public_suffix 1.0.0.rc1

data/lib/public_suffix/domain.rb

@@ -0,0 +1,387 @@
+#--
+# Public Suffix
+#
+# Domain name parser based on the Public Suffix List.
+#
+# Copyright (c) 2009-2011 Simone Carletti <weppos@weppos.net>
+#++
+
+
+module PublicSuffix
+
+  class Domain
+
+    # Splits a string into its possible labels
+    # as a domain in reverse order from the input string.
+    #
+    # The input is not validated, but it is assumed to be a valid domain.
+    #
+    # @param  [String, #to_s] domain
+    #   The domain name to split.
+    #
+    # @return [Array<String>]
+    #
+    # @example
+    #
+    #   domain_to_labels('google.com')
+    #   # => ['com', 'google']
+    #
+    #   domain_to_labels('google.co.uk')
+    #   # => ['uk', 'co', 'google']
+    #
+    def self.domain_to_labels(domain)
+      domain.to_s.split(".").reverse
+    end
+
+    # Creates and returns a new {PublicSuffix::Domain} instance.
+    #
+    # @overload initialize(tld)
+    #   Initializes with a +tld+.
+    #   @param [String] tld The TLD (extension)
+    # @overload initialize(tld, sld)
+    #   Initializes with a +tld+ and +sld+.
+    #   @param [String] tld The TLD (extension)
+    #   @param [String] sld The TRD (domain)
+    # @overload initialize(tld, sld, trd)
+    #   Initializes with a +tld+, +sld+ and +trd+.
+    #   @param [String] tld The TLD (extension)
+    #   @param [String] sld The SLD (domain)
+    #   @param [String] tld The TRD (subdomain)
+    #
+    # @yield [self] Yields on self.
+    # @yieldparam [PublicSuffix::Domain] self The newly creates instance
+    #
+    # @example Initialize with a TLD
+    #   PublicSuffix::Domain.new("com")
+    #   # => #<PublicSuffix::Domain @tld="com">
+    #
+    # @example Initialize with a TLD and SLD
+    #   PublicSuffix::Domain.new("com", "example")
+    #   # => #<PublicSuffix::Domain @tld="com", @trd=nil>
+    #
+    # @example Initialize with a TLD, SLD and TRD
+    #   PublicSuffix::Domain.new("com", "example", "wwww")
+    #   # => #<PublicSuffix::Domain @tld="com", @trd=nil, @sld="example">
+    #
+    def initialize(*args, &block)
+      @tld, @sld, @trd = args
+      yield(self) if block_given?
+    end
+
+    # Returns a string representation of this object.
+    #
+    # @return [String]
+    def to_s
+      name
+    end
+
+    # Returns an array containing the domain parts.
+    #
+    # @return [Array<String, nil>]
+    #
+    # @example
+    #
+    #   PublicSuffix::Domain.new("google.com").to_a
+    #   # => [nil, "google", "com"]
+    #
+    #   PublicSuffix::Domain.new("www.google.com").to_a
+    #   # => [nil, "google", "com"]
+    #
+    def to_a
+      [trd, sld, tld]
+    end
+
+
+    # Returns the Top Level Domain part, aka the extension.
+    #
+    # @return [String, nil]
+    def tld
+      @tld
+    end
+
+    # Returns the Second Level Domain part, aka the domain part.
+    #
+    # @return [String, nil]
+    def sld
+      @sld
+    end
+
+    # Returns the Third Level Domain part, aka the subdomain part.
+    #
+    # @return [String, nil]
+    def trd
+      @trd
+    end
+
+
+    # Returns the full domain name.
+    #
+    # @return [String]
+    #
+    # @example Gets the domain name of a domain
+    #   PublicSuffix::Domain.new("com", "google").name
+    #   # => "google.com"
+    #
+    # @example Gets the domain name of a subdomain
+    #   PublicSuffix::Domain.new("com", "google", "www").name
+    #   # => "www.google.com"
+    #
+    def name
+      [trd, sld, tld].reject { |part| part.nil? }.join(".")
+    end
+
+    # Returns a domain-like representation of this object
+    # if the object is a {#domain?}, <tt>nil</tt> otherwise.
