double_agent 0.0.1 → 0.0.3

data/CHANGELOG

@@ -0,0 +1,17 @@
+== Release 0.0.3 (May 6, 2011)
+
+* Fixed bug from 0.0.2 in Ruby 1.8 where browser versions never got parsed
+
+== Release 0.0.2 (May 6, 2011)
+
+* Fixed detection for some versions of Windows XP and Opera
+
+* Added detection for Windows 8, Fedora, Slackware, FreeBSD, BlackBerry, Konqueror, Epiphany
+
+* Added parsing tests for each detectable OS and browser
+
+* Misc. minor internal refactoring and bug fixes
+
+== Release 0.0.1 (April 30, 2011) **
+
+* Initial release

data/README.rdoc

@@ -0,0 +1,118 @@
+= Double Agent
+
+double_agent is a library for parsing browser and operating system info out of user 
+agent strings. It is designed for parsing large sets for review or analysis.
+
+    # Load core, resources and stats
+    require 'double_agent'
+
+    # Load pieces individually
+    require 'double_agent/core'
+    require 'double_agent/resources'
+    require 'double_agent/stats'
+    require 'double_agent/logs'
+
+    # Load everything at once
+    require 'double_agent/all'
+
+= Core
+
+The core parser.
+
+    ua_string = "pretent I'm a user agent string for Firefox 4 on Ubuntu"
+
+    DoubleAgent.browser(ua_string)
+    => "Firefox 4"
+
+    DoubleAgent.browser_family(ua_string)
+    => "Firefox"
+
+    DoubleAgent.browser_sym(ua_string)
+    => :firefox
+
+    DoubleAgent.browser_family_sym(ua_string)
+    => :firefox
+
+    DoubleAgent.os(ua_string)
+    => "Ubuntu"
+
+    DoubleAgent.os_family(ua_string)
+    => "GNU/Linux"
+
+    DoubleAgent.os_sym(ua_string)
+    => :ubuntu
+
+    DoubleAgent.os_family_sym(ua_string)
+    => :linux
+
+= Resources
+
+Say you're saving a record of each user's login so you can determine their favorite browser. Just make sure
+the user agent is available through user_agent, and presto!
+
+    class Login
+      include DoubleAgent::Resource
+
+      def user_agent
+        #returns this object's user agent string
+      end
+    end
+
+    login = Login.find(76)
+
+    login.browser
+    => "Firefox 4"
+
+    login.os_family
+    => "OS X"
+
+= Stats
+
+Figure out what percent use which browser, browser family, os, etc.
+
+== Example 1
+
+    logins = Login.all
+    stats = DoubleAgent.percentages_for(logins, :browser)
+
+    p stats
+    => [["Firefox 4", 20.0], ["Internet Explorer 8", 18.0], ...]
+
+    stats.each do |browser, percent|
+      puts "#{browser} - #{percent}%"
+    end
+
+== Example 2
+
+    logins = Login.all
+    stats = DoubleAgent.percentages_for(logins, :browser_family, :os_family)
+
+    p stats
+    => [["Firefox", "Windows", 50.0], ["Internet Explorer", "Windows", 20.0], ["Safari", "OS X", 20.0], ["Firefox", "GNU/Linux", 10.0]]
+
+    stats.each do |browser_family, os_family, percent|
+      puts "#{browser_family} on #{os_family} - #{percent}%"
+    end
+
+= Logs
+
+DoubleAgent#log_entries parses through Apache and Nginx access logs, instantiating each log line into a LogEntry
+object. It even reads gzipped logs (requires zlib)! The LogEntry class mixes in DoubleAgent::Resource, so this is
+a great way to generate browser and OS breakdowns of who's visiting your site.
+
+    require 'double_agent'
+    require 'double_agent/logs'
+
+    entries = DoubleAgent.log_entries("/var/log/nginx/my-site.access.log*")
+    entries.each do |entry|
+      puts entry.browser
+    end
+
+    Firefox 3
+    Internet Explorer 8
+    Internet Explorer 9
+    Firefox 4
+    Internet Explorer
+    Safari
+    Chrome
+    ...

data/data/browsers.yml

@@ -3,18 +3,10 @@
 
 - :name: Internet Explorer %s
   :sym: :msie
-  :family_sym: :msie
   :regex: 'msie \d+'
   :version: '(?<=msie )[0-9]+'
   :safe_version: ["msie [0-9]+", "[0-9]+"]
 
-- :name: Chromium %s
-  :sym: :chromium
-  :family_sym: :chromium
-  :regex: 'chromium/\d+'
-  :version: '(?<=chromium/)[0-9]+'
-  :safe_version: ["chromium/[0-9]+", "[0-9]+"]
-
 - :name: Chrome %s
   :sym: :chrome
   :family_sym: :chromium
@@ -22,6 +14,12 @@
   :version: '(?<=chrome/)[0-9]+'
   :safe_version: ["chrome/[0-9]+", "[0-9]+"]
 
+- :name: Chromium %s
+  :sym: :chromium
+  :regex: 'chromium/\d+'
+  :version: '(?<=chromium/)[0-9]+'
+  :safe_version: ["chromium/[0-9]+", "[0-9]+"]
+
 - :name: Android %s
   :sym: :android
   :family_sym: :chromium
@@ -29,29 +27,39 @@
   :version: '(?<=android )[0-9]+(\.[0-9]+)?'
   :safe_version: ["android [0-9]+(\.[0-9]+)?", "[0-9]+(\.[0-9]+)?"]
 
