newspaper_works 0.1.0

Sign up to get free protection for your applications and to get access to all the features.
Files changed (461) hide show
  1. checksums.yaml +7 -0
  2. data/.fcrepo_wrapper +4 -0
  3. data/.gitignore +43 -0
  4. data/.rubocop.yml +143 -0
  5. data/.solr_wrapper +8 -0
  6. data/.travis.yml +50 -0
  7. data/Gemfile +47 -0
  8. data/LICENSE +203 -0
  9. data/README.md +159 -0
  10. data/Rakefile +38 -0
  11. data/app/actors/hyrax/actors/newspaper_article_actor.rb +8 -0
  12. data/app/actors/hyrax/actors/newspaper_container_actor.rb +8 -0
  13. data/app/actors/hyrax/actors/newspaper_issue_actor.rb +8 -0
  14. data/app/actors/hyrax/actors/newspaper_page_actor.rb +8 -0
  15. data/app/actors/hyrax/actors/newspaper_title_actor.rb +8 -0
  16. data/app/actors/newspaper_works/actors/newspaper_works_upload_actor.rb +88 -0
  17. data/app/assets/config/newspaper_works_manifest.js +2 -0
  18. data/app/assets/images/newspaper_works/.keep +0 -0
  19. data/app/assets/javascripts/newspaper_works/autocomplete_fix.js +33 -0
  20. data/app/assets/javascripts/newspaper_works/ocr_search.js.erb +6 -0
  21. data/app/assets/javascripts/newspaper_works/thumbnail_highlights.js.erb +102 -0
  22. data/app/assets/javascripts/newspaper_works.js +4 -0
  23. data/app/assets/stylesheets/newspaper_works/_issue_search.scss +13 -0
  24. data/app/assets/stylesheets/newspaper_works/_issues_calendar.scss +18 -0
  25. data/app/assets/stylesheets/newspaper_works/_newspaper_works.scss +4 -0
  26. data/app/assets/stylesheets/newspaper_works/_newspapers_search.scss +38 -0
  27. data/app/assets/stylesheets/newspaper_works/_search_results.scss +12 -0
  28. data/app/controllers/hyrax/newspaper_articles_controller.rb +14 -0
  29. data/app/controllers/hyrax/newspaper_containers_controller.rb +14 -0
  30. data/app/controllers/hyrax/newspaper_issues_controller.rb +14 -0
  31. data/app/controllers/hyrax/newspaper_pages_controller.rb +14 -0
  32. data/app/controllers/hyrax/newspaper_titles_controller.rb +13 -0
  33. data/app/controllers/newspaper_works/newspapers_controller.rb +117 -0
  34. data/app/controllers/newspaper_works/newspapers_search_controller.rb +26 -0
  35. data/app/forms/hyrax/newspaper_article_form.rb +11 -0
  36. data/app/forms/hyrax/newspaper_container_form.rb +11 -0
  37. data/app/forms/hyrax/newspaper_issue_form.rb +11 -0
  38. data/app/forms/hyrax/newspaper_page_form.rb +15 -0
  39. data/app/forms/hyrax/newspaper_title_form.rb +12 -0
  40. data/app/forms/newspaper_works/newspaper_core_form_data.rb +17 -0
  41. data/app/helpers/hyrax/newspaper_articles_helper.rb +5 -0
  42. data/app/helpers/hyrax/newspaper_containers_helper.rb +5 -0
  43. data/app/helpers/hyrax/newspaper_issues_helper.rb +5 -0
  44. data/app/helpers/hyrax/newspaper_pages_helper.rb +5 -0
  45. data/app/helpers/newspaper_works/application_helper.rb +5 -0
  46. data/app/helpers/newspaper_works/breadcrumb_helper.rb +92 -0
  47. data/app/helpers/newspaper_works/newspaper_works_helper_behavior.rb +103 -0
  48. data/app/helpers/newspaper_works/newspapers_helper.rb +5 -0
  49. data/app/indexers/concerns/newspaper_works/indexes_full_text.rb +17 -0
  50. data/app/indexers/concerns/newspaper_works/indexes_place_of_publication.rb +67 -0
  51. data/app/indexers/concerns/newspaper_works/indexes_publication_date_range.rb +35 -0
  52. data/app/indexers/concerns/newspaper_works/indexes_relationships.rb +125 -0
  53. data/app/indexers/newspaper_article_indexer.rb +16 -0
  54. data/app/indexers/newspaper_container_indexer.rb +18 -0
  55. data/app/indexers/newspaper_issue_indexer.rb +26 -0
  56. data/app/indexers/newspaper_page_indexer.rb +9 -0
  57. data/app/indexers/newspaper_title_indexer.rb +19 -0
  58. data/app/indexers/newspaper_works/newspaper_core_indexer.rb +21 -0
  59. data/app/jobs/newspaper_works/application_job.rb +4 -0
  60. data/app/jobs/newspaper_works/compose_issue_pdf_job.rb +13 -0
  61. data/app/jobs/newspaper_works/create_issue_pages_job.rb +19 -0
  62. data/app/mailers/newspaper_works/application_mailer.rb +8 -0
  63. data/app/models/concerns/newspaper_works/blacklight_iiif_search/annotation_behavior.rb +82 -0
  64. data/app/models/concerns/newspaper_works/blacklight_iiif_search/search_behavior.rb +27 -0
  65. data/app/models/concerns/newspaper_works/newspaper_core_metadata.rb +67 -0
  66. data/app/models/concerns/newspaper_works/place_of_publication_behavior.rb +15 -0
  67. data/app/models/concerns/newspaper_works/scanned_media_metadata.rb +43 -0
  68. data/app/models/concerns/newspaper_works/solr/document.rb +25 -0
  69. data/app/models/file_set.rb +10 -0
  70. data/app/models/newspaper_article.rb +158 -0
  71. data/app/models/newspaper_container.rb +86 -0
  72. data/app/models/newspaper_issue.rb +115 -0
  73. data/app/models/newspaper_page.rb +70 -0
  74. data/app/models/newspaper_title.rb +111 -0
  75. data/app/models/newspaper_works/application_record.rb +6 -0
  76. data/app/models/newspaper_works/derivative_attachment.rb +8 -0
  77. data/app/models/newspaper_works/ingest_file_relation.rb +14 -0
  78. data/app/presenters/hyrax/newspaper_article_presenter.rb +38 -0
  79. data/app/presenters/hyrax/newspaper_container_presenter.rb +11 -0
  80. data/app/presenters/hyrax/newspaper_issue_presenter.rb +62 -0
  81. data/app/presenters/hyrax/newspaper_page_presenter.rb +72 -0
  82. data/app/presenters/hyrax/newspaper_title_presenter.rb +86 -0
  83. data/app/presenters/newspaper_works/iiif_manifest_presenter_behavior.rb +29 -0
  84. data/app/presenters/newspaper_works/issue_info_presenter.rb +29 -0
  85. data/app/presenters/newspaper_works/newspaper_core_presenter.rb +9 -0
  86. data/app/presenters/newspaper_works/persistent_url_presenter_behavior.rb +16 -0
  87. data/app/presenters/newspaper_works/place_of_publication_presenter_behavior.rb +8 -0
  88. data/app/presenters/newspaper_works/scanned_media_presenter.rb +7 -0
  89. data/app/presenters/newspaper_works/title_info_presenter.rb +13 -0
  90. data/app/search_builders/concerns/newspaper_works/exclude_models.rb +16 -0
  91. data/app/search_builders/concerns/newspaper_works/highlight_search_params.rb +14 -0
  92. data/app/search_builders/newspaper_works/newspapers_search_builder.rb +26 -0
  93. data/app/services/hyrax/article_genre_service.rb +9 -0
  94. data/app/services/newspaper_works/jp2_derivative_service.rb +120 -0
  95. data/app/services/newspaper_works/newspaper_page_derivative_service.rb +91 -0
  96. data/app/services/newspaper_works/pdf_derivative_service.rb +45 -0
  97. data/app/services/newspaper_works/pluggable_derivative_service.rb +114 -0
  98. data/app/services/newspaper_works/text_extraction_derivative_service.rb +56 -0
