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 +1,39 @@
1
+ # frozen_string_literal: true
2
+
3
+ require "spec_helpers"
4
+
5
+ describe Wayfarer::CLI::Generate, cli: true do
6
+ subject(:cli) { Wayfarer::CLI::Runner }
7
+
8
+ describe "generate project" do
9
+ it "outputs" do
10
+ expected_output = <<-OUT
11
+ create foobar
12
+ create foobar/Gemfile
13
+ create foobar/app/jobs/foobar.rb
14
+ OUT
15
+
16
+ expect {
17
+ cli.start(%w[generate project foobar])
18
+ }.to output(expected_output).to_stdout
19
+ end
20
+
21
+ it "creates the project directory" do
22
+ expect {
23
+ cli.start(%w[generate project foobar])
24
+ }.to change { File.directory?("foobar") }.to(true)
25
+ end
26
+
27
+ it "creates the Gemfile" do
28
+ expect {
29
+ cli.start(%w[generate project foobar])
30
+ }.to change { File.file?("foobar/Gemfile") }.to(true)
31
+ end
32
+
33
+ it "creates the job" do
34
+ expect {
35
+ cli.start(%w[generate project foobar])
36
+ }.to change { File.file?("foobar/app/jobs/foobar.rb") }.to(true)
37
+ end
38
+ end
39
+ end
@@ -0,0 +1,74 @@
1
+ # frozen_string_literal: true
2
+
3
+ require "spec_helpers"
4
+
5
+ describe Wayfarer::CLI::Job, cli: true, redis: true do
6
+ include Wayfarer::Redis
7
+
8
+ let(:url) { test_app_path("/hello_world") }
9
+ let(:batch) { "my-batch" }
10
+ subject(:cli) { Wayfarer::CLI::Runner }
11
+
12
+ before do
13
+ write_file "app/jobs/dummy_job.rb", <<~FILE
14
+ class DummyJob < Wayfarer::Base
15
+ end
16
+ FILE
17
+ end
18
+
19
+ before { Wayfarer::CLI::Base.new.send(:load_environment) }
20
+
21
+ describe "job perform" do
22
+ it "performs the worker" do
23
+ expect_any_instance_of(DummyJob).to receive(:perform).with(kind_of(Wayfarer::Task))
24
+ cli.start(["job", "perform", "DummyJob", url])
25
+ end
26
+
27
+ it "collects garbage" do
28
+ expect_any_instance_of(Wayfarer::GC).to receive(:run).exactly(:once)
29
+ cli.start(["job", "perform", "DummyJob", url])
30
+ end
31
+
32
+ context "using MockRedis" do
33
+ it "performs the worker using MockRedis" do
34
+ cli.start(["job", "perform", "--mock-redis", "DummyJob", url])
35
+ expect(Wayfarer.config.redis.factory.call(nil)).to be_a(MockRedis)
36
+ end
37
+ end
38
+ end
39
+
40
+ describe "job enqueue" do
41
+ it "enqueues the job" do
42
+ expect(DummyJob).to receive(:crawl_later).with(Addressable::URI.parse(url), batch: kind_of(String))
43
+ cli.start(["job", "enqueue", "DummyJob", url])
44
+ end
45
+
46
+ context "with batch provided" do
47
+ it "enqueues the job" do
48
+ expect(DummyJob).to receive(:crawl_later).with(Addressable::URI.parse(url), batch: batch)
49
+ cli.start(["job", "enqueue", "--batch", batch, "DummyJob", url])
50
+ end
51
+ end
52
+ end
53
+
54
+ describe "job execute" do
55
+ it "executes the job" do
56
+ expect(DummyJob).to receive(:crawl_later).with(Addressable::URI.parse(url), batch: kind_of(String))
57
+ cli.start(["job", "execute", "DummyJob", url])
58
+ end
59
+
60
+ context "with batch provided" do
61
+ it "enqueues the job" do
62
+ expect(DummyJob).to receive(:crawl_later).with(Addressable::URI.parse(url), batch: batch)
63
+ cli.start(["job", "execute", "--batch", batch, "DummyJob", url])
64
+ end
65
+ end
66
+
67
+ context "using MockRedis" do
