newspaper_works 0.1.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
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
checksums.yaml ADDED
@@ -0,0 +1,7 @@
1
+ ---
2
+ SHA1:
3
+ metadata.gz: d0003c7935fbee94e245007e986fcdf7a085bfa5
4
+ data.tar.gz: 9609ad4d442b7d7630e0231c09bd0592f9828933
5
+ SHA512:
6
+ metadata.gz: 1522953bfcacedaea668eaf9b59790a6db6ffe3be317ed0e7388a51fa44b4cf3518f463c422f65b5bfedce77ec9731df49f49ea9a0611d5f44041566d596c453
7
+ data.tar.gz: ddda11224cc5a059c0aa13546ac77805ec1e4e94eae7da2cd9f95eacf4fec8abcc78ec8b68d460939bceed0ce4904cb9b596beca5a20535fa0f83c69554756d4
data/.fcrepo_wrapper ADDED
@@ -0,0 +1,4 @@
1
+ # Place any default configuration for solr_wrapper here
2
+ port: 8984
3
+ enable_jms: false
4
+ fcrepo_home_dir: tmp/fcrepo4-development-data
data/.gitignore ADDED
@@ -0,0 +1,43 @@
1
+ # See https://help.github.com/articles/ignoring-files for more about ignoring files.
2
+ #
3
+ # If you find yourself ignoring temporary files generated by your text editor
4
+ # or operating system, you probably want to add a global ignore instead:
5
+ # git config --global core.excludesfile '~/.gitignore_global'
6
+
7
+ # Ignore Gemfile.lock
8
+ Gemfile.lock
9
+
10
+ # Ignore coverage reports
11
+ coverage/*
12
+
13
+ # Ignore bundler config.
14
+ .bundle
15
+
16
+ # Ignore JetBrains IDE folder
17
+ .idea/*
18
+
19
+ # Ignore the default SQLite database.
20
+ /db/*.sqlite3
21
+ /db/*.sqlite3-journal
22
+
23
+ # Ignore all logfiles and tempfiles.
24
+ /log/*
25
+ /tmp/*
26
+ !/log/.keep
27
+ !/tmp/.keep
28
+ fits.log
29
+
30
+ # Ignore Byebug command history file.
31
+ .byebug_history
32
+
33
+ # Ignore generated engine_cart testing app:
34
+ .internal_test_app
35
+
36
+ # Ignore all RubyMine temp files
37
+ .idea/
38
+
39
+ # Ignore Gemfile.lock
40
+ Gemfile.lock
41
+
42
+ # Ignore wrapper downloads
43
+ fcrepo-webapp-*
data/.rubocop.yml ADDED
@@ -0,0 +1,143 @@
1
+ inherit_gem:
2
+ bixby: bixby_default.yml
3
+
4
+ RSpec/ExampleLength:
5
+ Max: 15
6
+ Exclude:
7
+ - 'spec/lib/newspaper_works/data/work_derivatives_spec.rb'
8
+ - 'spec/lib/newspaper_works/ingest/ndnp/issue_ingester_spec.rb'
9
+
10
+ AllCops:
11
+ TargetRubyVersion: 2.1
12
+ DisplayCopNames: true
13
+ Exclude:
14
+ - 'db/**/*'
15
+ - 'script/**/*'
16
+ - 'spec/test_app_templates/**/*'
17
+ - 'vendor/**/*'
18
+
19
+ Lint/ImplicitStringConcatenation:
20
+ Exclude:
21
+ - 'lib/generators/newspaper_works/**/*'
22
+
23
+ Metrics/AbcSize:
24
+ Exclude:
