gman 7.0.5 → 8.0.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- checksums.yaml +4 -4
- data/bin/gman +10 -15
- data/bin/gman_filter +1 -1
- data/config/domains.txt +497 -387
- data/config/vendor/academic.txt +0 -1
- data/config/vendor/dotgovs.csv +8688 -5786
- data/docs/README.md +3 -1
- data/lib/gman/domain_list.rb +1 -1
- data/lib/gman/identifier.rb +17 -14
- data/lib/gman/importer.rb +1 -1
- data/lib/gman/locality.rb +1 -1
- data/lib/gman/version.rb +1 -1
- data/lib/gman.rb +9 -8
- metadata +12 -216
- data/.github/CODEOWNERS +0 -3
- data/.github/ISSUE_TEMPLATE/bug_report.md +0 -28
- data/.github/ISSUE_TEMPLATE/feature_request.md +0 -21
- data/.github/config.yml +0 -23
- data/.github/funding.yml +0 -1
- data/.github/no-response.yml +0 -15
- data/.github/release-drafter.yml +0 -4
- data/.github/settings.yml +0 -33
- data/.github/stale.yml +0 -29
- data/.gitignore +0 -6
- data/.rspec +0 -2
- data/.rubocop.yml +0 -33
- data/.rubocop_todo.yml +0 -84
- data/.ruby-version +0 -1
- data/.travis.yml +0 -4
- data/Gemfile +0 -5
- data/docs/CODE_OF_CONDUCT.md +0 -46
- data/docs/CONTRIBUTING.md +0 -92
- data/docs/SECURITY.md +0 -3
- data/docs/_config.yml +0 -2
- data/gman.gemspec +0 -44
- data/script/add +0 -19
- data/script/alphabetize +0 -14
- data/script/bootstrap +0 -5
- data/script/cibuild +0 -8
- data/script/console +0 -3
- data/script/dedupe +0 -22
- data/script/profile +0 -21
- data/script/prune +0 -22
- data/script/reconcile-us +0 -72
- data/script/release +0 -38
- data/script/vendor +0 -13
- data/script/vendor-federal-de +0 -14
- data/script/vendor-gov-list +0 -17
- data/script/vendor-municipal-de +0 -23
- data/script/vendor-nl +0 -21
- data/script/vendor-public-suffix +0 -28
- data/script/vendor-se +0 -21
- data/script/vendor-swot +0 -43
- data/script/vendor-us +0 -38
- data/spec/fixtures/domains.txt +0 -4
- data/spec/fixtures/obama.txt +0 -5
- data/spec/gman/bin_spec.rb +0 -101
- data/spec/gman/country_code_spec.rb +0 -39
- data/spec/gman/domain_list_spec.rb +0 -110
- data/spec/gman/domains_spec.rb +0 -25
- data/spec/gman/identifier_spec.rb +0 -218
- data/spec/gman/importer_spec.rb +0 -236
- data/spec/gman/locality_spec.rb +0 -24
- data/spec/gman_spec.rb +0 -74
- data/spec/spec_helper.rb +0 -31
data/spec/gman/importer_spec.rb
DELETED
|
@@ -1,236 +0,0 @@
|
|
|
1
|
-
# frozen_string_literal: true
|
|
2
|
-
|
|
3
|
-
RSpec.describe Gman::Importer do
|
|
4
|
-
subject { described_class.new(domains) }
|
|
5
|
-
|
|
6
|
-
let(:domains) { { 'test' => ['example.com'] } }
|
|
7
|
-
let(:stdout) { StringIO.new }
|
|
8
|
-
let(:logger) { Logger.new(@stdout) }
|
|
9
|
-
let(:domain_list) { subject.domain_list }
|
|
10
|
-
|
|
11
|
-
before do
|
|
12
|
-
subject.instance_variable_set '@logger', logger
|
|
13
|
-
end
|
|
14
|
-
|
|
15
|
-
it 'inits the domain list' do
|
|
16
|
-
expect(domain_list).to be_a(Gman::DomainList)
|
|
17
|
-
expect(domain_list.count).to be(1)
|
|
18
|
-
