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
data/spec/fixtures/files/ocr_alto.xml ADDED
@@ -0,0 +1,202 @@
1
+ <?xml version="1.0" encoding="UTF-8"?>
2
+ <alto xmlns="http://www.loc.gov/standards/alto/ns-v2#">
3
+ <Description>
4
+ <MeasurementUnit>pixel</MeasurementUnit>
5
+ </Description>
6
+ <Layout>
7
+ <Page ID="ID1" PHYSICAL_IMG_NR="1" HEIGHT="1046" WIDTH="418">
8
+ <PrintSpace HEIGHT="1046" WIDTH="418" HPOS="0" VPOS="0">
9
+ <TextBlock ID="ID1a" HEIGHT="1046" WIDTH="418" HPOS="0" VPOS="0">
10
+ <TextLine HEIGHT="1046" WIDTH="418" HPOS="0" VPOS="0">
11
+ <String CONTENT="PEHNSYWAHIA" HEIGHT="52" WIDTH="281" HPOS="24" VPOS="17"></String>
12
+ <String CONTENT="_" HEIGHT="3" WIDTH="33" HPOS="176" VPOS="152"></String>
13
+ <String CONTENT="RESERVES." HEIGHT="52" WIDTH="201" HPOS="217" VPOS="83"></String>
14
+ <String CONTENT="Career" HEIGHT="24" WIDTH="82" HPOS="22" VPOS="174"></String>
15
+ <String CONTENT="of" HEIGHT="24" WIDTH="25" HPOS="118" VPOS="173"></String>
16
+ <String CONTENT="These" HEIGHT="25" WIDTH="71" HPOS="155" VPOS="172"></String>
17
+ <String CONTENT="Veterans" HEIGHT="24" WIDTH="113" HPOS="237" VPOS="172"></String>
18
+ <String CONTENT="from" HEIGHT="24" WIDTH="58" HPOS="360" VPOS="171"></String>
19
+ <String CONTENT="Cold" HEIGHT="25" WIDTH="54" HPOS="36" VPOS="222"></String>
20
+ <String CONTENT="Harbor" HEIGHT="24" WIDTH="89" HPOS="105" VPOS="221"></String>
21
+ <String CONTENT="to" HEIGHT="23" WIDTH="24" HPOS="209" VPOS="221"></String>
22
+ <String CONTENT="Appomattox." HEIGHT="30" WIDTH="159" HPOS="243" VPOS="220"></String>
23
+ <String CONTENT="Organizations" HEIGHT="24" WIDTH="140" HPOS="21" VPOS="295"></String>
24
+ <String CONTENT="Which" HEIGHT="19" WIDTH="67" HPOS="186" VPOS="293"></String>
25
+ <String CONTENT="Did" HEIGHT="20" WIDTH="37" HPOS="277" VPOS="292"></String>
26
+ <String CONTENT="Gallant" HEIGHT="20" WIDTH="74" HPOS="343" VPOS="291"></String>
27
+ <String CONTENT="Service—Led" HEIGHT="22" WIDTH="132" HPOS="44" VPOS="326"></String>
28
+ <String CONTENT="by" HEIGHT="25" WIDTH="25" HPOS="189" VPOS="326"></String>
29
+ <String CONTENT="Good" HEIGHT="20" WIDTH="48" HPOS="226" VPOS="325"></String>
30
+ <String CONTENT="one”;" HEIGHT="22" WIDTH="75" HPOS="289" VPOS="324"></String>
31
+ <String CONTENT="Dis-" HEIGHT="20" WIDTH="39" HPOS="377" VPOS="323"></String>
32
+ <String CONTENT="cipline" HEIGHT="25" WIDTH="67" HPOS="43" VPOS="361"></String>
33
+ <String CONTENT="and" HEIGHT="20" WIDTH="36" HPOS="130" VPOS="359"></String>
34
+ <String CONTENT="‘anery" HEIGHT="24" WIDTH="88" HPOS="183" VPOS="359"></String>
35
+ <String CONTENT="Snved" HEIGHT="20" WIDTH="59" HPOS="288" VPOS="357"></String>
36
+ <String CONTENT="Them" HEIGHT="19" WIDTH="54" HPOS="361" VPOS="356"></String>
37
+ <String CONTENT="bum" HEIGHT="20" WIDTH="46" HPOS="43" VPOS="394"></String>
38
+ <String CONTENT="Annihilation" HEIGHT="21" WIDTH="128" HPOS="101" VPOS="392"></String>
39
+ <String CONTENT="on" HEIGHT="14" WIDTH="23" HPOS="244" VPOS="396"></String>
40
+ <String CONTENT="Bud-Fought" HEIGHT="25" WIDTH="130" HPOS="284" VPOS="389"></String>
41
+ <String CONTENT="Fields—Memorable" HEIGHT="22" WIDTH="192" HPOS="42" VPOS="424"></String>
42
+ <String CONTENT="Combat:" HEIGHT="20" WIDTH="88" HPOS="244" VPOS="423"></String>
43
+ <String CONTENT="_" HEIGHT="2" WIDTH="32" HPOS="167" VPOS="464"></String>
44
+ <String CONTENT="._" HEIGHT="7" WIDTH="57" HPOS="209" VPOS="461"></String>
45
+ <String CONTENT="I!" HEIGHT="14" WIDTH="25" HPOS="129" VPOS="482"></String>
46
+ <String CONTENT="I." HEIGHT="14" WIDTH="18" HPOS="163" VPOS="482"></String>
47
+ <String CONTENT="E" HEIGHT="13" WIDTH="17" HPOS="189" VPOS="482"></String>
48
+ <String CONTENT="WI." HEIGHT="15" WIDTH="87" HPOS="213" VPOS="481"></String>
49
+ <String CONTENT="00." HEIGHT="13" WIDTH="26" HPOS="141" VPOS="502"></String>
50
+ <String CONTENT="G." HEIGHT="15" WIDTH="15" HPOS="178" VPOS="501"></String>
51
+ <String CONTENT="noun" HEIGHT="13" WIDTH="48" HPOS="203" VPOS="501"></String>
52
+ <String CONTENT="PI." HEIGHT="14" WIDTH="27" HPOS="261" VPOS="500"></String>
53
+ <String CONTENT="The" HEIGHT="16" WIDTH="34" HPOS="36" VPOS="547"></String>
