wukong 3.0.0.pre → 3.0.0.pre2

Sign up to get free protection for your applications and to get access to all the features.
Files changed (476) hide show
  1. data/.gitignore +46 -33
  2. data/.gitmodules +3 -0
  3. data/.rspec +1 -1
  4. data/.travis.yml +8 -1
  5. data/.yardopts +0 -13
  6. data/Guardfile +4 -6
  7. data/{LICENSE.textile → LICENSE.md} +43 -55
  8. data/README-old.md +422 -0
  9. data/README.md +279 -418
  10. data/Rakefile +21 -5
  11. data/TODO.md +6 -6
  12. data/bin/wu-clean-encoding +31 -0
  13. data/bin/wu-lign +2 -2
  14. data/bin/wu-local +69 -0
  15. data/bin/wu-server +70 -0
  16. data/examples/Gemfile +38 -0
  17. data/examples/README.md +9 -0
  18. data/examples/dataflow/apache_log_line.rb +64 -25
  19. data/examples/dataflow/fibonacci_series.rb +101 -0
  20. data/examples/dataflow/parse_apache_logs.rb +37 -7
  21. data/examples/{dataflow.rb → dataflow/scraper_macro_flow.rb} +0 -0
  22. data/examples/dataflow/simple.rb +4 -4
  23. data/examples/geo.rb +4 -0
  24. data/examples/geo/geo_grids.numbers +0 -0
  25. data/examples/geo/geolocated.rb +331 -0
  26. data/examples/geo/quadtile.rb +69 -0
  27. data/examples/geo/spec/geolocated_spec.rb +247 -0
  28. data/examples/geo/tile_fetcher.rb +77 -0
  29. data/examples/graph/minimum_spanning_tree.rb +61 -61
  30. data/examples/jabberwocky.txt +36 -0
  31. data/examples/models/wikipedia.rb +20 -0
  32. data/examples/munging/Gemfile +8 -0
  33. data/examples/munging/airline_flights/airline.rb +57 -0
  34. data/examples/munging/airline_flights/airline_flights.rake +83 -0
  35. data/{lib/wukong/settings.rb → examples/munging/airline_flights/airplane.rb} +0 -0
  36. data/examples/munging/airline_flights/airport.rb +211 -0
  37. data/examples/munging/airline_flights/airport_id_unification.rb +129 -0
  38. data/examples/munging/airline_flights/airport_ok_chars.rb +4 -0
  39. data/examples/munging/airline_flights/flight.rb +156 -0
  40. data/examples/munging/airline_flights/models.rb +4 -0
  41. data/examples/munging/airline_flights/parse.rb +26 -0
  42. data/examples/munging/airline_flights/reconcile_airports.rb +142 -0
  43. data/examples/munging/airline_flights/route.rb +35 -0
  44. data/examples/munging/airline_flights/tasks.rake +83 -0
  45. data/examples/munging/airline_flights/timezone_fixup.rb +62 -0
  46. data/examples/munging/airline_flights/topcities.rb +167 -0
  47. data/examples/munging/airports/40_wbans.txt +40 -0
  48. data/examples/munging/airports/filter_weather_reports.rb +37 -0
  49. data/examples/munging/airports/join.pig +31 -0
  50. data/examples/munging/airports/to_tsv.rb +33 -0
  51. data/examples/munging/airports/usa_wbans.pig +19 -0
  52. data/examples/munging/airports/usa_wbans.txt +2157 -0
  53. data/examples/munging/airports/wbans.pig +19 -0
  54. data/examples/munging/airports/wbans.txt +2310 -0
  55. data/examples/munging/geo/geo_json.rb +54 -0
  56. data/examples/munging/geo/geo_models.rb +69 -0
  57. data/examples/munging/geo/geonames_models.rb +78 -0
  58. data/examples/munging/geo/iso_codes.rb +172 -0
  59. data/examples/munging/geo/reconcile_countries.rb +124 -0
  60. data/examples/munging/geo/tasks.rake +71 -0
  61. data/examples/munging/rake_helper.rb +62 -0
  62. data/examples/munging/weather/.gitignore +1 -0
  63. data/examples/munging/weather/Gemfile +4 -0
  64. data/examples/munging/weather/Rakefile +28 -0
  65. data/examples/munging/weather/extract_ish.rb +13 -0
  66. data/examples/munging/weather/models/weather.rb +119 -0
  67. data/examples/munging/weather/utils/noaa_downloader.rb +46 -0
  68. data/examples/munging/wikipedia/README.md +34 -0
  69. data/examples/munging/wikipedia/Rakefile +193 -0
  70. data/examples/munging/wikipedia/articles/extract_articles-parsed.rb +79 -0
  71. data/examples/munging/wikipedia/articles/extract_articles-templated.rb +136 -0
  72. data/examples/munging/wikipedia/articles/textualize_articles.rb +54 -0
  73. data/examples/munging/wikipedia/articles/verify_structure.rb +43 -0
  74. data/examples/munging/wikipedia/articles/wp2txt-LICENSE.txt +22 -0
  75. data/examples/munging/wikipedia/articles/wp2txt_article.rb +259 -0
  76. data/examples/munging/wikipedia/articles/wp2txt_utils.rb +452 -0
  77. data/examples/munging/wikipedia/dbpedia/dbpedia_common.rb +4 -0
  78. data/examples/munging/wikipedia/dbpedia/dbpedia_extract_geocoordinates.rb +78 -0
  79. data/examples/munging/wikipedia/dbpedia/extract_links.rb +193 -0
  80. data/examples/munging/wikipedia/dbpedia/sameas_extractor.rb +20 -0
  81. data/examples/munging/wikipedia/n1_subuniverse/n1_nodes.pig +18 -0
  82. data/examples/munging/wikipedia/page_metadata/extract_page_metadata.rb +21 -0
  83. data/examples/munging/wikipedia/page_metadata/extract_page_metadata.rb.old +27 -0
  84. data/examples/munging/wikipedia/pagelinks/augment_pagelinks.pig +29 -0
  85. data/examples/munging/wikipedia/pagelinks/extract_pagelinks.rb +14 -0
  86. data/examples/munging/wikipedia/pagelinks/extract_pagelinks.rb.old +25 -0
  87. data/examples/munging/wikipedia/pagelinks/undirect_pagelinks.pig +29 -0
  88. data/examples/munging/wikipedia/pageviews/augment_pageviews.pig +32 -0