+    #
+    #   PublicSuffix::Domain.new("com").domain
+    #   # => nil
+    #
+    #   PublicSuffix::Domain.new("com", "google").domain
+    #   # => "google.com"
+    #
+    #   PublicSuffix::Domain.new("com", "google", "www").domain
+    #   # => "www.google.com"
+    #
+    # This method doesn't validate the input. It handles the domain
+    # as a valid domain name and simply applies the necessary transformations.
+    #
+    #   # This is an invalid domain
+    #   PublicSuffix::Domain.new("zip", "google").domain
+    #   # => "google.zip"
+    #
+    # This method returns a FQD, not just the domain part.
+    # To get the domain part, use <tt>#sld</tt> (aka second level domain).
+    #
+    #   PublicSuffix::Domain.new("com", "google", "www").domain
+    #   # => "google.com"
+    #
+    #   PublicSuffix::Domain.new("com", "google", "www").sld
+    #   # => "google"
+    #
+    # @return [String]
+    #
+    # @see #domain?
+    # @see #subdomain
+    #
+    def domain
+      return unless domain?
+      [sld, tld].join(".")
+    end
+
+    # Returns a domain-like representation of this object
+    # if the object is a {#subdomain?}, <tt>nil</tt> otherwise.
+    #
+    #   PublicSuffix::Domain.new("com").subdomain
+    #   # => nil
+    #
+    #   PublicSuffix::Domain.new("com", "google").subdomain
+    #   # => nil
+    #
+    #   PublicSuffix::Domain.new("com", "google", "www").subdomain
+    #   # => "www.google.com"
+    #
+    # This method doesn't validate the input. It handles the domain
+    # as a valid domain name and simply applies the necessary transformations.
+    #
+    #   # This is an invalid domain
+    #   PublicSuffix::Domain.new("zip", "google", "www").subdomain
+    #   # => "www.google.zip"
+    #
+    # This method returns a FQD, not just the domain part.
+    # To get the domain part, use <tt>#tld</tt> (aka third level domain).
+    #
+    #   PublicSuffix::Domain.new("com", "google", "www").subdomain
+    #   # => "www.google.com"
+    #
+    #   PublicSuffix::Domain.new("com", "google", "www").trd
+    #   # => "www"
+    #
+    # @return [String]
+    #
+    # @see #subdomain?
+    # @see #domain
+    #
+    def subdomain
+      return unless subdomain?
+      [trd, sld, tld].join(".")
+    end
+
+    # Returns the rule matching this domain
+    # in the default {PublicSuffix::List}.
+    #
+    # @return [PublicSuffix::Rule::Base, nil]
+    #   The rule instance a rule matches current domain,
+    #   nil if no rule is found.
+    def rule
+      List.default.find(name)
+    end
+
+
+    # Checks whether <tt>self</tt> looks like a domain.
+    #
+    # This method doesn't actually validate the domain.
+    # It only checks whether the instance contains
+    # a value for the {#tld} and {#sld} attributes.
+    # If you also want to validate the domain,
+    # use {#valid_domain?} instead.
+    #
+    # @return [Boolean]
+    #
+    # @example
+    #
+    #   PublicSuffix::Domain.new("com").domain?
+    #   # => false
+    #
+    #   PublicSuffix::Domain.new("com", "google").domain?
+    #   # => true
+    #
+    #   PublicSuffix::Domain.new("com", "google", "www").domain?
+    #   # => true
+    #
+    #   # This is an invalid domain, but returns true
+    #   # because this method doesn't validate the content.
+    #   PublicSuffix::Domain.new("zip", "google").domain?
+    #   # => true
+    #
+    # @see #subdomain?
+    #
+    def domain?
+      !(tld.nil? || sld.nil?)
+    end
+
+    # Checks whether <tt>self</tt> looks like a subdomain.
+    #
+    # This method doesn't actually validate the subdomain.
+    # It only checks whether the instance contains
+    # a value for the {#tld}, {#sld} and {#trd} attributes.
+    # If you also want to validate the domain,
+    # use {#valid_subdomain?} instead.
+    #
+    # @return [Boolean]
+    #
+    # @example
+    #
+    #   PublicSuffix::Domain.new("com").subdomain?
+    #   # => false
+    #
+    #   PublicSuffix::Domain.new("com", "google").subdomain?
+    #   # => false
+    #
+    #   PublicSuffix::Domain.new("com", "google", "www").subdomain?
+    #   # => true
+    #
+    #   # This is an invalid domain, but returns true
+    #   # because this method doesn't validate the content.
