wayfarer 0.0.3 → 0.4.0

Sign up to get free protection for your applications and to get access to all the features.
Files changed (339) hide show
  1. checksums.yaml +5 -5
  2. data/.github/workflows/ci.yaml +32 -0
  3. data/.gitignore +3 -4
  4. data/.rubocop.yml +25 -9
  5. data/.ruby-version +1 -1
  6. data/Dockerfile +5 -0
  7. data/Gemfile +1 -7
  8. data/Gemfile.lock +212 -0
  9. data/RELEASING.md +17 -0
  10. data/Rakefile +38 -90
  11. data/bin/wayfarer +1 -111
  12. data/docker-compose.yml +32 -0
  13. data/docs/cookbook/querying_html.md +42 -0
  14. data/docs/cookbook/screenshots.md +27 -0
  15. data/docs/cookbook/user_agent.md +7 -0
  16. data/docs/guides/browser_automation/capybara.md +3 -0
  17. data/docs/guides/browser_automation/ferrum.md +37 -0
  18. data/docs/guides/browser_automation/selenium.md +59 -0
  19. data/docs/guides/callbacks.md +27 -34
  20. data/docs/guides/configuration.md +20 -171
  21. data/docs/guides/error_handling.md +18 -33
  22. data/docs/guides/jobs.md +75 -0
  23. data/docs/guides/networking.md +20 -0
  24. data/docs/guides/pages.md +52 -0
  25. data/docs/guides/performance.md +22 -0
  26. data/docs/guides/tasks.md +38 -0
  27. data/docs/index.md +34 -68
  28. data/docs/reference/api/base.md +162 -0
  29. data/docs/reference/api/route.md +182 -0
  30. data/docs/reference/cli.md +139 -0
  31. data/docs/reference/environment_variables.md +85 -0
  32. data/lib/wayfarer/base.rb +60 -0
  33. data/lib/wayfarer/cli/base.rb +23 -0
  34. data/lib/wayfarer/cli/generate.rb +17 -0
  35. data/lib/wayfarer/cli/job.rb +58 -0
  36. data/lib/wayfarer/cli/route.rb +27 -0
  37. data/lib/wayfarer/cli/route_printer.rb +116 -0
  38. data/lib/wayfarer/cli/runner.rb +34 -0
  39. data/lib/wayfarer/cli/templates/Gemfile.tt +5 -0
  40. data/lib/wayfarer/cli/templates/job.rb.tt +8 -0
  41. data/lib/wayfarer/config.rb +67 -0
  42. data/lib/wayfarer/gc.rb +19 -0
  43. data/lib/wayfarer/middleware/chain.rb +19 -0
  44. data/lib/wayfarer/middleware/dedup.rb +25 -0
  45. data/lib/wayfarer/middleware/fetch.rb +32 -0
  46. data/lib/wayfarer/middleware/normalize.rb +25 -0
  47. data/lib/wayfarer/middleware/router.rb +21 -0
  48. data/lib/wayfarer/middleware/stage.rb +23 -0
  49. data/lib/wayfarer/middleware/worker.rb +47 -0
  50. data/lib/wayfarer/networking/ferrum.rb +70 -0
  51. data/lib/wayfarer/networking/healer.rb +21 -0
  52. data/lib/wayfarer/networking/net_http.rb +52 -0
  53. data/lib/wayfarer/networking/pool.rb +34 -0
  54. data/lib/wayfarer/networking/result.rb +18 -0
  55. data/lib/wayfarer/networking/selenium.rb +70 -0
  56. data/lib/wayfarer/page.rb +15 -71
  57. data/lib/wayfarer/parsing/json.rb +17 -0
  58. data/lib/wayfarer/parsing/xml.rb +17 -0
  59. data/lib/wayfarer/redis/barrier.rb +36 -0
  60. data/lib/wayfarer/redis/connection.rb +13 -0
  61. data/lib/wayfarer/redis/counter.rb +29 -0
  62. data/lib/wayfarer/redis/pool.rb +18 -0
  63. data/lib/wayfarer/redis/version.rb +19 -0
  64. data/lib/wayfarer/routing/custom_matcher.rb +21 -0
  65. data/lib/wayfarer/routing/dsl.rb +57 -0
  66. data/lib/wayfarer/routing/host_matcher.rb +23 -0
  67. data/lib/wayfarer/routing/path_finder.rb +46 -0
  68. data/lib/wayfarer/routing/path_matcher.rb +46 -0
  69. data/lib/wayfarer/routing/{query_rule.rb → query_matcher.rb} +24 -16
  70. data/lib/wayfarer/routing/result.rb +15 -0
  71. data/lib/wayfarer/routing/root_route.rb +7 -0
  72. data/lib/wayfarer/routing/route.rb +41 -0
  73. data/lib/wayfarer/routing/scheme_matcher.rb +21 -0
  74. data/lib/wayfarer/routing/suffix_matcher.rb +21 -0
  75. data/lib/wayfarer/routing/target_route.rb +7 -0
  76. data/lib/wayfarer/routing/url_matcher.rb +21 -0
  77. data/lib/wayfarer/serializer.rb +17 -0
  78. data/lib/wayfarer/stringify.rb +41 -0
  79. data/lib/wayfarer/task.rb +34 -0