+- :name: BlackBerry
+  :sym: :blackberry
+  :regex: blackberry
+
+- :name: Epiphany
+  :sym: :epiphany
+  :regex: epiphany
+  :version: '(?<=epiphany/)[0-9]+'
+  :safe_version: ["epiphany/[0-9]+", "[0-9]+"]
+
 - :name: Safari %s
   :sym: :safari
-  :family_sym: :safari
   :regex: safari
   :version: '(?<=version/)[0-9]+'
   :safe_version: ["version/[0-9]+", "[0-9]+"]
 
 - :name: Opera %s
   :sym: :opera
-  :family_sym: :opera
   :regex: opera
-  :version: '(?<=version/)[0-9]+'
-  :safe_version: ["version/[0-9]+", "[0-9]+"]
+  :version: '((?<=version/)[0-9]+)|((?<=opera )[0-9]+)'
+  :safe_version: ["(version/[0-9]+)|(opera [0-9]+)", "[0-9]+"]
+
+- :name: Konqueror
+  :sym: :konqueror
+  :regex: konqueror
 
 - :name: Firefox %s
   :sym: :firefox
-  :family_sym: :firefox
   :regex: firefox
   :version: '(?<=firefox/)[0-9]+'
   :safe_version: ["firefox/[0-9]+", "[0-9]+"]
 
 - :name: Unknown
   :sym: :unknown
-  :family_sym: :unkown
   :regex: .+
   :version: .+

data/data/oses.yml

@@ -8,11 +8,24 @@
   :family_sym: :linux
   :regex: ubuntu
 
+- :name: Fedora
+  :sym: :fedora
+  :family_sym: :linux
+  :regex: fedora
+
+- :name: Slackware
+  :sym: :slackware
+  :family_sym: :linux
+  :regex: slackware
+
 - :name: GNU/Linux
   :sym: :linux
-  :family_sym: :linux
   :regex: linux
 
+- :name: FreeBSD
+  :sym: :freebsd
+  :regex: freebsd
+
 - :name: iOS
   :sym: :ios
   :family_sym: :osx
@@ -20,13 +33,18 @@
 
 - :name: OS X
   :sym: :osx
-  :family_sym: :osx
   :regex: macintosh
 
-- :name: Windows XP
-  :sym: :windows_xp
+- :name: Windows 8
+  :sym: :windows_8
+  :family_sym: :windows
+  :regex: windows nt 6\.2
+  :icon: windows
+
+- :name: Windows 7
+  :sym: :windows_7
   :family_sym: :windows
-  :regex: windows nt 5\.1
+  :regex: windows nt 6\.1
   :icon: windows
 
 - :name: Windows Vista
@@ -35,18 +53,20 @@
   :regex: windows nt 6\.0
   :icon: windows
 
-- :name: Windows 7
-  :sym: :windows_7
+- :name: Windows XP
+  :sym: :windows_xp
   :family_sym: :windows
-  :regex: windows nt 6\.1
+  :regex: windows nt 5\.[12]
   :icon: windows
 
 - :name: Windows
   :sym: :windows
-  :family_sym: :windows
   :regex: windows
 
-- :family: Unknown
+- :name: BlackBerry
+  :sym: :blackberry
+  :regex: blackberry
+
+- :name: Unknown
   :sym: :unknown
-  :name: Unknown
   :regex: .+

data/lib/double_agent/core.rb

@@ -1,50 +1,60 @@
 require 'yaml'
 
 module DoubleAgent
-  # 
-  # Map browser/os ids to names, families and icons
-  # 
+  # An array of "browser knowledge hashes," the basis of browser parsing. You may edit this data and call load_browsers! to customize parsing.
   BROWSER_DATA = YAML.load_file(File.expand_path('../../../data/browsers.yml', __FILE__))
+
+  # An array of "OS knowledge hashes," the basis of OS parsing. You may edit this data and call load_oses! to customize parsing.
   OS_DATA = YAML.load_file(File.expand_path('../../../data/oses.yml', __FILE__))
 
+  # An array of BrowserParser objects created from the data in BROWSER_DATA.
   BROWSERS = {}
+
+  # An array of OSParser objects created from the data in OS_DATA.
   OSES = {}
 
+  # Each browser in BROWSER_DATA gets its own BrowserParser object. These 
+  # parser objects are then used to parse specific data out of a user agent string.
+
   class BrowserParser
     BLANK = ''
     MIN_VERSION = '1.9.2'
     attr_reader :sym, :family_sym, :icon
 
+    # Instantiate a new BrowserParser using a "browser family" element from BROWSER_DATA
     def initialize(attrs={})
-      @family_sym = attrs[:family_sym]
-      @name = attrs[:name]
       @sym = attrs[:sym]
+      @family_sym = attrs[:family_sym] || @sym
+      @name = attrs[:name]
       @icon = attrs[:icon] || @sym
       if RUBY_VERSION < MIN_VERSION and attrs[:safe_version]
         @safe_version = attrs[:safe_version].map { |r| Regexp.new r, Regexp::IGNORECASE }
-      else
+      elsif attrs[:version]
         @version = Regexp.new(attrs[:version], Regexp::IGNORECASE)
       end
     end
 
