public_suffix 3.1.1

data/lib/public_suffix.rb

@@ -0,0 +1,179 @@
+# frozen_string_literal: true
+
+# = Public Suffix
+#
+# Domain name parser based on the Public Suffix List.
+#
+# Copyright (c) 2009-2019 Simone Carletti <weppos@weppos.net>
+
+require_relative "public_suffix/domain"
+require_relative "public_suffix/version"
+require_relative "public_suffix/errors"
+require_relative "public_suffix/rule"
+require_relative "public_suffix/list"
+
+# PublicSuffix is a Ruby domain name parser based on the Public Suffix List.
+#
+# The [Public Suffix List](https://publicsuffix.org) is a cross-vendor initiative
+# to provide an accurate list of domain name suffixes.
+#
+# The Public Suffix List is an initiative of the Mozilla Project,
+# but is maintained as a community resource. It is available for use in any software,
+# but was originally created to meet the needs of browser manufacturers.
+module PublicSuffix
+
+  DOT   = "."
+  BANG  = "!"
+  STAR  = "*"
+
+  # Parses +name+ and returns the {PublicSuffix::Domain} instance.
+  #
+  # @example Parse a valid domain
+  #   PublicSuffix.parse("google.com")
+  #   # => #<PublicSuffix::Domain:0x007fec2e51e588 @sld="google", @tld="com", @trd=nil>
+  #
+  # @example Parse a valid subdomain
+  #   PublicSuffix.parse("www.google.com")
+  #   # => #<PublicSuffix::Domain:0x007fec276d4cf8 @sld="google", @tld="com", @trd="www">
+  #
+  # @example Parse a fully qualified domain
+  #   PublicSuffix.parse("google.com.")
+  #   # => #<PublicSuffix::Domain:0x007fec257caf38 @sld="google", @tld="com", @trd=nil>
+  #
+  # @example Parse a fully qualified domain (subdomain)
+  #   PublicSuffix.parse("www.google.com.")
+  #   # => #<PublicSuffix::Domain:0x007fec27b6bca8 @sld="google", @tld="com", @trd="www">
+  #
+  # @example Parse an invalid (unlisted) domain
+  #   PublicSuffix.parse("x.yz")
+  #   # => #<PublicSuffix::Domain:0x007fec2f49bec0 @sld="x", @tld="yz", @trd=nil>
+  #
+  # @example Parse an invalid (unlisted) domain with strict checking (without applying the default * rule)
+  #   PublicSuffix.parse("x.yz", default_rule: nil)
+  #   # => PublicSuffix::DomainInvalid: `x.yz` is not a valid domain
+  #
+  # @example Parse an URL (not supported, only domains)
+  #   PublicSuffix.parse("http://www.google.com")
+  #   # => PublicSuffix::DomainInvalid: http://www.google.com is not expected to contain a scheme
+  #
+  #
+  # @param  [String, #to_s] name The domain name or fully qualified domain name to parse.
+  # @param  [PublicSuffix::List] list The rule list to search, defaults to the default {PublicSuffix::List}
+  # @param  [Boolean] ignore_private
+  # @return [PublicSuffix::Domain]
+  #
+  # @raise [PublicSuffix::DomainInvalid]
+  #   If domain is not a valid domain.
+  # @raise [PublicSuffix::DomainNotAllowed]
+  #   If a rule for +domain+ is found, but the rule doesn't allow +domain+.
+  def self.parse(name, list: List.default, default_rule: list.default_rule, ignore_private: false)
+    what = normalize(name)
+    raise what if what.is_a?(DomainInvalid)
+
+    rule = list.find(what, default: default_rule, ignore_private: ignore_private)
+
+    # rubocop:disable Style/IfUnlessModifier
+    if rule.nil?
+      raise DomainInvalid, "`#{what}` is not a valid domain"
+    end
+    if rule.decompose(what).last.nil?
+      raise DomainNotAllowed, "`#{what}` is not allowed according to Registry policy"
+    end
+
+    # rubocop:enable Style/IfUnlessModifier
+
+    decompose(what, rule)
+  end
+
+  # Checks whether +domain+ is assigned and allowed, without actually parsing it.
+  #
+  # This method doesn't care whether domain is a domain or subdomain.
+  # The validation is performed using the default {PublicSuffix::List}.
+  #
+  # @example Validate a valid domain
+  #   PublicSuffix.valid?("example.com")
+  #   # => true
+  #
+  # @example Validate a valid subdomain
+  #   PublicSuffix.valid?("www.example.com")
+  #   # => true
+  #
+  # @example Validate a not-listed domain
+  #   PublicSuffix.valid?("example.tldnotlisted")
+  #   # => true
+  #
+  # @example Validate a not-listed domain with strict checking (without applying the default * rule)
+  #   PublicSuffix.valid?("example.tldnotlisted")
+  #   # => true
+  #   PublicSuffix.valid?("example.tldnotlisted", default_rule: nil)
+  #   # => false
+  #
+  # @example Validate a fully qualified domain
+  #   PublicSuffix.valid?("google.com.")
+  #   # => true
+  #   PublicSuffix.valid?("www.google.com.")
+  #   # => true
+  #
+  # @example Check an URL (which is not a valid domain)
+  #   PublicSuffix.valid?("http://www.example.com")
+  #   # => false
+  #
+  #
+  # @param  [String, #to_s] name The domain name or fully qualified domain name to validate.
+  # @param  [Boolean] ignore_private
+  # @return [Boolean]
+  def self.valid?(name, list: List.default, default_rule: list.default_rule, ignore_private: false)
+    what = normalize(name)
+    return false if what.is_a?(DomainInvalid)
+
+    rule = list.find(what, default: default_rule, ignore_private: ignore_private)
+
+    !rule.nil? && !rule.decompose(what).last.nil?
+  end
+
+  # Attempt to parse the name and returns the domain, if valid.
+  #
+  # This method doesn't raise. Instead, it returns nil if the domain is not valid for whatever reason.
+  #
+  # @param  [String, #to_s] name The domain name or fully qualified domain name to parse.
+  # @param  [PublicSuffix::List] list The rule list to search, defaults to the default {PublicSuffix::List}
+  # @param  [Boolean] ignore_private
+  # @return [String]
+  def self.domain(name, **options)
+    parse(name, **options).domain
+  rescue PublicSuffix::Error
+    nil
+  end
+
+
+  # private
+
+  def self.decompose(name, rule)
+    left, right = rule.decompose(name)
+
+    parts = left.split(DOT)
+    # If we have 0 parts left, there is just a tld and no domain or subdomain
+    # If we have 1 part  left, there is just a tld, domain and not subdomain
+    # If we have 2 parts left, the last part is the domain, the other parts (combined) are the subdomain
+    tld = right
+    sld = parts.empty? ? nil : parts.pop
+    trd = parts.empty? ? nil : parts.join(DOT)
+
+    Domain.new(tld, sld, trd)
+  end
+
+  # Pretend we know how to deal with user input.
+  def self.normalize(name)
+    name = name.to_s.dup
+    name.strip!
+    name.chomp!(DOT)
+    name.downcase!
+
+    return DomainInvalid.new("Name is blank") if name.empty?
+    return DomainInvalid.new("Name starts with a dot") if name.start_with?(DOT)
+    return DomainInvalid.new("%s is not expected to contain a scheme" % name) if name.include?("://")
+
+    name
+  end
+
+end