  99. data/app/services/newspaper_works/text_formats_from_alto_service.rb +77 -0
  100. data/app/services/newspaper_works/tiff_derivative_service.rb +54 -0
  101. data/app/validators/newspaper_works/publication_date_start_end_validator.rb +48 -0
  102. data/app/validators/newspaper_works/publication_date_validator.rb +16 -0
  103. data/app/views/catalog/_index_gallery_newspaper_article_wrapper.html.erb +9 -0
  104. data/app/views/catalog/_index_gallery_newspaper_page_wrapper.html.erb +9 -0
  105. data/app/views/catalog/_index_header_gallery_newspaper_article.html.erb +23 -0
  106. data/app/views/catalog/_index_header_gallery_newspaper_page.html.erb +23 -0
  107. data/app/views/catalog/_index_header_list_newspaper_article.html.erb +7 -0
  108. data/app/views/catalog/_index_header_list_newspaper_page.html.erb +7 -0
  109. data/app/views/catalog/_snippets_more.html.erb +16 -0
  110. data/app/views/catalog/_thumbnail_list_newspaper_article.html.erb +6 -0
  111. data/app/views/catalog/_thumbnail_list_newspaper_page.html.erb +6 -0
  112. data/app/views/hyrax/file_sets/_actions.html.erb +45 -0
  113. data/app/views/hyrax/newspaper_articles/_newspaper_article.html.erb +2 -0
  114. data/app/views/hyrax/newspaper_articles/show.html.erb +1 -0
  115. data/app/views/hyrax/newspaper_containers/_newspaper_container.html.erb +2 -0
  116. data/app/views/hyrax/newspaper_containers/show.html.erb +1 -0
  117. data/app/views/hyrax/newspaper_issues/_newspaper_issue.html.erb +2 -0
  118. data/app/views/hyrax/newspaper_issues/show.html.erb +1 -0
  119. data/app/views/hyrax/newspaper_pages/_newspaper_page.html.erb +2 -0
  120. data/app/views/hyrax/newspaper_pages/show.html.erb +1 -0
  121. data/app/views/hyrax/newspaper_titles/_all_front_pages_form.html.erb +5 -0
  122. data/app/views/hyrax/newspaper_titles/_issue_search_form.html.erb +33 -0
  123. data/app/views/hyrax/newspaper_titles/_issues_calendar.html.erb +63 -0
  124. data/app/views/hyrax/newspaper_titles/_newspaper_title.html.erb +2 -0
  125. data/app/views/hyrax/newspaper_titles/show.html.erb +54 -0
  126. data/app/views/newspaper_works/base/_attribute_rows.html.erb +42 -0
  127. data/app/views/newspaper_works/base/_attributes.html.erb +16 -0
  128. data/app/views/newspaper_works/base/_metadata.html.erb +6 -0
  129. data/app/views/newspaper_works/base/_newspaper_hierarchy.html.erb +14 -0
  130. data/app/views/newspaper_works/base/_persistent_url.html.erb +1 -0
  131. data/app/views/newspaper_works/base/_show.html.erb +45 -0
  132. data/app/views/newspaper_works/newspapers_search/_date_fields.html.erb +29 -0
  133. data/app/views/newspaper_works/newspapers_search/_facet_layout.html.erb +8 -0
  134. data/app/views/newspaper_works/newspapers_search/_facet_limit.html.erb +17 -0
  135. data/app/views/newspaper_works/newspapers_search/_front_pages_input.html.erb +5 -0
  136. data/app/views/newspaper_works/newspapers_search/_keyword_input.html.erb +18 -0
  137. data/app/views/newspaper_works/newspapers_search/_newspapers_facets.html.erb +5 -0
  138. data/app/views/newspaper_works/newspapers_search/_newspapers_search_form.html.erb +13 -0
  139. data/app/views/newspaper_works/newspapers_search/_newspapers_search_help.html.erb +8 -0
  140. data/app/views/newspaper_works/newspapers_search/search.html.erb +13 -0
  141. data/app/views/records/edit_fields/_alternate_title.html.erb +4 -0
  142. data/app/views/records/edit_fields/_genre.html.erb +4 -0
  143. data/app/views/records/edit_fields/_place_of_publication.html.erb +14 -0
  144. data/app/views/records/edit_fields/_subtitle.html.erb +4 -0
  145. data/bin/rails +13 -0
  146. data/config/fcrepo_wrapper_test.yml +5 -0
  147. data/config/initializers/assets.rb +2 -0
  148. data/config/locales/newspaper_article.de.yml +12 -0
  149. data/config/locales/newspaper_article.en.yml +12 -0
  150. data/config/locales/newspaper_article.es.yml +12 -0
  151. data/config/locales/newspaper_article.fr.yml +12 -0
  152. data/config/locales/newspaper_article.it.yml +12 -0
  153. data/config/locales/newspaper_article.pt-BR.yml +12 -0
  154. data/config/locales/newspaper_article.zh.yml +12 -0
  155. data/config/locales/newspaper_container.de.yml +8 -0
  156. data/config/locales/newspaper_container.en.yml +8 -0
  157. data/config/locales/newspaper_container.es.yml +8 -0
  158. data/config/locales/newspaper_container.fr.yml +8 -0
  159. data/config/locales/newspaper_container.it.yml +8 -0
  160. data/config/locales/newspaper_container.pt-BR.yml +8 -0
  161. data/config/locales/newspaper_container.zh.yml +8 -0
  162. data/config/locales/newspaper_issue.de.yml +8 -0
  163. data/config/locales/newspaper_issue.en.yml +8 -0
  164. data/config/locales/newspaper_issue.es.yml +8 -0
  165. data/config/locales/newspaper_issue.fr.yml +8 -0
  166. data/config/locales/newspaper_issue.it.yml +8 -0
  167. data/config/locales/newspaper_issue.pt-BR.yml +8 -0
  168. data/config/locales/newspaper_issue.zh.yml +8 -0
  169. data/config/locales/newspaper_page.de.yml +15 -0
  170. data/config/locales/newspaper_page.en.yml +15 -0
  171. data/config/locales/newspaper_page.es.yml +15 -0
  172. data/config/locales/newspaper_page.fr.yml +15 -0
  173. data/config/locales/newspaper_page.it.yml +15 -0
  174. data/config/locales/newspaper_page.pt-BR.yml +15 -0
  175. data/config/locales/newspaper_page.zh.yml +15 -0
  176. data/config/locales/newspaper_title.de.yml +8 -0
  177. data/config/locales/newspaper_title.en.yml +8 -0
  178. data/config/locales/newspaper_title.es.yml +8 -0
  179. data/config/locales/newspaper_title.fr.yml +8 -0
  180. data/config/locales/newspaper_title.it.yml +8 -0
  181. data/config/locales/newspaper_title.pt-BR.yml +8 -0
  182. data/config/locales/newspaper_title.zh.yml +8 -0
  183. data/config/locales/newspaper_works.de.yml +50 -0
  184. data/config/locales/newspaper_works.en.yml +52 -0
  185. data/config/locales/newspaper_works.es.yml +52 -0
  186. data/config/locales/newspaper_works.fr.yml +52 -0
  187. data/config/locales/newspaper_works.it.yml +52 -0
  188. data/config/locales/newspaper_works.pt-BR.yml +52 -0
  189. data/config/locales/newspaper_works.zh.yml +52 -0
  190. data/config/routes.rb +9 -0
  191. data/config/solr_wrapper_test.yml +9 -0
  192. data/config/test-fixture/solr-config/_rest_managed.json +3 -0
  193. data/config/test-fixture/solr-config/admin-extra.html +31 -0
  194. data/config/test-fixture/solr-config/elevate.xml +36 -0
  195. data/config/test-fixture/solr-config/mapping-ISOLatin1Accent.txt +246 -0
  196. data/config/test-fixture/solr-config/protwords.txt +21 -0
  197. data/config/test-fixture/solr-config/schema.xml +366 -0
  198. data/config/test-fixture/solr-config/scripts.conf +24 -0
