public_suffix_service 0.4.0 → 0.5.0
Sign up to get free protection for your applications and to get access to all the features.
- data/CHANGELOG.rdoc +7 -0
- data/README.rdoc +38 -12
- data/Rakefile +19 -8
- data/lib/public_suffix_service/domain.rb +106 -29
- data/lib/public_suffix_service/rule.rb +11 -14
- data/lib/public_suffix_service/rule_list.rb +50 -16
- data/lib/public_suffix_service/version.rb +2 -2
- data/lib/public_suffix_service.rb +10 -5
- data/public_suffix_service.gemspec +2 -2
- data/test/public_suffix_service/domain_test.rb +6 -1
- data/test/public_suffix_service/rule_list_test.rb +23 -1
- metadata +5 -5
data/CHANGELOG.rdoc
CHANGED
@@ -1,6 +1,13 @@
|
|
1
1
|
= Changelog
|
2
2
|
|
3
3
|
|
4
|
+
== Release 0.5.0
|
5
|
+
|
6
|
+
* CHANGED: Improve documentation for Domain#domain and Domain#subdomain (#1).
|
7
|
+
|
8
|
+
* CHANGED: Performance improvements (#2).
|
9
|
+
|
10
|
+
|
4
11
|
== Release 0.4.0
|
5
12
|
|
6
13
|
* CHANGED: Rename library from DomainName to PublicSuffixService to reduce the probability of name conflicts.
|
data/README.rdoc
CHANGED
@@ -1,13 +1,13 @@
|
|
1
1
|
= Public Suffix Service
|
2
2
|
|
3
|
-
Public Suffix Service is a Ruby domain name parser based on the Public Suffix List
|
3
|
+
*Public Suffix Service* is a Ruby domain name parser based on the {Public Suffix List}[http://publicsuffix.org].
|
4
4
|
|
5
5
|
|
6
6
|
== What is the Public Suffix List?
|
7
7
|
|
8
|
-
The Public Suffix List is a cross-vendor initiative to provide an accurate list of domain name suffixes.
|
8
|
+
The *Public Suffix List* is a cross-vendor initiative to provide an accurate list of domain name suffixes.
|
9
9
|
|
10
|
-
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.
|
10
|
+
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.
|
11
11
|
|
12
12
|
A "public suffix" is one under which Internet users can directly register names. Some examples of public suffixes are ".com", ".co.uk" and "pvt.k12.wy.us". The Public Suffix List is a list of all known public suffixes.
|
13
13
|
|
@@ -32,22 +32,22 @@ http://stackoverflow.com/questions/288810/get-the-subdomain-from-a-url
|
|
32
32
|
|
33
33
|
== Requirements
|
34
34
|
|
35
|
-
* Ruby >= 1.8.6
|
35
|
+
* Ruby >= 1.8.6 or Ruby 1.9.x
|
36
36
|
|
37
|
-
Successfully tested
|
37
|
+
Successfully tested with the following interpreters
|
38
38
|
|
39
39
|
* Ruby 1.8.6 / 1.8.7 / 1.9.1
|
40
|
-
* MacRuby
|
40
|
+
* MacRuby
|
41
41
|
* Ruby Enterprise Edition
|
42
42
|
|
43
43
|
|
44
44
|
== Installation
|
45
45
|
|
46
|
-
|
46
|
+
The best way to install *Public Suffix Service* is via {RubyGems}[http://www.rubygems.org].
|
47
47
|
|
48
48
|
$ gem install public_suffix_service
|
49
49
|
|
50
|
-
You might need administrator privileges on your system to install
|
50
|
+
You might need administrator privileges on your system to install the Gem.
|
51
51
|
|
52
52
|
|
53
53
|
== Usage
|
@@ -55,22 +55,32 @@ You might need administrator privileges on your system to install it.
|
|
55
55
|
Example domain without subdomains.
|
56
56
|
|
57
57
|
domain = PublicSuffixService.parse("google.com")
|
58
|
+
# => #<PublicSuffixService::Domain>
|
58
59
|
domain.tld
|
59
60
|
# => "com"
|
60
|
-
domain.
|
61
|
+
domain.sld
|
61
62
|
# => "google"
|
63
|
+
domain.trd
|
64
|
+
# => nil
|
65
|
+
domain.domain
|
66
|
+
# => "google.com"
|
62
67
|
domain.subdomain
|
63
68
|
# => nil
|
64
69
|
|
65
70
|
Example domain with subdomains.
|
66
71
|
|
67
72
|
domain = PublicSuffixService.parse("www.google.com")
|
73
|
+
# => #<PublicSuffixService::Domain>
|
68
74
|
domain.tld
|
69
75
|
# => "com"
|
70
|
-
domain.
|
76
|
+
domain.sld
|
71
77
|
# => "google"
|
72
|
-
domain.
|
78
|
+
domain.trd
|
73
79
|
# => "www"
|
80
|
+
domain.domain
|
81
|
+
# => "google.com"
|
82
|
+
domain.subdomain
|
83
|
+
# => "google.com"
|
74
84
|
|
75
85
|
Simple validation example.
|
76
86
|
|
@@ -89,6 +99,21 @@ Simple validation example.