data/lib/public_suffix/domain.rb

@@ -0,0 +1,235 @@
+# frozen_string_literal: true
+
+# = Public Suffix
+#
+# Domain name parser based on the Public Suffix List.
+#
+# Copyright (c) 2009-2019 Simone Carletti <weppos@weppos.net>
+
+module PublicSuffix
+
+  # Domain represents a domain name, composed by a TLD, SLD and TRD.
+  class Domain
+
+    # Splits a string into the labels, that is the dot-separated parts.
+    #
+    # The input is not validated, but it is assumed to be a valid domain name.
+    #
+    # @example
+    #
+    #   name_to_labels('example.com')
+    #   # => ['example', 'com']
+    #
+    #   name_to_labels('example.co.uk')
+    #   # => ['example', 'co', 'uk']
+    #
+    # @param  name [String, #to_s] The domain name to split.
+    # @return [Array<String>]
+    def self.name_to_labels(name)
+      name.to_s.split(DOT)
+    end
+
+
+    attr_reader :tld, :sld, :trd
+
+    # 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] trd 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)
+      @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 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].compact.join(DOT)
+    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 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"
+    #
+    # @see #domain?
+    # @see #subdomain
+    #
+    # @return [String]
+    def domain
+      [@sld, @tld].join(DOT) if domain?
+    end
+
+    # Returns a subdomain-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 method returns a FQD, not just the subdomain part.
+    # To get the subdomain part, use <tt>#trd</tt> (aka third level domain).
+    #
+    #   PublicSuffix::Domain.new("com", "google", "www").subdomain
+    #   # => "www.google.com"
+    #
+    #   PublicSuffix::Domain.new("com", "google", "www").trd
+    #   # => "www"
+    #
+    # @see #subdomain?
+    # @see #domain
+    #
+    # @return [String]
+    def subdomain
+      [@trd, @sld, @tld].join(DOT) if subdomain?
+    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.
+    #
+    # @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("com", nil).domain?
+    #   # => true
+    #
+    # @see #subdomain?
+    #
+    # @return [Boolean]
+    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.
+    #
+    # @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("com", "example", nil).subdomain?
+    #   # => true
+    #
+    # @see #domain?
+    #
+    # @return [Boolean]
+    def subdomain?
+      !(@tld.nil? || @sld.nil? || @trd.nil?)
+    end
+
+  end
+
+end

data/lib/public_suffix/errors.rb

@@ -0,0 +1,41 @@
+# frozen_string_literal: true
+
+# = Public Suffix
+#
+# Domain name parser based on the Public Suffix List.
+#
+# Copyright (c) 2009-2019 Simone Carletti <weppos@weppos.net>
+
+module PublicSuffix
+
+  class Error < StandardError
+  end
+
+  # Raised when trying to parse an invalid name.
+  # A name 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
+  #
+  class DomainInvalid < Error
+  end
+
+  # Raised when trying to parse a name that matches a suffix.
+  #
+  # @example
+  #
+  #   PublicSuffix.parse("nic.do")
+  #   # => PublicSuffix::DomainNotAllowed
+  #
+  #   PublicSuffix.parse("www.nic.do")
+  #   # => PublicSuffix::Domain
+  #
+  class DomainNotAllowed < DomainInvalid
+  end
+
+end