wayfarer 0.0.3

Sign up to get free protection for your applications and to get access to all the features.
Files changed (235) hide show
  1. checksums.yaml +7 -0
  2. data/.gitignore +8 -0
  3. data/.rbenv-gemsets +1 -0
  4. data/.rspec +3 -0
  5. data/.rubocop.yml +21 -0
  6. data/.ruby-version +1 -0
  7. data/.travis.yml +5 -0
  8. data/.yardopts +3 -0
  9. data/Changelog.md +10 -0
  10. data/Gemfile +11 -0
  11. data/LICENSE +19 -0
  12. data/README.md +21 -0
  13. data/Rakefile +114 -0
  14. data/benchmark/frontiers.rb +143 -0
  15. data/bin/wayfarer +116 -0
  16. data/docs/.gitignore +2 -0
  17. data/docs/_config.yml +15 -0
  18. data/docs/_includes/base.html +7 -0
  19. data/docs/_includes/head.html +10 -0
  20. data/docs/_includes/navigation.html +187 -0
  21. data/docs/_layouts/default.html +42 -0
  22. data/docs/_sass/base.scss +439 -0
  23. data/docs/_sass/variables.scss +24 -0
  24. data/docs/_sass/vendor/bourbon/_bourbon-deprecate.scss +19 -0
  25. data/docs/_sass/vendor/bourbon/_bourbon-deprecated-upcoming.scss +425 -0
  26. data/docs/_sass/vendor/bourbon/_bourbon.scss +90 -0
  27. data/docs/_sass/vendor/bourbon/addons/_border-color.scss +29 -0
  28. data/docs/_sass/vendor/bourbon/addons/_border-radius.scss +48 -0
  29. data/docs/_sass/vendor/bourbon/addons/_border-style.scss +28 -0
  30. data/docs/_sass/vendor/bourbon/addons/_border-width.scss +28 -0
  31. data/docs/_sass/vendor/bourbon/addons/_buttons.scss +69 -0
  32. data/docs/_sass/vendor/bourbon/addons/_clearfix.scss +25 -0
  33. data/docs/_sass/vendor/bourbon/addons/_ellipsis.scss +30 -0
  34. data/docs/_sass/vendor/bourbon/addons/_font-stacks.scss +31 -0
  35. data/docs/_sass/vendor/bourbon/addons/_hide-text.scss +27 -0
  36. data/docs/_sass/vendor/bourbon/addons/_margin.scss +29 -0
  37. data/docs/_sass/vendor/bourbon/addons/_padding.scss +29 -0
  38. data/docs/_sass/vendor/bourbon/addons/_position.scss +51 -0
  39. data/docs/_sass/vendor/bourbon/addons/_prefixer.scss +66 -0
  40. data/docs/_sass/vendor/bourbon/addons/_retina-image.scss +27 -0
  41. data/docs/_sass/vendor/bourbon/addons/_size.scss +56 -0
  42. data/docs/_sass/vendor/bourbon/addons/_text-inputs.scss +118 -0
  43. data/docs/_sass/vendor/bourbon/addons/_timing-functions.scss +34 -0
  44. data/docs/_sass/vendor/bourbon/addons/_triangle.scss +63 -0
  45. data/docs/_sass/vendor/bourbon/addons/_word-wrap.scss +29 -0
  46. data/docs/_sass/vendor/bourbon/css3/_animation.scss +61 -0
  47. data/docs/_sass/vendor/bourbon/css3/_appearance.scss +5 -0
  48. data/docs/_sass/vendor/bourbon/css3/_backface-visibility.scss +5 -0
  49. data/docs/_sass/vendor/bourbon/css3/_background-image.scss +44 -0
  50. data/docs/_sass/vendor/bourbon/css3/_background.scss +57 -0
  51. data/docs/_sass/vendor/bourbon/css3/_border-image.scss +61 -0
  52. data/docs/_sass/vendor/bourbon/css3/_calc.scss +6 -0
  53. data/docs/_sass/vendor/bourbon/css3/_columns.scss +67 -0
  54. data/docs/_sass/vendor/bourbon/css3/_filter.scss +6 -0
  55. data/docs/_sass/vendor/bourbon/css3/_flex-box.scss +327 -0
  56. data/docs/_sass/vendor/bourbon/css3/_font-face.scss +29 -0
  57. data/docs/_sass/vendor/bourbon/css3/_font-feature-settings.scss +6 -0
  58. data/docs/_sass/vendor/bourbon/css3/_hidpi-media-query.scss +12 -0
  59. data/docs/_sass/vendor/bourbon/css3/_hyphens.scss +6 -0
  60. data/docs/_sass/vendor/bourbon/css3/_image-rendering.scss +15 -0
  61. data/docs/_sass/vendor/bourbon/css3/_keyframes.scss +38 -0
  62. data/docs/_sass/vendor/bourbon/css3/_linear-gradient.scss +40 -0
  63. data/docs/_sass/vendor/bourbon/css3/_perspective.scss +12 -0
  64. data/docs/_sass/vendor/bourbon/css3/_placeholder.scss +10 -0
