public_suffix 3.1.1 → 5.0.4
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/CHANGELOG.md +150 -52
- data/LICENSE.txt +1 -1
- data/README.md +37 -15
- data/SECURITY.md +25 -0
- data/data/list.txt +4775 -2310
- data/lib/public_suffix/domain.rb +1 -1
- data/lib/public_suffix/errors.rb +1 -1
- data/lib/public_suffix/list.rb +6 -6
- data/lib/public_suffix/rule.rb +17 -17
- data/lib/public_suffix/version.rb +5 -4
- data/lib/public_suffix.rb +12 -14
- metadata +16 -104
- data/.gitignore +0 -11
- data/.rubocop.yml +0 -36
- data/.rubocop_defaults.yml +0 -179
- data/.ruby-gemset +0 -1
- data/.travis.yml +0 -31
- data/Gemfile +0 -12
- data/Rakefile +0 -51
- data/bin/console +0 -15
- data/public_suffix.gemspec +0 -25
- data/test/.empty +0 -2
- data/test/acceptance_test.rb +0 -129
- data/test/benchmarks/bm_find.rb +0 -66
- data/test/benchmarks/bm_find_all.rb +0 -102
- data/test/benchmarks/bm_names.rb +0 -91
- data/test/benchmarks/bm_select.rb +0 -26
- data/test/benchmarks/bm_select_incremental.rb +0 -25
- data/test/benchmarks/bm_valid.rb +0 -101
- data/test/profilers/domain_profiler.rb +0 -12
- data/test/profilers/find_profiler.rb +0 -12
- data/test/profilers/find_profiler_jp.rb +0 -12
- data/test/profilers/initialization_profiler.rb +0 -11
- data/test/profilers/list_profsize.rb +0 -11
- data/test/profilers/object_binsize.rb +0 -57
- data/test/psl_test.rb +0 -52
- data/test/test_helper.rb +0 -18
- data/test/tests.txt +0 -98
- data/test/unit/domain_test.rb +0 -106
- data/test/unit/errors_test.rb +0 -25
- data/test/unit/list_test.rb +0 -241
- data/test/unit/public_suffix_test.rb +0 -188
- data/test/unit/rule_test.rb +0 -222
data/.travis.yml
DELETED
@@ -1,31 +0,0 @@
|
|
1
|
-
language: ruby
|
2
|
-
|
3
|
-
rvm:
|
4
|
-
- 2.3
|
5
|
-
- 2.4
|
6
|
-
- 2.5
|
7
|
-
- 2.6
|
8
|
-
- jruby-9.1.5.0
|
9
|
-
- ruby-head
|
10
|
-
|
11
|
-
env:
|
12
|
-
- COVERAGE=1
|
13
|
-
|
14
|
-
cache:
|
15
|
-
- bundler
|
16
|
-
|
17
|
-
matrix:
|
18
|
-
include:
|
19
|
-
- rvm: 2.1
|
20
|
-
before_install:
|
21
|
-
- gem install bundler -v '< 2.0'
|
22
|
-
- rvm: 2.2
|
23
|
-
before_install:
|
24
|
-
- gem install bundler -v '< 2.0'
|
25
|
-
allow_failures:
|
26
|
-
- rvm: ruby-head
|
27
|
-
- rvm: jruby-9.1.5.0
|
28
|
-
|
29
|
-
before_install:
|
30
|
-
- gem update --system
|
31
|
-
- gem install bundler
|
data/Gemfile
DELETED
data/Rakefile
DELETED
@@ -1,51 +0,0 @@
|
|
1
|
-
# frozen_string_literal: true
|
2
|
-
|
3
|
-
require "bundler/gem_tasks"
|
4
|
-
|
5
|
-
# By default, run tests and linter.
|
6
|
-
task default: [:test, :rubocop]
|
7
|
-
|
8
|
-
|
9
|
-
require "rake/testtask"
|
10
|
-
|
11
|
-
Rake::TestTask.new do |t|
|
12
|
-
t.libs = %w( lib test )
|
13
|
-
t.pattern = "test/**/*_test.rb"
|
14
|
-
t.verbose = !ENV["VERBOSE"].nil?
|
15
|
-
t.warning = !ENV["WARNING"].nil?