|
|
89
99
|
Author:: {Simone Carletti}[http://www.simonecarletti.com/] <weppos@weppos.net>
|
90
100
|
|
91
101
|
|
102
|
+
== FeedBack and Bug reports
|
103
|
+
|
104
|
+
If you use this library and find yourself missing any functionality I have missed, please {let me know}[mailto:weppos@weppos.net].
|
105
|
+
|
106
|
+
Bug reports and Feature suggestions {are welcomed}[http://github.com/weppos/public_suffix_service/issues].
|
107
|
+
|
108
|
+
|
109
|
+
== More
|
110
|
+
|
111
|
+
* {Homepage}[http://www.simonecarletti.com/code/public_suffix_service]
|
112
|
+
* {Repository}[http://github.com/weppos/public_suffix_service]
|
113
|
+
* {API Documentation}[http://www.simonecarletti.com/code/public_suffix_service/api/] (RDoc)
|
114
|
+
* {Introducing the Public Suffix List library for Ruby}[http://www.simonecarletti.com/blog/2010/06/public-suffix-list-library-for-ruby/]
|
115
|
+
|
116
|
+
|
92
117
|
== Changelog
|
93
118
|
|
94
119
|
See the CHANGELOG.rdoc file for details.
|
@@ -96,4 +121,5 @@ See the CHANGELOG.rdoc file for details.
|
|
96
121
|
|
97
122
|
== License
|
98
123
|
|
99
|
-
Copyright (c) 2009-2010 Simone Carletti,
|
124
|
+
Copyright (c) 2009-2010 Simone Carletti,
|
125
|
+
*Public Suffix Service* is released under the MIT license.
|
data/Rakefile
CHANGED
@@ -1,10 +1,14 @@
|
|
1
1
|
require "rubygems"
|
2
2
|
require "rake/testtask"
|
3
|
-
require "rake/rdoctask"
|
4
3
|
require "rake/gempackagetask"
|
4
|
+
begin
|
5
|
+
require "hanna/rdoctask"
|
6
|
+
rescue LoadError
|
7
|
+
require "rake/rdoctask"
|
8
|
+
end
|
5
9
|
|
6
10
|
$:.unshift(File.dirname(__FILE__) + "/lib")
|
7
|
-
require
|
11
|
+
require "public_suffix_service"
|
8
12
|
|
9
13
|
|
10
14
|
# Common package properties
|
@@ -49,8 +53,8 @@ spec = Gem::Specification.new do |s|
|
|
49
53
|
s.email = "weppos@weppos.net"
|
50
54
|
s.homepage = "http://www.simonecarletti.com/code/public_suffix_service"
|
51
55
|
s.description = <<-EOD
|
52
|
-
Intelligent
|
53
|
-
|
56
|
+
Intelligent domain name parser based in the Public Suffic List. \
|
57
|
+
PublicSuffixService can parse and decompose a domain name into top level domain, \
|
54
58
|
domain and subdomains.
|
55
59
|
EOD
|
56
60
|
|
@@ -86,9 +90,9 @@ task :gemspec do
|
|
86
90
|
File.open(file, "w") {|f| f << spec.to_ruby }
|
87
91
|
end
|
88
92
|
|
89
|
-
desc "Remove any temporary products, including gemspec
|
93
|
+
desc "Remove any temporary products, including gemspec"
|
90
94
|
task :clean => [:clobber] do
|
91
|
-
rm "#{spec.name}.gemspec"
|
95
|
+
rm "#{spec.name}.gemspec" if File.file?("#{spec.name}.gemspec")
|
92
96
|
end
|
93
97
|
|
94
98
|
desc "Remove any generated file"
|
@@ -100,7 +104,7 @@ task :package => [:gemspec]
|
|
100
104
|
begin
|
101
105
|
require "rcov/rcovtask"
|
102
106
|
|
103
|
-
desc "Create a code coverage report
|
107
|
+
desc "Create a code coverage report"
|
104
108
|
Rcov::RcovTask.new do |t|
|
105
109
|
t.test_files = FileList["test/**/*_test.rb"]
|
106
110
|
t.ruby_opts << "-Itest -x mocha,rcov,Rakefile"
|
@@ -117,7 +121,7 @@ task :console do
|
|
117
121
|
end
|
118
122
|
|
119
123
|
begin
|
120
|
-
require
|
124
|
+
require "code_statistics"
|
121
125
|
desc "Show library's code statistics"
|
122
126
|
task :stats do
|
123
127
|
CodeStatistics.new(["Public Suffix Service", "lib"],
|
@@ -127,6 +131,13 @@ rescue LoadError
|
|
127
131
|
puts "CodeStatistics (Rails) is not available"
|
128
132
|
end
|
129
133
|
|
134
|
+
desc "Publish documentation to the site"
|
135
|
+
task :publish_rdoc => [:clobber_rdoc, :rdoc] do
|
136
|
+
ENV["username"] || raise(ArgumentError, "Missing ssh username")
|
137
|
+
sh "rsync -avz --delete rdoc/ #{ENV["username"]}@code:/var/www/apps/code/#{PKG_NAME}/api"
|
138
|
+
end
|
139
|
+
|
140
|
+
|
130
141
|
Dir["tasks/**/*.rake"].each do |file|
|
131
142
|
load(file)