  65. data/docs/_sass/vendor/bourbon/css3/_radial-gradient.scss +40 -0
  66. data/docs/_sass/vendor/bourbon/css3/_selection.scss +44 -0
  67. data/docs/_sass/vendor/bourbon/css3/_text-decoration.scss +27 -0
  68. data/docs/_sass/vendor/bourbon/css3/_transform.scss +21 -0
  69. data/docs/_sass/vendor/bourbon/css3/_transition.scss +81 -0
  70. data/docs/_sass/vendor/bourbon/css3/_user-select.scss +5 -0
  71. data/docs/_sass/vendor/bourbon/functions/_assign-inputs.scss +16 -0
  72. data/docs/_sass/vendor/bourbon/functions/_contains-falsy.scss +25 -0
  73. data/docs/_sass/vendor/bourbon/functions/_contains.scss +31 -0
  74. data/docs/_sass/vendor/bourbon/functions/_is-length.scss +16 -0
  75. data/docs/_sass/vendor/bourbon/functions/_is-light.scss +26 -0
  76. data/docs/_sass/vendor/bourbon/functions/_is-number.scss +16 -0
  77. data/docs/_sass/vendor/bourbon/functions/_is-size.scss +23 -0
  78. data/docs/_sass/vendor/bourbon/functions/_modular-scale.scss +74 -0
  79. data/docs/_sass/vendor/bourbon/functions/_px-to-em.scss +24 -0
  80. data/docs/_sass/vendor/bourbon/functions/_px-to-rem.scss +26 -0
  81. data/docs/_sass/vendor/bourbon/functions/_shade.scss +24 -0
  82. data/docs/_sass/vendor/bourbon/functions/_strip-units.scss +22 -0
  83. data/docs/_sass/vendor/bourbon/functions/_tint.scss +24 -0
  84. data/docs/_sass/vendor/bourbon/functions/_transition-property-name.scss +37 -0
  85. data/docs/_sass/vendor/bourbon/functions/_unpack.scss +32 -0
  86. data/docs/_sass/vendor/bourbon/helpers/_convert-units.scss +26 -0
  87. data/docs/_sass/vendor/bourbon/helpers/_directional-values.scss +108 -0
  88. data/docs/_sass/vendor/bourbon/helpers/_font-source-declaration.scss +53 -0
  89. data/docs/_sass/vendor/bourbon/helpers/_gradient-positions-parser.scss +24 -0
  90. data/docs/_sass/vendor/bourbon/helpers/_linear-angle-parser.scss +35 -0
  91. data/docs/_sass/vendor/bourbon/helpers/_linear-gradient-parser.scss +51 -0
  92. data/docs/_sass/vendor/bourbon/helpers/_linear-positions-parser.scss +77 -0
  93. data/docs/_sass/vendor/bourbon/helpers/_linear-side-corner-parser.scss +41 -0
  94. data/docs/_sass/vendor/bourbon/helpers/_radial-arg-parser.scss +74 -0
  95. data/docs/_sass/vendor/bourbon/helpers/_radial-gradient-parser.scss +55 -0
  96. data/docs/_sass/vendor/bourbon/helpers/_radial-positions-parser.scss +28 -0
  97. data/docs/_sass/vendor/bourbon/helpers/_render-gradients.scss +31 -0
  98. data/docs/_sass/vendor/bourbon/helpers/_shape-size-stripper.scss +15 -0
  99. data/docs/_sass/vendor/bourbon/helpers/_str-to-num.scss +55 -0
  100. data/docs/_sass/vendor/bourbon/settings/_asset-pipeline.scss +7 -0
  101. data/docs/_sass/vendor/bourbon/settings/_deprecation-warnings.scss +8 -0
  102. data/docs/_sass/vendor/bourbon/settings/_prefixer.scss +9 -0
  103. data/docs/_sass/vendor/bourbon/settings/_px-to-em.scss +1 -0
  104. data/docs/_sass/vendor/neat/_neat-helpers.scss +11 -0
  105. data/docs/_sass/vendor/neat/_neat.scss +23 -0
  106. data/docs/_sass/vendor/neat/functions/_new-breakpoint.scss +49 -0
  107. data/docs/_sass/vendor/neat/functions/_private.scss +114 -0
  108. data/docs/_sass/vendor/neat/grid/_box-sizing.scss +15 -0
  109. data/docs/_sass/vendor/neat/grid/_direction-context.scss +33 -0
  110. data/docs/_sass/vendor/neat/grid/_display-context.scss +28 -0
  111. data/docs/_sass/vendor/neat/grid/_fill-parent.scss +22 -0
  112. data/docs/_sass/vendor/neat/grid/_media.scss +92 -0
  113. data/docs/_sass/vendor/neat/grid/_omega.scss +87 -0
  114. data/docs/_sass/vendor/neat/grid/_outer-container.scss +34 -0
  115. data/docs/_sass/vendor/neat/grid/_pad.scss +25 -0