expect(domain_list.domains.first).to eql('example.com')
|
|
19
|
-
end
|
|
20
|
-
|
|
21
|
-
it 'inits the logger' do
|
|
22
|
-
expect(subject.logger).to be_a(Logger)
|
|
23
|
-
end
|
|
24
|
-
|
|
25
|
-
it 'returns the current domain list' do
|
|
26
|
-
expect(subject.current).to be_a(Gman::DomainList)
|
|
27
|
-
end
|
|
28
|
-
|
|
29
|
-
it 'returns the resolver' do
|
|
30
|
-
expect(subject.resolver).to be_a(Resolv::DNS)
|
|
31
|
-
end
|
|
32
|
-
|
|
33
|
-
context 'domain rejection' do
|
|
34
|
-
it 'returns false' do
|
|
35
|
-
expect(subject.reject('example.com', 'reasons')).to be(false)
|
|
36
|
-
end
|
|
37
|
-
|
|
38
|
-
it 'returns the reason why asked' do
|
|
39
|
-
with_env 'RECONCILING', 'true' do
|
|
40
|
-
expect(subject.reject('example.com', 'reasons')).to eql('reasons')
|
|
41
|
-
end
|
|
42
|
-
end
|
|
43
|
-
end
|
|
44
|
-
|
|
45
|
-
context 'manipulating the domain list' do
|
|
46
|
-
context 'normalizing domains' do
|
|
47
|
-
let(:domains) { { 'test' => ['www.EXAMPLE.com/'] } }
|
|
48
|
-
|
|
49
|
-
before { subject.send :normalize_domains! }
|
|
50
|
-
|
|
51
|
-
it 'normalizes the domains' do
|
|
52
|
-
expect(domain_list.domains.first).to eql('example.com')
|
|
53
|
-
end
|
|
54
|
-
end
|
|
55
|
-
|
|
56
|
-
context 'removing invalid domains' do
|
|
57
|
-
let(:domains) { { 'test' => ['foo.github.io', 'example.com'] } }
|
|
58
|
-
|
|
59
|
-
before { subject.send :ensure_validity! }
|
|
60
|
-
|
|
61
|
-
it 'removes invalid domains' do
|
|
62
|
-
expect(domain_list.count).to be(1)
|
|
63
|
-
end
|
|
64
|
-
end
|
|
65
|
-
end
|
|
66
|
-
|
|
67
|
-
context 'with the current list stubbed' do
|
|
68
|
-
let(:stubbed_list) { Gman::DomainList.new(path: stubbed_list_path) }
|
|
69
|
-
let(:stubbed_file_contents) { File.read(stubbed_list_path) }
|
|
70
|
-
|
|
71
|
-
before { subject.instance_variable_set '@current', stubbed_list }
|
|
72
|
-
|
|
73
|
-
context 'writing' do
|
|
74
|
-
before { @current = subject.current.to_s }
|
|
75
|
-
|
|
76
|
-
before { subject.send :add_to_current }
|
|
77
|
-
|
|
78
|
-
after { File.write(stubbed_list_path, @current) }
|
|
79
|
-
|
|
80
|
-
context 'adding domains' do
|
|
81
|
-
let(:domains) do
|
|
82
|
-
{ 'test' => ['example.com'], 'test2' => ['github.com'] }
|
|
83
|
-
end
|
|
84
|
-
|
|
85
|
-
it 'adds the domains' do
|
|
86
|
-
expected = "// test\nexample.com\n\n// test2\ngithub.com"
|
|
87
|
-
expect(stubbed_file_contents).to match(expected)
|
|
88
|
-
end
|
|
89
|
-
end
|
|
90
|
-
|
|
91
|
-
context 'importing' do
|
|
92
|
-
let(:domains) do
|
|
93
|
-
{
|
|
94
|
-
'test' => ['www.example.com', 'foo.github.io'],
|
|
95
|
-
'test2' => ['github.com', 'www.github.com', 'whitehouse.gov']
|
|
96
|
-
}
|
|
97
|
-
end
|
|
98
|
-
|
|
99
|
-
before { subject.import(skip_resolve: true) }
|
|
100
|
-
|
|
101
|
-
it 'imports' do
|
|
102
|
-
expected = "// test\nexample.com\nfoo.github.io"
|
|
103
|
-
expect(stubbed_file_contents).to match(expected)
|
|
104
|
-
|
|
105
|
-
