ul-wukong 4.1.0

Sign up to get free protection for your applications and to get access to all the features.
Files changed (261) hide show
  1. checksums.yaml +15 -0
  2. data/.gitignore +60 -0
  3. data/.gitmodules +6 -0
  4. data/.rspec +2 -0
  5. data/.travis.yml +19 -0
  6. data/.yardopts +6 -0
  7. data/CHANGELOG.md +7 -0
  8. data/Gemfile +17 -0
  9. data/Guardfile +12 -0
  10. data/LICENSE.md +95 -0
  11. data/NOTES-travis.md +31 -0
  12. data/README-old.md +422 -0
  13. data/README.md +1308 -0
  14. data/Rakefile +28 -0
  15. data/TODO.md +99 -0
  16. data/bin/cutc +30 -0
  17. data/bin/cuttab +5 -0
  18. data/bin/greptrue +6 -0
  19. data/bin/md5sort +20 -0
  20. data/bin/setcat +11 -0
  21. data/bin/tabchar +5 -0
  22. data/bin/uniq-ord +59 -0
  23. data/bin/uniqc +3 -0
  24. data/bin/wu +34 -0
  25. data/bin/wu-clean-encoding +31 -0
  26. data/bin/wu-date +13 -0
  27. data/bin/wu-datetime +13 -0
  28. data/bin/wu-hist +3 -0
  29. data/bin/wu-lign +186 -0
  30. data/bin/wu-local +4 -0
  31. data/bin/wu-plus +9 -0
  32. data/bin/wu-source +5 -0
  33. data/bin/wu-sum +31 -0
  34. data/diagrams/wu_local.dot +39 -0
  35. data/diagrams/wu_local.dot.png +0 -0
  36. data/examples/Gemfile +38 -0
  37. data/examples/README.md +9 -0
  38. data/examples/basic/string_reverser.rb +23 -0
  39. data/examples/basic/tiny_count.rb +8 -0
  40. data/examples/basic/word_count/accumulator.rb +26 -0
  41. data/examples/basic/word_count/tokenizer.rb +13 -0
  42. data/examples/basic/word_count/word_count.rb +6 -0
  43. data/examples/dataflow/scraper_macro_flow.rb +28 -0
  44. data/examples/deploy_pack/Gemfile +6 -0
  45. data/examples/deploy_pack/README.md +6 -0
  46. data/examples/deploy_pack/a/b/c/.gitkeep +0 -0
  47. data/examples/deploy_pack/app/processors/string_reverser.rb +5 -0
  48. data/examples/deploy_pack/config/environment.rb +1 -0
  49. data/examples/dsl/dataflow/fibonacci_series.rb +101 -0
  50. data/examples/dsl/dataflow/scraper_macro_flow.rb +28 -0
  51. data/examples/dsl/dataflow/simple.rb +12 -0
  52. data/examples/dsl/dataflow/telegram.rb +45 -0
  53. data/examples/dsl/workflow/cherry_pie.dot +97 -0
  54. data/examples/dsl/workflow/cherry_pie.md +104 -0
  55. data/examples/dsl/workflow/cherry_pie.png +0 -0
  56. data/examples/dsl/workflow/cherry_pie.rb +101 -0
  57. data/examples/empty/.gitkeep +0 -0
  58. data/examples/examples_helper.rb +9 -0
  59. data/examples/geo.rb +4 -0
  60. data/examples/geo/geo_grids.numbers +0 -0
  61. data/examples/geo/geolocated.rb +331 -0
  62. data/examples/geo/quadtile.rb +69 -0
  63. data/examples/geo/spec/geolocated_spec.rb +247 -0
  64. data/examples/geo/tile_fetcher.rb +77 -0
  65. data/examples/graph/implied_geolocation/README.md +63 -0
  66. data/examples/graph/minimum_spanning_tree/airfares_graphviz.rb +73 -0
  67. data/examples/improver/tweet_summary.rb +73 -0
  68. data/examples/loadable.rb +2 -0
  69. data/examples/munging/airline_flights/airline_flights.rake +83 -0
  70. data/examples/munging/airline_flights/airplane.rb +0 -0
  71. data/examples/munging/airline_flights/airport_id_unification.rb +129 -0
  72. data/examples/munging/airline_flights/airport_ok_chars.rb +4 -0
  73. data/examples/munging/airline_flights/indexable.rb +75 -0
  74. data/examples/munging/airline_flights/indexable_spec.rb +90 -0
  75. data/examples/munging/airline_flights/reconcile_airports.rb +142 -0
  76. data/examples/munging/airline_flights/tasks.rake +83 -0
  77. data/examples/munging/airline_flights/topcities.rb +167 -0
  78. data/examples/munging/geo/geo_json.rb +54 -0
  79. data/examples/munging/geo/geo_models.rb +69 -0
  80. data/examples/munging/geo/geonames_models.rb +107 -0
  81. data/examples/munging/geo/iso_codes.rb +172 -0
  82. data/examples/munging/geo/reconcile_countries.rb +124 -0
  83. data/examples/munging/geo/tasks.rake +71 -0
  84. data/examples/munging/wikipedia/articles/extract_articles-parsed.rb +79 -0
  85. data/examples/munging/wikipedia/articles/extract_articles-templated.rb +136 -0
  86. data/examples/munging/wikipedia/articles/textualize_articles.rb +54 -0
  87. data/examples/munging/wikipedia/articles/verify_structure.rb +43 -0
  88. data/examples/munging/wikipedia/articles/wp2txt-LICENSE.txt +22 -0
  89. data/examples/munging/wikipedia/articles/wp2txt_article.rb +259 -0
  90. data/examples/munging/wikipedia/articles/wp2txt_utils.rb +452 -0
  91. data/examples/munging/wikipedia/dbpedia/dbpedia_common.rb +5 -0