54
+ <String CONTENT="dhision" HEIGHT="15" WIDTH="68" HPOS="77" VPOS="546"></String>
55
+ <String CONTENT="known" HEIGHT="15" WIDTH="60" HPOS="156" VPOS="545"></String>
56
+ <String CONTENT="as" HEIGHT="10" WIDTH="18" HPOS="226" VPOS="549"></String>
57
+ <String CONTENT="the" HEIGHT="16" WIDTH="28" HPOS="256" VPOS="543"></String>
58
+ <String CONTENT="Penusylrnnin" HEIGHT="20" WIDTH="118" HPOS="295" VPOS="542"></String>
59
+ <String CONTENT="kernels" HEIGHT="19" WIDTH="81" HPOS="16" VPOS="569"></String>
60
+ <String CONTENT="which" HEIGHT="15" WIDTH="52" HPOS="103" VPOS="569"></String>
61
+ <String CONTENT="had" HEIGHT="15" WIDTH="31" HPOS="162" VPOS="569"></String>
62
+ <String CONTENT="among" HEIGHT="14" WIDTH="58" HPOS="200" VPOS="573"></String>
63
+ <String CONTENT="imolfinus" HEIGHT="15" WIDTH="84" HPOS="266" VPOS="567"></String>
64
+ <String CONTENT="during" HEIGHT="19" WIDTH="59" HPOS="354" VPOS="566"></String>
65
+ <String CONTENT="0M" HEIGHT="15" WIDTH="29" HPOS="15" VPOS="595"></String>
66
+ <String CONTENT="(its!" HEIGHT="14" WIDTH="33" HPOS="51" VPOS="595"></String>
67
+ <String CONTENT="yur" HEIGHT="15" WIDTH="38" HPOS="90" VPOS="598"></String>
68
+ <String CONTENT="of" HEIGHT="14" WIDTH="18" HPOS="132" VPOS="594"></String>
69
+ <String CONTENT="its" HEIGHT="15" WIDTH="21" HPOS="155" VPOS="593"></String>
70
+ <String CONTENT="sen-ice" HEIGHT="15" WIDTH="60" HPOS="182" VPOS="592"></String>
71
+ <String CONTENT="such" HEIGHT="15" WIDTH="40" HPOS="248" VPOS="591"></String>
72
+ <String CONTENT="distinguished" HEIGHT="20" WIDTH="118" HPOS="294" VPOS="590"></String>
73
+ <String CONTENT="”Idiom" HEIGHT="17" WIDTH="67" HPOS="15" VPOS="618"></String>
74
+ <String CONTENT="u" HEIGHT="10" WIDTH="17" HPOS="92" VPOS="622"></String>
75
+ <String CONTENT="Meade." HEIGHT="17" WIDTH="60" HPOS="121" VPOS="617"></String>
76
+ <String CONTENT="Reynolds," HEIGHT="20" WIDTH="85" HPOS="191" VPOS="615"></String>
77
+ <String CONTENT="Old" HEIGHT="15" WIDTH="32" HPOS="284" VPOS="615"></String>
78
+ <String CONTENT="Ind" HEIGHT="16" WIDTH="31" HPOS="330" VPOS="614"></String>
79
+ <String CONTENT="Sey-" HEIGHT="19" WIDTH="38" HPOS="374" VPOS="614"></String>
80
+ <String CONTENT="mour," HEIGHT="14" WIDTH="52" HPOS="15" VPOS="646"></String>
81
+ <String CONTENT="finished" HEIGHT="15" WIDTH="67" HPOS="75" VPOS="641"></String>
82
+ <String CONTENT="in" HEIGHT="14" WIDTH="21" HPOS="154" VPOS="641"></String>
83
+ <String CONTENT="history" HEIGHT="18" WIDTH="60" HPOS="185" VPOS="640"></String>
84
+ <String CONTENT=")1):" HEIGHT="19" WIDTH="38" HPOS="256" VPOS="639"></String>
85
+ <String CONTENT="30," HEIGHT="19" WIDTH="25" HPOS="303" VPOS="639"></String>
86
+ <String CONTENT="um," HEIGHT="18" WIDTH="43" HPOS="338" VPOS="638"></String>
87
+ <String CONTENT="I!" HEIGHT="13" WIDTH="17" HPOS="395" VPOS="640"></String>
88
+ <String CONTENT="Bethesda" HEIGHT="16" WIDTH="78" HPOS="16" VPOS="665"></String>
89
+ <String CONTENT="Chard]." HEIGHT="16" WIDTH="67" HPOS="104" VPOS="664"></String>
90
+ <String CONTENT="The" HEIGHT="16" WIDTH="34" HPOS="193" VPOS="663"></String>
91
+ <String CONTENT="men" HEIGHT="11" WIDTH="36" HPOS="239" VPOS="667"></String>
92
+ <String CONTENT="who" HEIGHT="15" WIDTH="37" HPOS="289" VPOS="662"></String>
93
+ <String CONTENT="Md" HEIGHT="15" WIDTH="32" HPOS="338" VPOS="662"></String>
94
+ <String CONTENT="not" HEIGHT="13" WIDTH="29" HPOS="384" VPOS="663"></String>
95
+ <String CONTENT="n—enlist-d" HEIGHT="16" WIDTH="92" HPOS="15" VPOS="689"></String>
96
+ <String CONTENT="wan" HEIGHT="13" WIDTH="42" HPOS="121" VPOS="690"></String>
97
+ <String CONTENT="ham" HEIGHT="16" WIDTH="50" HPOS="176" VPOS="687"></String>
98
+ <String CONTENT="Ind" HEIGHT="15" WIDTH="31" HPOS="238" VPOS="687"></String>
99
+ <String CONTENT="tbs" HEIGHT="15" WIDTH="28" HPOS="283" VPOS="686"></String>
100
+ <String CONTENT="nmnining" HEIGHT="19" WIDTH="88" HPOS="324" VPOS="685"></String>
101
+ <String CONTENT="lumen“" HEIGHT="19" WIDTH="87" HPOS="15" VPOS="713"></String>
102
+ <String CONTENT="of" HEIGHT="15" WIDTH="17" HPOS="108" VPOS="712"></String>
103