|
16
|
-
end
|
17
|
-
|
18
|
-
require "rubocop/rake_task"
|
19
|
-
|
20
|
-
RuboCop::RakeTask.new
|
21
|
-
|
22
|
-
|
23
|
-
require "yard/rake/yardoc_task"
|
24
|
-
|
25
|
-
YARD::Rake::YardocTask.new(:yardoc) do |y|
|
26
|
-
y.options = ["--output-dir", "yardoc"]
|
27
|
-
end
|
28
|
-
|
29
|
-
CLOBBER.include "yardoc"
|
30
|
-
|
31
|
-
|
32
|
-
task :benchmarks do
|
33
|
-
Dir["benchmarks/bm_*.rb"].each do |file|
|
34
|
-
sh "ruby #{file}"
|
35
|
-
end
|
36
|
-
end
|
37
|
-
task default: [:benchmarks] if ENV["BENCHMARKS"] == "1"
|
38
|
-
|
39
|
-
|
40
|
-
desc "Downloads the Public Suffix List file from the repository and stores it locally."
|
41
|
-
task :"update-list" do
|
42
|
-
require "net/http"
|
43
|
-
|
44
|
-
DEFINITION_URL = "https://raw.githubusercontent.com/publicsuffix/list/master/public_suffix_list.dat"
|
45
|
-
|
46
|
-
File.open("data/list.txt", "w+") do |f|
|
47
|
-
response = Net::HTTP.get_response(URI.parse(DEFINITION_URL))
|
48
|
-
response.body
|
49
|
-
f.write(response.body)
|
50
|
-
end
|
51
|
-
end
|
data/bin/console
DELETED
@@ -1,15 +0,0 @@
|
|
1
|
-
#!/usr/bin/env ruby
|
2
|
-
# frozen_string_literal: true
|
3
|
-
|
4
|
-
require "bundler/setup"
|
5
|
-
require "public_suffix"
|
6
|
-
|
7
|
-
# You can add fixtures and/or initialization code here to make experimenting
|
8
|
-
# with your gem easier. You can also use a different console, if you like.
|
9
|
-
|
10
|
-
# (If you use this, don't forget to add pry to your Gemfile!)
|
11
|
-
# require "pry"
|
12
|
-
# Pry.start
|
13
|
-
|
14
|
-
require "irb"
|
15
|
-
IRB.start
|
data/public_suffix.gemspec
DELETED
@@ -1,25 +0,0 @@
|
|
1
|
-
# -*- encoding: utf-8 -*-
|
2
|
-
$LOAD_PATH.push File.expand_path("../lib", __FILE__)
|
3
|
-
require "public_suffix/version"
|
4
|
-
|
5
|
-
Gem::Specification.new do |s|
|
6
|
-
s.name = "public_suffix"
|
7
|
-
s.version = PublicSuffix::VERSION
|
8
|
-
s.authors = ["Simone Carletti"]
|
9
|
-
s.email = ["weppos@weppos.net"]
|
10
|
-
s.homepage = "https://simonecarletti.com/code/publicsuffix-ruby"
|
11
|
-
s.summary = "Domain name parser based on the Public Suffix List."
|
12
|
-
s.description = "PublicSuffix can parse and decompose a domain name into top level domain, domain and subdomains."
|
13
|
-
s.licenses = ["MIT"]
|
14
|
-
|
15
|
-
s.required_ruby_version = ">= 2.1"
|
16
|
-
|
17
|
-
s.require_paths = ["lib"]
|
18
|
-
s.files = `git ls-files`.split("\n")
|
19
|
-
s.test_files = `git ls-files -- {test,spec,features}/*`.split("\n")
|
20
|
-
s.extra_rdoc_files = %w( LICENSE.txt )
|
21
|
-
|
22
|
-
s.add_development_dependency "rake"
|
23
|
-
s.add_development_dependency "mocha"
|
24
|
-
s.add_development_dependency "yard"
|
25
|
-
end
|
data/test/.empty
DELETED
data/test/acceptance_test.rb
DELETED
@@ -1,129 +0,0 @@
|
|
1
|
-
# frozen_string_literal: true
|
2
|
-
|
3
|
-
require "test_helper"
|
4
|
-
|
5
|
-
class AcceptanceTest < Minitest::Test
|
6
|
-
|
7
|
-
VALID_CASES = [
|
8
|
-
["example.com", "example.com", [nil, "example", "com"]],
|
9
|
-
["foo.example.com", "example.com", ["foo", "example", "com"]],
|
10
|
-
|
11
|
-
["verybritish.co.uk", "verybritish.co.uk", [nil, "verybritish", "co.uk"]],
|
12
|
-
["foo.verybritish.co.uk", "verybritish.co.uk", ["foo", "verybritish", "co.uk"]],
|
13
|
-
|
14
|
-
["parliament.uk", "parliament.uk", [nil, "parliament", "uk"]],
|
15
|
-
["foo.parliament.uk", "parliament.uk", ["foo", "parliament", "uk"]],
|
16
|
-
].freeze
|
17
|
-
|
18
|
-
def test_valid
|
19
|
-
VALID_CASES.each do |input, domain, results|
|
20
|
-
parsed = PublicSuffix.parse(input)
|
21
|
-
trd, sld, tld = results
|
22
|
-
assert_equal tld, parsed.tld, "Invalid tld for `#{name}`"
|
23
|
-
assert_equal sld, parsed.sld, "Invalid sld for `#{name}`"
|
24
|
-
if trd.nil?