  92. data/examples/munging/wikipedia/dbpedia/dbpedia_extract_geocoordinates.rb +78 -0
  93. data/examples/munging/wikipedia/dbpedia/extract_links-cruft.rb +66 -0
  94. data/examples/munging/wikipedia/dbpedia/extract_links.rb +260 -0
  95. data/examples/munging/wikipedia/dbpedia/sameas_extractor.rb +20 -0
  96. data/examples/rake_helper.rb +97 -0
  97. data/examples/ruby_project/Gemfile +6 -0
  98. data/examples/ruby_project/README.md +6 -0
  99. data/examples/ruby_project/a/b/c/.gitkeep +0 -0
  100. data/examples/server_logs/geo_ip_mapping/munge_geolite.rb +82 -0
  101. data/examples/server_logs/logline.rb +95 -0
  102. data/examples/server_logs/models.rb +66 -0
  103. data/examples/server_logs/page_counts.pig +48 -0
  104. data/examples/server_logs/server_logs-01-parse-script.rb +13 -0
  105. data/examples/server_logs/server_logs-02-histograms-full.rb +33 -0
  106. data/examples/server_logs/server_logs-02-histograms-mapper.rb +14 -0
  107. data/examples/server_logs/server_logs-03-breadcrumbs-full.rb +71 -0
  108. data/examples/server_logs/server_logs-04-page_page_edges-full.rb +40 -0
  109. data/examples/serverlogs/geo_ip_mapping/munge_geolite.rb +82 -0
  110. data/examples/serverlogs/models/logline.rb +102 -0
  111. data/examples/serverlogs/parser/apache_parser_widget.rb +46 -0
  112. data/examples/serverlogs/visit_paths/common.rb +4 -0
  113. data/examples/serverlogs/visit_paths/page_counts.pig +48 -0
  114. data/examples/serverlogs/visit_paths/serverlogs-01-parse-script.rb +11 -0
  115. data/examples/serverlogs/visit_paths/serverlogs-02-histograms-full.rb +31 -0
  116. data/examples/serverlogs/visit_paths/serverlogs-02-histograms-mapper.rb +12 -0
  117. data/examples/serverlogs/visit_paths/serverlogs-03-breadcrumbs-full.rb +67 -0
  118. data/examples/serverlogs/visit_paths/serverlogs-04-page_page_edges-full.rb +38 -0
  119. data/examples/splitter.rb +94 -0
  120. data/examples/string_reverser.rb +7 -0
  121. data/examples/text/pig_latin/pig_latinizer.rb +35 -0
  122. data/examples/text/pig_latin/pig_latinizer_widget.rb +16 -0
  123. data/examples/text/regional_flavor/README.md +14 -0
  124. data/examples/text/regional_flavor/article_wordbags.pig +39 -0
  125. data/examples/text/regional_flavor/j01-article_wordbags.rb +4 -0
  126. data/examples/text/regional_flavor/simple_pig_script.pig +27 -0
  127. data/examples/twitter.rb +5 -0
  128. data/lib/hanuman.rb +36 -0
  129. data/lib/hanuman/graph.rb +97 -0
  130. data/lib/hanuman/graphvizzer.rb +206 -0
  131. data/lib/hanuman/graphvizzer/gv_models.rb +161 -0
  132. data/lib/hanuman/graphvizzer/gv_presenter.rb +97 -0
  133. data/lib/hanuman/link.rb +35 -0
  134. data/lib/hanuman/registry.rb +46 -0
  135. data/lib/hanuman/stage.rb +128 -0
  136. data/lib/hanuman/tree.rb +67 -0
  137. data/lib/wu/geo.rb +4 -0
  138. data/lib/wu/geo/geo_grids.numbers +0 -0
  139. data/lib/wu/geo/geolocated.rb +331 -0
  140. data/lib/wu/geo/quadtile.rb +69 -0
  141. data/lib/wu/graph/union_find.rb +62 -0
  142. data/lib/wu/model/reconcilable.rb +63 -0
  143. data/lib/wu/munging.rb +71 -0
  144. data/lib/wu/social/models/twitter.rb +31 -0
  145. data/lib/wu/wikipedia/models.rb +20 -0
  146. data/lib/wukong.rb +54 -0
  147. data/lib/wukong/dataflow.rb +43 -0
  148. data/lib/wukong/doc_helpers.rb +14 -0
  149. data/lib/wukong/doc_helpers/dataflow_handler.rb +29 -0
  150. data/lib/wukong/doc_helpers/field_handler.rb +91 -0
  151. data/lib/wukong/doc_helpers/processor_handler.rb +29 -0
  152. data/lib/wukong/driver.rb +214 -0
  153. data/lib/wukong/driver/event_machine_driver.rb +15 -0
  154. data/lib/wukong/driver/wiring.rb +68 -0
  155. data/lib/wukong/local.rb +42 -0
  156. data/lib/wukong/local/runner.rb +96 -0
  157. data/lib/wukong/local/stdio_driver.rb +104 -0
  158. data/lib/wukong/logger.rb +102 -0
  159. data/lib/wukong/model/faker.rb +136 -0
  160. data/lib/wukong/model/flatpack_parser/flat.rb +60 -0
  161. data/lib/wukong/model/flatpack_parser/flatpack.rb +4 -0
  162. data/lib/wukong/model/flatpack_parser/lang.rb +46 -0
  163. data/lib/wukong/model/flatpack_parser/parser.rb +55 -0
  164. data/lib/wukong/model/flatpack_parser/tokens.rb +130 -0
  165. data/lib/wukong/plugin.rb +48 -0
  166. data/lib/wukong/processor.rb +110 -0
  167. data/lib/wukong/rake_helper.rb +6 -0
  168. data/lib/wukong/runner.rb +169 -0
  169. data/lib/wukong/runner/boot_sequence.rb +123 -0
