browserx 1.0.0 → 2.0.0

data/lib/browser/cloudflare.rb

@@ -0,0 +1,65 @@
+# frozen_string_literal: true
+
+module Browser
+  # What Cloudflare knows of the request, from the headers a Transform Rule
+  # sets (docs/guide.html#cloudflare) and its own CF-IPCountry. Each site names
+  # its headers in its rule: Browser::Cloudflare.header_names= changes them.
+  class Cloudflare
+    DEFAULT_HEADER_NAMES = {
+      verified_bot: "X-Bot-Verified",
+      bot_category: "X-Bot-Category",
+      bot_score: "X-Bot-Score",
+      country: "CF-IPCountry"
+    }.freeze
+
+    class << self
+      attr_reader :header_names, :env_key_by_signal
+    end
+
+    # Merged into the defaults: {bot_score: "X-Edge-Bot-Score"}.
+    def self.header_names=(names)
+      unknown_signals = names.keys - DEFAULT_HEADER_NAMES.keys
+      raise ArgumentError, "unknown Cloudflare signals: #{unknown_signals.inspect}" if unknown_signals.any?
+
+      @header_names = DEFAULT_HEADER_NAMES.merge(names).freeze
+      @env_key_by_signal = @header_names.transform_values { |name| "HTTP_#{name.upcase.tr("-", "_")}" }.freeze
+    end
+
+    self.header_names = {}
+
+    def initialize(headers)
+      @headers = headers
+    end
+
+    # cf.bot_management.verified_bot (cf.client.bot without Bot Management).
+    def verified_bot?
+      header(:verified_bot)&.casecmp?("true") || false
+    end
+
+    # cf.verified_bot_category, in bot.category's vocabulary: "Monitoring &
+    # Analytics" is :monitoring_and_analytics.
+    def bot_category
+      category = header(:bot_category)&.strip
+      return if category.nil? || category.empty?
+
+      category.downcase.gsub("&", "and").gsub(/[^a-z0-9]+/, "_").to_sym
+    end
+
+    # cf.bot_management.score, Bot Management only: 1 is a bot, 99 a human.
+    def bot_score
+      score = header(:bot_score)&.strip
+      score.to_i if score&.match?(/\A\d{1,2}\z/)
+    end
+
+    # The ISO 3166-1 alpha-2 country, "XX" when unknown, "T1" for Tor.
+    def country
+      country = header(:country)&.strip
+      country if country&.match?(/\A[A-Z0-9]{2}\z/)
+    end
+
+    private def header(signal)
+      value = @headers&.[](self.class.env_key_by_signal[signal])
+      value if value.is_a?(String)
+    end
+  end
+end

data/lib/browser/detection.rb

@@ -0,0 +1,25 @@
+# frozen_string_literal: true
+
+module Browser
+  # What a user agent is detected as, shared by every browser built from it
+  # while it stays in the cache. Each answer is computed on first use.
+  class Detection
+    attr_accessor :browser_class
+
+    def initialize(ua)
+      @ua = ua
+    end
+
+    def platform
+      @platform ||= Platform.new(@ua)
+    end
+
+    def device
+      @device ||= Device.new(@ua, platform:)
+    end
+
+    def bot
+      @bot ||= Bot.new(@ua)
+    end
+  end
+end

data/lib/browser/device/psvita.rb

@@ -12,7 +12,7 @@ module Browser
       end
 
       def match?
-        ua.match?("Playstation Vita")
+        ua.include?("Playstation Vita")
       end
     end
   end

data/lib/browser/device/surface.rb

@@ -12,7 +12,7 @@ module Browser
       end
 
       def match?
-        platform.windows_rt? && ua.include?("Touch")
+        ua.include?("Touch") && platform.windows_rt?
       end
 
       private def platform

data/lib/browser/device.rb

@@ -53,9 +53,19 @@ module Browser
       ]
     end
 
-    def initialize(ua, platform: nil)
+    def initialize(ua, platform: nil, client_hints: nil)
       @ua = ua
       @platform = platform
+      @client_hints = client_hints
+    end
+
+    # This device, or one built with the client hints when Sec-CH-UA-Mobile or
+    # the platform they gave change its answers.
+    def with_client_hints(client_hints, platform:)
+      mobile = client_hints.mobile?
+      return self if platform.equal?(self.platform) && (mobile.nil? || mobile == detect_mobile?)
+
+      self.class.new(ua, platform:, client_hints:)
     end
 