  89. data/examples/munging/wikipedia/pageviews/extract_pageviews.rb +85 -0
  90. data/examples/munging/wikipedia/pig_style_guide.md +25 -0
  91. data/examples/munging/wikipedia/redirects/redirects_page_metadata.pig +19 -0
  92. data/examples/munging/wikipedia/subuniverse/sub_articles.pig +23 -0
  93. data/examples/munging/wikipedia/subuniverse/sub_page_metadata.pig +24 -0
  94. data/examples/munging/wikipedia/subuniverse/sub_pagelinks_from.pig +22 -0
  95. data/examples/munging/wikipedia/subuniverse/sub_pagelinks_into.pig +22 -0
  96. data/examples/munging/wikipedia/subuniverse/sub_pagelinks_within.pig +26 -0
  97. data/examples/munging/wikipedia/subuniverse/sub_pageviews.pig +29 -0
  98. data/examples/munging/wikipedia/subuniverse/sub_undirected_pagelinks_within.pig +24 -0
  99. data/examples/munging/wikipedia/utils/get_namespaces.rb +86 -0
  100. data/examples/munging/wikipedia/utils/munging_utils.rb +68 -0
  101. data/examples/munging/wikipedia/utils/namespaces.json +1 -0
  102. data/examples/rake_helper.rb +85 -0
  103. data/examples/server_logs/geo_ip_mapping/munge_geolite.rb +82 -0
  104. data/examples/server_logs/logline.rb +95 -0
  105. data/examples/server_logs/models.rb +66 -0
  106. data/examples/server_logs/page_counts.pig +48 -0
  107. data/examples/server_logs/server_logs-01-parse-script.rb +13 -0
  108. data/examples/server_logs/server_logs-02-histograms-full.rb +33 -0
  109. data/examples/server_logs/server_logs-02-histograms-mapper.rb +14 -0
  110. data/{old/examples/server_logs/breadcrumbs.rb → examples/server_logs/server_logs-03-breadcrumbs-full.rb} +26 -30
  111. data/examples/server_logs/server_logs-04-page_page_edges-full.rb +40 -0
  112. data/examples/string_reverser.rb +26 -0
  113. data/examples/text/pig_latin.rb +2 -2
  114. data/examples/text/regional_flavor/README.md +14 -0
  115. data/examples/text/regional_flavor/article_wordbags.pig +39 -0
  116. data/examples/text/regional_flavor/j01-article_wordbags.rb +4 -0
  117. data/examples/text/regional_flavor/simple_pig_script.pig +27 -0
  118. data/examples/word_count/accumulator.rb +26 -0
  119. data/examples/word_count/tokenizer.rb +13 -0
  120. data/examples/word_count/word_count.rb +6 -0
  121. data/examples/workflow/cherry_pie.dot +97 -0
  122. data/examples/workflow/cherry_pie.png +0 -0
  123. data/examples/workflow/cherry_pie.rb +61 -26
  124. data/lib/hanuman.rb +34 -7
  125. data/lib/hanuman/graph.rb +55 -31
  126. data/lib/hanuman/graphvizzer.rb +199 -178
  127. data/lib/hanuman/graphvizzer/gv_models.rb +161 -0
  128. data/lib/hanuman/graphvizzer/gv_presenter.rb +97 -0
  129. data/lib/hanuman/link.rb +35 -0
  130. data/lib/hanuman/registry.rb +46 -0
  131. data/lib/hanuman/stage.rb +76 -32
  132. data/lib/wukong.rb +23 -24
  133. data/lib/wukong/boot.rb +87 -0
  134. data/lib/wukong/configuration.rb +8 -0
  135. data/lib/wukong/dataflow.rb +45 -78
  136. data/lib/wukong/driver.rb +99 -0
  137. data/lib/wukong/emitter.rb +22 -0
  138. data/lib/wukong/model/faker.rb +24 -24
  139. data/lib/wukong/model/flatpack_parser/flat.rb +60 -0
  140. data/lib/wukong/model/flatpack_parser/flatpack.rb +4 -0
  141. data/lib/wukong/model/flatpack_parser/lang.rb +46 -0
  142. data/lib/wukong/model/flatpack_parser/parser.rb +55 -0
  143. data/lib/wukong/model/flatpack_parser/tokens.rb +130 -0
  144. data/lib/wukong/processor.rb +60 -114
  145. data/lib/wukong/spec_helpers.rb +81 -0
  146. data/lib/wukong/spec_helpers/integration_driver.rb +144 -0
  147. data/lib/wukong/spec_helpers/integration_driver_matchers.rb +219 -0
  148. data/lib/wukong/spec_helpers/processor_helpers.rb +95 -0
  149. data/lib/wukong/spec_helpers/processor_methods.rb +108 -0
  150. data/lib/wukong/spec_helpers/shared_examples.rb +15 -0
  151. data/lib/wukong/spec_helpers/spec_driver.rb +28 -0
  152. data/lib/wukong/spec_helpers/spec_driver_matchers.rb +195 -0
  153. data/lib/wukong/version.rb +2 -1
  154. data/lib/wukong/widget/filters.rb +311 -0
  155. data/lib/wukong/widget/processors.rb +156 -0
  156. data/lib/wukong/widget/reducers.rb +7 -0
  157. data/lib/wukong/widget/reducers/accumulator.rb +73 -0
  158. data/lib/wukong/widget/reducers/bin.rb +318 -0
  159. data/lib/wukong/widget/reducers/count.rb +61 -0
  160. data/lib/wukong/widget/reducers/group.rb +85 -0
  161. data/lib/wukong/widget/reducers/group_concat.rb +70 -0
  162. data/lib/wukong/widget/reducers/moments.rb +72 -0
  163. data/lib/wukong/widget/reducers/sort.rb +130 -0
  164. data/lib/wukong/widget/serializers.rb +287 -0
  165. data/lib/wukong/widget/sink.rb +10 -52
  166. data/lib/wukong/widget/source.rb +7 -113
  167. data/lib/wukong/widget/utils.rb +46 -0
  168. data/lib/wukong/widgets.rb +6 -0
  169. data/spec/examples/dataflow/fibonacci_series_spec.rb +18 -0
  170. data/spec/examples/dataflow/parsing_spec.rb +12 -11
  171. data/spec/examples/dataflow/simple_spec.rb +32 -6
  172. data/spec/examples/dataflow/telegram_spec.rb +36 -36
  173. data/spec/examples/graph/minimum_spanning_tree_spec.rb +30 -31
  174. data/spec/examples/munging/airline_flights/identifiers_spec.rb +16 -0
  175. data/spec/examples/munging/airline_flights_spec.rb +202 -0
