krikri 0.3.3 → 0.4.0

Sign up to get free protection for your applications and to get access to all the features.
Files changed (222) hide show
  1. checksums.yaml +4 -4
  2. data/app/controllers/krikri/records_controller.rb +14 -0
  3. data/app/models/krikri/search_index_document.rb +10 -0
  4. data/lib/krikri/engine.rb +1 -0
  5. data/lib/krikri/enricher.rb +156 -0
  6. data/lib/krikri/enrichment.rb +0 -2
  7. data/lib/krikri/enrichments/{deduplication.rb~ → dedup_values.rb~} +1 -4
  8. data/lib/krikri/enrichments/genre_filter.rb +45 -0
  9. data/lib/krikri/enrichments/strip_ending_punctuation.rb +21 -0
  10. data/lib/krikri/enrichments/strip_ending_punctuation.rb~ +18 -0
  11. data/lib/krikri/enrichments/strip_leading_colons.rb +15 -0
  12. data/lib/krikri/enrichments/strip_leading_colons.rb~ +15 -0
  13. data/lib/krikri/enrichments/strip_leading_punctuation.rb +18 -0
  14. data/lib/krikri/enrichments/strip_leading_punctuation.rb~ +18 -0
  15. data/lib/krikri/enrichments/timespan_split.rb +43 -1
  16. data/lib/krikri/harvesters/api_harvester.rb +164 -0
  17. data/lib/krikri/harvesters/api_harvester.rb~ +44 -0
  18. data/lib/krikri/harvesters/mdl_api_harvester.rb~ +7 -0
  19. data/lib/krikri/harvesters/mdl_harvester.rb~ +4 -0
  20. data/lib/krikri/harvesters/oai_harvester.rb +8 -0
  21. data/lib/krikri/ldp/rdf_source.rb +30 -0
  22. data/lib/krikri/mapper.rb +1 -3
  23. data/lib/krikri/provenance_query_client.rb +11 -1
  24. data/lib/krikri/util/extended_date_parser.rb +46 -11
  25. data/lib/krikri/version.rb +1 -1
  26. data/spec/internal/Gemfile.lock +12 -12
  27. data/spec/internal/config/initializers/blacklight_initializer.rb +1 -1
  28. data/spec/internal/config/initializers/devise.rb +2 -2
  29. data/spec/internal/config/secrets.yml +2 -2
  30. data/spec/internal/db/development.sqlite3 +0 -0
  31. data/spec/internal/db/migrate/{20150310190235_devise_create_users.rb → 20150320153132_devise_create_users.rb} +0 -0
  32. data/spec/internal/db/migrate/{20150310190253_create_searches.blacklight.rb → 20150320153151_create_searches.blacklight.rb} +0 -0
  33. data/spec/internal/db/migrate/{20150310190254_create_bookmarks.blacklight.rb → 20150320153152_create_bookmarks.blacklight.rb} +0 -0
  34. data/spec/internal/db/migrate/{20150310190255_add_polymorphic_type_to_bookmarks.blacklight.rb → 20150320153153_add_polymorphic_type_to_bookmarks.blacklight.rb} +0 -0
  35. data/spec/internal/db/schema.rb +1 -1
  36. data/spec/internal/db/test.sqlite3 +0 -0
  37. data/spec/internal/log/development.log +75 -73
  38. data/spec/internal/log/test.log +85076 -0
  39. data/spec/internal/tmp/cache/assets/test/sass/4a3ee647961c7e45976eb2c0a94406aad3427b3d/_alerts.scssc +0 -0
  40. data/spec/internal/tmp/cache/assets/test/sass/4a3ee647961c7e45976eb2c0a94406aad3427b3d/_background-variant.scssc +0 -0
  41. data/spec/internal/tmp/cache/assets/test/sass/4a3ee647961c7e45976eb2c0a94406aad3427b3d/_border-radius.scssc +0 -0
  42. data/spec/internal/tmp/cache/assets/test/sass/4a3ee647961c7e45976eb2c0a94406aad3427b3d/_buttons.scssc +0 -0
  43. data/spec/internal/tmp/cache/assets/test/sass/4a3ee647961c7e45976eb2c0a94406aad3427b3d/_center-block.scssc +0 -0
  44. data/spec/internal/tmp/cache/assets/test/sass/4a3ee647961c7e45976eb2c0a94406aad3427b3d/_clearfix.scssc +0 -0
  45. data/spec/internal/tmp/cache/assets/test/sass/4a3ee647961c7e45976eb2c0a94406aad3427b3d/_forms.scssc +0 -0
  46. data/spec/internal/tmp/cache/assets/test/sass/4a3ee647961c7e45976eb2c0a94406aad3427b3d/_gradients.scssc +0 -0
  47. data/spec/internal/tmp/cache/assets/test/sass/4a3ee647961c7e45976eb2c0a94406aad3427b3d/_grid-framework.scssc +0 -0
  48. data/spec/internal/tmp/cache/assets/test/sass/4a3ee647961c7e45976eb2c0a94406aad3427b3d/_grid.scssc +0 -0
  49. data/spec/internal/tmp/cache/assets/test/sass/4a3ee647961c7e45976eb2c0a94406aad3427b3d/_hide-text.scssc +0 -0
  50. data/spec/internal/tmp/cache/assets/test/sass/4a3ee647961c7e45976eb2c0a94406aad3427b3d/_image.scssc +0 -0
  51. data/spec/internal/tmp/cache/assets/test/sass/4a3ee647961c7e45976eb2c0a94406aad3427b3d/_labels.scssc +0 -0