+ <String CONTENT="these" HEIGHT="15" WIDTH="44" HPOS="134" VPOS="712"></String>
104
+ <String CONTENT="ngimenll" HEIGHT="19" WIDTH="87" HPOS="189" VPOS="711"></String>
105
+ <String CONTENT="were" HEIGHT="11" WIDTH="40" HPOS="282" VPOS="714"></String>
106
+ <String CONTENT="organized" HEIGHT="19" WIDTH="83" HPOS="328" VPOS="709"></String>
107
+ <String CONTENT="Into" HEIGHT="16" WIDTH="36" HPOS="15" VPOS="736"></String>
108
+ <String CONTENT="um" HEIGHT="12" WIDTH="32" HPOS="57" VPOS="739"></String>
109
+ <String CONTENT="\‘etmn" HEIGHT="13" WIDTH="64" HPOS="96" VPOS="738"></String>
110
+ <String CONTENT="regiments," HEIGHT="19" WIDTH="91" HPOS="167" VPOS="735"></String>
111
+ <String CONTENT="nnmbeml" HEIGHT="15" WIDTH="86" HPOS="266" VPOS="734"></String>
112
+ <String CONTENT="19w:" HEIGHT="16" WIDTH="47" HPOS="364" VPOS="732"></String>
113
+ <String CONTENT="Ind" HEIGHT="16" WIDTH="33" HPOS="15" VPOS="760"></String>
114
+ <String CONTENT="1815!," HEIGHT="18" WIDTH="48" HPOS="61" VPOS="760"></String>
115
+ <String CONTENT="who" HEIGHT="15" WIDTH="49" HPOS="117" VPOS="759"></String>
116
+ <String CONTENT="and" HEIGHT="16" WIDTH="32" HPOS="178" VPOS="758"></String>
117
+ <String CONTENT="W" HEIGHT="15" WIDTH="20" HPOS="222" VPOS="758"></String>
118
+ <String CONTENT="Vcnmn" HEIGHT="15" WIDTH="69" HPOS="250" VPOS="758"></String>
119
+ <String CONTENT="Roi-nu,‘" HEIGHT="26" WIDTH="87" HPOS="331" VPOS="757"></String>
120
+ <String CONTENT="with" HEIGHT="15" WIDTH="40" HPOS="15" VPOS="784"></String>
121
+ <String CONTENT="In" HEIGHT="11" WIDTH="20" HPOS="63" VPOS="788"></String>
122
+ <String CONTENT="nun-gnu" HEIGHT="17" WIDTH="84" HPOS="90" VPOS="785"></String>
123
+ <String CONTENT="at" HEIGHT="14" WIDTH="18" HPOS="179" VPOS="783"></String>
124
+ <String CONTENT="about" HEIGHT="15" WIDTH="50" HPOS="205" VPOS="783"></String>
125
+ <String CONTENT="l,l29" HEIGHT="19" WIDTH="45" HPOS="262" VPOS="782"></String>
126
+ <String CONTENT="adieu" HEIGHT="15" WIDTH="61" HPOS="313" VPOS="782"></String>
127
+ <String CONTENT="3nd" HEIGHT="15" WIDTH="32" HPOS="379" VPOS="781"></String>
128
+ <String CONTENT="m." HEIGHT="14" WIDTH="44" HPOS="14" VPOS="812"></String>
129
+ <String CONTENT="the" HEIGHT="15" WIDTH="27" HPOS="65" VPOS="807"></String>
130
+ <String CONTENT="former" HEIGHT="15" WIDTH="59" HPOS="99" VPOS="807"></String>
131
+ <String CONTENT="under" HEIGHT="15" WIDTH="51" HPOS="165" VPOS="807"></String>
132
+ <String CONTENT="the" HEIGHT="15" WIDTH="28" HPOS="226" VPOS="806"></String>
133
+ <String CONTENT="omnnund" HEIGHT="15" WIDTH="83" HPOS="260" VPOS="806"></String>
134
+ <String CONTENT="of" HEIGHT="14" WIDTH="19" HPOS="349" VPOS="806"></String>
135
+ <String CONTENT="OoL" HEIGHT="16" WIDTH="32" HPOS="377" VPOS="805"></String>
136
+ <String CONTENT="W." HEIGHT="16" WIDTH="26" HPOS="14" VPOS="831"></String>
137
+ <String CONTENT="IL" HEIGHT="15" WIDTH="18" HPOS="49" VPOS="832"></String>
138
+ <String CONTENT="Hnnnhorne." HEIGHT="18" WIDTH="101" HPOS="76" VPOS="831"></String>
139
+ <String CONTENT="formal]" HEIGHT="19" WIDTH="74" HPOS="186" VPOS="830"></String>
140
+ <String CONTENT="of" HEIGHT="16" WIDTH="19" HPOS="267" VPOS="829"></String>
141
+ <String CONTENT="the" HEIGHT="15" WIDTH="28" HPOS="295" VPOS="830"></String>
142
+ <String CONTENT="13m" HEIGHT="16" WIDTH="38" HPOS="332" VPOS="829"></String>
143
+ <String CONTENT="Re~" HEIGHT="15" WIDTH="30" HPOS="381" VPOS="829"></String>
144
+ <String CONTENT="m;" HEIGHT="14" WIDTH="58" HPOS="14" VPOS="860"></String>
145
+ <String CONTENT="the" HEIGHT="15" WIDTH="28" HPOS="82" VPOS="855"></String>
146
+ <String CONTENT="lam" HEIGHT="15" WIDTH="48" HPOS="122" VPOS="855"></String>
147
+ <String CONTENT="under" HEIGHT="15" WIDTH="51" HPOS="181" VPOS="854"></String>
148
+ <String CONTENT="Col" HEIGHT="15" WIDTH="33" HPOS="242" VPOS="854"></String>
149
+ <String CONTENT="James" HEIGHT="16" WIDTH="54" HPOS="284" VPOS="853"></String>
150
+ <String CONTENT="Carl," HEIGHT="19" WIDTH="41" HPOS="345" VPOS="853"></String>
151
+ <String CONTENT="of" HEIGHT="15" WIDTH="20" HPOS="394" VPOS="853"></String>
152
+ <String CONTENT="the" HEIGHT="16" WIDTH="29" HPOS="14" VPOS="879"></String>