     def subject
@@ -201,15 +211,29 @@ module Browser
     end
 
     # Regex taken from http://detectmobilebrowsers.com
-    # rubocop:disable-next Layout/LineLength
+    MOBILE_REGEX = %r{(android|bb\d+|meego).+mobile|avantgo|bada/|blackberry|blazer|compal|elaine|fennec|hiptop|iemobile|ip(hone|od)|iris|kindle|lge |maemo|midp|mmp|mobile.+firefox|netfront|opera m(ob|in)i|palm( os)?|phone|p(ixi|re)/|plucker|pocket|psp|series(4|6)0|symbian|treo|up\.(browser|link)|vodafone|wap|windows ce|xda|xiino}i
+    MOBILE_PREFIX_REGEX = %r{1207|6310|6590|3gso|4thp|50[1-6]i|770s|802s|a wa|abac|ac(er|oo|s-)|ai(ko|rn)|al(av|ca|co)|amoi|an(ex|ny|yw)|aptu|ar(ch|go)|as(te|us)|attw|au(di|-m|r |s )|avan|be(ck|ll|nq)|bi(lb|rd)|bl(ac|az)|br(e|v)w|bumb|bw-(n|u)|c55/|capi|ccwa|cdm-|cell|chtm|cldc|cmd-|co(mp|nd)|craw|da(it|ll|ng)|dbte|dc-s|devi|dica|dmob|do(c|p)o|ds(12|-d)|el(49|ai)|em(l2|ul)|er(ic|k0)|esl8|ez([4-7]0|os|wa|ze)|fetc|fly(-|_)|g1 u|g560|gene|gf-5|g-mo|go(\.w|od)|gr(ad|un)|haie|hcit|hd-(m|p|t)|hei-|hi(pt|ta)|hp( i|ip)|hs-c|ht(c(-| |_|a|g|p|s|t)|tp)|hu(aw|tc)|i-(20|go|ma)|i230|iac( |-|/)|ibro|idea|ig01|ikom|im1k|inno|ipaq|iris|ja(t|v)a|jbro|jemu|jigs|kddi|keji|kgt( |/)|klon|kpt |kwc-|kyo(c|k)|le(no|xi)|lg( g|/(k|l|u)|50|54|-[a-w])|libw|lynx|m1-w|m3ga|m50/|ma(te|ui|xo)|mc(01|21|ca)|m-cr|me(rc|ri)|mi(o8|oa|ts)|mmef|mo(01|02|bi|de|do|t(-| |o|v)|zz)|mt(50|p1|v )|mwbp|mywa|n10[0-2]|n20[2-3]|n30(0|2)|n50(0|2|5)|n7(0(0|1)|10)|ne((c|m)-|on|tf|wf|wg|wt)|nok(6|i)|nzph|o2im|op(ti|wv)|oran|owg1|p800|pan(a|d|t)|pdxg|pg(13|-([1-8]|c))|phil|pire|pl(ay|uc)|pn-2|po(ck|rt|se)|prox|psio|pt-g|qa-a|qc(07|12|21|32|60|-[2-7]|i-)|qtek|r380|r600|raks|rim9|ro(ve|zo)|s55/|sa(ge|ma|mm|ms|ny|va)|sc(01|h-|oo|p-)|sdk/|se(c(-|0|1)|47|mc|nd|ri)|sgh-|shar|sie(-|m)|sk-0|sl(45|id)|sm(al|ar|b3|it|t5)|so(ft|ny)|sp(01|h-|v-|v )|sy(01|mb)|t2(18|50)|t6(00|10|18)|ta(gt|lk)|tcl-|tdg-|tel(i|m)|tim-|t-mo|to(pl|sh)|ts(70|m-|m3|m5)|tx-9|up(\.b|g1|si)|utst|v400|v750|veri|vi(rg|te)|vk(40|5[0-3]|-v)|vm40|voda|vulc|vx(52|53|60|61|70|80|81|83|85|98)|w3c(-| )|webc|whit|wi(g |nc|nw)|wmlb|wonu|x700|yas-|your|zeto|zte-}i
+    # Both are lowercase: on an ASCII user agent, matching its downcased copy
+    # without /i gives the same answer several times faster. Every prefix is 4
+    # characters long, so anchoring it tests the first 4 without copying them.
+    MOBILE_LOWERCASE_REGEX = Regexp.new(MOBILE_REGEX.source)
+    MOBILE_PREFIX_LOWERCASE_REGEX = Regexp.new("\\A(?:#{MOBILE_PREFIX_REGEX.source})")
+    private_constant :MOBILE_REGEX, :MOBILE_PREFIX_REGEX, :MOBILE_LOWERCASE_REGEX,
+      :MOBILE_PREFIX_LOWERCASE_REGEX
+
     private def detect_mobile?
       return @detect_mobile if defined?(@detect_mobile)
 
