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
data/spec/spec_helpers.rb CHANGED
@@ -1,62 +1,97 @@
1
1
  # frozen_string_literal: true
2
- require_relative "../lib/wayfarer"
3
-
4
- require("bundler") && Bundler.require
5
2
 
6
- include Wayfarer
7
- include Wayfarer::HTTPAdapters
8
- include Wayfarer::Routing
9
- include Wayfarer::Frontiers
3
+ require "factory_bot"
4
+ require "pry"
5
+ require "sinatra"
10
6
 
11
- if RUBY_PLATFORM == "java"
12
- Wayfarer::Frontiers::MemoryBloomfilter = \
13
- Wayfarer::Frontiers::MemoryTrieFrontier = \
14
- Wayfarer::Frontiers::RedisBloomfilter = nil
15
- end
16
-
17
- Dir["./spec/shared/**/*.rb"].sort.each { |file| require file }
7
+ require_relative "../lib/wayfarer"
8
+ require_relative "support/test_app"
18
9
 
19
10
  module SpecHelpers
20
- def jruby?
21
- RUBY_PLATFORM == "java"
11
+ def test_app_path(path)
12
+ File.join(test_app_host, path)
22
13
  end
23
14
 
24
- def test_app(path)
25
- URI("http://localhost:9876#{path}")
15
+ def test_app_host
16
+ if ENV["CI"]
17
+ "http://test:9876"
18
+ else
19
+ "http://localhost:9876"
20
+ end
26
21
  end
27
22
 
28
- def fetch_page(uri)
29
- NetHTTPAdapter.instance.fetch(URI(uri))
23
+ def redis_host
24
+ if ENV["CI"]
25
+ "redis://redis:6379"
26
+ else
27
+ "redis://localhost:6379"
28
+ end
30
29
  end
31
30
 
32
- def html_fragment(html)
33
- Nokogiri::HTML.fragment(html)
34
- end
35
-
36
- def node_set(html)
37
- html_fragment(html).css("*")
31
+ def write_file(path, contents)
32
+ FileUtils.mkdir_p(Pathname.new(path).dirname)
33
+ IO.write(path, contents)
38
34
  end
39
35
  end
40
36
 
41
37
  RSpec.configure do |config|
38
+ config.include(FactoryBot::Syntax::Methods)
39
+ config.include(ActiveJob::TestHelper)
42
40
  config.include(SpecHelpers)
43
41
 
44
- config.before do
45
- Wayfarer.config.reset!
46
- Wayfarer.config.selenium_argv = [:phantomjs]
47
- end
42
+ config.before(:suite) do
43
+ FactoryBot.find_definitions
48
44
 
49
- config.before(integration: true) do
50
- Wayfarer.logger.level = :fatal
51
- end
45
+ mutex = Mutex.new
46
+ cvar = ConditionVariable.new
47
+
48
+ Thread.new do
49
+ Rack::Handler::WEBrick.run(TestApp,
50
+ Host: "0.0.0.0",
51
+ Port: 9876,
52
+ Logger: WEBrick::Log.new("/dev/null"),
53
+ AccessLog: [],
54
+ StartCallback: proc { cvar.signal })
55
+ end
52
56
 
53
- config.after(integration: true) do
54
- Wayfarer.logger.level = :debug
57
+ mutex.lock
58
+ cvar.wait(mutex)
55
59
  end
56
60
 
57
- config.before(mri_only: true) do
58
- skip("Not supported on JRuby") and fail if RUBY_PLATFORM == "java"
61
+ config.before do
62
+ Wayfarer.config = Wayfarer::Config::Root.new
63
+ Wayfarer.config.redis.url = redis_host
64
+
65
+ ::Redis.new(url: redis_host).flushall
66
+
67
+ ActiveJob::Base.queue_adapter = :test
68
+ ActiveJob::Base.logger = Logger.new(nil)
69
+ ActiveJob::Base.queue_adapter.enqueued_jobs.clear
70
+ ActiveJob::Base.queue_adapter.performed_jobs.clear
71
+
72
+ if ENV["CI"]
73
+ # For unknown reasons, Wayfarer::Networking::Ferrum#renew can take a very
74
+ # long time to instantiate a new ::Ferrum::Browser and requires the 60s
75
+ # timeout. TODO: Figure out what's going on
76
+ Wayfarer.config.ferrum.options = { url: "http://chrome:3000", timeout: 120 }
77
+ Wayfarer.config.selenium.driver = :firefox
78
+ Wayfarer.config.selenium.options = { url: "http://firefox:4444" }
79
+ Wayfarer.config.selenium.client_timeout = 10
80
+ end
81
+
82
+ # TODO: Undo side-effect
83
+ Capybara.register_driver(:cuprite) do |app|
84
+ Capybara::Cuprite::Driver.new(app, Wayfarer.config.ferrum.options)
85
+ end
86
+ Wayfarer.config.capybara.driver = :cuprite
59
87
  end
60
88
 
