sitediff 0.0.6 → 1.0.0

data/lib/sitediff/sanitize/regexp.rb

@@ -2,41 +2,62 @@
 
 class SiteDiff
   class Sanitizer
+    # Regular Expression Object.
     class Regexp
+      ##
+      # Creates a RegExp object.
       def initialize(rule)
         @rule = rule
       end
 
+      ##
+      # Whether the RegExp has a selector.
       def selector?
         false
       end
 
+      ##
+      # Whether the RegExp applies to the given markup.
       def applies?(html, _node)
         applies_to_string?(html)
       end
 
+      ##
+      # Applies the RegExp to the markup.
       def apply(html)
         gsub!(html)
       end
 
+      ##
+      # Creates a RegExp object as per rule.
       def self.create(rule)
         rule['selector'] ? WithSelector.new(rule) : new(rule)
       end
 
+      ##
+      # A RegExp with selector.
       class WithSelector < Regexp
+        ##
+        # Whether the RegExp has a selector.
         def selector?
           true
         end
 
+        ##
+        # TODO: Document what this method does.
         def contexts(node)
-          sels = @rule['selector']
-          node.css(sels).each { |e| yield(e) }
+          selectors = @rule['selector']
+          node.css(selectors).each { |e| yield(e) }
         end
 
+        ##
+        # Whether the RegExp applies to the given markup.
         def applies?(_html, node)
           enum_for(:contexts, node).any? { |e| applies_to_string?(e.to_html) }
         end
 
+        ##
+        # Applies the RegExp to the markup.
         def apply(node)
           contexts(node) { |e| e.replace(gsub!(e.to_html)) }
         end

data/lib/sitediff/uriwrapper.rb

@@ -7,10 +7,14 @@ require 'addressable/uri'
 class SiteDiff
   class SiteDiffReadFailure < SiteDiffException; end
 
+  # SiteDiff URI Wrapper.
   class UriWrapper
+    # TODO: Move these CURL OPTS to Config.DEFAULT_CONFIG.
     DEFAULT_CURL_OPTS = {
-      connecttimeout: 3,     # Don't hang on servers that don't exist
-      followlocation: true,  # Follow HTTP redirects (code 301 and 302)
+      # Don't hang on servers that don't exist.
+      connecttimeout: 3,
+      # Follow HTTP redirects (code 301 and 302).
+      followlocation: true,
       headers: {
         'User-Agent' => 'Sitediff - https://github.com/evolvingweb/sitediff'
       }
@@ -20,6 +24,8 @@ class SiteDiff
     class ReadResult
       attr_accessor :encoding, :content, :error_code, :error
 
+      ##
+      # Creates a ReadResult.
       def initialize(content = nil, encoding = 'utf-8')
         @content = content
         @encoding = encoding
@@ -27,14 +33,18 @@ class SiteDiff
         @error_code = nil
       end
 
-      def self.error(err, code = nil)
+      ##
+      # Creates a ReadResult with an error.
+      def self.error(message, code = nil)
         res = new
         res.error_code = code
-        res.error = err
+        res.error = message
         res
       end
     end
 
+    ##
+    # Creates a UriWrapper.
     def initialize(uri, curl_opts = DEFAULT_CURL_OPTS, debug = true)
       @uri = uri.respond_to?(:scheme) ? uri : Addressable::URI.parse(uri)
       # remove trailing '/'s from local URIs
@@ -43,14 +53,20 @@ class SiteDiff
       @debug = debug
     end
 
+    ##
+    # Returns the "user" part of the URI.
     def user
       @uri.user
     end
 
+    ##
+    # Returns the "password" part of the URI.
     def password
       @uri.password
     end
 
+    ##
+    # Converts the URI to a string.
     def to_s
       uri = @uri.dup
       uri.user = nil
@@ -58,19 +74,22 @@ class SiteDiff
       uri.to_s
     end
 
+    ##
     # Is this a local filesystem path?
     def local?
       @uri.scheme.nil?
     end
 
