wayfarer 0.0.3 → 0.4.3

Sign up to get free protection for your applications and to get access to all the features.
Files changed (369) 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 +221 -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/batch_routing.md +22 -0
  14. data/docs/cookbook/consent_screen.md +36 -0
  15. data/docs/cookbook/executing_javascript.md +41 -0
  16. data/docs/cookbook/querying_html.md +42 -0
  17. data/docs/cookbook/screenshots.md +27 -0
  18. data/docs/cookbook/user_agent.md +7 -0
  19. data/docs/guides/browser_automation/capybara.md +69 -0
  20. data/docs/guides/browser_automation/custom_adapters.md +100 -0
  21. data/docs/guides/browser_automation/ferrum.md +39 -0
  22. data/docs/guides/browser_automation/selenium.md +63 -0
  23. data/docs/guides/callbacks.md +131 -31
  24. data/docs/guides/configuration.md +24 -169
  25. data/docs/guides/debugging.md +17 -0
  26. data/docs/guides/error_handling.md +30 -45
  27. data/docs/guides/jobs.md +101 -0
  28. data/docs/guides/navigation.md +73 -0
  29. data/docs/guides/networking.md +94 -0
  30. data/docs/guides/pages.md +52 -0
  31. data/docs/guides/performance.md +130 -0
  32. data/docs/guides/reliability.md +41 -0
  33. data/docs/guides/routing/steering.md +30 -0
  34. data/docs/guides/tasks.md +14 -0
  35. data/docs/index.md +40 -66
  36. data/docs/reference/api/base.md +48 -0
  37. data/docs/reference/api/route.md +182 -0
  38. data/docs/reference/cli.md +61 -0
  39. data/docs/reference/configuration_keys.md +42 -0
  40. data/docs/reference/environment_variables.md +83 -0
  41. data/lib/wayfarer/base.rb +50 -0
  42. data/lib/wayfarer/callbacks.rb +71 -0
  43. data/lib/wayfarer/cli/base.rb +27 -0
  44. data/lib/wayfarer/cli/generate.rb +17 -0
  45. data/lib/wayfarer/cli/job.rb +60 -0
  46. data/lib/wayfarer/cli/route.rb +29 -0
  47. data/lib/wayfarer/cli/route_printer.rb +116 -0
  48. data/lib/wayfarer/cli/runner.rb +34 -0
  49. data/lib/wayfarer/cli/templates/Gemfile.tt +5 -0
  50. data/lib/wayfarer/cli/templates/job.rb.tt +10 -0
  51. data/lib/wayfarer/config/capybara.rb +10 -0
  52. data/lib/wayfarer/config/ferrum.rb +11 -0
  53. data/lib/wayfarer/config/networking.rb +26 -0
  54. data/lib/wayfarer/config/redis.rb +14 -0
  55. data/lib/wayfarer/config/root.rb +11 -0
  56. data/lib/wayfarer/config/selenium.rb +21 -0
  57. data/lib/wayfarer/config/strconv.rb +45 -0
  58. data/lib/wayfarer/config/struct.rb +72 -0
  59. data/lib/wayfarer/gc.rb +15 -0
  60. data/lib/wayfarer/middleware/chain.rb +19 -0
  61. data/lib/wayfarer/middleware/dedup.rb +25 -0
  62. data/lib/wayfarer/middleware/fetch.rb +47 -0
  63. data/lib/wayfarer/middleware/normalize.rb +25 -0
  64. data/lib/wayfarer/middleware/router.rb +53 -0
  65. data/lib/wayfarer/middleware/stage.rb +23 -0
  66. data/lib/wayfarer/middleware/worker.rb +30 -0
  67. data/lib/wayfarer/networking/capybara.rb +28 -0
  68. data/lib/wayfarer/networking/context.rb +36 -0
  69. data/lib/wayfarer/networking/ferrum.rb +35 -0
  70. data/lib/wayfarer/networking/http.rb +34 -0
  71. data/lib/wayfarer/networking/pool.rb +40 -0
  72. data/lib/wayfarer/networking/result.rb +18 -0
  73. data/lib/wayfarer/networking/selenium.rb +43 -0
  74. data/lib/wayfarer/networking/strategy.rb +38 -0
  75. data/lib/wayfarer/page.rb +17 -74
  76. data/lib/wayfarer/parsing/json.rb +17 -0
  77. data/lib/wayfarer/parsing/xml.rb +17 -0
  78. data/lib/wayfarer/redis/.#barrier.rb +1 -0
  79. data/lib/wayfarer/redis/barrier.rb +36 -0
  80. data/lib/wayfarer/redis/connection.rb +13 -0
  81. data/lib/wayfarer/redis/counter.rb +29 -0
  82. data/lib/wayfarer/redis/pool.rb +20 -0
  83. data/lib/wayfarer/redis/version.rb +19 -0
  84. data/lib/wayfarer/routing/dsl.rb +57 -0
  85. data/lib/wayfarer/routing/matchers/custom.rb +25 -0
  86. data/lib/wayfarer/routing/matchers/host.rb +19 -0
  87. data/lib/wayfarer/routing/matchers/path.rb +49 -0
  88. data/lib/wayfarer/routing/matchers/query.rb +63 -0
  89. data/lib/wayfarer/routing/matchers/scheme.rb +17 -0
  90. data/lib/wayfarer/routing/matchers/suffix.rb +17 -0
  91. data/lib/wayfarer/routing/matchers/url.rb +17 -0
  92. data/lib/wayfarer/routing/path_finder.rb +46 -0
  93. data/lib/wayfarer/routing/result.rb +15 -0
  94. data/lib/wayfarer/routing/root_route.rb +7 -0
  95. data/lib/wayfarer/routing/route.rb +47 -0
  96. data/lib/wayfarer/routing/router.rb +10 -54
  97. data/lib/wayfarer/routing/target_route.rb +7 -0
  98. data/lib/wayfarer/serializer.rb +17 -0
  99. data/lib/wayfarer/stringify.rb +47 -0