  176. data/spec/examples/text/pig_latin_spec.rb +13 -16
  177. data/spec/examples/workflow/cherry_pie_spec.rb +34 -4
  178. data/spec/hanuman/graph_spec.rb +27 -2
  179. data/spec/hanuman/hanuman_spec.rb +10 -0
  180. data/spec/hanuman/registry_spec.rb +123 -0
  181. data/spec/hanuman/stage_spec.rb +61 -7
  182. data/spec/spec_helper.rb +29 -19
  183. data/spec/support/hanuman_test_helpers.rb +14 -12
  184. data/spec/support/shared_context_for_reducers.rb +37 -0
  185. data/spec/support/shared_examples_for_builders.rb +101 -0
  186. data/spec/support/shared_examples_for_shortcuts.rb +57 -0
  187. data/spec/support/wukong_test_helpers.rb +37 -11
  188. data/spec/wukong/dataflow_spec.rb +77 -55
  189. data/spec/wukong/local_runner_spec.rb +24 -24
  190. data/spec/wukong/model/faker_spec.rb +132 -131
  191. data/spec/wukong/runner_spec.rb +8 -8
  192. data/spec/wukong/widget/filters_spec.rb +61 -0
  193. data/spec/wukong/widget/processors_spec.rb +126 -0
  194. data/spec/wukong/widget/reducers/bin_spec.rb +92 -0
  195. data/spec/wukong/widget/reducers/count_spec.rb +11 -0
  196. data/spec/wukong/widget/reducers/group_spec.rb +20 -0
  197. data/spec/wukong/widget/reducers/moments_spec.rb +36 -0
  198. data/spec/wukong/widget/reducers/sort_spec.rb +26 -0
  199. data/spec/wukong/widget/serializers_spec.rb +92 -0
  200. data/spec/wukong/widget/sink_spec.rb +15 -15
  201. data/spec/wukong/widget/source_spec.rb +65 -41
  202. data/spec/wukong/wukong_spec.rb +10 -0
  203. data/wukong.gemspec +17 -10
  204. metadata +359 -335
  205. data/.document +0 -5
  206. data/VERSION +0 -1
  207. data/bin/hdp-bin +0 -44
  208. data/bin/hdp-bzip +0 -23
  209. data/bin/hdp-cat +0 -3
  210. data/bin/hdp-catd +0 -3
  211. data/bin/hdp-cp +0 -3
  212. data/bin/hdp-du +0 -86
  213. data/bin/hdp-get +0 -3
  214. data/bin/hdp-kill +0 -3
  215. data/bin/hdp-kill-task +0 -3
  216. data/bin/hdp-ls +0 -11
  217. data/bin/hdp-mkdir +0 -2
  218. data/bin/hdp-mkdirp +0 -12
  219. data/bin/hdp-mv +0 -3
  220. data/bin/hdp-parts_to_keys.rb +0 -77
  221. data/bin/hdp-ps +0 -3
  222. data/bin/hdp-put +0 -3
  223. data/bin/hdp-rm +0 -32
  224. data/bin/hdp-sort +0 -40
  225. data/bin/hdp-stream +0 -40
  226. data/bin/hdp-stream-flat +0 -22
  227. data/bin/hdp-stream2 +0 -39
  228. data/bin/hdp-sync +0 -17
  229. data/bin/hdp-wc +0 -67
  230. data/bin/wu-flow +0 -10
  231. data/bin/wu-map +0 -17
  232. data/bin/wu-red +0 -17
  233. data/bin/wukong +0 -17
  234. data/data/CREDITS.md +0 -355
  235. data/data/graph/airfares.tsv +0 -2174
  236. data/data/text/gift_of_the_magi.txt +0 -225
  237. data/data/text/jabberwocky.txt +0 -36
  238. data/data/text/rectification_of_names.txt +0 -33
  239. data/data/twitter/a_atsigns_b.tsv +0 -64
  240. data/data/twitter/a_follows_b.tsv +0 -53
  241. data/data/twitter/tweet.tsv +0 -167
  242. data/data/twitter/twitter_user.tsv +0 -55
  243. data/data/wikipedia/dbpedia-sentences.tsv +0 -1000
  244. data/docpages/INSTALL.textile +0 -92
  245. data/docpages/LICENSE.textile +0 -107
  246. data/docpages/README-elastic_map_reduce.textile +0 -377
  247. data/docpages/README-performance.textile +0 -90
  248. data/docpages/README-wulign.textile +0 -65
  249. data/docpages/UsingWukong-part1-get_ready.textile +0 -17
  250. data/docpages/UsingWukong-part2-ThinkingBigData.textile +0 -75
  251. data/docpages/UsingWukong-part3-parsing.textile +0 -138
  252. data/docpages/_config.yml +0 -39
  253. data/docpages/avro/avro_notes.textile +0 -56
  254. data/docpages/avro/performance.textile +0 -36
  255. data/docpages/avro/tethering.textile +0 -19
  256. data/docpages/bigdata-tips.textile +0 -143
  257. data/docpages/code/api_response_example.txt +0 -20
  258. data/docpages/code/parser_skeleton.rb +0 -38
  259. data/docpages/diagrams/MapReduceDiagram.graffle +0 -0
  260. data/docpages/favicon.ico +0 -0
  261. data/docpages/gem.css +0 -16
  262. data/docpages/hadoop-tips.textile +0 -83
  263. data/docpages/index.textile +0 -92
  264. data/docpages/intro.textile +0 -8
  265. data/docpages/moreinfo.textile +0 -174
  266. data/docpages/news.html +0 -24
  267. data/docpages/pig/PigLatinExpressionsList.txt +0 -122
  268. data/docpages/pig/PigLatinReferenceManual.txt +0 -1640
  269. data/docpages/pig/commandline_params.txt +0 -26
  270. data/docpages/pig/cookbook.html +0 -481
  271. data/docpages/pig/images/hadoop-logo.jpg +0 -0
  272. data/docpages/pig/images/instruction_arrow.png +0 -0
  273. data/docpages/pig/images/pig-logo.gif +0 -0
  274. data/docpages/pig/piglatin_ref1.html +0 -1103
  275. data/docpages/pig/piglatin_ref2.html +0 -14340
  276. data/docpages/pig/setup.html +0 -505
  277. data/docpages/pig/skin/basic.css +0 -166
  278. data/docpages/pig/skin/breadcrumbs.js +0 -237
  279. data/docpages/pig/skin/fontsize.js +0 -166
  280. data/docpages/pig/skin/getBlank.js +0 -40
  281. data/docpages/pig/skin/getMenu.js +0 -45
  282. data/docpages/pig/skin/images/chapter.gif +0 -0
  283. data/docpages/pig/skin/images/chapter_open.gif +0 -0
  284. data/docpages/pig/skin/images/current.gif +0 -0
  285. data/docpages/pig/skin/images/external-link.gif +0 -0
  286. data/docpages/pig/skin/images/header_white_line.gif +0 -0