|
25
|
-
assert_nil parsed.trd, "Invalid trd for `#{name}`"
|
26
|
-
else
|
27
|
-
assert_equal trd, parsed.trd, "Invalid trd for `#{name}`"
|
28
|
-
end
|
29
|
-
|
30
|
-
assert_equal domain, PublicSuffix.domain(input)
|
31
|
-
assert PublicSuffix.valid?(input)
|
32
|
-
end
|
33
|
-
end
|
34
|
-
|
35
|
-
|
36
|
-
INVALID_CASES = [
|
37
|
-
["nic.bd", PublicSuffix::DomainNotAllowed],
|
38
|
-
[nil, PublicSuffix::DomainInvalid],
|
39
|
-
["", PublicSuffix::DomainInvalid],
|
40
|
-
[" ", PublicSuffix::DomainInvalid],
|
41
|
-
].freeze
|
42
|
-
|
43
|
-
def test_invalid
|
44
|
-
INVALID_CASES.each do |(name, error)|
|
45
|
-
assert_raises(error) { PublicSuffix.parse(name) }
|
46
|
-
assert !PublicSuffix.valid?(name)
|
47
|
-
end
|
48
|
-
end
|
49
|
-
|
50
|
-
|
51
|
-
REJECTED_CASES = [
|
52
|
-
["www. .com", true],
|
53
|
-
["foo.co..uk", true],
|
54
|
-
["goo,gle.com", true],
|
55
|
-
["-google.com", true],
|
56
|
-
["google-.com", true],
|
57
|
-
|
58
|
-
# This case was covered in GH-15.
|
59
|
-
# I decided to cover this case because it's not easily reproducible with URI.parse
|
60
|
-
# and can lead to several false positives.
|
61
|
-
["http://google.com", false],
|
62
|
-
].freeze
|
63
|
-
|
64
|
-
def test_rejected
|
65
|
-
REJECTED_CASES.each do |name, expected|
|
66
|
-
assert_equal expected, PublicSuffix.valid?(name),
|
67
|
-
"Expected %s to be %s" % [name.inspect, expected.inspect]
|
68
|
-
assert !valid_domain?(name),
|
69
|
-
"#{name} expected to be invalid"
|
70
|
-
end
|
71
|
-
end
|
72
|
-
|
73
|
-
|
74
|
-
CASE_CASES = [
|
75
|
-
["Www.google.com", %w( www google com )],
|
76
|
-
["www.Google.com", %w( www google com )],
|
77
|
-
["www.google.Com", %w( www google com )],
|
78
|
-
].freeze
|
79
|
-
|
80
|
-
def test_ignore_case
|
81
|
-
CASE_CASES.each do |name, results|
|
82
|
-
domain = PublicSuffix.parse(name)
|
83
|
-
trd, sld, tld = results
|
84
|
-
assert_equal tld, domain.tld, "Invalid tld for `#{name}'"
|
85
|
-
assert_equal sld, domain.sld, "Invalid sld for `#{name}'"
|
86
|
-
assert_equal trd, domain.trd, "Invalid trd for `#{name}'"
|
87
|
-
assert PublicSuffix.valid?(name)
|
88
|
-
end
|
89
|
-
end
|
90
|
-
|
91
|
-
|
92
|
-
INCLUDE_PRIVATE_CASES = [
|
93
|
-
["blogspot.com", true, "blogspot.com"],
|
94
|
-
["blogspot.com", false, nil],
|
95
|
-
["subdomain.blogspot.com", true, "blogspot.com"],
|
96
|
-
["subdomain.blogspot.com", false, "subdomain.blogspot.com"],
|
97
|
-
].freeze
|
98
|
-
|
99
|
-
def test_ignore_private
|
100
|
-
# test domain and parse
|
101
|
-
INCLUDE_PRIVATE_CASES.each do |given, ignore_private, expected|
|
102
|
-
if expected.nil?
