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
@@ -0,0 +1,96 @@
1
+ # frozen_string_literal: true
2
+
3
+ require "spec_helpers"
4
+
5
+ describe Wayfarer::Middleware::Chain do
6
+ let(:task) { build(:task) }
7
+ subject(:chain) { build(:chain, middlewares: middlewares) }
8
+
9
+ describe "#call" do
10
+ context "without middlewares" do
11
+ let(:middlewares) { [] }
12
+
13
+ it "does not raise" do
14
+ expect { chain.call(task) }.not_to raise_error
15
+ end
16
+
17
+ it "yields" do
18
+ expect { |spy| chain.call(task, &spy) }.to yield_control
19
+ end
20
+ end
21
+
22
+ context "when middleware yields" do
23
+ let(:middlewares) { [spy, spy] }
24
+
25
+ it "yields" do
26
+ allow(middlewares.first).to receive(:call).and_yield
27
+ expect(middlewares.last).to receive(:call).with(task).and_yield
28
+ expect { |spy| chain.call(task, &spy) }.to yield_control
29
+ end
30
+ end
31
+
32
+ context "when middleware does not yield" do
33
+ let(:middlewares) { [spy, spy] }
34
+
35
+ it "does not yield" do
36
+ allow(middlewares.first).to receive(:call)
37
+ expect(middlewares.last).not_to receive(:call)
38
+ expect { |spy| chain.call(task, &spy) }.not_to yield_control
39
+ end
40
+ end
41
+
42
+ describe "Immutability" do
43
+ let(:middlewares) { [spy, spy] }
44
+
45
+ it "does not alter its middleware" do
46
+ allow(middlewares.first).to receive(:call).and_yield
47
+ allow(middlewares.second).to receive(:call).and_yield
48
+ expect { chain.call(task) }.not_to(change { chain.middlewares })
49
+ end
50
+ end
51
+
52
+ describe "Return value" do
53
+ let(:middlewares) do
54
+ [build(:middleware, callee: lambda do |task, &block|
55
+ task.metadata.foobar = 42
56
+ block.call
57
+ end),
58
+ build(:middleware, callee: lambda do |task|
59
+ task.metadata.foobar *= 1337
60
+ end)]
61
+ end
62
+
63
+ it "is the last middleware's return value" do
64
+ expect(chain.call(task)).to be(56_154)
65
+ end
66
+ end
67
+
68
+ describe "Metadata" do
69
+ let(:first) do
70
+ build(:middleware, callee: lambda do |task, &block|
71
+ task.metadata.foobar = 42
72
+ block.call
73
+ task.metadata.barqux = 1337
74
+ end)
75
+ end
76
+
77
+ let(:last) do
78
+ build(:middleware, callee: lambda do |task|
79
+ raise unless task.metadata.foobar == 42
80
+ raise if task.metadata.barqux
81
+ end)
82
+ end
83
+
84
+ let(:middlewares) { [first, last] }
85
+
86
+ it "is accessible across middleware" do
87
+ expect {
88
+ chain.call(task)
89
+ }.not_to raise_error
90
+
91
+ expect(task.metadata.foobar).to be(42)
92
+ expect(task.metadata.barqux).to be(1337)
93
+ end
94
+ end
95
+ end
96
+ end
@@ -0,0 +1,76 @@
1
+ # frozen_string_literal: true
2
+
3
+ require "spec_helpers"
4
+
5
+ describe Wayfarer::Middleware::Dedup, redis: true do
6
+ let(:task) { build(:task) }
7
+ subject(:dedup) { Wayfarer::Middleware::Dedup.new }
8
+
9
+ before { task.metadata.staged_urls = SortedSet.new }
10
+
11
+ describe "#call" do
12
+ context "without staged URLs" do
13
+ it "does not raise" do
14
+ expect { dedup.call(task) }.not_to raise_error
15
+ end
16
+ end
17
+
18
+ context "with unseen URL" do
19
+ it "marks the URL as seen" do
20
+ expect {
21
+ dedup.call(task)
22
+ }.to change { task.barrier.seen?(task.url) }.to(true)
23
+ end
24
+
25
+ it "yields" do
26
+ expect { |spy| dedup.call(task, &spy) }.to yield_control
27
+ end
28
+ end
29
+
30
+ context "with seen URL" do
31
+ before { task.barrier.seen?(task.url) }
32
+
33
+ it "does not yield" do
34
+ expect { |spy| dedup.call(task, &spy) }.not_to yield_control
35
+ end
36
+ end
37
+
38
+ context "with exception raised" do
39
