atlas_engine 0.1.0

Sign up to get free protection for your applications and to get access to all the features.
Files changed (298) hide show
  1. checksums.yaml +7 -0
  2. data/README.md +123 -0
  3. data/Rakefile +20 -0
  4. data/app/assets/config/atlas_engine_manifest.js +3 -0
  5. data/app/assets/stylesheets/atlas_engine/application.css +15 -0
  6. data/app/concerns/atlas_engine/handles_blob.rb +26 -0
  7. data/app/concerns/atlas_engine/handles_interruption.rb +22 -0
  8. data/app/controllers/atlas_engine/application_controller.rb +7 -0
  9. data/app/controllers/atlas_engine/connectivity_controller.rb +21 -0
  10. data/app/controllers/atlas_engine/country_imports_controller.rb +73 -0
  11. data/app/controllers/atlas_engine/graphql_controller.rb +59 -0
  12. data/app/countries/atlas_engine/ar/country_profile.yml +9 -0
  13. data/app/countries/atlas_engine/at/address_importer/corrections/open_address/city_corrector.rb +23 -0
  14. data/app/countries/atlas_engine/at/country_profile.yml +24 -0
  15. data/app/countries/atlas_engine/at/index_configuration.yml +63 -0
  16. data/app/countries/atlas_engine/at/synonyms.yml +6 -0
  17. data/app/countries/atlas_engine/at/validation_transcriber/address_parser.rb +58 -0
  18. data/app/countries/atlas_engine/au/address_importer/open_address/filter.rb +26 -0
  19. data/app/countries/atlas_engine/au/address_importer/open_address/mapper.rb +41 -0
  20. data/app/countries/atlas_engine/au/country_profile.yml +13 -0
  21. data/app/countries/atlas_engine/au/synonyms.yml +209 -0
  22. data/app/countries/atlas_engine/au/validation_transcriber/address_parser.rb +121 -0
  23. data/app/countries/atlas_engine/be/country_profile.yml +12 -0
  24. data/app/countries/atlas_engine/bm/address_importer/corrections/open_address/city_alias_corrector.rb +38 -0
  25. data/app/countries/atlas_engine/bm/address_importer/open_address/mapper.rb +40 -0
  26. data/app/countries/atlas_engine/bm/country_profile.yml +12 -0
  27. data/app/countries/atlas_engine/br/country_profile.yml +4 -0
  28. data/app/countries/atlas_engine/ca/country_profile.yml +7 -0
  29. data/app/countries/atlas_engine/ca/synonyms.yml +1615 -0
  30. data/app/countries/atlas_engine/ch/address_importer/corrections/open_address/city_corrector.rb +29 -0
  31. data/app/countries/atlas_engine/ch/address_importer/corrections/open_address/locale_corrector.rb +74 -0
  32. data/app/countries/atlas_engine/ch/address_importer/open_address/mapper.rb +40 -0
  33. data/app/countries/atlas_engine/ch/country_profile.yml +15 -0
  34. data/app/countries/atlas_engine/ch/locales/de/country_profile.yml +15 -0
  35. data/app/countries/atlas_engine/ch/locales/de/index_configuration.yml +63 -0
  36. data/app/countries/atlas_engine/ch/locales/de/synonyms.yml +7 -0
  37. data/app/countries/atlas_engine/ch/locales/fr/synonyms.yml +21 -0
  38. data/app/countries/atlas_engine/cz/country_profile.yml +6 -0
  39. data/app/countries/atlas_engine/de/country_profile.yml +19 -0
  40. data/app/countries/atlas_engine/de/index_configuration.yml +64 -0
  41. data/app/countries/atlas_engine/de/synonyms.yml +2 -0
  42. data/app/countries/atlas_engine/de/validation_transcriber/address_parser.rb +19 -0
  43. data/app/countries/atlas_engine/dk/country_profile.yml +6 -0
  44. data/app/countries/atlas_engine/dk/synonyms.yml +3 -0
  45. data/app/countries/atlas_engine/dk/validation_transcriber/address_parser.rb +21 -0
  46. data/app/countries/atlas_engine/fo/country_profile.yml +5 -0
  47. data/app/countries/atlas_engine/fr/address_importer/corrections/open_address/city_corrector.rb +28 -0
  48. data/app/countries/atlas_engine/fr/country_profile.yml +13 -0
  49. data/app/countries/atlas_engine/fr/synonyms.yml +21 -0
  50. data/app/countries/atlas_engine/fr/validation_transcriber/address_parser.rb +34 -0
  51. data/app/countries/atlas_engine/gb/address_validation/es/query_builder.rb +98 -0
  52. data/app/countries/atlas_engine/gb/country_profile.yml +10 -0
  53. data/app/countries/atlas_engine/gb/validation_transcriber/full_address_parser.rb +164 -0
  54. data/app/countries/atlas_engine/gb/validation_transcriber/parsed_address.rb +120 -0
  55. data/app/countries/atlas_engine/gg/address_validation/validators/full_address/restrictions/unsupported_city.rb +39 -0
  56. data/app/countries/atlas_engine/gg/country_profile.yml +7 -0
  57. data/app/countries/atlas_engine/ie/country_profile.yml +3 -0
  58. data/app/countries/atlas_engine/it/address_importer/corrections/open_address/city_corrector.rb +27 -0
  59. data/app/countries/atlas_engine/it/address_importer/corrections/open_address/province_corrector.rb +29 -0
  60. data/app/countries/atlas_engine/it/address_importer/open_address/mapper.rb +42 -0
  61. data/app/countries/atlas_engine/it/country_profile.yml +11 -0
  62. data/app/countries/atlas_engine/jp/address_validation/es/data_mapper.rb +63 -0
  63. data/app/countries/atlas_engine/jp/country_profile.yml +6 -0
