gman 0.0.7 → 0.1.0

data/README.md

@@ -28,6 +28,15 @@ Or add this to your `Gemfile` before doing a `bundle install`:
 Gman.valid? "foo@bar.gov" #true
 Gman.valid? "foo@bar.com" #false
 ```
+
+### Really verify an email address
+
+(also verifies that the server returns a valid MX record)
+
+```ruby
+Gman.valid? "foo@whitehouse.gov", true #true
+Gman.valid? "foo@bar.gov", true #false
+```
 ### Verify domain
 
 ```ruby
@@ -37,6 +46,17 @@ Gman.valid? "foo.gov" #true
 Gman.valid? "foo.biz" #false
 ```
 
+### Get a domain name from an arbitrary domainy string
+
+```ruby
+Gman.get_domain "http://foo.bar.gov" # foo.bar.gov
+Gman.get_domain "foo@bar.gov" # bar.gov
+Gman.get_domain "foo.bar.gov" # foo.bar.gov
+Gman.get_domain "asdf@asdf" # nil (no domain within the string)
+Gman.get_domain "foo@bar.gov", true #false (no MX record)
+Gman.get_domain "foo@whitehouse.gov", true # true (valid MX record)
+```
+
 ## Contributing
 
 Contributions welcome! Please see [the contribution guidelines](CONTRIBUTING.md) for code contributions or for details on how to add, update, or delete government domains.

data/gman.gemspec

@@ -2,7 +2,7 @@ Gem::Specification.new do |s|
   s.name = "gman"
   s.summary = "Check if a given domain or email address belong to a governemnt entity"
   s.description = "A ruby gem to check if the owner of a given email address is working for THE MAN."
-  s.version = "0.0.7"
+  s.version = "0.1.0"
   s.authors = ["Ben Balter"]
   s.email = "ben.balter@github.com"
   s.homepage = "https://github.com/benbalter/gman"
@@ -26,6 +26,8 @@ Gem::Specification.new do |s|
   s.require_paths = ["lib"]
   s.add_dependency( "public_suffix" )
   s.add_dependency( "swot" )
+  s.add_dependency( "email_veracity" )
+  s.add_dependency( "addressable" )
 
   s.add_development_dependency( "rake" )
   s.add_development_dependency( "shoulda" )

data/lib/gman.rb

@@ -1,6 +1,8 @@
 require 'public_suffix'
 require 'yaml'
 require 'swot'
+require "addressable/uri"
+require "email_veracity"
 
 module Gman
 
@@ -14,10 +16,19 @@ module Gman
     #   "foo.gov.uk"
     #   "http://foo.bar.gov"
     #
+    # check_mx - if an email is passed, check the domain for an mx record
+    #
     # Returns boolean true if a government domain
-    def valid?(text)
-      return false if text.nil?
+    def valid?(text, check_mx=false)
+
       domain = get_domain text
+      return false unless PublicSuffix.valid?(domain)
+
+      # validate mx record
+      if check_mx && email?(text)
+        EmailVeracity::Config[:skip_lookup] = false
+        return false unless EmailVeracity::Address.new(text).valid?
+      end
 
       # Ensure non-edu
       return false if Swot::is_academic?(domain)
@@ -27,8 +38,6 @@ module Gman
       return true if !rule.nil? && rule.allow?(domain)
 
       # also allow for explicit matches to domain list
-      # but still make sure it's at least a valid domain
-      return false unless PublicSuffix.valid? domain
       list.rules.any? { |rule| rule.value == domain }
     end
 
@@ -41,18 +50,31 @@ module Gman
     # Get the FQDN name from a URL or email address.
     #
     # Returns a string with the FQDN; nil if there's an error.
-    # Source: https://github.com/leereilly/swot/blob/master/lib/swot.rb#L190
     def get_domain(text)
-      text.strip.downcase.match(domain_regex).captures.first
-    rescue
-      return nil
-    end
 
-    private
+      return nil if text.to_s.empty?
 
-    # Source: https://github.com/leereilly/swot/blob/master/lib/swot.rb#L202
-    def domain_regex
-      /([^@\/:]+)[:\d]*$/
+      text = text.downcase
+      uri = Addressable::URI.parse(text)
+
+      if uri.host # valid https?://* URI
+        uri.host
+      elsif email?(text)
+        EmailVeracity::Address.new(text).domain.to_s
+      else # url sans http://