  199. data/config/test-fixture/solr-config/solrconfig.xml +322 -0
  200. data/config/test-fixture/solr-config/spellings.txt +2 -0
  201. data/config/test-fixture/solr-config/stopwords.txt +58 -0
  202. data/config/test-fixture/solr-config/stopwords_en.txt +58 -0
  203. data/config/test-fixture/solr-config/synonyms.txt +31 -0
  204. data/config/test-fixture/solr-config/xslt/example.xsl +132 -0
  205. data/config/test-fixture/solr-config/xslt/example_atom.xsl +67 -0
  206. data/config/test-fixture/solr-config/xslt/example_rss.xsl +66 -0
  207. data/config/test-fixture/solr-config/xslt/luke.xsl +337 -0
  208. data/config/vendor/imagemagick-6-policy.xml +76 -0
  209. data/db/migrate/20181214181358_create_newspaper_works_derivative_attachments.rb +12 -0
  210. data/db/migrate/20190107165909_create_newspaper_works_ingest_file_relations.rb +11 -0
  211. data/lib/generators/newspaper_works/assets_generator.rb +29 -0
  212. data/lib/generators/newspaper_works/blacklight_advanced_search_generator.rb +44 -0
  213. data/lib/generators/newspaper_works/blacklight_iiif_search_generator.rb +41 -0
  214. data/lib/generators/newspaper_works/catalog_controller_generator.rb +60 -0
  215. data/lib/generators/newspaper_works/install_generator.rb +97 -0
  216. data/lib/generators/newspaper_works/templates/annotation_behavior.rb +6 -0
  217. data/lib/generators/newspaper_works/templates/config/authorities/newspaper_article_genres.yml +86 -0
  218. data/lib/generators/newspaper_works/templates/config/initializers/newspaper_works.rb +12 -0
  219. data/lib/generators/newspaper_works/templates/config/initializers/patch_blacklight_advanced_search.rb +74 -0
  220. data/lib/generators/newspaper_works/templates/custom_search_builder.rb +23 -0
  221. data/lib/generators/newspaper_works/templates/newspaper_works.scss +1 -0
  222. data/lib/generators/newspaper_works/templates/newspaper_works_helper.rb +3 -0
  223. data/lib/generators/newspaper_works/templates/search_behavior.rb +6 -0
  224. data/lib/newspaper_works/configuration.rb +14 -0
  225. data/lib/newspaper_works/data/fileset_helper.rb +25 -0
  226. data/lib/newspaper_works/data/path_helper.rb +40 -0
  227. data/lib/newspaper_works/data/work_derivatives.rb +314 -0
  228. data/lib/newspaper_works/data/work_file.rb +92 -0
  229. data/lib/newspaper_works/data/work_files.rb +181 -0
  230. data/lib/newspaper_works/data.rb +35 -0
  231. data/lib/newspaper_works/engine.rb +42 -0
  232. data/lib/newspaper_works/errors.rb +14 -0
  233. data/lib/newspaper_works/ingest/base_ingest.rb +69 -0
  234. data/lib/newspaper_works/ingest/base_publication_info.rb +35 -0
  235. data/lib/newspaper_works/ingest/batch_ingest_helper.rb +44 -0
  236. data/lib/newspaper_works/ingest/batch_issue_ingester.rb +129 -0
  237. data/lib/newspaper_works/ingest/chronam_publication_info.rb +133 -0
  238. data/lib/newspaper_works/ingest/from_command.rb +52 -0
  239. data/lib/newspaper_works/ingest/image_ingest_issues.rb +43 -0
  240. data/lib/newspaper_works/ingest/issue_images.rb +51 -0
  241. data/lib/newspaper_works/ingest/lc_publication_info.rb +144 -0
  242. data/lib/newspaper_works/ingest/named_issue_metadata.rb +60 -0
  243. data/lib/newspaper_works/ingest/ndnp/batch_ingester.rb +64 -0
  244. data/lib/newspaper_works/ingest/ndnp/batch_xml_ingest.rb +72 -0
  245. data/lib/newspaper_works/ingest/ndnp/container_ingest.rb +99 -0
  246. data/lib/newspaper_works/ingest/ndnp/container_ingester.rb +84 -0
  247. data/lib/newspaper_works/ingest/ndnp/container_metadata.rb +87 -0
  248. data/lib/newspaper_works/ingest/ndnp/issue_ingest.rb +81 -0
  249. data/lib/newspaper_works/ingest/ndnp/issue_ingester.rb +101 -0
  250. data/lib/newspaper_works/ingest/ndnp/issue_metadata.rb +96 -0
  251. data/lib/newspaper_works/ingest/ndnp/ndnp_asset_helper.rb +20 -0
  252. data/lib/newspaper_works/ingest/ndnp/ndnp_mets_helper.rb +70 -0
  253. data/lib/newspaper_works/ingest/ndnp/page_ingest.rb +47 -0
  254. data/lib/newspaper_works/ingest/ndnp/page_ingester.rb +157 -0
  255. data/lib/newspaper_works/ingest/ndnp/page_metadata.rb +112 -0
  256. data/lib/newspaper_works/ingest/ndnp.rb +21 -0
  257. data/lib/newspaper_works/ingest/newspaper_issue_ingest.rb +56 -0
  258. data/lib/newspaper_works/ingest/newspaper_page_ingest.rb +6 -0
  259. data/lib/newspaper_works/ingest/page_image.rb +52 -0
  260. data/lib/newspaper_works/ingest/path_enumeration.rb +52 -0
  261. data/lib/newspaper_works/ingest/pdf_images.rb +85 -0
  262. data/lib/newspaper_works/ingest/pdf_issue.rb +20 -0
  263. data/lib/newspaper_works/ingest/pdf_issues.rb +39 -0
  264. data/lib/newspaper_works/ingest/pdf_pages.rb +114 -0
  265. data/lib/newspaper_works/ingest/pub_finder.rb +89 -0
  266. data/lib/newspaper_works/ingest/publication_info.rb +44 -0
  267. data/lib/newspaper_works/ingest.rb +90 -0
  268. data/lib/newspaper_works/issue_pdf_composer.rb +111 -0
  269. data/lib/newspaper_works/logging.rb +54 -0
  270. data/lib/newspaper_works/page_finder.rb +62 -0
  271. data/lib/newspaper_works/resource_fetcher.rb +78 -0
  272. data/lib/newspaper_works/text_extraction/alto_reader.rb +122 -0
  273. data/lib/newspaper_works/text_extraction/page_ocr.rb +100 -0
  274. data/lib/newspaper_works/text_extraction/render_alto.rb +84 -0
  275. data/lib/newspaper_works/text_extraction/word_coords_builder.rb +30 -0
  276. data/lib/newspaper_works/text_extraction.rb +10 -0
  277. data/lib/newspaper_works/version.rb +3 -0
  278. data/lib/newspaper_works.rb +19 -0
  279. data/lib/tasks/newspaper_works_tasks.rake +39 -0
  280. data/newspaper_works.gemspec +49 -0
  281. data/spec/.keep.txt +1 -0
  282. data/spec/actors/newspaper_works/actors/newspaper_works_upload_actor_spec.rb +69 -0
  283. data/spec/controllers/catalog_controller_spec.rb +63 -0
  284. data/spec/controllers/newspaper_works/newspapers_controller_spec.rb +114 -0
  285. data/spec/controllers/newspaper_works/newspapers_search_controller_spec.rb +21 -0
  286. data/spec/factories/ability.rb +6 -0
  287. data/spec/factories/newspaper_issue.rb +7 -0
  288. data/spec/factories/newspaper_issue_ingest.rb +6 -0
  289. data/spec/factories/newspaper_page.rb +7 -0
  290. data/spec/factories/newspaper_page_ingest.rb +6 -0
  291. data/spec/factories/newspaper_page_solr_document.rb +12 -0
  292. data/spec/factories/newspaper_title.rb +8 -0
  293. data/spec/factories/uploaded_pdf_file.rb +9 -0
  294. data/spec/factories/user.rb +13 -0
  295. data/spec/features/front_pages_for_title_spec.rb +19 -0
  296. data/spec/features/newspaper_title_search_spec.rb +30 -0
  297. data/spec/features/newspapers_search_spec.rb +49 -0