  287. data/docpages/pig/skin/images/page.gif +0 -0
  288. data/docpages/pig/skin/images/pdfdoc.gif +0 -0
  289. data/docpages/pig/skin/images/rc-b-l-15-1body-2menu-3menu.png +0 -0
  290. data/docpages/pig/skin/images/rc-b-r-15-1body-2menu-3menu.png +0 -0
  291. data/docpages/pig/skin/images/rc-b-r-5-1header-2tab-selected-3tab-selected.png +0 -0
  292. data/docpages/pig/skin/images/rc-t-l-5-1header-2searchbox-3searchbox.png +0 -0
  293. data/docpages/pig/skin/images/rc-t-l-5-1header-2tab-selected-3tab-selected.png +0 -0
  294. data/docpages/pig/skin/images/rc-t-l-5-1header-2tab-unselected-3tab-unselected.png +0 -0
  295. data/docpages/pig/skin/images/rc-t-r-15-1body-2menu-3menu.png +0 -0
  296. data/docpages/pig/skin/images/rc-t-r-5-1header-2searchbox-3searchbox.png +0 -0
  297. data/docpages/pig/skin/images/rc-t-r-5-1header-2tab-selected-3tab-selected.png +0 -0
  298. data/docpages/pig/skin/images/rc-t-r-5-1header-2tab-unselected-3tab-unselected.png +0 -0
  299. data/docpages/pig/skin/print.css +0 -54
  300. data/docpages/pig/skin/profile.css +0 -181
  301. data/docpages/pig/skin/screen.css +0 -587
  302. data/docpages/pig/tutorial.html +0 -1059
  303. data/docpages/pig/udf.html +0 -1509
  304. data/docpages/tutorial.textile +0 -283
  305. data/docpages/usage.textile +0 -195
  306. data/docpages/wutils.textile +0 -263
  307. data/examples/dataflow/complex.rb +0 -11
  308. data/examples/dataflow/donuts.rb +0 -13
  309. data/examples/tiny_count/jabberwocky_output.tsv +0 -92
  310. data/examples/word_count.rb +0 -48
  311. data/examples/workflow/fiddle.rb +0 -24
  312. data/lib/away/escapement.rb +0 -129
  313. data/lib/away/exe.rb +0 -11
  314. data/lib/away/experimental.rb +0 -5
  315. data/lib/away/from_file.rb +0 -52
  316. data/lib/away/job.rb +0 -56
  317. data/lib/away/job/rake_compat.rb +0 -17
  318. data/lib/away/registry.rb +0 -79
  319. data/lib/away/runner.rb +0 -276
  320. data/lib/away/runner/execute.rb +0 -121
  321. data/lib/away/script.rb +0 -161
  322. data/lib/away/script/hadoop_command.rb +0 -240
  323. data/lib/away/source/file_list_source.rb +0 -15
  324. data/lib/away/source/looper.rb +0 -18
  325. data/lib/away/task.rb +0 -219
  326. data/lib/hanuman/action.rb +0 -21
  327. data/lib/hanuman/chain.rb +0 -4
  328. data/lib/hanuman/graphviz.rb +0 -74
  329. data/lib/hanuman/resource.rb +0 -6
  330. data/lib/hanuman/slot.rb +0 -87
  331. data/lib/hanuman/slottable.rb +0 -220
  332. data/lib/wukong/bad_record.rb +0 -15
  333. data/lib/wukong/event.rb +0 -44
  334. data/lib/wukong/local_runner.rb +0 -55
  335. data/lib/wukong/mapred.rb +0 -3
  336. data/lib/wukong/universe.rb +0 -48
  337. data/lib/wukong/widget/filter.rb +0 -81
  338. data/lib/wukong/widget/gibberish.rb +0 -123
  339. data/lib/wukong/widget/monitor.rb +0 -26
  340. data/lib/wukong/widget/reducer.rb +0 -66
  341. data/lib/wukong/widget/stringifier.rb +0 -50
  342. data/lib/wukong/workflow.rb +0 -22
  343. data/lib/wukong/workflow/command.rb +0 -42
  344. data/old/config/emr-example.yaml +0 -48
  345. data/old/examples/README.txt +0 -17
  346. data/old/examples/contrib/jeans/README.markdown +0 -165
  347. data/old/examples/contrib/jeans/data/normalized_sizes +0 -3
  348. data/old/examples/contrib/jeans/data/orders.tsv +0 -1302
  349. data/old/examples/contrib/jeans/data/sizes +0 -3
  350. data/old/examples/contrib/jeans/normalize.rb +0 -20
  351. data/old/examples/contrib/jeans/sizes.rb +0 -55
  352. data/old/examples/corpus/bnc_word_freq.rb +0 -44
  353. data/old/examples/corpus/bucket_counter.rb +0 -47
  354. data/old/examples/corpus/dbpedia_abstract_to_sentences.rb +0 -86
  355. data/old/examples/corpus/sentence_bigrams.rb +0 -53
  356. data/old/examples/corpus/sentence_coocurrence.rb +0 -66
  357. data/old/examples/corpus/stopwords.rb +0 -138
  358. data/old/examples/corpus/words_to_bigrams.rb +0 -53
  359. data/old/examples/emr/README.textile +0 -110
  360. data/old/examples/emr/dot_wukong_dir/credentials.json +0 -7
  361. data/old/examples/emr/dot_wukong_dir/emr.yaml +0 -69
  362. data/old/examples/emr/dot_wukong_dir/emr_bootstrap.sh +0 -33
  363. data/old/examples/emr/elastic_mapreduce_example.rb +0 -28
  364. data/old/examples/network_graph/adjacency_list.rb +0 -74
  365. data/old/examples/network_graph/breadth_first_search.rb +0 -72
  366. data/old/examples/network_graph/gen_2paths.rb +0 -68
  367. data/old/examples/network_graph/gen_multi_edge.rb +0 -112
  368. data/old/examples/network_graph/gen_symmetric_links.rb +0 -64
  369. data/old/examples/pagerank/README.textile +0 -6
  370. data/old/examples/pagerank/gen_initial_pagerank_graph.pig +0 -57
  371. data/old/examples/pagerank/pagerank.rb +0 -72
  372. data/old/examples/pagerank/pagerank_initialize.rb +0 -42
  373. data/old/examples/pagerank/run_pagerank.sh +0 -21
  374. data/old/examples/sample_records.rb +0 -33
  375. data/old/examples/server_logs/apache_log_parser.rb +0 -15
  376. data/old/examples/server_logs/nook.rb +0 -48
  377. data/old/examples/server_logs/nook/faraday_dummy_adapter.rb +0 -94
  378. data/old/examples/server_logs/user_agent.rb +0 -40
