domain_name 0.5.11 → 0.5.12

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 0eafc47a4b3dfe9f636fec6cb6705d0dec0bd44a
-  data.tar.gz: 5ffe41e86eddfcd6507808b68f61d360af8eee9f
+  metadata.gz: dd0379bf0cffbaf14dcf3006b9730ebd1b1c1332
+  data.tar.gz: 1bc901f30c3e6b574b05c34bcd1ba9a082052fc3
 SHA512:
-  metadata.gz: 770918024fa90f8ea009cb899bc98386140cf2deea2be85a7172217b0e7b627647a4ca737699bdbf8ffe6a99c50c2d0ac00cad6e078094d72b13cc129e4687f0
-  data.tar.gz: f8b2089004b251798c407995e5a5539bb7f2b71a5624b22c4c77decf045eb77e71ec42ac31e8e9a5619e29c15c4ad24e42781c2fe8d43cb18a1197828bd49ece
+  metadata.gz: 62d3caed3da3692ea0d37db18f8079aebfd6a64fdc31b22acd1824eb6a43d51850a8b81a1bfc59597fecf6a5f9d3246440fbe5e2a85b2ec7aa67f9ed9eb24d2d
+  data.tar.gz: 13573bc251f0356604e1409e4da30365ddfa3b31e0d2c0968b87ec171ffedef0e62a9726ba63c736093e9195cec6f15103fa4fed3c8490787f6036fa03ee43b0

data/README.md

@@ -24,12 +24,14 @@ Description
         host.ipaddr?        #=> true
         host.cookie_domain?("0:0:0:0:0:0:0:1")  #=> true
 
+* Implements rudimental IDNA support.
 
 To-do's
 -------
 
-* Implement the strict domain label validation defined in RFC 5891 and
-  5892.  It will be worked on on the `unicode` branch.
+* Implement IDNA 2008 (and/or 2003) including the domain label
+  validation and mapping defined in RFC 5891-5895 and UTS #46.
+  (work in progress)
 
 * Define a compact YAML serialization format.
 

data/Rakefile

@@ -9,26 +9,25 @@ task :default => :test
 
 task :test => ETLD_DATA_RB
 
-file ETLD_DATA_RB => [
-  ETLD_DATA_FILE,
-  ETLD_DATA_RB + '.erb',
-  'tool/gen_etld_data.rb'
-] do
-  ruby 'tool/gen_etld_data.rb'
-end
-
 task :import => :etld_data
 
+#
+# eTLD Database
+#
+
 task :etld_data do
   require 'open-uri'
   require 'time'
 
   begin
-    load File.join('.', ETLD_DATA_RB)
-
-    data = ETLD_DATA_URI.read(
-      'If-Modified-Since' => Time.parse(DomainName::ETLD_DATA_DATE).rfc2822
-    )
+    begin
+      load File.join('.', ETLD_DATA_RB)
+      data = ETLD_DATA_URI.read(
+        'If-Modified-Since' => Time.parse(DomainName::ETLD_DATA_DATE).rfc2822
+      )
+    rescue LoadError, NameError
+      data = ETLD_DATA_URI.read
+    end
     puts 'eTLD database is modified.'
     File.write(ETLD_DATA_FILE, data)
     File.utime Time.now, data.last_modified, ETLD_DATA_FILE
@@ -42,6 +41,14 @@ task :etld_data do
   end
 end
 
+file ETLD_DATA_RB => [
+  ETLD_DATA_FILE,
+  ETLD_DATA_RB + '.erb',
+  'tool/gen_etld_data.rb'
+] do
+  ruby 'tool/gen_etld_data.rb'
+end
+
 require 'rake/testtask'
 Rake::TestTask.new(:test) do |test|
   test.libs << 'test'

data/data/effective_tld_names.dat

@@ -6561,6 +6561,26 @@ xxx
 // Requested by Donavan Miller <donavanm@amazon.com> 2013-03-22
 cloudfront.net
 