25
+ - 'spec/model_shared.rb'
26
+
27
+ Metrics/BlockLength:
28
+ ExcludedMethods: ['included']
29
+ Exclude:
30
+ - 'newspaper_works.gemspec'
31
+ - 'lib/tasks/*.rake'
32
+ - 'spec/**/*.rb'
33
+
34
+ Metrics/CyclomaticComplexity:
35
+ Exclude:
36
+ - 'spec/model_shared.rb'
37
+
38
+ Metrics/ClassLength:
39
+ Exclude:
40
+ - 'lib/newspaper_works/data/work_derivatives.rb'
41
+ - 'lib/newspaper_works/ingest/ndnp/page_ingester.rb'
42
+ - 'lib/newspaper_works/ingest/lc_publication_info.rb'
43
+
44
+ Metrics/LineLength:
45
+ Exclude:
46
+ - 'lib/generators/newspaper_works/catalog_controller_generator.rb'
47
+
48
+ Metrics/MethodLength:
49
+ Exclude:
50
+ - 'app/helpers/newspaper_works/breadcrumb_helper.rb'
51
+ - 'lib/generators/newspaper_works/catalog_controller_generator.rb'
52
+ - 'lib/newspaper_works/page_finder.rb'
53
+ - 'lib/newspaper_works/ingest/ndnp/ndnp_mets_helper.rb'
54
+ - 'lib/newspaper_works/ingest/pdf_issue_ingester.rb'
55
+ - 'spec/model_shared.rb'
56
+
57
+ Naming/PredicateName:
58
+ Exclude:
59
+ - ''
60
+
61
+ Performance/StringReplacement:
62
+ Exclude:
63
+ - 'app/indexers/concerns/newspaper_works/indexes_full_text.rb'
64
+
65
+ Style/AsciiComments:
66
+ Enabled: false
67
+
68
+ Style/CollectionMethods:
69
+ PreferredMethods:
70
+ collect: 'map'
71
+ collect!: 'map!'
72
+ inject: 'reduce'
73
+ detect: 'find'
74
+ find_all: 'select'
75
+
76
+ Style/SymbolArray:
77
+ Enabled: false
78
+
79
+ Style/ClassAndModuleChildren:
80
+ Enabled: false
81
+
82
+ Style/SingleLineBlockParams:
83
+ Enabled: false
84
+
85
+ Rails/ApplicationJob:
86
+ Enabled: false
87
+
88
+ Rails/ApplicationRecord:
89
+ Enabled: false
90
+
91
+ # We define custom methods like `find_by_user_key`,
92
+ # `find_by_created_date`, etc
93
+ Rails/DynamicFindBy:
94
+ Enabled: false
95
+
96
+ Rails/FilePath:
97
+ Exclude:
98
+ - 'spec/abilities/**/*'
99
+
100
+ Rails/OutputSafety:
101
+ Exclude:
102
+ - 'lib/generators/newspaper_works/templates/config/initializers/patch_blacklight_advanced_search.rb'
103
+ - 'spec/helpers/newspaper_works_helper_spec.rb'
104
+
105
+ RSpec/DescribeClass:
106
+ Exclude:
107
+ - 'spec/abilities/**/*'
108
+ - 'spec/conversions/**/*'
109
+ - 'spec/features/**/*'
110
+ - 'spec/inputs/**/*'
111
+ - 'spec/views/**/*'
112
+ - 'spec/lib/tasks/**/*'
113
+
114
+ # # By default RSpec/MessageSpies has the following:
115
+ # # Prefer have_received for setting message expectations. Setup form as a spy using allow or instance_spy.