  379. data/old/examples/simple_word_count.rb +0 -82
  380. data/old/examples/size.rb +0 -61
  381. data/old/examples/stats/avg_value_frequency.rb +0 -86
  382. data/old/examples/stats/binning_percentile_estimator.rb +0 -140
  383. data/old/examples/stats/data/avg_value_frequency.tsv +0 -3
  384. data/old/examples/stats/rank_and_bin.rb +0 -173
  385. data/old/examples/stupidly_simple_filter.rb +0 -40
  386. data/old/examples/word_count.rb +0 -75
  387. data/old/graph/graphviz_builder.rb +0 -580
  388. data/old/graph_easy/Attributes.pm +0 -4181
  389. data/old/graph_easy/Graphviz.pm +0 -2232
  390. data/old/wukong.rb +0 -18
  391. data/old/wukong/and_pig.rb +0 -38
  392. data/old/wukong/bad_record.rb +0 -18
  393. data/old/wukong/datatypes.rb +0 -24
  394. data/old/wukong/datatypes/enum.rb +0 -127
  395. data/old/wukong/datatypes/fake_types.rb +0 -17
  396. data/old/wukong/decorator.rb +0 -28
  397. data/old/wukong/encoding/asciize.rb +0 -108
  398. data/old/wukong/extensions.rb +0 -16
  399. data/old/wukong/extensions/array.rb +0 -18
  400. data/old/wukong/extensions/blank.rb +0 -93
  401. data/old/wukong/extensions/class.rb +0 -189
  402. data/old/wukong/extensions/date_time.rb +0 -53
  403. data/old/wukong/extensions/emittable.rb +0 -69
  404. data/old/wukong/extensions/enumerable.rb +0 -79
  405. data/old/wukong/extensions/hash.rb +0 -167
  406. data/old/wukong/extensions/hash_keys.rb +0 -16
  407. data/old/wukong/extensions/hash_like.rb +0 -150
  408. data/old/wukong/extensions/hashlike_class.rb +0 -47
  409. data/old/wukong/extensions/module.rb +0 -2
  410. data/old/wukong/extensions/pathname.rb +0 -27
  411. data/old/wukong/extensions/string.rb +0 -65
  412. data/old/wukong/extensions/struct.rb +0 -17
  413. data/old/wukong/extensions/symbol.rb +0 -11
  414. data/old/wukong/filename_pattern.rb +0 -74
  415. data/old/wukong/helper.rb +0 -7
  416. data/old/wukong/helper/stopwords.rb +0 -195
  417. data/old/wukong/helper/tokenize.rb +0 -35
  418. data/old/wukong/logger.rb +0 -38
  419. data/old/wukong/periodic_monitor.rb +0 -72
  420. data/old/wukong/schema.rb +0 -269
  421. data/old/wukong/script.rb +0 -286
  422. data/old/wukong/script/avro_command.rb +0 -5
  423. data/old/wukong/script/cassandra_loader_script.rb +0 -40
  424. data/old/wukong/script/emr_command.rb +0 -168
  425. data/old/wukong/script/hadoop_command.rb +0 -237
  426. data/old/wukong/script/local_command.rb +0 -41
  427. data/old/wukong/store.rb +0 -10
  428. data/old/wukong/store/base.rb +0 -27
  429. data/old/wukong/store/cassandra.rb +0 -10
  430. data/old/wukong/store/cassandra/streaming.rb +0 -75
  431. data/old/wukong/store/cassandra/struct_loader.rb +0 -21
  432. data/old/wukong/store/cassandra_model.rb +0 -91
  433. data/old/wukong/store/chh_chunked_flat_file_store.rb +0 -37
  434. data/old/wukong/store/chunked_flat_file_store.rb +0 -48
  435. data/old/wukong/store/conditional_store.rb +0 -57
  436. data/old/wukong/store/factory.rb +0 -8
  437. data/old/wukong/store/flat_file_store.rb +0 -89
  438. data/old/wukong/store/key_store.rb +0 -51
  439. data/old/wukong/store/null_store.rb +0 -15
  440. data/old/wukong/store/read_thru_store.rb +0 -22
  441. data/old/wukong/store/tokyo_tdb_key_store.rb +0 -33
  442. data/old/wukong/store/tyrant_rdb_key_store.rb +0 -57
  443. data/old/wukong/store/tyrant_tdb_key_store.rb +0 -20
  444. data/old/wukong/streamer.rb +0 -30
  445. data/old/wukong/streamer/accumulating_reducer.rb +0 -83
  446. data/old/wukong/streamer/base.rb +0 -126
  447. data/old/wukong/streamer/counting_reducer.rb +0 -25
  448. data/old/wukong/streamer/filter.rb +0 -20
  449. data/old/wukong/streamer/instance_streamer.rb +0 -15
  450. data/old/wukong/streamer/json_streamer.rb +0 -21
  451. data/old/wukong/streamer/line_streamer.rb +0 -12
  452. data/old/wukong/streamer/list_reducer.rb +0 -31
  453. data/old/wukong/streamer/rank_and_bin_reducer.rb +0 -145
  454. data/old/wukong/streamer/record_streamer.rb +0 -14
  455. data/old/wukong/streamer/reducer.rb +0 -11
  456. data/old/wukong/streamer/set_reducer.rb +0 -14
  457. data/old/wukong/streamer/struct_streamer.rb +0 -48
  458. data/old/wukong/streamer/summing_reducer.rb +0 -29
  459. data/old/wukong/streamer/uniq_by_last_reducer.rb +0 -51
  460. data/old/wukong/typed_struct.rb +0 -12
  461. data/spec/away/encoding_spec.rb +0 -32
  462. data/spec/away/exe_spec.rb +0 -20
  463. data/spec/away/flow_spec.rb +0 -82
  464. data/spec/away/graph_spec.rb +0 -6
  465. data/spec/away/job_spec.rb +0 -15
  466. data/spec/away/rake_compat_spec.rb +0 -9
  467. data/spec/away/script_spec.rb +0 -81
  468. data/spec/hanuman/graphviz_spec.rb +0 -29
  469. data/spec/hanuman/slot_spec.rb +0 -2
  470. data/spec/support/examples_helper.rb +0 -10
  471. data/spec/support/streamer_test_helpers.rb +0 -6
  472. data/spec/support/wukong_widget_helpers.rb +0 -66
  473. data/spec/wukong/processor_spec.rb +0 -109
  474. data/spec/wukong/widget/filter_spec.rb +0 -99
  475. data/spec/wukong/widget/stringifier_spec.rb +0 -51
  476. data/spec/wukong/workflow/command_spec.rb +0 -5
@@ -1,16 +0,0 @@
1
- class Hash
2
-
3
- # Return a new hash with all keys converted to symbols.
