wayfarer 0.0.3 → 0.4.0

Sign up to get free protection for your applications and to get access to all the features.
Files changed (339) 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 +212 -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/querying_html.md +42 -0
  14. data/docs/cookbook/screenshots.md +27 -0
  15. data/docs/cookbook/user_agent.md +7 -0
  16. data/docs/guides/browser_automation/capybara.md +3 -0
  17. data/docs/guides/browser_automation/ferrum.md +37 -0
  18. data/docs/guides/browser_automation/selenium.md +59 -0
  19. data/docs/guides/callbacks.md +27 -34
  20. data/docs/guides/configuration.md +20 -171
  21. data/docs/guides/error_handling.md +18 -33
  22. data/docs/guides/jobs.md +75 -0
  23. data/docs/guides/networking.md +20 -0
  24. data/docs/guides/pages.md +52 -0
  25. data/docs/guides/performance.md +22 -0
  26. data/docs/guides/tasks.md +38 -0
  27. data/docs/index.md +34 -68
  28. data/docs/reference/api/base.md +162 -0
  29. data/docs/reference/api/route.md +182 -0
  30. data/docs/reference/cli.md +139 -0
  31. data/docs/reference/environment_variables.md +85 -0
  32. data/lib/wayfarer/base.rb +60 -0
  33. data/lib/wayfarer/cli/base.rb +23 -0
  34. data/lib/wayfarer/cli/generate.rb +17 -0
  35. data/lib/wayfarer/cli/job.rb +58 -0
  36. data/lib/wayfarer/cli/route.rb +27 -0
  37. data/lib/wayfarer/cli/route_printer.rb +116 -0
  38. data/lib/wayfarer/cli/runner.rb +34 -0
  39. data/lib/wayfarer/cli/templates/Gemfile.tt +5 -0
  40. data/lib/wayfarer/cli/templates/job.rb.tt +8 -0
  41. data/lib/wayfarer/config.rb +67 -0
  42. data/lib/wayfarer/gc.rb +19 -0
  43. data/lib/wayfarer/middleware/chain.rb +19 -0
  44. data/lib/wayfarer/middleware/dedup.rb +25 -0
  45. data/lib/wayfarer/middleware/fetch.rb +32 -0
  46. data/lib/wayfarer/middleware/normalize.rb +25 -0
  47. data/lib/wayfarer/middleware/router.rb +21 -0
  48. data/lib/wayfarer/middleware/stage.rb +23 -0
  49. data/lib/wayfarer/middleware/worker.rb +47 -0
  50. data/lib/wayfarer/networking/ferrum.rb +70 -0
  51. data/lib/wayfarer/networking/healer.rb +21 -0
  52. data/lib/wayfarer/networking/net_http.rb +52 -0
  53. data/lib/wayfarer/networking/pool.rb +34 -0
  54. data/lib/wayfarer/networking/result.rb +18 -0
  55. data/lib/wayfarer/networking/selenium.rb +70 -0
  56. data/lib/wayfarer/page.rb +15 -71
  57. data/lib/wayfarer/parsing/json.rb +17 -0
  58. data/lib/wayfarer/parsing/xml.rb +17 -0
  59. data/lib/wayfarer/redis/barrier.rb +36 -0
  60. data/lib/wayfarer/redis/connection.rb +13 -0
  61. data/lib/wayfarer/redis/counter.rb +29 -0
  62. data/lib/wayfarer/redis/pool.rb +18 -0
  63. data/lib/wayfarer/redis/version.rb +19 -0
  64. data/lib/wayfarer/routing/custom_matcher.rb +21 -0
  65. data/lib/wayfarer/routing/dsl.rb +57 -0
  66. data/lib/wayfarer/routing/host_matcher.rb +23 -0
  67. data/lib/wayfarer/routing/path_finder.rb +46 -0
  68. data/lib/wayfarer/routing/path_matcher.rb +46 -0
  69. data/lib/wayfarer/routing/{query_rule.rb → query_matcher.rb} +24 -16
  70. data/lib/wayfarer/routing/result.rb +15 -0
  71. data/lib/wayfarer/routing/root_route.rb +7 -0
  72. data/lib/wayfarer/routing/route.rb +41 -0
  73. data/lib/wayfarer/routing/scheme_matcher.rb +21 -0
  74. data/lib/wayfarer/routing/suffix_matcher.rb +21 -0
  75. data/lib/wayfarer/routing/target_route.rb +7 -0
  76. data/lib/wayfarer/routing/url_matcher.rb +21 -0
  77. data/lib/wayfarer/serializer.rb +17 -0
  78. data/lib/wayfarer/stringify.rb +41 -0
  79. data/lib/wayfarer/task.rb +34 -0
  80. data/lib/wayfarer.rb +47 -58
  81. data/mkdocs.yml +47 -0
  82. data/requirements.txt +1 -0
  83. data/spec/base_spec.rb +219 -0
  84. data/spec/cli/generate_spec.rb +39 -0
  85. data/spec/cli/job_spec.rb +74 -0
  86. data/spec/cli/version_spec.rb +13 -0
  87. data/spec/config_spec.rb +144 -0
  88. data/spec/factories/queue/chain.rb +11 -0
  89. data/spec/factories/queue/middleware.rb +15 -0
  90. data/spec/factories/queue/page.rb +78 -0
