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
@@ -1,70 +1,26 @@
1
1
  # frozen_string_literal: true
2
2
 
3
- require "forwardable"
4
-
5
3
  module Wayfarer
6
4
  module Routing
7
- # A {Router} maps URIs onto a {Job}'s instance methods.
8
5
  class Router
9
- extend Forwardable
6
+ ArgumentCountError = Class.new(StandardError)
10
7
 
11
- # @!attribute [r] rule
12
- # @return [Rule]
13
- attr_reader :rule
8
+ extend Forwardable
14
9
 
15
- # @!attribute [r] blacklist
16
- # @return [Rule]
17
- attr_reader :blacklist
10
+ attr_reader :root
18
11
 
19
12
  def initialize
20
- @rule = Rule.new
21
- @blacklist = Rule.new
22
- end
23
-
24
- delegate %i[
25
- uri
26
- host
27
- path
28
- query
29
- ] => :rule
30
-
31
- # Returns the associated instance method (action) of the first rule that
32
- # matches a URI and the collected parameter hash from the rule chain.
33
- # @return [[Boolean, Symbol, Hash]] if a matching rule exists.
34
- # @return [false] if no matching rule exists or the URI is forbidden.
35
- def route(uri)
36
- return false if forbids?(uri)
37
-
38
- # TODO: Use structs instead
39
- is_matching, params, action = @rule.invoke(uri)
40
- return action, params if is_matching && params
41
-
42
- false
43
- end
44
-
45
- # Whether a route matches the URI.
46
- # TODO: Test
47
- def routes?(uri)
48
- !!route(uri)
49
- end
50
-
51
- # Adds a {Rule} to the blacklist.
52
- def forbid(opts = {}, &proc)
53
- @blacklist.build_child_rule_chain_from_options(opts)
54
- @blacklist.instance_eval(&proc) if block_given?
55
- @blacklist
13
+ @blocks = []
56
14
  end
57
15
 
58
- # Whether the URI is matched by the blacklist rule.
59
- # @see #forbid
60
- def forbids?(uri)
61
- @blacklist.matches?(uri)
16
+ def draw(&block)
17
+ @blocks.push(block)
62
18
  end
63
19
 
