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
@@ -1,42 +0,0 @@
1
- # frozen_string_literal: true
2
- require "spec_helpers"
3
-
4
- describe Wayfarer, integration: true do
5
- describe "Callbacks" do
6
- subject(:job) do
7
- Class.new(Wayfarer::Job) do
8
- config.reraise_exceptions = true
9
- end
10
- end
11
-
12
- describe "ActiveJob-inherited callbacks" do
13
- they "fire" do
14
- job.class_eval do
15
- before_perform { fail }
16
- end
17
-
18
- expect {
19
- job.perform_now
20
- }.to raise_error
21
- end
22
- end
23
-
24
- describe "Own callbacks" do
25
- describe "::before_crawl" do
26
- it "fires" do
27
- job.class_eval { before_crawl { fail } }
28
-
29
- expect { job.perform_now }.to raise_error
30
- end
31
- end
32
-
33
- describe "::after_crawl" do
34
- it "fires" do
35
- job.class_eval { after_crawl { fail } }
36
-
37
- expect { job.perform_now }.to raise_error
38
- end
39
- end
40
- end
41
- end
42
- end
@@ -1,106 +0,0 @@
1
- # frozen_string_literal: true
2
- require "spec_helpers"
3
-
4
- describe Wayfarer, integration: true do
5
- describe "Locals" do
6
- subject(:job) do
7
- Class.new(Wayfarer::Job) do
8
- config.reraise_exceptions = true
9
- end
10
- end
11
-
12
- describe "Initial local values" do
13
- let(:entry) { test_app("/hello_world") }
14
-
15
- they "do not change" do
16
- job.class_eval do
17
- route.path "/hello_world", to: :foobar
18
-
19
- let(:foo) { {} }
20
-
21
- def foobar
22
- foo[:bar] = :qux
23
- end
24
- end
25
-
26
- expect {
27
- job.perform_now(entry)
28
- }.not_to change { job.locals[:foo] }
29
- end
30
-
31
- context "when declared with ::let" do
32
- they "get replaced with thread-safe counterparts" do
33
- job.class_eval do
34
- route.path "/hello_world", to: :foobar
35
-
36
- let(:hash) { {} }
37
- let(:array) { [] }
38
- let(:fixnum) { 123 }
39
- let(:tru) { true }
40
- let(:fuls) { false }
41
-
42
- def foobar
43
- fail unless hash.is_a? Concurrent::Hash
44
- fail unless array.is_a? Concurrent::Array
45
- fail unless fixnum.is_a? Concurrent::AtomicFixnum
46
- fail unless tru.is_a? Concurrent::AtomicBoolean
47
- fail unless fuls.is_a? Concurrent::AtomicBoolean
48
- end
49
- end
50
-
51
- expect {
52
- job.perform_now(entry)
53
- }.not_to raise_error
54
- end
55
- end
56
- end
57
-
58
- describe "Locals" do
59
- let(:entry) { test_app("/graph/index.html") }
60
-
61
- they "can be mutated within actions" do
62
- job.class_eval do
63
- route.path "/graph/index.html", to: :index
64
- route.path "/graph/details/a.html", to: :detail
65
-
66
- let(:hash) { {} }
67
-
68
- def index
69
- hash[:foo] = 42
70
- stage page.links
71
- end
72
-
73
- def detail
74
- fail unless hash[:foo] == 42
75
- end
76
- end
77
-
78
- expect {
79
- job.perform_now(entry)
80
- }.not_to raise_error
81
- end
82
-
83
- they "are accessible within callbacks" do
84
- job.class_eval do
85
- route.path "/graph/index.html", to: :index
86
-
87
- let(:hash) { { foo: :bar} }
88
-
89
- before_crawl do
90
- fail unless hash[:foo] == :bar
91
- end
92
-
93
- after_crawl do
94
- fail unless hash[:foo] == :qux
95
- end
96
-
97
- def index
98
- hash[:foo] = :qux
99
- end
100
- end
101
-
102