  298. data/spec/features/search_results_thumbnail_highlights_spec.rb +33 -0
  299. data/spec/features_shared.rb +71 -0
  300. data/spec/fixtures/files/4.1.07.jp2 +0 -0
  301. data/spec/fixtures/files/4.1.07.tiff +0 -0
  302. data/spec/fixtures/files/README.md +7 -0
  303. data/spec/fixtures/files/alto-2-0.xsd +714 -0
  304. data/spec/fixtures/files/broken-truncated.pdf +0 -0
  305. data/spec/fixtures/files/credits.md +16 -0
  306. data/spec/fixtures/files/lowres-gray-via-ndnp-sample.tiff +0 -0
  307. data/spec/fixtures/files/minimal-1-page.pdf +0 -0
  308. data/spec/fixtures/files/minimal-2-page.pdf +0 -0
  309. data/spec/fixtures/files/minimal-alto.xml +31 -0
  310. data/spec/fixtures/files/ndnp-alto-sample.xml +24 -0
  311. data/spec/fixtures/files/ndnp-sample1-json.json +1 -0
  312. data/spec/fixtures/files/ndnp-sample1-txt.txt +1 -0
  313. data/spec/fixtures/files/ndnp-sample1.pdf +0 -0
  314. data/spec/fixtures/files/ocr_alto.xml +202 -0
  315. data/spec/fixtures/files/ocr_alto_scaled_4pts_per_px.xml +202 -0
  316. data/spec/fixtures/files/ocr_color.tiff +0 -0
  317. data/spec/fixtures/files/ocr_gray.jp2 +0 -0
  318. data/spec/fixtures/files/ocr_gray.tiff +0 -0
  319. data/spec/fixtures/files/ocr_mono.tiff +0 -0
  320. data/spec/fixtures/files/page1.tiff +0 -0
  321. data/spec/fixtures/files/resource_mocks/chronam/http404-expected +0 -0
  322. data/spec/fixtures/files/resource_mocks/chronam/sn84038814.rdf +1028 -0
  323. data/spec/fixtures/files/resource_mocks/chronam/sn93059126.rdf +36 -0
  324. data/spec/fixtures/files/resource_mocks/chronam/sn94051019.rdf +37 -0
  325. data/spec/fixtures/files/resource_mocks/geonames/Chicopee +1104 -0
  326. data/spec/fixtures/files/resource_mocks/geonames/Denver +1104 -0
  327. data/spec/fixtures/files/resource_mocks/geonames/Marysville +279 -0
  328. data/spec/fixtures/files/resource_mocks/geonames/Marysville2 +279 -0
  329. data/spec/fixtures/files/resource_mocks/geonames/SLC +1104 -0
  330. data/spec/fixtures/files/resource_mocks/lccn/sn2099999999 +1 -0
  331. data/spec/fixtures/files/resource_mocks/lccn/sn82014496 +2 -0
  332. data/spec/fixtures/files/resource_mocks/lccn/sn83020109 +1 -0
  333. data/spec/fixtures/files/resource_mocks/lccn/sn83021453 +2 -0
  334. data/spec/fixtures/files/resource_mocks/lccn/sn83045396 +2 -0
  335. data/spec/fixtures/files/resource_mocks/lccn/sn84038814 +2 -0
  336. data/spec/fixtures/files/resource_mocks/lccn/sn93059126 +1 -0
  337. data/spec/fixtures/files/resource_mocks/lccn/sn94051019 +1 -0
  338. data/spec/fixtures/files/resource_mocks/lccn/sn99999999 +1 -0
  339. data/spec/fixtures/files/resource_mocks/urls.json +82 -0
  340. data/spec/fixtures/files/sample-4page-issue.pdf +0 -0
  341. data/spec/fixtures/files/sample-color-newsletter.pdf +0 -0
  342. data/spec/fixtures/files/thumbnail.jpg +0 -0
  343. data/spec/forms/hyrax/newspaper_article_form_spec.rb +33 -0
  344. data/spec/forms/hyrax/newspaper_container_form_spec.rb +30 -0
  345. data/spec/forms/hyrax/newspaper_issue_form_spec.rb +31 -0
  346. data/spec/forms/hyrax/newspaper_page_form_spec.rb +28 -0
  347. data/spec/forms/hyrax/newspaper_title_form_spec.rb +31 -0
  348. data/spec/forms/newspaper_works/newspaper_core_form_data_spec.rb +12 -0
  349. data/spec/helpers/newspaper_works/breadcrumb_helper_spec.rb +82 -0
  350. data/spec/helpers/newspaper_works_helper_spec.rb +57 -0
  351. data/spec/indexers/concerns/newspaper_works/indexes_full_text_spec.rb +31 -0
  352. data/spec/indexers/concerns/newspaper_works/indexes_place_of_publication_spec.rb +53 -0
  353. data/spec/indexers/concerns/newspaper_works/indexes_publication_date_range_spec.rb +39 -0
  354. data/spec/indexers/concerns/newspaper_works/indexes_relationships_spec.rb +86 -0
  355. data/spec/indexers/newspaper_article_indexer_spec.rb +29 -0
  356. data/spec/indexers/newspaper_issue_indexer_spec.rb +19 -0
  357. data/spec/indexers/newspaper_title_indexer_spec.rb +22 -0
  358. data/spec/indexers/newspaper_works/newspaper_core_indexer_spec.rb +23 -0
  359. data/spec/lib/newspaper_works/configuration_spec.rb +18 -0
  360. data/spec/lib/newspaper_works/data/work_derivatives_spec.rb +245 -0
  361. data/spec/lib/newspaper_works/data/work_file_spec.rb +99 -0
  362. data/spec/lib/newspaper_works/data/work_files_spec.rb +224 -0
  363. data/spec/lib/newspaper_works/ingest/batch_issue_ingester_spec.rb +158 -0
  364. data/spec/lib/newspaper_works/ingest/chronam_publication_info_spec.rb +35 -0
  365. data/spec/lib/newspaper_works/ingest/from_command_spec.rb +75 -0
  366. data/spec/lib/newspaper_works/ingest/image_ingest_issues_spec.rb +62 -0
  367. data/spec/lib/newspaper_works/ingest/ingest_shared.rb +75 -0
  368. data/spec/lib/newspaper_works/ingest/issue_images_spec.rb +65 -0
  369. data/spec/lib/newspaper_works/ingest/lc_publication_info_spec.rb +34 -0
  370. data/spec/lib/newspaper_works/ingest/ndnp/batch_ingester_spec.rb +131 -0
  371. data/spec/lib/newspaper_works/ingest/ndnp/batch_xml_ingest_spec.rb +64 -0
  372. data/spec/lib/newspaper_works/ingest/ndnp/container_ingest_spec.rb +44 -0
  373. data/spec/lib/newspaper_works/ingest/ndnp/container_ingester_spec.rb +126 -0
  374. data/spec/lib/newspaper_works/ingest/ndnp/container_metadata_spec.rb +36 -0
  375. data/spec/lib/newspaper_works/ingest/ndnp/issue_ingest_spec.rb +108 -0
  376. data/spec/lib/newspaper_works/ingest/ndnp/issue_ingester_spec.rb +155 -0
  377. data/spec/lib/newspaper_works/ingest/ndnp/issue_metadata_spec.rb +84 -0
  378. data/spec/lib/newspaper_works/ingest/ndnp/page_ingest_spec.rb +79 -0
  379. data/spec/lib/newspaper_works/ingest/ndnp/page_ingester_spec.rb +184 -0
  380. data/spec/lib/newspaper_works/ingest/ndnp/page_metadata_spec.rb +85 -0
  381. data/spec/lib/newspaper_works/ingest/newspaper_issue_ingest_spec.rb +83 -0
  382. data/spec/lib/newspaper_works/ingest/newspaper_page_ingest_spec.rb +77 -0
  383. data/spec/lib/newspaper_works/ingest/page_image_spec.rb +29 -0
  384. data/spec/lib/newspaper_works/ingest/pdf_images_spec.rb +32 -0
  385. data/spec/lib/newspaper_works/ingest/pdf_issue_spec.rb +29 -0
  386. data/spec/lib/newspaper_works/ingest/pdf_issues_spec.rb +62 -0
  387. data/spec/lib/newspaper_works/ingest/pdf_pages_spec.rb +110 -0
  388. data/spec/lib/newspaper_works/ingest/pub_finder_spec.rb +58 -0
  389. data/spec/lib/newspaper_works/ingest/publication_info_spec.rb +61 -0
  390. data/spec/lib/newspaper_works/ingest_spec.rb +45 -0
  391. data/spec/lib/newspaper_works/issue_pdf_composer_spec.rb +101 -0
  392. data/spec/lib/newspaper_works/logging_spec.rb +53 -0
  393. data/spec/lib/newspaper_works/page_finder_spec.rb +53 -0
  394. data/spec/lib/newspaper_works/resource_fetcher_spec.rb +65 -0
