public_suffix 1.0.0.rc1
Sign up to get free protection for your applications and to get access to all the features.
- data/.gemtest +0 -0
- data/.gitignore +4 -0
- data/.travis.yml +11 -0
- data/.yardopts +2 -0
- data/CHANGELOG.md +134 -0
- data/Gemfile +4 -0
- data/Gemfile.lock +22 -0
- data/LICENSE +22 -0
- data/README.md +151 -0
- data/Rakefile +109 -0
- data/lib/public_suffix.rb +134 -0
- data/lib/public_suffix/definitions.txt +5190 -0
- data/lib/public_suffix/domain.rb +387 -0
- data/lib/public_suffix/errors.rb +57 -0
- data/lib/public_suffix/list.rb +283 -0
- data/lib/public_suffix/rule.rb +373 -0
- data/lib/public_suffix/rule_list.rb +14 -0
- data/lib/public_suffix/version.rb +23 -0
- data/public_suffix.gemspec +37 -0
- data/test/acceptance_test.rb +36 -0
- data/test/test_helper.rb +6 -0
- data/test/unit/domain_test.rb +170 -0
- data/test/unit/errors_test.rb +23 -0
- data/test/unit/list_test.rb +193 -0
- data/test/unit/public_suffix_test.rb +85 -0
- data/test/unit/rule_test.rb +307 -0
- metadata +111 -0
@@ -0,0 +1,373 @@
|
|
1
|
+
#--
|
2
|
+
# Public Suffix
|
3
|
+
#
|
4
|
+
# Domain name parser based on the Public Suffix List.
|
5
|
+
#
|
6
|
+
# Copyright (c) 2009-2011 Simone Carletti <weppos@weppos.net>
|
7
|
+
#++
|
8
|
+
|
9
|
+
|
10
|
+
module PublicSuffix
|
11
|
+
|
12
|
+
# A Rule is a special object which holds a single definition
|
13
|
+
# of the Public Suffix List.
|
14
|
+
#
|
15
|
+
# There are 3 types of ruleas, each one represented by a specific
|
16
|
+
# subclass within the +PublicSuffix::Rule+ namespace.
|
17
|
+
#
|
18
|
+
# To create a new Rule, use the {PublicSuffix::Rule#factory} method.
|
19
|
+
#
|
20
|
+
# PublicSuffix::Rule.factory("ar")
|
21
|
+
# # => #<PublicSuffix::Rule::Normal>
|
22
|
+
#
|
23
|
+
class Rule
|
24
|
+
|
25
|
+
# Takes the +name+ of the rule, detects the specific rule class
|
26
|
+
# and creates a new instance of that class.
|
27
|
+
# The +name+ becomes the rule +value+.
|
28
|
+
#
|
29
|
+
# @param [String] name The rule definition.
|
30
|
+
#
|
31
|
+
# @return [PublicSuffix::Rule::*] A rule instance.
|
32
|
+
#
|
33
|
+
# @example Creates a Normal rule
|
34
|
+
# PublicSuffix::Rule.factory("ar")
|
35
|
+
# # => #<PublicSuffix::Rule::Normal>
|
36
|
+
#
|
37
|
+
# @example Creates a Wildcard rule
|
38
|
+
# PublicSuffix::Rule.factory("*.ar")
|
39
|
+
# # => #<PublicSuffix::Rule::Wildcard>
|
40
|
+
#
|
41
|
+
# @example Creates an Exception rule
|
42
|
+
# PublicSuffix::Rule.factory("!congresodelalengua3.ar")
|
43
|
+
# # => #<PublicSuffix::Rule::Exception>
|
44
|
+
#
|
45
|
+
def self.factory(name)
|
46
|
+
klass = case name.to_s[0..0]
|
47
|
+
when "*" then "wildcard"
|
48
|
+
when "!" then "exception"
|
49
|
+
else "normal"
|
50
|
+
end
|
51
|
+
const_get(klass.capitalize).new(name)