+    #   PublicSuffix::Domain.new("zip", "google", "www").subdomain?
+    #   # => true
+    #
+    # @see #domain?
+    #
+    def subdomain?
+      !(tld.nil? || sld.nil? || trd.nil?)
+    end
+
+    # Checks whether <tt>self</tt> is exclusively a domain,
+    # and not a subdomain.
+    #
+    # @return [Boolean]
+    def is_a_domain?
+      domain? && !subdomain?
+    end
+
+    # Checks whether <tt>self</tt> is exclusively a subdomain.
+    #
+    # @return [Boolean]
+    def is_a_subdomain?
+      subdomain?
+    end
+
+    # Checks whether <tt>self</tt> is assigned and allowed
+    # according to default {List}.
+    #
+    # This method triggers a new rule lookup in the default {List},
+    # which is a quite intensive task.
+    #
+    # @return [Boolean]
+    #
+    # @example Check a valid domain
+    #   Domain.new("com", "example").valid?
+    #   # => true
+    #
+    # @example Check a valid subdomain
+    #   Domain.new("com", "example", "www").valid?
+    #   # => true
+    #
+    # @example Check a not-assigned domain
+    #   Domain.new("zip", "example").valid?
+    #   # => false
+    #
+    # @example Check a not-allowed domain
+    #   Domain.new("do", "example").valid?
+    #   # => false
+    #   Domain.new("do", "example", "www").valid?
+    #   # => true
+    #
+    def valid?
+      r = rule
+      !r.nil? && r.allow?(name)
+    end
+
+
+    # Checks whether <tt>self</tt> looks like a domain and validates
+    # according to default {List}.
+    #
+    # @return [Boolean]
+    #
+    # @example
+    #
+    #   PublicSuffix::Domain.new("com").domain?
+    #   # => false
+    #
+    #   PublicSuffix::Domain.new("com", "google").domain?
+    #   # => true
+    #
+    #   PublicSuffix::Domain.new("com", "google", "www").domain?
+    #   # => true
+    #
+    #   # This is an invalid domain
+    #   PublicSuffix::Domain.new("zip", "google").false?
+    #   # => true
+    #
+    # @see #domain?
+    # @see #valid?
+    #
+    def valid_domain?
+      domain? && valid?
+    end
+
+    # Checks whether <tt>self</tt> looks like a subdomain and validates
+    # according to default {List}.
+    #
+    # @return [Boolean]
+    #
+    # @example
+    #
+    #   PublicSuffix::Domain.new("com").subdomain?
+    #   # => false
+    #
+    #   PublicSuffix::Domain.new("com", "google").subdomain?
+    #   # => false
+    #
+    #   PublicSuffix::Domain.new("com", "google", "www").subdomain?
+    #   # => true
+    #
+    #   # This is an invalid domain
+    #   PublicSuffix::Domain.new("zip", "google", "www").subdomain?
+    #   # => false
+    #
+    # @see #subdomain?
+    # @see #valid?
+    #
+    def valid_subdomain?
+      subdomain? && valid?
+    end
+
+  end
+
+end

data/lib/public_suffix/errors.rb

@@ -0,0 +1,57 @@
+#--
+# Public Suffix
+#
+# Domain name parser based on the Public Suffix List.
+#
+# Copyright (c) 2009-2011 Simone Carletti <weppos@weppos.net>
+#++
+
+
+module PublicSuffix
+
+  class Error < StandardError
+  end
+
+  # Raised when trying to parse an invalid domain.
+  # A domain is considered invalid when no rule is found
+  # in the definition list.
+  #
+  # @example
+  #
+  #   PublicSuffix.parse("nic.test")
+  #   # => PublicSuffix::DomainInvalid
+  #
+  #   PublicSuffix.parse("http://www.nic.it")
+  #   # => PublicSuffix::DomainInvalid
+  #
+  # @since 0.6.0
+  #
+  class DomainInvalid < Error
+  end
+
+  # Raised when trying to parse a domain
+  # which is formally defined by a rule,
+  # but the rules set a requirement which is not satisfied
+  # by the input you are trying to parse.
+  #
+  # @example
+  #
+  #   PublicSuffix.parse("nic.do")
+  #   # => PublicSuffix::DomainNotAllowed
+  #
+  #   PublicSuffix.parse("www.nic.do")
+  #   # => PublicSuffix::Domain
+  #
+  # @since 0.6.0
+  #
+  class DomainNotAllowed < DomainInvalid
+  end
+
+
+  # Backward Compatibility
+  #
+  # @deprecated Use {PublicSuffix::DomainInvalid}.