  116. data/docs/_sass/vendor/neat/grid/_private.scss +35 -0
  117. data/docs/_sass/vendor/neat/grid/_row.scss +52 -0
  118. data/docs/_sass/vendor/neat/grid/_shift.scss +50 -0
  119. data/docs/_sass/vendor/neat/grid/_span-columns.scss +94 -0
  120. data/docs/_sass/vendor/neat/grid/_to-deprecate.scss +97 -0
  121. data/docs/_sass/vendor/neat/grid/_visual-grid.scss +42 -0
  122. data/docs/_sass/vendor/neat/mixins/_clearfix.scss +25 -0
  123. data/docs/_sass/vendor/neat/settings/_disable-warnings.scss +13 -0
  124. data/docs/_sass/vendor/neat/settings/_grid.scss +51 -0
  125. data/docs/_sass/vendor/neat/settings/_visual-grid.scss +27 -0
  126. data/docs/_sass/vendor/normalize-3.0.2.scss +427 -0
  127. data/docs/_sass/vendor/pygments.scss +356 -0
  128. data/docs/automating_browsers/capybara.md +70 -0
  129. data/docs/css/screen.scss +7 -0
  130. data/docs/guides/callbacks.md +45 -0
  131. data/docs/guides/cli.md +52 -0
  132. data/docs/guides/configuration.md +184 -0
  133. data/docs/guides/error_handling.md +46 -0
  134. data/docs/guides/frontiers.md +93 -0
  135. data/docs/guides/halting.md +23 -0
  136. data/docs/guides/job_queues.md +26 -0
  137. data/docs/guides/locals.md +36 -0
  138. data/docs/guides/logging.md +22 -0
  139. data/docs/guides/page_objects.md +67 -0
  140. data/docs/guides/peeking.md +46 -0
  141. data/docs/guides/selenium_capybara.md +100 -0
  142. data/docs/guides/tutorial.md +452 -0
  143. data/docs/index.md +82 -0
  144. data/docs/js/navigation.js +11 -0
  145. data/docs/misc/contributing.md +20 -0
  146. data/docs/misc/testing.md +11 -0
  147. data/docs/recipes/authentication.md +23 -0
  148. data/docs/recipes/csv.md +29 -0
  149. data/docs/recipes/javascript.md +20 -0
  150. data/docs/recipes/multiple_uris.md +18 -0
  151. data/docs/recipes/screenshots.md +20 -0
  152. data/docs/routing/custom_rules.md +16 -0
  153. data/docs/routing/filetypes_rules.md +21 -0
  154. data/docs/routing/host_rules.md +24 -0
  155. data/docs/routing/path_rules.md +33 -0
  156. data/docs/routing/protocol_rules.md +17 -0
  157. data/docs/routing/query_rules.md +69 -0
  158. data/docs/routing/routes.md +96 -0
  159. data/docs/routing/uri_rules.md +18 -0
  160. data/examples/collect_github_issues.rb +65 -0
  161. data/examples/find_foobar_on_wikipedia.rb +23 -0
  162. data/lib/wayfarer/configuration.rb +86 -0
  163. data/lib/wayfarer/crawl.rb +79 -0
  164. data/lib/wayfarer/crawl_observer.rb +103 -0
  165. data/lib/wayfarer/dispatcher.rb +104 -0
  166. data/lib/wayfarer/finders.rb +61 -0
  167. data/lib/wayfarer/frontiers/frontier.rb +79 -0
  168. data/lib/wayfarer/frontiers/memory_bloomfilter.rb +32 -0
  169. data/lib/wayfarer/frontiers/memory_frontier.rb +76 -0
  170. data/lib/wayfarer/frontiers/memory_trie_frontier.rb +39 -0
  171. data/lib/wayfarer/frontiers/normalize_uris.rb +48 -0
  172. data/lib/wayfarer/frontiers/redis_bloomfilter.rb +34 -0
  173. data/lib/wayfarer/frontiers/redis_frontier.rb +83 -0
  174. data/lib/wayfarer/http_adapters/adapter_pool.rb +62 -0
  175. data/lib/wayfarer/http_adapters/net_http_adapter.rb +77 -0
  176. data/lib/wayfarer/http_adapters/selenium_adapter.rb +80 -0
  177. data/lib/wayfarer/job.rb +211 -0
  178. data/lib/wayfarer/locals.rb +40 -0
  179. data/lib/wayfarer/page.rb +94 -0
  180. data/lib/wayfarer/parsers/json_parser.rb +20 -0
  181. data/lib/wayfarer/parsers/xml_parser.rb +27 -0
  182. data/lib/wayfarer/processor.rb +103 -0
  183. data/lib/wayfarer/routing/custom_rule.rb +21 -0
  184. data/lib/wayfarer/routing/filetypes_rule.rb +20 -0
  185. data/lib/wayfarer/routing/host_rule.rb +19 -0
  186. data/lib/wayfarer/routing/path_rule.rb +54 -0