expected = "// test2\ngithub.com\nwhitehouse.gov"
|
|
106
|
-
expect(stubbed_file_contents).to match(expected)
|
|
107
|
-
end
|
|
108
|
-
end
|
|
109
|
-
end
|
|
110
|
-
end
|
|
111
|
-
|
|
112
|
-
context 'domain validation' do
|
|
113
|
-
let(:domain) { '' }
|
|
114
|
-
let(:valid?) { subject.send(:ensure_valid, domain) }
|
|
115
|
-
|
|
116
|
-
context 'a valid domain' do
|
|
117
|
-
let(:domain) { 'whitehouse.gov' }
|
|
118
|
-
|
|
119
|
-
it 'is valid' do
|
|
120
|
-
expect(valid?).to be(true)
|
|
121
|
-
end
|
|
122
|
-
end
|
|
123
|
-
|
|
124
|
-
{
|
|
125
|
-
empty: '',
|
|
126
|
-
blacklisted: 'egovlink.com',
|
|
127
|
-
invalid: 'foo.invalid',
|
|
128
|
-
academic: 'harvard.edu',
|
|
129
|
-
"rejex'd": 'foo.github.io'
|
|
130
|
-
}.each_key do |type|
|
|
131
|
-
context "a #{type} domain" do
|
|
132
|
-
it 'is invalid' do
|
|
133
|
-
expect(valid?).to be(false)
|
|
134
|
-
end
|
|
135
|
-
end
|
|
136
|
-
end
|
|
137
|
-
end
|
|
138
|
-
|
|
139
|
-
context 'duplicate domains' do
|
|
140
|
-
let(:dupe?) { subject.send(:dupe?, domain) }
|
|
141
|
-
let(:ensure_not_dupe) { subject.send(:ensure_not_dupe, domain) }
|
|
142
|
-
|
|
143
|
-
context 'a unique domain' do
|
|
144
|
-
let(:domain) { 'gman.com' }
|
|
145
|
-
|
|
146
|
-
it 'is not a dupe' do
|
|
147
|
-
expect(dupe?).to be_falsy
|
|
148
|
-
expect(ensure_not_dupe).to be_truthy
|
|
149
|
-
end
|
|
150
|
-
end
|
|
151
|
-
|
|
152
|
-
context 'a duplicate domain' do
|
|
153
|
-
let(:domain) { 'gov' }
|
|
154
|
-
|
|
155
|
-
it "knows it's a dupe" do
|
|
156
|
-
expect(dupe?).to be_truthy
|
|
157
|
-
expect(ensure_not_dupe).to be_falsy
|
|
158
|
-
end
|
|
159
|
-
|
|
160
|
-
context 'a subdomain' do
|
|
161
|
-
let(:domain) { 'whitehouse.gov' }
|
|
162
|
-
|
|
163
|
-
it "know when a domain's a subdomain of an existing domain" do
|
|
164
|
-
expect(dupe?).to be_truthy
|
|
165
|
-
expect(ensure_not_dupe).to be_falsy
|
|
166
|
-
end
|
|
167
|
-
end
|
|
168
|
-
end
|
|
169
|
-
end
|
|
170
|
-
|
|
171
|
-
context 'domain resolution' do
|
|
172
|
-
let(:resolves?) { subject.domain_resolves?(domain) }
|
|
173
|
-
let(:ensure_resolves) { subject.send(:ensure_resolves, domain) }
|
|
174
|
-
|
|
175
|
-
context 'a valid domain' do
|
|
176
|
-
let(:domain) { 'github.com' }
|
|
177
|
-
|
|
178
|
-
it 'resolves' do
|
|
179
|
-
expect(resolves?).to be_truthy
|
|
180
|
-
expect(ensure_resolves).to be_truthy
|
|
181
|
-
end
|
|
182
|
-
end
|
|
183
|
-
|
|
184
|
-
context 'an invalid domain' do
|
|
185
|
-
let(:domain) { 'foo.invalid' }
|
|
186
|
-
|
|
187
|
-
it "doesn't resolve" do
|
|
188
|
-
expect(resolves?).to be_falsy
|
|
189
|
-
expect(ensure_resolves).to be_falsy
|
|
190
|
-
end
|
|
191
|
-
end
|
|
192
|
-
end
|
|
193
|
-
|
|
194
|
-
context 'regex checks' do
|
|
195
|
-
let(:ensure_regex) { subject.send(:ensure_regex, domain) }
|
|
196
|
-
|
|
197
|
-
context 'valid domains' do
|
|
198
|
-
let(:domain) { 'example.com' }
|
|
199
|
-
|
|
200
|
-