|
132
143
|
end
|
@@ -18,6 +18,22 @@ module PublicSuffixService
|
|
18
18
|
|
19
19
|
class Domain
|
20
20
|
|
21
|
+
# Splits a string into its possible labels as a domain in reverse order
|
22
|
+
# from the input string.
|
23
|
+
# The input is not validated, but it is assumed to be a valid domain.
|
24
|
+
#
|
25
|
+
# domain - The String domain to be split.
|
26
|
+
#
|
27
|
+
# Examples
|
28
|
+
#
|
29
|
+
# domain_to_labels('google.com.uk')
|
30
|
+
# # => ['uk', 'com', 'google']
|
31
|
+
#
|
32
|
+
# Returns an Array of String representing the possible labels.
|
33
|
+
def self.domain_to_labels(domain)
|
34
|
+
domain.to_s.split(".").reverse
|
35
|
+
end
|
36
|
+
|
21
37
|
def initialize(*args, &block)
|
22
38
|
@tld, @sld, @trd = args
|
23
39
|
yield(self) if block_given?
|
@@ -61,10 +77,10 @@ module PublicSuffixService
|
|
61
77
|
#
|
62
78
|
# Examples
|
63
79
|
#
|
64
|
-
#
|
80
|
+
# PublicSuffixService::Domain.new("com", "google").name
|
65
81
|
# # => "google.com"
|
66
82
|
#
|
67
|
-
#
|
83
|
+
# PublicSuffixService::Domain.new("com", "google", "www").name
|
68
84
|
# # => "www.google.com"
|
69
85
|
#
|
70
86
|
# Returns a String with the domain name.
|
@@ -75,23 +91,78 @@ module PublicSuffixService
|
|
75
91
|
# Returns a domain-like representation of this object
|
76
92
|
# if the object is a <tt>domain?</tt>,
|
77
93
|
# <tt>nil</tt> otherwise.
|
94
|
+
#
|
95
|
+
# PublicSuffixService::Domain.new("com").domain
|
96
|
+
# # => nil
|
97
|
+
#
|
98
|
+
# PublicSuffixService::Domain.new("com", "google").domain
|
99
|
+
# # => "google.com"
|
100
|
+
#
|
101
|
+
# PublicSuffixService::Domain.new("com", "google", "www").domain
|
102
|
+
# # => "www.google.com"
|
103
|
+
#
|
104
|
+
# This method doesn't validate the input. It handles the domain
|
105
|
+
# as a valid domain name and simply applies the necessary transformations.
|
106
|
+
#
|
107
|
+
# # This is an invalid domain
|
108
|
+
# PublicSuffixService::Domain.new("zip", "google").domain
|
109
|
+
# # => "google.zip"
|
110
|
+
#
|
111
|
+
# This method returns a FQD, not just the domain part.
|
112
|
+
# To get the domain part, use <tt>#sld</tt> (aka second level domain).
|
113
|
+
#
|
114
|
+
# PublicSuffixService::Domain.new("com", "google", "www").domain
|
115
|
+
# # => "google.com"
|
116
|
+
#
|
117
|
+
# PublicSuffixService::Domain.new("com", "google", "www").sld
|
118
|
+
# # => "google"
|
119
|
+
#
|
120
|
+
# Returns a String or nil.
|
78
121
|
def domain
|
79
122
|
return unless domain?
|
80
123
|
[sld, tld].join(".")
|
81
124
|
end
|
82
125
|
|
83
|
-
# Returns a
|
126
|
+
# Returns a domain-like representation of this object
|
84
127
|
# if the object is a <tt>subdomain?</tt>,
|
85
128
|
# <tt>nil</tt> otherwise.
|
129
|
+
#
|
130
|
+
# PublicSuffixService::Domain.new("com").subdomain
|
131
|
+
# # => nil
|
132
|
+
#
|
133
|
+
# PublicSuffixService::Domain.new("com", "google").subdomain
|
134
|
+
# # => nil
|
135
|
+
#
|
136
|
+
# PublicSuffixService::Domain.new("com", "google", "www").subdomain
|
137
|
+
# # => "www.google.com"
|
138
|
+
#
|
139
|
+
# This method doesn't validate the input. It handles the domain
|
140
|
+
# as a valid domain name and simply applies the necessary transformations.
|
141
|
+
#
|
142
|
+
# # This is an invalid domain
|
143
|
+
# PublicSuffixService::Domain.new("zip", "google", "www").subdomain
|
144
|
+
# # => "www.google.zip"
|
145
|
+
#
|
146
|
+
# This method returns a FQD, not just the domain part.
|
147
|
+
# To get the domain part, use <tt>#tld</tt> (aka third level domain).
|
148
|
+
#
|
149
|
+
# PublicSuffixService::Domain.new("com", "google", "www").subdomain
|
150
|
+
# # => "www.google.com"
|
151
|
+
#
|
152
|
+
# PublicSuffixService::Domain.new("com", "google", "www").trd
|
153
|
+
# # => "www"
|
154
|
+
#
|
155
|
+
# Returns a String or nil.
|
86
156
|
def subdomain
|
87
157
|
return unless subdomain?
|
88
158
|
[trd, sld, tld].join(".")