61
- config.alias_example_to :they
89
+ config.around(cli: true) do |example|
90
+ origin = Dir.pwd
91
+ tmp = Dir.mktmpdir
92
+ Dir.chdir(tmp)
93
+ example.run
94
+ Dir.chdir(origin)
95
+ FileUtils.rm_r(tmp)
96
+ end
62
97
  end
@@ -0,0 +1,23 @@
1
+ # frozen_string_literal: true
2
+
3
+ require "spec_helpers"
4
+
5
+ describe Wayfarer::Stringify do
6
+ let(:klass) do
7
+ Class.new(Struct.new(:a, :b, :c, :d)) do
8
+ include Wayfarer::Stringify
9
+
10
+ stringify :a, :c, :d
11
+ end
12
+ end
13
+
14
+ subject(:instance) { klass.new(1, 2.0, :three, "four") }
15
+
16
+ before { stub_const("Foobar", klass) }
17
+
18
+ describe "#to_s" do
19
+ it "returns the expected string" do
20
+ expect(instance.to_s).to eq('#<Foobar a=1, c=:three, d="four">')
21
+ end
22
+ end
23
+ end
File without changes
File without changes
File without changes
File without changes
File without changes
@@ -1,5 +1,4 @@
1
1
  # frozen_string_literal: true
2
- require "sinatra"
3
2
 
4
3
  class TestApp < Sinatra::Base
5
4
  set :root, File.dirname(__FILE__)
@@ -9,11 +8,19 @@ class TestApp < Sinatra::Base
9
8
  status params[:code]
10
9
  end
11
10
 
11
+ get "/headers/:header" do
12
+ request.env[params[:header]]
13
+ end
14
+
12
15
  get "/hello_world" do
13
16
  headers "hello" => "world"
14
17
  "Hello world!"
15
18
  end
16
19
 
20
+ get "/body/:content" do
21
+ params[:content]
22
+ end
23
+
17
24
  get "/redirect_loop" do
18
25
  redirect to "/redirect_loop"
19
26
  end
@@ -37,7 +44,7 @@ class TestApp < Sinatra::Base
37
44
  send_file(static_file("xml/#{params[:file]}"))
38
45
  end
39
46
 
40
- private
47
+ private
41
48
 
42
49
  def static_file(file_path)
43
50
  File.expand_path(file_path, settings.public_folder)
data/spec/task_spec.rb ADDED
@@ -0,0 +1,27 @@
1
+ # frozen_string_literal: true
2
+
3
+ require "spec_helpers"
4
+
5
+ describe Wayfarer::Task do
6
+ subject(:task) { build(:task) }
7
+
8
+ describe "#metadata" do
9
+ it "returns an OpenStruct" do
10
+ expect(task.metadata).to be_an(OpenStruct)
11
+ end
12
+ end
13
+
14
+ describe "#barrier" do
15
+ it "returns its batch barrier" do
16
+ expect(task.barrier).to be_a(Wayfarer::Redis::Barrier)
17
+ expect(task.barrier.batch).to eq(task.batch)
18
+ end
19
+ end
20
+
21
+ describe "#counter" do
22
+ it "returns its batch counter" do
23
+ expect(task.counter).to be_a(Wayfarer::Redis::Counter)
24
+ expect(task.counter.batch).to eq(task.batch)
25
+ end
26
+ end
27
+ end
@@ -1,4 +1,5 @@
1
1
  # frozen_string_literal: true
2
+
2
3
  require "spec_helpers"
3
4
 
4
5
  describe Wayfarer do
@@ -6,19 +7,7 @@ describe Wayfarer do
6
7
  it("is present") { expect(defined? Wayfarer::VERSION).not_to be nil }
7
8
  end
8
9
 
9
- describe "::logger, ::logger=" do
10
- it "returns and alters the logger" do
11
- expect(Wayfarer.logger).to be_a Logger
12
- end
13
- end
14
-
15
10
  describe "::config" do
16
- it "alters keys and values" do
17
- Wayfarer.config.foo = :bar
18
- expect(Wayfarer.config.foo).to be :bar
19
-
20
- Wayfarer.config { |config| config.baz = :qux }
21
- expect(Wayfarer.config.baz).to be :qux
22
- end
11
+ it("returns a config") { expect(Wayfarer.config).to be_a(Wayfarer::Config::Root) }
23
12
  end
24
13
  end
data/wayfarer.gemspec CHANGED
@@ -1,53 +1,51 @@
1
1
  # frozen_string_literal: true
2
+
2
3
  Gem::Specification.new do |s|
3
- s.name = "wayfarer"
4
- s.version = "0.0.3"
5
- s.license = "MIT"
4
+ s.name = "wayfarer"
5
+ s.version = "0.4.3"
6
+ s.license = "MIT"
6
7
 
7
- s.homepage = "http://github.com/bauerd/wayfarer"
8
- s.description = "Versatile web crawling with Ruby"
9
- s.summary = s.description
8
+ s.homepage = "http://github.com/bauerd/wayfarer"
9
+ s.summary = "Versatile web crawling with Ruby"
10
+ s.description = "Web crawling framework based on ActiveJob"
10
11
 