+        uri = Addressable::URI.parse("http://#{text}")
+        # properly parse http://foo edge cases
+        # see https://github.com/sporkmonger/addressable/issues/145
+        uri.host if uri.host =~ /\./
+      end
+    end
+
+    # Is the given string in the form of a valid email address?
+    #
+    # Returns true if email, otherwise false
+    def email?(text)
+      EmailVeracity::Config[:skip_lookup] = true
+      EmailVeracity::Address.new(text).valid?
     end
   end
 end

data/test/test_gman.rb

@@ -1,14 +1,15 @@
 require 'helper'
-require 'swot'
 
 VALID = [  "foo.gov",
             "http://foo.mil",
             "foo@bar.gc.ca",
             "foo.gov.au",
-            "http://www.foo.gouv.fr",
+            "https://www.foo.gouv.fr",
             "foo@ci.champaign.il.us",
             "foo.bar.baz.gov.au",
-            "foo@bar.gov.uk"
+            "foo@bar.gov.uk",
+            ".gov",
+            "foo.fed.us",
         ]
 
 INVALID = [ "foo.bar.com",
@@ -17,7 +18,10 @@ INVALID = [ "foo.bar.com",
             "foo.uk",
             "gov",
             "foo@k12.champaign.il.us",
-            "foo@kii.gov.by"
+            "foo@kii.gov.by",
+            "foo",
+            "",
+            nil,
           ]
 
 class TestGman < Test::Unit::TestCase
@@ -39,4 +43,48 @@ class TestGman < Test::Unit::TestCase
       assert_equal false, Swot::is_academic?(entry.name), "#{entry.name} is an academic domain"
     end
   end
+
+  should "not contain any invalid domains" do
+    Gman.list.each do |entry|
+      assert_equal true, PublicSuffix.valid?("foo.#{entry.name}"), "#{entry.name} is not a valid domain"
+    end
+  end
+
+  should "not allow educational domains" do
+    assert_equal false, Gman::valid?("foo@gwu.edu")
+  end
+
+  should "properly parse domains from strings" do
+    assert_equal "github.gov", Gman::get_domain("foo@github.gov")
+    assert_equal "foo.github.gov", Gman::get_domain("foo.github.gov")
+    assert_equal "github.gov", Gman::get_domain("http://github.gov")
+    assert_equal "github.gov", Gman::get_domain("https://github.gov")
+    assert_equal ".gov", Gman::get_domain(".gov")
+    assert_equal nil, Gman.get_domain("foo")
+  end
+
+  should "validate mx records when asked" do
+    assert_equal true, Gman.valid?("foo@nasa.gov", true)
+    assert_equal false, Gman.valid?("foo@github.gov", true)
+    assert_equal true, Gman.valid?("foo@github.gov", false)
+  end
+
+  should "pass any url on the list" do
+    Gman.list.each do |entry|
+      assert_equal true, Gman.valid?("http://foo.#{entry.name}/bar"), "http://foo.#{entry.name}/bar is not a valid"
+    end
+  end
+
+  should "pass any email on the list" do
+    Gman.list.each do |entry|
+      assert_equal true, Gman.valid?("foo@bar.#{entry.name}"), "foo@bar.#{entry.name} is not a valid"
+    end
+  end
+
+  should "pass any domain on the list" do
+    Gman.list.each do |entry|
+      assert_equal true, Gman.valid?("foo.#{entry.name}"), "foo.#{entry.name} is not a valid domain"
+    end
+  end
+
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: gman
 version: !ruby/object:Gem::Version
-  version: 0.0.7
+  version: 0.1.0
   prerelease: 
 platform: ruby
 authors:
@@ -9,7 +9,7 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2013-11-25 00:00:00.000000000 Z
+date: 2013-11-27 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: public_suffix
@@ -43,6 +43,38 @@ dependencies:
     - - ! '>='
       - !ruby/object:Gem::Version
         version: '0'
+- !ruby/object:Gem::Dependency
+  name: email_veracity
+  requirement: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: addressable
+  requirement: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
 - !ruby/object:Gem::Dependency
   name: rake
   requirement: !ruby/object:Gem::Requirement