|
89
159
|
end
|
90
160
|
|
91
|
-
# Gets the rule matching this domain
|
161
|
+
# Gets the rule matching this domain
|
162
|
+
# in the default PublicSuffixService::RuleList.
|
92
163
|
#
|
93
|
-
# Returns
|
94
|
-
# nil if no rule is found.
|
164
|
+
# Returns the PublicSuffixService::Rule::Base instance
|
165
|
+
# if a rule matches current domain, nil if no rule is found.
|
95
166
|
def rule
|
96
167
|
RuleList.default.find(name)
|
97
168
|
end
|
@@ -102,25 +173,26 @@ module PublicSuffixService
|
|
102
173
|
# This method doesn't actually validate the domain.
|
103
174
|
# It only checks whether the instance contains
|
104
175
|
# a value for the <tt>tld</tt> and <tt>sld</tt> attributes.
|
105
|
-
# If you also want to validate the domain,
|
176
|
+
# If you also want to validate the domain,
|
177
|
+
# use <tt>#valid_domain?</tt> instead.
|
106
178
|
#
|
107
179
|
# Examples
|
108
180
|
#
|
109
|
-
#
|
181
|
+
# PublicSuffixService::Domain.new("com").domain?
|
110
182
|
# # => false
|
111
183
|
#
|
112
|
-
#
|
184
|
+
# PublicSuffixService::Domain.new("com", "google").domain?
|
113
185
|
# # => true
|
114
186
|
#
|
115
|
-
#
|
187
|
+
# PublicSuffixService::Domain.new("com", "google", "www").domain?
|
116
188
|
# # => true
|
117
189
|
#
|
118
190
|
# # This is an invalid domain, but returns true
|
119
191
|
# # because this method doesn't validate the content.
|
120
|
-
#
|
192
|
+
# PublicSuffixService::Domain.new("zip", "google").domain?
|
121
193
|
# # => true
|
122
194
|
#
|
123
|
-
# Returns
|
195
|
+
# Returns Boolean.
|
124
196
|
def domain?
|
125
197
|
!(tld.nil? || sld.nil?)
|
126
198
|
end
|
@@ -130,36 +202,41 @@ module PublicSuffixService
|
|
130
202
|
# This method doesn't actually validate the subdomain.
|
131
203
|
# It only checks whether the instance contains
|
132
204
|
# a value for the <tt>tld</tt>, <tt>sld</tt> and <tt>trd</tt> attributes.
|
133
|
-
# If you also want to validate the domain,
|
205
|
+
# If you also want to validate the domain,
|
206
|
+
# use <tt>#valid_subdomain?</tt> instead.
|
134
207
|
#
|
135
208
|
# Examples
|
136
209
|
#
|
137
|
-
#
|
210
|
+
# PublicSuffixService::Domain.new("com").subdomain?
|
138
211
|
# # => false
|
139
212
|
#
|
140
|
-
#
|
213
|
+
# PublicSuffixService::Domain.new("com", "google").subdomain?
|
141
214
|
# # => false
|
142
215
|
#
|
143
|
-
#
|
216
|
+
# PublicSuffixService::Domain.new("com", "google", "www").subdomain?
|
144
217
|
# # => true
|
145
218
|
#
|
146
219
|
# # This is an invalid domain, but returns true
|
147
220
|
# # because this method doesn't validate the content.
|
148
|
-
#
|
221
|
+
# PublicSuffixService::Domain.new("zip", "google", "www").subdomain?
|
149
222
|
# # => true
|
150
223
|
#
|
151
|
-
# Returns
|
224
|
+
# Returns Boolean.
|
152
225
|
def subdomain?
|
153
226
|
!(tld.nil? || sld.nil? || trd.nil?)
|
154
227
|
end
|
155
228
|
|
156
229
|
# Checks whether <tt>self</tt> is exclusively a domain,
|
157
230
|
# and not a subdomain.
|
231
|
+
#
|
232
|
+
# Returns Boolean.
|
158
233
|
def is_a_domain?
|
159
234
|
domain? && !subdomain?
|
160
235
|
end
|
161
236
|
|
162
237
|
# Checks whether <tt>self</tt> is exclusively a subdomain.
|
238
|
+
#
|
239
|
+
# Returns Boolean.
|
163
240
|
def is_a_subdomain?
|
164
241
|
subdomain?
|
165
242
|
end
|
@@ -170,7 +247,7 @@ module PublicSuffixService
|
|
170
247
|
# Note: this method triggers a new rule lookup in the default RuleList,
|
171
248
|
# which is a quite intensive task.
|
172
249
|
#
|
173
|
-
# Returns
|
250
|
+
# Returns Boolean.
|
174
251
|
def valid?
|
175
252
|
!rule.nil?