  91. data/spec/factories/queue/task.rb +12 -0
  92. data/spec/fixtures/dummy_job.rb +7 -0
  93. data/spec/gc_spec.rb +61 -0
  94. data/spec/middleware/chain_spec.rb +96 -0
  95. data/spec/middleware/dedup_spec.rb +76 -0
  96. data/spec/middleware/fetch_spec.rb +72 -0
  97. data/spec/middleware/normalize_spec.rb +28 -0
  98. data/spec/middleware/router_spec.rb +46 -0
  99. data/spec/middleware/stage_spec.rb +39 -0
  100. data/spec/middleware/worker_spec.rb +90 -0
  101. data/spec/networking/adapter.rb +135 -0
  102. data/spec/networking/ferrum_spec.rb +28 -0
  103. data/spec/networking/healer_spec.rb +46 -0
  104. data/spec/networking/net_http_spec.rb +37 -0
  105. data/spec/networking/pool_spec.rb +42 -0
  106. data/spec/networking/selenium_spec.rb +28 -0
  107. data/spec/page_spec.rb +21 -12
  108. data/spec/{parsers/json_parser_spec.rb → parsing/json_spec.rb} +5 -4
  109. data/spec/{parsers/xml_parser_spec.rb → parsing/xml_spec.rb} +3 -2
  110. data/spec/redis/barrier_spec.rb +78 -0
  111. data/spec/redis/counter_spec.rb +32 -0
  112. data/spec/redis/pool_spec.rb +18 -0
  113. data/spec/redis/version_spec.rb +13 -0
  114. data/spec/routing/custom_matcher_spec.rb +31 -0
  115. data/spec/routing/dsl_spec.rb +98 -0
  116. data/spec/routing/host_matcher_spec.rb +49 -0
  117. data/spec/routing/integration_spec.rb +110 -0
  118. data/spec/routing/path_finder_spec.rb +33 -0
  119. data/spec/routing/path_matcher_spec.rb +43 -0
  120. data/spec/routing/{query_rule_spec.rb → query_matcher_spec.rb} +39 -26
  121. data/spec/routing/root_route_spec.rb +29 -0
  122. data/spec/routing/route_spec.rb +43 -0
  123. data/spec/routing/scheme_matcher_spec.rb +25 -0
  124. data/spec/routing/{filetypes_rule_spec.rb → suffix_matcher_spec.rb} +14 -13
  125. data/spec/routing/uri_matcher_spec.rb +27 -0
  126. data/spec/spec_helpers.rb +65 -38
  127. data/spec/stringify_spec.rb +23 -0
  128. data/{support → spec/support}/static/finders.html +0 -0
  129. data/{support → spec/support}/static/graph/details/a.html +0 -0
  130. data/{support → spec/support}/static/graph/details/b.html +0 -0
  131. data/{support → spec/support}/static/graph/index.html +0 -0
  132. data/{support → spec/support}/static/json/dummy.json +0 -0
  133. data/{support → spec/support}/static/links/links.html +0 -0
  134. data/{support → spec/support}/static/xml/dummy.xml +0 -0
  135. data/{support → spec/support}/test_app.rb +9 -2
  136. data/spec/task_spec.rb +27 -0
  137. data/spec/wayfarer_spec.rb +2 -13
  138. data/wayfarer.gemspec +39 -42
  139. metadata +191 -368
  140. data/.travis.yml +0 -5
  141. data/Changelog.md +0 -10
  142. data/README.md +0 -21
  143. data/benchmark/frontiers.rb +0 -143
  144. data/docs/.gitignore +0 -2
  145. data/docs/_config.yml +0 -15
  146. data/docs/_includes/base.html +0 -7
  147. data/docs/_includes/head.html +0 -10
  148. data/docs/_includes/navigation.html +0 -187
  149. data/docs/_layouts/default.html +0 -42
  150. data/docs/_sass/base.scss +0 -439
  151. data/docs/_sass/variables.scss +0 -24
  152. data/docs/_sass/vendor/bourbon/_bourbon-deprecate.scss +0 -19
  153. data/docs/_sass/vendor/bourbon/_bourbon-deprecated-upcoming.scss +0 -425
  154. data/docs/_sass/vendor/bourbon/_bourbon.scss +0 -90
  155. data/docs/_sass/vendor/bourbon/addons/_border-color.scss +0 -29
  156. data/docs/_sass/vendor/bourbon/addons/_border-radius.scss +0 -48
  157. data/docs/_sass/vendor/bourbon/addons/_border-style.scss +0 -28
  158. data/docs/_sass/vendor/bourbon/addons/_border-width.scss +0 -28
  159. data/docs/_sass/vendor/bourbon/addons/_buttons.scss +0 -69
  160. data/docs/_sass/vendor/bourbon/addons/_clearfix.scss +0 -25
  161. data/docs/_sass/vendor/bourbon/addons/_ellipsis.scss +0 -30
  162. data/docs/_sass/vendor/bourbon/addons/_font-stacks.scss +0 -31
  163. data/docs/_sass/vendor/bourbon/addons/_hide-text.scss +0 -27
  164. data/docs/_sass/vendor/bourbon/addons/_margin.scss +0 -29
  165. data/docs/_sass/vendor/bourbon/addons/_padding.scss +0 -29