153
+ <String CONTENT="6th" HEIGHT="15" WIDTH="29" HPOS="58" VPOS="879"></String>
154
+ <String CONTENT="Rue&quot;;" HEIGHT="15" WIDTH="79" HPOS="104" VPOS="879"></String>
155
+ <String CONTENT="They" HEIGHT="19" WIDTH="44" HPOS="204" VPOS="878"></String>
156
+ <String CONTENT="wnslitnusd" HEIGHT="16" WIDTH="98" HPOS="265" VPOS="877"></String>
157
+ <String CONTENT="the" HEIGHT="15" WIDTH="28" HPOS="383" VPOS="877"></String>
158
+ <String CONTENT="Third" HEIGHT="16" WIDTH="50" HPOS="14" VPOS="903"></String>
159
+ <String CONTENT="Brig-d;" HEIGHT="19" WIDTH="71" HPOS="77" VPOS="903"></String>
160
+ <String CONTENT="Thild" HEIGHT="15" WIDTH="50" HPOS="156" VPOS="902"></String>
161
+ <String CONTENT="Division," HEIGHT="19" WIDTH="78" HPOS="218" VPOS="902"></String>
162
+ <String CONTENT="Hm:" HEIGHT="15" WIDTH="44" HPOS="306" VPOS="901"></String>
163
+ <String CONTENT="om;" HEIGHT="19" WIDTH="52" HPOS="357" VPOS="901"></String>
164
+ <String CONTENT="For" HEIGHT="17" WIDTH="32" HPOS="14" VPOS="926"></String>
165
+ <String CONTENT="lune" HEIGHT="11" WIDTH="43" HPOS="55" VPOS="931"></String>
166
+ <String CONTENT="unn" HEIGHT="11" WIDTH="47" HPOS="108" VPOS="931"></String>
167
+ <String CONTENT="00L" HEIGHT="15" WIDTH="33" HPOS="161" VPOS="926"></String>
168
+ <String CONTENT="Hawthorne" HEIGHT="15" WIDTH="98" HPOS="203" VPOS="926"></String>
169
+ <String CONTENT="wnn" HEIGHT="11" WIDTH="33" HPOS="312" VPOS="929"></String>
170
+ <String CONTENT="nhsent" HEIGHT="15" WIDTH="56" HPOS="355" VPOS="925"></String>
171
+ <String CONTENT="until" HEIGHT="16" WIDTH="43" HPOS="14" VPOS="950"></String>
172
+ <String CONTENT="Inn" HEIGHT="16" WIDTH="41" HPOS="64" VPOS="950"></String>
173
+ <String CONTENT="the" HEIGHT="15" WIDTH="27" HPOS="111" VPOS="950"></String>
174
+ <String CONTENT="my" HEIGHT="15" WIDTH="45" HPOS="145" VPOS="954"></String>
175
+ <String CONTENT="undid" HEIGHT="16" WIDTH="66" HPOS="197" VPOS="949"></String>
176
+ <String CONTENT="rambling," HEIGHT="19" WIDTH="99" HPOS="271" VPOS="949"></String>
177
+ <String CONTENT="and" HEIGHT="16" WIDTH="32" HPOS="378" VPOS="948"></String>
178
+ <String CONTENT="Ike" HEIGHT="16" WIDTH="29" HPOS="14" VPOS="974"></String>
179
+ <String CONTENT="1900!" HEIGHT="16" WIDTH="47" HPOS="56" VPOS="974"></String>
180
+ <String CONTENT="In:" HEIGHT="11" WIDTH="33" HPOS="115" VPOS="978"></String>
181
+ <String CONTENT="mum-add" HEIGHT="16" WIDTH="104" HPOS="161" VPOS="973"></String>
182
+ <String CONTENT="by" HEIGHT="19" WIDTH="21" HPOS="279" VPOS="973"></String>
183
+ <String CONTENT="LioIILoCoL" HEIGHT="16" WIDTH="94" HPOS="314" VPOS="972"></String>
184
+ <String CONTENT="Joe»" HEIGHT="20" WIDTH="61" HPOS="13" VPOS="997"></String>
185
+ <String CONTENT="B." HEIGHT="15" WIDTH="17" HPOS="81" VPOS="998"></String>
186
+ <String CONTENT="Puma," HEIGHT="18" WIDTH="59" HPOS="107" VPOS="998"></String>
187
+ <String CONTENT="whflz" HEIGHT="16" WIDTH="48" HPOS="172" VPOS="997"></String>
188
+ <String CONTENT="Col." HEIGHT="15" WIDTH="33" HPOS="226" VPOS="997"></String>
189
+ <String CONTENT="(XII" HEIGHT="15" WIDTH="37" HPOS="265" VPOS="997"></String>
190
+ <String CONTENT="wmmlnded" HEIGHT="16" WIDTH="104" HPOS="306" VPOS="996"></String>
191
+ <String CONTENT="[M" HEIGHT="16" WIDTH="28" HPOS="14" VPOS="1021"></String>
192
+ <String CONTENT="brig-d:" HEIGHT="20" WIDTH="63" HPOS="49" VPOS="1021"></String>
193
+ <String CONTENT="until" HEIGHT="15" WIDTH="42" HPOS="119" VPOS="1021"></String>
194
+ <String CONTENT="Aug." HEIGHT="20" WIDTH="40" HPOS="170" VPOS="1021"></String>
195
+ <String CONTENT="19." HEIGHT="17" WIDTH="23" HPOS="219" VPOS="1022"></String>
196
+ <String CONTENT="1864." HEIGHT="15" WIDTH="43" HPOS="251" VPOS="1021"></String>
197
+ </TextLine>
198
+ </TextBlock>
199
+ </PrintSpace>
200
+ </Page>
201
+ </Layout>
202
+ </alto>
data/spec/fixtures/files/ocr_alto_scaled_4pts_per_px.xml ADDED
@@ -0,0 +1,202 @@
1
+ <?xml version="1.0" encoding="UTF-8"?>
2
+ <alto xmlns="http://www.loc.gov/standards/alto/ns-v2#">
3
+ <Description>
4
+ <MeasurementUnit>pixel</MeasurementUnit>
5
+ </Description>
6
+ <Layout>
7
+ <Page ID="ID1" PHYSICAL_IMG_NR="1" HEIGHT="4184" WIDTH="1672">