+    # Returns the browser's name. If you provide an user agent string as an argument,
+    # it will attempt to also return the major version number. E.g. "Firefox 4".
     def browser(ua=nil)
-      if ua
+      if ua and (@version or @safe_version)
         @name % version(ua)
       else
         (@name % BLANK).rstrip
       end
     end
 
-    def icon
-      @icon || @sym
-    end
-
+    # Returns the BrowserParser for this BrowserParser object's Family. E.g. the Chrome 
+    # BrowserParser would return the Chromium BrowserParser. For browsers that are their 
+    # own family (e.g. Firefox, IE) it will end up returning itself.
     def family
       BROWSERS[family_sym]
     end
     
     private
 
+    # Attempts to parse and return the browser's version from a user agent string. Returns
+    # nil if nothing is found.
     def version(ua)
       if @safe_version and RUBY_VERSION < MIN_VERSION
         ua.slice(@safe_version[0]).slice(@safe_version[1])
@@ -54,81 +64,101 @@ module DoubleAgent
     end
   end
 
+  # Each OS in OS_DATA gets its own OSParser object. In theory, these parser
+  # objects can then be used to grab further info from user agent strings, though
+  # that is not currently happening.
+
   class OSParser
     attr_reader :os, :sym, :family_sym, :icon
 
+    # Instantiate a new OSParser using an "OS family" element from OS_DATA
     def initialize(attrs={})
-      @family_sym = attrs[:family_sym]
-      @os = attrs[:name]
       @sym = attrs[:sym]
+      @family_sym = attrs[:family_sym] || @sym
+      @os = attrs[:name]
       @icon = attrs[:icon] || @sym
     end
 
+    # Returns the OSParser for this OSParser object's Family. E.g. the Ubuntu
+    # OSParser would return the GNU/Linux OSerParser. For OSes that are their own
+    # family (e.g. OS X) it will end up returning itself.
     def family
       OSES[family_sym]
     end
   end
 
-  # 
-  # Methods for getting browser/os names, families, and icons either by passing a user agent string.
-  # 
-
+  # Returns the browser's name, possibly including the version number, e.g. "Chrome 12"
   def self.browser(ua)
     browser_parser(ua).browser(ua)
   end
 
+  # Returns the browser's symbol name, e.g. :chrome
   def self.browser_sym(user_agent)
+    # This method is overwitten by load_browsers!
   end
 
+  # Returns the browser's icon name, e.g. :chrome
   def self.browser_icon(ua)
     browser_parser(ua).icon
   end
 
+  # Returns the browser's family name, e.g. "Chromium"
   def self.browser_family(ua)
     browser_parser(ua).family.browser
   end
 
+  # Returns the browser's family's symbol name, e.g. :chromium
   def self.browser_family_sym(ua)
     browser_parser(ua).family_sym
   end
 
+  # Returns the browser's family's icon name, e.g. :chromium
   def self.browser_family_icon(ua)
     browser_parser(ua).family.icon
   end
 
+  # Returns the OS's name, e.g. "Ubuntu"
   def self.os(ua)
     os_parser(ua).os
   end
 
+  # Returns the OS's symbol name, e.g. :ubuntu
   def self.os_sym(user_agent)
+    # This method is overwitten by load_oses!
   end
 
+  # Returns the OS's icon name, e.g. :ubuntu
   def self.os_icon(ua)
     os_parser(ua).icon
   end
 
+  # Returns the OS's family, e.g. "GNU/Linux"
   def self.os_family(ua)
     os_parser(ua).family.os
   end
 
+  # Returns the OS's family's symbol name, e.g. :linux
   def self.os_family_sym(ua)
     os_parser(ua).family_sym
   end
 
+  # Returns the OS's family's symbol icon, e.g. :linux
   def self.os_family_icon(ua)
     os_parser(ua).family.icon
   end
 
-  # Get a browser parser with either a user agent or symbol
+  # Returns the correct BrowerParser for the given user agent or symbol
   def self.browser_parser(ua_or_sym)
     BROWSERS[ua_or_sym.is_a?(Symbol) ? ua_or_sym : browser_sym(ua_or_sym)]
   end
 
-  # Get an OS parser with either a user agent or symbol
+  # Returns the correct OSParser for the given user agent or symbol
   def self.os_parser(ua_or_sym)
     OSES[ua_or_sym.is_a?(Symbol) ? ua_or_sym : os_sym(ua_or_sym)]
   end
 
+  # Parses BROWSER_DATA into BROWSERS, a hash of BrowserParser objects indexed by their symbol names.
+  # Parses and evals BROWSER_DATA into a case statement inside of the browser_sym method.
   def self.load_browsers!
     BROWSERS.clear
     str = "case user_agent\n"
@@ -140,6 +170,8 @@ module DoubleAgent
     module_eval "def self.browser_sym(user_agent); #{str}; end"
   end
 