|
52
|
+
end
|
53
|
+
|
54
|
+
|
55
|
+
#
|
56
|
+
# = Abstract rule class
|
57
|
+
#
|
58
|
+
# This represent the base class for a Rule definition
|
59
|
+
# in the {Public Suffix List}[http://publicsuffix.org].
|
60
|
+
#
|
61
|
+
# This is intended to be an Abstract class
|
62
|
+
# and you shouldn't create a direct instance. The only purpose
|
63
|
+
# of this class is to expose a common interface
|
64
|
+
# for all the available subclasses.
|
65
|
+
#
|
66
|
+
# * {PublicSuffix::Rule::Normal}
|
67
|
+
# * {PublicSuffix::Rule::Exception}
|
68
|
+
# * {PublicSuffix::Rule::Wildcard}
|
69
|
+
#
|
70
|
+
# == Properties
|
71
|
+
#
|
72
|
+
# A rule is composed by 4 properties:
|
73
|
+
#
|
74
|
+
# name - The name of the rule, corresponding to the rule definition
|
75
|
+
# in the public suffix list
|
76
|
+
# value - The value, a normalized version of the rule name.
|
77
|
+
# The normalization process depends on rule tpe.
|
78
|
+
# type - The rule type (:normal, :wildcard, :exception)
|
79
|
+
# labels - The canonicalized rule name
|
80
|
+
#
|
81
|
+
# Here's an example
|
82
|
+
#
|
83
|
+
# PublicSuffix::Rule.factory("*.google.com")
|
84
|
+
# #<PublicSuffix::Rule::Wildcard:0x1015c14b0
|
85
|
+
# @labels=["com", "google"],
|
86
|
+
# @name="*.google.com",
|
87
|
+
# @type=:wildcard,
|
88
|
+
# @value="google.com"
|
89
|
+
# >
|
90
|
+
#
|
91
|
+
# == Rule Creation
|
92
|
+
#
|
93
|
+
# The best way to create a new rule is passing the rule name
|
94
|
+
# to the <tt>PublicSuffix::Rule.factory</tt> method.
|
95
|
+
#
|
96
|
+
# PublicSuffix::Rule.factory("com")
|
97
|
+
# # => PublicSuffix::Rule::Normal
|
98
|
+
#
|
99
|
+
# PublicSuffix::Rule.factory("*.com")
|
100
|
+
# # => PublicSuffix::Rule::Wildcard
|
101
|
+
#
|
102
|
+
# This method will detect the rule type and create an instance
|
103
|
+
# from the proper rule class.
|
104
|
+
#
|
105
|
+
# == Rule Usage
|
106
|
+
#
|
107
|
+
# A rule describes the composition of a domain name
|
108
|
+
# and explains how to tokenize the domain name
|
109
|
+
# into tld, sld and trd.
|
110
|
+
#
|
111
|
+
# To use a rule, you first need to be sure the domain you want to tokenize
|
112
|
+
# can be handled by the current rule.
|
113
|
+
# You can use the <tt>#match?</tt> method.
|
114
|
+
#
|
115
|
+
# rule = PublicSuffix::Rule.factory("com")
|
116
|
+
#
|
117
|
+
# rule.match?("google.com")
|
118
|
+
# # => true
|
119
|
+
#
|
120
|
+
# rule.match?("google.com")
|
121
|
+
# # => false
|
122
|
+
#
|
123
|
+
# Rule order is significant. A domain can match more than one rule.
|
124
|
+
# See the {Public Suffix Documentation}[http://publicsuffix.org/format/]
|
125
|
+
# to learn more about rule priority.
|
126
|
+
#
|
127
|
+
# When you have the right rule, you can use it to tokenize the domain name.
|
128
|
+
#
|
129
|
+
# rule = PublicSuffix::Rule.factory("com")
|
130
|
+
#
|
131
|
+
# rule.decompose("google.com")
|
132
|
+
# # => ["google", "com"]
|
133
|
+
#
|
134
|
+
# rule.decompose("www.google.com")
|
135
|
+
# # => ["www.google", "com"]
|
136
|
+
#
|
137
|
+
# @abstract
|
138
|
+
#
|
139
|
+
class Base
|
140
|
+
|
141
|
+
attr_reader :name, :value, :type, :labels
|
142
|
+
|
143
|
+
# Initializes a new rule with name and value.
|
144
|
+
# If value is +nil+, name also becomes the value for this rule.
|
145
|
+
#
|
146
|
+
# @param [String] name
|
147
|
+
# The name of the rule
|
148
|
+
# @param [String] value
|
149
|
+
# The value of the rule. If nil, defaults to +name+.
|
150
|
+
#
|
151
|
+
def initialize(name, value = nil)
|
152
|
+
@name = name.to_s
|
153
|
+
@value = value || @name
|
154
|
+
@type = self.class.name.split("::").last.downcase.to_sym
|
155
|
+
@labels = Domain.domain_to_labels(@value)