116
+ # # The default assumes EnforcedStyle is 'have_received'. Most of our specs are 'receive'
117
+ RSpec/MessageSpies:
118
+ Enabled: false
119
+
120
+ RSpec/InstanceVariable:
121
+ Exclude:
122
+ - 'spec/**/*'
123
+
124
+ RSpec/ExpectActual:
125
+ Enabled: false
126
+
127
+ RSpec/LetSetup:
128
+ Enabled: false
129
+
130
+ RSpec/MessageExpectation:
131
+ Enabled: false
132
+
133
+ RSpec/NamedSubject:
134
+ Enabled: false
135
+
136
+ RSpec/NestedGroups:
137
+ Enabled: false
138
+
139
+ RSpec/LeadingSubject:
140
+ Enabled: false
141
+
142
+ RSpec/VerifiedDoubles:
143
+ Enabled: false
data/.solr_wrapper ADDED
@@ -0,0 +1,8 @@
1
+ # Place any default configuration for solr_wrapper here
2
+ version: 7.7.2
3
+ # port: 8983
4
+ instance_dir: tmp/solr-development
5
+ collection:
6
+ persist: true
7
+ dir: .internal_test_app/solr/config/
8
+ name: hydra-development
data/.travis.yml ADDED
@@ -0,0 +1,50 @@
1
+ language: ruby
2
+ dist: xenial
3
+
4
+ jdk:
5
+ - openjdk8
6
+
7
+ addons:
8
+ chrome: stable
9
+ apt:
10
+ sources:
11
+ - "xenial-media"
12
+ packages:
13
+ - ghostscript
14
+ - graphicsmagick
15
+ - imagemagick
16
+ - libreoffice
17
+ - poppler-utils
18
+ - tesseract-ocr
19
+ - libopenjp2-7
20
+ - libopenjp2-tools
21
+ cache:
22
+ bundler: true
23
+
24
+ before_install:
25
+ - sudo apt-get update -q
26
+ - gem update --system
27
+ - gem install bundler
28
+ - google-chrome-stable --headless --disable-gpu --no-sandbox --remote-debugging-port=9222 http://localhost &
29
+ - sudo wget -P /opt/install https://brussels.lib.utah.edu/FITS/fits-1.4.1.zip
30
+ - sudo unzip /opt/install/fits-1.4.1.zip -d /opt/install/fits-1.4.1
31
+ - sudo chmod +x /opt/install/fits-1.4.1/*.sh
32
+ - sudo ln -s /opt/install/fits-1.4.1/fits.sh /usr/local/bin/fits.sh
33
+ - sudo wget -q -O /etc/ImageMagick-6/policy.xml https://raw.githubusercontent.com/marriott-library/newspaper_works/7052ff3bf58022572870a0720d8c5a705090a833/config/vendor/imagemagick-6-policy.xml
34
+ - sudo wget -q -O /opt/install/fits-1.4.1/xml/fits.xml https://gist.githubusercontent.com/brianmcbride/af3fb21fb50a1331d84eca9a9a170f8f/raw/ebb1a285726e4f5c2309b4f6eceed29fa1369538/fits.xml
35
+ rvm:
36
+ - 2.5.5
37
+
38
+ env:
39
+ global:
40
+ - NOKOGIRI_USE_SYSTEM_LIBRARIES=true
41
+ #- ENGINE_CART_RAILS_OPTIONS='--skip-git --skip-bundle --skip-listen --skip-spring --skip-yarn --skip-keeps --skip-action-cable --skip-coffee --skip-puma --skip-test'
42
+ # Travis should check every minor version in a range of supported versions, because
43
+ # rails does not follow sem-ver conventions, see http://guides.rubyonrails.org/maintenance_policy.html
44
+ # It should be sufficient to test only the latest of the patch versions for a minor version, they
45
+ # should be compatible across patch versions (only bug fixes are released in patch versions).
46
+ matrix:
47
+ - "RAILS_VERSION=5.1.7"
48
+
49
+ services:
50
+ - redis
data/Gemfile ADDED
@@ -0,0 +1,47 @@
1
+ source 'https://rubygems.org'
2
+
3
+ # Please see newspaper_works.gemspec for dependency information.
4
+ gemspec
5
+
6
+ group :development, :test do
7
+ gem 'coveralls', require: false
8
+ end
9
+
10
+ # BEGIN ENGINE_CART BLOCK
11
+ # engine_cart: 1.2.0
12
+ # engine_cart stanza: 0.10.0
13
+ # the below comes from engine_cart, a gem used to test this Rails engine gem in the context of a Rails app.