-      @detect_mobile =
-        psp? ||
-        /zunewp7|crios/i.match?(ua) ||
-        %r{(android|bb\d+|meego).+mobile|avantgo|bada/|blackberry|blazer|compal|elaine|fennec|hiptop|iemobile|ip(hone|od)|iris|kindle|lge |maemo|midp|mmp|mobile.+firefox|netfront|opera m(ob|in)i|palm( os)?|phone|p(ixi|re)/|plucker|pocket|psp|series(4|6)0|symbian|treo|up\.(browser|link)|vodafone|wap|windows ce|xda|xiino}i.match?(ua) ||
-        %r{1207|6310|6590|3gso|4thp|50[1-6]i|770s|802s|a wa|abac|ac(er|oo|s-)|ai(ko|rn)|al(av|ca|co)|amoi|an(ex|ny|yw)|aptu|ar(ch|go)|as(te|us)|attw|au(di|-m|r |s )|avan|be(ck|ll|nq)|bi(lb|rd)|bl(ac|az)|br(e|v)w|bumb|bw-(n|u)|c55/|capi|ccwa|cdm-|cell|chtm|cldc|cmd-|co(mp|nd)|craw|da(it|ll|ng)|dbte|dc-s|devi|dica|dmob|do(c|p)o|ds(12|-d)|el(49|ai)|em(l2|ul)|er(ic|k0)|esl8|ez([4-7]0|os|wa|ze)|fetc|fly(-|_)|g1 u|g560|gene|gf-5|g-mo|go(\.w|od)|gr(ad|un)|haie|hcit|hd-(m|p|t)|hei-|hi(pt|ta)|hp( i|ip)|hs-c|ht(c(-| |_|a|g|p|s|t)|tp)|hu(aw|tc)|i-(20|go|ma)|i230|iac( |-|/)|ibro|idea|ig01|ikom|im1k|inno|ipaq|iris|ja(t|v)a|jbro|jemu|jigs|kddi|keji|kgt( |/)|klon|kpt |kwc-|kyo(c|k)|le(no|xi)|lg( g|/(k|l|u)|50|54|-[a-w])|libw|lynx|m1-w|m3ga|m50/|ma(te|ui|xo)|mc(01|21|ca)|m-cr|me(rc|ri)|mi(o8|oa|ts)|mmef|mo(01|02|bi|de|do|t(-| |o|v)|zz)|mt(50|p1|v )|mwbp|mywa|n10[0-2]|n20[2-3]|n30(0|2)|n50(0|2|5)|n7(0(0|1)|10)|ne((c|m)-|on|tf|wf|wg|wt)|nok(6|i)|nzph|o2im|op(ti|wv)|oran|owg1|p800|pan(a|d|t)|pdxg|pg(13|-([1-8]|c))|phil|pire|pl(ay|uc)|pn-2|po(ck|rt|se)|prox|psio|pt-g|qa-a|qc(07|12|21|32|60|-[2-7]|i-)|qtek|r380|r600|raks|rim9|ro(ve|zo)|s55/|sa(ge|ma|mm|ms|ny|va)|sc(01|h-|oo|p-)|sdk/|se(c(-|0|1)|47|mc|nd|ri)|sgh-|shar|sie(-|m)|sk-0|sl(45|id)|sm(al|ar|b3|it|t5)|so(ft|ny)|sp(01|h-|v-|v )|sy(01|mb)|t2(18|50)|t6(00|10|18)|ta(gt|lk)|tcl-|tdg-|tel(i|m)|tim-|t-mo|to(pl|sh)|ts(70|m-|m3|m5)|tx-9|up(\.b|g1|si)|utst|v400|v750|veri|vi(rg|te)|vk(40|5[0-3]|-v)|vm40|voda|vulc|vx(52|53|60|61|70|80|81|83|85|98)|w3c(-| )|webc|whit|wi(g |nc|nw)|wmlb|wonu|x700|yas-|your|zeto|zte-}i.match?(ua[0..3])
+      mobile = @client_hints&.mobile?
+      @detect_mobile = mobile.nil? ? psp? || /zunewp7|crios/i.match?(ua) || mobile_user_agent? : mobile
+    end
+
+    private def mobile_user_agent?
+      return MOBILE_REGEX.match?(ua) || MOBILE_PREFIX_REGEX.match?(ua[0..3]) unless ua.ascii_only?
+
+      lowercase_ua = ua.downcase
+      MOBILE_LOWERCASE_REGEX.match?(lowercase_ua) ||
+        MOBILE_PREFIX_LOWERCASE_REGEX.match?(lowercase_ua)
     end
 