+ it "does not mark the URL as seen" do
40
+ begin
41
+ dedup.call(task) { raise }
42
+ rescue StandardError
43
+ nil
44
+ end
45
+ expect(task.barrier.seen?(task.url)).to be(false)
46
+ end
47
+
48
+ it "re-raises the exception" do
49
+ expect {
50
+ dedup.call(task) { raise }
51
+ }.to raise_error(RuntimeError)
52
+ end
53
+ end
54
+
55
+ describe "staged URL filtering" do
56
+ let(:seen_urls) { %w[https://yahoo.com https://google.com] }
57
+ let(:unseen_urls) { %w[https://w3c.org https://nasa.gov] }
58
+
59
+ before do
60
+ seen_urls.each do |url|
61
+ task.barrier.seen?(url)
62
+ end
63
+
64
+ [*seen_urls, *unseen_urls].each do |url|
65
+ task.metadata.staged_urls.add(url)
66
+ end
67
+ end
68
+
69
+ it "filters seen staged URLs" do
70
+ expect {
71
+ dedup.call(task)
72
+ }.to change { task.metadata.staged_urls }.to(SortedSet.new(unseen_urls))
73
+ end
74
+ end
75
+ end
76
+ end
@@ -0,0 +1,72 @@
1
+ # frozen_string_literal: true
2
+
3
+ require "spec_helpers"
4
+
5
+ describe Wayfarer::Middleware::Fetch do
6
+ let(:task) { build(:task) }
7
+ let(:adapter) { spy }
8
+ subject(:fetch) { Wayfarer::Middleware::Fetch.new }
9
+
10
+ before { allow(fetch.pool).to receive(:with).and_yield(adapter) }
11
+
12
+ describe "#call" do
13
+ it "assigns the task" do
14
+ expect {
15
+ fetch.call(task)
16
+ }.to change { fetch.task }.to(task)
17
+ end
18
+
19
+ it "assigns the adapter" do
20
+ expect {
21
+ fetch.call(task)
22
+ }.to change { task.metadata.adapter }.to(adapter)
23
+ end
24
+
25
+ it "retrieves the page" do
26
+ expect(adapter).to receive(:fetch).with(task.url)
27
+ fetch.call(task)
28
+ end
29
+
30
+ context "when encountering an HTTP redirect" do
31
+ let(:redirect_url) { "https://redirect.com" }
32
+
33
+ let(:result) do
34
+ Wayfarer::Networking::Result::Redirect.new(task.url, redirect_url)
35
+ end
36
+
37
+ before do
38
+ task.metadata.staged_urls = Set.new
39
+ allow(adapter).to receive(:fetch).with(task.url).and_return(result)
40
+ end
41
+
42
+ it "stages the redirect URL" do
43
+ expect {
44
+ fetch.call(task)
45
+ }.to change { task.metadata.staged_urls }.to([redirect_url])
46
+ end
47
+
48
+ it "does not yield" do
49
+ expect { |spy| fetch.call(task, &spy) }.not_to yield_control
50
+ end
51
+ end
52
+
53
+ context "when retrieval succeeds" do
54
+ let(:page) { build(:page) }
55
+ let(:result) { Wayfarer::Networking::Result::Success.new(page) }
56
+
57
+ before do
58
+ allow(adapter).to receive(:fetch).with(task.url).and_return(result)
59
+ end
60
+
61
+ it "assigns the page" do
62
+ expect {
63
+ fetch.call(task)
64
+ }.to change { task.metadata.page }.to(page)
65
+ end
66
+
67
+ it "yields" do
68
+ expect { |spy| fetch.call(task, &spy) }.to yield_control
69
+ end
70
+ end
71
+ end
72
+ end
@@ -0,0 +1,28 @@
1
+ # frozen_string_literal: true
2
+
3
+ require "spec_helpers"
4
+
5
+ describe Wayfarer::Middleware::Normalize do
6
+ let(:task) { build(:task) }
7
+ subject(:normalize) { Wayfarer::Middleware::Normalize.new }
8
+
9
+ describe "#call" do
10
+ let(:urls) do
11
+ ["http://example.com/products?product_id=123",
12
+ "HTTP://EXAMPLE.COM/products/?product_id=123",
13
+ "http://example.com/products/?product_id=123",
14
+ "http://example.com/foo/../products?product_id=123"]
15
+ end
16
+
17
+ before { task.metadata.staged_urls = SortedSet.new(urls) }
18
+
19
+ it "yields" do
20
+ expect { |spy| normalize.call(task, &spy) }.to yield_control
21
+ end
22
+
23
+ it "normalizes and compacts URLs" do
24
+ normalize.call(task)
25
+ expect(task.metadata.staged_urls).to eq(SortedSet[urls.first])
26
+ end
27
+ end
28
+ end
@@ -0,0 +1,46 @@