  166. data/docs/_sass/vendor/bourbon/addons/_position.scss +0 -51
  167. data/docs/_sass/vendor/bourbon/addons/_prefixer.scss +0 -66
  168. data/docs/_sass/vendor/bourbon/addons/_retina-image.scss +0 -27
  169. data/docs/_sass/vendor/bourbon/addons/_size.scss +0 -56
  170. data/docs/_sass/vendor/bourbon/addons/_text-inputs.scss +0 -118
  171. data/docs/_sass/vendor/bourbon/addons/_timing-functions.scss +0 -34
  172. data/docs/_sass/vendor/bourbon/addons/_triangle.scss +0 -63
  173. data/docs/_sass/vendor/bourbon/addons/_word-wrap.scss +0 -29
  174. data/docs/_sass/vendor/bourbon/css3/_animation.scss +0 -61
  175. data/docs/_sass/vendor/bourbon/css3/_appearance.scss +0 -5
  176. data/docs/_sass/vendor/bourbon/css3/_backface-visibility.scss +0 -5
  177. data/docs/_sass/vendor/bourbon/css3/_background-image.scss +0 -44
  178. data/docs/_sass/vendor/bourbon/css3/_background.scss +0 -57
  179. data/docs/_sass/vendor/bourbon/css3/_border-image.scss +0 -61
  180. data/docs/_sass/vendor/bourbon/css3/_calc.scss +0 -6
  181. data/docs/_sass/vendor/bourbon/css3/_columns.scss +0 -67
  182. data/docs/_sass/vendor/bourbon/css3/_filter.scss +0 -6
  183. data/docs/_sass/vendor/bourbon/css3/_flex-box.scss +0 -327
  184. data/docs/_sass/vendor/bourbon/css3/_font-face.scss +0 -29
  185. data/docs/_sass/vendor/bourbon/css3/_font-feature-settings.scss +0 -6
  186. data/docs/_sass/vendor/bourbon/css3/_hidpi-media-query.scss +0 -12
  187. data/docs/_sass/vendor/bourbon/css3/_hyphens.scss +0 -6
  188. data/docs/_sass/vendor/bourbon/css3/_image-rendering.scss +0 -15
  189. data/docs/_sass/vendor/bourbon/css3/_keyframes.scss +0 -38
  190. data/docs/_sass/vendor/bourbon/css3/_linear-gradient.scss +0 -40
  191. data/docs/_sass/vendor/bourbon/css3/_perspective.scss +0 -12
  192. data/docs/_sass/vendor/bourbon/css3/_placeholder.scss +0 -10
  193. data/docs/_sass/vendor/bourbon/css3/_radial-gradient.scss +0 -40
  194. data/docs/_sass/vendor/bourbon/css3/_selection.scss +0 -44
  195. data/docs/_sass/vendor/bourbon/css3/_text-decoration.scss +0 -27
  196. data/docs/_sass/vendor/bourbon/css3/_transform.scss +0 -21
  197. data/docs/_sass/vendor/bourbon/css3/_transition.scss +0 -81
  198. data/docs/_sass/vendor/bourbon/css3/_user-select.scss +0 -5
  199. data/docs/_sass/vendor/bourbon/functions/_assign-inputs.scss +0 -16
  200. data/docs/_sass/vendor/bourbon/functions/_contains-falsy.scss +0 -25
  201. data/docs/_sass/vendor/bourbon/functions/_contains.scss +0 -31
  202. data/docs/_sass/vendor/bourbon/functions/_is-length.scss +0 -16
  203. data/docs/_sass/vendor/bourbon/functions/_is-light.scss +0 -26
  204. data/docs/_sass/vendor/bourbon/functions/_is-number.scss +0 -16
  205. data/docs/_sass/vendor/bourbon/functions/_is-size.scss +0 -23
  206. data/docs/_sass/vendor/bourbon/functions/_modular-scale.scss +0 -74
  207. data/docs/_sass/vendor/bourbon/functions/_px-to-em.scss +0 -24
  208. data/docs/_sass/vendor/bourbon/functions/_px-to-rem.scss +0 -26
  209. data/docs/_sass/vendor/bourbon/functions/_shade.scss +0 -24
  210. data/docs/_sass/vendor/bourbon/functions/_strip-units.scss +0 -22
  211. data/docs/_sass/vendor/bourbon/functions/_tint.scss +0 -24
  212. data/docs/_sass/vendor/bourbon/functions/_transition-property-name.scss +0 -37
  213. data/docs/_sass/vendor/bourbon/functions/_unpack.scss +0 -32
  214. data/docs/_sass/vendor/bourbon/helpers/_convert-units.scss +0 -26
  215. data/docs/_sass/vendor/bourbon/helpers/_directional-values.scss +0 -108
  216. data/docs/_sass/vendor/bourbon/helpers/_font-source-declaration.scss +0 -53
  217. data/docs/_sass/vendor/bourbon/helpers/_gradient-positions-parser.scss +0 -24
  218. data/docs/_sass/vendor/bourbon/helpers/_linear-angle-parser.scss +0 -35
  219. data/docs/_sass/vendor/bourbon/helpers/_linear-gradient-parser.scss +0 -51
  220. data/docs/_sass/vendor/bourbon/helpers/_linear-positions-parser.scss +0 -77
  221. data/docs/_sass/vendor/bourbon/helpers/_linear-side-corner-parser.scss +0 -41