  52. data/spec/internal/tmp/cache/assets/test/sass/4a3ee647961c7e45976eb2c0a94406aad3427b3d/_list-group.scssc +0 -0
  53. data/spec/internal/tmp/cache/assets/test/sass/4a3ee647961c7e45976eb2c0a94406aad3427b3d/_nav-divider.scssc +0 -0
  54. data/spec/internal/tmp/cache/assets/test/sass/4a3ee647961c7e45976eb2c0a94406aad3427b3d/_nav-vertical-align.scssc +0 -0
  55. data/spec/internal/tmp/cache/assets/test/sass/4a3ee647961c7e45976eb2c0a94406aad3427b3d/_opacity.scssc +0 -0
  56. data/spec/internal/tmp/cache/assets/test/sass/4a3ee647961c7e45976eb2c0a94406aad3427b3d/_pagination.scssc +0 -0
  57. data/spec/internal/tmp/cache/assets/test/sass/4a3ee647961c7e45976eb2c0a94406aad3427b3d/_panels.scssc +0 -0
  58. data/spec/internal/tmp/cache/assets/test/sass/4a3ee647961c7e45976eb2c0a94406aad3427b3d/_progress-bar.scssc +0 -0
  59. data/spec/internal/tmp/cache/assets/test/sass/4a3ee647961c7e45976eb2c0a94406aad3427b3d/_reset-filter.scssc +0 -0
  60. data/spec/internal/tmp/cache/assets/test/sass/4a3ee647961c7e45976eb2c0a94406aad3427b3d/_resize.scssc +0 -0
  61. data/spec/internal/tmp/cache/assets/test/sass/4a3ee647961c7e45976eb2c0a94406aad3427b3d/_responsive-visibility.scssc +0 -0
  62. data/spec/internal/tmp/cache/assets/test/sass/4a3ee647961c7e45976eb2c0a94406aad3427b3d/_size.scssc +0 -0
  63. data/spec/internal/tmp/cache/assets/test/sass/4a3ee647961c7e45976eb2c0a94406aad3427b3d/_tab-focus.scssc +0 -0
  64. data/spec/internal/tmp/cache/assets/test/sass/4a3ee647961c7e45976eb2c0a94406aad3427b3d/_table-row.scssc +0 -0
  65. data/spec/internal/tmp/cache/assets/test/sass/4a3ee647961c7e45976eb2c0a94406aad3427b3d/_text-emphasis.scssc +0 -0
  66. data/spec/internal/tmp/cache/assets/test/sass/4a3ee647961c7e45976eb2c0a94406aad3427b3d/_text-overflow.scssc +0 -0
  67. data/spec/internal/tmp/cache/assets/test/sass/4a3ee647961c7e45976eb2c0a94406aad3427b3d/_vendor-prefixes.scssc +0 -0
  68. data/spec/internal/tmp/cache/assets/test/sass/93e201cf4a11978a1f491a057a3bd569c3825210/blacklight.css.scssc +0 -0
  69. data/spec/internal/tmp/cache/assets/test/sass/a1ec1bb9c9cafeb054d542e861ebc8ffd5904439/_alerts.scssc +0 -0
  70. data/spec/internal/tmp/cache/assets/test/sass/a1ec1bb9c9cafeb054d542e861ebc8ffd5904439/_badges.scssc +0 -0
  71. data/spec/internal/tmp/cache/assets/test/sass/a1ec1bb9c9cafeb054d542e861ebc8ffd5904439/_breadcrumbs.scssc +0 -0
  72. data/spec/internal/tmp/cache/assets/test/sass/a1ec1bb9c9cafeb054d542e861ebc8ffd5904439/_button-groups.scssc +0 -0
  73. data/spec/internal/tmp/cache/assets/test/sass/a1ec1bb9c9cafeb054d542e861ebc8ffd5904439/_buttons.scssc +0 -0
  74. data/spec/internal/tmp/cache/assets/test/sass/a1ec1bb9c9cafeb054d542e861ebc8ffd5904439/_carousel.scssc +0 -0
  75. data/spec/internal/tmp/cache/assets/test/sass/a1ec1bb9c9cafeb054d542e861ebc8ffd5904439/_close.scssc +0 -0
  76. data/spec/internal/tmp/cache/assets/test/sass/a1ec1bb9c9cafeb054d542e861ebc8ffd5904439/_code.scssc +0 -0
  77. data/spec/internal/tmp/cache/assets/test/sass/a1ec1bb9c9cafeb054d542e861ebc8ffd5904439/_component-animations.scssc +0 -0
  78. data/spec/internal/tmp/cache/assets/test/sass/a1ec1bb9c9cafeb054d542e861ebc8ffd5904439/_dropdowns.scssc +0 -0
  79. data/spec/internal/tmp/cache/assets/test/sass/a1ec1bb9c9cafeb054d542e861ebc8ffd5904439/_forms.scssc +0 -0
  80. data/spec/internal/tmp/cache/assets/test/sass/a1ec1bb9c9cafeb054d542e861ebc8ffd5904439/_glyphicons.scssc +0 -0
  81. data/spec/internal/tmp/cache/assets/test/sass/a1ec1bb9c9cafeb054d542e861ebc8ffd5904439/_grid.scssc +0 -0
  82. data/spec/internal/tmp/cache/assets/test/sass/a1ec1bb9c9cafeb054d542e861ebc8ffd5904439/_input-groups.scssc +0 -0
  83. data/spec/internal/tmp/cache/assets/test/sass/a1ec1bb9c9cafeb054d542e861ebc8ffd5904439/_jumbotron.scssc +0 -0
  84. data/spec/internal/tmp/cache/assets/test/sass/a1ec1bb9c9cafeb054d542e861ebc8ffd5904439/_labels.scssc +0 -0
  85. data/spec/internal/tmp/cache/assets/test/sass/a1ec1bb9c9cafeb054d542e861ebc8ffd5904439/_list-group.scssc +0 -0
  86. data/spec/internal/tmp/cache/assets/test/sass/a1ec1bb9c9cafeb054d542e861ebc8ffd5904439/_media.scssc +0 -0
  87. data/spec/internal/tmp/cache/assets/test/sass/a1ec1bb9c9cafeb054d542e861ebc8ffd5904439/_mixins.scssc +0 -0