+// Amazon Elastic Compute Cloud: https://aws.amazon.com/ec2/
+// Requested by Osman Surkatty <osmans@amazon.com> 2013-04-02
+compute.amazonaws.com
+us-east-1.amazonaws.com
+compute-1.amazonaws.com
+z-1.compute-1.amazonaws.com
+z-2.compute-1.amazonaws.com
+ap-northeast-1.compute.amazonaws.com
+ap-southeast-1.compute.amazonaws.com
+ap-southeast-2.compute.amazonaws.com
+eu-west-1.compute.amazonaws.com
+sa-east-1.compute.amazonaws.com
+us-gov-west-1.compute.amazonaws.com
+us-west-1.compute.amazonaws.com
+us-west-2.compute.amazonaws.com
+
+// Amazon Elastic Beanstalk : https://aws.amazon.com/elasticbeanstalk/ 
+// Requested by Adam Stein <astein@amazon.com> 2013-04-02
+elasticbeanstalk.com
+
 // Amazon Elastic Load Balancing : https://aws.amazon.com/elasticloadbalancing/
 // Requested by Scott Vidmar <svidmar@amazon.com> 2013-03-27
 elb.amazonaws.com
@@ -6916,6 +6936,10 @@ webhop.org
 worse-than.tv
 writesthisblog.com
 
+// GitHub, Inc.
+// Requested by Ben Toews <btoews@github.com> 2013-04-18
+github.io
+
 // Google, Inc.
 // Requested by Eduardo Vela <evn@google.com> 2012-10-24
 appspot.com
@@ -6963,6 +6987,11 @@ codespot.com
 googleapis.com
 googlecode.com
 
+// Heroku : https://www.heroku.com/
+// Requested by Tom Maher <tmaher@heroku.com> 2013-05-02
+herokuapp.com
+herokussl.com
+
 // iki.fi
 // Requested by Hannu Aronsson <haa@iki.fi> 2009-11-05
 iki.fi

data/lib/domain_name.rb

@@ -20,6 +20,10 @@ class DomainName
   # suitable for opening a connection to.
   attr_reader :hostname
 
+  # The Unicode representation of the #hostname property.
+  #
+  # :attr_reader: hostname_idn
+
   # The least "universally original" domain part of this domain name.
   # For example, "example.co.uk" for "www.sub.example.co.uk".  This
   # may be nil if the hostname does not have one, like when it is an
@@ -27,6 +31,10 @@ class DomainName
   # non-canonical domain.
   attr_reader :domain
 
+  # The Unicode representation of the #domain property.
+  #
+  # :attr_reader: domain_idn
+
   # The TLD part of this domain name.  For example, if the hostname is
   # "www.sub.example.co.uk", the TLD part is "uk".  This property is
   # nil only if +ipaddr?+ is true.  This may be nil if the hostname
@@ -34,6 +42,10 @@ class DomainName
   # non-canonical domain.
   attr_reader :tld
 
+  # The Unicode representation of the #tld property.
+  #
+  # :attr_reader: tld_idn
+
   # Returns an IPAddr object if this is an IP address.
   attr_reader :ipaddr
 
@@ -230,6 +242,35 @@ class DomainName
 
   alias to_str to_s
 
+  def hostname_idn
+    @hostname_idn ||=
+      if @ipaddr
+        @hostname
+      else
+        DomainName::Punycode.decode_hostname(@hostname)
+      end
+  end
+
+  alias idn hostname_idn
+
+  def domain_idn
+    @domain_idn ||=
+      if @ipaddr
+        @domain
+      else
+        DomainName::Punycode.decode_hostname(@domain)
+      end
+  end
+
+  def tld_idn
+    @tld_idn ||=
+      if @ipaddr
+        @tld
+      else
+        DomainName::Punycode.decode_hostname(@tld)
+      end
+  end
+
   def inspect
     str = '#<%s:%s' % [self.class.name, @hostname]
     if @ipaddr

data/lib/domain_name/etld_data.rb

@@ -1,5 +1,5 @@
 class DomainName
-  ETLD_DATA_DATE = '2013-04-05T23:00:49Z'
+  ETLD_DATA_DATE = '2013-06-06T23:00:56Z'
 