+    ## What does this one do?
     # FIXME: this is not used anymore
-    def +(path)
+    def +(other)
       # 'path' for SiteDiff includes (parts of) path, query, and fragment.
       sep = ''
       sep = '/' if local? || @uri.path.empty?
-      self.class.new(@uri.to_s + sep + path)
+      self.class.new(@uri.to_s + sep + other)
     end
 
+    ##
     # Reads a file and yields to the completion handler, see .queue()
     def read_file
       File.open(@uri.to_s, 'r:UTF-8') { |f| yield ReadResult.new(f.read) }
@@ -114,25 +133,35 @@ class SiteDiff
         rescue ArgumentError => e
           raise if @debug
 
-          yield ReadResult.error("Parsing error for #{@uri}: #{e.message}")
-        rescue => e
+          yield ReadResult.error(
+            "Parsing error for #{@uri}: #{e.message}"
+          )
+        rescue StandardError => e
           raise if @debug
 
-          yield ReadResult.error("Unknown parsing error for #{@uri}: #{e.message}")
+          yield ReadResult.error(
+            "Unknown parsing error for #{@uri}: #{e.message}"
+          )
         end
       end
 
       req.on_failure do |resp|
         if resp&.status_message
           msg = resp.status_message
-          yield ReadResult.error("HTTP error when loading #{@uri}: #{msg}",
-                                 resp.response_code)
+          yield ReadResult.error(
+            "HTTP error when loading #{@uri}: #{msg}",
+            resp.response_code
+          )
         elsif (msg = resp.options[:return_code])
-          yield ReadResult.error("Connection error when loading #{@uri}: #{msg}",
-                                 resp.response_code)
+          yield ReadResult.error(
+            "Connection error when loading #{@uri}: #{msg}",
+            resp.response_code
+          )
         else
-          yield ReadResult.error("Unknown error when loading #{@uri}: #{msg}",
-                                 resp.response_code)
+          yield ReadResult.error(
+            "Unknown error when loading #{@uri}: #{msg}",
+            resp.response_code
+          )
         end
       end
 
@@ -152,5 +181,17 @@ class SiteDiff
         hydra.queue(typhoeus_request(&handler))
       end
     end
+
+    ##
+    # Canonicalize a path.
+    #
+    # @param [String] path
+    #   A base relative path. Example: /foo/bar
+    def self.canonicalize(path)
+      # Ignore trailing slashes for all paths except "/" (front page).
+      path = path.chomp('/') unless path == '/'
+      # If the path is empty, assume that it's the front page.
+      path.empty? ? '/' : path
+    end
   end
 end

data/lib/sitediff/webserver.rb

@@ -3,13 +3,15 @@
 require 'webrick'
 
 class SiteDiff
+  # SiteDiff Web Server.
   class Webserver
-    # Simple webserver for testing purposes
+    # Simple web server for testing purposes.
     DEFAULT_PORT = 13_080
 
     attr_accessor :ports
 
-    # Serve a list of directories
+    ##
+    # Serve a list of directories.
     def initialize(start_port, dirs, opts = {})
       start_port ||= DEFAULT_PORT
       @ports = (start_port...(start_port + dirs.size)).to_a
@@ -25,14 +27,20 @@ class SiteDiff
       end
     end
 
+    ##
+    # Kills the server.
     def kill
       @threads.each(&:kill)
     end
 
+    ##
+    # Waits for the server.
     def wait
       @threads.each(&:join)
     end
 
+    ##
+    # Maps URIs to defined ports and returns a list of URIs.
     def uris
       ports.map { |p| "http://localhost:#{p}" }
     end
@@ -63,9 +71,10 @@ class SiteDiff
 
     public
 
+    # SiteDiff Fixture Server.
     class FixtureServer < Webserver
       PORT = DEFAULT_PORT + 1
-      BASE = 'spec/fixtures/ruby-doc.org'
+      BASE = 'spec/sites/ruby-doc.org'
       NAMES = %w[core-1.9.3 core-2.0].freeze
 
       def initialize(port = PORT, base = BASE, names = NAMES)

data/lib/sitediff/webserver/resultserver.rb

@@ -1,18 +1,24 @@
 # frozen_string_literal: true
 
 require 'sitediff'
+require 'sitediff/report'
 require 'sitediff/webserver'
 require 'erb'
 
 class SiteDiff
   class Webserver
+    # SiteDiff Result Server.
     class ResultServer < Webserver
       # Display a page from the cache
       class CacheServlet < WEBrick::HTTPServlet::AbstractServlet
+        ##
+        # Creates a Cache Servlet.
         def initialize(_server, cache)
           @cache = cache
         end
 