  88. data/spec/internal/tmp/cache/assets/test/sass/a1ec1bb9c9cafeb054d542e861ebc8ffd5904439/_modals.scssc +0 -0
  89. data/spec/internal/tmp/cache/assets/test/sass/a1ec1bb9c9cafeb054d542e861ebc8ffd5904439/_navbar.scssc +0 -0
  90. data/spec/internal/tmp/cache/assets/test/sass/a1ec1bb9c9cafeb054d542e861ebc8ffd5904439/_navs.scssc +0 -0
  91. data/spec/internal/tmp/cache/assets/test/sass/a1ec1bb9c9cafeb054d542e861ebc8ffd5904439/_normalize.scssc +0 -0
  92. data/spec/internal/tmp/cache/assets/test/sass/a1ec1bb9c9cafeb054d542e861ebc8ffd5904439/_pager.scssc +0 -0
  93. data/spec/internal/tmp/cache/assets/test/sass/a1ec1bb9c9cafeb054d542e861ebc8ffd5904439/_pagination.scssc +0 -0
  94. data/spec/internal/tmp/cache/assets/test/sass/a1ec1bb9c9cafeb054d542e861ebc8ffd5904439/_panels.scssc +0 -0
  95. data/spec/internal/tmp/cache/assets/test/sass/a1ec1bb9c9cafeb054d542e861ebc8ffd5904439/_popovers.scssc +0 -0
  96. data/spec/internal/tmp/cache/assets/test/sass/a1ec1bb9c9cafeb054d542e861ebc8ffd5904439/_print.scssc +0 -0
  97. data/spec/internal/tmp/cache/assets/test/sass/a1ec1bb9c9cafeb054d542e861ebc8ffd5904439/_progress-bars.scssc +0 -0
  98. data/spec/internal/tmp/cache/assets/test/sass/a1ec1bb9c9cafeb054d542e861ebc8ffd5904439/_responsive-embed.scssc +0 -0
  99. data/spec/internal/tmp/cache/assets/test/sass/a1ec1bb9c9cafeb054d542e861ebc8ffd5904439/_responsive-utilities.scssc +0 -0
  100. data/spec/internal/tmp/cache/assets/test/sass/a1ec1bb9c9cafeb054d542e861ebc8ffd5904439/_scaffolding.scssc +0 -0
  101. data/spec/internal/tmp/cache/assets/test/sass/a1ec1bb9c9cafeb054d542e861ebc8ffd5904439/_tables.scssc +0 -0
  102. data/spec/internal/tmp/cache/assets/test/sass/a1ec1bb9c9cafeb054d542e861ebc8ffd5904439/_thumbnails.scssc +0 -0
  103. data/spec/internal/tmp/cache/assets/test/sass/a1ec1bb9c9cafeb054d542e861ebc8ffd5904439/_tooltip.scssc +0 -0
  104. data/spec/internal/tmp/cache/assets/test/sass/a1ec1bb9c9cafeb054d542e861ebc8ffd5904439/_type.scssc +0 -0
  105. data/spec/internal/tmp/cache/assets/test/sass/a1ec1bb9c9cafeb054d542e861ebc8ffd5904439/_utilities.scssc +0 -0
  106. data/spec/internal/tmp/cache/assets/test/sass/a1ec1bb9c9cafeb054d542e861ebc8ffd5904439/_variables.scssc +0 -0
  107. data/spec/internal/tmp/cache/assets/test/sass/a1ec1bb9c9cafeb054d542e861ebc8ffd5904439/_wells.scssc +0 -0
  108. data/spec/internal/tmp/cache/assets/test/sass/b28605b1c659cf09fc72f3c1fff32918869d28b8/_bootstrap-sprockets.scssc +0 -0
  109. data/spec/internal/tmp/cache/assets/test/sass/b28605b1c659cf09fc72f3c1fff32918869d28b8/_bootstrap.scssc +0 -0
  110. data/spec/internal/tmp/cache/assets/test/sass/ca8c12d03785e0d6cd4554f4d3939e7836d38282/_blacklight_base.scssc +0 -0
  111. data/spec/internal/tmp/cache/assets/test/sass/ca8c12d03785e0d6cd4554f4d3939e7836d38282/_bookmark.scssc +0 -0
  112. data/spec/internal/tmp/cache/assets/test/sass/ca8c12d03785e0d6cd4554f4d3939e7836d38282/_catalog.scssc +0 -0
  113. data/spec/internal/tmp/cache/assets/test/sass/ca8c12d03785e0d6cd4554f4d3939e7836d38282/_facets.scssc +0 -0
  114. data/spec/internal/tmp/cache/assets/test/sass/ca8c12d03785e0d6cd4554f4d3939e7836d38282/_group.scssc +0 -0
  115. data/spec/internal/tmp/cache/assets/test/sass/ca8c12d03785e0d6cd4554f4d3939e7836d38282/_header.scssc +0 -0
  116. data/spec/internal/tmp/cache/assets/test/sass/ca8c12d03785e0d6cd4554f4d3939e7836d38282/_layout.scssc +0 -0
  117. data/spec/internal/tmp/cache/assets/test/sass/ca8c12d03785e0d6cd4554f4d3939e7836d38282/_modal.scssc +0 -0
  118. data/spec/internal/tmp/cache/assets/test/sass/ca8c12d03785e0d6cd4554f4d3939e7836d38282/_search_history.scssc +0 -0
  119. data/spec/internal/tmp/cache/assets/test/sass/ca8c12d03785e0d6cd4554f4d3939e7836d38282/blacklight.scssc +0 -0
  120. data/spec/internal/tmp/cache/assets/test/sass/ca8c12d03785e0d6cd4554f4d3939e7836d38282/blacklight_defaults.scssc +0 -0
  121. data/spec/internal/tmp/cache/assets/test/sprockets/059eceaa18e2eaee3d5168f3949f4957 +0 -0
  122. data/spec/internal/tmp/cache/assets/test/sprockets/093d898bf3f20b26b13c82714a77c040 +0 -0
  123. data/spec/internal/tmp/cache/assets/test/sprockets/10517c9579f8d23c82fb8caa66dca6a7 +0 -0