  64. data/app/countries/atlas_engine/kr/address_importer/open_address/mapper.rb +41 -0
  65. data/app/countries/atlas_engine/kr/country_profile.yml +11 -0
  66. data/app/countries/atlas_engine/li/address_importer/corrections/open_address/city_corrector.rb +25 -0
  67. data/app/countries/atlas_engine/li/country_profile.yml +21 -0
  68. data/app/countries/atlas_engine/li/index_configuration.yml +63 -0
  69. data/app/countries/atlas_engine/li/synonyms.yml +6 -0
  70. data/app/countries/atlas_engine/lt/country_profile.yml +6 -0
  71. data/app/countries/atlas_engine/lt/synonyms.yml +7 -0
  72. data/app/countries/atlas_engine/lt/validation_transcriber/address_parser.rb +24 -0
  73. data/app/countries/atlas_engine/lu/address_importer/corrections/open_address/locale_corrector.rb +54 -0
  74. data/app/countries/atlas_engine/lu/country_profile.yml +12 -0
  75. data/app/countries/atlas_engine/nl/address_importer/corrections/open_address/city_corrector.rb +25 -0
  76. data/app/countries/atlas_engine/nl/country_profile.yml +18 -0
  77. data/app/countries/atlas_engine/nl/index_configuration.yml +52 -0
  78. data/app/countries/atlas_engine/nl/synonyms.yml +92 -0
  79. data/app/countries/atlas_engine/nl/validation_transcriber/address_parser.rb +85 -0
  80. data/app/countries/atlas_engine/no/country_profile.yml +5 -0
  81. data/app/countries/atlas_engine/nz/country_profile.yml +3 -0
  82. data/app/countries/atlas_engine/pl/country_profile.yml +5 -0
  83. data/app/countries/atlas_engine/pl/validation_transcriber/address_parser.rb +19 -0
  84. data/app/countries/atlas_engine/pt/address_importer/corrections/open_address/city_corrector.rb +32 -0
  85. data/app/countries/atlas_engine/pt/address_importer/open_address/mapper.rb +39 -0
  86. data/app/countries/atlas_engine/pt/country_profile.yml +10 -0
  87. data/app/countries/atlas_engine/pt/synonyms.yml +7 -0
  88. data/app/countries/atlas_engine/sa/country_profile.yml +10 -0
  89. data/app/countries/atlas_engine/se/country_profile.yml +5 -0
  90. data/app/countries/atlas_engine/tt/address_importer/open_address/mapper.rb +38 -0
  91. data/app/countries/atlas_engine/tt/country_profile.yml +7 -0
  92. data/app/countries/atlas_engine/us/country_profile.yml +12 -0
  93. data/app/countries/atlas_engine/us/synonyms.yml +350 -0
  94. data/app/graphql/atlas_engine/errors/locale_unsupported_error.rb +17 -0
  95. data/app/graphql/atlas_engine/schema.graphql +1293 -0
  96. data/app/graphql/atlas_engine/schema.rb +23 -0
  97. data/app/graphql/atlas_engine/types/address_validation/address_input.rb +51 -0
  98. data/app/graphql/atlas_engine/types/address_validation/concern_type.rb +20 -0
  99. data/app/graphql/atlas_engine/types/address_validation/enums/concern_enum.rb +15 -0
  100. data/app/graphql/atlas_engine/types/address_validation/field_type.rb +15 -0
  101. data/app/graphql/atlas_engine/types/address_validation/suggestion_type.rb +21 -0
  102. data/app/graphql/atlas_engine/types/base_argument.rb +9 -0
  103. data/app/graphql/atlas_engine/types/base_enum.rb +9 -0
  104. data/app/graphql/atlas_engine/types/base_field.rb +10 -0
  105. data/app/graphql/atlas_engine/types/base_input_object.rb +9 -0
  106. data/app/graphql/atlas_engine/types/base_interface.rb +10 -0
  107. data/app/graphql/atlas_engine/types/base_object.rb +9 -0
  108. data/app/graphql/atlas_engine/types/base_scalar.rb +9 -0
  109. data/app/graphql/atlas_engine/types/base_union.rb +9 -0
  110. data/app/graphql/atlas_engine/types/matching_strategy_type.rb +12 -0
  111. data/app/graphql/atlas_engine/types/mutation_type.rb +9 -0
  112. data/app/graphql/atlas_engine/types/query_type.rb +61 -0
  113. data/app/graphql/atlas_engine/types/validation_supported_country.rb +12 -0
  114. data/app/graphql/atlas_engine/types/validation_type.rb +22 -0
  115. data/app/helpers/atlas_engine/address_importer/import_log_helper.rb +66 -0
  116. data/app/helpers/atlas_engine/application_helper.rb +7 -0
  117. data/app/helpers/atlas_engine/locale_format_helper.rb +40 -0
  118. data/app/helpers/atlas_engine/log_base.rb +32 -0
  119. data/app/helpers/atlas_engine/log_helper.rb +24 -0
  120. data/app/helpers/atlas_engine/metrics_helper.rb +25 -0
  121. data/app/jobs/atlas_engine/address_importer/clear_records_job.rb +39 -0
  122. data/app/jobs/atlas_engine/address_importer/open_address/geo_json_import_job.rb +212 -0
  123. data/app/jobs/atlas_engine/address_importer/open_address/geo_json_import_launcher_job.rb +67 -0
  124. data/app/jobs/atlas_engine/address_importer/open_address/prepares_geo_json_file.rb +41 -0
  125. data/app/jobs/atlas_engine/address_importer/resumable_import_job.rb +49 -0
  126. data/app/jobs/atlas_engine/address_importer/street_backfill_job.rb +63 -0
  127. data/app/jobs/atlas_engine/application_job.rb +10 -0
  128. data/app/jobs/atlas_engine/concerns/address_importer/handles_errors.rb +43 -0
