sitediff 0.0.1 → 1.0.0

data/lib/sitediff/webserver/resultserver.rb

@@ -0,0 +1,134 @@
+# 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)) ||
+            raise(WEBrick::HTTPStatus::NotFound)
+          tag, path = *md.captures
+          (r = @cache.get(tag.to_sym, path)) ||
+            raise(WEBrick::HTTPStatus::NotFound)
+
+          raise WEBrick::HTTPStatus[r.error_code] if r.error_code
+          raise WEBrick::HTTPStatus::InternalServerError, r.error if r.error
+
+          res['content-type'] = 'text/html'
+          res.body = r.content
+        end
+      end
+
+      ##
+      # 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]
+            base = "/cache/#{tag}" if @settings['cached'].include? tag
+            base + path
+          end
+        end
+
+        ##
+        # Performs a GET request.
+        def do_GET(req, res)
+          path = req.path_info
+          before, after = *urls(path)
+
+          res['content-type'] = 'text/html'
+          erb = File.join(SiteDiff::FILES_DIR, 'sidebyside.html.erb')
+          res.body = ERB.new(File.read(erb)).result(binding)
+        end
+      end
+
+      ##
+      # Creates a Result Server.
+      def initialize(port, dir, opts = {})
+        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, 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/#{Report::REPORT_FILE_HTML}")
+          else
+            res.set_redirect(WEBrick::HTTPStatus::TemporaryRedirect,
+                             "#{@settings['after']}#{req.path}")
+          end
+        end
+
+        srv.mount('/files', WEBrick::HTTPServlet::FileHandler, dir, true)
+        srv.mount('/cache', CacheServlet, @cache)
+        srv.mount('/sidebyside', SideBySideServlet, @cache, @settings)
+        srv
+      end
+
+      ##
+      # Sets up the server.
+      def setup
+        super
+        root = uris.first
+        puts "Serving at #{root}"
+        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) }
+        system(cmd, url) if cmd
+        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)
+          return file if File.executable?(file)
+        end
+        nil
+      end
+    end
+  end
+end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: sitediff
 version: !ruby/object:Gem::Version
-  version: 0.0.1
+  version: 1.0.0
 platform: ruby
 authors:
 - Alex Dergachev
@@ -10,121 +10,181 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2015-04-21 00:00:00.000000000 Z
+date: 2020-06-08 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
-  name: thor
+  name: pkg-config
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - '>='
+    - - "~>"
       - !ruby/object:Gem::Version
-        version: '0'
+        version: '1.1'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - '>='
+    - - "~>"
       - !ruby/object:Gem::Version
-        version: '0'
+        version: '1.1'
 - !ruby/object:Gem::Dependency
-  name: nokogiri
+  name: minitar
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - '>='
+    - - "~>"
       - !ruby/object:Gem::Version
-        version: '0'
+        version: '0.9'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - '>='
+    - - "~>"
       - !ruby/object:Gem::Version
-        version: '0'
+        version: '0.9'
 - !ruby/object:Gem::Dependency
-  name: diffy
+  name: thor
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - '>='
+    - - "~>"
       - !ruby/object:Gem::Version
-        version: '0'
+        version: 0.20.0
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - '>='
+    - - "~>"
       - !ruby/object:Gem::Version
-        version: '0'
+        version: 0.20.0
 - !ruby/object:Gem::Dependency
   name: typhoeus
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - '>='
+    - - "~>"
       - !ruby/object:Gem::Version
-        version: '0'
+        version: '1.0'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - '>='
+    - - "~>"
       - !ruby/object:Gem::Version
-        version: '0'
+        version: '1.0'
 - !ruby/object:Gem::Dependency
   name: rainbow
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - '>='
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 3.0.0
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 3.0.0
+- !ruby/object:Gem::Dependency
+  name: nokogiri
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
       - !ruby/object:Gem::Version
-        version: '0'
+        version: 1.10.4
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - '>='
+    - - ">="
       - !ruby/object:Gem::Version
-        version: '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 SiteDiff generates an HTML report of all the status of HTML comparison between the given paths together with a readable diff-like HTML for each specified path containing the differences between the two versions of the site. It is useful tool for QAing re-deployments, site upgrades, etc.
+        version: 1.10.4
+- !ruby/object:Gem::Dependency
+  name: addressable
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 2.5.2
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 2.5.2
+- !ruby/object:Gem::Dependency
+  name: diffy
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 3.3.0
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        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
+  SiteDiff generates an HTML report of all the status of HTML comparison between the
+  given paths together with a readable diff-like HTML for each specified path containing
+  the differences between the two versions of the site. It is useful tool for QAing
+  re-deployments, site upgrades, etc.\n"
 email: alex@evolvingweb.ca
 executables:
 - sitediff
 extensions: []
 extra_rdoc_files: []
 files:
+- bin/sitediff
+- lib/sitediff.rb
+- lib/sitediff/cache.rb
 - 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/result.rb
-- lib/sitediff/sanitize.rb
-- lib/sitediff/uriwrapper.rb
-- lib/sitediff/util/cache.rb
-- lib/sitediff/util/webserver.rb
-- lib/sitediff.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/report.html.erb
+- lib/sitediff/files/sidebyside.html.erb
 - lib/sitediff/files/sitediff.css
-- bin/sitediff
-homepage: https://github.com/evolvingweb/sitediff/
+- lib/sitediff/files/sitediff.js
+- lib/sitediff/report.rb
+- lib/sitediff/result.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://sitediff.io/
 licenses:
-- GPL-2
-metadata: {}
+- GPL-2.0
+metadata:
+  source_code_uri: https://github.com/evolvingweb/sitediff
 post_install_message: 
 rdoc_options: []
 require_paths:
 - lib
 required_ruby_version: !ruby/object:Gem::Requirement
   requirements:
-  - - '>='
+  - - ">="
     - !ruby/object:Gem::Version
-      version: 1.9.3
+      version: '2.4'
 required_rubygems_version: !ruby/object:Gem::Requirement
   requirements:
-  - - '>='
+  - - ">="
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubyforge_project: 
-rubygems_version: 2.0.14
+rubygems_version: 3.1.2
 signing_key: 
 specification_version: 4
 summary: Compare two versions of a site with ease!