  187. data/lib/wayfarer/routing/protocol_rule.rb +21 -0
  188. data/lib/wayfarer/routing/query_rule.rb +59 -0
  189. data/lib/wayfarer/routing/router.rb +71 -0
  190. data/lib/wayfarer/routing/rule.rb +114 -0
  191. data/lib/wayfarer/routing/uri_rule.rb +21 -0
  192. data/lib/wayfarer.rb +68 -0
  193. data/spec/configuration_spec.rb +26 -0
  194. data/spec/crawl_spec.rb +48 -0
  195. data/spec/finders_spec.rb +49 -0
  196. data/spec/frontiers/memory_bloomfilter_spec.rb +6 -0
  197. data/spec/frontiers/memory_frontier_spec.rb +6 -0
  198. data/spec/frontiers/memory_trie_frontier_spec.rb +6 -0
  199. data/spec/frontiers/normalize_uris_spec.rb +59 -0
  200. data/spec/frontiers/redis_bloomfilter_spec.rb +6 -0
  201. data/spec/frontiers/redis_frontier_spec.rb +6 -0
  202. data/spec/http_adapters/adapter_pool_spec.rb +33 -0
  203. data/spec/http_adapters/net_http_adapter_spec.rb +83 -0
  204. data/spec/http_adapters/selenium_adapter_spec.rb +53 -0
  205. data/spec/integration/callbacks_spec.rb +42 -0
  206. data/spec/integration/locals_spec.rb +106 -0
  207. data/spec/integration/peeking_spec.rb +61 -0
  208. data/spec/job_spec.rb +122 -0
  209. data/spec/page_spec.rb +38 -0
  210. data/spec/parsers/json_parser_spec.rb +30 -0
  211. data/spec/parsers/xml_parser_spec.rb +24 -0
  212. data/spec/processor_spec.rb +31 -0
  213. data/spec/routing/custom_rule_spec.rb +26 -0
  214. data/spec/routing/filetypes_rule_spec.rb +40 -0
  215. data/spec/routing/host_rule_spec.rb +48 -0
  216. data/spec/routing/path_rule_spec.rb +66 -0
  217. data/spec/routing/protocol_rule_spec.rb +26 -0
  218. data/spec/routing/query_rule_spec.rb +124 -0
  219. data/spec/routing/router_spec.rb +67 -0
  220. data/spec/routing/rule_spec.rb +251 -0
  221. data/spec/routing/uri_rule_spec.rb +24 -0
  222. data/spec/shared/frontier.rb +96 -0
  223. data/spec/spec_helpers.rb +62 -0
  224. data/spec/wayfarer_spec.rb +24 -0
  225. data/support/static/finders.html +38 -0
  226. data/support/static/graph/details/a.html +10 -0
  227. data/support/static/graph/details/b.html +10 -0
  228. data/support/static/graph/index.html +20 -0
  229. data/support/static/json/dummy.json +13 -0
  230. data/support/static/links/links.html +28 -0
  231. data/support/static/xml/dummy.xml +120 -0
  232. data/support/test_app.rb +45 -0
  233. data/wayfarer-jruby.gemspec +49 -0
  234. data/wayfarer.gemspec +53 -0
  235. metadata +697 -0
@@ -0,0 +1,53 @@
1
+ # frozen_string_literal: true
2
+ require "spec_helpers"
3
+
4
+ describe Wayfarer::HTTPAdapters::SeleniumAdapter, selenium: true do
5
+ subject(:adapter) { Wayfarer::HTTPAdapters::SeleniumAdapter.new }
6
+ after { adapter.free }
7
+
8
+ describe "#fetch" do
9
+ it "returns a Page" do
10
+ uri = URI("http://0.0.0.0:9876/hello_world")
11
+ page = adapter.fetch(uri)
12
+ expect(page).to be_a Page
13
+ end
14
+
15
+ it "sets the correct URI" do
16
+ uri = URI("http://0.0.0.0:9876/status_code/404")
17
+ page = adapter.fetch(uri)
18
+ expect(page.uri.to_s).to eq "http://0.0.0.0:9876/status_code/404"
19
+ end
20
+
21
+ it "retrieves the correct HTTP status code" do
22
+ uri = URI("http://0.0.0.0:9876/status_code/404")
23
+ page = adapter.fetch(uri)
24
+ expect(page.status_code).to be 404
25
+ end
26
+
27
+ it "retrieves the correct response body" do
28
+ uri = URI("http://0.0.0.0:9876/hello_world")
29
+ page = adapter.fetch(uri)
30
+ expect(page.body).to match /Hello world!/
31
+ end
32
+
33
+ it "retrieves the correct response headers" do
34
+ uri = test_app("/hello_world")
35
+ page = adapter.fetch(uri)
36
+ expect(page.headers["hello"]).to eq ["world"]
37
+ end
38
+
39
+ context "when response is a redirect" do