  129. data/app/lib/atlas_engine/concern_formatter.rb +40 -0
  130. data/app/lib/atlas_engine/restrictions/base.rb +20 -0
  131. data/app/lib/atlas_engine/restrictions/unsupported_script.rb +31 -0
  132. data/app/lib/atlas_engine/validation_transcriber/address_parser_base.rb +201 -0
  133. data/app/lib/atlas_engine/validation_transcriber/address_parser_factory.rb +27 -0
  134. data/app/lib/atlas_engine/validation_transcriber/address_parser_north_america.rb +39 -0
  135. data/app/lib/atlas_engine/validation_transcriber/address_parser_oceanic.rb +17 -0
  136. data/app/lib/atlas_engine/validation_transcriber/address_parser_preprocessor.rb +132 -0
  137. data/app/lib/atlas_engine/validation_transcriber/address_parsing_helper.rb +38 -0
  138. data/app/lib/atlas_engine/validation_transcriber/address_parsings.rb +54 -0
  139. data/app/lib/atlas_engine/validation_transcriber/constants.rb +50 -0
  140. data/app/lib/atlas_engine/validation_transcriber/english_street_parser.rb +59 -0
  141. data/app/lib/atlas_engine/validation_transcriber/formatter.rb +46 -0
  142. data/app/lib/atlas_engine/validation_transcriber/french_street_parser.rb +50 -0
  143. data/app/lib/atlas_engine/validation_transcriber/province_code_normalizer.rb +45 -0
  144. data/app/lib/atlas_engine/validation_transcriber/street_parser.rb +18 -0
  145. data/app/lib/atlas_engine/validation_transcriber/zip_normalizer.rb +23 -0
  146. data/app/mailers/atlas_engine/application_mailer.rb +9 -0
  147. data/app/models/atlas_engine/address_importer/corrections/corrector.rb +33 -0
  148. data/app/models/atlas_engine/address_importer/import_events_notifier/base.rb +35 -0
  149. data/app/models/atlas_engine/address_importer/import_events_notifier/notifier.rb +26 -0
  150. data/app/models/atlas_engine/address_importer/open_address/default_mapper.rb +46 -0
  151. data/app/models/atlas_engine/address_importer/open_address/feature_helper.rb +110 -0
  152. data/app/models/atlas_engine/address_importer/open_address/filter.rb +17 -0
  153. data/app/models/atlas_engine/address_importer/open_address/loader.rb +27 -0
  154. data/app/models/atlas_engine/address_importer/open_address/transformer.rb +39 -0
  155. data/app/models/atlas_engine/address_importer/open_address.rb +10 -0
  156. data/app/models/atlas_engine/address_importer/validation/base_validator.rb +86 -0
  157. data/app/models/atlas_engine/address_importer/validation/default_validator.rb +27 -0
  158. data/app/models/atlas_engine/address_importer/validation/field_validations/city.rb +47 -0
  159. data/app/models/atlas_engine/address_importer/validation/field_validations/interface.rb +29 -0
  160. data/app/models/atlas_engine/address_importer/validation/field_validations/province.rb +73 -0
  161. data/app/models/atlas_engine/address_importer/validation/field_validations/zip.rb +84 -0
  162. data/app/models/atlas_engine/address_importer/validation/validator.rb +17 -0
  163. data/app/models/atlas_engine/address_importer/validation/wrapper.rb +70 -0
  164. data/app/models/atlas_engine/address_number.rb +36 -0
  165. data/app/models/atlas_engine/address_number_range.rb +200 -0
  166. data/app/models/atlas_engine/address_validation/abstract_address.rb +49 -0
  167. data/app/models/atlas_engine/address_validation/address.rb +47 -0
  168. data/app/models/atlas_engine/address_validation/candidate.rb +109 -0
  169. data/app/models/atlas_engine/address_validation/candidate_tuple.rb +15 -0
  170. data/app/models/atlas_engine/address_validation/concern.rb +74 -0
  171. data/app/models/atlas_engine/address_validation/concern_producer.rb +19 -0
  172. data/app/models/atlas_engine/address_validation/concern_queue.rb +20 -0
  173. data/app/models/atlas_engine/address_validation/concern_record.rb +122 -0
  174. data/app/models/atlas_engine/address_validation/datastore_base.rb +27 -0
  175. data/app/models/atlas_engine/address_validation/errors.rb +13 -0
  176. data/app/models/atlas_engine/address_validation/es/candidate_selector.rb +70 -0
  177. data/app/models/atlas_engine/address_validation/es/data_mappers/decompounding_data_mapper.rb +39 -0
  178. data/app/models/atlas_engine/address_validation/es/data_mappers/default_data_mapper.rb +110 -0
  179. data/app/models/atlas_engine/address_validation/es/datastore.rb +229 -0
  180. data/app/models/atlas_engine/address_validation/es/default_query_builder.rb +30 -0
  181. data/app/models/atlas_engine/address_validation/es/query_builder.rb +160 -0
  182. data/app/models/atlas_engine/address_validation/es/term_vectors.rb +78 -0
  183. data/app/models/atlas_engine/address_validation/es/validators/full_address.rb +123 -0
  184. data/app/models/atlas_engine/address_validation/es/validators/full_address_street.rb +18 -0
  185. data/app/models/atlas_engine/address_validation/es/validators/restriction_evaluator.rb +37 -0
  186. data/app/models/atlas_engine/address_validation/field.rb +30 -0