  100. data/lib/wayfarer/task.rb +34 -0
  101. data/lib/wayfarer.rb +48 -57
  102. data/mkdocs.yml +47 -0
  103. data/requirements.txt +1 -0
  104. data/spec/base_spec.rb +233 -0
  105. data/spec/callbacks_spec.rb +102 -0
  106. data/spec/cli/generate_spec.rb +39 -0
  107. data/spec/cli/job_spec.rb +74 -0
  108. data/spec/cli/version_spec.rb +13 -0
  109. data/spec/config/capybara_spec.rb +18 -0
  110. data/spec/config/ferrum_spec.rb +24 -0
  111. data/spec/config/networking_spec.rb +73 -0
  112. data/spec/config/redis_spec.rb +32 -0
  113. data/spec/config/root_spec.rb +31 -0
  114. data/spec/config/selenium_spec.rb +56 -0
  115. data/spec/config/strconv_spec.rb +58 -0
  116. data/spec/config/struct_spec.rb +66 -0
  117. data/spec/factories/middleware.rb +15 -0
  118. data/spec/factories/page.rb +78 -0
  119. data/spec/factories/task.rb +12 -0
  120. data/spec/fixtures/dummy_job.rb +7 -0
  121. data/spec/gc_spec.rb +63 -0
  122. data/spec/middleware/chain_spec.rb +96 -0
  123. data/spec/middleware/dedup_spec.rb +76 -0
  124. data/spec/middleware/fetch_spec.rb +100 -0
  125. data/spec/middleware/normalize_spec.rb +28 -0
  126. data/spec/middleware/router_spec.rb +80 -0
  127. data/spec/middleware/stage_spec.rb +39 -0
  128. data/spec/middleware/worker_spec.rb +117 -0
  129. data/spec/networking/capybara_spec.rb +12 -0
  130. data/spec/networking/context_spec.rb +127 -0
  131. data/spec/networking/ferrum_spec.rb +12 -0
  132. data/spec/networking/http_spec.rb +12 -0
  133. data/spec/networking/pool_spec.rb +67 -0
  134. data/spec/networking/selenium_spec.rb +12 -0
  135. data/spec/networking/strategy.rb +170 -0
  136. data/spec/page_spec.rb +21 -12
  137. data/spec/{parsers/json_parser_spec.rb → parsing/json_spec.rb} +5 -4
  138. data/spec/{parsers/xml_parser_spec.rb → parsing/xml_spec.rb} +3 -2
  139. data/spec/redis/barrier_spec.rb +78 -0
  140. data/spec/redis/counter_spec.rb +32 -0
  141. data/spec/redis/pool_spec.rb +18 -0
  142. data/spec/redis/version_spec.rb +13 -0
  143. data/spec/routing/dsl_spec.rb +98 -0
  144. data/spec/routing/integration_spec.rb +110 -0
  145. data/spec/routing/matchers/custom_spec.rb +31 -0
  146. data/spec/routing/matchers/host_spec.rb +49 -0
  147. data/spec/routing/matchers/path_spec.rb +43 -0
  148. data/spec/routing/matchers/query_spec.rb +137 -0
  149. data/spec/routing/matchers/scheme_spec.rb +25 -0
  150. data/spec/routing/{filetypes_rule_spec.rb → matchers/suffix_spec.rb} +14 -13
  151. data/spec/routing/matchers/uri_spec.rb +27 -0
  152. data/spec/routing/path_finder_spec.rb +33 -0
  153. data/spec/routing/root_route_spec.rb +29 -0
  154. data/spec/routing/route_spec.rb +43 -0
  155. data/spec/routing/router_spec.rb +13 -56
  156. data/spec/spec_helpers.rb +73 -38
  157. data/spec/stringify_spec.rb +23 -0
  158. data/{support → spec/support}/static/finders.html +0 -0
  159. data/{support → spec/support}/static/graph/details/a.html +0 -0
  160. data/{support → spec/support}/static/graph/details/b.html +0 -0
  161. data/{support → spec/support}/static/graph/index.html +0 -0
  162. data/{support → spec/support}/static/json/dummy.json +0 -0
  163. data/{support → spec/support}/static/links/links.html +0 -0
  164. data/{support → spec/support}/static/xml/dummy.xml +0 -0
  165. data/{support → spec/support}/test_app.rb +9 -2
  166. data/spec/task_spec.rb +27 -0
  167. data/spec/wayfarer_spec.rb +2 -13
  168. data/wayfarer.gemspec +40 -42
  169. metadata +234 -361
  170. data/.travis.yml +0 -5
  171. data/Changelog.md +0 -10
  172. data/README.md +0 -21
  173. data/benchmark/frontiers.rb +0 -143
  174. data/docs/.gitignore +0 -2
  175. data/docs/_config.yml +0 -15
  176. data/docs/_includes/base.html +0 -7
  177. data/docs/_includes/head.html +0 -10
  178. data/docs/_includes/navigation.html +0 -187
  179. data/docs/_layouts/default.html +0 -42
  180. data/docs/_sass/base.scss +0 -439
  181. data/docs/_sass/variables.scss +0 -24
  182. data/docs/_sass/vendor/bourbon/_bourbon-deprecate.scss +0 -19
  183. data/docs/_sass/vendor/bourbon/_bourbon-deprecated-upcoming.scss +0 -425
  184. data/docs/_sass/vendor/bourbon/_bourbon.scss +0 -90
  185. data/docs/_sass/vendor/bourbon/addons/_border-color.scss +0 -29
  186. data/docs/_sass/vendor/bourbon/addons/_border-radius.scss +0 -48
  187. data/docs/_sass/vendor/bourbon/addons/_border-style.scss +0 -28
  188. data/docs/_sass/vendor/bourbon/addons/_border-width.scss +0 -28
  189. data/docs/_sass/vendor/bourbon/addons/_buttons.scss +0 -69
  190. data/docs/_sass/vendor/bourbon/addons/_clearfix.scss +0 -25