40
+ it "follows the redirect" do
41
+ uri = test_app("/redirect?times=3")
42
+ page = adapter.fetch(uri)
43
+ expect(page.uri.to_s).to eq test_app("/redirect?times=0").to_s
44
+ end
45
+
46
+ context "when encountering a redirect loop" do
47
+ it "returns `nil` as HTTP status code" do
48
+ pending; fail
49
+ end
50
+ end
51
+ end
52
+ end
53
+ end
@@ -0,0 +1,42 @@
1
+ # frozen_string_literal: true
2
+ require "spec_helpers"
3
+
4
+ describe Wayfarer, integration: true do
5
+ describe "Callbacks" do
6
+ subject(:job) do
7
+ Class.new(Wayfarer::Job) do
8
+ config.reraise_exceptions = true
9
+ end
10
+ end
11
+
12
+ describe "ActiveJob-inherited callbacks" do
13
+ they "fire" do
14
+ job.class_eval do
15
+ before_perform { fail }
16
+ end
17
+
18
+ expect {
19
+ job.perform_now
20
+ }.to raise_error
21
+ end
22
+ end
23
+
24
+ describe "Own callbacks" do
25
+ describe "::before_crawl" do
26
+ it "fires" do
27
+ job.class_eval { before_crawl { fail } }
28
+
29
+ expect { job.perform_now }.to raise_error
30
+ end
31
+ end
32
+
33
+ describe "::after_crawl" do
34
+ it "fires" do
35
+ job.class_eval { after_crawl { fail } }
36
+
37
+ expect { job.perform_now }.to raise_error
38
+ end
39
+ end
40
+ end
41
+ end
42
+ end
@@ -0,0 +1,106 @@
1
+ # frozen_string_literal: true
2
+ require "spec_helpers"
3
+
4
+ describe Wayfarer, integration: true do
5
+ describe "Locals" do
6
+ subject(:job) do
7
+ Class.new(Wayfarer::Job) do
8
+ config.reraise_exceptions = true
9
+ end
10
+ end
11
+
12
+ describe "Initial local values" do
13
+ let(:entry) { test_app("/hello_world") }
14
+
15
+ they "do not change" do
16
+ job.class_eval do
17
+ route.path "/hello_world", to: :foobar
18
+
19
+ let(:foo) { {} }
20
+
21
+ def foobar
22
+ foo[:bar] = :qux
23
+ end
24
+ end
25
+
26
+ expect {
27
+ job.perform_now(entry)
28
+ }.not_to change { job.locals[:foo] }
29
+ end
30
+
31
+ context "when declared with ::let" do
32
+ they "get replaced with thread-safe counterparts" do
33
+ job.class_eval do
34
+ route.path "/hello_world", to: :foobar
35
+
36
+ let(:hash) { {} }
37
+ let(:array) { [] }
38
+ let(:fixnum) { 123 }
39
+ let(:tru) { true }
40
+ let(:fuls) { false }
41
+
42
+ def foobar
43
+ fail unless hash.is_a? Concurrent::Hash
44
+ fail unless array.is_a? Concurrent::Array
45
+ fail unless fixnum.is_a? Concurrent::AtomicFixnum
46
+ fail unless tru.is_a? Concurrent::AtomicBoolean
47
+ fail unless fuls.is_a? Concurrent::AtomicBoolean
48
+ end
49
+ end
50
+
51
+ expect {
52
+ job.perform_now(entry)
53
+ }.not_to raise_error
54
+ end
55
+ end
56
+ end
57
+
58
+ describe "Locals" do
59
+ let(:entry) { test_app("/graph/index.html") }
60
+
61
+ they "can be mutated within actions" do
62
+ job.class_eval do
63
+ route.path "/graph/index.html", to: :index
64
+ route.path "/graph/details/a.html", to: :detail
65
+
66
+ let(:hash) { {} }
67
+
68
+ def index
69
+ hash[:foo] = 42
70
+ stage page.links
71
+ end
72
+
73
+ def detail
74
+ fail unless hash[:foo] == 42
75
+ end
76
+ end
77
+
78
+ expect {
79
+ job.perform_now(entry)
80
+ }.not_to raise_error
81
+ end
82
+
83
+ they "are accessible within callbacks" do
84
+ job.class_eval do
85
+ route.path "/graph/index.html", to: :index
86
+
87
+ let(:hash) { { foo: :bar} }
88
+
89
+ before_crawl do
90
+ fail unless hash[:foo] == :bar
91
+ end
92
+
93
+ after_crawl do
94
+ fail unless hash[:foo] == :qux
95
+ end
96
+
97
+ def index
98
+ hash[:foo] = :qux
99
+ end
100
+ end
101
+
102
+ expect { job.perform_now(entry) }.not_to raise_error
103
+ end
104
+ end
105
+ end
106
+ end
@@ -0,0 +1,61 @@
1
+ # frozen_string_literal: true
2
+ require "spec_helpers"
3
+
4