  222. data/docs/_sass/vendor/bourbon/helpers/_radial-arg-parser.scss +0 -74
  223. data/docs/_sass/vendor/bourbon/helpers/_radial-gradient-parser.scss +0 -55
  224. data/docs/_sass/vendor/bourbon/helpers/_radial-positions-parser.scss +0 -28
  225. data/docs/_sass/vendor/bourbon/helpers/_render-gradients.scss +0 -31
  226. data/docs/_sass/vendor/bourbon/helpers/_shape-size-stripper.scss +0 -15
  227. data/docs/_sass/vendor/bourbon/helpers/_str-to-num.scss +0 -55
  228. data/docs/_sass/vendor/bourbon/settings/_asset-pipeline.scss +0 -7
  229. data/docs/_sass/vendor/bourbon/settings/_deprecation-warnings.scss +0 -8
  230. data/docs/_sass/vendor/bourbon/settings/_prefixer.scss +0 -9
  231. data/docs/_sass/vendor/bourbon/settings/_px-to-em.scss +0 -1
  232. data/docs/_sass/vendor/neat/_neat-helpers.scss +0 -11
  233. data/docs/_sass/vendor/neat/_neat.scss +0 -23
  234. data/docs/_sass/vendor/neat/functions/_new-breakpoint.scss +0 -49
  235. data/docs/_sass/vendor/neat/functions/_private.scss +0 -114
  236. data/docs/_sass/vendor/neat/grid/_box-sizing.scss +0 -15
  237. data/docs/_sass/vendor/neat/grid/_direction-context.scss +0 -33
  238. data/docs/_sass/vendor/neat/grid/_display-context.scss +0 -28
  239. data/docs/_sass/vendor/neat/grid/_fill-parent.scss +0 -22
  240. data/docs/_sass/vendor/neat/grid/_media.scss +0 -92
  241. data/docs/_sass/vendor/neat/grid/_omega.scss +0 -87
  242. data/docs/_sass/vendor/neat/grid/_outer-container.scss +0 -34
  243. data/docs/_sass/vendor/neat/grid/_pad.scss +0 -25
  244. data/docs/_sass/vendor/neat/grid/_private.scss +0 -35
  245. data/docs/_sass/vendor/neat/grid/_row.scss +0 -52
  246. data/docs/_sass/vendor/neat/grid/_shift.scss +0 -50
  247. data/docs/_sass/vendor/neat/grid/_span-columns.scss +0 -94
  248. data/docs/_sass/vendor/neat/grid/_to-deprecate.scss +0 -97
  249. data/docs/_sass/vendor/neat/grid/_visual-grid.scss +0 -42
  250. data/docs/_sass/vendor/neat/mixins/_clearfix.scss +0 -25
  251. data/docs/_sass/vendor/neat/settings/_disable-warnings.scss +0 -13
  252. data/docs/_sass/vendor/neat/settings/_grid.scss +0 -51
  253. data/docs/_sass/vendor/neat/settings/_visual-grid.scss +0 -27
  254. data/docs/_sass/vendor/normalize-3.0.2.scss +0 -427
  255. data/docs/_sass/vendor/pygments.scss +0 -356
  256. data/docs/automating_browsers/capybara.md +0 -70
  257. data/docs/css/screen.scss +0 -7
  258. data/docs/guides/cli.md +0 -52
  259. data/docs/guides/frontiers.md +0 -93
  260. data/docs/guides/halting.md +0 -23
  261. data/docs/guides/job_queues.md +0 -26
  262. data/docs/guides/locals.md +0 -36
  263. data/docs/guides/logging.md +0 -22
  264. data/docs/guides/page_objects.md +0 -67
  265. data/docs/guides/peeking.md +0 -46
  266. data/docs/guides/selenium_capybara.md +0 -100
  267. data/docs/guides/tutorial.md +0 -452
  268. data/docs/js/navigation.js +0 -11
  269. data/docs/misc/contributing.md +0 -20
  270. data/docs/misc/testing.md +0 -11
  271. data/docs/recipes/authentication.md +0 -23
  272. data/docs/recipes/csv.md +0 -29
  273. data/docs/recipes/javascript.md +0 -20
  274. data/docs/recipes/multiple_uris.md +0 -18
  275. data/docs/recipes/screenshots.md +0 -20
  276. data/docs/routing/custom_rules.md +0 -16
  277. data/docs/routing/filetypes_rules.md +0 -21
  278. data/docs/routing/host_rules.md +0 -24
  279. data/docs/routing/path_rules.md +0 -33
  280. data/docs/routing/protocol_rules.md +0 -17
  281. data/docs/routing/query_rules.md +0 -69
  282. data/docs/routing/routes.md +0 -96
  283. data/docs/routing/uri_rules.md +0 -18
  284. data/examples/collect_github_issues.rb +0 -65
  285. data/examples/find_foobar_on_wikipedia.rb +0 -23
  286. data/lib/wayfarer/configuration.rb +0 -86
  287. data/lib/wayfarer/crawl.rb +0 -79
  288. data/lib/wayfarer/crawl_observer.rb +0 -103
  289. data/lib/wayfarer/dispatcher.rb +0 -104
  290. data/lib/wayfarer/finders.rb +0 -61
  291. data/lib/wayfarer/frontiers/frontier.rb +0 -79