  80. data/lib/wayfarer.rb +47 -58
  81. data/mkdocs.yml +47 -0
  82. data/requirements.txt +1 -0
  83. data/spec/base_spec.rb +219 -0
  84. data/spec/cli/generate_spec.rb +39 -0
  85. data/spec/cli/job_spec.rb +74 -0
  86. data/spec/cli/version_spec.rb +13 -0
  87. data/spec/config_spec.rb +144 -0
  88. data/spec/factories/queue/chain.rb +11 -0
  89. data/spec/factories/queue/middleware.rb +15 -0
  90. data/spec/factories/queue/page.rb +78 -0
  91. data/spec/factories/queue/task.rb +12 -0
  92. data/spec/fixtures/dummy_job.rb +7 -0
  93. data/spec/gc_spec.rb +61 -0
  94. data/spec/middleware/chain_spec.rb +96 -0
  95. data/spec/middleware/dedup_spec.rb +76 -0
  96. data/spec/middleware/fetch_spec.rb +72 -0
  97. data/spec/middleware/normalize_spec.rb +28 -0
  98. data/spec/middleware/router_spec.rb +46 -0
  99. data/spec/middleware/stage_spec.rb +39 -0
  100. data/spec/middleware/worker_spec.rb +90 -0
  101. data/spec/networking/adapter.rb +135 -0
  102. data/spec/networking/ferrum_spec.rb +28 -0
  103. data/spec/networking/healer_spec.rb +46 -0
  104. data/spec/networking/net_http_spec.rb +37 -0
  105. data/spec/networking/pool_spec.rb +42 -0
  106. data/spec/networking/selenium_spec.rb +28 -0
  107. data/spec/page_spec.rb +21 -12
  108. data/spec/{parsers/json_parser_spec.rb → parsing/json_spec.rb} +5 -4
  109. data/spec/{parsers/xml_parser_spec.rb → parsing/xml_spec.rb} +3 -2
  110. data/spec/redis/barrier_spec.rb +78 -0
  111. data/spec/redis/counter_spec.rb +32 -0
  112. data/spec/redis/pool_spec.rb +18 -0
  113. data/spec/redis/version_spec.rb +13 -0
  114. data/spec/routing/custom_matcher_spec.rb +31 -0
  115. data/spec/routing/dsl_spec.rb +98 -0
  116. data/spec/routing/host_matcher_spec.rb +49 -0
  117. data/spec/routing/integration_spec.rb +110 -0
  118. data/spec/routing/path_finder_spec.rb +33 -0
  119. data/spec/routing/path_matcher_spec.rb +43 -0
  120. data/spec/routing/{query_rule_spec.rb → query_matcher_spec.rb} +39 -26
  121. data/spec/routing/root_route_spec.rb +29 -0
  122. data/spec/routing/route_spec.rb +43 -0
  123. data/spec/routing/scheme_matcher_spec.rb +25 -0
  124. data/spec/routing/{filetypes_rule_spec.rb → suffix_matcher_spec.rb} +14 -13
  125. data/spec/routing/uri_matcher_spec.rb +27 -0
  126. data/spec/spec_helpers.rb +65 -38
  127. data/spec/stringify_spec.rb +23 -0
  128. data/{support → spec/support}/static/finders.html +0 -0
  129. data/{support → spec/support}/static/graph/details/a.html +0 -0
  130. data/{support → spec/support}/static/graph/details/b.html +0 -0
  131. data/{support → spec/support}/static/graph/index.html +0 -0
  132. data/{support → spec/support}/static/json/dummy.json +0 -0
  133. data/{support → spec/support}/static/links/links.html +0 -0
  134. data/{support → spec/support}/static/xml/dummy.xml +0 -0
  135. data/{support → spec/support}/test_app.rb +9 -2
  136. data/spec/task_spec.rb +27 -0
  137. data/spec/wayfarer_spec.rb +2 -13
  138. data/wayfarer.gemspec +39 -42
  139. metadata +191 -368
  140. data/.travis.yml +0 -5
  141. data/Changelog.md +0 -10
  142. data/README.md +0 -21
  143. data/benchmark/frontiers.rb +0 -143
  144. data/docs/.gitignore +0 -2
  145. data/docs/_config.yml +0 -15
  146. data/docs/_includes/base.html +0 -7
  147. data/docs/_includes/head.html +0 -10
  148. data/docs/_includes/navigation.html +0 -187
  149. data/docs/_layouts/default.html +0 -42
  150. data/docs/_sass/base.scss +0 -439
  151. data/docs/_sass/variables.scss +0 -24
  152. data/docs/_sass/vendor/bourbon/_bourbon-deprecate.scss +0 -19
  153. data/docs/_sass/vendor/bourbon/_bourbon-deprecated-upcoming.scss +0 -425
  154. data/docs/_sass/vendor/bourbon/_bourbon.scss +0 -90
  155. data/docs/_sass/vendor/bourbon/addons/_border-color.scss +0 -29
  156. data/docs/_sass/vendor/bourbon/addons/_border-radius.scss +0 -48