4
- def symbolize_keys
5
- inject({}) do |options, (key, value)|
6
- options[(key.to_sym rescue key) || key] = value
7
- options
8
- end
9
- end
10
-
11
- # Destructively convert all keys to symbols.
12
- def symbolize_keys!
13
- self.replace(self.symbolize_keys)
14
- end
15
-
16
- end
@@ -1,150 +0,0 @@
1
- module Wukong
2
- #
3
- # A hashlike has to
4
- #
5
- # *
6
- # * The arguments to your initializer should be the same as the keys, in order
7
- # If not, you must override #from_hash
8
- #
9
- #
10
- module HashLike
11
-
12
- # List of possible keys --
13
- # delegates to the class
14
- def keys
15
- self.class.keys
16
- end
17
-
18
- #
19
- # Return a Hash containing only values for the given keys.
20
- #
21
- # Since this is intended to mirror Hash#slice it will harmlessly ignore keys
22
- # not present in the struct. They will be unset (hsh.include? is not true)
23
- # as opposed to nil.
24
- #
25
- def slice *keys
26
- keys.inject({}) do |hsh, key|
27
- hsh[key] = send(key) if respond_to?(key)
28
- hsh
29
- end
30
- end
31
-
32
- #
33
- # values_at like a hash
34
- #
35
- # Since this is intended to mirror Hash#values_at it will harmlessly ignore
36
- # keys not present in the struct
37
- #
38
- def values_of *keys
39
- keys.map{|key| self.send(key) if respond_to?(key) }
40
- end
41
-
42
- #
43
- # Convert to a hash
44
- #
45
- def to_hash
46
- slice(*self.class.members)
47
- end
48
-
49
- #
50
- # Analagous to Hash#each_pair
51
- #
52
- def pairs
53
- self.class.members.map{|attr| [attr, self[attr]] }
54
- end
55
-
56
- #
57
- # Analagous to Hash#each_pair
58
- #
59
- def each_pair *args, &block
60
- pairs.each(*args, &block)
61
- end
62
-
63
- #
64
- # Analagous to Hash#merge
65
- #
66
- def merge *args
67
- self.dup.merge!(*args)
68
- end
69
- def merge! hsh, &block
70
- raise "can't handle block arg yet" if block
71
- hsh.each_pair{|key, val| self.send("#{key}=", val) if self.respond_to?("#{key}=") }
72
- self
73
- end
74
- alias_method :update, :merge!
75
-
76
- #
77
- # Merge hashes recursively.
78
- # Nothing special happens to array values
79
- #
80
- # x = { :subhash => { 1 => :val_from_x, 222 => :only_in_x, 333 => :only_in_x }, :scalar => :scalar_from_x}
81
- # y = { :subhash => { 1 => :val_from_y, 999 => :only_in_y }, :scalar => :scalar_from_y }
82
- # x.deep_merge y
83
- # => {:subhash=>{1=>:val_from_y, 222=>:only_in_x, 333=>:only_in_x, 999=>:only_in_y}, :scalar=>:scalar_from_y}
84
- # y.deep_merge x
85
- # => {:subhash=>{1=>:val_from_x, 222=>:only_in_x, 333=>:only_in_x, 999=>:only_in_y}, :scalar=>:scalar_from_x}
86
- #
87
- def deep_merge hsh2
88
- merge hsh2, &Hash::DEEP_MERGER
89
- end
90
-
91
- #
92
- # remove all key-value pairs where the value is blank
93
- #
94
- def compact_blank
95
- to_hash.compact_blank!