data/lib/sitediff/files/html_report.html.erb

@@ -1,47 +0,0 @@
-<!DOCTYPE html>
-<html>
-  <head>
-    <!-- important: otherwise chrome will choke on non-ascii characters -->
-    <meta charset="utf-8" />
-    <style>
-      <%= SiteDiff::Diff.css %>
-    </style>
-    <title> SiteDiff Report </title>
-  </head>
-  <body>
-    <div class="sitediff">
-      <div class="legend">
-        <strong>before</strong> (base url): <a href="<%=before%>"><%=before%></a> |
-        <strong>after </strong> (base url): <a href="<%=after%>" ><%=after %></a>
-      </div>
-      <table class="results">
-
-        <colgroup>
-          <col class="before-col">
-          <col class="after-col">
-          <col class="path-col">
-          <col class="diff-stat-col">
-        </colgroup>
-
-        <thead>
-          <tr>
-            <th> Before </th>
-            <th> After </th>
-            <th> Path </th>
-            <th> Status </th>
-          </tr>
-        </thead>
-
-        <% results.each do |result| %>
-        <tr class="<%= result.status_text %>">
-          <td class="before"><a href="<%= result.url(before) %>">[before]</a></td>
-          <td class="after"><a href="<%= result.url(after) %>">[after]</a></td>
-          <td class="path"><%= result.path %></td>
-          <td class="status"><%= result.link %></td>
-        </tr>
-        <% end %>
-
-      </table>
-    </div>
-  </body>
-</html>

data/lib/sitediff/util/cache.rb

@@ -1,32 +0,0 @@
-class SiteDiff
-  module Util
-    # A typhoeus cache, backed by DBM
-    class Cache
-      def initialize(file)
-        # Default to GDBM, if we have it, we don't want pag/dir files
-        begin
-          require 'gdbm'
-          @dbm = GDBM.new(file)
-        rescue LoadError
-          require 'dbm'
-          @dbm = DBM.new(file)
-        end
-      end
-
-      # Older Typhoeus doesn't have cache_key
-      def cache_key(req)
-        return req.cache_key if req.respond_to?(:cache_key)
-        return Marshal.dump([req.base_url, req.options])
-      end
-
-      def get(req)
-        resp = @dbm[cache_key(req)] or return nil
-        Marshal.load(resp)
-      end
-
-      def set(req, resp)
-        @dbm[cache_key(req)] = Marshal.dump(resp)
-      end
-    end
-  end
-end

data/lib/sitediff/util/webserver.rb

@@ -1,77 +0,0 @@
-require 'webrick'
-
-class SiteDiff
-  module Util
-    # Simple webserver for testing purposes
-    class Webserver
-      DEFAULT_PORT = 13080
-
-      attr_accessor :ports
-
-      # Serve a list of directories
-      def initialize(start_port, dirs, params = {})
-        start_port ||= DEFAULT_PORT
-        @ports = (start_port...(start_port + dirs.size)).to_a
-
-        if params[:announce]
-          puts "Serving at #{uris.join(", ")}"
-        end
-
-        opts = {}
-        if params[:quiet]
-          opts[:Logger] = WEBrick::Log.new(IO::NULL)
-          opts[:AccessLog] = []
-        end
-
-        @threads = []
-        dirs.each_with_index do |dir, idx|
-          opts[:Port] = @ports[idx]
-          opts[:DocumentRoot] = dir
-          server = WEBrick::HTTPServer.new(opts)
-          @threads << Thread.new { server.start }
-        end
-
-        if block_given?
-          yield self
-          kill
-        end
-      end
-
-      def kill
-        @threads.each { |t| t.kill }
-      end
-
-      def wait
-        @threads.each { |t| t.join }
-      end
-
-      def uris
-        ports.map { |p| "http://localhost:#{p}" }
-      end
-
-
-      # Helper to serve one dir
-      def self.serve(port, dir, params = {})
-        new(port, [dir], params)
-      end
-    end
-
-    class FixtureServer < Webserver
-      PORT = DEFAULT_PORT + 1
-      BASE = 'spec/fixtures/ruby-doc.org'
-      NAMES = %w[core-1.9.3 core-2.0]
-
-      def initialize(port = PORT, base = BASE, names = NAMES)
-        dirs = names.map { |n| File.join(base, n) }
-        super(port, dirs, :quiet => true)
-      end
-
-      def before
-        uris.first
-      end
-      def after
-        uris.last
-      end
-    end
-  end
-end