8
+ <PrintSpace HEIGHT="4184" WIDTH="1672" HPOS="0" VPOS="0">
9
+ <TextBlock ID="ID1a" HEIGHT="4184" WIDTH="1672" HPOS="0" VPOS="0">
10
+ <TextLine HEIGHT="4184" WIDTH="1672" HPOS="0" VPOS="0">
11
+ <String CONTENT="PEHNSYWAHIA" HEIGHT="208" WIDTH="1124" HPOS="96" VPOS="68"></String>
12
+ <String CONTENT="_" HEIGHT="12" WIDTH="132" HPOS="704" VPOS="608"></String>
13
+ <String CONTENT="RESERVES." HEIGHT="208" WIDTH="804" HPOS="868" VPOS="332"></String>
14
+ <String CONTENT="Career" HEIGHT="96" WIDTH="328" HPOS="88" VPOS="696"></String>
15
+ <String CONTENT="of" HEIGHT="96" WIDTH="100" HPOS="472" VPOS="692"></String>
16
+ <String CONTENT="These" HEIGHT="100" WIDTH="284" HPOS="620" VPOS="688"></String>
17
+ <String CONTENT="Veterans" HEIGHT="96" WIDTH="452" HPOS="948" VPOS="688"></String>
18
+ <String CONTENT="from" HEIGHT="96" WIDTH="232" HPOS="1440" VPOS="684"></String>
19
+ <String CONTENT="Cold" HEIGHT="100" WIDTH="216" HPOS="144" VPOS="888"></String>
20
+ <String CONTENT="Harbor" HEIGHT="96" WIDTH="356" HPOS="420" VPOS="884"></String>
21
+ <String CONTENT="to" HEIGHT="92" WIDTH="96" HPOS="836" VPOS="884"></String>
22
+ <String CONTENT="Appomattox." HEIGHT="120" WIDTH="636" HPOS="972" VPOS="880"></String>
23
+ <String CONTENT="Organizations" HEIGHT="96" WIDTH="560" HPOS="84" VPOS="1180"></String>
24
+ <String CONTENT="Which" HEIGHT="76" WIDTH="268" HPOS="744" VPOS="1172"></String>
25
+ <String CONTENT="Did" HEIGHT="80" WIDTH="148" HPOS="1108" VPOS="1168"></String>
26
+ <String CONTENT="Gallant" HEIGHT="80" WIDTH="296" HPOS="1372" VPOS="1164"></String>
27
+ <String CONTENT="Service—Led" HEIGHT="88" WIDTH="528" HPOS="176" VPOS="1304"></String>
28
+ <String CONTENT="by" HEIGHT="100" WIDTH="100" HPOS="756" VPOS="1304"></String>
29
+ <String CONTENT="Good" HEIGHT="80" WIDTH="192" HPOS="904" VPOS="1300"></String>
30
+ <String CONTENT="one”;" HEIGHT="88" WIDTH="300" HPOS="1156" VPOS="1296"></String>
31
+ <String CONTENT="Dis-" HEIGHT="80" WIDTH="156" HPOS="1508" VPOS="1292"></String>
32
+ <String CONTENT="cipline" HEIGHT="100" WIDTH="268" HPOS="172" VPOS="1444"></String>
33
+ <String CONTENT="and" HEIGHT="80" WIDTH="144" HPOS="520" VPOS="1436"></String>
34
+ <String CONTENT="‘anery" HEIGHT="96" WIDTH="352" HPOS="732" VPOS="1436"></String>
35
+ <String CONTENT="Snved" HEIGHT="80" WIDTH="236" HPOS="1152" VPOS="1428"></String>
36
+ <String CONTENT="Them" HEIGHT="76" WIDTH="216" HPOS="1444" VPOS="1424"></String>
37
+ <String CONTENT="bum" HEIGHT="80" WIDTH="184" HPOS="172" VPOS="1576"></String>
38
+ <String CONTENT="Annihilation" HEIGHT="84" WIDTH="512" HPOS="404" VPOS="1568"></String>
39
+ <String CONTENT="on" HEIGHT="56" WIDTH="92" HPOS="976" VPOS="1584"></String>
40
+ <String CONTENT="Bud-Fought" HEIGHT="100" WIDTH="520" HPOS="1136" VPOS="1556"></String>
41
+ <String CONTENT="Fields—Memorable" HEIGHT="88" WIDTH="768" HPOS="168" VPOS="1696"></String>
42
+ <String CONTENT="Combat:" HEIGHT="80" WIDTH="352" HPOS="976" VPOS="1692"></String>
43
+ <String CONTENT="_" HEIGHT="8" WIDTH="128" HPOS="668" VPOS="1856"></String>
44
+ <String CONTENT="._" HEIGHT="28" WIDTH="228" HPOS="836" VPOS="1844"></String>
45
+ <String CONTENT="I!" HEIGHT="56" WIDTH="100" HPOS="516" VPOS="1928"></String>
46
+ <String CONTENT="I." HEIGHT="56" WIDTH="72" HPOS="652" VPOS="1928"></String>
47
+ <String CONTENT="E" HEIGHT="52" WIDTH="68" HPOS="756" VPOS="1928"></String>
48
+ <String CONTENT="WI." HEIGHT="60" WIDTH="348" HPOS="852" VPOS="1924"></String>
49
+ <String CONTENT="00." HEIGHT="52" WIDTH="104" HPOS="564" VPOS="2008"></String>
50
+ <String CONTENT="G." HEIGHT="60" WIDTH="60" HPOS="712" VPOS="2004"></String>
51
+ <String CONTENT="noun" HEIGHT="52" WIDTH="192" HPOS="812" VPOS="2004"></String>
52
+ <String CONTENT="PI." HEIGHT="56" WIDTH="108" HPOS="1044" VPOS="2000"></String>
53
+ <String CONTENT="The" HEIGHT="64" WIDTH="136" HPOS="144" VPOS="2188"></String>
54
+ <String CONTENT="dhision" HEIGHT="60" WIDTH="272" HPOS="308" VPOS="2184"></String>
55
+ <String CONTENT="known" HEIGHT="60" WIDTH="240" HPOS="624" VPOS="2180"></String>
56
+ <String CONTENT="as" HEIGHT="40" WIDTH="72" HPOS="904" VPOS="2196"></String>