|
156
|
+
end
|
157
|
+
|
158
|
+
# Checks whether this rule is equal to <tt>other</tt>.
|
159
|
+
#
|
160
|
+
# @param [PublicSuffix::Rule::*] other
|
161
|
+
# The rule to compare.
|
162
|
+
#
|
163
|
+
# @return [Boolean]
|
164
|
+
# Returns true if this rule and other are instances of the same class
|
165
|
+
# and has the same value, false otherwise.
|
166
|
+
def ==(other)
|
167
|
+
return false unless other.is_a?(self.class)
|
168
|
+
self.equal?(other) ||
|
169
|
+
self.name == other.name
|
170
|
+
end
|
171
|
+
alias :eql? :==
|
172
|
+
|
173
|
+
|
174
|
+
# Checks if this rule matches +domain+.
|
175
|
+
#
|
176
|
+
# @param [String, #to_s] domain
|
177
|
+
# The domain name to check.
|
178
|
+
#
|
179
|
+
# @return [Boolean]
|
180
|
+
#
|
181
|
+
# @example
|
182
|
+
# rule = Rule.factory("com")
|
183
|
+
# # #<PublicSuffix::Rule::Normal>
|
184
|
+
# rule.match?("example.com")
|
185
|
+
# # => true
|
186
|
+
# rule.match?("example.net")
|
187
|
+
# # => false
|
188
|
+
#
|
189
|
+
def match?(domain)
|
190
|
+
l1 = labels
|
191
|
+
l2 = Domain.domain_to_labels(domain)
|
192
|
+
odiff(l1, l2).empty?
|
193
|
+
end
|
194
|
+
|
195
|
+
# Checks if this rule allows +domain+.
|
196
|
+
#
|
197
|
+
# @param [String, #to_s] domain
|
198
|
+
# The domain name to check.
|
199
|
+
#
|
200
|
+
# @return [Boolean]
|
201
|
+
#
|
202
|
+
# @example
|
203
|
+
# rule = Rule.factory("*.do")
|
204
|
+
# # => #<PublicSuffix::Rule::Wildcard>
|
205
|
+
# rule.allow?("example.do")
|
206
|
+
# # => false
|
207
|
+
# rule.allow?("www.example.do")
|
208
|
+
# # => true
|
209
|
+
#
|
210
|
+
def allow?(domain)
|
211
|
+
!decompose(domain).last.nil?
|
212
|
+
end
|
213
|
+
|
214
|
+
|
215
|
+
# Gets the length of this rule for comparison.
|
216
|
+
# The length usually matches the number of rule +parts+.
|
217
|
+
#
|
218
|
+
# Subclasses might actually override this method.
|
219
|
+
#
|
220
|
+
# @return [Integer] The number of parts.
|
221
|
+
def length
|
222
|
+
parts.length
|
223
|
+
end
|
224
|
+
|
225
|
+
#
|
226
|
+
# @raise [NotImplementedError]
|
227
|
+
# @abstract
|
228
|
+
def parts
|
229
|
+
raise NotImplementedError
|
230
|
+
end
|
231
|
+
|
232
|
+
#
|
233
|
+
# @param [String, #to_s] domain
|
234
|
+
# The domain name to decompose.
|
235
|
+
#
|
236
|
+
# @return [Array<String, nil>]
|
237
|
+
#
|
238
|
+
# @raise [NotImplementedError]
|
239
|
+
# @abstract
|
240
|
+
def decompose(domain)
|
241
|
+
raise NotImplementedError
|
242
|
+
end
|
243
|
+
|
244
|
+
|
245
|
+
private
|
246
|
+
|
247
|
+
def odiff(one, two)
|
248
|
+
ii = 0
|
249
|
+
while(ii < one.size && one[ii] == two[ii])
|
250
|
+
ii += 1
|
251
|
+
end
|
252
|
+
one[ii..one.length]
|
253
|
+
end
|
254
|
+
|
255
|
+
end
|
256
|
+
|
257
|
+
class Normal < Base
|
258
|
+
|
259
|
+
# Initializes a new rule with +name+.
|
260
|
+
#
|
261
|
+
# @param [String] name
|
262
|
+
# The name of this rule.
|
263
|
+
#
|
264
|
+
def initialize(name)
|
265
|
+
super(name, name)
|
266
|
+
end
|
267
|
+
|
268
|
+
# dot-split rule value and returns all rule parts
|
269
|
+
# in the order they appear in the value.
|
270
|
+
#
|
271
|
+
# @return [Array<String>]
|
272
|
+
def parts
|
273
|
+
@parts ||= @value.split(".")