  157. data/docs/_sass/vendor/bourbon/addons/_border-style.scss +0 -28
  158. data/docs/_sass/vendor/bourbon/addons/_border-width.scss +0 -28
  159. data/docs/_sass/vendor/bourbon/addons/_buttons.scss +0 -69
  160. data/docs/_sass/vendor/bourbon/addons/_clearfix.scss +0 -25
  161. data/docs/_sass/vendor/bourbon/addons/_ellipsis.scss +0 -30
  162. data/docs/_sass/vendor/bourbon/addons/_font-stacks.scss +0 -31
  163. data/docs/_sass/vendor/bourbon/addons/_hide-text.scss +0 -27
  164. data/docs/_sass/vendor/bourbon/addons/_margin.scss +0 -29
  165. data/docs/_sass/vendor/bourbon/addons/_padding.scss +0 -29
  166. data/docs/_sass/vendor/bourbon/addons/_position.scss +0 -51
  167. data/docs/_sass/vendor/bourbon/addons/_prefixer.scss +0 -66
  168. data/docs/_sass/vendor/bourbon/addons/_retina-image.scss +0 -27
  169. data/docs/_sass/vendor/bourbon/addons/_size.scss +0 -56
  170. data/docs/_sass/vendor/bourbon/addons/_text-inputs.scss +0 -118
  171. data/docs/_sass/vendor/bourbon/addons/_timing-functions.scss +0 -34
  172. data/docs/_sass/vendor/bourbon/addons/_triangle.scss +0 -63
  173. data/docs/_sass/vendor/bourbon/addons/_word-wrap.scss +0 -29
  174. data/docs/_sass/vendor/bourbon/css3/_animation.scss +0 -61
  175. data/docs/_sass/vendor/bourbon/css3/_appearance.scss +0 -5
  176. data/docs/_sass/vendor/bourbon/css3/_backface-visibility.scss +0 -5
  177. data/docs/_sass/vendor/bourbon/css3/_background-image.scss +0 -44
  178. data/docs/_sass/vendor/bourbon/css3/_background.scss +0 -57
  179. data/docs/_sass/vendor/bourbon/css3/_border-image.scss +0 -61
  180. data/docs/_sass/vendor/bourbon/css3/_calc.scss +0 -6
  181. data/docs/_sass/vendor/bourbon/css3/_columns.scss +0 -67
  182. data/docs/_sass/vendor/bourbon/css3/_filter.scss +0 -6
  183. data/docs/_sass/vendor/bourbon/css3/_flex-box.scss +0 -327
  184. data/docs/_sass/vendor/bourbon/css3/_font-face.scss +0 -29
  185. data/docs/_sass/vendor/bourbon/css3/_font-feature-settings.scss +0 -6
  186. data/docs/_sass/vendor/bourbon/css3/_hidpi-media-query.scss +0 -12
  187. data/docs/_sass/vendor/bourbon/css3/_hyphens.scss +0 -6
  188. data/docs/_sass/vendor/bourbon/css3/_image-rendering.scss +0 -15
  189. data/docs/_sass/vendor/bourbon/css3/_keyframes.scss +0 -38
  190. data/docs/_sass/vendor/bourbon/css3/_linear-gradient.scss +0 -40
  191. data/docs/_sass/vendor/bourbon/css3/_perspective.scss +0 -12
  192. data/docs/_sass/vendor/bourbon/css3/_placeholder.scss +0 -10
  193. data/docs/_sass/vendor/bourbon/css3/_radial-gradient.scss +0 -40
  194. data/docs/_sass/vendor/bourbon/css3/_selection.scss +0 -44
  195. data/docs/_sass/vendor/bourbon/css3/_text-decoration.scss +0 -27
  196. data/docs/_sass/vendor/bourbon/css3/_transform.scss +0 -21
  197. data/docs/_sass/vendor/bourbon/css3/_transition.scss +0 -81
  198. data/docs/_sass/vendor/bourbon/css3/_user-select.scss +0 -5
  199. data/docs/_sass/vendor/bourbon/functions/_assign-inputs.scss +0 -16
  200. data/docs/_sass/vendor/bourbon/functions/_contains-falsy.scss +0 -25
  201. data/docs/_sass/vendor/bourbon/functions/_contains.scss +0 -31
  202. data/docs/_sass/vendor/bourbon/functions/_is-length.scss +0 -16
  203. data/docs/_sass/vendor/bourbon/functions/_is-light.scss +0 -26
  204. data/docs/_sass/vendor/bourbon/functions/_is-number.scss +0 -16
  205. data/docs/_sass/vendor/bourbon/functions/_is-size.scss +0 -23
  206. data/docs/_sass/vendor/bourbon/functions/_modular-scale.scss +0 -74
  207. data/docs/_sass/vendor/bourbon/functions/_px-to-em.scss +0 -24
  208. data/docs/_sass/vendor/bourbon/functions/_px-to-rem.scss +0 -26
  209. data/docs/_sass/vendor/bourbon/functions/_shade.scss +0 -24
  210. data/docs/_sass/vendor/bourbon/functions/_strip-units.scss +0 -22
  211. data/docs/_sass/vendor/bourbon/functions/_tint.scss +0 -24