64
- # Whether the URI is allowed.
65
- # @see #forbid
66
- def allows?(uri)
67
- !forbids?(uri)
20
+ def invoke(url, arguments)
21
+ @root = Wayfarer::Routing::RootRoute.new
22
+ @blocks.each { |block| Docile.dsl_eval(@root, *arguments, &block) }
23
+ root.invoke(url)
68
24
  end
69
25
  end
70
26
  end
@@ -0,0 +1,7 @@
1
+ # frozen_string_literal: true
2
+
3
+ module Wayfarer
4
+ module Routing
5
+ class TargetRoute < Route; end
6
+ end
7
+ end
@@ -0,0 +1,17 @@
1
+ # frozen_string_literal: true
2
+
3
+ module Wayfarer
4
+ class Serializer < ActiveJob::Serializers::ObjectSerializer
5
+ def serialize?(obj)
6
+ obj.is_a?(Wayfarer::Task)
7
+ end
8
+
9
+ def serialize(task)
10
+ super(url: task.url, batch: task.batch)
11
+ end
12
+
13
+ def deserialize(hash)
14
+ Wayfarer::Task.new(*hash.values_at(:url, :batch))
15
+ end
16
+ end
17
+ end
@@ -0,0 +1,47 @@
1
+ # frozen_string_literal: true
2
+
3
+ # 346325
4
+
5
+ module Wayfarer
6
+ module Stringify
7
+ def self.included(base)
8
+ base.include(InstanceMethods)
9
+ base.extend(ClassMethods)
10
+ base.instance_eval do
11
+ cattr_accessor :stringified_attributes do
12
+ []
13
+ end
14
+ end
15
+ end
16
+
17
+ module ClassMethods
18
+ def stringify(*variables)
19
+ stringified_attributes.concat(variables)
20
+ end
21
+ end
22
+
23
+ module InstanceMethods
24
+ def to_s
25
+ if self.class.stringified_attributes.any?
26
+ "#<#{class_name} #{attributes.join(', ')}>"
27
+ else
28
+ "#<#{class_name}>"
29
+ end
30
+ end
31
+
32
+ alias inspect to_s
33
+
34
+ def class_name
35
+ self.class.name
36
+ end
37
+
38
+ def attributes
39
+ self.class
40
+ .stringified_attributes
41
+ .map { |attr| [attr, public_send(attr)] }
42
+ .to_h
43
+ .map { |k, v| [k, "=", v.inspect].join }
44
+ end
45
+ end
46
+ end
47
+ end
@@ -0,0 +1,34 @@
1
+ # frozen_string_literal: true
2
+
3
+ module Wayfarer
4
+ class Task
5
+ include Stringify
6
+
7
+ attr_reader :url,
8
+ :batch,
9
+ :metadata
10
+
11
+ attr_accessor :job
12
+
13
+ stringify :url,
14
+ :batch
15
+
16
+ def initialize(url, batch)
17
+ @url = url
18
+ @batch = batch
19
+ @metadata = OpenStruct.new
20
+ end
21
+
22
+ def ==(other)
23
+ [url, batch] == [other.url, other.batch]
24
+ end
25
+
26
+ def barrier
27
+ @barrier ||= Wayfarer::Redis::Barrier.new(batch)
28
+ end
29
+
30
+ def counter
31
+ @counter ||= Wayfarer::Redis::Counter.new(batch)
32
+ end
33
+ end
34
+ end
data/lib/wayfarer.rb CHANGED
@@ -1,68 +1,59 @@
1
1
  # frozen_string_literal: true
2
2
 
3
- # rubocop:disable Style/Documentation
4
- require "logger"
3
+ require "cgi"
4
+ require "forwardable"
5
+ require "net/http"
6
+ require "securerandom"
5
7
  require "uri"
6
8
 
7
- # Plumbing
8
- require_relative "wayfarer/configuration"
9
+ require "active_job"
10
+ require "capybara"
11
+ require "capybara/cuprite"
12
+ require "connection_pool"
13
+ require "docile"
14
+ require "ferrum"
15
+ require "metainspector"
16
+ require "mime/types"
17
+ require "mime-types"
18
+ require "mock_redis"
19
+ require "mustermann"
20
+ require "net/http/persistent"
21
+ require "nokogiri"
22
+ require "normalize_url"
23
+ require "selenium-webdriver"
24
+ require "redis"
25
+ require "thor"
26
+ require "zeitwerk"
27
+
28
+ loader = Zeitwerk::Loader.for_gem
29
+ loader.inflector.inflect("cli" => "CLI",
30
+ "dsl" => "DSL",
31
+ "http" => "HTTP",
32
+ "url" => "URL",
33
+ "xml" => "XML",
34
+ "json" => "JSON",
35
+ "gc" => "GC")
36
+ loader.setup
9
37
 
10
- # Routing
11
- require_relative "wayfarer/routing/rule"
12
- require_relative "wayfarer/routing/uri_rule"
13
- require_relative "wayfarer/routing/host_rule"
14
- require_relative "wayfarer/routing/path_rule"
15
- require_relative "wayfarer/routing/query_rule"
16
- require_relative "wayfarer/routing/protocol_rule"
17
- require_relative "wayfarer/routing/filetypes_rule"
18
- require_relative "wayfarer/routing/custom_rule"
19
- require_relative "wayfarer/routing/router"
20
-
21
- # Networking
22
- require_relative "wayfarer/http_adapters/net_http_adapter"
23
- require_relative "wayfarer/http_adapters/selenium_adapter"
24
- require_relative "wayfarer/http_adapters/adapter_pool"
38
+ module Wayfarer
39
+ module VERSION
40
+ MAJOR = 0
41
+ MINOR = 4
42
+ TINY = 3
43
+ STRING = [MAJOR, MINOR, TINY].join(".")
44
+ end
25
45
 