|
176
253
|
end
|
@@ -178,21 +255,21 @@ module PublicSuffixService
|
|
178
255
|
# Checks whether <tt>self</tt> looks like a domain and validates
|
179
256
|
# according to default <tt>RuleList</tt>.
|
180
257
|
#
|
181
|
-
# See also <tt
|
258
|
+
# See also <tt>#domain?</tt> and <tt>#valid?</tt>.
|
182
259
|
#
|
183
260
|
# Examples
|
184
261
|
#
|
185
|
-
#
|
262
|
+
# PublicSuffixService::Domain.new("com").domain?
|
186
263
|
# # => false
|
187
264
|
#
|
188
|
-
#
|
265
|
+
# PublicSuffixService::Domain.new("com", "google").domain?
|
189
266
|
# # => true
|
190
267
|
#
|
191
|
-
#
|
268
|
+
# PublicSuffixService::Domain.new("com", "google", "www").domain?
|
192
269
|
# # => true
|
193
270
|
#
|
194
271
|
# # This is an invalid domain
|
195
|
-
#
|
272
|
+
# PublicSuffixService::Domain.new("zip", "google").false?
|
196
273
|
# # => true
|
197
274
|
#
|
198
275
|
# Returns true if this instance looks like a domain and is valid.
|
@@ -203,21 +280,21 @@ module PublicSuffixService
|
|
203
280
|
# Checks whether <tt>self</tt> looks like a subdomain and validates
|
204
281
|
# according to default <tt>RuleList</tt>.
|
205
282
|
#
|
206
|
-
# See also <tt
|
283
|
+
# See also <tt>#subdomain?</tt> and <tt>#valid?</tt>.
|
207
284
|
#
|
208
285
|
# Examples
|
209
286
|
#
|
210
|
-
#
|
287
|
+
# PublicSuffixService::Domain.new("com").subdomain?
|
211
288
|
# # => false
|
212
289
|
#
|
213
|
-
#
|
290
|
+
# PublicSuffixService::Domain.new("com", "google").subdomain?
|
214
291
|
# # => false
|
215
292
|
#
|
216
|
-
#
|
293
|
+
# PublicSuffixService::Domain.new("com", "google", "www").subdomain?
|
217
294
|
# # => true
|
218
295
|
#
|
219
296
|
# # This is an invalid domain
|
220
|
-
#
|
297
|
+
# PublicSuffixService::Domain.new("zip", "google", "www").subdomain?
|
221
298
|
# # => false
|
222
299
|
#
|
223
300
|
# Returns true if this instance looks like a domain and is valid.
|
@@ -22,7 +22,7 @@ module PublicSuffixService
|
|
22
22
|
# and creates a new instance of that class.
|
23
23
|
# The <tt>name</tt> becomes the rule value.
|
24
24
|
#
|
25
|
-
# name - The rule
|
25
|
+
# name - The String rule definition.
|
26
26
|
#
|
27
27
|
# Examples
|
28
28
|
#
|
@@ -35,6 +35,7 @@ module PublicSuffixService
|
|
35
35
|
# PublicSuffixService::Rule.factory("!congresodelalengua3.ar")
|
36
36
|
# # => #<PublicSuffixService::Rule::Exception>
|
37
37
|
#
|
38
|
+
# Returns a rule instance, a kind of PublicSuffixService::Rule::Base.
|
38
39
|
def self.factory(name)
|
39
40
|
klass = case name.to_s[0..0]
|
40
41
|
when "*" then "wildcard"
|
@@ -137,12 +138,12 @@ module PublicSuffixService
|
|
137
138
|
@name = name.to_s
|
138
139
|
@value = value || @name
|
139
140
|
@type = self.class.name.split("::").last.downcase.to_sym
|
140
|
-
@labels = domain_to_labels(@value)
|
141
|
+
@labels = Domain.domain_to_labels(@value)
|
141
142
|
end
|
142
143
|
|
143
144
|
# Checks whether this rule is equal to <tt>other</tt>.
|
144
145
|
#
|
145
|
-
# other -
|
146
|
+
# other - The PublicSuffixService::Rule::Base to compare.
|
146
147
|
#
|
147
148
|
# Returns true if this rule and other are instances of the same class
|
148
149
|
# and has the same value, false otherwise.
|
@@ -156,13 +157,12 @@ module PublicSuffixService
|
|
156
157
|
|
157
158
|
# Checks whether this rule matches <tt>domain</tt>.
|
158
159
|
#
|
159
|
-
# domain -
|
160
|
+
# domain - The String domain name to check.
|
160
161
|
#
|
161
|
-
# Returns
|
162
|
-
# false otherwise.
|
162
|
+
# Returns Boolean.
|
163
163
|
def match?(domain)
|
164
164
|
l1 = labels
|
165
|
-
l2 = domain_to_labels(domain)
|
165
|
+
l2 = Domain.domain_to_labels(domain)
|
166
166
|
odiff(l1, l2).empty?