  191. data/docs/_sass/vendor/bourbon/addons/_ellipsis.scss +0 -30
  192. data/docs/_sass/vendor/bourbon/addons/_font-stacks.scss +0 -31
  193. data/docs/_sass/vendor/bourbon/addons/_hide-text.scss +0 -27
  194. data/docs/_sass/vendor/bourbon/addons/_margin.scss +0 -29
  195. data/docs/_sass/vendor/bourbon/addons/_padding.scss +0 -29
  196. data/docs/_sass/vendor/bourbon/addons/_position.scss +0 -51
  197. data/docs/_sass/vendor/bourbon/addons/_prefixer.scss +0 -66
  198. data/docs/_sass/vendor/bourbon/addons/_retina-image.scss +0 -27
  199. data/docs/_sass/vendor/bourbon/addons/_size.scss +0 -56
  200. data/docs/_sass/vendor/bourbon/addons/_text-inputs.scss +0 -118
  201. data/docs/_sass/vendor/bourbon/addons/_timing-functions.scss +0 -34
  202. data/docs/_sass/vendor/bourbon/addons/_triangle.scss +0 -63
  203. data/docs/_sass/vendor/bourbon/addons/_word-wrap.scss +0 -29
  204. data/docs/_sass/vendor/bourbon/css3/_animation.scss +0 -61
  205. data/docs/_sass/vendor/bourbon/css3/_appearance.scss +0 -5
  206. data/docs/_sass/vendor/bourbon/css3/_backface-visibility.scss +0 -5
  207. data/docs/_sass/vendor/bourbon/css3/_background-image.scss +0 -44
  208. data/docs/_sass/vendor/bourbon/css3/_background.scss +0 -57
  209. data/docs/_sass/vendor/bourbon/css3/_border-image.scss +0 -61
  210. data/docs/_sass/vendor/bourbon/css3/_calc.scss +0 -6
  211. data/docs/_sass/vendor/bourbon/css3/_columns.scss +0 -67
  212. data/docs/_sass/vendor/bourbon/css3/_filter.scss +0 -6
  213. data/docs/_sass/vendor/bourbon/css3/_flex-box.scss +0 -327
  214. data/docs/_sass/vendor/bourbon/css3/_font-face.scss +0 -29
  215. data/docs/_sass/vendor/bourbon/css3/_font-feature-settings.scss +0 -6
  216. data/docs/_sass/vendor/bourbon/css3/_hidpi-media-query.scss +0 -12
  217. data/docs/_sass/vendor/bourbon/css3/_hyphens.scss +0 -6
  218. data/docs/_sass/vendor/bourbon/css3/_image-rendering.scss +0 -15
  219. data/docs/_sass/vendor/bourbon/css3/_keyframes.scss +0 -38
  220. data/docs/_sass/vendor/bourbon/css3/_linear-gradient.scss +0 -40
  221. data/docs/_sass/vendor/bourbon/css3/_perspective.scss +0 -12
  222. data/docs/_sass/vendor/bourbon/css3/_placeholder.scss +0 -10
  223. data/docs/_sass/vendor/bourbon/css3/_radial-gradient.scss +0 -40
  224. data/docs/_sass/vendor/bourbon/css3/_selection.scss +0 -44
  225. data/docs/_sass/vendor/bourbon/css3/_text-decoration.scss +0 -27
  226. data/docs/_sass/vendor/bourbon/css3/_transform.scss +0 -21
  227. data/docs/_sass/vendor/bourbon/css3/_transition.scss +0 -81
  228. data/docs/_sass/vendor/bourbon/css3/_user-select.scss +0 -5
  229. data/docs/_sass/vendor/bourbon/functions/_assign-inputs.scss +0 -16
  230. data/docs/_sass/vendor/bourbon/functions/_contains-falsy.scss +0 -25
  231. data/docs/_sass/vendor/bourbon/functions/_contains.scss +0 -31
  232. data/docs/_sass/vendor/bourbon/functions/_is-length.scss +0 -16
  233. data/docs/_sass/vendor/bourbon/functions/_is-light.scss +0 -26
  234. data/docs/_sass/vendor/bourbon/functions/_is-number.scss +0 -16
  235. data/docs/_sass/vendor/bourbon/functions/_is-size.scss +0 -23
  236. data/docs/_sass/vendor/bourbon/functions/_modular-scale.scss +0 -74
  237. data/docs/_sass/vendor/bourbon/functions/_px-to-em.scss +0 -24
  238. data/docs/_sass/vendor/bourbon/functions/_px-to-rem.scss +0 -26
  239. data/docs/_sass/vendor/bourbon/functions/_shade.scss +0 -24
  240. data/docs/_sass/vendor/bourbon/functions/_strip-units.scss +0 -22
  241. data/docs/_sass/vendor/bourbon/functions/_tint.scss +0 -24
  242. data/docs/_sass/vendor/bourbon/functions/_transition-property-name.scss +0 -37
  243. data/docs/_sass/vendor/bourbon/functions/_unpack.scss +0 -32
  244. data/docs/_sass/vendor/bourbon/helpers/_convert-units.scss +0 -26
  245. data/docs/_sass/vendor/bourbon/helpers/_directional-values.scss +0 -108
  246. data/docs/_sass/vendor/bourbon/helpers/_font-source-declaration.scss +0 -53
  247. data/docs/_sass/vendor/bourbon/helpers/_gradient-positions-parser.scss +0 -24
  248. data/docs/_sass/vendor/bourbon/helpers/_linear-angle-parser.scss +0 -35
  249. data/docs/_sass/vendor/bourbon/helpers/_linear-gradient-parser.scss +0 -51
  250. data/docs/_sass/vendor/bourbon/helpers/_linear-positions-parser.scss +0 -77
  251. data/docs/_sass/vendor/bourbon/helpers/_linear-side-corner-parser.scss +0 -41
  252. data/docs/_sass/vendor/bourbon/helpers/_radial-arg-parser.scss +0 -74
  253. data/docs/_sass/vendor/bourbon/helpers/_radial-gradient-parser.scss +0 -55