68
+ it "performs the worker using MockRedis" do
69
+ cli.start(["job", "execute", "--mock-redis", "DummyJob", url])
70
+ expect(Wayfarer.config.redis.factory.call(nil)).to be_a(MockRedis)
71
+ end
72
+ end
73
+ end
74
+ end
@@ -0,0 +1,13 @@
1
+ # frozen_string_literal: true
2
+
3
+ require "spec_helpers"
4
+
5
+ describe Wayfarer::CLI::Runner, cli: true do
6
+ describe "version" do
7
+ it "prints the version" do
8
+ expect {
9
+ described_class.start(%w[version])
10
+ }.to output(Wayfarer::VERSION::STRING << "\n").to_stdout
11
+ end
12
+ end
13
+ end
@@ -0,0 +1,18 @@
1
+ # frozen_string_literal: true
2
+
3
+ require "spec_helpers"
4
+
5
+ describe Wayfarer::Config::Capybara do
6
+ let(:env) { {} }
7
+ subject(:capybara) { Wayfarer::Config::Capybara.new(env) }
8
+
9
+ describe "#driver" do
10
+ context "with env var set" do
11
+ before { env["WAYFARER_CAPYBARA_DRIVER"] = "cuprite" }
12
+
13
+ it "parses the env var" do
14
+ expect(capybara.driver).to be(:cuprite)
15
+ end
16
+ end
17
+ end
18
+ end
@@ -0,0 +1,24 @@
1
+ # frozen_string_literal: true
2
+
3
+ require "spec_helpers"
4
+
5
+ describe Wayfarer::Config::Ferrum do
6
+ let(:env) { {} }
7
+ subject(:ferrum) { Wayfarer::Config::Ferrum.new(env) }
8
+
9
+ describe "#options" do
10
+ context "by default" do
11
+ it "is {}" do
12
+ expect(ferrum.options).to eq({})
13
+ end
14
+ end
15
+
16
+ context "with env var set" do
17
+ before { env["WAYFARER_FERRUM_OPTIONS"] = "url:http://chrome:3000,headless:false" }
18
+
19
+ it "parses the env var" do
20
+ expect(ferrum.options).to eq(url: "http://chrome:3000", headless: false)
21
+ end
22
+ end
23
+ end
24
+ end
@@ -0,0 +1,73 @@
1
+ # frozen_string_literal: true
2
+
3
+ require "spec_helpers"
4
+
5
+ describe Wayfarer::Config::Networking do
6
+ let(:env) { {} }
7
+ subject(:network) { Wayfarer::Config::Networking.new(env) }
8
+
9
+ describe "#agent" do
10
+ context "by default" do
11
+ it "is :http" do
12
+ expect(network.agent).to be(:http)
13
+ end
14
+ end
15
+
16
+ context "with env var set" do
17
+ before { env["WAYFARER_NETWORK_AGENT"] = "ferrum" }
18
+
19
+ it "parses the env var" do
20
+ expect(network.agent).to be(:ferrum)
21
+ end
22
+ end
23
+ end
24
+
25
+ describe "#pool_size" do
26
+ context "by default" do
27
+ it "is 1" do
28
+ expect(network.pool_size).to be(1)
29
+ end
30
+ end
31
+
32
+ context "with env var set" do
33
+ before { env["WAYFARER_NETWORK_POOL_SIZE"] = "42" }
34
+
35
+ it "parses the env var" do
36
+ expect(network.pool_size).to be(42)
37
+ end
38
+ end
39
+ end
40
+
41
+ describe "#pool_timeout" do
42
+ context "by default" do
43
+ it "is 10" do
44
+ expect(network.pool_timeout).to be(10)
45
+ end
46
+ end
47
+
48
+ context "with env var set" do
49
+ before { env["WAYFARER_NETWORK_POOL_SIZE"] = "1337" }
50
+
51
+ it "parses the env var" do
52
+ expect(network.pool_size).to be(1337)
53
+ end
54
+ end
55
+ end
56
+
57
+ describe "#http_headers" do
58
+ context "by default" do
59
+ it "is {}" do
60
+ expect(network.http_headers).to eq({})
61
+ end
62
+ end
63
+
64
+ context "with env var set" do
65
+ before { env["WAYFARER_NETWORK_HTTP_HEADERS"] = "user-agent:foo,authorization:bar" }
66
+
67
+ it "parses the env var" do
68