- expect { job.perform_now(entry) }.not_to raise_error
103
- end
104
- end
105
- end
106
- end
@@ -1,61 +0,0 @@
1
- # frozen_string_literal: true
2
- require "spec_helpers"
3
-
4
- describe Wayfarer, integration: true do
5
- subject(:job) do
6
- Class.new(Wayfarer::Job) do
7
- config.reraise_exceptions = true
8
- end
9
- end
10
-
11
- let(:entry) { test_app("/graph/index.html") }
12
-
13
- describe "Peeking" do
14
- it "works" do
15
- job.class_eval do
16
- route.path "/graph/index.html", to: :index
17
- route.path "/graph/details/a.html", to: :detail
18
-
19
- def index
20
- peek = yield "http://localhost:9876/graph/details/a.html"
21
- fail unless peek == :ok
22
- end
23
-
24
- def detail
25
- :ok
26
- end
27
- end
28
-
29
- expect {
30
- job.perform_now(entry)
31
- }.not_to raise_error
32
- end
33
- end
34
-
35
- describe "Recursive peeking" do
36
- it "does not work" do
37
- job.class_eval do
38
- route.path "/graph/index.html", to: :index
39
- route.path "/graph/details/a.html", to: :a
40
- route.path "/graph/details/a.html", to: :b
41
-
42
- def index
43
- peek = yield "http://localhost:9876/graph/details/a.html"
44
- fail unless peek == :ok
45
- end
46
-
47
- def a
48
- yield "http://localhost:9876/graph/details/b.html" or :ok
49
- end
50
-
51
- def b
52
- yield "http://localhost:9876/graph/details/a.html"
53
- end
54
- end
55
-
56
- expect {
57
- job.perform_now(entry)
58
- }.not_to raise_error
59
- end
60
- end
61
- end
data/spec/job_spec.rb DELETED
@@ -1,122 +0,0 @@
1
- # frozen_string_literal: true
2
- require "spec_helpers"
3
-
4
- describe Wayfarer::Job do
5
- subject(:job) { Class.new(Wayfarer::Job) }
6
-
7
- describe "::prepare" do
8
- it "copies the router" do
9
- job.class_eval do
10
- route.host "example.com", to: :foobar
11
- end
12
-
13
- prepared_job = job.prepare
14
-
15
- expect(prepared_job.router).not_to be job.router
16
-
17
- uri = URI("http://example.com")
18
- expect(prepared_job.router.routes?(uri)).to be true
19
- end
20
-
21
- it "copies locals" do
22
- job.class_eval do
23
- let(:foo) { { bar: :qux } }
24
- let(:baz) { 42 }
25
- end
26
-
27
- prepared_job = job.prepare
28
-
29
- expect(prepared_job.locals).not_to be job.locals
30
-
31
- expect(prepared_job.locals[:foo]).to be_a Concurrent::Hash
32
- expect(prepared_job.locals[:baz]).to be_a Concurrent::AtomicFixnum
33
- end
34
-
35
- it "defines instance accessors for locals" do
36
- job.class_eval do
37
- let(:foo) { { bar: :qux } }
38
- let(:baz) { 42 }
39
- end
40
-
41
- prepared_job = job.prepare
42
-
43
- expect(prepared_job).to respond_to(:foo)
44
- expect(prepared_job).to respond_to(:baz)
45
- end
46
- end
47
-
48
- describe "::config" do
49
- it "allows manipulating the configuration" do
50
- expect {
51
- job.config { |c| c.http_adapter = :selenium }
52
- }.to change { job.config.http_adapter }.to(:selenium)
53
- end
54
-
55
- it "does not manipulate the global configuration" do
56
- expect {
57
- job.config { |c| c.http_adapter = :selenium }
58
- }.not_to change { Wayfarer.config.http_adapter }
59
- end
60
- end
61
-
62
- describe "#halt" do
63
- it "sets the halting flag" do
64
- job_instance = job.new
65
-
66
- expect {