26
- # Parsers
27
- require_relative "wayfarer/parsers/xml_parser"
28
- require_relative "wayfarer/parsers/json_parser"
46
+ mattr_accessor :config, default: Wayfarer::Config::Root.new
29
47
 
30
- # Frontiers
31
- require_relative "wayfarer/frontiers/frontier"
32
- require_relative "wayfarer/frontiers/memory_frontier"
33
- require_relative "wayfarer/frontiers/redis_frontier"
34
- require_relative "wayfarer/frontiers/normalize_uris"
48
+ mattr_accessor :middleware, default: [Wayfarer::Middleware::Stage.new,
49
+ Wayfarer::Middleware::Dedup.new,
50
+ Wayfarer::Middleware::Normalize.new,
51
+ Wayfarer::Middleware::Router.new,
52
+ Wayfarer::Middleware::Fetch.new]
35
53
 
36
- unless RUBY_PLATFORM == "java"
37
- require_relative "wayfarer/frontiers/memory_trie_frontier"
38
- require_relative "wayfarer/frontiers/memory_bloomfilter"
39
- require_relative "wayfarer/frontiers/redis_bloomfilter"
54
+ UserAgentTimeoutError = Class.new(StandardError)
40
55
  end
41
56
 
42
- # Processing
43
- require_relative "wayfarer/crawl"
44
- require_relative "wayfarer/crawl_observer"
45
- require_relative "wayfarer/locals"
46
- require_relative "wayfarer/job"
47
- require_relative "wayfarer/finders"
48
- require_relative "wayfarer/page"
49
- require_relative "wayfarer/dispatcher"
50
- require_relative "wayfarer/processor"
51
-
52
- module Wayfarer
53
- VERSION = "0.0.3"
54
-
55
- def self.logger
56
- return @logger if @logger
57
-
58
- @logger = Logger.new(STDOUT)
59
- @logger.level = Logger::WARN
60
- @logger
61
- end
57
+ loader.eager_load
62
58
 