96
- end
97
-
98
- module ClassMethods
99
- #
100
- # Instantiate an instance of the struct from a hash
101
- #
102
- # Specify has_symbol_keys if the supplied hash's keys are symbolic;
103
- # otherwise they must be uniformly strings
104
- #
105
- def from_hash(hsh, has_symbol_keys=false)
106
- extract_keys = has_symbol_keys ? self.keys.map(&:to_sym) : self.keys.map(&:to_s)
107
- self.new(*hsh.values_of(*extract_keys))
108
- end
109
- #
110
- # The last portion of the class in underscored form
111
- # memoized
112
- #
113
- def resource_name
114
- @resource_name ||= self.class_basename.underscore.to_sym
115
- end
116
- # The last portion of the class name
117
- # memoized
118
- #
119
- # @example
120
- # This::That::TheOther.new.class_basename # => TheOther
121
- def class_basename
122
- @class_basename ||= self.to_s.gsub(%r{.*::}, '')
123
- end
124
- end
125
-
126
- def self.included base
127
- base.class_eval do
128
- extend ClassMethods
129
- end
130
- end
131
-
132
- def coerce_attr attr, coerce_blank_to_nil=false, &block
133
- orig_val = self.send(attr)
134
- new_val = (coerce_blank_to_nil && orig_val.blank?) ? nil : block.call(orig_val)
135
- self.send("#{attr}=", new_val)
136
- end
137
-
138
- def coerce_to_int! attr, *args
139
- coerce_attr(attr, *args) do |val|
140
- val.to_i
141
- end
142
- end
143
-
144
- def coerce_to_date! attr, *args
145
- coerce_attr(attr, *args){|val| val.is_a?(DateTime) ? val : DateTime.parse(val) rescue nil }
146
- end
147
-
148
- end
149
-
150
- end
@@ -1,47 +0,0 @@
1
- require 'wukong/extensions/class'
2
- module Wukong
3
-
4
- module HashlikeClass
5
- module ClassMethods
6
- def has_members *members
7
- self.members ||= []
8
- self.members = members.map(&:to_s) + self.members
9
- self.members.each do |member|
10
- attr_accessor member.to_sym
11
- end
12
- end
13
- alias_method :has_member, :has_members
14
- def keys
15
- members
16
- end
17
- end
18
-
19
- def [](key)
20
- self.send(key)
21
- end
22
-
23
- def []=(key, val)
24
- self.send("#{key}=", val)
25
- end
26
-
27
- def to_a
28
- values_of(*members)
29
- end
30
-
31
- def to_flat
32
- to_a.map(&:to_flat).flatten
33
- end
34
-
35
- def self.included base
36
- base.class_eval do
37
- extend ClassMethods
38
- include HashLike
39
- class_inheritable_accessor :members
40
-
41
- def to_hash *args
42
- super(*args).merge 'type' => self.class.to_s
43
- end
44
- end
45
- end
46
- end
47
- end
@@ -1,2 +0,0 @@
1
- require 'extlib/object'
2
- require 'extlib/module'
@@ -1,27 +0,0 @@
1
- require 'pathname'
2
- class Pathname
3
- # Append path segments and expand to absolute path
4
- #
5
- # file = Pathname(Dir.pwd) / "subdir1" / :subdir2 / "filename.ext"
6
- #
7
- # @param [Pathname, String, #to_s] path path segment to concatenate with receiver
8
- #
9
- # @return [Pathname]
10
- # receiver with _path_ appended and expanded to an absolute path
11
- #
12
- # @api public
13
- def /(path)
14
- (self + path).expand_path
15
- end
16
-
17
- def self.[](*vals)
18
- new( File.join(vals) )
19
- end
20
- end
21
-
22
- class Subdir < Pathname
23
- def self.[](*vals)
24
- dir = File.dirname(vals.shift)
25
- new(File.join(dir, *vals))
26
- end
27
- end
@@ -1,65 +0,0 @@
1
- #
2
- # String Monkeypatched for processing with wukong: see wukong/extensions/string
3
- #
4
- String.class_eval do
5
- # By default, +camelize+ converts strings to UpperCamelCase. If the argument to +camelize+
6
- # is set to <tt>:lower</tt> then +camelize+ produces lowerCamelCase.
7
- #
8
- # +camelize+ will also convert '/' to '::' which is useful for converting paths to namespaces.
9
- #
10
- # Examples:
11
- # "active_record".camelize # => "ActiveRecord"
12
- # "active_record".camelize(:lower) # => "activeRecord"
13
- # "active_record/errors".camelize # => "ActiveRecord::Errors"
14
- # "active_record/errors".camelize(:lower) # => "activeRecord::Errors"
15
- def camelize(first_letter_in_uppercase = true)
16
- if first_letter_in_uppercase
17
- self.to_s.gsub(/\/(.?)/) { "::#{$1.upcase}" }.gsub(/(?:^|_)(.)/) { $1.upcase }
18
- else
19
- self.first + camelize(self)[1..-1]
20
- end
21
- end
22
-
23
- #
24
- # The reverse of +camelize+. Makes an underscored, lowercase form from the expression in the string.
25
- #
26
- # Changes '::' to '/' to convert namespaces to paths.
27
- #
28
- # Examples:
29
- # "ActiveRecord".underscore # => "active_record"
30
- # "ActiveRecord::Errors".underscore # => active_record/errors
31
- #
32
- # Stolen from active_support
33
- #
34
- def underscore
35
- gsub(/::/, '/').
36
- gsub(/([A-Z]+)([A-Z][a-z])/,'\1_\2').
37
- gsub(/([a-z\d])([A-Z])/,'\1_\2').
38
- tr("-", "_").
39
- downcase
40
- end
41
-
42
- # Tries to find a constant with the name specified in the argument string:
43
- #
44
- # "Module".constantize # => Module
45
- # "Test::Unit".constantize # => Test::Unit
46
- #
47
- # The name is assumed to be the one of a top-level constant, no matter whether
48
- # it starts with "::" or not. No lexical context is taken into account:
49
- #
50
- # C = 'outside'
51
- # module M
52
- # C = 'inside'
53
- # C # => 'inside'
54
- # "C".constantize # => 'outside', same as ::C
55
- # end
56
- #
57
- # NameError is raised when the name is not in CamelCase or the constant is
58
- # unknown.
59
- def constantize
60
- unless /\A(?:::)?([A-Z]\w*(?:::[A-Z]\w*)*)\z/ =~ self
61
- raise NameError, "#{self.inspect} is not a valid constant name!"
62
- end
63
- Object.module_eval("::#{$1}", __FILE__, __LINE__)
64
- end
65
- end
@@ -1,17 +0,0 @@
1
- require 'wukong/extensions/hash'
2
- require 'wukong/extensions/hash_like'
3
- require 'wukong/extensions/symbol'
4
-
5
- #
6
- # extensions/struct
7
- #
8
- # Add several methods to make a struct duck-type much more like a Hash
9
- #
10
- Struct.class_eval do
11
- include Wukong::HashLike
12
- def self.keys
13
- members
14
- end
15
- end
16
-
17
-
@@ -1,11 +0,0 @@
1
- #
2
- # h2. extensions/symbol.rb -- extensions to symbol class
3
- #
4
- class Symbol
5
- #
6
- # Turn the symbol into a simple proc (stolen from
7
- # <tt>ActiveSupport::CoreExtensions::Symbol</tt>).