14
+ file = File.expand_path('Gemfile', ENV['ENGINE_CART_DESTINATION'] || ENV['RAILS_ROOT'] || File.expand_path('.internal_test_app', File.dirname(__FILE__)))
15
+ if File.exist?(file)
16
+ begin
17
+ eval_gemfile file
18
+ rescue Bundler::GemfileError => e
19
+ Bundler.ui.warn '[EngineCart] Skipping Rails application dependencies:'
20
+ Bundler.ui.warn e.message
21
+ end
22
+ else
23
+ Bundler.ui.warn "[EngineCart] Unable to find test application dependencies in #{file}, using placeholder dependencies"
24
+
25
+ if ENV['RAILS_VERSION']
26
+ if ENV['RAILS_VERSION'] == 'edge'
27
+ gem 'rails', github: 'rails/rails'
28
+ ENV['ENGINE_CART_RAILS_OPTIONS'] = '--edge --skip-turbolinks'
29
+ else
30
+ # rubocop:disable Bundler/DuplicatedGem
31
+ gem 'rails', ENV['RAILS_VERSION']
32
+ # rubocop:enable Bundler/DuplicatedGem
33
+ end
34
+ end
35
+
36
+ case ENV['RAILS_VERSION']
37
+ when /^4.2/
38
+ gem 'coffee-rails', '~> 4.1.0'
39
+ gem 'responders', '~> 2.0'
40
+ gem 'sass-rails', '>= 5.0'
41
+ when /^4.[01]/
42
+ # rubocop:disable Bundler/DuplicatedGem
43
+ gem 'sass-rails', '< 5.0'
44
+ # rubocop:enable Bundler/DuplicatedGem
45
+ end
46
+ end
47
+ # END ENGINE_CART BLOCK
data/LICENSE ADDED
@@ -0,0 +1,203 @@
1
+ Apache License
2
+ Version 2.0, January 2004
3
+ http://www.apache.org/licenses/
4
+
5
+ TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
6
+
7
+ 1. Definitions.
8
+
9
+ "License" shall mean the terms and conditions for use, reproduction,
10
+ and distribution as defined by Sections 1 through 9 of this document.
11
+
12
+ "Licensor" shall mean the copyright owner or entity authorized by
13
+ the copyright owner that is granting the License.
14
+
15
+ "Legal Entity" shall mean the union of the acting entity and all
16
+ other entities that control, are controlled by, or are under common
17
+ control with that entity. For the purposes of this definition,
18
+ "control" means (i) the power, direct or indirect, to cause the
19
+ direction or management of such entity, whether by contract or
20
+ otherwise, or (ii) ownership of fifty percent (50%) or more of the
21
+ outstanding shares, or (iii) beneficial ownership of such entity.
22
+
23
+ "You" (or "Your") shall mean an individual or Legal Entity
24
+ exercising permissions granted by this License.
25
+
26
+ "Source" form shall mean the preferred form for making modifications,
27
+ including but not limited to software source code, documentation
28
+ source, and configuration files.
29
+
30
+ "Object" form shall mean any form resulting from mechanical
31
+ transformation or translation of a Source form, including but
32
+ not limited to compiled object code, generated documentation,
33
+ and conversions to other media types.
34
+
35
+ "Work" shall mean the work of authorship, whether in Source or
36
+ Object form, made available under the License, as indicated by a
37
+ copyright notice that is included in or attached to the work
38
+ (an example is provided in the Appendix below).
39
+
40
+ "Derivative Works" shall mean any work, whether in Source or Object
41
+ form, that is based on (or derived from) the Work and for which the
42
+ editorial revisions, annotations, elaborations, or other modifications
43
+ represent, as a whole, an original work of authorship. For the purposes
44
+ of this License, Derivative Works shall not include works that remain
45
+ separable from, or merely link (or bind by name) to the interfaces of,
46
+ the Work and Derivative Works thereof.
47
+
48
+ "Contribution" shall mean any work of authorship, including
49
+ the original version of the Work and any modifications or additions
50
+ to that Work or Derivative Works thereof, that is intentionally
51
+ submitted to Licensor for inclusion in the Work by the copyright owner
52
+ or by an individual or Legal Entity authorized to submit on behalf of
53
+ the copyright owner. For the purposes of this definition, "submitted"
54
+ means any form of electronic, verbal, or written communication sent
55
+ to the Licensor or its representatives, including but not limited to
56
+ communication on electronic mailing lists, source code control systems,
57
+ and issue tracking systems that are managed by, or on behalf of, the
58
+ Licensor for the purpose of discussing and improving the Work, but
59
+ excluding communication that is conspicuously marked or otherwise
60
+ designated in writing by the copyright owner as "Not a Contribution."
61
+
62
+ "Contributor" shall mean Licensor and any individual or Legal Entity
63
+ on behalf of whom a Contribution has been received by Licensor and
64
+ subsequently incorporated within the Work.