57
+ <String CONTENT="the" HEIGHT="64" WIDTH="112" HPOS="1024" VPOS="2172"></String>
58
+ <String CONTENT="Penusylrnnin" HEIGHT="80" WIDTH="472" HPOS="1180" VPOS="2168"></String>
59
+ <String CONTENT="kernels" HEIGHT="76" WIDTH="324" HPOS="64" VPOS="2276"></String>
60
+ <String CONTENT="which" HEIGHT="60" WIDTH="208" HPOS="412" VPOS="2276"></String>
61
+ <String CONTENT="had" HEIGHT="60" WIDTH="124" HPOS="648" VPOS="2276"></String>
62
+ <String CONTENT="among" HEIGHT="56" WIDTH="232" HPOS="800" VPOS="2292"></String>
63
+ <String CONTENT="imolfinus" HEIGHT="60" WIDTH="336" HPOS="1064" VPOS="2268"></String>
64
+ <String CONTENT="during" HEIGHT="76" WIDTH="236" HPOS="1416" VPOS="2264"></String>
65
+ <String CONTENT="0M" HEIGHT="60" WIDTH="116" HPOS="60" VPOS="2380"></String>
66
+ <String CONTENT="(its!" HEIGHT="56" WIDTH="132" HPOS="204" VPOS="2380"></String>
67
+ <String CONTENT="yur" HEIGHT="60" WIDTH="152" HPOS="360" VPOS="2392"></String>
68
+ <String CONTENT="of" HEIGHT="56" WIDTH="72" HPOS="528" VPOS="2376"></String>
69
+ <String CONTENT="its" HEIGHT="60" WIDTH="84" HPOS="620" VPOS="2372"></String>
70
+ <String CONTENT="sen-ice" HEIGHT="60" WIDTH="240" HPOS="728" VPOS="2368"></String>
71
+ <String CONTENT="such" HEIGHT="60" WIDTH="160" HPOS="992" VPOS="2364"></String>
72
+ <String CONTENT="distinguished" HEIGHT="80" WIDTH="472" HPOS="1176" VPOS="2360"></String>
73
+ <String CONTENT="”Idiom" HEIGHT="68" WIDTH="268" HPOS="60" VPOS="2472"></String>
74
+ <String CONTENT="u" HEIGHT="40" WIDTH="68" HPOS="368" VPOS="2488"></String>
75
+ <String CONTENT="Meade." HEIGHT="68" WIDTH="240" HPOS="484" VPOS="2468"></String>
76
+ <String CONTENT="Reynolds," HEIGHT="80" WIDTH="340" HPOS="764" VPOS="2460"></String>
77
+ <String CONTENT="Old" HEIGHT="60" WIDTH="128" HPOS="1136" VPOS="2460"></String>
78
+ <String CONTENT="Ind" HEIGHT="64" WIDTH="124" HPOS="1320" VPOS="2456"></String>
79
+ <String CONTENT="Sey-" HEIGHT="76" WIDTH="152" HPOS="1496" VPOS="2456"></String>
80
+ <String CONTENT="mour," HEIGHT="56" WIDTH="208" HPOS="60" VPOS="2584"></String>
81
+ <String CONTENT="finished" HEIGHT="60" WIDTH="268" HPOS="300" VPOS="2564"></String>
82
+ <String CONTENT="in" HEIGHT="56" WIDTH="84" HPOS="616" VPOS="2564"></String>
83
+ <String CONTENT="history" HEIGHT="72" WIDTH="240" HPOS="740" VPOS="2560"></String>
84
+ <String CONTENT=")1):" HEIGHT="76" WIDTH="152" HPOS="1024" VPOS="2556"></String>
85
+ <String CONTENT="30," HEIGHT="76" WIDTH="100" HPOS="1212" VPOS="2556"></String>
86
+ <String CONTENT="um," HEIGHT="72" WIDTH="172" HPOS="1352" VPOS="2552"></String>
87
+ <String CONTENT="I!" HEIGHT="52" WIDTH="68" HPOS="1580" VPOS="2560"></String>
88
+ <String CONTENT="Bethesda" HEIGHT="64" WIDTH="312" HPOS="64" VPOS="2660"></String>
89
+ <String CONTENT="Chard]." HEIGHT="64" WIDTH="268" HPOS="416" VPOS="2656"></String>
90
+ <String CONTENT="The" HEIGHT="64" WIDTH="136" HPOS="772" VPOS="2652"></String>
91
+ <String CONTENT="men" HEIGHT="44" WIDTH="144" HPOS="956" VPOS="2668"></String>
92
+ <String CONTENT="who" HEIGHT="60" WIDTH="148" HPOS="1156" VPOS="2648"></String>
93
+ <String CONTENT="Md" HEIGHT="60" WIDTH="128" HPOS="1352" VPOS="2648"></String>
94
+ <String CONTENT="not" HEIGHT="52" WIDTH="116" HPOS="1536" VPOS="2652"></String>
95
+ <String CONTENT="n—enlist-d" HEIGHT="64" WIDTH="368" HPOS="60" VPOS="2756"></String>
96
+ <String CONTENT="wan" HEIGHT="52" WIDTH="168" HPOS="484" VPOS="2760"></String>
97
+ <String CONTENT="ham" HEIGHT="64" WIDTH="200" HPOS="704" VPOS="2748"></String>
98
+ <String CONTENT="Ind" HEIGHT="60" WIDTH="124" HPOS="952" VPOS="2748"></String>
99
+ <String CONTENT="tbs" HEIGHT="60" WIDTH="112" HPOS="1132" VPOS="2744"></String>
100
+ <String CONTENT="nmnining" HEIGHT="76" WIDTH="352" HPOS="1296" VPOS="2740"></String>
101
+ <String CONTENT="lumen“" HEIGHT="76" WIDTH="348" HPOS="60" VPOS="2852"></String>
102
+ <String CONTENT="of" HEIGHT="60" WIDTH="68" HPOS="432" VPOS="2848"></String>
103
+ <String CONTENT="these" HEIGHT="60" WIDTH="176" HPOS="536" VPOS="2848"></String>
104
+ <String CONTENT="ngimenll" HEIGHT="76" WIDTH="348" HPOS="756" VPOS="2844"></String>
105