  212. data/docs/_sass/vendor/bourbon/functions/_transition-property-name.scss +0 -37
  213. data/docs/_sass/vendor/bourbon/functions/_unpack.scss +0 -32
  214. data/docs/_sass/vendor/bourbon/helpers/_convert-units.scss +0 -26
  215. data/docs/_sass/vendor/bourbon/helpers/_directional-values.scss +0 -108
  216. data/docs/_sass/vendor/bourbon/helpers/_font-source-declaration.scss +0 -53
  217. data/docs/_sass/vendor/bourbon/helpers/_gradient-positions-parser.scss +0 -24
  218. data/docs/_sass/vendor/bourbon/helpers/_linear-angle-parser.scss +0 -35
  219. data/docs/_sass/vendor/bourbon/helpers/_linear-gradient-parser.scss +0 -51
  220. data/docs/_sass/vendor/bourbon/helpers/_linear-positions-parser.scss +0 -77
  221. data/docs/_sass/vendor/bourbon/helpers/_linear-side-corner-parser.scss +0 -41
  222. data/docs/_sass/vendor/bourbon/helpers/_radial-arg-parser.scss +0 -74
  223. data/docs/_sass/vendor/bourbon/helpers/_radial-gradient-parser.scss +0 -55
  224. data/docs/_sass/vendor/bourbon/helpers/_radial-positions-parser.scss +0 -28
  225. data/docs/_sass/vendor/bourbon/helpers/_render-gradients.scss +0 -31
  226. data/docs/_sass/vendor/bourbon/helpers/_shape-size-stripper.scss +0 -15
  227. data/docs/_sass/vendor/bourbon/helpers/_str-to-num.scss +0 -55
  228. data/docs/_sass/vendor/bourbon/settings/_asset-pipeline.scss +0 -7
  229. data/docs/_sass/vendor/bourbon/settings/_deprecation-warnings.scss +0 -8
  230. data/docs/_sass/vendor/bourbon/settings/_prefixer.scss +0 -9
  231. data/docs/_sass/vendor/bourbon/settings/_px-to-em.scss +0 -1
  232. data/docs/_sass/vendor/neat/_neat-helpers.scss +0 -11
  233. data/docs/_sass/vendor/neat/_neat.scss +0 -23
  234. data/docs/_sass/vendor/neat/functions/_new-breakpoint.scss +0 -49
  235. data/docs/_sass/vendor/neat/functions/_private.scss +0 -114
  236. data/docs/_sass/vendor/neat/grid/_box-sizing.scss +0 -15
  237. data/docs/_sass/vendor/neat/grid/_direction-context.scss +0 -33
  238. data/docs/_sass/vendor/neat/grid/_display-context.scss +0 -28
  239. data/docs/_sass/vendor/neat/grid/_fill-parent.scss +0 -22
  240. data/docs/_sass/vendor/neat/grid/_media.scss +0 -92
  241. data/docs/_sass/vendor/neat/grid/_omega.scss +0 -87
  242. data/docs/_sass/vendor/neat/grid/_outer-container.scss +0 -34
  243. data/docs/_sass/vendor/neat/grid/_pad.scss +0 -25
  244. data/docs/_sass/vendor/neat/grid/_private.scss +0 -35
  245. data/docs/_sass/vendor/neat/grid/_row.scss +0 -52
  246. data/docs/_sass/vendor/neat/grid/_shift.scss +0 -50
  247. data/docs/_sass/vendor/neat/grid/_span-columns.scss +0 -94
  248. data/docs/_sass/vendor/neat/grid/_to-deprecate.scss +0 -97
  249. data/docs/_sass/vendor/neat/grid/_visual-grid.scss +0 -42
  250. data/docs/_sass/vendor/neat/mixins/_clearfix.scss +0 -25
  251. data/docs/_sass/vendor/neat/settings/_disable-warnings.scss +0 -13
  252. data/docs/_sass/vendor/neat/settings/_grid.scss +0 -51
  253. data/docs/_sass/vendor/neat/settings/_visual-grid.scss +0 -27
  254. data/docs/_sass/vendor/normalize-3.0.2.scss +0 -427
  255. data/docs/_sass/vendor/pygments.scss +0 -356
  256. data/docs/automating_browsers/capybara.md +0 -70
  257. data/docs/css/screen.scss +0 -7
  258. data/docs/guides/cli.md +0 -52
  259. data/docs/guides/frontiers.md +0 -93
  260. data/docs/guides/halting.md +0 -23
  261. data/docs/guides/job_queues.md +0 -26
  262. data/docs/guides/locals.md +0 -36
  263. data/docs/guides/logging.md +0 -22
  264. data/docs/guides/page_objects.md +0 -67
  265. data/docs/guides/peeking.md +0 -46
  266. data/docs/guides/selenium_capybara.md +0 -100
  267. data/docs/guides/tutorial.md +0 -452
  268. data/docs/js/navigation.js +0 -11
  269. data/docs/misc/contributing.md +0 -20
  270. data/docs/misc/testing.md +0 -11
  271. data/docs/recipes/authentication.md +0 -23
  272. data/docs/recipes/csv.md +0 -29