  254. data/docs/_sass/vendor/bourbon/helpers/_radial-positions-parser.scss +0 -28
  255. data/docs/_sass/vendor/bourbon/helpers/_render-gradients.scss +0 -31
  256. data/docs/_sass/vendor/bourbon/helpers/_shape-size-stripper.scss +0 -15
  257. data/docs/_sass/vendor/bourbon/helpers/_str-to-num.scss +0 -55
  258. data/docs/_sass/vendor/bourbon/settings/_asset-pipeline.scss +0 -7
  259. data/docs/_sass/vendor/bourbon/settings/_deprecation-warnings.scss +0 -8
  260. data/docs/_sass/vendor/bourbon/settings/_prefixer.scss +0 -9
  261. data/docs/_sass/vendor/bourbon/settings/_px-to-em.scss +0 -1
  262. data/docs/_sass/vendor/neat/_neat-helpers.scss +0 -11
  263. data/docs/_sass/vendor/neat/_neat.scss +0 -23
  264. data/docs/_sass/vendor/neat/functions/_new-breakpoint.scss +0 -49
  265. data/docs/_sass/vendor/neat/functions/_private.scss +0 -114
  266. data/docs/_sass/vendor/neat/grid/_box-sizing.scss +0 -15
  267. data/docs/_sass/vendor/neat/grid/_direction-context.scss +0 -33
  268. data/docs/_sass/vendor/neat/grid/_display-context.scss +0 -28
  269. data/docs/_sass/vendor/neat/grid/_fill-parent.scss +0 -22
  270. data/docs/_sass/vendor/neat/grid/_media.scss +0 -92
  271. data/docs/_sass/vendor/neat/grid/_omega.scss +0 -87
  272. data/docs/_sass/vendor/neat/grid/_outer-container.scss +0 -34
  273. data/docs/_sass/vendor/neat/grid/_pad.scss +0 -25
  274. data/docs/_sass/vendor/neat/grid/_private.scss +0 -35
  275. data/docs/_sass/vendor/neat/grid/_row.scss +0 -52
  276. data/docs/_sass/vendor/neat/grid/_shift.scss +0 -50
  277. data/docs/_sass/vendor/neat/grid/_span-columns.scss +0 -94
  278. data/docs/_sass/vendor/neat/grid/_to-deprecate.scss +0 -97
  279. data/docs/_sass/vendor/neat/grid/_visual-grid.scss +0 -42
  280. data/docs/_sass/vendor/neat/mixins/_clearfix.scss +0 -25
  281. data/docs/_sass/vendor/neat/settings/_disable-warnings.scss +0 -13
  282. data/docs/_sass/vendor/neat/settings/_grid.scss +0 -51
  283. data/docs/_sass/vendor/neat/settings/_visual-grid.scss +0 -27
  284. data/docs/_sass/vendor/normalize-3.0.2.scss +0 -427
  285. data/docs/_sass/vendor/pygments.scss +0 -356
  286. data/docs/automating_browsers/capybara.md +0 -70
  287. data/docs/css/screen.scss +0 -7
  288. data/docs/guides/cli.md +0 -52
  289. data/docs/guides/frontiers.md +0 -93
  290. data/docs/guides/halting.md +0 -23
  291. data/docs/guides/job_queues.md +0 -26
  292. data/docs/guides/locals.md +0 -36
  293. data/docs/guides/logging.md +0 -22
  294. data/docs/guides/page_objects.md +0 -67
  295. data/docs/guides/peeking.md +0 -46
  296. data/docs/guides/selenium_capybara.md +0 -100
  297. data/docs/guides/tutorial.md +0 -452
  298. data/docs/js/navigation.js +0 -11
  299. data/docs/misc/contributing.md +0 -20
  300. data/docs/misc/testing.md +0 -11
  301. data/docs/recipes/authentication.md +0 -23
  302. data/docs/recipes/csv.md +0 -29
  303. data/docs/recipes/javascript.md +0 -20
  304. data/docs/recipes/multiple_uris.md +0 -18
  305. data/docs/recipes/screenshots.md +0 -20
  306. data/docs/routing/custom_rules.md +0 -16
  307. data/docs/routing/filetypes_rules.md +0 -21
  308. data/docs/routing/host_rules.md +0 -24
  309. data/docs/routing/path_rules.md +0 -33
  310. data/docs/routing/protocol_rules.md +0 -17
  311. data/docs/routing/query_rules.md +0 -69
  312. data/docs/routing/routes.md +0 -96
  313. data/docs/routing/uri_rules.md +0 -18
  314. data/examples/collect_github_issues.rb +0 -65
  315. data/examples/find_foobar_on_wikipedia.rb +0 -23
  316. data/lib/wayfarer/configuration.rb +0 -86
  317. data/lib/wayfarer/crawl.rb +0 -79
  318. data/lib/wayfarer/crawl_observer.rb +0 -103
  319. data/lib/wayfarer/dispatcher.rb +0 -104
  320. data/lib/wayfarer/finders.rb +0 -61
  321. data/lib/wayfarer/frontiers/frontier.rb +0 -79
  322. data/lib/wayfarer/frontiers/memory_bloomfilter.rb +0 -32
  323. data/lib/wayfarer/frontiers/memory_frontier.rb +0 -76
  324. data/lib/wayfarer/frontiers/memory_trie_frontier.rb +0 -39
  325. data/lib/wayfarer/frontiers/normalize_uris.rb +0 -48
  326. data/lib/wayfarer/frontiers/redis_bloomfilter.rb +0 -34
  327. data/lib/wayfarer/frontiers/redis_frontier.rb +0 -83
  328. data/lib/wayfarer/http_adapters/adapter_pool.rb +0 -62
  329. data/lib/wayfarer/http_adapters/net_http_adapter.rb +0 -77
  330. data/lib/wayfarer/http_adapters/selenium_adapter.rb +0 -80
  331. data/lib/wayfarer/job.rb +0 -211
  332. data/lib/wayfarer/locals.rb +0 -40
  333. data/lib/wayfarer/parsers/json_parser.rb +0 -20
  334. data/lib/wayfarer/parsers/xml_parser.rb +0 -27
  335. data/lib/wayfarer/processor.rb +0 -103