  292. data/lib/wayfarer/frontiers/memory_bloomfilter.rb +0 -32
  293. data/lib/wayfarer/frontiers/memory_frontier.rb +0 -76
  294. data/lib/wayfarer/frontiers/memory_trie_frontier.rb +0 -39
  295. data/lib/wayfarer/frontiers/normalize_uris.rb +0 -48
  296. data/lib/wayfarer/frontiers/redis_bloomfilter.rb +0 -34
  297. data/lib/wayfarer/frontiers/redis_frontier.rb +0 -83
  298. data/lib/wayfarer/http_adapters/adapter_pool.rb +0 -62
  299. data/lib/wayfarer/http_adapters/net_http_adapter.rb +0 -77
  300. data/lib/wayfarer/http_adapters/selenium_adapter.rb +0 -80
  301. data/lib/wayfarer/job.rb +0 -211
  302. data/lib/wayfarer/locals.rb +0 -40
  303. data/lib/wayfarer/parsers/json_parser.rb +0 -20
  304. data/lib/wayfarer/parsers/xml_parser.rb +0 -27
  305. data/lib/wayfarer/processor.rb +0 -103
  306. data/lib/wayfarer/routing/custom_rule.rb +0 -21
  307. data/lib/wayfarer/routing/filetypes_rule.rb +0 -20
  308. data/lib/wayfarer/routing/host_rule.rb +0 -19
  309. data/lib/wayfarer/routing/path_rule.rb +0 -54
  310. data/lib/wayfarer/routing/protocol_rule.rb +0 -21
  311. data/lib/wayfarer/routing/router.rb +0 -71
  312. data/lib/wayfarer/routing/rule.rb +0 -114
  313. data/lib/wayfarer/routing/uri_rule.rb +0 -21
  314. data/spec/configuration_spec.rb +0 -26
  315. data/spec/crawl_spec.rb +0 -48
  316. data/spec/finders_spec.rb +0 -49
  317. data/spec/frontiers/memory_bloomfilter_spec.rb +0 -6
  318. data/spec/frontiers/memory_frontier_spec.rb +0 -6
  319. data/spec/frontiers/memory_trie_frontier_spec.rb +0 -6
  320. data/spec/frontiers/normalize_uris_spec.rb +0 -59
  321. data/spec/frontiers/redis_bloomfilter_spec.rb +0 -6
  322. data/spec/frontiers/redis_frontier_spec.rb +0 -6
  323. data/spec/http_adapters/adapter_pool_spec.rb +0 -33
  324. data/spec/http_adapters/net_http_adapter_spec.rb +0 -83
  325. data/spec/http_adapters/selenium_adapter_spec.rb +0 -53
  326. data/spec/integration/callbacks_spec.rb +0 -42
  327. data/spec/integration/locals_spec.rb +0 -106
  328. data/spec/integration/peeking_spec.rb +0 -61
  329. data/spec/job_spec.rb +0 -122
  330. data/spec/processor_spec.rb +0 -31
  331. data/spec/routing/custom_rule_spec.rb +0 -26
  332. data/spec/routing/host_rule_spec.rb +0 -48
  333. data/spec/routing/path_rule_spec.rb +0 -66
  334. data/spec/routing/protocol_rule_spec.rb +0 -26
  335. data/spec/routing/router_spec.rb +0 -67
  336. data/spec/routing/rule_spec.rb +0 -251
  337. data/spec/routing/uri_rule_spec.rb +0 -24
  338. data/spec/shared/frontier.rb +0 -96
  339. data/wayfarer-jruby.gemspec +0 -49
data/spec/base_spec.rb ADDED
@@ -0,0 +1,219 @@
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 "decrements the counter" do
159
+ 3.times { task.counter.increment }
160
+
161
+ DummyJob.crawl_later(url, batch: batch)
162
+ 3.times { perform_enqueued_jobs }
163
+
164
+ expect(task.counter.value).to be(3)
165
+ end
166
+
167
+ it "runs after batch callbacks" do
168
+ expect { |spy|
169
+ klass.after_batch(&spy)
170
+ DummyJob.crawl_later(url, batch: batch)
171
+ 3.times { perform_enqueued_jobs }
172
+ }.to yield_control
173
+ end
174
+ end
175
+
176
+ describe "Discarding" do
177
+ let(:klass) do
178
+ Class.new(Wayfarer::Base) do
179
+ discard_on RuntimeError do |job, error|
180
+ Spy.call(job, error)
181
+ end
182
+ end
183
+ end
184
+
185
+ before do
186
+ allow_any_instance_of(DummyJob).to receive(:perform).and_raise(RuntimeError.new)
187
+ stub_const("Spy", spy)
188
+ end
189
+
190
+ it "discards the job" do
191
+ expect(Spy).to receive(:call).exactly(:once)
192
+ .with(kind_of(DummyJob),
193
+ kind_of(RuntimeError))
194
+
195
+ DummyJob.crawl_later(url, batch: batch)
196
+
197
+ expect {
198
+ perform_enqueued_jobs
199
+ }.to change { enqueued_jobs.size }.by(-1)
200
+ end
201
+
202
+ it "decrements the counter" do
203
+ 3.times { task.counter.increment }
204
+
205
+ DummyJob.crawl_later(url, batch: batch)
206
+ perform_enqueued_jobs
207
+
208