  395. data/spec/lib/newspaper_works/text_extraction/alto_reader_spec.rb +49 -0
  396. data/spec/lib/newspaper_works/text_extraction/page_ocr_spec.rb +84 -0
  397. data/spec/lib/newspaper_works/text_extraction/render_alto_spec.rb +54 -0
  398. data/spec/lib/newspaper_works/text_extraction/word_coords_builder_spec.rb +30 -0
  399. data/spec/lib/tasks/newspaper_works_rake_spec.rb +124 -0
  400. data/spec/misc_shared.rb +109 -0
  401. data/spec/model_shared.rb +134 -0
  402. data/spec/models/concerns/newspaper_works/blacklight_iiif_search/annotation_behavior_spec.rb +45 -0
  403. data/spec/models/concerns/newspaper_works/blacklight_iiif_search/search_behavior_spec.rb +27 -0
  404. data/spec/models/concerns/newspaper_works/newspaper_core_metadata_spec.rb +45 -0
  405. data/spec/models/concerns/newspaper_works/place_of_publication_behavior_spec.rb +17 -0
  406. data/spec/models/concerns/newspaper_works/scanned_media_metadata_spec.rb +35 -0
  407. data/spec/models/newspaper_article_spec.rb +73 -0
  408. data/spec/models/newspaper_container_spec.rb +111 -0
  409. data/spec/models/newspaper_issue_spec.rb +91 -0
  410. data/spec/models/newspaper_page_spec.rb +44 -0
  411. data/spec/models/newspaper_title_spec.rb +116 -0
  412. data/spec/models/newspaper_works/derivative_attachment_spec.rb +37 -0
  413. data/spec/models/newspaper_works/ingest_file_relation_spec.rb +56 -0
  414. data/spec/models/solr_document_spec.rb +14 -0
  415. data/spec/ndnp_shared.rb +48 -0
  416. data/spec/presenters/hyrax/newspaper_article_presenter_spec.rb +53 -0
  417. data/spec/presenters/hyrax/newspaper_container_presenter_spec.rb +20 -0
  418. data/spec/presenters/hyrax/newspaper_issue_presenter_spec.rb +65 -0
  419. data/spec/presenters/hyrax/newspaper_page_presenter_spec.rb +75 -0
  420. data/spec/presenters/hyrax/newspaper_title_presenter_spec.rb +153 -0
  421. data/spec/presenters/newspaper_works/iiif_manifest_presenter_behavior_spec.rb +32 -0
  422. data/spec/presenters/newspaper_works/issue_info_presenter_spec.rb +51 -0
  423. data/spec/presenters/newspaper_works/newspaper_core_presenter_spec.rb +22 -0
  424. data/spec/presenters/newspaper_works/persistent_url_presenter_behavior_spec.rb +24 -0
  425. data/spec/presenters/newspaper_works/place_of_publication_presenter_behavior_spec.rb +17 -0
  426. data/spec/presenters/newspaper_works/scanned_media_presenter_spec.rb +18 -0
  427. data/spec/presenters/newspaper_works/title_info_presenter_spec.rb +23 -0
  428. data/spec/routing/route_spec.rb +52 -0
  429. data/spec/search_builders/custom_search_builder_spec.rb +34 -0
  430. data/spec/search_builders/newspaper_works/newspapers_search_builder_spec.rb +33 -0
  431. data/spec/services/hyrax/article_genre_service_spec.rb +12 -0
  432. data/spec/services/hyrax/resource_types_service_spec.rb +12 -0
  433. data/spec/services/newspaper_works/jp2_derivative_service_spec.rb +62 -0
  434. data/spec/services/newspaper_works/newspaper_page_derivative_service_spec.rb +125 -0
  435. data/spec/services/newspaper_works/pdf_derivative_service_spec.rb +62 -0
  436. data/spec/services/newspaper_works/pluggable_derivative_service_spec.rb +204 -0
  437. data/spec/services/newspaper_works/text_extraction_derivative_service_spec.rb +82 -0
  438. data/spec/services/newspaper_works/text_formats_from_alto_service_spec.rb +129 -0
  439. data/spec/services/newspaper_works/tiff_derivative_service_spec.rb +58 -0
  440. data/spec/spec_helper.rb +261 -0
  441. data/spec/support/controller_level_helpers.rb +28 -0
  442. data/spec/test_app_templates/lib/generators/test_app_generator.rb +22 -0
  443. data/spec/views/catalog/_index_gallery_newspaper_page_wrapper.html.erb_spec.rb +36 -0
  444. data/spec/views/catalog/_index_header_list_newspaper_page.html.erb_spec.rb +26 -0
  445. data/spec/views/catalog/_thumbnail_list_newspaper_page.html.erb_spec.rb +35 -0
  446. data/spec/views/hyrax/newspaper_titles/_all_front_pages_form.html.erb_spec.rb +16 -0
  447. data/spec/views/hyrax/newspaper_titles/_issue_search_form.html.erb_spec.rb +33 -0
  448. data/spec/views/hyrax/newspaper_titles/_issues_calendar.html.erb_spec.rb +37 -0
  449. data/spec/views/hyrax/newspaper_titles/show.html.erb_spec.rb +87 -0
  450. data/spec/views/newspaper_works/base/_attribute_rows.html.erb_spec.rb +60 -0
  451. data/spec/views/newspaper_works/base/_newspaper_hierarchy.html.erb_spec.rb +80 -0
  452. data/spec/views/newspaper_works/base/_show.html.erb_spec.rb +78 -0
  453. data/spec/views/newspaper_works/newspapers_search/search.html.erb_spec.rb +54 -0
  454. data/spec/views/records/edit_fields/_place_of_publication.html.erb_spec.rb +26 -0
  455. data/tasks/newspaperworks_dev.rake +26 -0
  456. data/test/integration/navigation_test.rb +7 -0
  457. data/test/lib/generators/newspaper_works/install_generator_test.rb +16 -0
  458. data/test/newspaper_works_test.rb +7 -0
  459. data/test/test_helper.rb +17 -0
  460. data/tmp/.keep +0 -0
  461. metadata +1037 -0
@@ -0,0 +1,366 @@
1
+ <?xml version="1.0" encoding="UTF-8" ?>
2
+ <!--
3
+ Licensed to the Apache Software Foundation (ASF) under one or more
4
+ contributor license agreements. See the NOTICE file distributed with
5
+ this work for additional information regarding copyright ownership.
6
+ The ASF licenses this file to You under the Apache License, Version 2.0
7
+ (the "License"); you may not use this file except in compliance with
8
+ the License. You may obtain a copy of the License at
9
+
10
+ http://www.apache.org/licenses/LICENSE-2.0
11
+
12
+ Unless required by applicable law or agreed to in writing, software
13
+ distributed under the License is distributed on an "AS IS" BASIS,
14
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
15
+ See the License for the specific language governing permissions and
16
+ limitations under the License.
17
+ -->
18
+
19
+ <!--
20
+ This is the Solr schema file. This file should be named "schema.xml" and
21
+ should be in the conf directory under the solr home
22
+ (i.e. ./solr/conf/schema.xml by default)
23
+ or located where the classloader for the Solr webapp can find it.
24
+
25
+ This example schema is the recommended starting point for users.
26
+ It should be kept correct and concise, usable out-of-the-box.
27
+
28
+ For more information, on how to customize this file, please see
29
+ http://wiki.apache.org/solr/SchemaXml
30
+
31
+ PERFORMANCE NOTE: this schema includes many optional features and should not
32
+ be used for benchmarking. To improve performance one could
33
+ - set stored="false" for all fields possible (esp large fields) when you
34
+ only need to search on the field but don't need to return the original
35
+ value.