  170. data/lib/wukong/runner/code_loader.rb +52 -0
  171. data/lib/wukong/runner/command_runner.rb +44 -0
  172. data/lib/wukong/runner/deploy_pack_loader.rb +75 -0
  173. data/lib/wukong/runner/help_message.rb +42 -0
  174. data/lib/wukong/source.rb +33 -0
  175. data/lib/wukong/source/source_driver.rb +74 -0
  176. data/lib/wukong/source/source_runner.rb +38 -0
  177. data/lib/wukong/spec_helpers.rb +74 -0
  178. data/lib/wukong/spec_helpers/integration_tests.rb +150 -0
  179. data/lib/wukong/spec_helpers/integration_tests/integration_test_matchers.rb +207 -0
  180. data/lib/wukong/spec_helpers/integration_tests/integration_test_runner.rb +97 -0
  181. data/lib/wukong/spec_helpers/shared_examples.rb +22 -0
  182. data/lib/wukong/spec_helpers/unit_tests.rb +135 -0
  183. data/lib/wukong/spec_helpers/unit_tests/unit_test_driver.rb +132 -0
  184. data/lib/wukong/spec_helpers/unit_tests/unit_test_matchers.rb +169 -0
  185. data/lib/wukong/spec_helpers/unit_tests/unit_test_runner.rb +60 -0
  186. data/lib/wukong/version.rb +3 -0
  187. data/lib/wukong/widget/echo.rb +55 -0
  188. data/lib/wukong/widget/extract.rb +122 -0
  189. data/lib/wukong/widget/filters.rb +452 -0
  190. data/lib/wukong/widget/logger.rb +56 -0
  191. data/lib/wukong/widget/operators.rb +82 -0
  192. data/lib/wukong/widget/reducers.rb +10 -0
  193. data/lib/wukong/widget/reducers/accumulator.rb +73 -0
  194. data/lib/wukong/widget/reducers/bin.rb +368 -0
  195. data/lib/wukong/widget/reducers/count.rb +73 -0
  196. data/lib/wukong/widget/reducers/group.rb +128 -0
  197. data/lib/wukong/widget/reducers/group_concat.rb +98 -0
  198. data/lib/wukong/widget/reducers/improver.rb +71 -0
  199. data/lib/wukong/widget/reducers/join_xml.rb +37 -0
  200. data/lib/wukong/widget/reducers/moments.rb +72 -0
  201. data/lib/wukong/widget/reducers/sort.rb +180 -0
  202. data/lib/wukong/widget/reducers/uniq.rb +91 -0
  203. data/lib/wukong/widget/serializers.rb +317 -0
  204. data/lib/wukong/widget/utils.rb +46 -0
  205. data/lib/wukong/widgets.rb +7 -0
  206. data/spec/examples/dataflow/fibonacci_series_spec.rb +18 -0
  207. data/spec/examples/dataflow/parse_apache_logs_spec.rb +8 -0
  208. data/spec/examples/dataflow/parsing_spec.rb +14 -0
  209. data/spec/examples/dataflow/simple_spec.rb +34 -0
  210. data/spec/examples/dataflow/telegram_spec.rb +43 -0
  211. data/spec/examples/graph/minimum_spanning_tree_spec.rb +34 -0
  212. data/spec/examples/munging/airline_flights/identifiers_spec.rb +16 -0
  213. data/spec/examples/munging/airline_flights_spec.rb +202 -0
  214. data/spec/examples/text/pig_latin_spec.rb +18 -0
  215. data/spec/examples/workflow/cherry_pie_spec.rb +36 -0
  216. data/spec/hanuman/graph_spec.rb +119 -0
  217. data/spec/hanuman/hanuman_spec.rb +10 -0
  218. data/spec/hanuman/registry_spec.rb +123 -0
  219. data/spec/hanuman/stage_spec.rb +81 -0
  220. data/spec/hanuman/tree_spec.rb +119 -0
  221. data/spec/spec.opts +1 -0
  222. data/spec/spec_helper.rb +43 -0
  223. data/spec/support/example_test_helpers.rb +95 -0
  224. data/spec/support/hanuman_test_helpers.rb +92 -0
  225. data/spec/support/integration_helper.rb +38 -0
  226. data/spec/support/model_test_helpers.rb +115 -0
  227. data/spec/support/shared_context_for_graphs.rb +57 -0
  228. data/spec/support/shared_context_for_reducers.rb +37 -0
  229. data/spec/support/shared_examples_for_builders.rb +94 -0
  230. data/spec/support/shared_examples_for_shortcuts.rb +57 -0
  231. data/spec/wu/model/reconcilable_spec.rb +152 -0
  232. data/spec/wukong/dataflow_spec.rb +87 -0
  233. data/spec/wukong/driver_spec.rb +154 -0
  234. data/spec/wukong/local/runner_spec.rb +29 -0
  235. data/spec/wukong/local/stdio_driver_spec.rb +73 -0
  236. data/spec/wukong/local_spec.rb +6 -0
  237. data/spec/wukong/logger_spec.rb +49 -0
  238. data/spec/wukong/model/faker_spec.rb +132 -0
  239. data/spec/wukong/processor_spec.rb +21 -0
  240. data/spec/wukong/runner_spec.rb +132 -0
  241. data/spec/wukong/source_spec.rb +6 -0
  242. data/spec/wukong/widget/extract_spec.rb +101 -0
  243. data/spec/wukong/widget/filters_spec.rb +79 -0
  244. data/spec/wukong/widget/logger_spec.rb +23 -0
  245. data/spec/wukong/widget/operators_spec.rb +25 -0
  246. data/spec/wukong/widget/reducers/bin_spec.rb +92 -0
  247. data/spec/wukong/widget/reducers/count_spec.rb +11 -0
  248. data/spec/wukong/widget/reducers/group_spec.rb +21 -0
  249. data/spec/wukong/widget/reducers/join_xml_spec.rb +25 -0