+ expect(task.counter.value).to be(3)
209
+ end
210
+
211
+ it "runs after batch callbacks" do
212
+ expect { |spy|
213
+ klass.after_batch(&spy)
214
+ DummyJob.crawl_later(url, batch: batch)
215
+ perform_enqueued_jobs
216
+ }.to yield_control
217
+ end
218
+ end
219
+ end
@@ -0,0 +1,39 @@
1
+ # frozen_string_literal: true
2
+
3
+ require "spec_helpers"
4
+
5
+ describe Wayfarer::CLI::Generate, cli: true do
6
+ subject(:cli) { Wayfarer::CLI::Runner }
7
+
8
+ describe "generate project" do
9
+ it "outputs" do
10
+ expected_output = <<-OUT
11
+ create foobar
12
+ create foobar/Gemfile
13
+ create foobar/app/jobs/foobar.rb
14
+ OUT
15
+
16
+ expect {
17
+ cli.start(%w[generate project foobar])
18
+ }.to output(expected_output).to_stdout
19
+ end
20
+
21
+ it "creates the project directory" do
22
+ expect {
23
+ cli.start(%w[generate project foobar])
24
+ }.to change { File.directory?("foobar") }.to(true)
25
+ end
26
+
27
+ it "creates the Gemfile" do
28
+ expect {
29
+ cli.start(%w[generate project foobar])
30
+ }.to change { File.file?("foobar/Gemfile") }.to(true)
31
+ end
32
+
33
+ it "creates the job" do
34
+ expect {
35
+ cli.start(%w[generate project foobar])
36
+ }.to change { File.file?("foobar/app/jobs/foobar.rb") }.to(true)
37
+ end
38
+ end
39
+ end
@@ -0,0 +1,74 @@
1
+ # frozen_string_literal: true
2
+
3
+ require "spec_helpers"
4
+
5
+ describe Wayfarer::CLI::Job, cli: true, redis: true do
6
+ include Wayfarer::Redis
7
+
8
+ let(:url) { test_app_path("/hello_world") }
9
+ let(:batch) { "my-batch" }
10
+ subject(:cli) { Wayfarer::CLI::Runner }
11
+
12
+ before do
13
+ write_file "app/jobs/dummy_job.rb", <<~FILE
14
+ class DummyJob < Wayfarer::Base
15
+ end
16
+ FILE
17
+ end
18
+
19
+ before { Wayfarer::CLI::Base.new.send(:load_environment) }
20
+
21
+ describe "job perform" do
22
+ it "performs the worker" do
23
+ expect_any_instance_of(DummyJob).to receive(:perform).with(kind_of(Wayfarer::Task))
24
+ cli.start(["job", "perform", "DummyJob", url])
25
+ end
26
+
27
+ it "collects garbage" do
28
+ expect_any_instance_of(Wayfarer::GC).to receive(:run).exactly(:once)
29
+ cli.start(["job", "perform", "DummyJob", url])
30
+ end
31
+
32
+ context "using MockRedis" do
33
+ it "performs the worker using MockRedis" do
34
+ cli.start(["job", "perform", "--mock-redis", "DummyJob", url])
35
+ expect(Wayfarer.config.redis_factory.call).to be_a(MockRedis)
36
+ end
37
+ end
38
+ end
39
+
40
+ describe "job enqueue" do
41
+ it "enqueues the job" do
42
+ expect(DummyJob).to receive(:crawl_later).with(URI(url), batch: kind_of(String))
43
+ cli.start(["job", "enqueue", "DummyJob", url])
44
+ end
45
+
46
+ context "with batch provided" do
47
+ it "enqueues the job" do
48
+ expect(DummyJob).to receive(:crawl_later).with(URI(url), batch: batch)
49
+ cli.start(["job", "enqueue", "--batch", batch, "DummyJob", url])
50
+ end
51
+ end
52
+ end
53
+
54
+ describe "job execute" do
55
+ it "executes the job" do
56
+ expect(DummyJob).to receive(:crawl_later).with(URI(url), batch: kind_of(String))
57
+ cli.start(["job", "execute", "DummyJob", url])
58
+ end
59
+
60
+ context "with batch provided" do
61
+ it "enqueues the job" do
62
+ expect(DummyJob).to receive(:crawl_later).with(URI(url), batch: batch)
63
+ cli.start(["job", "execute", "--batch", batch, "DummyJob", url])
64
+ end
65
+ end
66
+
67
+ context "using MockRedis" do
68
+ it "performs the worker using MockRedis" do
69
+ cli.start(["job", "execute", "--mock-redis", "DummyJob", url])
70
+ expect(Wayfarer.config.redis_factory.call).to be_a(MockRedis)
71
+ end
72
+ end
73
+ end
74
+ end
@@ -0,0 +1,13 @@
1
+ # frozen_string_literal: true
2
+
3
+ require "spec_helpers"
4
+
5
+ describe Wayfarer::CLI::Runner, cli: true do
6
+ describe "version" do
7
+ it "prints the version" do
8
+ expect {
9
+ described_class.start(%w[version])
10
+ }.to output(Wayfarer::VERSION::STRING << "\n").to_stdout
11
+ end
12
+ end
13
+ end
@@ -0,0 +1,144 @@
1
+ # frozen_string_literal: true
2
+
3