  336. data/lib/wayfarer/routing/custom_rule.rb +0 -21
  337. data/lib/wayfarer/routing/filetypes_rule.rb +0 -20
  338. data/lib/wayfarer/routing/host_rule.rb +0 -19
  339. data/lib/wayfarer/routing/path_rule.rb +0 -54
  340. data/lib/wayfarer/routing/protocol_rule.rb +0 -21
  341. data/lib/wayfarer/routing/query_rule.rb +0 -59
  342. data/lib/wayfarer/routing/rule.rb +0 -114
  343. data/lib/wayfarer/routing/uri_rule.rb +0 -21
  344. data/spec/configuration_spec.rb +0 -26
  345. data/spec/crawl_spec.rb +0 -48
  346. data/spec/finders_spec.rb +0 -49
  347. data/spec/frontiers/memory_bloomfilter_spec.rb +0 -6
  348. data/spec/frontiers/memory_frontier_spec.rb +0 -6
  349. data/spec/frontiers/memory_trie_frontier_spec.rb +0 -6
  350. data/spec/frontiers/normalize_uris_spec.rb +0 -59
  351. data/spec/frontiers/redis_bloomfilter_spec.rb +0 -6
  352. data/spec/frontiers/redis_frontier_spec.rb +0 -6
  353. data/spec/http_adapters/adapter_pool_spec.rb +0 -33
  354. data/spec/http_adapters/net_http_adapter_spec.rb +0 -83
  355. data/spec/http_adapters/selenium_adapter_spec.rb +0 -53
  356. data/spec/integration/callbacks_spec.rb +0 -42
  357. data/spec/integration/locals_spec.rb +0 -106
  358. data/spec/integration/peeking_spec.rb +0 -61
  359. data/spec/job_spec.rb +0 -122
  360. data/spec/processor_spec.rb +0 -31
  361. data/spec/routing/custom_rule_spec.rb +0 -26
  362. data/spec/routing/host_rule_spec.rb +0 -48
  363. data/spec/routing/path_rule_spec.rb +0 -66
  364. data/spec/routing/protocol_rule_spec.rb +0 -26
  365. data/spec/routing/query_rule_spec.rb +0 -124
  366. data/spec/routing/rule_spec.rb +0 -251
  367. data/spec/routing/uri_rule_spec.rb +0 -24
  368. data/spec/shared/frontier.rb +0 -96
  369. data/wayfarer-jruby.gemspec +0 -49
@@ -0,0 +1,67 @@
1
+ # frozen_string_literal: true
2
+
3
+ require "spec_helpers"
4
+
5
+ describe Wayfarer::Networking::Pool do
6
+ subject(:pool) { Wayfarer::Networking::Pool.send(:new) }
7
+
8
+ after { pool.free }
9
+
10
+ describe "#with" do
11
+ context "by default" do
12
+ it "yields HTTP" do
13
+ pool.with do |context|
14
+ expect(context.strategy).to be_a(Wayfarer::Networking::HTTP)
15
+ end
16
+ end
17
+ end
18
+
19
+ context "when using Ferrum", ferrum: true do
20
+ before { Wayfarer.config.network.agent = :ferrum }
21
+
22
+ it "yields Ferrum" do
23
+ pool.with do |context|
24
+ expect(context.strategy).to be_a(Wayfarer::Networking::Ferrum)
25
+ end
26
+ end
27
+ end
28
+
29
+ context "when using Selenium", selenium: true do
30
+ before { Wayfarer.config.network.agent = :selenium }
31
+
32
+ it "yields Selenium" do
33
+ pool.with do |context|
34
+ expect(context.strategy).to be_a(Wayfarer::Networking::Selenium)
35
+ end
36
+ end
37
+ end
38
+
39
+ context "when using Capybara", ferrum: true do
40
+ before do
41
+ Wayfarer.config.network.agent = :capybara
42
+ Wayfarer.config.capybara.driver = :cuprite
43
+ end
44
+
45
+ it "yields Capybara" do
46
+ pool.with do |context|
47
+ expect(context.strategy).to be_a(Wayfarer::Networking::Capybara)
48
+ end
49
+ end
50
+ end
51
+ end
52
+
53
+ describe "#free" do
54
+ let(:strategy) { double(create: spy) }
55
+
56
+ before do
57
+ pool.class.registry[:foobar] = double(new: strategy)
58
+ Wayfarer.config.network.agent = :foobar
59
+ end
60
+
61
+ it "destroys the strategy" do
62
+ expect(strategy).to receive(:destroy)
63
+ pool.with {}
64
+ pool.free
65
+ end
66
+ end
67
+ end
@@ -0,0 +1,12 @@
1
+ # frozen_string_literal: true
2
+
3
+ require "spec_helpers"
4
+ require_relative "strategy"
5
+
6
+ describe Wayfarer::Networking::Selenium, selenium: true do
7
+ include_examples "Network strategy", strategy: described_class,
8
+ browser: true,
9
+ request_headers: false,
10
+ response_headers: false,
11
+ status_code: false
12
+ end
@@ -0,0 +1,170 @@
1
+ # frozen_string_literal: true
2
+
3
+ require "spec_helpers"
4
+
5
+ RSpec.shared_examples "Network strategy" do |options|
6
+ attr_accessor :context
7
+
8
+ before(:all) do
9
+ self.context = Wayfarer::Networking::Context.new(options[:strategy].new)
10
+ end
11
+
12
+ after(:all) do
13
+ context.renew
14
+ end
15
+
16
+ describe "#renew_on" do
17
+ it "returns an Array" do
18
+ expect(context.strategy.renew_on).to be_an(Array)
19
+ end
20
+ end
21
+
22
+ describe "Context" do
23
+ describe "#fetch" do
24
+ it "returns Success" do
25
+ url = test_app_path("/hello_world")
26
+ result = context.fetch(url)
27
+ expect(result).to be_a(Wayfarer::Networking::Result::Success)
28
+ expect(result.page).to be_a(Wayfarer::Page)