|
167
167
|
end
|
168
168
|
|
@@ -188,9 +188,6 @@ module PublicSuffixService
|
|
188
188
|
|
189
189
|
private
|
190
190
|
|
191
|
-
def domain_to_labels(domain)
|
192
|
-
domain.to_s.split(".").reverse
|
193
|
-
end
|
194
191
|
|
195
192
|
def odiff(one, two)
|
196
193
|
ii = 0
|
@@ -218,7 +215,7 @@ module PublicSuffixService
|
|
218
215
|
|
219
216
|
# Decomposes the domain according to rule properties.
|
220
217
|
#
|
221
|
-
# domain -
|
218
|
+
# domain - The String domain name to parse.
|
222
219
|
#
|
223
220
|
# Return an Array with [trd + sld, tld].
|
224
221
|
def decompose(domain)
|
@@ -248,7 +245,7 @@ module PublicSuffixService
|
|
248
245
|
|
249
246
|
# Decomposes the domain according to rule properties.
|
250
247
|
#
|
251
|
-
# domain -
|
248
|
+
# domain - The String domain name to parse.
|
252
249
|
#
|
253
250
|
# Return an Array with [trd + sld, tld].
|
254
251
|
def decompose(domain)
|
@@ -279,7 +276,7 @@ module PublicSuffixService
|
|
279
276
|
|
280
277
|
# Decomposes the domain according to rule properties.
|
281
278
|
#
|
282
|
-
# domain -
|
279
|
+
# domain - The String domain name to parse.
|
283
280
|
#
|
284
281
|
# Return an Array with [trd + sld, tld].
|
285
282
|
def decompose(domain)
|
@@ -291,4 +288,4 @@ module PublicSuffixService
|
|
291
288
|
|
292
289
|
end
|
293
290
|
|
294
|
-
end
|
291
|
+
end
|
@@ -51,17 +51,43 @@ module PublicSuffixService
|
|
51
51
|
include Enumerable
|
52
52
|
|
53
53
|
# Gets the list of rules.
|
54
|
-
# Each rule is expected to be a subclass of PublicSuffixService::Rule::Base.
|
55
54
|
#
|
56
|
-
# Returns
|
55
|
+
# Returns the Array of rule instances.
|
56
|
+
# Each rule is an instance of the proper corresponding of
|
57
|
+
# PublicSuffixService::Rule::Base.
|
57
58
|
attr_reader :list
|
58
59
|
|
60
|
+
# Gets the naive index, a hash that with the keys being the first label of
|
61
|
+
# every rule pointing to an array of integers (indexes of the rules in @list)
|
62
|
+
attr_reader :indexes
|
63
|
+
|
59
64
|
|
60
65
|
# Initializes an empty PublicSuffixService::RuleList.
|
61
66
|
# If block is given, yields on self.
|
62
67
|
def initialize(&block) # :yields: self
|
63
|
-
@list
|
68
|
+
@list = []
|
69
|
+
@indexes = {}
|
64
70
|
yield(self) if block_given?
|
71
|
+
create_index!
|
72
|
+
end
|
73
|
+
|
74
|
+
# Creates a naive index for @list. Just a hash that will tell
|
75
|
+
# us where the elements of @list are relative to its first
|
76
|
+
# Rule#labels element.
|
77
|
+
#
|
78
|
+
# For instance if @list[5] and @list[4] are the only elements of the list
|
79
|
+
# where Rule#labels.first is 'us' @indexes['us'] #=> [5,4], that way in
|
80
|
+
# select we can avoid mapping every single rule against the candidate domain.
|
81
|
+
#
|
82
|
+
# Returns nothing.
|
83
|
+
def create_index!
|
84
|
+
@list.map{|l| l.labels.first }.each_with_index do |elm, inx|
|
85
|
+
if !@indexes.has_key?(elm)
|
86
|
+
@indexes[elm] = [inx]
|
87
|
+
else
|
88
|
+
@indexes[elm] << inx
|
89
|
+
end
|
90
|
+
end
|
65
91
|
end
|
66
92
|
|
67
93
|
# Checks whether two lists are equal.
|
@@ -161,10 +187,15 @@ module PublicSuffixService
|
|
161
187
|
|
162
188
|
# Selects all the rules matching given domain.
|
163
189
|
#
|
164
|
-
#
|
165
|
-
#
|
190
|
+
# Will use @indexes to try only the rules that share the same first label,
|
191
|
+
# that will speed up things when using RuleList.find('foo') a lot.
|
192
|
+
#
|
193
|
+
# Returns an Array of rule instances.
|
194
|
+
# Each rule is an instance of the corresponding subclass of
|
195
|
+
# PublicSuffixService::Rule::Base.
|
166
196
|
def select(domain)
|
167
|
-
|
197
|
+
indices = (@indexes[ Domain.domain_to_labels(domain).first ] || [])
|
198
|
+
@list.values_at(*indices).select { |rule| rule.match?(domain) }
|
168
199
|
end
|
169
200
|
|
170
201
|
|
@@ -172,11 +203,11 @@ module PublicSuffixService
|
|
172
203
|
|
173
204
|
class << self
|
174
205
|
|
175
|
-
# Gets the default
|
176
|
-
# Initializes a new
|
177
|
-
#
|
206
|
+
# Gets the default PublicSuffixService::RuleList.
|
207
|
+
# Initializes a new PublicSuffixService::RuleList parsing the content
|
208
|
+
# of PublicSuffixService::RuleList.default_definition, if required.
|
178
209
|
#
|
179
|
-
# Returns
|
210
|
+
# Returns a PublicSuffixService::RuleList.
|
180
211
|
def default
|
181
212
|
@@default ||= parse(default_definition)
