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
@@ -0,0 +1,46 @@
1
+ # frozen_string_literal: true
2
+
3
+ module Wayfarer
4
+ module Routing
5
+ class PathFinder
6
+ def self.result(route, url)
7
+ finder = new(url)
8
+ route.accept(finder)
9
+ return Result::Mismatch.new if finder.path.none?
10
+
11
+ Result::Match.new(finder.action, finder.params)
12
+ end
13
+
14
+ attr_reader :url,
15
+ :path,
16
+ :action,
17
+ :params
18
+
19
+ def initialize(url)
20
+ @url = url
21
+ @path = []
22
+ @action = nil
23
+ @params = {}
24
+ end
25
+
26
+ def visit(route)
27
+ return false if path.any?
28
+ return false unless route.match(url)
29
+
30
+ follow(route) if route.children.none?
31
+ true
32
+ end
33
+
34
+ private
35
+
36
+ # Follows the route back to the root. Collects parameters and action on
37
+ # the way.
38
+ def follow(route)
39
+ path.unshift(route)
40
+ @params.merge!(route.matcher.params(url))
41
+ @action = route.action unless action
42
+ follow(route.parent) if route.parent
43
+ end
44
+ end
45
+ end
46
+ end
@@ -0,0 +1,46 @@
1
+ # frozen_string_literal: true
2
+
3
+ module Wayfarer
4
+ module Routing
5
+ class PathMatcher
6
+ attr_reader :path,
7
+ :route,
8
+ :peeking,
9
+ :matcher
10
+
11
+ def initialize(path, route)
12
+ @path = path
13
+ @route = route
14
+ @peeking = false
15
+ @matcher = Mustermann.new(path, type: "sinatra")
16
+ end
17
+
18
+ def match(url)
19
+ route.accept(self)
20
+
21
+ # If the route's branch contains other path matchers in child routes,
22
+ # match the beginning of the path (peeking), instead of the whole path.
23
+ !!(if peeking
24
+ matcher.peek(url.path)
25
+ else
26
+ matcher.match(url.path)
27
+ end)
28
+ end
29
+
30
+ def params(url)
31
+ return {} unless match(url)
32
+
33
+ matcher.params(url.path) || {}
34
+ end
35
+
36
+ def visit(route)
37
+ return true if route == self.route
38
+
39
+ return unless route.matcher.is_a?(self.class)
40
+
41
+ @peeking = true
42
+ false
43
+ end
44
+ end
45
+ end
46
+ end
@@ -1,29 +1,37 @@
1
1
  # frozen_string_literal: true
2
2
 
3
- require "cgi"
4
-
5
3
  module Wayfarer
6
4
  module Routing
7
- # @private
8
- class QueryRule < Rule
9
- def initialize(field_constraints, opts = {}, &proc)
10
- @field_constraints = field_constraints
11
- super(opts, &proc)
5
+ class QueryMatcher
6
+ attr_reader :fields
7
+
8
+ def initialize(fields)
9
+ @fields = fields
10
+ end
11
+
12
+ def match(url)
13
+ query = url.query
14
+
15
+ # CGI::parse throws a NoMethodError if the query is an empty string
16
+ return false if query.nil? || query.empty?
17
+
18
+ CGI.parse(query).none? { |field, vals| violates?(field, vals) }
12
19
  end
13
20
 
14
- private
21
+ def params(url)
22
+ return {} unless match(url)
15
23
 
16
- def match!(uri)
17
- CGI.parse(uri.query).none? do |field, vals| violates?(field, vals) end
18
- rescue NoMethodError
19
- # `CGI::parse` throws a `NoMethodError` if `uri.query` is an empty
20
- # string
21
- false
24
+ CGI.parse(url.query)
25
+ .select { |(k, _)| fields.keys.include?(k.to_sym) }
26
+ .transform_values(&:last)
22
27
  end
23
28
 
29
+ private
30
+
24
31
  # rubocop:disable Lint/AssignmentInCondition
25
32
  def violates?(field, vals)
26
- return false unless constraint = @field_constraints[field.to_sym]
33
+ return false unless constraint = fields[field.to_sym]
34
+
27
35
  violates_constraint?(constraint, vals)
28
36
  end
29
37
  # rubocop:enable Lint/AssignmentInCondition
@@ -42,7 +50,7 @@ module Wayfarer
42
50
  end
43
51
 