+ describe Wayfarer, integration: true do
5
+ subject(:job) do
6
+ Class.new(Wayfarer::Job) do
7
+ config.reraise_exceptions = true
8
+ end
9
+ end
10
+
11
+ let(:entry) { test_app("/graph/index.html") }
12
+
13
+ describe "Peeking" do
14
+ it "works" do
15
+ job.class_eval do
16
+ route.path "/graph/index.html", to: :index
17
+ route.path "/graph/details/a.html", to: :detail
18
+
19
+ def index
20
+ peek = yield "http://localhost:9876/graph/details/a.html"
21
+ fail unless peek == :ok
22
+ end
23
+
24
+ def detail
25
+ :ok
26
+ end
27
+ end
28
+
29
+ expect {
30
+ job.perform_now(entry)
31
+ }.not_to raise_error
32
+ end
33
+ end
34
+
35
+ describe "Recursive peeking" do
36
+ it "does not work" do
37
+ job.class_eval do
38
+ route.path "/graph/index.html", to: :index
39
+ route.path "/graph/details/a.html", to: :a
40
+ route.path "/graph/details/a.html", to: :b
41
+
42
+ def index
43
+ peek = yield "http://localhost:9876/graph/details/a.html"
44
+ fail unless peek == :ok
45
+ end
46
+
47
+ def a
48
+ yield "http://localhost:9876/graph/details/b.html" or :ok
49
+ end
50
+
51
+ def b
52
+ yield "http://localhost:9876/graph/details/a.html"
53
+ end
54
+ end
55
+
56
+ expect {
57
+ job.perform_now(entry)
58
+ }.not_to raise_error
59
+ end
60
+ end
61
+ end
data/spec/job_spec.rb ADDED
@@ -0,0 +1,122 @@
1
+ # frozen_string_literal: true
2
+ require "spec_helpers"
3
+
4
+ describe Wayfarer::Job do
5
+ subject(:job) { Class.new(Wayfarer::Job) }
6
+
7
+ describe "::prepare" do
8
+ it "copies the router" do
9
+ job.class_eval do
10
+ route.host "example.com", to: :foobar
11
+ end
12
+
13
+ prepared_job = job.prepare
14
+
15
+ expect(prepared_job.router).not_to be job.router
16
+
17
+ uri = URI("http://example.com")
18
+ expect(prepared_job.router.routes?(uri)).to be true
19
+ end
20
+
21
+ it "copies locals" do
22
+ job.class_eval do
23
+ let(:foo) { { bar: :qux } }
24
+ let(:baz) { 42 }
25
+ end
26
+
27
+ prepared_job = job.prepare
28
+
29
+ expect(prepared_job.locals).not_to be job.locals
30
+
31
+ expect(prepared_job.locals[:foo]).to be_a Concurrent::Hash
32
+ expect(prepared_job.locals[:baz]).to be_a Concurrent::AtomicFixnum
33
+ end
34
+
35
+ it "defines instance accessors for locals" do
36
+ job.class_eval do
37
+ let(:foo) { { bar: :qux } }
38
+ let(:baz) { 42 }
39
+ end
40
+
41
+ prepared_job = job.prepare
42
+
43
+ expect(prepared_job).to respond_to(:foo)
44
+ expect(prepared_job).to respond_to(:baz)
45
+ end
46
+ end
47
+
48
+ describe "::config" do
49
+ it "allows manipulating the configuration" do
50
+ expect {
51
+ job.config { |c| c.http_adapter = :selenium }
52
+ }.to change { job.config.http_adapter }.to(:selenium)
53
+ end
54
+
55
+ it "does not manipulate the global configuration" do
56
+ expect {
57
+ job.config { |c| c.http_adapter = :selenium }
58
+ }.not_to change { Wayfarer.config.http_adapter }
59
+ end
60
+ end
61
+
62
+ describe "#halt" do
63
+ it "sets the halting flag" do
64
+ job_instance = job.new
65
+
66
+ expect {
67
+ job_instance.send(:halt)
68
+ }.to change { job_instance.halts? }.from(false).to(true)
69
+ end
70
+ end
71
+
72
+ describe "#stage" do
73
+ it "stages URIs" do
74
+ job_instance = job.new
75
+ job_instance.page = Page.new(uri: URI("https://yahoo.com/qux"))
76
+
77
+ uris = %w(
78
+ http://google.com
79
+ http://example.com
80
+ )
81
+
82
+ expected = uris.map { |u| URI(u) }
83
+
84
+ expect {
85
+ job_instance.send(:stage, *uris)
86
+ }.to change { job_instance.staged_uris }.from([]).to(expected)
87
+ end
88
+
89
+ it "expands relative URIs" do
90
+ job_instance = job.new
91
+ job_instance.page = Page.new(uri: URI("https://yahoo.com/qux"))
92
+
93
+ uris = %w(
