gman 0.0.2 → 0.0.3

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: 334405ee7b8d7e8277e8fa070f048725e8189f20
+  data.tar.gz: 579a6efbb98841f92c49775fd4902551407303d7
+SHA512:
+  metadata.gz: fbb201ea872a5a481285ff39da33a7b7db6fb75064970e1931edd60f0a55bf30341b65c19534bd82b902b486fd30d8f9a8ef7370b6f28c51394e6a2ecb09b185
+  data.tar.gz: 51e3c96b16b6dec39ca0817ad050489bcb982985b74a34f9a7212f84897ccdd3e1b0190ad4e4c83576ad73c58dfdf29e718b1e5e535fad6330b885081863d1de

data/README.md

@@ -1,5 +1,7 @@
 # Gman Gem
 
+[![Build Status](https://travis-ci.org/benbalter/gman.png)](https://travis-ci.org/benbalter/gman) [![Gem Version](https://badge.fury.io/rb/gman.png)](http://badge.fury.io/rb/gman)
+
 A ruby gem to check if the owner of a given email address or website is working for THE MAN (a.k.a verifies government domains). It does this by leveraging the power of the [Public Suffix List](http://publicsuffix.org/), and the associated [Ruby Gem](https://github.com/weppos/publicsuffix-ruby).
 
 You could theoretically [use regex](https://gist.github.com/benbalter/6147066), but either you'll a bunch of false positives, or your regex will be insanely complicated. `gov.uk`, may be valid, for example, but `gov.fr` is not (it's `gouv.fr`, for what it's worth).

data/gman.gemspec

@@ -2,9 +2,9 @@ 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 = "0.0.2"
+  s.version = "0.0.3"
   s.authors = ["Ben Balter"]
-  s.date = "2013-08-30"
+  s.date = "2013-09-30"
   s.email = "ben.balter@github.com"
   s.homepage = "https://github.com/benbalter/gman"
   s.licenses = ["MIT"]
@@ -15,7 +15,7 @@ Gem::Specification.new do |s|
     "CONTRIBUTING.md",
     "LICENSE",
     "lib/gman.rb",
-    "lib/domains.yml",
+    "lib/domains.txt",
     "script/build",
     "script/release",
     "gman.gemspec",

data/lib/domains.txt

@@ -0,0 +1,196 @@
+// US Federal
+fed.us
+gov
+mil
+
+// Non-US gov
+gc.ca
+gob.bo
+gob.cl
+gob.do
+gob.ec
+gob.es
+gob.gt
+gob.hn
+gob.mx
+gob.pa
+gob.pe
+gob.pk
+gouv.bj
+gouv.ci
+gouv.fr
+gouv.ht
+gouv.km
+gouv.ml
+gouv.rw
+gouv.sn
+gov.ac
+gov.ae
+gov.af
+gov.al
+gov.as
+gov.au
+gov.az
+gov.ba
+gov.bb
+gov.bf
+gov.bh
+gov.bm
+gov.bo
+gov.br
+gov.bs
+gov.bt
+gov.by
+gov.bz
+gov.cd
+gov.cl
+gov.cm
+gov.cn
+gov.co
+gov.cu
+gov.cx
+gov.dm
+gov.do
+gov.dz
+gov.ec
+gov.ee
+gov.eg
+gov.ge
+gov.gg
+gov.gh
+gov.gi
+gov.gn
+gov.gr
+gov.hk
+gov.ie
+gov.im
+gov.in
+gov.iq
+gov.ir
+gov.is
+gov.it
+gov.je
+gov.jo
+gov.kg
+gov.ki
+gov.km
+gov.kn
+gov.kp
+gov.ky
+gov.kz
+gov.la
+gov.lb
+gov.lc
+gov.lk
+gov.lr
+gov.lt
+gov.lv
+gov.ly
+gov.ma
+gov.me
+gov.mg
+gov.mk
+gov.ml
+gov.mn
+gov.mo
+gov.mr
+gov.mu
+gov.mv
+gov.mw
+gov.my
+gov.ng
+gov.nr
+gov.ph
+gov.pk
+gov.pl
+gov.pn
+gov.pr
+gov.ps
+gov.pt
+gov.py
+gov.qa
+gov.rs
+gov.ru
+gov.rw
+gov.sa
+gov.sb
+gov.sc
+gov.sd
+gov.sg
+gov.sh
+gov.sl
+gov.st
+gov.sx
+gov.sy
+gov.tj
+gov.tl
+gov.tm
+gov.tn
+gov.to
+gov.tt
+gov.tw
+gov.ua
+gov.vc
+gov.ve
+gov.vn
+gov.ws
+gub.uy
+
+//non-US mil
+mil.ac
+mil.ae
+mil.al
+mil.az
+mil.ba
+mil.bo
+mil.br
+mil.by
+mil.cl
+mil.cn
+mil.co
+mil.do
+mil.ec
+mil.eg
+mil.ge
+mil.gh
+mil.gt
+mil.hn
+mil.id
+mil.in
+mil.iq
+mil.jo
+mil.kg
+mil.km
+mil.kr
+mil.kz
+mil.lv
+mil.mg
+mil.mv
+mil.my
+mil.no
+mil.pe
+mil.ph
+mil.pl
+mil.py
+mil.qa
+mil.ru
+mil.rw
+mil.sh
+mil.st
+mil.sy
+mil.tj
+mil.tm
+mil.to
+mil.tw
+mil.tz
+mil.uy
+mil.vc
+mil.ve
+
+// US State, County, Local
+boudercounty.org
+ci.champaign.il.us
+ci.longmont.co.us
+sfgov.org
+state.de.us
+state.or.us