36
+ - set indexed="false" if you don't need to search on the field, but only
37
+ return the field as a result of searching on other indexed fields.
38
+ - remove all unneeded copyField statements
39
+ - for best index size and searching performance, set "index" to false
40
+ for all general text fields, use copyField to copy them to the
41
+ catchall "text" field, and use that for searching.
42
+ - For maximum indexing performance, use the StreamingUpdateSolrServer
43
+ java client.
44
+ - Remember to run the JVM in server mode, and use a higher logging level
45
+ that avoids logging every request
46
+ -->
47
+
48
+ <schema name="Hydra Demo Index" version="1.5">
49
+ <!-- attribute "name" is the name of this schema and is only used for display purposes.
50
+ Applications should change this to reflect the nature of the search collection.
51
+ version="1.4" is Solr's version number for the schema syntax and semantics. It should
52
+ not normally be changed by applications.
53
+ 1.0: multiValued attribute did not exist, all fields are multiValued by nature
54
+ 1.1: multiValued attribute introduced, false by default
55
+ 1.2: omitTermFreqAndPositions attribute introduced, true by default except for text fields.
56
+ 1.3: removed optional field compress feature
57
+ 1.4: default auto-phrase (QueryParser feature) to off
58
+ -->
59
+
60
+ <types>
61
+ <fieldType name="string" class="solr.StrField" sortMissingLast="true" />
62
+ <fieldType name="boolean" class="solr.BoolField" sortMissingLast="true"/>
63
+ <fieldType name="rand" class="solr.RandomSortField" omitNorms="true"/>
64
+
65
+ <!-- Default numeric field types. -->
66
+ <fieldType name="int" class="solr.TrieIntField" precisionStep="0" positionIncrementGap="0"/>
67
+ <fieldType name="float" class="solr.TrieFloatField" precisionStep="0" positionIncrementGap="0"/>
68
+ <fieldType name="long" class="solr.TrieLongField" precisionStep="0" positionIncrementGap="0"/>
69
+ <fieldType name="double" class="solr.TrieDoubleField" precisionStep="0" positionIncrementGap="0"/>
70
+
71
+ <!-- trie numeric field types for faster range queries -->
72
+ <fieldType name="tint" class="solr.TrieIntField" precisionStep="8" positionIncrementGap="0"/>
73
+ <fieldType name="tfloat" class="solr.TrieFloatField" precisionStep="8" positionIncrementGap="0"/>
74
+ <fieldType name="tlong" class="solr.TrieLongField" precisionStep="8" positionIncrementGap="0"/>
75
+ <fieldType name="tdouble" class="solr.TrieDoubleField" precisionStep="8" positionIncrementGap="0"/>
76
+
77
+ <!-- The format for this date field is of the form 1995-12-31T23:59:59Z
78
+ Optional fractional seconds are allowed: 1995-12-31T23:59:59.999Z
79
+ -->
80
+ <fieldType name="date" class="solr.TrieDateField" precisionStep="0" positionIncrementGap="0"/>
81
+ <!-- A Trie based date field for faster date range queries and date faceting. -->
82
+ <fieldType name="tdate" class="solr.TrieDateField" precisionStep="6" positionIncrementGap="0"/>
83
+
84
+
85
+ <!-- This point type indexes the coordinates as separate fields (subFields)
86
+ If subFieldType is defined, it references a type, and a dynamic field
87
+ definition is created matching *___<typename>. Alternately, if
88
+ subFieldSuffix is defined, that is used to create the subFields.
89
+ Example: if subFieldType="double", then the coordinates would be
90
+ indexed in fields myloc_0___double,myloc_1___double.
91
+ Example: if subFieldSuffix="_d" then the coordinates would be indexed
92
+ in fields myloc_0_d,myloc_1_d
93
+ The subFields are an implementation detail of the fieldType, and end
94
+ users normally should not need to know about them.
95
+ -->
96
+ <fieldType name="point" class="solr.PointType" dimension="2" subFieldSuffix="_d"/>
97
+
98
+ <!-- A specialized field for geospatial search. If indexed, this fieldType must not be multivalued. -->
99
+ <fieldType name="location" class="solr.LatLonType" subFieldSuffix="_coordinate"/>
100
+
101
+ <!-- An alternative geospatial field type new to Solr 4. It supports multiValued and polygon shapes.
102
+ For more information about this and other Spatial fields new to Solr 4, see:
103
+ http://wiki.apache.org/solr/SolrAdaptersForLuceneSpatial4
104
+ -->
105
+ <fieldType name="location_rpt" class="solr.SpatialRecursivePrefixTreeFieldType"
106
+ geo="true" distErrPct="0.025" maxDistErr="0.000009" distanceUnits="degrees" />
107
+
108
+ <fieldType name="text" class="solr.TextField" omitNorms="false">
109
+ <analyzer>
110
+ <tokenizer class="solr.ICUTokenizerFactory"/>
111
+ <filter class="solr.ICUFoldingFilterFactory"/> <!-- NFKC, case folding, diacritics removed -->
112
+ <filter class="solr.TrimFilterFactory"/>
113
+ </analyzer>
114
+ </fieldType>
115
+
116
+ <!-- A text field that only splits on whitespace for exact matching of words -->
117
+ <fieldType name="text_ws" class="solr.TextField" positionIncrementGap="100">
118
+ <analyzer>
119
+ <tokenizer class="solr.WhitespaceTokenizerFactory"/>
120
+ <filter class="solr.TrimFilterFactory"/>
121
+ </analyzer>
122
+ </fieldType>
123
+
124
+ <!-- single token analyzed text, for sorting. Punctuation is significant. -->
125
+ <fieldtype name="alphaSort" class="solr.TextField" sortMissingLast="true" omitNorms="true">
126
+ <analyzer>
127
+ <tokenizer class="solr.KeywordTokenizerFactory" />
128
+ <filter class="solr.ICUFoldingFilterFactory"/>
129
+ <filter class="solr.TrimFilterFactory" />
130
+ </analyzer>
131
+ </fieldtype>
132
+
133
+ <!-- A text field with defaults appropriate for English -->
134
+ <fieldType name="text_en" class="solr.TextField" positionIncrementGap="100">
135
+ <analyzer>
136
+ <tokenizer class="solr.ICUTokenizerFactory"/>
137
+ <filter class="solr.ICUFoldingFilterFactory"/> <!-- NFKC, case folding, diacritics removed -->
138
+ <filter class="solr.EnglishPossessiveFilterFactory"/>
139
+ <!-- EnglishMinimalStemFilterFactory is less aggressive than PorterStemFilterFactory: -->
140
+ <filter class="solr.EnglishMinimalStemFilterFactory"/>
141
+ <!--
142
+ <filter class="solr.PorterStemFilterFactory"/>
143
+ -->
144
+ <filter class="solr.TrimFilterFactory"/>
145
+ </analyzer>
146
+ </fieldType>
147
+
148
+ <!-- queries for paths match documents at that path, or in descendent paths -->
149
+ <fieldType name="descendent_path" class="solr.TextField">
150
+ <analyzer type="index">
151
+ <tokenizer class="solr.PathHierarchyTokenizerFactory" delimiter="/" />
152
+ </analyzer>
153
+ <analyzer type="query">
154
+ <tokenizer class="solr.KeywordTokenizerFactory" />
155
+ </analyzer>
156
+ </fieldType>
157
+
158
+ <!-- queries for paths match documents at that path, or in ancestor paths -->
159
+ <fieldType name="ancestor_path" class="solr.TextField">
160
+ <analyzer type="index">
161
+ <tokenizer class="solr.KeywordTokenizerFactory" />
162
+ </analyzer>
163
+ <analyzer type="query">
164
+ <tokenizer class="solr.PathHierarchyTokenizerFactory" delimiter="/" />
165
+ </analyzer>
166
+ </fieldType>
167
+
168
+ <fieldType class="solr.TextField" name="textSuggest" positionIncrementGap="100">
169
+ <analyzer>
170
+ <tokenizer class="solr.KeywordTokenizerFactory"/>
171
+ <filter class="solr.StandardFilterFactory"/>
172
+ <filter class="solr.LowerCaseFilterFactory"/>
173
+ <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
174
+ </analyzer>
175
+ </fieldType>
176
+ </types>
177