     private def platform

data/lib/browser/middleware/context.rb

@@ -10,7 +10,8 @@ module Browser
 
         @browser = Browser.new(
           request.user_agent,
-          accept_language: request.env["HTTP_ACCEPT_LANGUAGE"]
+          accept_language: request.env["HTTP_ACCEPT_LANGUAGE"],
+          headers: request.env
         )
       end
 

data/lib/browser/platform.rb

@@ -41,15 +41,23 @@ module Browser
       ]
     end
 
-    def initialize(ua)
+    def initialize(ua, client_hints: nil)
       @ua = ua
+      @client_hints = client_hints
+    end
+
+    # This platform, or one built with the client hints when they tell more
+    # than the user agent: the cached platform of a user agent ignores them.
+    def with_client_hints(client_hints)
+      hinted_class = client_hints.platform_class
+      return self unless hinted_class
+      return self if subject.instance_of?(hinted_class) && client_hints.platform_version.nil?
+
+      self.class.new(ua, client_hints:)
     end
 
     def subject
-      @subject ||= self.class.matchers.each do |matcher|
-        candidate = matcher.new(ua, self)
-        break candidate if candidate.match?
-      end
+      @subject ||= @client_hints&.platform_class&.new(ua, self) || detect_subject
     end
 
     def adobe_air?(expected_version = nil)
@@ -109,7 +117,7 @@ module Browser
     end
 
     def version
-      subject.version
+      @version ||= hinted_version || subject.version
     end
 
     def name
@@ -163,7 +171,12 @@ module Browser
     end
 
     def windows10?
-      windows? && ua.include?("Windows NT 10")
+      windows? && ua.include?("Windows NT 10") && !windows11?
+    end
+
+    # Only the client hints tell Windows 11 apart (ClientHints#windows11?).
+    def windows11?
+      windows? && version == "11"
     end
 
     def windows_rt?
@@ -187,6 +200,20 @@ module Browser
       windows? && ua.include?("Touch")
     end
 
+    private def detect_subject
+      self.class.matchers.each do |matcher|
+        candidate = matcher.new(ua, self)
+        break candidate if candidate.match?
+      end
+    end
+
+    private def hinted_version
+      return unless @client_hints&.platform_class
+      return @client_hints.platform_version unless id == :windows
+
+      "11" if @client_hints.windows11?
+    end
+
     private :subject
     private :ua
   end

data/lib/browser/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module Browser
-  VERSION = "1.0.0"
+  VERSION = "2.0.0"
 end

data/lib/browserx.rb

@@ -1,3 +1,3 @@
 # frozen_string_literal: true
 
-require "browser"
+require_relative "browser"

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: browserx
 version: !ruby/object:Gem::Version
-  version: 1.0.0
+  version: 2.0.0
 platform: ruby
 authors:
 - Nando Vieira
@@ -114,14 +114,14 @@ dependencies:
     requirements:
     - - ">="
       - !ruby/object:Gem::Version
-        version: '0'
+        version: '1.0'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
       - !ruby/object:Gem::Version
-        version: '0'
+        version: '1.0'
 description: 'A drop-in replacement for the browser gem: the same Browser API and
   require paths, answering nearly twice as fast with half the allocations.'
 executables: []
@@ -131,7 +131,9 @@ files:
 - CHANGELOG.md
 - LICENSE.md
 - README.md
+- bot_categories.yml
 - bot_exceptions.yml
+- bot_ip_ranges.yml
 - bots.yml
 - languages.yml
 - lib/browser.rb
@@ -143,11 +145,16 @@ files:
 - lib/browser/blackberry.rb
 - lib/browser/bot.rb
 - lib/browser/bot/empty_user_agent_matcher.rb
+- lib/browser/bot/ip_ranges.rb
 - lib/browser/bot/keyword_matcher.rb
 - lib/browser/bot/known_bots_matcher.rb
 - lib/browser/browser.rb
+- lib/browser/cache.rb
 - lib/browser/chrome.rb
+- lib/browser/client_hints.rb
+- lib/browser/cloudflare.rb
 - lib/browser/detect_version.rb
+- lib/browser/detection.rb
 - lib/browser/device.rb
 - lib/browser/device/android.rb
 - lib/browser/device/base.rb
@@ -261,7 +268,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 4.0.23
+rubygems_version: 4.0.20
 specification_version: 4
 summary: 'Browser detection for Ruby: the browser gem''s API, faster'
 test_files: []