  250. data/spec/wukong/widget/reducers/moments_spec.rb +36 -0
  251. data/spec/wukong/widget/reducers/sort_spec.rb +26 -0
  252. data/spec/wukong/widget/reducers/uniq_spec.rb +14 -0
  253. data/spec/wukong/widget/serializers_spec.rb +114 -0
  254. data/spec/wukong/widget/sink_spec.rb +19 -0
  255. data/spec/wukong/widget/source_spec.rb +65 -0
  256. data/spec/wukong/wu-local_spec.rb +109 -0
  257. data/spec/wukong/wu-source_spec.rb +32 -0
  258. data/spec/wukong/wu_spec.rb +14 -0
  259. data/spec/wukong/wukong_spec.rb +10 -0
  260. data/wukong.gemspec +35 -0
  261. metadata +465 -0
@@ -0,0 +1,67 @@
1
+ require 'tsort'
2
+ module Hanuman
3
+
4
+ module TreeInstanceMethods
5
+ include TSort
6
+
7
+ MultipleRoots = Class.new(TSort::Cyclic)
8
+
9
+ def tsort_each_node(&blk)
10
+ stages.keys.each(&blk)
11
+ end
12
+
13
+ def tsort_each_child(label, &blk)
14
+ links.select { |link| link.into == label }.map(&:from).each(&blk)
15
+ end
16
+
17
+ def directed_sort() self.tsort ; end
18
+
19
+ def each_stage &blk
20
+ directed_sort.map { |label| stages[label]}.compact.each(&blk)
21
+ end
22
+
23
+ def root stage=nil
24
+ return stages[directed_sort.first] unless stage
25
+ return stage unless ancestor(stage)
26
+ self.root(ancestor(stage))
27
+ end
28
+
29
+ def ancestor(stage)
30
+ ancestors(stage).first
31
+ end
32
+
33
+ def leaves
34
+ the_leaves = (descendents - ancestors)
35
+ the_leaves.empty? ? [root] : the_leaves
36
+ end
37
+
38
+ def add_link type, from, into
39
+ return if has_link?(from, into)
40
+ raise TSort::Cyclic.new("Cannot link from a stage <#{from.label}> to itself") if into == from
41
+ raise MultipleRoots.new("Cannot link from <#{from.label}> to <#{into.label}> because <#{into.label}> aleady has an ancestor <#{ancestor(into).label}>") if ancestor(into)
42
+ raise TSort::Cyclic.new("Cannot link from leaf <#{from.label}> to the root <#{into.label}>") if into == root && leaves.include?(from)
43
+ super(type, from, into)
44
+ end
45
+
46
+ def prepend stage
47
+ add_link(:simple, stage, root)
48
+ end
49
+
50
+ def append stage
51
+ leaves.each do |leaf|
52
+ stage_for_leaf = stage.clone
53
+ stage_for_leaf.label = "#{stage_for_leaf.label}_for_#{leaf.label}".to_sym
54
+ add_link(:simple, leaf, stage_for_leaf)
55
+ end
56
+ end
57
+
58
+ end
59
+
60
+ class Tree < Graph
61
+ include TreeInstanceMethods
62
+ end
63
+
64
+ class TreeBuilder < GraphBuilder
65
+ include TreeInstanceMethods
66
+ end
67
+ end
@@ -0,0 +1,4 @@
1
+
2
+ require 'gorillib/data_munging'
3
+ require_relative 'geo/geolocated'
4
+ require_relative 'geo/quadtile'
@@ -0,0 +1,331 @@
1
+ require 'gorillib/numeric/clamp'
2
+
3
+ Numeric.class_eval do
4
+ def to_radians() self.to_f * Math::PI / 180.0 ; end
5
+ def to_degrees() self.to_f * 180.0 / Math::PI ; end
6
+ end
7
+
8
+ module Wukong
9
+ #
10
+ # reference: [Bing Maps Tile System](http://msdn.microsoft.com/en-us/library/bb259689.aspx)
11
+ #
12
+ module Geolocated
13
+ module_function # call methods as eg Wukong::Geolocated.tile_xy_to_quadkey or, if included in class, on self as private methods
14
+
15
+ # field :longitude, type: Float, description: "Longitude (X) of a point, in decimal degrees"
16
+ # field :latitude, type: Float, description: "Latitude (Y) of a point, in decimal degrees"
17
+ # field :zoom_level, type: Integer, description: "Zoom level of tile to fetch. An integer between 0 (world) and 16 or so"
18
+ # field :quadkey, type: String, description: "Quadkey of tile, eg 002313012"
19
+ # field :tile_x, type: Integer, description: "Tile X index, an integer between 0 and 2^zoom_level - 1"
20
+ # field :tile_y, type: Integer, description: "Tile Y index, an integer between 0 and 2^zoom_level - 1"
21
+
22
+ module ByCoordinates
23
+ extend Gorillib::Concern
24
+
25
+ # The quadkey is a string of 2-bit tile selectors for a quadtile
26
+ #
27
+ # @example
28
+ # infochimps_hq = Geo::Place.receive("Infochimps HQ", -97.759003, 30.273884)
29
+ # infochimps_hq.quadkey(8) # => "02313012"
30
+ #
31
+ # Interesting quadkey properties:
32
+ #
33
+ # * The quadkey length is its zoom level
34
+ #
35
+ # * To zoom out (lower zoom level, larger quadtile), just truncate the
36
+ # quadkey: austin at ZL=8 has quadkey "02313012"; at ZL=3, "023"
37
+ #
38
+ # * Nearby points typically have "nearby" quadkeys: up to the smallest
39
+ # tile that contains both, their quadkeys will have a common prefix.