  273. data/docs/recipes/javascript.md +0 -20
  274. data/docs/recipes/multiple_uris.md +0 -18
  275. data/docs/recipes/screenshots.md +0 -20
  276. data/docs/routing/custom_rules.md +0 -16
  277. data/docs/routing/filetypes_rules.md +0 -21
  278. data/docs/routing/host_rules.md +0 -24
  279. data/docs/routing/path_rules.md +0 -33
  280. data/docs/routing/protocol_rules.md +0 -17
  281. data/docs/routing/query_rules.md +0 -69
  282. data/docs/routing/routes.md +0 -96
  283. data/docs/routing/uri_rules.md +0 -18
  284. data/examples/collect_github_issues.rb +0 -65
  285. data/examples/find_foobar_on_wikipedia.rb +0 -23
  286. data/lib/wayfarer/configuration.rb +0 -86
  287. data/lib/wayfarer/crawl.rb +0 -79
  288. data/lib/wayfarer/crawl_observer.rb +0 -103
  289. data/lib/wayfarer/dispatcher.rb +0 -104
  290. data/lib/wayfarer/finders.rb +0 -61
  291. data/lib/wayfarer/frontiers/frontier.rb +0 -79
  292. data/lib/wayfarer/frontiers/memory_bloomfilter.rb +0 -32
  293. data/lib/wayfarer/frontiers/memory_frontier.rb +0 -76
  294. data/lib/wayfarer/frontiers/memory_trie_frontier.rb +0 -39
  295. data/lib/wayfarer/frontiers/normalize_uris.rb +0 -48
  296. data/lib/wayfarer/frontiers/redis_bloomfilter.rb +0 -34
  297. data/lib/wayfarer/frontiers/redis_frontier.rb +0 -83
  298. data/lib/wayfarer/http_adapters/adapter_pool.rb +0 -62
  299. data/lib/wayfarer/http_adapters/net_http_adapter.rb +0 -77
  300. data/lib/wayfarer/http_adapters/selenium_adapter.rb +0 -80
  301. data/lib/wayfarer/job.rb +0 -211
  302. data/lib/wayfarer/locals.rb +0 -40
  303. data/lib/wayfarer/parsers/json_parser.rb +0 -20
  304. data/lib/wayfarer/parsers/xml_parser.rb +0 -27
  305. data/lib/wayfarer/processor.rb +0 -103
  306. data/lib/wayfarer/routing/custom_rule.rb +0 -21
  307. data/lib/wayfarer/routing/filetypes_rule.rb +0 -20
  308. data/lib/wayfarer/routing/host_rule.rb +0 -19
  309. data/lib/wayfarer/routing/path_rule.rb +0 -54
  310. data/lib/wayfarer/routing/protocol_rule.rb +0 -21
  311. data/lib/wayfarer/routing/router.rb +0 -71
  312. data/lib/wayfarer/routing/rule.rb +0 -114
  313. data/lib/wayfarer/routing/uri_rule.rb +0 -21
  314. data/spec/configuration_spec.rb +0 -26
  315. data/spec/crawl_spec.rb +0 -48
  316. data/spec/finders_spec.rb +0 -49
  317. data/spec/frontiers/memory_bloomfilter_spec.rb +0 -6
  318. data/spec/frontiers/memory_frontier_spec.rb +0 -6
  319. data/spec/frontiers/memory_trie_frontier_spec.rb +0 -6
  320. data/spec/frontiers/normalize_uris_spec.rb +0 -59
  321. data/spec/frontiers/redis_bloomfilter_spec.rb +0 -6
  322. data/spec/frontiers/redis_frontier_spec.rb +0 -6
  323. data/spec/http_adapters/adapter_pool_spec.rb +0 -33
  324. data/spec/http_adapters/net_http_adapter_spec.rb +0 -83
  325. data/spec/http_adapters/selenium_adapter_spec.rb +0 -53
  326. data/spec/integration/callbacks_spec.rb +0 -42
  327. data/spec/integration/locals_spec.rb +0 -106
  328. data/spec/integration/peeking_spec.rb +0 -61
  329. data/spec/job_spec.rb +0 -122
  330. data/spec/processor_spec.rb +0 -31
  331. data/spec/routing/custom_rule_spec.rb +0 -26
  332. data/spec/routing/host_rule_spec.rb +0 -48
  333. data/spec/routing/path_rule_spec.rb +0 -66
  334. data/spec/routing/protocol_rule_spec.rb +0 -26
  335. data/spec/routing/router_spec.rb +0 -67
  336. data/spec/routing/rule_spec.rb +0 -251
  337. data/spec/routing/uri_rule_spec.rb +0 -24
  338. data/spec/shared/frontier.rb +0 -96
  339. data/wayfarer-jruby.gemspec +0 -49
@@ -1,251 +0,0 @@
1
- # frozen_string_literal: true
2
- require "spec_helpers"
3
-
4
- describe Wayfarer::Routing::Rule do
5
- subject(:rule) { Rule.new }
6
-
7
- describe "#initialize" do
8
- it "evaluates the Proc in its instance context" do
9
- this = nil
10
- rule = Rule.new { this = self }
11
- expect(this).to be rule
12
- end
13
-
14