  124. data/spec/internal/tmp/cache/assets/test/sprockets/13fe41fee1fe35b49d145bcc06610705 +0 -0
  125. data/spec/internal/tmp/cache/assets/test/sprockets/19f4ba6fa86d2609c171da9f5ee3b11a +0 -0
  126. data/spec/internal/tmp/cache/assets/test/sprockets/2bec18569db80effd80a2a19a038100b +0 -0
  127. data/spec/internal/tmp/cache/assets/test/sprockets/2f5173deea6c795b8fdde723bb4b63af +0 -0
  128. data/spec/internal/tmp/cache/assets/test/sprockets/30ca7caa200fa8eaddaef443913ad9ad +0 -0
  129. data/spec/internal/tmp/cache/assets/test/sprockets/350a65d446eb7398f96d102f7a1a6d69 +0 -0
  130. data/spec/internal/tmp/cache/assets/test/sprockets/357970feca3ac29060c1e3861e2c0953 +0 -0
  131. data/spec/internal/tmp/cache/assets/test/sprockets/3cc20a63495e66e9251101ccfb0d389c +0 -0
  132. data/spec/internal/tmp/cache/assets/test/sprockets/4052820c15af72ba690230a0f92bd75e +0 -0
  133. data/spec/internal/tmp/cache/assets/test/sprockets/41b62fb10530766b5b9fef3338f5f30b +0 -0
  134. data/spec/internal/tmp/cache/assets/test/sprockets/421c89c58d3e76046a0294dae1f731ff +0 -0
  135. data/spec/internal/tmp/cache/assets/test/sprockets/43da966542fafc2a4c768be78527391c +0 -0
  136. data/spec/internal/tmp/cache/assets/test/sprockets/496a0d7dce1ff6bf4a9c3a089ea3a635 +0 -0
  137. data/spec/internal/tmp/cache/assets/test/sprockets/4e93570db72bb61820711448b78d548d +0 -0
  138. data/spec/internal/tmp/cache/assets/test/sprockets/50b9db0b908b421a9b941a445dbaeacc +0 -0
  139. data/spec/internal/tmp/cache/assets/test/sprockets/5155772cce704d83a64aa83eeda20c5a +0 -0
  140. data/spec/internal/tmp/cache/assets/test/sprockets/528c628cf107f8be6dd122e1154344be +0 -0
  141. data/spec/internal/tmp/cache/assets/test/sprockets/5ed02c7072bb024fa0832a1ca4113227 +0 -0
  142. data/spec/internal/tmp/cache/assets/test/sprockets/60141dc3d16c502963c3d798a099862d +0 -0
  143. data/spec/internal/tmp/cache/assets/test/sprockets/6df5b5c0a8e6d87ced9504a460df875e +0 -0
  144. data/spec/internal/tmp/cache/assets/test/sprockets/6eefd2765a716d66ff857cfcda69a119 +0 -0
  145. data/spec/internal/tmp/cache/assets/test/sprockets/813e23719129cf9f19349f720bebdf70 +0 -0
  146. data/spec/internal/tmp/cache/assets/test/sprockets/88ded10f28177bec1bddb0d72d6b1cd2 +0 -0
  147. data/spec/internal/tmp/cache/assets/test/sprockets/8ad5c3dc0f5fcc5d7a775d6294dda9f5 +0 -0
  148. data/spec/internal/tmp/cache/assets/test/sprockets/8edfca9082e02111be92e79000667f22 +0 -0
  149. data/spec/internal/tmp/cache/assets/test/sprockets/90b54a819800edfa41b67722d1561040 +0 -0
  150. data/spec/internal/tmp/cache/assets/test/sprockets/93aaa9231a32901266b05632f3d35ecd +0 -0
  151. data/spec/internal/tmp/cache/assets/test/sprockets/9c653367feff82588eb6041d783a5809 +0 -0
  152. data/spec/internal/tmp/cache/assets/test/sprockets/9ce190f082dc4fb74bddb818cc011ce6 +0 -0
  153. data/spec/internal/tmp/cache/assets/test/sprockets/9f68eb44ffcb9dd95623c179300414fd +0 -0
  154. data/spec/internal/tmp/cache/assets/test/sprockets/ab2a05b91d7d316d4ceb47ce067006fb +0 -0
  155. data/spec/internal/tmp/cache/assets/test/sprockets/ad4a54c43c2a4c3874bfde1c9f08c248 +0 -0
  156. data/spec/internal/tmp/cache/assets/test/sprockets/b1a42de74c934edd0e5eed0f98a23597 +0 -0
  157. data/spec/internal/tmp/cache/assets/test/sprockets/b1c03c36188b4f58f819510adb9a7e9c +0 -0
  158. data/spec/internal/tmp/cache/assets/test/sprockets/b225d67626669cb154cbe08a3c439d48 +0 -0
  159. data/spec/internal/tmp/cache/assets/test/sprockets/b35e12934e9f05662777579549e31cd7 +0 -0
  160. data/spec/internal/tmp/cache/assets/test/sprockets/b3ae9e3cdd9991d7103b0a00e33b5778 +0 -0
  161. data/spec/internal/tmp/cache/assets/test/sprockets/b42c247628daaf44109584724682a6ad +0 -0
  162. data/spec/internal/tmp/cache/assets/test/sprockets/b660ec1ede271559cfd0259eed96ae9c +0 -0
  163. data/spec/internal/tmp/cache/assets/test/sprockets/ba078b29a7f067b3acdd538a286235a8 +0 -0
  164. data/spec/internal/tmp/cache/assets/test/sprockets/bb108ef3fc4c96d1c20cc41f97d943a0 +0 -0
  165. data/spec/internal/tmp/cache/assets/test/sprockets/bb92f4b8c1bedafe60b6f226b549138a +0 -0
  166. data/spec/internal/tmp/cache/assets/test/sprockets/c644ecad928e076f999e9c9a3bc350c9 +0 -0