29
+ end
30
+
31
+ it "sets the URL" do
32
+ url = test_app_path("/status_code/404")
33
+ page = context.fetch(url).page
34
+ expect(page.url).to eq test_app_path("/status_code/404")
35
+ end
36
+
37
+ it "sets the response body" do
38
+ url = test_app_path("/hello_world")
39
+ page = context.fetch(url).page
40
+ expect(page.body).to match(/Hello world!/)
41
+ end
42
+
43
+ it "sets the status code" do
44
+ skip unless options[:status_code]
45
+
46
+ url = test_app_path("/status_code/418")
47
+ page = context.fetch(url).page
48
+ expect(page.status_code).to be(418)
49
+ end
50
+
51
+ it "sets response headers" do
52
+ skip unless options[:response_headers]
53
+
54
+ url = test_app_path("/hello_world")
55
+ page = context.fetch(url).page
56
+ expect(page.headers["hello"]).to eq("world")
57
+ end
58
+
59
+ context "Selenium" do
60
+ before { skip unless context.strategy.is_a?(Wayfarer::Networking::Selenium) }
61
+
62
+ it "sets a mock status code" do
63
+ skip if options[:status_code]
64
+
65
+ url = test_app_path("/status_code/418")
66
+ page = context.fetch(url).page
67
+ expect(page.status_code).to be(options[:strategy]::MOCK_STATUS_CODE)
68
+ end
69
+
70
+ it "sets mock response headers" do
71
+ url = test_app_path("/hello_world")
72
+ page = context.fetch(url).page
73
+ expect(page.headers).to eq(options[:strategy]::MOCK_RESPONSE_HEADERS)
74
+ end
75
+ end
76
+
77
+ describe "HTTP headers" do
78
+ before do
79
+ Wayfarer.config.network.http_headers = { "User-Agent" => "Foobar" }
80
+ context.renew
81
+ end
82
+
83
+ it "uses configured HTTP headers" do
84
+ skip unless options[:request_headers]
85
+
86
+ url = test_app_path("/headers/HTTP_USER_AGENT")
87
+ page = context.fetch(url).page
88
+ expect(page.body).to match(/Foobar/)
89
+ end
90
+ end
91
+
92
+ context "when encountering a redirect" do
93
+ it "returns a Redirect" do
94
+ skip if options[:browser]
95
+
96
+ url = test_app_path("/redirect?times=3")
97
+ result = context.fetch(url)
98
+ expect(result).to be_a(Wayfarer::Networking::Result::Redirect)
99
+ expect(result.redirect_url).to eq test_app_path("/redirect?times=2")
100
+ end
101
+ end
102
+ end
103
+
104
+ describe "#live" do
105
+ context "when automating a browser" do
106
+ let(:url) { test_app_path("/body/foobar") }
107
+
108
+ before do
109
+ skip unless options[:browser]
110
+
111
+ context.fetch(test_app_path("/hello_world"))
112
+ context.strategy.navigate(context.instance, url)
113
+ end
114
+
115
+ subject(:page) { context.live.page }
116
+
117
+ it "sets the URL" do
118
+ expect(page.url).to eq(url)
119
+ end
120
+
121
+ it "sets the response body" do
122
+ expect(page.body).to match(/foobar/)
123
+ end
124
+
125
+ it "sets response headers" do
126
+ skip unless options[:response_headers]
127
+
128
+ expect(page.headers["content-length"]).to eq("6")
129
+ end
130
+
131
+ it "sets the status code" do
132
+ skip unless options[:status_code]
133
+
134
+ expect(page.status_code).to be(200)
135
+ end
136
+ end
137
+
138
+ context "when using plain HTTP" do
139
+ it "returns nil" do
140
+ skip if options[:browser]
141
+
142
+ expect(context.live).to be(nil)
143
+ end
144
+ end
145
+ end
146
+
147
+ describe "#renew" do
148
+ it "replaces the instance", foo: true do
149
+ expect {
150
+ context.renew
151
+ }.to(change { context.instance })
152
+ end
153
+ end
154
+ end
155
+
156
+ describe "Selenium" do
157
+ before { skip unless context.strategy.is_a?(Wayfarer::Networking::Selenium) }
158
+
159
+ describe "Client timeout" do
160
+ before do
161
+ Wayfarer.config.selenium.client_timeout = 42
162
+ context.renew
163
+ end
164
+
165
+ it "sets the client timeout" do
166
+ expect(context.instance.send(:bridge).send(:http).read_timeout).to be(42)
167
+ end
168
+ end
169
+ end
170
+ end
data/spec/page_spec.rb CHANGED
@@ -1,38 +1,47 @@
1
1
  # frozen_string_literal: true
2
+
2
3
  require "spec_helpers"
3
4
 
4
5
  describe Wayfarer::Page do
5
- subject(:page) { fetch_page(test_app("/links/links.html")) }
6
-
7
6
  describe "#doc" do
7
+ context "when Content-Type is absent" do
8
+ subject(:page) { build(:page, :html, headers: {}) }
9
+
10
+ it "returns a Nokogiri::HTML::Document" do
11
+ expect(page.doc).to be_a(Nokogiri::HTML::Document)
12
+ end
13
+ end
14
+
8
15
  context "when Content-Type is HTML" do
16
+ subject(:page) { build(:page, :html) }
17
+
9
18
  it "returns a Nokogiri::HTML::Document" do
10
- expect(page.doc).to be_a Nokogiri::HTML::Document
19
+ expect(page.doc).to be_a(Nokogiri::HTML::Document)