+
178
+
179
+ <fields>
180
+ <!-- If you remove this field, you must _also_ disable the update log in solrconfig.xml
181
+ or Solr won't start. _version_ and update log are required for SolrCloud
182
+ -->
183
+ <field name="_version_" type="long" indexed="true" stored="true"/>
184
+
185
+ <field name="id" type="string" stored="true" indexed="true" multiValued="false" required="true"/>
186
+ <field name="timestamp" type="date" indexed="true" stored="true" default="NOW" multiValued="false"/>
187
+
188
+ <field name="lat" type="tdouble" stored="true" indexed="true" multiValued="false"/>
189
+ <field name="lng" type="tdouble" stored="true" indexed="true" multiValued="false"/>
190
+
191
+ <!-- NOTE: not all possible Solr field types are represented in the dynamic fields -->
192
+
193
+ <!-- text (_t...) -->
194
+ <dynamicField name="*_ti" type="text" stored="false" indexed="true" multiValued="false"/>
195
+ <dynamicField name="*_tim" type="text" stored="false" indexed="true" multiValued="true"/>
196
+ <dynamicField name="*_ts" type="text" stored="true" indexed="false" multiValued="false"/>
197
+ <dynamicField name="*_tsm" type="text" stored="true" indexed="false" multiValued="true"/>
198
+ <dynamicField name="*_tsi" type="text" stored="true" indexed="true" multiValued="false"/>
199
+ <dynamicField name="*_tsim" type="text" stored="true" indexed="true" multiValued="true"/>
200
+ <dynamicField name="*_tiv" type="text" stored="false" indexed="true" multiValued="false" termVectors="true" termPositions="true" termOffsets="true"/>
201
+ <dynamicField name="*_timv" type="text" stored="false" indexed="true" multiValued="true" termVectors="true" termPositions="true" termOffsets="true"/>
202
+ <dynamicField name="*_tsiv" type="text" stored="true" indexed="true" multiValued="false" termVectors="true" termPositions="true" termOffsets="true"/>
203
+ <dynamicField name="*_tsimv" type="text" stored="true" indexed="true" multiValued="true" termVectors="true" termPositions="true" termOffsets="true"/>
204
+
205
+ <!-- English text (_te...) -->
206
+ <dynamicField name="*_tei" type="text_en" stored="false" indexed="true" multiValued="false"/>
207
+ <dynamicField name="*_teim" type="text_en" stored="false" indexed="true" multiValued="true"/>
208
+ <dynamicField name="*_tes" type="text_en" stored="true" indexed="false" multiValued="false"/>
209
+ <dynamicField name="*_tesm" type="text_en" stored="true" indexed="false" multiValued="true"/>
210
+ <dynamicField name="*_tesi" type="text_en" stored="true" indexed="true" multiValued="false"/>
211
+ <dynamicField name="*_tesim" type="text_en" stored="true" indexed="true" multiValued="true"/>
212
+ <dynamicField name="*_teiv" type="text_en" stored="false" indexed="true" multiValued="false" termVectors="true" termPositions="true" termOffsets="true"/>
213
+ <dynamicField name="*_teimv" type="text_en" stored="false" indexed="true" multiValued="true" termVectors="true" termPositions="true" termOffsets="true"/>
214
+ <dynamicField name="*_tesiv" type="text_en" stored="true" indexed="true" multiValued="false" termVectors="true" termPositions="true" termOffsets="true"/>
215
+ <dynamicField name="*_tesimv" type="text_en" stored="true" indexed="true" multiValued="true" termVectors="true" termPositions="true" termOffsets="true"/>
216
+
217
+ <!-- string (_s...) -->
218
+ <dynamicField name="*_si" type="string" stored="false" indexed="true" multiValued="false"/>
219
+ <dynamicField name="*_sim" type="string" stored="false" indexed="true" multiValued="true"/>
220
+ <dynamicField name="*_ss" type="string" stored="true" indexed="false" multiValued="false"/>
221
+ <dynamicField name="*_ssm" type="string" stored="true" indexed="false" multiValued="true"/>
222
+ <dynamicField name="*_ssi" type="string" stored="true" indexed="true" multiValued="false"/>
223
+ <dynamicField name="*_ssim" type="string" stored="true" indexed="true" multiValued="true"/>
224
+ <dynamicField name="*_ssort" type="alphaSort" stored="false" indexed="true" multiValued="false"/>
225
+
226
+ <!-- integer (_i...) -->
227
+ <dynamicField name="*_ii" type="int" stored="false" indexed="true" multiValued="false"/>
228
+ <dynamicField name="*_iim" type="int" stored="false" indexed="true" multiValued="true"/>
229
+ <dynamicField name="*_is" type="int" stored="true" indexed="false" multiValued="false"/>
230
+ <dynamicField name="*_ism" type="int" stored="true" indexed="false" multiValued="true"/>
231
+ <dynamicField name="*_isi" type="int" stored="true" indexed="true" multiValued="false"/>
232
+ <dynamicField name="*_isim" type="int" stored="true" indexed="true" multiValued="true"/>
233
+
234
+ <!-- trie integer (_it...) (for faster range queries) -->
235
+ <dynamicField name="*_iti" type="tint" stored="false" indexed="true" multiValued="false"/>
236
+ <dynamicField name="*_itim" type="tint" stored="false" indexed="true" multiValued="true"/>
237
+ <dynamicField name="*_its" type="tint" stored="true" indexed="false" multiValued="false"/>
238
+ <dynamicField name="*_itsm" type="tint" stored="true" indexed="false" multiValued="true"/>
239
+ <dynamicField name="*_itsi" type="tint" stored="true" indexed="true" multiValued="false"/>
240
+ <dynamicField name="*_itsim" type="tint" stored="true" indexed="true" multiValued="true"/>
241
+
242
+ <!-- date (_dt...) -->
243
+ <!-- The format for this date field is of the form 1995-12-31T23:59:59Z
244
+ Optional fractional seconds are allowed: 1995-12-31T23:59:59.999Z -->
245
+ <dynamicField name="*_dti" type="date" stored="false" indexed="true" multiValued="false"/>
246
+ <dynamicField name="*_dtim" type="date" stored="false" indexed="true" multiValued="true"/>
247
+ <dynamicField name="*_dts" type="date" stored="true" indexed="false" multiValued="false"/>
248
+ <dynamicField name="*_dtsm" type="date" stored="true" indexed="false" multiValued="true"/>
249
+ <dynamicField name="*_dtsi" type="date" stored="true" indexed="true" multiValued="false"/>
250
+ <dynamicField name="*_dtsim" type="date" stored="true" indexed="true" multiValued="true"/>
251
+
252
+ <!-- trie date (_dtt...) (for faster range queries) -->
253
+ <dynamicField name="*_dtti" type="tdate" stored="false" indexed="true" multiValued="false"/>
254
+ <dynamicField name="*_dttim" type="tdate" stored="false" indexed="true" multiValued="true"/>
255
+ <dynamicField name="*_dtts" type="tdate" stored="true" indexed="false" multiValued="false"/>
256
+ <dynamicField name="*_dttsm" type="tdate" stored="true" indexed="false" multiValued="true"/>
257
+ <dynamicField name="*_dttsi" type="tdate" stored="true" indexed="true" multiValued="false"/>
258
+ <dynamicField name="*_dttsim" type="tdate" stored="true" indexed="true" multiValued="true"/>
259
+
260
+ <!-- long (_l...) -->
261
+ <dynamicField name="*_li" type="long" stored="false" indexed="true" multiValued="false"/>
262
+ <dynamicField name="*_lim" type="long" stored="false" indexed="true" multiValued="true"/>
263
+ <dynamicField name="*_ls" type="long" stored="true" indexed="false" multiValued="false"/>
264
+ <dynamicField name="*_lsm" type="long" stored="true" indexed="false" multiValued="true"/>
265
+ <dynamicField name="*_lsi" type="long" stored="true" indexed="true" multiValued="false"/>
266
+ <dynamicField name="*_lsim" type="long" stored="true" indexed="true" multiValued="true"/>
267
+
268