40
+ # If you sort your records by quadkey,
41
+ # - Nearby points are nearby-ish on disk. (hello, HBase/Cassandra
42
+ # database owners!) This allows efficient lookup and caching of
43
+ # "popular" regions or repeated queries in an area.
44
+ # - the tiles covering a region can be covered by a limited, enumerable
45
+ # set of range scans. For map-reduce programmers, this leads to very
46
+ # efficient reducers
47
+ #
48
+ # * The quadkey is the bit-interleaved combination of its tile ids:
49
+ #
50
+ # tile_x 58 binary 0 0 1 1 1 0 1 0
51
+ # tile_y 105 binary 0 1 1 0 1 0 0 1
52
+ # interleaved binary 00 10 11 01 11 00 01 10
53
+ # quadkey 0 2 3 1 3 0 1 2 # "02313012"
54
+ #
55
+ def quadkey(zl) ; Wukong::Geolocated.tile_xy_zl_to_quadkey( tile_x(zl), tile_y(zl), zl) ; end
56
+
57
+ # the packed quadkey is the integer formed by interleaving the bits of tile_x with tile_y:
58
+ #
59
+ # tile_x 58 binary 0 0 1 1 1 0 1 0
60
+ # tile_y 105 binary 0 1 1 0 1 0 0 1
61
+ # interleaved binary 00 10 11 01 11 00 01 10
62
+ # quadkey 0 2 3 1 3 0 1 2 # "02313012"
63
+ #
64
+ # (see `quadkey` for more.)
65
+ #
66
+ # At zoom level 15, the packed quadkey is a 30-bit unsigned integer --
67
+ # meaning you can store it in a pig `int`; for languages with an `unsigned
68
+ # int` type, you can go to zoom level 16 before you have to use a
69
+ # less-efficient type. Zoom level 15 has a resolution of about one tile
70
+ # per kilometer (about 1.25 km/tile near the equator; 0.75 km/tile at
71
+ # London's latitude). It takes 1 billion tiles to tile the world at that
72
+ # scale. Ruby's integer type goes up to 60 bits, enough for any practical
73
+ # zoom level.
74
+ #
75
+ def packed_qk ; Wukong::Geolocated.tile_xy_zl_to_packed_qk(tile_x(zl), tile_y(zl), zl) ; end
76
+
77
+ # @return [Float] x index of the tile this object lies on at given zoom level
78
+ def tile_xf(zl) ; Wukong::Geolocated.lng_zl_to_tile_xf(longitude, zl) ; end
79
+ # @return [Float] y index of the tile this object lies on at given zoom level
80
+ def tile_yf(zl) ; Wukong::Geolocated.lat_zl_to_tile_yf(latitude, zl) ; end
81
+ # @return [Integer] x index of the tile this object lies on at given zoom level
82
+ def tile_x(zl) ; tile_xf(zl).floor ; end
83
+ # @return [Integer] y index of the tile this object lies on at given zoom level
84
+ def tile_y(zl) ; tile_yf(zl).floor ; end
85
+
86
+ # @return [Float] tile coordinates `(x,y)` for this object at given zoom level
87
+ def tile_xy(zl) ; [tile_x(xl), tile_y(zl)] ; end
88
+
89
+ # @returns [Array<Numeric, Numeric>] a `[longitude, latitude]` pair representing object as a point.