65
+
66
+ 2. Grant of Copyright License. Subject to the terms and conditions of
67
+ this License, each Contributor hereby grants to You a perpetual,
68
+ worldwide, non-exclusive, no-charge, royalty-free, irrevocable
69
+ copyright license to reproduce, prepare Derivative Works of,
70
+ publicly display, publicly perform, sublicense, and distribute the
71
+ Work and such Derivative Works in Source or Object form.
72
+
73
+ 3. Grant of Patent License. Subject to the terms and conditions of
74
+ this License, each Contributor hereby grants to You a perpetual,
75
+ worldwide, non-exclusive, no-charge, royalty-free, irrevocable
76
+ (except as stated in this section) patent license to make, have made,
77
+ use, offer to sell, sell, import, and otherwise transfer the Work,
78
+ where such license applies only to those patent claims licensable
79
+ by such Contributor that are necessarily infringed by their
80
+ Contribution(s) alone or by combination of their Contribution(s)
81
+ with the Work to which such Contribution(s) was submitted. If You
82
+ institute patent litigation against any entity (including a
83
+ cross-claim or counterclaim in a lawsuit) alleging that the Work
84
+ or a Contribution incorporated within the Work constitutes direct
85
+ or contributory patent infringement, then any patent licenses
86
+ granted to You under this License for that Work shall terminate
87
+ as of the date such litigation is filed.
88
+
89
+ 4. Redistribution. You may reproduce and distribute copies of the
90
+ Work or Derivative Works thereof in any medium, with or without
91
+ modifications, and in Source or Object form, provided that You
92
+ meet the following conditions:
93
+
94
+ (a) You must give any other recipients of the Work or
95
+ Derivative Works a copy of this License; and
96
+
97
+ (b) You must cause any modified files to carry prominent notices
98
+ stating that You changed the files; and
99
+
100
+ (c) You must retain, in the Source form of any Derivative Works
101
+ that You distribute, all copyright, patent, trademark, and
102
+ attribution notices from the Source form of the Work,
103
+ excluding those notices that do not pertain to any part of
104
+ the Derivative Works; and
105
+
106
+ (d) If the Work includes a "NOTICE" text file as part of its
107
+ distribution, then any Derivative Works that You distribute must
108
+ include a readable copy of the attribution notices contained
109
+ within such NOTICE file, excluding those notices that do not
110
+ pertain to any part of the Derivative Works, in at least one
111
+ of the following places: within a NOTICE text file distributed
112
+ as part of the Derivative Works; within the Source form or
113
+ documentation, if provided along with the Derivative Works; or,
114
+ within a display generated by the Derivative Works, if and
115
+ wherever such third-party notices normally appear. The contents
116
+ of the NOTICE file are for informational purposes only and
117
+ do not modify the License. You may add Your own attribution
118
+ notices within Derivative Works that You distribute, alongside
119
+ or as an addendum to the NOTICE text from the Work, provided
120
+ that such additional attribution notices cannot be construed
121
+ as modifying the License.
122
+
123
+ You may add Your own copyright statement to Your modifications and
124
+ may provide additional or different license terms and conditions
125
+ for use, reproduction, or distribution of Your modifications, or
126
+ for any such Derivative Works as a whole, provided Your use,
127
+ reproduction, and distribution of the Work otherwise complies with
128
+ the conditions stated in this License.
129
+
130
+ 5. Submission of Contributions. Unless You explicitly state otherwise,
131
+ any Contribution intentionally submitted for inclusion in the Work
132
+ by You to the Licensor shall be under the terms and conditions of
133
+ this License, without any additional terms or conditions.
134
+ Notwithstanding the above, nothing herein shall supersede or modify
135
+ the terms of any separate license agreement you may have executed
136
+ with Licensor regarding such Contributions.
137
+
138
+ 6. Trademarks. This License does not grant permission to use the trade
139
+ names, trademarks, service marks, or product names of the Licensor,
140
+ except as required for reasonable and customary use in describing the
141
+ origin of the Work and reproducing the content of the NOTICE file.
142
+
143
+ 7. Disclaimer of Warranty. Unless required by applicable law or
144
+ agreed to in writing, Licensor provides the Work (and each
145
+ Contributor provides its Contributions) on an "AS IS" BASIS,
146
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
147
+ implied, including, without limitation, any warranties or conditions
148
+ of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
149
+ PARTICULAR PURPOSE. You are solely responsible for determining the
150
+ appropriateness of using or redistributing the Work and assume any
151
+ risks associated with Your exercise of permissions under this License.