+  #
+  InvalidDomain = DomainInvalid
+
+end

data/lib/public_suffix/list.rb

@@ -0,0 +1,283 @@
+#--
+# Public Suffix
+#
+# Domain name parser based on the Public Suffix List.
+#
+# Copyright (c) 2009-2011 Simone Carletti <weppos@weppos.net>
+#++
+
+
+module PublicSuffix
+
+  # A {PublicSuffix::List} is a collection of one
+  # or more {PublicSuffix::Rule}.
+  #
+  # Given a {PublicSuffix::List},
+  # you can add or remove {PublicSuffix::Rule},
+  # iterate all items in the list or search for the first rule
+  # which matches a specific domain name.
+  #
+  #   # Create a new list
+  #   list =  PublicSuffix::List.new
+  #
+  #   # Push two rules to the list
+  #   list << PublicSuffix::Rule.factory("it")
+  #   list << PublicSuffix::Rule.factory("com")
+  #
+  #   # Get the size of the list
+  #   list.size
+  #   # => 2
+  #
+  #   # Search for the rule matching given domain
+  #   list.find("example.com")
+  #   # => #<PublicSuffix::Rule::Normal>
+  #   list.find("example.org")
+  #   # => nil
+  #
+  # You can create as many {PublicSuffix::List} you want.
+  # The {PublicSuffix::List.default} rule list is used
+  # to tokenize and validate a domain.
+  #
+  # {PublicSuffix::List} implements +Enumerable+ module.
+  #
+  class List
+    include Enumerable
+
+    # Gets the array of rules.
+    #
+    # @return [Array<PublicSuffix::Rule::*>]
+    attr_reader :rules
+
+    # Gets the naive index, a hash that with the keys being the first label of
+    # every rule pointing to an array of integers (indexes of the rules in @rules).
+    #
+    # @return [Array]
+    attr_reader :indexes
+
+
+    # Initializes an empty {PublicSuffix::List}.
+    #
+    # @yield [self] Yields on self.
+    # @yieldparam [PublicSuffix::List] self The newly created instance.
+    #
+    def initialize(&block)
+      @rules   = []
+      @indexes = {}
+      yield(self) if block_given?
+      create_index!
+    end
+
+    # Creates a naive index for +@rules+. Just a hash that will tell
+    # us where the elements of +@rules+ are relative to its first
+    # {PublicSuffix::Rule::Base#labels} element.
+    #
+    # For instance if @rules[5] and @rules[4] are the only elements of the list
+    # where Rule#labels.first is 'us' @indexes['us'] #=> [5,4], that way in 
+    # select we can avoid mapping every single rule against the candidate domain.
+    def create_index!
+      @rules.map { |l| l.labels.first }.each_with_index do |elm, inx|
+        if !@indexes.has_key?(elm)
+          @indexes[elm] = [inx]
+        else
+          @indexes[elm] << inx
+        end
+      end
+    end
+
+    # Checks whether two lists are equal.
+    #
+    # List <tt>one</tt> is equal to <tt>two</tt>, if <tt>two</tt> is an instance of
+    # {PublicSuffix::List} and each +PublicSuffix::Rule::*+
+    # in list <tt>one</tt> is available in list <tt>two</tt>, in the same order.
+    #
+    # @param [PublicSuffix::List] other
+    #   The List to compare.
+    #
+    # @return [Boolean]
+    def ==(other)
+      return false unless other.is_a?(List)
+      self.equal?(other) ||
+      self.rules == other.rules
+    end
+    alias :eql? :==
+
+    # Iterates each rule in the list.
+    def each(*args, &block)
+      @rules.each(*args, &block)
+    end
+
+    # Gets the list as array.
+    #
+    # @return [Array<PublicSuffix::Rule::*>]
+    def to_a
+      @rules
+    end
+
+    # Adds the given object to the list
+    # and optionally refreshes the rule index.
+    #
+    # @param [PublicSuffix::Rule::*] rule
+    #   The rule to add to the list.
+    # @param [Boolean] index
+    #   Set to true to recreate the rule index
+    #   after the rule has been added to the list.
+    #
+    # @return [self]
+    #
+    # @see #create_index!