  187. data/app/models/atlas_engine/address_validation/full_address_validator_base.rb +27 -0
  188. data/app/models/atlas_engine/address_validation/log_emitter.rb +66 -0
  189. data/app/models/atlas_engine/address_validation/matching_strategies.rb +16 -0
  190. data/app/models/atlas_engine/address_validation/normalizer.rb +38 -0
  191. data/app/models/atlas_engine/address_validation/predicate_pipeline.rb +80 -0
  192. data/app/models/atlas_engine/address_validation/request.rb +12 -0
  193. data/app/models/atlas_engine/address_validation/result.rb +154 -0
  194. data/app/models/atlas_engine/address_validation/runs_validation.rb +16 -0
  195. data/app/models/atlas_engine/address_validation/session.rb +47 -0
  196. data/app/models/atlas_engine/address_validation/statsd_emitter.rb +72 -0
  197. data/app/models/atlas_engine/address_validation/strategies.rb +10 -0
  198. data/app/models/atlas_engine/address_validation/suggestion.rb +97 -0
  199. data/app/models/atlas_engine/address_validation/token/comparator.rb +44 -0
  200. data/app/models/atlas_engine/address_validation/token/comparison.rb +76 -0
  201. data/app/models/atlas_engine/address_validation/token/sequence/comparator.rb +158 -0
  202. data/app/models/atlas_engine/address_validation/token/sequence/comparison.rb +166 -0
  203. data/app/models/atlas_engine/address_validation/token/sequence.rb +147 -0
  204. data/app/models/atlas_engine/address_validation/token/synonyms.rb +77 -0
  205. data/app/models/atlas_engine/address_validation/token.rb +113 -0
  206. data/app/models/atlas_engine/address_validation/validator.rb +147 -0
  207. data/app/models/atlas_engine/address_validation/validators/full_address/address_comparison.rb +97 -0
  208. data/app/models/atlas_engine/address_validation/validators/full_address/candidate_result.rb +164 -0
  209. data/app/models/atlas_engine/address_validation/validators/full_address/candidate_result_base.rb +46 -0
  210. data/app/models/atlas_engine/address_validation/validators/full_address/comparison_helper.rb +135 -0
  211. data/app/models/atlas_engine/address_validation/validators/full_address/components_to_validate.rb +88 -0
  212. data/app/models/atlas_engine/address_validation/validators/full_address/concern_builder.rb +127 -0
  213. data/app/models/atlas_engine/address_validation/validators/full_address/exclusions/exclusion_base.rb +23 -0
  214. data/app/models/atlas_engine/address_validation/validators/full_address/invalid_zip_concern_builder.rb +42 -0
  215. data/app/models/atlas_engine/address_validation/validators/full_address/invalid_zip_for_country_concern.rb +37 -0
  216. data/app/models/atlas_engine/address_validation/validators/full_address/invalid_zip_for_province_concern.rb +37 -0
  217. data/app/models/atlas_engine/address_validation/validators/full_address/no_candidate_result.rb +26 -0
  218. data/app/models/atlas_engine/address_validation/validators/full_address/number_comparison.rb +31 -0
  219. data/app/models/atlas_engine/address_validation/validators/full_address/postal_code_matcher.rb +60 -0
  220. data/app/models/atlas_engine/address_validation/validators/full_address/result_updater.rb +42 -0
  221. data/app/models/atlas_engine/address_validation/validators/full_address/suggestion_builder.rb +140 -0
  222. data/app/models/atlas_engine/address_validation/validators/full_address/unknown_address_concern.rb +30 -0
  223. data/app/models/atlas_engine/address_validation/validators/full_address/unknown_province_concern.rb +38 -0
  224. data/app/models/atlas_engine/address_validation/validators/full_address/unknown_zip_for_address_concern.rb +32 -0
  225. data/app/models/atlas_engine/address_validation/validators/full_address/unmatched_field_concern.rb +84 -0
  226. data/app/models/atlas_engine/address_validation/validators/full_address/unsupported_script_result.rb +22 -0
  227. data/app/models/atlas_engine/address_validation/validators/predicates/cache.rb +38 -0
  228. data/app/models/atlas_engine/address_validation/validators/predicates/city/present.rb +36 -0
  229. data/app/models/atlas_engine/address_validation/validators/predicates/country/exists.rb +34 -0
  230. data/app/models/atlas_engine/address_validation/validators/predicates/country/valid_for_zip.rb +60 -0
  231. data/app/models/atlas_engine/address_validation/validators/predicates/no_emojis.rb +38 -0
  232. data/app/models/atlas_engine/address_validation/validators/predicates/no_html_tags.rb +39 -0
  233. data/app/models/atlas_engine/address_validation/validators/predicates/no_url.rb +38 -0
  234. data/app/models/atlas_engine/address_validation/validators/predicates/not_exceed_max_length.rb +34 -0
  235. data/app/models/atlas_engine/address_validation/validators/predicates/not_exceed_max_token_count.rb +63 -0
  236. data/app/models/atlas_engine/address_validation/validators/predicates/phone/valid.rb +41 -0
  237. data/app/models/atlas_engine/address_validation/validators/predicates/predicate.rb +37 -0