+  # Parses OS_DATA into OSES, a hash of OSParser objects indexed by their symbol names.
+  # Parses and evals OS_DATA into a case statement inside of the os_sym method.
   def self.load_oses!
     OSES.clear
     str = "case user_agent\n"

data/lib/double_agent/logs.rb

@@ -1,6 +1,11 @@
 require 'zlib'
 
 module DoubleAgent
+  # Accepts a glob path like /var/logs/apache/my-site.access.log*,
+  # parses all matching files into an array of LegEntry objects, and returns them.
+  #
+  # If a Regexp is passed as the second argument, lines which do not match
+  # it will be ignored.
   def self.log_entries(glob_str, regex=nil)
     entries, gz_regexp = [], /\.gz\Z/i
     Dir.glob(glob_str).each do |f|
@@ -14,12 +19,20 @@ module DoubleAgent
     entries
   end
 
+  # This class represents a line in an Apache or Nginx access log.
+  # The user agent string is parsed out and available through the
+  # user_agent attribute, making it available to the mixed-in DoubleAgent::Resource.
+
   class LogEntry
+    # Regular expression for pulling a user agent string out of a log entry
     USER_AGENT_REGEXP = /[^"]+(?="$)/
     include DoubleAgent::Resource
 
+    # Returns the user agent string
     attr_reader :user_agent
 
+    # Initializes a new LogEntry object. An Apache or Nginx log line should be
+    # passed to it.
     def initialize(line)
       #@line = line
       @user_agent = line.slice(USER_AGENT_REGEXP)

data/lib/double_agent/resources.rb

@@ -1,63 +1,77 @@
 module DoubleAgent
   # 
-  # Any class with a "user_agent" method which returns a User Agent string
+  # Any class with a "user_agent" method returning a User Agent string
   # may include this module to easily parse out Browser and OS info.
   # 
   module Resource
+    # Return's this object's browser name
     def browser
       _browser_parser.browser(user_agent)
     end
 
+    # Return's this object's browser symbol name
     def browser_sym
       _browser_parser.sym
     end
 
+    # Return's this object's browser icon name
     def browser_icon
       _browser_parser.icon
     end
 
+    # Return's this object's browser family name
     def browser_family
       _browser_parser.family.browser
     end
 
+    # Return's this object's browser family symbol name
     def browser_family_sym
       _browser_parser.family_sym
     end
 
+    # Return's this object's browser family icon name
     def browser_family_icon
       _browser_parser.family.icon
     end
 
+    # Return's this object's OS name
     def os
       _os_parser.os
     end
 
+    # Return's this object's OS symbol name
     def os_sym
       _os_parser.sym
     end
 
+    # Return's this object's OS icon name
     def os_icon
       _os_parser.icon
     end
 
+    # Return's this object's OS family name
     def os_family
       _os_parser.family.os
     end
 
+    # Return's this object's OS family symbol name
     def os_family_sym
       _os_parser.family_sym
     end
 
+    # Return's this object's OS family icon name
     def os_family_icon
       _os_parser.family.icon
     end
 
     private
 
+    # Returns and caches a BrowserParser for this object
     def _browser_parser
       @browser_parser ||= DoubleAgent.browser_parser(user_agent)
     end
 
+    # Returns and caches an OSParser for this object
     def _os_parser
       @os_parser ||= DoubleAgent.os_parser(user_agent)
     end

data/lib/double_agent/stats.rb

@@ -1,33 +1,29 @@
-# Time for some monkey patching!
-
 module DoubleAgent
+  # True if running under less than Ruby 1.9
   BAD_RUBY = RUBY_VERSION < '1.9.0'
 
   if BAD_RUBY
     require 'bigdecimal'
+    # If BAD_RUBY, this is used in lieu of the native round method
     def self.better_round(f, n)
       d = BigDecimal.new f.to_s
       d.round(n).to_f
     end
   end
 
-  # 
   # For the given "things", returns the share of the group that each attr has.
   # 
   # "things" is an array of objects who's classes "include DoubleAgent::Resource".
   # 
-  # "attrs" is one or more method symbols from DoubleAgent::Resource. The *_sym methods
-  # are probably the most useful here, as you can use the symbol results to query DoubleAgent 
-  # methods and get the browser/os name, family and icons.
+  # "attrs" is one or more method symbols from DoubleAgent::Resource.
   # 
   # Example, Browser Family share:
   # DoubleAgent.percentages_for(logins, :browser_family)
-  # => [['Firefox', 50.4], ['Chrome', 19.6], ['Internet Explorer', 15], ['Safari', 10], ['Unknown', 5]]
+  #   [['Firefox', 50.4], ['Chrome', 19.6], ['Internet Explorer', 15], ['Safari', 10], ['Unknown', 5]]
   # 
   # Example, Browser/OS share, asking for symbols back:
   # DoubleAgent.percentages_for(server_log_entries, :browser_sym, :os_sym)
-  # => [[:firefox_4, :windows_7, 50.4], [:firefox_3, :osx, 19.6], [:msie, :windows_xp, 15], [:safari, :osx, 10], [:other, :other, 5]]
-  # 
+  #   [[:firefox, :windows_7, 50.4], [:chrome, :osx, 19.6], [:msie, :windows_xp, 15], [:safari, :osx, 10], [:other, :other, 5]]
   def self.percentages_for(things, *attrs)
     p = {}
     things.each do |h|