152
+
153
+ 8. Limitation of Liability. In no event and under no legal theory,
154
+ whether in tort (including negligence), contract, or otherwise,
155
+ unless required by applicable law (such as deliberate and grossly
156
+ negligent acts) or agreed to in writing, shall any Contributor be
157
+ liable to You for damages, including any direct, indirect, special,
158
+ incidental, or consequential damages of any character arising as a
159
+ result of this License or out of the use or inability to use the
160
+ Work (including but not limited to damages for loss of goodwill,
161
+ work stoppage, computer failure or malfunction, or any and all
162
+ other commercial damages or losses), even if such Contributor
163
+ has been advised of the possibility of such damages.
164
+
165
+ 9. Accepting Warranty or Additional Liability. While redistributing
166
+ the Work or Derivative Works thereof, You may choose to offer,
167
+ and charge a fee for, acceptance of support, warranty, indemnity,
168
+ or other liability obligations and/or rights consistent with this
169
+ License. However, in accepting such obligations, You may act only
170
+ on Your own behalf and on Your sole responsibility, not on behalf
171
+ of any other Contributor, and only if You agree to indemnify,
172
+ defend, and hold each Contributor harmless for any liability
173
+ incurred by, or claims asserted against, such Contributor by reason
174
+ of your accepting any such warranty or additional liability.
175
+
176
+ END OF TERMS AND CONDITIONS
177
+
178
+ APPENDIX: How to apply the Apache License to your work.
179
+
180
+ To apply the Apache License to your work, attach the following
181
+ boilerplate notice, with the fields enclosed by brackets "{}"
182
+ replaced with your own identifying information. (Don't include
183
+ the brackets!) The text should be enclosed in the appropriate
184
+ comment syntax for the file format. We also recommend that a
185
+ file or class name and description of purpose be included on the
186
+ same "printed page" as the copyright notice for easier
187
+ identification within third-party archives.
188
+
189
+ Copyright 2019 Boston Public Library
190
+ Copyright 2019 J. Willard Marriott Library, The University of Utah
191
+ Additional copyright may be held by others, as reflected in the commit history.
192
+
193
+ Licensed under the Apache License, Version 2.0 (the "License");
194
+ you may not use this file except in compliance with the License.
195
+ You may obtain a copy of the License at
196
+
197
+ http://www.apache.org/licenses/LICENSE-2.0
198
+
199
+ Unless required by applicable law or agreed to in writing, software
200
+ distributed under the License is distributed on an "AS IS" BASIS,
201
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
202
+ See the License for the specific language governing permissions and
203
+ limitations under the License.
data/README.md ADDED
@@ -0,0 +1,159 @@
1
+ NewspaperWorks
2
+ ===================================================
3
+ Code:
4
+ [![Build Status](https://travis-ci.org/marriott-library/newspaper_works.svg?branch=master)](https://travis-ci.org/marriott-library/newspaper_works) [![Coverage Status](https://coveralls.io/repos/github/marriott-library/newspaper_works/badge.svg)](https://coveralls.io/github/marriott-library/newspaper_works)
5
+
6
+ Docs:
7
+ [![Apache 2.0 License](http://img.shields.io/badge/APACHE2-license-blue.svg)](./LICENSE)
8
+ [![Contribution Guidelines](http://img.shields.io/badge/CONTRIBUTING-Guidelines-blue.svg)](./.github/CONTRIBUTING.md)
9
+
10
+ Jump in: [![Slack Status](http://slack.samvera.org/badge.svg)](http://slack.samvera.org/)
11
+
12
+ <!-- TOC -->
13
+
14
+ - [Overview](#overview)
15
+ - [Documentation](#documentation)
16
+ - [Requirements](#requirements)
17
+ - [Dependencies](#dependencies)
18
+ - [Installation](#installation)
19
+ - [Application/Site Specific Configuration](#applicationsite-specific-configuration)
20
+ - [Config changes made by the installer:](#config-changes-made-by-the-installer)
21
+ - [Configuration changes you should make after running the installer](#configuration-changes-you-should-make-after-running-the-installer)
22
+ - [Ingesting Content](#ingesting-content)
23
+ - [Developing, Testing, and Contributing](#developing-testing-and-contributing)
24
+ - [Contributing](#contributing)
25
+ - [Acknowledgements](#acknowledgements)
26
+ - [Sponsoring Organizations](#sponsoring-organizations)
27
+ - [More Information](#more-information)
28
+ - [Contact](#contact)
29
+
30
+ <!-- /TOC -->
31
+
32
+ # Overview
33
+ NewspaperWorks is a gem (Rails "engine") for [Hyrax](https://hyrax.samvera.org/) -based digital repository applications to support ingest, management, and display of digitzed newspaper content.