|
103
|
-
assert_nil PublicSuffix.domain(given, ignore_private: ignore_private)
|
104
|
-
else
|
105
|
-
assert_equal expected, PublicSuffix.domain(given, ignore_private: ignore_private)
|
106
|
-
end
|
107
|
-
end
|
108
|
-
# test valid?
|
109
|
-
INCLUDE_PRIVATE_CASES.each do |given, ignore_private, expected|
|
110
|
-
assert_equal !expected.nil?, PublicSuffix.valid?(given, ignore_private: ignore_private)
|
111
|
-
end
|
112
|
-
end
|
113
|
-
|
114
|
-
|
115
|
-
def valid_uri?(name)
|
116
|
-
uri = URI.parse(name)
|
117
|
-
!uri.host.nil?
|
118
|
-
rescue
|
119
|
-
false
|
120
|
-
end
|
121
|
-
|
122
|
-
def valid_domain?(name)
|
123
|
-
uri = URI.parse(name)
|
124
|
-
!uri.host.nil? && uri.scheme.nil?
|
125
|
-
rescue
|
126
|
-
false
|
127
|
-
end
|
128
|
-
|
129
|
-
end
|
data/test/benchmarks/bm_find.rb
DELETED
@@ -1,66 +0,0 @@
|
|
1
|
-
require 'benchmark'
|
2
|
-
require_relative "../../lib/public_suffix"
|
3
|
-
|
4
|
-
NAME_SHORT = "example.de"
|
5
|
-
NAME_MEDIUM = "www.subdomain.example.de"
|
6
|
-
NAME_LONG = "one.two.three.four.five.example.de"
|
7
|
-
NAME_WILD = "one.two.three.four.five.example.bd"
|
8
|
-
NAME_EXCP = "one.two.three.four.five.www.ck"
|
9
|
-
|
10
|
-
IAAA = "www.example.ac"
|
11
|
-
IZZZ = "www.example.zone"
|
12
|
-
|
13
|
-
PAAA = "one.two.three.four.five.example.beep.pl"
|
14
|
-
PZZZ = "one.two.three.four.five.example.now.sh"
|
15
|
-
|
16
|
-
JP = "www.yokoshibahikari.chiba.jp"
|
17
|
-
IT = "www.example.it"
|
18
|
-
COM = "www.example.com"
|
19
|
-
|
20
|
-
TIMES = (ARGV.first || 50_000).to_i
|
21
|
-
|
22
|
-
# Initialize
|
23
|
-
PublicSuffixList = PublicSuffix::List.default
|
24
|
-
PublicSuffixList.find("example.com")
|
25
|
-
|
26
|
-
Benchmark.bmbm(25) do |x|
|
27
|
-
x.report("NAME_SHORT") do
|
28
|
-
TIMES.times { PublicSuffixList.find(NAME_SHORT) != nil }
|
29
|
-
end
|
30
|
-
x.report("NAME_MEDIUM") do
|
31
|
-
TIMES.times { PublicSuffixList.find(NAME_MEDIUM) != nil }
|
32
|
-
end
|
33
|
-
x.report("NAME_LONG") do
|
34
|
-
TIMES.times { PublicSuffixList.find(NAME_LONG) != nil }
|
35
|
-
end
|
36
|
-
x.report("NAME_WILD") do
|
37
|
-
TIMES.times { PublicSuffixList.find(NAME_WILD) != nil }
|
38
|
-
end
|
39
|
-
x.report("NAME_EXCP") do
|
40
|
-
TIMES.times { PublicSuffixList.find(NAME_EXCP) != nil }
|
41
|
-
end
|
42
|
-
|
43
|
-
x.report("IAAA") do
|
44
|
-
TIMES.times { PublicSuffixList.find(IAAA) != nil }
|
45
|
-
end
|
46
|
-
x.report("IZZZ") do
|
47
|
-
TIMES.times { PublicSuffixList.find(IZZZ) != nil }
|
48
|
-
end
|
49
|
-
|
50
|
-
x.report("PAAA") do
|
51
|
-
TIMES.times { PublicSuffixList.find(PAAA) != nil }
|
52
|
-
end
|
53
|
-
x.report("PZZZ") do
|
54
|
-
TIMES.times { PublicSuffixList.find(PZZZ) != nil }
|
55
|
-
end
|
56
|
-
|
57
|
-
x.report("JP") do
|
58
|
-
TIMES.times { PublicSuffixList.find(JP) != nil }
|
59
|
-
end
|
60
|
-
x.report("IT") do
|
61
|
-
TIMES.times { PublicSuffixList.find(IT) != nil }
|
62
|
-
end
|
63
|
-
x.report("COM") do
|
64
|
-
TIMES.times { PublicSuffixList.find(COM) != nil }
|
65
|
-
end
|
66
|
-
end
|
@@ -1,102 +0,0 @@
|
|
1
|
-
require 'benchmark'
|
2
|
-