+ expect(network.http_headers).to eq("user-agent": "foo",
69
+ authorization: "bar")
70
+ end
71
+ end
72
+ end
73
+ end
@@ -0,0 +1,32 @@
1
+ # frozen_string_literal: true
2
+
3
+ require "spec_helpers"
4
+
5
+ describe Wayfarer::Config::Redis do
6
+ let(:env) { {} }
7
+ subject(:redis) { Wayfarer::Config::Redis.new(env) }
8
+
9
+ describe "#url" do
10
+ context "by default" do
11
+ it "is redis://localhost:6379" do
12
+ expect(redis.url).to eq("redis://localhost:6379")
13
+ end
14
+ end
15
+
16
+ context "with env var set" do
17
+ before { env["WAYFARER_REDIS_URL"] = "redis://redis:6379" }
18
+
19
+ it "parses the env var" do
20
+ expect(redis.url).to eq("redis://redis:6379")
21
+ end
22
+ end
23
+ end
24
+
25
+ describe "#factory" do
26
+ context "by default" do
27
+ it "instantiates Redis" do
28
+ expect(redis.factory.call(redis)).to be_a(::Redis)
29
+ end
30
+ end
31
+ end
32
+ end
@@ -0,0 +1,31 @@
1
+ # frozen_string_literal: true
2
+
3
+ require "spec_helpers"
4
+
5
+ describe Wayfarer::Config::Root do
6
+ subject(:config) { Wayfarer::Config::Root.new }
7
+
8
+ describe "#ferrum" do
9
+ it "returns a Ferrum config" do
10
+ expect(config.ferrum).to be_a(Wayfarer::Config::Ferrum)
11
+ end
12
+ end
13
+
14
+ describe "#network" do
15
+ it "returns a network config" do
16
+ expect(config.network).to be_a(Wayfarer::Config::Networking)
17
+ end
18
+ end
19
+
20
+ describe "#redis" do
21
+ it "returns a Redis config" do
22
+ expect(config.redis).to be_a(Wayfarer::Config::Redis)
23
+ end
24
+ end
25
+
26
+ describe "#selenium" do
27
+ it "returns a Selenium config" do
28
+ expect(config.selenium).to be_a(Wayfarer::Config::Selenium)
29
+ end
30
+ end
31
+ end
@@ -0,0 +1,56 @@
1
+ # frozen_string_literal: true
2
+
3
+ require "spec_helpers"
4
+
5
+ describe Wayfarer::Config::Selenium do
6
+ let(:env) { {} }
7
+ subject(:selenium) { Wayfarer::Config::Selenium.new(env) }
8
+
9
+ describe "#driver" do
10
+ context "by default" do
11
+ it "is :chrome" do
12
+ expect(selenium.driver).to be(:chrome)
13
+ end
14
+ end
15
+
16
+ context "with env var set" do
17
+ before { env["WAYFARER_SELENIUM_DRIVER"] = "firefox" }
18
+
19
+ it "parses the env var" do
20
+ expect(selenium.driver).to be(:firefox)
21
+ end
22
+ end
23
+ end
24
+
25
+ describe "#options" do
26
+ context "by default" do
27
+ it "is {}" do
28
+ expect(selenium.options).to eq({})
29
+ end
30
+ end
31
+
32
+ context "with env var set" do
33
+ before { env["WAYFARER_SELENIUM_OPTIONS"] = "url:http://firefox" }
34
+
35
+ it "parses the env var" do
36
+ expect(selenium.options).to eq(url: "http://firefox")
37
+ end
38
+ end
39
+ end
40
+
41
+ describe "#client_timeout" do
42
+ context "by default" do
43
+ it "is 60" do
44
+ expect(selenium.client_timeout).to be(60)
45
+ end
46
+ end
47
+
48
+ context "with env var set" do
49
+ before { env["WAYFARER_SELENIUM_CLIENT_TIMEOUT"] = "10" }
50
+
51
+ it "parses the env var" do
52
+ expect(selenium.client_timeout).to be(10)
53
+ end
54
+ end
55
+ end
56
+ end
@@ -0,0 +1,58 @@
1
+ # frozen_string_literal: true
2
+
3
+ require "spec_helpers"
4
+
5
+ describe Wayfarer::Config::Strconv do
6
+ subject(:strconv) { Wayfarer::Config::Strconv }
7
+
8
+ describe "::parse" do
9