63
- def self.config
64
- @config ||= Configuration.new
65
- yield(@config) if block_given?
66
- @config
67
- end
68
- end
59
+ ActiveJob::Serializers.serializers << Wayfarer::Serializer
data/mkdocs.yml ADDED
@@ -0,0 +1,47 @@
1
+ repo_url: https://github.com/bauerd/wayfarer
2
+ edit_uri: edit/develop/docs/
3
+ repo_name: Source Code
4
+ site_name: Wayfarer
5
+ markdown_extensions:
6
+ - admonition
7
+ - meta
8
+ - def_list
9
+ - pymdownx.details
10
+ - pymdownx.highlight
11
+ - pymdownx.superfences
12
+ - pymdownx.critic
13
+ - pymdownx.caret
14
+ - pymdownx.mark
15
+ - pymdownx.tilde
16
+ - pymdownx.tabbed
17
+ - pymdownx.tasklist:
18
+ custom_checkbox: true
19
+
20
+ theme:
21
+ name: material
22
+ features:
23
+ - navigation.tabs
24
+ - navigation.sections
25
+ - navigation.expand
26
+ font:
27
+ text: IBM Plex Sans
28
+ code: IBM Plex Sans Mono
29
+ palette:
30
+ - scheme: default
31
+ primary: black
32
+ accent: light blue
33
+ media: "(prefers-color-scheme: light)"
34
+ toggle:
35
+ icon: material/lightbulb-outline
36
+ name: Switch to dark mode
37
+ - scheme: slate
38
+ primary: blue grey
39
+ accent: cyan
40
+ media: "(prefers-color-scheme: dark)"
41
+ toggle:
42
+ icon: material/lightbulb
43
+ name: Switch to light mode
44
+ icon:
45
+ repo: fontawesome/brands/git
46
+
47
+
data/requirements.txt ADDED
@@ -0,0 +1 @@
1
+ mkdocs-material == 7.3.0
data/spec/base_spec.rb ADDED
@@ -0,0 +1,233 @@
1
+ # frozen_string_literal: true
2
+
3
+ require "spec_helpers"
4
+
5
+ describe Wayfarer::Base, redis: true do
6
+ include Wayfarer::Redis::Connection
7
+
8
+ let(:url) { "https://example.com" }
9
+ let(:batch) { "batch" }
10
+ let(:task) { build(:task, batch: batch, url: url) }
11
+ let(:klass) { Class.new(Wayfarer::Base) }
12
+
13
+ before { stub_const("DummyJob", klass) }
14
+
15
+ describe "::crawl_later" do
16
+ it "enqueues a task" do
17
+ expect(DummyJob).to receive(:perform_later).with(task)
18
+ DummyJob.crawl_later(url, batch: batch)
19
+ end
20
+ end
21
+
22
+ describe "#perform" do
23
+ it "assigns itself to the task" do
24
+ job = DummyJob.new
25
+ job.perform(task)
26
+ expect(task.job).to be(job)
27
+ end
28
+
29
+ it "calls the middleware chain" do
30
+ job = DummyJob.new
31
+ allow(job).to receive(:chain).and_return(spy)
32
+ expect(job.chain).to receive(:call).with(task)
33
+ job.perform(task)
34
+ end
35
+ end
36
+
37
+ describe "Callbacks" do
38
+ let(:counter) { task.counter }
39
+
40
+ describe "after enqueue" do
41
+ it "increments the counter" do
42
+ expect {
43
+ DummyJob.crawl_later(url, batch: batch)
44
+ }.to change { counter.value }.by(1)
45
+ end
46
+ end
47
+
48
+ describe "after perform" do
49
+ it "decrements the counter" do
50
+ DummyJob.crawl_later(url, batch: batch)
51
+ task.counter.increment
52
+ expect { perform_enqueued_jobs }.to change { task.counter.value }.by(-1)
53
+ end
54
+
55
+ context "when counter reaches 0" do
56
+ it "resets the barrier" do
57
+ DummyJob.crawl_later(url, batch: batch)
58
+ perform_enqueued_jobs
59
+ redis do |conn|
60
+ expect(conn.exists?(task.barrier.redis_key)).to be(false)
61
+ end
62
+ end
63
+
64
+ it "resets the counter" do
65
+ DummyJob.crawl_later(url, batch: batch)
66
+ perform_enqueued_jobs
67
+ redis do |conn|
68
+ expect(conn.exists?(task.counter.redis_key)).to be(false)
69
+ end
70
+ end
71
+
72
+ it "runs after batch callbacks" do
73
+ expect { |spy|
74
+ klass.after_batch(&spy)
75
