true
 
+require 'bundler'
 require 'thor'
 require 'sitediff'
 require 'sitediff/api'
@@ -40,7 +41,11 @@ class SiteDiff
     ##
     # Show version information.
     def version
-      gemspec = SiteDiff.gemspec
+      filename = '../../sitediff.gemspec'
+      filename = '/sitediff/sitediff.gemspec' if !File.exist?(File.expand_path(filename, __dir__)) && File.exist?(File.expand_path('/sitediff/sitediff.gemspec', __dir__))
+
+      gemspec = Bundler.load_gemspec(File.expand_path(filename, __dir__))
+
       output = []
       output.push("Sitediff CLI #{gemspec.version}")
       if options[:verbose]
@@ -95,6 +100,11 @@ class SiteDiff
            default: false,
            aliases: '-e',
            desc: 'Export report to files. This option forces HTML format.'
+    option 'remove_html_comments',
+           type: :boolean,
+           default: false,
+           aliases: '-c',
+           desc: 'Remove HTML comments from the output.'
     desc 'diff [OPTIONS] [CONFIG-FILE]',
          'Compute diffs on configured URLs.'
     ##
@@ -121,9 +131,11 @@ class SiteDiff
           :debug,
           :report_format,
           :before_report,
-          :after_report
+          :after_report,
+          :remove_html_comments
         )
       api_options[:cli_mode] = true
+      puts api_options
       api.diff(api_options)
     end
 

data/lib/sitediff/config.rb

@@ -304,6 +304,16 @@ class SiteDiff
       @config['ignore_whitespace'] = ignore_whitespace
     end
 
+    # Get remove_html_comments option
+    def remove_html_comments
+      @config['remove_html_comments']
+    end
+
+    # Set ignore_whitespace option
+    def remove_html_comments=(remove_html_comments)
+      @config['remove_html_comments'] = remove_html_comments
+    end
+
     # Get export option
     def export
       @config['export']

data/lib/sitediff/crawler.rb

@@ -134,7 +134,7 @@ class SiteDiff
         is_included = @include_regex.nil? ? false : @include_regex.match(u.path)
         is_excluded = @exclude_regex.nil? ? false : @exclude_regex.match(u.path)
         if is_excluded && !is_included
-          SiteDiff.log "Ignoring excluded URL #{u.path}", :info
+          SiteDiff.log "Ignoring excluded URL #{u.path}", :debug
         end
         is_included || !is_excluded
       end

data/lib/sitediff/presets/drupal.yaml

@@ -30,7 +30,7 @@ sanitization:
     substitute: '\1'
   - title: Strip domain names from absolute URLs
     pattern: 'https?:\/\/[a-zA-Z0-9.:-]+'
-    substitute: '__domain__'
+    substitute: ''
   - title: Strip form build ID
     selector: input
     pattern: 'autocomplete="off" data-drupal-selector="form-[-\w]{40,43}"'

data/lib/sitediff.rb

@@ -100,6 +100,8 @@ class SiteDiff
   def sanitize(path_passed, read_results)
     %i[before after].map do |tag|
       html = read_results[tag].content
+      html = remove_html_comments(html) if @config.remove_html_comments
+
       # TODO: See why encoding is empty while running tests.
       #
       # The presence of an "encoding" value used to be used to determine
@@ -117,6 +119,11 @@ class SiteDiff
     end
   end
 
+  # Remove HTML comments.
+  def remove_html_comments(html_content)
+    html_content.gsub(/<!--.*?-->/m, '')
+  end
+
   ##
   # Process a set of read results.
   #

data/sitediff.gemspec

@@ -2,7 +2,7 @@
 
 Gem::Specification.new do |s|
   s.name        = 'sitediff'
-  s.version     = '1.2.8'
+  s.version     = '1.2.11'
   s.required_ruby_version = '>= 3.1.2'
   s.summary     = 'Compare two versions of a site with ease!'
   s.description = <<DESC

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: sitediff
 version: !ruby/object:Gem::Version
-  version: 1.2.8
+  version: 1.2.11
 platform: ruby
 authors:
 - Alex Dergachev
@@ -10,7 +10,7 @@ authors:
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2023-09-07 00:00:00.000000000 Z
+date: 2024-08-22 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: pkg-config
@@ -229,7 +229,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.4.14
+rubygems_version: 3.4.19
 signing_key:
 specification_version: 4
 summary: Compare two versions of a site with ease!