+    #
+    def add(rule, index = true)
+      @rules << rule
+      create_index! if index == true
+      self
+    end
+    alias << add
+
+    # Gets the number of elements in the list.
+    #
+    # @return [Integer]
+    def size
+      @rules.size
+    end
+    alias length size
+
+    # Checks whether the list is empty.
+    #
+    # @return [Boolean]
+    def empty?
+      @rules.empty?
+    end
+
+    # Removes all elements.
+    #
+    # @return [self]
+    def clear
+      @rules.clear
+      self
+    end
+
+
+    # Returns the most appropriate rule for domain.
+    #
+    # From the Public Suffix List documentation:
+    #
+    # * If a hostname matches more than one rule in the file,
+    #   the longest matching rule (the one with the most levels) will be used.
+    # * An exclamation mark (!) at the start of a rule marks an exception to a previous wildcard rule.
+    #   An exception rule takes priority over any other matching rule.
+    #
+    # == Algorithm description
+    #
+    # * Match domain against all rules and take note of the matching ones.
+    # * If no rules match, the prevailing rule is "*".
+    # * If more than one rule matches, the prevailing rule is the one which is an exception rule.
+    # * If there is no matching exception rule, the prevailing rule is the one with the most labels.
+    # * If the prevailing rule is a exception rule, modify it by removing the leftmost label.
+    # * The public suffix is the set of labels from the domain
+    #   which directly match the labels of the prevailing rule (joined by dots).
+    # * The registered domain is the public suffix plus one additional label.
+    #
+    # @param  [String, #to_s] domain The domain name.
+    #
+    # @return [PublicSuffix::Rule::*, nil]
+    def find(domain)
+      rules = select(domain)
+      rules.select { |r|   r.type == :exception }.first ||
+      rules.inject { |t,r| t.length > r.length ? t : r }
+    end
+
+    # Selects all the rules matching given domain.
+    #
+    # Will use +@indexes+ to try only the rules that share the same first label,
+    # that will speed up things when using +List.find('foo')+ a lot.
+    #
+    # @param  [String, #to_s] domain The domain name.
+    #
+    # @return [Array<PublicSuffix::Rule::*>]
+    def select(domain)
+      indices = (@indexes[Domain.domain_to_labels(domain).first] || [])
+      @rules.values_at(*indices).select { |rule| rule.match?(domain) }
+    end
+
+
+    @@default = nil
+
+    class << self
+
+      # Gets the default rule list.
+      # Initializes a new {PublicSuffix::List} parsing the content
+      # of {PublicSuffix::List.default_definition}, if required.
+      #
+      # @return [PublicSuffix::List]
+      def default
+        @@default ||= parse(default_definition)
+      end
+
+      # Sets the default rule list to +value+.
+      #
+      # @param [PublicSuffix::List] value
+      #   The new rule list.
+      #
+      # @return [PublicSuffix::List]
+      def default=(value)
+        @@default = value
+      end
+
+      # Sets the default rule list to +nil+.
+      #
+      # @return [self]
+      def clear
+        self.default = nil
+        self
+      end
+
+      # Resets the default rule list and reinitialize it
+      # parsing the content of {PublicSuffix::List.default_definition}.
+      #
+      # @return [PublicSuffix::List]
+      def reload
+        self.clear.default
+      end
+
+      # Gets the default definition list.
+      # Can be any <tt>IOStream</tt> including a <tt>File</tt>
+      # or a simple <tt>String</tt>.
+      # The object must respond to <tt>#each_line</tt>.
+      #
+      # @return [File]
+      def default_definition
+        File.new(File.join(File.dirname(__FILE__), "definitions.txt"), "r:utf-8")
+      end
+
+
+      # Parse given +input+ treating the content as Public Suffix List.
+      #
+      # See http://publicsuffix.org/format/ for more details about input format.
+      #
+      # @param [String] input The rule list to parse.
+      #
+      # @return [Array<PublicSuffix::Rule::*>]
+      def parse(input)
+        new do |list|
+          input.each_line do |line|
+            line.strip!
+
+            # strip blank lines
+            if line.empty?
+              next
+            # strip comments
+            elsif line =~ %r{^//}
+              next
+            # append rule
+            else
+              list.add(Rule.factory(line), false)
+            end
+          end
+        end
+      end
+
+    end
+
+  end
+
+end