require_relative "../../lib/public_suffix"
|
3
|
-
|
4
|
-
NAME_SHORT = "example.de"
|
5
|
-
NAME_MEDIUM = "www.subdomain.example.de"
|
6
|
-
NAME_LONG = "one.two.three.four.five.example.de"
|
7
|
-
NAME_WILD = "one.two.three.four.five.example.bd"
|
8
|
-
NAME_EXCP = "one.two.three.four.five.www.ck"
|
9
|
-
|
10
|
-
IAAA = "www.example.ac"
|
11
|
-
IZZZ = "www.example.zone"
|
12
|
-
|
13
|
-
PAAA = "one.two.three.four.five.example.beep.pl"
|
14
|
-
PZZZ = "one.two.three.four.five.example.now.sh"
|
15
|
-
|
16
|
-
JP = "www.yokoshibahikari.chiba.jp"
|
17
|
-
IT = "www.example.it"
|
18
|
-
COM = "www.example.com"
|
19
|
-
|
20
|
-
TIMES = (ARGV.first || 50_000).to_i
|
21
|
-
|
22
|
-
# Initialize
|
23
|
-
PublicSuffixList = PublicSuffix::List.default
|
24
|
-
PublicSuffixList.find("example.com")
|
25
|
-
|
26
|
-
Benchmark.bmbm(25) do |x|
|
27
|
-
x.report("NAME_SHORT") do
|
28
|
-
TIMES.times { PublicSuffixList.find(NAME_SHORT) != nil }
|
29
|
-
end
|
30
|
-
x.report("NAME_SHORT (noprivate)") do
|
31
|
-
TIMES.times { PublicSuffixList.find(NAME_SHORT, ignore_private: true) != nil }
|
32
|
-
end
|
33
|
-
x.report("NAME_MEDIUM") do
|
34
|
-
TIMES.times { PublicSuffixList.find(NAME_MEDIUM) != nil }
|
35
|
-
end
|
36
|
-
x.report("NAME_MEDIUM (noprivate)") do
|
37
|
-
TIMES.times { PublicSuffixList.find(NAME_MEDIUM, ignore_private: true) != nil }
|
38
|
-
end
|
39
|
-
x.report("NAME_LONG") do
|
40
|
-
TIMES.times { PublicSuffixList.find(NAME_LONG) != nil }
|
41
|
-
end
|
42
|
-
x.report("NAME_LONG (noprivate)") do
|
43
|
-
TIMES.times { PublicSuffixList.find(NAME_LONG, ignore_private: true) != nil }
|
44
|
-
end
|
45
|
-
x.report("NAME_WILD") do
|
46
|
-
TIMES.times { PublicSuffixList.find(NAME_WILD) != nil }
|
47
|
-
end
|
48
|
-
x.report("NAME_WILD (noprivate)") do
|
49
|
-
TIMES.times { PublicSuffixList.find(NAME_WILD, ignore_private: true) != nil }
|
50
|
-
end
|
51
|
-
x.report("NAME_EXCP") do
|
52
|
-
TIMES.times { PublicSuffixList.find(NAME_EXCP) != nil }
|
53
|
-
end
|
54
|
-
x.report("NAME_EXCP (noprivate)") do
|
55
|
-
TIMES.times { PublicSuffixList.find(NAME_EXCP, ignore_private: true) != nil }
|
56
|
-
end
|
57
|
-
|
58
|
-
x.report("IAAA") do
|
59
|
-
TIMES.times { PublicSuffixList.find(IAAA) != nil }
|
60
|
-
end
|
61
|
-
x.report("IAAA (noprivate)") do
|
62
|
-
TIMES.times { PublicSuffixList.find(IAAA, ignore_private: true) != nil }
|
63
|
-
end
|
64
|
-
x.report("IZZZ") do
|
65
|
-
TIMES.times { PublicSuffixList.find(IZZZ) != nil }
|
66
|
-
end
|
67
|
-
x.report("IZZZ (noprivate)") do
|
68
|
-
TIMES.times { PublicSuffixList.find(IZZZ, ignore_private: true) != nil }
|
69
|
-
end
|
70
|
-
|
71
|
-
x.report("PAAA") do
|
72
|
-
TIMES.times { PublicSuffixList.find(PAAA) != nil }
|
73
|
-
end
|
74
|
-
x.report("PAAA (noprivate)") do
|
75
|
-
TIMES.times { PublicSuffixList.find(PAAA, ignore_private: true) != nil }
|
76
|
-
end
|
77
|
-
x.report("PZZZ") do
|
78
|
-
TIMES.times { PublicSuffixList.find(PZZZ) != nil }
|
79
|
-
end
|
80
|
-
x.report("PZZZ (noprivate)") do
|
81
|
-
TIMES.times { PublicSuffixList.find(PZZZ, ignore_private: true) != nil }
|
82
|