   ETLD_DATA = {
     "ac" => 0,
@@ -5717,6 +5717,20 @@ class DomainName
     "zm" => -1,
     "zw" => -1,
     "cloudfront.net" => 0,
+    "compute.amazonaws.com" => 0,
+    "us-east-1.amazonaws.com" => 0,
+    "compute-1.amazonaws.com" => 0,
+    "z-1.compute-1.amazonaws.com" => 0,
+    "z-2.compute-1.amazonaws.com" => 0,
+    "ap-northeast-1.compute.amazonaws.com" => 0,
+    "ap-southeast-1.compute.amazonaws.com" => 0,
+    "ap-southeast-2.compute.amazonaws.com" => 0,
+    "eu-west-1.compute.amazonaws.com" => 0,
+    "sa-east-1.compute.amazonaws.com" => 0,
+    "us-gov-west-1.compute.amazonaws.com" => 0,
+    "us-west-1.compute.amazonaws.com" => 0,
+    "us-west-2.compute.amazonaws.com" => 0,
+    "elasticbeanstalk.com" => 0,
     "elb.amazonaws.com" => 0,
     "s3.amazonaws.com" => 0,
     "s3-us-west-2.amazonaws.com" => 0,
@@ -6049,6 +6063,7 @@ class DomainName
     "webhop.org" => 0,
     "worse-than.tv" => 0,
     "writesthisblog.com" => 0,
+    "github.io" => 0,
     "appspot.com" => 0,
     "blogspot.be" => 0,
     "blogspot.bj" => 0,
@@ -6093,6 +6108,8 @@ class DomainName
     "codespot.com" => 0,
     "googleapis.com" => 0,
     "googlecode.com" => 0,
+    "herokuapp.com" => 0,
+    "herokussl.com" => 0,
     "iki.fi" => 0,
     "biz.at" => 0,
     "info.at" => 0,

data/lib/domain_name/punycode.rb

@@ -2,7 +2,7 @@
 #--
 # punycode.rb - PunyCode encoder for the Domain Name library
 #
-# Copyright (C) 2011, 2012 Akinori MUSHA, All rights reserved.
+# Copyright (C) 2011, 2012, 2013 Akinori MUSHA, All rights reserved.
 #
 # Ported from puny.c, a part of VeriSign XCode (encode/decode) IDN
 # Library.
@@ -57,7 +57,7 @@ class DomainName
     DAMP = 700
     INITIAL_BIAS = 72
     INITIAL_N = 0x80
-    DELIMITER = '-'
+    DELIMITER = '-'.freeze
 
     MAXINT = (1 << 32) - 1
 
@@ -66,6 +66,9 @@ class DomainName
 
     RE_NONBASIC = /[^\x00-\x7f]/
 
+    # Returns the numeric value of a basic code point (for use in
+    # representing integers) in the range 0 to base-1, or nil if cp
+    # is does not represent a value.
     DECODE_DIGIT = {}.tap { |map|
       # ASCII A..Z map to 0..25
       # ASCII a..z map to 0..25
@@ -74,34 +77,26 @@ class DomainName
       (26..35).each { |i| map[22 + i] = i }
     }
 
+    # Returns the basic code point whose value (when used for
+    # representing integers) is d, which must be in the range 0 to
+    # BASE-1.  The lowercase form is used unless flag is true, in
+    # which case the uppercase form is used.  The behavior is
+    # undefined if flag is nonzero and digit d has no uppercase
+    # form.
+    ENCODE_DIGIT = proc { |d, flag|
+      (d + 22 + (d < 26 ? 75 : 0) - (flag ? (1 << 5) : 0)).chr
+      #  0..25 map to ASCII a..z or A..Z
+      # 26..35 map to ASCII 0..9
+    }
+
+    DOT = '.'.freeze
+    PREFIX = 'xn--'.freeze
+
     # Most errors we raise are basically kind of ArgumentError.
     class ArgumentError < ::ArgumentError; end
     class BufferOverflowError < ArgumentError; end
 