67
- job_instance.send(:halt)
68
- }.to change { job_instance.halts? }.from(false).to(true)
69
- end
70
- end
71
-
72
- describe "#stage" do
73
- it "stages URIs" do
74
- job_instance = job.new
75
- job_instance.page = Page.new(uri: URI("https://yahoo.com/qux"))
76
-
77
- uris = %w(
78
- http://google.com
79
- http://example.com
80
- )
81
-
82
- expected = uris.map { |u| URI(u) }
83
-
84
- expect {
85
- job_instance.send(:stage, *uris)
86
- }.to change { job_instance.staged_uris }.from([]).to(expected)
87
- end
88
-
89
- it "expands relative URIs" do
90
- job_instance = job.new
91
- job_instance.page = Page.new(uri: URI("https://yahoo.com/qux"))
92
-
93
- uris = %w(
94
- /foo/bar
95
- bar/qux.html
96
- barfoo
97
- )
98
-
99
- expected = %w(
100
- https://yahoo.com/qux/foo/bar
101
- https://yahoo.com/qux/bar/qux.html
102
- https://yahoo.com/qux/barfoo
103
- ).map { |u| URI(u) }
104
-
105
- expect {
106
- job_instance.send(:stage, *uris)
107
- }.to change { job_instance.staged_uris }.from([]).to(expected)
108
- end
109
-
110
- context "with non-HTTP(s) URIs" do
111
- it "ignores them and does not raise an exception" do
112
- job_instance = job.new
113
-
114
- expect {
115
- job_instance.send(:stage, "ftp://example.com")
116
- }.not_to raise_error
117
-
118
- expect(job_instance.staged_uris).to be_empty
119
- end
120
- end
121
- end
122
- end
@@ -1,31 +0,0 @@
1
- # frozen_string_literal: true
2
- require "spec_helpers"
3
-
4
- describe Wayfarer::Processor do
5
- let(:job) { Class.new(Wayfarer::Job) }
6
- let(:frontier) { Frontiers::MemoryFrontier.new(job.config) }
7
- let(:dispatcher) { Dispatcher.new(job) }
8
- subject(:processor) { Processor.new(job, frontier, dispatcher) }
9
-
10
- describe "#halt!" do
11
- it "sets a halting flag" do
12
- processor.halt!
13
- expect(processor).to be_halted
14
- end
15
- end
16
-
17
- describe "#halted?" do
18
- context "when not halted" do
19
- it "returns false" do
20
- expect(processor.halted?).to be false
21
- end
22
- end
23
-
24
- context "when halted" do
25
- it "returns true" do
26
- processor.halt!
27
- expect(processor.halted?).to be true
28
- end
29
- end
30
- end
31
- end
@@ -1,26 +0,0 @@
1
- # frozen_string_literal: true
2
- require "spec_helpers"
3
-
4
- describe Wayfarer::Routing::CustomRule do
5
- let(:uri) { URI("http://example.com") }
6
-
7
- describe "#matches?" do
8
- context "with a block" do
9
- context "when block is truthy" do
10
- subject(:rule) { CustomRule.new -> (uri) { uri.is_a?(URI) } }
11
-
12
- it "returns true" do
13
- expect(rule.matches?(uri)).to be true
14
- end
15
- end
16
-
17
- context "when block is fals-y" do
18
- subject(:rule) { CustomRule.new -> (_) { false } }
19
-
20
- it "returns true" do
21
- expect(rule.matches?(uri)).to be false
22
- end
23
- end
24
- end
25
- end
26
- end
@@ -1,48 +0,0 @@
1
- # frozen_string_literal: true
2
- require "spec_helpers"
3
-
4
- describe Wayfarer::Routing::HostRule do
5
- subject(:rule) { HostRule.new(str_or_regexp) }
6
-
7
- describe "#matches?" do
8
- describe "String matching" do
9
- let(:str_or_regexp) { "example.com" }
10
-
11
- context "with matching URI" do
12
- let(:uri) { URI("http://example.com/foo/bar") }