-
end
|
83
|
-
|
84
|
-
x.report("JP") do
|
85
|
-
TIMES.times { PublicSuffixList.find(JP) != nil }
|
86
|
-
end
|
87
|
-
x.report("JP (noprivate)") do
|
88
|
-
TIMES.times { PublicSuffixList.find(JP, ignore_private: true) != nil }
|
89
|
-
end
|
90
|
-
x.report("IT") do
|
91
|
-
TIMES.times { PublicSuffixList.find(IT) != nil }
|
92
|
-
end
|
93
|
-
x.report("IT (noprivate)") do
|
94
|
-
TIMES.times { PublicSuffixList.find(IT, ignore_private: true) != nil }
|
95
|
-
end
|
96
|
-
x.report("COM") do
|
97
|
-
TIMES.times { PublicSuffixList.find(COM) != nil }
|
98
|
-
end
|
99
|
-
x.report("COM (noprivate)") do
|
100
|
-
TIMES.times { PublicSuffixList.find(COM, ignore_private: true) != nil }
|
101
|
-
end
|
102
|
-
end
|
data/test/benchmarks/bm_names.rb
DELETED
@@ -1,91 +0,0 @@
|
|
1
|
-
require 'benchmark/ips'
|
2
|
-
|
3
|
-
STRING = "www.subdomain.example.com"
|
4
|
-
ARRAY = %w(
|
5
|
-
com
|
6
|
-
example.com
|
7
|
-
subdomain.example.com
|
8
|
-
www.subdomain.example.com
|
9
|
-
)
|
10
|
-
|
11
|
-
def tokenizer1(string)
|
12
|
-
parts = string.split(".").reverse!
|
13
|
-
index = 0
|
14
|
-
query = parts[index]
|
15
|
-
names = []
|
16
|
-
|
17
|
-
loop do
|
18
|
-
names << query
|
19
|
-
|
20
|
-
index += 1
|
21
|
-
break if index >= parts.size
|
22
|
-
query = parts[index] + "." + query
|
23
|
-
end
|
24
|
-
names
|
25
|
-
end
|
26
|
-
|
27
|
-
def tokenizer2(string)
|
28
|
-
parts = string.split(".")
|
29
|
-
index = parts.size - 1
|
30
|
-
query = parts[index]
|
31
|
-
names = []
|
32
|
-
|
33
|
-
loop do
|
34
|
-
names << query
|
35
|
-
|
36
|
-
index -= 1
|
37
|
-
break if index < 0
|
38
|
-
query = parts[index] + "." + query
|
39
|
-
end
|
40
|
-
names
|
41
|
-
end
|
42
|
-
|
43
|
-
def tokenizer3(string)
|
44
|
-
isx = string.size
|
45
|
-
idx = string.size - 1
|
46
|
-
names = []
|
47
|
-
|
48
|
-
loop do
|
49
|
-
isx = string.rindex(".", isx - 1) || -1
|
50
|
-
names << string[isx + 1, idx - isx]
|
51
|
-
|
52
|
-
break if isx <= 0
|
53
|
-
end
|
54
|
-
names
|
55
|
-
end
|
56
|
-
|
57
|
-
def tokenizer4(string)
|
58
|
-
isx = string.size
|
59
|
-
idx = string.size - 1
|
60
|
-
names = []
|
61
|
-
|
62
|
-
loop do
|
63
|
-
isx = string.rindex(".", isx - 1) || -1
|
64
|
-
names << string[(isx+1)..idx]
|
65
|
-
|
66
|
-
break if isx <= 0
|
67
|
-
end
|
68
|
-
names
|
69
|
-
end
|
70
|
-
|
71
|
-
(x = tokenizer1(STRING)) == ARRAY or fail("tokenizer1 failed: #{x.inspect}")
|
72
|
-
(x = tokenizer2(STRING)) == ARRAY or fail("tokenizer2 failed: #{x.inspect}")
|
73
|
-
(x = tokenizer3(STRING)) == ARRAY or fail("tokenizer3 failed: #{x.inspect}")
|
74
|
-
(x = tokenizer4(STRING)) == ARRAY or fail("tokenizer4 failed: #{x.inspect}")
|
75
|
-
|
76
|
-
Benchmark.ips do |x|
|
77
|
-
x.report("tokenizer1") do
|
78
|
-
tokenizer1(STRING).is_a?(Array)
|
79
|
-
end
|
80
|
-
x.report("tokenizer2") do
|
81
|
-
tokenizer2(STRING).is_a?(Array)
|
82
|
-
end
|
83
|
-
x.report("tokenizer3") do
|
84
|
-
tokenizer3(STRING).is_a?(Array)
|
85
|
-
end
|
86
|
-
x.report("tokenizer4") do
|
87
|
-
tokenizer4(STRING).is_a?(Array)
|
88
|
-
end
|
89
|
-
|
90
|
-
x.compare!