  238. data/app/models/atlas_engine/address_validation/validators/predicates/province/exists.rb +43 -0
  239. data/app/models/atlas_engine/address_validation/validators/predicates/province/valid_for_country.rb +48 -0
  240. data/app/models/atlas_engine/address_validation/validators/predicates/street/building_number_in_address1.rb +45 -0
  241. data/app/models/atlas_engine/address_validation/validators/predicates/street/building_number_in_address1_or_address2.rb +43 -0
  242. data/app/models/atlas_engine/address_validation/validators/predicates/street/present.rb +35 -0
  243. data/app/models/atlas_engine/address_validation/validators/predicates/zip/present.rb +58 -0
  244. data/app/models/atlas_engine/address_validation/validators/predicates/zip/valid_for_country.rb +45 -0
  245. data/app/models/atlas_engine/address_validation/validators/predicates/zip/valid_for_province.rb +55 -0
  246. data/app/models/atlas_engine/address_validation/validators/predicates/zip/zip_base.rb +25 -0
  247. data/app/models/atlas_engine/address_validation/zip_truncator.rb +32 -0
  248. data/app/models/atlas_engine/application_record.rb +8 -0
  249. data/app/models/atlas_engine/coded_error.rb +18 -0
  250. data/app/models/atlas_engine/coded_errors.rb +17 -0
  251. data/app/models/atlas_engine/country_import.rb +44 -0
  252. data/app/models/atlas_engine/country_profile.rb +270 -0
  253. data/app/models/atlas_engine/country_profile_ingestion_subset.rb +42 -0
  254. data/app/models/atlas_engine/country_profile_subset_base.rb +22 -0
  255. data/app/models/atlas_engine/country_profile_validation_subset.rb +48 -0
  256. data/app/models/atlas_engine/country_repository.rb +110 -0
  257. data/app/models/atlas_engine/elasticsearch/client.rb +116 -0
  258. data/app/models/atlas_engine/elasticsearch/client_interface.rb +89 -0
  259. data/app/models/atlas_engine/elasticsearch/repository.rb +246 -0
  260. data/app/models/atlas_engine/elasticsearch/repository_interface.rb +82 -0
  261. data/app/models/atlas_engine/elasticsearch/response.rb +20 -0
  262. data/app/models/atlas_engine/event.rb +12 -0
  263. data/app/models/atlas_engine/field_decompounder.rb +36 -0
  264. data/app/models/atlas_engine/index_configuration_factory.rb +188 -0
  265. data/app/models/atlas_engine/post_address.rb +114 -0
  266. data/app/models/atlas_engine/post_address_importer.rb +34 -0
  267. data/app/models/atlas_engine/services/service_helper.rb +21 -0
  268. data/app/models/atlas_engine/services/validation.rb +65 -0
  269. data/app/models/atlas_engine/services/validation_eligibility.rb +18 -0
  270. data/app/models/atlas_engine/street.rb +34 -0
  271. data/app/tasks/maintenance/atlas_engine/elasticsearch_index_create_task.rb +106 -0
  272. data/app/tasks/maintenance/atlas_engine/geo_json_import_task.rb +29 -0
  273. data/app/views/atlas_engine/connectivity/index.html.erb +50 -0
  274. data/app/views/atlas_engine/country_imports/index.html.erb +49 -0
  275. data/app/views/atlas_engine/country_imports/show.html.erb +73 -0
  276. data/app/views/layouts/atlas_engine/application.html.erb +15 -0
  277. data/config/initializers/1.ruby_patches.rb +18 -0
  278. data/config/initializers/sorbet.rb +5 -0
  279. data/config/initializers/worldwide.rb +5 -0
  280. data/config/locales/internal/en.yml +14 -0
  281. data/config/routes.rb +17 -0
  282. data/db/data/address_synonyms/index_configurations/default.yml +141 -0
  283. data/db/data/country_profiles/default.yml +23 -0
  284. data/db/data/transcriber.yml +760 -0
  285. data/db/data/validation_pipelines/es.yml +58 -0
  286. data/db/data/validation_pipelines/es_street.yml +58 -0
  287. data/db/data/validation_pipelines/local.yml +60 -0
  288. data/db/migrate/20230919173037_create_atlas_engine_post_addresses.rb +25 -0
  289. data/db/migrate/20231117142735_add_building_and_unit_ranges_column.rb +7 -0
  290. data/db/migrate/20231117143536_create_atlas_engine_country_imports.rb +11 -0
  291. data/db/migrate/20231117145844_create_atlas_engine_events_table.rb +13 -0
  292. data/db/migrate/20231123153554_add_unique_index_to_atlas_engine_post_addresses.rb +14 -0
  293. data/db/migrate/20231123154658_add_index_to_post_addresses_on_source_id_locale_country_code.rb +12 -0
  294. data/lib/atlas_engine/engine.rb +10 -0
  295. data/lib/atlas_engine/version.rb +6 -0
  296. data/lib/atlas_engine.rb +66 -0
  297. data/lib/tasks/atlas_engine/address_importer.rake +20 -0
  298. metadata +553 -0
@@ -0,0 +1,74 @@
1
+ # typed: strict
2
+ # frozen_string_literal: true
3
+
4
+ module AtlasEngine
5
+ module AddressValidation
6
+ class Concern
7
+ extend T::Sig
8
+
9
+ TYPES = T.let(
10
+ {
11
+ warning: "warning",
12
+ error: "error",
13
+ }.freeze,
14
+ T::Hash[Symbol, String],
15
+ )
16
+
17
+ sig { returns(Symbol) }
18
+ attr_reader :code
19
+
20
+ sig { returns(String) }
21
+ attr_reader :message
22
+
23
+ sig { returns(String) }
24
+ attr_reader :type