+        ##
+        # Performs a GET request.
         def do_GET(req, res)
           path = req.path_info
           (md = %r{^/([^/]+)(/.*)$}.match(path)) ||
@@ -29,13 +35,18 @@ class SiteDiff
         end
       end
 
-      # Display two pages side by side
+      ##
+      # Display two pages side by side.
       class SideBySideServlet < WEBrick::HTTPServlet::AbstractServlet
+        ##
+        # Creates a Side By Side Servlet.
         def initialize(_server, cache, settings)
           @cache = cache
           @settings = settings
         end
 
+        ##
+        # Generates URLs for a given path.
         def urls(path)
           %w[before after].map do |tag|
             base = @settings[tag]
@@ -44,6 +55,8 @@ class SiteDiff
           end
         end
 
+        ##
+        # Performs a GET request.
         def do_GET(req, res)
           path = req.path_info
           before, after = *urls(path)
@@ -54,52 +67,29 @@ class SiteDiff
         end
       end
 
-      # Run sitediff command from browser. Probably dangerous in general.
-      class RunServlet < WEBrick::HTTPServlet::AbstractServlet
-        def initialize(_server, dir)
-          @dir = dir
-        end
-
-        def do_GET(req, res)
-          path = req.path_info
-          if path != '/diff'
-            res['content-type'] = 'text/plain'
-            res.body = 'ERROR: Only /run/diff is supported by the /run API at the moment'
-            return
-          end
-          # Thor assumes only one command is called and some values like
-          # `options` are share across all SiteDiff::Cli instances so
-          # we can't just call SiteDiff::Cli.new().diff
-          # This is likely to go very wrong depending on how `sitediff serve`
-          # was actually called
-          cmd = "#{$PROGRAM_NAME} diff -C #{@dir} --cached=all"
-          system(cmd)
-
-          # Could also add a message to indicate success/failure
-          # But for the moment, all our files are static
-          res.set_redirect(WEBrick::HTTPStatus::Found,
-                           "/files/#{SiteDiff::REPORT_FILE}")
-        end
-      end
-
+      ##
+      # Creates a Result Server.
       def initialize(port, dir, opts = {})
-        unless File.exist?(File.join(dir, SiteDiff::SETTINGS_FILE))
+        unless File.exist?(File.join(dir, Report::SETTINGS_FILE))
           raise SiteDiffException,
                 "Please run 'sitediff diff' before running 'sitediff serve'"
         end
 
-        @settings = YAML.load_file(File.join(dir, SiteDiff::SETTINGS_FILE))
+        @settings = YAML.load_file(File.join(dir, Report::SETTINGS_FILE))
+        puts @settings
         @cache = opts[:cache]
         super(port, [dir], opts)
       end
 
+      ##
+      # TODO: Document what this method does.
       def server(opts)
         dir = opts.delete(:DocumentRoot)
         srv = super(opts)
         srv.mount_proc('/') do |req, res|
           if req.path == '/'
             res.set_redirect(WEBrick::HTTPStatus::Found,
-                             "/files/#{SiteDiff::REPORT_FILE}")
+                             "/files/#{Report::REPORT_FILE_HTML}")
           else
             res.set_redirect(WEBrick::HTTPStatus::TemporaryRedirect,
                              "#{@settings['after']}#{req.path}")
@@ -109,10 +99,11 @@ class SiteDiff
         srv.mount('/files', WEBrick::HTTPServlet::FileHandler, dir, true)
         srv.mount('/cache', CacheServlet, @cache)
         srv.mount('/sidebyside', SideBySideServlet, @cache, @settings)
-        srv.mount('/run', RunServlet, dir)
         srv
       end
 