|
274
|
+
end
|
275
|
+
|
276
|
+
# Decomposes the domain according to rule properties.
|
277
|
+
#
|
278
|
+
# @param [String, #to_s] domain
|
279
|
+
# The domain name to decompose.
|
280
|
+
#
|
281
|
+
# @return [Array<String>]
|
282
|
+
# The array with [trd + sld, tld].
|
283
|
+
#
|
284
|
+
def decompose(domain)
|
285
|
+
domain.to_s.chomp(".") =~ /^(.*)\.(#{parts.join('\.')})$/
|
286
|
+
[$1, $2]
|
287
|
+
end
|
288
|
+
|
289
|
+
end
|
290
|
+
|
291
|
+
class Wildcard < Base
|
292
|
+
|
293
|
+
# Initializes a new rule with +name+.
|
294
|
+
#
|
295
|
+
# @param [String] name
|
296
|
+
# The name of this rule.
|
297
|
+
#
|
298
|
+
def initialize(name)
|
299
|
+
super(name, name.to_s[2..-1])
|
300
|
+
end
|
301
|
+
|
302
|
+
# dot-split rule value and returns all rule parts
|
303
|
+
# in the order they appear in the value.
|
304
|
+
#
|
305
|
+
# @return [Array<String>]
|
306
|
+
def parts
|
307
|
+
@parts ||= @value.split(".")
|
308
|
+
end
|
309
|
+
|
310
|
+
# Overwrites the default implementation to cope with
|
311
|
+
# the +*+ char.
|
312
|
+
#
|
313
|
+
# @return [Integer] The number of parts.
|
314
|
+
def length
|
315
|
+
parts.length + 1 # * counts as 1
|
316
|
+
end
|
317
|
+
|
318
|
+
# Decomposes the domain according to rule properties.
|
319
|
+
#
|
320
|
+
# @param [String, #to_s] domain
|
321
|
+
# The domain name to decompose.
|
322
|
+
#
|
323
|
+
# @return [Array<String>]
|
324
|
+
# The array with [trd + sld, tld].
|
325
|
+
#
|
326
|
+
def decompose(domain)
|
327
|
+
domain.to_s.chomp(".") =~ /^(.*)\.(.*?\.#{parts.join('\.')})$/
|
328
|
+
[$1, $2]
|
329
|
+
end
|
330
|
+
|
331
|
+
end
|
332
|
+
|
333
|
+
class Exception < Base
|
334
|
+
|
335
|
+
# Initializes a new rule with +name+.
|
336
|
+
#
|
337
|
+
# @param [String] name The name of this rule.
|
338
|
+
#
|
339
|
+
def initialize(name)
|
340
|
+
super(name, name.to_s[1..-1])
|
341
|
+
end
|
342
|
+
|
343
|
+
# dot-split rule value and returns all rule parts
|
344
|
+
# in the order they appear in the value.
|
345
|
+
# The leftmost label is not considered a label.
|
346
|
+
#
|
347
|
+
# See http://publicsuffix.org/format/:
|
348
|
+
# If the prevailing rule is a exception rule,
|
349
|
+
# modify it by removing the leftmost label.
|
350
|
+
#
|
351
|
+
# @return [Array<String>]
|
352
|
+
def parts
|
353
|
+
@parts ||= @value.split(".")[1..-1]
|
354
|
+
end
|
355
|
+
|
356
|
+
# Decomposes the domain according to rule properties.
|
357
|
+
#
|
358
|
+
# @param [String, #to_s] domain
|
359
|
+
# The domain name to decompose.
|
360
|
+
#
|
361
|
+
# @return [Array<String>]
|
362
|
+
# The array with [trd + sld, tld].
|
363
|
+
#
|
364
|
+
def decompose(domain)
|
365
|
+
domain.to_s.chomp(".") =~ /^(.*)\.(#{parts.join('\.')})$/
|
366
|
+
[$1, $2]
|
367
|
+
end
|
368
|
+
|
369
|
+
end
|
370
|
+
|
371
|
+
end
|
372
|
+
|
373
|
+
end
|
@@ -0,0 +1,14 @@
|
|
1
|
+
#--
|
2
|
+
# Public Suffix
|
3
|
+
#
|
4
|
+
# Domain name parser based on the Public Suffix List.
|
5
|
+
#
|
6
|
+
# Copyright (c) 2009-2011 Simone Carletti <weppos@weppos.net>
|
7
|
+
#++
|
8
|
+
|
9
|
+
|
10
|
+
warn("The PublicSuffix::RuleList object has been deprecated and will be removed in PublicSuffix 1.1. Please use PublicSuffix::List instead.")