13
-
14
- it "returns true" do
15
- expect(rule.matches?(uri)).to be true
16
- end
17
- end
18
-
19
- context "with mismatching URI" do
20
- let(:uri) { URI("http://google.com/bar/qux") }
21
-
22
- it "returns false" do
23
- expect(rule.matches?(uri)).to be false
24
- end
25
- end
26
- end
27
-
28
- describe "RegExp matching" do
29
- let(:str_or_regexp) { /example.com/ }
30
-
31
- context "with matching URI" do
32
- let(:uri) { URI("http://sub.example.com") }
33
-
34
- it "returns true" do
35
- expect(rule.matches?(uri)).to be true
36
- end
37
- end
38
-
39
- context "with mismatching URI" do
40
- let(:uri) { URI("http://example.sub.com") }
41
-
42
- it "returns false" do
43
- expect(rule.matches?(uri)).to be false
44
- end
45
- end
46
- end
47
- end
48
- end
@@ -1,66 +0,0 @@
1
- # frozen_string_literal: true
2
- require "spec_helpers"
3
-
4
- describe Wayfarer::Routing::PathRule, mri: true do
5
- describe "#matches?" do
6
- context "with a string" do
7
- subject(:rule) { PathRule.new("/{alpha}/{beta}") }
8
-
9
- context "with matching URI" do
10
- let(:uri) { URI("http://example.com/foo/bar") }
11
-
12
- it "returns true" do
13
- expect(rule.matches?(uri)).to be true
14
- end
15
- end
16
-
17
- context "with mismatching URI" do
18
- let(:uri) { URI("http://example.com/foo") }
19
-
20
- it "returns false" do
21
- expect(rule.matches?(uri)).to be false
22
- end
23
- end
24
- end
25
-
26
- context "with a RegExp" do
27
- subject(:rule) { PathRule.new(/\/(\w+)\/(\w+)/) }
28
-
29
- context "with matching URI" do
30
- let(:uri) { URI("http://example.com/foo/bar") }
31
-
32
- it "returns true" do
33
- expect(rule.matches?(uri)).to be true
34
- end
35
- end
36
-
37
- context "with mismatching URI" do
38
- let(:uri) { URI("http://example.com/foo") }
39
-
40
- it "returns false" do
41
- expect(rule.matches?(uri)).to be false
42
- end
43
- end
44
- end
45
- end
46
-
47
- describe "#params" do
48
- context "with a string" do
49
- subject(:rule) { PathRule.new("/{alpha}/{beta}") }
50
-
51
- it "returns the correct parameters" do
52
- uri = URI("http://example.com/foo/bar")
53
- expect(rule.params(uri)).to eq("alpha" => "foo", "beta" => "bar")
54
- end
55
- end
56
-
57
- context "with a RegExp" do
58
- subject(:rule) { PathRule.new(/\/(\w+)\/(\w+)/) }
59
-
60
- it "returns the correct parameters" do
61
- uri = URI("http://example.com/foo/bar")
62
- expect(rule.params(uri)).to eq("0" => "foo", "1" => "bar")
63
- end
64
- end
65
- end
66
- end
@@ -1,26 +0,0 @@
1
- # frozen_string_literal: true
2
- require "spec_helpers"
3
-
4
- describe Wayfarer::Routing::ProtocolRule do
5
- describe "#matches?" do
6
- context "with a string" do
7
- subject(:rule) { ProtocolRule.new(:http) }
8
-
9
- context "with matching URI" do
10
- let(:uri) { URI("http://example.com") }
11
-
12
- it "returns true" do
13
- expect(rule.matches?(uri)).to be true
14
- end
15
- end
16
-
17
- context "with mismatching URI" do
18
- let(:uri) { URI("https://example.com") }
19
-
20
- it "returns true" do
21
- expect(rule.matches?(uri)).to be false
22
- end
23
- end
24
- end
25
- end
26
- end
@@ -1,124 +0,0 @@
1
- # frozen_string_literal: true