90
+ def lng_lat ; [longitude, latitude] ; end
91
+
92
+ # @returns [left, btm, right, top]
93
+ def bbox_for_radius(radius) ; Wukong::Geolocated.lng_lat_rad_to_bbox(longitude, latitude, radius) ; end
94
+ end
95
+
96
+ EARTH_RADIUS = 6371000 # meters
97
+ MIN_LONGITUDE = -180
98
+ MAX_LONGITUDE = 180
99
+ MIN_LATITUDE = -85.05112878
100
+ MAX_LATITUDE = 85.05112878
101
+ ALLOWED_LONGITUDE = (MIN_LONGITUDE..MAX_LONGITUDE)
102
+ ALLOWED_LATITUDE = (MIN_LATITUDE..MAX_LATITUDE)
103
+ TILE_PIXEL_SIZE = 256
104
+
105
+ # Width or height in number of tiles
106
+ def map_tile_size(zl)
107
+ 1 << zl
108
+ end
109
+
110
+ #
111
+ # Tile coordinates
112
+ #
113
+
114
+ # Convert longitude in degrees to _floating-point_ tile x,y coordinates at given zoom level
115
+ def lng_zl_to_tile_xf(longitude, zl)
116
+ raise ArgumentError, "longitude must be within bounds ((#{longitude}) vs #{ALLOWED_LONGITUDE})" unless (ALLOWED_LONGITUDE.include?(longitude))
117
+ xx = (longitude.to_f + 180.0) / 360.0
118
+ (map_tile_size(zl) * xx)
119
+ end
120
+
121
+ # Convert latitude in degrees to _floating-point_ tile x,y coordinates at given zoom level
122
+ def lat_zl_to_tile_yf(latitude, zl)
123
+ raise ArgumentError, "latitude must be within bounds ((#{latitude}) vs #{ALLOWED_LATITUDE})" unless (ALLOWED_LATITUDE.include?(latitude))
124
+ sin_lat = Math.sin(latitude.to_radians)
125
+ yy = Math.log((1 + sin_lat) / (1 - sin_lat)) / (4 * Math::PI)
126
+ (map_tile_size(zl) * (0.5 - yy))
127
+ end
128
+
129
+ # Convert latitude in degrees to integer tile x,y coordinates at given zoom level
130
+ def lng_lat_zl_to_tile_xy(longitude, latitude, zl)
131
+ [lng_zl_to_tile_xf(longitude, zl).floor, lat_zl_to_tile_yf(latitude, zl).floor]
132
+ end
133
+
134
+ # Convert from tile_x, tile_y, zoom level to longitude and latitude in
135
+ # degrees (slight loss of precision).
136
+ #
137
+ # Tile coordinates may be floats or integer; they must lie within map range.
138
+ def tile_xy_zl_to_lng_lat(tile_x, tile_y, zl)
139
+ tile_size = map_tile_size(zl)
140
+ raise ArgumentError, "tile index must be within bounds ((#{tile_x},#{tile_y}) vs #{tile_size})" unless ((0..(tile_size-1)).include?(tile_x)) && ((0..(tile_size-1)).include?(tile_x))
141
+ xx = (tile_x.to_f / tile_size)
142
+ yy = 0.5 - (tile_y.to_f / tile_size)
143
+ lng = 360.0 * xx - 180.0
144
+ lat = 90 - 360 * Math.atan(Math.exp(-yy * 2 * Math::PI)) / Math::PI
145
+ [lng, lat]
146
+ end
147
+
148
+ #
149
+ # Quadkey coordinates
150
+ #
151
+
152
+ # converts from even/odd state of tile x and tile y to quadkey. NOTE: bit order means y, x
153
+ BIT_TO_QUADKEY = { [false, false] => "0", [false, true] => "1", [true, false] => "2", [true, true] => "3", }
154
+ # converts from quadkey char to bits. NOTE: bit order means y, x
155
+ QUADKEY_TO_BIT = { "0" => [0,0], "1" => [0,1], "2" => [1,0], "3" => [1,1]}
156
+
157
+ # Convert from tile x,y into a quadkey at a specified zoom level
158
+ def tile_xy_zl_to_quadkey(tile_x, tile_y, zl)
159
+ quadkey_chars = []
160
+ tx = tile_x.to_i
161
+ ty = tile_y.to_i
162
+ zl.times do
163
+ quadkey_chars.push BIT_TO_QUADKEY[[ty.odd?, tx.odd?]] # bit order y,x
164
+ tx >>= 1 ; ty >>= 1
165
+ end
166
+ quadkey_chars.join.reverse
167
+ end
168
+
169
+ # Convert a quadkey into tile x,y coordinates and level
170
+ def quadkey_to_tile_xy_zl(quadkey)
171
+ raise ArgumentError, "Quadkey must contain only the characters 0, 1, 2 or 3: #{quadkey}!" unless quadkey =~ /\A[0-3]*\z/
172
+ zl = quadkey.to_s.length
173
+ tx = 0 ; ty = 0
174
+ quadkey.chars.each do |char|
175
+ ybit, xbit = QUADKEY_TO_BIT[char] # bit order y, x
176
+ tx = (tx << 1) + xbit
177
+ ty = (ty << 1) + ybit
178
+ end
179
+ [tx, ty, zl]
180
+ end
181
+
182
+ # Convert from tile x,y into a packed quadkey at a specified zoom level
183
+ def tile_xy_zl_to_packed_qk(tile_x, tile_y, zl)
184
+ # don't optimize unless you're sure your way is faster; string ops are
185
+ # faster than you think and loops are slower than you think
186
+ quadkey_str = tile_xy_zl_to_quadkey(tile_x, tile_y, zl)
187
+ quadkey_str.to_i(4)
188
+ end
189
+
190
+ # Convert a packed quadkey (integer) into tile x,y coordinates and level
191
+ def packed_qk_zl_to_tile_xy(packed_qk, zl=16)
192