     class << self
-      private
-
-      # Returns the basic code point whose value (when used for
-      # representing integers) is d, which must be in the range 0 to
-      # BASE-1.  The lowercase form is used unless flag is true, in
-      # which case the uppercase form is used.  The behavior is
-      # undefined if flag is nonzero and digit d has no uppercase
-      # form.
-      def encode_digit(d, flag)
-        (d + 22 + (d < 26 ? 75 : 0) - (flag ? (1 << 5) : 0)).chr
-        #  0..25 map to ASCII a..z or A..Z
-        # 26..35 map to ASCII 0..9
-      end
-
-      # Returns the numeric value of a basic code point (for use in
-      # representing integers) in the range 0 to base-1, or nil if cp
-      # is does not represent a value.
-      def decode_digit(cp)
-        DECODE_DIGIT[cp]
-      end
-
-      public
-
       # Encode a +string+ in Punycode
       def encode(string)
         input = string.unpack('U*')
@@ -154,11 +149,11 @@ class DomainName
                 t = k <= bias ? TMIN : k - bias >= TMAX ? TMAX : k - bias
                 break if q < t
                 q, r = (q - t).divmod(BASE - t)
-                output << encode_digit(t + r, false)
+                output << ENCODE_DIGIT[t + r, false]
                 k += BASE
               }
 
-              output << encode_digit(q, false)
+              output << ENCODE_DIGIT[q, false]
 
               # Adapt the bias
               delta = h == b ? delta / DAMP : delta >> 1
@@ -186,13 +181,13 @@ class DomainName
       def encode_hostname(hostname)
         hostname.match(RE_NONBASIC) or return hostname
 
-        hostname.split('.').map { |name|
+        hostname.split(DOT).map { |name|
           if name.match(RE_NONBASIC)
-            'xn--' << encode(name)
+            PREFIX + encode(name)
           else
             name
           end
-        }.join('.')
+        }.join(DOT)
       end
 
       # Decode a +string+ encoded in Punycode
@@ -237,7 +232,7 @@ class DomainName
           k = BASE
 
           loop {
-            digit = decode_digit(input[h]) or
+            digit = DECODE_DIGIT[input[h]] or
             raise ArgumentError, "Illegal character is found in non-basic part: #{string.inspect}"
             h += 1
             i += digit * w
@@ -279,7 +274,7 @@ class DomainName
 
       # Decode a hostname using IDN/Punycode algorithms
       def decode_hostname(hostname)
-        hostname.gsub(/(\A|\.)xn--([^.]*)/) {
+        hostname.gsub(/(\A|#{Regexp.quote(DOT)})#{Regexp.quote(PREFIX)}([^#{Regexp.quote(DOT)}]*)/o) {
           $1 << decode($2)
         }
       end

data/lib/domain_name/version.rb

@@ -1,3 +1,3 @@
 class DomainName
-  VERSION = "0.5.11"
+  VERSION = "0.5.12"
 end

data/test/test_domain_name.rb

@@ -1,3 +1,4 @@
+# -*- coding: utf-8 -*-
 require 'helper'
 require 'ipaddr'
 
@@ -282,4 +283,15 @@ class TestDomainName < Test::Unit::TestCase
       assert_equal nil, dn.superdomain
     }
   end
+
+  should "have idn methods" do
+    dn = DomainName("金八先生.B組.3年.日本語ドメイン名Example.日本")
+
+    assert_equal "xn--44q1cv48kq8x.xn--b-gf6c.xn--3-pj3b.xn--example-6q4fyliikhk162btq3b2zd4y2o.xn--wgv71a", dn.hostname
+    assert_equal "金八先生.b組.3年.日本語ドメイン名example.日本", dn.hostname_idn
+    assert_equal "xn--example-6q4fyliikhk162btq3b2zd4y2o.xn--wgv71a", dn.domain
+    assert_equal "日本語ドメイン名example.日本", dn.domain_idn
+    assert_equal "xn--wgv71a", dn.tld
+    assert_equal "日本", dn.tld_idn
+  end
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: domain_name
 version: !ruby/object:Gem::Version
-  version: 0.5.11
+  version: 0.5.12
 platform: ruby
 authors:
 - Akinori MUSHA
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2013-04-12 00:00:00.000000000 Z
+date: 2013-06-07 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: unf