94
+ /foo/bar
95
+ bar/qux.html
96
+ barfoo
97
+ )
98
+
99
+ expected = %w(
100
+ https://yahoo.com/qux/foo/bar
101
+ https://yahoo.com/qux/bar/qux.html
102
+ https://yahoo.com/qux/barfoo
103
+ ).map { |u| URI(u) }
104
+
105
+ expect {
106
+ job_instance.send(:stage, *uris)
107
+ }.to change { job_instance.staged_uris }.from([]).to(expected)
108
+ end
109
+
110
+ context "with non-HTTP(s) URIs" do
111
+ it "ignores them and does not raise an exception" do
112
+ job_instance = job.new
113
+
114
+ expect {
115
+ job_instance.send(:stage, "ftp://example.com")
116
+ }.not_to raise_error
117
+
118
+ expect(job_instance.staged_uris).to be_empty
119
+ end
120
+ end
121
+ end
122
+ end
data/spec/page_spec.rb ADDED
@@ -0,0 +1,38 @@
1
+ # frozen_string_literal: true
2
+ require "spec_helpers"
3
+
4
+ describe Wayfarer::Page do
5
+ subject(:page) { fetch_page(test_app("/links/links.html")) }
6
+
7
+ describe "#doc" do
8
+ context "when Content-Type is HTML" do
9
+ it "returns a Nokogiri::HTML::Document" do
10
+ expect(page.doc).to be_a Nokogiri::HTML::Document
11
+ end
12
+ end
13
+
14
+ context "when Content-Type is XML" do
15
+ subject(:page) { fetch_page(test_app("/xml/dummy.xml")) }
16
+
17
+ it "returns a Nokogiri::XML::Document" do
18
+ expect(page.doc).to be_a Nokogiri::XML::Document
19
+ end
20
+ end
21
+
22
+ context "when Content-Type is JSON" do
23
+ subject(:page) { fetch_page(test_app("/json/dummy.json")) }
24
+
25
+ it "returns a Hash" do
26
+ expect(page.doc).to be_a Hash
27
+ end
28
+ end
29
+ end
30
+
31
+ describe "Forwarding" do
32
+ it "forwards calls to Pismo", mri_only: true do
33
+ Pismo::Document::ATTRIBUTE_METHODS.each do |method|
34
+ expect(page).to respond_to(method)
35
+ end
36
+ end
37
+ end
38
+ end
@@ -0,0 +1,30 @@
1
+ # frozen_string_literal: true
2
+ require "spec_helpers"
3
+
4
+ describe Wayfarer::Parsers::JSONParser do
5
+ subject(:parser) { Parsers::JSONParser }
6
+
7
+ describe ".parse" do
8
+ it "returns a Hash" do
9
+ json_str = <<-json
10
+ {
11
+ "id": 1,
12
+ "name": "Foo",
13
+ "price": 123,
14
+ "tags": [
15
+ "Bar",
16
+ "Eek"
17
+ ],
18
+ "stock": {
19
+ "warehouse": 300,
20
+ "retail": 20
21
+ }
22
+ }
23
+ json
24
+
25
+ doc = parser.parse(json_str)
26
+
27
+ expect(doc).to be_a Hash
28
+ end
29
+ end
30
+ end
@@ -0,0 +1,24 @@
1
+ # frozen_string_literal: true
2
+ require "spec_helpers"
3
+
4
+ describe Wayfarer::Parsers::XMLParser do
5
+ subject(:parser) { Parsers::XMLParser }
6
+
7
+ describe ".parse_html" do
8
+ it "returns a Nokogiri::HTML::Document" do
9
+ html_str = "<span>Foobar</span>"
10
+ doc = parser.parse_html(html_str)
11
+
12
+ expect(doc).to be_a Nokogiri::HTML::Document
13
+ end
14
+ end
15
+
16
+ describe ".parse_xml" do
17
+ it "returns a Nokogiri::XML::Document" do
18
+ xml_str = "<barqux>Foobar</barqux>"
19
+ doc = parser.parse_xml(xml_str)
20
+
21
+ expect(doc).to be_a Nokogiri::XML::Document
22
+ end
23
+ end
24
+ end
@@ -0,0 +1,31 @@
1
+ # frozen_string_literal: true
2
+ require "spec_helpers"
3
+
4
+ describe Wayfarer::Processor do
5
+ let(:job) { Class.new(Wayfarer::Job) }
6
+ let(:frontier) { Frontiers::MemoryFrontier.new(job.config) }
7
+ let(:dispatcher) { Dispatcher.new(job) }
8
+ subject(:processor) { Processor.new(job, frontier, dispatcher) }
9
+
10
+ describe "#halt!" do
11
+ it "sets a halting flag" do
12
+ processor.halt!
13
+ expect(processor).to be_halted
14
+ end
15
+ end
16
+
17
+ describe "#halted?" do
18
+ context "when not halted" do
19
+ it "returns false" do
20
+ expect(processor.halted?).to be false
21
+ end
22
+ end
23
+
24
+ context "when halted" do
25
+ it "returns true" do
26
+ processor.halt!