- it "builds the expected Rule chain from options" do
15
- rule = Rule.new(host: "example.com", query: { bar: 42 })
16
-
17
- first = rule.child_rules.first
18
- second = first.child_rules.first
19
- third = second.child_rules.first
20
-
21
- expect(first).to be_a HostRule
22
- expect(second).to be_a QueryRule
23
- end
24
- end
25
-
26
- describe "#params" do
27
- it "returns an empty Hash" do
28
- expect(rule.params(URI("http://example.com"))).to eq({})
29
- end
30
- end
31
-
32
- describe "#matching_rule_chain" do
33
- let(:uri) { URI("http://example.com/foo/bar") }
34
-
35
- context "with matching Rule" do
36
- let(:host_rule_a) { HostRule.new("example.com") }
37
- let(:host_rule_b) { HostRule.new("google.com") }
38
- let(:path_rule_a) { PathRule.new("/{alpha}/{beta}") }
39
- let(:path_rule_b) { PathRule.new("/{gamma}/{delta}") }
40
-
41
- before do
42
- host_rule_a.send(:append_child_rule, path_rule_a)
43
- host_rule_a.send(:append_child_rule, path_rule_b)
44
-
45
- host_rule_b.send(:append_child_rule, path_rule_a)
46
- host_rule_b.send(:append_child_rule, path_rule_b)
47
- end
48
-
49
- subject(:rule) do
50
- rule = Rule.new
51
- rule.send(:append_child_rule, host_rule_a)
52
- rule.send(:append_child_rule, host_rule_b)
53
- rule
54
- end
55
-
56
- it "returns the expected Array" do
57
- expect(rule.matching_rule_chain(uri)).to eq [
58
- rule, host_rule_a, path_rule_a
59
- ]
60
- end
61
- end
62
-
63
- context "without matching Rule" do
64
- subject(:rule) do
65
- rule = Rule.new
66
- rule.host("yahoo.com")
67
- rule.host("google.com")
68
- rule
69
- end
70
-
71
- it "returns an empty Array" do
72
- expect(rule.matching_rule_chain(uri)).to eq []
73
- end
74
- end
75
- end
76
-
77
- describe "#params_from_rule_chain" do
78
- let(:uri) { URI("http://example.com/foo/bar") }
79
-
80
- context "with matching Rule" do
81
- subject(:rule_chain) do
82
- rule = Rule.new
83
- rule.host("example.com").path("/{alpha}/{beta}")
84
- rule.host("example.com").path("/{foo}/{bar}")
85
- rule.matching_rule_chain(uri)
86
- end
87
-
88
- it "returns the expected URI parameters" do
89
- expect(rule.send(:params_from_rule_chain, rule_chain, uri)).to eq("alpha" => "foo", "beta" => "bar")
90
- end
91
- end
92
- end
93
-
94
- describe "#invoke" do
95
- let(:uri) { URI("http://example.com/foo/bar") }
96
-
97
- context "with matching Rule" do
98
- subject(:rule) do
99
- rule = Rule.new
100
- rule.host("example.com").path("/{alpha}/{beta}")
101
- rule
102
- end
103
-
104
- it "returns a truthy value" do
105
- expect(rule.invoke(uri)).to be_truthy
106
- end
107
-
108
- it "returns the URI parameters" do
109
- _, params = rule.invoke(uri)
110
- expect(params).to eq("alpha" => "foo", "beta" => "bar")
111
- end
112
- end
113
-
114
- context "with mismatching Rule" do
115
- subject(:rule) do
116
- rule = Rule.new
117
- rule.host("google.com").path("/{alpha}/{beta}")
118
- rule
119
- end
120
-
121
- it "returns false" do
122
- expect(rule.invoke(uri)).to be false
123
- end
124
- end
125
- end
126
-
127
- describe "#uri" do
128
- it "adds a URIRule as a sub-rule" do
129
- rule.uri("http://example.com/foo/bar")
130
- expect(rule.child_rules.first).to be_a URIRule
131
- end
132
-
133
- it "returns the added URIRule" do
134
- expect(rule.uri("http://example.com/foo/bar")).to be_a URIRule
135
- end
136
- end
137
-
138
- describe "#host" do
139
- it "adds a HostRule as a sub-rule" do
140
- rule.host("example.com")
141
- expect(rule.child_rules.first).to be_a HostRule
142
- end
143
-
144
- it "returns the added HostRule" do
145
- expect(rule.host("example.com")).to be_a HostRule
146
- end
147
- end
148
-
149
- describe "#path" do
150
- it "adds a PathRule as a sub-rule" do
151
- rule.path("/foo/bar")
152
- expect(rule.child_rules.first).to be_a PathRule
153
- end
154
-
155