  167. data/spec/internal/tmp/cache/assets/test/sprockets/c78dd20a0df27e9394a413bf2e4abf92 +0 -0
  168. data/spec/internal/tmp/cache/assets/test/sprockets/c9efce42580b0ad0374a052aa61f2a07 +0 -0
  169. data/spec/internal/tmp/cache/assets/test/sprockets/cffd775d018f68ce5dba1ee0d951a994 +0 -0
  170. data/spec/internal/tmp/cache/assets/test/sprockets/d1bce36d6e3ab792562b9c929f2ce897 +0 -0
  171. data/spec/internal/tmp/cache/assets/test/sprockets/d24a7c4b8ac71a90e809881a64970898 +0 -0
  172. data/spec/internal/tmp/cache/assets/test/sprockets/d771ace226fc8215a3572e0aa35bb0d6 +0 -0
  173. data/spec/internal/tmp/cache/assets/test/sprockets/db0d9534ecdebba33af5d1d81060e855 +0 -0
  174. data/spec/internal/tmp/cache/assets/test/sprockets/dbba4bbc32c17ade3d618c5d0baeb371 +0 -0
  175. data/spec/internal/tmp/cache/assets/test/sprockets/e8276b98892dcac8285a592bb63fe75b +0 -0
  176. data/spec/internal/tmp/cache/assets/test/sprockets/e9f7ccc553ce1a217709cc7a08cfb032 +0 -0
  177. data/spec/internal/tmp/cache/assets/test/sprockets/ecfc314951b349e27742c1b26880619e +0 -0
  178. data/spec/internal/tmp/cache/assets/test/sprockets/eddae0741d973a8ab3df27c1ea5b635e +0 -0
  179. data/spec/internal/tmp/cache/assets/test/sprockets/f274b5f22db177b6464b50691d531688 +0 -0
  180. data/spec/internal/tmp/cache/assets/test/sprockets/f3935581a84aba9a499005ed6a8e18be +0 -0
  181. data/spec/internal/tmp/cache/assets/test/sprockets/f3e7729c53b8a2c408086a61b58922ae +0 -0
  182. data/spec/internal/tmp/cache/assets/test/sprockets/f45dfdb34e84d3c72a3319399a7316a3 +0 -0
  183. data/spec/internal/tmp/cache/assets/test/sprockets/f74af03e26e893af40b07a6d0f970cd4 +0 -0
  184. data/spec/internal/tmp/cache/assets/test/sprockets/f7cbd26ba1d28d48de824f0e94586655 +0 -0
  185. data/spec/internal/tmp/cache/assets/test/sprockets/fa11f1beb15b0f04503ce1f06701a8bf +0 -0
  186. data/spec/internal/tmp/cache/assets/test/sprockets/faac2909046aa87e1f1f08b2bf0ad2b2 +0 -0
  187. data/spec/lib/krikri/enricher_spec.rb +130 -0
  188. data/spec/lib/krikri/enrichments/dedup_values_spec.rb~ +10 -0
  189. data/spec/lib/krikri/enrichments/genre_filter_spec.rb +21 -0
  190. data/spec/lib/krikri/enrichments/remove_empty_fields_spec.rb +1 -0
  191. data/spec/lib/krikri/enrichments/strip_ending_punctuation_spec.rb +28 -0
  192. data/spec/lib/krikri/enrichments/strip_ending_punctuation_spec.rb~ +16 -0
  193. data/spec/lib/krikri/enrichments/strip_html_spec.rb +1 -0
  194. data/spec/lib/krikri/enrichments/strip_leading_colons_spec.rb +16 -0
  195. data/spec/lib/krikri/enrichments/strip_leading_colons_spec.rb~ +16 -0
  196. data/spec/lib/krikri/enrichments/strip_leading_punctuation_spec.rb +16 -0
  197. data/spec/lib/krikri/enrichments/strip_leading_punctuation_spec.rb~ +16 -0
  198. data/spec/lib/krikri/enrichments/strip_punctuation_spec.rb +1 -0
  199. data/spec/lib/krikri/enrichments/strip_whitespace_spec.rb +1 -0
  200. data/spec/lib/krikri/enrichments/timespan_split_spec.rb +15 -0
  201. data/spec/lib/krikri/harvesters/api_harvester_spec.rb +98 -0
  202. data/spec/lib/krikri/harvesters/api_harvester_spec.rb~ +47 -0
  203. data/spec/lib/krikri/harvesters/mdl_api_harvester_spec.rb~ +11 -0
  204. data/spec/lib/krikri/harvesters/mdl_harvester_spec.rb~ +8 -0
  205. data/spec/lib/krikri/harvesters/oai_harvester_spec.rb +12 -6
  206. data/spec/lib/krikri/job_spec.rb +40 -0
  207. data/spec/lib/krikri/mapper_agent_spec.rb +10 -6
  208. data/spec/lib/krikri/util/extended_date_parser_spec.rb +14 -2
  209. data/spec/models/search_index_document_spec.rb +8 -0
  210. data/spec/spec_helper.rb +5 -0
  211. data/spec/support/shared_examples/harvester.rb +8 -1
  212. data/spec/support/shared_examples/rdf_source.rb +22 -0
  213. data/spec/support/shared_examples/string_enrichment.rb +13 -4
  214. metadata +365 -21
  215. data/lib/krikri/enrichments/capitalize.rb~ +0 -24
  216. data/lib/krikri/enrichments/genre_filter.rb~ +0 -9
  217. data/lib/krikri/enrichments/iso_enrcich.rb~ +0 -8
  218. data/lib/krikri/enrichments/iso_enrich.rb~ +0 -13
  219. data/lib/krikri/enrichments/parse_date.rb~ +0 -10
  220. data/lib/krikri/enrichments/strip_html.rb~ +0 -16