it 'passes' do
|
|
201
|
-
expect(ensure_regex).to be_truthy
|
|
202
|
-
end
|
|
203
|
-
end
|
|
204
|
-
|
|
205
|
-
[
|
|
206
|
-
'home.example.com', 'site.example.com', 'user.example.com',
|
|
207
|
-
'foo.weebly.com', 'foo.wordpress.com', 'foo.govoffice.com',
|
|
208
|
-
'foo.govoffice1.com', 'foo.homestead.com', 'foo.wix.com',
|
|
209
|
-
'foo.blogspot.com', 'foo.tripod.com', 'foo.squarespace.com',
|
|
210
|
-
'foo.github.io', 'ci.champaign.il.us'
|
|
211
|
-
].each do |domain|
|
|
212
|
-
context "a #{domain} domain" do
|
|
213
|
-
let(:domain) { domain }
|
|
214
|
-
|
|
215
|
-
it 'rejects the domain' do
|
|
216
|
-
expect(ensure_regex).to be_falsy
|
|
217
|
-
end
|
|
218
|
-
end
|
|
219
|
-
end
|
|
220
|
-
end
|
|
221
|
-
|
|
222
|
-
context 'normalizing domains' do
|
|
223
|
-
let(:normalized_domain) { subject.normalize_domain(domain) }
|
|
224
|
-
|
|
225
|
-
[
|
|
226
|
-
'http://example.com', 'www.example.com', 'example.com/',
|
|
227
|
-
'example.com/foo', 'example.com/foo/', 'EXAMPLE.com'
|
|
228
|
-
].each do |domain|
|
|
229
|
-
let(:domain) { domain }
|
|
230
|
-
|
|
231
|
-
it 'normalizes the domain' do
|
|
232
|
-
expect(normalized_domain).to eql('example.com')
|
|
233
|
-
end
|
|
234
|
-
end
|
|
235
|
-
end
|
|
236
|
-
end
|
data/spec/gman/locality_spec.rb
DELETED
|
@@ -1,24 +0,0 @@
|
|
|
1
|
-
# frozen_string_literal: true
|
|
2
|
-
|
|
3
|
-
RSpec.describe Gman::Locality do
|
|
4
|
-
context 'valid domains' do
|
|
5
|
-
['foo.state.il.us', 'ci.foo.il.us'].each do |domain|
|
|
6
|
-
context "the #{domain} domain" do
|
|
7
|
-
it 'is valid' do
|
|
8
|
-
expect(described_class.valid?(domain)).to be(true)
|
|
9
|
-
end
|
|
10
|
-
end
|
|
11
|
-
end
|
|
12
|
-
end
|
|
13
|
-
|
|
14
|
-
context 'invalid domains' do
|
|
15
|
-
['state.foo.il.us', 'foo.ci.il.us',
|
|
16
|
-
'k12.il.us', 'ci.foo.zx.us'].each do |domain|
|
|
17
|
-
context "the #{domain} domain" do
|
|
18
|
-
it 'is invalid' do
|
|
19
|
-
expect(described_class.valid?(domain)).to be(false)
|
|
20
|
-
end
|
|
21
|
-
end
|
|
22
|
-
end
|
|
23
|
-
end
|
|
24
|
-
end
|
data/spec/gman_spec.rb
DELETED
|
@@ -1,74 +0,0 @@
|
|
|
1
|
-
# frozen_string_literal: true
|
|
2
|
-
|
|
3
|
-
RSpec.describe Gman do
|
|
4
|
-
context 'valid domains' do
|
|
5
|
-
['foo.gov', 'http://foo.mil', 'foo@bar.gc.ca', 'foo.gov.au',
|
|
6
|
-
'https://www.foo.gouv.fr', 'foo@ci.champaign.il.us',
|
|
7
|
-
'foo.bar.baz.gov.au', 'foo@bar.gov.uk', 'foo.gov',
|
|
8
|
-
'foo.fed.us', 'foo.state.il.us', 'state.il.us',
|
|
9
|
-
'foo@af.mil', 'foo.gov.in'].each do |domain|
|
|
10
|
-
subject { described_class.new(domain) }
|
|
11
|
-
|
|
12
|
-
it "knows #{domain.inspect} is valid government domain" do
|
|
13
|
-
expect(described_class.valid?(domain)).to be(true)
|
|
14
|
-
expect(subject.valid?).to be(true)
|
|
15
|
-
end
|
|
16
|
-
end
|
|
17
|
-
end
|
|
18
|
-
|
|
19
|
-
context 'invalid domains' do
|
|
20
|
-
['foo.bar.com', 'bar@foo.biz', 'http://www.foo.biz',
|