|
182
213
|
end
|
@@ -185,12 +216,12 @@ module PublicSuffixService
|
|
185
216
|
#
|
186
217
|
# value - The new PublicSuffixService::RuleList.
|
187
218
|
#
|
188
|
-
# Returns the
|
219
|
+
# Returns the PublicSuffixService::RuleList.
|
189
220
|
def default=(value)
|
190
221
|
@@default = value
|
191
222
|
end
|
192
223
|
|
193
|
-
# Sets the default
|
224
|
+
# Sets the default PublicSuffixService::RuleList to nil.
|
194
225
|
#
|
195
226
|
# Returns self.
|
196
227
|
def clear
|
@@ -201,16 +232,17 @@ module PublicSuffixService
|
|
201
232
|
# Resets the default <tt>PublicSuffixService::RuleList</tt> and reinitialize it
|
202
233
|
# parsing the content of <tt>PublicSuffixService::RuleList.default_definition</tt>.
|
203
234
|
#
|
204
|
-
# Returns
|
235
|
+
# Returns a PublicSuffixService::RuleList.
|
205
236
|
def reload
|
206
237
|
self.clear.default
|
207
238
|
end
|
208
239
|
|
209
240
|
# Gets the default definition list.
|
210
|
-
# Can be any <tt>IOStream</tt> including a <tt>File</tt>
|
241
|
+
# Can be any <tt>IOStream</tt> including a <tt>File</tt>
|
242
|
+
# or a simple <tt>String</tt>.
|
211
243
|
# The object must respond to <tt>#each_line</tt>.
|
212
244
|
#
|
213
|
-
# Returns
|
245
|
+
# Returns a File.
|
214
246
|
def default_definition
|
215
247
|
File.new(File.join(File.dirname(__FILE__), "definitions.dat"))
|
216
248
|
end
|
@@ -219,7 +251,9 @@ module PublicSuffixService
|
|
219
251
|
# Parse given <tt>input</tt> treating the content as Public Suffic List.
|
220
252
|
# See http://publicsuffix.org/format/ for more details about input format.
|
221
253
|
#
|
222
|
-
# Returns an Array of
|
254
|
+
# Returns an Array of rule instances.
|
255
|
+
# Each rule is an instance of the corresponding subclass of
|
256
|
+
# PublicSuffixService::Rule::Base.
|
223
257
|
def parse(input)
|
224
258
|
new do |list|
|
225
259
|
input.each_line do |line|
|
@@ -28,9 +28,12 @@ module PublicSuffixService
|
|
28
28
|
AUTHORS = ["Simone Carletti <weppos@weppos.net>"]
|
29
29
|
|
30
30
|
|
31
|
-
# Parses <tt>domain</tt> and returns
|
31
|
+
# Parses <tt>domain</tt> and returns the
|
32
|
+
# PubliSuffixService::Domain instance.
|
32
33
|
#
|
33
|
-
# domain -
|
34
|
+
# domain - The String domain name to parse.
|
35
|
+
#
|
36
|
+
# Examples
|
34
37
|
#
|
35
38
|
# PublicSuffixService.parse("google.com")
|
36
39
|
# # => #<PubliSuffixService::Domain ...>
|
@@ -45,6 +48,8 @@ module PublicSuffixService
|
|
45
48
|
# # => PublicSuffixService::InvalidDomain
|
46
49
|
#
|
47
50
|
# Raises PublicSuffixService::Error if domain is not a valid domain
|
51
|
+
#
|
52
|
+
# Returns the PubliSuffixService::Domain domain.
|
48
53
|
def self.parse(domain)
|
49
54
|
rule = RuleList.default.find(domain) || raise(InvalidDomain, "`#{domain}' is not a valid domain")
|
50
55
|
|
@@ -64,9 +69,9 @@ module PublicSuffixService
|
|
64
69
|
# Checks whether <tt>domain</tt> is a valid domain name.
|
65
70
|
#
|
66
71
|
# This method doesn't care whether domain is a domain or subdomain.
|
67
|
-
# The check is performed using the default
|
72
|
+
# The check is performed using the default PublicSuffixService::RuleList.
|
68
73
|
#
|
69
|
-
# domain -
|
74
|
+
# domain - The String domain name to parse.
|
70
75
|
#
|
71
76
|
# Examples
|
72
77
|
#
|
@@ -82,7 +87,7 @@ module PublicSuffixService
|
|
82
87
|
# PublicSuffixService.valid?("x.yz")
|
83
88
|
# # => false
|
84
89
|
#
|
85
|
-
# Returns
|
90
|
+
# Returns Boolean.
|
86
91
|
def self.valid?(domain)
|
87
92
|
!RuleList.default.find(domain).nil?
|
88
93
|
end
|
@@ -2,7 +2,7 @@
|
|
2
2
|
|
3
3
|
Gem::Specification.new do |s|
|
4
4
|
s.name = %q{public_suffix_service}
|
5
|
-
s.version = "0.