11
20
  end
12
21
  end
13
22
 
14
23
  context "when Content-Type is XML" do
15
- subject(:page) { fetch_page(test_app("/xml/dummy.xml")) }
24
+ subject(:page) { build(:page, :xml) }
16
25
 
17
26
  it "returns a Nokogiri::XML::Document" do
18
- expect(page.doc).to be_a Nokogiri::XML::Document
27
+ expect(page.doc).to be_a(Nokogiri::XML::Document)
19
28
  end
20
29
  end
21
30
 
22
31
  context "when Content-Type is JSON" do
23
- subject(:page) { fetch_page(test_app("/json/dummy.json")) }
32
+ subject(:page) { build(:page, :json) }
24
33
 
25
34
  it "returns a Hash" do
26
- expect(page.doc).to be_a Hash
35
+ expect(page.doc).to be_a(Hash)
27
36
  end
28
37
  end
29
38
  end
30
39
 
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
40
+ describe "#meta" do
41
+ subject(:page) { build(:page, :html) }
42
+
43
+ it "returns a MetaInspector document" do
44
+ expect(page.meta).to be_a(MetaInspector::Document)
36
45
  end
37
46
  end
38
47
  end
@@ -1,12 +1,13 @@
1
1
  # frozen_string_literal: true
2
+
2
3
  require "spec_helpers"
3
4
 
4
- describe Wayfarer::Parsers::JSONParser do
5
- subject(:parser) { Parsers::JSONParser }
5
+ describe Wayfarer::Parsing::JSON do
6
+ subject(:parser) { Wayfarer::Parsing::JSON }
6
7
 
7
8
  describe ".parse" do
8
9
  it "returns a Hash" do
9
- json_str = <<-json
10
+ json_str = <<-JSON
10
11
  {
11
12
  "id": 1,
12
13
  "name": "Foo",
@@ -20,7 +21,7 @@ describe Wayfarer::Parsers::JSONParser do
20
21
  "retail": 20
21
22
  }
22
23
  }
23
- json
24
+ JSON
24
25
 
25
26
  doc = parser.parse(json_str)
26
27
 
@@ -1,8 +1,9 @@
1
1
  # frozen_string_literal: true
2
+
2
3
  require "spec_helpers"
3
4
 
4
- describe Wayfarer::Parsers::XMLParser do
5
- subject(:parser) { Parsers::XMLParser }
5
+ describe Wayfarer::Parsing::XML do
6
+ subject(:parser) { Wayfarer::Parsing::XML }
6
7
 
7
8
  describe ".parse_html" do
8
9
  it "returns a Nokogiri::HTML::Document" do
@@ -0,0 +1,78 @@
1
+ # frozen_string_literal: true
2
+
3
+ require "spec_helpers"
4
+
5
+ describe Wayfarer::Redis::Barrier, redis: true do
6
+ let(:url) { "https://example.com" }
7
+ subject(:barrier) { Wayfarer::Redis::Barrier.new("batch") }
8
+
9
+ describe "#redis_key" do
10
+ it "returns the expected Redis key" do
11
+ expect(barrier.redis_key).to eq("wayfarer-barrier-batch")
12
+ end
13
+ end
14
+
15
+ describe "#reset!" do
16
+ it "resets seen URLs" do
17
+ barrier.seen?(url)
18
+ barrier.reset!
19
+ expect(barrier.seen?(url)).to be false
20
+ end
21
+ end
22
+
23
+ describe "#seen?" do
24
+ context "with seen URL" do
25
+ before { barrier.seen?(url) }
26
+
27
+ it "returns true" do
28
+ expect(barrier.seen?(url)).to be(true)
29
+ end
30
+ end
31
+
32
+ context "with unseen URL" do
33
+ it "returns false" do
34
+ expect(barrier.seen?(url)).to be(false)
35
+ end
36
+ end
37
+ end
38
+
39
+ describe "#peek" do
40
+ let(:seen_urls) { %w[https://yahoo.com https://google.com] }
41
+ let(:unseen_urls) { %w[https://w3c.org https://nasa.gov] }
42
+
43
+ before do
44
+ allow(Wayfarer::Redis::Version).to receive(:determine).and_return(redis_version)
45
+
46
+ seen_urls.each do |url|
47
+ barrier.seen?(url)
48
+ end
49
+ end
50
+
51
+ context "Redis >= 6.2.0" do
52
+ let(:redis_version) { [6, 2, 5] }
53
+
54
+ it "returns membership" do
55
+ urls = [*seen_urls, *unseen_urls]
56
+ expect(barrier.peek(urls)).to eq([true, true, false, false])
57
+ end
58
+ end
59
+
60
+ context "Redis < 6.2.0" do
61
+ let(:redis_version) { [2, 6, 10] }
62
+
63
+ it "returns membership" do
64
+ urls = [*seen_urls, *unseen_urls]
65
+ expect(barrier.peek(urls)).to eq([true, true, false, false])
66
+ end
67
+ end
68
+ end
69
+
70
+ describe "#unsee" do
71
+ it "removes a seen URL" do
72
+ barrier.seen?(url)
73
+ expect {
74
+ barrier.unsee(url)
75
+ }.to change { barrier.seen?(url) }.to(false)
76
+ end
77
+ end
78
+ end
@@ -0,0 +1,32 @@
1
+ # frozen_string_literal: true
2
+
3
+ require "spec_helpers"
4
+
5
+ describe Wayfarer::Redis::Counter, redis: true do
6
+ subject(:counter) { Wayfarer::Redis::Counter.new("batch") }
7
+
8
+ describe "#redis_key" do
9
+ it "returns the expected Redis key" do
10
+ expect(counter.redis_key).to eq("wayfarer-counter-batch")
11
+ end
12
+ end
13
+
14
+ describe "#increment" do
15
+ it "increments" do
16
+ expect { counter.increment }.to change { counter.value }.by(1)
17
+ end
18
+ end
19
+
20
+ describe "#decrement" do
21
+ it "decrements" do
22
+ expect { counter.decrement }.to change { counter.value }.by(-1)
23
+ end
24
+ end
25
+
26
+ describe "#reset!" do