  221. data/lib/krikri/enrichments/timespan.rb~ +0 -6
  222. data/lib/krikri/enrichments/timespan_split.rb~ +0 -83
@@ -0,0 +1,10 @@
1
+ require 'spec_helper'
2
+
3
+ describe Krikri::Enrichments::DedupValues do
4
+ it_behaves_like 'a field enrichment'
5
+
6
+ it do
7
+ binding.pry
8
+ require 'pry'
9
+ end
10
+ end
@@ -0,0 +1,21 @@
1
+ require 'spec_helper'
2
+
3
+ describe Krikri::Enrichments::GenreFilter do
4
+ it_behaves_like 'a field enrichment'
5
+
6
+ values = [{ :string => 'removes non-genre terms',
7
+ :start => 'Not A Term',
8
+ :end => nil
9
+ },
10
+ { :string => 'retains genre terms',
11
+ :start => 'Book',
12
+ :end => 'Book'
13
+ },
14
+ { :string => 'normalizes string form',
15
+ :start => "\n bO O-k! \t",
16
+ :end => 'Book'
17
+ }]
18
+
19
+ it_behaves_like 'a string enrichment', values
20
+ include_examples 'deletes non-strings'
21
+ end
@@ -21,4 +21,5 @@ describe Krikri::Enrichments::RemoveEmptyFields do
21
21
  }]
22
22
 
23
23
  it_behaves_like 'a string enrichment', values
24
+ include_examples 'skips non-strings'
24
25
  end
@@ -0,0 +1,28 @@
1
+ require 'spec_helper'
2
+
3
+ describe Krikri::Enrichments::StripEndingPunctuation do
4
+ it_behaves_like 'a field enrichment'
5
+
6
+ values = [{ :string => 'removes punctuation from end of field',
7
+ :start => "moomin!...!;,.",
8
+ :end => "moomin"
9
+ },
10
+ { :string => 'keeps initials',
11
+ :start => "Smith, Smithy Q.",
12
+ :end => "Smith, Smithy Q."
13
+ },
14
+ { :string => 'keeps closing parentheses',
15
+ :start => "(Smith)",
16
+ :end => "(Smith)"
17
+ },
18
+ { :string => 'keeps two letter abbreviations',
19
+ :start => "66 cm.",
20
+ :end => "66 cm."
21
+ },
22
+ { :string => 'leaves other fields unaltered',
23
+ :start => "moominpapa;:;:; moominmama",
24
+ :end => "moominpapa;:;:; moominmama"
25
+ }]
26
+
27
+ it_behaves_like 'a string enrichment', values
28
+ end
@@ -0,0 +1,16 @@
1
+ require 'spec_helper'
2
+
3
+ describe Krikri::Enrichments::StripLeadingPunctuation do
4
+ it_behaves_like 'a field enrichment'
5
+
6
+ values = [{ :string => 'removes punctuation from beginning of field',
7
+ :start => "([!.;:\tmoominpapa;:;:; moominmama! ...\n",
8
+ :end => "\tmoominpapa;:;:; moominmama! ...\n"
9
+ },
10
+ { :string => 'leaves other fields unaltered',
11
+ :start => "'moominpapa;:;:; moominmama! ...\n'",
12
+ :end => "'moominpapa;:;:; moominmama! ...\n'"
13
+ }]
14
+
15
+ it_behaves_like 'a string enrichment', values
16
+ end
@@ -18,4 +18,5 @@ describe Krikri::Enrichments::StripHtml do
18
18
  }]
19
19
 
20
20
  it_behaves_like 'a string enrichment', values
21
+ include_examples 'skips non-strings'
21
22
  end
@@ -0,0 +1,16 @@
1
+ require 'spec_helper'
2
+
3
+ describe Krikri::Enrichments::StripLeadingColons do
4
+ it_behaves_like 'a field enrichment'
5
+
6
+ values = [{ :string => 'removes (semi)colons from beginning of field',
7
+ :start => ";:\tmoominpa()pa;;;",
8
+ :end => "\tmoominpa()pa;;;"
9
+ },
10
+ { :string => 'leaves other fields unaltered',
11
+ :start => ";:\tmoominpapa;:;:; moominmama! ...\n",
12
+ :end => "\tmoominpapa;:;:; moominmama! ...\n"
13
+ }]
14
+
15
+ it_behaves_like 'a string enrichment', values
16
+ end
@@ -0,0 +1,16 @@
1
+ require 'spec_helper'
2
+
3
+ describe Krikri::Enrichments::StripLeadingColons do
4
+ it_behaves_like 'a field enrichment'
5
+
6
+ values = [{ :string => 'removes (semi)colons from beginning of field',
7
+ :start => "\tmoominpapa;... !@#$ moominmama ",
8
+ :end => "\tmoominpapa moominmama "
9
+ },
10
+ { :string => 'leaves other fields unaltered',
11
+ :start => "\tmoominpapa;:;:; moominmama",
12
+ :end => "\tmoominpapa;:;:; moominmama"
13
+ }]
14
+
15
+ it_behaves_like 'a string enrichment', values
16
+ end
@@ -0,0 +1,16 @@
1
+ require 'spec_helper'
2
+
3
+ describe Krikri::Enrichments::StripLeadingPunctuation do
4
+ it_behaves_like 'a field enrichment'
5
+
6
+ values = [{ :string => 'removes punctuation from beginning of field',
7
+ :start => "([!.;:\tmoominpapa;:;:; moominmama! ...\n",
8
+ :end => "\tmoominpapa;:;:; moominmama! ...\n"
9
+ },
10
+ { :string => 'leaves other fields unaltered',
11
+ :start => "'moominpapa;:;:; moominmama! ...\n'",
12