|
21
|
-
'foo.uk', 'gov', 'foo@k12.champaign.il.us', 'foo@kii.gov.by',
|
|
22
|
-
'foo', '', nil, ' ', 'foo.city.il.us', 'foo.ci.il.us',
|
|
23
|
-
'foo.zx.us', 'foo@mail.gov.ua', 'foo@gwu.edu'].each do |domain|
|
|
24
|
-
subject { described_class.new(domain) }
|
|
25
|
-
|
|
26
|
-
it "knows #{domain.inspect} is not a valid government domain" do
|
|
27
|
-
expect(described_class.valid?(domain)).to be(false)
|
|
28
|
-
expect(subject.valid?).to be(false)
|
|
29
|
-
end
|
|
30
|
-
end
|
|
31
|
-
end
|
|
32
|
-
|
|
33
|
-
context 'localities' do
|
|
34
|
-
subject { described_class.new(domain) }
|
|
35
|
-
|
|
36
|
-
context 'when given github.gov' do
|
|
37
|
-
let(:domain) { 'github.gov' }
|
|
38
|
-
|
|
39
|
-
it "knows it's not a locality" do
|
|
40
|
-
expect(subject.locality?).to be(false)
|
|
41
|
-
end
|
|
42
|
-
end
|
|
43
|
-
|
|
44
|
-
context 'when given foo.state.il.us' do
|
|
45
|
-
let(:domain) { 'foo.state.il.us' }
|
|
46
|
-
|
|
47
|
-
it "knows it's a locality" do
|
|
48
|
-
expect(subject.locality?).to be(true)
|
|
49
|
-
end
|
|
50
|
-
end
|
|
51
|
-
end
|
|
52
|
-
|
|
53
|
-
context 'class methods' do
|
|
54
|
-
it 'returns the domain list' do
|
|
55
|
-
expect(described_class.list).to be_a(Gman::DomainList)
|
|
56
|
-
end
|
|
57
|
-
|
|
58
|
-
it 'returns the academic list' do
|
|
59
|
-
expect(described_class.academic_list).to be_a(Gman::DomainList)
|
|
60
|
-
end
|
|
61
|
-
|
|
62
|
-
it 'returns the config path' do
|
|
63
|
-
expect(Dir.exist?(described_class.config_path)).to be(true)
|
|
64
|
-
end
|
|
65
|
-
|
|
66
|
-
it 'returns the list path' do
|
|
67
|
-
expect(File.exist?(described_class.list_path)).to be(true)
|
|
68
|
-
end
|
|
69
|
-
|
|
70
|
-
it 'returns the academic list path' do
|
|
71
|
-
expect(File.exist?(described_class.academic_list_path)).to be(true)
|
|
72
|
-
end
|
|
73
|
-
end
|
|
74
|
-
end
|
data/spec/spec_helper.rb
DELETED
|
@@ -1,31 +0,0 @@
|
|
|
1
|
-
# frozen_string_literal: true
|
|
2
|
-
|
|
3
|
-
require 'parallel'
|
|
4
|
-
require 'open3'
|
|
5
|
-
|
|
6
|
-
RSpec.configure do |config|
|
|
7
|
-
config.example_status_persistence_file_path = 'spec/examples.txt'
|
|
8
|
-
config.disable_monkey_patching!
|
|
9
|
-
config.default_formatter = 'doc' if config.files_to_run.one?
|
|
10
|
-
config.order = :random
|
|
11
|
-
Kernel.srand config.seed
|
|
12
|
-
end
|
|
13
|
-
|
|
14
|
-
require_relative '../lib/gman'
|
|
15
|
-
require_relative '../lib/gman/domain_list'
|
|
16
|
-
require_relative '../lib/gman/importer'
|
|
17
|
-
|
|
18
|
-
def fixture_path(fixture)
|
|
19
|
-
File.expand_path "./fixtures/#{fixture}", File.dirname(__FILE__)
|
|
20
|
-
end
|
|
21
|
-
|
|
22
|
-
def stubbed_list_path
|
|
23
|
-
File.expand_path './fixtures/domains.txt', File.dirname(__FILE__)
|
|
24
|
-
end
|
|
25
|
-
|
|
26
|
-
def with_env(key, value)
|
|
27
|
-
old_env = ENV[key]
|
|
28
|
-
ENV[key] = value
|
|
29
|
-
yield
|
|
30
|
-
ENV[key] = old_env
|
|
31
|
-
end
|