|
91
|
-
end
|
@@ -1,26 +0,0 @@
|
|
1
|
-
require 'benchmark'
|
2
|
-
require_relative "../../lib/public_suffix"
|
3
|
-
|
4
|
-
JP = "www.yokoshibahikari.chiba.jp"
|
5
|
-
|
6
|
-
TIMES = (ARGV.first || 50_000).to_i
|
7
|
-
|
8
|
-
# Initialize
|
9
|
-
class PublicSuffix::List
|
10
|
-
public :select
|
11
|
-
end
|
12
|
-
PublicSuffixList = PublicSuffix::List.default
|
13
|
-
PublicSuffixList.select("example.jp")
|
14
|
-
PublicSuffixList.find("example.jp")
|
15
|
-
|
16
|
-
Benchmark.bmbm(25) do |x|
|
17
|
-
x.report("JP select") do
|
18
|
-
TIMES.times { PublicSuffixList.select(JP) }
|
19
|
-
end
|
20
|
-
x.report("JP find") do
|
21
|
-
TIMES.times { PublicSuffixList.find(JP) }
|
22
|
-
end
|
23
|
-
# x.report("JP (noprivate)") do
|
24
|
-
# TIMES.times { PublicSuffixList.find(JP, ignore_private: true) != nil }
|
25
|
-
# end
|
26
|
-
end
|
@@ -1,25 +0,0 @@
|
|
1
|
-
require 'benchmark'
|
2
|
-
require_relative "../../lib/public_suffix"
|
3
|
-
|
4
|
-
JP = "www.yokoshibahikari.chiba.jp"
|
5
|
-
|
6
|
-
TIMES = (ARGV.first || 50_000).to_i
|
7
|
-
|
8
|
-
# Initialize
|
9
|
-
class PublicSuffix::List
|
10
|
-
public :select
|
11
|
-
end
|
12
|
-
PublicSuffixList = PublicSuffix::List.default
|
13
|
-
PublicSuffixList.select("example.jp")
|
14
|
-
|
15
|
-
Benchmark.bmbm(25) do |x|
|
16
|
-
x.report("select jp") do
|
17
|
-
TIMES.times { PublicSuffixList.select("jp") }
|
18
|
-
end
|
19
|
-
x.report("select example.jp") do
|
20
|
-
TIMES.times { PublicSuffixList.select("example.jp") }
|
21
|
-
end
|
22
|
-
x.report("select www.example.jp") do
|
23
|
-
TIMES.times { PublicSuffixList.select("www.example.jp") }
|
24
|
-
end
|
25
|
-
end
|
data/test/benchmarks/bm_valid.rb
DELETED
@@ -1,101 +0,0 @@
|
|
1
|
-
require 'benchmark'
|
2
|
-
require_relative "../../lib/public_suffix"
|
3
|
-
|
4
|
-
NAME_SHORT = "example.de"
|
5
|
-
NAME_MEDIUM = "www.subdomain.example.de"
|
6
|
-
NAME_LONG = "one.two.three.four.five.example.de"
|
7
|
-
NAME_WILD = "one.two.three.four.five.example.bd"
|
8
|
-
NAME_EXCP = "one.two.three.four.five.www.ck"
|
9
|
-
|
10
|
-
IAAA = "www.example.ac"
|
11
|
-
IZZZ = "www.example.zone"
|
12
|
-
|
13
|
-
PAAA = "one.two.three.four.five.example.beep.pl"
|
14
|
-
PZZZ = "one.two.three.four.five.example.now.sh"
|
15
|
-
|
16
|
-
JP = "www.yokoshibahikari.chiba.jp"
|
17
|
-
IT = "www.example.it"
|
18
|
-
COM = "www.example.com"
|
19
|
-
|
20
|
-
TIMES = (ARGV.first || 50_000).to_i
|
21
|
-
|
22
|
-
# Initialize
|
23
|
-
PublicSuffix.valid?("example.com")
|
24
|
-
|
25
|
-
Benchmark.bmbm(25) do |x|
|
26
|
-
x.report("NAME_SHORT") do
|
27
|
-
TIMES.times { PublicSuffix.valid?(NAME_SHORT) == true }
|
28
|
-
end
|
29
|
-
x.report("NAME_SHORT (noprivate)") do
|
30
|
-