+ :end => "'moominpapa;:;:; moominmama! ...\n'"
13
+ }]
14
+
15
+ it_behaves_like 'a string enrichment', values
16
+ end
@@ -0,0 +1,16 @@
1
+ require 'spec_helper'
2
+
3
+ describe Krikri::Enrichments::StripLeadingPunctuation do
4
+ it_behaves_like 'a field enrichment'
5
+
6
+ values = [{ :string => 'removes punctuation from beginning of field',
7
+ :start => ";:\tmoominpa()pa;;;",
8
+ :end => "\tmoominpa()pa;;;"
9
+ },
10
+ { :string => 'leaves other fields unaltered',
11
+ :start => ";:\tmoominpapa;:;:; moominmama! ...\n",
12
+ :end => "\tmoominpapa;:;:; moominmama! ...\n"
13
+ }]
14
+
15
+ it_behaves_like 'a string enrichment', values
16
+ end
@@ -12,4 +12,5 @@ describe Krikri::Enrichments::StripPunctuation do
12
12
  :end => "\tmoominpapa moominmama"
13
13
  }]
14
14
  it_behaves_like 'a string enrichment', values
15
+ include_examples 'skips non-strings'
15
16
  end
@@ -13,4 +13,5 @@ describe Krikri::Enrichments::StripWhitespace do
13
13
  }]
14
14
 
15
15
  it_behaves_like 'a string enrichment', values
16
+ include_examples 'skips non-strings'
16
17
  end
@@ -87,6 +87,21 @@ describe Krikri::Enrichments::TimespanSplit do
87
87
  end
88
88
  end
89
89
  end
90
+
91
+ context 'with precision' do
92
+ let(:label) { '2019' }
93
+
94
+ it 'sets begin to correct precision' do
95
+ expect(subject.enrich_value(timespan).begin.first.to_s)
96
+ .to eql Date.parse('2019-01-01').to_s
97
+ end
98
+
99
+ it 'sets end to correct precision' do
100
+ expect(subject.enrich_value(timespan).end.first.to_s)
101
+ .to eql Date.parse('2019-12-31').to_s
102
+
103
+ end
104
+ end
90
105
  end
91
106
  end
92
107
  end
@@ -0,0 +1,98 @@
1
+ # -*- coding: utf-8 -*-
2
+ require 'spec_helper'
3
+
4
+ describe Krikri::Harvesters::ApiHarvester do
5
+ let(:args) { { uri: 'http://example.org/endpoint', api: query_opts } }
6
+ let(:query_opts) { {} }
7
+ subject { described_class.new(args) }
8
+
9
+ describe '#new' do
10
+ let(:query_opts) { { 'params' => { 'q' => :abc } } }
11
+
12
+ it 'accepts api parameters' do
13
+ expect(described_class.new(args)).to have_attributes(:opts => query_opts)
14
+ end
15
+ end
16
+
17
+ context 'with responses' do
18
+ let(:query_opts) { { 'params' => { 'q' => 'tags_ssim:dpla' } } }
19
+ let(:response_string) do
20
+ <<EOM
21
+ { "response": {
22
+ "numFound": 4,
23
+ "start": 0,
24
+ "docs": [{"record_id": "123"}]
25
+ }
26
+ }
27
+ EOM
28
+ end
29
+
30
+ let(:second_response) do
31
+ <<EOM
32
+ { "response": {
33
+ "numFound": 4,
34
+ "start": 1,
35
+ "docs": [{"record_id": "345"},
36
+ {"record_id": "678"},
37
+ {"record_id": "910"}]
38
+ }
39
+ }
40
+ EOM
41
+ end
42
+
43
+ let(:empty_response) do
44
+ <<EOM
45
+ { "response": {
46
+ "numFound": 4,
47
+ "start": 1,
48
+ "docs": []
49
+ }
50
+ }
51
+ EOM
52
+ end
53
+
54
+ let(:single_record) do
55
+ <<EOM
56
+ { "response": {
57
+ "numFound": 1,
58
+ "start": 0,
59
+ "docs": [{"record_id": "123"}]
60
+ }
61
+ }
62
+ EOM
63
+ end
64
+
65
+ before do
66
+ stub_request(:get, "http://example.org/endpoint?q=tags_ssim:dpla")
67
+ .to_return(:status => 200, :body => response_string, :headers => {})
68
+ stub_request(:get, "http://example.org/endpoint?q=tags_ssim:dpla&start=1")
69
+ .to_return(:status => 200, :body => second_response, :headers => {})
70
+ stub_request(:get, "http://example.org/endpoint?q=tags_ssim:dpla&start=4")
71
+ .to_return(:status => 200, :body => empty_response, :headers => {})
72
+
73
+ stub_request(:get, "http://example.org/endpoint?q=id:123")
74
+ .to_return(:status => 200, :body => single_record, :headers => {})
75
+
76
+ end
77
+
78
+ it_behaves_like 'a harvester'
79
+
80
+ describe '#count' do
81
+ it 'returns a count' do
82
+ expect(subject.count).to eq 4
83
+ end
84
+ end
85
+
86
+ describe '#records' do
87
+ it 'returns records lazily' do
88
+ expect(subject).to receive(:request).once.with(args[:api])
89
+ .and_return(JSON.parse(response_string))
90
+ subject.records.first
91
+ end
92
+
93
+ it 'gets all records' do
94
+ expect(subject.records.count).to eq 4
95
+ end
96
+ end
97
+ end
98
+ end
@@ -0,0 +1,47 @@
1
+ # -*- coding: utf-8 -*-
2
+ require 'spec_helper'
3
+
4
+ describe Krikri::Harvesters::ApiHarvester do