data/lib/gman.rb

@@ -3,7 +3,7 @@ require 'yaml'
 
 module Gman
 
-  VERSION='0.0.2'
+  VERSION='0.0.3'
 
   class << self
 
@@ -18,35 +18,22 @@ module Gman
     # Returns boolean true if a government domain
     def valid?(text)
       return false if text.nil?
-      text.strip!
+      domain = get_domain text
 
-      begin
-        domain = get_domain(text)
-        return false if domain.nil?
-
-        match_government_domain?(domain)
-
-      rescue PublicSuffix::DomainInvalid => di
-        false
-
-      rescue PublicSuffix::DomainNotAllowed => dna
-        false
-      end
+      # check using public suffix's standard logic
+      rule = list.find domain
+      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
 
-    # Checks the TLD (e.g., .gov) or TLD+SLD (e.g., .gov.uk)
-    # Against list of known government domains
-    def match_government_domain?(domain)
-      domains.include?(domain.tld) || domains.include?("#{domain.tld}.#{domain.sld}")
-    end
-
-    # Parses YML domain list into an array
-    # TODO: Cache this
-    #
-    # Returns an array of TLD and TLD+SLD known government domains
-    def domains
-       YAML.load_file File.expand_path("../domains.yml", __FILE__)
+    # returns an instance of our custom public suffix list
+    # list behaves like PublicSuffix::List but is limited to our whitelisted domains
+    def list
+      @list || PublicSuffix::List::parse( File.new(File.join(File.dirname(__FILE__), "domains.txt"), "r:utf-8"))
     end
 
     # Get the FQDN name from a URL or email address.
@@ -54,7 +41,7 @@ module Gman
     # 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)
-      PublicSuffix.parse text.downcase.match(domain_regex).captures.first
+      text.strip.downcase.match(domain_regex).captures.first
     rescue
       return nil
     end

data/test/test_gman.rb

@@ -1,15 +1,15 @@
 require 'helper'
 
-VALID = ["foo.gov", "http://foo.mil", "foo@bar.gc.ca", "foo.gov.au", "http://www.foo.gouv.fr"]
-INVALID = ["foo.bar.com", "bar@foo.biz", "http://www.foo.biz", "foo.uk", "gov"]
+VALID = ["foo.gov", "http://foo.mil", "foo@bar.gc.ca", "foo.gov.au", "http://www.foo.gouv.fr", "foo@ci.champaign.il.us", "foo.bar.baz.gov.au"]
+INVALID = ["foo.bar.com", "bar@foo.biz", "http://www.foo.biz", "foo.uk", "gov", "foo@k12.champaign.il.us"]
 
 class TestGman < Test::Unit::TestCase
   should "recognize government email addresses and domains" do
     VALID.each do |test|
-      assert_equal Gman::is_government?(test), true
+      assert_equal true, Gman::valid?(test), "#{test} should be detected as a valid government domain"
     end
     INVALID.each do |test|
-      assert_equal Gman::is_government?(test), false
+      assert_equal false, Gman::valid?(test), "#{test} should be detected as an invalid government domain"
     end
   end
 end