|
5
|
+
s.version = "0.4.0"
|
6
6
|
|
7
7
|
s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
|
8
8
|
s.authors = ["Simone Carletti"]
|
@@ -12,7 +12,7 @@ Gem::Specification.new do |s|
|
|
12
12
|
s.email = %q{weppos@weppos.net}
|
13
13
|
s.extra_rdoc_files = ["CHANGELOG.rdoc", "LICENSE.rdoc", "README.rdoc"]
|
14
14
|
s.files = ["Rakefile", "CHANGELOG.rdoc", "LICENSE.rdoc", "README.rdoc", "public_suffix_service.gemspec", "test/acceptance_test.rb", "test/public_suffix_service/domain_test.rb", "test/public_suffix_service/rule_list_test.rb", "test/public_suffix_service/rule_test.rb", "test/public_suffix_service_test.rb", "test/test_helper.rb", "lib/public_suffix_service/definitions.dat", "lib/public_suffix_service/domain.rb", "lib/public_suffix_service/errors.rb", "lib/public_suffix_service/rule.rb", "lib/public_suffix_service/rule_list.rb", "lib/public_suffix_service/version.rb", "lib/public_suffix_service.rb"]
|
15
|
-
s.homepage = %q{http://www.simonecarletti.com/code/
|
15
|
+
s.homepage = %q{http://www.simonecarletti.com/code/public_suffix_service}
|
16
16
|
s.rdoc_options = ["--main", "README.rdoc"]
|
17
17
|
s.require_paths = ["lib"]
|
18
18
|
s.rubygems_version = %q{1.3.7}
|
@@ -6,6 +6,11 @@ class PublicSuffixService::DomainTest < Test::Unit::TestCase
|
|
6
6
|
@klass = PublicSuffixService::Domain
|
7
7
|
end
|
8
8
|
|
9
|
+
def test_domain_to_lables
|
10
|
+
assert_equal %w{com live spaces someone}, PublicSuffixService::Domain.domain_to_labels('someone.spaces.live.com')
|
11
|
+
assert_equal %w{com zoho wiki leontina23samiko}, PublicSuffixService::Domain.domain_to_labels('leontina23samiko.wiki.zoho.com')
|
12
|
+
end
|
13
|
+
|
9
14
|
|
10
15
|
def test_initialize_with_tld
|
11
16
|
domain = @klass.new("com")
|
@@ -138,4 +143,4 @@ class PublicSuffixService::DomainTest < Test::Unit::TestCase
|
|
138
143
|
assert !@klass.new("com", "google").valid_subdomain?
|
139
144
|
end
|
140
145
|
|
141
|
-
end
|
146
|
+
end
|
@@ -16,6 +16,28 @@ class PublicSuffixService::RuleListTest < Test::Unit::TestCase
|
|
16
16
|
assert_equal 0, @list.length
|
17
17
|
end
|
18
18
|
|
19
|
+
def test_initialize_create_index_when_empty
|
20
|
+
assert_equal({}, @list.indexes)
|
21
|
+
end
|
22
|
+
|
23
|
+
def test_find__with_index
|
24
|
+
@list = PublicSuffixService::RuleList.parse(<<EOS)
|
25
|
+
// com : http://en.wikipedia.org/wiki/.com
|
26
|
+
com
|
27
|
+
|
28
|
+
// uk : http://en.wikipedia.org/wiki/.uk
|
29
|
+
*.uk
|
30
|
+
*.sch.uk
|
31
|
+
!bl.uk
|
32
|
+
!british-library.uk
|
33
|
+
EOS
|
34
|
+
|
35
|
+
assert !@list.indexes.empty?
|
36
|
+
assert_equal [1,2,3,4], @list.indexes.delete('uk')
|
37
|
+
assert_equal [0], @list.indexes.delete('com')
|
38
|
+
assert @list.indexes.empty?
|
39
|
+
end
|
40
|
+
|
19
41
|
|
20
42
|
def test_equality_with_self
|
21
43
|
list = PublicSuffixService::RuleList.new
|
@@ -179,4 +201,4 @@ EOS
|
|
179
201
|
assert_equal %w(ac com.ac ad *.ar !congresodelalengua3.ar).map { |name| PublicSuffixService::Rule.factory(name) }, list.to_a
|
180
202
|
end
|
181
203
|
|
182
|
-
end
|
204
|
+
end
|
metadata
CHANGED
@@ -1,13 +1,13 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: public_suffix_service
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
hash:
|
4
|
+
hash: 11
|
5
5
|
prerelease: false
|
6
6
|
segments:
|
7
7
|
- 0
|
8
|
-
-
|
8
|
+
- 5
|
9
9
|
- 0
|
10
|
-
version: 0.
|
10
|
+
version: 0.5.0
|
11
11
|
platform: ruby
|
12
12
|
authors:
|
13
13
|
- Simone Carletti
|
@@ -15,7 +15,7 @@ autorequire:
|
|
15
15
|
bindir: bin
|
16
16
|
cert_chain: []
|
17
17
|
|
18
|
-
date: 2010-
|
18
|
+
date: 2010-09-13 00:00:00 +02:00
|
19
19
|
default_executable:
|
20
20
|
dependencies:
|
21
21
|
- !ruby/object:Gem::Dependency
|
@@ -32,7 +32,7 @@ dependencies:
|
|
32
32
|
version: "0"
|
33
33
|
type: :development
|
34
34
|
version_requirements: *id001
|
35
|
-
description: " Intelligent
|
35
|
+
description: " Intelligent domain name parser based in the Public Suffic List. PublicSuffixService can parse and decompose a domain name into top level domain, domain and subdomains.\n"
|
36
36
|
email: weppos@weppos.net
|
37
37
|
executables: []
|
38
38
|
|