+ <!-- trie long (_lt...) (for faster range queries) -->
269
+ <dynamicField name="*_lti" type="tlong" stored="false" indexed="true" multiValued="false"/>
270
+ <dynamicField name="*_ltim" type="tlong" stored="false" indexed="true" multiValued="true"/>
271
+ <dynamicField name="*_lts" type="tlong" stored="true" indexed="false" multiValued="false"/>
272
+ <dynamicField name="*_ltsm" type="tlong" stored="true" indexed="false" multiValued="true"/>
273
+ <dynamicField name="*_ltsi" type="tlong" stored="true" indexed="true" multiValued="false"/>
274
+ <dynamicField name="*_ltsim" type="tlong" stored="true" indexed="true" multiValued="true"/>
275
+
276
+ <!-- double (_db...) -->
277
+ <dynamicField name="*_dbi" type="double" stored="false" indexed="true" multiValued="false"/>
278
+ <dynamicField name="*_dbim" type="double" stored="false" indexed="true" multiValued="true"/>
279
+ <dynamicField name="*_dbs" type="double" stored="true" indexed="false" multiValued="false"/>
280
+ <dynamicField name="*_dbsm" type="double" stored="true" indexed="false" multiValued="true"/>
281
+ <dynamicField name="*_dbsi" type="double" stored="true" indexed="true" multiValued="false"/>
282
+ <dynamicField name="*_dbsim" type="double" stored="true" indexed="true" multiValued="true"/>
283
+
284
+ <!-- trie double (_dbt...) (for faster range queries) -->
285
+ <dynamicField name="*_dbti" type="tdouble" stored="false" indexed="true" multiValued="false"/>
286
+ <dynamicField name="*_dbtim" type="tdouble" stored="false" indexed="true" multiValued="true"/>
287
+ <dynamicField name="*_dbts" type="tdouble" stored="true" indexed="false" multiValued="false"/>
288
+ <dynamicField name="*_dbtsm" type="tdouble" stored="true" indexed="false" multiValued="true"/>
289
+ <dynamicField name="*_dbtsi" type="tdouble" stored="true" indexed="true" multiValued="false"/>
290
+ <dynamicField name="*_dbtsim" type="tdouble" stored="true" indexed="true" multiValued="true"/>
291
+
292
+ <!-- float (_f...) -->
293
+ <dynamicField name="*_fi" type="float" stored="false" indexed="true" multiValued="false"/>
294
+ <dynamicField name="*_fim" type="float" stored="false" indexed="true" multiValued="true"/>
295
+ <dynamicField name="*_fs" type="float" stored="true" indexed="false" multiValued="false"/>
296
+ <dynamicField name="*_fsm" type="float" stored="true" indexed="false" multiValued="true"/>
297
+ <dynamicField name="*_fsi" type="float" stored="true" indexed="true" multiValued="false"/>
298
+ <dynamicField name="*_fsim" type="float" stored="true" indexed="true" multiValued="true"/>
299
+
300
+ <!-- trie float (_ft...) (for faster range queries) -->
301
+ <dynamicField name="*_fti" type="tfloat" stored="false" indexed="true" multiValued="false"/>
302
+ <dynamicField name="*_ftim" type="tfloat" stored="false" indexed="true" multiValued="true"/>
303
+ <dynamicField name="*_fts" type="tfloat" stored="true" indexed="false" multiValued="false"/>
304
+ <dynamicField name="*_ftsm" type="tfloat" stored="true" indexed="false" multiValued="true"/>
305
+ <dynamicField name="*_ftsi" type="tfloat" stored="true" indexed="true" multiValued="false"/>
306
+ <dynamicField name="*_ftsim" type="tfloat" stored="true" indexed="true" multiValued="true"/>
307
+
308
+ <!-- boolean (_b...) -->
309
+ <dynamicField name="*_bi" type="boolean" stored="false" indexed="true" multiValued="false"/>
310
+ <dynamicField name="*_bs" type="boolean" stored="true" indexed="false" multiValued="false"/>
311
+ <dynamicField name="*_bsi" type="boolean" stored="true" indexed="true" multiValued="false"/>
312
+
313
+ <!-- Type used to index the lat and lon components for the "location" FieldType -->
314
+ <dynamicField name="*_coordinate" type="tdouble" indexed="true" stored="false" />
315
+
316
+ <!-- location (_ll...) -->
317
+ <dynamicField name="*_lli" type="location" stored="false" indexed="true" multiValued="false"/>
318
+ <dynamicField name="*_llim" type="location" stored="false" indexed="true" multiValued="true"/>
319
+ <dynamicField name="*_lls" type="location" stored="true" indexed="false" multiValued="false"/>
320
+ <dynamicField name="*_llsm" type="location" stored="true" indexed="false" multiValued="true"/>
321
+ <dynamicField name="*_llsi" type="location" stored="true" indexed="true" multiValued="false"/>
322
+ <dynamicField name="*_llsim" type="location" stored="true" indexed="true" multiValued="true"/>
323
+
324
+ <dynamicField name="*suggest" type="textSuggest" indexed="true" stored="false" multiValued="true" />
325
+
326
+ <!-- you must define copyField source and dest fields explicity or schemaBrowser doesn't work -->
327
+ <field name="all_text_timv" type="text" stored="false" indexed="true" multiValued="true" termVectors="true" termPositions="true" termOffsets="true"/>
328
+
329
+
330
+ </fields>
331
+
332
+ <!-- Field to use to determine and enforce document uniqueness.
333
+ Unless this field is marked with required="false", it will be a required field
334
+ -->
335
+ <uniqueKey>id</uniqueKey>
336
+
337
+ <!-- copyField commands copy one field to another at the time a document
338
+ is added to the index. It's used either to index the same field differently,
339
+ or to add multiple fields to the same field for easier/faster searching. -->
340
+ <!-- Copy Fields -->
341
+
342
+ <!-- Above, multiple source fields are copied to the [text] field.
343
+ Another way to map multiple source fields to the same
344
+ destination field is to use the dynamic field syntax.
345
+ copyField also supports a maxChars to copy setting. -->
346
+
347
+ <!-- <copyField source="*_tesim" dest="all_text_timv" maxChars="3000"/> -->
348
+ <!-- for suggestions -->
349
+ <copyField source="*_tesim" dest="suggest"/>
350
+ <copyField source="*_ssim" dest="suggest"/>
351
+
352
+ <!-- Similarity is the scoring routine for each document vs. a query.
353
+ A custom similarity may be specified here, but the default is fine
354
+ for most applications. -->
355
+ <!-- <similarity class="org.apache.lucene.search.DefaultSimilarity"/> -->
356
+ <!-- ... OR ...
357
+ Specify a SimilarityFactory class name implementation
358
+ allowing parameters to be used.
359
+ -->
360
+ <!--
361
+ <similarity class="com.example.solr.CustomSimilarityFactory">
362
+ <str name="paramkey">param value</str>
363
+ </similarity>
364
+ -->
365
+
366
+ </schema>
@@ -0,0 +1,24 @@
1
+ # Licensed to the Apache Software Foundation (ASF) under one or more
2
+ # contributor license agreements. See the NOTICE file distributed with
3
+ # this work for additional information regarding copyright ownership.
4
+ # The ASF licenses this file to You under the Apache License, Version 2.0
5
+ # (the "License"); you may not use this file except in compliance with
6
+ # the License. You may obtain a copy of the License at
7
+ #
8
+ # http://www.apache.org/licenses/LICENSE-2.0
9
+ #
10
+ # Unless required by applicable law or agreed to in writing, software
11
+ # distributed under the License is distributed on an "AS IS" BASIS,
12
+ # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
13
+ # See the License for the specific language governing permissions and
14
+ # limitations under the License.
15
+
16
+ user=
17
+ solr_hostname=localhost
18
+ solr_port=8983
19
+ rsyncd_port=18983
20
+ data_dir=
21
+ webapp_name=solr
22
+ master_host=
23
+ master_data_dir=
24
+ master_status_dir=