1
+ # frozen_string_literal: true
2
+
3
+ require "spec_helpers"
4
+
5
+ describe Wayfarer::Middleware::Router do
6
+ let(:task) { build(:task, url: url) }
7
+ let(:klass) do
8
+ Class.new(Wayfarer::Base) do
9
+ route.to :index, host: "example.com", path: "/foobar"
10
+ end
11
+ end
12
+
13
+ subject(:router) { Wayfarer::Middleware::Router.new }
14
+
15
+ before { task.job = klass.new }
16
+
17
+ describe "#call" do
18
+ context "when URL matches a route" do
19
+ let(:url) { "https://example.com/foobar" }
20
+
21
+ it "yields" do
22
+ expect { |spy| router.call(task, &spy) }.to yield_control
23
+ end
24
+
25
+ it "assigns metadata" do
26
+ router.call(task)
27
+ expect(task.metadata.action).to be(:index)
28
+ expect(task.metadata.params).to eq({})
29
+ end
30
+ end
31
+
32
+ context "when URL does not match a route" do
33
+ let(:url) { "https://yahoo.com/foobar" }
34
+
35
+ it "does not yield" do
36
+ expect { |spy| router.call(task, &spy) }.not_to yield_control
37
+ end
38
+
39
+ it "does not assign metadata" do
40
+ router.call(task) {}
41
+ expect(task.metadata.action).to be(nil)
42
+ expect(task.metadata.params).to be(nil)
43
+ end
44
+ end
45
+ end
46
+ end
@@ -0,0 +1,39 @@
1
+ # frozen_string_literal: true
2
+
3
+ require "spec_helpers"
4
+
5
+ describe Wayfarer::Middleware::Stage do
6
+ include ActiveJob::TestHelper
7
+
8
+ let(:task) { build(:task) }
9
+ subject(:stage) { Wayfarer::Middleware::Stage.new }
10
+
11
+ describe "#call" do
12
+ it "assigns staged URLs" do
13
+ stage.call(task) do
14
+ expect(task.metadata.staged_urls).to eq(SortedSet.new)
15
+ end
16
+ end
17
+
18
+ it "yields" do
19
+ expect { |spy| stage.call(task, &spy) }.to yield_control
20
+ end
21
+
22
+ describe "Task queuing" do
23
+ let(:klass) { Class.new(Wayfarer::Base) }
24
+ let(:urls) { %w[https://example.com https://w3c.org] }
25
+
26
+ before { task.job = klass.new }
27
+
28
+ it "enqueues tasks" do
29
+ expect(klass).to receive(:crawl_later).with(urls.first, batch: task.batch)
30
+ expect(klass).to receive(:crawl_later).with(urls.second, batch: task.batch)
31
+
32
+ stage.call(task) do
33
+ extend Wayfarer::Middleware::Stage::API
34
+ stage(urls)
35
+ end
36
+ end
37
+ end
38
+ end
39
+ end
@@ -0,0 +1,90 @@
1
+ # frozen_string_literal: true
2
+
3
+ require "spec_helpers"
4
+
5
+ describe Wayfarer::Middleware::Worker do
6
+ let(:task) { build(:task) }
7
+
8
+ before { task.metadata.action = :index }
9
+
10
+ let(:job) do
11
+ Class.new(Wayfarer::Base) do
12
+ def index
13
+ :foobar
14
+ end
15
+ end
16
+ end
17
+
18
+ describe "::route" do
19
+ it "returns a route" do
20
+ expect(job.route).to be_a(Wayfarer::Routing::Route)
21
+ end
22
+ end
23
+
24
+ describe "#call" do
25
+ it "assigns the task" do
26
+ worker = job.new
27
+ expect { worker.call(task) }.to change { worker.task }.to(task)
28
+ end
29
+
30
+ it "calls the action method" do
31
+ worker = job.new
32
+ expect(worker).to receive(:index)
33
+ worker.call(task)
34
+ end
35
+
36
+ it "yields" do
37
+ expect { |spy| job.new.call(task, &spy) }.to yield_control
38
+ end
39
+ end
40
+
41
+ describe "#chain" do
42
+ it "returns its middleware chain" do
43
+ worker = job.new
44
+ expect(worker.chain.middlewares).to eq([*Wayfarer.core_middleware, worker])
45
+ end
46
+ end
47
+
48
+ describe "#redis" do
49
+ it "yields a Redis connection" do
50
+ job.new.redis do |conn|
51
+ expect(conn).to be_a(Redis)
52
+ end
53
+ end
54
+ end
55
+
56
+ describe "#page" do
57
+ let(:page) { Object.new }
58
+ let(:worker) { job.new }
59
+
60
+ before do
61
+ task.metadata.page = page
62
+ worker.task = task