27
+ expect(processor.halted?).to be true
28
+ end
29
+ end
30
+ end
31
+ end
@@ -0,0 +1,26 @@
1
+ # frozen_string_literal: true
2
+ require "spec_helpers"
3
+
4
+ describe Wayfarer::Routing::CustomRule do
5
+ let(:uri) { URI("http://example.com") }
6
+
7
+ describe "#matches?" do
8
+ context "with a block" do
9
+ context "when block is truthy" do
10
+ subject(:rule) { CustomRule.new -> (uri) { uri.is_a?(URI) } }
11
+
12
+ it "returns true" do
13
+ expect(rule.matches?(uri)).to be true
14
+ end
15
+ end
16
+
17
+ context "when block is fals-y" do
18
+ subject(:rule) { CustomRule.new -> (_) { false } }
19
+
20
+ it "returns true" do
21
+ expect(rule.matches?(uri)).to be false
22
+ end
23
+ end
24
+ end
25
+ end
26
+ end
@@ -0,0 +1,40 @@
1
+ # frozen_string_literal: true
2
+ require "spec_helpers"
3
+
4
+ describe Wayfarer::Routing::FiletypesRule do
5
+ subject(:rule) { FiletypesRule.new([:png, :js]) }
6
+
7
+ describe "#matches?" do
8
+ context "with matching URI" do
9
+ it "returns true" do
10
+ uris = %w(
11
+ http://example.com/foo.png
12
+ https://example.com/a/b.png/c.png
13
+ http://example.com/foobar.html.png
14
+ https://example.com/foo.png/bar.png
15
+ ).map { |u| URI(u) }
16
+
17
+ uris.each do |uri|
18
+ expect(rule.matches?(uri)).to be true
19
+ end
20
+ end
21
+ end
22
+
23
+ context "with mismatching URI" do
24
+ it "returns false" do
25
+ uris = %w(
26
+ http://example.png
27
+ http://example.com.png
28
+ https://example.com/a/b.png/c
29
+ http://example.com.html
30
+ http://example.com/foobar.html
31
+ https://example.com/foo.png/bar.png.html
32
+ ).map { |u| URI(u) }
33
+
34
+ uris.each do |uri|
35
+ expect(rule.matches?(uri)).to be false
36
+ end
37
+ end
38
+ end
39
+ end
40
+ end
@@ -0,0 +1,48 @@
1
+ # frozen_string_literal: true
2
+ require "spec_helpers"
3
+
4
+ describe Wayfarer::Routing::HostRule do
5
+ subject(:rule) { HostRule.new(str_or_regexp) }
6
+
7
+ describe "#matches?" do
8
+ describe "String matching" do
9
+ let(:str_or_regexp) { "example.com" }
10
+
11
+ context "with matching URI" do
12
+ let(:uri) { URI("http://example.com/foo/bar") }
13
+
14
+ it "returns true" do
15
+ expect(rule.matches?(uri)).to be true
16
+ end
17
+ end
18
+
19
+ context "with mismatching URI" do
20
+ let(:uri) { URI("http://google.com/bar/qux") }
21
+
22
+ it "returns false" do
23
+ expect(rule.matches?(uri)).to be false
24
+ end
25
+ end
26
+ end
27
+
28
+ describe "RegExp matching" do
29
+ let(:str_or_regexp) { /example.com/ }
30
+
31
+ context "with matching URI" do
32
+ let(:uri) { URI("http://sub.example.com") }
33
+
34
+ it "returns true" do
35
+ expect(rule.matches?(uri)).to be true
36
+ end
37
+ end
38
+
39
+ context "with mismatching URI" do
40
+ let(:uri) { URI("http://example.sub.com") }
41
+
42
+ it "returns false" do
43
+ expect(rule.matches?(uri)).to be false
44
+ end
45
+ end
46
+ end
47
+ end
48
+ end
@@ -0,0 +1,66 @@
1
+ # frozen_string_literal: true
2
+ require "spec_helpers"
3
+
4
+ describe Wayfarer::Routing::PathRule, mri: true do
5
+ describe "#matches?" do
6
+ context "with a string" do
7
+ subject(:rule) { PathRule.new("/{alpha}/{beta}") }
8
+
9
+ context "with matching URI" do
10
+ let(:uri) { URI("http://example.com/foo/bar") }
11
+
12
+ it "returns true" do
13
+ expect(rule.matches?(uri)).to be true
14
+ end
15
+ end
16
+
17
+ context "with mismatching URI" do
18
+ let(:uri) { URI("http://example.com/foo") }
19
+
20
+ it "returns false" do
21
+ expect(rule.matches?(uri)).to be false
22
+ end
23
+ end
24
+ end
25
+
26
+ context "with a RegExp" do
27
+ subject(:rule) { PathRule.new(/\/(\w+)\/(\w+)/) }
28
+
29
+ context "with matching URI" do
30
+ let(:uri) { URI("http://example.com/foo/bar") }
31
+
32
+ it "returns true" do
33
+ expect(rule.matches?(uri)).to be true
34
+ end
35
+ end
36
+
37
+ context "with mismatching URI" do
38
+ let(:uri) { URI("http://example.com/foo") }
39
+
40
+ it "returns false" do
41
+ expect(rule.matches?(uri)).to be false
42
+ end
43
+ end
44
+ end
45
+ end
46
+
47
+ describe "#params" do
48
+ context "with a string" do
49
+ subject(:rule) { PathRule.new("/{alpha}/{beta}") }
50
+
51
+ it "returns the correct parameters" do
52
+ uri = URI("http://example.com/foo/bar")
53
+ expect(rule.params(uri)).to eq("alpha" => "foo", "beta" => "bar")
54
+ end
55
+ end
56
+
57
+ context "with a RegExp" do
58
+ subject(:rule) { PathRule.new(/\/(\w+)\/(\w+)/) }
59
+
60
+ it "returns the correct parameters" do
61
+ uri = URI("http://example.com/foo/bar")
62
+ expect(rule.params(uri)).to eq("0" => "foo", "1" => "bar")
63
+ end
64
+ end
65
+ end
66
+ end