34
+
35
+ NewspaperWorks is not a stand-alone application. It is designed to be integrated into a new or existing Hyrax (2.5.x) application, providing content models, ingest workflows, and feature-rich UX for newspaper repository use-cases.
36
+
37
+ NewspaperWorks supports:
38
+ * models for Title, Issue, Page, and Article
39
+ * batch ingest via command line
40
+ * OCR and ALTO creation
41
+ * newspaper-specific metadata fields
42
+ * full-text search
43
+ * calendar-based issue browsing
44
+ * advanced search
45
+ * OCR keyword match highlighting
46
+ * viewer with page navigation and deep zooming
47
+
48
+ A complete list of features can be found [here](wiki/Features-List).
49
+
50
+ ## Documentation
51
+ A set of helpful documents to help you learn more and deploy NewspaperWorks can be found on the [Project Wiki](./newspaper_works/wiki), including a PCDM model diagram, metadata schema, batch ingest instructions, and more details on installing, developing, and testing the code.
52
+
53
+ ## Requirements
54
+
55
+ * [Ruby](https://rubyonrails.org/) >=2.4
56
+ * [Rails](https://rubyonrails.org/) ~>5.1
57
+ * [Bundler](http://bundler.io/)
58
+ * [Hyrax](https://github.com/samvera/hyrax) ~>2.5
59
+ - ..._and various [Samvera dependencies](https://github.com/samvera/hyrax#getting-started) that entails_.
60
+ * A Hyrax-based Rails application
61
+
62
+ ## Dependencies
63
+
64
+ * [FITS](https://projects.iq.harvard.edu/fits/home)
65
+ * [Tesseract-ocr](https://github.com/tesseract-ocr/)
66
+ * [LibreOffice](https://www.libreoffice.org/)
67
+ * [ghostscript](https://www.ghostscript.com/)
68
+ * [poppler-utils](https://poppler.freedesktop.org/)
69
+ * [GraphicsMagick](http://www.graphicsmagick.org/)
70
+ * [libcurl3](https://packages.ubuntu.com/search?keywords=libcurl3)
71
+
72
+ See the [wiki](./newspaper_works/wiki/Installing,-Developing,-and-Testing) for more details on how to install and configure dependencies.
73
+
74
+ # Installation
75
+ NewspaperWorks easily integrates with your Hyrax 2.5.x applications.
76
+
77
+ * Add `gem 'newspaper_works'` to your Gemfile.
78
+ * Run `bundle install`
79
+ * Run `rails generate newspaper_works:generate`
80
+ * Set config options as indicated below...
81
+
82
+ ## Application/Site Specific Configuration
83
+
84
+ ### Config changes made by the installer:
85
+ * In `app/controllers/catalog_controller.rb`, the `config.search_builder_class` is set to a new `CustomSearchBuiler` to support newspapers search features.
86
+ * Additional facet fields for newspaper metadata are added to `app/controllers/catalog_controller.rb`.
87
+ * Newspaper resource types added to `config/authorities/resource_types.yml`.
88
+
89
+ (It may be helpful to run `git diff` after installation to see all the changes made by the installer.)