25
+
26
+ sig { returns(Integer) }
27
+ attr_reader :type_level
28
+
29
+ sig { returns(T::Array[String]) }
30
+ attr_reader :suggestion_ids
31
+
32
+ sig { returns(T::Array[Symbol]) }
33
+ attr_reader :field_names
34
+
35
+ sig { returns(T.nilable(Suggestion)) }
36
+ attr_reader :suggestion
37
+
38
+ alias_attribute :component_names, :field_names
39
+
40
+ sig do
41
+ params(
42
+ code: Symbol,
43
+ message: String,
44
+ type: String,
45
+ type_level: Integer,
46
+ suggestion_ids: T::Array[String],
47
+ field_names: T::Array[Symbol],
48
+ suggestion: T.nilable(Suggestion),
49
+ ).void
50
+ end
51
+ def initialize(code:, message:, type:, type_level:, suggestion_ids:, field_names:, suggestion: nil)
52
+ @code = code
53
+ @type = type
54
+ @type_level = type_level
55
+ @suggestion_ids = suggestion_ids
56
+ @field_names = field_names
57
+ @message = message
58
+ @suggestion = T.let(suggestion, T.nilable(Suggestion))
59
+ end
60
+
61
+ sig { returns(T::Hash[Symbol, T.untyped]) }
62
+ def attributes
63
+ {
64
+ field_names: field_names,
65
+ message: message,
66
+ code: code,
67
+ type: type,
68
+ type_level: type_level,
69
+ suggestion_ids: suggestion_ids,
70
+ }
71
+ end
72
+ end
73
+ end
74
+ end
@@ -0,0 +1,19 @@
1
+ # typed: true
2
+ # frozen_string_literal: true
3
+
4
+ module AtlasEngine
5
+ module AddressValidation
6
+ class ConcernProducer
7
+ class << self
8
+ extend T::Sig
9
+
10
+ sig { params(result: Result, context: Hash).void }
11
+ def add(result, context = {})
12
+ return if result.concerns.empty?
13
+
14
+ ConcernQueue.instance.queue.push(ConcernRecord.from_result(result, context))
15
+ end
16
+ end
17
+ end
18
+ end
19
+ end
@@ -0,0 +1,20 @@
1
+ # typed: strict
2
+ # frozen_string_literal: true
3
+
4
+ module AtlasEngine
5
+ module AddressValidation
6
+ class ConcernQueue
7
+ extend T::Sig
8
+ include Singleton
9
+
10
+ sig { returns(Queue) }
11
+ attr_reader :queue
12
+
13
+ sig { void }
14
+ def initialize
15
+ super
16
+ @queue = T.let(Queue.new, Queue)
17
+ end
18
+ end
19
+ end
20
+ end
@@ -0,0 +1,122 @@
1
+ # typed: strict
2
+ # frozen_string_literal: true
3
+
4
+ module AtlasEngine
5
+ module AddressValidation
6
+ class ConcernRecord
7
+ extend T::Sig
8
+
9
+ sig { returns(String) }
10
+ attr_reader :address1
11
+
12
+ sig { returns(String) }
13
+ attr_reader :address2
14
+
15
+ sig { returns(String) }
16
+ attr_reader :city
17
+
18
+ sig { returns(String) }
19
+ attr_reader :country_code
20
+
21
+ sig { returns(String) }
22
+ attr_reader :province_code
23
+
24
+ sig { returns(String) }
25
+ attr_reader :zip
26
+
27
+ sig { returns(String) }
28
+ attr_reader :phone
29
+
30
+ sig { returns(Result) }
31
+ attr_reader :result
32
+
33
+ sig { returns(T.nilable(String)) }
34
+ attr_reader :version
35
+
36
+ sig { returns(T.nilable(String)) }
37
+ attr_reader :request_id
38
+
39
+ sig { returns(T.nilable(String)) }
40
+ attr_reader :client_request_id
41
+
42
+ sig { returns(Time) }
43
+ attr_reader :timestamp
44
+
45
+ sig { returns(String) }
46
+ attr_reader :origin
47
+
48
+ class << self
49
+ extend T::Sig
50
+
51
+ sig { params(result: Result, context: T::Hash[T.untyped, T.untyped]).returns(ConcernRecord) }
52
+ def from_result(result, context = {})
53
+ new(
54
+ **T.unsafe(
55
+ {
56
+ result: result,
57
+ **result.address,
58
+ **context.except(:client_request_id),
59
+ },
60
+ ),
61
+ )
62
+ end
63
+ end
64
+
65
+ sig do
66
+ params(
67
+ request_id: T.nilable(String),
68
+ timestamp: Time,
69
+ origin: String,
70
+ address1: String,
71
+ address2: String,
72
+ city: String,
73
+ province_code: String,
74
+ country_code: String,
75
+ zip: String,
76
+ phone: String,
77
+ result: Result,
78
+ ).void
79
+ end
80
+ def initialize(
81
+ request_id: nil,
82
+ timestamp: Time.zone.now,
83
+ origin: "",
84
+ address1: "",
85
+ address2: "",
86
+ city: "",
87
+ province_code: "",
88
+ country_code: "",
89
+ zip: "",
90
+ phone: "",
91
+ result: Result.new
92
+ )
93
+ @request_id = request_id
94
+ @client_request_id = T.let(result.client_request_id, T.nilable(String))
95
+ @timestamp = timestamp
96
+ @origin = origin
97
+ @address1 = address1
98
+ @address2 = address2
99
+ @city = city
100
+ @province_code = province_code
101
+ @country_code = country_code
102
+ @zip = zip
103
+ @phone = phone
104
+ @result = result
105
+ @version = T.let(Rails.configuration.version, T.nilable(String))
106
+ end
107
+
108
+ sig { returns(T::Hash[Symbol, String]) }
109
+ def address_attributes
110
+ {
111
+ address1: address1,
112
+ address2: address2,
113
+ city: city,
114
+ province_code: province_code,
115
+ zip: zip,
116
+ country_code: country_code,
117
+ phone: phone,
118
+ }
119
+ end
120
+ end
121
+ end
122
+ end
@@ -0,0 +1,27 @@
1
+ # typed: strict
2
+ # frozen_string_literal: true
3
+
4
+ module AtlasEngine
5
+ module AddressValidation
6
+ module DatastoreBase
7
+ extend T::Sig
8
+ extend T::Helpers
9
+ interface!