+ require "spec_helpers"
4
+
5
+ describe Wayfarer::Config do
6
+ describe "::defaults" do
7
+ it "returns the default config" do
8
+ config = Wayfarer::Config.default
9
+ expect(config.adapter).to be(:net_http)
10
+ expect(config.adapter_pool_size).to be(3)
11
+ expect(config.adapter_pool_timeout).to eq(ConnectionPool::DEFAULTS[:timeout])
12
+ expect(config.ferrum_options).to eq({})
13
+ expect(config.selenium_argv).to eq(%i[chrome])
14
+ expect(config.redis_url).to eq("redis://localhost:6379")
15
+ expect(config.redis_factory).not_to be(nil)
16
+ end
17
+ end
18
+
19
+ describe "::from_environment" do
20
+ let(:env) { {} }
21
+ subject(:config) { Wayfarer::Config.from_environment(env) }
22
+
23
+ describe "#adapter" do
24
+ context "by default" do
25
+ it "returns :net_http" do
26
+ expect(config.adapter).to be(:net_http)
27
+ end
28
+ end
29
+
30
+ context "with env var set" do
31
+ before { env["WAYFARER_ADAPTER"] = "ferrum" }
32
+
33
+ it "symbolizes the env var" do
34
+ expect(config.adapter).to be(:ferrum)
35
+ end
36
+ end
37
+ end
38
+
39
+ describe "#adapter_pool_size" do
40
+ context "by default" do
41
+ it "returns the default config value" do
42
+ expect(config.adapter_pool_size).to be(3)
43
+ end
44
+ end
45
+
46
+ context "with env var set" do
47
+ before { env["WAYFARER_POOL_SIZE"] = "1234" }
48
+
49
+ it "parses the env var to a number" do
50
+ expect(config.adapter_pool_size).to be(1234)
51
+ end
52
+ end
53
+ end
54
+
55
+ describe "#adapter_pool_timeout" do
56
+ context "by default" do
57
+ it "returns the default config value" do
58
+ expect(config.adapter_pool_timeout).to be(ConnectionPool::DEFAULTS[:timeout])
59
+ end
60
+ end
61
+
62
+ context "with env var set" do
63
+ let(:env) { { "WAYFARER_POOL_TIMEOUT" => "1000" } }
64
+
65
+ it "parses the env var to a number" do
66
+ expect(config.adapter_pool_timeout).to be(1000)
67
+ end
68
+ end
69
+ end
70
+
71
+ describe "#ferrum_options" do
72
+ context "by default" do
73
+ it "is empty" do
74
+ expect(config.ferrum_options).to eq({})
75
+ end
76
+ end
77
+
78
+ context "with env var set" do
79
+ before { env["WAYFARER_FERRUM_OPTIONS"] = "url:http://chrome:3000,headless:false" }
80
+
81
+ it "parses the env var to a Hash" do
82
+ expect(config.ferrum_options).to eq(url: "http://chrome:3000", headless: false)
83
+ end
84
+ end
85
+ end
86
+
87
+ describe "#selenium_argv" do
88
+ context "by default" do
89
+ it "is [:chrome]" do
90
+ expect(config.selenium_argv).to eq(%i[chrome])
91
+ end
92
+ end
93
+
94
+ context "with env var set" do
95
+ before { env["WAYFARER_SELENIUM_ARGV"] = "firefox" }
96
+
97
+ it "parses the env var to an array" do
98
+ expect(config.selenium_argv).to eq(%w[firefox])
99
+ end
100
+ end
101
+ end
102
+
103
+ describe "#redis_url" do
104
+ context "by default" do
105
+ it "is redis://localhost:6379" do
106
+ expect(config.redis_url).to eq("redis://localhost:6379")
107
+ end
108
+ end
109
+
110
+ context "with env var set" do
111
+ before { env["WAYFARER_REDIS_URL"] = "redis://redis:6379" }
112
+
113
+ it "reads the env var" do
114
+ expect(config.redis_url).to eq("redis://redis:6379")
115
+ end
116
+ end
117
+ end
118
+
119
+ describe "#http_headers" do
120
+ context "by default" do
121
+ it "is {}" do
122
+ expect(config.http_headers).to eq({})
123
+ end
124
+ end
125
+
126
+ context "with env var set" do
127
+ before { env["WAYFARER_HTTP_HEADERS"] = "user-agent:foo,authorization:bar" }
128
+
129
+ it "reads the env var" do
130
+ expect(config.http_headers).to eq("user-agent": "foo",
131
+ authorization: "bar")
132
+ end
133
+ end
134
+ end
135
+ end
136
+
137
+ describe "#redis_factory" do
138
+ let(:config) { Wayfarer::Config.default }
139
+
140
+ it "instantiates Redis clients" do
141
+ expect(config.redis_factory.call).to be_a(Redis)
142
+ end
143
+ end
144
+ end
@@ -0,0 +1,11 @@
1
+ # frozen_string_literal: true
2
+
3
+ FactoryBot.define do
4
+ factory :chain, class: Wayfarer::Middleware::Chain do