metadata

@@ -1,30 +1,27 @@
 --- !ruby/object:Gem::Specification
 name: gman
 version: !ruby/object:Gem::Version
-  version: 0.0.2
-  prerelease: 
+  version: 0.0.3
 platform: ruby
 authors:
 - Ben Balter
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2013-08-30 00:00:00.000000000 Z
+date: 2013-09-30 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: public_suffix
   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'
 description: A ruby gem to check if the owner of a given email address is working
@@ -39,7 +36,7 @@ files:
 - CONTRIBUTING.md
 - LICENSE
 - lib/gman.rb
-- lib/domains.yml
+- lib/domains.txt
 - script/build
 - script/release
 - gman.gemspec
@@ -50,26 +47,25 @@ files:
 homepage: https://github.com/benbalter/gman
 licenses:
 - MIT
+metadata: {}
 post_install_message: 
 rdoc_options: []
 require_paths:
 - lib
 required_ruby_version: !ruby/object:Gem::Requirement
-  none: false
   requirements:
-  - - ! '>='
+  - - '>='
     - !ruby/object:Gem::Version
       version: '0'
 required_rubygems_version: !ruby/object:Gem::Requirement
-  none: false
   requirements:
-  - - ! '>='
+  - - '>='
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 1.8.23
+rubygems_version: 2.0.3
 signing_key: 
-specification_version: 3
+specification_version: 4
 summary: Check if a given domain or email address belong to a governemnt entity
 test_files: []

data/lib/domains.yml

@@ -1,184 +0,0 @@
----
-- fed.us
-- gc.ca
-- gob.bo
-- gob.cl
-- gob.do
-- gob.ec
-- gob.es
-- gob.gt
-- gob.hn
-- gob.mx
-- gob.pa
-- gob.pe
-- gob.pk
-- gouv.bj
-- gouv.ci
-- gouv.fr
-- gouv.ht
-- gouv.km
-- gouv.ml
-- gouv.rw
-- gouv.sn
-- gov
-- gov.ac
-- gov.ae
-- gov.af
-- gov.al
-- gov.as
-- gov.au
-- gov.az
-- gov.ba
-- gov.bb
-- gov.bf
-- gov.bh
-- gov.bm
-- gov.bo
-- gov.br
-- gov.bs
-- gov.bt
-- gov.by
-- gov.bz
-- gov.cd
-- gov.cl
-- gov.cm
-- gov.cn
-- gov.co
-- gov.cu
-- gov.cx
-- gov.dm
-- gov.do
-- gov.dz
-- gov.ec
-- gov.ee
-- gov.eg
-- gov.ge
-- gov.gg
-- gov.gh
-- gov.gi
-- gov.gn
-- gov.gr
-- gov.hk
-- gov.ie
-- gov.im
-- gov.in
-- gov.iq
-- gov.ir
-- gov.is
-- gov.it
-- gov.je
-- gov.jo
-- gov.kg
-- gov.ki
-- gov.km
-- gov.kn
-- gov.kp
-- gov.ky
-- gov.kz
-- gov.la
-- gov.lb
-- gov.lc
-- gov.lk
-- gov.lr
-- gov.lt
-- gov.lv
-- gov.ly
-- gov.ma
-- gov.me
-- gov.mg
-- gov.mk
-- gov.ml
-- gov.mn
-- gov.mo
-- gov.mr
-- gov.mu
-- gov.mv
-- gov.mw
-- gov.my
-- gov.ng
-- gov.nr
-- gov.ph
-- gov.pk
-- gov.pl
-- gov.pn
-- gov.pr
-- gov.ps
-- gov.pt
-- gov.py
-- gov.qa
-- gov.rs
-- gov.ru
-- gov.rw
-- gov.sa
-- gov.sb
-- gov.sc
-- gov.sd
-- gov.sg
-- gov.sh
-- gov.sl
-- gov.st
-- gov.sx
-- gov.sy
-- gov.tj
-- gov.tl
-- gov.tm
-- gov.tn
-- gov.to
-- gov.tt
-- gov.tw
-- gov.ua
-- gov.vc
-- gov.ve
-- gov.vn
-- gov.ws
-- gub.uy
-- mil
-- mil.ac
-- mil.ae
-- mil.al
-- mil.az
-- mil.ba
-- mil.bo
-- mil.br
-- mil.by
-- mil.cl
-- mil.cn
-- mil.co
-- mil.do
-- mil.ec
-- mil.eg
-- mil.ge
-- mil.gh
-- mil.gt
-- mil.hn
-- mil.id
-- mil.in
-- mil.iq
-- mil.jo
-- mil.kg
-- mil.km
-- mil.kr
-- mil.kz
-- mil.lv
-- mil.mg
-- mil.mv
-- mil.my
-- mil.no
-- mil.pe
-- mil.ph
-- mil.pl
-- mil.py
-- mil.qa
-- mil.ru
-- mil.rw
-- mil.sh
-- mil.st
-- mil.sy
-- mil.tj
-- mil.tm
-- mil.to
-- mil.tw
-- mil.tz
-- mil.uy
-- mil.vc
-- mil.ve