10
+
11
+ sig { abstract.returns(Token::Sequence) }
12
+ def fetch_city_sequence; end
13
+
14
+ sig { abstract.returns(T::Array[Token::Sequence]) }
15
+ def fetch_street_sequences; end
16
+
17
+ sig { abstract.returns(T::Array[Candidate]) }
18
+ def fetch_full_address_candidates; end
19
+
20
+ sig { abstract.returns(T::Hash[T.untyped, T.untyped]) }
21
+ def validation_response; end
22
+
23
+ sig { abstract.returns(ValidationTranscriber::AddressParsings) }
24
+ def parsings; end
25
+ end
26
+ end
27
+ end
@@ -0,0 +1,13 @@
1
+ # typed: strict
2
+ # frozen_string_literal: true
3
+
4
+ module AtlasEngine
5
+ module AddressValidation
6
+ class Errors < AtlasEngine::CodedErrors
7
+ HTTP_ISSUE = T.let(error(:http_issue, "There was an issue processing the request."), CodedError)
8
+ REQUEST_ISSUE = T.let(error(:request_issue, "There is an error with the given request."), CodedError)
9
+ MISSING_PARAMETER =
10
+ T.let(error(:missing_parameter, "The given request is missing a required parameter."), CodedError)
11
+ end
12
+ end
13
+ end
@@ -0,0 +1,70 @@
1
+ # typed: true
2
+ # frozen_string_literal: true
3
+
4
+ module AtlasEngine
5
+ module AddressValidation
6
+ module Es
7
+ class CandidateSelector
8
+ include LogHelper
9
+ extend T::Sig
10
+
11
+ sig { params(datastore: DatastoreBase, address: AbstractAddress).void }
12
+ def initialize(datastore:, address:)
13
+ @datastore = T.let(datastore, DatastoreBase)
14
+ @address = T.let(address, AbstractAddress)
15
+ end
16
+
17
+ sig { returns(Concurrent::Promises::Future) }
18
+ def best_candidate_async
19
+ Concurrent::Promises.future do
20
+ best_candidate
21
+ end
22
+ end
23
+
24
+ sig { returns(T.nilable(CandidateTuple)) }
25
+ def best_candidate
26
+ street_sequences_future = datastore.fetch_street_sequences_async
27
+ city_sequences_future = datastore.fetch_city_sequence_async
28
+ sorted_candidates.first
29
+ ensure
30
+ # We want our futures to complete even when we do not consume their value.
31
+ street_sequences_future&.wait!
32
+ city_sequences_future&.wait!
33
+ end
34
+
35
+ private
36
+
37
+ attr_reader :datastore, :address
38
+
39
+ sig { returns(T::Array[CandidateTuple]) }
40
+ def sorted_candidates
41
+ sorted_candidate_tuples = datastore.fetch_full_address_candidates
42
+ .filter_map.with_index(1) do |candidate, position|
43
+ address_comparison = AtlasEngine::AddressValidation::Validators::FullAddress::AddressComparison.new(
44
+ address: address,
45
+ candidate: candidate,
46
+ datastore: datastore,
47
+ )
48
+ tuple = CandidateTuple.new(address_comparison, position, candidate)
49
+ tuple if tuple.address_comparison.potential_match?