+ <String CONTENT="were" HEIGHT="44" WIDTH="160" HPOS="1128" VPOS="2856"></String>
106
+ <String CONTENT="organized" HEIGHT="76" WIDTH="332" HPOS="1312" VPOS="2836"></String>
107
+ <String CONTENT="Into" HEIGHT="64" WIDTH="144" HPOS="60" VPOS="2944"></String>
108
+ <String CONTENT="um" HEIGHT="48" WIDTH="128" HPOS="228" VPOS="2956"></String>
109
+ <String CONTENT="\‘etmn" HEIGHT="52" WIDTH="256" HPOS="384" VPOS="2952"></String>
110
+ <String CONTENT="regiments," HEIGHT="76" WIDTH="364" HPOS="668" VPOS="2940"></String>
111
+ <String CONTENT="nnmbeml" HEIGHT="60" WIDTH="344" HPOS="1064" VPOS="2936"></String>
112
+ <String CONTENT="19w:" HEIGHT="64" WIDTH="188" HPOS="1456" VPOS="2928"></String>
113
+ <String CONTENT="Ind" HEIGHT="64" WIDTH="132" HPOS="60" VPOS="3040"></String>
114
+ <String CONTENT="1815!," HEIGHT="72" WIDTH="192" HPOS="244" VPOS="3040"></String>
115
+ <String CONTENT="who" HEIGHT="60" WIDTH="196" HPOS="468" VPOS="3036"></String>
116
+ <String CONTENT="and" HEIGHT="64" WIDTH="128" HPOS="712" VPOS="3032"></String>
117
+ <String CONTENT="W" HEIGHT="60" WIDTH="80" HPOS="888" VPOS="3032"></String>
118
+ <String CONTENT="Vcnmn" HEIGHT="60" WIDTH="276" HPOS="1000" VPOS="3032"></String>
119
+ <String CONTENT="Roi-nu,‘" HEIGHT="104" WIDTH="348" HPOS="1324" VPOS="3028"></String>
120
+ <String CONTENT="with" HEIGHT="60" WIDTH="160" HPOS="60" VPOS="3136"></String>
121
+ <String CONTENT="In" HEIGHT="44" WIDTH="80" HPOS="252" VPOS="3152"></String>
122
+ <String CONTENT="nun-gnu" HEIGHT="68" WIDTH="336" HPOS="360" VPOS="3140"></String>
123
+ <String CONTENT="at" HEIGHT="56" WIDTH="72" HPOS="716" VPOS="3132"></String>
124
+ <String CONTENT="about" HEIGHT="60" WIDTH="200" HPOS="820" VPOS="3132"></String>
125
+ <String CONTENT="l,l29" HEIGHT="76" WIDTH="180" HPOS="1048" VPOS="3128"></String>
126
+ <String CONTENT="adieu" HEIGHT="60" WIDTH="244" HPOS="1252" VPOS="3128"></String>
127
+ <String CONTENT="3nd" HEIGHT="60" WIDTH="128" HPOS="1516" VPOS="3124"></String>
128
+ <String CONTENT="m." HEIGHT="56" WIDTH="176" HPOS="56" VPOS="3248"></String>
129
+ <String CONTENT="the" HEIGHT="60" WIDTH="108" HPOS="260" VPOS="3228"></String>
130
+ <String CONTENT="former" HEIGHT="60" WIDTH="236" HPOS="396" VPOS="3228"></String>
131
+ <String CONTENT="under" HEIGHT="60" WIDTH="204" HPOS="660" VPOS="3228"></String>
132
+ <String CONTENT="the" HEIGHT="60" WIDTH="112" HPOS="904" VPOS="3224"></String>
133
+ <String CONTENT="omnnund" HEIGHT="60" WIDTH="332" HPOS="1040" VPOS="3224"></String>
134
+ <String CONTENT="of" HEIGHT="56" WIDTH="76" HPOS="1396" VPOS="3224"></String>
135
+ <String CONTENT="OoL" HEIGHT="64" WIDTH="128" HPOS="1508" VPOS="3220"></String>
136
+ <String CONTENT="W." HEIGHT="64" WIDTH="104" HPOS="56" VPOS="3324"></String>
137
+ <String CONTENT="IL" HEIGHT="60" WIDTH="72" HPOS="196" VPOS="3328"></String>
138
+ <String CONTENT="Hnnnhorne." HEIGHT="72" WIDTH="404" HPOS="304" VPOS="3324"></String>
139
+ <String CONTENT="formal]" HEIGHT="76" WIDTH="296" HPOS="744" VPOS="3320"></String>
140
+ <String CONTENT="of" HEIGHT="64" WIDTH="76" HPOS="1068" VPOS="3316"></String>
141
+ <String CONTENT="the" HEIGHT="60" WIDTH="112" HPOS="1180" VPOS="3320"></String>
142
+ <String CONTENT="13m" HEIGHT="64" WIDTH="152" HPOS="1328" VPOS="3316"></String>
143
+ <String CONTENT="Re~" HEIGHT="60" WIDTH="120" HPOS="1524" VPOS="3316"></String>
144
+ <String CONTENT="m;" HEIGHT="56" WIDTH="232" HPOS="56" VPOS="3440"></String>
145
+ <String CONTENT="the" HEIGHT="60" WIDTH="112" HPOS="328" VPOS="3420"></String>
146
+ <String CONTENT="lam" HEIGHT="60" WIDTH="192" HPOS="488" VPOS="3420"></String>
147
+ <String CONTENT="under" HEIGHT="60" WIDTH="204" HPOS="724" VPOS="3416"></String>
148
+ <String CONTENT="Col" HEIGHT="60" WIDTH="132" HPOS="968" VPOS="3416"></String>
149
+ <String CONTENT="James" HEIGHT="64" WIDTH="216" HPOS="1136" VPOS="3412"></String>
150
+ <String CONTENT="Carl," HEIGHT="76" WIDTH="164" HPOS="1380" VPOS="3412"></String>
151
+ <String CONTENT="of" HEIGHT="60" WIDTH="80" HPOS="1576" VPOS="3412"></String>
152
+ <String CONTENT="the" HEIGHT="64" WIDTH="116" HPOS="56" VPOS="3516"></String>
153