data/spec/core_spec.rb

@@ -0,0 +1,81 @@
+require File.dirname(__FILE__) + '/spec_helper'
+
+describe DoubleAgent do
+  context 'Core' do
+    before do
+      @ua_string = 'Mozilla/5.0 (X11; Ubuntu Linux i686; rv:2.0) Gecko/20100101 Firefox/4.0'
+    end
+
+    #browser
+    it 'returns Firefox 4 for browser' do
+      DoubleAgent.browser(@ua_string).should == 'Firefox 4'
+    end
+    it 'returns Unknown for browser' do
+      DoubleAgent.browser('froofroo').should == 'Unknown'
+    end
+
+    #browser_sym
+    it 'returns :firefox for browser_sym' do
+      DoubleAgent.browser_sym(@ua_string).should == :firefox
+    end
+    it 'returns :unknown for browser_sym' do
+      DoubleAgent.browser_sym('froofroo').should == :unknown
+    end
+
+    #browser_family
+    it 'returns Firefox for browser family' do
+      DoubleAgent.browser_family(@ua_string).should == 'Firefox'
+    end
+
+    #browser_family_sym
+    it 'returns :firefox for browser_family_sym' do
+      DoubleAgent.browser_family_sym(@ua_string).should == :firefox
+    end
+
+    #browser_icon
+    it 'returns :firefox for browser_sym' do
+      DoubleAgent.browser_icon(@ua_string).should == :firefox
+    end
+
+    #browser_family_icon
+    it 'returns :firefox for browser_family_sym' do
+      DoubleAgent.browser_family_icon(@ua_string).should == :firefox
+    end
+
+    #os
+    it 'returns Ubuntua for OS' do
+      DoubleAgent.os(@ua_string).should == 'Ubuntu'
+    end
+    it 'returns Unknowna for OS' do
+      DoubleAgent.os('froofroo').should == 'Unknown'
+    end
+
+    #os_sym
+    it 'returns :ubuntu for os_sym' do
+      DoubleAgent.os_sym(@ua_string).should == :ubuntu
+    end
+    it 'returns :unknown for os_sym' do
+      DoubleAgent.os_sym('froofroo').should == :unknown
+    end
+
+    #os_family
+    it 'returns GNU/Linux OS family' do
+      DoubleAgent.os_family(@ua_string).should == 'GNU/Linux'
+    end
+
+    #os_family_sym
+    it 'returns :linux for os_family_sym' do
+      DoubleAgent.os_family_sym(@ua_string).should == :linux
+    end
+
+    #os_icon
+    it 'returns :ubuntu for os_sym' do
+      DoubleAgent.os_icon(@ua_string).should == :ubuntu
+    end
+
+    #os_family_icon
+    it 'returns :linux for os_family_sym' do
+      DoubleAgent.os_family_icon(@ua_string).should == :linux
+    end
+  end
+end