50
+ end.sort
51
+
52
+ emit_sorted_candidates(sorted_candidate_tuples)
53
+ sorted_candidate_tuples
54
+ end
55
+
56
+ sig { params(sorted_candidate_tuples: T::Array[CandidateTuple]).void }
57
+ def emit_sorted_candidates(sorted_candidate_tuples)
58
+ log_info("Sorted candidates:\n #{sorted_candidate_tuples.map { |tuple| tuple.candidate.serialize }}")
59
+
60
+ initial_position_top_candidate = sorted_candidate_tuples.first&.position || 0
61
+ StatsD.distribution(
62
+ "AddressValidation.query.initial_position_top_candidate",
63
+ initial_position_top_candidate,
64
+ tags: { position: initial_position_top_candidate },
65
+ )
66
+ end
67
+ end
68
+ end
69
+ end
70
+ end
@@ -0,0 +1,39 @@
1
+ # typed: strict
2
+ # frozen_string_literal: true
3
+
4
+ module AtlasEngine
5
+ module AddressValidation
6
+ module Es
7
+ module DataMappers
8
+ class DecompoundingDataMapper < DefaultDataMapper
9
+ sig do
10
+ override.returns(T::Hash[Symbol, T.untyped])
11
+ end
12
+ def map_data
13
+ super.tap do |data|
14
+ decompounded_fields.each do |field|
15
+ data["#{field}_decompounded".to_sym] = decompound(field: field, value: data[field])
16
+ end
17
+ end
18
+ end
19
+
20
+ private
21
+
22
+ sig { returns(T::Array[Symbol]) }
23
+ def decompounded_fields
24
+ country_profile.attributes.dig("decompounding_patterns").keys.map(&:to_sym)
25
+ end
26
+
27
+ sig { params(field: Symbol, value: T.nilable(String)).returns(T.nilable(String)) }
28
+ def decompound(field:, value:)
29
+ FieldDecompounder.new(
30
+ field: field,
31
+ value: value,
32
+ country_profile: country_profile,
33
+ ).call
34
+ end
35
+ end
36
+ end
37
+ end
38
+ end
39
+ end
@@ -0,0 +1,110 @@
1
+ # typed: strict
2
+ # frozen_string_literal: true
3
+
4
+ module AtlasEngine
5
+ module AddressValidation
6
+ module Es
7
+ module DataMappers
8
+ class DefaultDataMapper
9
+ extend T::Sig
10
+ include LogHelper
11
+
12
+ sig { returns(CountryRepository::PostAddressData) }
13
+ attr_reader :post_address
14
+
15
+ sig { returns(String) }
16
+ attr_reader :locale
17
+
18
+ sig do
19
+ params(
20
+ post_address: CountryRepository::PostAddressData,
21
+ country_profile: CountryProfile,
22
+ locale: String,
23
+ ).void
24
+ end
25
+ def initialize(post_address:, country_profile:, locale: "")
26
+ @post_address = post_address
27
+ @country_profile = country_profile
28
+ @locale = T.let((locale.empty? ? post_address[:locale] : locale), String)
29
+ end
30
+
31
+ sig do
32
+ returns(T::Hash[Symbol, T.untyped])
33
+ end
34
+ def map_data
35
+ {}.tap do |data|
36
+ data.update(
37
+ post_address
38
+ .slice(:id, :locale, :country_code, :province_code, :region1, :region2, :region3, :region4)
39
+ .deep_symbolize_keys,
40
+ )
41
+ data[:city_aliases] = city_aliases(post_address[:city])
42
+ data[:suburb] = post_address[:suburb]
43
+ data[:zip] = Worldwide::Zip.normalize(
44
+ country_code: post_address[:country_code],
45
+ zip: post_address[:zip],
46
+ )
47
+ data[:street] = post_address[:street]
48
+ data[:street_stripped] = street_stripped(post_address[:street])
49
+ data[:street_decompounded] = nil
50
+ data[:building_and_unit_ranges] = JSON.generate(post_address[:building_and_unit_ranges])
51
+ data[:approx_building_ranges] = approx_building_ranges(post_address[:building_and_unit_ranges]&.keys)
52
+ data.update(
53
+ post_address.slice(:building_name, :latitude, :longitude).deep_symbolize_keys,
54
+ )
55
+ data[:location] = {
56
+ lat: post_address[:latitude],
57
+ lon: post_address[:longitude],
58
+ }
59
+ end
60
+ end
61
+
62
+ protected
63
+
64
+ sig { returns(CountryProfile) }
65
+ attr_reader :country_profile
66
+
67
+ sig { params(cities: T::Array[String]).returns(T::Array[T::Hash[Symbol, String]]) }
68
+ def city_aliases(cities)
69
+ cities.map do |city|
70
+ {
71
+ alias: city,
72
+ }
73
+ end
74
+ end
75
+
76
+ sig { params(street: T.nilable(String)).returns(T.nilable(String)) }
77
+ def street_stripped(street)
78
+ return if street.blank?
79
+
80
+ Street.new(street: street).with_stripped_name
81
+ end
82
+
83
+ sig { params(ranges: T.nilable(T::Array[String])).returns(T.nilable(T::Array[T::Hash[String, Integer]])) }
84
+ def approx_building_ranges(ranges)
85
+ return unless ranges
86
+
87
+ numeric_ranges = ranges.filter_map do |range_str|
88
+ AddressNumberRange.new(range_string: range_str).approx_numeric_range
89
+ end
90
+ merged_ranges = AddressNumberRange.merge_overlapping_ranges(numeric_ranges)
91
+ merged_ranges.map { |range| es_integer_range(min: range.min, max: range.max) }
92
+ rescue AddressNumberRange::RangeError => e
93
+ log_warn("[#{e.class}]: #{e.message}")
94
+ nil
95
+ end
96
+
97
+ sig { params(min: Integer, max: Integer).returns(T::Hash[String, Integer]) }
98
+ def es_integer_range(min:, max:)
99
+ { "gte" => min, "lte" => max }
100
+ end
101
+
102
+ sig { returns(String) }
103
+ def locale_language_code
104
+ Worldwide.locale(code: locale).language_subtag
105
+ end
106
+ end
107
+ end
108
+ end
109
+ end
110
+ end