+ <String CONTENT="6th" HEIGHT="60" WIDTH="116" HPOS="232" VPOS="3516"></String>
154
+ <String CONTENT="Rue&quot;;" HEIGHT="60" WIDTH="316" HPOS="416" VPOS="3516"></String>
155
+ <String CONTENT="They" HEIGHT="76" WIDTH="176" HPOS="816" VPOS="3512"></String>
156
+ <String CONTENT="wnslitnusd" HEIGHT="64" WIDTH="392" HPOS="1060" VPOS="3508"></String>
157
+ <String CONTENT="the" HEIGHT="60" WIDTH="112" HPOS="1532" VPOS="3508"></String>
158
+ <String CONTENT="Third" HEIGHT="64" WIDTH="200" HPOS="56" VPOS="3612"></String>
159
+ <String CONTENT="Brig-d;" HEIGHT="76" WIDTH="284" HPOS="308" VPOS="3612"></String>
160
+ <String CONTENT="Thild" HEIGHT="60" WIDTH="200" HPOS="624" VPOS="3608"></String>
161
+ <String CONTENT="Division," HEIGHT="76" WIDTH="312" HPOS="872" VPOS="3608"></String>
162
+ <String CONTENT="Hm:" HEIGHT="60" WIDTH="176" HPOS="1224" VPOS="3604"></String>
163
+ <String CONTENT="om;" HEIGHT="76" WIDTH="208" HPOS="1428" VPOS="3604"></String>
164
+ <String CONTENT="For" HEIGHT="68" WIDTH="128" HPOS="56" VPOS="3704"></String>
165
+ <String CONTENT="lune" HEIGHT="44" WIDTH="172" HPOS="220" VPOS="3724"></String>
166
+ <String CONTENT="unn" HEIGHT="44" WIDTH="188" HPOS="432" VPOS="3724"></String>
167
+ <String CONTENT="00L" HEIGHT="60" WIDTH="132" HPOS="644" VPOS="3704"></String>
168
+ <String CONTENT="Hawthorne" HEIGHT="60" WIDTH="392" HPOS="812" VPOS="3704"></String>
169
+ <String CONTENT="wnn" HEIGHT="44" WIDTH="132" HPOS="1248" VPOS="3716"></String>
170
+ <String CONTENT="nhsent" HEIGHT="60" WIDTH="224" HPOS="1420" VPOS="3700"></String>
171
+ <String CONTENT="until" HEIGHT="64" WIDTH="172" HPOS="56" VPOS="3800"></String>
172
+ <String CONTENT="Inn" HEIGHT="64" WIDTH="164" HPOS="256" VPOS="3800"></String>
173
+ <String CONTENT="the" HEIGHT="60" WIDTH="108" HPOS="444" VPOS="3800"></String>
174
+ <String CONTENT="my" HEIGHT="60" WIDTH="180" HPOS="580" VPOS="3816"></String>
175
+ <String CONTENT="undid" HEIGHT="64" WIDTH="264" HPOS="788" VPOS="3796"></String>
176
+ <String CONTENT="rambling," HEIGHT="76" WIDTH="396" HPOS="1084" VPOS="3796"></String>
177
+ <String CONTENT="and" HEIGHT="64" WIDTH="128" HPOS="1512" VPOS="3792"></String>
178
+ <String CONTENT="Ike" HEIGHT="64" WIDTH="116" HPOS="56" VPOS="3896"></String>
179
+ <String CONTENT="1900!" HEIGHT="64" WIDTH="188" HPOS="224" VPOS="3896"></String>
180
+ <String CONTENT="In:" HEIGHT="44" WIDTH="132" HPOS="460" VPOS="3912"></String>
181
+ <String CONTENT="mum-add" HEIGHT="64" WIDTH="416" HPOS="644" VPOS="3892"></String>
182
+ <String CONTENT="by" HEIGHT="76" WIDTH="84" HPOS="1116" VPOS="3892"></String>
183
+ <String CONTENT="LioIILoCoL" HEIGHT="64" WIDTH="376" HPOS="1256" VPOS="3888"></String>
184
+ <String CONTENT="Joe»" HEIGHT="80" WIDTH="244" HPOS="52" VPOS="3988"></String>
185
+ <String CONTENT="B." HEIGHT="60" WIDTH="68" HPOS="324" VPOS="3992"></String>
186
+ <String CONTENT="Puma," HEIGHT="72" WIDTH="236" HPOS="428" VPOS="3992"></String>
187
+ <String CONTENT="whflz" HEIGHT="64" WIDTH="192" HPOS="688" VPOS="3988"></String>
188
+ <String CONTENT="Col." HEIGHT="60" WIDTH="132" HPOS="904" VPOS="3988"></String>
189
+ <String CONTENT="(XII" HEIGHT="60" WIDTH="148" HPOS="1060" VPOS="3988"></String>
190
+ <String CONTENT="wmmlnded" HEIGHT="64" WIDTH="416" HPOS="1224" VPOS="3984"></String>
191
+ <String CONTENT="[M" HEIGHT="64" WIDTH="112" HPOS="56" VPOS="4084"></String>
192
+ <String CONTENT="brig-d:" HEIGHT="80" WIDTH="252" HPOS="196" VPOS="4084"></String>
193
+ <String CONTENT="until" HEIGHT="60" WIDTH="168" HPOS="476" VPOS="4084"></String>
194
+ <String CONTENT="Aug." HEIGHT="80" WIDTH="160" HPOS="680" VPOS="4084"></String>
195
+ <String CONTENT="19." HEIGHT="68" WIDTH="92" HPOS="876" VPOS="4088"></String>
196
+ <String CONTENT="1864." HEIGHT="60" WIDTH="172" HPOS="1004" VPOS="4084"></String>
197
+ </TextLine>
198
+ </TextBlock>
199
+ </PrintSpace>
200
+ </Page>
201
+ </Layout>
202
+ </alto>
data/spec/fixtures/files/ocr_color.tiff ADDED
Binary file
data/spec/fixtures/files/ocr_gray.jp2 ADDED
Binary file
data/spec/fixtures/files/ocr_gray.tiff ADDED
Binary file
data/spec/fixtures/files/ocr_mono.tiff ADDED
Binary file
data/spec/fixtures/files/page1.tiff ADDED
Binary file