11
- s.date = "2017-05-31"
12
- s.authors = ["Dominic Bauer"]
13
- s.email = "bauerdominic@gmail.com"
12
+ s.date = "2021-09-26"
13
+ s.authors = ["Dominic Bauer"]
14
+ s.email = "mail@bauerd.com"
14
15
 
15
- s.files = `git ls-files`.split("\n")
16
- s.test_files = `git ls-files -- {spec}/*`.split("\n")
16
+ s.files = `git ls-files`.split("\n")
17
+ s.test_files = `git ls-files -- {spec}/*`.split("\n")
17
18
 
18
19
  s.require_paths = ["lib"]
19
20
 
20
21
  s.executables << "wayfarer"
21
22
 
22
- s.add_runtime_dependency "connection_pool", "~> 2.2"
23
- s.add_runtime_dependency "nokogiri", "~> 1.6"
24
- s.add_runtime_dependency "selenium-webdriver", "~> 3.4"
25
- s.add_runtime_dependency "selenium-emulated_features", "2.0.1"
26
- s.add_runtime_dependency "net-http-persistent", "~> 2.9"
27
- s.add_runtime_dependency "mime-types", "~> 2.6"
28
- s.add_runtime_dependency "pismo", "~> 0.7"
29
- s.add_runtime_dependency "mustermann", "~> 0.4"
30
- s.add_runtime_dependency "activejob", "~> 4.2"
31
- s.add_runtime_dependency "thor", "~> 0.19"
32
- s.add_runtime_dependency "activesupport", "~> 4.2"
33
- s.add_runtime_dependency "capybara", "~> 2.5"
34
- s.add_runtime_dependency "chronic", "~> 0.10"
35
- s.add_runtime_dependency "redis", "~> 3.2"
36
- s.add_runtime_dependency "concurrent-ruby", "~> 1.0"
37
- s.add_runtime_dependency "hooks", "~> 0.4"
38
- s.add_runtime_dependency "bloomfilter-rb", "~> 2.1"
39
- s.add_runtime_dependency "oj", "~> 2.12"
40
- s.add_runtime_dependency "fast_trie", "~> 0.5"
41
- s.add_runtime_dependency "parallel", "~> 1.11"
42
- s.add_runtime_dependency "normalize_url", "~> 0.0.6"
43
-
44
- s.add_development_dependency "pry", "~> 0.10"
45
- s.add_development_dependency "rake", "~> 10.4"
46
- s.add_development_dependency "rspec", "~> 3.3"
47
- s.add_development_dependency "sinatra", "~> 1.4"
48
- s.add_development_dependency "rubocop", "~> 0.34"
49
- s.add_development_dependency "yard", "~> 0.9"
50
- s.add_development_dependency "bourbon", "~> 4.3"
51
- s.add_development_dependency "neat", "~> 1.8"
52
- s.add_development_dependency "faker", "~> 1.7"
23
+ s.required_ruby_version = "~> 2.7"
24
+
25
+ s.add_runtime_dependency "activejob", ">= 6.0"
26
+ s.add_runtime_dependency "addressable", "~> 2.8"
27
+ s.add_runtime_dependency "capybara", "~> 3.0"
28
+ s.add_runtime_dependency "connection_pool", "~> 2.2"
29
+ s.add_runtime_dependency "docile", "~> 1.1"
30
+ s.add_runtime_dependency "ferrum", "~> 0.9"
31
+ s.add_runtime_dependency "metainspector", "~> 5.0"
32
+ s.add_runtime_dependency "mime-types", "~> 3.0"
33
+ s.add_runtime_dependency "mustermann", "~> 1.1"
34
+ s.add_runtime_dependency "mock_redis", "~> 0.29"
35
+ s.add_runtime_dependency "net-http-persistent", "~> 3.0"
36
+ s.add_runtime_dependency "nokogiri", "~> 1.11"
37
+ s.add_runtime_dependency "normalize_url", "~> 0.0.6"
38
+ s.add_runtime_dependency "redis", "~> 4.4", "< 4.5" # redis 4.5.x broke SMISMEMBER
39
+ s.add_runtime_dependency "selenium-webdriver", "~> 3.4"
40
+ s.add_runtime_dependency "thor", "~> 1.0"
41
+
42
+ s.add_development_dependency "cuprite", "~> 0.13"
43
+ s.add_development_dependency "factory_bot", "~> 6.0"
44
+ s.add_development_dependency "faker", "~> 1.7"
45
+ s.add_development_dependency "pry", "~> 0.10"
46
+ s.add_development_dependency "rake", "~> 10.4"
47
+ s.add_development_dependency "rspec", "~> 3.4"
48
+ s.add_development_dependency "rubocop", "~> 0.49"
49
+ s.add_development_dependency "sinatra", "~> 1.4"
50
+ s.add_development_dependency "yard", "~> 0.9"
53
51
  end