+ DummyJob.crawl_later(url, batch: batch)
76
+ perform_enqueued_jobs
77
+ }.to yield_control
78
+ end
79
+ end
80
+ end
81
+ end
82
+
83
+ describe "Unhandled exceptions" do
84
+ let(:klass) { Class.new(Wayfarer::Base) }
85
+
86
+ before do
87
+ allow_any_instance_of(DummyJob).to receive(:perform).and_raise(RuntimeError.new)
88
+ end
89
+
90
+ it "does not retry the job" do
91
+ DummyJob.crawl_later(url, batch: batch)
92
+
93
+ expect {
94
+ begin
95
+ perform_enqueued_jobs
96
+ rescue StandardError
97
+ nil
98
+ end
99
+ }.to change { enqueued_jobs.size }.by(-1)
100
+ end
101
+
102
+ it "decrements the counter" do
103
+ 3.times { task.counter.increment }
104
+
105
+ DummyJob.crawl_later(url, batch: batch)
106
+ begin
107
+ perform_enqueued_jobs
108
+ rescue StandardError
109
+ nil
110
+ end
111
+
112
+ expect(task.counter.value).to be(3)
113
+ end
114
+
115
+ # it "runs after batch callbacks" do
116
+ # expect do |spy|
117
+ # klass.after_batch(&spy)
118
+ # DummyJob.crawl_later(url, batch: batch)
119
+ # 3.times { perform_enqueued_jobs }
120
+ # end.to yield_control
121
+ # end
122
+ end
123
+
124
+ describe "Retries" do
125
+ let(:klass) do
126
+ Class.new(Wayfarer::Base) do
127
+ retry_on RuntimeError, attempts: 3 do |job, error|
128
+ Spy.call(job, error)
129
+ end
130
+ end
131
+ end
132
+
133
+ before do
134
+ allow_any_instance_of(DummyJob).to receive(:perform).and_raise(RuntimeError.new)
135
+ stub_const("Spy", spy)
136
+ end
137
+
138
+ it "retries the job" do
139
+ expect(Spy).to receive(:call).exactly(:once)
140
+ .with(kind_of(DummyJob),
141
+ kind_of(RuntimeError))
142
+
143
+ DummyJob.crawl_later(url, batch: batch)
144
+
145
+ expect {
146
+ perform_enqueued_jobs
147
+ }.to change { enqueued_jobs.last["executions"] }.by(1)
148
+
149
+ expect {
150
+ perform_enqueued_jobs
151
+ }.to change { enqueued_jobs.last["executions"] }.by(1)
152
+
153
+ expect {
154
+ perform_enqueued_jobs
155
+ }.to change { enqueued_jobs.size }.by(-1)
156
+ end
157
+
158
+ it "marks the URL seen" do
159
+ task.counter.increment # otherwise barrier gets reset
160
+ DummyJob.crawl_later(url, batch: batch)
161
+ 3.times { perform_enqueued_jobs }
162
+ expect(task.barrier.seen?(task.url)).to be(true)
163
+ end
164
+
165
+ it "decrements the counter" do
166
+ 3.times { task.counter.increment }
167
+
168
+ DummyJob.crawl_later(url, batch: batch)
169
+ 3.times { perform_enqueued_jobs }
170
+
171
+ expect(task.counter.value).to be(3)
172
+ end
173
+
174
+ it "runs after batch callbacks" do
175
+ expect { |spy|
176
+ klass.after_batch(&spy)
177
+ DummyJob.crawl_later(url, batch: batch)
178
+ 3.times { perform_enqueued_jobs }
179
+ }.to yield_control
180
+ end
181
+ end
182
+
183
+ describe "Discarding" do
184
+ let(:klass) do
185
+ Class.new(Wayfarer::Base) do
186
+ discard_on RuntimeError do |job, error|
187
+ Spy.call(job, error)
188
+ end
189
+ end
190
+ end
191
+
192
+ before do
193
+ allow_any_instance_of(DummyJob).to receive(:perform).and_raise(RuntimeError.new)
194
+ stub_const("Spy", spy)
195
+ end
196
+
197
+ it "discards the job" do
198
+ expect(Spy).to receive(:call).exactly(:once)
199
+ .with(kind_of(DummyJob),
200
+ kind_of(RuntimeError))
201
+
202
+ DummyJob.crawl_later(url, batch: batch)
203
+
204
+ expect {
205
+ perform_enqueued_jobs
206
+ }.to change { enqueued_jobs.size }.by(-1)
207
+ end
208
+
209
+ it "marks the URL seen" do
210
+ task.counter.increment # otherwise barrier gets reset