90
+
91
+ ### Configuration changes you should make after running the installer:
92
+
93
+ #### in config/intitializers/hyrax.rb:
94
+ * set `config.geonames_username`
95
+ * Enables geolocation tagging of content
96
+ * [how to create a Geonames username](http://www.geonames.org/login)
97
+ * set `config.work_requires_files = false`
98
+ * set `config.iiif_image_server = true`
99
+ * set `config.fits_path = /location/of/fits.sh`
100
+
101
+ #### in config/environments/production.rb:
102
+
103
+ * set `config.public_file_server.enabled = true`
104
+
105
+ # Ingesting Content
106
+
107
+ NewspaperWorks supports a range of different ingest workflows:
108
+ * single-item ingest via the UI
109
+ * batch ingest of [NDNP materials](./newspaper_works/wiki/NDNP-Batch-Ingest-Guide) (page-level digitization) via command line
110
+ * batch ingest of [PDF issues](./newspaper_works/wiki/PDF-Batch-Ingest-Guide) via command line
111
+ * batch ingest of [TIFF or JP2 master files](./newspaper_works/wiki/TIFF-or-JP2-Batch-Ingest-Guide) via command line
112
+
113
+ The ingest process creates a full complement of derivatives for each Page object, including:
114
+ * TIFF
115
+ * JP2
116
+ * PDF
117
+ * OCR text
118
+ * word-coordinate JSON
119
+
120
+ For more information on derivatives, see the [wiki](./newspaper_works/wiki/Image-Format-and-Derivative-Notes).
121
+
122
+ # Developing, Testing, and Contributing
123
+
124
+ Detailed information regarding development and testing environments setup and configuration can be found [here](./newspaper_works/wiki/Installing,-Developing,-and-Testing)
125
+
126
+ A Vagrant VM is available for users and developers to quickly and easily deploy the latest NewspaperWorks codebase using Vagrant and VirtualBox. See [samvera-newspapers-vagrant](https://github.com/marriott-library/samvera-newspapers-vagrant) for more.
127
+
128
+ Additionally, the [NewspaperWorks Demo Site](https://newspaperworks.digitalnewspapers.org/) is available for those interested in testing out NewspaperWorks as deployed in a vanilla Hyrax application. (**NOTE:** The demo site may not be running the latest release of NewspaperWorks.)
129
+
130
+ ## Contributing
131
+
132
+ We encourage anyone who is interested in newspapers and Samvera to contribute to this project. [How can I contribute?](https://github.com/samvera/hyrax/blob/master/.github/CONTRIBUTING.md)
133
+
134
+ # Acknowledgements
135
+
136
+ ## Sponsoring Organizations
137
+
138
+ This gem is part of a project developed in a collaboration between [The University of Utah](https://www.utah.edu/), [J. Willard Marriott Library](https://www.lib.utah.edu/) and [Boston Public Library](https://www.bpl.org/), as part of a "Newspapers in Samvera" project grant funded by the [Institute for Museum and Library Services](https:///imls.gov).
139
+
140
+ The development team is grateful for input, collaboration, and support we receive from the Samvera Community, related working groups, and our project's advisory board.
141
+
142
+ ## More Information
143
+ * [Samvera Newspapers Group](https://wiki.duraspace.org/display/samvera/Samvera+Newspapers+Interest+Group) - The Samvera Newspapers Interest groups meets on the first Thursday of every month to discuss the Samvera newspapers project and general newspaper topics.
144
+ * [Newspapers in Samvera IMLS Grant (formerly Hydra)](https://www.imls.gov/grants/awarded/lg-70-17-0043-17) - The official grant award for the project.
145
+ * [National Digital Newspapers Program NDNP](https://www.loc.gov/ndnp/)
146
+
147
+ ## Contact
148
+ Contact any contributors above by email, or ping us on [Samvera Community Slack channel(s)](http://slack.samvera.org/)
149
+
150
+ ![Institute of Museum and Library Services Logo](https://imls.gov/sites/default/files/logo.png)
151
+
152
+ ![University of Utah Logo](http://www.utah.edu/_images/imagine_u.png)
153
+
154
+ ![Boston Public Library Logo](https://cor-liv-cdn-static.bibliocommons.com/images/MA-BOSTON-BRANCH/logo.png?1528788420451)
155
+
156
+ This software has been developed by and is brought to you by the Samvera community. Learn more at the
157
+ [Samvera website](http://samvera.org/).
158
+
159
+ ![Samvera Logo](https://wiki.duraspace.org/download/thumbnails/87459292/samvera-fall-font2-200w.png?version=1&modificationDate=1498550535816&api=v2)