data/spec/data/httpd.access.log

@@ -0,0 +1,20 @@
+68.52.99.211 - - [05/May/2011:08:21:04 -0400] "GET / HTTP/1.1" 200 1312 "-" "Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10.6; en-US; rv:1.9.2.17) Gecko/20110420 Firefox/3.6.17"
+68.52.99.211 - - [05/May/2011:08:25:47 -0400] "POST /entries HTTP/1.1" 200 7889 "http://www.example.com/entries/new" "Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10.6; en-US; rv:1.9.2.17) Gecko/20110420 Firefox/3.6.17"
+216.84.130.30 - - [04/May/2011:09:45:42 -0400] "GET /dashboard HTTP/1.1" 302 104 "-" "Mozilla/5.0 (iPhone; U; CPU iPhone OS 4_2_6 like Mac OS X; en-us) AppleWebKit/533.17.9 (KHTML, like Gecko) Version/5.0.2 Mobile/8E200 Safari/6533.18.5"
+173.190.91.2 - - [04/May/2011:10:51:09 -0400] "GET /images/icons/opera_browser.png?1295928127 HTTP/1.1" 304 0 "http://cur8.cur8.net/sbin/sites/2/page_hit_stats" "Mozilla/5.0 (X11; Linux i686; rv:2.0.1) Gecko/20100101 Firefox/4.0.1"
+173.190.91.2 - - [04/May/2011:10:51:09 -0400] "GET /images/icons/ubuntu_os.png?1295928127 HTTP/1.1" 304 0 "http://cur8.cur8.net/sbin/sites/2/page_hit_stats" "Mozilla/5.0 (X11; Linux i686; rv:2.0.1) Gecko/20100101 Firefox/4.0.1"
+173.190.91.2 - - [04/May/2011:10:52:29 -0400] "GET /sbin/sites/2/login_stats HTTP/1.1" 200 10131 "http://cur8.cur8.net/sbin/sites/2/page_hit_stats" "Mozilla/5.0 (X11; Linux i686; rv:2.0.1) Gecko/20100101 Firefox/4.0.1"
+173.190.91.2 - - [04/May/2011:10:52:34 -0400] "GET /sbin/sites/2/page_hit_stats HTTP/1.1" 200 12460 "http://cur8.cur8.net/sbin/sites/2/login_stats" "Mozilla/5.0 (X11; Linux i686; rv:2.0.1) Gecko/20100101 Firefox/4.0.1"
+bad log line!
+173.190.91.2 - - [04/May/2011:10:53:10 -0400] "GET /sbin/sites/2 HTTP/1.1" 304 0 "http://cur8.cur8.net/sbin/sites/2/page_hit_stats" "Mozilla/5.0 (X11; Linux i686; rv:2.0.1) Gecko/20100101 Firefox/4.0.1"
+216.84.130.30 - - [04/May/2011:11:11:39 -0400] "GET /login HTTP/1.1" 200 1104 "-" "Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 5.1; Trident/4.0; .NET CLR 2.0.50727; .NET CLR 3.0.04506.648; .NET CLR 3.5.21022; .NET CLR 3.0.4506.2152; .NET CLR 3.5.30729)"
+216.84.130.30 - - [04/May/2011:11:11:39 -0400] "GET /stylesheets/styles.css?1303352447 HTTP/1.1" 304 0 "http://www.example.com/login" "Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 5.1; Trident/4.0; .NET CLR 2.0.50727; .NET CLR 3.0.04506.648; .NET CLR 3.5.21022; .NET CLR 3.0.4506.2152; .NET CLR 3.5.30729)"
+216.84.130.30 - - [04/May/2011:11:11:39 -0400] "GET /javascripts/lib.js?1303099416 HTTP/1.1" 304 0 "http://www.example.com/login" "Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 5.1; Trident/4.0; .NET CLR 2.0.50727; .NET CLR 3.0.04506.648; .NET CLR 3.5.21022; .NET CLR 3.0.4506.2152; .NET CLR 3.5.30729)"
+216.84.130.30 - - [04/May/2011:11:11:39 -0400] "GET /stylesheets/print.css?1290464093 HTTP/1.1" 304 0 "http://www.example.com/login" "Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 5.1; Trident/4.0; .NET CLR 2.0.50727; .NET CLR 3.0.04506.648; .NET CLR 3.5.21022; .NET CLR 3.0.4506.2152; .NET CLR 3.5.30729)"
+bad log line!
+216.84.130.30 - - [04/May/2011:11:11:39 -0400] "GET /javascripts/application.js?1303352447 HTTP/1.1" 304 0 "http://www.example.com/login" "Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 5.1; Trident/4.0; .NET CLR 2.0.50727; .NET CLR 3.0.04506.648; .NET CLR 3.5.21022; .NET CLR 3.0.4506.2152; .NET CLR 3.5.30729)"
+75.201.10.91 - - [04/May/2011:18:37:10 -0400] "GET /entries/new HTTP/1.1" 302 104 "-" "Mozilla/5.0 (Linux; U; Android 2.2.1; en-us; ADR6400L 4G Build/FRG83D) AppleWebKit/533.1 (KHTML, like Gecko) Version/4.0 Mobile Safari/533.1"
+75.201.10.91 - - [04/May/2011:18:37:10 -0400] "GET /login HTTP/1.1" 200 1107 "-" "Mozilla/5.0 (Linux; U; Android 2.2.1; en-us; ADR6400L 4G Build/FRG83D) AppleWebKit/533.1 (KHTML, like Gecko) Version/4.0 Mobile Safari/533.1"
+75.201.10.91 - - [04/May/2011:18:43:33 -0400] "GET /dashboard HTTP/1.1" 200 8098 "http://www.example.com/login" "Mozilla/5.0 (Linux; U; Android 2.2.1; en-us; ADR6400L 4G Build/FRG83D) AppleWebKit/533.1 (KHTML, like Gecko) Version/4.0 Mobile Safari/533.1"
+75.201.10.91 - - [04/May/2011:18:43:55 -0400] "GET /search HTTP/1.1" 200 4070 "http://www.example.com/dashboard" "Mozilla/5.0 (Linux; U; Android 2.2.1; en-us; ADR6400L 4G Build/FRG83D) AppleWebKit/533.1 (KHTML, like Gecko) Version/4.0 Mobile Safari/533.1"
+bad log line!