+ describe Hash do
10
+ it "parses" do
11
+ input = "alpha:1,beta:two,gamma:true"
12
+ output = strconv.parse(input, Hash)
13
+ expect(output).to eq(alpha: 1, beta: "two", gamma: true)
14
+ end
15
+ end
16
+
17
+ describe Array do
18
+ it "parses" do
19
+ input = "alpha, beta , gamma"
20
+ output = strconv.parse(input, Array)
21
+ expect(output).to eq(%w[alpha beta gamma])
22
+ end
23
+ end
24
+
25
+ describe Symbol do
26
+ it "parses" do
27
+ expect(strconv.parse("foobar", Symbol)).to be(:foobar)
28
+ end
29
+ end
30
+
31
+ describe Integer do
32
+ it "parses" do
33
+ expect(strconv.parse("42", Integer)).to be(42)
34
+ end
35
+ end
36
+
37
+ describe "Primitives" do
38
+ context "Booleans" do
39
+ it "parses" do
40
+ expect(strconv.parse("true")).to be(true)
41
+ expect(strconv.parse("false")).to be(false)
42
+ end
43
+ end
44
+
45
+ context "Numbers" do
46
+ it "parses" do
47
+ expect(strconv.parse("42")).to be(42)
48
+ end
49
+ end
50
+
51
+ context "Strings" do
52
+ it "parses" do
53
+ expect(strconv.parse("foobar")).to be("foobar")
54
+ end
55
+ end
56
+ end
57
+ end
58
+ end
@@ -0,0 +1,66 @@
1
+ # frozen_string_literal: true
2
+
3
+ require "spec_helpers"
4
+
5
+ describe Wayfarer::Config::Struct do
6
+ let(:struct) do
7
+ Wayfarer::Config::Struct.new(members)
8
+ end
9
+
10
+ let(:members) { { foo: options } }
11
+ let(:options) { {} }
12
+ let(:env) { {} }
13
+ subject { struct.new(env) }
14
+
15
+ describe "Reader" do
16
+ context "without environment values and default" do
17
+ let(:options) { {} }
18
+
19
+ it "returns nil" do
20
+ expect(subject.foo).to be(nil)
21
+ end
22
+ end
23
+
24
+ context "with default only" do
25
+ let(:options) { { default: 42 } }
26
+
27
+ it "returns the default" do
28
+ expect(subject.foo).to be(42)
29
+ end
30
+ end
31
+
32
+ context "with environment key specified" do
33
+ let(:options) { { env_key: "FOO" } }
34
+
35
+ context "with environment value" do
36
+ let(:env) { { "FOO" => "hello" } }
37
+
38
+ it "returns the value" do
39
+ expect(subject.foo).to eq("hello")
40
+ end
41
+
42
+ context "with type specified" do
43
+ let(:options) { { env_key: "FOO", type: Symbol } }
44
+
45
+ it "parses the value" do
46
+ expect(subject.foo).to be(:hello)
47
+ end
48
+ end
49
+ end
50
+
51
+ context "without environment value" do
52
+ it "returns nil" do
53
+ expect(subject.foo).to be(nil)
54
+ end
55
+ end
56
+ end
57
+ end
58
+
59
+ describe "Writer" do
60
+ it "allows overriding environment values and defaults" do
61
+ expect {
62
+ subject.foo = 3
63
+ }.to change { subject.foo }.from(nil).to(3)
64
+ end
65
+ end
66
+ end
@@ -0,0 +1,15 @@
1
+ # frozen_string_literal: true
2
+
3
+ FactoryBot.define do
4
+ factory :middleware, class: OpenStruct do
5
+ receiver { -> {} }
6
+
7
+ initialize_with do
8
+ new(receiver: receiver).tap do |middleware|
9
+ middleware.define_singleton_method(:call) do |task, &block|
10
+ receiver.call(task, &block)
11
+ end
12
+ end
13
+ end
14
+ end
15
+ end
@@ -0,0 +1,78 @@
1
+ # frozen_string_literal: true
2
+
3
+ FactoryBot.define do
4
+ factory :page, class: Wayfarer::Page do
5
+ url { "https://example.com" }
6
+ status_code { 200 }
7
+ headers { {} }
8
+ body { "" }
9
+
10
+ trait :html do
11