63
+ end
64
+
65
+ it "returns the page" do
66
+ expect(worker.page).to be(page)
67
+ end
68
+
69
+ context "with live keyword" do
70
+ let(:adapter) { spy }
71
+ let(:body) { "foobar" }
72
+ let(:live) { Object.new }
73
+
74
+ before do
75
+ task.metadata.adapter = adapter
76
+ allow(adapter).to receive(:live).with(page).and_return(live)
77
+ end
78
+
79
+ it "returns a live page" do
80
+ expect(worker.page(live: true)).to be(live)
81
+ end
82
+
83
+ it "replaces the existing page" do
84
+ expect {
85
+ worker.page(live: true)
86
+ }.to change { task.metadata.page }.to(live)
87
+ end
88
+ end
89
+ end
90
+ end
@@ -0,0 +1,135 @@
1
+ # frozen_string_literal: true
2
+
3
+ require "spec_helpers"
4
+
5
+ RSpec.shared_examples "Network adapter" do |options|
6
+ describe "::renew_on" do
7
+ it "returns an Array" do
8
+ expect(adapter.class.renew_on).to be_an(Array)
9
+ end
10
+ end
11
+
12
+ describe "#fetch" do
13
+ it "returns Success" do
14
+ url = test_app_path("/hello_world")
15
+ result = adapter.fetch(url)
16
+ expect(result).to be_a(Wayfarer::Networking::Result::Success)
17
+ expect(result.page).to be_a(Wayfarer::Page)
18
+ end
19
+
20
+ it "sets the URL" do
21
+ url = test_app_path("/status_code/404")
22
+ page = adapter.fetch(url).page
23
+ expect(page.url).to eq test_app_path("/status_code/404")
24
+ end
25
+
26
+ it "sets the response body" do
27
+ url = test_app_path("/hello_world")
28
+ page = adapter.fetch(url).page
29
+ expect(page.body).to match(/Hello world!/)
30
+ end
31
+ end
32
+
33
+ describe "#live" do
34
+ context "when automating a browser" do
35
+ before { skip unless options[:browser] }
36
+
37
+ it "returns a live page" do
38
+ adapter.fetch(test_app_path("/hello_world"))
39
+
40
+ url = test_app_path("/body/foobar")
41
+ case adapter
42
+ when Wayfarer::Networking::Selenium then adapter.browser.navigate.to(url)
43
+ when Wayfarer::Networking::Ferrum then adapter.browser.goto(url)
44
+ end
45
+
46
+ page = adapter.live(nil)
47
+ expect(page.url).to eq(url)
48
+ expect(page.body).to match(/foobar/)
49
+ # Response headers and status code cannot be tested here, because
50
+ # Selenium does not support them.
51
+ end
52
+ end
53
+
54
+ context "when using plain HTTP" do
55
+ before { skip if options[:browser] }
56
+
57
+ it "returns the same page" do
58
+ page = build(:page)
59
+ expect(adapter.live(page)).to be(page)
60
+ end
61
+ end
62
+ end
63
+
64
+ describe "#body" do
65
+ it "returns the body" do
66
+ url = test_app_path("/hello_world")
67
+ adapter.fetch(url).page
68
+ expect(adapter.body).to match(/Hello world!/)
69
+ end
70
+ end
71
+
72
+ describe "#free" do
73
+ it "frees the browser" do
74
+ skip unless options[:browser]
75
+
76
+ expect {
77
+ adapter.free
78
+ }.to change { adapter.browser }.to(nil)
79
+ end
80
+
81
+ it "frees the Capybara session" do
82
+ skip unless options[:capybara]
83
+
84
+ adapter.capybara
85
+
86
+ expect {
87
+ adapter.free
88
+ }.to change { adapter.instance_variable_get(:@capybara) }.to(nil)
89
+ end
90
+ end
91
+
92
+ describe "#renew" do
93
+ it "does not raise" do
94
+ expect { adapter.renew }.not_to raise_error
95
+ end
96
+
97
+ it "renews the browser" do
98
+ skip unless options[:browser]
99
+
100
+ expect {
101
+ adapter.renew
102
+ }.to(change { adapter.browser })
103
+ end
104
+
105
+ it "frees the Capybara session" do
106
+ skip unless options[:capybara]
107
+
108
+ adapter.capybara
109
+
110
+ expect {
111
+ adapter.renew
112
+ }.to change { adapter.instance_variable_get(:@capybara) }.to(nil)
113
+ end
114
+ end
115
+
116
+ describe "#capybara" do