data/spec/parser_spec.rb

@@ -0,0 +1,100 @@
+require File.dirname(__FILE__) + '/spec_helper'
+
+DA = DoubleAgent
+
+describe DoubleAgent do
+  # Internet Explorer
+  it 'should be Internet Explorer 10 on Windows 8' do
+    ua = "Mozilla/5.0 (compatible; MSIE 10.0; Windows NT 6.2; Win64; x64; Trident/5.0"
+    "#{DA.browser ua} on #{DA.os ua}".should == 'Internet Explorer 10 on Windows 8'
+  end
+
+  it 'should be Internet Explorer 9 on Windows 7' do
+    ua = "Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Win64; x64; Trident/5.0"
+    "#{DA.browser ua} on #{DA.os ua}".should == 'Internet Explorer 9 on Windows 7'
+  end
+
+  it 'should be Internet Explorer 8 on Windows Vista' do
+    ua = "Mozilla/5.0 (compatible; MSIE 8.0; Windows NT 6.0; Win64; x64; Trident/5.0"
+    "#{DA.browser ua} on #{DA.os ua}".should == 'Internet Explorer 8 on Windows Vista'
+  end
+
+  it 'should be Internet Explorer 7 on Windows XP' do
+    ua = "Mozilla/5.0 (compatible; MSIE 7.0; Windows NT 5.2; Win64; x64; Trident/5.0"
+    "#{DA.browser ua} on #{DA.os ua}".should == 'Internet Explorer 7 on Windows XP'
+  end
+
+  it 'should be Internet Explorer 7 on Windows XP' do
+    ua = "Mozilla/5.0 (compatible; MSIE 7.0; Windows NT 5.1; Win64; x64; Trident/5.0"
+    "#{DA.browser ua} on #{DA.os ua}".should == 'Internet Explorer 7 on Windows XP'
+  end
+
+  # Chrome
+  it 'should be Chrome 12 on Windows XP' do
+    ua = "Mozilla/5.0 (Windows NT 5.1) AppleWebKit/534.25 (KHTML, like Gecko) Chrome/12.0.706.0 Safari/534.25"
+    "#{DA.browser ua} on #{DA.os ua}".should == 'Chrome 12 on Windows XP'
+  end
+
+  # Chromium
+  it 'should be Chrome 12 on Ubuntu' do
+    ua = "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/534.24 (KHTML, like Gecko) Ubuntu/10.10 Chromium/12.0.703.0 Chrome/12.0.703.0 Safari/534.24"
+    "#{DA.browser ua} on #{DA.os ua}".should == 'Chrome 12 on Ubuntu'
+  end
+
+  # Android
+  it 'should be Android 2.3 on Android' do
+    ua = "Mozilla/5.0 (Linux; U; Android 2.3.3; zh-tw; HTC_Pyramid Build/GRI40) AppleWebKit/533.1 (KHTML, like Gecko) Version/4.0 Mobile Safari/533.1"
+    "#{DA.browser ua} on #{DA.os ua}".should == 'Android 2.3 on Android'
+  end
+
+  # Safari
+  it 'should be Safari 5 on OS X' do
+    ua = "Mozilla/5.0 (Macintosh; U; PPC Mac OS X 10_5_8; zh-cn) AppleWebKit/533.20.25 (KHTML, like Gecko) Version/5.0.4 Safari/533.20.27"
+    "#{DA.browser ua} on #{DA.os ua}".should == 'Safari 5 on OS X'
+  end
+
+  # Opera
+  it 'should be Opera 11 on GNU/Linux' do
+    ua = "Opera/9.80 (X11; Linux x86_64; U; pl) Presto/2.7.62 Version/11.00"
+    "#{DA.browser ua} on #{DA.os ua}".should == 'Opera 11 on GNU/Linux'
+  end
+
+  it 'should be Opera 11 on Windows 7' do
+    ua = "Mozilla/5.0 (Windows NT 6.1; U; nl; rv:1.9.1.6) Gecko/20091201 Firefox/3.5.6 Opera 11.01"
+    "#{DA.browser ua} on #{DA.os ua}".should == 'Opera 11 on Windows 7'
+  end
+
+  # Firefox
+  it 'should be Firefox 4 on GNU/Linux' do
+    ua = "Mozilla/5.0 (X11; U; Linux x86_64; pl-PL; rv:2.0) Gecko/20110307 Firefox/4.0"
+    "#{DA.browser ua} on #{DA.os ua}".should == 'Firefox 4 on GNU/Linux'
+  end
+
+  # Epiphany
+  it 'should be Epiphany on GNU/Linux' do
+    ua = "Mozilla/5.0 (X11; U; Linux x86_64; fr-FR) AppleWebKit/534.7 (KHTML, like Gecko) Epiphany/2.30.6 Safari/534.7"
+    "#{DA.browser ua} on #{DA.os ua}".should == 'Epiphany on GNU/Linux'
+  end
+
+  # Konqueror
+  it 'should be Konqueror on FreeBSD' do
+    ua = "Mozilla/5.0 (compatible; Konqueror/4.5; FreeBSD) KHTML/4.5.4 (like Gecko)"
+    "#{DA.browser ua} on #{DA.os ua}".should == 'Konqueror on FreeBSD'
+  end
+
+  it 'should be Konqueror on Fedora' do
+    ua = "Mozilla/5.0 (compatible; Konqueror/4.4; Linux) KHTML/4.4.1 (like Gecko) Fedora/4.4.1-1.fc12"
+    "#{DA.browser ua} on #{DA.os ua}".should == 'Konqueror on Fedora'
+  end
+
+  it 'should be Konqueror on Slackware' do
+    ua = "Mozilla/5.0 (compatible; Konqueror/4.2; Linux) KHTML/4.2.4 (like Gecko) Slackware/13.0"
+    "#{DA.browser ua} on #{DA.os ua}".should == 'Konqueror on Slackware'
+  end
+
+  # BlackBerry
+  it 'should be BlackBerry on BlackBerry' do
+    ua = "Mozilla/5.0 (BlackBerry; U; BlackBerry 9800; zh-TW) AppleWebKit/534.8+ (KHTML, like Gecko) Version/6.0.0.448 Mobile Safari/534.8+"
+    "#{DA.browser ua} on #{DA.os ua}".should == 'BlackBerry on BlackBerry'
+  end
+end