+ headers { { "Content-Type" => "text/html" } }
12
+ body do
13
+ <<~HTML
14
+ <!doctype html>
15
+ <html lang=en>
16
+ <head>
17
+ <meta charset=utf-8>
18
+ <title>Title</title>
19
+ </head>
20
+ <body></body>
21
+ </html>
22
+ HTML
23
+ end
24
+ end
25
+
26
+ trait :xml do
27
+ headers { { "Content-Type" => "application/xml" } }
28
+ body do
29
+ <<~XML
30
+ <menu id="file" value="File">
31
+ <popup>
32
+ <menuitem value="New" onclick="CreateNewDoc()" />
33
+ <menuitem value="Open" onclick="OpenDoc()" />
34
+ <menuitem value="Close" onclick="CloseDoc()" />
35
+ </popup>
36
+ </menu>
37
+ XML
38
+ end
39
+ end
40
+
41
+ trait :json do
42
+ headers { { "Content-Type" => "application/json" } }
43
+ body do
44
+ <<~JSON
45
+ {
46
+ "menu":{
47
+ "id":"file",
48
+ "value":"File",
49
+ "popup":{
50
+ "menuitem":[
51
+ {
52
+ "value":"New",
53
+ "onclick":"CreateNewDoc()"
54
+ },
55
+ {
56
+ "value":"Open",
57
+ "onclick":"OpenDoc()"
58
+ },
59
+ {
60
+ "value":"Close",
61
+ "onclick":"CloseDoc()"
62
+ }
63
+ ]
64
+ }
65
+ }
66
+ }
67
+ JSON
68
+ end
69
+ end
70
+
71
+ initialize_with do
72
+ new(url: url,
73
+ status_code: status_code,
74
+ body: body,
75
+ headers: headers)
76
+ end
77
+ end
78
+ end
@@ -0,0 +1,12 @@
1
+ # frozen_string_literal: true
2
+
3
+ FactoryBot.define do
4
+ factory :task, class: Wayfarer::Task do
5
+ url { "https://example.com" }
6
+ batch { "batch" }
7
+
8
+ initialize_with do
9
+ new(url, batch)
10
+ end
11
+ end
12
+ end
@@ -0,0 +1,7 @@
1
+ # frozen_string_literal: true
2
+
3
+ class DummyJob < Wayfarer::Base
4
+ route { to :index }
5
+
6
+ def hello; end
7
+ end
data/spec/gc_spec.rb ADDED
@@ -0,0 +1,63 @@
1
+ # frozen_string_literal: true
2
+
3
+ require "spec_helpers"
4
+
5
+ describe Wayfarer::GC, redis: true do
6
+ include Wayfarer::Redis::Connection
7
+
8
+ let(:task) { build(:task) }
9
+ let(:klass) { Class.new(Wayfarer::Base) }
10
+ let(:job) { klass.new }
11
+ subject(:gc) { Wayfarer::GC.new(job) }
12
+
13
+ before do
14
+ job.arguments = [task]
15
+ task.barrier.seen?(task.url)
16
+ end
17
+
18
+ describe "#run" do
19
+ context "when counter reaches 0" do
20
+ before { task.counter.increment }
21
+
22
+ it "resets the barrier" do
23
+ expect {
24
+ gc.run
25
+ }.to change { redis { |conn| conn.exists?(task.barrier.redis_key) } }.to(false)
26
+ end
27
+
28
+ it "resets the counter" do
29
+ expect {
30
+ gc.run
31
+ }.to change { redis { |conn| conn.exists?(task.counter.redis_key) } }.to(false)
32
+ end
33
+
34
+ it "runs after batch callbacks" do
35
+ expect { |spy|
36
+ klass.after_batch(&spy)
37
+ gc.run
38
+ }.to yield_control
39
+ end
40
+ end
41
+
42
+ context "when counter does not reach 0" do
43
+ before { 2.times { task.counter.increment } }
44
+
45
+ it "does not reset the barrier" do
46
+ expect {
47
+ gc.run
48
+ }.not_to(change { redis { |conn| conn.exists?(task.barrier.redis_key) } })
49
+ end
50
+
51
+ it "does not reset the counter" do
52
+ expect {
53
+ gc.run
54
+ }.not_to(change { redis { |conn| conn.exists?(task.counter.redis_key) } })
55
+ end
56
+
57
+ it "does not run after batch callbacks" do
58
+ expect(klass).not_to receive(:run_after_batch_callbacks)
59
+ gc.run
60
+ end
61
+ end
62
+ end
63
+ end