8
- def to_proc
9
- Proc.new { |*args| args.shift.__send__(self, *args) }
10
- end unless method_defined?(:to_proc)
11
- end
@@ -1,74 +0,0 @@
1
- module Wukong
2
- class FilenamePattern
3
- # the filename pattern, e.g. 'ripd/:handle/:date/:handle+:timestamp-:pid-:hostname.tsv'
4
- attr_accessor :pattern
5
- # custom token replacements
6
- attr_accessor :token_val_defaults
7
-
8
- DEFAULT_PATTERN_STR = ":dest_dir/:handle_prefix/:handle/:date/:handle:timestamp-:pid-:hostname.tsv"
9
-
10
- def initialize pattern, token_val_defaults={}
11
- self.pattern = pattern
12
- self.token_val_defaults = token_val_defaults
13
- end
14
-
15
- #
16
- # walk through pattern, replacing tokens (eg :time or :pid) with the
17
- # corresponding value.
18
- #
19
- # Don't use ':' in a pattern except to introduce a token
20
- # and separate tokens with '-', '+' '/' or '.'
21
- #
22
- def make token_vals={}
23
- token_vals = token_val_defaults.merge token_vals
24
- token_vals[:timestamp] ||= Time.now.utc.strftime("%Y%m%d%H%M%S")
25
- val = pattern.gsub(/:(\w+)/){ replace($1, token_vals) }
26
- val
27
- end
28
-
29
- def to_s token_vals={}
30
- make token_vals
31
- end
32
-
33
- #
34
- # substitute for token
35
- #
36
- def replace token, token_vals
37
- token = token.to_sym
38
- return token_vals[token] if token_vals.include? token
39
- case token
40
- when :pid then pid
41
- when :hostname then hostname
42
- when :handle then token_vals[:handle]
43
- when :handle_prefix then token_vals[:handle].to_s[0..5]
44
- when :timestamp then token_vals[:timestamp]
45
- when :date then token_vals[:timestamp][ 0..7]
46
- when :time then token_vals[:timestamp][ 8..13]
47
- when :hour then token_vals[:timestamp][ 8..9]
48
- when :h4 then "%0.2d" % (( token_vals[:timestamp][8..9].to_i / 4 ) * 4)
49
- when :min then token_vals[:timestamp][10..11]
50
- when :sec then token_vals[:timestamp][12..13]
51
- when :s10 then "%0.2d" % (( token_vals[:timestamp][12..13].to_i / 10 ) * 10)
52
- else
53
- raise "Don't know how to encode token #{token} #{token_vals[token]}"
54
- end
55
- end
56
-
57
- # Memoized: the hostname for the machine running this script.
58
- def hostname
59
- @hostname ||= ENV['HOSTNAME'] || `hostname`.chomp
60
- end
61
- # Memoized: the Process ID for this invocation.
62
- def pid
63
- @pid ||= Process.pid
64
- end
65
-
66
- # Characters deemed safe in a filename;
67
- SAFE_CHARS = 'a-zA-Z0-9_\-\.\+\/'
68
- RE_SAFE_FILENAME = %r{[^#{SAFE_CHARS}]+}moxi
69
- def self.sanitize str
70
- str.gsub(RE_SAFE_FILENAME, '-')
71
- end
72
-
73
- end
74
- end
@@ -1,7 +0,0 @@
1
- module Wukong
2
- module Helper
3
-
4
- autoload :Tokenize, 'wukong/helper/tokenize'
5
-
6
- end
7
- end
@@ -1,195 +0,0 @@
1
- module Wukong
2
- module Corpus
3
- STOPWORDS = %w[
4
- the
5
- of
6
- and
7
- a
8
- in
9
- to
10
- it
11
- is
12
- was
13
- I
14
- for
15
- that
16
- you
17
- he
18
- be
19
- with
20
- on
21
- by
22
- at
23
- have
24
- are
25
- not
26
- this
27
- but
28
- had
29
- they
30
- his
31
- from
32
- she
33
- which
34
- or
35
- we
36
- an
37
- were
38
- as
39
- do
40
- been
41
- their
42
- has
43
- would
44
- there
45
- what
46
- will
47
- all
48
- if
49
- can
50
- her
51
- said
52
- who
53
- so
54
- up
55
- them
56
- when
57
- some
58
- could
59
- him
60
- into
61
- its
62
- then
63
- out
64
- my
65
- about
66
- did
67
- your
68
- me
69
- other
70
- just
71
- more
72
- these
73
- also
74
- any
75
- see
76
- very
77
- may
78
- well
79
- should
80
- than
81
- how
82
- get
83
- way
84
- our
85
- made
86
- got
87
- after
88
- many
89
- those
90
- go
91
- being
92
- because
93
- down
94
- such
95
- over
96
- must
97
- still
98
- even
99
- too
100
- here
101
- come
102
- own
103
- last
104
- does
105
- oh
106
- no
107
- where
108
- us
109
- same
110
- might
111
- yes
112
- put
113
- another
114
- most
115
- again
116
- under
117
- much
118
- why
119
- each
120
- while
121
- off
122
- went
123
- used
124
- without
125
- give
126
- within
127
-
128
- am
129
- aren't
130
- between
131
- both
132
- can't
133
- cannot
134
- couldn't
135
- didn't
136
- doesn't
137
- doing
138
- don't
139
- hadn't
140
- hasn't
141
- haven't
142
- having
143
- he'd
144
- he'll
145
- he's
146
- here's
147
- hers
148
- how's
149
- i'd
150
- i'll
151
- i'm
152
- i've
153
- isn't
154
- it'd
155
- it'll
156
- it's
157
- let's
158
- once
159
- only
160
- ought
161
- ours
162
- she'd
163
- she'll
164
- she's
165
- shouldn't
166
- that's
167
- theirs
168
- there's
169
- they'd
170
- they'll
171
- they're
172
- they've
173
- through
174
- wasn't
175
- we'd
176
- we'll
177
- we're
178
- we've
179
- weren't
180
- what's
181
- where's
182
- who's
183
- won't
184
- wouldn't
185
- you'd
186
- you'll
187
- you're
188
- you've
189
- yours
190
-
191
- ].to_set
192
- STOPWORDS_3 = STOPWORDS.reject{|w| w.length < 3 }.to_set
193
-
194
- end
195
- end