TIMES.times { PublicSuffix.valid?(NAME_SHORT, ignore_private: true) == true }
|
31
|
-
end
|
32
|
-
x.report("NAME_MEDIUM") do
|
33
|
-
TIMES.times { PublicSuffix.valid?(NAME_MEDIUM) == true }
|
34
|
-
end
|
35
|
-
x.report("NAME_MEDIUM (noprivate)") do
|
36
|
-
TIMES.times { PublicSuffix.valid?(NAME_MEDIUM, ignore_private: true) == true }
|
37
|
-
end
|
38
|
-
x.report("NAME_LONG") do
|
39
|
-
TIMES.times { PublicSuffix.valid?(NAME_LONG) == true }
|
40
|
-
end
|
41
|
-
x.report("NAME_LONG (noprivate)") do
|
42
|
-
TIMES.times { PublicSuffix.valid?(NAME_LONG, ignore_private: true) == true }
|
43
|
-
end
|
44
|
-
x.report("NAME_WILD") do
|
45
|
-
TIMES.times { PublicSuffix.valid?(NAME_WILD) == true }
|
46
|
-
end
|
47
|
-
x.report("NAME_WILD (noprivate)") do
|
48
|
-
TIMES.times { PublicSuffix.valid?(NAME_WILD, ignore_private: true) == true }
|
49
|
-
end
|
50
|
-
x.report("NAME_EXCP") do
|
51
|
-
TIMES.times { PublicSuffix.valid?(NAME_EXCP) == true }
|
52
|
-
end
|
53
|
-
x.report("NAME_EXCP (noprivate)") do
|
54
|
-
TIMES.times { PublicSuffix.valid?(NAME_EXCP, ignore_private: true) == true }
|
55
|
-
end
|
56
|
-
|
57
|
-
x.report("IAAA") do
|
58
|
-
TIMES.times { PublicSuffix.valid?(IAAA) == true }
|
59
|
-
end
|
60
|
-
x.report("IAAA (noprivate)") do
|
61
|
-
TIMES.times { PublicSuffix.valid?(IAAA, ignore_private: true) == true }
|
62
|
-
end
|
63
|
-
x.report("IZZZ") do
|
64
|
-
TIMES.times { PublicSuffix.valid?(IZZZ) == true }
|
65
|
-
end
|
66
|
-
x.report("IZZZ (noprivate)") do
|
67
|
-
TIMES.times { PublicSuffix.valid?(IZZZ, ignore_private: true) == true }
|
68
|
-
end
|
69
|
-
|
70
|
-
x.report("PAAA") do
|
71
|
-
TIMES.times { PublicSuffix.valid?(PAAA) == true }
|
72
|
-
end
|
73
|
-
x.report("PAAA (noprivate)") do
|
74
|
-
TIMES.times { PublicSuffix.valid?(PAAA, ignore_private: true) == true }
|
75
|
-
end
|
76
|
-
x.report("PZZZ") do
|
77
|
-
TIMES.times { PublicSuffix.valid?(PZZZ) == true }
|
78
|
-
end
|
79
|
-
x.report("PZZZ (noprivate)") do
|
80
|
-
TIMES.times { PublicSuffix.valid?(PZZZ, ignore_private: true) == true }
|
81
|
-
end
|
82
|
-
|
83
|
-
x.report("JP") do
|
84
|
-
TIMES.times { PublicSuffix.valid?(JP) == true }
|
85
|
-
end
|
86
|
-
x.report("JP (noprivate)") do
|
87
|
-
TIMES.times { PublicSuffix.valid?(JP, ignore_private: true) == true }
|
88
|
-
end
|
89
|
-
x.report("IT") do
|
90
|
-
TIMES.times { PublicSuffix.valid?(IT) == true }
|
91
|
-
end
|
92
|
-
x.report("IT (noprivate)") do
|
93
|
-
TIMES.times { PublicSuffix.valid?(IT, ignore_private: true) == true }
|
94
|
-
end
|
95
|
-
x.report("COM") do
|
96
|
-
TIMES.times { PublicSuffix.valid?(COM) == true }
|
97
|
-
end
|
98
|
-
x.report("COM (noprivate)") do
|
99
|
-
TIMES.times { PublicSuffix.valid?(COM, ignore_private: true) == true }
|
100
|
-
end
|
101
|
-
end
|