+      ##
+      # Sets up the server.
       def setup
         super
         root = uris.first
@@ -120,6 +111,8 @@ class SiteDiff
         open_in_browser(root) if @opts[:browse]
       end
 
+      ##
+      # Opens a URL in a browser.
       def open_in_browser(url)
         commands = %w[xdg-open open]
         cmd = commands.find { |c| which(c) }
@@ -127,6 +120,8 @@ class SiteDiff
         cmd
       end
 
+      ##
+      # TODO: Document what this method does.
       def which(cmd)
         ENV['PATH'].split(File::PATH_SEPARATOR).each do |path|
           file = File.join(path, cmd)

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: sitediff
 version: !ruby/object:Gem::Version
-  version: 0.0.6
+  version: 1.0.0
 platform: ruby
 authors:
 - Alex Dergachev
@@ -10,7 +10,7 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2019-04-02 00:00:00.000000000 Z
+date: 2020-06-08 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: pkg-config
@@ -26,6 +26,20 @@ dependencies:
     - - "~>"
       - !ruby/object:Gem::Version
         version: '1.1'
+- !ruby/object:Gem::Dependency
+  name: minitar
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '0.9'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '0.9'
 - !ruby/object:Gem::Dependency
   name: thor
   requirement: !ruby/object:Gem::Requirement
@@ -72,16 +86,16 @@ dependencies:
   name: nokogiri
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ">="
       - !ruby/object:Gem::Version
-        version: 1.8.2
+        version: 1.10.4
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ">="
       - !ruby/object:Gem::Version
-        version: 1.8.2
+        version: 1.10.4
 - !ruby/object:Gem::Dependency
   name: addressable
   requirement: !ruby/object:Gem::Requirement
@@ -102,14 +116,14 @@ dependencies:
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 3.2.0
+        version: 3.3.0
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 3.2.0
+        version: 3.3.0
 description: "  SiteDiff makes it easy to see differences between two versions of
   a website. It accepts a set of paths to compare two versions of the site together
   with potential normalization/sanitization rules. From the provided paths and configuration
@@ -129,28 +143,32 @@ files:
 - lib/sitediff/cli.rb
 - lib/sitediff/config.rb
 - lib/sitediff/config/creator.rb
+- lib/sitediff/config/preset.rb
 - lib/sitediff/crawler.rb
 - lib/sitediff/diff.rb
 - lib/sitediff/exception.rb
 - lib/sitediff/fetch.rb
 - lib/sitediff/files/diff.html.erb
-- lib/sitediff/files/html_report.html.erb
+- lib/sitediff/files/jquery.min.js
+- lib/sitediff/files/normalize.css
 - lib/sitediff/files/pretty_print.xsl
-- lib/sitediff/files/rules/drupal.yaml
+- lib/sitediff/files/report.html.erb
 - lib/sitediff/files/sidebyside.html.erb
 - lib/sitediff/files/sitediff.css
+- lib/sitediff/files/sitediff.js
+- lib/sitediff/report.rb
 - lib/sitediff/result.rb
-- lib/sitediff/rules.rb
 - lib/sitediff/sanitize.rb
 - lib/sitediff/sanitize/dom_transform.rb
 - lib/sitediff/sanitize/regexp.rb
 - lib/sitediff/uriwrapper.rb
 - lib/sitediff/webserver.rb
 - lib/sitediff/webserver/resultserver.rb
-homepage: https://github.com/evolvingweb/sitediff/
+homepage: https://sitediff.io/
 licenses:
 - GPL-2.0
-metadata: {}
+metadata:
+  source_code_uri: https://github.com/evolvingweb/sitediff
 post_install_message: 
 rdoc_options: []
 require_paths:
@@ -159,15 +177,14 @@ required_ruby_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
-      version: '2.3'
+      version: '2.4'
 required_rubygems_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubyforge_project: 
-rubygems_version: 2.5.2.3
+rubygems_version: 3.1.2
 signing_key: 
 specification_version: 4
 summary: Compare two versions of a site with ease!