27
+ it "resets" do
28
+ 3.times { counter.increment }
29
+ expect { counter.reset! }.to change { counter.value }.to(0)
30
+ end
31
+ end
32
+ end
@@ -0,0 +1,18 @@
1
+ # frozen_string_literal: true
2
+
3
+ require "spec_helpers"
4
+
5
+ describe Wayfarer::Redis::Pool, redis: true do
6
+ let(:conn) { spy }
7
+ subject(:pool) { Wayfarer::Redis::Pool.send(:new) }
8
+
9
+ describe "::with" do
10
+ before do
11
+ Wayfarer.config.redis.factory = ->(_) { conn }
12
+ end
13
+
14
+ it "instantiates the factory and yields" do
15
+ pool.with { |x| expect(x).to be(conn) }
16
+ end
17
+ end
18
+ end
@@ -0,0 +1,13 @@
1
+ # frozen_string_literal: true
2
+
3
+ require "spec_helpers"
4
+
5
+ describe Wayfarer::Redis::Version, redis: true do
6
+ describe "::determine" do
7
+ it "returns Redis major, minor, patch version" do
8
+ Wayfarer::Redis::Version.instance_variable_set(:@determine, nil)
9
+ expect(Wayfarer::Redis::Version).to receive(:server_version).and_return("1.20.300")
10
+ expect(Wayfarer::Redis::Version.determine).to eq([1, 20, 300])
11
+ end
12
+ end
13
+ end
@@ -0,0 +1,98 @@
1
+ # frozen_string_literal: true
2
+
3
+ require "spec_helpers"
4
+
5
+ describe Wayfarer::Routing::DSL do
6
+ subject(:root) { Wayfarer::Routing::RootRoute.new }
7
+ let(:child) { root.children.first }
8
+
9
+ describe "#to" do
10
+ it "adds a child with an always-matching matcher" do
11
+ expect(root.to(:foobar)).to be_a(Wayfarer::Routing::Route)
12
+ expect(child.action).to be(:foobar)
13
+ expect(child.matcher).to be_a(Wayfarer::Routing::Matchers::Custom)
14
+ expect(child.parent).to be(root)
15
+
16
+ %w[http://example.com http://w3c.org http://google.com].each do |url|
17
+ expect(child.matcher.match(url)).to be(true)
18
+ end
19
+ end
20
+ end
21
+
22
+ describe "#url" do
23
+ it "adds a child with an URL matcher" do
24
+ expect(root.url("http://example.com")).to be_a(Wayfarer::Routing::Route)
25
+ expect(child.matcher).to be_a(Wayfarer::Routing::Matchers::URL)
26
+ expect(child.matcher.url).to eq("http://example.com")
27
+ expect(child.parent).to be(root)
28
+ end
29
+ end
30
+
31
+ describe "#host" do
32
+ it "adds a child with a host matcher" do
33
+ expect(root.host("example.com")).to be_a(Wayfarer::Routing::Route)
34
+ expect(child.matcher).to be_a(Wayfarer::Routing::Matchers::Host)
35
+ expect(child.matcher.host).to eq("example.com")
36
+ expect(child.parent).to be(root)
37
+ end
38
+ end
39
+
40
+ describe "#path" do
41
+ it "adds a child with a path matcher" do
42
+ expect(root.path("/foo/bar")).to be_a(Wayfarer::Routing::Route)
43
+ expect(child.matcher).to be_a(Wayfarer::Routing::Matchers::Path)
44
+ expect(child.matcher.path).to eq("/foo/bar")
45
+ expect(child.parent).to be(root)
46
+ end
47
+ end
48
+
49
+ describe "#query" do
50
+ it "adds a child with a query matcher" do
51
+ expect(root.query(foo: "bar")).to be_a(Wayfarer::Routing::Route)
52
+ expect(child.matcher).to be_a(Wayfarer::Routing::Matchers::Query)
53
+ expect(child.matcher.fields).to eq({ foo: "bar" })
54
+ expect(child.parent).to be(root)
55
+ end
56
+ end
57
+
58
+ describe "#scheme" do
59
+ it "adds a child with a scheme matcher" do
60
+ expect(root.scheme(:https)).to be_a(Wayfarer::Routing::Route)
61
+ expect(child.matcher).to be_a(Wayfarer::Routing::Matchers::Scheme)
62
+ expect(child.matcher.scheme).to be(:https)
63
+ expect(child.parent).to be(root)
64
+ end
65
+ end
66
+
67
+ describe "#suffix" do
68
+ it "adds a child with a suffix matcher" do
69
+ expect(root.suffix(".png")).to be_a(Wayfarer::Routing::Route)
70
+ expect(child.matcher).to be_a(Wayfarer::Routing::Matchers::Suffix)
71
+ expect(child.matcher.suffix).to eq(".png")
72
+ expect(child.parent).to be(root)
73
+ end
74
+ end
75
+
76
+ describe "#custom" do
77
+ it "adds a child with a custom matcher" do
78
+ expect(root.custom(->(_) { true })).to be_a(Wayfarer::Routing::Route)
79
+ expect(child.matcher).to be_a(Wayfarer::Routing::Matchers::Custom)
80
+ expect(child.matcher.delegate).to be_a(Proc)
81
+ expect(child.parent).to be(root)
82
+ end
83
+ end
84
+
85
+ describe "Complex routing tree" do
86
+ it "constructs the expected tree" do
87
+ root.host "example.com", path: "/foo" do
88
+ query foo: 4, bar: 2
89
+ end
90
+
91
+ expect(root.children.count).to be(1)
92
+ expect(root.children.first.matcher).to be_a(Wayfarer::Routing::Matchers::Host)
93
+
94
+ expect(root.children.first.children.count).to be(1)
95
+ expect(root.children.first.children.first.matcher).to be_a(Wayfarer::Routing::Matchers::Path)
96
+ end
97
+ end
98
+ end