data/spec/resources_spec.rb

@@ -0,0 +1,78 @@
+require File.dirname(__FILE__) + '/spec_helper'
+
+class Login
+  include DoubleAgent::Resource
+  attr_accessor :user_agent
+
+  def initialize(ua)
+    @user_agent = ua
+  end
+end
+
+describe DoubleAgent do
+  context 'Resource' do
+    before do
+      @login = Login.new 'Mozilla/5.0 (X11; Ubuntu Linux i686; rv:2.0) Gecko/20100101 Firefox/4.0'
+    end
+
+    #browser
+    it 'returns Firefox 4 for browser' do
+      @login.browser.should == 'Firefox 4'
+    end
+
+    #browser_sym
+    it 'returns :firefox for browser_sym' do
+      @login.browser_sym.should == :firefox
+    end
+
+    #browser_family
+    it 'returns Firefox for browser family' do
+      @login.browser_family.should == 'Firefox'
+    end
+
+    #browser_family_sym
+    it 'returns :firefox for browser_family_sym' do
+      @login.browser_family_sym.should == :firefox
+    end
+
+    #browser_icon
+    it 'returns :firefox for browser_sym' do
+      @login.browser_icon.should == :firefox
+    end
+
+    #browser_family_icon
+    it 'returns :firefox for browser_family_sym' do
+      @login.browser_family_icon.should == :firefox
+    end
+
+    #os
+    it 'returns Ubuntua for OS' do
+      @login.os.should == 'Ubuntu'
+    end
+
+    #os_sym
+    it 'returns :ubuntu for os_sym' do
+      @login.os_sym.should == :ubuntu
+    end
+
+    #os_family
+    it 'returns GNU/Linux OS family' do
+      @login.os_family.should == 'GNU/Linux'
+    end
+
+    #os_family_sym
+    it 'returns :linux for os_family_sym' do
+      @login.os_family_sym.should == :linux
+    end
+
+    #os_icon
+    it 'returns :ubuntu for os_sym' do
+      @login.os_icon.should == :ubuntu
+    end
+
+    #os_family_icon
+    it 'returns :linux for os_family_sym' do
+      @login.os_family_icon.should == :linux
+    end
+  end
+end

data/spec/spec_helper.rb

@@ -0,0 +1,9 @@
+require 'rspec'
+require File.dirname(__FILE__) + '/../lib/double_agent/core'
+require File.dirname(__FILE__) + '/../lib/double_agent/resources'
+require File.dirname(__FILE__) + '/../lib/double_agent/stats'
+require File.dirname(__FILE__) + '/../lib/double_agent/logs'
+
+Rspec.configure do |c|
+  c.mock_with :rspec
+end

data/spec/stats_spec.rb

@@ -0,0 +1,22 @@
+require File.dirname(__FILE__) + '/spec_helper'
+
+log_glob = File.dirname(__FILE__) + '/data/*.access.log*'
+entries = DoubleAgent::log_entries(log_glob, /^\d/)
+
+describe DoubleAgent do
+  context 'Logs' do
+    it 'should have loaded n log entries' do
+      entries.size.should == 47
+    end
+  end
+
+  context 'Stats' do
+    stats = DoubleAgent.percentages_for entries, :browser_family, :os_family
+    answer = [["Internet Explorer", "Windows", 42.55],
+              ["Chromium", "GNU/Linux", 40.43],
+              ["Firefox", "GNU/Linux", 10.64],
+              ["Firefox", "OS X", 4.26],
+              ["Safari", "OS X", 2.13]]
+    stats.should == answer
+  end
+end

metadata

@@ -1,13 +1,8 @@
 --- !ruby/object:Gem::Specification 
 name: double_agent
 version: !ruby/object:Gem::Version 
-  hash: 29
-  prerelease: false
-  segments: 
-  - 0
-  - 0
-  - 1
-  version: 0.0.1
+  prerelease: 
+  version: 0.0.3
 platform: ruby
 authors: 
 - Jordan Hollinger
@@ -15,8 +10,7 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2011-04-30 00:00:00 -04:00
-default_executable: 
+date: 2011-04-30 00:00:00 Z
 dependencies: []
 
 description: Browser User Agent string parser with resource, stats, and a log reader
@@ -25,19 +19,28 @@ executables: []
 
 extensions: []
 
-extra_rdoc_files: []
-
+extra_rdoc_files: 
+- README.rdoc
+- CHANGELOG
 files: 
-- lib/double_agent.rb
 - lib/double_agent/all.rb
-- lib/double_agent/stats.rb
-- lib/double_agent/resources.rb
 - lib/double_agent/core.rb
+- lib/double_agent/resources.rb
 - lib/double_agent/logs.rb
-- data/browsers.yml
+- lib/double_agent/stats.rb
+- lib/double_agent.rb
 - data/oses.yml
+- data/browsers.yml
+- spec/resources_spec.rb
+- spec/core_spec.rb
+- spec/spec_helper.rb
+- spec/parser_spec.rb
+- spec/data/httpd.access.log
+- spec/data/httpd.access.log.1.gz
+- spec/stats_spec.rb
+- README.rdoc
 - LICENSE
-has_rdoc: true
+- CHANGELOG
 homepage: http://github.com/jhollinger/double_agent
 licenses: []
 
@@ -51,23 +54,17 @@ required_ruby_version: !ruby/object:Gem::Requirement
   requirements: 
   - - ">="
     - !ruby/object:Gem::Version 
-      hash: 3
-      segments: 
-      - 0
       version: "0"
 required_rubygems_version: !ruby/object:Gem::Requirement 
   none: false
   requirements: 
   - - ">="
     - !ruby/object:Gem::Version 
-      hash: 3
-      segments: 
-      - 0
       version: "0"
 requirements: []
 
 rubyforge_project: 
-rubygems_version: 1.3.7
+rubygems_version: 1.7.2
 signing_key: 
 specification_version: 3
 summary: Browser User Agent string parser