|
11
|
+
|
12
|
+
module PublicSuffix
|
13
|
+
RuleList = List
|
14
|
+
end
|
@@ -0,0 +1,23 @@
|
|
1
|
+
#--
|
2
|
+
# Public Suffix
|
3
|
+
#
|
4
|
+
# Domain name parser based on the Public Suffix List.
|
5
|
+
#
|
6
|
+
# Copyright (c) 2009-2011 Simone Carletti <weppos@weppos.net>
|
7
|
+
#++
|
8
|
+
|
9
|
+
|
10
|
+
module PublicSuffix
|
11
|
+
|
12
|
+
module Version
|
13
|
+
MAJOR = 1
|
14
|
+
MINOR = 0
|
15
|
+
PATCH = 0
|
16
|
+
BUILD = "rc1"
|
17
|
+
|
18
|
+
STRING = [MAJOR, MINOR, PATCH, BUILD].compact.join(".")
|
19
|
+
end
|
20
|
+
|
21
|
+
VERSION = Version::STRING
|
22
|
+
|
23
|
+
end
|
@@ -0,0 +1,37 @@
|
|
1
|
+
# -*- encoding: utf-8 -*-
|
2
|
+
|
3
|
+
Gem::Specification.new do |s|
|
4
|
+
s.name = "public_suffix"
|
5
|
+
s.version = "1.0.0.rc1"
|
6
|
+
|
7
|
+
s.required_rubygems_version = Gem::Requirement.new("> 1.3.1") if s.respond_to? :required_rubygems_version=
|
8
|
+
s.authors = ["Simone Carletti"]
|
9
|
+
s.date = "2011-12-23"
|
10
|
+
s.description = "PublicSuffix can parse and decompose a domain name into top level domain, domain and subdomains."
|
11
|
+
s.email = "weppos@weppos.net"
|
12
|
+
s.files = [".gemtest", ".gitignore", ".travis.yml", ".yardopts", "CHANGELOG.md", "Gemfile", "Gemfile.lock", "LICENSE", "README.md", "Rakefile", "lib/public_suffix.rb", "lib/public_suffix/definitions.txt", "lib/public_suffix/domain.rb", "lib/public_suffix/errors.rb", "lib/public_suffix/list.rb", "lib/public_suffix/rule.rb", "lib/public_suffix/rule_list.rb", "lib/public_suffix/version.rb", "public_suffix.gemspec", "test/acceptance_test.rb", "test/test_helper.rb", "test/unit/domain_test.rb", "test/unit/errors_test.rb", "test/unit/list_test.rb", "test/unit/public_suffix_test.rb", "test/unit/rule_test.rb"]
|
13
|
+
s.homepage = "http://www.simonecarletti.com/code/public_suffix_service"
|
14
|
+
s.require_paths = ["lib"]
|
15
|
+
s.required_ruby_version = Gem::Requirement.new(">= 1.8.7")
|
16
|
+
s.rubygems_version = "1.8.11"
|
17
|
+
s.summary = "Domain name parser based in the Public Suffix List."
|
18
|
+
s.test_files = ["test/acceptance_test.rb", "test/test_helper.rb", "test/unit/domain_test.rb", "test/unit/errors_test.rb", "test/unit/list_test.rb", "test/unit/public_suffix_test.rb", "test/unit/rule_test.rb"]
|
19
|
+
|
20
|
+
if s.respond_to? :specification_version then
|
21
|
+
s.specification_version = 3
|
22
|
+
|
23
|
+
if Gem::Version.new(Gem::VERSION) >= Gem::Version.new('1.2.0') then
|
24
|
+
s.add_development_dependency(%q<rake>, [">= 0"])
|
25
|
+
s.add_development_dependency(%q<mocha>, [">= 0"])
|
26
|
+
s.add_development_dependency(%q<yard>, [">= 0"])
|
27
|
+
else
|
28
|
+
s.add_dependency(%q<rake>, [">= 0"])
|
29
|
+
s.add_dependency(%q<mocha>, [">= 0"])
|
30
|
+
s.add_dependency(%q<yard>, [">= 0"])
|
31
|
+
end
|
32
|
+
else
|
33
|
+
s.add_dependency(%q<rake>, [">= 0"])
|
34
|
+
s.add_dependency(%q<mocha>, [">= 0"])
|
35
|
+
s.add_dependency(%q<yard>, [">= 0"])
|
36
|
+
end
|
37
|
+
end
|