2
- require "spec_helpers"
3
-
4
- describe Wayfarer::Routing::QueryRule do
5
- subject(:rule) { QueryRule.new(constraints) }
6
-
7
- describe "String constraints" do
8
- let(:constraints) { Hash[arg: "foo"] }
9
-
10
- context "with matching query field value" do
11
- let(:uri) { URI("http://example.com?arg=foo") }
12
-
13
- it "returns true" do
14
- expect(rule.matches?(uri)).to be true
15
- end
16
- end
17
-
18
- context "with mismatching query field value" do
19
- let(:uri) { URI("http://example.com?arg=bar") }
20
-
21
- it "returns false" do
22
- expect(rule.matches?(uri)).to be false
23
- end
24
- end
25
- end
26
-
27
- describe "Integer constraints" do
28
- let(:constraints) { Hash[arg: 0] }
29
-
30
- context "with matching query field value" do
31
- let(:uri) { URI("http://example.com?arg=0") }
32
-
33
- it "returns true" do
34
- expect(rule.matches?(uri)).to be true
35
- end
36
- end
37
-
38
- context "with mismatching query field value" do
39
- let(:uri) { URI("http://example.com?arg=1") }
40
-
41
- it "returns false" do
42
- expect(rule.matches?(uri)).to be false
43
- end
44
- end
45
-
46
- context "with non-numeric query field value" do
47
- let(:uri) { URI("http://example.com?arg=foo") }
48
-
49
- it "returns false" do
50
- expect(rule.matches?(uri)).to be false
51
- end
52
- end
53
- end
54
-
55
- describe "Regexp constraints" do
56
- let(:constraints) { Hash[arg: /foo/] }
57
-
58
- context "with matching query field value" do
59
- let(:uri) { URI("http://example.com?arg=foo") }
60
-
61
- it "returns true" do
62
- expect(rule.matches?(uri)).to be true
63
- end
64
- end
65
-
66
- context "with mismatching query field value" do
67
- let(:uri) { URI("http://example.com?arg=bar") }
68
-
69
- it "returns false" do
70
- expect(rule.matches?(uri)).to be false
71
- end
72
- end
73
- end
74
-
75
- describe "Range constraints" do
76
- let(:constraints) { Hash[arg: 1..10] }
77
-
78
- context "with matching query field value" do
79
- let(:uri) { URI("http://example.com?arg=5") }
80
-
81
- it "returns true" do
82
- expect(rule.matches?(uri)).to be true
83
- end
84
- end
85
-
86
- context "with mismatching query field value" do
87
- let(:uri) { URI("http://example.com?arg=11") }
88
-
89
- it "returns false" do
90
- expect(rule.matches?(uri)).to be false
91
- end
92
- end
93
-
94
- context "with non-numeric query field value" do
95
- let(:uri) { URI("http://example.com?arg=foo") }
96
-
97
- it "returns false" do
98
- expect(rule.matches?(uri)).to be false
99
- end
100
- end
101
- end
102
-
103
- describe "Compound constraints" do
104
- let(:constraints) do
105
- Hash[foo: 1..5, bar: /baz/, qux: "zot", toto: 2]
106
- end
107
-
108
- context "with matching query field values" do
109
- let(:uri) { URI("http://example.com?foo=4&bar=bazqux&qux=zot&toto=2") }
110
-
111
- it "returns true" do
112
- expect(rule.matches?(uri)).to be true
113
- end
114
- end
115
-
116
- context "with mismatching query field values" do
117
- let(:uri) { URI("http://example.com?foo=bar&bar=qux&qux=6toto=0") }
118
-
119
- it "returns false" do
120
- expect(rule.matches?(uri)).to be false
121
- end
122
- end
123
- end
124
- end