+ # don't "optimize" this without testing... string operations are faster than you think in ruby
193
+ raise ArgumentError, "Quadkey must be an integer in range of the zoom level: #{packed_qk}, #{zl}" unless packed_qk.is_a?(Fixnum) && (packed_qk < 2 ** (zl*2))
194
+ quadkey_rhs = packed_qk.to_s(4)
195
+ quadkey = ("0" * (zl - quadkey_rhs.length)) << quadkey_rhs
196
+ quadkey_to_tile_xy_zl(quadkey)
197
+ end
198
+
199
+ # Convert a lat/lng and zoom level into a quadkey
200
+ def lng_lat_zl_to_quadkey(longitude, latitude, zl)
201
+ tile_x, tile_y = lng_lat_zl_to_tile_xy(longitude, latitude, zl)
202
+ tile_xy_zl_to_quadkey(tile_x, tile_y, zl)
203
+ end
204
+
205
+ #
206
+ # Bounding box coordinates
207
+ #
208
+
209
+ # Convert a quadkey into a bounding box using adjacent tile
210
+ def quadkey_to_bbox(quadkey)
211
+ tile_x, tile_y, zl = quadkey_to_tile_xy_zl(quadkey)
212
+ # bottom right of me is top left of my southeast neighbor
213
+ left, top = tile_xy_zl_to_lng_lat(tile_x, tile_y, zl)
214
+ right, btm = tile_xy_zl_to_lng_lat(tile_x + 1, tile_y + 1, zl)
215
+ [left, btm, right, top]
216
+ end
217
+
218
+ # Retuns the smallest quadkey containing both of corners of the given bounding box
219
+ def quadkey_containing_bbox(left, btm, right, top)
220
+ qk_tl = lng_lat_zl_to_quadkey(left, top, 23)
221
+ qk_2 = lng_lat_zl_to_quadkey(right, btm, 23)
222
+ # the containing qk is the longest one that both agree on
223
+ containing_key = ""
224
+ qk_tl.chars.zip(qk_2.chars).each do |char_tl, char_2|
225
+ break if char_tl != char_2
226
+ containing_key << char_tl
227
+ end
228
+ containing_key
229
+ end
230
+
231
+ # Returns a bounding box containing the circle created by the lat/lng and radius
232
+ def lng_lat_rad_to_bbox(longitude, latitude, radius)
233
+ left, _ = point_east( longitude, latitude, -radius)
234
+ _, btm = point_north(longitude, latitude, -radius)
235
+ right, _ = point_east( longitude, latitude, radius)
236
+ _, top = point_north(longitude, latitude, radius)
237
+ [left, btm, right, top]
238
+ end
239
+
240
+ # Returns the centroid of a bounding box
241
+ #
242
+ # @param [Array<Float, Float>] left_btm Longitude, Latitude of SW point
243
+ # @param [Array<Float, Float>] right_top Longitude, Latitude of NE point
244
+ #
245
+ # @return [Array<Float, Float>] Longitude, Latitude of centroid
246
+ def bbox_centroid(left_btm, right_top)
247
+ haversine_midpoint(*left_btm, *right_top)
248
+ end
249
+
250
+ # Return the haversine distance in meters between two points
251
+ def haversine_distance(left, btm, right, top)
252
+ delta_lng = (right - left).abs.to_radians
253
+ delta_lat = (top - btm ).abs.to_radians
254
+ btm_rad = btm.to_radians
255
+ top_rad = top.to_radians
256
+
257
+ aa = (Math.sin(delta_lat / 2.0))**2 + Math.cos(top_rad) * Math.cos(btm_rad) * (Math.sin(delta_lng / 2.0))**2
258
+ cc = 2.0 * Math.atan2(Math.sqrt(aa), Math.sqrt(1.0 - aa))
259
+ cc * EARTH_RADIUS
260
+ end
261
+
262
+ # Return the haversine midpoint in meters between two points
263
+ def haversine_midpoint(left, btm, right, top)
264
+ cos_btm = Math.cos(btm.to_radians)
265
+ cos_top = Math.cos(top.to_radians)
266
+ bearing_x = cos_btm * Math.cos((right - left).to_radians)
267
+ bearing_y = cos_btm * Math.sin((right - left).to_radians)
268
+ mid_lat = Math.atan2(
269
+ (Math.sin(top.to_radians) + Math.sin(btm.to_radians)),
270
+ (Math.sqrt((cos_top + bearing_x)**2 + bearing_y**2)))
271
+ mid_lng = left.to_radians + Math.atan2(bearing_y, (cos_top + bearing_x))
272
+ [mid_lng.to_degrees, mid_lat.to_degrees]
273
+ end
274
+
275
+ # From a given point, calculate the point directly north a specified distance
276
+ def point_north(longitude, latitude, distance)
277
+ north_lat = (latitude.to_radians + (distance.to_f / EARTH_RADIUS)).to_degrees
278
+ [longitude, north_lat]
279
+ end
280
+
281
+ # From a given point, calculate the change in degrees directly east a given distance
282
+ def point_east(longitude, latitude, distance)
283
+ radius = EARTH_RADIUS * Math.sin(((Math::PI / 2.0) - latitude.to_radians.abs))
284
+ east_lng = (longitude.to_radians + (distance.to_f / radius)).to_degrees
285
+ [east_lng, latitude]
286
+ end
287
+
288
+ #
289
+ # Pixel coordinates
290
+ #
291