44
52
  def violates_integer?(int, vals)
45
- vals.none? do |val| int == Integer(val) end
53
+ vals.none? { |val| int == Integer(val) }
46
54
  rescue ArgumentError
47
55
  true
48
56
  end
@@ -0,0 +1,15 @@
1
+ # frozen_string_literal: true
2
+
3
+ module Wayfarer
4
+ module Routing
5
+ module Result
6
+ # Signals that a URL matched a route.
7
+ # @!attribute [rw] action
8
+ # @return [Page] the retrieved page.
9
+ Match = Struct.new(:action, :params)
10
+
11
+ # Signals that a URL matched no route.
12
+ Mismatch = Class.new
13
+ end
14
+ end
15
+ end
@@ -0,0 +1,7 @@
1
+ # frozen_string_literal: true
2
+
3
+ module Wayfarer
4
+ module Routing
5
+ class RootRoute < Route; end
6
+ end
7
+ end
@@ -0,0 +1,41 @@
1
+ # frozen_string_literal: true
2
+
3
+ module Wayfarer
4
+ module Routing
5
+ class Route
6
+ include DSL
7
+
8
+ attr_reader :children
9
+
10
+ attr_accessor :matcher,
11
+ :parent,
12
+ :action,
13
+ :path_offset
14
+
15
+ def initialize(matcher = CustomMatcher.new { children.any? }, path_offset = "/")
16
+ @matcher = matcher
17
+ @children = []
18
+ @path_offset = path_offset
19
+ end
20
+
21
+ def match(url)
22
+ matcher.match(url)
23
+ end
24
+
25
+ def matches?(url)
26
+ invoke(url).is_a?(Result::Match)
27
+ end
28
+
29
+ def invoke(url)
30
+ PathFinder.result(self, url)
31
+ end
32
+
33
+ # Accepts a visitor for in-order traversal.
34
+ def accept(visitor)
35
+ return unless visitor.visit(self)
36
+
37
+ children.each { |child| child.accept(visitor) }
38
+ end
39
+ end
40
+ end
41
+ end
@@ -0,0 +1,21 @@
1
+ # frozen_string_literal: true
2
+
3
+ module Wayfarer
4
+ module Routing
5
+ class SchemeMatcher
6
+ attr_reader :scheme
7
+
8
+ def initialize(scheme)
9
+ @scheme = scheme
10
+ end
11
+
12
+ def match(url)
13
+ url.scheme == scheme.to_s
14
+ end
15
+
16
+ def params(_)
17
+ {}
18
+ end
19
+ end
20
+ end
21
+ end
@@ -0,0 +1,21 @@
1
+ # frozen_string_literal: true
2
+
3
+ module Wayfarer
4
+ module Routing
5
+ class SuffixMatcher
6
+ attr_reader :suffix
7
+
8
+ def initialize(suffix)
9
+ @suffix = suffix
10
+ end
11
+
12
+ def match(url)
13
+ url.path.end_with?(suffix)
14
+ end
15
+
16
+ def params(_)
17
+ {}
18
+ end
19
+ end
20
+ end
21
+ 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 +1,21 @@
1
+ # frozen_string_literal: true
2
+
3
+ module Wayfarer
4
+ module Routing
5
+ class URLMatcher
6
+ attr_reader :url
7
+
8
+ def initialize(url)
9
+ @url = url
10
+ end
11
+
12
+ def match(url)
13
+ url == URI(@url)
14
+ end
15
+
16
+ def params(_)
17
+ {}
18
+ end
19
+ end
20
+ end
21
+ 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 +1,41 @@
1
+ # frozen_string_literal: true
2
+
3
+ module Wayfarer
4
+ module Stringify
5
+ def self.included(base)
6
+ base.include(InstanceMethods)
7
+ base.extend(ClassMethods)
8
+ end
9
+
10
+ module ClassMethods
11
+ def stringify(*variables)
12
+ stringified_attributes.concat(variables)
13
+ end
14
+
15
+ def stringified_attributes
16
+ @stringified_attributes ||= []
17
+ end
18
+ end
19
+
20
+ module InstanceMethods
21
+ def to_s
22
+ "#<#{class_name} #{attributes}>"
23
+ end
24
+
25
+ alias inspect to_s
26
+
27
+ def class_name
28
+ self.class.name.split("::").last
29
+ end
30
+
31
+ def attributes
32
+ self.class
33
+ .stringified_attributes
34
+ .map { |attr| [attr, public_send(attr)] }
35
+ .to_h
36
+ .map { |k, v| [k, "=", v.inspect].join }
37
+ .join(", ")
38
+ end
39
+ end
40
+ end
41
+ 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 +1,57 @@
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
+ "url_matcher" => "URLMatcher",
32
+ "net_http" => "NetHTTP",
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"
25
-
26
- # Parsers
27
- require_relative "wayfarer/parsers/xml_parser"
28
- require_relative "wayfarer/parsers/json_parser"
38
+ module Wayfarer
39
+ module VERSION
40
+ MAJOR = 0
41
+ MINOR = 4
42
+ TINY = 0
43
+ STRING = [MAJOR, MINOR, TINY].join(".")
44
+ end
29
45
 
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"
46
+ mattr_accessor :config, default: Wayfarer::Config.from_environment
35
47
 
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"
48
+ mattr_accessor :core_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]
40
53
  end
41
54
 
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"
55
+ loader.eager_load
54
56
 
55
- def self.logger
56
- return @logger if @logger
57
-
58
- @logger = Logger.new(STDOUT)
59
- @logger.level = Logger::WARN
60
- @logger
61
- end
62
-
63
- def self.config
64
- @config ||= Configuration.new
65
- yield(@config) if block_given?
66
- @config
67
- end
68
- end
57
+ 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