- it "returns the added PathRule" do
156
- expect(rule.path("/foo/bar")).to be_a PathRule
157
- end
158
- end
159
-
160
- describe "#query" do
161
- it "adds a QueryRule as a sub-rule" do
162
- rule.query(foo: "bar")
163
- expect(rule.child_rules.first).to be_a QueryRule
164
- end
165
-
166
- it "returns the added QueryRule" do
167
- expect(rule.query(foo: "bar")).to be_a QueryRule
168
- end
169
- end
170
-
171
- describe "#protocol" do
172
- it "adds a ProtocolRule as a sub-rule" do
173
- rule.protocol(:https)
174
- expect(rule.child_rules.first).to be_a ProtocolRule
175
- end
176
-
177
- it "returns the added QueryRule" do
178
- expect(rule.protocol(:https)).to be_a ProtocolRule
179
- end
180
- end
181
-
182
- describe "#if" do
183
- it "adds a CustomRule as a sub-rule" do
184
- rule.if -> () { true }
185
- expect(rule.child_rules.first).to be_a CustomRule
186
- end
187
-
188
- it "returns the added QueryRule" do
189
- expect(rule.if -> () { true }).to be_a CustomRule
190
- end
191
- end
192
-
193
- describe "#filetypes" do
194
- it "adds a FiletypesRule as a sub-rule" do
195
- rule.filetypes [:png, :jpg]
196
- expect(rule.child_rules.first).to be_a FiletypesRule
197
- end
198
-
199
- it "returns the added FiletypeRule" do
200
- expect(rule.filetypes [:png]).to be_a FiletypesRule
201
- end
202
- end
203
-
204
- describe "#build_child_rule_chain_from_options" do
205
- subject(:rule) do
206
- rule = Rule.new
207
- rule.build_child_rule_chain_from_options(opts)
208
- rule
209
- end
210
-
211
- describe ":path option" do
212
- let(:opts) { { path: "/foo" } }
213
-
214
- it "adds a PathRule" do
215
- expect(rule.child_rules.first).to be_a PathRule
216
- end
217
- end
218
-
219
- describe ":query option" do
220
- let(:opts) { { query: { bar: "qux" } } }
221
-
222
- it "adds a QueryRule" do
223
- expect(rule.child_rules.first).to be_a QueryRule
224
- end
225
- end
226
-
227
- describe ":host option" do
228
- let(:opts) { { host: "example.com" } }
229
-
230
- it "adds a HostRule" do
231
- expect(rule.child_rules.first).to be_a HostRule
232
- end
233
- end
234
-
235
- context "with multiple options present" do
236
- let(:opts) do
237
- { host: "example.com", path: "/foo", query: { bar: "qux" } }
238
- end
239
-
240
- it "adds chained sub-rules" do
241
- first = rule.child_rules.first
242
- second = first.child_rules.first
243
- third = second.child_rules.first
244
-
245
- expect(first).to be_a HostRule
246
- expect(second).to be_a PathRule
247
- expect(third).to be_a QueryRule
248
- end
249
- end
250
- end
251
- end
@@ -1,24 +0,0 @@
1
- # frozen_string_literal: true
2
- require "spec_helpers"
3
-
4
- describe Wayfarer::Routing::URIRule do
5
- subject(:rule) { URIRule.new("http://example.com/foo/bar") }
6
-
7
- describe "#matches?" do
8
- context "with matching URI" do
9
- let(:uri) { URI("http://example.com/foo/bar") }
10
-
11
- it "returns true" do
12
- expect(rule.matches?(uri)).to be true
13
- end
14
- end
15
-
16
- context "with mismatching URI" do
17
- let(:uri) { URI("http://example.com/foo/qux") }
18
-
19
- it "returns true" do
20
- expect(rule.matches?(uri)).to be false
21
- end
22
- end
23
- end
24
- end
@@ -1,96 +0,0 @@
1
- # frozen_string_literal: true
2
- require "securerandom"
3
-
4
- RSpec.shared_examples "Frontier" do |klass|
5
- subject(:frontier) { klass.new(Configuration.new) }
6
-
7
- after { frontier.free }
8
-
9
- describe "#stage" do
10
- let(:uri) { "http://example.com/foo#bar" }
11
-
12
- it "stages a URI" do
13
- frontier.stage("http://example.com")
14
- expect(frontier.staged?("http://example.com")).to be true
15
- end
16
-
17
- it "stages multiple URIs" do
18
- frontier.stage("http://example.com", "http://google.com")
19
- expect(frontier.staged?("http://example.com")).to be true
20
- expect(frontier.staged?("http://google.com")).to be true