+ # Use with a standard (256x256 pixel) grid-based tileserver
292
+ #
293
+
294
+ # Width or height of grid bitmap in pixels at given zoom level
295
+ def map_pixel_size(zl)
296
+ TILE_PIXEL_SIZE * map_tile_size(zl)
297
+ end
298
+
299
+ # Return pixel resolution in meters per pixel at a specified latitude and zoom level
300
+ def pixel_resolution(latitude, zl)
301
+ lat = latitude.clamp(MIN_LATITUDE, MAX_LATITUDE)
302
+ Math.cos(lat.to_radians) * 2 * Math::PI * EARTH_RADIUS / map_pixel_size(zl).to_f
303
+ end
304
+
305
+ # Map scale at a specified latitude, zoom level, & screen resolution in dpi
306
+ def map_scale_for_dpi(latitude, zl, screen_dpi)
307
+ pixel_resolution(latitude, zl) * screen_dpi / 0.0254
308
+ end
309
+
310
+ # Convert from x,y pixel pair into tile x,y coordinates
311
+ def pixel_xy_to_tile_xy(pixel_x, pixel_y)
312
+ [pixel_x / TILE_PIXEL_SIZE, pixel_y / TILE_PIXEL_SIZE]
313
+ end
314
+
315
+ # Convert from x,y tile pair into pixel x,y coordinates (top left corner)
316
+ def tile_xy_to_pixel_xy(tile_x, tile_y)
317
+ [tile_x * TILE_PIXEL_SIZE, tile_y * TILE_PIXEL_SIZE]
318
+ end
319
+
320
+ def pixel_xy_zl_to_lng_lat(pixel_x, pixel_y, zl)
321
+ tile_xy_zl_to_lng_lat(pixel_x.to_f / TILE_PIXEL_SIZE, pixel_y.to_f / TILE_PIXEL_SIZE, zl)
322
+ end
323
+
324
+ def lng_lat_zl_to_pixel_xy(lng, lat, zl)
325
+ pixel_x = lng_zl_to_tile_xf(lng, zl)
326
+ pixel_y = lat_zl_to_tile_yf(lat, zl)
327
+ [(pixel_x * TILE_PIXEL_SIZE + 0.5).floor, (pixel_y * TILE_PIXEL_SIZE + 0.5).floor]
328
+ end
329
+
330
+ end
331
+ end
@@ -0,0 +1,69 @@
1
+ module Wukong
2
+ module Geo
3
+ class Quadtile
4
+ include Gorillib::Model
5
+ #
6
+ field :tile_x, Integer, position: 0, doc: "Tile X index, an integer between 0 and 2^zoom_level - 1"
7
+ field :tile_y, Integer, position: 1, doc: "Tile Y index, an integer between 0 and 2^zoom_level - 1"
8
+ field :zl, Integer, position: 2, doc: "Zoom level of tile to fetch. 0 is the world; 16 is about a kilometer."
9
+ field :slug, String, default: 'tile', doc: "Name, prefixed on saved tiles"
10
+
11
+ def quadkey ; Wukong::Geolocated.tile_xy_zl_to_quadkey( tile_x, tile_y, zl) ; end
12
+ def packed_qk ; Wukong::Geolocated.tile_xy_zl_to_packed_qk(tile_x, tile_y, zl) ; end
13
+
14
+ # Base of URL for map tile server; anything X/Y/Z.png-addressable works,
15
+ # eg `http://b.tile.openstreetmap.org`. Defaults to 'http://b.tile.stamen.com/toner-lite'`.
16
+ class_attribute :tileserver_url_base
17
+ self.tileserver_url_base = 'http://a.tile.stamen.com/toner-lite'
18
+
19
+ def self.from_whatever(hsh)
20
+ zl = hsh[:zl] ? hsh[:zl].to_i : nil
21
+ case
22
+ when hsh[:tile_x].present? && hsh[:tile_y].present? && zl.present?
23
+ tile_x, tile_y = [hsh[:tile_x], hsh[:tile_y]]
24
+ when hsh[:longitude].present? && hsh[:latitude].present? && zl.present?
25
+ tile_x, tile_y = Wukong::Geolocated.lng_lat_zl_to_tile_xy(hsh[:longitude], hsh[:latitude], zl)
26
+ when hsh[:quadkey].present?
27
+ quadkey = hsh[:quadkey]
28
+ quadkey = quadkey[0..zl] if zl.to_i > 0
29
+ tile_x, tile_y, zl = Wukong::Geolocated.quadkey_to_tile_xy_zl(quadkey)
30
+ else
31
+ raise ArgumentError, "You must supply keys for either `:longitude`, `:latitude` and `:zl`; `:tile_x`, `:tile_y` and `:zl`; or `:quadkey`: #{hsh.inspect}"
32
+ end
33
+ return new(tile_x, tile_y, zl, hsh.to_hash)
34
+ end
35
+
36
+ def self.tileserver_conn
37
+ @tileserver_conn = Faraday.new(:url => tileserver_url_base)
38
+ end
39
+
40
+ def tile_url
41
+ [tileserver_url_base, zl, tile_x, tile_y].join('/') << ".png"
42
+ end
43
+
44
+ # A
45
+ #
46
+ # @example
47
+ # qt = Quadtile.from_whatever(longitude: -97.759003, latitude: 30.273884, zl: 15)
48
+ # qt.slug # tile-15-64587
49
+ #
50
+ #
51
+ # @returns [String]
52
+ def basename(options={})
53
+ options = { sep: '-', ext: 'png'}
54
+ sep = options[:sep]
55
+ # "%s%s%02d%s%04d%s%04d.%s" % [slug, sep, zl, sep, tile_x, sep, tile_y, options[:ext]]
56
+ "%s/%02d/%s%s%s.%s" % [slug, zl, slug, sep, quadkey, options[:ext]]
57
+ end
58
+
59
+ # Fetch the contents of a map tile from a tileserver
60
+ #
61
+ # You are responsible for requiring the faraday library and its adapter
62
+ #
63
+ def fetch
64
+ self.class.tileserver_conn.get(tile_url)
65
+ end
66
+
67
+ end
68
+ end
69
+ end