5
+ middlewares { [] }
6
+
7
+ initialize_with do
8
+ new(middlewares)
9
+ end
10
+ end
11
+ end
@@ -0,0 +1,15 @@
1
+ # frozen_string_literal: true
2
+
3
+ FactoryBot.define do
4
+ factory :middleware, class: OpenStruct do
5
+ callee { -> {} }
6
+
7
+ initialize_with do
8
+ new(callee: callee).tap do |middleware|
9
+ middleware.define_singleton_method(:call) do |task, &block|
10
+ callee.call(task, &block)
11
+ end
12
+ end
13
+ end
14
+ end
15
+ end
@@ -0,0 +1,78 @@
1
+ # frozen_string_literal: true
2
+
3
+ FactoryBot.define do
4
+ factory :page, class: Wayfarer::Page do
5
+ url { "https://example.com" }
6
+ status_code { 200 }
7
+ headers { {} }
8
+ body { "" }
9
+
10
+ trait :html do
11
+ headers { { "Content-Type" => %w[text/html] } }
12
+ body do
13
+ <<~HTML
14
+ <!doctype html>
15
+ <html lang=en>
16
+ <head>
17
+ <meta charset=utf-8>
18
+ <title>Title</title>
19
+ </head>
20
+ <body></body>
21
+ </html>
22
+ HTML
23
+ end
24
+ end
25
+
26
+ trait :xml do
27
+ headers { { "Content-Type" => %w[application/xml] } }
28
+ body do
29
+ <<~XML
30
+ <menu id="file" value="File">
31
+ <popup>
32
+ <menuitem value="New" onclick="CreateNewDoc()" />
33
+ <menuitem value="Open" onclick="OpenDoc()" />
34
+ <menuitem value="Close" onclick="CloseDoc()" />
35
+ </popup>
36
+ </menu>
37
+ XML
38
+ end
39
+ end
40
+
41
+ trait :json do
42
+ headers { { "Content-Type" => %w[application/json] } }
43
+ body do
44
+ <<~JSON
45
+ {
46
+ "menu":{
47
+ "id":"file",
48
+ "value":"File",
49
+ "popup":{
50
+ "menuitem":[
51
+ {
52
+ "value":"New",
53
+ "onclick":"CreateNewDoc()"
54
+ },
55
+ {
56
+ "value":"Open",
57
+ "onclick":"OpenDoc()"
58
+ },
59
+ {
60
+ "value":"Close",
61
+ "onclick":"CloseDoc()"
62
+ }
63
+ ]
64
+ }
65
+ }
66
+ }
67
+ JSON
68
+ end
69
+ end
70
+
71
+ initialize_with do
72
+ new(url: url,
73
+ status_code: status_code,
74
+ body: body,
75
+ headers: headers)
76
+ end
77
+ end
78
+ end
@@ -0,0 +1,12 @@
1
+ # frozen_string_literal: true
2
+
3
+ FactoryBot.define do
4
+ factory :task, class: Wayfarer::Task do
5
+ url { "https://example.com" }
6
+ batch { "batch" }
7
+
8
+ initialize_with do
9
+ new(url, batch)
10
+ end
11
+ end
12
+ end
@@ -0,0 +1,7 @@
1
+ # frozen_string_literal: true
2
+
3
+ class DummyJob < Wayfarer::Base
4
+ route.to :index
5
+
6
+ def hello; end
7
+ end
data/spec/gc_spec.rb ADDED
@@ -0,0 +1,61 @@
1
+ # frozen_string_literal: true
2
+
3
+ require "spec_helpers"
4
+
5
+ describe Wayfarer::GC, redis: true do
6
+ include Wayfarer::Redis::Connection
7
+
8
+ let(:task) { build(:task) }
9
+ let(:klass) { Struct.new(:arguments) }
10
+ let(:job) { klass.new([task]) }
11
+ subject(:gc) { Wayfarer::GC.new(job) }
12
+
13
+ before do
14
+ allow(klass).to receive(:run_after_batch_callbacks)
15
+ task.barrier.seen?("https://example.com")
16
+ end
17
+
18
+ describe "#run" do
19
+ context "when counter reaches 0" do
20
+ before { task.counter.increment }
21
+
22
+ it "resets the barrier" do
23
+ expect {
24
+ gc.run
25
+ }.to change { redis { |conn| conn.exists?(task.barrier.redis_key) } }.to(false)
26
+ end
27
+
28
+ it "resets the counter" do
29
+ expect {
30
+ gc.run
31
+ }.to change { redis { |conn| conn.exists?(task.counter.redis_key) } }.to(false)
32
+ end
33
+
34
+ it "runs after batch callbacks" do
35
+ expect(klass).to receive(:run_after_batch_callbacks).exactly(:once)
36
+ gc.run
37
+ end
38
+ end
39
+
40
+ context "when counter does not reach 0" do
41
+ before { 2.times { task.counter.increment } }
42
+
43
+ it "does not reset the barrier" do
44
+ expect {
45
+ gc.run
46
+ }.not_to(change { redis { |conn| conn.exists?(task.barrier.redis_key) } })
47
+ end
48
+
49
+ it "does not reset the counter" do
50
+ expect {
51
+ gc.run
52
+ }.not_to(change { redis { |conn| conn.exists?(task.counter.redis_key) } })
53
+ end
54
+
55
+ it "does not run after batch callbacks" do
56
+ expect(klass).not_to receive(:run_after_batch_callbacks)
57
+ gc.run
58
+ end
59
+ end
60
+ end
61
+ end