211
+ DummyJob.crawl_later(url, batch: batch)
212
+ perform_enqueued_jobs
213
+ expect(task.barrier.seen?(task.url)).to be(true)
214
+ end
215
+
216
+ it "decrements the counter" do
217
+ 3.times { task.counter.increment }
218
+
219
+ DummyJob.crawl_later(url, batch: batch)
220
+ perform_enqueued_jobs
221
+
222
+ expect(task.counter.value).to be(3)
223
+ end
224
+
225
+ it "runs after batch callbacks" do
226
+ expect { |spy|
227
+ klass.after_batch(&spy)
228
+ DummyJob.crawl_later(url, batch: batch)
229
+ perform_enqueued_jobs
230
+ }.to yield_control
231
+ end
232
+ end
233
+ end
@@ -0,0 +1,102 @@
1
+ # frozen_string_literal: true
2
+
3
+ require "spec_helpers"
4
+
5
+ describe Wayfarer::Callbacks do
6
+ let(:url) { "https://alpha.com" }
7
+ let(:task) { build(:task, batch: "batch", url: url) }
8
+
9
+ let(:klass) do
10
+ Class.new(Wayfarer::Base) do
11
+ route { host "alpha.com", to: :alpha }
12
+ route { host "beta.com", to: :beta }
13
+
14
+ before_fetch do |job|
15
+ Spy.before_fetch(self, job)
16
+ end
17
+
18
+ before_fetch(except: %i[alpha beta], only: :alpha) do |job|
19
+ Spy.before_fetch_except_alpha_beta_only_alpha(self, job)
20
+ end
21
+
22
+ before_action do |job|
23
+ Spy.before_action(self, job)
24
+ end
25
+
26
+ before_action(only: :alpha) do |job|
27
+ Spy.before_action_only_alpha(self, job)
28
+ end
29
+
30
+ before_action(only: :beta) do |job|
31
+ Spy.before_action_only_beta(self, job)
32
+ end
33
+
34
+ before_action(only: %i[alpha gamma]) do |job|
35
+ Spy.before_action_only_alpha_gamma(self, job)
36
+ end
37
+
38
+ before_action(except: :alpha) do |job|
39
+ Spy.before_action_except_alpha(self, job)
40
+ end
41
+
42
+ before_action(except: %i[beta gamma]) do |job|
43
+ Spy.before_action_except_beta_gamma(self, job)
44
+ end
45
+
46
+ before_action :callback_a, only: :alpha
47
+
48
+ before_action :callback_b
49
+
50
+ before_action :callback_c, except: %i[beta]
51
+
52
+ def alpha; end
53
+
54
+ def beta; end
55
+
56
+ private
57
+
58
+ def callback_a
59
+ Spy.before_action_callback_a_only_alpha(self)
60
+ end
61
+
62
+ def callback_b
63
+ false
64
+ end
65
+
66
+ def callback_c
67
+ Spy.before_action_callback_c(self)
68
+ end
69
+ end
70
+ end
71
+
72
+ let(:job) { klass.new }
73
+
74
+ before do
75
+ stub_const("DummyJob", klass)
76
+ stub_const("Spy", spy)
77
+
78
+ allow(job).to receive(:arguments).and_return([task])
79
+ end
80
+
81
+ describe "before_fetch" do
82
+ it "fires" do
83
+ expect(Spy).to receive(:before_fetch).exactly(:once).with(job, job)
84
+ expect(Spy).not_to receive(:before_fetch_except_alpha_beta_only_alpha)
85
+ job.perform(task)
86
+ end
87
+ end
88
+
89
+ describe "before_action" do
90
+ it "fires" do
91
+ expect(Spy).to receive(:before_action).exactly(:once).with(job, job)
92
+ expect(Spy).to receive(:before_action_only_alpha).exactly(:once).with(job, job)
93
+ expect(Spy).not_to receive(:before_action_only_beta).with(job, job)
94
+ expect(Spy).to receive(:before_action_only_alpha_gamma).exactly(:once).with(job, job)
95
+ expect(Spy).not_to receive(:before_action_except_alpha).with(job, job)
96
+ expect(Spy).to receive(:before_action_except_beta_gamma).exactly(:once).with(job, job)
97
+ expect(Spy).to receive(:before_action_callback_a_only_alpha).exactly(:once).with(job)
98
+ expect(Spy).not_to receive(:before_action_callback_c).with(job)
99
+ job.perform(task)
100
+ end
101
+ end
102
+ end