117
+ before { skip unless options[:capybara] }
118
+
119
+ it "returns a Capybara driver" do
120
+ expect(adapter.capybara).to be_a(Capybara::Session)
121
+ end
122
+ end
123
+
124
+ describe "HTTP headers" do
125
+ before { Wayfarer.config.http_headers = { "User-Agent" => "Foobar" } }
126
+
127
+ it "uses configured HTTP headers" do
128
+ skip unless options[:request_headers]
129
+
130
+ url = test_app_path("/headers/HTTP_USER_AGENT")
131
+ page = adapter.fetch(url).page
132
+ expect(page.body).to match(/Foobar/)
133
+ end
134
+ end
135
+ end
@@ -0,0 +1,28 @@
1
+ # frozen_string_literal: true
2
+
3
+ require "spec_helpers"
4
+ require_relative "adapter"
5
+
6
+ describe Wayfarer::Networking::Ferrum, ferrum: true do
7
+ subject(:adapter) { Wayfarer::Networking::Ferrum.new }
8
+
9
+ after { adapter.free }
10
+
11
+ include_examples "Network adapter", browser: true,
12
+ capybara: true,
13
+ request_headers: true
14
+
15
+ describe "#fetch" do
16
+ it "sets the status code" do
17
+ url = test_app_path("/status_code/418")
18
+ page = adapter.fetch(url).page
19
+ expect(page.status_code).to be(418)
20
+ end
21
+
22
+ it "sets response headers" do
23
+ url = test_app_path("/hello_world")
24
+ page = adapter.fetch(url).page
25
+ expect(page.headers["hello"]).to eq("world")
26
+ end
27
+ end
28
+ end
@@ -0,0 +1,46 @@
1
+ # frozen_string_literal: true
2
+
3
+ require "spec_helpers"
4
+
5
+ describe Wayfarer::Networking::Healer do
6
+ let(:error) { Class.new(StandardError) }
7
+ let(:renew_on) { [error] }
8
+
9
+ let(:adapter) do
10
+ double.tap do |adapter|
11
+ allow(adapter.class).to receive(:renew_on).and_return([error])
12
+ end
13
+ end
14
+
15
+ subject(:healer) do
16
+ Wayfarer::Networking::Healer.new(adapter)
17
+ end
18
+
19
+ describe "#fetch" do
20
+ context "when proxied call raises renewing error" do
21
+ before do
22
+ allow(adapter).to receive(:fetch).and_raise(error)
23
+ end
24
+
25
+ it "renews its adapter and re-raises" do
26
+ expect(adapter).to receive(:renew)
27
+ expect {
28
+ healer.fetch(URI("https://example.com"))
29
+ }.to raise_error(error)
30
+ end
31
+ end
32
+
33
+ context "when proxied call raises non-renewing error" do
34
+ before do
35
+ allow(adapter).to receive(:fetch).and_raise(StandardError.new)
36
+ end
37
+
38
+ it "does not renew its adapter and intercept" do
39
+ expect(adapter).not_to receive(:renew)
40
+ expect {
41
+ healer.fetch(URI("https://example.com"))
42
+ }.to raise_error(StandardError)
43
+ end
44
+ end
45
+ end
46
+ end
@@ -0,0 +1,37 @@
1
+ # frozen_string_literal: true
2
+
3
+ require "spec_helpers"
4
+ require_relative "adapter"
5
+
6
+ describe Wayfarer::Networking::NetHTTP do
7
+ subject(:adapter) { Wayfarer::Networking::NetHTTP.send(:new) }
8
+
9
+ after { adapter.free }
10
+
11
+ include_examples "Network adapter", browser: false,
12
+ capybara: false,
13
+ request_headers: true
14
+
15
+ describe "#fetch" do
16
+ it "sets the status code" do
17
+ url = test_app_path("/status_code/404")
18
+ page = adapter.fetch(url).page
19
+ expect(page.status_code).to be 404
20
+ end
21
+
22
+ it "sets response headers" do
23
+ url = test_app_path("/hello_world")
24
+ page = adapter.fetch(url).page
25
+ expect(page.headers["hello"]).to eq ["world"]
26
+ end
27
+
28
+ context "when encountering a redirect" do
29
+ it "returns a Redirect" do
30
+ url = test_app_path("/redirect?times=3")
31
+ result = adapter.fetch(url)
32
+ expect(result).to be_a Wayfarer::Networking::Result::Redirect
33
+ expect(result.redirect_url).to eq test_app_path("/redirect?times=2")
34
+ end
35
+ end
36
+ end
37
+ end