21
- end
22
- end
23
-
24
- describe "#cache" do
25
- it "caches a URI" do
26
- frontier.cache("http://example.com")
27
- expect(frontier.cached?("http://example.com")).to be true
28
- end
29
-
30
- it "caches multiple URIs" do
31
- frontier.cache("http://example.com", "http://google.com")
32
- expect(frontier.cached?("http://example.com")).to be true
33
- expect(frontier.cached?("http://google.com")).to be true
34
- end
35
- end
36
-
37
- describe "#cycle" do
38
- let(:uri) { "http://example.com" }
39
-
40
- it "does not stage the same URI twice" do
41
- 2.times { frontier.stage(uri) }
42
-
43
- expect { frontier.cycle }.to change { frontier.current_uris.count }.by(1)
44
- end
45
-
46
- it "caches URIs" do
47
- frontier.stage(uri)
48
-
49
- 2.times { frontier.cycle }
50
-
51
- expect(frontier.cached?(uri)).to be true
52
- end
53
-
54
- context "with staged URIs" do
55
- before { frontier.stage(uri) }
56
-
57
- it "swaps current and staged URIs" do
58
- frontier.cycle
59
- expect(frontier.current_uris).to eq [URI(uri)]
60
- expect(frontier.staged_uris).to eq []
61
- end
62
-
63
- it "returns true" do
64
- expect(frontier.cycle).to be true
65
- end
66
- end
67
-
68
- context "without staged URIs" do
69
- it "returns false" do
70
- expect(frontier.cycle).to be false
71
- end
72
- end
73
-
74
- it "does not set cached URIs as current" do
75
- frontier.cache(uri)
76
- frontier.stage(uri)
77
- frontier.cycle
78
-
79
- expect(frontier.current_uris).to be_empty
80
- end
81
-
82
- context "when circulation is allowed" do
83
- subject(:frontier) do
84
- klass.new(Configuration.new(allow_circulation: true))
85
- end
86
-
87
- it "sets cached URIs as current" do
88
- 3.times do
89
- frontier.stage(uri)
90
- frontier.cycle
91
- expect(frontier.current_uris).to eq [URI(uri)]
92
- end
93
- end
94
- end
95
- end
96
- end
@@ -1,49 +0,0 @@
1
- # frozen_string_literal: true
2
-
3
- Gem::Specification.new do |s|
4
- s.name = "wayfarer-jruby"
5
- s.version = "0.0.3"
6
- s.license = "MIT"
7
-
8
- s.homepage = "http://github.com/bauerd/wayfarer"
9
- s.description = "Versatile web crawling with JRuby"
10
- s.summary = s.description
11
-
12
- s.date = "2017-05-31"
13
- s.authors = ["Dominic Bauer"]
14
- s.email = "bauerdominic@gmail.com"
15
-
16
- s.files = `git ls-files`.split("\n")
17
- s.test_files = `git ls-files -- {spec}/*`.split("\n")
18
-
19
- s.require_paths = ["lib"]
20
-
21
- s.executables << "wayfarer"
22
-
23
- s.add_runtime_dependency "connection_pool", "~> 2.2"
24
- s.add_runtime_dependency "nokogiri", "~> 1.6"
25
- s.add_runtime_dependency "selenium-webdriver", "~> 3.4"
26
- s.add_runtime_dependency "selenium-emulated_features", "2.0.1"
27
- s.add_runtime_dependency "net-http-persistent", "~> 2.9"
28
- s.add_runtime_dependency "mime-types", "~> 2.6"
29
- s.add_runtime_dependency "mustermann", "~> 0.4"
30
- s.add_runtime_dependency "activejob", "~> 4.2"
31
- s.add_runtime_dependency "thor", "~> 0.19"
32
- s.add_runtime_dependency "activesupport", "~> 4.2"
33
- s.add_runtime_dependency "capybara", "~> 2.5"
34
- s.add_runtime_dependency "chronic", "~> 0.10"
35
- s.add_runtime_dependency "redis", "~> 3.2"
36
- s.add_runtime_dependency "concurrent-ruby", "~> 1.0"
37
- s.add_runtime_dependency "hooks", "~> 0.4"
38
- s.add_runtime_dependency "normalize_url", "~> 0.0.6"
39
-
40
- s.add_development_dependency "pry", "~> 0.10"
41
- s.add_development_dependency "rake", "~> 10.4"
42
- s.add_development_dependency "rspec", "~> 3.3"
43
- s.add_development_dependency "sinatra", "~> 1.4"
44
- s.add_development_dependency "rubocop", "~> 0.34"
45
- s.add_development_dependency "yard", "~> 0.9"
46
- s.add_development_dependency "bourbon", "~> 4.3"
47
- s.add_development_dependency "neat", "~> 1.8"
48
- s.add_development_dependency "faker", "~> 1.7"
49
- end