5
+ it_behaves_like 'a harvester'
6
+
7
+ let(:args) { { uri: 'http://example.org/endpoint' } }
8
+ subject { described_class.new(args) }
9
+
10
+ shared_context 'with responses' do
11
+ let(:query_opts) { { :q => 'tags_ssim:dpla' } }
12
+ let(:response_string) do
13
+ <<EOM
14
+ { "response": {
15
+ "numFound": 467354,
16
+ "start": 0,
17
+ "docs": []
18
+ }
19
+ }
20
+ EOM
21
+ end
22
+
23
+ before do
24
+ allow(RestClient).to recieve(:get).with(args[:uri], query_opts)
25
+ .and_return(response_string)
26
+ end
27
+ end
28
+
29
+ describe '#new' do
30
+ it 'accepts api parameters' do
31
+ described_class.new()
32
+ require 'pry'
33
+ binding.pry
34
+ end
35
+ end
36
+
37
+ describe '.expected_opts' do
38
+ it 'returns a hash with key and options' do
39
+ end
40
+ end
41
+
42
+ describe '#count' do
43
+ it 'returns a count' do
44
+ expect(subject.count).to eq 100
45
+ end
46
+ end
47
+ end
@@ -0,0 +1,11 @@
1
+ # -*- coding: utf-8 -*-
2
+ require 'spec_helper'
3
+
4
+ describe Krikri::Harvesters::MdlApiHarvester do
5
+ it_behaves_like 'a harvester'
6
+
7
+ let(:args) { { uri: 'http://example.org/endpoint' } }
8
+ subject { described_class.new(args) }
9
+
10
+
11
+ end
@@ -0,0 +1,8 @@
1
+ require 'spec_helper'
2
+
3
+ describe Krikri::Harvesters::MdlHarvester do
4
+ let(:args) { { uri: 'http://example.org/endpoint', api: query_opts } }
5
+ let(:query_opts) { {} }
6
+ subject { described_class.new(args) }
7
+
8
+ end
@@ -361,21 +361,28 @@ EOM
361
361
  end
362
362
 
363
363
  describe '#request_with_sets' do
364
+ let(:sets) { [double('first'), double('second')] }
365
+ let(:opts) { { :set => sets } }
366
+
364
367
  it 'is lazy' do
365
- sets = [double('first'), double('second')]
366
- opts = { :set => sets }
367
368
  expect { |b| subject.send(:request_with_sets, opts, &b) }
368
369
  .not_to yield_control
369
370
  end
370
371
 
371
372
  it 'sends requests' do
372
- sets = [double('first'), double('second')]
373
- opts = { :set => sets }
374
373
  expect { |b| subject.send(:request_with_sets, opts, &b) }
375
374
  .not_to yield_successive_args({ :set => opts[:set][0] },
376
375
  { :set => opts[:set][1] })
377
376
  end
378
377
 
378
+ it 'sends requests lazily' do
379
+ expect(subject).to receive(:give_results).once
380
+ .and_return([1,2,3])
381
+ enum = subject.send(:request_with_sets, opts) do |b|
382
+ subject.give_results
383
+ end
384
+ 3.times { enum.next }
385
+ end
379
386
  end
380
387
 
381
388
  describe '#enqueue' do
@@ -416,7 +423,6 @@ EOM
416
423
  end
417
424
 
418
425
  describe 'concat_enum' do
419
-
420
426
  it 'concatenates enums' do
421
427
  expect(subject.concat_enum([(1..10), (100..110)]).to_a)
422
428
  .to eq (1..10).to_a.concat((100..110).to_a)
@@ -425,7 +431,7 @@ EOM
425
431
  it 'works with lazy' do
426
432
  enum = double
427
433
  expect(enum).not_to receive :each
428
- subject.concat_enum([(1..10), enum]).lazy.take(10)
434
+ subject.concat_enum([(1..10), enum]).lazy.take(10).each(&:inspect)
429
435
  end
430
436
  end
431
437
 
@@ -0,0 +1,40 @@
1
+ require 'spec_helper'
2
+
3
+ describe Krikri::Job do
4
+ let(:agent) { double('agent') }
5
+
6
+ describe '.perform' do
7
+ let(:activity_id) { 1 }
8
+ let(:activity) { double('activity') }
9
+
10
+ before do
11
+ allow(Krikri::Activity).to receive(:find).with(activity_id)
12
+ .and_return(activity)
13
+ end
14
+
15
+ it 'calls #run on activity by id' do
16
+ expect(activity).to receive(:run).and_return(true)
17
+ described_class.perform(activity_id)
18
+ end
19
+
20
+ it 'passes its run method to block' do
21
+ uri = double('uri')
22
+ expect(activity).to receive(:run).and_yield(agent, uri)
23
+ expect(described_class).to receive(:run).with(agent, uri)
24
+ described_class.perform(activity_id)
25
+ end
26
+ end
27
+
28
+ describe '.run' do
29
+ it 'calls #run on agent' do
30
+ activity_uri = double('uri')
31
+ expect(agent).to receive(:run).with(activity_uri).and_return(true)
32
+ described_class.run(agent, activity_uri)
33
+ end
34
+
35
+ it 'defaults activity to nil' do
36
+ expect(agent).to receive(:run).with(nil).and_return(true)
37
+ described_class.run(agent)
38
+ end
39
+ end
40
+ end